From 02ec6cafd78c2052283516afc74c309745d20271 Mon Sep 17 00:00:00 2001
From: Hoang Le <hoang.h.le@dektech.com.au>
Date: Tue, 19 Mar 2019 18:49:48 +0700
Subject: tipc: support broadcast/replicast configurable for bc-link

Currently, a multicast stream uses either broadcast or replicast as
transmission method, based on the ratio between number of actual
destinations nodes and cluster size.

However, when an L2 interface (e.g., VXLAN) provides pseudo
broadcast support, this becomes very inefficient, as it blindly
replicates multicast packets to all cluster/subnet nodes,
irrespective of whether they host actual target sockets or not.

The TIPC multicast algorithm is able to distinguish real destination
nodes from other nodes, and hence provides a smarter and more
efficient method for transferring multicast messages than
pseudo broadcast can do.

Because of this, we now make it possible for users to force
the broadcast link to permanently switch to using replicast,
irrespective of which capabilities the bearer provides,
or pretend to provide.
Conversely, we also make it possible to force the broadcast link
to always use true broadcast. While maybe less useful in
deployed systems, this may at least be useful for testing the
broadcast algorithm in small clusters.

We retain the current AUTOSELECT ability, i.e., to let the broadcast link
automatically select which algorithm to use, and to switch back and forth
between broadcast and replicast as the ratio between destination
node number and cluster size changes. This remains the default method.

Furthermore, we make it possible to configure the threshold ratio for
such switches. The default ratio is now set to 10%, down from 25% in the
earlier implementation.

Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Hoang Le <hoang.h.le@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 0ebe02ef1a86..efb958fd167d 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -281,6 +281,8 @@ enum {
 	TIPC_NLA_PROP_TOL,		/* u32 */
 	TIPC_NLA_PROP_WIN,		/* u32 */
 	TIPC_NLA_PROP_MTU,		/* u32 */
+	TIPC_NLA_PROP_BROADCAST,	/* u32 */
+	TIPC_NLA_PROP_BROADCAST_RATIO,	/* u32 */
 
 	__TIPC_NLA_PROP_MAX,
 	TIPC_NLA_PROP_MAX = __TIPC_NLA_PROP_MAX - 1
-- 
cgit v1.2.3


From 9403cf2302588022d06f1878b072d3f6933021f0 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Tue, 19 Mar 2019 16:05:44 +0100
Subject: tcp: free request sock directly upon TFO or syncookies error

Since the request socket is created locally, it'd make more sense to
use reqsk_free() instead of reqsk_put() in TFO and syncookies' error
path.

However, tcp_get_cookie_sock() may set ->rsk_refcnt before freeing the
socket; tcp_conn_request() may also have non-null ->rsk_refcnt because
of tcp_try_fastopen(). In both cases 'req' hasn't been exposed
to the outside world and is safe to free immediately, but that'd
trigger the WARN_ON_ONCE in reqsk_free().

Define __reqsk_free() for these situations where we know nobody's
referencing the socket, even though ->rsk_refcnt might be non-null.
Now we can consolidate the error path of tcp_get_cookie_sock() and
tcp_conn_request().

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/request_sock.h | 10 +++++++---
 net/ipv4/syncookies.c      | 17 ++++++++---------
 net/ipv4/tcp_input.c       |  5 ++---
 3 files changed, 17 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index 21a5243fecd1..9dfd7960d90a 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -106,10 +106,8 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
 	return req;
 }
 
-static inline void reqsk_free(struct request_sock *req)
+static inline void __reqsk_free(struct request_sock *req)
 {
-	WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0);
-
 	req->rsk_ops->destructor(req);
 	if (req->rsk_listener)
 		sock_put(req->rsk_listener);
@@ -117,6 +115,12 @@ static inline void reqsk_free(struct request_sock *req)
 	kmem_cache_free(req->rsk_ops->slab, req);
 }
 
+static inline void reqsk_free(struct request_sock *req)
+{
+	WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0);
+	__reqsk_free(req);
+}
+
 static inline void reqsk_put(struct request_sock *req)
 {
 	if (refcount_dec_and_test(&req->rsk_refcnt))
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index e531344611a0..008545f63667 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -216,16 +216,15 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 		refcount_set(&req->rsk_refcnt, 1);
 		tcp_sk(child)->tsoffset = tsoff;
 		sock_rps_save_rxhash(child, skb);
-		if (!inet_csk_reqsk_queue_add(sk, req, child)) {
-			bh_unlock_sock(child);
-			sock_put(child);
-			child = NULL;
-			reqsk_put(req);
-		}
-	} else {
-		reqsk_free(req);
+		if (inet_csk_reqsk_queue_add(sk, req, child))
+			return child;
+
+		bh_unlock_sock(child);
+		sock_put(child);
 	}
-	return child;
+	__reqsk_free(req);
+
+	return NULL;
 }
 EXPORT_SYMBOL(tcp_get_cookie_sock);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5def3c48870e..5dfbc333e79a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6502,8 +6502,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			reqsk_fastopen_remove(fastopen_sk, req, false);
 			bh_unlock_sock(fastopen_sk);
 			sock_put(fastopen_sk);
-			reqsk_put(req);
-			goto drop;
+			goto drop_and_free;
 		}
 		sk->sk_data_ready(sk);
 		bh_unlock_sock(fastopen_sk);
@@ -6527,7 +6526,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 drop_and_release:
 	dst_release(dst);
 drop_and_free:
-	reqsk_free(req);
+	__reqsk_free(req);
 drop:
 	tcp_listendrop(sk);
 	return 0;
-- 
cgit v1.2.3


From 03f1eccc7a69c965351e6bee41c62afa2844752f Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Tue, 19 Mar 2019 12:37:12 -0400
Subject: ipv6: Add icmp_echo_ignore_multicast support for ICMPv6

IPv4 has icmp_echo_ignore_broadcast to prevent responding to broadcast pings.
IPv6 needs a similar mechanism.

v1->v2:
- Remove NET_IPV6_ICMP_ECHO_IGNORE_MULTICAST.

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  5 +++++
 include/net/netns/ipv6.h               |  1 +
 net/ipv6/af_inet6.c                    |  1 +
 net/ipv6/icmp.c                        | 12 ++++++++++++
 4 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index acdfb5d2bcaa..55ea7def46be 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1918,6 +1918,11 @@ echo_ignore_all - BOOLEAN
 	requests sent to it over the IPv6 protocol.
 	Default: 0
 
+echo_ignore_multicast - BOOLEAN
+	If set non-zero, then the kernel will ignore all ICMP ECHO
+	requests sent to it over the IPv6 protocol via multicast.
+	Default: 0
+
 xfrm6_gc_thresh - INTEGER
 	The threshold at which we will start garbage collecting for IPv6
 	destination cache entries.  At twice this value the system will
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index b028a1dc150d..e29aff15acc9 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -33,6 +33,7 @@ struct netns_sysctl_ipv6 {
 	int auto_flowlabels;
 	int icmpv6_time;
 	int icmpv6_echo_ignore_all;
+	int icmpv6_echo_ignore_multicast;
 	int anycast_src_echo_reply;
 	int ip_nonlocal_bind;
 	int fwmark_reflect;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2f45d2a3e3a3..fdc117de849c 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -847,6 +847,7 @@ static int __net_init inet6_net_init(struct net *net)
 	net->ipv6.sysctl.bindv6only = 0;
 	net->ipv6.sysctl.icmpv6_time = 1*HZ;
 	net->ipv6.sysctl.icmpv6_echo_ignore_all = 0;
+	net->ipv6.sysctl.icmpv6_echo_ignore_multicast = 0;
 	net->ipv6.sysctl.flowlabel_consistency = 1;
 	net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS;
 	net->ipv6.sysctl.idgen_retries = 3;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 802faa2fcc0e..0907bcede5e5 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -684,6 +684,10 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	struct ipcm6_cookie ipc6;
 	u32 mark = IP6_REPLY_MARK(net, skb->mark);
 
+	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) &&
+	    net->ipv6.sysctl.icmpv6_echo_ignore_multicast)
+		return;
+
 	saddr = &ipv6_hdr(skb)->daddr;
 
 	if (!ipv6_unicast_destination(skb) &&
@@ -1115,6 +1119,13 @@ static struct ctl_table ipv6_icmp_table_template[] = {
 		.mode		= 0644,
 		.proc_handler = proc_dointvec,
 	},
+	{
+		.procname	= "echo_ignore_multicast",
+		.data		= &init_net.ipv6.sysctl.icmpv6_echo_ignore_multicast,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler = proc_dointvec,
+	},
 	{ },
 };
 
@@ -1129,6 +1140,7 @@ struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
 	if (table) {
 		table[0].data = &net->ipv6.sysctl.icmpv6_time;
 		table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all;
+		table[2].data = &net->ipv6.sysctl.icmpv6_echo_ignore_multicast;
 	}
 	return table;
 }
-- 
cgit v1.2.3


From f295b3ae9f5927e084bd5decdff82390e3471801 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Wed, 20 Mar 2019 02:03:36 +0000
Subject: net/tls: Add support of AES128-CCM based ciphers

Added support for AES128-CCM based record encryption. AES128-CCM is
similar to AES128-GCM. Both of them have same salt/iv/mac size. The
notable difference between the two is that while invoking AES128-CCM
operation, the salt||nonce (which is passed as IV) has to be prefixed
with a hardcoded value '2'. Further, CCM implementation in kernel
requires IV passed in crypto_aead_request() to be full '16' bytes.
Therefore, the record structure 'struct tls_rec' has been modified to
reserve '16' bytes for IV. This works for both GCM and CCM based cipher.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h        | 15 +++++++++--
 include/uapi/linux/tls.h | 15 +++++++++++
 net/tls/tls_main.c       | 31 ++++++++++++----------
 net/tls/tls_sw.c         | 67 ++++++++++++++++++++++++++++++++++++------------
 4 files changed, 97 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/net/tls.h b/include/net/tls.h
index a5a938583295..3ce71d78414c 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -60,6 +60,17 @@
 #define TLS_AAD_SPACE_SIZE		13
 #define TLS_DEVICE_NAME_MAX		32
 
+#define MAX_IV_SIZE			16
+
+/* For AES-CCM, the full 16-bytes of IV is made of '4' fields of given sizes.
+ *
+ * IV[16] = b0[1] || implicit nonce[4] || explicit nonce[8] || length[3]
+ *
+ * The field 'length' is encoded in field 'b0' as '(length width - 1)'.
+ * Hence b0 contains (3 - 1) = 2.
+ */
+#define TLS_AES_CCM_IV_B0_BYTE		2
+
 /*
  * This structure defines the routines for Inline TLS driver.
  * The following routines are optional and filled with a
@@ -123,8 +134,7 @@ struct tls_rec {
 	struct scatterlist sg_content_type;
 
 	char aad_space[TLS_AAD_SPACE_SIZE];
-	u8 iv_data[TLS_CIPHER_AES_GCM_128_IV_SIZE +
-		   TLS_CIPHER_AES_GCM_128_SALT_SIZE];
+	u8 iv_data[MAX_IV_SIZE];
 	struct aead_request aead_req;
 	u8 aead_req_ctx[];
 };
@@ -219,6 +229,7 @@ struct tls_prot_info {
 	u16 tag_size;
 	u16 overhead_size;
 	u16 iv_size;
+	u16 salt_size;
 	u16 rec_seq_size;
 	u16 aad_size;
 	u16 tail_size;
diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h
index 401d6f01de6a..5b9c26753e46 100644
--- a/include/uapi/linux/tls.h
+++ b/include/uapi/linux/tls.h
@@ -70,6 +70,13 @@
 #define TLS_CIPHER_AES_GCM_256_TAG_SIZE		16
 #define TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE		8
 
+#define TLS_CIPHER_AES_CCM_128				53
+#define TLS_CIPHER_AES_CCM_128_IV_SIZE			8
+#define TLS_CIPHER_AES_CCM_128_KEY_SIZE		16
+#define TLS_CIPHER_AES_CCM_128_SALT_SIZE		4
+#define TLS_CIPHER_AES_CCM_128_TAG_SIZE		16
+#define TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE		8
+
 #define TLS_SET_RECORD_TYPE	1
 #define TLS_GET_RECORD_TYPE	2
 
@@ -94,4 +101,12 @@ struct tls12_crypto_info_aes_gcm_256 {
 	unsigned char rec_seq[TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE];
 };
 
+struct tls12_crypto_info_aes_ccm_128 {
+	struct tls_crypto_info info;
+	unsigned char iv[TLS_CIPHER_AES_CCM_128_IV_SIZE];
+	unsigned char key[TLS_CIPHER_AES_CCM_128_KEY_SIZE];
+	unsigned char salt[TLS_CIPHER_AES_CCM_128_SALT_SIZE];
+	unsigned char rec_seq[TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE];
+};
+
 #endif /* _UAPI_LINUX_TLS_H */
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index df921a2904b9..0e24edab2535 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -469,27 +469,32 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 
 	switch (crypto_info->cipher_type) {
 	case TLS_CIPHER_AES_GCM_128:
+		optsize = sizeof(struct tls12_crypto_info_aes_gcm_128);
+		break;
 	case TLS_CIPHER_AES_GCM_256: {
-		optsize = crypto_info->cipher_type == TLS_CIPHER_AES_GCM_128 ?
-			sizeof(struct tls12_crypto_info_aes_gcm_128) :
-			sizeof(struct tls12_crypto_info_aes_gcm_256);
-		if (optlen != optsize) {
-			rc = -EINVAL;
-			goto err_crypto_info;
-		}
-		rc = copy_from_user(crypto_info + 1, optval + sizeof(*crypto_info),
-				    optlen - sizeof(*crypto_info));
-		if (rc) {
-			rc = -EFAULT;
-			goto err_crypto_info;
-		}
+		optsize = sizeof(struct tls12_crypto_info_aes_gcm_256);
 		break;
 	}
+	case TLS_CIPHER_AES_CCM_128:
+		optsize = sizeof(struct tls12_crypto_info_aes_ccm_128);
+		break;
 	default:
 		rc = -EINVAL;
 		goto err_crypto_info;
 	}
 
+	if (optlen != optsize) {
+		rc = -EINVAL;
+		goto err_crypto_info;
+	}
+
+	rc = copy_from_user(crypto_info + 1, optval + sizeof(*crypto_info),
+			    optlen - sizeof(*crypto_info));
+	if (rc) {
+		rc = -EFAULT;
+		goto err_crypto_info;
+	}
+
 	if (tx) {
 #ifdef CONFIG_TLS_DEVICE
 		rc = tls_set_device_offload(sk, ctx);
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 425351ac2a9b..f635c103581e 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -42,8 +42,6 @@
 #include <net/strparser.h>
 #include <net/tls.h>
 
-#define MAX_IV_SIZE	TLS_CIPHER_AES_GCM_128_IV_SIZE
-
 static int __skb_nsg(struct sk_buff *skb, int offset, int len,
                      unsigned int recursion_level)
 {
@@ -479,11 +477,18 @@ static int tls_do_encryption(struct sock *sk,
 	struct tls_rec *rec = ctx->open_rec;
 	struct sk_msg *msg_en = &rec->msg_encrypted;
 	struct scatterlist *sge = sk_msg_elem(msg_en, start);
-	int rc;
+	int rc, iv_offset = 0;
+
+	/* For CCM based ciphers, first byte of IV is a constant */
+	if (prot->cipher_type == TLS_CIPHER_AES_CCM_128) {
+		rec->iv_data[0] = TLS_AES_CCM_IV_B0_BYTE;
+		iv_offset = 1;
+	}
+
+	memcpy(&rec->iv_data[iv_offset], tls_ctx->tx.iv,
+	       prot->iv_size + prot->salt_size);
 
-	memcpy(rec->iv_data, tls_ctx->tx.iv, sizeof(rec->iv_data));
-	xor_iv_with_seq(prot->version, rec->iv_data,
-			tls_ctx->tx.rec_seq);
+	xor_iv_with_seq(prot->version, rec->iv_data, tls_ctx->tx.rec_seq);
 
 	sge->offset += prot->prepend_size;
 	sge->length -= prot->prepend_size;
@@ -1344,6 +1349,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
 	struct scatterlist *sgout = NULL;
 	const int data_len = rxm->full_len - prot->overhead_size +
 			     prot->tail_size;
+	int iv_offset = 0;
 
 	if (*zc && (out_iov || out_sg)) {
 		if (out_iov)
@@ -1386,18 +1392,25 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
 	aad = (u8 *)(sgout + n_sgout);
 	iv = aad + prot->aad_size;
 
+	/* For CCM based ciphers, first byte of nonce+iv is always '2' */
+	if (prot->cipher_type == TLS_CIPHER_AES_CCM_128) {
+		iv[0] = 2;
+		iv_offset = 1;
+	}
+
 	/* Prepare IV */
 	err = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE,
-			    iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+			    iv + iv_offset + prot->salt_size,
 			    prot->iv_size);
 	if (err < 0) {
 		kfree(mem);
 		return err;
 	}
 	if (prot->version == TLS_1_3_VERSION)
-		memcpy(iv, tls_ctx->rx.iv, crypto_aead_ivsize(ctx->aead_recv));
+		memcpy(iv + iv_offset, tls_ctx->rx.iv,
+		       crypto_aead_ivsize(ctx->aead_recv));
 	else
-		memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+		memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size);
 
 	xor_iv_with_seq(prot->version, iv, tls_ctx->rx.rec_seq);
 
@@ -2152,14 +2165,15 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	struct tls_crypto_info *crypto_info;
 	struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
 	struct tls12_crypto_info_aes_gcm_256 *gcm_256_info;
+	struct tls12_crypto_info_aes_ccm_128 *ccm_128_info;
 	struct tls_sw_context_tx *sw_ctx_tx = NULL;
 	struct tls_sw_context_rx *sw_ctx_rx = NULL;
 	struct cipher_context *cctx;
 	struct crypto_aead **aead;
 	struct strp_callbacks cb;
-	u16 nonce_size, tag_size, iv_size, rec_seq_size;
+	u16 nonce_size, tag_size, iv_size, rec_seq_size, salt_size;
 	struct crypto_tfm *tfm;
-	char *iv, *rec_seq, *key, *salt;
+	char *iv, *rec_seq, *key, *salt, *cipher_name;
 	size_t keysize;
 	int rc = 0;
 
@@ -2224,6 +2238,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		keysize = TLS_CIPHER_AES_GCM_128_KEY_SIZE;
 		key = gcm_128_info->key;
 		salt = gcm_128_info->salt;
+		salt_size = TLS_CIPHER_AES_GCM_128_SALT_SIZE;
+		cipher_name = "gcm(aes)";
 		break;
 	}
 	case TLS_CIPHER_AES_GCM_256: {
@@ -2239,6 +2255,25 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		keysize = TLS_CIPHER_AES_GCM_256_KEY_SIZE;
 		key = gcm_256_info->key;
 		salt = gcm_256_info->salt;
+		salt_size = TLS_CIPHER_AES_GCM_256_SALT_SIZE;
+		cipher_name = "gcm(aes)";
+		break;
+	}
+	case TLS_CIPHER_AES_CCM_128: {
+		nonce_size = TLS_CIPHER_AES_CCM_128_IV_SIZE;
+		tag_size = TLS_CIPHER_AES_CCM_128_TAG_SIZE;
+		iv_size = TLS_CIPHER_AES_CCM_128_IV_SIZE;
+		iv = ((struct tls12_crypto_info_aes_ccm_128 *)crypto_info)->iv;
+		rec_seq_size = TLS_CIPHER_AES_CCM_128_REC_SEQ_SIZE;
+		rec_seq =
+		((struct tls12_crypto_info_aes_ccm_128 *)crypto_info)->rec_seq;
+		ccm_128_info =
+		(struct tls12_crypto_info_aes_ccm_128 *)crypto_info;
+		keysize = TLS_CIPHER_AES_CCM_128_KEY_SIZE;
+		key = ccm_128_info->key;
+		salt = ccm_128_info->salt;
+		salt_size = TLS_CIPHER_AES_CCM_128_SALT_SIZE;
+		cipher_name = "ccm(aes)";
 		break;
 	}
 	default:
@@ -2268,16 +2303,16 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	prot->overhead_size = prot->prepend_size +
 			      prot->tag_size + prot->tail_size;
 	prot->iv_size = iv_size;
-	cctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
-			   GFP_KERNEL);
+	prot->salt_size = salt_size;
+	cctx->iv = kmalloc(iv_size + salt_size, GFP_KERNEL);
 	if (!cctx->iv) {
 		rc = -ENOMEM;
 		goto free_priv;
 	}
 	/* Note: 128 & 256 bit salt are the same size */
-	memcpy(cctx->iv, salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
-	memcpy(cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
 	prot->rec_seq_size = rec_seq_size;
+	memcpy(cctx->iv, salt, salt_size);
+	memcpy(cctx->iv + salt_size, iv, iv_size);
 	cctx->rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL);
 	if (!cctx->rec_seq) {
 		rc = -ENOMEM;
@@ -2285,7 +2320,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	}
 
 	if (!*aead) {
-		*aead = crypto_alloc_aead("gcm(aes)", 0, 0);
+		*aead = crypto_alloc_aead(cipher_name, 0, 0);
 		if (IS_ERR(*aead)) {
 			rc = PTR_ERR(*aead);
 			*aead = NULL;
-- 
cgit v1.2.3


From 4bd97d51a5e602ea1fbdab8c2d653513dea17115 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 20 Mar 2019 11:02:04 +0100
Subject: net: dev: rename queue selection helpers.

With the following patches, we are going to use __netdev_pick_tx() in
many modules. Rename it to netdev_pick_tx(), to make it clear is
a public API.

Also rename the existing netdev_pick_tx() to netdev_core_pick_tx(),
to avoid name clashes.

Suggested-by: Eric Dumazet <edumazet@google.com>
Suggested-by: David Miller <davem@davemloft.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  6 +++---
 net/core/dev.c            | 18 +++++++++---------
 net/core/netpoll.c        |  2 +-
 net/xfrm/xfrm_device.c    |  2 +-
 4 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 26f69cf763f4..57cd2bdd9f78 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2152,9 +2152,9 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 				  &qdisc_xmit_lock_key);	\
 }
 
-struct netdev_queue *netdev_pick_tx(struct net_device *dev,
-				    struct sk_buff *skb,
-				    struct net_device *sb_dev);
+struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
+					 struct sk_buff *skb,
+					 struct net_device *sb_dev);
 
 /* returns the headroom that the master device needs to take in account
  * when forwarding to this dev
diff --git a/net/core/dev.c b/net/core/dev.c
index 2b67f2aa59dd..5dd3e3f7dd12 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3704,8 +3704,8 @@ u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(dev_pick_tx_cpu_id);
 
-static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
-			    struct net_device *sb_dev)
+static u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
+			  struct net_device *sb_dev)
 {
 	struct sock *sk = skb->sk;
 	int queue_index = sk_tx_queue_get(sk);
@@ -3730,9 +3730,9 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 	return queue_index;
 }
 
-struct netdev_queue *netdev_pick_tx(struct net_device *dev,
-				    struct sk_buff *skb,
-				    struct net_device *sb_dev)
+struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
+					 struct sk_buff *skb,
+					 struct net_device *sb_dev)
 {
 	int queue_index = 0;
 
@@ -3748,9 +3748,9 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 
 		if (ops->ndo_select_queue)
 			queue_index = ops->ndo_select_queue(dev, skb, sb_dev,
-							    __netdev_pick_tx);
+							    netdev_pick_tx);
 		else
-			queue_index = __netdev_pick_tx(dev, skb, sb_dev);
+			queue_index = netdev_pick_tx(dev, skb, sb_dev);
 
 		queue_index = netdev_cap_txqueue(dev, queue_index);
 	}
@@ -3824,7 +3824,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	else
 		skb_dst_force(skb);
 
-	txq = netdev_pick_tx(dev, skb, sb_dev);
+	txq = netdev_core_pick_tx(dev, skb, sb_dev);
 	q = rcu_dereference_bh(txq->qdisc);
 
 	trace_net_dev_queue(skb);
@@ -4429,7 +4429,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
 	bool free_skb = true;
 	int cpu, rc;
 
-	txq = netdev_pick_tx(dev, skb, NULL);
+	txq = netdev_core_pick_tx(dev, skb, NULL);
 	cpu = smp_processor_id();
 	HARD_TX_LOCK(dev, txq, cpu);
 	if (!netif_xmit_stopped(txq)) {
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 361aabffb8c0..e365e8fb1c40 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -323,7 +323,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 	if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
 		struct netdev_queue *txq;
 
-		txq = netdev_pick_tx(dev, skb, NULL);
+		txq = netdev_core_pick_tx(dev, skb, NULL);
 
 		/* try until next clock tick */
 		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index b8736f56e7f7..2db1626557c5 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -247,7 +247,7 @@ void xfrm_dev_resume(struct sk_buff *skb)
 	unsigned long flags;
 
 	rcu_read_lock();
-	txq = netdev_pick_tx(dev, skb, NULL);
+	txq = netdev_core_pick_tx(dev, skb, NULL);
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_stopped(txq))
-- 
cgit v1.2.3


From b71b5837f8711dbc4bc0424cb5c75e5921be055c Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 20 Mar 2019 11:02:05 +0100
Subject: packet: rework packet_pick_tx_queue() to use common code selection

Currently packet_pick_tx_queue() is the only caller of
ndo_select_queue() using a fallback argument other than
netdev_pick_tx.

Leveraging rx queue, we can obtain a similar queue selection
behavior using core helpers. After this change, ndo_select_queue()
is always invoked with netdev_pick_tx() as fallback.
We can change ndo_select_queue() signature in a followup patch,
dropping an indirect call per transmitted packet in some scenarios
(e.g. TCP syn and XDP generic xmit)

This changes slightly how af packet queue selection happens when
PACKET_QDISC_BYPASS is set. It's now more similar to plan dev_queue_xmit()
tacking in account both XPS and TC mapping.

 v1  -> v2:
  - rebased after helper name change
 RFC -> v1:
  - initialize sender_cpu to the expected value

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            |  5 +++--
 net/packet/af_packet.c    | 15 +++++++--------
 3 files changed, 12 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 57cd2bdd9f78..0ff28db4239f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2152,6 +2152,8 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 				  &qdisc_xmit_lock_key);	\
 }
 
+u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
+		     struct net_device *sb_dev);
 struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
 					 struct sk_buff *skb,
 					 struct net_device *sb_dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 5dd3e3f7dd12..1a76b4fe9b97 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3704,8 +3704,8 @@ u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(dev_pick_tx_cpu_id);
 
-static u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
-			  struct net_device *sb_dev)
+u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
+		     struct net_device *sb_dev)
 {
 	struct sock *sk = skb->sk;
 	int queue_index = sk_tx_queue_get(sk);
@@ -3729,6 +3729,7 @@ static u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 
 	return queue_index;
 }
+EXPORT_SYMBOL(netdev_pick_tx);
 
 struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
 					 struct sk_buff *skb,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 323655a25674..a8809dc0e1ab 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -275,24 +275,23 @@ static bool packet_use_direct_xmit(const struct packet_sock *po)
 	return po->xmit == packet_direct_xmit;
 }
 
-static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb,
-				  struct net_device *sb_dev)
-{
-	return dev_pick_tx_cpu_id(dev, skb, sb_dev, NULL);
-}
-
 static u16 packet_pick_tx_queue(struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int cpu = raw_smp_processor_id();
 	u16 queue_index;
 
+#ifdef CONFIG_XPS
+	skb->sender_cpu = cpu + 1;
+#endif
+	skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues);
 	if (ops->ndo_select_queue) {
 		queue_index = ops->ndo_select_queue(dev, skb, NULL,
-						    __packet_pick_tx_queue);
+						    netdev_pick_tx);
 		queue_index = netdev_cap_txqueue(dev, queue_index);
 	} else {
-		queue_index = __packet_pick_tx_queue(dev, skb, NULL);
+		queue_index = netdev_pick_tx(dev, skb, NULL);
 	}
 
 	return queue_index;
-- 
cgit v1.2.3


From a350eccee5830d9a1f29e393a88dc05a15326d44 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 20 Mar 2019 11:02:06 +0100
Subject: net: remove 'fallback' argument from dev->ndo_select_queue()

After the previous patch, all the callers of ndo_select_queue()
provide as a 'fallback' argument netdev_pick_tx.
The only exceptions are nested calls to ndo_select_queue(),
which pass down the 'fallback' available in the current scope
- still netdev_pick_tx.

We can drop such argument and replace fallback() invocation with
netdev_pick_tx(). This avoids an indirect call per xmit packet
in some scenarios (TCP syn, UDP unconnected, XDP generic, pktgen)
with device drivers implementing such ndo. It also clean the code
a bit.

Tested with ixgbe and CONFIG_FCOE=m

With pktgen using queue xmit:
threads		vanilla 	patched
		(kpps)		(kpps)
1		2334		2428
2		4166		4278
4		7895		8100

 v1 -> v2:
 - rebased after helper's name change

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/hfi1/vnic_main.c            |  3 +--
 drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c |  6 ++----
 drivers/net/bonding/bond_main.c                   |  3 +--
 drivers/net/ethernet/amazon/ena/ena_netdev.c      |  5 ++---
 drivers/net/ethernet/broadcom/bcmsysport.c        |  7 +++----
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c   |  5 ++---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h   |  3 +--
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c   |  5 ++---
 drivers/net/ethernet/hisilicon/hns/hns_enet.c     |  5 ++---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c     |  5 ++---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c        |  7 +++----
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h      |  3 +--
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  3 +--
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c   |  5 ++---
 drivers/net/ethernet/qlogic/qede/qede.h           |  3 +--
 drivers/net/ethernet/qlogic/qede/qede_fp.c        |  5 ++---
 drivers/net/ethernet/renesas/ravb_main.c          |  3 +--
 drivers/net/ethernet/sun/ldmvsw.c                 |  3 +--
 drivers/net/ethernet/sun/sunvnet.c                |  3 +--
 drivers/net/hyperv/netvsc_drv.c                   | 10 ++++------
 drivers/net/net_failover.c                        |  8 +++-----
 drivers/net/team/team.c                           |  3 +--
 drivers/net/tun.c                                 |  3 +--
 drivers/net/wireless/marvell/mwifiex/main.c       |  3 +--
 drivers/net/xen-netback/interface.c               |  6 +++---
 drivers/net/xen-netfront.c                        |  3 +--
 drivers/staging/rtl8188eu/os_dep/os_intfs.c       |  3 +--
 drivers/staging/rtl8723bs/os_dep/os_intfs.c       |  3 +--
 include/linux/netdevice.h                         | 12 ++++--------
 net/core/dev.c                                    |  9 +++------
 net/mac80211/iface.c                              |  6 ++----
 net/packet/af_packet.c                            |  3 +--
 32 files changed, 57 insertions(+), 97 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c
index a922db58be14..2b07032dbdda 100644
--- a/drivers/infiniband/hw/hfi1/vnic_main.c
+++ b/drivers/infiniband/hw/hfi1/vnic_main.c
@@ -423,8 +423,7 @@ tx_finish:
 
 static u16 hfi1_vnic_select_queue(struct net_device *netdev,
 				  struct sk_buff *skb,
-				  struct net_device *sb_dev,
-				  select_queue_fallback_t fallback)
+				  struct net_device *sb_dev)
 {
 	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
 	struct opa_vnic_skb_mdata *mdata;
diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
index ae70cd18903e..aeff68f582d3 100644
--- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
@@ -95,8 +95,7 @@ static netdev_tx_t opa_netdev_start_xmit(struct sk_buff *skb,
 }
 
 static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
-				 struct net_device *sb_dev,
-				 select_queue_fallback_t fallback)
+				 struct net_device *sb_dev)
 {
 	struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
 	struct opa_vnic_skb_mdata *mdata;
@@ -106,8 +105,7 @@ static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
 	mdata = skb_push(skb, sizeof(*mdata));
 	mdata->entropy = opa_vnic_calc_entropy(skb);
 	mdata->vl = opa_vnic_get_vl(adapter, skb);
-	rc = adapter->rn_ops->ndo_select_queue(netdev, skb,
-					       sb_dev, fallback);
+	rc = adapter->rn_ops->ndo_select_queue(netdev, skb, sb_dev);
 	skb_pull(skb, sizeof(*mdata));
 	return rc;
 }
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b59708c35faf..8ddbada9e281 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4114,8 +4114,7 @@ static inline int bond_slave_override(struct bonding *bond,
 
 
 static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     struct net_device *sb_dev,
-			     select_queue_fallback_t fallback)
+			     struct net_device *sb_dev)
 {
 	/* This helper function exists to help dev_pick_tx get the correct
 	 * destination queue.  Using a helper function skips a call to
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index a6eacf2099c3..71c8cac6e44e 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2258,8 +2258,7 @@ error_drop_packet:
 }
 
 static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    struct net_device *sb_dev,
-			    select_queue_fallback_t fallback)
+			    struct net_device *sb_dev)
 {
 	u16 qid;
 	/* we suspect that this is good for in--kernel network services that
@@ -2269,7 +2268,7 @@ static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
 	if (skb_rx_queue_recorded(skb))
 		qid = skb_get_rx_queue(skb);
 	else
-		qid = fallback(dev, skb, NULL);
+		qid = netdev_pick_tx(dev, skb, NULL);
 
 	return qid;
 }
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index bc3ac369cbe3..a9d3d26a7202 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2274,8 +2274,7 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 };
 
 static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
-				    struct net_device *sb_dev,
-				    select_queue_fallback_t fallback)
+				    struct net_device *sb_dev)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	u16 queue = skb_get_queue_mapping(skb);
@@ -2283,7 +2282,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
 	unsigned int q, port;
 
 	if (!netdev_uses_dsa(dev))
-		return fallback(dev, skb, NULL);
+		return netdev_pick_tx(dev, skb, NULL);
 
 	/* DSA tagging layer will have configured the correct queue */
 	q = BRCM_TAG_GET_QUEUE(queue);
@@ -2291,7 +2290,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
 	tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues];
 
 	if (unlikely(!tx_ring))
-		return fallback(dev, skb, NULL);
+		return netdev_pick_tx(dev, skb, NULL);
 
 	return tx_ring->index;
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ecb1bd7eb508..6012fe61735e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1909,8 +1909,7 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
 }
 
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev,
-		       select_queue_fallback_t fallback)
+		       struct net_device *sb_dev)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
@@ -1932,7 +1931,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return fallback(dev, skb, NULL) %
+	return netdev_pick_tx(dev, skb, NULL) %
 	       (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 2462e7aa0c5d..7f8df08a7a4c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -498,8 +498,7 @@ int bnx2x_set_vf_spoofchk(struct net_device *dev, int idx, bool val);
 
 /* select_queue callback */
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev,
-		       select_queue_fallback_t fallback);
+		       struct net_device *sb_dev);
 
 static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 					struct bnx2x_fastpath *fp,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 89179e316687..3339f1f4bcdd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -979,8 +979,7 @@ freeout:
 }
 
 static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     struct net_device *sb_dev,
-			     select_queue_fallback_t fallback)
+			     struct net_device *sb_dev)
 {
 	int txq;
 
@@ -1022,7 +1021,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
 		return txq;
 	}
 
-	return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
+	return netdev_pick_tx(dev, skb, NULL) % dev->real_num_tx_queues;
 }
 
 static int closest_timer(const struct sge *s, int time)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 60e7d7ae3787..e37a0ca0db89 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1964,8 +1964,7 @@ static void hns_nic_get_stats64(struct net_device *ndev,
 
 static u16
 hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
-		     struct net_device *sb_dev,
-		     select_queue_fallback_t fallback)
+		     struct net_device *sb_dev)
 {
 	struct ethhdr *eth_hdr = (struct ethhdr *)skb->data;
 	struct hns_nic_priv *priv = netdev_priv(ndev);
@@ -1975,7 +1974,7 @@ hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	    is_multicast_ether_addr(eth_hdr->h_dest))
 		return 0;
 	else
-		return fallback(ndev, skb, NULL);
+		return netdev_pick_tx(ndev, skb, NULL);
 }
 
 static const struct net_device_ops hns_nic_netdev_ops = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 76aeed845a73..16c728984164 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8483,8 +8483,7 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
 
 #ifdef IXGBE_FCOE
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
-			      struct net_device *sb_dev,
-			      select_queue_fallback_t fallback)
+			      struct net_device *sb_dev)
 {
 	struct ixgbe_adapter *adapter;
 	struct ixgbe_ring_feature *f;
@@ -8514,7 +8513,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 			break;
 		/* fall through */
 	default:
-		return fallback(dev, skb, sb_dev);
+		return netdev_pick_tx(dev, skb, sb_dev);
 	}
 
 	f = &adapter->ring_feature[RING_F_FCOE];
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 2cbd2bd7c67c..fba54fb06e18 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -685,16 +685,15 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
 }
 
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 struct net_device *sb_dev,
-			 select_queue_fallback_t fallback)
+			 struct net_device *sb_dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u16 rings_p_up = priv->num_tx_rings_p_up;
 
 	if (netdev_get_num_tc(dev))
-		return fallback(dev, skb, NULL);
+		return netdev_pick_tx(dev, skb, NULL);
 
-	return fallback(dev, skb, NULL) % rings_p_up;
+	return netdev_pick_tx(dev, skb, NULL) % rings_p_up;
 }
 
 static void mlx4_bf_copy(void __iomem *dst, const void *src,
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 8137454e2534..630f15977f09 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -698,8 +698,7 @@ void mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq);
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 struct net_device *sb_dev,
-			 select_queue_fallback_t fallback);
+			 struct net_device *sb_dev);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_rx_alloc *frame,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 71c65cc17904..5c2e3276d9cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -769,8 +769,7 @@ struct mlx5e_profile {
 void mlx5e_build_ptys2ethtool_map(void);
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev,
-		       select_queue_fallback_t fallback);
+		       struct net_device *sb_dev);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			  struct mlx5e_tx_wqe *wqe, u16 pi);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 25a8f8260c14..ce1406bb1512 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -110,11 +110,10 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb
 #endif
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev,
-		       select_queue_fallback_t fallback)
+		       struct net_device *sb_dev)
 {
+	int channel_ix = netdev_pick_tx(dev, skb, NULL);
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	int channel_ix = fallback(dev, skb, NULL);
 	u16 num_channels;
 	int up = 0;
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 63a78162cfaf..92fe226980fd 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -498,8 +498,7 @@ struct qede_reload_args {
 /* Datapath functions definition */
 netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
-		      struct net_device *sb_dev,
-		      select_queue_fallback_t fallback);
+		      struct net_device *sb_dev);
 netdev_features_t qede_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
 				      netdev_features_t features);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 31b046e24565..c342b07e3a93 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1696,8 +1696,7 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 }
 
 u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
-		      struct net_device *sb_dev,
-		      select_queue_fallback_t fallback)
+		      struct net_device *sb_dev)
 {
 	struct qede_dev *edev = netdev_priv(dev);
 	int total_txq;
@@ -1705,7 +1704,7 @@ u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
 	total_txq = QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc;
 
 	return QEDE_TSS_COUNT(edev) ?
-		fallback(dev, skb, NULL) % total_txq :  0;
+		netdev_pick_tx(dev, skb, NULL) % total_txq :  0;
 }
 
 /* 8B udp header + 8B base tunnel header + 32B option length */
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 8154b38c08f7..4f648394e645 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1615,8 +1615,7 @@ drop:
 }
 
 static u16 ravb_select_queue(struct net_device *ndev, struct sk_buff *skb,
-			     struct net_device *sb_dev,
-			     select_queue_fallback_t fallback)
+			     struct net_device *sb_dev)
 {
 	/* If skb needs TX timestamp, it is handled in network control queue */
 	return (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) ? RAVB_NC :
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index 644e42c181ee..01ea0d6f8819 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -101,8 +101,7 @@ static struct vnet_port *vsw_tx_port_find(struct sk_buff *skb,
 }
 
 static u16 vsw_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    struct net_device *sb_dev,
-			    select_queue_fallback_t fallback)
+			    struct net_device *sb_dev)
 {
 	struct vnet_port *port = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 590172818b92..96b883f965f6 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -234,8 +234,7 @@ static struct vnet_port *vnet_tx_port_find(struct sk_buff *skb,
 }
 
 static u16 vnet_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     struct net_device *sb_dev,
-			     select_queue_fallback_t fallback)
+			     struct net_device *sb_dev)
 {
 	struct vnet *vp = netdev_priv(dev);
 	struct vnet_port *port = __tx_port_find(vp, skb);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index cf4897043e83..1a08679f90ce 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -308,7 +308,7 @@ static inline int netvsc_get_tx_queue(struct net_device *ndev,
  * If a valid queue has already been assigned, then use that.
  * Otherwise compute tx queue based on hash and the send table.
  *
- * This is basically similar to default (__netdev_pick_tx) with the added step
+ * This is basically similar to default (netdev_pick_tx) with the added step
  * of using the host send_table when no other queue has been assigned.
  *
  * TODO support XPS - but get_xps_queue not exported
@@ -331,8 +331,7 @@ static u16 netvsc_pick_tx(struct net_device *ndev, struct sk_buff *skb)
 }
 
 static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
-			       struct net_device *sb_dev,
-			       select_queue_fallback_t fallback)
+			       struct net_device *sb_dev)
 {
 	struct net_device_context *ndc = netdev_priv(ndev);
 	struct net_device *vf_netdev;
@@ -344,10 +343,9 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 		const struct net_device_ops *vf_ops = vf_netdev->netdev_ops;
 
 		if (vf_ops->ndo_select_queue)
-			txq = vf_ops->ndo_select_queue(vf_netdev, skb,
-						       sb_dev, fallback);
+			txq = vf_ops->ndo_select_queue(vf_netdev, skb, sb_dev);
 		else
-			txq = fallback(vf_netdev, skb, NULL);
+			txq = netdev_pick_tx(vf_netdev, skb, NULL);
 
 		/* Record the queue selected by VF so that it can be
 		 * used for common case where VF has more queues than
diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index ed1166adaa2f..b16a1221d19b 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -115,8 +115,7 @@ static netdev_tx_t net_failover_start_xmit(struct sk_buff *skb,
 
 static u16 net_failover_select_queue(struct net_device *dev,
 				     struct sk_buff *skb,
-				     struct net_device *sb_dev,
-				     select_queue_fallback_t fallback)
+				     struct net_device *sb_dev)
 {
 	struct net_failover_info *nfo_info = netdev_priv(dev);
 	struct net_device *primary_dev;
@@ -127,10 +126,9 @@ static u16 net_failover_select_queue(struct net_device *dev,
 		const struct net_device_ops *ops = primary_dev->netdev_ops;
 
 		if (ops->ndo_select_queue)
-			txq = ops->ndo_select_queue(primary_dev, skb,
-						    sb_dev, fallback);
+			txq = ops->ndo_select_queue(primary_dev, skb, sb_dev);
 		else
-			txq = fallback(primary_dev, skb, NULL);
+			txq = netdev_pick_tx(primary_dev, skb, NULL);
 
 		qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 6ed96fdfd96d..ee950aa48e3b 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1691,8 +1691,7 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev)
 }
 
 static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     struct net_device *sb_dev,
-			     select_queue_fallback_t fallback)
+			     struct net_device *sb_dev)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e9ca1c088d0b..ef3b65514976 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -606,8 +606,7 @@ static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 }
 
 static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    struct net_device *sb_dev,
-			    select_queue_fallback_t fallback)
+			    struct net_device *sb_dev)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 	u16 ret;
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 20cee5c397fb..f6da8edab7f1 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -1282,8 +1282,7 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev)
 
 static u16
 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
-				struct net_device *sb_dev,
-				select_queue_fallback_t fallback)
+				struct net_device *sb_dev)
 {
 	skb->priority = cfg80211_classify8021d(skb, NULL);
 	return mwifiex_1d_to_wmm_queue[skb->priority];
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 6da12518e693..783198844dd7 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -148,8 +148,7 @@ void xenvif_wake_queue(struct xenvif_queue *queue)
 }
 
 static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
-			       struct net_device *sb_dev,
-			       select_queue_fallback_t fallback)
+			       struct net_device *sb_dev)
 {
 	struct xenvif *vif = netdev_priv(dev);
 	unsigned int size = vif->hash.size;
@@ -162,7 +161,8 @@ static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
 		return 0;
 
 	if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
-		return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
+		return netdev_pick_tx(dev, skb, NULL) %
+		       dev->real_num_tx_queues;
 
 	xenvif_set_skb_hash(vif, skb);
 
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index c914c24f880b..80c30321de41 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -543,8 +543,7 @@ static int xennet_count_skb_slots(struct sk_buff *skb)
 }
 
 static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
-			       struct net_device *sb_dev,
-			       select_queue_fallback_t fallback)
+			       struct net_device *sb_dev)
 {
 	unsigned int num_queues = dev->real_num_tx_queues;
 	u32 hash;
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index 8dde5a40e253..2c088af44c8b 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -245,8 +245,7 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb)
 }
 
 static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    struct net_device *sb_dev,
-			    select_queue_fallback_t fallback)
+			    struct net_device *sb_dev)
 {
 	struct adapter *padapter = rtw_netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/drivers/staging/rtl8723bs/os_dep/os_intfs.c b/drivers/staging/rtl8723bs/os_dep/os_intfs.c
index 143e3f9b31aa..0a20a4e9e19a 100644
--- a/drivers/staging/rtl8723bs/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8723bs/os_dep/os_intfs.c
@@ -404,8 +404,7 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb)
 
 
 static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    struct net_device *sb_dev,
-			    select_queue_fallback_t fallback)
+			    struct net_device *sb_dev)
 {
 	struct adapter	*padapter = rtw_netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0ff28db4239f..823762291ebf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -986,8 +986,7 @@ struct devlink;
  *	those the driver believes to be appropriate.
  *
  * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
- *                         struct net_device *sb_dev,
- *                         select_queue_fallback_t fallback);
+ *                         struct net_device *sb_dev);
  *	Called to decide which queue to use when device supports multiple
  *	transmit queues.
  *
@@ -1268,8 +1267,7 @@ struct net_device_ops {
 						      netdev_features_t features);
 	u16			(*ndo_select_queue)(struct net_device *dev,
 						    struct sk_buff *skb,
-						    struct net_device *sb_dev,
-						    select_queue_fallback_t fallback);
+						    struct net_device *sb_dev);
 	void			(*ndo_change_rx_flags)(struct net_device *dev,
 						       int flags);
 	void			(*ndo_set_rx_mode)(struct net_device *dev);
@@ -2641,11 +2639,9 @@ void dev_close_many(struct list_head *head, bool unlink);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
 u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
-		     struct net_device *sb_dev,
-		     select_queue_fallback_t fallback);
+		     struct net_device *sb_dev);
 u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev,
-		       select_queue_fallback_t fallback);
+		       struct net_device *sb_dev);
 int dev_queue_xmit(struct sk_buff *skb);
 int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
 int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
diff --git a/net/core/dev.c b/net/core/dev.c
index 1a76b4fe9b97..357111431ec9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3689,16 +3689,14 @@ get_cpus_map:
 }
 
 u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
-		     struct net_device *sb_dev,
-		     select_queue_fallback_t fallback)
+		     struct net_device *sb_dev)
 {
 	return 0;
 }
 EXPORT_SYMBOL(dev_pick_tx_zero);
 
 u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev,
-		       select_queue_fallback_t fallback)
+		       struct net_device *sb_dev)
 {
 	return (u16)raw_smp_processor_id() % dev->real_num_tx_queues;
 }
@@ -3748,8 +3746,7 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
 		const struct net_device_ops *ops = dev->netdev_ops;
 
 		if (ops->ndo_select_queue)
-			queue_index = ops->ndo_select_queue(dev, skb, sb_dev,
-							    netdev_pick_tx);
+			queue_index = ops->ndo_select_queue(dev, skb, sb_dev);
 		else
 			queue_index = netdev_pick_tx(dev, skb, sb_dev);
 
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 4a6ff1482a9f..f0d97eba250b 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1133,8 +1133,7 @@ static void ieee80211_uninit(struct net_device *dev)
 
 static u16 ieee80211_netdev_select_queue(struct net_device *dev,
 					 struct sk_buff *skb,
-					 struct net_device *sb_dev,
-					 select_queue_fallback_t fallback)
+					 struct net_device *sb_dev)
 {
 	return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
 }
@@ -1179,8 +1178,7 @@ static const struct net_device_ops ieee80211_dataif_ops = {
 
 static u16 ieee80211_monitor_select_queue(struct net_device *dev,
 					  struct sk_buff *skb,
-					  struct net_device *sb_dev,
-					  select_queue_fallback_t fallback)
+					  struct net_device *sb_dev)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a8809dc0e1ab..741953b42f44 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -287,8 +287,7 @@ static u16 packet_pick_tx_queue(struct sk_buff *skb)
 #endif
 	skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues);
 	if (ops->ndo_select_queue) {
-		queue_index = ops->ndo_select_queue(dev, skb, NULL,
-						    netdev_pick_tx);
+		queue_index = ops->ndo_select_queue(dev, skb, NULL);
 		queue_index = netdev_cap_txqueue(dev, queue_index);
 	} else {
 		queue_index = netdev_pick_tx(dev, skb, NULL);
-- 
cgit v1.2.3


From 0b03a5ca8b14321366eec4a903922d2b46d585ff Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Wed, 20 Mar 2019 10:29:27 -0400
Subject: ipv6: Add icmp_echo_ignore_anycast for ICMPv6

In addition to icmp_echo_ignore_multicast, there is a need to also
prevent responding to pings to anycast addresses for security.

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  5 +++++
 include/net/netns/ipv6.h               |  1 +
 net/ipv6/af_inet6.c                    |  1 +
 net/ipv6/icmp.c                        | 16 ++++++++++++++--
 4 files changed, 21 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 55ea7def46be..bd029fc55ccb 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1923,6 +1923,11 @@ echo_ignore_multicast - BOOLEAN
 	requests sent to it over the IPv6 protocol via multicast.
 	Default: 0
 
+echo_ignore_anycast - BOOLEAN
+	If set non-zero, then the kernel will ignore all ICMP ECHO
+	requests sent to it over the IPv6 protocol destined to anycast address.
+	Default: 0
+
 xfrm6_gc_thresh - INTEGER
 	The threshold at which we will start garbage collecting for IPv6
 	destination cache entries.  At twice this value the system will
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index e29aff15acc9..64e29b58bb5e 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -34,6 +34,7 @@ struct netns_sysctl_ipv6 {
 	int icmpv6_time;
 	int icmpv6_echo_ignore_all;
 	int icmpv6_echo_ignore_multicast;
+	int icmpv6_echo_ignore_anycast;
 	int anycast_src_echo_reply;
 	int ip_nonlocal_bind;
 	int fwmark_reflect;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index fdc117de849c..fa6b404cbd10 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -848,6 +848,7 @@ static int __net_init inet6_net_init(struct net *net)
 	net->ipv6.sysctl.icmpv6_time = 1*HZ;
 	net->ipv6.sysctl.icmpv6_echo_ignore_all = 0;
 	net->ipv6.sysctl.icmpv6_echo_ignore_multicast = 0;
+	net->ipv6.sysctl.icmpv6_echo_ignore_anycast = 0;
 	net->ipv6.sysctl.flowlabel_consistency = 1;
 	net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS;
 	net->ipv6.sysctl.idgen_retries = 3;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 0907bcede5e5..cc14b9998941 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -683,6 +683,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	struct dst_entry *dst;
 	struct ipcm6_cookie ipc6;
 	u32 mark = IP6_REPLY_MARK(net, skb->mark);
+	bool acast;
 
 	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) &&
 	    net->ipv6.sysctl.icmpv6_echo_ignore_multicast)
@@ -690,9 +691,12 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 
 	saddr = &ipv6_hdr(skb)->daddr;
 
+	acast = ipv6_anycast_destination(skb_dst(skb), saddr);
+	if (acast && net->ipv6.sysctl.icmpv6_echo_ignore_anycast)
+		return;
+
 	if (!ipv6_unicast_destination(skb) &&
-	    !(net->ipv6.sysctl.anycast_src_echo_reply &&
-	      ipv6_anycast_destination(skb_dst(skb), saddr)))
+	    !(net->ipv6.sysctl.anycast_src_echo_reply && acast))
 		saddr = NULL;
 
 	memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
@@ -1126,6 +1130,13 @@ static struct ctl_table ipv6_icmp_table_template[] = {
 		.mode		= 0644,
 		.proc_handler = proc_dointvec,
 	},
+	{
+		.procname	= "echo_ignore_anycast",
+		.data		= &init_net.ipv6.sysctl.icmpv6_echo_ignore_anycast,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler = proc_dointvec,
+	},
 	{ },
 };
 
@@ -1141,6 +1152,7 @@ struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
 		table[0].data = &net->ipv6.sysctl.icmpv6_time;
 		table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all;
 		table[2].data = &net->ipv6.sysctl.icmpv6_echo_ignore_multicast;
+		table[3].data = &net->ipv6.sysctl.icmpv6_echo_ignore_anycast;
 	}
 	return table;
 }
-- 
cgit v1.2.3


From c7a1ce397adacaf5d4bb2eab0a738b5f80dc3e43 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 21 Mar 2019 05:21:35 -0700
Subject: ipv6: Change addrconf_f6i_alloc to use ip6_route_info_create

Change addrconf_f6i_alloc to generate a fib6_config and call
ip6_route_info_create. addrconf_f6i_alloc is the last caller to
fib6_info_alloc besides ip6_route_info_create, and there is no
reason for it to do its own initialization on a fib6_info.

Host routes need to be created even if the device is down, so add a
new flag, fc_ignore_dev_down, to fib6_config and update fib6_nh_init
to not error out if device is not up.

Notes on the conversion:
- ip_fib_metrics_init is the same as fib6_config has fc_mx set to NULL
  and fc_mx_len set to 0
- dst_nocount is handled by the RTF_ADDRCONF flag
- dst_host is handled by fc_dst_len = 128

nh_gw does not get set after the conversion to ip6_route_info_create
but it should not be set in addrconf_f6i_alloc since this is a host
route not a gateway route.

Everything else is a straight forward map between fib6_info and
fib6_config.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  3 ++-
 net/ipv6/route.c      | 42 ++++++++++++++++--------------------------
 2 files changed, 18 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 84097010237c..2acb78a762ee 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -50,7 +50,8 @@ struct fib6_config {
 	u32		fc_protocol;
 	u16		fc_type;        /* only 8 bits are used */
 	u16		fc_delete_all_nh : 1,
-			__unused : 15;
+			fc_ignore_dev_down:1,
+			__unused : 14;
 
 	struct in6_addr	fc_dst;
 	struct in6_addr	fc_src;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b9df5f8f1199..0c8c148ab61f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3079,7 +3079,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		goto out;
 	}
 
-	if (!(dev->flags & IFF_UP)) {
+	if (!(dev->flags & IFF_UP) && !cfg->fc_ignore_dev_down) {
 		NL_SET_ERR_MSG(extack, "Nexthop device is not up");
 		err = -ENETDOWN;
 		goto out;
@@ -3712,36 +3712,26 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 				     const struct in6_addr *addr,
 				     bool anycast, gfp_t gfp_flags)
 {
-	u32 tb_id;
-	struct net_device *dev = idev->dev;
-	struct fib6_info *f6i;
-
-	f6i = fib6_info_alloc(gfp_flags);
-	if (!f6i)
-		return ERR_PTR(-ENOMEM);
+	struct fib6_config cfg = {
+		.fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL,
+		.fc_ifindex = idev->dev->ifindex,
+		.fc_flags = RTF_UP | RTF_ADDRCONF | RTF_NONEXTHOP,
+		.fc_dst = *addr,
+		.fc_dst_len = 128,
+		.fc_protocol = RTPROT_KERNEL,
+		.fc_nlinfo.nl_net = net,
+		.fc_ignore_dev_down = true,
+	};
 
-	f6i->fib6_metrics = ip_fib_metrics_init(net, NULL, 0, NULL);
-	f6i->dst_nocount = true;
-	f6i->dst_host = true;
-	f6i->fib6_protocol = RTPROT_KERNEL;
-	f6i->fib6_flags = RTF_UP | RTF_NONEXTHOP;
 	if (anycast) {
-		f6i->fib6_type = RTN_ANYCAST;
-		f6i->fib6_flags |= RTF_ANYCAST;
+		cfg.fc_type = RTN_ANYCAST;
+		cfg.fc_flags |= RTF_ANYCAST;
 	} else {
-		f6i->fib6_type = RTN_LOCAL;
-		f6i->fib6_flags |= RTF_LOCAL;
+		cfg.fc_type = RTN_LOCAL;
+		cfg.fc_flags |= RTF_LOCAL;
 	}
 
-	f6i->fib6_nh.nh_gw = *addr;
-	dev_hold(dev);
-	f6i->fib6_nh.nh_dev = dev;
-	f6i->fib6_dst.addr = *addr;
-	f6i->fib6_dst.plen = 128;
-	tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
-	f6i->fib6_table = fib6_get_table(net, tb_id);
-
-	return f6i;
+	return ip6_route_info_create(&cfg, gfp_flags, NULL);
 }
 
 /* remove deleted ip from prefsrc entries */
-- 
cgit v1.2.3


From 0c3e0e3bb623c3735b8c9ab8aa8332f944f83a9f Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <ktkhai@virtuozzo.com>
Date: Wed, 20 Mar 2019 12:16:42 +0300
Subject: tun: Add ioctl() TUNGETDEVNETNS cmd to allow obtaining real net ns of
 tun device

In commit f2780d6d7475 "tun: Add ioctl() SIOCGSKNS cmd to allow
obtaining net ns of tun device" it was missed that tun may change
its net ns, while net ns of socket remains the same as it was
created initially. SIOCGSKNS returns net ns of socket, so it is
not suitable for obtaining net ns of device.

We may have two tun devices with the same names in two net ns,
and in this case it's not possible to determ, which of them
fd refers to (TUNGETIFF will return the same name).

This patch adds new ioctl() cmd for obtaining net ns of a device.

Reported-by: Harald Albrecht <harald.albrecht@gmx.net>
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c           | 8 ++++++++
 include/uapi/linux/if_tun.h | 1 +
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ef3b65514976..60d0a4e60ec5 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -3102,6 +3102,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 
 	tun_debug(KERN_INFO, tun, "tun_chr_ioctl cmd %u\n", cmd);
 
+	net = dev_net(tun->dev);
 	ret = 0;
 	switch (cmd) {
 	case TUNGETIFF:
@@ -3327,6 +3328,13 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		ret = tun_net_change_carrier(tun->dev, (bool)carrier);
 		break;
 
+	case TUNGETDEVNETNS:
+		ret = -EPERM;
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			goto unlock;
+		ret = open_related_ns(&net->ns, get_net_ns);
+		break;
+
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 23a6753b37df..454ae31b93c7 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -60,6 +60,7 @@
 #define TUNSETSTEERINGEBPF _IOR('T', 224, int)
 #define TUNSETFILTEREBPF _IOR('T', 225, int)
 #define TUNSETCARRIER _IOW('T', 226, int)
+#define TUNGETDEVNETNS _IO('T', 227)
 
 /* TUNSETIFF ifr flags */
 #define IFF_TUN		0x0001
-- 
cgit v1.2.3


From 9ab948a91b2c2abc8e82845c0e61f4b1683e3a4f Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 20 Mar 2019 09:18:59 -0700
Subject: ipv4: Allow amount of dirty memory from fib resizing to be
 controllable

fib_trie implementation calls synchronize_rcu when a certain amount of
pages are dirty from freed entries. The number of pages was determined
experimentally in 2009 (commit c3059477fce2d).

At the current setting, synchronize_rcu is called often -- 51 times in a
second in one test with an average of an 8 msec delay adding a fib entry.
The total impact is a lot of slow down modifying the fib. This is seen
in the output of 'time' - the difference between real time and sys+user.
For example, using 720,022 single path routes and 'ip -batch'[1]:

    $ time ./ip -batch ipv4/routes-1-hops
    real    0m14.214s
    user    0m2.513s
    sys     0m6.783s

So roughly 35% of the actual time to install the routes is from the ip
command getting scheduled out, most notably due to synchronize_rcu (this
is observed using 'perf sched timehist').

This patch makes the amount of dirty memory configurable between 64k where
the synchronize_rcu is called often (small, low end systems that are memory
sensitive) to 64M where synchronize_rcu is called rarely during a large
FIB change (for high end systems with lots of memory). The default is 512kB
which corresponds to the current setting of 128 pages with a 4kB page size.

As an example, at 16MB the worst interval shows 4 calls to synchronize_rcu
in a second blocking for up to 30 msec in a single instance, and a total
of almost 100 msec across the 4 calls in the second. The trade off is
allowing FIB entries to consume more memory in a given time window but
but with much better fib insertion rates (~30% increase in prefixes/sec).
With this patch and net.ipv4.fib_sync_mem set to 16MB, the same batch
file runs in:

    $ time ./ip -batch ipv4/routes-1-hops
    real    0m9.692s
    user    0m2.491s
    sys     0m6.769s

So the dead time is reduced to about 1/2 second or <5% of the real time.

[1] 'ip' modified to not request ACK messages which improves route
    insertion times by about 20%

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  5 +++++
 include/net/ip.h                       |  4 ++++
 net/ipv4/fib_trie.c                    | 14 ++++++++------
 net/ipv4/sysctl_net_ipv4.c             |  9 +++++++++
 4 files changed, 26 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index bd029fc55ccb..5eedc6941ce5 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -81,6 +81,11 @@ fib_multipath_hash_policy - INTEGER
 	0 - Layer 3
 	1 - Layer 4
 
+fib_sync_mem - UNSIGNED INTEGER
+	Amount of dirty memory from fib entries that can be backlogged before
+	synchronize_rcu is forced.
+	  Default: 512kB   Minimum: 64kB   Maximum: 64MB
+
 ip_forward_update_priority - INTEGER
 	Whether to update SKB priority from "TOS" field in IPv4 header after it
 	is forwarded. The new SKB priority is mapped from TOS field value
diff --git a/include/net/ip.h b/include/net/ip.h
index be3cad9c2e4c..aa09ae5f01a5 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -38,6 +38,10 @@
 #define IPV4_MAX_PMTU		65535U		/* RFC 2675, Section 5.1 */
 #define IPV4_MIN_MTU		68			/* RFC 791 */
 
+extern unsigned int sysctl_fib_sync_mem;
+extern unsigned int sysctl_fib_sync_mem_min;
+extern unsigned int sysctl_fib_sync_mem_max;
+
 struct sock;
 
 struct inet_skb_parm {
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index a573e37e0615..1704f432de1f 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -183,14 +183,16 @@ struct trie {
 };
 
 static struct key_vector *resize(struct trie *t, struct key_vector *tn);
-static size_t tnode_free_size;
+static unsigned int tnode_free_size;
 
 /*
- * synchronize_rcu after call_rcu for that many pages; it should be especially
- * useful before resizing the root node with PREEMPT_NONE configs; the value was
- * obtained experimentally, aiming to avoid visible slowdown.
+ * synchronize_rcu after call_rcu for outstanding dirty memory; it should be
+ * especially useful before resizing the root node with PREEMPT_NONE configs;
+ * the value was obtained experimentally, aiming to avoid visible slowdown.
  */
-static const int sync_pages = 128;
+unsigned int sysctl_fib_sync_mem = 512 * 1024;
+unsigned int sysctl_fib_sync_mem_min = 64 * 1024;
+unsigned int sysctl_fib_sync_mem_max = 64 * 1024 * 1024;
 
 static struct kmem_cache *fn_alias_kmem __ro_after_init;
 static struct kmem_cache *trie_leaf_kmem __ro_after_init;
@@ -504,7 +506,7 @@ static void tnode_free(struct key_vector *tn)
 		tn = container_of(head, struct tnode, rcu)->kv;
 	}
 
-	if (tnode_free_size >= PAGE_SIZE * sync_pages) {
+	if (tnode_free_size >= sysctl_fib_sync_mem) {
 		tnode_free_size = 0;
 		synchronize_rcu();
 	}
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index ba0fc4b18465..2316c08e9591 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -549,6 +549,15 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
 	},
+	{
+		.procname	= "fib_sync_mem",
+		.data		= &sysctl_fib_sync_mem,
+		.maxlen		= sizeof(sysctl_fib_sync_mem),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= &sysctl_fib_sync_mem_min,
+		.extra2		= &sysctl_fib_sync_mem_max,
+	},
 	{ }
 };
 
-- 
cgit v1.2.3


From 02afc7ad45bd6cfc9fd51fdbc132455371b63469 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 20 Mar 2019 20:02:56 +0100
Subject: net: dst: remove gc leftovers

Get rid of some obsolete gc-related documentation and macros that were
missed in commit 5b7c9a8ff828 ("net: remove dst gc related code").

CC: Wei Wang <weiwan@google.com>
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dst.h | 11 -----------
 net/core/dst.c    | 17 -----------------
 net/ipv4/route.c  |  2 +-
 3 files changed, 1 insertion(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/net/dst.h b/include/net/dst.h
index 6cf0870414c7..12b31c602cb0 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -19,17 +19,6 @@
 #include <net/neighbour.h>
 #include <asm/processor.h>
 
-#define DST_GC_MIN	(HZ/10)
-#define DST_GC_INC	(HZ/2)
-#define DST_GC_MAX	(120*HZ)
-
-/* Each dst_entry has reference count and sits in some parent list(s).
- * When it is removed from parent list, it is "freed" (dst_free).
- * After this it enters dead state (dst->obsolete > 0) and if its refcnt
- * is zero, it can be destroyed immediately, otherwise it is added
- * to gc list and garbage collector periodically checks the refcnt.
- */
-
 struct sk_buff;
 
 struct dst_entry {
diff --git a/net/core/dst.c b/net/core/dst.c
index a263309df115..1f13d90cd0e4 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -26,23 +26,6 @@
 #include <net/dst.h>
 #include <net/dst_metadata.h>
 
-/*
- * Theory of operations:
- * 1) We use a list, protected by a spinlock, to add
- *    new entries from both BH and non-BH context.
- * 2) In order to keep spinlock held for a small delay,
- *    we use a second list where are stored long lived
- *    entries, that are handled by the garbage collect thread
- *    fired by a workqueue.
- * 3) This list is guarded by a mutex,
- *    so that the gc_task and dst_dev_event() can be synchronized.
- */
-
-/*
- * We want to keep lock & list close together
- * to dirty as few cache lines as possible in __dst_free().
- * As this is not a very strong hint, we dont force an alignment on SMP.
- */
 int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	kfree_skb(skb);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a5da63e5faa2..14c7fdacaa72 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1176,7 +1176,7 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 	 *
 	 * When a PMTU/redirect information update invalidates a route,
 	 * this is indicated by setting obsolete to DST_OBSOLETE_KILL or
-	 * DST_OBSOLETE_DEAD by dst_free().
+	 * DST_OBSOLETE_DEAD.
 	 */
 	if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt))
 		return NULL;
-- 
cgit v1.2.3


From 4feb7c7a4fbb8f63371be31cda79433c7cf3da86 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Thu, 21 Mar 2019 14:42:40 +1100
Subject: rhashtable: don't hold lock on first table throughout insertion.

rhashtable_try_insert() currently holds a lock on the bucket in
the first table, while also locking buckets in subsequent tables.
This is unnecessary and looks like a hold-over from some earlier
version of the implementation.

As insert and remove always lock a bucket in each table in turn, and
as insert only inserts in the final table, there cannot be any races
that are not covered by simply locking a bucket in each table in turn.

When an insert call reaches that last table it can be sure that there
is no matchinf entry in any other table as it has searched them all, and
insertion never happens anywhere but in the last table.  The fact that
code tests for the existence of future_tbl while holding a lock on
the relevant bucket ensures that two threads inserting the same key
will make compatible decisions about which is the "last" table.

This simplifies the code and allows the ->rehash field to be
discarded.

We still need a way to ensure that a dead bucket_table is never
re-linked by rhashtable_walk_stop().  This can be achieved by calling
call_rcu() inside the locked region, and checking with
rcu_head_after_call_rcu() in rhashtable_walk_stop() to see if the
bucket table is empty and dead.

Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Reviewed-by: Paul E. McKenney <paulmck@linux.ibm.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 13 ------------
 lib/rhashtable.c           | 52 ++++++++++++++--------------------------------
 2 files changed, 16 insertions(+), 49 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index ae9c0f71f311..3864193d5e2e 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -63,7 +63,6 @@
 struct bucket_table {
 	unsigned int		size;
 	unsigned int		nest;
-	unsigned int		rehash;
 	u32			hash_rnd;
 	unsigned int		locks_mask;
 	spinlock_t		*locks;
@@ -776,12 +775,6 @@ static inline int rhltable_insert(
  * @obj:	pointer to hash head inside object
  * @params:	hash table parameters
  *
- * Locks down the bucket chain in both the old and new table if a resize
- * is in progress to ensure that writers can't remove from the old table
- * and can't insert to the new table during the atomic operation of search
- * and insertion. Searches for duplicates in both the old and new table if
- * a resize is in progress.
- *
  * This lookup function may only be used for fixed key hash table (key_len
  * parameter set). It will BUG() if used inappropriately.
  *
@@ -837,12 +830,6 @@ static inline void *rhashtable_lookup_get_insert_fast(
  * @obj:	pointer to hash head inside object
  * @params:	hash table parameters
  *
- * Locks down the bucket chain in both the old and new table if a resize
- * is in progress to ensure that writers can't remove from the old table
- * and can't insert to the new table during the atomic operation of search
- * and insertion. Searches for duplicates in both the old and new table if
- * a resize is in progress.
- *
  * Lookups may occur in parallel with hashtable mutations and resizing.
  *
  * Will trigger an automatic deferred table resizing if residency in the
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 0a105d4af166..776b3a82d3a1 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -197,6 +197,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 		return NULL;
 	}
 
+	rcu_head_init(&tbl->rcu);
 	INIT_LIST_HEAD(&tbl->walkers);
 
 	tbl->hash_rnd = get_random_u32();
@@ -280,10 +281,9 @@ static int rhashtable_rehash_chain(struct rhashtable *ht,
 	while (!(err = rhashtable_rehash_one(ht, old_hash)))
 		;
 
-	if (err == -ENOENT) {
-		old_tbl->rehash++;
+	if (err == -ENOENT)
 		err = 0;
-	}
+
 	spin_unlock_bh(old_bucket_lock);
 
 	return err;
@@ -330,13 +330,16 @@ static int rhashtable_rehash_table(struct rhashtable *ht)
 	spin_lock(&ht->lock);
 	list_for_each_entry(walker, &old_tbl->walkers, list)
 		walker->tbl = NULL;
-	spin_unlock(&ht->lock);
 
 	/* Wait for readers. All new readers will see the new
 	 * table, and thus no references to the old table will
 	 * remain.
+	 * We do this inside the locked region so that
+	 * rhashtable_walk_stop() can use rcu_head_after_call_rcu()
+	 * to check if it should not re-link the table.
 	 */
 	call_rcu(&old_tbl->rcu, bucket_table_free_rcu);
+	spin_unlock(&ht->lock);
 
 	return rht_dereference(new_tbl->future_tbl, ht) ? -EAGAIN : 0;
 }
@@ -578,46 +581,22 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 	struct bucket_table *new_tbl;
 	struct bucket_table *tbl;
 	unsigned int hash;
-	spinlock_t *lock;
 	void *data;
 
-	tbl = rcu_dereference(ht->tbl);
-
-	/* All insertions must grab the oldest table containing
-	 * the hashed bucket that is yet to be rehashed.
-	 */
-	for (;;) {
-		hash = rht_head_hashfn(ht, tbl, obj, ht->p);
-		lock = rht_bucket_lock(tbl, hash);
-		spin_lock_bh(lock);
-
-		if (tbl->rehash <= hash)
-			break;
-
-		spin_unlock_bh(lock);
-		tbl = rht_dereference_rcu(tbl->future_tbl, ht);
-	}
-
-	data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
-	new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data);
-	if (PTR_ERR(new_tbl) != -EEXIST)
-		data = ERR_CAST(new_tbl);
+	new_tbl = rcu_dereference(ht->tbl);
 
-	while (!IS_ERR_OR_NULL(new_tbl)) {
+	do {
 		tbl = new_tbl;
 		hash = rht_head_hashfn(ht, tbl, obj, ht->p);
-		spin_lock_nested(rht_bucket_lock(tbl, hash),
-				 SINGLE_DEPTH_NESTING);
+		spin_lock_bh(rht_bucket_lock(tbl, hash));
 
 		data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
 		new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data);
 		if (PTR_ERR(new_tbl) != -EEXIST)
 			data = ERR_CAST(new_tbl);
 
-		spin_unlock(rht_bucket_lock(tbl, hash));
-	}
-
-	spin_unlock_bh(lock);
+		spin_unlock_bh(rht_bucket_lock(tbl, hash));
+	} while (!IS_ERR_OR_NULL(new_tbl));
 
 	if (PTR_ERR(data) == -EAGAIN)
 		data = ERR_PTR(rhashtable_insert_rehash(ht, tbl) ?:
@@ -939,10 +918,11 @@ void rhashtable_walk_stop(struct rhashtable_iter *iter)
 	ht = iter->ht;
 
 	spin_lock(&ht->lock);
-	if (tbl->rehash < tbl->size)
-		list_add(&iter->walker.list, &tbl->walkers);
-	else
+	if (rcu_head_after_call_rcu(&tbl->rcu, bucket_table_free_rcu))
+		/* This bucket table is being freed, don't re-link it. */
 		iter->walker.tbl = NULL;
+	else
+		list_add(&iter->walker.list, &tbl->walkers);
 	spin_unlock(&ht->lock);
 
 out:
-- 
cgit v1.2.3


From f7ad68bf98506f48129267438ada1255fc4edfa2 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Thu, 21 Mar 2019 14:42:40 +1100
Subject: rhashtable: rename rht_for_each*continue as *from.

The pattern set by list.h is that for_each..continue()
iterators start at the next entry after the given one,
while for_each..from() iterators start at the given
entry.

The rht_for_each*continue() iterators are documented as though the
start at the 'next' entry, but actually start at the given entry,
and they are used expecting that behaviour.
So fix the documentation and change the names to *from for consistency
with list.h

Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .clang-format              |  8 ++++----
 include/linux/rhashtable.h | 40 ++++++++++++++++++++--------------------
 lib/rhashtable.c           |  2 +-
 3 files changed, 25 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/.clang-format b/.clang-format
index f49620f506f1..3a4c8220df2f 100644
--- a/.clang-format
+++ b/.clang-format
@@ -366,14 +366,14 @@ ForEachMacros:
   - 'rhl_for_each_entry_rcu'
   - 'rhl_for_each_rcu'
   - 'rht_for_each'
-  - 'rht_for_each_continue'
+  - 'rht_for_each_from'
   - 'rht_for_each_entry'
-  - 'rht_for_each_entry_continue'
+  - 'rht_for_each_entry_from'
   - 'rht_for_each_entry_rcu'
-  - 'rht_for_each_entry_rcu_continue'
+  - 'rht_for_each_entry_rcu_from'
   - 'rht_for_each_entry_safe'
   - 'rht_for_each_rcu'
-  - 'rht_for_each_rcu_continue'
+  - 'rht_for_each_rcu_from'
   - '__rq_for_each_bio'
   - 'rq_for_each_segment'
   - 'scsi_for_each_prot_sg'
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 3864193d5e2e..86dfa417848d 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -306,13 +306,13 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
 }
 
 /**
- * rht_for_each_continue - continue iterating over hash chain
+ * rht_for_each_from - iterate over hash chain from given head
  * @pos:	the &struct rhash_head to use as a loop cursor.
- * @head:	the previous &struct rhash_head to continue from
+ * @head:	the &struct rhash_head to start from
  * @tbl:	the &struct bucket_table
  * @hash:	the hash value / bucket index
  */
-#define rht_for_each_continue(pos, head, tbl, hash) \
+#define rht_for_each_from(pos, head, tbl, hash) \
 	for (pos = rht_dereference_bucket(head, tbl, hash); \
 	     !rht_is_a_nulls(pos); \
 	     pos = rht_dereference_bucket((pos)->next, tbl, hash))
@@ -324,18 +324,18 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * @hash:	the hash value / bucket index
  */
 #define rht_for_each(pos, tbl, hash) \
-	rht_for_each_continue(pos, *rht_bucket(tbl, hash), tbl, hash)
+	rht_for_each_from(pos, *rht_bucket(tbl, hash), tbl, hash)
 
 /**
- * rht_for_each_entry_continue - continue iterating over hash chain
+ * rht_for_each_entry_from - iterate over hash chain from given head
  * @tpos:	the type * to use as a loop cursor.
  * @pos:	the &struct rhash_head to use as a loop cursor.
- * @head:	the previous &struct rhash_head to continue from
+ * @head:	the &struct rhash_head to start from
  * @tbl:	the &struct bucket_table
  * @hash:	the hash value / bucket index
  * @member:	name of the &struct rhash_head within the hashable struct.
  */
-#define rht_for_each_entry_continue(tpos, pos, head, tbl, hash, member)	\
+#define rht_for_each_entry_from(tpos, pos, head, tbl, hash, member)	\
 	for (pos = rht_dereference_bucket(head, tbl, hash);		\
 	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	\
 	     pos = rht_dereference_bucket((pos)->next, tbl, hash))
@@ -349,7 +349,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * @member:	name of the &struct rhash_head within the hashable struct.
  */
 #define rht_for_each_entry(tpos, pos, tbl, hash, member)		\
-	rht_for_each_entry_continue(tpos, pos, *rht_bucket(tbl, hash),	\
+	rht_for_each_entry_from(tpos, pos, *rht_bucket(tbl, hash),	\
 				    tbl, hash, member)
 
 /**
@@ -374,9 +374,9 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
 		       rht_dereference_bucket(pos->next, tbl, hash) : NULL)
 
 /**
- * rht_for_each_rcu_continue - continue iterating over rcu hash chain
+ * rht_for_each_rcu_from - iterate over rcu hash chain from given head
  * @pos:	the &struct rhash_head to use as a loop cursor.
- * @head:	the previous &struct rhash_head to continue from
+ * @head:	the &struct rhash_head to start from
  * @tbl:	the &struct bucket_table
  * @hash:	the hash value / bucket index
  *
@@ -384,7 +384,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * the _rcu mutation primitives such as rhashtable_insert() as long as the
  * traversal is guarded by rcu_read_lock().
  */
-#define rht_for_each_rcu_continue(pos, head, tbl, hash)			\
+#define rht_for_each_rcu_from(pos, head, tbl, hash)			\
 	for (({barrier(); }),						\
 	     pos = rht_dereference_bucket_rcu(head, tbl, hash);		\
 	     !rht_is_a_nulls(pos);					\
@@ -401,13 +401,13 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * traversal is guarded by rcu_read_lock().
  */
 #define rht_for_each_rcu(pos, tbl, hash)				\
-	rht_for_each_rcu_continue(pos, *rht_bucket(tbl, hash), tbl, hash)
+	rht_for_each_rcu_from(pos, *rht_bucket(tbl, hash), tbl, hash)
 
 /**
- * rht_for_each_entry_rcu_continue - continue iterating over rcu hash chain
+ * rht_for_each_entry_rcu_from - iterated over rcu hash chain from given head
  * @tpos:	the type * to use as a loop cursor.
  * @pos:	the &struct rhash_head to use as a loop cursor.
- * @head:	the previous &struct rhash_head to continue from
+ * @head:	the &struct rhash_head to start from
  * @tbl:	the &struct bucket_table
  * @hash:	the hash value / bucket index
  * @member:	name of the &struct rhash_head within the hashable struct.
@@ -416,7 +416,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * the _rcu mutation primitives such as rhashtable_insert() as long as the
  * traversal is guarded by rcu_read_lock().
  */
-#define rht_for_each_entry_rcu_continue(tpos, pos, head, tbl, hash, member) \
+#define rht_for_each_entry_rcu_from(tpos, pos, head, tbl, hash, member) \
 	for (({barrier(); }),						    \
 	     pos = rht_dereference_bucket_rcu(head, tbl, hash);		    \
 	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	    \
@@ -435,7 +435,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * traversal is guarded by rcu_read_lock().
  */
 #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member)		   \
-	rht_for_each_entry_rcu_continue(tpos, pos, *rht_bucket(tbl, hash), \
+	rht_for_each_entry_rcu_from(tpos, pos, *rht_bucket(tbl, hash), \
 					tbl, hash, member)
 
 /**
@@ -491,7 +491,7 @@ restart:
 	hash = rht_key_hashfn(ht, tbl, key, params);
 	head = rht_bucket(tbl, hash);
 	do {
-		rht_for_each_rcu_continue(he, *head, tbl, hash) {
+		rht_for_each_rcu_from(he, *head, tbl, hash) {
 			if (params.obj_cmpfn ?
 			    params.obj_cmpfn(&arg, rht_obj(ht, he)) :
 			    rhashtable_compare(&arg, rht_obj(ht, he)))
@@ -625,7 +625,7 @@ slow_path:
 	if (!pprev)
 		goto out;
 
-	rht_for_each_continue(head, *pprev, tbl, hash) {
+	rht_for_each_from(head, *pprev, tbl, hash) {
 		struct rhlist_head *plist;
 		struct rhlist_head *list;
 
@@ -890,7 +890,7 @@ static inline int __rhashtable_remove_fast_one(
 	spin_lock_bh(lock);
 
 	pprev = rht_bucket_var(tbl, hash);
-	rht_for_each_continue(he, *pprev, tbl, hash) {
+	rht_for_each_from(he, *pprev, tbl, hash) {
 		struct rhlist_head *list;
 
 		list = container_of(he, struct rhlist_head, rhead);
@@ -1042,7 +1042,7 @@ static inline int __rhashtable_replace_fast(
 	spin_lock_bh(lock);
 
 	pprev = rht_bucket_var(tbl, hash);
-	rht_for_each_continue(he, *pprev, tbl, hash) {
+	rht_for_each_from(he, *pprev, tbl, hash) {
 		if (he != obj_old) {
 			pprev = &he->next;
 			continue;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 776b3a82d3a1..f65e43fb1ff8 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -490,7 +490,7 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 
 	elasticity = RHT_ELASTICITY;
 	pprev = rht_bucket_var(tbl, hash);
-	rht_for_each_continue(head, *pprev, tbl, hash) {
+	rht_for_each_from(head, *pprev, tbl, hash) {
 		struct rhlist_head *list;
 		struct rhlist_head *plist;
 
-- 
cgit v1.2.3


From 85a51f8c28b9812642d76db6889f3f39dc3fbab3 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 22 Mar 2019 09:54:00 +0800
Subject: bpf: allow helpers to return PTR_TO_SOCK_COMMON

It's currently not possible to access timewait or request sockets
from eBPF, since there is no way to return a PTR_TO_SOCK_COMMON
from a helper. Introduce RET_PTR_TO_SOCK_COMMON to enable this
behaviour.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   | 1 +
 kernel/bpf/verifier.c | 4 ++++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f02367faa58d..f62897198844 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -205,6 +205,7 @@ enum bpf_return_type {
 	RET_PTR_TO_MAP_VALUE_OR_NULL,	/* returns a pointer to map elem value or NULL */
 	RET_PTR_TO_SOCKET_OR_NULL,	/* returns a pointer to a socket or NULL */
 	RET_PTR_TO_TCP_SOCK_OR_NULL,	/* returns a pointer to a tcp_sock or NULL */
+	RET_PTR_TO_SOCK_COMMON_OR_NULL,	/* returns a pointer to a sock_common or NULL */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 868a82ad5597..a476e13201d6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3148,6 +3148,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
 		regs[BPF_REG_0].id = ++env->id_gen;
+	} else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) {
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL;
+		regs[BPF_REG_0].id = ++env->id_gen;
 	} else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
-- 
cgit v1.2.3


From edbf8c01de5a104a71ed6df2bf6421ceb2836a8e Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 22 Mar 2019 09:54:01 +0800
Subject: bpf: add skc_lookup_tcp helper

Allow looking up a sock_common. This gives eBPF programs
access to timewait and request sockets.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h |  20 ++++++-
 kernel/bpf/verifier.c    |   3 +-
 net/core/filter.c        | 144 +++++++++++++++++++++++++++++++++++++++--------
 3 files changed, 143 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 929c8e537a14..fab05317f5e7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2431,6 +2431,23 @@ union bpf_attr {
  *	Return
  *		A **struct bpf_sock** pointer on success, or **NULL** in
  *		case of failure.
+ *
+ * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ *	Description
+ *		Look for TCP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ *		This function is identical to bpf_sk_lookup_tcp, except that it
+ *		also returns timewait or request sockets. Use bpf_sk_fullsock
+ *		or bpf_tcp_socket to access the full structure.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ *		For sockets with reuseport option, the **struct bpf_sock**
+ *		result is from **reuse->socks**\ [] using the hash of the tuple.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2531,7 +2548,8 @@ union bpf_attr {
 	FN(sk_fullsock),		\
 	FN(tcp_sock),			\
 	FN(skb_ecn_set_ce),		\
-	FN(get_listener_sock),
+	FN(get_listener_sock),		\
+	FN(skc_lookup_tcp),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a476e13201d6..dffeec3706ce 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -369,7 +369,8 @@ static bool is_release_function(enum bpf_func_id func_id)
 static bool is_acquire_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_sk_lookup_tcp ||
-		func_id == BPF_FUNC_sk_lookup_udp;
+		func_id == BPF_FUNC_sk_lookup_udp ||
+		func_id == BPF_FUNC_skc_lookup_tcp;
 }
 
 static bool is_ptr_cast_function(enum bpf_func_id func_id)
diff --git a/net/core/filter.c b/net/core/filter.c
index 647c63a7b25b..b6d83ba97621 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5156,15 +5156,15 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 	return sk;
 }
 
-/* bpf_sk_lookup performs the core lookup for different types of sockets,
+/* bpf_skc_lookup performs the core lookup for different types of sockets,
  * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE.
  * Returns the socket as an 'unsigned long' to simplify the casting in the
  * callers to satisfy BPF_CALL declarations.
  */
-static unsigned long
-__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
-		struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
-		u64 flags)
+static struct sock *
+__bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+		 struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
+		 u64 flags)
 {
 	struct sock *sk = NULL;
 	u8 family = AF_UNSPEC;
@@ -5192,15 +5192,27 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		put_net(net);
 	}
 
+out:
+	return sk;
+}
+
+static struct sock *
+__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+		struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
+		u64 flags)
+{
+	struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net,
+					   ifindex, proto, netns_id, flags);
+
 	if (sk)
 		sk = sk_to_full_sk(sk);
-out:
-	return (unsigned long) sk;
+
+	return sk;
 }
 
-static unsigned long
-bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
-	      u8 proto, u64 netns_id, u64 flags)
+static struct sock *
+bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+	       u8 proto, u64 netns_id, u64 flags)
 {
 	struct net *caller_net;
 	int ifindex;
@@ -5213,14 +5225,47 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		ifindex = 0;
 	}
 
-	return __bpf_sk_lookup(skb, tuple, len, caller_net, ifindex,
-			      proto, netns_id, flags);
+	return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto,
+				netns_id, flags);
 }
 
+static struct sock *
+bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+	      u8 proto, u64 netns_id, u64 flags)
+{
+	struct sock *sk = bpf_skc_lookup(skb, tuple, len, proto, netns_id,
+					 flags);
+
+	if (sk)
+		sk = sk_to_full_sk(sk);
+
+	return sk;
+}
+
+BPF_CALL_5(bpf_skc_lookup_tcp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return (unsigned long)bpf_skc_lookup(skb, tuple, len, IPPROTO_TCP,
+					     netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = {
+	.func		= bpf_skc_lookup_tcp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCK_COMMON_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
-	return bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags);
+	return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP,
+					    netns_id, flags);
 }
 
 static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
@@ -5238,7 +5283,8 @@ static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
 BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
-	return bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags);
+	return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP,
+					    netns_id, flags);
 }
 
 static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
@@ -5273,8 +5319,9 @@ BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
 	struct net *caller_net = dev_net(ctx->rxq->dev);
 	int ifindex = ctx->rxq->dev->ifindex;
 
-	return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
-			      IPPROTO_UDP, netns_id, flags);
+	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
+					      ifindex, IPPROTO_UDP, netns_id,
+					      flags);
 }
 
 static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
@@ -5289,14 +5336,38 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
 	.arg5_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx,
+	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
+{
+	struct net *caller_net = dev_net(ctx->rxq->dev);
+	int ifindex = ctx->rxq->dev->ifindex;
+
+	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net,
+					       ifindex, IPPROTO_TCP, netns_id,
+					       flags);
+}
+
+static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
+	.func           = bpf_xdp_skc_lookup_tcp,
+	.gpl_only       = false,
+	.pkt_access     = true,
+	.ret_type       = RET_PTR_TO_SOCK_COMMON_OR_NULL,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_PTR_TO_MEM,
+	.arg3_type      = ARG_CONST_SIZE,
+	.arg4_type      = ARG_ANYTHING,
+	.arg5_type      = ARG_ANYTHING,
+};
+
 BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(ctx->rxq->dev);
 	int ifindex = ctx->rxq->dev->ifindex;
 
-	return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
-			      IPPROTO_TCP, netns_id, flags);
+	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
+					      ifindex, IPPROTO_TCP, netns_id,
+					      flags);
 }
 
 static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
@@ -5311,11 +5382,31 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
 	.arg5_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len,
+					       sock_net(ctx->sk), 0,
+					       IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = {
+	.func		= bpf_sock_addr_skc_lookup_tcp,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_SOCK_COMMON_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
-	return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,
-			       IPPROTO_TCP, netns_id, flags);
+	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
+					      sock_net(ctx->sk), 0, IPPROTO_TCP,
+					      netns_id, flags);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
@@ -5332,8 +5423,9 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
 BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
-	return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,
-			       IPPROTO_UDP, netns_id, flags);
+	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
+					      sock_net(ctx->sk), 0, IPPROTO_UDP,
+					      netns_id, flags);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
@@ -5586,6 +5678,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sock_addr_sk_lookup_udp_proto;
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
+	case BPF_FUNC_skc_lookup_tcp:
+		return &bpf_sock_addr_skc_lookup_tcp_proto;
 #endif /* CONFIG_INET */
 	default:
 		return bpf_base_func_proto(func_id);
@@ -5719,6 +5813,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_sock_proto;
 	case BPF_FUNC_get_listener_sock:
 		return &bpf_get_listener_sock_proto;
+	case BPF_FUNC_skc_lookup_tcp:
+		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -5754,6 +5850,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_sk_lookup_tcp_proto;
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
+	case BPF_FUNC_skc_lookup_tcp:
+		return &bpf_xdp_skc_lookup_tcp_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -5846,6 +5944,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_lookup_udp_proto;
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
+	case BPF_FUNC_skc_lookup_tcp:
+		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
-- 
cgit v1.2.3


From 399040847084a69f345e0a52fd62f04654e0fce3 Mon Sep 17 00:00:00 2001
From: Lorenz Bauer <lmb@cloudflare.com>
Date: Fri, 22 Mar 2019 09:54:02 +0800
Subject: bpf: add helper to check for a valid SYN cookie

Using bpf_skc_lookup_tcp it's possible to ascertain whether a packet
belongs to a known connection. However, there is one corner case: no
sockets are created if SYN cookies are active. This means that the final
ACK in the 3WHS is misclassified.

Using the helper, we can look up the listening socket via
bpf_skc_lookup_tcp and then check whether a packet is a valid SYN
cookie ACK.

Signed-off-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h | 18 +++++++++++-
 net/core/filter.c        | 72 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 89 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index fab05317f5e7..3c04410137d9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2448,6 +2448,21 @@ union bpf_attr {
  *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
  *		For sockets with reuseport option, the **struct bpf_sock**
  *		result is from **reuse->socks**\ [] using the hash of the tuple.
+ *
+ * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * 	Description
+ * 		Check whether iph and th contain a valid SYN cookie ACK for
+ * 		the listening socket in sk.
+ *
+ * 		iph points to the start of the IPv4 or IPv6 header, while
+ * 		iph_len contains sizeof(struct iphdr) or sizeof(struct ip6hdr).
+ *
+ * 		th points to the start of the TCP header, while th_len contains
+ * 		sizeof(struct tcphdr).
+ *
+ * 	Return
+ * 		0 if iph and th are a valid SYN cookie ACK, or a negative error
+ * 		otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2549,7 +2564,8 @@ union bpf_attr {
 	FN(tcp_sock),			\
 	FN(skb_ecn_set_ce),		\
 	FN(get_listener_sock),		\
-	FN(skc_lookup_tcp),
+	FN(skc_lookup_tcp),		\
+	FN(tcp_check_syncookie),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/net/core/filter.c b/net/core/filter.c
index b6d83ba97621..d2511fe46db3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5553,6 +5553,74 @@ static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = {
 	.ret_type       = RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
+
+BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
+	   struct tcphdr *, th, u32, th_len)
+{
+#ifdef CONFIG_SYN_COOKIES
+	u32 cookie;
+	int ret;
+
+	if (unlikely(th_len < sizeof(*th)))
+		return -EINVAL;
+
+	/* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */
+	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
+		return -EINVAL;
+
+	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
+		return -EINVAL;
+
+	if (!th->ack || th->rst || th->syn)
+		return -ENOENT;
+
+	if (tcp_synq_no_recent_overflow(sk))
+		return -ENOENT;
+
+	cookie = ntohl(th->ack_seq) - 1;
+
+	switch (sk->sk_family) {
+	case AF_INET:
+		if (unlikely(iph_len < sizeof(struct iphdr)))
+			return -EINVAL;
+
+		ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
+		break;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+	case AF_INET6:
+		if (unlikely(iph_len < sizeof(struct ipv6hdr)))
+			return -EINVAL;
+
+		ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
+		break;
+#endif /* CONFIG_IPV6 */
+
+	default:
+		return -EPROTONOSUPPORT;
+	}
+
+	if (ret > 0)
+		return 0;
+
+	return -ENOENT;
+#else
+	return -ENOTSUPP;
+#endif
+}
+
+static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = {
+	.func		= bpf_tcp_check_syncookie,
+	.gpl_only	= true,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -5815,6 +5883,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_listener_sock_proto;
 	case BPF_FUNC_skc_lookup_tcp:
 		return &bpf_skc_lookup_tcp_proto;
+	case BPF_FUNC_tcp_check_syncookie:
+		return &bpf_tcp_check_syncookie_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -5852,6 +5922,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_release_proto;
 	case BPF_FUNC_skc_lookup_tcp:
 		return &bpf_xdp_skc_lookup_tcp_proto;
+	case BPF_FUNC_tcp_check_syncookie:
+		return &bpf_tcp_check_syncookie_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
-- 
cgit v1.2.3


From 3b0f31f2b8c9fb348e4530b88f6b64f9621f83d6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 21 Mar 2019 22:51:02 +0100
Subject: genetlink: make policy common to family

Since maxattr is common, the policy can't really differ sanely,
so make it common as well.

The only user that did in fact manage to make a non-common policy
is taskstats, which has to be really careful about it (since it's
still using a common maxattr!). This is no longer supported, but
we can fake it using pre_doit.

This reduces the size of e.g. nl80211.o (which has lots of commands):

   text	   data	    bss	    dec	    hex	filename
 398745	  14323	   2240	 415308	  6564c	net/wireless/nl80211.o (before)
 397913	  14331	   2240	 414484	  65314	net/wireless/nl80211.o (after)
--------------------------------
   -832      +8       0    -824

Which is obviously just 8 bytes for each command, and an added 8
bytes for the new policy pointer. I'm not sure why the ops list is
counted as .text though.

Most of the code transformations were done using the following spatch:
    @ops@
    identifier OPS;
    expression POLICY;
    @@
    struct genl_ops OPS[] = {
    ...,
     {
    -	.policy = POLICY,
     },
    ...
    };

    @@
    identifier ops.OPS;
    expression ops.POLICY;
    identifier fam;
    expression M;
    @@
    struct genl_family fam = {
            .ops = OPS,
            .maxattr = M,
    +       .policy = POLICY,
            ...
    };

This also gets rid of devlink_nl_cmd_region_read_dumpit() accessing
the cb->data as ops, which we want to change in a later genl patch.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/nbd.c                      |   5 +-
 drivers/net/gtp.c                        |   4 +-
 drivers/net/ieee802154/mac802154_hwsim.c |   7 +--
 drivers/net/macsec.c                     |  11 +---
 drivers/net/team/team.c                  |   5 +-
 drivers/net/wireless/mac80211_hwsim.c    |   7 +--
 drivers/target/target_core_user.c        |   5 +-
 include/linux/genl_magic_func.h          |   4 +-
 include/net/genetlink.h                  |   4 +-
 kernel/taskstats.c                       |  28 ++++++++-
 net/batman-adv/netlink.c                 |  19 +-----
 net/core/devlink.c                       |  43 +------------
 net/hsr/hsr_netlink.c                    |   3 +-
 net/ieee802154/ieee802154.h              |   2 -
 net/ieee802154/netlink.c                 |   1 +
 net/ieee802154/nl802154.c                |  30 +--------
 net/ipv4/fou.c                           |   4 +-
 net/ipv4/tcp_metrics.c                   |   3 +-
 net/ipv6/ila/ila_main.c                  |   5 +-
 net/ipv6/seg6.c                          |   5 +-
 net/l2tp/l2tp_netlink.c                  |  10 +--
 net/ncsi/ncsi-netlink.c                  |   7 +--
 net/netfilter/ipvs/ip_vs_ctl.c           |  13 +---
 net/netlabel/netlabel_calipso.c          |   5 +-
 net/netlabel/netlabel_cipso_v4.c         |   5 +-
 net/netlabel/netlabel_mgmt.c             |   9 +--
 net/netlabel/netlabel_unlabeled.c        |   9 +--
 net/netlink/genetlink.c                  |   6 +-
 net/nfc/netlink.c                        |  20 +-----
 net/openvswitch/conntrack.c              |   4 +-
 net/openvswitch/datapath.c               |  17 ++---
 net/openvswitch/meter.c                  |   5 +-
 net/smc/smc_pnet.c                       |   5 +-
 net/tipc/netlink.c                       |  22 +------
 net/wimax/stack.c                        |   5 +-
 net/wireless/nl80211.c                   | 105 +------------------------------
 36 files changed, 68 insertions(+), 374 deletions(-)

(limited to 'include')

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 90ba9f4c03f3..92b8aafb8bb4 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1999,22 +1999,18 @@ out:
 static const struct genl_ops nbd_connect_genl_ops[] = {
 	{
 		.cmd	= NBD_CMD_CONNECT,
-		.policy	= nbd_attr_policy,
 		.doit	= nbd_genl_connect,
 	},
 	{
 		.cmd	= NBD_CMD_DISCONNECT,
-		.policy	= nbd_attr_policy,
 		.doit	= nbd_genl_disconnect,
 	},
 	{
 		.cmd	= NBD_CMD_RECONFIGURE,
-		.policy	= nbd_attr_policy,
 		.doit	= nbd_genl_reconfigure,
 	},
 	{
 		.cmd	= NBD_CMD_STATUS,
-		.policy	= nbd_attr_policy,
 		.doit	= nbd_genl_status,
 	},
 };
@@ -2031,6 +2027,7 @@ static struct genl_family nbd_genl_family __ro_after_init = {
 	.ops		= nbd_connect_genl_ops,
 	.n_ops		= ARRAY_SIZE(nbd_connect_genl_ops),
 	.maxattr	= NBD_ATTR_MAX,
+	.policy = nbd_attr_policy,
 	.mcgrps		= nbd_mcast_grps,
 	.n_mcgrps	= ARRAY_SIZE(nbd_mcast_grps),
 };
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 7a145172d503..c06e31747288 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1271,20 +1271,17 @@ static const struct genl_ops gtp_genl_ops[] = {
 	{
 		.cmd = GTP_CMD_NEWPDP,
 		.doit = gtp_genl_new_pdp,
-		.policy = gtp_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = GTP_CMD_DELPDP,
 		.doit = gtp_genl_del_pdp,
-		.policy = gtp_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = GTP_CMD_GETPDP,
 		.doit = gtp_genl_get_pdp,
 		.dumpit = gtp_genl_dump_pdp,
-		.policy = gtp_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 };
@@ -1294,6 +1291,7 @@ static struct genl_family gtp_genl_family __ro_after_init = {
 	.version	= 0,
 	.hdrsize	= 0,
 	.maxattr	= GTPA_MAX,
+	.policy = gtp_genl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
 	.ops		= gtp_genl_ops,
diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index b6743f03dce0..49866737f138 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -598,37 +598,31 @@ static const struct nla_policy hwsim_genl_policy[MAC802154_HWSIM_ATTR_MAX + 1] =
 static const struct genl_ops hwsim_nl_ops[] = {
 	{
 		.cmd = MAC802154_HWSIM_CMD_NEW_RADIO,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_new_radio_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = MAC802154_HWSIM_CMD_DEL_RADIO,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_del_radio_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = MAC802154_HWSIM_CMD_GET_RADIO,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_get_radio_nl,
 		.dumpit = hwsim_dump_radio_nl,
 	},
 	{
 		.cmd = MAC802154_HWSIM_CMD_NEW_EDGE,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_new_edge_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = MAC802154_HWSIM_CMD_DEL_EDGE,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_del_edge_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = MAC802154_HWSIM_CMD_SET_EDGE,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_set_edge_lqi,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
@@ -638,6 +632,7 @@ static struct genl_family hwsim_genl_family __ro_after_init = {
 	.name = "MAC802154_HWSIM",
 	.version = 1,
 	.maxattr = MAC802154_HWSIM_ATTR_MAX,
+	.policy = hwsim_genl_policy,
 	.module = THIS_MODULE,
 	.ops = hwsim_nl_ops,
 	.n_ops = ARRAY_SIZE(hwsim_nl_ops),
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 64a982563d59..947c40f112d1 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2637,60 +2637,50 @@ static const struct genl_ops macsec_genl_ops[] = {
 	{
 		.cmd = MACSEC_CMD_GET_TXSC,
 		.dumpit = macsec_dump_txsc,
-		.policy = macsec_genl_policy,
 	},
 	{
 		.cmd = MACSEC_CMD_ADD_RXSC,
 		.doit = macsec_add_rxsc,
-		.policy = macsec_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_DEL_RXSC,
 		.doit = macsec_del_rxsc,
-		.policy = macsec_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_UPD_RXSC,
 		.doit = macsec_upd_rxsc,
-		.policy = macsec_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_ADD_TXSA,
 		.doit = macsec_add_txsa,
-		.policy = macsec_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_DEL_TXSA,
 		.doit = macsec_del_txsa,
-		.policy = macsec_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_UPD_TXSA,
 		.doit = macsec_upd_txsa,
-		.policy = macsec_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_ADD_RXSA,
 		.doit = macsec_add_rxsa,
-		.policy = macsec_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_DEL_RXSA,
 		.doit = macsec_del_rxsa,
-		.policy = macsec_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_UPD_RXSA,
 		.doit = macsec_upd_rxsa,
-		.policy = macsec_genl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 };
@@ -2700,6 +2690,7 @@ static struct genl_family macsec_fam __ro_after_init = {
 	.hdrsize	= 0,
 	.version	= MACSEC_GENL_VERSION,
 	.maxattr	= MACSEC_ATTR_MAX,
+	.policy = macsec_genl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
 	.ops		= macsec_genl_ops,
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ee950aa48e3b..6ad74f898832 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2725,24 +2725,20 @@ static const struct genl_ops team_nl_ops[] = {
 	{
 		.cmd = TEAM_CMD_NOOP,
 		.doit = team_nl_cmd_noop,
-		.policy = team_nl_policy,
 	},
 	{
 		.cmd = TEAM_CMD_OPTIONS_SET,
 		.doit = team_nl_cmd_options_set,
-		.policy = team_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = TEAM_CMD_OPTIONS_GET,
 		.doit = team_nl_cmd_options_get,
-		.policy = team_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = TEAM_CMD_PORT_LIST_GET,
 		.doit = team_nl_cmd_port_list_get,
-		.policy = team_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 };
@@ -2755,6 +2751,7 @@ static struct genl_family team_nl_family __ro_after_init = {
 	.name		= TEAM_GENL_NAME,
 	.version	= TEAM_GENL_VERSION,
 	.maxattr	= TEAM_ATTR_MAX,
+	.policy = team_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
 	.ops		= team_nl_ops,
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 0838af04d681..4cc7b222859c 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3620,35 +3620,29 @@ done:
 static const struct genl_ops hwsim_ops[] = {
 	{
 		.cmd = HWSIM_CMD_REGISTER,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_register_received_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = HWSIM_CMD_FRAME,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_cloned_frame_received_nl,
 	},
 	{
 		.cmd = HWSIM_CMD_TX_INFO_FRAME,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_tx_info_frame_received_nl,
 	},
 	{
 		.cmd = HWSIM_CMD_NEW_RADIO,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_new_radio_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = HWSIM_CMD_DEL_RADIO,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_del_radio_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = HWSIM_CMD_GET_RADIO,
-		.policy = hwsim_genl_policy,
 		.doit = hwsim_get_radio_nl,
 		.dumpit = hwsim_dump_radio_nl,
 	},
@@ -3658,6 +3652,7 @@ static struct genl_family hwsim_genl_family __ro_after_init = {
 	.name = "MAC80211_HWSIM",
 	.version = 1,
 	.maxattr = HWSIM_ATTR_MAX,
+	.policy = hwsim_genl_policy,
 	.netnsok = true,
 	.module = THIS_MODULE,
 	.ops = hwsim_ops,
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 5831e0eecea1..845b32eaff36 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -442,25 +442,21 @@ static const struct genl_ops tcmu_genl_ops[] = {
 	{
 		.cmd	= TCMU_CMD_SET_FEATURES,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= tcmu_attr_policy,
 		.doit	= tcmu_genl_set_features,
 	},
 	{
 		.cmd	= TCMU_CMD_ADDED_DEVICE_DONE,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= tcmu_attr_policy,
 		.doit	= tcmu_genl_add_dev_done,
 	},
 	{
 		.cmd	= TCMU_CMD_REMOVED_DEVICE_DONE,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= tcmu_attr_policy,
 		.doit	= tcmu_genl_rm_dev_done,
 	},
 	{
 		.cmd	= TCMU_CMD_RECONFIG_DEVICE_DONE,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= tcmu_attr_policy,
 		.doit	= tcmu_genl_reconfig_dev_done,
 	},
 };
@@ -472,6 +468,7 @@ static struct genl_family tcmu_genl_family __ro_after_init = {
 	.name = "TCM-USER",
 	.version = 2,
 	.maxattr = TCMU_ATTR_MAX,
+	.policy = tcmu_attr_policy,
 	.mcgrps = tcmu_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(tcmu_mcgrps),
 	.netnsok = true,
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 83f81ac53282..6cb82301d8e9 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -233,7 +233,6 @@ const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd)
 {								\
 	handler							\
 	.cmd = op_name,						\
-	.policy	= CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy),	\
 },
 
 #define ZZZ_genl_ops		CONCAT_(GENL_MAGIC_FAMILY, _genl_ops)
@@ -290,7 +289,8 @@ static struct genl_family ZZZ_genl_family __ro_after_init = {
 #ifdef GENL_MAGIC_FAMILY_HDRSZ
 	.hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ),
 #endif
-	.maxattr = ARRAY_SIZE(drbd_tla_nl_policy)-1,
+	.maxattr = ARRAY_SIZE(CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy))-1,
+	.policy	= CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy),
 	.ops = ZZZ_genl_ops,
 	.n_ops = ARRAY_SIZE(ZZZ_genl_ops),
 	.mcgrps = ZZZ_genl_mcgrps,
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index aa2e5888f18d..6850c7b1a3a6 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -26,6 +26,7 @@ struct genl_info;
  * @name: name of family
  * @version: protocol version
  * @maxattr: maximum number of attributes supported
+ * @policy: netlink policy
  * @netnsok: set to true if the family can handle network
  *	namespaces and should be presented in all of them
  * @parallel_ops: operations can be called in parallel and aren't
@@ -56,6 +57,7 @@ struct genl_family {
 	unsigned int		maxattr;
 	bool			netnsok;
 	bool			parallel_ops;
+	const struct nla_policy *policy;
 	int			(*pre_doit)(const struct genl_ops *ops,
 					    struct sk_buff *skb,
 					    struct genl_info *info);
@@ -124,14 +126,12 @@ static inline int genl_err_attr(struct genl_info *info, int err,
  * @cmd: command identifier
  * @internal_flags: flags used by the family
  * @flags: flags
- * @policy: attribute validation policy
  * @doit: standard command callback
  * @start: start callback for dumps
  * @dumpit: callback for dumpers
  * @done: completion callback for dumps
  */
 struct genl_ops {
-	const struct nla_policy	*policy;
 	int		       (*doit)(struct sk_buff *skb,
 				       struct genl_info *info);
 	int		       (*start)(struct netlink_callback *cb);
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 4e62a4a8fa91..1b942a7caf26 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -650,16 +650,37 @@ static const struct genl_ops taskstats_ops[] = {
 	{
 		.cmd		= TASKSTATS_CMD_GET,
 		.doit		= taskstats_user_cmd,
-		.policy		= taskstats_cmd_get_policy,
-		.flags		= GENL_ADMIN_PERM,
+		/* policy enforced later */
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_HASPOL,
 	},
 	{
 		.cmd		= CGROUPSTATS_CMD_GET,
 		.doit		= cgroupstats_user_cmd,
-		.policy		= cgroupstats_cmd_get_policy,
+		/* policy enforced later */
+		.flags		= GENL_CMD_CAP_HASPOL,
 	},
 };
 
+static int taskstats_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
+			      struct genl_info *info)
+{
+	const struct nla_policy *policy = NULL;
+
+	switch (ops->cmd) {
+	case TASKSTATS_CMD_GET:
+		policy = taskstats_cmd_get_policy;
+		break;
+	case CGROUPSTATS_CMD_GET:
+		policy = cgroupstats_cmd_get_policy;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return nlmsg_validate(info->nlhdr, GENL_HDRLEN, TASKSTATS_CMD_ATTR_MAX,
+			      policy, info->extack);
+}
+
 static struct genl_family family __ro_after_init = {
 	.name		= TASKSTATS_GENL_NAME,
 	.version	= TASKSTATS_GENL_VERSION,
@@ -667,6 +688,7 @@ static struct genl_family family __ro_after_init = {
 	.module		= THIS_MODULE,
 	.ops		= taskstats_ops,
 	.n_ops		= ARRAY_SIZE(taskstats_ops),
+	.pre_doit	= taskstats_pre_doit,
 };
 
 /* Needed early in initialization */
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 67a58da2e6a0..d3033a3d2a63 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -1345,34 +1345,29 @@ static const struct genl_ops batadv_netlink_ops[] = {
 	{
 		.cmd = BATADV_CMD_GET_MESH,
 		/* can be retrieved by unprivileged users */
-		.policy = batadv_netlink_policy,
 		.doit = batadv_netlink_get_mesh,
 		.internal_flags = BATADV_FLAG_NEED_MESH,
 	},
 	{
 		.cmd = BATADV_CMD_TP_METER,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.doit = batadv_netlink_tp_meter_start,
 		.internal_flags = BATADV_FLAG_NEED_MESH,
 	},
 	{
 		.cmd = BATADV_CMD_TP_METER_CANCEL,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.doit = batadv_netlink_tp_meter_cancel,
 		.internal_flags = BATADV_FLAG_NEED_MESH,
 	},
 	{
 		.cmd = BATADV_CMD_GET_ROUTING_ALGOS,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_algo_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_HARDIF,
 		/* can be retrieved by unprivileged users */
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_netlink_dump_hardif,
 		.doit = batadv_netlink_get_hardif,
 		.internal_flags = BATADV_FLAG_NEED_MESH |
@@ -1381,68 +1376,57 @@ static const struct genl_ops batadv_netlink_ops[] = {
 	{
 		.cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_tt_local_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_TRANSTABLE_GLOBAL,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_tt_global_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_ORIGINATORS,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_orig_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_NEIGHBORS,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_hardif_neigh_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_GATEWAYS,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_gw_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_BLA_CLAIM,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_bla_claim_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_BLA_BACKBONE,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_bla_backbone_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_DAT_CACHE,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_dat_cache_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_MCAST_FLAGS,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.dumpit = batadv_mcast_flags_dump,
 	},
 	{
 		.cmd = BATADV_CMD_SET_MESH,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.doit = batadv_netlink_set_mesh,
 		.internal_flags = BATADV_FLAG_NEED_MESH,
 	},
 	{
 		.cmd = BATADV_CMD_SET_HARDIF,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.doit = batadv_netlink_set_hardif,
 		.internal_flags = BATADV_FLAG_NEED_MESH |
 				  BATADV_FLAG_NEED_HARDIF,
@@ -1450,7 +1434,6 @@ static const struct genl_ops batadv_netlink_ops[] = {
 	{
 		.cmd = BATADV_CMD_GET_VLAN,
 		/* can be retrieved by unprivileged users */
-		.policy = batadv_netlink_policy,
 		.doit = batadv_netlink_get_vlan,
 		.internal_flags = BATADV_FLAG_NEED_MESH |
 				  BATADV_FLAG_NEED_VLAN,
@@ -1458,7 +1441,6 @@ static const struct genl_ops batadv_netlink_ops[] = {
 	{
 		.cmd = BATADV_CMD_SET_VLAN,
 		.flags = GENL_ADMIN_PERM,
-		.policy = batadv_netlink_policy,
 		.doit = batadv_netlink_set_vlan,
 		.internal_flags = BATADV_FLAG_NEED_MESH |
 				  BATADV_FLAG_NEED_VLAN,
@@ -1470,6 +1452,7 @@ struct genl_family batadv_netlink_family __ro_after_init = {
 	.name = BATADV_NL_NAME,
 	.version = 1,
 	.maxattr = BATADV_ATTR_MAX,
+	.policy = batadv_netlink_policy,
 	.netnsok = true,
 	.pre_doit = batadv_pre_doit,
 	.post_doit = batadv_post_doit,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 78e22cea4cc7..1a65cbf1ab05 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3640,7 +3640,6 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 					     struct netlink_callback *cb)
 {
 	u64 ret_offset, start_offset, end_offset = 0;
-	const struct genl_ops *ops = cb->data;
 	struct devlink_region *region;
 	struct nlattr *chunks_attr;
 	const char *region_name;
@@ -3657,7 +3656,8 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		return -ENOMEM;
 
 	err = nlmsg_parse(cb->nlh, GENL_HDRLEN + devlink_nl_family.hdrsize,
-			  attrs, DEVLINK_ATTR_MAX, ops->policy, cb->extack);
+			  attrs, DEVLINK_ATTR_MAX, devlink_nl_family.policy,
+			  cb->extack);
 	if (err)
 		goto out_free;
 
@@ -4923,7 +4923,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_GET,
 		.doit = devlink_nl_cmd_get_doit,
 		.dumpit = devlink_nl_cmd_get_dumpit,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
@@ -4931,21 +4930,18 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_PORT_GET,
 		.doit = devlink_nl_cmd_port_get_doit,
 		.dumpit = devlink_nl_cmd_port_get_dumpit,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_PORT_SET,
 		.doit = devlink_nl_cmd_port_set_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
 	{
 		.cmd = DEVLINK_CMD_PORT_SPLIT,
 		.doit = devlink_nl_cmd_port_split_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NO_LOCK,
@@ -4953,7 +4949,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_PORT_UNSPLIT,
 		.doit = devlink_nl_cmd_port_unsplit_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NO_LOCK,
@@ -4962,7 +4957,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_SB_GET,
 		.doit = devlink_nl_cmd_sb_get_doit,
 		.dumpit = devlink_nl_cmd_sb_get_dumpit,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NEED_SB,
 		/* can be retrieved by unprivileged users */
@@ -4971,7 +4965,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_SB_POOL_GET,
 		.doit = devlink_nl_cmd_sb_pool_get_doit,
 		.dumpit = devlink_nl_cmd_sb_pool_get_dumpit,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NEED_SB,
 		/* can be retrieved by unprivileged users */
@@ -4979,7 +4972,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_SB_POOL_SET,
 		.doit = devlink_nl_cmd_sb_pool_set_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NEED_SB,
@@ -4988,7 +4980,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_SB_PORT_POOL_GET,
 		.doit = devlink_nl_cmd_sb_port_pool_get_doit,
 		.dumpit = devlink_nl_cmd_sb_port_pool_get_dumpit,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
 				  DEVLINK_NL_FLAG_NEED_SB,
 		/* can be retrieved by unprivileged users */
@@ -4996,7 +4987,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_SB_PORT_POOL_SET,
 		.doit = devlink_nl_cmd_sb_port_pool_set_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
 				  DEVLINK_NL_FLAG_NEED_SB,
@@ -5005,7 +4995,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET,
 		.doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit,
 		.dumpit = devlink_nl_cmd_sb_tc_pool_bind_get_dumpit,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
 				  DEVLINK_NL_FLAG_NEED_SB,
 		/* can be retrieved by unprivileged users */
@@ -5013,7 +5002,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET,
 		.doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
 				  DEVLINK_NL_FLAG_NEED_SB,
@@ -5021,7 +5009,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT,
 		.doit = devlink_nl_cmd_sb_occ_snapshot_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NEED_SB,
@@ -5029,7 +5016,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR,
 		.doit = devlink_nl_cmd_sb_occ_max_clear_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NEED_SB,
@@ -5037,14 +5023,12 @@ static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_ESWITCH_GET,
 		.doit = devlink_nl_cmd_eswitch_get_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_ESWITCH_SET,
 		.doit = devlink_nl_cmd_eswitch_set_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NO_LOCK,
@@ -5052,49 +5036,42 @@ static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
 		.doit = devlink_nl_cmd_dpipe_table_get,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
 		.doit = devlink_nl_cmd_dpipe_entries_get,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
 		.doit = devlink_nl_cmd_dpipe_headers_get,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
 		.doit = devlink_nl_cmd_dpipe_table_counters_set,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_RESOURCE_SET,
 		.doit = devlink_nl_cmd_resource_set,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_RESOURCE_DUMP,
 		.doit = devlink_nl_cmd_resource_dump,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_RELOAD,
 		.doit = devlink_nl_cmd_reload,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NO_LOCK,
@@ -5103,14 +5080,12 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_PARAM_GET,
 		.doit = devlink_nl_cmd_param_get_doit,
 		.dumpit = devlink_nl_cmd_param_get_dumpit,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_PARAM_SET,
 		.doit = devlink_nl_cmd_param_set_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
@@ -5118,14 +5093,12 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_PORT_PARAM_GET,
 		.doit = devlink_nl_cmd_port_param_get_doit,
 		.dumpit = devlink_nl_cmd_port_param_get_dumpit,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_PORT_PARAM_SET,
 		.doit = devlink_nl_cmd_port_param_set_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
@@ -5133,21 +5106,18 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_REGION_GET,
 		.doit = devlink_nl_cmd_region_get_doit,
 		.dumpit = devlink_nl_cmd_region_get_dumpit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_REGION_DEL,
 		.doit = devlink_nl_cmd_region_del,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_REGION_READ,
 		.dumpit = devlink_nl_cmd_region_read_dumpit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
@@ -5155,7 +5125,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_INFO_GET,
 		.doit = devlink_nl_cmd_info_get_doit,
 		.dumpit = devlink_nl_cmd_info_get_dumpit,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
@@ -5163,35 +5132,30 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_GET,
 		.doit = devlink_nl_cmd_health_reporter_get_doit,
 		.dumpit = devlink_nl_cmd_health_reporter_get_dumpit,
-		.policy = devlink_nl_policy,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_SET,
 		.doit = devlink_nl_cmd_health_reporter_set_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
 		.doit = devlink_nl_cmd_health_reporter_recover_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
 		.doit = devlink_nl_cmd_health_reporter_diagnose_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
 		.doit = devlink_nl_cmd_health_reporter_dump_get_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NO_LOCK,
@@ -5199,7 +5163,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
 		.doit = devlink_nl_cmd_health_reporter_dump_clear_doit,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NO_LOCK,
@@ -5207,7 +5170,6 @@ static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_FLASH_UPDATE,
 		.doit = devlink_nl_cmd_flash_update,
-		.policy = devlink_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
@@ -5217,6 +5179,7 @@ static struct genl_family devlink_nl_family __ro_after_init = {
 	.name		= DEVLINK_GENL_NAME,
 	.version	= DEVLINK_GENL_VERSION,
 	.maxattr	= DEVLINK_ATTR_MAX,
+	.policy = devlink_nl_policy,
 	.netnsok	= true,
 	.pre_doit	= devlink_nl_pre_doit,
 	.post_doit	= devlink_nl_post_doit,
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index b9cce0fd5696..bcc04d3e724f 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -449,14 +449,12 @@ static const struct genl_ops hsr_ops[] = {
 	{
 		.cmd = HSR_C_GET_NODE_STATUS,
 		.flags = 0,
-		.policy = hsr_genl_policy,
 		.doit = hsr_get_node_status,
 		.dumpit = NULL,
 	},
 	{
 		.cmd = HSR_C_GET_NODE_LIST,
 		.flags = 0,
-		.policy = hsr_genl_policy,
 		.doit = hsr_get_node_list,
 		.dumpit = NULL,
 	},
@@ -467,6 +465,7 @@ static struct genl_family hsr_genl_family __ro_after_init = {
 	.name = "HSR",
 	.version = 1,
 	.maxattr = HSR_A_MAX,
+	.policy = hsr_genl_policy,
 	.module = THIS_MODULE,
 	.ops = hsr_ops,
 	.n_ops = ARRAY_SIZE(hsr_ops),
diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h
index a5d7515b7f62..bc147bc8e36a 100644
--- a/net/ieee802154/ieee802154.h
+++ b/net/ieee802154/ieee802154.h
@@ -20,7 +20,6 @@ void ieee802154_nl_exit(void);
 #define IEEE802154_OP(_cmd, _func)			\
 	{						\
 		.cmd	= _cmd,				\
-		.policy	= ieee802154_policy,		\
 		.doit	= _func,			\
 		.dumpit	= NULL,				\
 		.flags	= GENL_ADMIN_PERM,		\
@@ -29,7 +28,6 @@ void ieee802154_nl_exit(void);
 #define IEEE802154_DUMP(_cmd, _func, _dump)		\
 	{						\
 		.cmd	= _cmd,				\
-		.policy	= ieee802154_policy,		\
 		.doit	= _func,			\
 		.dumpit	= _dump,			\
 	}
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 96636e3b7aa9..098d67439b6d 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -136,6 +136,7 @@ struct genl_family nl802154_family __ro_after_init = {
 	.name		= IEEE802154_NL_NAME,
 	.version	= 1,
 	.maxattr	= IEEE802154_ATTR_MAX,
+	.policy		= ieee802154_policy,
 	.module		= THIS_MODULE,
 	.ops		= ieee802154_ops,
 	.n_ops		= ARRAY_SIZE(ieee802154_ops),
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 99f6c254ea77..308370cfd668 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -2220,7 +2220,6 @@ static const struct genl_ops nl802154_ops[] = {
 		.doit = nl802154_get_wpan_phy,
 		.dumpit = nl802154_dump_wpan_phy,
 		.done = nl802154_dump_wpan_phy_done,
-		.policy = nl802154_policy,
 		/* can be retrieved by unprivileged users */
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2229,7 +2228,6 @@ static const struct genl_ops nl802154_ops[] = {
 		.cmd = NL802154_CMD_GET_INTERFACE,
 		.doit = nl802154_get_interface,
 		.dumpit = nl802154_dump_interface,
-		.policy = nl802154_policy,
 		/* can be retrieved by unprivileged users */
 		.internal_flags = NL802154_FLAG_NEED_WPAN_DEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2237,7 +2235,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_NEW_INTERFACE,
 		.doit = nl802154_new_interface,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2245,7 +2242,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_DEL_INTERFACE,
 		.doit = nl802154_del_interface,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_DEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2253,7 +2249,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_CHANNEL,
 		.doit = nl802154_set_channel,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2261,7 +2256,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_CCA_MODE,
 		.doit = nl802154_set_cca_mode,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2269,7 +2263,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_CCA_ED_LEVEL,
 		.doit = nl802154_set_cca_ed_level,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2277,7 +2270,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_TX_POWER,
 		.doit = nl802154_set_tx_power,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2285,7 +2277,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_WPAN_PHY_NETNS,
 		.doit = nl802154_wpan_phy_netns,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2293,7 +2284,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_PAN_ID,
 		.doit = nl802154_set_pan_id,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2301,7 +2291,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_SHORT_ADDR,
 		.doit = nl802154_set_short_addr,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2309,7 +2298,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_BACKOFF_EXPONENT,
 		.doit = nl802154_set_backoff_exponent,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2317,7 +2305,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_MAX_CSMA_BACKOFFS,
 		.doit = nl802154_set_max_csma_backoffs,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2325,7 +2312,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_MAX_FRAME_RETRIES,
 		.doit = nl802154_set_max_frame_retries,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2333,7 +2319,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_LBT_MODE,
 		.doit = nl802154_set_lbt_mode,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2341,7 +2326,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_ACKREQ_DEFAULT,
 		.doit = nl802154_set_ackreq_default,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2350,7 +2334,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_SET_SEC_PARAMS,
 		.doit = nl802154_set_llsec_params,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2359,7 +2342,6 @@ static const struct genl_ops nl802154_ops[] = {
 		.cmd = NL802154_CMD_GET_SEC_KEY,
 		/* TODO .doit by matching key id? */
 		.dumpit = nl802154_dump_llsec_key,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2367,7 +2349,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_NEW_SEC_KEY,
 		.doit = nl802154_add_llsec_key,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2375,7 +2356,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_DEL_SEC_KEY,
 		.doit = nl802154_del_llsec_key,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2385,7 +2365,6 @@ static const struct genl_ops nl802154_ops[] = {
 		.cmd = NL802154_CMD_GET_SEC_DEV,
 		/* TODO .doit by matching extended_addr? */
 		.dumpit = nl802154_dump_llsec_dev,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2393,7 +2372,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_NEW_SEC_DEV,
 		.doit = nl802154_add_llsec_dev,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2401,7 +2379,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_DEL_SEC_DEV,
 		.doit = nl802154_del_llsec_dev,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2411,7 +2388,6 @@ static const struct genl_ops nl802154_ops[] = {
 		.cmd = NL802154_CMD_GET_SEC_DEVKEY,
 		/* TODO doit by matching ??? */
 		.dumpit = nl802154_dump_llsec_devkey,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2419,7 +2395,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_NEW_SEC_DEVKEY,
 		.doit = nl802154_add_llsec_devkey,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2427,7 +2402,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_DEL_SEC_DEVKEY,
 		.doit = nl802154_del_llsec_devkey,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2436,7 +2410,6 @@ static const struct genl_ops nl802154_ops[] = {
 		.cmd = NL802154_CMD_GET_SEC_LEVEL,
 		/* TODO .doit by matching frame_type? */
 		.dumpit = nl802154_dump_llsec_seclevel,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2444,7 +2417,6 @@ static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_NEW_SEC_LEVEL,
 		.doit = nl802154_add_llsec_seclevel,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2453,7 +2425,6 @@ static const struct genl_ops nl802154_ops[] = {
 		.cmd = NL802154_CMD_DEL_SEC_LEVEL,
 		/* TODO match frame_type only? */
 		.doit = nl802154_del_llsec_seclevel,
-		.policy = nl802154_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
 				  NL802154_FLAG_NEED_RTNL,
@@ -2466,6 +2437,7 @@ static struct genl_family nl802154_fam __ro_after_init = {
 	.hdrsize = 0,			/* no private header */
 	.version = 1,			/* no particular meaning now */
 	.maxattr = NL802154_ATTR_MAX,
+	.policy = nl802154_policy,
 	.netnsok = true,
 	.pre_doit = nl802154_pre_doit,
 	.post_doit = nl802154_post_doit,
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 79e98e21cdd7..a23fbb52d265 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -808,20 +808,17 @@ static const struct genl_ops fou_nl_ops[] = {
 	{
 		.cmd = FOU_CMD_ADD,
 		.doit = fou_nl_cmd_add_port,
-		.policy = fou_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = FOU_CMD_DEL,
 		.doit = fou_nl_cmd_rm_port,
-		.policy = fou_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = FOU_CMD_GET,
 		.doit = fou_nl_cmd_get_port,
 		.dumpit = fou_nl_dump,
-		.policy = fou_nl_policy,
 	},
 };
 
@@ -830,6 +827,7 @@ static struct genl_family fou_nl_family __ro_after_init = {
 	.name		= FOU_GENL_NAME,
 	.version	= FOU_GENL_VERSION,
 	.maxattr	= FOU_ATTR_MAX,
+	.policy = fou_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
 	.ops		= fou_nl_ops,
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index b467a7cabf40..4ccec4c705f7 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -953,12 +953,10 @@ static const struct genl_ops tcp_metrics_nl_ops[] = {
 		.cmd = TCP_METRICS_CMD_GET,
 		.doit = tcp_metrics_nl_cmd_get,
 		.dumpit = tcp_metrics_nl_dump,
-		.policy = tcp_metrics_nl_policy,
 	},
 	{
 		.cmd = TCP_METRICS_CMD_DEL,
 		.doit = tcp_metrics_nl_cmd_del,
-		.policy = tcp_metrics_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 };
@@ -968,6 +966,7 @@ static struct genl_family tcp_metrics_nl_family __ro_after_init = {
 	.name		= TCP_METRICS_GENL_NAME,
 	.version	= TCP_METRICS_GENL_VERSION,
 	.maxattr	= TCP_METRICS_ATTR_MAX,
+	.policy = tcp_metrics_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
 	.ops		= tcp_metrics_nl_ops,
diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c
index 18fac76b9520..8d31a5066d0c 100644
--- a/net/ipv6/ila/ila_main.c
+++ b/net/ipv6/ila/ila_main.c
@@ -17,19 +17,16 @@ static const struct genl_ops ila_nl_ops[] = {
 	{
 		.cmd = ILA_CMD_ADD,
 		.doit = ila_xlat_nl_cmd_add_mapping,
-		.policy = ila_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = ILA_CMD_DEL,
 		.doit = ila_xlat_nl_cmd_del_mapping,
-		.policy = ila_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = ILA_CMD_FLUSH,
 		.doit = ila_xlat_nl_cmd_flush,
-		.policy = ila_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
@@ -38,7 +35,6 @@ static const struct genl_ops ila_nl_ops[] = {
 		.start = ila_xlat_nl_dump_start,
 		.dumpit = ila_xlat_nl_dump,
 		.done = ila_xlat_nl_dump_done,
-		.policy = ila_nl_policy,
 	},
 };
 
@@ -49,6 +45,7 @@ struct genl_family ila_nl_family __ro_after_init = {
 	.name		= ILA_GENL_NAME,
 	.version	= ILA_GENL_VERSION,
 	.maxattr	= ILA_ATTR_MAX,
+	.policy = ila_nl_policy,
 	.netnsok	= true,
 	.parallel_ops	= true,
 	.module		= THIS_MODULE,
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 9b2f272ca164..ceff773471e7 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -399,7 +399,6 @@ static const struct genl_ops seg6_genl_ops[] = {
 	{
 		.cmd	= SEG6_CMD_SETHMAC,
 		.doit	= seg6_genl_sethmac,
-		.policy	= seg6_genl_policy,
 		.flags	= GENL_ADMIN_PERM,
 	},
 	{
@@ -407,19 +406,16 @@ static const struct genl_ops seg6_genl_ops[] = {
 		.start	= seg6_genl_dumphmac_start,
 		.dumpit	= seg6_genl_dumphmac,
 		.done	= seg6_genl_dumphmac_done,
-		.policy	= seg6_genl_policy,
 		.flags	= GENL_ADMIN_PERM,
 	},
 	{
 		.cmd	= SEG6_CMD_SET_TUNSRC,
 		.doit	= seg6_genl_set_tunsrc,
-		.policy	= seg6_genl_policy,
 		.flags	= GENL_ADMIN_PERM,
 	},
 	{
 		.cmd	= SEG6_CMD_GET_TUNSRC,
 		.doit	= seg6_genl_get_tunsrc,
-		.policy = seg6_genl_policy,
 		.flags	= GENL_ADMIN_PERM,
 	},
 };
@@ -429,6 +425,7 @@ static struct genl_family seg6_genl_family __ro_after_init = {
 	.name		= SEG6_GENL_NAME,
 	.version	= SEG6_GENL_VERSION,
 	.maxattr	= SEG6_ATTR_MAX,
+	.policy = seg6_genl_policy,
 	.netnsok	= true,
 	.parallel_ops	= true,
 	.ops		= seg6_genl_ops,
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index edbd5d1fbcde..77595fcc9f75 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -916,57 +916,48 @@ static const struct genl_ops l2tp_nl_ops[] = {
 	{
 		.cmd = L2TP_CMD_NOOP,
 		.doit = l2tp_nl_cmd_noop,
-		.policy = l2tp_nl_policy,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_CREATE,
 		.doit = l2tp_nl_cmd_tunnel_create,
-		.policy = l2tp_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_DELETE,
 		.doit = l2tp_nl_cmd_tunnel_delete,
-		.policy = l2tp_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_MODIFY,
 		.doit = l2tp_nl_cmd_tunnel_modify,
-		.policy = l2tp_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_GET,
 		.doit = l2tp_nl_cmd_tunnel_get,
 		.dumpit = l2tp_nl_cmd_tunnel_dump,
-		.policy = l2tp_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_CREATE,
 		.doit = l2tp_nl_cmd_session_create,
-		.policy = l2tp_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_DELETE,
 		.doit = l2tp_nl_cmd_session_delete,
-		.policy = l2tp_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_MODIFY,
 		.doit = l2tp_nl_cmd_session_modify,
-		.policy = l2tp_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_GET,
 		.doit = l2tp_nl_cmd_session_get,
 		.dumpit = l2tp_nl_cmd_session_dump,
-		.policy = l2tp_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 };
@@ -976,6 +967,7 @@ static struct genl_family l2tp_nl_family __ro_after_init = {
 	.version	= L2TP_GENL_VERSION,
 	.hdrsize	= 0,
 	.maxattr	= L2TP_ATTR_MAX,
+	.policy = l2tp_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
 	.ops		= l2tp_nl_ops,
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index bad17bba8ba7..367b2f6513e0 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -723,38 +723,32 @@ static int ncsi_set_channel_mask_nl(struct sk_buff *msg,
 static const struct genl_ops ncsi_ops[] = {
 	{
 		.cmd = NCSI_CMD_PKG_INFO,
-		.policy = ncsi_genl_policy,
 		.doit = ncsi_pkg_info_nl,
 		.dumpit = ncsi_pkg_info_all_nl,
 		.flags = 0,
 	},
 	{
 		.cmd = NCSI_CMD_SET_INTERFACE,
-		.policy = ncsi_genl_policy,
 		.doit = ncsi_set_interface_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NCSI_CMD_CLEAR_INTERFACE,
-		.policy = ncsi_genl_policy,
 		.doit = ncsi_clear_interface_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NCSI_CMD_SEND_CMD,
-		.policy = ncsi_genl_policy,
 		.doit = ncsi_send_cmd_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NCSI_CMD_SET_PACKAGE_MASK,
-		.policy = ncsi_genl_policy,
 		.doit = ncsi_set_package_mask_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NCSI_CMD_SET_CHANNEL_MASK,
-		.policy = ncsi_genl_policy,
 		.doit = ncsi_set_channel_mask_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
@@ -764,6 +758,7 @@ static struct genl_family ncsi_genl_family __ro_after_init = {
 	.name = "NCSI",
 	.version = 0,
 	.maxattr = NCSI_ATTR_MAX,
+	.policy = ncsi_genl_policy,
 	.module = THIS_MODULE,
 	.ops = ncsi_ops,
 	.n_ops = ARRAY_SIZE(ncsi_ops),
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 053cd96b9c76..4b933669fd83 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3775,19 +3775,16 @@ static const struct genl_ops ip_vs_genl_ops[] = {
 	{
 		.cmd	= IPVS_CMD_NEW_SERVICE,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_SET_SERVICE,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_DEL_SERVICE,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
@@ -3795,42 +3792,35 @@ static const struct genl_ops ip_vs_genl_ops[] = {
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_get_cmd,
 		.dumpit	= ip_vs_genl_dump_services,
-		.policy	= ip_vs_cmd_policy,
 	},
 	{
 		.cmd	= IPVS_CMD_NEW_DEST,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_SET_DEST,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_DEL_DEST,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_GET_DEST,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.dumpit	= ip_vs_genl_dump_dests,
 	},
 	{
 		.cmd	= IPVS_CMD_NEW_DAEMON,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.doit	= ip_vs_genl_set_daemon,
 	},
 	{
 		.cmd	= IPVS_CMD_DEL_DAEMON,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.doit	= ip_vs_genl_set_daemon,
 	},
 	{
@@ -3841,7 +3831,6 @@ static const struct genl_ops ip_vs_genl_ops[] = {
 	{
 		.cmd	= IPVS_CMD_SET_CONFIG,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
@@ -3857,7 +3846,6 @@ static const struct genl_ops ip_vs_genl_ops[] = {
 	{
 		.cmd	= IPVS_CMD_ZERO,
 		.flags	= GENL_ADMIN_PERM,
-		.policy	= ip_vs_cmd_policy,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
@@ -3872,6 +3860,7 @@ static struct genl_family ip_vs_genl_family __ro_after_init = {
 	.name		= IPVS_GENL_NAME,
 	.version	= IPVS_GENL_VERSION,
 	.maxattr	= IPVS_CMD_ATTR_MAX,
+	.policy = ip_vs_cmd_policy,
 	.netnsok        = true,         /* Make ipvsadm to work on netns */
 	.module		= THIS_MODULE,
 	.ops		= ip_vs_genl_ops,
diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c
index 4d748975117d..80184513b2b2 100644
--- a/net/netlabel/netlabel_calipso.c
+++ b/net/netlabel/netlabel_calipso.c
@@ -322,28 +322,24 @@ static const struct genl_ops netlbl_calipso_ops[] = {
 	{
 	.cmd = NLBL_CALIPSO_C_ADD,
 	.flags = GENL_ADMIN_PERM,
-	.policy = calipso_genl_policy,
 	.doit = netlbl_calipso_add,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CALIPSO_C_REMOVE,
 	.flags = GENL_ADMIN_PERM,
-	.policy = calipso_genl_policy,
 	.doit = netlbl_calipso_remove,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CALIPSO_C_LIST,
 	.flags = 0,
-	.policy = calipso_genl_policy,
 	.doit = netlbl_calipso_list,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CALIPSO_C_LISTALL,
 	.flags = 0,
-	.policy = calipso_genl_policy,
 	.doit = NULL,
 	.dumpit = netlbl_calipso_listall,
 	},
@@ -354,6 +350,7 @@ static struct genl_family netlbl_calipso_gnl_family __ro_after_init = {
 	.name = NETLBL_NLTYPE_CALIPSO_NAME,
 	.version = NETLBL_PROTO_VERSION,
 	.maxattr = NLBL_CALIPSO_A_MAX,
+	.policy = calipso_genl_policy,
 	.module = THIS_MODULE,
 	.ops = netlbl_calipso_ops,
 	.n_ops = ARRAY_SIZE(netlbl_calipso_ops),
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 9aacf2da3d98..ba7800f94ccc 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -734,28 +734,24 @@ static const struct genl_ops netlbl_cipsov4_ops[] = {
 	{
 	.cmd = NLBL_CIPSOV4_C_ADD,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_cipsov4_genl_policy,
 	.doit = netlbl_cipsov4_add,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CIPSOV4_C_REMOVE,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_cipsov4_genl_policy,
 	.doit = netlbl_cipsov4_remove,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CIPSOV4_C_LIST,
 	.flags = 0,
-	.policy = netlbl_cipsov4_genl_policy,
 	.doit = netlbl_cipsov4_list,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CIPSOV4_C_LISTALL,
 	.flags = 0,
-	.policy = netlbl_cipsov4_genl_policy,
 	.doit = NULL,
 	.dumpit = netlbl_cipsov4_listall,
 	},
@@ -766,6 +762,7 @@ static struct genl_family netlbl_cipsov4_gnl_family __ro_after_init = {
 	.name = NETLBL_NLTYPE_CIPSOV4_NAME,
 	.version = NETLBL_PROTO_VERSION,
 	.maxattr = NLBL_CIPSOV4_A_MAX,
+	.policy = netlbl_cipsov4_genl_policy,
 	.module = THIS_MODULE,
 	.ops = netlbl_cipsov4_ops,
 	.n_ops = ARRAY_SIZE(netlbl_cipsov4_ops),
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index 21e0095b1d14..a16eacfb2236 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -773,56 +773,48 @@ static const struct genl_ops netlbl_mgmt_genl_ops[] = {
 	{
 	.cmd = NLBL_MGMT_C_ADD,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_mgmt_genl_policy,
 	.doit = netlbl_mgmt_add,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_MGMT_C_REMOVE,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_mgmt_genl_policy,
 	.doit = netlbl_mgmt_remove,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_MGMT_C_LISTALL,
 	.flags = 0,
-	.policy = netlbl_mgmt_genl_policy,
 	.doit = NULL,
 	.dumpit = netlbl_mgmt_listall,
 	},
 	{
 	.cmd = NLBL_MGMT_C_ADDDEF,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_mgmt_genl_policy,
 	.doit = netlbl_mgmt_adddef,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_MGMT_C_REMOVEDEF,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_mgmt_genl_policy,
 	.doit = netlbl_mgmt_removedef,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_MGMT_C_LISTDEF,
 	.flags = 0,
-	.policy = netlbl_mgmt_genl_policy,
 	.doit = netlbl_mgmt_listdef,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_MGMT_C_PROTOCOLS,
 	.flags = 0,
-	.policy = netlbl_mgmt_genl_policy,
 	.doit = NULL,
 	.dumpit = netlbl_mgmt_protocols,
 	},
 	{
 	.cmd = NLBL_MGMT_C_VERSION,
 	.flags = 0,
-	.policy = netlbl_mgmt_genl_policy,
 	.doit = netlbl_mgmt_version,
 	.dumpit = NULL,
 	},
@@ -833,6 +825,7 @@ static struct genl_family netlbl_mgmt_gnl_family __ro_after_init = {
 	.name = NETLBL_NLTYPE_MGMT_NAME,
 	.version = NETLBL_PROTO_VERSION,
 	.maxattr = NLBL_MGMT_A_MAX,
+	.policy = netlbl_mgmt_genl_policy,
 	.module = THIS_MODULE,
 	.ops = netlbl_mgmt_genl_ops,
 	.n_ops = ARRAY_SIZE(netlbl_mgmt_genl_ops),
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index c92894c3e40a..6b1b6c2b5141 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -1318,56 +1318,48 @@ static const struct genl_ops netlbl_unlabel_genl_ops[] = {
 	{
 	.cmd = NLBL_UNLABEL_C_STATICADD,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_unlabel_genl_policy,
 	.doit = netlbl_unlabel_staticadd,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_STATICREMOVE,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_unlabel_genl_policy,
 	.doit = netlbl_unlabel_staticremove,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_STATICLIST,
 	.flags = 0,
-	.policy = netlbl_unlabel_genl_policy,
 	.doit = NULL,
 	.dumpit = netlbl_unlabel_staticlist,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_STATICADDDEF,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_unlabel_genl_policy,
 	.doit = netlbl_unlabel_staticadddef,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_STATICREMOVEDEF,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_unlabel_genl_policy,
 	.doit = netlbl_unlabel_staticremovedef,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_STATICLISTDEF,
 	.flags = 0,
-	.policy = netlbl_unlabel_genl_policy,
 	.doit = NULL,
 	.dumpit = netlbl_unlabel_staticlistdef,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_ACCEPT,
 	.flags = GENL_ADMIN_PERM,
-	.policy = netlbl_unlabel_genl_policy,
 	.doit = netlbl_unlabel_accept,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_LIST,
 	.flags = 0,
-	.policy = netlbl_unlabel_genl_policy,
 	.doit = netlbl_unlabel_list,
 	.dumpit = NULL,
 	},
@@ -1378,6 +1370,7 @@ static struct genl_family netlbl_unlabel_gnl_family __ro_after_init = {
 	.name = NETLBL_NLTYPE_UNLABELED_NAME,
 	.version = NETLBL_PROTO_VERSION,
 	.maxattr = NLBL_UNLABEL_A_MAX,
+	.policy = netlbl_unlabel_genl_policy,
 	.module = THIS_MODULE,
 	.ops = netlbl_unlabel_genl_ops,
 	.n_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops),
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 25eeb6d2a75a..a75ea33fb5ea 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -577,7 +577,7 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 
 	if (attrbuf) {
 		err = nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr,
-				  ops->policy, extack);
+				  family->policy, extack);
 		if (err < 0)
 			goto out;
 	}
@@ -677,7 +677,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 				op_flags |= GENL_CMD_CAP_DUMP;
 			if (ops->doit)
 				op_flags |= GENL_CMD_CAP_DO;
-			if (ops->policy)
+			if (family->policy)
 				op_flags |= GENL_CMD_CAP_HASPOL;
 
 			nest = nla_nest_start(skb, i + 1);
@@ -939,7 +939,6 @@ static const struct genl_ops genl_ctrl_ops[] = {
 		.cmd		= CTRL_CMD_GETFAMILY,
 		.doit		= ctrl_getfamily,
 		.dumpit		= ctrl_dumpfamily,
-		.policy		= ctrl_policy,
 	},
 };
 
@@ -957,6 +956,7 @@ static struct genl_family genl_ctrl __ro_after_init = {
 	.name = "nlctrl",
 	.version = 0x2,
 	.maxattr = CTRL_ATTR_MAX,
+	.policy = ctrl_policy,
 	.netnsok = true,
 };
 
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 376181cc1def..4d9f3ac8d562 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1670,99 +1670,80 @@ static const struct genl_ops nfc_genl_ops[] = {
 		.doit = nfc_genl_get_device,
 		.dumpit = nfc_genl_dump_devices,
 		.done = nfc_genl_dump_devices_done,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_DEV_UP,
 		.doit = nfc_genl_dev_up,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_DEV_DOWN,
 		.doit = nfc_genl_dev_down,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_START_POLL,
 		.doit = nfc_genl_start_poll,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_STOP_POLL,
 		.doit = nfc_genl_stop_poll,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_DEP_LINK_UP,
 		.doit = nfc_genl_dep_link_up,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_DEP_LINK_DOWN,
 		.doit = nfc_genl_dep_link_down,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_GET_TARGET,
 		.dumpit = nfc_genl_dump_targets,
 		.done = nfc_genl_dump_targets_done,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_LLC_GET_PARAMS,
 		.doit = nfc_genl_llc_get_params,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_LLC_SET_PARAMS,
 		.doit = nfc_genl_llc_set_params,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_LLC_SDREQ,
 		.doit = nfc_genl_llc_sdreq,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_FW_DOWNLOAD,
 		.doit = nfc_genl_fw_download,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_ENABLE_SE,
 		.doit = nfc_genl_enable_se,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_DISABLE_SE,
 		.doit = nfc_genl_disable_se,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_GET_SE,
 		.dumpit = nfc_genl_dump_ses,
 		.done = nfc_genl_dump_ses_done,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_SE_IO,
 		.doit = nfc_genl_se_io,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_ACTIVATE_TARGET,
 		.doit = nfc_genl_activate_target,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_VENDOR,
 		.doit = nfc_genl_vendor_cmd,
-		.policy = nfc_genl_policy,
 	},
 	{
 		.cmd = NFC_CMD_DEACTIVATE_TARGET,
 		.doit = nfc_genl_deactivate_target,
-		.policy = nfc_genl_policy,
 	},
 };
 
@@ -1771,6 +1752,7 @@ static struct genl_family nfc_genl_family __ro_after_init = {
 	.name = NFC_GENL_NAME,
 	.version = NFC_GENL_VERSION,
 	.maxattr = NFC_ATTR_MAX,
+	.policy = nfc_genl_policy,
 	.module = THIS_MODULE,
 	.ops = nfc_genl_ops,
 	.n_ops = ARRAY_SIZE(nfc_genl_ops),
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 1b6896896fff..51080004677e 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -2154,18 +2154,15 @@ static struct genl_ops ct_limit_genl_ops[] = {
 	{ .cmd = OVS_CT_LIMIT_CMD_SET,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
 					   * privilege. */
-		.policy = ct_limit_policy,
 		.doit = ovs_ct_limit_cmd_set,
 	},
 	{ .cmd = OVS_CT_LIMIT_CMD_DEL,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
 					   * privilege. */
-		.policy = ct_limit_policy,
 		.doit = ovs_ct_limit_cmd_del,
 	},
 	{ .cmd = OVS_CT_LIMIT_CMD_GET,
 		.flags = 0,		  /* OK for unprivileged users. */
-		.policy = ct_limit_policy,
 		.doit = ovs_ct_limit_cmd_get,
 	},
 };
@@ -2179,6 +2176,7 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = {
 	.name = OVS_CT_LIMIT_FAMILY,
 	.version = OVS_CT_LIMIT_VERSION,
 	.maxattr = OVS_CT_LIMIT_ATTR_MAX,
+	.policy = ct_limit_policy,
 	.netnsok = true,
 	.parallel_ops = true,
 	.ops = ct_limit_genl_ops,
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 9dd158ab51b3..a64d3eb1f9a9 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -639,7 +639,6 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
 static const struct genl_ops dp_packet_genl_ops[] = {
 	{ .cmd = OVS_PACKET_CMD_EXECUTE,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
-	  .policy = packet_policy,
 	  .doit = ovs_packet_cmd_execute
 	}
 };
@@ -649,6 +648,7 @@ static struct genl_family dp_packet_genl_family __ro_after_init = {
 	.name = OVS_PACKET_FAMILY,
 	.version = OVS_PACKET_VERSION,
 	.maxattr = OVS_PACKET_ATTR_MAX,
+	.policy = packet_policy,
 	.netnsok = true,
 	.parallel_ops = true,
 	.ops = dp_packet_genl_ops,
@@ -1424,23 +1424,19 @@ static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
 static const struct genl_ops dp_flow_genl_ops[] = {
 	{ .cmd = OVS_FLOW_CMD_NEW,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
-	  .policy = flow_policy,
 	  .doit = ovs_flow_cmd_new
 	},
 	{ .cmd = OVS_FLOW_CMD_DEL,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
-	  .policy = flow_policy,
 	  .doit = ovs_flow_cmd_del
 	},
 	{ .cmd = OVS_FLOW_CMD_GET,
 	  .flags = 0,		    /* OK for unprivileged users. */
-	  .policy = flow_policy,
 	  .doit = ovs_flow_cmd_get,
 	  .dumpit = ovs_flow_cmd_dump
 	},
 	{ .cmd = OVS_FLOW_CMD_SET,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
-	  .policy = flow_policy,
 	  .doit = ovs_flow_cmd_set,
 	},
 };
@@ -1450,6 +1446,7 @@ static struct genl_family dp_flow_genl_family __ro_after_init = {
 	.name = OVS_FLOW_FAMILY,
 	.version = OVS_FLOW_VERSION,
 	.maxattr = OVS_FLOW_ATTR_MAX,
+	.policy = flow_policy,
 	.netnsok = true,
 	.parallel_ops = true,
 	.ops = dp_flow_genl_ops,
@@ -1817,23 +1814,19 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
 static const struct genl_ops dp_datapath_genl_ops[] = {
 	{ .cmd = OVS_DP_CMD_NEW,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
-	  .policy = datapath_policy,
 	  .doit = ovs_dp_cmd_new
 	},
 	{ .cmd = OVS_DP_CMD_DEL,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
-	  .policy = datapath_policy,
 	  .doit = ovs_dp_cmd_del
 	},
 	{ .cmd = OVS_DP_CMD_GET,
 	  .flags = 0,		    /* OK for unprivileged users. */
-	  .policy = datapath_policy,
 	  .doit = ovs_dp_cmd_get,
 	  .dumpit = ovs_dp_cmd_dump
 	},
 	{ .cmd = OVS_DP_CMD_SET,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
-	  .policy = datapath_policy,
 	  .doit = ovs_dp_cmd_set,
 	},
 };
@@ -1843,6 +1836,7 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = {
 	.name = OVS_DATAPATH_FAMILY,
 	.version = OVS_DATAPATH_VERSION,
 	.maxattr = OVS_DP_ATTR_MAX,
+	.policy = datapath_policy,
 	.netnsok = true,
 	.parallel_ops = true,
 	.ops = dp_datapath_genl_ops,
@@ -2260,23 +2254,19 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 static const struct genl_ops dp_vport_genl_ops[] = {
 	{ .cmd = OVS_VPORT_CMD_NEW,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
-	  .policy = vport_policy,
 	  .doit = ovs_vport_cmd_new
 	},
 	{ .cmd = OVS_VPORT_CMD_DEL,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
-	  .policy = vport_policy,
 	  .doit = ovs_vport_cmd_del
 	},
 	{ .cmd = OVS_VPORT_CMD_GET,
 	  .flags = 0,		    /* OK for unprivileged users. */
-	  .policy = vport_policy,
 	  .doit = ovs_vport_cmd_get,
 	  .dumpit = ovs_vport_cmd_dump
 	},
 	{ .cmd = OVS_VPORT_CMD_SET,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
-	  .policy = vport_policy,
 	  .doit = ovs_vport_cmd_set,
 	},
 };
@@ -2286,6 +2276,7 @@ struct genl_family dp_vport_genl_family __ro_after_init = {
 	.name = OVS_VPORT_FAMILY,
 	.version = OVS_VPORT_VERSION,
 	.maxattr = OVS_VPORT_ATTR_MAX,
+	.policy = vport_policy,
 	.netnsok = true,
 	.parallel_ops = true,
 	.ops = dp_vport_genl_ops,
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 43849d752a1e..0be3d097ae01 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -527,26 +527,22 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
 static struct genl_ops dp_meter_genl_ops[] = {
 	{ .cmd = OVS_METER_CMD_FEATURES,
 		.flags = 0,		  /* OK for unprivileged users. */
-		.policy = meter_policy,
 		.doit = ovs_meter_cmd_features
 	},
 	{ .cmd = OVS_METER_CMD_SET,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
 					   *  privilege.
 					   */
-		.policy = meter_policy,
 		.doit = ovs_meter_cmd_set,
 	},
 	{ .cmd = OVS_METER_CMD_GET,
 		.flags = 0,		  /* OK for unprivileged users. */
-		.policy = meter_policy,
 		.doit = ovs_meter_cmd_get,
 	},
 	{ .cmd = OVS_METER_CMD_DEL,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
 					   *  privilege.
 					   */
-		.policy = meter_policy,
 		.doit = ovs_meter_cmd_del
 	},
 };
@@ -560,6 +556,7 @@ struct genl_family dp_meter_genl_family __ro_after_init = {
 	.name = OVS_METER_FAMILY,
 	.version = OVS_METER_VERSION,
 	.maxattr = OVS_METER_ATTR_MAX,
+	.policy = meter_policy,
 	.netnsok = true,
 	.parallel_ops = true,
 	.ops = dp_meter_genl_ops,
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 8d2f6296279c..3cdf81cf97a3 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -611,7 +611,6 @@ static const struct genl_ops smc_pnet_ops[] = {
 	{
 		.cmd = SMC_PNETID_GET,
 		.flags = GENL_ADMIN_PERM,
-		.policy = smc_pnet_policy,
 		.doit = smc_pnet_get,
 		.dumpit = smc_pnet_dump,
 		.start = smc_pnet_dump_start
@@ -619,19 +618,16 @@ static const struct genl_ops smc_pnet_ops[] = {
 	{
 		.cmd = SMC_PNETID_ADD,
 		.flags = GENL_ADMIN_PERM,
-		.policy = smc_pnet_policy,
 		.doit = smc_pnet_add
 	},
 	{
 		.cmd = SMC_PNETID_DEL,
 		.flags = GENL_ADMIN_PERM,
-		.policy = smc_pnet_policy,
 		.doit = smc_pnet_del
 	},
 	{
 		.cmd = SMC_PNETID_FLUSH,
 		.flags = GENL_ADMIN_PERM,
-		.policy = smc_pnet_policy,
 		.doit = smc_pnet_flush
 	}
 };
@@ -642,6 +638,7 @@ static struct genl_family smc_pnet_nl_family __ro_after_init = {
 	.name = SMCR_GENL_FAMILY_NAME,
 	.version = SMCR_GENL_FAMILY_VERSION,
 	.maxattr = SMC_PNETID_MAX,
+	.policy = smc_pnet_policy,
 	.netnsok = true,
 	.module = THIS_MODULE,
 	.ops = smc_pnet_ops,
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 5240f64e8ccc..2d178df0a89f 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -144,114 +144,93 @@ static const struct genl_ops tipc_genl_v2_ops[] = {
 	{
 		.cmd	= TIPC_NL_BEARER_DISABLE,
 		.doit	= tipc_nl_bearer_disable,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_BEARER_ENABLE,
 		.doit	= tipc_nl_bearer_enable,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_BEARER_GET,
 		.doit	= tipc_nl_bearer_get,
 		.dumpit	= tipc_nl_bearer_dump,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_BEARER_ADD,
 		.doit	= tipc_nl_bearer_add,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_BEARER_SET,
 		.doit	= tipc_nl_bearer_set,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_SOCK_GET,
 		.start = tipc_dump_start,
 		.dumpit	= tipc_nl_sk_dump,
 		.done	= tipc_dump_done,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_PUBL_GET,
 		.dumpit	= tipc_nl_publ_dump,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_LINK_GET,
 		.doit   = tipc_nl_node_get_link,
 		.dumpit	= tipc_nl_node_dump_link,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_LINK_SET,
 		.doit	= tipc_nl_node_set_link,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_LINK_RESET_STATS,
 		.doit   = tipc_nl_node_reset_link_stats,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_MEDIA_GET,
 		.doit	= tipc_nl_media_get,
 		.dumpit	= tipc_nl_media_dump,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_MEDIA_SET,
 		.doit	= tipc_nl_media_set,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_NODE_GET,
 		.dumpit	= tipc_nl_node_dump,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_NET_GET,
 		.dumpit	= tipc_nl_net_dump,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_NET_SET,
 		.doit	= tipc_nl_net_set,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_NAME_TABLE_GET,
 		.dumpit	= tipc_nl_name_table_dump,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_MON_SET,
 		.doit	= tipc_nl_node_set_monitor,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_MON_GET,
 		.doit	= tipc_nl_node_get_monitor,
 		.dumpit	= tipc_nl_node_dump_monitor,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_MON_PEER_GET,
 		.dumpit	= tipc_nl_node_dump_monitor_peer,
-		.policy = tipc_nl_policy,
 	},
 	{
 		.cmd	= TIPC_NL_PEER_REMOVE,
 		.doit	= tipc_nl_peer_rm,
-		.policy = tipc_nl_policy,
 	},
 #ifdef CONFIG_TIPC_MEDIA_UDP
 	{
 		.cmd	= TIPC_NL_UDP_GET_REMOTEIP,
 		.dumpit	= tipc_udp_nl_dump_remoteip,
-		.policy = tipc_nl_policy,
 	},
 #endif
 };
@@ -261,6 +240,7 @@ struct genl_family tipc_genl_family __ro_after_init = {
 	.version	= TIPC_GENL_V2_VERSION,
 	.hdrsize	= 0,
 	.maxattr	= TIPC_NLA_MAX,
+	.policy = tipc_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
 	.ops		= tipc_genl_v2_ops,
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
index a6307813b6d5..b7f571e55448 100644
--- a/net/wimax/stack.c
+++ b/net/wimax/stack.c
@@ -420,25 +420,21 @@ static const struct genl_ops wimax_gnl_ops[] = {
 	{
 		.cmd = WIMAX_GNL_OP_MSG_FROM_USER,
 		.flags = GENL_ADMIN_PERM,
-		.policy = wimax_gnl_policy,
 		.doit = wimax_gnl_doit_msg_from_user,
 	},
 	{
 		.cmd = WIMAX_GNL_OP_RESET,
 		.flags = GENL_ADMIN_PERM,
-		.policy = wimax_gnl_policy,
 		.doit = wimax_gnl_doit_reset,
 	},
 	{
 		.cmd = WIMAX_GNL_OP_RFKILL,
 		.flags = GENL_ADMIN_PERM,
-		.policy = wimax_gnl_policy,
 		.doit = wimax_gnl_doit_rfkill,
 	},
 	{
 		.cmd = WIMAX_GNL_OP_STATE_GET,
 		.flags = GENL_ADMIN_PERM,
-		.policy = wimax_gnl_policy,
 		.doit = wimax_gnl_doit_state_get,
 	},
 };
@@ -582,6 +578,7 @@ struct genl_family wimax_gnl_family __ro_after_init = {
 	.version = WIMAX_GNL_VERSION,
 	.hdrsize = 0,
 	.maxattr = WIMAX_GNL_ATTR_MAX,
+	.policy = wimax_gnl_policy,
 	.module = THIS_MODULE,
 	.ops = wimax_gnl_ops,
 	.n_ops = ARRAY_SIZE(wimax_gnl_ops),
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 25a9e3b5c154..33408ba1d7ee 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -13368,7 +13368,6 @@ static const struct genl_ops nl80211_ops[] = {
 		.doit = nl80211_get_wiphy,
 		.dumpit = nl80211_dump_wiphy,
 		.done = nl80211_dump_wiphy_done,
-		.policy = nl80211_policy,
 		/* can be retrieved by unprivileged users */
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13376,7 +13375,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_WIPHY,
 		.doit = nl80211_set_wiphy,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_RTNL,
 	},
@@ -13384,7 +13382,6 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_GET_INTERFACE,
 		.doit = nl80211_get_interface,
 		.dumpit = nl80211_dump_interface,
-		.policy = nl80211_policy,
 		/* can be retrieved by unprivileged users */
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13392,7 +13389,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_INTERFACE,
 		.doit = nl80211_set_interface,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13400,7 +13396,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_NEW_INTERFACE,
 		.doit = nl80211_new_interface,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13408,7 +13403,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_DEL_INTERFACE,
 		.doit = nl80211_del_interface,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13416,7 +13410,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_GET_KEY,
 		.doit = nl80211_get_key,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13424,7 +13417,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_KEY,
 		.doit = nl80211_set_key,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
@@ -13433,7 +13425,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_NEW_KEY,
 		.doit = nl80211_new_key,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
@@ -13442,14 +13433,12 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_DEL_KEY,
 		.doit = nl80211_del_key,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_SET_BEACON,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_set_beacon,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13457,7 +13446,6 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_START_AP,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_start_ap,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13465,7 +13453,6 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_STOP_AP,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_stop_ap,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13475,14 +13462,12 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_GET_STATION,
 		.doit = nl80211_get_station,
 		.dumpit = nl80211_dump_station,
-		.policy = nl80211_policy,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_SET_STATION,
 		.doit = nl80211_set_station,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13490,7 +13475,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_NEW_STATION,
 		.doit = nl80211_new_station,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13498,7 +13482,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_DEL_STATION,
 		.doit = nl80211_del_station,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13507,7 +13490,6 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_GET_MPATH,
 		.doit = nl80211_get_mpath,
 		.dumpit = nl80211_dump_mpath,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13516,7 +13498,6 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_GET_MPP,
 		.doit = nl80211_get_mpp,
 		.dumpit = nl80211_dump_mpp,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13524,7 +13505,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_MPATH,
 		.doit = nl80211_set_mpath,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13532,7 +13512,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_NEW_MPATH,
 		.doit = nl80211_new_mpath,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13540,7 +13519,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_DEL_MPATH,
 		.doit = nl80211_del_mpath,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13548,7 +13526,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_BSS,
 		.doit = nl80211_set_bss,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13557,7 +13534,6 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_GET_REG,
 		.doit = nl80211_get_reg_do,
 		.dumpit = nl80211_get_reg_dump,
-		.policy = nl80211_policy,
 		.internal_flags = NL80211_FLAG_NEED_RTNL,
 		/* can be retrieved by unprivileged users */
 	},
@@ -13565,7 +13541,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_REG,
 		.doit = nl80211_set_reg,
-		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_RTNL,
 	},
@@ -13573,19 +13548,16 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_REQ_SET_REG,
 		.doit = nl80211_req_set_reg,
-		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NL80211_CMD_RELOAD_REGDB,
 		.doit = nl80211_reload_regdb,
-		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NL80211_CMD_GET_MESH_CONFIG,
 		.doit = nl80211_get_mesh_config,
-		.policy = nl80211_policy,
 		/* can be retrieved by unprivileged users */
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13593,7 +13565,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_MESH_CONFIG,
 		.doit = nl80211_update_mesh_config,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13601,7 +13572,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_TRIGGER_SCAN,
 		.doit = nl80211_trigger_scan,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13609,20 +13579,17 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_ABORT_SCAN,
 		.doit = nl80211_abort_scan,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_GET_SCAN,
-		.policy = nl80211_policy,
 		.dumpit = nl80211_dump_scan,
 	},
 	{
 		.cmd = NL80211_CMD_START_SCHED_SCAN,
 		.doit = nl80211_start_sched_scan,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13630,7 +13597,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_STOP_SCHED_SCAN,
 		.doit = nl80211_stop_sched_scan,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13638,7 +13604,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_AUTHENTICATE,
 		.doit = nl80211_authenticate,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
@@ -13647,7 +13612,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_ASSOCIATE,
 		.doit = nl80211_associate,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13655,7 +13619,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_DEAUTHENTICATE,
 		.doit = nl80211_deauthenticate,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13663,7 +13626,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_DISASSOCIATE,
 		.doit = nl80211_disassociate,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13671,7 +13633,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_JOIN_IBSS,
 		.doit = nl80211_join_ibss,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13679,7 +13640,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_LEAVE_IBSS,
 		.doit = nl80211_leave_ibss,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13689,7 +13649,6 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_TESTMODE,
 		.doit = nl80211_testmode_do,
 		.dumpit = nl80211_testmode_dump,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13698,7 +13657,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_CONNECT,
 		.doit = nl80211_connect,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13706,7 +13664,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS,
 		.doit = nl80211_update_connect_params,
-		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13714,7 +13671,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_DISCONNECT,
 		.doit = nl80211_disconnect,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13722,20 +13678,17 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_WIPHY_NETNS,
 		.doit = nl80211_wiphy_netns,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_GET_SURVEY,
-		.policy = nl80211_policy,
 		.dumpit = nl80211_dump_survey,
 	},
 	{
 		.cmd = NL80211_CMD_SET_PMKSA,
 		.doit = nl80211_setdel_pmksa,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13743,7 +13696,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_DEL_PMKSA,
 		.doit = nl80211_setdel_pmksa,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13751,7 +13703,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_FLUSH_PMKSA,
 		.doit = nl80211_flush_pmksa,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13759,7 +13710,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_REMAIN_ON_CHANNEL,
 		.doit = nl80211_remain_on_channel,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13767,7 +13717,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL,
 		.doit = nl80211_cancel_remain_on_channel,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13775,7 +13724,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_TX_BITRATE_MASK,
 		.doit = nl80211_set_tx_bitrate_mask,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13783,7 +13731,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_REGISTER_FRAME,
 		.doit = nl80211_register_mgmt,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13791,7 +13738,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_FRAME,
 		.doit = nl80211_tx_mgmt,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13799,7 +13745,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_FRAME_WAIT_CANCEL,
 		.doit = nl80211_tx_mgmt_cancel_wait,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13807,7 +13752,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_POWER_SAVE,
 		.doit = nl80211_set_power_save,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13815,7 +13759,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_GET_POWER_SAVE,
 		.doit = nl80211_get_power_save,
-		.policy = nl80211_policy,
 		/* can be retrieved by unprivileged users */
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13823,7 +13766,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_CQM,
 		.doit = nl80211_set_cqm,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13831,7 +13773,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_CHANNEL,
 		.doit = nl80211_set_channel,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13839,7 +13780,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_WDS_PEER,
 		.doit = nl80211_set_wds_peer,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13847,7 +13787,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_JOIN_MESH,
 		.doit = nl80211_join_mesh,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13855,7 +13794,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_LEAVE_MESH,
 		.doit = nl80211_leave_mesh,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13863,7 +13801,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_JOIN_OCB,
 		.doit = nl80211_join_ocb,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13871,7 +13808,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_LEAVE_OCB,
 		.doit = nl80211_leave_ocb,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13880,7 +13816,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_GET_WOWLAN,
 		.doit = nl80211_get_wowlan,
-		.policy = nl80211_policy,
 		/* can be retrieved by unprivileged users */
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13888,7 +13823,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_WOWLAN,
 		.doit = nl80211_set_wowlan,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13897,7 +13831,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_REKEY_OFFLOAD,
 		.doit = nl80211_set_rekey_data,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
@@ -13906,7 +13839,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_TDLS_MGMT,
 		.doit = nl80211_tdls_mgmt,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13914,7 +13846,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_TDLS_OPER,
 		.doit = nl80211_tdls_oper,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13922,7 +13853,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_UNEXPECTED_FRAME,
 		.doit = nl80211_register_unexpected_frame,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13930,7 +13860,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_PROBE_CLIENT,
 		.doit = nl80211_probe_client,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13938,7 +13867,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_REGISTER_BEACONS,
 		.doit = nl80211_register_beacons,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13946,7 +13874,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_NOACK_MAP,
 		.doit = nl80211_set_noack_map,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13954,7 +13881,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_START_P2P_DEVICE,
 		.doit = nl80211_start_p2p_device,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13962,7 +13888,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_STOP_P2P_DEVICE,
 		.doit = nl80211_stop_p2p_device,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13970,7 +13895,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_START_NAN,
 		.doit = nl80211_start_nan,
-		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13978,7 +13902,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_STOP_NAN,
 		.doit = nl80211_stop_nan,
-		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13986,7 +13909,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_ADD_NAN_FUNCTION,
 		.doit = nl80211_nan_add_func,
-		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -13994,7 +13916,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_DEL_NAN_FUNCTION,
 		.doit = nl80211_nan_del_func,
-		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14002,7 +13923,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_CHANGE_NAN_CONFIG,
 		.doit = nl80211_nan_change_config,
-		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14010,7 +13930,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_MCAST_RATE,
 		.doit = nl80211_set_mcast_rate,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14018,7 +13937,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_MAC_ACL,
 		.doit = nl80211_set_mac_acl,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14026,7 +13944,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_RADAR_DETECT,
 		.doit = nl80211_start_radar_detection,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14034,12 +13951,10 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_GET_PROTOCOL_FEATURES,
 		.doit = nl80211_get_protocol_features,
-		.policy = nl80211_policy,
 	},
 	{
 		.cmd = NL80211_CMD_UPDATE_FT_IES,
 		.doit = nl80211_update_ft_ies,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14047,7 +13962,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_CRIT_PROTOCOL_START,
 		.doit = nl80211_crit_protocol_start,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14055,7 +13969,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_CRIT_PROTOCOL_STOP,
 		.doit = nl80211_crit_protocol_stop,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14063,14 +13976,12 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_GET_COALESCE,
 		.doit = nl80211_get_coalesce,
-		.policy = nl80211_policy,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_SET_COALESCE,
 		.doit = nl80211_set_coalesce,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14078,7 +13989,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_CHANNEL_SWITCH,
 		.doit = nl80211_channel_switch,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14087,7 +13997,6 @@ static const struct genl_ops nl80211_ops[] = {
 		.cmd = NL80211_CMD_VENDOR,
 		.doit = nl80211_vendor_cmd,
 		.dumpit = nl80211_vendor_cmd_dump,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14095,7 +14004,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_QOS_MAP,
 		.doit = nl80211_set_qos_map,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14103,7 +14011,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_ADD_TX_TS,
 		.doit = nl80211_add_tx_ts,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14111,7 +14018,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_DEL_TX_TS,
 		.doit = nl80211_del_tx_ts,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14119,7 +14025,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_TDLS_CHANNEL_SWITCH,
 		.doit = nl80211_tdls_channel_switch,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14127,7 +14032,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH,
 		.doit = nl80211_tdls_cancel_channel_switch,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14135,7 +14039,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_MULTICAST_TO_UNICAST,
 		.doit = nl80211_set_multicast_to_unicast,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14143,21 +14046,18 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_PMK,
 		.doit = nl80211_set_pmk,
-		.policy = nl80211_policy,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_DEL_PMK,
 		.doit = nl80211_del_pmk,
-		.policy = nl80211_policy,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_EXTERNAL_AUTH,
 		.doit = nl80211_external_auth,
-		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14165,7 +14065,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_CONTROL_PORT_FRAME,
 		.doit = nl80211_tx_control_port,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14173,14 +14072,12 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_GET_FTM_RESPONDER_STATS,
 		.doit = nl80211_get_ftm_responder_stats,
-		.policy = nl80211_policy,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_PEER_MEASUREMENT_START,
 		.doit = nl80211_pmsr_start,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14188,7 +14085,6 @@ static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_NOTIFY_RADAR,
 		.doit = nl80211_notify_radar_detection,
-		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
@@ -14200,6 +14096,7 @@ static struct genl_family nl80211_fam __ro_after_init = {
 	.hdrsize = 0,			/* no private header */
 	.version = 1,			/* no particular meaning now */
 	.maxattr = NL80211_ATTR_MAX,
+	.policy = nl80211_policy,
 	.netnsok = true,
 	.pre_doit = nl80211_pre_doit,
 	.post_doit = nl80211_post_doit,
-- 
cgit v1.2.3


From 974eff2b5793eeaa2eb433bca7eba9640d890c4a Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Thu, 21 Mar 2019 15:51:36 -0700
Subject: net: Move the definition of the default Geneve udp port to public
 header file

Move the definition of the default Geneve udp port from the geneve
source to the header file, so we can re-use it from drivers.
Modify existing drivers to use it.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Cc: John Hurley <john.hurley@netronome.com>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c  | 2 +-
 drivers/net/ethernet/netronome/nfp/flower/main.h    | 1 -
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 2 +-
 drivers/net/geneve.c                                | 2 --
 include/net/geneve.h                                | 2 ++
 5 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index eeda4ed98333..269ddcffa218 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -163,7 +163,7 @@ nfp_fl_get_tun_from_act_l4_port(struct nfp_app *app,
 	switch (tun->key.tp_dst) {
 	case htons(NFP_FL_VXLAN_PORT):
 		return NFP_FL_TUNNEL_VXLAN;
-	case htons(NFP_FL_GENEVE_PORT):
+	case htons(GENEVE_UDP_PORT):
 		if (priv->flower_ext_feats & NFP_FL_FEATS_GENEVE)
 			return NFP_FL_TUNNEL_GENEVE;
 		/* FALLTHROUGH */
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index c0945a5fd1a4..6c27e9b403bc 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -35,7 +35,6 @@ struct nfp_app;
 #define NFP_FL_MASK_ID_LOCATION		1
 
 #define NFP_FL_VXLAN_PORT		4789
-#define NFP_FL_GENEVE_PORT		6081
 
 /* Extra features bitmap. */
 #define NFP_FL_FEATS_GENEVE		BIT(0)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 450d7296fd57..bdd551f36cb7 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -203,7 +203,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			if (enc_op.key)
 				return -EOPNOTSUPP;
 			break;
-		case htons(NFP_FL_GENEVE_PORT):
+		case htons(GENEVE_UDP_PORT):
 			if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE))
 				return -EOPNOTSUPP;
 			*tun_type = NFP_FL_TUNNEL_GENEVE;
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 5583d993480d..c05b1207358d 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -22,8 +22,6 @@
 
 #define GENEVE_NETDEV_VER	"0.6"
 
-#define GENEVE_UDP_PORT		6081
-
 #define GENEVE_N_VID		(1u << 24)
 #define GENEVE_VID_MASK		(GENEVE_N_VID - 1)
 
diff --git a/include/net/geneve.h b/include/net/geneve.h
index fc6a7e0a874a..bced0b1d9fe4 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -4,6 +4,8 @@
 
 #include <net/udp_tunnel.h>
 
+#define GENEVE_UDP_PORT		6081
+
 /* Geneve Header:
  *  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  *  |Ver|  Opt Len  |O|C|    Rsvd.  |          Protocol Type        |
-- 
cgit v1.2.3


From bea964107fa78ffe484ef8659ecc26f9ae2bcd2f Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Thu, 21 Mar 2019 15:51:39 -0700
Subject: net: Add IANA_VXLAN_UDP_PORT definition to vxlan header file

Added IANA_VXLAN_UDP_PORT (4789) definition to vxlan header file so it
can be used by drivers instead of local definition.
Updated drivers which locally defined it as 4789 to use it.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Cc: John Hurley <john.hurley@netronome.com>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Yunsheng Lin <linyunsheng@huawei.com>
Cc: Peng Li <lipeng321@huawei.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c     | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c | 5 +++--
 drivers/net/ethernet/netronome/nfp/flower/action.c  | 2 +-
 drivers/net/ethernet/netronome/nfp/flower/main.h    | 2 --
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 2 +-
 include/net/vxlan.h                                 | 2 ++
 6 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 1c1f17ec6be2..1f4d181f169f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -826,12 +826,12 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
  */
 static bool hns3_tunnel_csum_bug(struct sk_buff *skb)
 {
-#define IANA_VXLAN_PORT	4789
 	union l4_hdr_info l4;
 
 	l4.hdr = skb_transport_header(skb);
 
-	if (!(!skb->encapsulation && l4.udp->dest == htons(IANA_VXLAN_PORT)))
+	if (!(!skb->encapsulation &&
+	      l4.udp->dest == htons(IANA_VXLAN_UDP_PORT)))
 		return false;
 
 	skb_checksum_help(skb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
index 9a8fd762167b..b9d4f4e19ff9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
@@ -33,6 +33,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
+#include <net/vxlan.h>
 #include "mlx5_core.h"
 #include "vxlan.h"
 
@@ -204,8 +205,8 @@ struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
 	spin_lock_init(&vxlan->lock);
 	hash_init(vxlan->htable);
 
-	/* Hardware adds 4789 by default */
-	mlx5_vxlan_add_port(vxlan, 4789);
+	/* Hardware adds 4789 (IANA_VXLAN_UDP_PORT) by default */
+	mlx5_vxlan_add_port(vxlan, IANA_VXLAN_UDP_PORT);
 
 	return vxlan;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 269ddcffa218..ce54b6c2a9ad 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -161,7 +161,7 @@ nfp_fl_get_tun_from_act_l4_port(struct nfp_app *app,
 	struct nfp_flower_priv *priv = app->priv;
 
 	switch (tun->key.tp_dst) {
-	case htons(NFP_FL_VXLAN_PORT):
+	case htons(IANA_VXLAN_UDP_PORT):
 		return NFP_FL_TUNNEL_VXLAN;
 	case htons(GENEVE_UDP_PORT):
 		if (priv->flower_ext_feats & NFP_FL_FEATS_GENEVE)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 6c27e9b403bc..f6ca8dc9cc92 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -34,8 +34,6 @@ struct nfp_app;
 #define NFP_FL_MASK_REUSE_TIME_NS	40000
 #define NFP_FL_MASK_ID_LOCATION		1
 
-#define NFP_FL_VXLAN_PORT		4789
-
 /* Extra features bitmap. */
 #define NFP_FL_FEATS_GENEVE		BIT(0)
 #define NFP_FL_NBI_MTU_SETTING		BIT(1)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index bdd551f36cb7..9f16920da81d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -195,7 +195,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			flow_rule_match_enc_opts(rule, &enc_op);
 
 		switch (enc_ports.key->dst) {
-		case htons(NFP_FL_VXLAN_PORT):
+		case htons(IANA_VXLAN_UDP_PORT):
 			*tun_type = NFP_FL_TUNNEL_VXLAN;
 			key_layer |= NFP_FLOWER_LAYER_VXLAN;
 			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 00254a58824b..83b5999a2587 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -8,6 +8,8 @@
 #include <net/rtnetlink.h>
 #include <net/switchdev.h>
 
+#define IANA_VXLAN_UDP_PORT     4789
+
 /* VXLAN protocol (RFC 7348) header:
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  * |R|R|R|R|I|R|R|R|               Reserved                        |
-- 
cgit v1.2.3


From 0eb69bb9962973f4852bb35b8151332c98741770 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Thu, 21 Mar 2019 15:51:40 -0700
Subject: net/mlx5e: Add VLAN ID rewrite fields

Add VLAN ID rewrite fields as a pre-step to support this rewrite.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 2 ++
 include/linux/mlx5/mlx5_ifc.h                   | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b4967a0ff8c7..1b446307f448 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1827,6 +1827,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 
 struct pedit_headers {
 	struct ethhdr  eth;
+	struct vlan_hdr vlan;
 	struct iphdr   ip4;
 	struct ipv6hdr ip6;
 	struct tcphdr  tcp;
@@ -1884,6 +1885,7 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0),
 	OFFLOAD(SMAC_15_0,  2, eth.h_source[4], 0),
 	OFFLOAD(ETHERTYPE,  2, eth.h_proto, 0),
+	OFFLOAD(FIRST_VID,  2, vlan.h_vlan_TCI, 0),
 
 	OFFLOAD(IP_TTL, 1, ip4.ttl,   0),
 	OFFLOAD(SIPV4,  4, ip4.saddr, 0),
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 3b83288749c6..b0e17c94566c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -5110,6 +5110,7 @@ enum {
 	MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0    = 0x14,
 	MLX5_ACTION_IN_FIELD_OUT_SIPV4         = 0x15,
 	MLX5_ACTION_IN_FIELD_OUT_DIPV4         = 0x16,
+	MLX5_ACTION_IN_FIELD_OUT_FIRST_VID     = 0x17,
 	MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47,
 };
 
-- 
cgit v1.2.3


From 14aa31929b724b70fb63a9b0e7877da325b25cfe Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 22 Mar 2019 14:32:54 -0400
Subject: bpf: add bpf_skb_adjust_room mode BPF_ADJ_ROOM_MAC

bpf_skb_adjust_room net allows inserting room in an skb.

Existing mode BPF_ADJ_ROOM_NET inserts room after the network header
by pulling the skb, moving the network header forward and zeroing the
new space.

Add new mode BPF_ADJUST_ROOM_MAC that inserts room after the mac
header. This allows inserting tunnel headers in front of the network
header without having to recreate the network header in the original
space, avoiding two copies.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h |  6 +++++-
 net/core/filter.c        | 38 ++++++++++++++++++++------------------
 2 files changed, 25 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3c04410137d9..7c8fd0647070 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1478,7 +1478,10 @@ union bpf_attr {
  * 		Grow or shrink the room for data in the packet associated to
  * 		*skb* by *len_diff*, and according to the selected *mode*.
  *
- * 		There is a single supported mode at this time:
+ *		There are two supported modes at this time:
+ *
+ *		* **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer
+ *		  (room space is added or removed below the layer 2 header).
  *
  * 		* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
  * 		  (room space is added or removed below the layer 3 header).
@@ -2627,6 +2630,7 @@ enum bpf_func_id {
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
+	BPF_ADJ_ROOM_MAC,
 };
 
 /* Mode for BPF_FUNC_skb_load_bytes_relative helper. */
diff --git a/net/core/filter.c b/net/core/filter.c
index d21e1acdde29..e7b7720b18e9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2963,9 +2963,8 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 	}
 }
 
-static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff)
+static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff)
 {
-	u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb);
 	int ret;
 
 	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb))
@@ -2992,9 +2991,8 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff)
 	return 0;
 }
 
-static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff)
+static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff)
 {
-	u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb);
 	int ret;
 
 	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb))
@@ -3027,7 +3025,8 @@ static u32 __bpf_skb_max_len(const struct sk_buff *skb)
 			  SKB_MAX_ALLOC;
 }
 
-static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
+BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
+	   u32, mode, u64, flags)
 {
 	bool trans_same = skb->transport_header == skb->network_header;
 	u32 len_cur, len_diff_abs = abs(len_diff);
@@ -3035,14 +3034,28 @@ static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
 	u32 len_max = __bpf_skb_max_len(skb);
 	__be16 proto = skb->protocol;
 	bool shrink = len_diff < 0;
+	u32 off;
 	int ret;
 
+	if (unlikely(flags))
+		return -EINVAL;
 	if (unlikely(len_diff_abs > 0xfffU))
 		return -EFAULT;
 	if (unlikely(proto != htons(ETH_P_IP) &&
 		     proto != htons(ETH_P_IPV6)))
 		return -ENOTSUPP;
 
+	off = skb_mac_header_len(skb);
+	switch (mode) {
+	case BPF_ADJ_ROOM_NET:
+		off += bpf_skb_net_base_len(skb);
+		break;
+	case BPF_ADJ_ROOM_MAC:
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
 	len_cur = skb->len - skb_network_offset(skb);
 	if (skb_transport_header_was_set(skb) && !trans_same)
 		len_cur = skb_network_header_len(skb);
@@ -3052,24 +3065,13 @@ static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
 			 !skb_is_gso(skb))))
 		return -ENOTSUPP;
 
-	ret = shrink ? bpf_skb_net_shrink(skb, len_diff_abs) :
-		       bpf_skb_net_grow(skb, len_diff_abs);
+	ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs) :
+		       bpf_skb_net_grow(skb, off, len_diff_abs);
 
 	bpf_compute_data_pointers(skb);
 	return ret;
 }
 
-BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
-	   u32, mode, u64, flags)
-{
-	if (unlikely(flags))
-		return -EINVAL;
-	if (likely(mode == BPF_ADJ_ROOM_NET))
-		return bpf_skb_adjust_net(skb, len_diff);
-
-	return -ENOTSUPP;
-}
-
 static const struct bpf_func_proto bpf_skb_adjust_room_proto = {
 	.func		= bpf_skb_adjust_room,
 	.gpl_only	= false,
-- 
cgit v1.2.3


From 2278f6cc151a8bef6ba0b3fe3009d14dc3c51c4a Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 22 Mar 2019 14:32:55 -0400
Subject: bpf: add bpf_skb_adjust_room flag BPF_F_ADJ_ROOM_FIXED_GSO

bpf_skb_adjust_room adjusts gso_size of gso packets to account for the
pushed or popped header room.

This is not allowed with UDP, where gso_size delineates datagrams. Add
an option to avoid these updates and allow this call for datagrams.

It can also be used with TCP, when MSS is known to allow headroom,
e.g., through MSS clamping or route MTU.

Changes v1->v2:
  - document flag BPF_F_ADJ_ROOM_FIXED_GSO
  - do not expose BPF_F_ADJ_ROOM_MASK through uapi, as it may change.

Link: https://patchwork.ozlabs.org/patch/1052497/
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h |  9 +++++++--
 net/core/filter.c        | 38 +++++++++++++++++++++++++++-----------
 2 files changed, 34 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7c8fd0647070..4f157d0ec571 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1486,8 +1486,10 @@ union bpf_attr {
  * 		* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
  * 		  (room space is added or removed below the layer 3 header).
  *
- * 		All values for *flags* are reserved for future usage, and must
- * 		be left at zero.
+ *		There is one supported flag at this time:
+ *
+ *		* **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size.
+ *		  Adjusting mss in this way is not allowed for datagrams.
  *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
@@ -2627,6 +2629,9 @@ enum bpf_func_id {
 /* Current network namespace */
 #define BPF_F_CURRENT_NETNS		(-1L)
 
+/* BPF_FUNC_skb_adjust_room flags. */
+#define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
diff --git a/net/core/filter.c b/net/core/filter.c
index e7b7720b18e9..d3240a0a0eeb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2963,12 +2963,19 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 	}
 }
 
-static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff)
+#define BPF_F_ADJ_ROOM_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO)
+
+static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
+			    u64 flags)
 {
 	int ret;
 
-	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb))
-		return -ENOTSUPP;
+	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) {
+		/* udp gso_size delineates datagrams, only allow if fixed */
+		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ||
+		    !(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+			return -ENOTSUPP;
+	}
 
 	ret = skb_cow_head(skb, len_diff);
 	if (unlikely(ret < 0))
@@ -2982,7 +2989,9 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff)
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
 		/* Due to header grow, MSS needs to be downgraded. */
-		skb_decrease_gso_size(shinfo, len_diff);
+		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+			skb_decrease_gso_size(shinfo, len_diff);
+
 		/* Header must be checked, and gso_segs recomputed. */
 		shinfo->gso_type |= SKB_GSO_DODGY;
 		shinfo->gso_segs = 0;
@@ -2991,12 +3000,17 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff)
 	return 0;
 }
 
-static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff)
+static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
+			      u64 flags)
 {
 	int ret;
 
-	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb))
-		return -ENOTSUPP;
+	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) {
+		/* udp gso_size delineates datagrams, only allow if fixed */
+		if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ||
+		    !(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+			return -ENOTSUPP;
+	}
 
 	ret = skb_unclone(skb, GFP_ATOMIC);
 	if (unlikely(ret < 0))
@@ -3010,7 +3024,9 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff)
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
 		/* Due to header shrink, MSS can be upgraded. */
-		skb_increase_gso_size(shinfo, len_diff);
+		if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+			skb_increase_gso_size(shinfo, len_diff);
+
 		/* Header must be checked, and gso_segs recomputed. */
 		shinfo->gso_type |= SKB_GSO_DODGY;
 		shinfo->gso_segs = 0;
@@ -3037,7 +3053,7 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	u32 off;
 	int ret;
 
-	if (unlikely(flags))
+	if (unlikely(flags & ~BPF_F_ADJ_ROOM_MASK))
 		return -EINVAL;
 	if (unlikely(len_diff_abs > 0xfffU))
 		return -EFAULT;
@@ -3065,8 +3081,8 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 			 !skb_is_gso(skb))))
 		return -ENOTSUPP;
 
-	ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs) :
-		       bpf_skb_net_grow(skb, off, len_diff_abs);
+	ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) :
+		       bpf_skb_net_grow(skb, off, len_diff_abs, flags);
 
 	bpf_compute_data_pointers(skb);
 	return ret;
-- 
cgit v1.2.3


From 868d523535c2d00b696753ece606e641a816e91e Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 22 Mar 2019 14:32:56 -0400
Subject: bpf: add bpf_skb_adjust_room encap flags

When pushing tunnel headers, annotate skbs in the same way as tunnel
devices.

For GSO packets, the network stack requires certain fields set to
segment packets with tunnel headers. gro_gse_segment depends on
transport and inner mac header, for instance.

Add an option to pass this information.

Remove the restriction on len_diff to network header length, which
is too short, e.g., for GRE protocols.

Changes
  v1->v2:
  - document new flags
  - BPF_F_ADJ_ROOM_MASK moved
  v2->v3:
  - BPF_F_ADJ_ROOM_ENCAP_L3_MASK moved

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h | 16 +++++++++++-
 net/core/filter.c        | 66 ++++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 76 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4f157d0ec571..837024512baf 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1486,11 +1486,20 @@ union bpf_attr {
  * 		* **BPF_ADJ_ROOM_NET**: Adjust room at the network layer
  * 		  (room space is added or removed below the layer 3 header).
  *
- *		There is one supported flag at this time:
+ *		The following flags are supported at this time:
  *
  *		* **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size.
  *		  Adjusting mss in this way is not allowed for datagrams.
  *
+ *		* **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 **:
+ *		* **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 **:
+ *		  Any new space is reserved to hold a tunnel header.
+ *		  Configure skb offsets and other fields accordingly.
+ *
+ *		* **BPF_F_ADJ_ROOM_ENCAP_L4_GRE **:
+ *		* **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **:
+ *		  Use with ENCAP_L3 flags to further specify the tunnel type.
+ *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
  * 		previously done by the verifier are invalidated and must be
@@ -2632,6 +2641,11 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_adjust_room flags. */
 #define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
 
+#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
+#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
+#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
+#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
diff --git a/net/core/filter.c b/net/core/filter.c
index d3240a0a0eeb..c1d19b074d6c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2963,11 +2963,20 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 	}
 }
 
-#define BPF_F_ADJ_ROOM_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO)
+#define BPF_F_ADJ_ROOM_ENCAP_L3_MASK	(BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \
+					 BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+
+#define BPF_F_ADJ_ROOM_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO | \
+					 BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
+					 BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
+					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
 
 static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			    u64 flags)
 {
+	bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK;
+	unsigned int gso_type = SKB_GSO_DODGY;
+	u16 mac_len, inner_net, inner_trans;
 	int ret;
 
 	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) {
@@ -2981,10 +2990,60 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 	if (unlikely(ret < 0))
 		return ret;
 
+	if (encap) {
+		if (skb->protocol != htons(ETH_P_IP) &&
+		    skb->protocol != htons(ETH_P_IPV6))
+			return -ENOTSUPP;
+
+		if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 &&
+		    flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+			return -EINVAL;
+
+		if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE &&
+		    flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
+			return -EINVAL;
+
+		if (skb->encapsulation)
+			return -EALREADY;
+
+		mac_len = skb->network_header - skb->mac_header;
+		inner_net = skb->network_header;
+		inner_trans = skb->transport_header;
+	}
+
 	ret = bpf_skb_net_hdr_push(skb, off, len_diff);
 	if (unlikely(ret < 0))
 		return ret;
 
+	if (encap) {
+		/* inner mac == inner_net on l3 encap */
+		skb->inner_mac_header = inner_net;
+		skb->inner_network_header = inner_net;
+		skb->inner_transport_header = inner_trans;
+		skb_set_inner_protocol(skb, skb->protocol);
+
+		skb->encapsulation = 1;
+		skb_set_network_header(skb, mac_len);
+
+		if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
+			gso_type |= SKB_GSO_UDP_TUNNEL;
+		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE)
+			gso_type |= SKB_GSO_GRE;
+		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+			gso_type |= SKB_GSO_IPXIP6;
+		else
+			gso_type |= SKB_GSO_IPXIP4;
+
+		if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE ||
+		    flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) {
+			int nh_len = flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 ?
+					sizeof(struct ipv6hdr) :
+					sizeof(struct iphdr);
+
+			skb_set_transport_header(skb, mac_len + nh_len);
+		}
+	}
+
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
@@ -2993,7 +3052,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			skb_decrease_gso_size(shinfo, len_diff);
 
 		/* Header must be checked, and gso_segs recomputed. */
-		shinfo->gso_type |= SKB_GSO_DODGY;
+		shinfo->gso_type |= gso_type;
 		shinfo->gso_segs = 0;
 	}
 
@@ -3044,7 +3103,6 @@ static u32 __bpf_skb_max_len(const struct sk_buff *skb)
 BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	   u32, mode, u64, flags)
 {
-	bool trans_same = skb->transport_header == skb->network_header;
 	u32 len_cur, len_diff_abs = abs(len_diff);
 	u32 len_min = bpf_skb_net_base_len(skb);
 	u32 len_max = __bpf_skb_max_len(skb);
@@ -3073,8 +3131,6 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	}
 
 	len_cur = skb->len - skb_network_offset(skb);
-	if (skb_transport_header_was_set(skb) && !trans_same)
-		len_cur = skb_network_header_len(skb);
 	if ((shrink && (len_diff_abs >= len_cur ||
 			len_cur - len_diff_abs < len_min)) ||
 	    (!shrink && (skb->len + len_diff_abs > len_max &&
-- 
cgit v1.2.3


From 576fd2f7cac3daa36025f0039f9e7cb75b4b4ae0 Mon Sep 17 00:00:00 2001
From: Soheil Hassas Yeganeh <soheil@google.com>
Date: Fri, 22 Mar 2019 10:59:47 -0400
Subject: tcp: add documentation for tcp_ca_state

Add documentation to the tcp_ca_state enum, since this enum is
exposed in uapi.

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Sowmini Varadhan <sowmini05@gmail.com>
Acked-by: Sowmini Varadhan <sowmini05@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tcp.h | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 8bb6cc5f3235..b521464ea962 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -160,15 +160,42 @@ enum {
 #define TCPI_OPT_ECN_SEEN	16 /* we received at least one packet with ECT */
 #define TCPI_OPT_SYN_DATA	32 /* SYN-ACK acked data in SYN sent or rcvd */
 
+/*
+ * Sender's congestion state indicating normal or abnormal situations
+ * in the last round of packets sent. The state is driven by the ACK
+ * information and timer events.
+ */
 enum tcp_ca_state {
+	/*
+	 * Nothing bad has been observed recently.
+	 * No apparent reordering, packet loss, or ECN marks.
+	 */
 	TCP_CA_Open = 0,
 #define TCPF_CA_Open	(1<<TCP_CA_Open)
+	/*
+	 * The sender enters disordered state when it has received DUPACKs or
+	 * SACKs in the last round of packets sent. This could be due to packet
+	 * loss or reordering but needs further information to confirm packets
+	 * have been lost.
+	 */
 	TCP_CA_Disorder = 1,
 #define TCPF_CA_Disorder (1<<TCP_CA_Disorder)
+	/*
+	 * The sender enters Congestion Window Reduction (CWR) state when it
+	 * has received ACKs with ECN-ECE marks, or has experienced congestion
+	 * or packet discard on the sender host (e.g. qdisc).
+	 */
 	TCP_CA_CWR = 2,
 #define TCPF_CA_CWR	(1<<TCP_CA_CWR)
+	/*
+	 * The sender is in fast recovery and retransmitting lost packets,
+	 * typically triggered by ACK events.
+	 */
 	TCP_CA_Recovery = 3,
 #define TCPF_CA_Recovery (1<<TCP_CA_Recovery)
+	/*
+	 * The sender is in loss recovery triggered by retransmission timeout.
+	 */
 	TCP_CA_Loss = 4
 #define TCPF_CA_Loss	(1<<TCP_CA_Loss)
 };
-- 
cgit v1.2.3


From 28cff537ef2eed9307bc7e4e40745075637bec56 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 22 Mar 2019 16:01:55 +0100
Subject: net: sched: add empty status flag for NOLOCK qdisc

The queue is marked not empty after acquiring the seqlock,
and it's up to the NOLOCK qdisc clearing such flag on dequeue.
Since the empty status lays on the same cache-line of the
seqlock, it's always hot on cache during the updates.

This makes the empty flag update a little bit loosy. Given
the lack of synchronization between enqueue and dequeue, this
is unavoidable.

v2 -> v3:
 - qdisc_is_empty() has a const argument (Eric)

v1 -> v2:
 - use really an 'empty' flag instead of 'not_empty', as
   suggested by Eric

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 11 +++++++++++
 net/sched/sch_generic.c   |  3 +++
 2 files changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 31284c078d06..e227475e78ca 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -113,6 +113,9 @@ struct Qdisc {
 
 	spinlock_t		busylock ____cacheline_aligned_in_smp;
 	spinlock_t		seqlock;
+
+	/* for NOLOCK qdisc, true if there are no enqueued skbs */
+	bool			empty;
 	struct rcu_head		rcu;
 };
 
@@ -143,11 +146,19 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc)
 	return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
 }
 
+static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
+{
+	if (qdisc->flags & TCQ_F_NOLOCK)
+		return qdisc->empty;
+	return !qdisc->q.qlen;
+}
+
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
 	if (qdisc->flags & TCQ_F_NOLOCK) {
 		if (!spin_trylock(&qdisc->seqlock))
 			return false;
+		qdisc->empty = false;
 	} else if (qdisc_is_running(qdisc)) {
 		return false;
 	}
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a117d9260558..81356ef38d1d 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -671,6 +671,8 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 		qdisc_qstats_cpu_backlog_dec(qdisc, skb);
 		qdisc_bstats_cpu_update(qdisc, skb);
 		qdisc_qstats_atomic_qlen_dec(qdisc);
+	} else {
+		qdisc->empty = true;
 	}
 
 	return skb;
@@ -880,6 +882,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	sch->enqueue = ops->enqueue;
 	sch->dequeue = ops->dequeue;
 	sch->dev_queue = dev_queue;
+	sch->empty = true;
 	dev_hold(dev);
 	refcount_set(&sch->refcnt, 1);
 
-- 
cgit v1.2.3


From dc05360fee660a9dbe59824b3f7896534210432b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Mar 2019 08:56:38 -0700
Subject: net: convert rps_needed and rfs_needed to new static branch api

We prefer static_branch_unlikely() over static_key_false() these days.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c          |  2 +-
 include/linux/netdevice.h  |  4 ++--
 include/net/sock.h         |  2 +-
 net/core/dev.c             | 10 +++++-----
 net/core/net-sysfs.c       |  4 ++--
 net/core/sysctl_net_core.c |  8 ++++----
 6 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 27798aacb671..24d0220b9ba0 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1042,7 +1042,7 @@ static int tun_net_close(struct net_device *dev)
 static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb)
 {
 #ifdef CONFIG_RPS
-	if (tun->numqueues == 1 && static_key_false(&rps_needed)) {
+	if (tun->numqueues == 1 && static_branch_unlikely(&rps_needed)) {
 		/* Select queue was not called for the skbuff, so we extract the
 		 * RPS hash and save it into the flow_table here.
 		 */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 823762291ebf..166fdc0a78b4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -194,8 +194,8 @@ struct net_device_stats {
 
 #ifdef CONFIG_RPS
 #include <linux/static_key.h>
-extern struct static_key rps_needed;
-extern struct static_key rfs_needed;
+extern struct static_key_false rps_needed;
+extern struct static_key_false rfs_needed;
 #endif
 
 struct neighbour;
diff --git a/include/net/sock.h b/include/net/sock.h
index 8de5ee258b93..fecdf639225c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -966,7 +966,7 @@ static inline void sock_rps_record_flow_hash(__u32 hash)
 static inline void sock_rps_record_flow(const struct sock *sk)
 {
 #ifdef CONFIG_RPS
-	if (static_key_false(&rfs_needed)) {
+	if (static_branch_unlikely(&rfs_needed)) {
 		/* Reading sk->sk_rxhash might incur an expensive cache line
 		 * miss.
 		 *
diff --git a/net/core/dev.c b/net/core/dev.c
index 676c9418f8e4..9ca2d3abfd1a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3982,9 +3982,9 @@ EXPORT_SYMBOL(rps_sock_flow_table);
 u32 rps_cpu_mask __read_mostly;
 EXPORT_SYMBOL(rps_cpu_mask);
 
-struct static_key rps_needed __read_mostly;
+struct static_key_false rps_needed __read_mostly;
 EXPORT_SYMBOL(rps_needed);
-struct static_key rfs_needed __read_mostly;
+struct static_key_false rfs_needed __read_mostly;
 EXPORT_SYMBOL(rfs_needed);
 
 static struct rps_dev_flow *
@@ -4510,7 +4510,7 @@ static int netif_rx_internal(struct sk_buff *skb)
 	}
 
 #ifdef CONFIG_RPS
-	if (static_key_false(&rps_needed)) {
+	if (static_branch_unlikely(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu;
 
@@ -5179,7 +5179,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 
 	rcu_read_lock();
 #ifdef CONFIG_RPS
-	if (static_key_false(&rps_needed)) {
+	if (static_branch_unlikely(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu = get_rps_cpu(skb->dev, skb, &rflow);
 
@@ -5227,7 +5227,7 @@ static void netif_receive_skb_list_internal(struct list_head *head)
 
 	rcu_read_lock();
 #ifdef CONFIG_RPS
-	if (static_key_false(&rps_needed)) {
+	if (static_branch_unlikely(&rps_needed)) {
 		list_for_each_entry_safe(skb, next, head, list) {
 			struct rps_dev_flow voidflow, *rflow = &voidflow;
 			int cpu = get_rps_cpu(skb->dev, skb, &rflow);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 4ff661f6f989..851cabb90bce 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -754,9 +754,9 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
 	rcu_assign_pointer(queue->rps_map, map);
 
 	if (map)
-		static_key_slow_inc(&rps_needed);
+		static_branch_inc(&rps_needed);
 	if (old_map)
-		static_key_slow_dec(&rps_needed);
+		static_branch_dec(&rps_needed);
 
 	mutex_unlock(&rps_map_mutex);
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 84bf2861f45f..1a2685694abd 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -95,12 +95,12 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
 		if (sock_table != orig_sock_table) {
 			rcu_assign_pointer(rps_sock_flow_table, sock_table);
 			if (sock_table) {
-				static_key_slow_inc(&rps_needed);
-				static_key_slow_inc(&rfs_needed);
+				static_branch_inc(&rps_needed);
+				static_branch_inc(&rfs_needed);
 			}
 			if (orig_sock_table) {
-				static_key_slow_dec(&rps_needed);
-				static_key_slow_dec(&rfs_needed);
+				static_branch_dec(&rps_needed);
+				static_branch_dec(&rfs_needed);
 				synchronize_rcu();
 				vfree(orig_sock_table);
 			}
-- 
cgit v1.2.3


From 472c2e07eef045145bc1493cc94a01c87140780a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Mar 2019 08:56:39 -0700
Subject: tcp: add one skb cache for tx

On hosts with a lot of cores, RPC workloads suffer from heavy contention on slab spinlocks.

    20.69%  [kernel]       [k] queued_spin_lock_slowpath
     5.64%  [kernel]       [k] _raw_spin_lock
     3.83%  [kernel]       [k] syscall_return_via_sysret
     3.48%  [kernel]       [k] __entry_text_start
     1.76%  [kernel]       [k] __netif_receive_skb_core
     1.64%  [kernel]       [k] __fget

For each sendmsg(), we allocate one skb, and free it at the time ACK packet comes.

In many cases, ACK packets are handled by another cpus, and this unfortunately
incurs heavy costs for slab layer.

This patch uses an extra pointer in socket structure, so that we try to reuse
the same skb and avoid these expensive costs.

We cache at most one skb per socket so this should be safe as far as
memory pressure is concerned.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h |  5 +++++
 net/ipv4/tcp.c     | 50 +++++++++++++++++++++++---------------------------
 2 files changed, 28 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index fecdf639225c..314c47a8f5d1 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -414,6 +414,7 @@ struct sock {
 		struct sk_buff	*sk_send_head;
 		struct rb_root	tcp_rtx_queue;
 	};
+	struct sk_buff		*sk_tx_skb_cache;
 	struct sk_buff_head	sk_write_queue;
 	__s32			sk_peek_off;
 	int			sk_write_pending;
@@ -1463,6 +1464,10 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
 
 static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
 {
+	if (!sk->sk_tx_skb_cache) {
+		sk->sk_tx_skb_cache = skb;
+		return;
+	}
 	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 	sk->sk_wmem_queued -= skb->truesize;
 	sk_mem_uncharge(sk, skb->truesize);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6baa6dc1b13b..f0b5a5999145 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -865,6 +865,21 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
 {
 	struct sk_buff *skb;
 
+	skb = sk->sk_tx_skb_cache;
+	if (skb && !size) {
+		const struct sk_buff_fclones *fclones;
+
+		fclones = container_of(skb, struct sk_buff_fclones, skb1);
+		if (refcount_read(&fclones->fclone_ref) == 1) {
+			sk->sk_wmem_queued -= skb->truesize;
+			sk_mem_uncharge(sk, skb->truesize);
+			skb->truesize -= skb->data_len;
+			sk->sk_tx_skb_cache = NULL;
+			pskb_trim(skb, 0);
+			INIT_LIST_HEAD(&skb->tcp_tsorted_anchor);
+			return skb;
+		}
+	}
 	/* The TCP header must be at least 32-bit aligned.  */
 	size = ALIGN(size, 4);
 
@@ -1098,30 +1113,6 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset,
 }
 EXPORT_SYMBOL(tcp_sendpage);
 
-/* Do not bother using a page frag for very small frames.
- * But use this heuristic only for the first skb in write queue.
- *
- * Having no payload in skb->head allows better SACK shifting
- * in tcp_shift_skb_data(), reducing sack/rack overhead, because
- * write queue has less skbs.
- * Each skb can hold up to MAX_SKB_FRAGS * 32Kbytes, or ~0.5 MB.
- * This also speeds up tso_fragment(), since it wont fallback
- * to tcp_fragment().
- */
-static int linear_payload_sz(bool first_skb)
-{
-	if (first_skb)
-		return SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER);
-	return 0;
-}
-
-static int select_size(bool first_skb, bool zc)
-{
-	if (zc)
-		return 0;
-	return linear_payload_sz(first_skb);
-}
-
 void tcp_free_fastopen_req(struct tcp_sock *tp)
 {
 	if (tp->fastopen_req) {
@@ -1272,7 +1263,6 @@ restart:
 
 		if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) {
 			bool first_skb;
-			int linear;
 
 new_segment:
 			if (!sk_stream_memory_free(sk))
@@ -1283,8 +1273,7 @@ new_segment:
 				goto restart;
 			}
 			first_skb = tcp_rtx_and_write_queues_empty(sk);
-			linear = select_size(first_skb, zc);
-			skb = sk_stream_alloc_skb(sk, linear, sk->sk_allocation,
+			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
 						  first_skb);
 			if (!skb)
 				goto wait_for_memory;
@@ -2552,6 +2541,13 @@ void tcp_write_queue_purge(struct sock *sk)
 		sk_wmem_free_skb(sk, skb);
 	}
 	tcp_rtx_queue_purge(sk);
+	skb = sk->sk_tx_skb_cache;
+	if (skb) {
+		sk->sk_wmem_queued -= skb->truesize;
+		sk_mem_uncharge(sk, skb->truesize);
+		__kfree_skb(skb);
+		sk->sk_tx_skb_cache = NULL;
+	}
 	INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue);
 	sk_mem_reclaim(sk);
 	tcp_clear_all_retrans_hints(tcp_sk(sk));
-- 
cgit v1.2.3


From 8b27dae5a2e89a61c46c6dbc76c040c0e6d0ed4c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Mar 2019 08:56:40 -0700
Subject: tcp: add one skb cache for rx

Often times, recvmsg() system calls and BH handling for a particular
TCP socket are done on different cpus.

This means the incoming skb had to be allocated on a cpu,
but freed on another.

This incurs a high spinlock contention in slab layer for small rpc,
but also a high number of cache line ping pongs for larger packets.

A full size GRO packet might use 45 page fragments, meaning
that up to 45 put_page() can be involved.

More over performing the __kfree_skb() in the recvmsg() context
adds a latency for user applications, and increase probability
of trapping them in backlog processing, since the BH handler
might found the socket owned by the user.

This patch, combined with the prior one increases the rpc
performance by about 10 % on servers with large number of cores.

(tcp_rr workload with 10,000 flows and 112 threads reach 9 Mpps
 instead of 8 Mpps)

This also increases single bulk flow performance on 40Gbit+ links,
since in this case there are often two cpus working in tandem :

 - CPU handling the NIC rx interrupts, feeding the receive queue,
  and (after this patch) freeing the skbs that were consumed.

 - CPU in recvmsg() system call, essentially 100 % busy copying out
  data to user space.

Having at most one skb in a per-socket cache has very little risk
of memory exhaustion, and since it is protected by socket lock,
its management is essentially free.

Note that if rps/rfs is used, we do not enable this feature, because
there is high chance that the same cpu is handling both the recvmsg()
system call and the TCP rx path, but that another cpu did the skb
allocations in the device driver right before the RPS/RFS logic.

To properly handle this case, it seems we would need to record
on which cpu skb was allocated, and use a different channel
to give skbs back to this cpu.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h  | 10 ++++++++++
 net/ipv4/af_inet.c  |  4 ++++
 net/ipv4/tcp.c      |  4 ++++
 net/ipv4/tcp_ipv4.c | 11 +++++++++--
 net/ipv6/tcp_ipv6.c | 12 +++++++++---
 5 files changed, 36 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 314c47a8f5d1..577d91fb5626 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -368,6 +368,7 @@ struct sock {
 	atomic_t		sk_drops;
 	int			sk_rcvlowat;
 	struct sk_buff_head	sk_error_queue;
+	struct sk_buff		*sk_rx_skb_cache;
 	struct sk_buff_head	sk_receive_queue;
 	/*
 	 * The backlog queue is special, it is always used with
@@ -2438,6 +2439,15 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
 static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);
+	if (
+#ifdef CONFIG_RPS
+	    !static_branch_unlikely(&rps_needed) &&
+#endif
+	    !sk->sk_rx_skb_cache) {
+		sk->sk_rx_skb_cache = skb;
+		skb_orphan(skb);
+		return;
+	}
 	__kfree_skb(skb);
 }
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index eab3ebde981e..7f3a984ad618 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -136,6 +136,10 @@ void inet_sock_destruct(struct sock *sk)
 	struct inet_sock *inet = inet_sk(sk);
 
 	__skb_queue_purge(&sk->sk_receive_queue);
+	if (sk->sk_rx_skb_cache) {
+		__kfree_skb(sk->sk_rx_skb_cache);
+		sk->sk_rx_skb_cache = NULL;
+	}
 	__skb_queue_purge(&sk->sk_error_queue);
 
 	sk_mem_reclaim(sk);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f0b5a5999145..29b94edf05f9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2583,6 +2583,10 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	tcp_clear_xmit_timers(sk);
 	__skb_queue_purge(&sk->sk_receive_queue);
+	if (sk->sk_rx_skb_cache) {
+		__kfree_skb(sk->sk_rx_skb_cache);
+		sk->sk_rx_skb_cache = NULL;
+	}
 	tp->copied_seq = tp->rcv_nxt;
 	tp->urg_data = 0;
 	tcp_write_queue_purge(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 277d71239d75..3979939804b7 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1774,6 +1774,7 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
 int tcp_v4_rcv(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	struct sk_buff *skb_to_free;
 	int sdif = inet_sdif(skb);
 	const struct iphdr *iph;
 	const struct tcphdr *th;
@@ -1905,11 +1906,17 @@ process:
 	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
+		skb_to_free = sk->sk_rx_skb_cache;
+		sk->sk_rx_skb_cache = NULL;
 		ret = tcp_v4_do_rcv(sk, skb);
-	} else if (tcp_add_backlog(sk, skb)) {
-		goto discard_and_relse;
+	} else {
+		if (tcp_add_backlog(sk, skb))
+			goto discard_and_relse;
+		skb_to_free = NULL;
 	}
 	bh_unlock_sock(sk);
+	if (skb_to_free)
+		__kfree_skb(skb_to_free);
 
 put_and_return:
 	if (refcounted)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 983ad7a75102..77d723bbe050 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1436,6 +1436,7 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 
 static int tcp_v6_rcv(struct sk_buff *skb)
 {
+	struct sk_buff *skb_to_free;
 	int sdif = inet6_sdif(skb);
 	const struct tcphdr *th;
 	const struct ipv6hdr *hdr;
@@ -1562,12 +1563,17 @@ process:
 	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
+		skb_to_free = sk->sk_rx_skb_cache;
+		sk->sk_rx_skb_cache = NULL;
 		ret = tcp_v6_do_rcv(sk, skb);
-	} else if (tcp_add_backlog(sk, skb)) {
-		goto discard_and_relse;
+	} else {
+		if (tcp_add_backlog(sk, skb))
+			goto discard_and_relse;
+		skb_to_free = NULL;
 	}
 	bh_unlock_sock(sk);
-
+	if (skb_to_free)
+		__kfree_skb(skb_to_free);
 put_and_return:
 	if (refcounted)
 		sock_put(sk);
-- 
cgit v1.2.3


From b8f975545cdbcc316cf20e827e7966d4410b5c5a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 24 Mar 2019 11:14:37 +0100
Subject: net: devlink: add port type spinlock

Add spinlock to protect port type and type_dev pointer consistency.
Without that, userspace may see inconsistent type and type_dev
combinations.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
v1->v2:
- rebased
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h |  4 ++++
 net/core/devlink.c    | 17 +++++++++++++----
 2 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 63de99e09f04..cb9b060033e1 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -16,6 +16,7 @@
 #include <linux/gfp.h>
 #include <linux/list.h>
 #include <linux/netdevice.h>
+#include <linux/spinlock.h>
 #include <net/net_namespace.h>
 #include <uapi/linux/devlink.h>
 
@@ -53,6 +54,9 @@ struct devlink_port {
 	struct devlink *devlink;
 	unsigned index;
 	bool registered;
+	spinlock_t type_lock; /* Protects type and type_dev
+			       * pointer consistency.
+			       */
 	enum devlink_port_type type;
 	enum devlink_port_type desired_type;
 	void *type_dev;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 860ab3a721e0..19fa5be28127 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -19,6 +19,7 @@
 #include <linux/device.h>
 #include <linux/list.h>
 #include <linux/netdevice.h>
+#include <linux/spinlock.h>
 #include <rdma/ib_verbs.h>
 #include <net/netlink.h>
 #include <net/genetlink.h>
@@ -543,12 +544,14 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
 		goto nla_put_failure;
 	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
 		goto nla_put_failure;
+
+	spin_lock(&devlink_port->type_lock);
 	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))
-		goto nla_put_failure;
+		goto nla_put_failure_type_locked;
 	if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET &&
 	    nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE,
 			devlink_port->desired_type))
-		goto nla_put_failure;
+		goto nla_put_failure_type_locked;
 	if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
 		struct net_device *netdev = devlink_port->type_dev;
 
@@ -557,7 +560,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
 				 netdev->ifindex) ||
 		     nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,
 				    netdev->name)))
-			goto nla_put_failure;
+			goto nla_put_failure_type_locked;
 	}
 	if (devlink_port->type == DEVLINK_PORT_TYPE_IB) {
 		struct ib_device *ibdev = devlink_port->type_dev;
@@ -565,14 +568,17 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
 		if (ibdev &&
 		    nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME,
 				   ibdev->name))
-			goto nla_put_failure;
+			goto nla_put_failure_type_locked;
 	}
+	spin_unlock(&devlink_port->type_lock);
 	if (devlink_nl_port_attrs_put(msg, devlink_port))
 		goto nla_put_failure;
 
 	genlmsg_end(msg, hdr);
 	return 0;
 
+nla_put_failure_type_locked:
+	spin_unlock(&devlink_port->type_lock);
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	return -EMSGSIZE;
@@ -5300,6 +5306,7 @@ int devlink_port_register(struct devlink *devlink,
 	devlink_port->devlink = devlink;
 	devlink_port->index = port_index;
 	devlink_port->registered = true;
+	spin_lock_init(&devlink_port->type_lock);
 	list_add_tail(&devlink_port->list, &devlink->port_list);
 	INIT_LIST_HEAD(&devlink_port->param_list);
 	mutex_unlock(&devlink->lock);
@@ -5330,8 +5337,10 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port,
 {
 	if (WARN_ON(!devlink_port->registered))
 		return;
+	spin_lock(&devlink_port->type_lock);
 	devlink_port->type = type;
 	devlink_port->type_dev = type_dev;
+	spin_unlock(&devlink_port->type_lock);
 	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
 }
 
-- 
cgit v1.2.3


From f6b19b354d50c5ae46ad66b5273f92e563fbc847 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 24 Mar 2019 11:14:38 +0100
Subject: net: devlink: select NET_DEVLINK from drivers

Some drivers are becoming more dependent on NET_DEVLINK being selected
in configuration. With upcoming compat functions, the behavior would be
wrong in case devlink was not compiled in. So make the drivers select
NET_DEVLINK and rely on the functions being there, not just stubs.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/Kconfig                             |   1 +
 drivers/net/ethernet/broadcom/Kconfig           |   1 +
 drivers/net/ethernet/cavium/Kconfig             |   1 +
 drivers/net/ethernet/mellanox/mlx4/Kconfig      |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig |   1 +
 drivers/net/ethernet/mellanox/mlxsw/Kconfig     |   1 +
 drivers/net/ethernet/netronome/Kconfig          |   1 +
 include/net/devlink.h                           | 495 +-----------------------
 net/Kconfig                                     |   7 +-
 net/dsa/Kconfig                                 |   1 +
 10 files changed, 13 insertions(+), 497 deletions(-)

(limited to 'include')

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 7a96d168efc4..bc42f131f47c 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -505,6 +505,7 @@ source "drivers/net/hyperv/Kconfig"
 config NETDEVSIM
 	tristate "Simulated networking device"
 	depends on DEBUG_FS
+	select NET_DEVLINK
 	help
 	  This driver is a developer testing tool and software model that can
 	  be used to test various control path networking APIs, especially
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 716bfbba59cf..461b2c0b2ed6 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -196,6 +196,7 @@ config BNXT
 	depends on PCI
 	select FW_LOADER
 	select LIBCRC32C
+	select NET_DEVLINK
 	---help---
 	  This driver supports Broadcom NetXtreme-C/E 10/25/40/50 gigabit
 	  Ethernet cards.  To compile this driver as a module, choose M here:
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 6650e2a5f171..7612ab6b286d 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -68,6 +68,7 @@ config LIQUIDIO
 	imply PTP_1588_CLOCK
 	select FW_LOADER
 	select LIBCRC32C
+	select NET_DEVLINK
 	---help---
 	  This driver supports Cavium LiquidIO Intelligent Server Adapters
 	  based on CN66XX, CN68XX and CN23XX chips.
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index ff8057ed97ee..8491db57b0b0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -26,6 +26,7 @@ config MLX4_EN_DCB
 config MLX4_CORE
 	tristate
 	depends on PCI
+	select NET_DEVLINK
 	default n
 
 config MLX4_DEBUG
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 6debffb8336b..9aca8086ee01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -5,6 +5,7 @@
 config MLX5_CORE
 	tristate "Mellanox 5th generation network adapters (ConnectX series) core driver"
 	depends on PCI
+	select NET_DEVLINK
 	imply PTP_1588_CLOCK
 	imply VXLAN
 	default n
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index 9c195dfed031..b6b3ff0fe17f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -4,6 +4,7 @@
 
 config MLXSW_CORE
 	tristate "Mellanox Technologies Switch ASICs support"
+	select NET_DEVLINK
 	---help---
 	  This driver supports Mellanox Technologies Switch ASICs family.
 
diff --git a/drivers/net/ethernet/netronome/Kconfig b/drivers/net/ethernet/netronome/Kconfig
index 549898d5d450..f0d0e09f60e2 100644
--- a/drivers/net/ethernet/netronome/Kconfig
+++ b/drivers/net/ethernet/netronome/Kconfig
@@ -19,6 +19,7 @@ config NFP
 	tristate "Netronome(R) NFP4000/NFP6000 NIC driver"
 	depends on PCI && PCI_MSI
 	depends on VXLAN || VXLAN=n
+	select NET_DEVLINK
 	---help---
 	  This driver supports the Netronome(R) NFP4000/NFP6000 based
 	  cards working as a advanced Ethernet NIC.  It works with both
diff --git a/include/net/devlink.h b/include/net/devlink.h
index cb9b060033e1..03fb16f4fb6c 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -549,17 +549,13 @@ static inline struct devlink *priv_to_devlink(void *priv)
 
 static inline struct devlink *netdev_to_devlink(struct net_device *dev)
 {
-#if IS_ENABLED(CONFIG_NET_DEVLINK)
 	if (dev->netdev_ops->ndo_get_devlink)
 		return dev->netdev_ops->ndo_get_devlink(dev);
-#endif
 	return NULL;
 }
 
 struct ib_device;
 
-#if IS_ENABLED(CONFIG_NET_DEVLINK)
-
 struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size);
 int devlink_register(struct devlink *devlink, struct device *dev);
 void devlink_unregister(struct devlink *devlink);
@@ -728,500 +724,14 @@ void
 devlink_health_reporter_state_update(struct devlink_health_reporter *reporter,
 				     enum devlink_health_reporter_state state);
 
+#if IS_ENABLED(CONFIG_NET_DEVLINK)
+
 void devlink_compat_running_version(struct net_device *dev,
 				    char *buf, size_t len);
 int devlink_compat_flash_update(struct net_device *dev, const char *file_name);
 
 #else
 
-static inline struct devlink *devlink_alloc(const struct devlink_ops *ops,
-					    size_t priv_size)
-{
-	return kzalloc(sizeof(struct devlink) + priv_size, GFP_KERNEL);
-}
-
-static inline int devlink_register(struct devlink *devlink, struct device *dev)
-{
-	return 0;
-}
-
-static inline void devlink_unregister(struct devlink *devlink)
-{
-}
-
-static inline void devlink_params_publish(struct devlink *devlink)
-{
-}
-
-static inline void devlink_params_unpublish(struct devlink *devlink)
-{
-}
-
-static inline void devlink_free(struct devlink *devlink)
-{
-	kfree(devlink);
-}
-
-static inline int devlink_port_register(struct devlink *devlink,
-					struct devlink_port *devlink_port,
-					unsigned int port_index)
-{
-	return 0;
-}
-
-static inline void devlink_port_unregister(struct devlink_port *devlink_port)
-{
-}
-
-static inline void devlink_port_type_eth_set(struct devlink_port *devlink_port,
-					     struct net_device *netdev)
-{
-}
-
-static inline void devlink_port_type_ib_set(struct devlink_port *devlink_port,
-					    struct ib_device *ibdev)
-{
-}
-
-static inline void devlink_port_type_clear(struct devlink_port *devlink_port)
-{
-}
-
-static inline void devlink_port_attrs_set(struct devlink_port *devlink_port,
-					  enum devlink_port_flavour flavour,
-					  u32 port_number, bool split,
-					  u32 split_subport_number)
-{
-}
-
-static inline int
-devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
-				char *name, size_t len)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int devlink_sb_register(struct devlink *devlink,
-				      unsigned int sb_index, u32 size,
-				      u16 ingress_pools_count,
-				      u16 egress_pools_count,
-				      u16 ingress_tc_count,
-				      u16 egress_tc_count)
-{
-	return 0;
-}
-
-static inline void devlink_sb_unregister(struct devlink *devlink,
-					 unsigned int sb_index)
-{
-}
-
-static inline int
-devlink_dpipe_table_register(struct devlink *devlink,
-			     const char *table_name,
-			     struct devlink_dpipe_table_ops *table_ops,
-			     void *priv, bool counter_control_extern)
-{
-	return 0;
-}
-
-static inline void devlink_dpipe_table_unregister(struct devlink *devlink,
-						  const char *table_name)
-{
-}
-
-static inline int devlink_dpipe_headers_register(struct devlink *devlink,
-						 struct devlink_dpipe_headers *
-						 dpipe_headers)
-{
-	return 0;
-}
-
-static inline void devlink_dpipe_headers_unregister(struct devlink *devlink)
-{
-}
-
-static inline bool devlink_dpipe_table_counter_enabled(struct devlink *devlink,
-						       const char *table_name)
-{
-	return false;
-}
-
-static inline int
-devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
-{
-	return 0;
-}
-
-static inline int
-devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx,
-			       struct devlink_dpipe_entry *entry)
-{
-	return 0;
-}
-
-static inline int
-devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx)
-{
-	return 0;
-}
-
-static inline void
-devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry)
-{
-}
-
-static inline int
-devlink_dpipe_action_put(struct sk_buff *skb,
-			 struct devlink_dpipe_action *action)
-{
-	return 0;
-}
-
-static inline int
-devlink_dpipe_match_put(struct sk_buff *skb,
-			struct devlink_dpipe_match *match)
-{
-	return 0;
-}
-
-static inline int
-devlink_resource_register(struct devlink *devlink,
-			  const char *resource_name,
-			  u64 resource_size,
-			  u64 resource_id,
-			  u64 parent_resource_id,
-			  const struct devlink_resource_size_params *size_params)
-{
-	return 0;
-}
-
-static inline void
-devlink_resources_unregister(struct devlink *devlink,
-			     struct devlink_resource *resource)
-{
-}
-
-static inline int
-devlink_resource_size_get(struct devlink *devlink, u64 resource_id,
-			  u64 *p_resource_size)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int
-devlink_dpipe_table_resource_set(struct devlink *devlink,
-				 const char *table_name, u64 resource_id,
-				 u64 resource_units)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline void
-devlink_resource_occ_get_register(struct devlink *devlink,
-				  u64 resource_id,
-				  devlink_resource_occ_get_t *occ_get,
-				  void *occ_get_priv)
-{
-}
-
-static inline void
-devlink_resource_occ_get_unregister(struct devlink *devlink,
-				    u64 resource_id)
-{
-}
-
-static inline int
-devlink_params_register(struct devlink *devlink,
-			const struct devlink_param *params,
-			size_t params_count)
-{
-	return 0;
-}
-
-static inline void
-devlink_params_unregister(struct devlink *devlink,
-			  const struct devlink_param *params,
-			  size_t params_count)
-{
-
-}
-
-static inline int
-devlink_port_params_register(struct devlink_port *devlink_port,
-			     const struct devlink_param *params,
-			     size_t params_count)
-{
-	return 0;
-}
-
-static inline void
-devlink_port_params_unregister(struct devlink_port *devlink_port,
-			       const struct devlink_param *params,
-			       size_t params_count)
-{
-}
-
-static inline int
-devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
-				   union devlink_param_value *init_val)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int
-devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
-				   union devlink_param_value init_val)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int
-devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port,
-					u32 param_id,
-					union devlink_param_value *init_val)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int
-devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port,
-					u32 param_id,
-					union devlink_param_value init_val)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline void
-devlink_param_value_changed(struct devlink *devlink, u32 param_id)
-{
-}
-
-static inline void
-devlink_port_param_value_changed(struct devlink_port *devlink_port,
-				 u32 param_id)
-{
-}
-
-static inline void
-devlink_param_value_str_fill(union devlink_param_value *dst_val,
-			     const char *src)
-{
-}
-
-static inline struct devlink_region *
-devlink_region_create(struct devlink *devlink,
-		      const char *region_name,
-		      u32 region_max_snapshots,
-		      u64 region_size)
-{
-	return NULL;
-}
-
-static inline void
-devlink_region_destroy(struct devlink_region *region)
-{
-}
-
-static inline u32
-devlink_region_shapshot_id_get(struct devlink *devlink)
-{
-	return 0;
-}
-
-static inline int
-devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
-			       u8 *data, u32 snapshot_id,
-			       devlink_snapshot_data_dest_t *data_destructor)
-{
-	return 0;
-}
-
-static inline int
-devlink_info_driver_name_put(struct devlink_info_req *req, const char *name)
-{
-	return 0;
-}
-
-static inline int
-devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn)
-{
-	return 0;
-}
-
-static inline int
-devlink_info_version_fixed_put(struct devlink_info_req *req,
-			       const char *version_name,
-			       const char *version_value)
-{
-	return 0;
-}
-
-static inline int
-devlink_info_version_stored_put(struct devlink_info_req *req,
-				const char *version_name,
-				const char *version_value)
-{
-	return 0;
-}
-
-static inline int
-devlink_info_version_running_put(struct devlink_info_req *req,
-				 const char *version_name,
-				 const char *version_value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg,
-				 const char *name)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value,
-			u16 value_len)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name,
-			   bool value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name,
-			 u8 value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name,
-			  u32 value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name,
-			  u64 value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name,
-			     const char *value)
-{
-	return 0;
-}
-
-static inline int
-devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name,
-			     const void *value, u16 value_len)
-{
-	return 0;
-}
-
-static inline struct devlink_health_reporter *
-devlink_health_reporter_create(struct devlink *devlink,
-			       const struct devlink_health_reporter_ops *ops,
-			       u64 graceful_period, bool auto_recover,
-			       void *priv)
-{
-	return NULL;
-}
-
-static inline void
-devlink_health_reporter_destroy(struct devlink_health_reporter *reporter)
-{
-}
-
-static inline void *
-devlink_health_reporter_priv(struct devlink_health_reporter *reporter)
-{
-	return NULL;
-}
-
-static inline int
-devlink_health_report(struct devlink_health_reporter *reporter,
-		      const char *msg, void *priv_ctx)
-{
-	return 0;
-}
-
-static inline void
-devlink_health_reporter_state_update(struct devlink_health_reporter *reporter,
-				     enum devlink_health_reporter_state state)
-{
-}
-
 static inline void
 devlink_compat_running_version(struct net_device *dev, char *buf, size_t len)
 {
@@ -1232,6 +742,7 @@ devlink_compat_flash_update(struct net_device *dev, const char *file_name)
 {
 	return -EOPNOTSUPP;
 }
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/net/Kconfig b/net/Kconfig
index 1efe1f9ee492..3e8fdd688329 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -429,11 +429,8 @@ config NET_SOCK_MSG
 	  with the help of BPF programs.
 
 config NET_DEVLINK
-	bool "Network physical/parent device Netlink interface"
-	help
-	  Network physical/parent device Netlink interface provides
-	  infrastructure to support access to physical chip-wide config and
-	  monitoring.
+	bool
+	default n
 
 config PAGE_POOL
        bool
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index fab49132345f..b695170795c2 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -10,6 +10,7 @@ config NET_DSA
 	depends on BRIDGE || BRIDGE=n
 	select NET_SWITCHDEV
 	select PHYLINK
+	select NET_DEVLINK
 	---help---
 	  Say Y if you want to enable support for the hardware switches supported
 	  by the Distributed Switch Architecture.
-- 
cgit v1.2.3


From 0d5f20c42b24adffa1505ec3d4930d11dfaea82f Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 3 Mar 2019 15:52:07 +0100
Subject: batman-adv: Drop license boilerplate

All files got a SPDX-License-Identifier with commit 7db7d9f369a4
("batman-adv: Add SPDX license identifier above copyright header"). All the
required information about the license conditions can be found in
LICENSES/.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 include/uapi/linux/batadv_packet.h     | 12 ------------
 include/uapi/linux/batman_adv.h        | 18 ------------------
 net/batman-adv/Kconfig                 | 12 ------------
 net/batman-adv/Makefile                | 13 -------------
 net/batman-adv/bat_algo.c              | 12 ------------
 net/batman-adv/bat_algo.h              | 12 ------------
 net/batman-adv/bat_iv_ogm.c            | 12 ------------
 net/batman-adv/bat_iv_ogm.h            | 12 ------------
 net/batman-adv/bat_v.c                 | 12 ------------
 net/batman-adv/bat_v.h                 | 12 ------------
 net/batman-adv/bat_v_elp.c             | 12 ------------
 net/batman-adv/bat_v_elp.h             | 12 ------------
 net/batman-adv/bat_v_ogm.c             | 12 ------------
 net/batman-adv/bat_v_ogm.h             | 12 ------------
 net/batman-adv/bitarray.c              | 12 ------------
 net/batman-adv/bitarray.h              | 12 ------------
 net/batman-adv/bridge_loop_avoidance.c | 12 ------------
 net/batman-adv/bridge_loop_avoidance.h | 12 ------------
 net/batman-adv/debugfs.c               | 12 ------------
 net/batman-adv/debugfs.h               | 12 ------------
 net/batman-adv/distributed-arp-table.c | 12 ------------
 net/batman-adv/distributed-arp-table.h | 12 ------------
 net/batman-adv/fragmentation.c         | 12 ------------
 net/batman-adv/fragmentation.h         | 12 ------------
 net/batman-adv/gateway_client.c        | 12 ------------
 net/batman-adv/gateway_client.h        | 12 ------------
 net/batman-adv/gateway_common.c        | 12 ------------
 net/batman-adv/gateway_common.h        | 12 ------------
 net/batman-adv/hard-interface.c        | 12 ------------
 net/batman-adv/hard-interface.h        | 12 ------------
 net/batman-adv/hash.c                  | 12 ------------
 net/batman-adv/hash.h                  | 12 ------------
 net/batman-adv/icmp_socket.c           | 12 ------------
 net/batman-adv/icmp_socket.h           | 12 ------------
 net/batman-adv/log.c                   | 12 ------------
 net/batman-adv/log.h                   | 12 ------------
 net/batman-adv/main.c                  | 12 ------------
 net/batman-adv/main.h                  | 12 ------------
 net/batman-adv/multicast.c             | 12 ------------
 net/batman-adv/multicast.h             | 12 ------------
 net/batman-adv/netlink.c               | 12 ------------
 net/batman-adv/netlink.h               | 12 ------------
 net/batman-adv/network-coding.c        | 12 ------------
 net/batman-adv/network-coding.h        | 12 ------------
 net/batman-adv/originator.c            | 12 ------------
 net/batman-adv/originator.h            | 12 ------------
 net/batman-adv/routing.c               | 12 ------------
 net/batman-adv/routing.h               | 12 ------------
 net/batman-adv/send.c                  | 12 ------------
 net/batman-adv/send.h                  | 12 ------------
 net/batman-adv/soft-interface.c        | 12 ------------
 net/batman-adv/soft-interface.h        | 12 ------------
 net/batman-adv/sysfs.c                 | 12 ------------
 net/batman-adv/sysfs.h                 | 12 ------------
 net/batman-adv/tp_meter.c              | 12 ------------
 net/batman-adv/tp_meter.h              | 12 ------------
 net/batman-adv/trace.c                 | 12 ------------
 net/batman-adv/trace.h                 | 12 ------------
 net/batman-adv/translation-table.c     | 12 ------------
 net/batman-adv/translation-table.h     | 12 ------------
 net/batman-adv/tvlv.c                  | 12 ------------
 net/batman-adv/tvlv.h                  | 12 ------------
 net/batman-adv/types.h                 | 12 ------------
 63 files changed, 763 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h
index c99336f4eefe..4ebc2135e950 100644
--- a/include/uapi/linux/batadv_packet.h
+++ b/include/uapi/linux/batadv_packet.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _UAPI_LINUX_BATADV_PACKET_H_
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index 305bf316dd03..e53f2b5e7ee7 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -2,24 +2,6 @@
 /* Copyright (C) 2016-2019  B.A.T.M.A.N. contributors:
  *
  * Matthias Schiffer
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
  */
 
 #ifndef _UAPI_LINUX_BATMAN_ADV_H_
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index a31db5e9ac8e..17595ec0961a 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -2,18 +2,6 @@
 # Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
 #
 # Marek Lindner, Simon Wunderlich
-#
-# This program is free software; you can redistribute it and/or
-# modify it under the terms of version 2 of the GNU General Public
-# License as published by the Free Software Foundation.
-#
-# This program is distributed in the hope that it will be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
-# General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, see <http://www.gnu.org/licenses/>.
 
 #
 # B.A.T.M.A.N meshing protocol
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index a887ecc3efa1..1bf7acfea17a 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -2,19 +2,6 @@
 # Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
 #
 # Marek Lindner, Simon Wunderlich
-#
-# This program is free software; you can redistribute it and/or
-# modify it under the terms of version 2 of the GNU General Public
-# License as published by the Free Software Foundation.
-#
-# This program is distributed in the hope that it will be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
-# General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, see <http://www.gnu.org/licenses/>.
-#
 
 obj-$(CONFIG_BATMAN_ADV) += batman-adv.o
 batman-adv-y += bat_algo.o
diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c
index 7b7e15641fef..fa39eaaab9d7 100644
--- a/net/batman-adv/bat_algo.c
+++ b/net/batman-adv/bat_algo.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h
index 25e7bb51928c..cb7d57d16c9d 100644
--- a/net/batman-adv/bat_algo.h
+++ b/net/batman-adv/bat_algo.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2011-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Linus Lüssing
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_BAT_ALGO_H_
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index de61091af666..bd4138ddf7e0 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "bat_iv_ogm.h"
diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h
index 785f6666273c..c7a9ba305bfc 100644
--- a/net/batman-adv/bat_iv_ogm.h
+++ b/net/batman-adv/bat_iv_ogm.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_BAT_IV_OGM_H_
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 445594ed58af..231b4aab4d8d 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2013-2019  B.A.T.M.A.N. contributors:
  *
  * Linus Lüssing, Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "bat_v.h"
diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h
index 465a4fc23354..37833db098e6 100644
--- a/net/batman-adv/bat_v.h
+++ b/net/batman-adv/bat_v.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2011-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Linus Lüssing
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_BAT_V_H_
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index a9b7919c9de5..13b9ab860a25 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2011-2019  B.A.T.M.A.N. contributors:
  *
  * Linus Lüssing, Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "bat_v_elp.h"
diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h
index 75f189ee4a1c..bb3d40f73bfe 100644
--- a/net/batman-adv/bat_v_elp.h
+++ b/net/batman-adv/bat_v_elp.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2013-2019  B.A.T.M.A.N. contributors:
  *
  * Linus Lüssing, Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_BAT_V_ELP_H_
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index c9698ad41854..fad95ef64e01 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2013-2019  B.A.T.M.A.N. contributors:
  *
  * Antonio Quartulli
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "bat_v_ogm.h"
diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h
index f67cf7ee06b2..616bf2ea8755 100644
--- a/net/batman-adv/bat_v_ogm.h
+++ b/net/batman-adv/bat_v_ogm.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2013-2019  B.A.T.M.A.N. contributors:
  *
  * Antonio Quartulli
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_BAT_V_OGM_H_
diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c
index 63e134e763e3..7f04a6acf14e 100644
--- a/net/batman-adv/bitarray.c
+++ b/net/batman-adv/bitarray.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2006-2019  B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich, Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "bitarray.h"
diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h
index f3a05ad9afad..84ad2d2b6ac9 100644
--- a/net/batman-adv/bitarray.h
+++ b/net/batman-adv/bitarray.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2006-2019  B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich, Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_BITARRAY_H_
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index ef39aabdb694..ee92bbc25058 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2011-2019  B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "bridge_loop_avoidance.h"
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index 31771c751efb..012d72c8d064 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2011-2019  B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_BLA_H_
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index 3b9d1ad2f467..d38d70ccdd5a 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2010-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "debugfs.h"
diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h
index c0b8694041ec..7fac680cf740 100644
--- a/net/batman-adv/debugfs.h
+++ b/net/batman-adv/debugfs.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2010-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_DEBUGFS_H_
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 310a4f353008..c14faaa32ca4 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2011-2019  B.A.T.M.A.N. contributors:
  *
  * Antonio Quartulli
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "distributed-arp-table.h"
diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h
index 68c0ff321acd..110c27447d70 100644
--- a/net/batman-adv/distributed-arp-table.h
+++ b/net/batman-adv/distributed-arp-table.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2011-2019  B.A.T.M.A.N. contributors:
  *
  * Antonio Quartulli
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_DISTRIBUTED_ARP_TABLE_H_
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index b506d15b8230..385fccdcf69d 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2013-2019  B.A.T.M.A.N. contributors:
  *
  * Martin Hundebøll <martin@hundeboll.net>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "fragmentation.h"
diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h
index abdac26579bf..d6074ba2ada7 100644
--- a/net/batman-adv/fragmentation.h
+++ b/net/batman-adv/fragmentation.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2013-2019  B.A.T.M.A.N. contributors:
  *
  * Martin Hundebøll <martin@hundeboll.net>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_FRAGMENTATION_H_
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index f5811f61aa92..be63d6706659 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2009-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "gateway_client.h"
diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h
index b5732c8be81a..0e14026feebd 100644
--- a/net/batman-adv/gateway_client.h
+++ b/net/batman-adv/gateway_client.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2009-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_GATEWAY_CLIENT_H_
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index e064de45e22c..dac097f9be03 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2009-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "gateway_common.h"
diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h
index 128467a0fb89..5cf50736c635 100644
--- a/net/batman-adv/gateway_common.h
+++ b/net/batman-adv/gateway_common.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2009-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_GATEWAY_COMMON_H_
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 96ef7c70b4d9..79d1731b8306 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "hard-interface.h"
diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index 48de28c83401..c8ef6aa0e865 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_HARD_INTERFACE_H_
diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c
index 56a08ce193d5..a9d4e176f4de 100644
--- a/net/batman-adv/hash.c
+++ b/net/batman-adv/hash.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2006-2019  B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich, Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "hash.h"
diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h
index 37507b6d4006..ceef171f7f98 100644
--- a/net/batman-adv/hash.h
+++ b/net/batman-adv/hash.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2006-2019  B.A.T.M.A.N. contributors:
  *
  * Simon Wunderlich, Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_HASH_H_
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 9859ababb82e..de81b5ecad91 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "icmp_socket.h"
diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h
index 5f8926522ff0..35eecbfd2e65 100644
--- a/net/batman-adv/icmp_socket.h
+++ b/net/batman-adv/icmp_socket.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_ICMP_SOCKET_H_
diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c
index 3e610df8debf..60ce11e16a90 100644
--- a/net/batman-adv/log.c
+++ b/net/batman-adv/log.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2010-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "log.h"
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
index 660e9bcc85a2..5504637e63d8 100644
--- a/net/batman-adv/log.h
+++ b/net/batman-adv/log.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_LOG_H_
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 75750870cf04..33b9b38b82da 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 3ed669d7dc6b..c5de987778d1 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_MAIN_H_
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index f91b1b6265cf..4d6e89e04aa0 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2014-2019  B.A.T.M.A.N. contributors:
  *
  * Linus Lüssing
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "multicast.h"
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index 466013fe88af..34fb922a4566 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2014-2019  B.A.T.M.A.N. contributors:
  *
  * Linus Lüssing
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_MULTICAST_H_
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 67a58da2e6a0..8e82e656b870 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2016-2019  B.A.T.M.A.N. contributors:
  *
  * Matthias Schiffer
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "netlink.h"
diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h
index 7273368544fc..d1e0681b8743 100644
--- a/net/batman-adv/netlink.h
+++ b/net/batman-adv/netlink.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2016-2019  B.A.T.M.A.N. contributors:
  *
  * Matthias Schiffer
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_NETLINK_H_
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 278762bd94c6..c5e7906045f3 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2012-2019  B.A.T.M.A.N. contributors:
  *
  * Martin Hundebøll, Jeppe Ledet-Pedersen
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "network-coding.h"
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
index 96ef0a511fc7..74f56113a5d0 100644
--- a/net/batman-adv/network-coding.h
+++ b/net/batman-adv/network-coding.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2012-2019  B.A.T.M.A.N. contributors:
  *
  * Martin Hundebøll, Jeppe Ledet-Pedersen
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_NETWORK_CODING_H_
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index e5cdf89ef63c..45db798a7297 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2009-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "originator.h"
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index dca1e4a34ec6..3829e26f9c5d 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_ORIGINATOR_H_
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index cae0e5dd0768..f0f864820dea 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "routing.h"
diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h
index 0102d69d345c..b96c6d06d188 100644
--- a/net/batman-adv/routing.h
+++ b/net/batman-adv/routing.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_ROUTING_H_
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 66a8b3e44501..3ce5f7bad369 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "send.h"
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index 1f6132922e60..5921ee4e107c 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_SEND_H_
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 2e367230376b..f8fcdd6de656 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "soft-interface.h"
diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h
index 538bb661878c..275442a7acb6 100644
--- a/net/batman-adv/soft-interface.h
+++ b/net/batman-adv/soft-interface.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_SOFT_INTERFACE_H_
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 0b4b3fb778a6..4fc9f7305174 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2010-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "sysfs.h"
diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h
index 705ffbe763f4..2d13f59efb1a 100644
--- a/net/batman-adv/sysfs.h
+++ b/net/batman-adv/sysfs.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2010-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_SYSFS_H_
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index 500109bbd551..820392146249 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2012-2019  B.A.T.M.A.N. contributors:
  *
  * Edo Monticelli, Antonio Quartulli
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "tp_meter.h"
diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h
index 6b4d0f733896..604b3799c972 100644
--- a/net/batman-adv/tp_meter.h
+++ b/net/batman-adv/tp_meter.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2012-2019  B.A.T.M.A.N. contributors:
  *
  * Edo Monticelli, Antonio Quartulli
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_TP_METER_H_
diff --git a/net/batman-adv/trace.c b/net/batman-adv/trace.c
index f77c917ed20d..3cedd2c36528 100644
--- a/net/batman-adv/trace.c
+++ b/net/batman-adv/trace.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2010-2019  B.A.T.M.A.N. contributors:
  *
  * Sven Eckelmann
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #define CREATE_TRACE_POINTS
diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h
index 5e5579051400..d8f764521c0b 100644
--- a/net/batman-adv/trace.h
+++ b/net/batman-adv/trace.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2010-2019  B.A.T.M.A.N. contributors:
  *
  * Sven Eckelmann
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #if !defined(_NET_BATMAN_ADV_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index f73d79139ae7..842e7634d20f 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich, Antonio Quartulli
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "translation-table.h"
diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h
index 61bca75e5911..a328979836b2 100644
--- a/net/batman-adv/translation-table.h
+++ b/net/batman-adv/translation-table.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich, Antonio Quartulli
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_TRANSLATION_TABLE_H_
diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c
index 7e947b01919d..aae63f0d21eb 100644
--- a/net/batman-adv/tvlv.c
+++ b/net/batman-adv/tvlv.c
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #include "main.h"
diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h
index c0f033b1acb8..114ac01e06af 100644
--- a/net/batman-adv/tvlv.h
+++ b/net/batman-adv/tvlv.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_TVLV_H_
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index a21b34ed6548..e19fdb5c1281 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -2,18 +2,6 @@
 /* Copyright (C) 2007-2019  B.A.T.M.A.N. contributors:
  *
  * Marek Lindner, Simon Wunderlich
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef _NET_BATMAN_ADV_TYPES_H_
-- 
cgit v1.2.3


From 32e727449c792b689c2a06a8b4cc9fef6270c5a7 Mon Sep 17 00:00:00 2001
From: Linus Lüssing <linus.luessing@c0d3.blue>
Date: Sat, 23 Mar 2019 05:47:41 +0100
Subject: batman-adv: Add multicast-to-unicast support for multiple targets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With this patch multicast packets with a limited number of destinations
(current default: 16) will be split and transmitted by the originator as
individual unicast transmissions.

Wifi broadcasts with their low bitrate are still a costly undertaking.
In a mesh network this cost multiplies with the overall size of the mesh
network. Therefore using multiple unicast transmissions instead of
broadcast flooding is almost always less burdensome for the mesh
network.

The maximum amount of unicast packets can be configured via the newly
introduced multicast_fanout parameter. If this limit is exceeded
distribution will fall back to classic broadcast flooding.

The multicast-to-unicast conversion is performed on the initial
multicast sender node and counts on a final destination node, mesh-wide
basis (and not next hop, neighbor node basis).

Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 include/uapi/linux/batman_adv.h    |   7 ++
 net/batman-adv/multicast.c         | 199 ++++++++++++++++++++++++++++++++++++-
 net/batman-adv/multicast.h         |  18 ++++
 net/batman-adv/netlink.c           |  11 ++
 net/batman-adv/soft-interface.c    |   8 +-
 net/batman-adv/translation-table.c |   5 +-
 net/batman-adv/translation-table.h |   4 +
 net/batman-adv/types.h             |   6 ++
 8 files changed, 252 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index e53f2b5e7ee7..67f4636758af 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -473,6 +473,13 @@ enum batadv_nl_attrs {
 	 */
 	BATADV_ATTR_THROUGHPUT_OVERRIDE,
 
+	/**
+	 * @BATADV_ATTR_MULTICAST_FANOUT: defines the maximum number of packet
+	 * copies that may be generated for a multicast-to-unicast conversion.
+	 * Once this limit is exceeded distribution will fall back to broadcast.
+	 */
+	BATADV_ATTR_MULTICAST_FANOUT,
+
 	/* add attributes above here, update the policy in netlink.c */
 
 	/**
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 4d6e89e04aa0..3feb9435b715 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -54,6 +54,7 @@
 #include "hash.h"
 #include "log.h"
 #include "netlink.h"
+#include "send.h"
 #include "soft-interface.h"
 #include "translation-table.h"
 #include "tvlv.h"
@@ -979,6 +980,7 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
 {
 	int ret, tt_count, ip_count, unsnoop_count, total_count;
 	bool is_unsnoopable = false;
+	unsigned int mcast_fanout;
 	struct ethhdr *ethhdr;
 
 	ret = batadv_mcast_forw_mode_check(bat_priv, skb, &is_unsnoopable);
@@ -1013,8 +1015,203 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
 	case 0:
 		return BATADV_FORW_NONE;
 	default:
-		return BATADV_FORW_ALL;
+		mcast_fanout = atomic_read(&bat_priv->multicast_fanout);
+
+		if (!unsnoop_count && total_count <= mcast_fanout)
+			return BATADV_FORW_SOME;
+	}
+
+	return BATADV_FORW_ALL;
+}
+
+/**
+ * batadv_mcast_forw_tt() - forwards a packet to multicast listeners
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to transmit
+ * @vid: the vlan identifier
+ *
+ * Sends copies of a frame with multicast destination to any multicast
+ * listener registered in the translation table. A transmission is performed
+ * via a batman-adv unicast packet for each such destination node.
+ *
+ * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS
+ * otherwise.
+ */
+static int
+batadv_mcast_forw_tt(struct batadv_priv *bat_priv, struct sk_buff *skb,
+		     unsigned short vid)
+{
+	int ret = NET_XMIT_SUCCESS;
+	struct sk_buff *newskb;
+
+	struct batadv_tt_orig_list_entry *orig_entry;
+
+	struct batadv_tt_global_entry *tt_global;
+	const u8 *addr = eth_hdr(skb)->h_dest;
+
+	tt_global = batadv_tt_global_hash_find(bat_priv, addr, vid);
+	if (!tt_global)
+		goto out;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(orig_entry, &tt_global->orig_list, list) {
+		newskb = skb_copy(skb, GFP_ATOMIC);
+		if (!newskb) {
+			ret = NET_XMIT_DROP;
+			break;
+		}
+
+		batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0,
+					orig_entry->orig_node, vid);
+	}
+	rcu_read_unlock();
+
+	batadv_tt_global_entry_put(tt_global);
+
+out:
+	return ret;
+}
+
+/**
+ * batadv_mcast_forw_want_all_ipv4() - forward to nodes with want-all-ipv4
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to transmit
+ * @vid: the vlan identifier
+ *
+ * Sends copies of a frame with multicast destination to any node with a
+ * BATADV_MCAST_WANT_ALL_IPV4 flag set. A transmission is performed via a
+ * batman-adv unicast packet for each such destination node.
+ *
+ * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS
+ * otherwise.
+ */
+static int
+batadv_mcast_forw_want_all_ipv4(struct batadv_priv *bat_priv,
+				struct sk_buff *skb, unsigned short vid)
+{
+	struct batadv_orig_node *orig_node;
+	int ret = NET_XMIT_SUCCESS;
+	struct sk_buff *newskb;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(orig_node,
+				 &bat_priv->mcast.want_all_ipv4_list,
+				 mcast_want_all_ipv4_node) {
+		newskb = skb_copy(skb, GFP_ATOMIC);
+		if (!newskb) {
+			ret = NET_XMIT_DROP;
+			break;
+		}
+
+		batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0,
+					orig_node, vid);
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * batadv_mcast_forw_want_all_ipv6() - forward to nodes with want-all-ipv6
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: The multicast packet to transmit
+ * @vid: the vlan identifier
+ *
+ * Sends copies of a frame with multicast destination to any node with a
+ * BATADV_MCAST_WANT_ALL_IPV6 flag set. A transmission is performed via a
+ * batman-adv unicast packet for each such destination node.
+ *
+ * Return: NET_XMIT_DROP on memory allocation failure, NET_XMIT_SUCCESS
+ * otherwise.
+ */
+static int
+batadv_mcast_forw_want_all_ipv6(struct batadv_priv *bat_priv,
+				struct sk_buff *skb, unsigned short vid)
+{
+	struct batadv_orig_node *orig_node;
+	int ret = NET_XMIT_SUCCESS;
+	struct sk_buff *newskb;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(orig_node,
+				 &bat_priv->mcast.want_all_ipv6_list,
+				 mcast_want_all_ipv6_node) {
+		newskb = skb_copy(skb, GFP_ATOMIC);
+		if (!newskb) {
+			ret = NET_XMIT_DROP;
+			break;
+		}
+
+		batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0,
+					orig_node, vid);
 	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * batadv_mcast_forw_want_all() - forward packet to nodes in a want-all list
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to transmit
+ * @vid: the vlan identifier
+ *
+ * Sends copies of a frame with multicast destination to any node with a
+ * BATADV_MCAST_WANT_ALL_IPV4 or BATADV_MCAST_WANT_ALL_IPV6 flag set. A
+ * transmission is performed via a batman-adv unicast packet for each such
+ * destination node.
+ *
+ * Return: NET_XMIT_DROP on memory allocation failure or if the protocol family
+ * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise.
+ */
+static int
+batadv_mcast_forw_want_all(struct batadv_priv *bat_priv,
+			   struct sk_buff *skb, unsigned short vid)
+{
+	switch (ntohs(eth_hdr(skb)->h_proto)) {
+	case ETH_P_IP:
+		return batadv_mcast_forw_want_all_ipv4(bat_priv, skb, vid);
+	case ETH_P_IPV6:
+		return batadv_mcast_forw_want_all_ipv6(bat_priv, skb, vid);
+	default:
+		/* we shouldn't be here... */
+		return NET_XMIT_DROP;
+	}
+}
+
+/**
+ * batadv_mcast_forw_send() - send packet to any detected multicast recpient
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: the multicast packet to transmit
+ * @vid: the vlan identifier
+ *
+ * Sends copies of a frame with multicast destination to any node that signaled
+ * interest in it, that is either via the translation table or the according
+ * want-all flags. A transmission is performed via a batman-adv unicast packet
+ * for each such destination node.
+ *
+ * The given skb is consumed/freed.
+ *
+ * Return: NET_XMIT_DROP on memory allocation failure or if the protocol family
+ * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise.
+ */
+int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
+			   unsigned short vid)
+{
+	int ret;
+
+	ret = batadv_mcast_forw_tt(bat_priv, skb, vid);
+	if (ret != NET_XMIT_SUCCESS) {
+		kfree_skb(skb);
+		return ret;
+	}
+
+	ret = batadv_mcast_forw_want_all(bat_priv, skb, vid);
+	if (ret != NET_XMIT_SUCCESS) {
+		kfree_skb(skb);
+		return ret;
+	}
+
+	consume_skb(skb);
+	return ret;
 }
 
 /**
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index 34fb922a4566..653b9b76fabe 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -23,6 +23,13 @@ enum batadv_forw_mode {
 	 */
 	BATADV_FORW_ALL,
 
+	/**
+	 * @BATADV_FORW_SOME: forward the packet to some nodes (currently via
+	 *  a multicast-to-unicast conversion and the BATMAN unicast routing
+	 *  protocol)
+	 */
+	BATADV_FORW_SOME,
+
 	/**
 	 * @BATADV_FORW_SINGLE: forward the packet to a single node (currently
 	 *  via the BATMAN unicast routing protocol)
@@ -39,6 +46,9 @@ enum batadv_forw_mode
 batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		       struct batadv_orig_node **mcast_single_orig);
 
+int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
+			   unsigned short vid);
+
 void batadv_mcast_init(struct batadv_priv *bat_priv);
 
 int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset);
@@ -61,6 +71,14 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
 	return BATADV_FORW_ALL;
 }
 
+static inline int
+batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
+		       unsigned short vid)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+
 static inline int batadv_mcast_init(struct batadv_priv *bat_priv)
 {
 	return 0;
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 8e82e656b870..daf56933223d 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -145,6 +145,7 @@ static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = {
 	[BATADV_ATTR_HOP_PENALTY]		= { .type = NLA_U8 },
 	[BATADV_ATTR_LOG_LEVEL]			= { .type = NLA_U32 },
 	[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]	= { .type = NLA_U8 },
+	[BATADV_ATTR_MULTICAST_FANOUT]		= { .type = NLA_U32 },
 	[BATADV_ATTR_NETWORK_CODING_ENABLED]	= { .type = NLA_U8 },
 	[BATADV_ATTR_ORIG_INTERVAL]		= { .type = NLA_U32 },
 	[BATADV_ATTR_ELP_INTERVAL]		= { .type = NLA_U32 },
@@ -341,6 +342,10 @@ static int batadv_netlink_mesh_fill(struct sk_buff *msg,
 	if (nla_put_u8(msg, BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED,
 		       !atomic_read(&bat_priv->multicast_mode)))
 		goto nla_put_failure;
+
+	if (nla_put_u32(msg, BATADV_ATTR_MULTICAST_FANOUT,
+			atomic_read(&bat_priv->multicast_fanout)))
+		goto nla_put_failure;
 #endif /* CONFIG_BATMAN_ADV_MCAST */
 
 #ifdef CONFIG_BATMAN_ADV_NC
@@ -580,6 +585,12 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info)
 
 		atomic_set(&bat_priv->multicast_mode, !nla_get_u8(attr));
 	}
+
+	if (info->attrs[BATADV_ATTR_MULTICAST_FANOUT]) {
+		attr = info->attrs[BATADV_ATTR_MULTICAST_FANOUT];
+
+		atomic_set(&bat_priv->multicast_fanout, nla_get_u32(attr));
+	}
 #endif /* CONFIG_BATMAN_ADV_MCAST */
 
 #ifdef CONFIG_BATMAN_ADV_NC
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index f8fcdd6de656..a7677e1d000f 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -197,7 +197,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
 	unsigned short vid;
 	u32 seqno;
 	int gw_mode;
-	enum batadv_forw_mode forw_mode;
+	enum batadv_forw_mode forw_mode = BATADV_FORW_SINGLE;
 	struct batadv_orig_node *mcast_single_orig = NULL;
 	int network_offset = ETH_HLEN;
 	__be16 proto;
@@ -305,7 +305,8 @@ send:
 			if (forw_mode == BATADV_FORW_NONE)
 				goto dropped;
 
-			if (forw_mode == BATADV_FORW_SINGLE)
+			if (forw_mode == BATADV_FORW_SINGLE ||
+			    forw_mode == BATADV_FORW_SOME)
 				do_bcast = false;
 		}
 	}
@@ -365,6 +366,8 @@ send:
 			ret = batadv_send_skb_unicast(bat_priv, skb,
 						      BATADV_UNICAST, 0,
 						      mcast_single_orig, vid);
+		} else if (forw_mode == BATADV_FORW_SOME) {
+			ret = batadv_mcast_forw_send(bat_priv, skb, vid);
 		} else {
 			if (batadv_dat_snoop_outgoing_arp_request(bat_priv,
 								  skb))
@@ -806,6 +809,7 @@ static int batadv_softif_init_late(struct net_device *dev)
 	bat_priv->mcast.querier_ipv6.shadowing = false;
 	bat_priv->mcast.flags = BATADV_NO_FLAGS;
 	atomic_set(&bat_priv->multicast_mode, 1);
+	atomic_set(&bat_priv->multicast_fanout, 16);
 	atomic_set(&bat_priv->mcast.num_want_all_unsnoopables, 0);
 	atomic_set(&bat_priv->mcast.num_want_all_ipv4, 0);
 	atomic_set(&bat_priv->mcast.num_want_all_ipv6, 0);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 842e7634d20f..5d8bf8048e4e 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -193,7 +193,7 @@ batadv_tt_local_hash_find(struct batadv_priv *bat_priv, const u8 *addr,
  * Return: a pointer to the corresponding tt_global_entry struct if the client
  * is found, NULL otherwise.
  */
-static struct batadv_tt_global_entry *
+struct batadv_tt_global_entry *
 batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const u8 *addr,
 			   unsigned short vid)
 {
@@ -288,8 +288,7 @@ static void batadv_tt_global_entry_release(struct kref *ref)
  *  possibly release it
  * @tt_global_entry: tt_global_entry to be free'd
  */
-static void
-batadv_tt_global_entry_put(struct batadv_tt_global_entry *tt_global_entry)
+void batadv_tt_global_entry_put(struct batadv_tt_global_entry *tt_global_entry)
 {
 	kref_put(&tt_global_entry->common.refcount,
 		 batadv_tt_global_entry_release);
diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h
index a328979836b2..c8c48d62a430 100644
--- a/net/batman-adv/translation-table.h
+++ b/net/batman-adv/translation-table.h
@@ -29,6 +29,10 @@ int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb);
 void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
 			       struct batadv_orig_node *orig_node,
 			       s32 match_vid, const char *message);
+struct batadv_tt_global_entry *
+batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const u8 *addr,
+			   unsigned short vid);
+void batadv_tt_global_entry_put(struct batadv_tt_global_entry *tt_global_entry);
 int batadv_tt_global_hash_count(struct batadv_priv *bat_priv,
 				const u8 *addr, unsigned short vid);
 struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv,
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index e19fdb5c1281..357ca119329a 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1553,6 +1553,12 @@ struct batadv_priv {
 	 *  node's sender/originating side
 	 */
 	atomic_t multicast_mode;
+
+	/**
+	 * @multicast_fanout: Maximum number of packet copies to generate for a
+	 *  multicast-to-unicast conversion
+	 */
+	atomic_t multicast_fanout;
 #endif
 
 	/** @orig_interval: OGM broadcast interval in milliseconds */
-- 
cgit v1.2.3


From 1713cb37bf671e5d98919536941a8b56337874fd Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Wed, 27 Mar 2019 11:16:03 +0100
Subject: fou: Support binding FoU socket
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

An FoU socket is currently bound to the wildcard-address. While this
works fine, there are several use-cases where the use of the
wildcard-address is not desirable. For example, I use FoU on some
multi-homed servers and would like to use FoU on only one of the
interfaces.

This commit adds support for binding FoU sockets to a given source
address/interface, as well as connecting the socket to a given
destination address/port. udp_tunnel already provides the required
infrastructure, so most of the code added is for exposing and setting
the different attributes (local address, peer address, etc.).

The lookups performed when we add, delete or get an FoU-socket has also
been updated to compare all the attributes a user can set. Since the
comparison now involves several elements, I have added a separate
comparison-function instead of open-coding.

In order to test the code and ensure that the new comparison code works
correctly, I started by creating a wildcard socket bound to port 1234 on
my machine. I then tried to create a non-wildcarded socket bound to the
same port, as well as fetching and deleting the socket (including source
address, peer address or interface index in the netlink request).  Both
the create, fetch and delete request failed. Deleting/fetching the
socket was only successful when my netlink request attributes matched
those used to create the socket.

I then repeated the tests, but with a socket bound to a local ip
address, a socket bound to a local address + interface, and a bound
socket that was also «connected» to a peer. Add only worked when no
socket with the matching source address/interface (or wildcard) existed,
while fetch/delete was only successful when all attributes matched.

In addition to testing that the new code work, I also checked that the
current behavior is kept. If none of the new attributes are provided,
then an FoU-socket is configured as before (i.e., wildcarded).  If any
of the new attributes are provided, the FoU-socket is configured as
expected.

v1->v2:
* Fixed building with IPv6 disabled (kbuild).
* Fixed a return type warning and make the ugly comparison function more
readable (kbuild).
* Describe more in detail what has been tested (thanks David Miller).
* Make peer port required if peer address is specified.

Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/fou.h |   6 +++
 net/ipv4/fou.c           | 138 +++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 128 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h
index f2ea833a2812..87c2c9f08803 100644
--- a/include/uapi/linux/fou.h
+++ b/include/uapi/linux/fou.h
@@ -16,6 +16,12 @@ enum {
 	FOU_ATTR_IPPROTO,			/* u8 */
 	FOU_ATTR_TYPE,				/* u8 */
 	FOU_ATTR_REMCSUM_NOPARTIAL,		/* flag */
+	FOU_ATTR_LOCAL_V4,			/* u32 */
+	FOU_ATTR_LOCAL_V6,			/* in6_addr */
+	FOU_ATTR_PEER_V4,			/* u32 */
+	FOU_ATTR_PEER_V6,			/* in6_addr */
+	FOU_ATTR_PEER_PORT,			/* u16 */
+	FOU_ATTR_IFINDEX,			/* s32 */
 
 	__FOU_ATTR_MAX,
 };
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index a23fbb52d265..100e63f57ea6 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -499,15 +499,45 @@ out_unlock:
 	return err;
 }
 
-static int fou_add_to_port_list(struct net *net, struct fou *fou)
+static bool fou_cfg_cmp(struct fou *fou, struct fou_cfg *cfg)
+{
+	struct sock *sk = fou->sock->sk;
+	struct udp_port_cfg *udp_cfg = &cfg->udp_config;
+
+	if (fou->family != udp_cfg->family ||
+	    fou->port != udp_cfg->local_udp_port ||
+	    sk->sk_dport != udp_cfg->peer_udp_port ||
+	    sk->sk_bound_dev_if != udp_cfg->bind_ifindex)
+		return false;
+
+	if (fou->family == AF_INET) {
+		if (sk->sk_rcv_saddr != udp_cfg->local_ip.s_addr ||
+		    sk->sk_daddr != udp_cfg->peer_ip.s_addr)
+			return false;
+		else
+			return true;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		if (ipv6_addr_cmp(&sk->sk_v6_rcv_saddr, &udp_cfg->local_ip6) ||
+		    ipv6_addr_cmp(&sk->sk_v6_daddr, &udp_cfg->peer_ip6))
+			return false;
+		else
+			return true;
+#endif
+	}
+
+	return false;
+}
+
+static int fou_add_to_port_list(struct net *net, struct fou *fou,
+				struct fou_cfg *cfg)
 {
 	struct fou_net *fn = net_generic(net, fou_net_id);
 	struct fou *fout;
 
 	mutex_lock(&fn->fou_lock);
 	list_for_each_entry(fout, &fn->fou_list, list) {
-		if (fou->port == fout->port &&
-		    fou->family == fout->family) {
+		if (fou_cfg_cmp(fout, cfg)) {
 			mutex_unlock(&fn->fou_lock);
 			return -EALREADY;
 		}
@@ -585,7 +615,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 
 	sk->sk_allocation = GFP_ATOMIC;
 
-	err = fou_add_to_port_list(net, fou);
+	err = fou_add_to_port_list(net, fou, cfg);
 	if (err)
 		goto error;
 
@@ -605,14 +635,12 @@ error:
 static int fou_destroy(struct net *net, struct fou_cfg *cfg)
 {
 	struct fou_net *fn = net_generic(net, fou_net_id);
-	__be16 port = cfg->udp_config.local_udp_port;
-	u8 family = cfg->udp_config.family;
 	int err = -EINVAL;
 	struct fou *fou;
 
 	mutex_lock(&fn->fou_lock);
 	list_for_each_entry(fou, &fn->fou_list, list) {
-		if (fou->port == port && fou->family == family) {
+		if (fou_cfg_cmp(fou, cfg)) {
 			fou_release(fou);
 			err = 0;
 			break;
@@ -626,16 +654,27 @@ static int fou_destroy(struct net *net, struct fou_cfg *cfg)
 static struct genl_family fou_nl_family;
 
 static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
-	[FOU_ATTR_PORT] = { .type = NLA_U16, },
-	[FOU_ATTR_AF] = { .type = NLA_U8, },
-	[FOU_ATTR_IPPROTO] = { .type = NLA_U8, },
-	[FOU_ATTR_TYPE] = { .type = NLA_U8, },
-	[FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, },
+	[FOU_ATTR_PORT]			= { .type = NLA_U16, },
+	[FOU_ATTR_AF]			= { .type = NLA_U8, },
+	[FOU_ATTR_IPPROTO]		= { .type = NLA_U8, },
+	[FOU_ATTR_TYPE]			= { .type = NLA_U8, },
+	[FOU_ATTR_REMCSUM_NOPARTIAL]	= { .type = NLA_FLAG, },
+	[FOU_ATTR_LOCAL_V4]		= { .type = NLA_U32, },
+	[FOU_ATTR_PEER_V4]		= { .type = NLA_U32, },
+	[FOU_ATTR_LOCAL_V6]		= { .type = sizeof(struct in6_addr), },
+	[FOU_ATTR_PEER_V6]		= { .type = sizeof(struct in6_addr), },
+	[FOU_ATTR_PEER_PORT]		= { .type = NLA_U16, },
+	[FOU_ATTR_IFINDEX]		= { .type = NLA_S32, },
 };
 
 static int parse_nl_config(struct genl_info *info,
 			   struct fou_cfg *cfg)
 {
+	bool has_local = false, has_peer = false;
+	struct nlattr *attr;
+	int ifindex;
+	__be16 port;
+
 	memset(cfg, 0, sizeof(*cfg));
 
 	cfg->udp_config.family = AF_INET;
@@ -657,8 +696,7 @@ static int parse_nl_config(struct genl_info *info,
 	}
 
 	if (info->attrs[FOU_ATTR_PORT]) {
-		__be16 port = nla_get_be16(info->attrs[FOU_ATTR_PORT]);
-
+		port = nla_get_be16(info->attrs[FOU_ATTR_PORT]);
 		cfg->udp_config.local_udp_port = port;
 	}
 
@@ -671,6 +709,52 @@ static int parse_nl_config(struct genl_info *info,
 	if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL])
 		cfg->flags |= FOU_F_REMCSUM_NOPARTIAL;
 
+	if (cfg->udp_config.family == AF_INET) {
+		if (info->attrs[FOU_ATTR_LOCAL_V4]) {
+			attr = info->attrs[FOU_ATTR_LOCAL_V4];
+			cfg->udp_config.local_ip.s_addr = nla_get_in_addr(attr);
+			has_local = true;
+		}
+
+		if (info->attrs[FOU_ATTR_PEER_V4]) {
+			attr = info->attrs[FOU_ATTR_PEER_V4];
+			cfg->udp_config.peer_ip.s_addr = nla_get_in_addr(attr);
+			has_peer = true;
+		}
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		if (info->attrs[FOU_ATTR_LOCAL_V6]) {
+			attr = info->attrs[FOU_ATTR_LOCAL_V6];
+			cfg->udp_config.local_ip6 = nla_get_in6_addr(attr);
+			has_local = true;
+		}
+
+		if (info->attrs[FOU_ATTR_PEER_V6]) {
+			attr = info->attrs[FOU_ATTR_PEER_V6];
+			cfg->udp_config.peer_ip6 = nla_get_in6_addr(attr);
+			has_peer = true;
+		}
+#endif
+	}
+
+	if (has_peer) {
+		if (info->attrs[FOU_ATTR_PEER_PORT]) {
+			port = nla_get_be16(info->attrs[FOU_ATTR_PEER_PORT]);
+			cfg->udp_config.peer_udp_port = port;
+		} else {
+			return -EINVAL;
+		}
+	}
+
+	if (info->attrs[FOU_ATTR_IFINDEX]) {
+		if (!has_local)
+			return -EINVAL;
+
+		ifindex = nla_get_s32(info->attrs[FOU_ATTR_IFINDEX]);
+
+		cfg->udp_config.bind_ifindex = ifindex;
+	}
+
 	return 0;
 }
 
@@ -702,15 +786,37 @@ static int fou_nl_cmd_rm_port(struct sk_buff *skb, struct genl_info *info)
 
 static int fou_fill_info(struct fou *fou, struct sk_buff *msg)
 {
+	struct sock *sk = fou->sock->sk;
+
 	if (nla_put_u8(msg, FOU_ATTR_AF, fou->sock->sk->sk_family) ||
 	    nla_put_be16(msg, FOU_ATTR_PORT, fou->port) ||
+	    nla_put_be16(msg, FOU_ATTR_PEER_PORT, sk->sk_dport) ||
 	    nla_put_u8(msg, FOU_ATTR_IPPROTO, fou->protocol) ||
-	    nla_put_u8(msg, FOU_ATTR_TYPE, fou->type))
+	    nla_put_u8(msg, FOU_ATTR_TYPE, fou->type) ||
+	    nla_put_s32(msg, FOU_ATTR_IFINDEX, sk->sk_bound_dev_if))
 		return -1;
 
 	if (fou->flags & FOU_F_REMCSUM_NOPARTIAL)
 		if (nla_put_flag(msg, FOU_ATTR_REMCSUM_NOPARTIAL))
 			return -1;
+
+	if (fou->sock->sk->sk_family == AF_INET) {
+		if (nla_put_in_addr(msg, FOU_ATTR_LOCAL_V4, sk->sk_rcv_saddr))
+			return -1;
+
+		if (nla_put_in_addr(msg, FOU_ATTR_PEER_V4, sk->sk_daddr))
+			return -1;
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		if (nla_put_in6_addr(msg, FOU_ATTR_LOCAL_V6,
+				     &sk->sk_v6_rcv_saddr))
+			return -1;
+
+		if (nla_put_in6_addr(msg, FOU_ATTR_PEER_V6, &sk->sk_v6_daddr))
+			return -1;
+#endif
+	}
+
 	return 0;
 }
 
@@ -763,7 +869,7 @@ static int fou_nl_cmd_get_port(struct sk_buff *skb, struct genl_info *info)
 	ret = -ESRCH;
 	mutex_lock(&fn->fou_lock);
 	list_for_each_entry(fout, &fn->fou_list, list) {
-		if (port == fout->port && family == fout->family) {
+		if (fou_cfg_cmp(fout, &cfg)) {
 			ret = fou_dump_info(fout, info->snd_portid,
 					    info->snd_seq, 0, msg,
 					    info->genlhdr->cmd);
-- 
cgit v1.2.3


From 3aeb0803f7ea11ff2fc478f7d58f2b8e713af380 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 25 Mar 2019 19:34:58 +0100
Subject: ethtool: add PHY Fast Link Down support

This adds support for Fast Link Down as new PHY tunable.
Fast Link Down reduces the time until a link down event is reported
for 1000BaseT. According to the standard it's 750ms what is too long
for several use cases.

v2:
- add comment describing the constants

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ethtool.h | 8 ++++++++
 net/core/ethtool.c           | 2 ++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 3652b239dad1..50c76f4fa402 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -252,9 +252,17 @@ struct ethtool_tunable {
 #define DOWNSHIFT_DEV_DEFAULT_COUNT	0xff
 #define DOWNSHIFT_DEV_DISABLE		0
 
+/* Time in msecs after which link is reported as down
+ * 0 = lowest time supported by the PHY
+ * 0xff = off, link down detection according to standard
+ */
+#define ETHTOOL_PHY_FAST_LINK_DOWN_ON	0
+#define ETHTOOL_PHY_FAST_LINK_DOWN_OFF	0xff
+
 enum phy_tunable_id {
 	ETHTOOL_PHY_ID_UNSPEC,
 	ETHTOOL_PHY_DOWNSHIFT,
+	ETHTOOL_PHY_FAST_LINK_DOWN,
 	/*
 	 * Add your fresh new phy tunable attribute above and remember to update
 	 * phy_tunable_strings[] in net/core/ethtool.c
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index b1eb32419732..387d67eb75ab 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -136,6 +136,7 @@ static const char
 phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN] = {
 	[ETHTOOL_ID_UNSPEC]     = "Unspec",
 	[ETHTOOL_PHY_DOWNSHIFT]	= "phy-downshift",
+	[ETHTOOL_PHY_FAST_LINK_DOWN] = "phy-fast-link-down",
 };
 
 static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
@@ -2432,6 +2433,7 @@ static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna)
 {
 	switch (tuna->id) {
 	case ETHTOOL_PHY_DOWNSHIFT:
+	case ETHTOOL_PHY_FAST_LINK_DOWN:
 		if (tuna->len != sizeof(u8) ||
 		    tuna->type_id != ETHTOOL_TUNABLE_U8)
 			return -EINVAL;
-- 
cgit v1.2.3


From 4d5ec89fc8d14dcdab7214a0c13a1c7321dc6ea9 Mon Sep 17 00:00:00 2001
From: Numan Siddique <nusiddiq@redhat.com>
Date: Tue, 26 Mar 2019 06:13:46 +0530
Subject: net: openvswitch: Add a new action check_pkt_len

This patch adds a new action - 'check_pkt_len' which checks the
packet length and executes a set of actions if the packet
length is greater than the specified length or executes
another set of actions if the packet length is lesser or equal to.

This action takes below nlattrs
  * OVS_CHECK_PKT_LEN_ATTR_PKT_LEN - 'pkt_len' to check for

  * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER - Nested actions
    to apply if the packet length is greater than the specified 'pkt_len'

  * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL - Nested
    actions to apply if the packet length is lesser or equal to the
    specified 'pkt_len'.

The main use case for adding this action is to solve the packet
drops because of MTU mismatch in OVN virtual networking solution.
When a VM (which belongs to a logical switch of OVN) sends a packet
destined to go via the gateway router and if the nic which provides
external connectivity, has a lesser MTU, OVS drops the packet
if the packet length is greater than this MTU.

With the help of this action, OVN will check the packet length
and if it is greater than the MTU size, it will generate an
ICMP packet (type 3, code 4) and includes the next hop mtu in it
so that the sender can fragment the packets.

Reported-at:
https://mail.openvswitch.org/pipermail/ovs-discuss/2018-July/047039.html
Suggested-by: Ben Pfaff <blp@ovn.org>
Signed-off-by: Numan Siddique <nusiddiq@redhat.com>
CC: Gregory Rose <gvrose8192@gmail.com>
CC: Pravin B Shelar <pshelar@ovn.org>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Tested-by: Greg Rose <gvrose8192@gmail.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/openvswitch.h |  42 ++++++++++
 net/openvswitch/actions.c        |  48 +++++++++++
 net/openvswitch/flow_netlink.c   | 171 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 261 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index dbe0cbe4f1b7..dfabacee6903 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -798,6 +798,44 @@ struct ovs_action_push_eth {
 	struct ovs_key_ethernet addresses;
 };
 
+/*
+ * enum ovs_check_pkt_len_attr - Attributes for %OVS_ACTION_ATTR_CHECK_PKT_LEN.
+ *
+ * @OVS_CHECK_PKT_LEN_ATTR_PKT_LEN: u16 Packet length to check for.
+ * @OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER: Nested OVS_ACTION_ATTR_*
+ * actions to apply if the packer length is greater than the specified
+ * length in the attr - OVS_CHECK_PKT_LEN_ATTR_PKT_LEN.
+ * @OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL - Nested OVS_ACTION_ATTR_*
+ * actions to apply if the packer length is lesser or equal to the specified
+ * length in the attr - OVS_CHECK_PKT_LEN_ATTR_PKT_LEN.
+ */
+enum ovs_check_pkt_len_attr {
+	OVS_CHECK_PKT_LEN_ATTR_UNSPEC,
+	OVS_CHECK_PKT_LEN_ATTR_PKT_LEN,
+	OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER,
+	OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL,
+	__OVS_CHECK_PKT_LEN_ATTR_MAX,
+
+#ifdef __KERNEL__
+	OVS_CHECK_PKT_LEN_ATTR_ARG          /* struct check_pkt_len_arg  */
+#endif
+};
+
+#define OVS_CHECK_PKT_LEN_ATTR_MAX (__OVS_CHECK_PKT_LEN_ATTR_MAX - 1)
+
+#ifdef __KERNEL__
+struct check_pkt_len_arg {
+	u16 pkt_len;	/* Same value as OVS_CHECK_PKT_LEN_ATTR_PKT_LEN'. */
+	bool exec_for_greater;	/* When true, actions in IF_GREATER will
+				 * not change flow keys. False otherwise.
+				 */
+	bool exec_for_lesser_equal; /* When true, actions in IF_LESS_EQUAL
+				     * will not change flow keys. False
+				     * otherwise.
+				     */
+};
+#endif
+
 /**
  * enum ovs_action_attr - Action types.
  *
@@ -842,6 +880,9 @@ struct ovs_action_push_eth {
  * packet, or modify the packet (e.g., change the DSCP field).
  * @OVS_ACTION_ATTR_CLONE: make a copy of the packet and execute a list of
  * actions without affecting the original packet and key.
+ * @OVS_ACTION_ATTR_CHECK_PKT_LEN: Check the packet length and execute a set
+ * of actions if greater than the specified packet length, else execute
+ * another set of actions.
  *
  * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
  * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
@@ -876,6 +917,7 @@ enum ovs_action_attr {
 	OVS_ACTION_ATTR_POP_NSH,      /* No argument. */
 	OVS_ACTION_ATTR_METER,        /* u32 meter ID. */
 	OVS_ACTION_ATTR_CLONE,        /* Nested OVS_CLONE_ATTR_*.  */
+	OVS_ACTION_ATTR_CHECK_PKT_LEN, /* Nested OVS_CHECK_PKT_LEN_ATTR_*. */
 
 	__OVS_ACTION_ATTR_MAX,	      /* Nothing past this will be accepted
 				       * from userspace. */
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index e47ebbbe71b8..2c151bb322c1 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -169,6 +169,10 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 			 const struct nlattr *actions, int len,
 			 bool last, bool clone_flow_key);
 
+static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			      struct sw_flow_key *key,
+			      const struct nlattr *attr, int len);
+
 static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
 			     __be16 ethertype)
 {
@@ -1213,6 +1217,40 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
 	return clone_execute(dp, skb, key, recirc_id, NULL, 0, last, true);
 }
 
+static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
+				 struct sw_flow_key *key,
+				 const struct nlattr *attr, bool last)
+{
+	const struct nlattr *actions, *cpl_arg;
+	const struct check_pkt_len_arg *arg;
+	int rem = nla_len(attr);
+	bool clone_flow_key;
+
+	/* The first netlink attribute in 'attr' is always
+	 * 'OVS_CHECK_PKT_LEN_ATTR_ARG'.
+	 */
+	cpl_arg = nla_data(attr);
+	arg = nla_data(cpl_arg);
+
+	if (skb->len <= arg->pkt_len) {
+		/* Second netlink attribute in 'attr' is always
+		 * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
+		 */
+		actions = nla_next(cpl_arg, &rem);
+		clone_flow_key = !arg->exec_for_lesser_equal;
+	} else {
+		/* Third netlink attribute in 'attr' is always
+		 * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER'.
+		 */
+		actions = nla_next(cpl_arg, &rem);
+		actions = nla_next(actions, &rem);
+		clone_flow_key = !arg->exec_for_greater;
+	}
+
+	return clone_execute(dp, skb, key, 0, nla_data(actions),
+			     nla_len(actions), last, clone_flow_key);
+}
+
 /* Execute a list of actions against 'skb'. */
 static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			      struct sw_flow_key *key,
@@ -1374,6 +1412,16 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 			break;
 		}
+
+		case OVS_ACTION_ATTR_CHECK_PKT_LEN: {
+			bool last = nla_is_last(a, rem);
+
+			err = execute_check_pkt_len(dp, skb, key, a, last);
+			if (last)
+				return err;
+
+			break;
+		}
 		}
 
 		if (unlikely(err)) {
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 691da853bef5..b7543700db87 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -91,6 +91,7 @@ static bool actions_may_change_flow(const struct nlattr *actions)
 		case OVS_ACTION_ATTR_SET:
 		case OVS_ACTION_ATTR_SET_MASKED:
 		case OVS_ACTION_ATTR_METER:
+		case OVS_ACTION_ATTR_CHECK_PKT_LEN:
 		default:
 			return true;
 		}
@@ -2838,6 +2839,87 @@ static int validate_userspace(const struct nlattr *attr)
 	return 0;
 }
 
+static const struct nla_policy cpl_policy[OVS_CHECK_PKT_LEN_ATTR_MAX + 1] = {
+	[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN] = {.type = NLA_U16 },
+	[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER] = {.type = NLA_NESTED },
+	[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL] = {.type = NLA_NESTED },
+};
+
+static int validate_and_copy_check_pkt_len(struct net *net,
+					   const struct nlattr *attr,
+					   const struct sw_flow_key *key,
+					   struct sw_flow_actions **sfa,
+					   __be16 eth_type, __be16 vlan_tci,
+					   bool log, bool last)
+{
+	const struct nlattr *acts_if_greater, *acts_if_lesser_eq;
+	struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1];
+	struct check_pkt_len_arg arg;
+	int nested_acts_start;
+	int start, err;
+
+	err = nla_parse_strict(a, OVS_CHECK_PKT_LEN_ATTR_MAX, nla_data(attr),
+			       nla_len(attr), cpl_policy, NULL);
+	if (err)
+		return err;
+
+	if (!a[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN] ||
+	    !nla_get_u16(a[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN]))
+		return -EINVAL;
+
+	acts_if_lesser_eq = a[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL];
+	acts_if_greater = a[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER];
+
+	/* Both the nested action should be present. */
+	if (!acts_if_greater || !acts_if_lesser_eq)
+		return -EINVAL;
+
+	/* validation done, copy the nested actions. */
+	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_CHECK_PKT_LEN,
+					log);
+	if (start < 0)
+		return start;
+
+	arg.pkt_len = nla_get_u16(a[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN]);
+	arg.exec_for_lesser_equal =
+		last || !actions_may_change_flow(acts_if_lesser_eq);
+	arg.exec_for_greater =
+		last || !actions_may_change_flow(acts_if_greater);
+
+	err = ovs_nla_add_action(sfa, OVS_CHECK_PKT_LEN_ATTR_ARG, &arg,
+				 sizeof(arg), log);
+	if (err)
+		return err;
+
+	nested_acts_start = add_nested_action_start(sfa,
+		OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL, log);
+	if (nested_acts_start < 0)
+		return nested_acts_start;
+
+	err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa,
+				     eth_type, vlan_tci, log);
+
+	if (err)
+		return err;
+
+	add_nested_action_end(*sfa, nested_acts_start);
+
+	nested_acts_start = add_nested_action_start(sfa,
+		OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER, log);
+	if (nested_acts_start < 0)
+		return nested_acts_start;
+
+	err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa,
+				     eth_type, vlan_tci, log);
+
+	if (err)
+		return err;
+
+	add_nested_action_end(*sfa, nested_acts_start);
+	add_nested_action_end(*sfa, start);
+	return 0;
+}
+
 static int copy_action(const struct nlattr *from,
 		       struct sw_flow_actions **sfa, bool log)
 {
@@ -2884,6 +2966,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			[OVS_ACTION_ATTR_POP_NSH] = 0,
 			[OVS_ACTION_ATTR_METER] = sizeof(u32),
 			[OVS_ACTION_ATTR_CLONE] = (u32)-1,
+			[OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1,
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
@@ -3085,6 +3168,19 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			break;
 		}
 
+		case OVS_ACTION_ATTR_CHECK_PKT_LEN: {
+			bool last = nla_is_last(a, rem);
+
+			err = validate_and_copy_check_pkt_len(net, a, key, sfa,
+							      eth_type,
+							      vlan_tci, log,
+							      last);
+			if (err)
+				return err;
+			skip_copy = true;
+			break;
+		}
+
 		default:
 			OVS_NLERR(log, "Unknown Action type %d", type);
 			return -EINVAL;
@@ -3183,6 +3279,75 @@ static int clone_action_to_attr(const struct nlattr *attr,
 	return err;
 }
 
+static int check_pkt_len_action_to_attr(const struct nlattr *attr,
+					struct sk_buff *skb)
+{
+	struct nlattr *start, *ac_start = NULL;
+	const struct check_pkt_len_arg *arg;
+	const struct nlattr *a, *cpl_arg;
+	int err = 0, rem = nla_len(attr);
+
+	start = nla_nest_start(skb, OVS_ACTION_ATTR_CHECK_PKT_LEN);
+	if (!start)
+		return -EMSGSIZE;
+
+	/* The first nested attribute in 'attr' is always
+	 * 'OVS_CHECK_PKT_LEN_ATTR_ARG'.
+	 */
+	cpl_arg = nla_data(attr);
+	arg = nla_data(cpl_arg);
+
+	if (nla_put_u16(skb, OVS_CHECK_PKT_LEN_ATTR_PKT_LEN, arg->pkt_len)) {
+		err = -EMSGSIZE;
+		goto out;
+	}
+
+	/* Second nested attribute in 'attr' is always
+	 * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
+	 */
+	a = nla_next(cpl_arg, &rem);
+	ac_start =  nla_nest_start(skb,
+		OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL);
+	if (!ac_start) {
+		err = -EMSGSIZE;
+		goto out;
+	}
+
+	err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
+	if (err) {
+		nla_nest_cancel(skb, ac_start);
+		goto out;
+	} else {
+		nla_nest_end(skb, ac_start);
+	}
+
+	/* Third nested attribute in 'attr' is always
+	 * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER.
+	 */
+	a = nla_next(a, &rem);
+	ac_start =  nla_nest_start(skb,
+				   OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER);
+	if (!ac_start) {
+		err = -EMSGSIZE;
+		goto out;
+	}
+
+	err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
+	if (err) {
+		nla_nest_cancel(skb, ac_start);
+		goto out;
+	} else {
+		nla_nest_end(skb, ac_start);
+	}
+
+	nla_nest_end(skb, start);
+	return 0;
+
+out:
+	nla_nest_cancel(skb, start);
+	return err;
+}
+
 static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 {
 	const struct nlattr *ovs_key = nla_data(a);
@@ -3277,6 +3442,12 @@ int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb)
 				return err;
 			break;
 
+		case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+			err = check_pkt_len_action_to_attr(a, skb);
+			if (err)
+				return err;
+			break;
+
 		default:
 			if (nla_put(skb, type, nla_len(a), nla_data(a)))
 				return -EMSGSIZE;
-- 
cgit v1.2.3


From 4f661542a40217713f2cee0bb6678fbb30d9d367 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 26 Mar 2019 08:34:55 -0700
Subject: tcp: fix zerocopy and notsent_lowat issues
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

My recent patch had at least three problems :

1) TX zerocopy wants notification when skb is acknowledged,
   thus we need to call skb_zcopy_clear() if the skb is
   cached into sk->sk_tx_skb_cache

2) Some applications might expect precise EPOLLOUT
   notifications, so we need to update sk->sk_wmem_queued
   and call sk_mem_uncharge() from sk_wmem_free_skb()
   in all cases. The SOCK_QUEUE_SHRUNK flag must also be set.

3) Reuse of saved skb should have used skb_cloned() instead
  of simply checking if the fast clone has been freed.

Fixes: 472c2e07eef0 ("tcp: add one skb cache for tx")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h |  7 ++++---
 net/ipv4/tcp.c     | 13 +++----------
 2 files changed, 7 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 577d91fb5626..7fa223278522 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1465,13 +1465,14 @@ static inline void sk_mem_uncharge(struct sock *sk, int size)
 
 static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
 {
+	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+	sk->sk_wmem_queued -= skb->truesize;
+	sk_mem_uncharge(sk, skb->truesize);
 	if (!sk->sk_tx_skb_cache) {
+		skb_zcopy_clear(skb, true);
 		sk->sk_tx_skb_cache = skb;
 		return;
 	}
-	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
-	sk->sk_wmem_queued -= skb->truesize;
-	sk_mem_uncharge(sk, skb->truesize);
 	__kfree_skb(skb);
 }
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 29b94edf05f9..82bd707c0347 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -865,14 +865,9 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
 {
 	struct sk_buff *skb;
 
-	skb = sk->sk_tx_skb_cache;
-	if (skb && !size) {
-		const struct sk_buff_fclones *fclones;
-
-		fclones = container_of(skb, struct sk_buff_fclones, skb1);
-		if (refcount_read(&fclones->fclone_ref) == 1) {
-			sk->sk_wmem_queued -= skb->truesize;
-			sk_mem_uncharge(sk, skb->truesize);
+	if (likely(!size)) {
+		skb = sk->sk_tx_skb_cache;
+		if (skb && !skb_cloned(skb)) {
 			skb->truesize -= skb->data_len;
 			sk->sk_tx_skb_cache = NULL;
 			pskb_trim(skb, 0);
@@ -2543,8 +2538,6 @@ void tcp_write_queue_purge(struct sock *sk)
 	tcp_rtx_queue_purge(sk);
 	skb = sk->sk_tx_skb_cache;
 	if (skb) {
-		sk->sk_wmem_queued -= skb->truesize;
-		sk_mem_uncharge(sk, skb->truesize);
 		__kfree_skb(skb);
 		sk->sk_tx_skb_cache = NULL;
 	}
-- 
cgit v1.2.3


From df453700e8d81b1bdafdf684365ee2b9431fb702 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 27 Mar 2019 12:40:33 -0700
Subject: inet: switch IP ID generator to siphash

According to Amit Klein and Benny Pinkas, IP ID generation is too weak
and might be used by attackers.

Even with recent net_hash_mix() fix (netns: provide pure entropy for net_hash_mix())
having 64bit key and Jenkins hash is risky.

It is time to switch to siphash and its 128bit keys.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Amit Klein <aksecurity@gmail.com>
Reported-by: Benny Pinkas <benny@pinkas.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/siphash.h  |  5 +++++
 include/net/netns/ipv4.h |  2 ++
 net/ipv4/route.c         | 12 +++++++-----
 net/ipv6/output_core.c   | 30 ++++++++++++++++--------------
 4 files changed, 30 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/siphash.h b/include/linux/siphash.h
index fa7a6b9cedbf..bf21591a9e5e 100644
--- a/include/linux/siphash.h
+++ b/include/linux/siphash.h
@@ -21,6 +21,11 @@ typedef struct {
 	u64 key[2];
 } siphash_key_t;
 
+static inline bool siphash_key_is_zero(const siphash_key_t *key)
+{
+	return !(key->key[0] | key->key[1]);
+}
+
 u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key);
 #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key);
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 104a6669e344..7698460a3dd1 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -9,6 +9,7 @@
 #include <linux/uidgid.h>
 #include <net/inet_frag.h>
 #include <linux/rcupdate.h>
+#include <linux/siphash.h>
 
 struct tcpm_hash_bucket;
 struct ctl_table_header;
@@ -217,5 +218,6 @@ struct netns_ipv4 {
 	unsigned int	ipmr_seq;	/* protected by rtnl_mutex */
 
 	atomic_t	rt_genid;
+	siphash_key_t	ip_id_key;
 };
 #endif
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 14c7fdacaa72..f2688fce39e1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -500,15 +500,17 @@ EXPORT_SYMBOL(ip_idents_reserve);
 
 void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
 {
-	static u32 ip_idents_hashrnd __read_mostly;
 	u32 hash, id;
 
-	net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));
+	/* Note the following code is not safe, but this is okay. */
+	if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key)))
+		get_random_bytes(&net->ipv4.ip_id_key,
+				 sizeof(net->ipv4.ip_id_key));
 
-	hash = jhash_3words((__force u32)iph->daddr,
+	hash = siphash_3u32((__force u32)iph->daddr,
 			    (__force u32)iph->saddr,
-			    iph->protocol ^ net_hash_mix(net),
-			    ip_idents_hashrnd);
+			    iph->protocol,
+			    &net->ipv4.ip_id_key);
 	id = ip_idents_reserve(hash, segs);
 	iph->id = htons(id);
 }
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 4fe7c90962dd..868ae23dbae1 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -10,15 +10,25 @@
 #include <net/secure_seq.h>
 #include <linux/netfilter.h>
 
-static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
+static u32 __ipv6_select_ident(struct net *net,
 			       const struct in6_addr *dst,
 			       const struct in6_addr *src)
 {
+	const struct {
+		struct in6_addr dst;
+		struct in6_addr src;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.dst = *dst,
+		.src = *src,
+	};
 	u32 hash, id;
 
-	hash = __ipv6_addr_jhash(dst, hashrnd);
-	hash = __ipv6_addr_jhash(src, hash);
-	hash ^= net_hash_mix(net);
+	/* Note the following code is not safe, but this is okay. */
+	if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key)))
+		get_random_bytes(&net->ipv4.ip_id_key,
+				 sizeof(net->ipv4.ip_id_key));
+
+	hash = siphash(&combined, sizeof(combined), &net->ipv4.ip_id_key);
 
 	/* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve,
 	 * set the hight order instead thus minimizing possible future
@@ -41,7 +51,6 @@ static u32 __ipv6_select_ident(struct net *net, u32 hashrnd,
  */
 __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
 {
-	static u32 ip6_proxy_idents_hashrnd __read_mostly;
 	struct in6_addr buf[2];
 	struct in6_addr *addrs;
 	u32 id;
@@ -53,11 +62,7 @@ __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb)
 	if (!addrs)
 		return 0;
 
-	net_get_random_once(&ip6_proxy_idents_hashrnd,
-			    sizeof(ip6_proxy_idents_hashrnd));
-
-	id = __ipv6_select_ident(net, ip6_proxy_idents_hashrnd,
-				 &addrs[1], &addrs[0]);
+	id = __ipv6_select_ident(net, &addrs[1], &addrs[0]);
 	return htonl(id);
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
@@ -66,12 +71,9 @@ __be32 ipv6_select_ident(struct net *net,
 			 const struct in6_addr *daddr,
 			 const struct in6_addr *saddr)
 {
-	static u32 ip6_idents_hashrnd __read_mostly;
 	u32 id;
 
-	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
-
-	id = __ipv6_select_ident(net, ip6_idents_hashrnd, daddr, saddr);
+	id = __ipv6_select_ident(net, daddr, saddr);
 	return htonl(id);
 }
 EXPORT_SYMBOL(ipv6_select_ident);
-- 
cgit v1.2.3


From 5dc37bb9b03586e8fdeb47d25e8d2a0399984936 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 28 Mar 2019 13:56:36 +0100
Subject: net: replace ndo_get_devlink with ndo_get_devlink_port

Follow-up patch is going to need a devlink port instance according to
a netdev. Devlink port instance should be always available when devlink
is used. So change the recently introduced ndo_get_devlink to
ndo_get_devlink_port. With that, adjust the wrapper for the only
user to get devlink pointer.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Michal Kubecek <mkubecek@suse.cz>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_app.h        |  2 +-
 drivers/net/ethernet/netronome/nfp/nfp_devlink.c    | 10 +++++-----
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c |  2 +-
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c   |  2 +-
 include/linux/netdevice.h                           |  6 +++---
 include/net/devlink.h                               | 14 ++++++++++++--
 6 files changed, 23 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index f8d422713705..a6fda07fce43 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -433,6 +433,6 @@ int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn,
 int nfp_app_nic_vnic_init_phy_port(struct nfp_pf *pf, struct nfp_app *app,
 				   struct nfp_net *nn, unsigned int id);
 
-struct devlink *nfp_devlink_get_devlink(struct net_device *netdev);
+struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev);
 
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index cb59a18ec6a6..919da0d84fb4 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -386,13 +386,13 @@ void nfp_devlink_port_type_clear(struct nfp_port *port)
 	devlink_port_type_clear(&port->dl_port);
 }
 
-struct devlink *nfp_devlink_get_devlink(struct net_device *netdev)
+struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev)
 {
-	struct nfp_app *app;
+	struct nfp_port *port;
 
-	app = nfp_app_from_netdev(netdev);
-	if (!app)
+	port = nfp_port_from_netdev(netdev);
+	if (!port)
 		return NULL;
 
-	return priv_to_devlink(app->pf);
+	return &port->dl_port;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index ad2f133bd545..b676943e54f4 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3531,7 +3531,7 @@ const struct net_device_ops nfp_net_netdev_ops = {
 	.ndo_udp_tunnel_del	= nfp_net_del_vxlan_port,
 	.ndo_bpf		= nfp_net_xdp,
 	.ndo_get_port_parent_id	= nfp_port_get_port_parent_id,
-	.ndo_get_devlink	= nfp_devlink_get_devlink,
+	.ndo_get_devlink_port	= nfp_devlink_get_devlink_port,
 };
 
 /**
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index d2c803bb4e56..bf621674f583 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -273,7 +273,7 @@ const struct net_device_ops nfp_repr_netdev_ops = {
 	.ndo_set_features	= nfp_port_set_features,
 	.ndo_set_mac_address    = eth_mac_addr,
 	.ndo_get_port_parent_id	= nfp_port_get_port_parent_id,
-	.ndo_get_devlink	= nfp_devlink_get_devlink,
+	.ndo_get_devlink_port	= nfp_devlink_get_devlink_port,
 };
 
 void
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 166fdc0a78b4..78f5ec4ebf64 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1250,8 +1250,8 @@ struct devlink;
  *	that got dropped are freed/returned via xdp_return_frame().
  *	Returns negative number, means general error invoking ndo, meaning
  *	no frames were xmit'ed and core-caller will free all frames.
- * struct devlink *(*ndo_get_devlink)(struct net_device *dev);
- *	Get devlink instance associated with a given netdev.
+ * struct devlink_port *(*ndo_get_devlink_port)(struct net_device *dev);
+ *	Get devlink port instance associated with a given netdev.
  *	Called with a reference on the netdevice and devlink locks only,
  *	rtnl_lock is not held.
  */
@@ -1451,7 +1451,7 @@ struct net_device_ops {
 						u32 flags);
 	int			(*ndo_xsk_async_xmit)(struct net_device *dev,
 						      u32 queue_id);
-	struct devlink *	(*ndo_get_devlink)(struct net_device *dev);
+	struct devlink_port *	(*ndo_get_devlink_port)(struct net_device *dev);
 };
 
 /**
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 03fb16f4fb6c..81b5ed04a341 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -547,10 +547,20 @@ static inline struct devlink *priv_to_devlink(void *priv)
 	return container_of(priv, struct devlink, priv);
 }
 
+static inline struct devlink_port *
+netdev_to_devlink_port(struct net_device *dev)
+{
+	if (dev->netdev_ops->ndo_get_devlink_port)
+		return dev->netdev_ops->ndo_get_devlink_port(dev);
+	return NULL;
+}
+
 static inline struct devlink *netdev_to_devlink(struct net_device *dev)
 {
-	if (dev->netdev_ops->ndo_get_devlink)
-		return dev->netdev_ops->ndo_get_devlink(dev);
+	struct devlink_port *devlink_port = netdev_to_devlink_port(dev);
+
+	if (devlink_port)
+		return devlink_port->devlink;
 	return NULL;
 }
 
-- 
cgit v1.2.3


From af3836df9a59e7339d60c9c46729a7d9094d0582 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 28 Mar 2019 13:56:37 +0100
Subject: net: devlink: introduce devlink_compat_phys_port_name_get()

Introduce devlink_compat_phys_port_name_get() helper that
gets the physical port name for specified netdevice
according to devlink port attributes.
Call this helper from dev_get_phys_port_name()
in case ndo_get_phys_port_name is not defined.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h |  9 +++++++++
 net/core/dev.c        | 11 ++++++++---
 net/core/devlink.c    | 28 ++++++++++++++++++++++++++--
 3 files changed, 43 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 81b5ed04a341..85e577d6ec3b 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -739,6 +739,8 @@ devlink_health_reporter_state_update(struct devlink_health_reporter *reporter,
 void devlink_compat_running_version(struct net_device *dev,
 				    char *buf, size_t len);
 int devlink_compat_flash_update(struct net_device *dev, const char *file_name);
+int devlink_compat_phys_port_name_get(struct net_device *dev,
+				      char *name, size_t len);
 
 #else
 
@@ -753,6 +755,13 @@ devlink_compat_flash_update(struct net_device *dev, const char *file_name)
 	return -EOPNOTSUPP;
 }
 
+static inline int
+devlink_compat_phys_port_name_get(struct net_device *dev,
+				  char *name, size_t len)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/net/core/dev.c b/net/core/dev.c
index 9ca2d3abfd1a..9823b7713f79 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -146,6 +146,7 @@
 #include <net/udp_tunnel.h>
 #include <linux/net_namespace.h>
 #include <linux/indirect_call_wrapper.h>
+#include <net/devlink.h>
 
 #include "net-sysfs.h"
 
@@ -7877,10 +7878,14 @@ int dev_get_phys_port_name(struct net_device *dev,
 			   char *name, size_t len)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int err;
 
-	if (!ops->ndo_get_phys_port_name)
-		return -EOPNOTSUPP;
-	return ops->ndo_get_phys_port_name(dev, name, len);
+	if (ops->ndo_get_phys_port_name) {
+		err = ops->ndo_get_phys_port_name(dev, name, len);
+		if (err != -EOPNOTSUPP)
+			return err;
+	}
+	return devlink_compat_phys_port_name_get(dev, name, len);
 }
 EXPORT_SYMBOL(dev_get_phys_port_name);
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 37d01c39071e..8bb2c3e3f202 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -5414,8 +5414,8 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
 
-int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
-				    char *name, size_t len)
+static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
+					     char *name, size_t len)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int n = 0;
@@ -5445,6 +5445,12 @@ int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
 
 	return 0;
 }
+
+int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
+				    char *name, size_t len)
+{
+	return __devlink_port_phys_port_name_get(devlink_port, name, len);
+}
 EXPORT_SYMBOL_GPL(devlink_port_get_phys_port_name);
 
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
@@ -6459,6 +6465,24 @@ out:
 	return ret;
 }
 
+int devlink_compat_phys_port_name_get(struct net_device *dev,
+				      char *name, size_t len)
+{
+	struct devlink_port *devlink_port;
+
+	/* RTNL mutex is held here which ensures that devlink_port
+	 * instance cannot disappear in the middle. No need to take
+	 * any devlink lock as only permanent values are accessed.
+	 */
+	ASSERT_RTNL();
+
+	devlink_port = netdev_to_devlink_port(dev);
+	if (!devlink_port)
+		return -EOPNOTSUPP;
+
+	return __devlink_port_phys_port_name_get(devlink_port, name, len);
+}
+
 static int __init devlink_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
-- 
cgit v1.2.3


From 14c03ac4c100e4b81ec4747f5ec861701ff52de2 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 28 Mar 2019 13:56:40 +0100
Subject: net: devlink: remove unused devlink_port_get_phys_port_name()
 function

Now it is unused, remove it.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 2 --
 net/core/devlink.c    | 7 -------
 2 files changed, 9 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 85e577d6ec3b..31d5cec4d06b 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -583,8 +583,6 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
 			    enum devlink_port_flavour flavour,
 			    u32 port_number, bool split,
 			    u32 split_subport_number);
-int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
-				    char *name, size_t len);
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u32 size, u16 ingress_pools_count,
 			u16 egress_pools_count, u16 ingress_tc_count,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 8bb2c3e3f202..6bbd07e3861e 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -5446,13 +5446,6 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 	return 0;
 }
 
-int devlink_port_get_phys_port_name(struct devlink_port *devlink_port,
-				    char *name, size_t len)
-{
-	return __devlink_port_phys_port_name_get(devlink_port, name, len);
-}
-EXPORT_SYMBOL_GPL(devlink_port_get_phys_port_name);
-
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u32 size, u16 ingress_pools_count,
 			u16 egress_pools_count, u16 ingress_tc_count,
-- 
cgit v1.2.3


From 717700d183d65bd2e6511566aa6d32395419d158 Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Tue, 26 Mar 2019 11:31:13 -0700
Subject: netfilter: Export nf_ct_{set,destroy}_timeout()

This patch exports nf_ct_set_timeout() and nf_ct_destroy_timeout().
The two functions are derived from xt_ct_destroy_timeout() and
xt_ct_set_timeout() in xt_CT.c, and moved to nf_conntrack_timeout.c
without any functional change.
It would be useful for other users (i.e. OVS) that utilizes the
finer-grain conntrack timeout feature.

CC: Pablo Neira Ayuso <pablo@netfilter.org>
CC: Pravin Shelar <pshelar@ovn.org>
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netfilter/nf_conntrack_timeout.h | 15 +++++
 net/netfilter/nf_conntrack_timeout.c         | 89 ++++++++++++++++++++++++++
 net/netfilter/xt_CT.c                        | 93 ++--------------------------
 3 files changed, 110 insertions(+), 87 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 3394d75e1c80..00a8fbb2d735 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -88,6 +88,9 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct)
 int nf_conntrack_timeout_init(void);
 void nf_conntrack_timeout_fini(void);
 void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout);
+int nf_ct_set_timeout(struct net *net, struct nf_conn *ct, u8 l3num, u8 l4num,
+		      const char *timeout_name);
+void nf_ct_destroy_timeout(struct nf_conn *ct);
 #else
 static inline int nf_conntrack_timeout_init(void)
 {
@@ -98,6 +101,18 @@ static inline void nf_conntrack_timeout_fini(void)
 {
         return;
 }
+
+static inline int nf_ct_set_timeout(struct net *net, struct nf_conn *ct,
+				    u8 l3num, u8 l4num,
+				    const char *timeout_name)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void nf_ct_destroy_timeout(struct nf_conn *ct)
+{
+	return;
+}
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
 
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c
index 91fbd183da2d..edac8ea4436d 100644
--- a/net/netfilter/nf_conntrack_timeout.c
+++ b/net/netfilter/nf_conntrack_timeout.c
@@ -48,6 +48,95 @@ void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout)
 }
 EXPORT_SYMBOL_GPL(nf_ct_untimeout);
 
+static void __nf_ct_timeout_put(struct nf_ct_timeout *timeout)
+{
+	typeof(nf_ct_timeout_put_hook) timeout_put;
+
+	timeout_put = rcu_dereference(nf_ct_timeout_put_hook);
+	if (timeout_put)
+		timeout_put(timeout);
+}
+
+int nf_ct_set_timeout(struct net *net, struct nf_conn *ct,
+		      u8 l3num, u8 l4num, const char *timeout_name)
+{
+	typeof(nf_ct_timeout_find_get_hook) timeout_find_get;
+	struct nf_ct_timeout *timeout;
+	struct nf_conn_timeout *timeout_ext;
+	const char *errmsg = NULL;
+	int ret = 0;
+
+	rcu_read_lock();
+	timeout_find_get = rcu_dereference(nf_ct_timeout_find_get_hook);
+	if (!timeout_find_get) {
+		ret = -ENOENT;
+		errmsg = "Timeout policy base is empty";
+		goto out;
+	}
+
+	timeout = timeout_find_get(net, timeout_name);
+	if (!timeout) {
+		ret = -ENOENT;
+		pr_info_ratelimited("No such timeout policy \"%s\"\n",
+				    timeout_name);
+		goto out;
+	}
+
+	if (timeout->l3num != l3num) {
+		ret = -EINVAL;
+		pr_info_ratelimited("Timeout policy `%s' can only be used by "
+				    "L%d protocol number %d\n",
+				    timeout_name, 3, timeout->l3num);
+		goto err_put_timeout;
+	}
+	/* Make sure the timeout policy matches any existing protocol tracker,
+	 * otherwise default to generic.
+	 */
+	if (timeout->l4proto->l4proto != l4num) {
+		ret = -EINVAL;
+		pr_info_ratelimited("Timeout policy `%s' can only be used by "
+				    "L%d protocol number %d\n",
+				    timeout_name, 4, timeout->l4proto->l4proto);
+		goto err_put_timeout;
+	}
+	timeout_ext = nf_ct_timeout_ext_add(ct, timeout, GFP_ATOMIC);
+	if (!timeout_ext) {
+		ret = -ENOMEM;
+		goto err_put_timeout;
+	}
+
+	rcu_read_unlock();
+	return ret;
+
+err_put_timeout:
+	__nf_ct_timeout_put(timeout);
+out:
+	rcu_read_unlock();
+	if (errmsg)
+		pr_info_ratelimited("%s\n", errmsg);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_ct_set_timeout);
+
+void nf_ct_destroy_timeout(struct nf_conn *ct)
+{
+	struct nf_conn_timeout *timeout_ext;
+	typeof(nf_ct_timeout_put_hook) timeout_put;
+
+	rcu_read_lock();
+	timeout_put = rcu_dereference(nf_ct_timeout_put_hook);
+
+	if (timeout_put) {
+		timeout_ext = nf_ct_timeout_find(ct);
+		if (timeout_ext) {
+			timeout_put(timeout_ext->timeout);
+			RCU_INIT_POINTER(timeout_ext->timeout, NULL);
+		}
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(nf_ct_destroy_timeout);
+
 static const struct nf_ct_ext_type timeout_extend = {
 	.len	= sizeof(struct nf_conn_timeout),
 	.align	= __alignof__(struct nf_conn_timeout),
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 0fa863f57575..d59cb4730fac 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -103,85 +103,24 @@ xt_ct_set_helper(struct nf_conn *ct, const char *helper_name,
 	return 0;
 }
 
-#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-static void __xt_ct_tg_timeout_put(struct nf_ct_timeout *timeout)
-{
-	typeof(nf_ct_timeout_put_hook) timeout_put;
-
-	timeout_put = rcu_dereference(nf_ct_timeout_put_hook);
-	if (timeout_put)
-		timeout_put(timeout);
-}
-#endif
-
 static int
 xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par,
 		  const char *timeout_name)
 {
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-	typeof(nf_ct_timeout_find_get_hook) timeout_find_get;
 	const struct nf_conntrack_l4proto *l4proto;
-	struct nf_ct_timeout *timeout;
-	struct nf_conn_timeout *timeout_ext;
-	const char *errmsg = NULL;
-	int ret = 0;
 	u8 proto;
 
-	rcu_read_lock();
-	timeout_find_get = rcu_dereference(nf_ct_timeout_find_get_hook);
-	if (timeout_find_get == NULL) {
-		ret = -ENOENT;
-		errmsg = "Timeout policy base is empty";
-		goto out;
-	}
-
 	proto = xt_ct_find_proto(par);
 	if (!proto) {
-		ret = -EINVAL;
-		errmsg = "You must specify a L4 protocol and not use inversions on it";
-		goto out;
-	}
-
-	timeout = timeout_find_get(par->net, timeout_name);
-	if (timeout == NULL) {
-		ret = -ENOENT;
-		pr_info_ratelimited("No such timeout policy \"%s\"\n",
-				    timeout_name);
-		goto out;
-	}
-
-	if (timeout->l3num != par->family) {
-		ret = -EINVAL;
-		pr_info_ratelimited("Timeout policy `%s' can only be used by L%d protocol number %d\n",
-				    timeout_name, 3, timeout->l3num);
-		goto err_put_timeout;
+		pr_info_ratelimited("You must specify a L4 protocol and not "
+				    "use inversions on it");
+		return -EINVAL;
 	}
-	/* Make sure the timeout policy matches any existing protocol tracker,
-	 * otherwise default to generic.
-	 */
 	l4proto = nf_ct_l4proto_find(proto);
-	if (timeout->l4proto->l4proto != l4proto->l4proto) {
-		ret = -EINVAL;
-		pr_info_ratelimited("Timeout policy `%s' can only be used by L%d protocol number %d\n",
-				    timeout_name, 4, timeout->l4proto->l4proto);
-		goto err_put_timeout;
-	}
-	timeout_ext = nf_ct_timeout_ext_add(ct, timeout, GFP_ATOMIC);
-	if (!timeout_ext) {
-		ret = -ENOMEM;
-		goto err_put_timeout;
-	}
+	return nf_ct_set_timeout(par->net, ct, par->family, l4proto->l4proto,
+				 timeout_name);
 
-	rcu_read_unlock();
-	return ret;
-
-err_put_timeout:
-	__xt_ct_tg_timeout_put(timeout);
-out:
-	rcu_read_unlock();
-	if (errmsg)
-		pr_info_ratelimited("%s\n", errmsg);
-	return ret;
 #else
 	return -EOPNOTSUPP;
 #endif
@@ -328,26 +267,6 @@ static int xt_ct_tg_check_v2(const struct xt_tgchk_param *par)
 	return xt_ct_tg_check(par, par->targinfo);
 }
 
-static void xt_ct_destroy_timeout(struct nf_conn *ct)
-{
-#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-	struct nf_conn_timeout *timeout_ext;
-	typeof(nf_ct_timeout_put_hook) timeout_put;
-
-	rcu_read_lock();
-	timeout_put = rcu_dereference(nf_ct_timeout_put_hook);
-
-	if (timeout_put) {
-		timeout_ext = nf_ct_timeout_find(ct);
-		if (timeout_ext) {
-			timeout_put(timeout_ext->timeout);
-			RCU_INIT_POINTER(timeout_ext->timeout, NULL);
-		}
-	}
-	rcu_read_unlock();
-#endif
-}
-
 static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par,
 			     struct xt_ct_target_info_v1 *info)
 {
@@ -361,7 +280,7 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par,
 
 		nf_ct_netns_put(par->net, par->family);
 
-		xt_ct_destroy_timeout(ct);
+		nf_ct_destroy_timeout(ct);
 		nf_ct_put(info->ct);
 	}
 }
-- 
cgit v1.2.3


From 06bd2bdf19d2f3d22731625e1a47fa1dff5ac407 Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Tue, 26 Mar 2019 11:31:14 -0700
Subject: openvswitch: Add timeout support to ct action

Add support for fine-grain timeout support to conntrack action.
The new OVS_CT_ATTR_TIMEOUT attribute of the conntrack action
specifies a timeout to be associated with this connection.
If no timeout is specified, it acts as is, that is the default
timeout for the connection will be automatically applied.

Example usage:
$ nfct timeout add timeout_1 inet tcp syn_sent 100 established 200
$ ovs-ofctl add-flow br0 in_port=1,ip,tcp,action=ct(commit,timeout=timeout_1)

CC: Pravin Shelar <pshelar@ovn.org>
CC: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/openvswitch.h |  3 +++
 net/openvswitch/conntrack.c      | 30 +++++++++++++++++++++++++++++-
 2 files changed, 32 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index dfabacee6903..0cac5d802c6a 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -734,6 +734,7 @@ struct ovs_action_hash {
  * be received on NFNLGRP_CONNTRACK_NEW and NFNLGRP_CONNTRACK_DESTROY groups,
  * respectively.  Remaining bits control the changes for which an event is
  * delivered on the NFNLGRP_CONNTRACK_UPDATE group.
+ * @OVS_CT_ATTR_TIMEOUT: Variable length string defining conntrack timeout.
  */
 enum ovs_ct_attr {
 	OVS_CT_ATTR_UNSPEC,
@@ -746,6 +747,8 @@ enum ovs_ct_attr {
 	OVS_CT_ATTR_NAT,        /* Nested OVS_NAT_ATTR_* */
 	OVS_CT_ATTR_FORCE_COMMIT,  /* No argument */
 	OVS_CT_ATTR_EVENTMASK,  /* u32 mask of IPCT_* events. */
+	OVS_CT_ATTR_TIMEOUT,	/* Associate timeout with this connection for
+				 * fine-grain timeout tuning. */
 	__OVS_CT_ATTR_MAX
 };
 
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 845b83598e0d..121b01d4a3c0 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -24,6 +24,7 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_labels.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include <net/ipv6_frag.h>
@@ -73,6 +74,7 @@ struct ovs_conntrack_info {
 	u32 eventmask;              /* Mask of 1 << IPCT_*. */
 	struct md_mark mark;
 	struct md_labels labels;
+	char timeout[CTNL_TIMEOUT_NAME_MAX];
 #ifdef CONFIG_NF_NAT_NEEDED
 	struct nf_nat_range2 range;  /* Only present for SRC NAT and DST NAT. */
 #endif
@@ -1471,6 +1473,8 @@ static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = {
 #endif
 	[OVS_CT_ATTR_EVENTMASK]	= { .minlen = sizeof(u32),
 				    .maxlen = sizeof(u32) },
+	[OVS_CT_ATTR_TIMEOUT] = { .minlen = 1,
+				  .maxlen = CTNL_TIMEOUT_NAME_MAX },
 };
 
 static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
@@ -1556,6 +1560,15 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 			info->have_eventmask = true;
 			info->eventmask = nla_get_u32(a);
 			break;
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+		case OVS_CT_ATTR_TIMEOUT:
+			memcpy(info->timeout, nla_data(a), nla_len(a));
+			if (!memchr(info->timeout, '\0', nla_len(a))) {
+				OVS_NLERR(log, "Invalid conntrack helper");
+				return -EINVAL;
+			}
+			break;
+#endif
 
 		default:
 			OVS_NLERR(log, "Unknown conntrack attr (%d)",
@@ -1637,6 +1650,14 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
 		OVS_NLERR(log, "Failed to allocate conntrack template");
 		return -ENOMEM;
 	}
+
+	if (ct_info.timeout[0]) {
+		if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto,
+				      ct_info.timeout))
+			pr_info_ratelimited("Failed to associated timeout "
+					    "policy `%s'\n", ct_info.timeout);
+	}
+
 	if (helper) {
 		err = ovs_ct_add_helper(&ct_info, helper, key, log);
 		if (err)
@@ -1757,6 +1778,10 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
 	if (ct_info->have_eventmask &&
 	    nla_put_u32(skb, OVS_CT_ATTR_EVENTMASK, ct_info->eventmask))
 		return -EMSGSIZE;
+	if (ct_info->timeout[0]) {
+		if (nla_put_string(skb, OVS_CT_ATTR_TIMEOUT, ct_info->timeout))
+			return -EMSGSIZE;
+	}
 
 #ifdef CONFIG_NF_NAT_NEEDED
 	if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb))
@@ -1778,8 +1803,11 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info)
 {
 	if (ct_info->helper)
 		nf_conntrack_helper_put(ct_info->helper);
-	if (ct_info->ct)
+	if (ct_info->ct) {
 		nf_ct_tmpl_free(ct_info->ct);
+		if (ct_info->timeout[0])
+			nf_ct_destroy_timeout(ct_info->ct);
+	}
 }
 
 #if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
-- 
cgit v1.2.3


From 331c7a402358de6206232f6aab7aa48ec6c1088a Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:47 -0700
Subject: ipv4: Move IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN to helper

in_dev lookup followed by IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN check
is called in several places, some with the rcu lock and others with the
rtnl held.

Move the check to a helper similar to what IPv6 has. Since the helper
can be invoked from either context use rcu_dereference_rtnl to
dereference ip_ptr.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/inetdevice.h | 14 ++++++++++++++
 net/ipv4/fib_semantics.c   | 31 +++++++------------------------
 net/ipv4/fib_trie.c        |  4 +---
 3 files changed, 22 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index a64f21a97369..367dc2a0f84a 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -237,6 +237,20 @@ static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev)
 	return rtnl_dereference(dev->ip_ptr);
 }
 
+/* called with rcu_read_lock or rtnl held */
+static inline bool ip_ignore_linkdown(const struct net_device *dev)
+{
+	struct in_device *in_dev;
+	bool rc = false;
+
+	in_dev = rcu_dereference_rtnl(dev->ip_ptr);
+	if (in_dev &&
+	    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
+		rc = true;
+
+	return rc;
+}
+
 static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev)
 {
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b5dbbdfd1e49..78631eb255f7 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -558,7 +558,6 @@ static void fib_rebalance(struct fib_info *fi)
 {
 	int total;
 	int w;
-	struct in_device *in_dev;
 
 	if (fi->fib_nhs < 2)
 		return;
@@ -568,10 +567,7 @@ static void fib_rebalance(struct fib_info *fi)
 		if (nh->nh_flags & RTNH_F_DEAD)
 			continue;
 
-		in_dev = __in_dev_get_rtnl(nh->nh_dev);
-
-		if (in_dev &&
-		    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+		if (ip_ignore_linkdown(nh->nh_dev) &&
 		    nh->nh_flags & RTNH_F_LINKDOWN)
 			continue;
 
@@ -582,12 +578,9 @@ static void fib_rebalance(struct fib_info *fi)
 	change_nexthops(fi) {
 		int upper_bound;
 
-		in_dev = __in_dev_get_rtnl(nexthop_nh->nh_dev);
-
 		if (nexthop_nh->nh_flags & RTNH_F_DEAD) {
 			upper_bound = -1;
-		} else if (in_dev &&
-			   IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+		} else if (ip_ignore_linkdown(nexthop_nh->nh_dev) &&
 			   nexthop_nh->nh_flags & RTNH_F_LINKDOWN) {
 			upper_bound = -1;
 		} else {
@@ -1325,12 +1318,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		    nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif))
 			goto nla_put_failure;
 		if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) {
-			struct in_device *in_dev;
-
 			rcu_read_lock();
-			in_dev = __in_dev_get_rcu(fi->fib_nh->nh_dev);
-			if (in_dev &&
-			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
+			if (ip_ignore_linkdown(fi->fib_nh->nh_dev))
 				rtm->rtm_flags |= RTNH_F_DEAD;
 			rcu_read_unlock();
 		}
@@ -1361,12 +1350,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 
 			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
 			if (nh->nh_flags & RTNH_F_LINKDOWN) {
-				struct in_device *in_dev;
-
 				rcu_read_lock();
-				in_dev = __in_dev_get_rcu(nh->nh_dev);
-				if (in_dev &&
-				    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
+				if (ip_ignore_linkdown(nh->nh_dev))
 					rtnh->rtnh_flags |= RTNH_F_DEAD;
 				rcu_read_unlock();
 			}
@@ -1433,7 +1418,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
 static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
 				 enum fib_event_type event_type)
 {
-	struct in_device *in_dev = __in_dev_get_rtnl(fib_nh->nh_dev);
+	bool ignore_link_down = ip_ignore_linkdown(fib_nh->nh_dev);
 	struct fib_nh_notifier_info info = {
 		.fib_nh = fib_nh,
 	};
@@ -1442,14 +1427,12 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
 	case FIB_EVENT_NH_ADD:
 		if (fib_nh->nh_flags & RTNH_F_DEAD)
 			break;
-		if (IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-		    fib_nh->nh_flags & RTNH_F_LINKDOWN)
+		if (ignore_link_down && fib_nh->nh_flags & RTNH_F_LINKDOWN)
 			break;
 		return call_fib4_notifiers(dev_net(fib_nh->nh_dev), event_type,
 					   &info.info);
 	case FIB_EVENT_NH_DEL:
-		if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-		     fib_nh->nh_flags & RTNH_F_LINKDOWN) ||
+		if ((ignore_link_down && fib_nh->nh_flags & RTNH_F_LINKDOWN) ||
 		    (fib_nh->nh_flags & RTNH_F_DEAD))
 			return call_fib4_notifiers(dev_net(fib_nh->nh_dev),
 						   event_type, &info.info);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 1704f432de1f..656d3d19f112 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1471,12 +1471,10 @@ found:
 			continue;
 		for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
 			const struct fib_nh *nh = &fi->fib_nh[nhsel];
-			struct in_device *in_dev = __in_dev_get_rcu(nh->nh_dev);
 
 			if (nh->nh_flags & RTNH_F_DEAD)
 				continue;
-			if (in_dev &&
-			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
+			if (ip_ignore_linkdown(nh->nh_dev) &&
 			    nh->nh_flags & RTNH_F_LINKDOWN &&
 			    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
 				continue;
-- 
cgit v1.2.3


From e4516ef65490ef29d48a98ad4d7c90dccf39068f Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:48 -0700
Subject: ipv4: Create init helper for fib_nh

Consolidate the fib_nh initialization which is duplicated between
fib_create_info for single path and fib_get_nhs for multipath.
Export the helper to allow for use with nexthop objects in the
future.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |   4 ++
 net/ipv4/fib_semantics.c | 180 ++++++++++++++++++++++++-----------------------
 2 files changed, 95 insertions(+), 89 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 9c8214d2116d..1af1f552644a 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -416,6 +416,10 @@ void fib_select_multipath(struct fib_result *res, int hash);
 void fib_select_path(struct net *net, struct fib_result *res,
 		     struct flowi4 *fl4, const struct sk_buff *skb);
 
+int fib_nh_init(struct net *net, struct fib_nh *fib_nh,
+		struct fib_config *cfg, int nh_weight,
+		struct netlink_ext_ack *extack);
+
 /* Exported by fib_trie.c */
 void fib_trie_init(void);
 struct fib_table *fib_trie_table(u32 id, struct fib_table *alias);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 78631eb255f7..cd15746e2b3f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -457,6 +457,54 @@ static int fib_detect_death(struct fib_info *fi, int order,
 	return 1;
 }
 
+int fib_nh_init(struct net *net, struct fib_nh *nh,
+		struct fib_config *cfg, int nh_weight,
+		struct netlink_ext_ack *extack)
+{
+	int err = -ENOMEM;
+
+	nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
+	if (!nh->nh_pcpu_rth_output)
+		goto err_out;
+
+	if (cfg->fc_encap) {
+		struct lwtunnel_state *lwtstate;
+
+		err = -EINVAL;
+		if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) {
+			NL_SET_ERR_MSG(extack, "LWT encap type not specified");
+			goto lwt_failure;
+		}
+		err = lwtunnel_build_state(cfg->fc_encap_type,
+					   cfg->fc_encap, AF_INET, cfg,
+					   &lwtstate, extack);
+		if (err)
+			goto lwt_failure;
+
+		nh->nh_lwtstate = lwtstate_get(lwtstate);
+	}
+
+	nh->nh_oif = cfg->fc_oif;
+	nh->nh_gw = cfg->fc_gw;
+	nh->nh_flags = cfg->fc_flags;
+
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	nh->nh_tclassid = cfg->fc_flow;
+	if (nh->nh_tclassid)
+		net->ipv4.fib_num_tclassid_users++;
+#endif
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+	nh->nh_weight = nh_weight;
+#endif
+	return 0;
+
+lwt_failure:
+	rt_fibinfo_free_cpus(nh->nh_pcpu_rth_output);
+	nh->nh_pcpu_rth_output = NULL;
+err_out:
+	return err;
+}
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 
 static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining,
@@ -483,11 +531,15 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 		       int remaining, struct fib_config *cfg,
 		       struct netlink_ext_ack *extack)
 {
+	struct net *net = fi->fib_net;
+	struct fib_config fib_cfg;
 	int ret;
 
 	change_nexthops(fi) {
 		int attrlen;
 
+		memset(&fib_cfg, 0, sizeof(fib_cfg));
+
 		if (!rtnh_ok(rtnh, remaining)) {
 			NL_SET_ERR_MSG(extack,
 				       "Invalid nexthop configuration - extra data after nexthop");
@@ -500,56 +552,54 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 			return -EINVAL;
 		}
 
-		nexthop_nh->nh_flags =
-			(cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
-		nexthop_nh->nh_oif = rtnh->rtnh_ifindex;
-		nexthop_nh->nh_weight = rtnh->rtnh_hops + 1;
+		fib_cfg.fc_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
+		fib_cfg.fc_oif = rtnh->rtnh_ifindex;
 
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
 			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
-			nexthop_nh->nh_gw = nla ? nla_get_in_addr(nla) : 0;
-#ifdef CONFIG_IP_ROUTE_CLASSID
+			if (nla)
+				fib_cfg.fc_gw = nla_get_in_addr(nla);
+
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
-			nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
-			if (nexthop_nh->nh_tclassid)
-				fi->fib_net->ipv4.fib_num_tclassid_users++;
-#endif
-			nla = nla_find(attrs, attrlen, RTA_ENCAP);
-			if (nla) {
-				struct lwtunnel_state *lwtstate;
-				struct nlattr *nla_entype;
-
-				nla_entype = nla_find(attrs, attrlen,
-						      RTA_ENCAP_TYPE);
-				if (!nla_entype) {
-					NL_SET_BAD_ATTR(extack, nla);
-					NL_SET_ERR_MSG(extack,
-						       "Encap type is missing");
-					goto err_inval;
-				}
+			if (nla)
+				fib_cfg.fc_flow = nla_get_u32(nla);
 
-				ret = lwtunnel_build_state(nla_get_u16(
-							   nla_entype),
-							   nla,  AF_INET, cfg,
-							   &lwtstate, extack);
-				if (ret)
-					goto errout;
-				nexthop_nh->nh_lwtstate =
-					lwtstate_get(lwtstate);
-			}
+			fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
+			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
+			if (nla)
+				fib_cfg.fc_encap_type = nla_get_u16(nla);
 		}
 
+		ret = fib_nh_init(net, nexthop_nh, &fib_cfg,
+				  rtnh->rtnh_hops + 1, extack);
+		if (ret)
+			goto errout;
+
 		rtnh = rtnh_next(rtnh, &remaining);
 	} endfor_nexthops(fi);
 
-	return 0;
-
-err_inval:
 	ret = -EINVAL;
-
+	if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) {
+		NL_SET_ERR_MSG(extack,
+			       "Nexthop device index does not match RTA_OIF");
+		goto errout;
+	}
+	if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) {
+		NL_SET_ERR_MSG(extack,
+			       "Nexthop gateway does not match RTA_GATEWAY");
+		goto errout;
+	}
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) {
+		NL_SET_ERR_MSG(extack,
+			       "Nexthop class id does not match RTA_FLOW");
+		goto errout;
+	}
+#endif
+	ret = 0;
 errout:
 	return ret;
 }
@@ -1098,63 +1148,15 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	fi->fib_nhs = nhs;
 	change_nexthops(fi) {
 		nexthop_nh->nh_parent = fi;
-		nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
-		if (!nexthop_nh->nh_pcpu_rth_output)
-			goto failure;
 	} endfor_nexthops(fi)
 
-	if (cfg->fc_mp) {
+	if (cfg->fc_mp)
 		err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack);
-		if (err != 0)
-			goto failure;
-		if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) {
-			NL_SET_ERR_MSG(extack,
-				       "Nexthop device index does not match RTA_OIF");
-			goto err_inval;
-		}
-		if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) {
-			NL_SET_ERR_MSG(extack,
-				       "Nexthop gateway does not match RTA_GATEWAY");
-			goto err_inval;
-		}
-#ifdef CONFIG_IP_ROUTE_CLASSID
-		if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) {
-			NL_SET_ERR_MSG(extack,
-				       "Nexthop class id does not match RTA_FLOW");
-			goto err_inval;
-		}
-#endif
-	} else {
-		struct fib_nh *nh = fi->fib_nh;
-
-		if (cfg->fc_encap) {
-			struct lwtunnel_state *lwtstate;
-
-			if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) {
-				NL_SET_ERR_MSG(extack,
-					       "LWT encap type not specified");
-				goto err_inval;
-			}
-			err = lwtunnel_build_state(cfg->fc_encap_type,
-						   cfg->fc_encap, AF_INET, cfg,
-						   &lwtstate, extack);
-			if (err)
-				goto failure;
+	else
+		err = fib_nh_init(net, fi->fib_nh, cfg, 1, extack);
 
-			nh->nh_lwtstate = lwtstate_get(lwtstate);
-		}
-		nh->nh_oif = cfg->fc_oif;
-		nh->nh_gw = cfg->fc_gw;
-		nh->nh_flags = cfg->fc_flags;
-#ifdef CONFIG_IP_ROUTE_CLASSID
-		nh->nh_tclassid = cfg->fc_flow;
-		if (nh->nh_tclassid)
-			fi->fib_net->ipv4.fib_num_tclassid_users++;
-#endif
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-		nh->nh_weight = 1;
-#endif
-	}
+	if (err != 0)
+		goto failure;
 
 	if (fib_props[cfg->fc_type].error) {
 		if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) {
-- 
cgit v1.2.3


From faa041a40b9fa64913789fcc0161c7c73161f57e Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:49 -0700
Subject: ipv4: Create cleanup helper for fib_nh

Move the fib_nh cleanup code from free_fib_info_rcu into a new helper,
fib_nh_release. Move classid accounting into fib_nh_release which is
called per fib_nh to make accounting symmetrical with fib_nh_init.
Export the helper to allow for use with nexthop objects in the
future.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  1 +
 net/ipv4/fib_semantics.c | 29 +++++++++++++++++------------
 2 files changed, 18 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 1af1f552644a..5a4df0ba175e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -419,6 +419,7 @@ void fib_select_path(struct net *net, struct fib_result *res,
 int fib_nh_init(struct net *net, struct fib_nh *fib_nh,
 		struct fib_config *cfg, int nh_weight,
 		struct netlink_ext_ack *extack);
+void fib_nh_release(struct net *net, struct fib_nh *fib_nh);
 
 /* Exported by fib_trie.c */
 void fib_trie_init(void);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index cd15746e2b3f..184940a06cb5 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -204,18 +204,28 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
 	free_percpu(rtp);
 }
 
+void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
+{
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	if (fib_nh->nh_tclassid)
+		net->ipv4.fib_num_tclassid_users--;
+#endif
+	if (fib_nh->nh_dev)
+		dev_put(fib_nh->nh_dev);
+
+	lwtstate_put(fib_nh->nh_lwtstate);
+	free_nh_exceptions(fib_nh);
+	rt_fibinfo_free_cpus(fib_nh->nh_pcpu_rth_output);
+	rt_fibinfo_free(&fib_nh->nh_rth_input);
+}
+
 /* Release a nexthop info record */
 static void free_fib_info_rcu(struct rcu_head *head)
 {
 	struct fib_info *fi = container_of(head, struct fib_info, rcu);
 
 	change_nexthops(fi) {
-		if (nexthop_nh->nh_dev)
-			dev_put(nexthop_nh->nh_dev);
-		lwtstate_put(nexthop_nh->nh_lwtstate);
-		free_nh_exceptions(nexthop_nh);
-		rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
-		rt_fibinfo_free(&nexthop_nh->nh_rth_input);
+		fib_nh_release(fi->fib_net, nexthop_nh);
 	} endfor_nexthops(fi);
 
 	ip_fib_metrics_put(fi->fib_metrics);
@@ -230,12 +240,7 @@ void free_fib_info(struct fib_info *fi)
 		return;
 	}
 	fib_info_cnt--;
-#ifdef CONFIG_IP_ROUTE_CLASSID
-	change_nexthops(fi) {
-		if (nexthop_nh->nh_tclassid)
-			fi->fib_net->ipv4.fib_num_tclassid_users--;
-	} endfor_nexthops(fi);
-#endif
+
 	call_rcu(&fi->rcu, free_fib_info_rcu);
 }
 EXPORT_SYMBOL_GPL(free_fib_info);
-- 
cgit v1.2.3


From 83c442515917812d4ff643e90cd456c630b7e762 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:50 -0700
Subject: ipv6: Create init helper for fib6_nh

Similar to IPv4, consolidate the fib6_nh initialization into a helper.
As a new standalone function, add a cleanup path to put lwtstate on
error.

To avoid modifying fib6_config flags, move the reject check to a helper
that is invoked once by fib6_nh_init to reset the device and then
again in ip6_route_info_create to set the fib6_flags.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |   4 +
 net/ipv6/route.c      | 249 ++++++++++++++++++++++++++++----------------------
 2 files changed, 145 insertions(+), 108 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 2acb78a762ee..ce1f81345c8e 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -444,6 +444,10 @@ static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i)
 	return f6i->fib6_nh.nh_dev;
 }
 
+int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
+		 struct fib6_config *cfg, gfp_t gfp_flags,
+		 struct netlink_ext_ack *extack);
+
 static inline
 struct lwtunnel_state *fib6_info_nh_lwt(const struct fib6_info *f6i)
 {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 61f231f58da5..8c5a998b28a1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2898,17 +2898,142 @@ out:
 	return err;
 }
 
+static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type)
+{
+	if ((flags & RTF_REJECT) ||
+	    (dev && (dev->flags & IFF_LOOPBACK) &&
+	     !(addr_type & IPV6_ADDR_LOOPBACK) &&
+	     !(flags & RTF_LOCAL)))
+		return true;
+
+	return false;
+}
+
+int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
+		 struct fib6_config *cfg, gfp_t gfp_flags,
+		 struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = NULL;
+	struct inet6_dev *idev = NULL;
+	int addr_type;
+	int err;
+
+	err = -ENODEV;
+	if (cfg->fc_ifindex) {
+		dev = dev_get_by_index(net, cfg->fc_ifindex);
+		if (!dev)
+			goto out;
+		idev = in6_dev_get(dev);
+		if (!idev)
+			goto out;
+	}
+
+	if (cfg->fc_flags & RTNH_F_ONLINK) {
+		if (!dev) {
+			NL_SET_ERR_MSG(extack,
+				       "Nexthop device required for onlink");
+			goto out;
+		}
+
+		if (!(dev->flags & IFF_UP)) {
+			NL_SET_ERR_MSG(extack, "Nexthop device is not up");
+			err = -ENETDOWN;
+			goto out;
+		}
+
+		fib6_nh->nh_flags |= RTNH_F_ONLINK;
+	}
+
+	if (cfg->fc_encap) {
+		struct lwtunnel_state *lwtstate;
+
+		err = lwtunnel_build_state(cfg->fc_encap_type,
+					   cfg->fc_encap, AF_INET6, cfg,
+					   &lwtstate, extack);
+		if (err)
+			goto out;
+
+		fib6_nh->nh_lwtstate = lwtstate_get(lwtstate);
+	}
+
+	fib6_nh->nh_weight = 1;
+
+	/* We cannot add true routes via loopback here,
+	 * they would result in kernel looping; promote them to reject routes
+	 */
+	addr_type = ipv6_addr_type(&cfg->fc_dst);
+	if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) {
+		/* hold loopback dev/idev if we haven't done so. */
+		if (dev != net->loopback_dev) {
+			if (dev) {
+				dev_put(dev);
+				in6_dev_put(idev);
+			}
+			dev = net->loopback_dev;
+			dev_hold(dev);
+			idev = in6_dev_get(dev);
+			if (!idev) {
+				err = -ENODEV;
+				goto out;
+			}
+		}
+		goto set_dev;
+	}
+
+	if (cfg->fc_flags & RTF_GATEWAY) {
+		err = ip6_validate_gw(net, cfg, &dev, &idev, extack);
+		if (err)
+			goto out;
+
+		fib6_nh->nh_gw = cfg->fc_gateway;
+	}
+
+	err = -ENODEV;
+	if (!dev)
+		goto out;
+
+	if (idev->cnf.disable_ipv6) {
+		NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device");
+		err = -EACCES;
+		goto out;
+	}
+
+	if (!(dev->flags & IFF_UP) && !cfg->fc_ignore_dev_down) {
+		NL_SET_ERR_MSG(extack, "Nexthop device is not up");
+		err = -ENETDOWN;
+		goto out;
+	}
+
+	if (!(cfg->fc_flags & (RTF_LOCAL | RTF_ANYCAST)) &&
+	    !netif_carrier_ok(dev))
+		fib6_nh->nh_flags |= RTNH_F_LINKDOWN;
+
+set_dev:
+	fib6_nh->nh_dev = dev;
+	err = 0;
+out:
+	if (idev)
+		in6_dev_put(idev);
+
+	if (err) {
+		lwtstate_put(fib6_nh->nh_lwtstate);
+		fib6_nh->nh_lwtstate = NULL;
+		if (dev)
+			dev_put(dev);
+	}
+
+	return err;
+}
+
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 					      gfp_t gfp_flags,
 					      struct netlink_ext_ack *extack)
 {
 	struct net *net = cfg->fc_nlinfo.nl_net;
 	struct fib6_info *rt = NULL;
-	struct net_device *dev = NULL;
-	struct inet6_dev *idev = NULL;
 	struct fib6_table *table;
-	int addr_type;
 	int err = -EINVAL;
+	int addr_type;
 
 	/* RTF_PCPU is an internal flag; can not be set by userspace */
 	if (cfg->fc_flags & RTF_PCPU) {
@@ -2942,30 +3067,6 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		goto out;
 	}
 #endif
-	if (cfg->fc_ifindex) {
-		err = -ENODEV;
-		dev = dev_get_by_index(net, cfg->fc_ifindex);
-		if (!dev)
-			goto out;
-		idev = in6_dev_get(dev);
-		if (!idev)
-			goto out;
-	}
-
-	if (cfg->fc_flags & RTNH_F_ONLINK) {
-		if (!dev) {
-			NL_SET_ERR_MSG(extack,
-				       "Nexthop device required for onlink");
-			err = -ENODEV;
-			goto out;
-		}
-
-		if (!(dev->flags & IFF_UP)) {
-			NL_SET_ERR_MSG(extack, "Nexthop device is not up");
-			err = -ENETDOWN;
-			goto out;
-		}
-	}
 
 	err = -ENOBUFS;
 	if (cfg->fc_nlinfo.nlh &&
@@ -3009,18 +3110,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		cfg->fc_protocol = RTPROT_BOOT;
 	rt->fib6_protocol = cfg->fc_protocol;
 
-	addr_type = ipv6_addr_type(&cfg->fc_dst);
-
-	if (cfg->fc_encap) {
-		struct lwtunnel_state *lwtstate;
-
-		err = lwtunnel_build_state(cfg->fc_encap_type,
-					   cfg->fc_encap, AF_INET6, cfg,
-					   &lwtstate, extack);
-		if (err)
-			goto out;
-		rt->fib6_nh.nh_lwtstate = lwtstate_get(lwtstate);
-	}
+	rt->fib6_table = table;
+	rt->fib6_metric = cfg->fc_metric;
+	rt->fib6_type = cfg->fc_type;
+	rt->fib6_flags = cfg->fc_flags;
 
 	ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
 	rt->fib6_dst.plen = cfg->fc_dst_len;
@@ -3031,62 +3124,20 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len);
 	rt->fib6_src.plen = cfg->fc_src_len;
 #endif
-
-	rt->fib6_metric = cfg->fc_metric;
-	rt->fib6_nh.nh_weight = 1;
-
-	rt->fib6_type = cfg->fc_type;
+	err = fib6_nh_init(net, &rt->fib6_nh, cfg, gfp_flags, extack);
+	if (err)
+		goto out;
 
 	/* We cannot add true routes via loopback here,
-	   they would result in kernel looping; promote them to reject routes
+	 * they would result in kernel looping; promote them to reject routes
 	 */
-	if ((cfg->fc_flags & RTF_REJECT) ||
-	    (dev && (dev->flags & IFF_LOOPBACK) &&
-	     !(addr_type & IPV6_ADDR_LOOPBACK) &&
-	     !(cfg->fc_flags & RTF_LOCAL))) {
-		/* hold loopback dev/idev if we haven't done so. */
-		if (dev != net->loopback_dev) {
-			if (dev) {
-				dev_put(dev);
-				in6_dev_put(idev);
-			}
-			dev = net->loopback_dev;
-			dev_hold(dev);
-			idev = in6_dev_get(dev);
-			if (!idev) {
-				err = -ENODEV;
-				goto out;
-			}
-		}
-		rt->fib6_flags = RTF_REJECT|RTF_NONEXTHOP;
-		goto install_route;
-	}
-
-	if (cfg->fc_flags & RTF_GATEWAY) {
-		err = ip6_validate_gw(net, cfg, &dev, &idev, extack);
-		if (err)
-			goto out;
-
-		rt->fib6_nh.nh_gw = cfg->fc_gateway;
-	}
-
-	err = -ENODEV;
-	if (!dev)
-		goto out;
-
-	if (idev->cnf.disable_ipv6) {
-		NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device");
-		err = -EACCES;
-		goto out;
-	}
-
-	if (!(dev->flags & IFF_UP) && !cfg->fc_ignore_dev_down) {
-		NL_SET_ERR_MSG(extack, "Nexthop device is not up");
-		err = -ENETDOWN;
-		goto out;
-	}
+	addr_type = ipv6_addr_type(&cfg->fc_dst);
+	if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh.nh_dev, addr_type))
+		rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP;
 
 	if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
+		struct net_device *dev = fib6_info_nh_dev(rt);
+
 		if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
 			NL_SET_ERR_MSG(extack, "Invalid source address");
 			err = -EINVAL;
@@ -3097,26 +3148,8 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	} else
 		rt->fib6_prefsrc.plen = 0;
 
-	rt->fib6_flags = cfg->fc_flags;
-
-install_route:
-	if (!(rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) &&
-	    !netif_carrier_ok(dev))
-		rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN;
-	rt->fib6_nh.nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK);
-	rt->fib6_nh.nh_dev = dev;
-	rt->fib6_table = table;
-
-	if (idev)
-		in6_dev_put(idev);
-
 	return rt;
 out:
-	if (dev)
-		dev_put(dev);
-	if (idev)
-		in6_dev_put(idev);
-
 	fib6_info_release(rt);
 	return ERR_PTR(err);
 }
-- 
cgit v1.2.3


From dac7d0f27075ce54017a7efdd6ae0a55352a0f80 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:51 -0700
Subject: ipv6: Create cleanup helper for fib6_nh

Move the fib6_nh cleanup code to a new helper, fib6_nh_release.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 1 +
 net/ipv6/ip6_fib.c    | 5 +----
 net/ipv6/route.c      | 8 ++++++++
 3 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index ce1f81345c8e..2d2a468b3d6d 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -447,6 +447,7 @@ static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i)
 int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 		 struct fib6_config *cfg, gfp_t gfp_flags,
 		 struct netlink_ext_ack *extack);
+void fib6_nh_release(struct fib6_nh *fib6_nh);
 
 static inline
 struct lwtunnel_state *fib6_info_nh_lwt(const struct fib6_info *f6i)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6613d8dbb0e5..db886085369b 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -199,10 +199,7 @@ void fib6_info_destroy_rcu(struct rcu_head *head)
 		free_percpu(f6i->rt6i_pcpu);
 	}
 
-	lwtstate_put(f6i->fib6_nh.nh_lwtstate);
-
-	if (f6i->fib6_nh.nh_dev)
-		dev_put(f6i->fib6_nh.nh_dev);
+	fib6_nh_release(&f6i->fib6_nh);
 
 	ip_fib_metrics_put(f6i->fib6_metrics);
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8c5a998b28a1..5f453c79dd00 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3025,6 +3025,14 @@ out:
 	return err;
 }
 
+void fib6_nh_release(struct fib6_nh *fib6_nh)
+{
+	lwtstate_put(fib6_nh->nh_lwtstate);
+
+	if (fib6_nh->nh_dev)
+		dev_put(fib6_nh->nh_dev);
+}
+
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 					      gfp_t gfp_flags,
 					      struct netlink_ext_ack *extack)
-- 
cgit v1.2.3


From 2b2450ca4a2d9d772dc45e1220c04cb3ba761843 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:52 -0700
Subject: ipv6: Move gateway checks to a fib6_nh setting

The gateway setting is not per fib6_info entry but per-fib6_nh. Add a new
fib_nh_has_gw flag to fib6_nh and convert references to RTF_GATEWAY to
the new flag. For IPv6 address the flag is cheaper than checking that
nh_gw is non-0 like IPv4 does.

While this increases fib6_nh by 8-bytes, the effective allocation size of
a fib6_info is unchanged. The 8 bytes is recovered later with a
fib_nh_common change.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  |  4 ++--
 include/net/ip6_fib.h                              |  1 +
 include/net/ip6_route.h                            |  4 ++--
 net/core/filter.c                                  |  2 +-
 net/ipv6/addrconf.c                                | 25 +++++++++++----------
 net/ipv6/ip6_fib.c                                 |  9 +++++---
 net/ipv6/route.c                                   | 26 +++++++++++++---------
 7 files changed, 41 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 52fed8c7bf1e..663d819a2a32 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4913,7 +4913,7 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6)
 static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
 {
 	/* RTF_CACHE routes are ignored */
-	return (rt->fib6_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY;
+	return !(rt->fib6_flags & RTF_ADDRCONF) && rt->fib6_nh.fib_nh_has_gw;
 }
 
 static struct fib6_info *
@@ -5053,7 +5053,7 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
 static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp,
 				    const struct fib6_info *rt)
 {
-	return rt->fib6_flags & RTF_GATEWAY ||
+	return rt->fib6_nh.fib_nh_has_gw ||
 	       mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL);
 }
 
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 2d2a468b3d6d..3b04b318cf13 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -126,6 +126,7 @@ struct rt6_exception {
 
 struct fib6_nh {
 	struct in6_addr		nh_gw;
+	bool			fib_nh_has_gw;
 	struct net_device	*nh_dev;
 	struct lwtunnel_state	*nh_lwtstate;
 
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 7ab119936e69..95cd8a2f6284 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -68,8 +68,8 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
 
 static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i)
 {
-	return (f6i->fib6_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
-	       RTF_GATEWAY;
+	return !(f6i->fib6_flags & (RTF_ADDRCONF|RTF_DYNAMIC)) &&
+		f6i->fib6_nh.fib_nh_has_gw;
 }
 
 void ip6_route_input(struct sk_buff *skb);
diff --git a/net/core/filter.c b/net/core/filter.c
index 22eb2edf5573..e7784764213a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4751,7 +4751,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (f6i->fib6_nh.nh_lwtstate)
 		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
-	if (f6i->fib6_flags & RTF_GATEWAY)
+	if (f6i->fib6_nh.fib_nh_has_gw)
 		*dst = f6i->fib6_nh.nh_gw;
 
 	dev = f6i->fib6_nh.nh_dev;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4ae17a966ae3..c5ac08fc6cc9 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -173,7 +173,8 @@ static int addrconf_ifdown(struct net_device *dev, int how);
 static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 						  int plen,
 						  const struct net_device *dev,
-						  u32 flags, u32 noflags);
+						  u32 flags, u32 noflags,
+						  bool no_gw);
 
 static void addrconf_dad_start(struct inet6_ifaddr *ifp);
 static void addrconf_dad_work(struct work_struct *w);
@@ -1230,10 +1231,8 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_r
 {
 	struct fib6_info *f6i;
 
-	f6i = addrconf_get_prefix_route(&ifp->addr,
-				       ifp->prefix_len,
-				       ifp->idev->dev,
-				       0, RTF_GATEWAY | RTF_DEFAULT);
+	f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len,
+					ifp->idev->dev, 0, RTF_DEFAULT, true);
 	if (f6i) {
 		if (del_rt)
 			ip6_del_rt(dev_net(ifp->idev->dev), f6i);
@@ -2402,7 +2401,8 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, u32 metric,
 static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 						  int plen,
 						  const struct net_device *dev,
-						  u32 flags, u32 noflags)
+						  u32 flags, u32 noflags,
+						  bool no_gw)
 {
 	struct fib6_node *fn;
 	struct fib6_info *rt = NULL;
@@ -2421,6 +2421,8 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 	for_each_fib6_node_rt_rcu(fn) {
 		if (rt->fib6_nh.nh_dev->ifindex != dev->ifindex)
 			continue;
+		if (no_gw && rt->fib6_nh.fib_nh_has_gw)
+			continue;
 		if ((rt->fib6_flags & flags) != flags)
 			continue;
 		if ((rt->fib6_flags & noflags) != 0)
@@ -2717,7 +2719,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 					       pinfo->prefix_len,
 					       dev,
 					       RTF_ADDRCONF | RTF_PREFIX_RT,
-					       RTF_GATEWAY | RTF_DEFAULT);
+					       RTF_DEFAULT, true);
 
 		if (rt) {
 			/* Autoconf prefix route */
@@ -4588,10 +4590,8 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
 	struct fib6_info *f6i;
 	u32 prio;
 
-	f6i = addrconf_get_prefix_route(&ifp->addr,
-					ifp->prefix_len,
-					ifp->idev->dev,
-					0, RTF_GATEWAY | RTF_DEFAULT);
+	f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len,
+					ifp->idev->dev, 0, RTF_DEFAULT, true);
 	if (!f6i)
 		return -ENOENT;
 
@@ -5972,7 +5972,8 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 			struct fib6_info *rt;
 
 			rt = addrconf_get_prefix_route(&ifp->peer_addr, 128,
-						       ifp->idev->dev, 0, 0);
+						       ifp->idev->dev, 0, 0,
+						       false);
 			if (rt)
 				ip6_del_rt(net, rt);
 		}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index db886085369b..91ce84ecdb57 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2294,6 +2294,7 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 {
 	struct fib6_info *rt = v;
 	struct ipv6_route_iter *iter = seq->private;
+	unsigned int flags = rt->fib6_flags;
 	const struct net_device *dev;
 
 	seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
@@ -2303,15 +2304,17 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 #else
 	seq_puts(seq, "00000000000000000000000000000000 00 ");
 #endif
-	if (rt->fib6_flags & RTF_GATEWAY)
+	if (rt->fib6_nh.fib_nh_has_gw) {
+		flags |= RTF_GATEWAY;
 		seq_printf(seq, "%pi6", &rt->fib6_nh.nh_gw);
-	else
+	} else {
 		seq_puts(seq, "00000000000000000000000000000000");
+	}
 
 	dev = rt->fib6_nh.nh_dev;
 	seq_printf(seq, " %08x %08x %08x %08x %8s\n",
 		   rt->fib6_metric, atomic_read(&rt->fib6_ref), 0,
-		   rt->fib6_flags, dev ? dev->name : "");
+		   flags, dev ? dev->name : "");
 	iter->w.leaf = NULL;
 	return 0;
 }
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5f453c79dd00..69c96cf37270 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -533,7 +533,7 @@ static void rt6_probe(struct fib6_info *rt)
 	 * Router Reachability Probe MUST be rate-limited
 	 * to no more than one per minute.
 	 */
-	if (!rt || !(rt->fib6_flags & RTF_GATEWAY))
+	if (!rt || !rt->fib6_nh.fib_nh_has_gw)
 		return;
 
 	nh_gw = &rt->fib6_nh.nh_gw;
@@ -595,7 +595,7 @@ static inline enum rt6_nud_state rt6_check_neigh(struct fib6_info *rt)
 	struct neighbour *neigh;
 
 	if (rt->fib6_flags & RTF_NONEXTHOP ||
-	    !(rt->fib6_flags & RTF_GATEWAY))
+	    !rt->fib6_nh.fib_nh_has_gw)
 		return RT6_NUD_SUCCEED;
 
 	rcu_read_lock_bh();
@@ -784,7 +784,7 @@ static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn,
 
 static bool rt6_is_gw_or_nonexthop(const struct fib6_info *rt)
 {
-	return (rt->fib6_flags & (RTF_NONEXTHOP | RTF_GATEWAY));
+	return (rt->fib6_flags & RTF_NONEXTHOP) || rt->fib6_nh.fib_nh_has_gw;
 }
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
@@ -989,8 +989,11 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
 
 	rt->rt6i_dst = ort->fib6_dst;
 	rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL;
-	rt->rt6i_gateway = ort->fib6_nh.nh_gw;
 	rt->rt6i_flags = ort->fib6_flags;
+	if (ort->fib6_nh.fib_nh_has_gw) {
+		rt->rt6i_gateway = ort->fib6_nh.nh_gw;
+		rt->rt6i_flags |= RTF_GATEWAY;
+	}
 	rt6_set_from(rt, ort);
 #ifdef CONFIG_IPV6_SUBTREES
 	rt->rt6i_src = ort->fib6_src;
@@ -1872,7 +1875,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		rcu_read_unlock();
 		return rt;
 	} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
-			    !(f6i->fib6_flags & RTF_GATEWAY))) {
+			    !f6i->fib6_nh.fib_nh_has_gw)) {
 		/* Create a RTF_CACHE clone which will not be
 		 * owned by the fib6 tree.  It is for the special case where
 		 * the daddr in the skb during the neighbor look-up is different
@@ -2442,7 +2445,7 @@ restart:
 			continue;
 		if (rt->fib6_flags & RTF_REJECT)
 			break;
-		if (!(rt->fib6_flags & RTF_GATEWAY))
+		if (!rt->fib6_nh.fib_nh_has_gw)
 			continue;
 		if (fl6->flowi6_oif != rt->fib6_nh.nh_dev->ifindex)
 			continue;
@@ -2986,6 +2989,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 			goto out;
 
 		fib6_nh->nh_gw = cfg->fc_gateway;
+		fib6_nh->fib_nh_has_gw = 1;
 	}
 
 	err = -ENODEV;
@@ -3121,7 +3125,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	rt->fib6_table = table;
 	rt->fib6_metric = cfg->fc_metric;
 	rt->fib6_type = cfg->fc_type;
-	rt->fib6_flags = cfg->fc_flags;
+	rt->fib6_flags = cfg->fc_flags & ~RTF_GATEWAY;
 
 	ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
 	rt->fib6_dst.plen = cfg->fc_dst_len;
@@ -3490,7 +3494,8 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 	for_each_fib6_node_rt_rcu(fn) {
 		if (rt->fib6_nh.nh_dev->ifindex != ifindex)
 			continue;
-		if ((rt->fib6_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
+		if (!(rt->fib6_flags & RTF_ROUTEINFO) ||
+		    !rt->fib6_nh.fib_nh_has_gw)
 			continue;
 		if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr))
 			continue;
@@ -3811,7 +3816,7 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 	fib6_clean_all(net, fib6_remove_prefsrc, &adni);
 }
 
-#define RTF_RA_ROUTER		(RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
+#define RTF_RA_ROUTER		(RTF_ADDRCONF | RTF_DEFAULT)
 
 /* Remove routers and update dst entries when gateway turn into host. */
 static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
@@ -3819,6 +3824,7 @@ static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
 	struct in6_addr *gateway = (struct in6_addr *)arg;
 
 	if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
+	    rt->fib6_nh.fib_nh_has_gw &&
 	    ipv6_addr_equal(gateway, &rt->fib6_nh.nh_gw)) {
 		return -1;
 	}
@@ -4607,7 +4613,7 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct fib6_info *rt,
 		rcu_read_unlock();
 	}
 
-	if (rt->fib6_flags & RTF_GATEWAY) {
+	if (rt->fib6_nh.fib_nh_has_gw) {
 		if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->fib6_nh.nh_gw) < 0)
 			goto nla_put_failure;
 	}
-- 
cgit v1.2.3


From 6d3d07b45c86f984424ccbad110ca500397fd18c Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:53 -0700
Subject: ipv6: Refactor fib6_ignore_linkdown

fib6_ignore_linkdown takes a fib6_info but only looks at the net_device
and its IPv6 config. Change it to take a net_device over a fib6_info as
its input argument.

In addition, move it to a header file to make the check inline and usable
later with IPv4 code without going through the ipv6 stub, and rename to
ip6_ignore_linkdown since it is only checking the setting based on the
ipv6 struct on a device.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h |  8 ++++++++
 net/ipv6/route.c       | 21 +++------------------
 2 files changed, 11 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 269ec27385e9..ec8e6784a6f7 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -425,6 +425,14 @@ static inline void in6_dev_hold(struct inet6_dev *idev)
 	refcount_inc(&idev->refcnt);
 }
 
+/* called with rcu_read_lock held */
+static inline bool ip6_ignore_linkdown(const struct net_device *dev)
+{
+	const struct inet6_dev *idev = __in6_dev_get(dev);
+
+	return !!idev->cnf.ignore_routes_with_linkdown;
+}
+
 void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp);
 
 static inline void in6_ifa_put(struct inet6_ifaddr *ifp)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 69c96cf37270..66cbb44cd92e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -639,21 +639,6 @@ static int rt6_score_route(struct fib6_info *rt, int oif, int strict)
 	return m;
 }
 
-/* called with rc_read_lock held */
-static inline bool fib6_ignore_linkdown(const struct fib6_info *f6i)
-{
-	const struct net_device *dev = fib6_info_nh_dev(f6i);
-	bool rc = false;
-
-	if (dev) {
-		const struct inet6_dev *idev = __in6_dev_get(dev);
-
-		rc = !!idev->cnf.ignore_routes_with_linkdown;
-	}
-
-	return rc;
-}
-
 static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict,
 				   int *mpri, struct fib6_info *match,
 				   bool *do_rr)
@@ -664,7 +649,7 @@ static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict,
 	if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
 		goto out;
 
-	if (fib6_ignore_linkdown(rt) &&
+	if (ip6_ignore_linkdown(rt->fib6_nh.nh_dev) &&
 	    rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
 	    !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
 		goto out;
@@ -3875,7 +3860,7 @@ static bool rt6_is_dead(const struct fib6_info *rt)
 {
 	if (rt->fib6_nh.nh_flags & RTNH_F_DEAD ||
 	    (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
-	     fib6_ignore_linkdown(rt)))
+	     ip6_ignore_linkdown(rt->fib6_nh.nh_dev)))
 		return true;
 
 	return false;
@@ -4608,7 +4593,7 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct fib6_info *rt,
 		*flags |= RTNH_F_LINKDOWN;
 
 		rcu_read_lock();
-		if (fib6_ignore_linkdown(rt))
+		if (ip6_ignore_linkdown(rt->fib6_nh.nh_dev))
 			*flags |= RTNH_F_DEAD;
 		rcu_read_unlock();
 	}
-- 
cgit v1.2.3


From b75ed8b1aa9c3a99702159c3be8b0c1d54972ae5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:55 -0700
Subject: ipv4: Rename fib_nh entries

Rename fib_nh entries that will be moved to a fib_nh_common struct.
Specifically, the device, oif, gateway, flags, scope, lwtstate,
nh_weight and nh_upper_bound are common with all nexthop definitions.
In the process shorten fib_nh_lwtstate to fib_nh_lws to avoid really
long lines.

Rename only; no functional change intended.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c   |  12 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  |  22 +-
 drivers/net/ethernet/rocker/rocker_ofdpa.c         |  10 +-
 include/net/ip_fib.h                               |  24 +--
 include/trace/events/fib.h                         |   7 +-
 net/core/filter.c                                  |   8 +-
 net/ipv4/fib_frontend.c                            |  10 +-
 net/ipv4/fib_semantics.c                           | 229 +++++++++++----------
 net/ipv4/fib_trie.c                                |  12 +-
 net/ipv4/route.c                                   |  18 +-
 10 files changed, 178 insertions(+), 174 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
index 5633f8572800..8212bfd05733 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -122,7 +122,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev,
 	/* Handle add/replace event */
 	if (fi->fib_nhs == 1) {
 		if (__mlx5_lag_is_active(ldev)) {
-			struct net_device *nh_dev = fi->fib_nh[0].nh_dev;
+			struct net_device *nh_dev = fi->fib_nh[0].fib_nh_dev;
 			int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev);
 
 			mlx5_lag_set_port_affinity(ldev, ++i);
@@ -134,10 +134,10 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev,
 		return;
 
 	/* Verify next hops are ports of the same hca */
-	if (!(fi->fib_nh[0].nh_dev == ldev->pf[0].netdev &&
-	      fi->fib_nh[1].nh_dev == ldev->pf[1].netdev) &&
-	    !(fi->fib_nh[0].nh_dev == ldev->pf[1].netdev &&
-	      fi->fib_nh[1].nh_dev == ldev->pf[0].netdev)) {
+	if (!(fi->fib_nh[0].fib_nh_dev == ldev->pf[0].netdev &&
+	      fi->fib_nh[1].fib_nh_dev == ldev->pf[1].netdev) &&
+	    !(fi->fib_nh[0].fib_nh_dev == ldev->pf[1].netdev &&
+	      fi->fib_nh[1].fib_nh_dev == ldev->pf[0].netdev)) {
 		mlx5_core_warn(ldev->pf[0].dev, "Multipath offload require two ports of the same HCA\n");
 		return;
 	}
@@ -167,7 +167,7 @@ static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev,
 
 	/* nh added/removed */
 	if (event == FIB_EVENT_NH_DEL) {
-		int i = mlx5_lag_dev_get_netdev_idx(ldev, fib_nh->nh_dev);
+		int i = mlx5_lag_dev_get_netdev_idx(ldev, fib_nh->fib_nh_dev);
 
 		if (i >= 0) {
 			i = (i + 1) % 2 + 1; /* peer port */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 663d819a2a32..a18e1ae1c2f6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -3610,7 +3610,7 @@ static bool mlxsw_sp_nexthop4_ipip_type(const struct mlxsw_sp *mlxsw_sp,
 					const struct fib_nh *fib_nh,
 					enum mlxsw_sp_ipip_type *p_ipipt)
 {
-	struct net_device *dev = fib_nh->nh_dev;
+	struct net_device *dev = fib_nh->fib_nh_dev;
 
 	return dev &&
 	       fib_nh->nh_parent->fib_type == RTN_UNICAST &&
@@ -3637,7 +3637,7 @@ static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp,
 				       struct fib_nh *fib_nh)
 {
 	const struct mlxsw_sp_ipip_ops *ipip_ops;
-	struct net_device *dev = fib_nh->nh_dev;
+	struct net_device *dev = fib_nh->fib_nh_dev;
 	struct mlxsw_sp_ipip_entry *ipip_entry;
 	struct mlxsw_sp_rif *rif;
 	int err;
@@ -3681,18 +3681,18 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_nexthop *nh,
 				  struct fib_nh *fib_nh)
 {
-	struct net_device *dev = fib_nh->nh_dev;
+	struct net_device *dev = fib_nh->fib_nh_dev;
 	struct in_device *in_dev;
 	int err;
 
 	nh->nh_grp = nh_grp;
 	nh->key.fib_nh = fib_nh;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	nh->nh_weight = fib_nh->nh_weight;
+	nh->nh_weight = fib_nh->fib_nh_weight;
 #else
 	nh->nh_weight = 1;
 #endif
-	memcpy(&nh->gw_addr, &fib_nh->nh_gw, sizeof(fib_nh->nh_gw));
+	memcpy(&nh->gw_addr, &fib_nh->fib_nh_gw4, sizeof(fib_nh->fib_nh_gw4));
 	err = mlxsw_sp_nexthop_insert(mlxsw_sp, nh);
 	if (err)
 		return err;
@@ -3705,7 +3705,7 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp,
 
 	in_dev = __in_dev_get_rtnl(dev);
 	if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
-	    fib_nh->nh_flags & RTNH_F_LINKDOWN)
+	    fib_nh->fib_nh_flags & RTNH_F_LINKDOWN)
 		return 0;
 
 	err = mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh);
@@ -3804,7 +3804,7 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp,
 static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp,
 				   const struct fib_info *fi)
 {
-	return fi->fib_nh->nh_scope == RT_SCOPE_LINK ||
+	return fi->fib_nh->fib_nh_scope == RT_SCOPE_LINK ||
 	       mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, fi->fib_nh, NULL);
 }
 
@@ -3966,7 +3966,7 @@ mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE ||
 	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP ||
 	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP) {
-		nh_grp->nexthops->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD;
+		nh_grp->nexthops->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
 		return;
 	}
 
@@ -3974,9 +3974,9 @@ mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
 
 		if (nh->offloaded)
-			nh->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD;
+			nh->key.fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
 		else
-			nh->key.fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
+			nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	}
 }
 
@@ -3992,7 +3992,7 @@ mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
 	for (i = 0; i < nh_grp->count; i++) {
 		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
 
-		nh->key.fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
+		nh->key.fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	}
 }
 
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index fa296a7c255d..30a49802fb51 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -2288,11 +2288,11 @@ static int ofdpa_port_fib_ipv4(struct ofdpa_port *ofdpa_port,  __be32 dst,
 
 	nh = fi->fib_nh;
 	nh_on_port = (fi->fib_dev == ofdpa_port->dev);
-	has_gw = !!nh->nh_gw;
+	has_gw = !!nh->fib_nh_gw4;
 
 	if (has_gw && nh_on_port) {
 		err = ofdpa_port_ipv4_nh(ofdpa_port, flags,
-					 nh->nh_gw, &index);
+					 nh->fib_nh_gw4, &index);
 		if (err)
 			return err;
 
@@ -2749,7 +2749,7 @@ static int ofdpa_fib4_add(struct rocker *rocker,
 				  fen_info->tb_id, 0);
 	if (err)
 		return err;
-	fen_info->fi->fib_nh->nh_flags |= RTNH_F_OFFLOAD;
+	fen_info->fi->fib_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
 	return 0;
 }
 
@@ -2764,7 +2764,7 @@ static int ofdpa_fib4_del(struct rocker *rocker,
 	ofdpa_port = ofdpa_port_dev_lower_find(fen_info->fi->fib_dev, rocker);
 	if (!ofdpa_port)
 		return 0;
-	fen_info->fi->fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
+	fen_info->fi->fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	return ofdpa_port_fib_ipv4(ofdpa_port, htonl(fen_info->dst),
 				   fen_info->dst_len, fen_info->fi,
 				   fen_info->tb_id, OFDPA_OP_FLAG_REMOVE);
@@ -2791,7 +2791,7 @@ static void ofdpa_fib4_abort(struct rocker *rocker)
 						       rocker);
 		if (!ofdpa_port)
 			continue;
-		flow_entry->fi->fib_nh->nh_flags &= ~RTNH_F_OFFLOAD;
+		flow_entry->fi->fib_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 		ofdpa_flow_tbl_del(ofdpa_port, OFDPA_OP_FLAG_REMOVE,
 				   flow_entry);
 	}
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 5a4df0ba175e..029acd333d29 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -77,26 +77,26 @@ struct fnhe_hash_bucket {
 #define FNHE_RECLAIM_DEPTH	5
 
 struct fib_nh {
-	struct net_device	*nh_dev;
+	struct net_device	*fib_nh_dev;
 	struct hlist_node	nh_hash;
 	struct fib_info		*nh_parent;
-	unsigned int		nh_flags;
-	unsigned char		nh_scope;
+	unsigned int		fib_nh_flags;
+	unsigned char		fib_nh_scope;
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	int			nh_weight;
-	atomic_t		nh_upper_bound;
+	int			fib_nh_weight;
+	atomic_t		fib_nh_upper_bound;
 #endif
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			nh_tclassid;
 #endif
-	int			nh_oif;
-	__be32			nh_gw;
+	int			fib_nh_oif;
+	__be32			fib_nh_gw4;
 	__be32			nh_saddr;
 	int			nh_saddr_genid;
 	struct rtable __rcu * __percpu *nh_pcpu_rth_output;
 	struct rtable __rcu	*nh_rth_input;
 	struct fnhe_hash_bucket	__rcu *nh_exceptions;
-	struct lwtunnel_state	*nh_lwtstate;
+	struct lwtunnel_state	*fib_nh_lws;
 };
 
 /*
@@ -125,7 +125,7 @@ struct fib_info {
 	int			fib_nhs;
 	struct rcu_head		rcu;
 	struct fib_nh		fib_nh[0];
-#define fib_dev		fib_nh[0].nh_dev
+#define fib_dev		fib_nh[0].fib_nh_dev
 };
 
 
@@ -180,9 +180,9 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh);
 	  atomic_read(&(net)->ipv4.dev_addr_genid)) ?	\
 	 FIB_RES_NH(res).nh_saddr :			\
 	 fib_info_update_nh_saddr((net), &FIB_RES_NH(res)))
-#define FIB_RES_GW(res)			(FIB_RES_NH(res).nh_gw)
-#define FIB_RES_DEV(res)		(FIB_RES_NH(res).nh_dev)
-#define FIB_RES_OIF(res)		(FIB_RES_NH(res).nh_oif)
+#define FIB_RES_GW(res)			(FIB_RES_NH(res).fib_nh_gw4)
+#define FIB_RES_DEV(res)		(FIB_RES_NH(res).fib_nh_dev)
+#define FIB_RES_OIF(res)		(FIB_RES_NH(res).fib_nh_oif)
 
 #define FIB_RES_PREFSRC(net, res)	((res).fi->fib_prefsrc ? : \
 					 FIB_RES_SADDR(net, res))
diff --git a/include/trace/events/fib.h b/include/trace/events/fib.h
index 6271bab63bfb..61ea7a24c8e5 100644
--- a/include/trace/events/fib.h
+++ b/include/trace/events/fib.h
@@ -63,13 +63,16 @@ TRACE_EVENT(fib_table_lookup,
 		}
 
 		if (nh) {
+			struct net_device *dev;
+
 			p32 = (__be32 *) __entry->saddr;
 			*p32 = nh->nh_saddr;
 
 			p32 = (__be32 *) __entry->gw;
-			*p32 = nh->nh_gw;
+			*p32 = nh->fib_nh_gw4;
 
-			__assign_str(name, nh->nh_dev ? nh->nh_dev->name : "-");
+			dev = nh->fib_nh_dev;
+			__assign_str(name, dev ? dev->name : "-");
 		} else {
 			p32 = (__be32 *) __entry->saddr;
 			*p32 = 0;
diff --git a/net/core/filter.c b/net/core/filter.c
index e7784764213a..79d319c636ea 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4634,12 +4634,12 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	nh = &res.fi->fib_nh[res.nh_sel];
 
 	/* do not handle lwt encaps right now */
-	if (nh->nh_lwtstate)
+	if (nh->fib_nh_lws)
 		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
-	dev = nh->nh_dev;
-	if (nh->nh_gw)
-		params->ipv4_dst = nh->nh_gw;
+	dev = nh->fib_nh_dev;
+	if (nh->fib_nh_gw4)
+		params->ipv4_dst = nh->fib_nh_gw4;
 
 	params->rt_metric = res.fi->fib_priority;
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index ed14ec245584..ffbe24397dbe 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -324,16 +324,16 @@ bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev)
 	for (ret = 0; ret < fi->fib_nhs; ret++) {
 		struct fib_nh *nh = &fi->fib_nh[ret];
 
-		if (nh->nh_dev == dev) {
+		if (nh->fib_nh_dev == dev) {
 			dev_match = true;
 			break;
-		} else if (l3mdev_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) {
+		} else if (l3mdev_master_ifindex_rcu(nh->fib_nh_dev) == dev->ifindex) {
 			dev_match = true;
 			break;
 		}
 	}
 #else
-	if (fi->fib_nh[0].nh_dev == dev)
+	if (fi->fib_nh[0].fib_nh_dev == dev)
 		dev_match = true;
 #endif
 
@@ -390,7 +390,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 
 	dev_match = fib_info_nh_uses_dev(res.fi, dev);
 	if (dev_match) {
-		ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
+		ret = FIB_RES_NH(res).fib_nh_scope >= RT_SCOPE_HOST;
 		return ret;
 	}
 	if (no_addr)
@@ -402,7 +402,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	ret = 0;
 	if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
 		if (res.type == RTN_UNICAST)
-			ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
+			ret = FIB_RES_NH(res).fib_nh_scope >= RT_SCOPE_HOST;
 	}
 	return ret;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 184940a06cb5..c1e16b52338b 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -210,10 +210,10 @@ void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
 	if (fib_nh->nh_tclassid)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
-	if (fib_nh->nh_dev)
-		dev_put(fib_nh->nh_dev);
+	if (fib_nh->fib_nh_dev)
+		dev_put(fib_nh->fib_nh_dev);
 
-	lwtstate_put(fib_nh->nh_lwtstate);
+	lwtstate_put(fib_nh->fib_nh_lws);
 	free_nh_exceptions(fib_nh);
 	rt_fibinfo_free_cpus(fib_nh->nh_pcpu_rth_output);
 	rt_fibinfo_free(&fib_nh->nh_rth_input);
@@ -253,7 +253,7 @@ void fib_release_info(struct fib_info *fi)
 		if (fi->fib_prefsrc)
 			hlist_del(&fi->fib_lhash);
 		change_nexthops(fi) {
-			if (!nexthop_nh->nh_dev)
+			if (!nexthop_nh->fib_nh_dev)
 				continue;
 			hlist_del(&nexthop_nh->nh_hash);
 		} endfor_nexthops(fi)
@@ -268,17 +268,17 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
 	const struct fib_nh *onh = ofi->fib_nh;
 
 	for_nexthops(fi) {
-		if (nh->nh_oif != onh->nh_oif ||
-		    nh->nh_gw  != onh->nh_gw ||
-		    nh->nh_scope != onh->nh_scope ||
+		if (nh->fib_nh_oif != onh->fib_nh_oif ||
+		    nh->fib_nh_gw4 != onh->fib_nh_gw4 ||
+		    nh->fib_nh_scope != onh->fib_nh_scope ||
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-		    nh->nh_weight != onh->nh_weight ||
+		    nh->fib_nh_weight != onh->fib_nh_weight ||
 #endif
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		    nh->nh_tclassid != onh->nh_tclassid ||
 #endif
-		    lwtunnel_cmp_encap(nh->nh_lwtstate, onh->nh_lwtstate) ||
-		    ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_COMPARE_MASK))
+		    lwtunnel_cmp_encap(nh->fib_nh_lws, onh->fib_nh_lws) ||
+		    ((nh->fib_nh_flags ^ onh->fib_nh_flags) & ~RTNH_COMPARE_MASK))
 			return -1;
 		onh++;
 	} endfor_nexthops(fi);
@@ -303,7 +303,7 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
 	val ^= (__force u32)fi->fib_prefsrc;
 	val ^= fi->fib_priority;
 	for_nexthops(fi) {
-		val ^= fib_devindex_hashfn(nh->nh_oif);
+		val ^= fib_devindex_hashfn(nh->fib_nh_oif);
 	} endfor_nexthops(fi)
 
 	return (val ^ (val >> 7) ^ (val >> 12)) & mask;
@@ -352,9 +352,9 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev)
 	hash = fib_devindex_hashfn(dev->ifindex);
 	head = &fib_info_devhash[hash];
 	hlist_for_each_entry(nh, head, nh_hash) {
-		if (nh->nh_dev == dev &&
-		    nh->nh_gw == gw &&
-		    !(nh->nh_flags & RTNH_F_DEAD)) {
+		if (nh->fib_nh_dev == dev &&
+		    nh->fib_nh_gw4 == gw &&
+		    !(nh->fib_nh_flags & RTNH_F_DEAD)) {
 			spin_unlock(&fib_info_lock);
 			return 0;
 		}
@@ -389,10 +389,10 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi)
 
 		/* grab encap info */
 		for_nexthops(fi) {
-			if (nh->nh_lwtstate) {
+			if (nh->fib_nh_lws) {
 				/* RTA_ENCAP_TYPE */
 				nh_encapsize += lwtunnel_get_encap_size(
-						nh->nh_lwtstate);
+						nh->fib_nh_lws);
 				/* RTA_ENCAP */
 				nh_encapsize +=  nla_total_size(2);
 			}
@@ -443,7 +443,7 @@ static int fib_detect_death(struct fib_info *fi, int order,
 	struct neighbour *n;
 	int state = NUD_NONE;
 
-	n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].nh_gw, fi->fib_dev);
+	n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].fib_nh_gw4, fi->fib_dev);
 	if (n) {
 		state = n->nud_state;
 		neigh_release(n);
@@ -486,12 +486,12 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 		if (err)
 			goto lwt_failure;
 
-		nh->nh_lwtstate = lwtstate_get(lwtstate);
+		nh->fib_nh_lws = lwtstate_get(lwtstate);
 	}
 
-	nh->nh_oif = cfg->fc_oif;
-	nh->nh_gw = cfg->fc_gw;
-	nh->nh_flags = cfg->fc_flags;
+	nh->fib_nh_oif = cfg->fc_oif;
+	nh->fib_nh_gw4 = cfg->fc_gw;
+	nh->fib_nh_flags = cfg->fc_flags;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	nh->nh_tclassid = cfg->fc_flow;
@@ -499,7 +499,7 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 		net->ipv4.fib_num_tclassid_users++;
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-	nh->nh_weight = nh_weight;
+	nh->fib_nh_weight = nh_weight;
 #endif
 	return 0;
 
@@ -587,12 +587,12 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 	} endfor_nexthops(fi);
 
 	ret = -EINVAL;
-	if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif) {
+	if (cfg->fc_oif && fi->fib_nh->fib_nh_oif != cfg->fc_oif) {
 		NL_SET_ERR_MSG(extack,
 			       "Nexthop device index does not match RTA_OIF");
 		goto errout;
 	}
-	if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) {
+	if (cfg->fc_gw && fi->fib_nh->fib_nh_gw4 != cfg->fc_gw) {
 		NL_SET_ERR_MSG(extack,
 			       "Nexthop gateway does not match RTA_GATEWAY");
 		goto errout;
@@ -619,32 +619,32 @@ static void fib_rebalance(struct fib_info *fi)
 
 	total = 0;
 	for_nexthops(fi) {
-		if (nh->nh_flags & RTNH_F_DEAD)
+		if (nh->fib_nh_flags & RTNH_F_DEAD)
 			continue;
 
-		if (ip_ignore_linkdown(nh->nh_dev) &&
-		    nh->nh_flags & RTNH_F_LINKDOWN)
+		if (ip_ignore_linkdown(nh->fib_nh_dev) &&
+		    nh->fib_nh_flags & RTNH_F_LINKDOWN)
 			continue;
 
-		total += nh->nh_weight;
+		total += nh->fib_nh_weight;
 	} endfor_nexthops(fi);
 
 	w = 0;
 	change_nexthops(fi) {
 		int upper_bound;
 
-		if (nexthop_nh->nh_flags & RTNH_F_DEAD) {
+		if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) {
 			upper_bound = -1;
-		} else if (ip_ignore_linkdown(nexthop_nh->nh_dev) &&
-			   nexthop_nh->nh_flags & RTNH_F_LINKDOWN) {
+		} else if (ip_ignore_linkdown(nexthop_nh->fib_nh_dev) &&
+			   nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) {
 			upper_bound = -1;
 		} else {
-			w += nexthop_nh->nh_weight;
+			w += nexthop_nh->fib_nh_weight;
 			upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31,
 							    total) - 1;
 		}
 
-		atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
+		atomic_set(&nexthop_nh->fib_nh_upper_bound, upper_bound);
 	} endfor_nexthops(fi);
 }
 #else /* CONFIG_IP_ROUTE_MULTIPATH */
@@ -677,7 +677,7 @@ static int fib_encap_match(u16 encap_type,
 	ret = lwtunnel_build_state(encap_type, encap, AF_INET,
 				   cfg, &lwtstate, extack);
 	if (!ret) {
-		result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate);
+		result = lwtunnel_cmp_encap(lwtstate, nh->fib_nh_lws);
 		lwtstate_free(lwtstate);
 	}
 
@@ -706,8 +706,8 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 		    cfg->fc_flow != fi->fib_nh->nh_tclassid)
 			return 1;
 #endif
-		if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
-		    (!cfg->fc_gw  || cfg->fc_gw == fi->fib_nh->nh_gw))
+		if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->fib_nh_oif) &&
+		    (!cfg->fc_gw  || cfg->fc_gw == fi->fib_nh->fib_nh_gw4))
 			return 0;
 		return 1;
 	}
@@ -725,7 +725,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 		if (!rtnh_ok(rtnh, remaining))
 			return -EINVAL;
 
-		if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->nh_oif)
+		if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->fib_nh_oif)
 			return 1;
 
 		attrlen = rtnh_attrlen(rtnh);
@@ -733,7 +733,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
-			if (nla && nla_get_in_addr(nla) != nh->nh_gw)
+			if (nla && nla_get_in_addr(nla) != nh->fib_nh_gw4)
 				return 1;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
@@ -840,10 +840,10 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
 	struct net_device *dev;
 
 	net = cfg->fc_nlinfo.nl_net;
-	if (nh->nh_gw) {
+	if (nh->fib_nh_gw4) {
 		struct fib_result res;
 
-		if (nh->nh_flags & RTNH_F_ONLINK) {
+		if (nh->fib_nh_flags & RTNH_F_ONLINK) {
 			unsigned int addr_type;
 
 			if (cfg->fc_scope >= RT_SCOPE_LINK) {
@@ -851,7 +851,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
 					       "Nexthop has invalid scope");
 				return -EINVAL;
 			}
-			dev = __dev_get_by_index(net, nh->nh_oif);
+			dev = __dev_get_by_index(net, nh->fib_nh_oif);
 			if (!dev) {
 				NL_SET_ERR_MSG(extack, "Nexthop device required for onlink");
 				return -ENODEV;
@@ -861,26 +861,27 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
 					       "Nexthop device is not up");
 				return -ENETDOWN;
 			}
-			addr_type = inet_addr_type_dev_table(net, dev, nh->nh_gw);
+			addr_type = inet_addr_type_dev_table(net, dev,
+							     nh->fib_nh_gw4);
 			if (addr_type != RTN_UNICAST) {
 				NL_SET_ERR_MSG(extack,
 					       "Nexthop has invalid gateway");
 				return -EINVAL;
 			}
 			if (!netif_carrier_ok(dev))
-				nh->nh_flags |= RTNH_F_LINKDOWN;
-			nh->nh_dev = dev;
+				nh->fib_nh_flags |= RTNH_F_LINKDOWN;
+			nh->fib_nh_dev = dev;
 			dev_hold(dev);
-			nh->nh_scope = RT_SCOPE_LINK;
+			nh->fib_nh_scope = RT_SCOPE_LINK;
 			return 0;
 		}
 		rcu_read_lock();
 		{
 			struct fib_table *tbl = NULL;
 			struct flowi4 fl4 = {
-				.daddr = nh->nh_gw,
+				.daddr = nh->fib_nh_gw4,
 				.flowi4_scope = cfg->fc_scope + 1,
-				.flowi4_oif = nh->nh_oif,
+				.flowi4_oif = nh->fib_nh_oif,
 				.flowi4_iif = LOOPBACK_IFINDEX,
 			};
 
@@ -917,9 +918,9 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
 			NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
 			goto out;
 		}
-		nh->nh_scope = res.scope;
-		nh->nh_oif = FIB_RES_OIF(res);
-		nh->nh_dev = dev = FIB_RES_DEV(res);
+		nh->fib_nh_scope = res.scope;
+		nh->fib_nh_oif = FIB_RES_OIF(res);
+		nh->fib_nh_dev = dev = FIB_RES_DEV(res);
 		if (!dev) {
 			NL_SET_ERR_MSG(extack,
 				       "No egress device for nexthop gateway");
@@ -927,19 +928,19 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
 		}
 		dev_hold(dev);
 		if (!netif_carrier_ok(dev))
-			nh->nh_flags |= RTNH_F_LINKDOWN;
+			nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 		err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN;
 	} else {
 		struct in_device *in_dev;
 
-		if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) {
+		if (nh->fib_nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) {
 			NL_SET_ERR_MSG(extack,
 				       "Invalid flags for nexthop - PERVASIVE and ONLINK can not be set");
 			return -EINVAL;
 		}
 		rcu_read_lock();
 		err = -ENODEV;
-		in_dev = inetdev_by_index(net, nh->nh_oif);
+		in_dev = inetdev_by_index(net, nh->fib_nh_oif);
 		if (!in_dev)
 			goto out;
 		err = -ENETDOWN;
@@ -947,11 +948,11 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh,
 			NL_SET_ERR_MSG(extack, "Device for nexthop is not up");
 			goto out;
 		}
-		nh->nh_dev = in_dev->dev;
-		dev_hold(nh->nh_dev);
-		nh->nh_scope = RT_SCOPE_HOST;
-		if (!netif_carrier_ok(nh->nh_dev))
-			nh->nh_flags |= RTNH_F_LINKDOWN;
+		nh->fib_nh_dev = in_dev->dev;
+		dev_hold(nh->fib_nh_dev);
+		nh->fib_nh_scope = RT_SCOPE_HOST;
+		if (!netif_carrier_ok(nh->fib_nh_dev))
+			nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 		err = 0;
 	}
 out:
@@ -1043,8 +1044,8 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
 
 __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
 {
-	nh->nh_saddr = inet_select_addr(nh->nh_dev,
-					nh->nh_gw,
+	nh->nh_saddr = inet_select_addr(nh->fib_nh_dev,
+					nh->fib_nh_gw4,
 					nh->nh_parent->fib_scope);
 	nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);
 
@@ -1198,15 +1199,15 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 				       "Route with host scope can not have multiple nexthops");
 			goto err_inval;
 		}
-		if (nh->nh_gw) {
+		if (nh->fib_nh_gw4) {
 			NL_SET_ERR_MSG(extack,
 				       "Route with host scope can not have a gateway");
 			goto err_inval;
 		}
-		nh->nh_scope = RT_SCOPE_NOWHERE;
-		nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif);
+		nh->fib_nh_scope = RT_SCOPE_NOWHERE;
+		nh->fib_nh_dev = dev_get_by_index(net, fi->fib_nh->fib_nh_oif);
 		err = -ENODEV;
-		if (!nh->nh_dev)
+		if (!nh->fib_nh_dev)
 			goto failure;
 	} else {
 		int linkdown = 0;
@@ -1215,7 +1216,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 			err = fib_check_nh(cfg, nexthop_nh, extack);
 			if (err != 0)
 				goto failure;
-			if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
+			if (nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN)
 				linkdown++;
 		} endfor_nexthops(fi)
 		if (linkdown == fi->fib_nhs)
@@ -1257,9 +1258,9 @@ link_it:
 		struct hlist_head *head;
 		unsigned int hash;
 
-		if (!nexthop_nh->nh_dev)
+		if (!nexthop_nh->fib_nh_dev)
 			continue;
-		hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex);
+		hash = fib_devindex_hashfn(nexthop_nh->fib_nh_dev->ifindex);
 		head = &fib_info_devhash[hash];
 		hlist_add_head(&nexthop_nh->nh_hash, head);
 	} endfor_nexthops(fi)
@@ -1318,27 +1319,27 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 	    nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc))
 		goto nla_put_failure;
 	if (fi->fib_nhs == 1) {
-		if (fi->fib_nh->nh_gw &&
-		    nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->nh_gw))
+		if (fi->fib_nh->fib_nh_gw4 &&
+		    nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->fib_nh_gw4))
 			goto nla_put_failure;
-		if (fi->fib_nh->nh_oif &&
-		    nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif))
+		if (fi->fib_nh->fib_nh_oif &&
+		    nla_put_u32(skb, RTA_OIF, fi->fib_nh->fib_nh_oif))
 			goto nla_put_failure;
-		if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) {
+		if (fi->fib_nh->fib_nh_flags & RTNH_F_LINKDOWN) {
 			rcu_read_lock();
-			if (ip_ignore_linkdown(fi->fib_nh->nh_dev))
+			if (ip_ignore_linkdown(fi->fib_nh->fib_nh_dev))
 				rtm->rtm_flags |= RTNH_F_DEAD;
 			rcu_read_unlock();
 		}
-		if (fi->fib_nh->nh_flags & RTNH_F_OFFLOAD)
+		if (fi->fib_nh->fib_nh_flags & RTNH_F_OFFLOAD)
 			rtm->rtm_flags |= RTNH_F_OFFLOAD;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		if (fi->fib_nh[0].nh_tclassid &&
 		    nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
 			goto nla_put_failure;
 #endif
-		if (fi->fib_nh->nh_lwtstate &&
-		    lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate) < 0)
+		if (fi->fib_nh->fib_nh_lws &&
+		    lwtunnel_fill_encap(skb, fi->fib_nh->fib_nh_lws) < 0)
 			goto nla_put_failure;
 	}
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -1355,26 +1356,26 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			if (!rtnh)
 				goto nla_put_failure;
 
-			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
-			if (nh->nh_flags & RTNH_F_LINKDOWN) {
+			rtnh->rtnh_flags = nh->fib_nh_flags & 0xFF;
+			if (nh->fib_nh_flags & RTNH_F_LINKDOWN) {
 				rcu_read_lock();
-				if (ip_ignore_linkdown(nh->nh_dev))
+				if (ip_ignore_linkdown(nh->fib_nh_dev))
 					rtnh->rtnh_flags |= RTNH_F_DEAD;
 				rcu_read_unlock();
 			}
-			rtnh->rtnh_hops = nh->nh_weight - 1;
-			rtnh->rtnh_ifindex = nh->nh_oif;
+			rtnh->rtnh_hops = nh->fib_nh_weight - 1;
+			rtnh->rtnh_ifindex = nh->fib_nh_oif;
 
-			if (nh->nh_gw &&
-			    nla_put_in_addr(skb, RTA_GATEWAY, nh->nh_gw))
+			if (nh->fib_nh_gw4 &&
+			    nla_put_in_addr(skb, RTA_GATEWAY, nh->fib_nh_gw4))
 				goto nla_put_failure;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 			if (nh->nh_tclassid &&
 			    nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
 				goto nla_put_failure;
 #endif
-			if (nh->nh_lwtstate &&
-			    lwtunnel_fill_encap(skb, nh->nh_lwtstate) < 0)
+			if (nh->fib_nh_lws &&
+			    lwtunnel_fill_encap(skb, nh->fib_nh_lws) < 0)
 				goto nla_put_failure;
 
 			/* length of rtnetlink header + attributes */
@@ -1422,26 +1423,26 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
 	return ret;
 }
 
-static int call_fib_nh_notifiers(struct fib_nh *fib_nh,
+static int call_fib_nh_notifiers(struct fib_nh *nh,
 				 enum fib_event_type event_type)
 {
-	bool ignore_link_down = ip_ignore_linkdown(fib_nh->nh_dev);
+	bool ignore_link_down = ip_ignore_linkdown(nh->fib_nh_dev);
 	struct fib_nh_notifier_info info = {
-		.fib_nh = fib_nh,
+		.fib_nh = nh,
 	};
 
 	switch (event_type) {
 	case FIB_EVENT_NH_ADD:
-		if (fib_nh->nh_flags & RTNH_F_DEAD)
+		if (nh->fib_nh_flags & RTNH_F_DEAD)
 			break;
-		if (ignore_link_down && fib_nh->nh_flags & RTNH_F_LINKDOWN)
+		if (ignore_link_down && nh->fib_nh_flags & RTNH_F_LINKDOWN)
 			break;
-		return call_fib4_notifiers(dev_net(fib_nh->nh_dev), event_type,
+		return call_fib4_notifiers(dev_net(nh->fib_nh_dev), event_type,
 					   &info.info);
 	case FIB_EVENT_NH_DEL:
-		if ((ignore_link_down && fib_nh->nh_flags & RTNH_F_LINKDOWN) ||
-		    (fib_nh->nh_flags & RTNH_F_DEAD))
-			return call_fib4_notifiers(dev_net(fib_nh->nh_dev),
+		if ((ignore_link_down && nh->fib_nh_flags & RTNH_F_LINKDOWN) ||
+		    (nh->fib_nh_flags & RTNH_F_DEAD))
+			return call_fib4_notifiers(dev_net(nh->fib_nh_dev),
 						   event_type, &info.info);
 	default:
 		break;
@@ -1495,7 +1496,7 @@ void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
 	struct fib_nh *nh;
 
 	hlist_for_each_entry(nh, head, nh_hash) {
-		if (nh->nh_dev == dev)
+		if (nh->fib_nh_dev == dev)
 			nh_update_mtu(nh, dev->mtu, orig_mtu);
 	}
 }
@@ -1523,22 +1524,22 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
 		int dead;
 
 		BUG_ON(!fi->fib_nhs);
-		if (nh->nh_dev != dev || fi == prev_fi)
+		if (nh->fib_nh_dev != dev || fi == prev_fi)
 			continue;
 		prev_fi = fi;
 		dead = 0;
 		change_nexthops(fi) {
-			if (nexthop_nh->nh_flags & RTNH_F_DEAD)
+			if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD)
 				dead++;
-			else if (nexthop_nh->nh_dev == dev &&
-				 nexthop_nh->nh_scope != scope) {
+			else if (nexthop_nh->fib_nh_dev == dev &&
+				 nexthop_nh->fib_nh_scope != scope) {
 				switch (event) {
 				case NETDEV_DOWN:
 				case NETDEV_UNREGISTER:
-					nexthop_nh->nh_flags |= RTNH_F_DEAD;
+					nexthop_nh->fib_nh_flags |= RTNH_F_DEAD;
 					/* fall through */
 				case NETDEV_CHANGE:
-					nexthop_nh->nh_flags |= RTNH_F_LINKDOWN;
+					nexthop_nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 					break;
 				}
 				call_fib_nh_notifiers(nexthop_nh,
@@ -1547,7 +1548,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
 			}
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 			if (event == NETDEV_UNREGISTER &&
-			    nexthop_nh->nh_dev == dev) {
+			    nexthop_nh->fib_nh_dev == dev) {
 				dead = fi->fib_nhs;
 				break;
 			}
@@ -1607,8 +1608,8 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 		if (next_fi->fib_scope != res->scope ||
 		    fa->fa_type != RTN_UNICAST)
 			continue;
-		if (!next_fi->fib_nh[0].nh_gw ||
-		    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
+		if (!next_fi->fib_nh[0].fib_nh_gw4 ||
+		    next_fi->fib_nh[0].fib_nh_scope != RT_SCOPE_LINK)
 			continue;
 
 		fib_alias_accessed(fa);
@@ -1679,24 +1680,24 @@ int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
 		int alive;
 
 		BUG_ON(!fi->fib_nhs);
-		if (nh->nh_dev != dev || fi == prev_fi)
+		if (nh->fib_nh_dev != dev || fi == prev_fi)
 			continue;
 
 		prev_fi = fi;
 		alive = 0;
 		change_nexthops(fi) {
-			if (!(nexthop_nh->nh_flags & nh_flags)) {
+			if (!(nexthop_nh->fib_nh_flags & nh_flags)) {
 				alive++;
 				continue;
 			}
-			if (!nexthop_nh->nh_dev ||
-			    !(nexthop_nh->nh_dev->flags & IFF_UP))
+			if (!nexthop_nh->fib_nh_dev ||
+			    !(nexthop_nh->fib_nh_dev->flags & IFF_UP))
 				continue;
-			if (nexthop_nh->nh_dev != dev ||
+			if (nexthop_nh->fib_nh_dev != dev ||
 			    !__in_dev_get_rtnl(dev))
 				continue;
 			alive++;
-			nexthop_nh->nh_flags &= ~nh_flags;
+			nexthop_nh->fib_nh_flags &= ~nh_flags;
 			call_fib_nh_notifiers(nexthop_nh, FIB_EVENT_NH_ADD);
 		} endfor_nexthops(fi)
 
@@ -1716,13 +1717,13 @@ static bool fib_good_nh(const struct fib_nh *nh)
 {
 	int state = NUD_REACHABLE;
 
-	if (nh->nh_scope == RT_SCOPE_LINK) {
+	if (nh->fib_nh_scope == RT_SCOPE_LINK) {
 		struct neighbour *n;
 
 		rcu_read_lock_bh();
 
-		n = __ipv4_neigh_lookup_noref(nh->nh_dev,
-					      (__force u32)nh->nh_gw);
+		n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev,
+					      (__force u32)nh->fib_nh_gw4);
 		if (n)
 			state = n->nud_state;
 
@@ -1748,7 +1749,7 @@ void fib_select_multipath(struct fib_result *res, int hash)
 			}
 		}
 
-		if (hash > atomic_read(&nh->nh_upper_bound))
+		if (hash > atomic_read(&nh->fib_nh_upper_bound))
 			continue;
 
 		res->nh_sel = nhsel;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 656d3d19f112..1e3b492690f9 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1472,15 +1472,15 @@ found:
 		for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
 			const struct fib_nh *nh = &fi->fib_nh[nhsel];
 
-			if (nh->nh_flags & RTNH_F_DEAD)
+			if (nh->fib_nh_flags & RTNH_F_DEAD)
 				continue;
-			if (ip_ignore_linkdown(nh->nh_dev) &&
-			    nh->nh_flags & RTNH_F_LINKDOWN &&
+			if (ip_ignore_linkdown(nh->fib_nh_dev) &&
+			    nh->fib_nh_flags & RTNH_F_LINKDOWN &&
 			    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
 				continue;
 			if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
 				if (flp->flowi4_oif &&
-				    flp->flowi4_oif != nh->nh_oif)
+				    flp->flowi4_oif != nh->fib_nh_oif)
 					continue;
 			}
 
@@ -2651,7 +2651,7 @@ static unsigned int fib_flag_trans(int type, __be32 mask, const struct fib_info
 
 	if (type == RTN_UNREACHABLE || type == RTN_PROHIBIT)
 		flags = RTF_REJECT;
-	if (fi && fi->fib_nh->nh_gw)
+	if (fi && fi->fib_nh->fib_nh_gw4)
 		flags |= RTF_GATEWAY;
 	if (mask == htonl(0xFFFFFFFF))
 		flags |= RTF_HOST;
@@ -2702,7 +2702,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v)
 				   "%d\t%08X\t%d\t%u\t%u",
 				   fi->fib_dev ? fi->fib_dev->name : "*",
 				   prefix,
-				   fi->fib_nh->nh_gw, flags, 0, 0,
+				   fi->fib_nh->fib_nh_gw4, flags, 0, 0,
 				   fi->fib_priority,
 				   mask,
 				   (fi->fib_advmss ?
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f2688fce39e1..7977514d90f5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -644,7 +644,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 	unsigned int i;
 	int depth;
 
-	genid = fnhe_genid(dev_net(nh->nh_dev));
+	genid = fnhe_genid(dev_net(nh->fib_nh_dev));
 	hval = fnhe_hashfun(daddr);
 
 	spin_lock_bh(&fnhe_lock);
@@ -1356,7 +1356,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 {
 	struct fib_info *fi = res->fi;
 	struct fib_nh *nh = &fi->fib_nh[res->nh_sel];
-	struct net_device *dev = nh->nh_dev;
+	struct net_device *dev = nh->fib_nh_dev;
 	u32 mtu = 0;
 
 	if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu ||
@@ -1374,7 +1374,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 	if (likely(!mtu))
 		mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU);
 
-	return mtu - lwtunnel_headroom(nh->nh_lwtstate, mtu);
+	return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
 }
 
 static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
@@ -1531,8 +1531,8 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 	if (fi) {
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
-		if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) {
-			rt->rt_gateway = nh->nh_gw;
+		if (nh->fib_nh_gw4 && nh->fib_nh_scope == RT_SCOPE_LINK) {
+			rt->rt_gateway = nh->fib_nh_gw4;
 			rt->rt_uses_gateway = 1;
 		}
 		ip_dst_init_metrics(&rt->dst, fi->fib_metrics);
@@ -1540,7 +1540,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
 #endif
-		rt->dst.lwtstate = lwtstate_get(nh->nh_lwtstate);
+		rt->dst.lwtstate = lwtstate_get(nh->fib_nh_lws);
 		if (unlikely(fnhe))
 			cached = rt_bind_exception(rt, fnhe, daddr, do_cache);
 		else if (do_cache)
@@ -2075,7 +2075,7 @@ local_input:
 	if (do_cache) {
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
-		rth->dst.lwtstate = lwtstate_get(nh->nh_lwtstate);
+		rth->dst.lwtstate = lwtstate_get(nh->fib_nh_lws);
 		if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
 			WARN_ON(rth->dst.input == lwtunnel_input);
 			rth->dst.lwtstate->orig_input = rth->dst.input;
@@ -2264,8 +2264,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		} else {
 			if (unlikely(fl4->flowi4_flags &
 				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->nh_gw &&
-				       nh->nh_scope == RT_SCOPE_LINK))) {
+				     !(nh->fib_nh_gw4 &&
+				       nh->fib_nh_scope == RT_SCOPE_LINK))) {
 				do_cache = false;
 				goto add;
 			}
-- 
cgit v1.2.3


From ad1601ae0260551f85691ca1ac814773fdcec239 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:56 -0700
Subject: ipv6: Rename fib6_nh entries

Rename fib6_nh entries that will be moved to a fib_nh_common struct.
Specifically, the device, gateway, flags, and lwtstate are common
with all nexthop definitions. In some places new temporary variables
are declared or local variables renamed to maintain line lengths.

Rename only; no functional change intended.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  |  34 ++--
 include/net/ip6_fib.h                              |  16 +-
 include/net/ip6_route.h                            |   8 +-
 include/trace/events/fib6.h                        |   6 +-
 net/core/filter.c                                  |   6 +-
 net/ipv6/addrconf.c                                |   2 +-
 net/ipv6/ip6_fib.c                                 |   4 +-
 net/ipv6/ndisc.c                                   |   8 +-
 net/ipv6/route.c                                   | 181 +++++++++++----------
 9 files changed, 138 insertions(+), 127 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index a18e1ae1c2f6..0ba9daa05a52 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2873,12 +2873,13 @@ mlxsw_sp_nexthop6_group_cmp(const struct mlxsw_sp_nexthop_group *nh_grp,
 		return false;
 
 	list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
+		struct fib6_nh *fib6_nh = &mlxsw_sp_rt6->rt->fib6_nh;
 		struct in6_addr *gw;
 		int ifindex, weight;
 
-		ifindex = mlxsw_sp_rt6->rt->fib6_nh.nh_dev->ifindex;
-		weight = mlxsw_sp_rt6->rt->fib6_nh.nh_weight;
-		gw = &mlxsw_sp_rt6->rt->fib6_nh.nh_gw;
+		ifindex = fib6_nh->fib_nh_dev->ifindex;
+		weight = fib6_nh->fib_nh_weight;
+		gw = &fib6_nh->fib_nh_gw6;
 		if (!mlxsw_sp_nexthop6_group_has_nexthop(nh_grp, gw, ifindex,
 							 weight))
 			return false;
@@ -2944,7 +2945,7 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed)
 	struct net_device *dev;
 
 	list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
-		dev = mlxsw_sp_rt6->rt->fib6_nh.nh_dev;
+		dev = mlxsw_sp_rt6->rt->fib6_nh.fib_nh_dev;
 		val ^= dev->ifindex;
 	}
 
@@ -3946,9 +3947,9 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp,
 		struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
 		struct fib6_info *rt = mlxsw_sp_rt6->rt;
 
-		if (nh->rif && nh->rif->dev == rt->fib6_nh.nh_dev &&
+		if (nh->rif && nh->rif->dev == rt->fib6_nh.fib_nh_dev &&
 		    ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr,
-				    &rt->fib6_nh.nh_gw))
+				    &rt->fib6_nh.fib_nh_gw6))
 			return nh;
 		continue;
 	}
@@ -4008,19 +4009,20 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 	if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL ||
 	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE) {
 		list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6,
-				 list)->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD;
+				 list)->rt->fib6_nh.fib_nh_flags |= RTNH_F_OFFLOAD;
 		return;
 	}
 
 	list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
 		struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group;
+		struct fib6_nh *fib6_nh = &mlxsw_sp_rt6->rt->fib6_nh;
 		struct mlxsw_sp_nexthop *nh;
 
 		nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6);
 		if (nh && nh->offloaded)
-			mlxsw_sp_rt6->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD;
+			fib6_nh->fib_nh_flags |= RTNH_F_OFFLOAD;
 		else
-			mlxsw_sp_rt6->rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD;
+			fib6_nh->fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	}
 }
 
@@ -4035,7 +4037,7 @@ mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
 	list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
 		struct fib6_info *rt = mlxsw_sp_rt6->rt;
 
-		rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD;
+		rt->fib6_nh.fib_nh_flags &= ~RTNH_F_OFFLOAD;
 	}
 }
 
@@ -4972,8 +4974,8 @@ static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp,
 					const struct fib6_info *rt,
 					enum mlxsw_sp_ipip_type *ret)
 {
-	return rt->fib6_nh.nh_dev &&
-	       mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh.nh_dev, ret);
+	return rt->fib6_nh.fib_nh_dev &&
+	       mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh.fib_nh_dev, ret);
 }
 
 static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
@@ -4983,7 +4985,7 @@ static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
 {
 	const struct mlxsw_sp_ipip_ops *ipip_ops;
 	struct mlxsw_sp_ipip_entry *ipip_entry;
-	struct net_device *dev = rt->fib6_nh.nh_dev;
+	struct net_device *dev = rt->fib6_nh.fib_nh_dev;
 	struct mlxsw_sp_rif *rif;
 	int err;
 
@@ -5026,11 +5028,11 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_nexthop *nh,
 				  const struct fib6_info *rt)
 {
-	struct net_device *dev = rt->fib6_nh.nh_dev;
+	struct net_device *dev = rt->fib6_nh.fib_nh_dev;
 
 	nh->nh_grp = nh_grp;
-	nh->nh_weight = rt->fib6_nh.nh_weight;
-	memcpy(&nh->gw_addr, &rt->fib6_nh.nh_gw, sizeof(nh->gw_addr));
+	nh->nh_weight = rt->fib6_nh.fib_nh_weight;
+	memcpy(&nh->gw_addr, &rt->fib6_nh.fib_nh_gw6, sizeof(nh->gw_addr));
 	mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
 
 	list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 3b04b318cf13..aff8570725c8 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -125,14 +125,14 @@ struct rt6_exception {
 #define FIB6_MAX_DEPTH 5
 
 struct fib6_nh {
-	struct in6_addr		nh_gw;
+	struct in6_addr		fib_nh_gw6;
 	bool			fib_nh_has_gw;
-	struct net_device	*nh_dev;
-	struct lwtunnel_state	*nh_lwtstate;
+	struct net_device	*fib_nh_dev;
+	struct lwtunnel_state	*fib_nh_lws;
 
-	unsigned int		nh_flags;
-	atomic_t		nh_upper_bound;
-	int			nh_weight;
+	unsigned int		fib_nh_flags;
+	atomic_t		fib_nh_upper_bound;
+	int			fib_nh_weight;
 };
 
 struct fib6_info {
@@ -442,7 +442,7 @@ void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr)
 
 static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i)
 {
-	return f6i->fib6_nh.nh_dev;
+	return f6i->fib6_nh.fib_nh_dev;
 }
 
 int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
@@ -453,7 +453,7 @@ void fib6_nh_release(struct fib6_nh *fib6_nh);
 static inline
 struct lwtunnel_state *fib6_info_nh_lwt(const struct fib6_info *f6i)
 {
-	return f6i->fib6_nh.nh_lwtstate;
+	return f6i->fib6_nh.fib_nh_lws;
 }
 
 void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 95cd8a2f6284..342180a7285c 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -274,9 +274,11 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
 
 static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b)
 {
-	return a->fib6_nh.nh_dev == b->fib6_nh.nh_dev &&
-	       ipv6_addr_equal(&a->fib6_nh.nh_gw, &b->fib6_nh.nh_gw) &&
-	       !lwtunnel_cmp_encap(a->fib6_nh.nh_lwtstate, b->fib6_nh.nh_lwtstate);
+	struct fib6_nh *nha = &a->fib6_nh, *nhb = &b->fib6_nh;
+
+	return nha->fib_nh_dev == nhb->fib_nh_dev &&
+	       ipv6_addr_equal(&nha->fib_nh_gw6, &nhb->fib_nh_gw6) &&
+	       !lwtunnel_cmp_encap(nha->fib_nh_lws, nhb->fib_nh_lws);
 }
 
 static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
diff --git a/include/trace/events/fib6.h b/include/trace/events/fib6.h
index b088b54d699c..6d05ebdd669c 100644
--- a/include/trace/events/fib6.h
+++ b/include/trace/events/fib6.h
@@ -62,8 +62,8 @@ TRACE_EVENT(fib6_table_lookup,
 			__entry->dport = 0;
 		}
 
-		if (f6i->fib6_nh.nh_dev) {
-			__assign_str(name, f6i->fib6_nh.nh_dev);
+		if (f6i->fib6_nh.fib_nh_dev) {
+			__assign_str(name, f6i->fib6_nh.fib_nh_dev);
 		} else {
 			__assign_str(name, "-");
 		}
@@ -75,7 +75,7 @@ TRACE_EVENT(fib6_table_lookup,
 
 		} else if (f6i) {
 			in6 = (struct in6_addr *)__entry->gw;
-			*in6 = f6i->fib6_nh.nh_gw;
+			*in6 = f6i->fib6_nh.fib_nh_gw6;
 		}
 	),
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 79d319c636ea..887ab073a0ea 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4748,13 +4748,13 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
-	if (f6i->fib6_nh.nh_lwtstate)
+	if (f6i->fib6_nh.fib_nh_lws)
 		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
 	if (f6i->fib6_nh.fib_nh_has_gw)
-		*dst = f6i->fib6_nh.nh_gw;
+		*dst = f6i->fib6_nh.fib_nh_gw6;
 
-	dev = f6i->fib6_nh.nh_dev;
+	dev = f6i->fib6_nh.fib_nh_dev;
 	params->rt_metric = f6i->fib6_metric;
 
 	/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c5ac08fc6cc9..2e8d1d2d8d3d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2419,7 +2419,7 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 		goto out;
 
 	for_each_fib6_node_rt_rcu(fn) {
-		if (rt->fib6_nh.nh_dev->ifindex != dev->ifindex)
+		if (rt->fib6_nh.fib_nh_dev->ifindex != dev->ifindex)
 			continue;
 		if (no_gw && rt->fib6_nh.fib_nh_has_gw)
 			continue;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 91ce84ecdb57..8c00609a1513 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2306,12 +2306,12 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 #endif
 	if (rt->fib6_nh.fib_nh_has_gw) {
 		flags |= RTF_GATEWAY;
-		seq_printf(seq, "%pi6", &rt->fib6_nh.nh_gw);
+		seq_printf(seq, "%pi6", &rt->fib6_nh.fib_nh_gw6);
 	} else {
 		seq_puts(seq, "00000000000000000000000000000000");
 	}
 
-	dev = rt->fib6_nh.nh_dev;
+	dev = rt->fib6_nh.fib_nh_dev;
 	seq_printf(seq, " %08x %08x %08x %08x %8s\n",
 		   rt->fib6_metric, atomic_read(&rt->fib6_ref), 0,
 		   flags, dev ? dev->name : "");
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 659ecf4e4b3c..66c8b294e02b 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1276,8 +1276,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev);
 
 	if (rt) {
-		neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw,
-					 rt->fib6_nh.nh_dev, NULL,
+		neigh = ip6_neigh_lookup(&rt->fib6_nh.fib_nh_gw6,
+					 rt->fib6_nh.fib_nh_dev, NULL,
 					  &ipv6_hdr(skb)->saddr);
 		if (!neigh) {
 			ND_PRINTK(0, err,
@@ -1306,8 +1306,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 			return;
 		}
 
-		neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw,
-					 rt->fib6_nh.nh_dev, NULL,
+		neigh = ip6_neigh_lookup(&rt->fib6_nh.fib_nh_gw6,
+					 rt->fib6_nh.fib_nh_dev, NULL,
 					  &ipv6_hdr(skb)->saddr);
 		if (!neigh) {
 			ND_PRINTK(0, err,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 681c7184e157..e4c2f8e43405 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -441,14 +441,14 @@ struct fib6_info *fib6_multipath_select(const struct net *net,
 	if (!fl6->mp_hash)
 		fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
 
-	if (fl6->mp_hash <= atomic_read(&match->fib6_nh.nh_upper_bound))
+	if (fl6->mp_hash <= atomic_read(&match->fib6_nh.fib_nh_upper_bound))
 		return match;
 
 	list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
 				 fib6_siblings) {
 		int nh_upper_bound;
 
-		nh_upper_bound = atomic_read(&sibling->fib6_nh.nh_upper_bound);
+		nh_upper_bound = atomic_read(&sibling->fib6_nh.fib_nh_upper_bound);
 		if (fl6->mp_hash > nh_upper_bound)
 			continue;
 		if (rt6_score_route(sibling, oif, strict) < 0)
@@ -473,13 +473,13 @@ static inline struct fib6_info *rt6_device_match(struct net *net,
 	struct fib6_info *sprt;
 
 	if (!oif && ipv6_addr_any(saddr) &&
-	    !(rt->fib6_nh.nh_flags & RTNH_F_DEAD))
+	    !(rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD))
 		return rt;
 
 	for (sprt = rt; sprt; sprt = rcu_dereference(sprt->fib6_next)) {
-		const struct net_device *dev = sprt->fib6_nh.nh_dev;
+		const struct net_device *dev = sprt->fib6_nh.fib_nh_dev;
 
-		if (sprt->fib6_nh.nh_flags & RTNH_F_DEAD)
+		if (sprt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
 			continue;
 
 		if (oif) {
@@ -495,7 +495,7 @@ static inline struct fib6_info *rt6_device_match(struct net *net,
 	if (oif && flags & RT6_LOOKUP_F_IFACE)
 		return net->ipv6.fib6_null_entry;
 
-	return rt->fib6_nh.nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt;
+	return rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt;
 }
 
 #ifdef CONFIG_IPV6_ROUTER_PREF
@@ -536,8 +536,8 @@ static void rt6_probe(struct fib6_info *rt)
 	if (!rt || !rt->fib6_nh.fib_nh_has_gw)
 		return;
 
-	nh_gw = &rt->fib6_nh.nh_gw;
-	dev = rt->fib6_nh.nh_dev;
+	nh_gw = &rt->fib6_nh.fib_nh_gw6;
+	dev = rt->fib6_nh.fib_nh_dev;
 	rcu_read_lock_bh();
 	idev = __in6_dev_get(dev);
 	neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
@@ -582,7 +582,7 @@ static inline void rt6_probe(struct fib6_info *rt)
  */
 static inline int rt6_check_dev(struct fib6_info *rt, int oif)
 {
-	const struct net_device *dev = rt->fib6_nh.nh_dev;
+	const struct net_device *dev = rt->fib6_nh.fib_nh_dev;
 
 	if (!oif || dev->ifindex == oif)
 		return 2;
@@ -599,8 +599,8 @@ static inline enum rt6_nud_state rt6_check_neigh(struct fib6_info *rt)
 		return RT6_NUD_SUCCEED;
 
 	rcu_read_lock_bh();
-	neigh = __ipv6_neigh_lookup_noref(rt->fib6_nh.nh_dev,
-					  &rt->fib6_nh.nh_gw);
+	neigh = __ipv6_neigh_lookup_noref(rt->fib6_nh.fib_nh_dev,
+					  &rt->fib6_nh.fib_nh_gw6);
 	if (neigh) {
 		read_lock(&neigh->lock);
 		if (neigh->nud_state & NUD_VALID)
@@ -646,11 +646,11 @@ static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict,
 	int m;
 	bool match_do_rr = false;
 
-	if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
+	if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
 		goto out;
 
-	if (ip6_ignore_linkdown(rt->fib6_nh.nh_dev) &&
-	    rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
+	if (ip6_ignore_linkdown(rt->fib6_nh.fib_nh_dev) &&
+	    rt->fib6_nh.fib_nh_flags & RTNH_F_LINKDOWN &&
 	    !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
 		goto out;
 
@@ -855,7 +855,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 /* called with rcu_lock held */
 static struct net_device *ip6_rt_get_dev_rcu(struct fib6_info *rt)
 {
-	struct net_device *dev = rt->fib6_nh.nh_dev;
+	struct net_device *dev = rt->fib6_nh.fib_nh_dev;
 
 	if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) {
 		/* for copies of local routes, dst->dev needs to be the
@@ -949,8 +949,8 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
 		rt->dst.input = ip6_forward;
 	}
 
-	if (ort->fib6_nh.nh_lwtstate) {
-		rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate);
+	if (ort->fib6_nh.fib_nh_lws) {
+		rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.fib_nh_lws);
 		lwtunnel_set_redirect(&rt->dst);
 	}
 
@@ -976,7 +976,7 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
 	rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL;
 	rt->rt6i_flags = ort->fib6_flags;
 	if (ort->fib6_nh.fib_nh_has_gw) {
-		rt->rt6i_gateway = ort->fib6_nh.nh_gw;
+		rt->rt6i_gateway = ort->fib6_nh.fib_nh_gw6;
 		rt->rt6i_flags |= RTF_GATEWAY;
 	}
 	rt6_set_from(rt, ort);
@@ -1023,7 +1023,7 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt)
 static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
 {
 	unsigned short flags = fib6_info_dst_flags(rt);
-	struct net_device *dev = rt->fib6_nh.nh_dev;
+	struct net_device *dev = rt->fib6_nh.fib_nh_dev;
 	struct rt6_info *nrt;
 
 	if (!fib6_info_hold_safe(rt))
@@ -1407,7 +1407,7 @@ static unsigned int fib6_mtu(const struct fib6_info *rt)
 
 	mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
 
-	return mtu - lwtunnel_headroom(rt->fib6_nh.nh_lwtstate, mtu);
+	return mtu - lwtunnel_headroom(rt->fib6_nh.fib_nh_lws, mtu);
 }
 
 static int rt6_insert_exception(struct rt6_info *nrt,
@@ -2424,7 +2424,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
 	for_each_fib6_node_rt_rcu(fn) {
-		if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
+		if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
 			continue;
 		if (fib6_check_expired(rt))
 			continue;
@@ -2432,14 +2432,14 @@ restart:
 			break;
 		if (!rt->fib6_nh.fib_nh_has_gw)
 			continue;
-		if (fl6->flowi6_oif != rt->fib6_nh.nh_dev->ifindex)
+		if (fl6->flowi6_oif != rt->fib6_nh.fib_nh_dev->ifindex)
 			continue;
 		/* rt_cache's gateway might be different from its 'parent'
 		 * in the case of an ip redirect.
 		 * So we keep searching in the exception table if the gateway
 		 * is different.
 		 */
-		if (!ipv6_addr_equal(&rdfl->gateway, &rt->fib6_nh.nh_gw)) {
+		if (!ipv6_addr_equal(&rdfl->gateway, &rt->fib6_nh.fib_nh_gw6)) {
 			rt_cache = rt6_find_cached_rt(rt,
 						      &fl6->daddr,
 						      &fl6->saddr);
@@ -2929,7 +2929,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 			goto out;
 		}
 
-		fib6_nh->nh_flags |= RTNH_F_ONLINK;
+		fib6_nh->fib_nh_flags |= RTNH_F_ONLINK;
 	}
 
 	if (cfg->fc_encap) {
@@ -2941,10 +2941,10 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 		if (err)
 			goto out;
 
-		fib6_nh->nh_lwtstate = lwtstate_get(lwtstate);
+		fib6_nh->fib_nh_lws = lwtstate_get(lwtstate);
 	}
 
-	fib6_nh->nh_weight = 1;
+	fib6_nh->fib_nh_weight = 1;
 
 	/* We cannot add true routes via loopback here,
 	 * they would result in kernel looping; promote them to reject routes
@@ -2973,7 +2973,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 		if (err)
 			goto out;
 
-		fib6_nh->nh_gw = cfg->fc_gateway;
+		fib6_nh->fib_nh_gw6 = cfg->fc_gateway;
 		fib6_nh->fib_nh_has_gw = 1;
 	}
 
@@ -2995,18 +2995,18 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 
 	if (!(cfg->fc_flags & (RTF_LOCAL | RTF_ANYCAST)) &&
 	    !netif_carrier_ok(dev))
-		fib6_nh->nh_flags |= RTNH_F_LINKDOWN;
+		fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 
 set_dev:
-	fib6_nh->nh_dev = dev;
+	fib6_nh->fib_nh_dev = dev;
 	err = 0;
 out:
 	if (idev)
 		in6_dev_put(idev);
 
 	if (err) {
-		lwtstate_put(fib6_nh->nh_lwtstate);
-		fib6_nh->nh_lwtstate = NULL;
+		lwtstate_put(fib6_nh->fib_nh_lws);
+		fib6_nh->fib_nh_lws = NULL;
 		if (dev)
 			dev_put(dev);
 	}
@@ -3016,10 +3016,10 @@ out:
 
 void fib6_nh_release(struct fib6_nh *fib6_nh)
 {
-	lwtstate_put(fib6_nh->nh_lwtstate);
+	lwtstate_put(fib6_nh->fib_nh_lws);
 
-	if (fib6_nh->nh_dev)
-		dev_put(fib6_nh->nh_dev);
+	if (fib6_nh->fib_nh_dev)
+		dev_put(fib6_nh->fib_nh_dev);
 }
 
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
@@ -3129,7 +3129,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	 * they would result in kernel looping; promote them to reject routes
 	 */
 	addr_type = ipv6_addr_type(&cfg->fc_dst);
-	if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh.nh_dev, addr_type))
+	if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh.fib_nh_dev, addr_type))
 		rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP;
 
 	if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
@@ -3287,6 +3287,8 @@ static int ip6_route_del(struct fib6_config *cfg,
 
 	if (fn) {
 		for_each_fib6_node_rt_rcu(fn) {
+			struct fib6_nh *nh;
+
 			if (cfg->fc_flags & RTF_CACHE) {
 				int rc;
 
@@ -3301,12 +3303,14 @@ static int ip6_route_del(struct fib6_config *cfg,
 				}
 				continue;
 			}
+
+			nh = &rt->fib6_nh;
 			if (cfg->fc_ifindex &&
-			    (!rt->fib6_nh.nh_dev ||
-			     rt->fib6_nh.nh_dev->ifindex != cfg->fc_ifindex))
+			    (!nh->fib_nh_dev ||
+			     nh->fib_nh_dev->ifindex != cfg->fc_ifindex))
 				continue;
 			if (cfg->fc_flags & RTF_GATEWAY &&
-			    !ipv6_addr_equal(&cfg->fc_gateway, &rt->fib6_nh.nh_gw))
+			    !ipv6_addr_equal(&cfg->fc_gateway, &nh->fib_nh_gw6))
 				continue;
 			if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric)
 				continue;
@@ -3477,12 +3481,12 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 		goto out;
 
 	for_each_fib6_node_rt_rcu(fn) {
-		if (rt->fib6_nh.nh_dev->ifindex != ifindex)
+		if (rt->fib6_nh.fib_nh_dev->ifindex != ifindex)
 			continue;
 		if (!(rt->fib6_flags & RTF_ROUTEINFO) ||
 		    !rt->fib6_nh.fib_nh_has_gw)
 			continue;
-		if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr))
+		if (!ipv6_addr_equal(&rt->fib6_nh.fib_nh_gw6, gwaddr))
 			continue;
 		if (!fib6_info_hold_safe(rt))
 			continue;
@@ -3540,9 +3544,11 @@ struct fib6_info *rt6_get_dflt_router(struct net *net,
 
 	rcu_read_lock();
 	for_each_fib6_node_rt_rcu(&table->tb6_root) {
-		if (dev == rt->fib6_nh.nh_dev &&
+		struct fib6_nh *nh = &rt->fib6_nh;
+
+		if (dev == nh->fib_nh_dev &&
 		    ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
-		    ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr))
+		    ipv6_addr_equal(&nh->fib_nh_gw6, addr))
 			break;
 	}
 	if (rt && !fib6_info_hold_safe(rt))
@@ -3779,7 +3785,7 @@ static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg)
 	struct net *net = ((struct arg_dev_net_ip *)arg)->net;
 	struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
 
-	if (((void *)rt->fib6_nh.nh_dev == dev || !dev) &&
+	if (((void *)rt->fib6_nh.fib_nh_dev == dev || !dev) &&
 	    rt != net->ipv6.fib6_null_entry &&
 	    ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr)) {
 		spin_lock_bh(&rt6_exception_lock);
@@ -3810,7 +3816,7 @@ static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
 
 	if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
 	    rt->fib6_nh.fib_nh_has_gw &&
-	    ipv6_addr_equal(gateway, &rt->fib6_nh.nh_gw)) {
+	    ipv6_addr_equal(gateway, &rt->fib6_nh.fib_nh_gw6)) {
 		return -1;
 	}
 
@@ -3858,9 +3864,9 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
 
 static bool rt6_is_dead(const struct fib6_info *rt)
 {
-	if (rt->fib6_nh.nh_flags & RTNH_F_DEAD ||
-	    (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
-	     ip6_ignore_linkdown(rt->fib6_nh.nh_dev)))
+	if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD ||
+	    (rt->fib6_nh.fib_nh_flags & RTNH_F_LINKDOWN &&
+	     ip6_ignore_linkdown(rt->fib6_nh.fib_nh_dev)))
 		return true;
 
 	return false;
@@ -3872,11 +3878,11 @@ static int rt6_multipath_total_weight(const struct fib6_info *rt)
 	int total = 0;
 
 	if (!rt6_is_dead(rt))
-		total += rt->fib6_nh.nh_weight;
+		total += rt->fib6_nh.fib_nh_weight;
 
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
 		if (!rt6_is_dead(iter))
-			total += iter->fib6_nh.nh_weight;
+			total += iter->fib6_nh.fib_nh_weight;
 	}
 
 	return total;
@@ -3887,11 +3893,11 @@ static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total)
 	int upper_bound = -1;
 
 	if (!rt6_is_dead(rt)) {
-		*weight += rt->fib6_nh.nh_weight;
+		*weight += rt->fib6_nh.fib_nh_weight;
 		upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31,
 						    total) - 1;
 	}
-	atomic_set(&rt->fib6_nh.nh_upper_bound, upper_bound);
+	atomic_set(&rt->fib6_nh.fib_nh_upper_bound, upper_bound);
 }
 
 static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total)
@@ -3934,8 +3940,9 @@ static int fib6_ifup(struct fib6_info *rt, void *p_arg)
 	const struct arg_netdev_event *arg = p_arg;
 	struct net *net = dev_net(arg->dev);
 
-	if (rt != net->ipv6.fib6_null_entry && rt->fib6_nh.nh_dev == arg->dev) {
-		rt->fib6_nh.nh_flags &= ~arg->nh_flags;
+	if (rt != net->ipv6.fib6_null_entry &&
+	    rt->fib6_nh.fib_nh_dev == arg->dev) {
+		rt->fib6_nh.fib_nh_flags &= ~arg->nh_flags;
 		fib6_update_sernum_upto_root(net, rt);
 		rt6_multipath_rebalance(rt);
 	}
@@ -3963,10 +3970,10 @@ static bool rt6_multipath_uses_dev(const struct fib6_info *rt,
 {
 	struct fib6_info *iter;
 
-	if (rt->fib6_nh.nh_dev == dev)
+	if (rt->fib6_nh.fib_nh_dev == dev)
 		return true;
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
-		if (iter->fib6_nh.nh_dev == dev)
+		if (iter->fib6_nh.fib_nh_dev == dev)
 			return true;
 
 	return false;
@@ -3987,12 +3994,12 @@ static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt,
 	struct fib6_info *iter;
 	unsigned int dead = 0;
 
-	if (rt->fib6_nh.nh_dev == down_dev ||
-	    rt->fib6_nh.nh_flags & RTNH_F_DEAD)
+	if (rt->fib6_nh.fib_nh_dev == down_dev ||
+	    rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
 		dead++;
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
-		if (iter->fib6_nh.nh_dev == down_dev ||
-		    iter->fib6_nh.nh_flags & RTNH_F_DEAD)
+		if (iter->fib6_nh.fib_nh_dev == down_dev ||
+		    iter->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
 			dead++;
 
 	return dead;
@@ -4004,11 +4011,11 @@ static void rt6_multipath_nh_flags_set(struct fib6_info *rt,
 {
 	struct fib6_info *iter;
 
-	if (rt->fib6_nh.nh_dev == dev)
-		rt->fib6_nh.nh_flags |= nh_flags;
+	if (rt->fib6_nh.fib_nh_dev == dev)
+		rt->fib6_nh.fib_nh_flags |= nh_flags;
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
-		if (iter->fib6_nh.nh_dev == dev)
-			iter->fib6_nh.nh_flags |= nh_flags;
+		if (iter->fib6_nh.fib_nh_dev == dev)
+			iter->fib6_nh.fib_nh_flags |= nh_flags;
 }
 
 /* called with write lock held for table with rt */
@@ -4023,12 +4030,12 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
 
 	switch (arg->event) {
 	case NETDEV_UNREGISTER:
-		return rt->fib6_nh.nh_dev == dev ? -1 : 0;
+		return rt->fib6_nh.fib_nh_dev == dev ? -1 : 0;
 	case NETDEV_DOWN:
 		if (rt->should_flush)
 			return -1;
 		if (!rt->fib6_nsiblings)
-			return rt->fib6_nh.nh_dev == dev ? -1 : 0;
+			return rt->fib6_nh.fib_nh_dev == dev ? -1 : 0;
 		if (rt6_multipath_uses_dev(rt, dev)) {
 			unsigned int count;
 
@@ -4044,10 +4051,10 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
 		}
 		return -2;
 	case NETDEV_CHANGE:
-		if (rt->fib6_nh.nh_dev != dev ||
+		if (rt->fib6_nh.fib_nh_dev != dev ||
 		    rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))
 			break;
-		rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN;
+		rt->fib6_nh.fib_nh_flags |= RTNH_F_LINKDOWN;
 		rt6_multipath_rebalance(rt);
 		break;
 	}
@@ -4103,7 +4110,7 @@ static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg)
 	   Since RFC 1981 doesn't include administrative MTU increase
 	   update PMTU increase is a MUST. (i.e. jumbo frame)
 	 */
-	if (rt->fib6_nh.nh_dev == arg->dev &&
+	if (rt->fib6_nh.fib_nh_dev == arg->dev &&
 	    !fib6_metric_locked(rt, RTAX_MTU)) {
 		u32 mtu = rt->fib6_pmtu;
 
@@ -4394,7 +4401,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			goto cleanup;
 		}
 
-		rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1;
+		rt->fib6_nh.fib_nh_weight = rtnh->rtnh_hops + 1;
 
 		err = ip6_route_info_append(info->nl_net, &rt6_nh_list,
 					    rt, &r_cfg);
@@ -4561,7 +4568,7 @@ static size_t rt6_nlmsg_size(struct fib6_info *rt)
 		nexthop_len = nla_total_size(0)	 /* RTA_MULTIPATH */
 			    + NLA_ALIGN(sizeof(struct rtnexthop))
 			    + nla_total_size(16) /* RTA_GATEWAY */
-			    + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate);
+			    + lwtunnel_get_encap_size(rt->fib6_nh.fib_nh_lws);
 
 		nexthop_len *= rt->fib6_nsiblings;
 	}
@@ -4579,41 +4586,41 @@ static size_t rt6_nlmsg_size(struct fib6_info *rt)
 	       + nla_total_size(sizeof(struct rta_cacheinfo))
 	       + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
 	       + nla_total_size(1) /* RTA_PREF */
-	       + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate)
+	       + lwtunnel_get_encap_size(rt->fib6_nh.fib_nh_lws)
 	       + nexthop_len;
 }
 
 static int rt6_nexthop_info(struct sk_buff *skb, const struct fib6_nh *fib6_nh,
 			    unsigned int *flags, bool skip_oif)
 {
-	if (fib6_nh->nh_flags & RTNH_F_DEAD)
+	if (fib6_nh->fib_nh_flags & RTNH_F_DEAD)
 		*flags |= RTNH_F_DEAD;
 
-	if (fib6_nh->nh_flags & RTNH_F_LINKDOWN) {
+	if (fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN) {
 		*flags |= RTNH_F_LINKDOWN;
 
 		rcu_read_lock();
-		if (ip6_ignore_linkdown(fib6_nh->nh_dev))
+		if (ip6_ignore_linkdown(fib6_nh->fib_nh_dev))
 			*flags |= RTNH_F_DEAD;
 		rcu_read_unlock();
 	}
 
 	if (fib6_nh->fib_nh_has_gw) {
-		if (nla_put_in6_addr(skb, RTA_GATEWAY, &fib6_nh->nh_gw) < 0)
+		if (nla_put_in6_addr(skb, RTA_GATEWAY, &fib6_nh->fib_nh_gw6) < 0)
 			goto nla_put_failure;
 	}
 
-	*flags |= (fib6_nh->nh_flags & RTNH_F_ONLINK);
-	if (fib6_nh->nh_flags & RTNH_F_OFFLOAD)
+	*flags |= (fib6_nh->fib_nh_flags & RTNH_F_ONLINK);
+	if (fib6_nh->fib_nh_flags & RTNH_F_OFFLOAD)
 		*flags |= RTNH_F_OFFLOAD;
 
 	/* not needed for multipath encoding b/c it has a rtnexthop struct */
-	if (!skip_oif && fib6_nh->nh_dev &&
-	    nla_put_u32(skb, RTA_OIF, fib6_nh->nh_dev->ifindex))
+	if (!skip_oif && fib6_nh->fib_nh_dev &&
+	    nla_put_u32(skb, RTA_OIF, fib6_nh->fib_nh_dev->ifindex))
 		goto nla_put_failure;
 
-	if (fib6_nh->nh_lwtstate &&
-	    lwtunnel_fill_encap(skb, fib6_nh->nh_lwtstate) < 0)
+	if (fib6_nh->fib_nh_lws &&
+	    lwtunnel_fill_encap(skb, fib6_nh->fib_nh_lws) < 0)
 		goto nla_put_failure;
 
 	return 0;
@@ -4625,7 +4632,7 @@ nla_put_failure:
 /* add multipath next hop */
 static int rt6_add_nexthop(struct sk_buff *skb, const struct fib6_nh *fib6_nh)
 {
-	const struct net_device *dev = fib6_nh->nh_dev;
+	const struct net_device *dev = fib6_nh->fib_nh_dev;
 	struct rtnexthop *rtnh;
 	unsigned int flags = 0;
 
@@ -4633,7 +4640,7 @@ static int rt6_add_nexthop(struct sk_buff *skb, const struct fib6_nh *fib6_nh)
 	if (!rtnh)
 		goto nla_put_failure;
 
-	rtnh->rtnh_hops = fib6_nh->nh_weight - 1;
+	rtnh->rtnh_hops = fib6_nh->fib_nh_weight - 1;
 	rtnh->rtnh_ifindex = dev ? dev->ifindex : 0;
 
 	if (rt6_nexthop_info(skb, fib6_nh, &flags, true) < 0)
@@ -4805,7 +4812,7 @@ nla_put_failure:
 static bool fib6_info_uses_dev(const struct fib6_info *f6i,
 			       const struct net_device *dev)
 {
-	if (f6i->fib6_nh.nh_dev == dev)
+	if (f6i->fib6_nh.fib_nh_dev == dev)
 		return true;
 
 	if (f6i->fib6_nsiblings) {
@@ -4813,7 +4820,7 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i,
 
 		list_for_each_entry_safe(sibling, next_sibling,
 					 &f6i->fib6_siblings, fib6_siblings) {
-			if (sibling->fib6_nh.nh_dev == dev)
+			if (sibling->fib6_nh.fib_nh_dev == dev)
 				return true;
 		}
 	}
@@ -5098,7 +5105,7 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 		return NOTIFY_OK;
 
 	if (event == NETDEV_REGISTER) {
-		net->ipv6.fib6_null_entry->fib6_nh.nh_dev = dev;
+		net->ipv6.fib6_null_entry->fib6_nh.fib_nh_dev = dev;
 		net->ipv6.ip6_null_entry->dst.dev = dev;
 		net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -5433,7 +5440,7 @@ void __init ip6_route_init_special_entries(void)
 	/* Registering of the loopback is done before this portion of code,
 	 * the loopback reference in rt6_info will not be taken, do it
 	 * manually for init_net */
-	init_net.ipv6.fib6_null_entry->fib6_nh.nh_dev = init_net.loopback_dev;
+	init_net.ipv6.fib6_null_entry->fib6_nh.fib_nh_dev = init_net.loopback_dev;
 	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
 	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
   #ifdef CONFIG_IPV6_MULTIPLE_TABLES
-- 
cgit v1.2.3


From f1741730dd18828fe3ea5fa91c22f41cf001c625 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:57 -0700
Subject: net: Add fib_nh_common and update fib_nh and fib6_nh

Add fib_nh_common struct with common nexthop attributes. Convert
fib_nh and fib6_nh to use it. Use macros to move existing
fib_nh_* references to the new nh_common.nhc_*.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h    | 10 ++--------
 include/net/ip_fib.h     | 41 +++++++++++++++++++++++++++++++----------
 net/ipv4/fib_semantics.c |  7 ++++++-
 net/ipv6/route.c         |  3 +++
 4 files changed, 42 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index aff8570725c8..58dbb4e82908 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -19,6 +19,7 @@
 #include <linux/notifier.h>
 #include <net/dst.h>
 #include <net/flow.h>
+#include <net/ip_fib.h>
 #include <net/netlink.h>
 #include <net/inetpeer.h>
 #include <net/fib_notifier.h>
@@ -125,14 +126,7 @@ struct rt6_exception {
 #define FIB6_MAX_DEPTH 5
 
 struct fib6_nh {
-	struct in6_addr		fib_nh_gw6;
-	bool			fib_nh_has_gw;
-	struct net_device	*fib_nh_dev;
-	struct lwtunnel_state	*fib_nh_lws;
-
-	unsigned int		fib_nh_flags;
-	atomic_t		fib_nh_upper_bound;
-	int			fib_nh_weight;
+	struct fib_nh_common	nh_common;
 };
 
 struct fib6_info {
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 029acd333d29..70548b1a6322 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -76,27 +76,48 @@ struct fnhe_hash_bucket {
 #define FNHE_HASH_SIZE		(1 << FNHE_HASH_SHIFT)
 #define FNHE_RECLAIM_DEPTH	5
 
+struct fib_nh_common {
+	struct net_device	*nhc_dev;
+	int			nhc_oif;
+	unsigned int		nhc_flags;
+	struct lwtunnel_state	*nhc_lwtstate;
+	unsigned char		nhc_scope;
+	u8			nhc_family;
+	u8			nhc_has_gw:1,
+				unused:7;
+	union {
+		__be32          ipv4;
+		struct in6_addr ipv6;
+	} nhc_gw;
+
+	int			nhc_weight;
+	atomic_t		nhc_upper_bound;
+};
+
 struct fib_nh {
-	struct net_device	*fib_nh_dev;
+	struct fib_nh_common	nh_common;
 	struct hlist_node	nh_hash;
 	struct fib_info		*nh_parent;
-	unsigned int		fib_nh_flags;
-	unsigned char		fib_nh_scope;
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-	int			fib_nh_weight;
-	atomic_t		fib_nh_upper_bound;
-#endif
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	__u32			nh_tclassid;
 #endif
-	int			fib_nh_oif;
-	__be32			fib_nh_gw4;
 	__be32			nh_saddr;
 	int			nh_saddr_genid;
 	struct rtable __rcu * __percpu *nh_pcpu_rth_output;
 	struct rtable __rcu	*nh_rth_input;
 	struct fnhe_hash_bucket	__rcu *nh_exceptions;
-	struct lwtunnel_state	*fib_nh_lws;
+#define fib_nh_family		nh_common.nhc_family
+#define fib_nh_dev		nh_common.nhc_dev
+#define fib_nh_oif		nh_common.nhc_oif
+#define fib_nh_flags		nh_common.nhc_flags
+#define fib_nh_lws		nh_common.nhc_lwtstate
+#define fib_nh_scope		nh_common.nhc_scope
+#define fib_nh_family		nh_common.nhc_family
+#define fib_nh_has_gw		nh_common.nhc_has_gw
+#define fib_nh_gw4		nh_common.nhc_gw.ipv4
+#define fib_nh_gw6		nh_common.nhc_gw.ipv6
+#define fib_nh_weight		nh_common.nhc_weight
+#define fib_nh_upper_bound	nh_common.nhc_upper_bound
 };
 
 /*
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c1e16b52338b..e9992407863e 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -468,6 +468,8 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 {
 	int err = -ENOMEM;
 
+	nh->fib_nh_family = AF_INET;
+
 	nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
 	if (!nh->nh_pcpu_rth_output)
 		goto err_out;
@@ -490,7 +492,10 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 	}
 
 	nh->fib_nh_oif = cfg->fc_oif;
-	nh->fib_nh_gw4 = cfg->fc_gw;
+	if (cfg->fc_gw) {
+		nh->fib_nh_gw4 = cfg->fc_gw;
+		nh->fib_nh_has_gw = 1;
+	}
 	nh->fib_nh_flags = cfg->fc_flags;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e4c2f8e43405..79ef590b7bc5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2906,6 +2906,8 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 	int addr_type;
 	int err;
 
+	fib6_nh->fib_nh_family = AF_INET6;
+
 	err = -ENODEV;
 	if (cfg->fc_ifindex) {
 		dev = dev_get_by_index(net, cfg->fc_ifindex);
@@ -2999,6 +3001,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 
 set_dev:
 	fib6_nh->fib_nh_dev = dev;
+	fib6_nh->fib_nh_oif = dev->ifindex;
 	err = 0;
 out:
 	if (idev)
-- 
cgit v1.2.3


From 979e276ebebd537782797c439c9cb42b6d3aba27 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 27 Mar 2019 20:53:58 -0700
Subject: net: Use common nexthop init and release helpers

With fib_nh_common in place, move common initialization and release
code into helpers used by both ipv4 and ipv6. For the moment, the init
is just the lwt encap and the release is both the netdev reference and
the the lwt state reference. More will be added later.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  4 ++++
 net/ipv4/fib_semantics.c | 60 +++++++++++++++++++++++++++++++-----------------
 net/ipv6/route.c         | 21 ++++-------------
 3 files changed, 48 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 70548b1a6322..12a6d759cf57 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -441,6 +441,10 @@ int fib_nh_init(struct net *net, struct fib_nh *fib_nh,
 		struct fib_config *cfg, int nh_weight,
 		struct netlink_ext_ack *extack);
 void fib_nh_release(struct net *net, struct fib_nh *fib_nh);
+int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *fc_encap,
+		       u16 fc_encap_type, void *cfg, gfp_t gfp_flags,
+		       struct netlink_ext_ack *extack);
+void fib_nh_common_release(struct fib_nh_common *nhc);
 
 /* Exported by fib_trie.c */
 void fib_trie_init(void);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e9992407863e..df777af7e278 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -204,16 +204,22 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
 	free_percpu(rtp);
 }
 
+void fib_nh_common_release(struct fib_nh_common *nhc)
+{
+	if (nhc->nhc_dev)
+		dev_put(nhc->nhc_dev);
+
+	lwtstate_put(nhc->nhc_lwtstate);
+}
+EXPORT_SYMBOL_GPL(fib_nh_common_release);
+
 void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
 {
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (fib_nh->nh_tclassid)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
-	if (fib_nh->fib_nh_dev)
-		dev_put(fib_nh->fib_nh_dev);
-
-	lwtstate_put(fib_nh->fib_nh_lws);
+	fib_nh_common_release(&fib_nh->nh_common);
 	free_nh_exceptions(fib_nh);
 	rt_fibinfo_free_cpus(fib_nh->nh_pcpu_rth_output);
 	rt_fibinfo_free(&fib_nh->nh_rth_input);
@@ -462,6 +468,30 @@ static int fib_detect_death(struct fib_info *fi, int order,
 	return 1;
 }
 
+int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *encap,
+		       u16 encap_type, void *cfg, gfp_t gfp_flags,
+		       struct netlink_ext_ack *extack)
+{
+	if (encap) {
+		struct lwtunnel_state *lwtstate;
+		int err;
+
+		if (encap_type == LWTUNNEL_ENCAP_NONE) {
+			NL_SET_ERR_MSG(extack, "LWT encap type not specified");
+			return -EINVAL;
+		}
+		err = lwtunnel_build_state(encap_type, encap, nhc->nhc_family,
+					   cfg, &lwtstate, extack);
+		if (err)
+			return err;
+
+		nhc->nhc_lwtstate = lwtstate_get(lwtstate);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fib_nh_common_init);
+
 int fib_nh_init(struct net *net, struct fib_nh *nh,
 		struct fib_config *cfg, int nh_weight,
 		struct netlink_ext_ack *extack)
@@ -474,22 +504,10 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 	if (!nh->nh_pcpu_rth_output)
 		goto err_out;
 
-	if (cfg->fc_encap) {
-		struct lwtunnel_state *lwtstate;
-
-		err = -EINVAL;
-		if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) {
-			NL_SET_ERR_MSG(extack, "LWT encap type not specified");
-			goto lwt_failure;
-		}
-		err = lwtunnel_build_state(cfg->fc_encap_type,
-					   cfg->fc_encap, AF_INET, cfg,
-					   &lwtstate, extack);
-		if (err)
-			goto lwt_failure;
-
-		nh->fib_nh_lws = lwtstate_get(lwtstate);
-	}
+	err = fib_nh_common_init(&nh->nh_common, cfg->fc_encap,
+				 cfg->fc_encap_type, cfg, GFP_KERNEL, extack);
+	if (err)
+		goto init_failure;
 
 	nh->fib_nh_oif = cfg->fc_oif;
 	if (cfg->fc_gw) {
@@ -508,7 +526,7 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 #endif
 	return 0;
 
-lwt_failure:
+init_failure:
 	rt_fibinfo_free_cpus(nh->nh_pcpu_rth_output);
 	nh->nh_pcpu_rth_output = NULL;
 err_out:
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 79ef590b7bc5..e0ee30cbd079 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2934,18 +2934,6 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 		fib6_nh->fib_nh_flags |= RTNH_F_ONLINK;
 	}
 
-	if (cfg->fc_encap) {
-		struct lwtunnel_state *lwtstate;
-
-		err = lwtunnel_build_state(cfg->fc_encap_type,
-					   cfg->fc_encap, AF_INET6, cfg,
-					   &lwtstate, extack);
-		if (err)
-			goto out;
-
-		fib6_nh->fib_nh_lws = lwtstate_get(lwtstate);
-	}
-
 	fib6_nh->fib_nh_weight = 1;
 
 	/* We cannot add true routes via loopback here,
@@ -2999,6 +2987,10 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 	    !netif_carrier_ok(dev))
 		fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 
+	err = fib_nh_common_init(&fib6_nh->nh_common, cfg->fc_encap,
+				 cfg->fc_encap_type, cfg, gfp_flags, extack);
+	if (err)
+		goto out;
 set_dev:
 	fib6_nh->fib_nh_dev = dev;
 	fib6_nh->fib_nh_oif = dev->ifindex;
@@ -3019,10 +3011,7 @@ out:
 
 void fib6_nh_release(struct fib6_nh *fib6_nh)
 {
-	lwtstate_put(fib6_nh->fib_nh_lws);
-
-	if (fib6_nh->fib_nh_dev)
-		dev_put(fib6_nh->fib_nh_dev);
+	fib_nh_common_release(&fib6_nh->nh_common);
 }
 
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
-- 
cgit v1.2.3


From 3616d08bcbb564c7765187cd45ad392e49bad73a Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 22 Mar 2019 06:06:09 -0700
Subject: ipv6: Move ipv6 stubs to a separate header file

The number of stubs is growing and has nothing to do with addrconf.
Move the definition of the stubs to a separate header file and update
users. In the move, drop the vxlan specific comment before ipv6_stub.

Code move only; no functional change intended.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/addr.c                  |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c |  1 +
 drivers/net/geneve.c                            |  1 +
 drivers/net/usb/cdc_mbim.c                      |  1 +
 drivers/net/vxlan.c                             |  1 +
 include/net/addrconf.h                          | 47 ------------------
 include/net/ipv6_stubs.h                        | 63 +++++++++++++++++++++++++
 include/net/udp_tunnel.h                        |  2 +-
 net/bridge/br_arp_nd_proxy.c                    |  1 +
 net/core/filter.c                               |  1 +
 net/core/lwt_bpf.c                              |  1 +
 net/ipv6/addrconf_core.c                        |  2 +-
 net/ipv6/af_inet6.c                             |  1 +
 net/mpls/af_mpls.c                              |  2 +-
 net/tipc/udp_media.c                            |  2 +-
 15 files changed, 76 insertions(+), 52 deletions(-)
 create mode 100644 include/net/ipv6_stubs.h

(limited to 'include')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 0dce94e3c495..2649e0f2ff65 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -42,7 +42,7 @@
 #include <net/neighbour.h>
 #include <net/route.h>
 #include <net/netevent.h>
-#include <net/addrconf.h>
+#include <net/ipv6_stubs.h>
 #include <net/ip6_route.h>
 #include <rdma/ib_addr.h>
 #include <rdma/ib_sa.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index c68edcc84af8..2fd425a7b156 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -44,6 +44,7 @@
 #include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_csum.h>
 #include <net/arp.h>
+#include <net/ipv6_stubs.h>
 #include "en.h"
 #include "en_rep.h"
 #include "en_tc.h"
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index c05b1207358d..98d1a45c0606 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/etherdevice.h>
 #include <linux/hash.h>
+#include <net/ipv6_stubs.h>
 #include <net/dst_metadata.h>
 #include <net/gro_cells.h>
 #include <net/rtnetlink.h>
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 0362acd5cdca..28321aca48fe 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -23,6 +23,7 @@
 #include <linux/usb/cdc_ncm.h>
 #include <net/ipv6.h>
 #include <net/addrconf.h>
+#include <net/ipv6_stubs.h>
 
 /* alternative VLAN for IP session 0 if not untagged */
 #define MBIM_IPS0_VID	4094
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d76dfed8d9bb..5994d5415a03 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -20,6 +20,7 @@
 #include <linux/ethtool.h>
 #include <net/arp.h>
 #include <net/ndisc.h>
+#include <net/ipv6_stubs.h>
 #include <net/ip.h>
 #include <net/icmp.h>
 #include <net/rtnetlink.h>
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index ec8e6784a6f7..2f67ae854ff0 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -238,53 +238,6 @@ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group,
 
 void ipv6_mc_dad_complete(struct inet6_dev *idev);
 
-/* A stub used by vxlan module. This is ugly, ideally these
- * symbols should be built into the core kernel.
- */
-struct ipv6_stub {
-	int (*ipv6_sock_mc_join)(struct sock *sk, int ifindex,
-				 const struct in6_addr *addr);
-	int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex,
-				 const struct in6_addr *addr);
-	int (*ipv6_dst_lookup)(struct net *net, struct sock *sk,
-			       struct dst_entry **dst, struct flowi6 *fl6);
-	int (*ipv6_route_input)(struct sk_buff *skb);
-
-	struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
-	struct fib6_info *(*fib6_lookup)(struct net *net, int oif,
-					 struct flowi6 *fl6, int flags);
-	struct fib6_info *(*fib6_table_lookup)(struct net *net,
-					      struct fib6_table *table,
-					      int oif, struct flowi6 *fl6,
-					      int flags);
-	struct fib6_info *(*fib6_multipath_select)(const struct net *net,
-						   struct fib6_info *f6i,
-						   struct flowi6 *fl6, int oif,
-						   const struct sk_buff *skb,
-						   int strict);
-	u32 (*ip6_mtu_from_fib6)(struct fib6_info *f6i, struct in6_addr *daddr,
-				 struct in6_addr *saddr);
-
-	void (*udpv6_encap_enable)(void);
-	void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
-			      const struct in6_addr *solicited_addr,
-			      bool router, bool solicited, bool override, bool inc_opt);
-	struct neigh_table *nd_tbl;
-};
-extern const struct ipv6_stub *ipv6_stub __read_mostly;
-
-/* A stub used by bpf helpers. Similarly ugly as ipv6_stub */
-struct ipv6_bpf_stub {
-	int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len,
-			  bool force_bind_address_no_port, bool with_lock);
-	struct sock *(*udp6_lib_lookup)(struct net *net,
-					const struct in6_addr *saddr, __be16 sport,
-					const struct in6_addr *daddr, __be16 dport,
-					int dif, int sdif, struct udp_table *tbl,
-					struct sk_buff *skb);
-};
-extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
-
 /*
  * identify MLD packets for MLD filter exceptions
  */
diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
new file mode 100644
index 000000000000..d8d9c0b0e8c0
--- /dev/null
+++ b/include/net/ipv6_stubs.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _IPV6_STUBS_H
+#define _IPV6_STUBS_H
+
+#include <linux/in6.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <net/dst.h>
+#include <net/flow.h>
+#include <net/neighbour.h>
+#include <net/sock.h>
+
+/* structs from net/ip6_fib.h */
+struct fib6_info;
+
+/* This is ugly, ideally these symbols should be built
+ * into the core kernel.
+ */
+struct ipv6_stub {
+	int (*ipv6_sock_mc_join)(struct sock *sk, int ifindex,
+				 const struct in6_addr *addr);
+	int (*ipv6_sock_mc_drop)(struct sock *sk, int ifindex,
+				 const struct in6_addr *addr);
+	int (*ipv6_dst_lookup)(struct net *net, struct sock *sk,
+			       struct dst_entry **dst, struct flowi6 *fl6);
+	int (*ipv6_route_input)(struct sk_buff *skb);
+
+	struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
+	struct fib6_info *(*fib6_lookup)(struct net *net, int oif,
+					 struct flowi6 *fl6, int flags);
+	struct fib6_info *(*fib6_table_lookup)(struct net *net,
+					      struct fib6_table *table,
+					      int oif, struct flowi6 *fl6,
+					      int flags);
+	struct fib6_info *(*fib6_multipath_select)(const struct net *net,
+						   struct fib6_info *f6i,
+						   struct flowi6 *fl6, int oif,
+						   const struct sk_buff *skb,
+						   int strict);
+	u32 (*ip6_mtu_from_fib6)(struct fib6_info *f6i, struct in6_addr *daddr,
+				 struct in6_addr *saddr);
+
+	void (*udpv6_encap_enable)(void);
+	void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
+			      const struct in6_addr *solicited_addr,
+			      bool router, bool solicited, bool override, bool inc_opt);
+	struct neigh_table *nd_tbl;
+};
+extern const struct ipv6_stub *ipv6_stub __read_mostly;
+
+/* A stub used by bpf helpers. Similarly ugly as ipv6_stub */
+struct ipv6_bpf_stub {
+	int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len,
+			  bool force_bind_address_no_port, bool with_lock);
+	struct sock *(*udp6_lib_lookup)(struct net *net,
+				     const struct in6_addr *saddr, __be16 sport,
+				     const struct in6_addr *daddr, __be16 dport,
+				     int dif, int sdif, struct udp_table *tbl,
+				     struct sk_buff *skb);
+};
+extern const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly;
+
+#endif
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index b8137953fea3..4b1f95e08307 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -7,7 +7,7 @@
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
-#include <net/addrconf.h>
+#include <net/ipv6_stubs.h>
 #endif
 
 struct udp_port_cfg {
diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c
index 6b78e6351719..724b474ade54 100644
--- a/net/bridge/br_arp_nd_proxy.c
+++ b/net/bridge/br_arp_nd_proxy.c
@@ -21,6 +21,7 @@
 #include <linux/if_vlan.h>
 #include <linux/inetdevice.h>
 #include <net/addrconf.h>
+#include <net/ipv6_stubs.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ip6_checksum.h>
 #endif
diff --git a/net/core/filter.c b/net/core/filter.c
index 887ab073a0ea..4a8455757507 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -74,6 +74,7 @@
 #include <net/seg6.h>
 #include <net/seg6_local.h>
 #include <net/lwtunnel.h>
+#include <net/ipv6_stubs.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 126d31ff5ee3..3c5c24a5d9f5 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -18,6 +18,7 @@
 #include <net/lwtunnel.h>
 #include <net/gre.h>
 #include <net/ip6_route.h>
+#include <net/ipv6_stubs.h>
 
 struct bpf_lwt_prog {
 	struct bpf_prog *prog;
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 6c79af056d9b..945b66e3008f 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -5,7 +5,7 @@
 
 #include <linux/export.h>
 #include <net/ipv6.h>
-#include <net/addrconf.h>
+#include <net/ipv6_stubs.h>
 #include <net/ip.h>
 
 /* if ipv6 module registers this function is used by xfrm to force all
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index fa6b404cbd10..1789bf99c419 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -56,6 +56,7 @@
 #include <net/transp_v6.h>
 #include <net/ip6_route.h>
 #include <net/addrconf.h>
+#include <net/ipv6_stubs.h>
 #include <net/ndisc.h>
 #ifdef CONFIG_IPV6_TUNNEL
 #include <net/ip6_tunnel.h>
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index f7c544592ec8..8120e04f15e4 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -22,7 +22,7 @@
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
 #endif
-#include <net/addrconf.h>
+#include <net/ipv6_stubs.h>
 #include <net/nexthop.h>
 #include "internal.h"
 
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 4d85d71f16e2..6f166fbbfff1 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -44,7 +44,7 @@
 #include <net/sock.h>
 #include <net/ip.h>
 #include <net/udp_tunnel.h>
-#include <net/addrconf.h>
+#include <net/ipv6_stubs.h>
 #include <linux/tipc_netlink.h>
 #include "core.h"
 #include "addr.h"
-- 
cgit v1.2.3


From 18b6f717483a835fb98de9f0df6c724df9324e78 Mon Sep 17 00:00:00 2001
From: wenxu <wenxu@ucloud.cn>
Date: Thu, 28 Mar 2019 12:43:23 +0800
Subject: openvswitch: Make metadata_dst tunnel work in IP_TUNNEL_INFO_BRIDGE
 mode

There is currently no support for the multicast/broadcast aspects
of VXLAN in ovs. In the datapath flow the tun_dst must specific.
But in the IP_TUNNEL_INFO_BRIDGE mode the tun_dst can not be specific.
And the packet can forward through the fdb table of vxlan devcice. In
this mode the broadcast/multicast packet can be sent through the
following ways in ovs.

ovs-vsctl add-port br0 vxlan -- set in vxlan type=vxlan \
        options:key=1000 options:remote_ip=flow
ovs-ofctl add-flow br0 in_port=LOCAL,dl_dst=ff:ff:ff:ff:ff:ff, \
        action=output:vxlan

bridge fdb append ff:ff:ff:ff:ff:ff dev vxlan_sys_4789 dst 172.168.0.1 \
        src_vni 1000 vni 1000 self
bridge fdb append ff:ff:ff:ff:ff:ff dev vxlan_sys_4789 dst 172.168.0.2 \
        src_vni 1000 vni 1000 self

Signed-off-by: wenxu <wenxu@ucloud.cn>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/openvswitch.h |  1 +
 net/openvswitch/flow_netlink.c   | 46 +++++++++++++++++++++++++++++++---------
 2 files changed, 37 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 0cac5d802c6a..f271f1ec50ae 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -364,6 +364,7 @@ enum ovs_tunnel_key_attr {
 	OVS_TUNNEL_KEY_ATTR_IPV6_DST,		/* struct in6_addr dst IPv6 address. */
 	OVS_TUNNEL_KEY_ATTR_PAD,
 	OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS,	/* struct erspan_metadata */
+	OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE,	/* No argument. IPV4_INFO_BRIDGE mode.*/
 	__OVS_TUNNEL_KEY_ATTR_MAX
 };
 
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index b7543700db87..bd019058fc6f 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -404,6 +404,7 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1]
 	[OVS_TUNNEL_KEY_ATTR_IPV6_SRC]      = { .len = sizeof(struct in6_addr) },
 	[OVS_TUNNEL_KEY_ATTR_IPV6_DST]      = { .len = sizeof(struct in6_addr) },
 	[OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS]   = { .len = OVS_ATTR_VARIABLE },
+	[OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE]   = { .len = 0 },
 };
 
 static const struct ovs_len_tbl
@@ -667,6 +668,7 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			      bool log)
 {
 	bool ttl = false, ipv4 = false, ipv6 = false;
+	bool info_bridge_mode = false;
 	__be16 tun_flags = 0;
 	int opts_type = 0;
 	struct nlattr *a;
@@ -783,6 +785,10 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			tun_flags |= TUNNEL_ERSPAN_OPT;
 			opts_type = type;
 			break;
+		case OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE:
+			info_bridge_mode = true;
+			ipv4 = true;
+			break;
 		default:
 			OVS_NLERR(log, "Unknown IP tunnel attribute %d",
 				  type);
@@ -813,16 +819,29 @@ static int ip_tun_from_nlattr(const struct nlattr *attr,
 			OVS_NLERR(log, "IP tunnel dst address not specified");
 			return -EINVAL;
 		}
-		if (ipv4 && !match->key->tun_key.u.ipv4.dst) {
-			OVS_NLERR(log, "IPv4 tunnel dst address is zero");
-			return -EINVAL;
+		if (ipv4) {
+			if (info_bridge_mode) {
+				if (match->key->tun_key.u.ipv4.src ||
+				    match->key->tun_key.u.ipv4.dst ||
+				    match->key->tun_key.tp_src ||
+				    match->key->tun_key.tp_dst ||
+				    match->key->tun_key.ttl ||
+				    match->key->tun_key.tos ||
+				    tun_flags & ~TUNNEL_KEY) {
+					OVS_NLERR(log, "IPv4 tun info is not correct");
+					return -EINVAL;
+				}
+			} else if (!match->key->tun_key.u.ipv4.dst) {
+				OVS_NLERR(log, "IPv4 tunnel dst address is zero");
+				return -EINVAL;
+			}
 		}
 		if (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) {
 			OVS_NLERR(log, "IPv6 tunnel dst address is zero");
 			return -EINVAL;
 		}
 
-		if (!ttl) {
+		if (!ttl && !info_bridge_mode) {
 			OVS_NLERR(log, "IP tunnel TTL not specified.");
 			return -EINVAL;
 		}
@@ -851,12 +870,17 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb,
 static int __ip_tun_to_nlattr(struct sk_buff *skb,
 			      const struct ip_tunnel_key *output,
 			      const void *tun_opts, int swkey_tun_opts_len,
-			      unsigned short tun_proto)
+			      unsigned short tun_proto, u8 mode)
 {
 	if (output->tun_flags & TUNNEL_KEY &&
 	    nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id,
 			 OVS_TUNNEL_KEY_ATTR_PAD))
 		return -EMSGSIZE;
+
+	if (mode & IP_TUNNEL_INFO_BRIDGE)
+		return nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE)
+		       ? -EMSGSIZE : 0;
+
 	switch (tun_proto) {
 	case AF_INET:
 		if (output->u.ipv4.src &&
@@ -919,7 +943,7 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb,
 static int ip_tun_to_nlattr(struct sk_buff *skb,
 			    const struct ip_tunnel_key *output,
 			    const void *tun_opts, int swkey_tun_opts_len,
-			    unsigned short tun_proto)
+			    unsigned short tun_proto, u8 mode)
 {
 	struct nlattr *nla;
 	int err;
@@ -929,7 +953,7 @@ static int ip_tun_to_nlattr(struct sk_buff *skb,
 		return -EMSGSIZE;
 
 	err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len,
-				 tun_proto);
+				 tun_proto, mode);
 	if (err)
 		return err;
 
@@ -943,7 +967,7 @@ int ovs_nla_put_tunnel_info(struct sk_buff *skb,
 	return __ip_tun_to_nlattr(skb, &tun_info->key,
 				  ip_tunnel_info_opts(tun_info),
 				  tun_info->options_len,
-				  ip_tunnel_info_af(tun_info));
+				  ip_tunnel_info_af(tun_info), tun_info->mode);
 }
 
 static int encode_vlan_from_nlattrs(struct sw_flow_match *match,
@@ -1981,7 +2005,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 			opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len);
 
 		if (ip_tun_to_nlattr(skb, &output->tun_key, opts,
-				     swkey->tun_opts_len, swkey->tun_proto))
+				     swkey->tun_opts_len, swkey->tun_proto, 0))
 			goto nla_put_failure;
 	}
 
@@ -2606,6 +2630,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	tun_info->mode = IP_TUNNEL_INFO_TX;
 	if (key.tun_proto == AF_INET6)
 		tun_info->mode |= IP_TUNNEL_INFO_IPV6;
+	else if (key.tun_proto == AF_INET && key.tun_key.u.ipv4.dst == 0)
+		tun_info->mode |= IP_TUNNEL_INFO_BRIDGE;
 	tun_info->key = key.tun_key;
 
 	/* We need to store the options in the action itself since
@@ -3367,7 +3393,7 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 		err =  ip_tun_to_nlattr(skb, &tun_info->key,
 					ip_tunnel_info_opts(tun_info),
 					tun_info->options_len,
-					ip_tunnel_info_af(tun_info));
+					ip_tunnel_info_af(tun_info), tun_info->mode);
 		if (err)
 			return err;
 		nla_nest_end(skb, start);
-- 
cgit v1.2.3


From a4e76ba6b4994773fbe7a4eed8228e47862ac8a3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 31 Mar 2019 06:49:41 +0000
Subject: mlxsw: spectrum_acl: Rename rehash_dis trace

The name of the trace is no longer correct, since there is no disable of
rehash done. So name it "rehash_rollback_failed".

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c | 4 ++--
 include/trace/events/mlxsw.h                            | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 2f0b61b87c99..e993159e8e4c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -1399,8 +1399,8 @@ mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp,
 		err2 = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion,
 							    ctx, credits);
 		if (err2) {
-			trace_mlxsw_sp_acl_tcam_vregion_rehash_dis(mlxsw_sp,
-								   vregion);
+			trace_mlxsw_sp_acl_tcam_vregion_rehash_rollback_failed(mlxsw_sp,
+									       vregion);
 			dev_err(mlxsw_sp->bus_info->dev, "Failed to rollback during vregion migration fail\n");
 			/* Let the rollback to be continued later on. */
 		}
diff --git a/include/trace/events/mlxsw.h b/include/trace/events/mlxsw.h
index 6a4cfaef33a2..19a25ed323a5 100644
--- a/include/trace/events/mlxsw.h
+++ b/include/trace/events/mlxsw.h
@@ -93,7 +93,7 @@ TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_migrate_end,
 		  __entry->mlxsw_sp, __entry->vregion)
 );
 
-TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_rehash_dis,
+TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_rehash_rollback_failed,
 	TP_PROTO(const struct mlxsw_sp *mlxsw_sp,
 		 const struct mlxsw_sp_acl_tcam_vregion *vregion),
 
-- 
cgit v1.2.3


From a2c7023f7075ca9b80f944d3f20f60e6574538e2 Mon Sep 17 00:00:00 2001
From: Xiaofei Shen <xiaofeis@codeaurora.org>
Date: Fri, 29 Mar 2019 11:04:58 +0530
Subject: net: dsa: read mac address from DT for slave device

Before creating a slave netdevice, get the mac address from DTS and
apply in case it is valid.

Signed-off-by: Xiaofei Shen <xiaofeis@codeaurora.org>
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 1 +
 net/dsa/dsa2.c    | 1 +
 net/dsa/slave.c   | 5 ++++-
 3 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index ae480bba11f5..0cfc2f828b87 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -140,6 +140,7 @@ struct dsa_port {
 	unsigned int		index;
 	const char		*name;
 	const struct dsa_port	*cpu_dp;
+	const char		*mac;
 	struct device_node	*dn;
 	unsigned int		ageing_time;
 	u8			stp_state;
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index fe0a6197db9c..0e1cce460406 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -266,6 +266,7 @@ static int dsa_port_setup(struct dsa_port *dp)
 		return 0;
 
 	memset(&dp->devlink_port, 0, sizeof(dp->devlink_port));
+	dp->mac = of_get_mac_address(dp->dn);
 
 	switch (dp->type) {
 	case DSA_PORT_TYPE_CPU:
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 80be8e86c82d..f83525909c57 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1393,7 +1393,10 @@ int dsa_slave_create(struct dsa_port *port)
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 	slave_dev->hw_features |= NETIF_F_HW_TC;
 	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
-	eth_hw_addr_inherit(slave_dev, master);
+	if (port->mac && is_valid_ether_addr(port->mac))
+		ether_addr_copy(slave_dev->dev_addr, port->mac);
+	else
+		eth_hw_addr_inherit(slave_dev, master);
 	slave_dev->priv_flags |= IFF_NO_QUEUE;
 	slave_dev->netdev_ops = &dsa_slave_netdev_ops;
 	slave_dev->min_mtu = 0;
-- 
cgit v1.2.3


From 97cdcf37b57e3f204be3000b9eab9686f38b4356 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 1 Apr 2019 16:42:13 +0200
Subject: net: place xmit recursion in softnet data

This fills a hole in softnet data, so no change in structure size.

Also prepares for xmit_more placement in the same spot;
skb->xmit_more will be removed in followup patch.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 40 ++++++++++++++++++++++++++++++++--------
 net/core/dev.c            | 10 +++-------
 net/core/filter.c         |  6 +++---
 3 files changed, 38 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 78f5ec4ebf64..2b25824642fa 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2659,14 +2659,6 @@ void netdev_freemem(struct net_device *dev);
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
-DECLARE_PER_CPU(int, xmit_recursion);
-#define XMIT_RECURSION_LIMIT	10
-
-static inline int dev_recursion_level(void)
-{
-	return this_cpu_read(xmit_recursion);
-}
-
 struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
@@ -3015,6 +3007,11 @@ struct softnet_data {
 #ifdef CONFIG_XFRM_OFFLOAD
 	struct sk_buff_head	xfrm_backlog;
 #endif
+	/* written and read only by owning cpu: */
+	struct {
+		u16 recursion;
+		u8  more;
+	} xmit;
 #ifdef CONFIG_RPS
 	/* input_queue_head should be written by cpu owning this struct,
 	 * and only read by other cpus. Worth using a cache line.
@@ -3050,6 +3047,28 @@ static inline void input_queue_tail_incr_save(struct softnet_data *sd,
 
 DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 
+static inline int dev_recursion_level(void)
+{
+	return __this_cpu_read(softnet_data.xmit.recursion);
+}
+
+#define XMIT_RECURSION_LIMIT	10
+static inline bool dev_xmit_recursion(void)
+{
+	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
+			XMIT_RECURSION_LIMIT);
+}
+
+static inline void dev_xmit_recursion_inc(void)
+{
+	__this_cpu_inc(softnet_data.xmit.recursion);
+}
+
+static inline void dev_xmit_recursion_dec(void)
+{
+	__this_cpu_dec(softnet_data.xmit.recursion);
+}
+
 void __netif_schedule(struct Qdisc *q);
 void netif_schedule_queue(struct netdev_queue *txq);
 
@@ -4409,6 +4428,11 @@ static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
 	return ops->ndo_start_xmit(skb, dev);
 }
 
+static inline bool netdev_xmit_more(void)
+{
+	return __this_cpu_read(softnet_data.xmit.more);
+}
+
 static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev,
 					    struct netdev_queue *txq, bool more)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index 9823b7713f79..d5b1315218d3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3566,9 +3566,6 @@ static void skb_update_prio(struct sk_buff *skb)
 #define skb_update_prio(skb)
 #endif
 
-DEFINE_PER_CPU(int, xmit_recursion);
-EXPORT_SYMBOL(xmit_recursion);
-
 /**
  *	dev_loopback_xmit - loop back @skb
  *	@net: network namespace this loopback is happening in
@@ -3857,8 +3854,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 		int cpu = smp_processor_id(); /* ok because BHs are off */
 
 		if (txq->xmit_lock_owner != cpu) {
-			if (unlikely(__this_cpu_read(xmit_recursion) >
-				     XMIT_RECURSION_LIMIT))
+			if (dev_xmit_recursion())
 				goto recursion_alert;
 
 			skb = validate_xmit_skb(skb, dev, &again);
@@ -3868,9 +3864,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
-				__this_cpu_inc(xmit_recursion);
+				dev_xmit_recursion_inc();
 				skb = dev_hard_start_xmit(skb, dev, txq, &rc);
-				__this_cpu_dec(xmit_recursion);
+				dev_xmit_recursion_dec();
 				if (dev_xmit_complete(rc)) {
 					HARD_TX_UNLOCK(dev, txq);
 					goto out;
diff --git a/net/core/filter.c b/net/core/filter.c
index 4a8455757507..cdaafa3322db 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2016,7 +2016,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
 {
 	int ret;
 
-	if (unlikely(__this_cpu_read(xmit_recursion) > XMIT_RECURSION_LIMIT)) {
+	if (dev_xmit_recursion()) {
 		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
 		kfree_skb(skb);
 		return -ENETDOWN;
@@ -2024,9 +2024,9 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
 
 	skb->dev = dev;
 
-	__this_cpu_inc(xmit_recursion);
+	dev_xmit_recursion_inc();
 	ret = dev_queue_xmit(skb);
-	__this_cpu_dec(xmit_recursion);
+	dev_xmit_recursion_dec();
 
 	return ret;
 }
-- 
cgit v1.2.3


From 6b16f9ee89b8d5709f24bc3ac89ae8b5452c0d7c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 1 Apr 2019 16:42:14 +0200
Subject: net: move skb->xmit_more hint to softnet data

There are two reasons for this.

First, the xmit_more flag conceptually doesn't fit into the skb, as
xmit_more is not a property related to the skb.
Its only a hint to the driver that the stack is about to transmit another
packet immediately.

Second, it was only done this way to not have to pass another argument
to ndo_start_xmit().

We can place xmit_more in the softnet data, next to the device recursion.
The recursion counter is already written to on each transmit. The "more"
indicator is placed right next to it.

Drivers can use the netdev_xmit_more() helper instead of skb->xmit_more
to check the "more packets coming" hint.

skb->xmit_more is retained (but always 0) to not cause build breakage.

This change takes care of the simple s/skb->xmit_more/netdev_xmit_more()/
conversions.  Remaining drivers are converted in the next patches.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c        | 2 +-
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c            | 2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.c           | 4 ++--
 drivers/net/ethernet/broadcom/genet/bcmgenet.c      | 2 +-
 drivers/net/ethernet/broadcom/tg3.c                 | 2 +-
 drivers/net/ethernet/cavium/liquidio/lio_main.c     | 2 +-
 drivers/net/ethernet/cavium/liquidio/lio_vf_main.c  | 2 +-
 drivers/net/ethernet/cisco/enic/enic_main.c         | 2 +-
 drivers/net/ethernet/emulex/benet/be_main.c         | 2 +-
 drivers/net/ethernet/huawei/hinic/hinic_tx.c        | 2 +-
 drivers/net/ethernet/intel/e1000/e1000_main.c       | 2 +-
 drivers/net/ethernet/intel/e1000e/netdev.c          | 2 +-
 drivers/net/ethernet/intel/fm10k/fm10k_main.c       | 2 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.c         | 2 +-
 drivers/net/ethernet/intel/iavf/iavf_txrx.c         | 2 +-
 drivers/net/ethernet/intel/ice/ice_txrx.c           | 2 +-
 drivers/net/ethernet/intel/igb/igb_main.c           | 2 +-
 drivers/net/ethernet/intel/igc/igc_main.c           | 2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c       | 2 +-
 drivers/net/ethernet/marvell/mvneta.c               | 2 +-
 drivers/net/ethernet/mediatek/mtk_eth_soc.c         | 3 ++-
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 2 +-
 drivers/net/ethernet/qlogic/qede/qede_fp.c          | 4 ++--
 drivers/net/ethernet/rdc/r6040.c                    | 2 +-
 drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c       | 2 +-
 drivers/net/hyperv/netvsc.c                         | 2 +-
 drivers/net/virtio_net.c                            | 2 +-
 drivers/staging/mt7621-eth/mtk_eth_soc.c            | 6 ++++--
 include/linux/netdevice.h                           | 2 +-
 29 files changed, 35 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 71c8cac6e44e..7e40d14682f7 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2236,7 +2236,7 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	if (netif_xmit_stopped(txq) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txq) || !netdev_xmit_more()) {
 		/* trigger the dma engine. ena_com_write_sq_doorbell()
 		 * has a mb
 		 */
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 4666084eda16..d5fd49dd25f3 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1887,7 +1887,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel)
 	smp_wmb();
 
 	ring->cur = cur_index + 1;
-	if (!packet->skb->xmit_more ||
+	if (!netdev_xmit_more() ||
 	    netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev,
 						   channel->queue_index)))
 		xgbe_tx_start_xmit(channel, ring);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 35e34e23ba33..d22691403d28 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -551,7 +551,7 @@ normal_tx:
 	prod = NEXT_TX(prod);
 	txr->tx_prod = prod;
 
-	if (!skb->xmit_more || netif_xmit_stopped(txq))
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
 		bnxt_db_write(bp, &txr->tx_db, prod);
 
 tx_done:
@@ -559,7 +559,7 @@ tx_done:
 	mmiowb();
 
 	if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
-		if (skb->xmit_more && !tx_buf->is_push)
+		if (netdev_xmit_more() && !tx_buf->is_push)
 			bnxt_db_write(bp, &txr->tx_db, prod);
 
 		netif_tx_stop_queue(txq);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 983245c0867c..4fd973571e4c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1665,7 +1665,7 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (ring->free_bds <= (MAX_SKB_FRAGS + 1))
 		netif_tx_stop_queue(txq);
 
-	if (!skb->xmit_more || netif_xmit_stopped(txq))
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
 		/* Packets are ready, update producer index */
 		bcmgenet_tdma_ring_writel(priv, ring->index,
 					  ring->prod_index, TDMA_PROD_INDEX);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 328373e0578f..45ccadee02af 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -8156,7 +8156,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			netif_tx_wake_queue(txq);
 	}
 
-	if (!skb->xmit_more || netif_xmit_stopped(txq)) {
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
 		/* Packets are ready, update Tx producer idx on card. */
 		tw32_tx_mbox(tnapi->prodmbox, entry);
 		mmiowb();
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index fb6f813cff65..eab805579f96 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2522,7 +2522,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 		irh->vlan = skb_vlan_tag_get(skb) & 0xfff;
 	}
 
-	xmit_more = skb->xmit_more;
+	xmit_more = netdev_xmit_more();
 
 	if (unlikely(cmdsetup.s.timestamp))
 		status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more);
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 54b245797d2e..db0b90555acb 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -1585,7 +1585,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev)
 		irh->vlan = skb_vlan_tag_get(skb) & VLAN_VID_MASK;
 	}
 
-	xmit_more = skb->xmit_more;
+	xmit_more = netdev_xmit_more();
 
 	if (unlikely(cmdsetup.s.timestamp))
 		status = send_nic_timestamp_pkt(oct, &ndata, finfo, xmit_more);
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 733d9172425b..acb2856936d2 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -897,7 +897,7 @@ static netdev_tx_t enic_hard_start_xmit(struct sk_buff *skb,
 	if (vnic_wq_desc_avail(wq) < MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)
 		netif_tx_stop_queue(txq);
 	skb_tx_timestamp(skb);
-	if (!skb->xmit_more || netif_xmit_stopped(txq))
+	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
 		vnic_wq_doorbell(wq);
 
 	spin_unlock(&enic->wq_lock[txq_map]);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 3c7c04406a2b..e2f9fbced174 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1376,7 +1376,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev)
 	u16 q_idx = skb_get_queue_mapping(skb);
 	struct be_tx_obj *txo = &adapter->tx_obj[q_idx];
 	struct be_wrb_params wrb_params = { 0 };
-	bool flush = !skb->xmit_more;
+	bool flush = !netdev_xmit_more();
 	u16 wrb_cnt;
 
 	skb = be_xmit_workarounds(adapter, skb, &wrb_params);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index e17bf33eba0c..0fbe8046824b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -518,7 +518,7 @@ process_sq_wqe:
 
 flush_skbs:
 	netdev_txq = netdev_get_tx_queue(netdev, q_id);
-	if ((!skb->xmit_more) || (netif_xmit_stopped(netdev_txq)))
+	if ((!netdev_xmit_more()) || (netif_xmit_stopped(netdev_txq)))
 		hinic_sq_write_db(txq->sq, prod_idx, wqe_size, 0);
 
 	return err;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index a7c76732849f..6f72ab139fd9 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3267,7 +3267,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 		/* Make sure there is space in the ring for the next send. */
 		e1000_maybe_stop_tx(netdev, tx_ring, desc_needed);
 
-		if (!skb->xmit_more ||
+		if (!netdev_xmit_more() ||
 		    netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
 			writel(tx_ring->next_to_use, hw->hw_addr + tx_ring->tdt);
 			/* we need this if more than one processor can write to
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 745c1242a2d9..a8fa4a1628f5 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -5897,7 +5897,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 				     DIV_ROUND_UP(PAGE_SIZE,
 						  adapter->tx_fifo_limit) + 2));
 
-		if (!skb->xmit_more ||
+		if (!netdev_xmit_more() ||
 		    netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
 			if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
 				e1000e_update_tdt_wa(tx_ring,
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 5a0419421511..e2fa112bed9a 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -1035,7 +1035,7 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring,
 	fm10k_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
 	/* notify HW of packet */
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 6c97667d20ef..1a95223c9f99 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3469,7 +3469,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	first->next_to_watch = tx_desc;
 
 	/* notify HW of packet */
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 9b4d7cec2e18..b64187753ad6 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -2358,7 +2358,7 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb,
 	first->next_to_watch = tx_desc;
 
 	/* notify HW of packet */
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index f2462799154a..a6f7b7feaf3c 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1646,7 +1646,7 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first,
 	ice_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
 	/* notify HW of packet */
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index bea7175d171b..32d61d5a2706 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6029,7 +6029,7 @@ static int igb_tx_map(struct igb_ring *tx_ring,
 	/* Make sure there is space in the ring for the next send. */
 	igb_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index a883b3f357e7..f79728381e8a 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -939,7 +939,7 @@ static int igc_tx_map(struct igc_ring *tx_ring,
 	/* Make sure there is space in the ring for the next send. */
 	igc_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 16c728984164..60cec3540dd7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8297,7 +8297,7 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 
 	ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
-	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index a944be3c57b1..bb68737dce56 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2467,7 +2467,7 @@ out:
 		if (txq->count >= txq->tx_stop_threshold)
 			netif_tx_stop_queue(nq);
 
-		if (!skb->xmit_more || netif_xmit_stopped(nq) ||
+		if (!netdev_xmit_more() || netif_xmit_stopped(nq) ||
 		    txq->pending + frags > MVNETA_TXQ_DEC_SENT_MASK)
 			mvneta_txq_pend_desc_add(pp, txq, frags);
 		else
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 549d36497b8c..53abe925ecb1 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -767,7 +767,8 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev,
 	 */
 	wmb();
 
-	if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more)
+	if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) ||
+	    !netdev_xmit_more())
 		mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR);
 
 	return 0;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 99200b5dac76..961cd5e7bf2b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -909,7 +909,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 		nfp_net_tx_ring_stop(nd_q, tx_ring);
 
 	tx_ring->wr_ptr_add += nr_frags + 1;
-	if (__netdev_tx_sent_queue(nd_q, txbuf->real_len, skb->xmit_more))
+	if (__netdev_tx_sent_queue(nd_q, txbuf->real_len, netdev_xmit_more()))
 		nfp_net_tx_xmit_more_flush(tx_ring);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index c342b07e3a93..954015d2011a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1665,12 +1665,12 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	txq->tx_db.data.bd_prod =
 		cpu_to_le16(qed_chain_get_prod_idx(&txq->tx_pbl));
 
-	if (!skb->xmit_more || netif_xmit_stopped(netdev_txq))
+	if (!netdev_xmit_more() || netif_xmit_stopped(netdev_txq))
 		qede_update_tx_producer(txq);
 
 	if (unlikely(qed_chain_get_elem_left(&txq->tx_pbl)
 		      < (MAX_SKB_FRAGS + 1))) {
-		if (skb->xmit_more)
+		if (netdev_xmit_more())
 			qede_update_tx_producer(txq);
 
 		netif_tx_stop_queue(netdev_txq);
diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c
index 04aa592f35c3..ad335bca3273 100644
--- a/drivers/net/ethernet/rdc/r6040.c
+++ b/drivers/net/ethernet/rdc/r6040.c
@@ -840,7 +840,7 @@ static netdev_tx_t r6040_start_xmit(struct sk_buff *skb,
 	skb_tx_timestamp(skb);
 
 	/* Trigger the MAC to check the TX descriptor */
-	if (!skb->xmit_more || netif_queue_stopped(dev))
+	if (!netdev_xmit_more() || netif_queue_stopped(dev))
 		iowrite16(TM2TX, ioaddr + MTPR);
 	lp->tx_insert_ptr = descptr->vndescp;
 
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
index 99d86e39ff54..bf6c1c6779ff 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
@@ -995,7 +995,7 @@ static void xlgmac_dev_xmit(struct xlgmac_channel *channel)
 	smp_wmb();
 
 	ring->cur = cur_index + 1;
-	if (!pkt_info->skb->xmit_more ||
+	if (!netdev_xmit_more() ||
 	    netif_xmit_stopped(netdev_get_tx_queue(pdata->netdev,
 						   channel->queue_index)))
 		xlgmac_tx_start_xmit(channel, ring);
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 813d195bbd57..9a022539d305 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -964,7 +964,7 @@ int netvsc_send(struct net_device *ndev,
 	/* Keep aggregating only if stack says more data is coming
 	 * and not doing mixed modes send and not flow blocked
 	 */
-	xmit_more = skb->xmit_more &&
+	xmit_more = netdev_xmit_more() &&
 		!packet->cp_partial &&
 		!netif_xmit_stopped(netdev_get_tx_queue(ndev, packet->q_idx));
 
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 1b03c4b6ebff..ba246fc475ae 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1568,7 +1568,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct send_queue *sq = &vi->sq[qnum];
 	int err;
 	struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
-	bool kick = !skb->xmit_more;
+	bool kick = !netdev_xmit_more();
 	bool use_napi = sq->napi.weight;
 
 	/* Free up any pending old buffers before queueing new ones. */
diff --git a/drivers/staging/mt7621-eth/mtk_eth_soc.c b/drivers/staging/mt7621-eth/mtk_eth_soc.c
index 6027b19f7bc2..02a8584b3d1d 100644
--- a/drivers/staging/mt7621-eth/mtk_eth_soc.c
+++ b/drivers/staging/mt7621-eth/mtk_eth_soc.c
@@ -741,7 +741,8 @@ static int mtk_pdma_tx_map(struct sk_buff *skb, struct net_device *dev,
 	wmb();
 	atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring));
 
-	if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more)
+	if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) ||
+	    !netdev_xmit_more())
 		mtk_reg_w32(eth, ring->tx_next_idx, MTK_REG_TX_CTX_IDX0);
 
 	return 0;
@@ -935,7 +936,8 @@ static int mtk_qdma_tx_map(struct sk_buff *skb, struct net_device *dev,
 	 */
 	wmb();
 
-	if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more)
+	if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) ||
+	    !netdev_xmit_more())
 		mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR);
 
 	return 0;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2b25824642fa..eb9f05e0863d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4424,7 +4424,7 @@ static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
 					      struct sk_buff *skb, struct net_device *dev,
 					      bool more)
 {
-	skb->xmit_more = more ? 1 : 0;
+	__this_cpu_write(softnet_data.xmit.more, more);
 	return ops->ndo_start_xmit(skb, dev);
 }
 
-- 
cgit v1.2.3


From 4f296edeb9d4cf76b876869461a7ae627c307110 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 1 Apr 2019 16:42:17 +0200
Subject: drivers: net: aurora: use netdev_xmit_more helper

This is the last driver using always-0 skb->xmit_more.
Switch it to netdev_xmit_more and remove the now unused xmit_more flag
from sk_buff.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aurora/nb8800.c | 8 +++++---
 include/linux/skbuff.h               | 2 --
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index 6f56276015a4..f62deeb6e941 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -404,6 +404,7 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int dma_len;
 	unsigned int align;
 	unsigned int next;
+	bool xmit_more;
 
 	if (atomic_read(&priv->tx_free) <= NB8800_DESC_LOW) {
 		netif_stop_queue(dev);
@@ -423,9 +424,10 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
+	xmit_more = netdev_xmit_more();
 	if (atomic_dec_return(&priv->tx_free) <= NB8800_DESC_LOW) {
 		netif_stop_queue(dev);
-		skb->xmit_more = 0;
+		xmit_more = false;
 	}
 
 	next = priv->tx_next;
@@ -450,7 +452,7 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev)
 	desc->n_addr = priv->tx_bufs[next].dma_desc;
 	desc->config = DESC_BTS(2) | DESC_DS | DESC_EOF | dma_len;
 
-	if (!skb->xmit_more)
+	if (!xmit_more)
 		desc->config |= DESC_EOC;
 
 	txb->skb = skb;
@@ -468,7 +470,7 @@ static int nb8800_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	priv->tx_next = next;
 
-	if (!skb->xmit_more) {
+	if (!xmit_more) {
 		smp_wmb();
 		priv->tx_chain->ready = true;
 		priv->tx_chain = NULL;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9027a8c4219f..69b5538adcea 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -657,7 +657,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@tc_index: Traffic control index
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
- *	@xmit_more: More SKBs are pending for this queue
  *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
  *	@active_extensions: active extensions (skb_ext_id types)
  *	@ndisc_nodetype: router type (from link layer)
@@ -764,7 +763,6 @@ struct sk_buff {
 				fclone:2,
 				peeked:1,
 				head_frag:1,
-				xmit_more:1,
 				pfmemalloc:1;
 #ifdef CONFIG_SKB_EXTENSIONS
 	__u8			active_extensions;
-- 
cgit v1.2.3


From 38702cce547a74493687fd8bb925fbb5c3898ce3 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 29 Mar 2019 15:37:51 -0700
Subject: net/mlx5: Remove unused MLX5_*_DOORBELL_LOCK macros

MLX5_*_DOORBELL_LOCK macros provided a way to avoid locking for
mlx5_write64 on 64-bit platforms where it's not necessary. Currently all
calls to mlx5_write64 don't use a spinlock, so the macros became unused.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/doorbell.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/mlx5/doorbell.h b/include/linux/mlx5/doorbell.h
index 0787de28f2fc..9ef3f9d00154 100644
--- a/include/linux/mlx5/doorbell.h
+++ b/include/linux/mlx5/doorbell.h
@@ -42,10 +42,6 @@
  * PCI so we won't worry about it.
  */
 
-#define MLX5_DECLARE_DOORBELL_LOCK(name)
-#define MLX5_INIT_DOORBELL_LOCK(ptr)    do { } while (0)
-#define MLX5_GET_DOORBELL_LOCK(ptr)      (NULL)
-
 static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
 				spinlock_t *doorbell_lock)
 {
@@ -59,10 +55,6 @@ static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
  * MMIO writes.
  */
 
-#define MLX5_DECLARE_DOORBELL_LOCK(name) spinlock_t name;
-#define MLX5_INIT_DOORBELL_LOCK(ptr)     spin_lock_init(ptr)
-#define MLX5_GET_DOORBELL_LOCK(ptr)      (ptr)
-
 static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
 				spinlock_t *doorbell_lock)
 {
-- 
cgit v1.2.3


From bbf29f618e8c5bfd6efdad5fdc050a84bab795ab Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maximmi@mellanox.com>
Date: Fri, 29 Mar 2019 15:37:52 -0700
Subject: net/mlx5: Remove spinlock support from mlx5_write64

As there is no user of mlx5_write64 that passes a spinlock to
mlx5_write64, remove this functionality and simplify the function.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/qp.c                    |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  2 +-
 .../net/ethernet/mellanox/mlx5/core/fpga/conn.c    |  2 +-
 include/linux/mlx5/cq.h                            |  2 +-
 include/linux/mlx5/doorbell.h                      | 31 +++++++---------------
 5 files changed, 13 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index dd2ae640bc84..816c34ee91cf 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -5015,7 +5015,7 @@ out:
 		wmb();
 
 		/* currently we support only regular doorbells */
-		mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset, NULL);
+		mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset);
 		/* Make sure doorbells don't leak out of SQ spinlock
 		 * and reach the HCA out of order.
 		 */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8fa8fdd30b85..2623d3fb6b96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -916,7 +916,7 @@ void mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc,
 	 */
 	wmb();
 
-	mlx5_write64((__be32 *)ctrl, uar_map, NULL);
+	mlx5_write64((__be32 *)ctrl, uar_map);
 }
 
 static inline void mlx5e_cq_arm(struct mlx5e_cq *cq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 873541ef4c1b..ca2296a2f9ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -135,7 +135,7 @@ static void mlx5_fpga_conn_notify_hw(struct mlx5_fpga_conn *conn, void *wqe)
 	*conn->qp.wq.sq.db = cpu_to_be32(conn->qp.sq.pc);
 	/* Make sure that doorbell record is visible before ringing */
 	wmb();
-	mlx5_write64(wqe, conn->fdev->conn_res.uar->map + MLX5_BF_OFFSET, NULL);
+	mlx5_write64(wqe, conn->fdev->conn_res.uar->map + MLX5_BF_OFFSET);
 }
 
 static void mlx5_fpga_conn_post_send(struct mlx5_fpga_conn *conn,
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 612c8c2f2466..769326ea1d9b 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -170,7 +170,7 @@ static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd,
 	doorbell[0] = cpu_to_be32(sn << 28 | cmd | ci);
 	doorbell[1] = cpu_to_be32(cq->cqn);
 
-	mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, NULL);
+	mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL);
 }
 
 static inline void mlx5_cq_hold(struct mlx5_core_cq *cq)
diff --git a/include/linux/mlx5/doorbell.h b/include/linux/mlx5/doorbell.h
index 9ef3f9d00154..5c267707e1df 100644
--- a/include/linux/mlx5/doorbell.h
+++ b/include/linux/mlx5/doorbell.h
@@ -36,38 +36,25 @@
 #define MLX5_BF_OFFSET	      0x800
 #define MLX5_CQ_DOORBELL      0x20
 
-#if BITS_PER_LONG == 64
 /* Assume that we can just write a 64-bit doorbell atomically.  s390
  * actually doesn't have writeq() but S/390 systems don't even have
  * PCI so we won't worry about it.
+ *
+ * Note that the write is not atomic on 32-bit systems! In contrast to 64-bit
+ * ones, it requires proper locking. mlx5_write64 doesn't do any locking, so use
+ * it at your own discretion, protected by some kind of lock on 32 bits.
+ *
+ * TODO: use write{q,l}_relaxed()
  */
 
-static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
-				spinlock_t *doorbell_lock)
+static inline void mlx5_write64(__be32 val[2], void __iomem *dest)
 {
+#if BITS_PER_LONG == 64
 	__raw_writeq(*(u64 *)val, dest);
-}
-
 #else
-
-/* Just fall back to a spinlock to protect the doorbell if
- * BITS_PER_LONG is 32 -- there's no portable way to do atomic 64-bit
- * MMIO writes.
- */
-
-static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
-				spinlock_t *doorbell_lock)
-{
-	unsigned long flags;
-
-	if (doorbell_lock)
-		spin_lock_irqsave(doorbell_lock, flags);
 	__raw_writel((__force u32) val[0], dest);
 	__raw_writel((__force u32) val[1], dest + 4);
-	if (doorbell_lock)
-		spin_unlock_irqrestore(doorbell_lock, flags);
-}
-
 #endif
+}
 
 #endif /* MLX5_DOORBELL_H */
-- 
cgit v1.2.3


From 52c368dc3da7beb7b283133024af1b6d07bf93b9 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 29 Mar 2019 15:37:55 -0700
Subject: net/mlx5: Move health and page alloc init to mdev_init

Software structure initialization should be in mdev_init stage.

This provides a better logical separation of mlx5 core device
initialization flow and will help to seamlessly support creating different
mlx5 device types such as PF, VF and SF mlx5 sub-function virtual device.

This patch does not change any functionality.

Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c |  7 +++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c   | 37 +++++++++++++-----------
 include/linux/mlx5/driver.h                      |  1 +
 3 files changed, 28 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 196c07383082..1ab694bc22c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -352,6 +352,13 @@ void mlx5_drain_health_recovery(struct mlx5_core_dev *dev)
 	cancel_delayed_work_sync(&dev->priv.health.recover_work);
 }
 
+void mlx5_health_flush(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_health *health = &dev->priv.health;
+
+	flush_workqueue(health->wq);
+}
+
 void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index e26246eacea5..4bdcbfcc5476 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1220,6 +1220,7 @@ static const struct devlink_ops mlx5_devlink_ops = {
 static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char *name)
 {
 	struct mlx5_priv *priv = &dev->priv;
+	int err;
 
 	strncpy(priv->name, name, MLX5_MAX_NAME_LEN);
 	priv->name[MLX5_MAX_NAME_LEN - 1] = 0;
@@ -1247,11 +1248,28 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char
 		return -ENOMEM;
 	}
 
+	err = mlx5_health_init(dev);
+	if (err)
+		goto err_health_init;
+
+	err = mlx5_pagealloc_init(dev);
+	if (err)
+		goto err_pagealloc_init;
+
 	return 0;
+
+err_pagealloc_init:
+	mlx5_health_cleanup(dev);
+err_health_init:
+	debugfs_remove(dev->priv.dbg_root);
+
+	return err;
 }
 
 static void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 {
+	mlx5_pagealloc_cleanup(dev);
+	mlx5_health_cleanup(dev);
 	debugfs_remove_recursive(dev->priv.dbg_root);
 }
 
@@ -1280,16 +1298,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto pci_init_err;
 	}
 
-	err = mlx5_health_init(dev);
-	if (err) {
-		dev_err(&pdev->dev, "mlx5_health_init failed with error code %d\n", err);
-		goto close_pci;
-	}
-
-	err = mlx5_pagealloc_init(dev);
-	if (err)
-		goto err_pagealloc_init;
-
 	err = mlx5_load_one(dev, true);
 	if (err) {
 		dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err);
@@ -1307,11 +1315,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 
 clean_load:
 	mlx5_unload_one(dev, true);
+
 err_load_one:
-	mlx5_pagealloc_cleanup(dev);
-err_pagealloc_init:
-	mlx5_health_cleanup(dev);
-close_pci:
 	mlx5_pci_close(dev);
 pci_init_err:
 	mlx5_mdev_uninit(dev);
@@ -1331,12 +1336,10 @@ static void remove_one(struct pci_dev *pdev)
 
 	if (mlx5_unload_one(dev, true)) {
 		dev_err(&dev->pdev->dev, "mlx5_unload_one failed\n");
-		mlx5_health_cleanup(dev);
+		mlx5_health_flush(dev);
 		return;
 	}
 
-	mlx5_pagealloc_cleanup(dev);
-	mlx5_health_cleanup(dev);
 	mlx5_pci_close(dev);
 	mlx5_mdev_uninit(dev);
 	devlink_free(devlink);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c5454f985e1d..d7f5c0e8c47a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -883,6 +883,7 @@ void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome);
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
 int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
+void mlx5_health_flush(struct mlx5_core_dev *dev);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
-- 
cgit v1.2.3


From aa8106f137b93628d531ef5ecbbcbecef99370d7 Mon Sep 17 00:00:00 2001
From: Huy Nguyen <huyn@mellanox.com>
Date: Fri, 29 Mar 2019 15:38:01 -0700
Subject: net/mlx5: Add explicit bar address field

Add bar_addr field to store bar-0 address to avoid calling
pci_resource_start with hard-coded bar-0 as parameter.
Also note that different mlx5 device types will have bar_addr
on different bars.

This patch does not change any functionality.

Signed-off-by: Huy Nguyen <huyn@mellanox.com>
Signed-off-by: Vu Pham <vuhuong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/infiniband/hw/mlx5/cmd.c               | 4 ++--
 drivers/infiniband/hw/mlx5/main.c              | 8 ++++----
 drivers/infiniband/hw/mlx5/mr.c                | 3 +--
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/uar.c  | 2 +-
 include/linux/mlx5/driver.h                    | 1 +
 6 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index 6bcc63aaa50b..be95ac5aeb30 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -148,7 +148,7 @@ int mlx5_cmd_alloc_memic(struct mlx5_memic *memic, phys_addr_t *addr,
 			return ret;
 		}
 
-		*addr = pci_resource_start(dev->pdev, 0) +
+		*addr = dev->bar_addr +
 			MLX5_GET64(alloc_memic_out, out, memic_start_addr);
 
 		return 0;
@@ -167,7 +167,7 @@ int mlx5_cmd_dealloc_memic(struct mlx5_memic *memic, u64 addr, u64 length)
 	u64 start_page_idx;
 	int err;
 
-	addr -= pci_resource_start(dev->pdev, 0);
+	addr -= dev->bar_addr;
 	start_page_idx = (addr - hw_start_addr) >> PAGE_SHIFT;
 
 	MLX5_SET(dealloc_memic_in, in, opcode, MLX5_CMD_OP_DEALLOC_MEMIC);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 581ae11e2fc9..a5333db0a4c7 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1984,7 +1984,7 @@ static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev,
 
 	fw_uars_per_page = MLX5_CAP_GEN(dev->mdev, uar_4k) ? MLX5_UARS_IN_PAGE : 1;
 
-	return (pci_resource_start(dev->mdev->pdev, 0) >> PAGE_SHIFT) + uar_idx / fw_uars_per_page;
+	return (dev->mdev->bar_addr >> PAGE_SHIFT) + uar_idx / fw_uars_per_page;
 }
 
 static int get_command(unsigned long offset)
@@ -2174,7 +2174,7 @@ static int dm_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 	    page_idx + npages)
 		return -EINVAL;
 
-	pfn = ((pci_resource_start(dev->mdev->pdev, 0) +
+	pfn = ((dev->mdev->bar_addr +
 	      MLX5_CAP64_DEV_MEM(dev->mdev, memic_bar_start_addr)) >>
 	      PAGE_SHIFT) +
 	      page_idx;
@@ -2258,7 +2258,7 @@ struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
 		goto err_free;
 
 	start_offset = memic_addr & ~PAGE_MASK;
-	page_idx = (memic_addr - pci_resource_start(memic->dev->pdev, 0) -
+	page_idx = (memic_addr - memic->dev->bar_addr -
 		    MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
 		    PAGE_SHIFT;
 
@@ -2301,7 +2301,7 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm)
 	if (ret)
 		return ret;
 
-	page_idx = (dm->dev_addr - pci_resource_start(memic->dev->pdev, 0) -
+	page_idx = (dm->dev_addr - memic->dev->bar_addr -
 		    MLX5_CAP64_DEV_MEM(memic->dev, memic_bar_start_addr)) >>
 		    PAGE_SHIFT;
 	bitmap_clear(to_mucontext(ibdm->uobject->context)->dm_pages,
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index bf2b6ea23851..2b90d8dc70cd 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1232,8 +1232,7 @@ static struct ib_mr *mlx5_ib_get_memic_mr(struct ib_pd *pd, u64 memic_addr,
 	MLX5_SET64(mkc, mkc, len, length);
 	MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
-	MLX5_SET64(mkc, mkc, start_addr,
-		   memic_addr - pci_resource_start(dev->mdev->pdev, 0));
+	MLX5_SET64(mkc, mkc, start_addr, memic_addr - dev->mdev->bar_addr);
 
 	err = mlx5_core_create_mkey(mdev, &mr->mmkey, in, inlen);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 8bedbe497f02..bda9c4bd17e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -739,6 +739,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 
 	pci_set_drvdata(dev->pdev, dev);
 
+	dev->bar_addr = pci_resource_start(pdev, 0);
 	priv->numa_node = dev_to_node(&dev->pdev->dev);
 
 	err = mlx5_pci_enable_device(dev);
@@ -766,7 +767,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 	    pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP128))
 		mlx5_core_dbg(dev, "Enabling pci atomics failed\n");
 
-	dev->iseg_base = pci_resource_start(dev->pdev, 0);
+	dev->iseg_base = dev->bar_addr;
 	dev->iseg = ioremap(dev->iseg_base, sizeof(*dev->iseg));
 	if (!dev->iseg) {
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 8b97066dd1f1..b7d52709b8b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -79,7 +79,7 @@ static u64 uar2pfn(struct mlx5_core_dev *mdev, u32 index)
 	else
 		system_page_index = index;
 
-	return (pci_resource_start(mdev->pdev, 0) >> PAGE_SHIFT) + system_page_index;
+	return (mdev->bar_addr >> PAGE_SHIFT) + system_page_index;
 }
 
 static void up_rel_func(struct kref *kref)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d7f5c0e8c47a..c0ee597f5457 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -658,6 +658,7 @@ struct mlx5_core_dev {
 	u64			sys_image_guid;
 	phys_addr_t		iseg_base;
 	struct mlx5_init_seg __iomem *iseg;
+	phys_addr_t             bar_addr;
 	enum mlx5_device_state	state;
 	/* sync interface state */
 	struct mutex		intf_state_mutex;
-- 
cgit v1.2.3


From 4039049b5c462d3bb9ee8a68c4375582f037d5f2 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Fri, 29 Mar 2019 15:38:03 -0700
Subject: net/mlx5: Expose MPEIN (Management PCIE INfo) register layout

Expose PRM layout for handling MPEIN (Management PCIE Info). It will be
used in the downstream patch for querying MPEIN via the driver.

Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/driver.h   |  1 +
 include/linux/mlx5/mlx5_ifc.h | 51 ++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 51 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c0ee597f5457..0bfb95e30e47 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -133,6 +133,7 @@ enum {
 	MLX5_REG_MTRC_CONF	 = 0x9041,
 	MLX5_REG_MTRC_STDB	 = 0x9042,
 	MLX5_REG_MTRC_CTRL	 = 0x9043,
+	MLX5_REG_MPEIN		 = 0x9050,
 	MLX5_REG_MPCNT		 = 0x9051,
 	MLX5_REG_MTPPS		 = 0x9053,
 	MLX5_REG_MTPPSE		 = 0x9054,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 5decffe565fb..d31712af5a7b 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -8025,6 +8025,52 @@ struct mlx5_ifc_ppcnt_reg_bits {
 	union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
 };
 
+struct mlx5_ifc_mpein_reg_bits {
+	u8         reserved_at_0[0x2];
+	u8         depth[0x6];
+	u8         pcie_index[0x8];
+	u8         node[0x8];
+	u8         reserved_at_18[0x8];
+
+	u8         capability_mask[0x20];
+
+	u8         reserved_at_40[0x8];
+	u8         link_width_enabled[0x8];
+	u8         link_speed_enabled[0x10];
+
+	u8         lane0_physical_position[0x8];
+	u8         link_width_active[0x8];
+	u8         link_speed_active[0x10];
+
+	u8         num_of_pfs[0x10];
+	u8         num_of_vfs[0x10];
+
+	u8         bdf0[0x10];
+	u8         reserved_at_b0[0x10];
+
+	u8         max_read_request_size[0x4];
+	u8         max_payload_size[0x4];
+	u8         reserved_at_c8[0x5];
+	u8         pwr_status[0x3];
+	u8         port_type[0x4];
+	u8         reserved_at_d4[0xb];
+	u8         lane_reversal[0x1];
+
+	u8         reserved_at_e0[0x14];
+	u8         pci_power[0xc];
+
+	u8         reserved_at_100[0x20];
+
+	u8         device_status[0x10];
+	u8         port_state[0x8];
+	u8         reserved_at_138[0x8];
+
+	u8         reserved_at_140[0x10];
+	u8         receiver_detect_result[0x10];
+
+	u8         reserved_at_160[0x20];
+};
+
 struct mlx5_ifc_mpcnt_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         pcie_index[0x8];
@@ -8344,7 +8390,9 @@ struct mlx5_ifc_pcam_reg_bits {
 };
 
 struct mlx5_ifc_mcam_enhanced_features_bits {
-	u8         reserved_at_0[0x74];
+	u8         reserved_at_0[0x6e];
+	u8         pci_status_and_power[0x1];
+	u8         reserved_at_6f[0x5];
 	u8         mark_tx_action_cnp[0x1];
 	u8         mark_tx_action_cqe[0x1];
 	u8         dynamic_tx_overflow[0x1];
@@ -8944,6 +8992,7 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_pmtu_reg_bits pmtu_reg;
 	struct mlx5_ifc_ppad_reg_bits ppad_reg;
 	struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg;
+	struct mlx5_ifc_mpein_reg_bits mpein_reg;
 	struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg;
 	struct mlx5_ifc_pplm_reg_bits pplm_reg;
 	struct mlx5_ifc_pplr_reg_bits pplr_reg;
-- 
cgit v1.2.3


From 045925e3fe5b98e402337a176d154252c56cef2e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 27 Mar 2019 21:58:44 +0100
Subject: net: phy: add genphy_read_abilities

Similar to genphy_c45_pma_read_abilities() add a function to dynamically
detect the abilities of a Clause 22 PHY. This is mainly copied from
genphy_config_init().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 48 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/phy.h          |  1 +
 2 files changed, 49 insertions(+)

(limited to 'include')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index de2b6333e7ea..0af66f32d363 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1880,6 +1880,54 @@ int genphy_config_init(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(genphy_config_init);
 
+/**
+ * genphy_read_abilities - read PHY abilities from Clause 22 registers
+ * @phydev: target phy_device struct
+ *
+ * Description: Reads the PHY's abilities and populates
+ * phydev->supported accordingly.
+ *
+ * Returns: 0 on success, < 0 on failure
+ */
+int genphy_read_abilities(struct phy_device *phydev)
+{
+	int val;
+
+	linkmode_set_bit_array(phy_basic_ports_array,
+			       ARRAY_SIZE(phy_basic_ports_array),
+			       phydev->supported);
+
+	val = phy_read(phydev, MII_BMSR);
+	if (val < 0)
+		return val;
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported,
+			 val & BMSR_ANEGCAPABLE);
+
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, phydev->supported,
+			 val & BMSR_100FULL);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, phydev->supported,
+			 val & BMSR_100HALF);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, phydev->supported,
+			 val & BMSR_10FULL);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, phydev->supported,
+			 val & BMSR_10HALF);
+
+	if (val & BMSR_ESTATEN) {
+		val = phy_read(phydev, MII_ESTATUS);
+		if (val < 0)
+			return val;
+
+		linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				 phydev->supported, val & ESTATUS_1000_TFULL);
+		linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+				 phydev->supported, val & ESTATUS_1000_THALF);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(genphy_read_abilities);
+
 /* This is used for the phy device which doesn't support the MMD extended
  * register access, but it does have side effect when we are trying to access
  * the MMD register via indirect method.
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 34084892a466..ad88f063e50f 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1075,6 +1075,7 @@ void phy_attached_info(struct phy_device *phydev);
 
 /* Clause 22 PHY */
 int genphy_config_init(struct phy_device *phydev);
+int genphy_read_abilities(struct phy_device *phydev);
 int genphy_setup_forced(struct phy_device *phydev);
 int genphy_restart_aneg(struct phy_device *phydev);
 int genphy_config_eee_advert(struct phy_device *phydev);
-- 
cgit v1.2.3


From 06ee7115b0d1742de745ad143fb5e06d77d27fba Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Mon, 1 Apr 2019 21:27:40 -0700
Subject: bpf: add verifier stats and log_level bit 2

In order to understand the verifier bottlenecks add various stats
and extend log_level:
log_level 1 and 2 are kept as-is:
bit 0 - level=1 - print every insn and verifier state at branch points
bit 1 - level=2 - print every insn and verifier state at every insn
bit 2 - level=4 - print verifier error and stats at the end of verification

When verifier rejects the program the libbpf is trying to load the program twice.
Once with log_level=0 (no messages, only error code is reported to user space)
and second time with log_level=1 to tell the user why the verifier rejected it.

With introduction of bit 2 - level=4 the libbpf can choose to always use that
level and load programs once, since the verification speed is not affected and
in case of error the verbose message will be available.

Note that the verifier stats are not part of uapi just like all other
verbose messages. They're expected to change in the future.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf_verifier.h | 21 ++++++++++++
 kernel/bpf/verifier.c        | 76 ++++++++++++++++++++++++++++++--------------
 2 files changed, 73 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7d8228d1c898..f7e15eeb60bb 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -248,6 +248,12 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
 	return log->len_used >= log->len_total - 1;
 }
 
+#define BPF_LOG_LEVEL1	1
+#define BPF_LOG_LEVEL2	2
+#define BPF_LOG_STATS	4
+#define BPF_LOG_LEVEL	(BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2)
+#define BPF_LOG_MASK	(BPF_LOG_LEVEL | BPF_LOG_STATS)
+
 static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 {
 	return log->level && log->ubuf && !bpf_verifier_log_full(log);
@@ -284,6 +290,21 @@ struct bpf_verifier_env {
 	struct bpf_verifier_log log;
 	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
 	u32 subprog_cnt;
+	/* number of instructions analyzed by the verifier */
+	u32 insn_processed;
+	/* total verification time */
+	u64 verification_time;
+	/* maximum number of verifier states kept in 'branching' instructions */
+	u32 max_states_per_insn;
+	/* total number of allocated verifier states */
+	u32 total_states;
+	/* some states are freed during program analysis.
+	 * this is peak number of states. this number dominates kernel
+	 * memory consumption during verification
+	 */
+	u32 peak_states;
+	/* longest register parentage chain walked for liveness marking */
+	u32 longest_mark_read_walk;
 };
 
 __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 87221fda1321..e2001c1e40b3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1092,7 +1092,7 @@ static int check_subprogs(struct bpf_verifier_env *env)
 	 */
 	subprog[env->subprog_cnt].start = insn_cnt;
 
-	if (env->log.level > 1)
+	if (env->log.level & BPF_LOG_LEVEL2)
 		for (i = 0; i < env->subprog_cnt; i++)
 			verbose(env, "func#%d @%d\n", i, subprog[i].start);
 
@@ -1139,6 +1139,7 @@ static int mark_reg_read(struct bpf_verifier_env *env,
 			 struct bpf_reg_state *parent)
 {
 	bool writes = parent == state->parent; /* Observe write marks */
+	int cnt = 0;
 
 	while (parent) {
 		/* if read wasn't screened by an earlier write ... */
@@ -1155,7 +1156,11 @@ static int mark_reg_read(struct bpf_verifier_env *env,
 		state = parent;
 		parent = state->parent;
 		writes = true;
+		cnt++;
 	}
+
+	if (env->longest_mark_read_walk < cnt)
+		env->longest_mark_read_walk = cnt;
 	return 0;
 }
 
@@ -1455,7 +1460,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 	 * need to try adding each of min_value and max_value to off
 	 * to make sure our theoretical access will be safe.
 	 */
-	if (env->log.level)
+	if (env->log.level & BPF_LOG_LEVEL)
 		print_verifier_state(env, state);
 
 	/* The minimum value is only important with signed
@@ -2938,7 +2943,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	/* and go analyze first insn of the callee */
 	*insn_idx = target_insn;
 
-	if (env->log.level) {
+	if (env->log.level & BPF_LOG_LEVEL) {
 		verbose(env, "caller:\n");
 		print_verifier_state(env, caller);
 		verbose(env, "callee:\n");
@@ -2978,7 +2983,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 		return err;
 
 	*insn_idx = callee->callsite + 1;
-	if (env->log.level) {
+	if (env->log.level & BPF_LOG_LEVEL) {
 		verbose(env, "returning from callee:\n");
 		print_verifier_state(env, callee);
 		verbose(env, "to caller at %d:\n", *insn_idx);
@@ -5001,7 +5006,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 			insn->dst_reg);
 		return -EACCES;
 	}
-	if (env->log.level)
+	if (env->log.level & BPF_LOG_LEVEL)
 		print_verifier_state(env, this_branch->frame[this_branch->curframe]);
 	return 0;
 }
@@ -6181,6 +6186,9 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 		states_cnt++;
 	}
 
+	if (env->max_states_per_insn < states_cnt)
+		env->max_states_per_insn = states_cnt;
+
 	if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
 		return 0;
 
@@ -6194,6 +6202,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 	new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
 	if (!new_sl)
 		return -ENOMEM;
+	env->total_states++;
+	env->peak_states++;
 
 	/* add new state to the head of linked list */
 	new = &new_sl->state;
@@ -6278,8 +6288,7 @@ static int do_check(struct bpf_verifier_env *env)
 	struct bpf_verifier_state *state;
 	struct bpf_insn *insns = env->prog->insnsi;
 	struct bpf_reg_state *regs;
-	int insn_cnt = env->prog->len, i;
-	int insn_processed = 0;
+	int insn_cnt = env->prog->len;
 	bool do_print_state = false;
 
 	env->prev_linfo = NULL;
@@ -6314,10 +6323,10 @@ static int do_check(struct bpf_verifier_env *env)
 		insn = &insns[env->insn_idx];
 		class = BPF_CLASS(insn->code);
 
-		if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
+		if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
 			verbose(env,
 				"BPF program is too large. Processed %d insn\n",
-				insn_processed);
+				env->insn_processed);
 			return -E2BIG;
 		}
 
@@ -6326,7 +6335,7 @@ static int do_check(struct bpf_verifier_env *env)
 			return err;
 		if (err == 1) {
 			/* found equivalent state, can prune the search */
-			if (env->log.level) {
+			if (env->log.level & BPF_LOG_LEVEL) {
 				if (do_print_state)
 					verbose(env, "\nfrom %d to %d%s: safe\n",
 						env->prev_insn_idx, env->insn_idx,
@@ -6344,8 +6353,9 @@ static int do_check(struct bpf_verifier_env *env)
 		if (need_resched())
 			cond_resched();
 
-		if (env->log.level > 1 || (env->log.level && do_print_state)) {
-			if (env->log.level > 1)
+		if (env->log.level & BPF_LOG_LEVEL2 ||
+		    (env->log.level & BPF_LOG_LEVEL && do_print_state)) {
+			if (env->log.level & BPF_LOG_LEVEL2)
 				verbose(env, "%d:", env->insn_idx);
 			else
 				verbose(env, "\nfrom %d to %d%s:",
@@ -6356,7 +6366,7 @@ static int do_check(struct bpf_verifier_env *env)
 			do_print_state = false;
 		}
 
-		if (env->log.level) {
+		if (env->log.level & BPF_LOG_LEVEL) {
 			const struct bpf_insn_cbs cbs = {
 				.cb_print	= verbose,
 				.private_data	= env,
@@ -6621,16 +6631,6 @@ process_bpf_exit:
 		env->insn_idx++;
 	}
 
-	verbose(env, "processed %d insns (limit %d), stack depth ",
-		insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
-	for (i = 0; i < env->subprog_cnt; i++) {
-		u32 depth = env->subprog_info[i].stack_depth;
-
-		verbose(env, "%d", depth);
-		if (i + 1 < env->subprog_cnt)
-			verbose(env, "+");
-	}
-	verbose(env, "\n");
 	env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
 	return 0;
 }
@@ -7854,9 +7854,34 @@ static void free_states(struct bpf_verifier_env *env)
 	kfree(env->explored_states);
 }
 
+static void print_verification_stats(struct bpf_verifier_env *env)
+{
+	int i;
+
+	if (env->log.level & BPF_LOG_STATS) {
+		verbose(env, "verification time %lld usec\n",
+			div_u64(env->verification_time, 1000));
+		verbose(env, "stack depth ");
+		for (i = 0; i < env->subprog_cnt; i++) {
+			u32 depth = env->subprog_info[i].stack_depth;
+
+			verbose(env, "%d", depth);
+			if (i + 1 < env->subprog_cnt)
+				verbose(env, "+");
+		}
+		verbose(env, "\n");
+	}
+	verbose(env, "processed %d insns (limit %d) max_states_per_insn %d "
+		"total_states %d peak_states %d mark_read %d\n",
+		env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS,
+		env->max_states_per_insn, env->total_states,
+		env->peak_states, env->longest_mark_read_walk);
+}
+
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	      union bpf_attr __user *uattr)
 {
+	u64 start_time = ktime_get_ns();
 	struct bpf_verifier_env *env;
 	struct bpf_verifier_log *log;
 	int i, len, ret = -EINVAL;
@@ -7899,7 +7924,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 		ret = -EINVAL;
 		/* log attributes have to be sane */
 		if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
-		    !log->level || !log->ubuf)
+		    !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK)
 			goto err_unlock;
 	}
 
@@ -7980,6 +8005,9 @@ skip_full_check:
 	if (ret == 0)
 		ret = fixup_call_args(env);
 
+	env->verification_time = ktime_get_ns() - start_time;
+	print_verification_stats(env);
+
 	if (log->level && bpf_verifier_log_full(log))
 		ret = -ENOSPC;
 	if (log->level && !log->ubuf) {
-- 
cgit v1.2.3


From 9f4686c41bdff051f557accb531af79dd1773687 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Mon, 1 Apr 2019 21:27:41 -0700
Subject: bpf: improve verification speed by droping states

Branch instructions, branch targets and calls in a bpf program are
the places where the verifier remembers states that led to successful
verification of the program.
These states are used to prune brute force program analysis.
For unprivileged programs there is a limit of 64 states per such
'branching' instructions (maximum length is tracked by max_states_per_insn
counter introduced in the previous patch).
Simply reducing this threshold to 32 or lower increases insn_processed
metric to the point that small valid programs get rejected.
For root programs there is no limit and cilium programs can have
max_states_per_insn to be 100 or higher.
Walking 100+ states multiplied by number of 'branching' insns during
verification consumes significant amount of cpu time.
Turned out simple LRU-like mechanism can be used to remove states
that unlikely will be helpful in future search pruning.
This patch introduces hit_cnt and miss_cnt counters:
hit_cnt - this many times this state successfully pruned the search
miss_cnt - this many times this state was not equivalent to other states
(and that other states were added to state list)

The heuristic introduced in this patch is:
if (sl->miss_cnt > sl->hit_cnt * 3 + 3)
  /* drop this state from future considerations */

Higher numbers increase max_states_per_insn (allow more states to be
considered for pruning) and slow verification speed, but do not meaningfully
reduce insn_processed metric.
Lower numbers drop too many states and insn_processed increases too much.
Many different formulas were considered.
This one is simple and works well enough in practice.
(the analysis was done on selftests/progs/* and on cilium programs)

The end result is this heuristic improves verification speed by 10 times.
Large synthetic programs that used to take a second more now take
1/10 of a second.
In cases where max_states_per_insn used to be 100 or more, now it's ~10.

There is a slight increase in insn_processed for cilium progs:
                       before   after
bpf_lb-DLB_L3.o 	1831	1838
bpf_lb-DLB_L4.o 	3029	3218
bpf_lb-DUNKNOWN.o 	1064	1064
bpf_lxc-DDROP_ALL.o	26309	26935
bpf_lxc-DUNKNOWN.o	33517	34439
bpf_netdev.o		9713	9721
bpf_overlay.o		6184	6184
bpf_lcx_jit.o		37335	39389
And 2-3 times improvement in the verification speed.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf_verifier.h |  2 ++
 kernel/bpf/verifier.c        | 44 +++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 43 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index f7e15eeb60bb..fc8254d6b569 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -207,6 +207,7 @@ struct bpf_verifier_state {
 struct bpf_verifier_state_list {
 	struct bpf_verifier_state state;
 	struct bpf_verifier_state_list *next;
+	int miss_cnt, hit_cnt;
 };
 
 /* Possible states for alu_state member. */
@@ -280,6 +281,7 @@ struct bpf_verifier_env {
 	bool strict_alignment;		/* perform strict pointer alignment checks */
 	struct bpf_verifier_state *cur_state; /* current verifier state */
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
+	struct bpf_verifier_state_list *free_list;
 	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
 	u32 used_map_cnt;		/* number of used maps */
 	u32 id_gen;			/* used to generate unique reg IDs */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e2001c1e40b3..a636db4a7a4e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6152,11 +6152,13 @@ static int propagate_liveness(struct bpf_verifier_env *env,
 static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 {
 	struct bpf_verifier_state_list *new_sl;
-	struct bpf_verifier_state_list *sl;
+	struct bpf_verifier_state_list *sl, **pprev;
 	struct bpf_verifier_state *cur = env->cur_state, *new;
 	int i, j, err, states_cnt = 0;
 
-	sl = env->explored_states[insn_idx];
+	pprev = &env->explored_states[insn_idx];
+	sl = *pprev;
+
 	if (!sl)
 		/* this 'insn_idx' instruction wasn't marked, so we will not
 		 * be doing state search here
@@ -6167,6 +6169,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 
 	while (sl != STATE_LIST_MARK) {
 		if (states_equal(env, &sl->state, cur)) {
+			sl->hit_cnt++;
 			/* reached equivalent register/stack state,
 			 * prune the search.
 			 * Registers read by the continuation are read by us.
@@ -6182,8 +6185,35 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 				return err;
 			return 1;
 		}
-		sl = sl->next;
 		states_cnt++;
+		sl->miss_cnt++;
+		/* heuristic to determine whether this state is beneficial
+		 * to keep checking from state equivalence point of view.
+		 * Higher numbers increase max_states_per_insn and verification time,
+		 * but do not meaningfully decrease insn_processed.
+		 */
+		if (sl->miss_cnt > sl->hit_cnt * 3 + 3) {
+			/* the state is unlikely to be useful. Remove it to
+			 * speed up verification
+			 */
+			*pprev = sl->next;
+			if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) {
+				free_verifier_state(&sl->state, false);
+				kfree(sl);
+				env->peak_states--;
+			} else {
+				/* cannot free this state, since parentage chain may
+				 * walk it later. Add it for free_list instead to
+				 * be freed at the end of verification
+				 */
+				sl->next = env->free_list;
+				env->free_list = sl;
+			}
+			sl = *pprev;
+			continue;
+		}
+		pprev = &sl->next;
+		sl = *pprev;
 	}
 
 	if (env->max_states_per_insn < states_cnt)
@@ -7836,6 +7866,14 @@ static void free_states(struct bpf_verifier_env *env)
 	struct bpf_verifier_state_list *sl, *sln;
 	int i;
 
+	sl = env->free_list;
+	while (sl) {
+		sln = sl->next;
+		free_verifier_state(&sl->state, false);
+		kfree(sl);
+		sl = sln;
+	}
+
 	if (!env->explored_states)
 		return;
 
-- 
cgit v1.2.3


From c04c0d2b968ac45d6ef020316808ef6c82325a82 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Mon, 1 Apr 2019 21:27:45 -0700
Subject: bpf: increase complexity limit and maximum program size

Large verifier speed improvements allow to increase
verifier complexity limit.
Now regardless of the program composition and its size it takes
little time for the verifier to hit insn_processed limit.
On typical x86 machine non-debug kernel processes 1M instructions
in 1/10 of a second.
(before these speed improvements specially crafted programs
could be hitting multi-second verification times)
Full kasan kernel with debug takes ~1 second for the same 1M insns.
Hence bump the BPF_COMPLEXITY_LIMIT_INSNS limit to 1M.
Also increase the number of instructions per program
from 4k to internal BPF_COMPLEXITY_LIMIT_INSNS limit.
4k limit was confusing to users, since small programs with hundreds
of insns could be hitting BPF_COMPLEXITY_LIMIT_INSNS limit.
Sometimes adding more insns and bpf_trace_printk debug statements
would make the verifier accept the program while removing
code would make the verifier reject it.
Some user space application started to add #define MAX_FOO to
their programs and do:
  MAX_FOO=100;
again:
  compile with MAX_FOO;
  try to load;
  if (fails_to_load) { reduce MAX_FOO; goto again; }
to be able to fit maximum amount of processing into single program.
Other users artificially split their single program into a set of programs
and use all 32 iterations of tail_calls to increase compute limits.
And the most advanced folks used unlimited tc-bpf filter list
to execute many bpf programs.
Essentially the users managed to workaround 4k insn limit.
This patch removes the limit for root programs from uapi.
BPF_COMPLEXITY_LIMIT_INSNS is the kernel internal limit
and success to load the program no longer depends on program size,
but on 'smartness' of the verifier only.
The verifier will continue to get smarter with every kernel release.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h   | 1 +
 kernel/bpf/syscall.c  | 3 ++-
 kernel/bpf/verifier.c | 1 -
 3 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f62897198844..a445194b5fb6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -421,6 +421,7 @@ struct bpf_array {
 	};
 };
 
+#define BPF_COMPLEXITY_LIMIT_INSNS      1000000 /* yes. 1M insns */
 #define MAX_TAIL_CALL_CNT 32
 
 struct bpf_event_entry {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index afca36f53c49..1d65e56594db 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1557,7 +1557,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	/* eBPF programs must be GPL compatible to use GPL-ed functions */
 	is_gpl = license_is_gpl_compatible(license);
 
-	if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
+	if (attr->insn_cnt == 0 ||
+	    attr->insn_cnt > (capable(CAP_SYS_ADMIN) ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
 		return -E2BIG;
 	if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
 	    type != BPF_PROG_TYPE_CGROUP_SKB &&
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6dcfeb44bb8e..b631e89e7a51 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -176,7 +176,6 @@ struct bpf_verifier_stack_elem {
 	struct bpf_verifier_stack_elem *next;
 };
 
-#define BPF_COMPLEXITY_LIMIT_INSNS	131072
 #define BPF_COMPLEXITY_LIMIT_STACK	1024
 #define BPF_COMPLEXITY_LIMIT_STATES	64
 
-- 
cgit v1.2.3


From 4950c2ba49cc6f2b38dbedcfa0ff67acf761419a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 2 Apr 2019 20:43:30 +0200
Subject: net: phy: fix autoneg mismatch case in genphy_read_status

The original patch didn't consider the case that autoneg process
finishes successfully but both link partners have no mode in common.
In this case there's no link, nevertheless we may be interested in
what the link partner advertised.

Like phydev->link we set phydev->autoneg_complete in
genphy_update_link() and use the stored value in genphy_read_status().
This way we don't have to read register BMSR again.

Fixes: b6163f194c69 ("net: phy: improve genphy_read_status")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 8 +++-----
 include/linux/phy.h          | 1 +
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 67fc581e3598..72fc714c9427 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1723,10 +1723,8 @@ int genphy_update_link(struct phy_device *phydev)
 	if (status < 0)
 		return status;
 
-	if ((status & BMSR_LSTATUS) == 0)
-		phydev->link = 0;
-	else
-		phydev->link = 1;
+	phydev->link = status & BMSR_LSTATUS ? 1 : 0;
+	phydev->autoneg_complete = status & BMSR_ANEGCOMPLETE ? 1 : 0;
 
 	return 0;
 }
@@ -1757,7 +1755,7 @@ int genphy_read_status(struct phy_device *phydev)
 
 	linkmode_zero(phydev->lp_advertising);
 
-	if (phydev->autoneg == AUTONEG_ENABLE && phydev->link) {
+	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) {
 		if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
 				      phydev->supported) ||
 		    linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index ad88f063e50f..ab7439b3da2b 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -390,6 +390,7 @@ struct phy_device {
 	unsigned autoneg:1;
 	/* The most recently read link state */
 	unsigned link:1;
+	unsigned autoneg_complete:1;
 
 	/* Interrupts are enabled */
 	unsigned interrupts:1;
-- 
cgit v1.2.3


From 0af7e7c128eb33f2dc16ed088ced00675785d628 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 2 Apr 2019 14:11:54 -0700
Subject: ipv4: Update fib_table_lookup tracepoint to take common nexthop

Update fib_table_lookup tracepoint to take a fib_nh_common struct and
dump the v6 gateway address if the nexthop uses it.

Over the years saddr has not proven useful and the output of the
tracepoint produces very long lines. Since saddr is not part of
fib_nh_common, drop it. If it needs to be added later, fib_nh which
contains saddr can be obtained from a fib_nh_common via container_of.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/fib.h | 45 ++++++++++++++++++++++++++-------------------
 net/ipv4/fib_trie.c        |  2 +-
 2 files changed, 27 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/fib.h b/include/trace/events/fib.h
index 61ea7a24c8e5..7f83b6eafc5c 100644
--- a/include/trace/events/fib.h
+++ b/include/trace/events/fib.h
@@ -13,9 +13,9 @@
 TRACE_EVENT(fib_table_lookup,
 
 	TP_PROTO(u32 tb_id, const struct flowi4 *flp,
-		 const struct fib_nh *nh, int err),
+		 const struct fib_nh_common *nhc, int err),
 
-	TP_ARGS(tb_id, flp, nh, err),
+	TP_ARGS(tb_id, flp, nhc, err),
 
 	TP_STRUCT__entry(
 		__field(	u32,	tb_id		)
@@ -28,14 +28,17 @@ TRACE_EVENT(fib_table_lookup,
 		__field(	__u8,	flags		)
 		__array(	__u8,	src,	4	)
 		__array(	__u8,	dst,	4	)
-		__array(	__u8,	gw,	4	)
-		__array(	__u8,	saddr,	4	)
+		__array(	__u8,	gw4,	4	)
+		__array(	__u8,	gw6,	16	)
 		__field(	u16,	sport		)
 		__field(	u16,	dport		)
 		__dynamic_array(char,  name,   IFNAMSIZ )
 	),
 
 	TP_fast_assign(
+		struct in6_addr in6_zero = {};
+		struct net_device *dev;
+		struct in6_addr *in6;
 		__be32 *p32;
 
 		__entry->tb_id = tb_id;
@@ -62,33 +65,37 @@ TRACE_EVENT(fib_table_lookup,
 			__entry->dport = 0;
 		}
 
-		if (nh) {
-			struct net_device *dev;
+		dev = nhc ? nhc->nhc_dev : NULL;
+		__assign_str(name, dev ? dev->name : "-");
 
-			p32 = (__be32 *) __entry->saddr;
-			*p32 = nh->nh_saddr;
+		if (nhc) {
+			if (nhc->nhc_family == AF_INET) {
+				p32 = (__be32 *) __entry->gw4;
+				*p32 = nhc->nhc_gw.ipv4;
 
-			p32 = (__be32 *) __entry->gw;
-			*p32 = nh->fib_nh_gw4;
+				in6 = (struct in6_addr *)__entry->gw6;
+				*in6 = in6_zero;
+			} else if (nhc->nhc_family == AF_INET6) {
+				p32 = (__be32 *) __entry->gw4;
+				*p32 = 0;
 
-			dev = nh->fib_nh_dev;
-			__assign_str(name, dev ? dev->name : "-");
+				in6 = (struct in6_addr *)__entry->gw6;
+				*in6 = nhc->nhc_gw.ipv6;
+			}
 		} else {
-			p32 = (__be32 *) __entry->saddr;
+			p32 = (__be32 *) __entry->gw4;
 			*p32 = 0;
 
-			p32 = (__be32 *) __entry->gw;
-			*p32 = 0;
-
-			__assign_str(name, "-");
+			in6 = (struct in6_addr *)__entry->gw6;
+			*in6 = in6_zero;
 		}
 	),
 
-	TP_printk("table %u oif %d iif %d proto %u %pI4/%u -> %pI4/%u tos %d scope %d flags %x ==> dev %s gw %pI4 src %pI4 err %d",
+	TP_printk("table %u oif %d iif %d proto %u %pI4/%u -> %pI4/%u tos %d scope %d flags %x ==> dev %s gw %pI4/%pI6c err %d",
 		  __entry->tb_id, __entry->oif, __entry->iif, __entry->proto,
 		  __entry->src, __entry->sport, __entry->dst, __entry->dport,
 		  __entry->tos, __entry->scope, __entry->flags,
-		  __get_str(name), __entry->gw, __entry->saddr, __entry->err)
+		  __get_str(name), __entry->gw4, __entry->gw6, __entry->err)
 );
 #endif /* _TRACE_FIB_H */
 
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 1e3b492690f9..13b3327206f9 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1498,7 +1498,7 @@ found:
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 			this_cpu_inc(stats->semantic_match_passed);
 #endif
-			trace_fib_table_lookup(tb->tb_id, flp, nh, err);
+			trace_fib_table_lookup(tb->tb_id, flp, &nh->nh_common, err);
 
 			return err;
 		}
-- 
cgit v1.2.3


From eba618abacade71669eb67c3360eecfee810cc88 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 2 Apr 2019 14:11:55 -0700
Subject: ipv4: Add fib_nh_common to fib_result

Most of the ipv4 code only needs data from fib_nh_common. Add
fib_nh_common selection to fib_result and update users to use it.

Right now, fib_nh_common in fib_result will point to a fib_nh struct
that is embedded within a fib_info:

        fib_info  --> fib_nh
                      fib_nh
                      ...
                      fib_nh
                        ^
    fib_result->nhc ----+

Later, nhc can point to a fib_nh within a nexthop struct:

        fib_info --> nexthop --> fib_nh
                                   ^
    fib_result->nhc ---------------+

or for a nexthop group:

        fib_info --> nexthop --> nexthop --> fib_nh
                                 nexthop --> fib_nh
                                 ...
                                 nexthop --> fib_nh
                                               ^
    fib_result->nhc ---------------------------+

In all cases nhsel within fib_result will point to which leg in the
multipath route is used.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     | 47 +++++++++++++++++--------------------
 net/core/filter.c        | 12 +++++-----
 net/ipv4/fib_frontend.c  |  6 ++---
 net/ipv4/fib_lookup.h    |  1 +
 net/ipv4/fib_semantics.c | 25 ++++++++++++++++----
 net/ipv4/fib_trie.c      | 13 ++++++-----
 net/ipv4/route.c         | 60 ++++++++++++++++++++++++++++++++----------------
 7 files changed, 99 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 12a6d759cf57..1f4a3b8bf584 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -156,15 +156,16 @@ struct fib_rule;
 
 struct fib_table;
 struct fib_result {
-	__be32		prefix;
-	unsigned char	prefixlen;
-	unsigned char	nh_sel;
-	unsigned char	type;
-	unsigned char	scope;
-	u32		tclassid;
-	struct fib_info *fi;
-	struct fib_table *table;
-	struct hlist_head *fa_head;
+	__be32			prefix;
+	unsigned char		prefixlen;
+	unsigned char		nh_sel;
+	unsigned char		type;
+	unsigned char		scope;
+	u32			tclassid;
+	struct fib_nh_common	*nhc;
+	struct fib_info		*fi;
+	struct fib_table	*table;
+	struct hlist_head	*fa_head;
 };
 
 struct fib_result_nl {
@@ -182,11 +183,10 @@ struct fib_result_nl {
 	int             err;
 };
 
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-#define FIB_RES_NH(res)		((res).fi->fib_nh[(res).nh_sel])
-#else /* CONFIG_IP_ROUTE_MULTIPATH */
-#define FIB_RES_NH(res)		((res).fi->fib_nh[0])
-#endif /* CONFIG_IP_ROUTE_MULTIPATH */
+static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel)
+{
+	return &fi->fib_nh[nhsel].nh_common;
+}
 
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 #define FIB_TABLE_HASHSZ 256
@@ -195,18 +195,11 @@ struct fib_result_nl {
 #endif
 
 __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh);
+__be32 fib_result_prefsrc(struct net *net, struct fib_result *res);
 
-#define FIB_RES_SADDR(net, res)				\
-	((FIB_RES_NH(res).nh_saddr_genid ==		\
-	  atomic_read(&(net)->ipv4.dev_addr_genid)) ?	\
-	 FIB_RES_NH(res).nh_saddr :			\
-	 fib_info_update_nh_saddr((net), &FIB_RES_NH(res)))
-#define FIB_RES_GW(res)			(FIB_RES_NH(res).fib_nh_gw4)
-#define FIB_RES_DEV(res)		(FIB_RES_NH(res).fib_nh_dev)
-#define FIB_RES_OIF(res)		(FIB_RES_NH(res).fib_nh_oif)
-
-#define FIB_RES_PREFSRC(net, res)	((res).fi->fib_prefsrc ? : \
-					 FIB_RES_SADDR(net, res))
+#define FIB_RES_NHC(res)		((res).nhc)
+#define FIB_RES_DEV(res)	(FIB_RES_NHC(res)->nhc_dev)
+#define FIB_RES_OIF(res)	(FIB_RES_NHC(res)->nhc_oif)
 
 struct fib_entry_notifier_info {
 	struct fib_notifier_info info; /* must be first */
@@ -453,10 +446,12 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias);
 static inline void fib_combine_itag(u32 *itag, const struct fib_result *res)
 {
 #ifdef CONFIG_IP_ROUTE_CLASSID
+	struct fib_nh_common *nhc = res->nhc;
+	struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	u32 rtag;
 #endif
-	*itag = FIB_RES_NH(*res).nh_tclassid<<16;
+	*itag = nh->nh_tclassid << 16;
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	rtag = res->tclassid;
 	if (*itag == 0)
diff --git a/net/core/filter.c b/net/core/filter.c
index cdaafa3322db..08b53af84132 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4555,11 +4555,11 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
 static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 			       u32 flags, bool check_mtu)
 {
+	struct fib_nh_common *nhc;
 	struct in_device *in_dev;
 	struct neighbour *neigh;
 	struct net_device *dev;
 	struct fib_result res;
-	struct fib_nh *nh;
 	struct flowi4 fl4;
 	int err;
 	u32 mtu;
@@ -4632,15 +4632,15 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
-	nh = &res.fi->fib_nh[res.nh_sel];
+	nhc = res.nhc;
 
 	/* do not handle lwt encaps right now */
-	if (nh->fib_nh_lws)
+	if (nhc->nhc_lwtstate)
 		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
-	dev = nh->fib_nh_dev;
-	if (nh->fib_nh_gw4)
-		params->ipv4_dst = nh->fib_nh_gw4;
+	dev = nhc->nhc_dev;
+	if (nhc->nhc_has_gw)
+		params->ipv4_dst = nhc->nhc_gw.ipv4;
 
 	params->rt_metric = res.fi->fib_priority;
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index ffbe24397dbe..15f779bd26b3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -307,7 +307,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 			.flowi4_mark = vmark ? skb->mark : 0,
 		};
 		if (!fib_lookup(net, &fl4, &res, 0))
-			return FIB_RES_PREFSRC(net, res);
+			return fib_result_prefsrc(net, &res);
 	} else {
 		scope = RT_SCOPE_LINK;
 	}
@@ -390,7 +390,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 
 	dev_match = fib_info_nh_uses_dev(res.fi, dev);
 	if (dev_match) {
-		ret = FIB_RES_NH(res).fib_nh_scope >= RT_SCOPE_HOST;
+		ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
 		return ret;
 	}
 	if (no_addr)
@@ -402,7 +402,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	ret = 0;
 	if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
 		if (res.type == RTN_UNICAST)
-			ret = FIB_RES_NH(res).fib_nh_scope >= RT_SCOPE_HOST;
+			ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
 	}
 	return ret;
 
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index e6ff282bb7f4..7945f0534db7 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -45,6 +45,7 @@ static inline void fib_result_assign(struct fib_result *res,
 {
 	/* we used to play games with refcounts, but we now use RCU */
 	res->fi = fi;
+	res->nhc = fib_info_nhc(fi, 0);
 }
 
 struct fib_prop {
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index df777af7e278..42666a409da0 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1075,6 +1075,21 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
 	return nh->nh_saddr;
 }
 
+__be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
+{
+	struct fib_nh_common *nhc = res->nhc;
+	struct fib_nh *nh;
+
+	if (res->fi->fib_prefsrc)
+		return res->fi->fib_prefsrc;
+
+	nh = container_of(nhc, struct fib_nh, nh_common);
+	if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid))
+		return nh->nh_saddr;
+
+	return fib_info_update_nh_saddr(net, nh);
+}
+
 static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
 {
 	if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
@@ -1762,20 +1777,22 @@ void fib_select_multipath(struct fib_result *res, int hash)
 	struct net *net = fi->fib_net;
 	bool first = false;
 
-	for_nexthops(fi) {
+	change_nexthops(fi) {
 		if (net->ipv4.sysctl_fib_multipath_use_neigh) {
-			if (!fib_good_nh(nh))
+			if (!fib_good_nh(nexthop_nh))
 				continue;
 			if (!first) {
 				res->nh_sel = nhsel;
+				res->nhc = &nexthop_nh->nh_common;
 				first = true;
 			}
 		}
 
-		if (hash > atomic_read(&nh->fib_nh_upper_bound))
+		if (hash > atomic_read(&nexthop_nh->fib_nh_upper_bound))
 			continue;
 
 		res->nh_sel = nhsel;
+		res->nhc = &nexthop_nh->nh_common;
 		return;
 	} endfor_nexthops(fi);
 }
@@ -1802,5 +1819,5 @@ void fib_select_path(struct net *net, struct fib_result *res,
 
 check_saddr:
 	if (!fl4->saddr)
-		fl4->saddr = FIB_RES_PREFSRC(net, *res);
+		fl4->saddr = fib_result_prefsrc(net, res);
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 13b3327206f9..334f723bdf80 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1470,17 +1470,17 @@ found:
 		if (fi->fib_flags & RTNH_F_DEAD)
 			continue;
 		for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
-			const struct fib_nh *nh = &fi->fib_nh[nhsel];
+			struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel);
 
-			if (nh->fib_nh_flags & RTNH_F_DEAD)
+			if (nhc->nhc_flags & RTNH_F_DEAD)
 				continue;
-			if (ip_ignore_linkdown(nh->fib_nh_dev) &&
-			    nh->fib_nh_flags & RTNH_F_LINKDOWN &&
+			if (ip_ignore_linkdown(nhc->nhc_dev) &&
+			    nhc->nhc_flags & RTNH_F_LINKDOWN &&
 			    !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE))
 				continue;
 			if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) {
 				if (flp->flowi4_oif &&
-				    flp->flowi4_oif != nh->fib_nh_oif)
+				    flp->flowi4_oif != nhc->nhc_oif)
 					continue;
 			}
 
@@ -1490,6 +1490,7 @@ found:
 			res->prefix = htonl(n->key);
 			res->prefixlen = KEYLENGTH - fa->fa_slen;
 			res->nh_sel = nhsel;
+			res->nhc = nhc;
 			res->type = fa->fa_type;
 			res->scope = fi->fib_scope;
 			res->fi = fi;
@@ -1498,7 +1499,7 @@ found:
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 			this_cpu_inc(stats->semantic_match_passed);
 #endif
-			trace_fib_table_lookup(tb->tb_id, flp, &nh->nh_common, err);
+			trace_fib_table_lookup(tb->tb_id, flp, nhc, err);
 
 			return err;
 		}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7977514d90f5..f3f2adf630d4 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -778,8 +778,10 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 			neigh_event_send(n, NULL);
 		} else {
 			if (fib_lookup(net, fl4, &res, 0) == 0) {
-				struct fib_nh *nh = &FIB_RES_NH(res);
+				struct fib_nh_common *nhc = FIB_RES_NHC(res);
+				struct fib_nh *nh;
 
+				nh = container_of(nhc, struct fib_nh, nh_common);
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
 						0, false,
 						jiffies + ip_rt_gc_timeout);
@@ -1027,8 +1029,10 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 
 	rcu_read_lock();
 	if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
-		struct fib_nh *nh = &FIB_RES_NH(res);
+		struct fib_nh_common *nhc = FIB_RES_NHC(res);
+		struct fib_nh *nh;
 
+		nh = container_of(nhc, struct fib_nh, nh_common);
 		update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock,
 				      jiffies + ip_rt_mtu_expires);
 	}
@@ -1235,7 +1239,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 
 		rcu_read_lock();
 		if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0)
-			src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res);
+			src = fib_result_prefsrc(dev_net(rt->dst.dev), &res);
 		else
 			src = inet_select_addr(rt->dst.dev,
 					       rt_nexthop(rt, iph->daddr),
@@ -1354,9 +1358,9 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 
 u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 {
+	struct fib_nh_common *nhc = res->nhc;
+	struct net_device *dev = nhc->nhc_dev;
 	struct fib_info *fi = res->fi;
-	struct fib_nh *nh = &fi->fib_nh[res->nh_sel];
-	struct net_device *dev = nh->fib_nh_dev;
 	u32 mtu = 0;
 
 	if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu ||
@@ -1364,6 +1368,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 		mtu = fi->fib_mtu;
 
 	if (likely(!mtu)) {
+		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 		struct fib_nh_exception *fnhe;
 
 		fnhe = find_exception(nh, daddr);
@@ -1374,7 +1379,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 	if (likely(!mtu))
 		mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU);
 
-	return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
+	return mtu - lwtunnel_headroom(nhc->nhc_lwtstate, mtu);
 }
 
 static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
@@ -1529,7 +1534,8 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 	bool cached = false;
 
 	if (fi) {
-		struct fib_nh *nh = &FIB_RES_NH(*res);
+		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 
 		if (nh->fib_nh_gw4 && nh->fib_nh_scope == RT_SCOPE_LINK) {
 			rt->rt_gateway = nh->fib_nh_gw4;
@@ -1699,15 +1705,18 @@ static int __mkroute_input(struct sk_buff *skb,
 			   struct in_device *in_dev,
 			   __be32 daddr, __be32 saddr, u32 tos)
 {
+	struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+	struct net_device *dev = nhc->nhc_dev;
 	struct fib_nh_exception *fnhe;
 	struct rtable *rth;
+	struct fib_nh *nh;
 	int err;
 	struct in_device *out_dev;
 	bool do_cache;
 	u32 itag = 0;
 
 	/* get a working reference to the output device */
-	out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
+	out_dev = __in_dev_get_rcu(dev);
 	if (!out_dev) {
 		net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n");
 		return -EINVAL;
@@ -1724,10 +1733,13 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	do_cache = res->fi && !itag;
 	if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
-	    skb->protocol == htons(ETH_P_IP) &&
-	    (IN_DEV_SHARED_MEDIA(out_dev) ||
-	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
-		IPCB(skb)->flags |= IPSKB_DOREDIRECT;
+	    skb->protocol == htons(ETH_P_IP)) {
+		__be32 gw = nhc->nhc_family == AF_INET ? nhc->nhc_gw.ipv4 : 0;
+
+		if (IN_DEV_SHARED_MEDIA(out_dev) ||
+		    inet_addr_onlink(out_dev, saddr, gw))
+			IPCB(skb)->flags |= IPSKB_DOREDIRECT;
+	}
 
 	if (skb->protocol != htons(ETH_P_IP)) {
 		/* Not IP (i.e. ARP). Do not create route, if it is
@@ -1744,12 +1756,13 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
-	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
+	nh = container_of(nhc, struct fib_nh, nh_common);
+	fnhe = find_exception(nh, daddr);
 	if (do_cache) {
 		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
 		else
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			rth = rcu_dereference(nh->nh_rth_input);
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2043,7 +2056,11 @@ local_input:
 	do_cache = false;
 	if (res->fi) {
 		if (!itag) {
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+			struct fib_nh *nh;
+
+			nh = container_of(nhc, struct fib_nh, nh_common);
+			rth = rcu_dereference(nh->nh_rth_input);
 			if (rt_cache_valid(rth)) {
 				skb_dst_set_noref(skb, &rth->dst);
 				err = 0;
@@ -2073,15 +2090,17 @@ local_input:
 	}
 
 	if (do_cache) {
-		struct fib_nh *nh = &FIB_RES_NH(*res);
+		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+		struct fib_nh *nh;
 
-		rth->dst.lwtstate = lwtstate_get(nh->fib_nh_lws);
+		rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate);
 		if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
 			WARN_ON(rth->dst.input == lwtunnel_input);
 			rth->dst.lwtstate->orig_input = rth->dst.input;
 			rth->dst.input = lwtunnel_input;
 		}
 
+		nh = container_of(nhc, struct fib_nh, nh_common);
 		if (unlikely(!rt_cache_route(nh, rth)))
 			rt_add_uncached_list(rth);
 	}
@@ -2253,8 +2272,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	fnhe = NULL;
 	do_cache &= fi != NULL;
 	if (fi) {
+		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
+		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 		struct rtable __rcu **prth;
-		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
 		if (!do_cache)
@@ -2264,8 +2284,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		} else {
 			if (unlikely(fl4->flowi4_flags &
 				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->fib_nh_gw4 &&
-				       nh->fib_nh_scope == RT_SCOPE_LINK))) {
+				     !(nhc->nhc_has_gw &&
+				       nhc->nhc_scope == RT_SCOPE_LINK))) {
 				do_cache = false;
 				goto add;
 			}
-- 
cgit v1.2.3


From c0a720770c01e67374b15f348f17a52409f6545c Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 2 Apr 2019 14:11:58 -0700
Subject: ipv6: Flip to fib_nexthop_info

Export fib_nexthop_info and fib_add_nexthop for use by IPv6 code.
Remove rt6_nexthop_info and rt6_add_nexthop in favor of the IPv4
versions. Update fib_nexthop_info for IPv6 linkdown check and
RTA_GATEWAY for AF_INET6.

Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  5 ++++
 net/ipv4/fib_semantics.c | 22 ++++++++++----
 net/ipv6/route.c         | 77 ++++--------------------------------------------
 3 files changed, 28 insertions(+), 76 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 1f4a3b8bf584..3ce07841dc3b 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -492,4 +492,9 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr);
 int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 			  struct fib_dump_filter *filter,
 			  struct netlink_callback *cb);
+
+int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh,
+		     unsigned int *flags, bool skip_oif);
+int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh,
+		    int nh_weight);
 #endif  /* _NET_FIB_H */
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 33a43965a232..8e0cb1687a74 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -45,6 +45,7 @@
 #include <net/nexthop.h>
 #include <net/lwtunnel.h>
 #include <net/fib_notifier.h>
+#include <net/addrconf.h>
 
 #include "fib_lookup.h"
 
@@ -1317,8 +1318,8 @@ failure:
 	return ERR_PTR(err);
 }
 
-static int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
-			    unsigned int *flags, bool skip_oif)
+int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
+		     unsigned int *flags, bool skip_oif)
 {
 	if (nhc->nhc_flags & RTNH_F_DEAD)
 		*flags |= RTNH_F_DEAD;
@@ -1332,6 +1333,10 @@ static int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc
 			if (ip_ignore_linkdown(nhc->nhc_dev))
 				*flags |= RTNH_F_DEAD;
 			break;
+		case AF_INET6:
+			if (ip6_ignore_linkdown(nhc->nhc_dev))
+				*flags |= RTNH_F_DEAD;
+			break;
 		}
 		rcu_read_unlock();
 	}
@@ -1342,6 +1347,11 @@ static int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc
 			if (nla_put_in_addr(skb, RTA_GATEWAY, nhc->nhc_gw.ipv4))
 				goto nla_put_failure;
 			break;
+		case AF_INET6:
+			if (nla_put_in6_addr(skb, RTA_GATEWAY,
+					     &nhc->nhc_gw.ipv6) < 0)
+				goto nla_put_failure;
+			break;
 		}
 	}
 
@@ -1362,10 +1372,11 @@ static int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc
 nla_put_failure:
 	return -EMSGSIZE;
 }
+EXPORT_SYMBOL_GPL(fib_nexthop_info);
 
-#ifdef CONFIG_IP_ROUTE_MULTIPATH
-static int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc,
-			   int nh_weight)
+#if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6)
+int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc,
+		    int nh_weight)
 {
 	const struct net_device *dev = nhc->nhc_dev;
 	struct rtnexthop *rtnh;
@@ -1391,6 +1402,7 @@ static int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc,
 nla_put_failure:
 	return -EMSGSIZE;
 }
+EXPORT_SYMBOL_GPL(fib_add_nexthop);
 #endif
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e0ee30cbd079..6e89151693d0 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4582,73 +4582,6 @@ static size_t rt6_nlmsg_size(struct fib6_info *rt)
 	       + nexthop_len;
 }
 
-static int rt6_nexthop_info(struct sk_buff *skb, const struct fib6_nh *fib6_nh,
-			    unsigned int *flags, bool skip_oif)
-{
-	if (fib6_nh->fib_nh_flags & RTNH_F_DEAD)
-		*flags |= RTNH_F_DEAD;
-
-	if (fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN) {
-		*flags |= RTNH_F_LINKDOWN;
-
-		rcu_read_lock();
-		if (ip6_ignore_linkdown(fib6_nh->fib_nh_dev))
-			*flags |= RTNH_F_DEAD;
-		rcu_read_unlock();
-	}
-
-	if (fib6_nh->fib_nh_has_gw) {
-		if (nla_put_in6_addr(skb, RTA_GATEWAY, &fib6_nh->fib_nh_gw6) < 0)
-			goto nla_put_failure;
-	}
-
-	*flags |= (fib6_nh->fib_nh_flags & RTNH_F_ONLINK);
-	if (fib6_nh->fib_nh_flags & RTNH_F_OFFLOAD)
-		*flags |= RTNH_F_OFFLOAD;
-
-	/* not needed for multipath encoding b/c it has a rtnexthop struct */
-	if (!skip_oif && fib6_nh->fib_nh_dev &&
-	    nla_put_u32(skb, RTA_OIF, fib6_nh->fib_nh_dev->ifindex))
-		goto nla_put_failure;
-
-	if (fib6_nh->fib_nh_lws &&
-	    lwtunnel_fill_encap(skb, fib6_nh->fib_nh_lws) < 0)
-		goto nla_put_failure;
-
-	return 0;
-
-nla_put_failure:
-	return -EMSGSIZE;
-}
-
-/* add multipath next hop */
-static int rt6_add_nexthop(struct sk_buff *skb, const struct fib6_nh *fib6_nh)
-{
-	const struct net_device *dev = fib6_nh->fib_nh_dev;
-	struct rtnexthop *rtnh;
-	unsigned int flags = 0;
-
-	rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
-	if (!rtnh)
-		goto nla_put_failure;
-
-	rtnh->rtnh_hops = fib6_nh->fib_nh_weight - 1;
-	rtnh->rtnh_ifindex = dev ? dev->ifindex : 0;
-
-	if (rt6_nexthop_info(skb, fib6_nh, &flags, true) < 0)
-		goto nla_put_failure;
-
-	rtnh->rtnh_flags = flags;
-
-	/* length of rtnetlink header + attributes */
-	rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh;
-
-	return 0;
-
-nla_put_failure:
-	return -EMSGSIZE;
-}
-
 static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			 struct fib6_info *rt, struct dst_entry *dst,
 			 struct in6_addr *dest, struct in6_addr *src,
@@ -4765,19 +4698,21 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		if (!mp)
 			goto nla_put_failure;
 
-		if (rt6_add_nexthop(skb, &rt->fib6_nh) < 0)
+		if (fib_add_nexthop(skb, &rt->fib6_nh.nh_common,
+				    rt->fib6_nh.fib_nh_weight) < 0)
 			goto nla_put_failure;
 
 		list_for_each_entry_safe(sibling, next_sibling,
 					 &rt->fib6_siblings, fib6_siblings) {
-			if (rt6_add_nexthop(skb, &sibling->fib6_nh) < 0)
+			if (fib_add_nexthop(skb, &sibling->fib6_nh.nh_common,
+					    sibling->fib6_nh.fib_nh_weight) < 0)
 				goto nla_put_failure;
 		}
 
 		nla_nest_end(skb, mp);
 	} else {
-		if (rt6_nexthop_info(skb, &rt->fib6_nh, &rtm->rtm_flags,
-				     false) < 0)
+		if (fib_nexthop_info(skb, &rt->fib6_nh.nh_common,
+				     &rtm->rtm_flags, false) < 0)
 			goto nla_put_failure;
 	}
 
-- 
cgit v1.2.3


From 28b05b92886871bdd8e6a9df73e3a15845fe8ef4 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 3 Apr 2019 08:28:35 +0200
Subject: net: use correct this_cpu primitive in dev_recursion_level

syzbot reports:
BUG: using __this_cpu_read() in preemptible code:
caller is dev_recursion_level include/linux/netdevice.h:3052 [inline]
 __this_cpu_preempt_check+0x246/0x270 lib/smp_processor_id.c:47
 dev_recursion_level include/linux/netdevice.h:3052 [inline]
 ip6_skb_dst_mtu include/net/ip6_route.h:245 [inline]

I erronously downgraded a this_cpu_read to __this_cpu_read when
moving dev_recursion_level() around.

Reported-by: syzbot+51471b4aae195285a4a3@syzkaller.appspotmail.com
Fixes: 97cdcf37b57e ("net: place xmit recursion in softnet data")
Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index eb9f05e0863d..521eb869555e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3049,7 +3049,7 @@ DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 
 static inline int dev_recursion_level(void)
 {
-	return __this_cpu_read(softnet_data.xmit.recursion);
+	return this_cpu_read(softnet_data.xmit.recursion);
 }
 
 #define XMIT_RECURSION_LIMIT	10
-- 
cgit v1.2.3


From 407dd706fb5245c138f3a972f8aaa1c8a09a574c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 3 Apr 2019 14:24:15 +0200
Subject: net: devlink: convert devlink_port_attrs bools to bits

In order to save space in the struct, convert bools to bits.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 31d5cec4d06b..4a1e3452a4ce 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -41,10 +41,10 @@ struct devlink {
 };
 
 struct devlink_port_attrs {
-	bool set;
+	u8 set:1,
+	   split:1;
 	enum devlink_port_flavour flavour;
 	u32 port_number; /* same value as "split group" */
-	bool split;
 	u32 split_subport_number;
 };
 
-- 
cgit v1.2.3


From bec5267cded268acdf679b651778c300d204e9f2 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 3 Apr 2019 14:24:16 +0200
Subject: net: devlink: extend port attrs for switch ID

Extend devlink_port_attrs_set() to pass switch ID for ports which are
part of switch and store it in port attrs. For other ports, this is
NULL.

Note that this allows the driver to group devlink ports into one or more
switches according to the actual topology.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/core.c        |  3 ++-
 drivers/net/ethernet/netronome/nfp/nfp_devlink.c  |  2 +-
 include/net/devlink.h                             |  8 ++++++--
 net/core/devlink.c                                | 16 +++++++++++++++-
 net/dsa/dsa2.c                                    |  2 +-
 6 files changed, 26 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index ab6fd05c462b..36ec4cb45276 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -230,7 +230,7 @@ int bnxt_dl_register(struct bnxt *bp)
 	}
 
 	devlink_port_attrs_set(&bp->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
-			       bp->pf.port_id, false, 0);
+			       bp->pf.port_id, false, 0, NULL, 0);
 	rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id);
 	if (rc) {
 		netdev_err(bp->dev, "devlink_port_register failed");
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index e55b4aa91e3b..d01bd9d71b90 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1730,7 +1730,8 @@ int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port,
 
 	mlxsw_core_port->local_port = local_port;
 	devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
-			       port_number, split, split_port_subnumber);
+			       port_number, split, split_port_subnumber,
+			       NULL, 0);
 	err = devlink_port_register(devlink, devlink_port, local_port);
 	if (err)
 		memset(mlxsw_core_port, 0, sizeof(*mlxsw_core_port));
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index 919da0d84fb4..15c4d2e0c86e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -364,7 +364,7 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port)
 
 	devlink_port_attrs_set(&port->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL,
 			       eth_port.label_port, eth_port.is_split,
-			       eth_port.label_subport);
+			       eth_port.label_subport, NULL, 0);
 
 	devlink = priv_to_devlink(app->pf);
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 4a1e3452a4ce..0f7968761204 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -42,10 +42,12 @@ struct devlink {
 
 struct devlink_port_attrs {
 	u8 set:1,
-	   split:1;
+	   split:1,
+	   switch_port:1;
 	enum devlink_port_flavour flavour;
 	u32 port_number; /* same value as "split group" */
 	u32 split_subport_number;
+	struct netdev_phys_item_id switch_id;
 };
 
 struct devlink_port {
@@ -582,7 +584,9 @@ void devlink_port_type_clear(struct devlink_port *devlink_port);
 void devlink_port_attrs_set(struct devlink_port *devlink_port,
 			    enum devlink_port_flavour flavour,
 			    u32 port_number, bool split,
-			    u32 split_subport_number);
+			    u32 split_subport_number,
+			    const unsigned char *switch_id,
+			    unsigned char switch_id_len);
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u32 size, u16 ingress_pools_count,
 			u16 egress_pools_count, u16 ingress_tc_count,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index dc3a99148ee7..5b2eb186bb92 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -5414,11 +5414,16 @@ EXPORT_SYMBOL_GPL(devlink_port_type_clear);
  *	@split: indicates if this is split port
  *	@split_subport_number: if the port is split, this is the number
  *	                       of subport.
+ *	@switch_id: if the port is part of switch, this is buffer with ID,
+ *	            otwerwise this is NULL
+ *	@switch_id_len: length of the switch_id buffer
  */
 void devlink_port_attrs_set(struct devlink_port *devlink_port,
 			    enum devlink_port_flavour flavour,
 			    u32 port_number, bool split,
-			    u32 split_subport_number)
+			    u32 split_subport_number,
+			    const unsigned char *switch_id,
+			    unsigned char switch_id_len)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 
@@ -5429,6 +5434,15 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
 	attrs->port_number = port_number;
 	attrs->split = split;
 	attrs->split_subport_number = split_subport_number;
+	if (switch_id) {
+		attrs->switch_port = true;
+		if (WARN_ON(switch_id_len > MAX_PHYS_ITEM_ID_LEN))
+			switch_id_len = MAX_PHYS_ITEM_ID_LEN;
+		memcpy(attrs->switch_id.id, switch_id, switch_id_len);
+		attrs->switch_id.id_len = switch_id_len;
+	} else {
+		attrs->switch_port = false;
+	}
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
 
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 0e1cce460406..4493b2ff3438 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -286,7 +286,7 @@ static int dsa_port_setup(struct dsa_port *dp)
 	 * independent from front panel port numbers.
 	 */
 	devlink_port_attrs_set(&dp->devlink_port, flavour,
-			       dp->index, false, 0);
+			       dp->index, false, 0, NULL, 0);
 	err = devlink_port_register(ds->devlink, &dp->devlink_port,
 				    dp->index);
 	if (err)
-- 
cgit v1.2.3


From 7e1146e8c10c00f859843817da8ecc5d902ea409 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 3 Apr 2019 14:24:17 +0200
Subject: net: devlink: introduce devlink_compat_switch_id_get() helper

Introduce devlink_compat_switch_id_get() helper which fills up switch_id
according to passed netdev pointer. Call it directly from
dev_get_port_parent_id() as a fallback when ndo_get_port_parent_id
is not defined for given netdev.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h |  9 +++++++++
 net/core/dev.c        | 15 +++++++++++----
 net/core/devlink.c    | 19 +++++++++++++++++++
 3 files changed, 39 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 0f7968761204..70c7d1ac8344 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -743,6 +743,8 @@ void devlink_compat_running_version(struct net_device *dev,
 int devlink_compat_flash_update(struct net_device *dev, const char *file_name);
 int devlink_compat_phys_port_name_get(struct net_device *dev,
 				      char *name, size_t len);
+int devlink_compat_switch_id_get(struct net_device *dev,
+				 struct netdev_phys_item_id *ppid);
 
 #else
 
@@ -764,6 +766,13 @@ devlink_compat_phys_port_name_get(struct net_device *dev,
 	return -EOPNOTSUPP;
 }
 
+static inline int
+devlink_compat_switch_id_get(struct net_device *dev,
+			     struct netdev_phys_item_id *ppid)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/net/core/dev.c b/net/core/dev.c
index 79e0c26988b8..a95782764360 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7900,13 +7900,20 @@ int dev_get_port_parent_id(struct net_device *dev,
 	struct netdev_phys_item_id first = { };
 	struct net_device *lower_dev;
 	struct list_head *iter;
-	int err = -EOPNOTSUPP;
+	int err;
+
+	if (ops->ndo_get_port_parent_id) {
+		err = ops->ndo_get_port_parent_id(dev, ppid);
+		if (err != -EOPNOTSUPP)
+			return err;
+	}
 
-	if (ops->ndo_get_port_parent_id)
-		return ops->ndo_get_port_parent_id(dev, ppid);
+	err = devlink_compat_switch_id_get(dev, ppid);
+	if (!err || err != -EOPNOTSUPP)
+		return err;
 
 	if (!recurse)
-		return err;
+		return -EOPNOTSUPP;
 
 	netdev_for_each_lower_dev(dev, lower_dev, iter) {
 		err = dev_get_port_parent_id(lower_dev, ppid, recurse);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 5b2eb186bb92..d9fbf94ea2a3 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -6508,6 +6508,25 @@ int devlink_compat_phys_port_name_get(struct net_device *dev,
 	return __devlink_port_phys_port_name_get(devlink_port, name, len);
 }
 
+int devlink_compat_switch_id_get(struct net_device *dev,
+				 struct netdev_phys_item_id *ppid)
+{
+	struct devlink_port *devlink_port;
+
+	/* RTNL mutex is held here which ensures that devlink_port
+	 * instance cannot disappear in the middle. No need to take
+	 * any devlink lock as only permanent values are accessed.
+	 */
+	ASSERT_RTNL();
+	devlink_port = netdev_to_devlink_port(dev);
+	if (!devlink_port || !devlink_port->attrs.switch_port)
+		return -EOPNOTSUPP;
+
+	memcpy(ppid, &devlink_port->attrs.switch_id, sizeof(*ppid));
+
+	return 0;
+}
+
 static int __init devlink_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
-- 
cgit v1.2.3


From 5d3c537f907036c1f18bd325ffc356e24cde664c Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@mellanox.com>
Date: Sun, 24 Mar 2019 09:21:40 +0200
Subject: net/mlx5: Handle event of power detection in the PCIE slot

Handle event of power state change in the PCIE slot. When the event
occurs, check if query power state and PCI power fields is supported. If
so, read these fields from MPEIN (management PCIE info) register and
issue a corresponding message.

Signed-off-by: Aya Levin <ayal@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 75 ++++++++++++++++++++++++
 include/linux/mlx5/device.h                      |  1 +
 2 files changed, 76 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 5d5864e8df3c..a81e8d2168d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -21,6 +21,7 @@ struct mlx5_event_nb {
 static int any_notifier(struct notifier_block *, unsigned long, void *);
 static int temp_warn(struct notifier_block *, unsigned long, void *);
 static int port_module(struct notifier_block *, unsigned long, void *);
+static int pcie_core(struct notifier_block *, unsigned long, void *);
 
 /* handler which forwards the event to events->nh, driver notifiers */
 static int forward_event(struct notifier_block *, unsigned long, void *);
@@ -30,6 +31,7 @@ static struct mlx5_nb events_nbs_ref[] = {
 	{.nb.notifier_call = any_notifier,  .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
 	{.nb.notifier_call = temp_warn,     .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
 	{.nb.notifier_call = port_module,   .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },
+	{.nb.notifier_call = pcie_core,     .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
 
 	/* Events to be forwarded (as is) to mlx5 core interfaces (mlx5e/mlx5_ib) */
 	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
@@ -51,11 +53,14 @@ static struct mlx5_nb events_nbs_ref[] = {
 
 struct mlx5_events {
 	struct mlx5_core_dev *dev;
+	struct workqueue_struct *wq;
 	struct mlx5_event_nb  notifiers[ARRAY_SIZE(events_nbs_ref)];
 	/* driver notifier chain */
 	struct atomic_notifier_head nh;
 	/* port module events stats */
 	struct mlx5_pme_stats pme_stats;
+	/*pcie_core*/
+	struct work_struct pcie_core_work;
 };
 
 static const char *eqe_type_str(u8 type)
@@ -249,6 +254,69 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data
 	return NOTIFY_OK;
 }
 
+enum {
+	MLX5_PCI_POWER_COULD_NOT_BE_READ = 0x0,
+	MLX5_PCI_POWER_SUFFICIENT_REPORTED = 0x1,
+	MLX5_PCI_POWER_INSUFFICIENT_REPORTED = 0x2,
+};
+
+static void mlx5_pcie_event(struct work_struct *work)
+{
+	u32 out[MLX5_ST_SZ_DW(mpein_reg)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mpein_reg)] = {0};
+	struct mlx5_events *events;
+	struct mlx5_core_dev *dev;
+	u8 power_status;
+	u16 pci_power;
+
+	events = container_of(work, struct mlx5_events, pcie_core_work);
+	dev  = events->dev;
+
+	if (!MLX5_CAP_MCAM_FEATURE(dev, pci_status_and_power))
+		return;
+
+	mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+			     MLX5_REG_MPEIN, 0, 0);
+	power_status = MLX5_GET(mpein_reg, out, pwr_status);
+	pci_power = MLX5_GET(mpein_reg, out, pci_power);
+
+	switch (power_status) {
+	case MLX5_PCI_POWER_COULD_NOT_BE_READ:
+		mlx5_core_info_rl(dev,
+				  "PCIe slot power capability was not advertised.\n");
+		break;
+	case MLX5_PCI_POWER_INSUFFICIENT_REPORTED:
+		mlx5_core_warn_rl(dev,
+				  "Detected insufficient power on the PCIe slot (%uW).\n",
+				  pci_power);
+		break;
+	case MLX5_PCI_POWER_SUFFICIENT_REPORTED:
+		mlx5_core_info_rl(dev,
+				  "PCIe slot advertised sufficient power (%uW).\n",
+				  pci_power);
+		break;
+	}
+}
+
+static int pcie_core(struct notifier_block *nb, unsigned long type, void *data)
+{
+	struct mlx5_event_nb    *event_nb = mlx5_nb_cof(nb,
+							struct mlx5_event_nb,
+							nb);
+	struct mlx5_events      *events   = event_nb->ctx;
+	struct mlx5_eqe         *eqe      = data;
+
+	switch (eqe->sub_type) {
+	case MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT:
+			queue_work(events->wq, &events->pcie_core_work);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
 void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats)
 {
 	*stats = dev->priv.events->pme_stats;
@@ -277,11 +345,17 @@ int mlx5_events_init(struct mlx5_core_dev *dev)
 	ATOMIC_INIT_NOTIFIER_HEAD(&events->nh);
 	events->dev = dev;
 	dev->priv.events = events;
+	events->wq = create_singlethread_workqueue("mlx5_events");
+	if (!events->wq)
+		return -ENOMEM;
+	INIT_WORK(&events->pcie_core_work, mlx5_pcie_event);
+
 	return 0;
 }
 
 void mlx5_events_cleanup(struct mlx5_core_dev *dev)
 {
+	destroy_workqueue(dev->priv.events->wq);
 	kvfree(dev->priv.events);
 }
 
@@ -304,6 +378,7 @@ void mlx5_events_stop(struct mlx5_core_dev *dev)
 
 	for (i = ARRAY_SIZE(events_nbs_ref) - 1; i >= 0 ; i--)
 		mlx5_eq_notifier_unregister(dev, &events->notifiers[i].nb);
+	flush_workqueue(events->wq);
 }
 
 int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index f93a5598b942..db7dca75d726 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -361,6 +361,7 @@ enum {
 
 enum {
 	MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1,
+	MLX5_GENERAL_SUBTYPE_PCI_POWER_CHANGE_EVENT = 0x5,
 };
 
 enum {
-- 
cgit v1.2.3


From ff302db965b57c141297911ea647d36d11fedfbe Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Tue, 2 Apr 2019 10:07:45 +1100
Subject: rhashtable: allow rht_bucket_var to return NULL.

Rather than returning a pointer to a static nulls, rht_bucket_var()
now returns NULL if the bucket doesn't exist.
This will make the next patch, which stores a bitlock in the
bucket pointer, somewhat cleaner.

This change involves introducing __rht_bucket_nested() which is
like rht_bucket_nested(), but doesn't provide the static nulls,
and changing rht_bucket_nested() to call this and possible
provide a static nulls - as is still needed for the non-var case.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 11 +++++++++--
 lib/rhashtable.c           | 29 ++++++++++++++++++++---------
 2 files changed, 29 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 86dfa417848d..0c9175aeab8a 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -265,6 +265,8 @@ void rhashtable_destroy(struct rhashtable *ht);
 
 struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
 					    unsigned int hash);
+struct rhash_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
+					      unsigned int hash);
 struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
 						   struct bucket_table *tbl,
 						   unsigned int hash);
@@ -294,7 +296,7 @@ static inline struct rhash_head __rcu *const *rht_bucket(
 static inline struct rhash_head __rcu **rht_bucket_var(
 	struct bucket_table *tbl, unsigned int hash)
 {
-	return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) :
+	return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) :
 				     &tbl->buckets[hash];
 }
 
@@ -890,6 +892,8 @@ static inline int __rhashtable_remove_fast_one(
 	spin_lock_bh(lock);
 
 	pprev = rht_bucket_var(tbl, hash);
+	if (!pprev)
+		goto out;
 	rht_for_each_from(he, *pprev, tbl, hash) {
 		struct rhlist_head *list;
 
@@ -934,6 +938,7 @@ static inline int __rhashtable_remove_fast_one(
 		break;
 	}
 
+out:
 	spin_unlock_bh(lock);
 
 	if (err > 0) {
@@ -1042,6 +1047,8 @@ static inline int __rhashtable_replace_fast(
 	spin_lock_bh(lock);
 
 	pprev = rht_bucket_var(tbl, hash);
+	if (!pprev)
+		goto out;
 	rht_for_each_from(he, *pprev, tbl, hash) {
 		if (he != obj_old) {
 			pprev = &he->next;
@@ -1053,7 +1060,7 @@ static inline int __rhashtable_replace_fast(
 		err = 0;
 		break;
 	}
-
+out:
 	spin_unlock_bh(lock);
 
 	return err;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 6c4f5c8e9baa..b28fdd560ea9 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -237,8 +237,10 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
 		goto out;
 
 	err = -ENOENT;
+	if (!pprev)
+		goto out;
 
-	rht_for_each(entry, old_tbl, old_hash) {
+	rht_for_each_from(entry, *pprev, old_tbl, old_hash) {
 		err = 0;
 		next = rht_dereference_bucket(entry->next, old_tbl, old_hash);
 
@@ -496,6 +498,8 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 
 	elasticity = RHT_ELASTICITY;
 	pprev = rht_bucket_var(tbl, hash);
+	if (!pprev)
+		return ERR_PTR(-ENOENT);
 	rht_for_each_from(head, *pprev, tbl, hash) {
 		struct rhlist_head *list;
 		struct rhlist_head *plist;
@@ -1161,11 +1165,10 @@ void rhashtable_destroy(struct rhashtable *ht)
 }
 EXPORT_SYMBOL_GPL(rhashtable_destroy);
 
-struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
-					    unsigned int hash)
+struct rhash_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
+					      unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
-	static struct rhash_head __rcu *rhnull;
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
 	unsigned int size = tbl->size >> tbl->nest;
 	unsigned int subhash = hash;
@@ -1183,15 +1186,23 @@ struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
 		subhash >>= shift;
 	}
 
-	if (!ntbl) {
-		if (!rhnull)
-			INIT_RHT_NULLS_HEAD(rhnull);
-		return &rhnull;
-	}
+	if (!ntbl)
+		return NULL;
 
 	return &ntbl[subhash].bucket;
 
 }
+EXPORT_SYMBOL_GPL(__rht_bucket_nested);
+
+struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
+					    unsigned int hash)
+{
+	static struct rhash_head __rcu *rhnull;
+
+	if (!rhnull)
+		INIT_RHT_NULLS_HEAD(rhnull);
+	return __rht_bucket_nested(tbl, hash) ?: &rhnull;
+}
 EXPORT_SYMBOL_GPL(rht_bucket_nested);
 
 struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
-- 
cgit v1.2.3


From 8f0db018006a421956965e1149234c4e8db718ee Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Tue, 2 Apr 2019 10:07:45 +1100
Subject: rhashtable: use bit_spin_locks to protect hash bucket.

This patch changes rhashtables to use a bit_spin_lock on BIT(1) of the
bucket pointer to lock the hash chain for that bucket.

The benefits of a bit spin_lock are:
 - no need to allocate a separate array of locks.
 - no need to have a configuration option to guide the
   choice of the size of this array
 - locking cost is often a single test-and-set in a cache line
   that will have to be loaded anyway.  When inserting at, or removing
   from, the head of the chain, the unlock is free - writing the new
   address in the bucket head implicitly clears the lock bit.
   For __rhashtable_insert_fast() we ensure this always happens
   when adding a new key.
 - even when lockings costs 2 updates (lock and unlock), they are
   in a cacheline that needs to be read anyway.

The cost of using a bit spin_lock is a little bit of code complexity,
which I think is quite manageable.

Bit spin_locks are sometimes inappropriate because they are not fair -
if multiple CPUs repeatedly contend of the same lock, one CPU can
easily be starved.  This is not a credible situation with rhashtable.
Multiple CPUs may want to repeatedly add or remove objects, but they
will typically do so at different buckets, so they will attempt to
acquire different locks.

As we have more bit-locks than we previously had spinlocks (by at
least a factor of two) we can expect slightly less contention to
go with the slightly better cache behavior and reduced memory
consumption.

To enhance type checking, a new struct is introduced to represent the
  pointer plus lock-bit
that is stored in the bucket-table.  This is "struct rhash_lock_head"
and is empty.  A pointer to this needs to be cast to either an
unsigned lock, or a "struct rhash_head *" to be useful.
Variables of this type are most often called "bkt".

Previously "pprev" would sometimes point to a bucket, and sometimes a
->next pointer in an rhash_head.  As these are now different types,
pprev is NULL when it would have pointed to the bucket. In that case,
'blk' is used, together with correct locking protocol.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable-types.h |   2 -
 include/linux/rhashtable.h       | 261 +++++++++++++++++++++++++--------------
 ipc/util.c                       |   1 -
 lib/rhashtable.c                 | 141 +++++++++++----------
 lib/test_rhashtable.c            |   2 +-
 net/bridge/br_fdb.c              |   1 -
 net/bridge/br_multicast.c        |   1 -
 net/bridge/br_vlan.c             |   1 -
 net/bridge/br_vlan_tunnel.c      |   1 -
 net/ipv4/ipmr.c                  |   1 -
 net/ipv6/ip6mr.c                 |   1 -
 net/netfilter/nf_tables_api.c    |   1 -
 12 files changed, 236 insertions(+), 178 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h
index 763d613ce2c2..57467cbf4c5b 100644
--- a/include/linux/rhashtable-types.h
+++ b/include/linux/rhashtable-types.h
@@ -48,7 +48,6 @@ typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg,
  * @head_offset: Offset of rhash_head in struct to be hashed
  * @max_size: Maximum size while expanding
  * @min_size: Minimum size while shrinking
- * @locks_mul: Number of bucket locks to allocate per cpu (default: 32)
  * @automatic_shrinking: Enable automatic shrinking of tables
  * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash)
  * @obj_hashfn: Function to hash object
@@ -62,7 +61,6 @@ struct rhashtable_params {
 	unsigned int		max_size;
 	u16			min_size;
 	bool			automatic_shrinking;
-	u8			locks_mul;
 	rht_hashfn_t		hashfn;
 	rht_obj_hashfn_t	obj_hashfn;
 	rht_obj_cmpfn_t		obj_cmpfn;
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 0c9175aeab8a..ccbbafdf5547 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -24,12 +24,27 @@
 #include <linux/list_nulls.h>
 #include <linux/workqueue.h>
 #include <linux/rculist.h>
+#include <linux/bit_spinlock.h>
 
 #include <linux/rhashtable-types.h>
 /*
+ * Objects in an rhashtable have an embedded struct rhash_head
+ * which is linked into as hash chain from the hash table - or one
+ * of two or more hash tables when the rhashtable is being resized.
  * The end of the chain is marked with a special nulls marks which has
- * the least significant bit set.
+ * the least significant bit set but otherwise stores the address of
+ * the hash bucket.  This allows us to be be sure we've found the end
+ * of the right list.
+ * The value stored in the hash bucket has BIT(2) used as a lock bit.
+ * This bit must be atomically set before any changes are made to
+ * the chain.  To avoid dereferencing this pointer without clearing
+ * the bit first, we use an opaque 'struct rhash_lock_head *' for the
+ * pointer stored in the bucket.  This struct needs to be defined so
+ * that rcu_derefernce() works on it, but it has no content so a
+ * cast is needed for it to be useful.  This ensures it isn't
+ * used by mistake with clearing the lock bit first.
  */
+struct rhash_lock_head {};
 
 /* Maximum chain length before rehash
  *
@@ -52,8 +67,6 @@
  * @nest: Number of bits of first-level nested table.
  * @rehash: Current bucket being rehashed
  * @hash_rnd: Random seed to fold into hash
- * @locks_mask: Mask to apply before accessing locks[]
- * @locks: Array of spinlocks protecting individual buckets
  * @walkers: List of active walkers
  * @rcu: RCU structure for freeing the table
  * @future_tbl: Table under construction during rehashing
@@ -64,16 +77,70 @@ struct bucket_table {
 	unsigned int		size;
 	unsigned int		nest;
 	u32			hash_rnd;
-	unsigned int		locks_mask;
-	spinlock_t		*locks;
 	struct list_head	walkers;
 	struct rcu_head		rcu;
 
 	struct bucket_table __rcu *future_tbl;
 
-	struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp;
+	struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp;
 };
 
+/*
+ * We lock a bucket by setting BIT(1) in the pointer - this is always
+ * zero in real pointers and in the nulls marker.
+ * bit_spin_locks do not handle contention well, but the whole point
+ * of the hashtable design is to achieve minimum per-bucket contention.
+ * A nested hash table might not have a bucket pointer.  In that case
+ * we cannot get a lock.  For remove and replace the bucket cannot be
+ * interesting and doesn't need locking.
+ * For insert we allocate the bucket if this is the last bucket_table,
+ * and then take the lock.
+ * Sometimes we unlock a bucket by writing a new pointer there.  In that
+ * case we don't need to unlock, but we do need to reset state such as
+ * local_bh. For that we have rht_assign_unlock().  As rcu_assign_pointer()
+ * provides the same release semantics that bit_spin_unlock() provides,
+ * this is safe.
+ */
+
+static inline void rht_lock(struct rhash_lock_head **bkt)
+{
+	local_bh_disable();
+	bit_spin_lock(1, (unsigned long *)bkt);
+}
+
+static inline void rht_unlock(struct rhash_lock_head **bkt)
+{
+	bit_spin_unlock(1, (unsigned long *)bkt);
+	local_bh_enable();
+}
+
+static inline void rht_assign_unlock(struct rhash_lock_head **bkt,
+				     struct rhash_head *obj)
+{
+	struct rhash_head **p = (struct rhash_head **)bkt;
+
+	rcu_assign_pointer(*p, obj);
+	preempt_enable();
+	__release(bitlock);
+	local_bh_enable();
+}
+
+/*
+ * If 'p' is a bucket head and might be locked:
+ *   rht_ptr() returns the address without the lock bit.
+ *   rht_ptr_locked() returns the address WITH the lock bit.
+ */
+static inline struct rhash_head __rcu *rht_ptr(const struct rhash_lock_head *p)
+{
+	return (void *)(((unsigned long)p) & ~BIT(1));
+}
+
+static inline struct rhash_lock_head __rcu *rht_ptr_locked(const
+							   struct rhash_head *p)
+{
+	return (void *)(((unsigned long)p) | BIT(1));
+}
+
 /*
  * NULLS_MARKER() expects a hash value with the low
  * bits mostly likely to be significant, and it discards
@@ -206,25 +273,6 @@ static inline bool rht_grow_above_max(const struct rhashtable *ht,
 	return atomic_read(&ht->nelems) >= ht->max_elems;
 }
 
-/* The bucket lock is selected based on the hash and protects mutations
- * on a group of hash buckets.
- *
- * A maximum of tbl->size/2 bucket locks is allocated. This ensures that
- * a single lock always covers both buckets which may both contains
- * entries which link to the same bucket of the old table during resizing.
- * This allows to simplify the locking as locking the bucket in both
- * tables during resize always guarantee protection.
- *
- * IMPORTANT: When holding the bucket lock of both the old and new table
- * during expansions and shrinking, the old bucket lock must always be
- * acquired first.
- */
-static inline spinlock_t *rht_bucket_lock(const struct bucket_table *tbl,
-					  unsigned int hash)
-{
-	return &tbl->locks[hash & tbl->locks_mask];
-}
-
 #ifdef CONFIG_PROVE_LOCKING
 int lockdep_rht_mutex_is_held(struct rhashtable *ht);
 int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash);
@@ -263,13 +311,13 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 				 void *arg);
 void rhashtable_destroy(struct rhashtable *ht);
 
-struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
-					    unsigned int hash);
-struct rhash_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
-					      unsigned int hash);
-struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
-						   struct bucket_table *tbl,
+struct rhash_lock_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
+						 unsigned int hash);
+struct rhash_lock_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
 						   unsigned int hash);
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
+							struct bucket_table *tbl,
+							unsigned int hash);
 
 #define rht_dereference(p, ht) \
 	rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht))
@@ -286,21 +334,21 @@ struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
 #define rht_entry(tpos, pos, member) \
 	({ tpos = container_of(pos, typeof(*tpos), member); 1; })
 
-static inline struct rhash_head __rcu *const *rht_bucket(
+static inline struct rhash_lock_head __rcu *const *rht_bucket(
 	const struct bucket_table *tbl, unsigned int hash)
 {
 	return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) :
 				     &tbl->buckets[hash];
 }
 
-static inline struct rhash_head __rcu **rht_bucket_var(
+static inline struct rhash_lock_head __rcu **rht_bucket_var(
 	struct bucket_table *tbl, unsigned int hash)
 {
 	return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) :
 				     &tbl->buckets[hash];
 }
 
-static inline struct rhash_head __rcu **rht_bucket_insert(
+static inline struct rhash_lock_head __rcu **rht_bucket_insert(
 	struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash)
 {
 	return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) :
@@ -326,7 +374,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * @hash:	the hash value / bucket index
  */
 #define rht_for_each(pos, tbl, hash) \
-	rht_for_each_from(pos, *rht_bucket(tbl, hash), tbl, hash)
+	rht_for_each_from(pos, rht_ptr(*rht_bucket(tbl, hash)), tbl, hash)
 
 /**
  * rht_for_each_entry_from - iterate over hash chain from given head
@@ -351,7 +399,7 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * @member:	name of the &struct rhash_head within the hashable struct.
  */
 #define rht_for_each_entry(tpos, pos, tbl, hash, member)		\
-	rht_for_each_entry_from(tpos, pos, *rht_bucket(tbl, hash),	\
+	rht_for_each_entry_from(tpos, pos, rht_ptr(*rht_bucket(tbl, hash)), \
 				    tbl, hash, member)
 
 /**
@@ -367,7 +415,8 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * remove the loop cursor from the list.
  */
 #define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member)	      \
-	for (pos = rht_dereference_bucket(*rht_bucket(tbl, hash), tbl, hash), \
+	for (pos = rht_dereference_bucket(rht_ptr(*rht_bucket(tbl, hash)),    \
+					  tbl, hash),			      \
 	     next = !rht_is_a_nulls(pos) ?				      \
 		       rht_dereference_bucket(pos->next, tbl, hash) : NULL;   \
 	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	      \
@@ -402,8 +451,12 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * the _rcu mutation primitives such as rhashtable_insert() as long as the
  * traversal is guarded by rcu_read_lock().
  */
-#define rht_for_each_rcu(pos, tbl, hash)				\
-	rht_for_each_rcu_from(pos, *rht_bucket(tbl, hash), tbl, hash)
+#define rht_for_each_rcu(pos, tbl, hash)			\
+	for (({barrier(); }),						\
+	     pos = rht_ptr(rht_dereference_bucket_rcu(			\
+				   *rht_bucket(tbl, hash), tbl, hash));	\
+	     !rht_is_a_nulls(pos);					\
+	     pos = rcu_dereference_raw(pos->next))
 
 /**
  * rht_for_each_entry_rcu_from - iterated over rcu hash chain from given head
@@ -437,7 +490,8 @@ static inline struct rhash_head __rcu **rht_bucket_insert(
  * traversal is guarded by rcu_read_lock().
  */
 #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member)		   \
-	rht_for_each_entry_rcu_from(tpos, pos, *rht_bucket(tbl, hash), \
+	rht_for_each_entry_rcu_from(tpos, pos,				   \
+					rht_ptr(*rht_bucket(tbl, hash)),   \
 					tbl, hash, member)
 
 /**
@@ -483,7 +537,7 @@ static inline struct rhash_head *__rhashtable_lookup(
 		.ht = ht,
 		.key = key,
 	};
-	struct rhash_head __rcu * const *head;
+	struct rhash_lock_head __rcu * const *bkt;
 	struct bucket_table *tbl;
 	struct rhash_head *he;
 	unsigned int hash;
@@ -491,9 +545,10 @@ static inline struct rhash_head *__rhashtable_lookup(
 	tbl = rht_dereference_rcu(ht->tbl, ht);
 restart:
 	hash = rht_key_hashfn(ht, tbl, key, params);
-	head = rht_bucket(tbl, hash);
+	bkt = rht_bucket(tbl, hash);
 	do {
-		rht_for_each_rcu_from(he, *head, tbl, hash) {
+		he = rht_ptr(rht_dereference_bucket_rcu(*bkt, tbl, hash));
+		rht_for_each_rcu_from(he, he, tbl, hash) {
 			if (params.obj_cmpfn ?
 			    params.obj_cmpfn(&arg, rht_obj(ht, he)) :
 			    rhashtable_compare(&arg, rht_obj(ht, he)))
@@ -503,7 +558,7 @@ restart:
 		/* An object might have been moved to a different hash chain,
 		 * while we walk along it - better check and retry.
 		 */
-	} while (he != RHT_NULLS_MARKER(head));
+	} while (he != RHT_NULLS_MARKER(bkt));
 
 	/* Ensure we see any new tables. */
 	smp_rmb();
@@ -599,10 +654,10 @@ static inline void *__rhashtable_insert_fast(
 		.ht = ht,
 		.key = key,
 	};
+	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct bucket_table *tbl;
 	struct rhash_head *head;
-	spinlock_t *lock;
 	unsigned int hash;
 	int elasticity;
 	void *data;
@@ -611,23 +666,22 @@ static inline void *__rhashtable_insert_fast(
 
 	tbl = rht_dereference_rcu(ht->tbl, ht);
 	hash = rht_head_hashfn(ht, tbl, obj, params);
-	lock = rht_bucket_lock(tbl, hash);
-	spin_lock_bh(lock);
+	elasticity = RHT_ELASTICITY;
+	bkt = rht_bucket_insert(ht, tbl, hash);
+	data = ERR_PTR(-ENOMEM);
+	if (!bkt)
+		goto out;
+	pprev = NULL;
+	rht_lock(bkt);
 
 	if (unlikely(rcu_access_pointer(tbl->future_tbl))) {
 slow_path:
-		spin_unlock_bh(lock);
+		rht_unlock(bkt);
 		rcu_read_unlock();
 		return rhashtable_insert_slow(ht, key, obj);
 	}
 
-	elasticity = RHT_ELASTICITY;
-	pprev = rht_bucket_insert(ht, tbl, hash);
-	data = ERR_PTR(-ENOMEM);
-	if (!pprev)
-		goto out;
-
-	rht_for_each_from(head, *pprev, tbl, hash) {
+	rht_for_each_from(head, rht_ptr(*bkt), tbl, hash) {
 		struct rhlist_head *plist;
 		struct rhlist_head *list;
 
@@ -643,7 +697,7 @@ slow_path:
 		data = rht_obj(ht, head);
 
 		if (!rhlist)
-			goto out;
+			goto out_unlock;
 
 
 		list = container_of(obj, struct rhlist_head, rhead);
@@ -652,9 +706,13 @@ slow_path:
 		RCU_INIT_POINTER(list->next, plist);
 		head = rht_dereference_bucket(head->next, tbl, hash);
 		RCU_INIT_POINTER(list->rhead.next, head);
-		rcu_assign_pointer(*pprev, obj);
-
-		goto good;
+		if (pprev) {
+			rcu_assign_pointer(*pprev, obj);
+			rht_unlock(bkt);
+		} else
+			rht_assign_unlock(bkt, obj);
+		data = NULL;
+		goto out;
 	}
 
 	if (elasticity <= 0)
@@ -662,12 +720,13 @@ slow_path:
 
 	data = ERR_PTR(-E2BIG);
 	if (unlikely(rht_grow_above_max(ht, tbl)))
-		goto out;
+		goto out_unlock;
 
 	if (unlikely(rht_grow_above_100(ht, tbl)))
 		goto slow_path;
 
-	head = rht_dereference_bucket(*pprev, tbl, hash);
+	/* Inserting at head of list makes unlocking free. */
+	head = rht_ptr(rht_dereference_bucket(*bkt, tbl, hash));
 
 	RCU_INIT_POINTER(obj->next, head);
 	if (rhlist) {
@@ -677,20 +736,21 @@ slow_path:
 		RCU_INIT_POINTER(list->next, NULL);
 	}
 
-	rcu_assign_pointer(*pprev, obj);
-
 	atomic_inc(&ht->nelems);
+	rht_assign_unlock(bkt, obj);
+
 	if (rht_grow_above_75(ht, tbl))
 		schedule_work(&ht->run_work);
 
-good:
 	data = NULL;
-
 out:
-	spin_unlock_bh(lock);
 	rcu_read_unlock();
 
 	return data;
+
+out_unlock:
+	rht_unlock(bkt);
+	goto out;
 }
 
 /**
@@ -699,9 +759,9 @@ out:
  * @obj:	pointer to hash head inside object
  * @params:	hash table parameters
  *
- * Will take a per bucket spinlock to protect against mutual mutations
+ * Will take the per bucket bitlock to protect against mutual mutations
  * on the same bucket. Multiple insertions may occur in parallel unless
- * they map to the same bucket lock.
+ * they map to the same bucket.
  *
  * It is safe to call this function from atomic context.
  *
@@ -728,9 +788,9 @@ static inline int rhashtable_insert_fast(
  * @list:	pointer to hash list head inside object
  * @params:	hash table parameters
  *
- * Will take a per bucket spinlock to protect against mutual mutations
+ * Will take the per bucket bitlock to protect against mutual mutations
  * on the same bucket. Multiple insertions may occur in parallel unless
- * they map to the same bucket lock.
+ * they map to the same bucket.
  *
  * It is safe to call this function from atomic context.
  *
@@ -751,9 +811,9 @@ static inline int rhltable_insert_key(
  * @list:	pointer to hash list head inside object
  * @params:	hash table parameters
  *
- * Will take a per bucket spinlock to protect against mutual mutations
+ * Will take the per bucket bitlock to protect against mutual mutations
  * on the same bucket. Multiple insertions may occur in parallel unless
- * they map to the same bucket lock.
+ * they map to the same bucket.
  *
  * It is safe to call this function from atomic context.
  *
@@ -880,21 +940,20 @@ static inline int __rhashtable_remove_fast_one(
 	struct rhash_head *obj, const struct rhashtable_params params,
 	bool rhlist)
 {
+	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct rhash_head *he;
-	spinlock_t * lock;
 	unsigned int hash;
 	int err = -ENOENT;
 
 	hash = rht_head_hashfn(ht, tbl, obj, params);
-	lock = rht_bucket_lock(tbl, hash);
+	bkt = rht_bucket_var(tbl, hash);
+	if (!bkt)
+		return -ENOENT;
+	pprev = NULL;
+	rht_lock(bkt);
 
-	spin_lock_bh(lock);
-
-	pprev = rht_bucket_var(tbl, hash);
-	if (!pprev)
-		goto out;
-	rht_for_each_from(he, *pprev, tbl, hash) {
+	rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) {
 		struct rhlist_head *list;
 
 		list = container_of(he, struct rhlist_head, rhead);
@@ -934,13 +993,17 @@ static inline int __rhashtable_remove_fast_one(
 			}
 		}
 
-		rcu_assign_pointer(*pprev, obj);
-		break;
+		if (pprev) {
+			rcu_assign_pointer(*pprev, obj);
+			rht_unlock(bkt);
+		} else {
+			rht_assign_unlock(bkt, obj);
+		}
+		goto unlocked;
 	}
 
-out:
-	spin_unlock_bh(lock);
-
+	rht_unlock(bkt);
+unlocked:
 	if (err > 0) {
 		atomic_dec(&ht->nelems);
 		if (unlikely(ht->p.automatic_shrinking &&
@@ -1029,9 +1092,9 @@ static inline int __rhashtable_replace_fast(
 	struct rhash_head *obj_old, struct rhash_head *obj_new,
 	const struct rhashtable_params params)
 {
+	struct rhash_lock_head __rcu **bkt;
 	struct rhash_head __rcu **pprev;
 	struct rhash_head *he;
-	spinlock_t *lock;
 	unsigned int hash;
 	int err = -ENOENT;
 
@@ -1042,27 +1105,33 @@ static inline int __rhashtable_replace_fast(
 	if (hash != rht_head_hashfn(ht, tbl, obj_new, params))
 		return -EINVAL;
 
-	lock = rht_bucket_lock(tbl, hash);
+	bkt = rht_bucket_var(tbl, hash);
+	if (!bkt)
+		return -ENOENT;
 
-	spin_lock_bh(lock);
+	pprev = NULL;
+	rht_lock(bkt);
 
-	pprev = rht_bucket_var(tbl, hash);
-	if (!pprev)
-		goto out;
-	rht_for_each_from(he, *pprev, tbl, hash) {
+	rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) {
 		if (he != obj_old) {
 			pprev = &he->next;
 			continue;
 		}
 
 		rcu_assign_pointer(obj_new->next, obj_old->next);
-		rcu_assign_pointer(*pprev, obj_new);
+		if (pprev) {
+			rcu_assign_pointer(*pprev, obj_new);
+			rht_unlock(bkt);
+		} else {
+			rht_assign_unlock(bkt, obj_new);
+		}
 		err = 0;
-		break;
+		goto unlocked;
 	}
-out:
-	spin_unlock_bh(lock);
 
+	rht_unlock(bkt);
+
+unlocked:
 	return err;
 }
 
diff --git a/ipc/util.c b/ipc/util.c
index 0af05752969f..095274a871f8 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -101,7 +101,6 @@ static const struct rhashtable_params ipc_kht_params = {
 	.head_offset		= offsetof(struct kern_ipc_perm, khtnode),
 	.key_offset		= offsetof(struct kern_ipc_perm, key),
 	.key_len		= FIELD_SIZEOF(struct kern_ipc_perm, key),
-	.locks_mul		= 1,
 	.automatic_shrinking	= true,
 };
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index b28fdd560ea9..c5d0974467ee 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -31,11 +31,10 @@
 
 #define HASH_DEFAULT_SIZE	64UL
 #define HASH_MIN_SIZE		4U
-#define BUCKET_LOCKS_PER_CPU	32UL
 
 union nested_table {
 	union nested_table __rcu *table;
-	struct rhash_head __rcu *bucket;
+	struct rhash_lock_head __rcu *bucket;
 };
 
 static u32 head_hashfn(struct rhashtable *ht,
@@ -56,9 +55,11 @@ EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);
 
 int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash)
 {
-	spinlock_t *lock = rht_bucket_lock(tbl, hash);
-
-	return (debug_locks) ? lockdep_is_held(lock) : 1;
+	if (!debug_locks)
+		return 1;
+	if (unlikely(tbl->nest))
+		return 1;
+	return bit_spin_is_locked(1, (unsigned long *)&tbl->buckets[hash]);
 }
 EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
 #else
@@ -104,7 +105,6 @@ static void bucket_table_free(const struct bucket_table *tbl)
 	if (tbl->nest)
 		nested_bucket_table_free(tbl);
 
-	free_bucket_spinlocks(tbl->locks);
 	kvfree(tbl);
 }
 
@@ -171,7 +171,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 					       gfp_t gfp)
 {
 	struct bucket_table *tbl = NULL;
-	size_t size, max_locks;
+	size_t size;
 	int i;
 
 	size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
@@ -189,16 +189,6 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 
 	tbl->size = size;
 
-	max_locks = size >> 1;
-	if (tbl->nest)
-		max_locks = min_t(size_t, max_locks, 1U << tbl->nest);
-
-	if (alloc_bucket_spinlocks(&tbl->locks, &tbl->locks_mask, max_locks,
-				   ht->p.locks_mul, gfp) < 0) {
-		bucket_table_free(tbl);
-		return NULL;
-	}
-
 	rcu_head_init(&tbl->rcu);
 	INIT_LIST_HEAD(&tbl->walkers);
 
@@ -223,24 +213,23 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht,
 	return new_tbl;
 }
 
-static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
+static int rhashtable_rehash_one(struct rhashtable *ht,
+				 struct rhash_lock_head __rcu **bkt,
+				 unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
 	struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl);
-	struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash);
 	int err = -EAGAIN;
 	struct rhash_head *head, *next, *entry;
-	spinlock_t *new_bucket_lock;
+	struct rhash_head **pprev = NULL;
 	unsigned int new_hash;
 
 	if (new_tbl->nest)
 		goto out;
 
 	err = -ENOENT;
-	if (!pprev)
-		goto out;
 
-	rht_for_each_from(entry, *pprev, old_tbl, old_hash) {
+	rht_for_each_from(entry, rht_ptr(*bkt), old_tbl, old_hash) {
 		err = 0;
 		next = rht_dereference_bucket(entry->next, old_tbl, old_hash);
 
@@ -255,18 +244,20 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
 
 	new_hash = head_hashfn(ht, new_tbl, entry);
 
-	new_bucket_lock = rht_bucket_lock(new_tbl, new_hash);
+	rht_lock(&new_tbl->buckets[new_hash]);
 
-	spin_lock_nested(new_bucket_lock, SINGLE_DEPTH_NESTING);
-	head = rht_dereference_bucket(new_tbl->buckets[new_hash],
-				      new_tbl, new_hash);
+	head = rht_ptr(rht_dereference_bucket(new_tbl->buckets[new_hash],
+					      new_tbl, new_hash));
 
 	RCU_INIT_POINTER(entry->next, head);
 
-	rcu_assign_pointer(new_tbl->buckets[new_hash], entry);
-	spin_unlock(new_bucket_lock);
+	rht_assign_unlock(&new_tbl->buckets[new_hash], entry);
 
-	rcu_assign_pointer(*pprev, next);
+	if (pprev)
+		rcu_assign_pointer(*pprev, next);
+	else
+		/* Need to preserved the bit lock. */
+		rcu_assign_pointer(*bkt, rht_ptr_locked(next));
 
 out:
 	return err;
@@ -276,19 +267,19 @@ static int rhashtable_rehash_chain(struct rhashtable *ht,
 				    unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
-	spinlock_t *old_bucket_lock;
+	struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash);
 	int err;
 
-	old_bucket_lock = rht_bucket_lock(old_tbl, old_hash);
+	if (!bkt)
+		return 0;
+	rht_lock(bkt);
 
-	spin_lock_bh(old_bucket_lock);
-	while (!(err = rhashtable_rehash_one(ht, old_hash)))
+	while (!(err = rhashtable_rehash_one(ht, bkt, old_hash)))
 		;
 
 	if (err == -ENOENT)
 		err = 0;
-
-	spin_unlock_bh(old_bucket_lock);
+	rht_unlock(bkt);
 
 	return err;
 }
@@ -485,6 +476,7 @@ fail:
 }
 
 static void *rhashtable_lookup_one(struct rhashtable *ht,
+				   struct rhash_lock_head __rcu **bkt,
 				   struct bucket_table *tbl, unsigned int hash,
 				   const void *key, struct rhash_head *obj)
 {
@@ -492,15 +484,12 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 		.ht = ht,
 		.key = key,
 	};
-	struct rhash_head __rcu **pprev;
+	struct rhash_head **pprev = NULL;
 	struct rhash_head *head;
 	int elasticity;
 
 	elasticity = RHT_ELASTICITY;
-	pprev = rht_bucket_var(tbl, hash);
-	if (!pprev)
-		return ERR_PTR(-ENOENT);
-	rht_for_each_from(head, *pprev, tbl, hash) {
+	rht_for_each_from(head, rht_ptr(*bkt), tbl, hash) {
 		struct rhlist_head *list;
 		struct rhlist_head *plist;
 
@@ -522,7 +511,11 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 		RCU_INIT_POINTER(list->next, plist);
 		head = rht_dereference_bucket(head->next, tbl, hash);
 		RCU_INIT_POINTER(list->rhead.next, head);
-		rcu_assign_pointer(*pprev, obj);
+		if (pprev)
+			rcu_assign_pointer(*pprev, obj);
+		else
+			/* Need to preserve the bit lock */
+			rcu_assign_pointer(*bkt, rht_ptr_locked(obj));
 
 		return NULL;
 	}
@@ -534,12 +527,12 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 }
 
 static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
+						  struct rhash_lock_head __rcu **bkt,
 						  struct bucket_table *tbl,
 						  unsigned int hash,
 						  struct rhash_head *obj,
 						  void *data)
 {
-	struct rhash_head __rcu **pprev;
 	struct bucket_table *new_tbl;
 	struct rhash_head *head;
 
@@ -562,11 +555,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
 	if (unlikely(rht_grow_above_100(ht, tbl)))
 		return ERR_PTR(-EAGAIN);
 
-	pprev = rht_bucket_insert(ht, tbl, hash);
-	if (!pprev)
-		return ERR_PTR(-ENOMEM);
-
-	head = rht_dereference_bucket(*pprev, tbl, hash);
+	head = rht_ptr(rht_dereference_bucket(*bkt, tbl, hash));
 
 	RCU_INIT_POINTER(obj->next, head);
 	if (ht->rhlist) {
@@ -576,7 +565,10 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
 		RCU_INIT_POINTER(list->next, NULL);
 	}
 
-	rcu_assign_pointer(*pprev, obj);
+	/* bkt is always the head of the list, so it holds
+	 * the lock, which we need to preserve
+	 */
+	rcu_assign_pointer(*bkt, rht_ptr_locked(obj));
 
 	atomic_inc(&ht->nelems);
 	if (rht_grow_above_75(ht, tbl))
@@ -590,6 +582,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 {
 	struct bucket_table *new_tbl;
 	struct bucket_table *tbl;
+	struct rhash_lock_head __rcu **bkt;
 	unsigned int hash;
 	void *data;
 
@@ -598,14 +591,25 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 	do {
 		tbl = new_tbl;
 		hash = rht_head_hashfn(ht, tbl, obj, ht->p);
-		spin_lock_bh(rht_bucket_lock(tbl, hash));
-
-		data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
-		new_tbl = rhashtable_insert_one(ht, tbl, hash, obj, data);
-		if (PTR_ERR(new_tbl) != -EEXIST)
-			data = ERR_CAST(new_tbl);
-
-		spin_unlock_bh(rht_bucket_lock(tbl, hash));
+		if (rcu_access_pointer(tbl->future_tbl))
+			/* Failure is OK */
+			bkt = rht_bucket_var(tbl, hash);
+		else
+			bkt = rht_bucket_insert(ht, tbl, hash);
+		if (bkt == NULL) {
+			new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
+			data = ERR_PTR(-EAGAIN);
+		} else {
+			rht_lock(bkt);
+			data = rhashtable_lookup_one(ht, bkt, tbl,
+						     hash, key, obj);
+			new_tbl = rhashtable_insert_one(ht, bkt, tbl,
+							hash, obj, data);
+			if (PTR_ERR(new_tbl) != -EEXIST)
+				data = ERR_CAST(new_tbl);
+
+			rht_unlock(bkt);
+		}
 	} while (!IS_ERR_OR_NULL(new_tbl));
 
 	if (PTR_ERR(data) == -EAGAIN)
@@ -1032,11 +1036,6 @@ int rhashtable_init(struct rhashtable *ht,
 
 	size = rounded_hashtable_size(&ht->p);
 
-	if (params->locks_mul)
-		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
-	else
-		ht->p.locks_mul = BUCKET_LOCKS_PER_CPU;
-
 	ht->key_len = ht->p.key_len;
 	if (!params->hashfn) {
 		ht->p.hashfn = jhash;
@@ -1138,7 +1137,7 @@ restart:
 			struct rhash_head *pos, *next;
 
 			cond_resched();
-			for (pos = rht_dereference(*rht_bucket(tbl, i), ht),
+			for (pos = rht_ptr(rht_dereference(*rht_bucket(tbl, i), ht)),
 			     next = !rht_is_a_nulls(pos) ?
 					rht_dereference(pos->next, ht) : NULL;
 			     !rht_is_a_nulls(pos);
@@ -1165,8 +1164,8 @@ void rhashtable_destroy(struct rhashtable *ht)
 }
 EXPORT_SYMBOL_GPL(rhashtable_destroy);
 
-struct rhash_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
-					      unsigned int hash)
+struct rhash_lock_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
+						   unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
@@ -1194,10 +1193,10 @@ struct rhash_head __rcu **__rht_bucket_nested(const struct bucket_table *tbl,
 }
 EXPORT_SYMBOL_GPL(__rht_bucket_nested);
 
-struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
-					    unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
+						 unsigned int hash)
 {
-	static struct rhash_head __rcu *rhnull;
+	static struct rhash_lock_head __rcu *rhnull;
 
 	if (!rhnull)
 		INIT_RHT_NULLS_HEAD(rhnull);
@@ -1205,9 +1204,9 @@ struct rhash_head __rcu **rht_bucket_nested(const struct bucket_table *tbl,
 }
 EXPORT_SYMBOL_GPL(rht_bucket_nested);
 
-struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
-						   struct bucket_table *tbl,
-						   unsigned int hash)
+struct rhash_lock_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
+							struct bucket_table *tbl,
+							unsigned int hash)
 {
 	const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *));
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 3bd2e91bfc29..02592c2a249c 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -500,7 +500,7 @@ static unsigned int __init print_ht(struct rhltable *rhlt)
 		struct rhash_head *pos, *next;
 		struct test_obj_rhl *p;
 
-		pos = rht_dereference(tbl->buckets[i], ht);
+		pos = rht_ptr(rht_dereference(tbl->buckets[i], ht));
 		next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL;
 
 		if (!rht_is_a_nulls(pos)) {
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 00573cc46c98..b1c91f66d79c 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -33,7 +33,6 @@ static const struct rhashtable_params br_fdb_rht_params = {
 	.key_offset = offsetof(struct net_bridge_fdb_entry, key),
 	.key_len = sizeof(struct net_bridge_fdb_key),
 	.automatic_shrinking = true,
-	.locks_mul = 1,
 };
 
 static struct kmem_cache *br_fdb_cache __read_mostly;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 8d82107c6419..812560d7f7a2 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -44,7 +44,6 @@ static const struct rhashtable_params br_mdb_rht_params = {
 	.key_offset = offsetof(struct net_bridge_mdb_entry, addr),
 	.key_len = sizeof(struct br_ip),
 	.automatic_shrinking = true,
-	.locks_mul = 1,
 };
 
 static void br_multicast_start_querier(struct net_bridge *br,
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 96abf8feb9dc..0a02822b5667 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -21,7 +21,6 @@ static const struct rhashtable_params br_vlan_rht_params = {
 	.key_offset = offsetof(struct net_bridge_vlan, vid),
 	.key_len = sizeof(u16),
 	.nelem_hint = 3,
-	.locks_mul = 1,
 	.max_size = VLAN_N_VID,
 	.obj_cmpfn = br_vlan_cmp,
 	.automatic_shrinking = true,
diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c
index 6d2c4eed2dc8..758151863669 100644
--- a/net/bridge/br_vlan_tunnel.c
+++ b/net/bridge/br_vlan_tunnel.c
@@ -34,7 +34,6 @@ static const struct rhashtable_params br_vlan_tunnel_rht_params = {
 	.key_offset = offsetof(struct net_bridge_vlan, tinfo.tunnel_id),
 	.key_len = sizeof(__be64),
 	.nelem_hint = 3,
-	.locks_mul = 1,
 	.obj_cmpfn = br_vlan_tunid_cmp,
 	.automatic_shrinking = true,
 };
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 2c931120c494..9a3f13edc98e 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -373,7 +373,6 @@ static const struct rhashtable_params ipmr_rht_params = {
 	.key_offset = offsetof(struct mfc_cache, cmparg),
 	.key_len = sizeof(struct mfc_cache_cmp_arg),
 	.nelem_hint = 3,
-	.locks_mul = 1,
 	.obj_cmpfn = ipmr_hash_cmp,
 	.automatic_shrinking = true,
 };
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index e4dd57976737..4e69847ed5be 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -355,7 +355,6 @@ static const struct rhashtable_params ip6mr_rht_params = {
 	.key_offset = offsetof(struct mfc6_cache, cmparg),
 	.key_len = sizeof(struct mfc6_cache_cmp_arg),
 	.nelem_hint = 3,
-	.locks_mul = 1,
 	.obj_cmpfn = ip6mr_hash_cmp,
 	.automatic_shrinking = true,
 };
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ef7772e976cc..90e6b09ef2af 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -53,7 +53,6 @@ static const struct rhashtable_params nft_chain_ht_params = {
 	.hashfn			= nft_chain_hash,
 	.obj_hashfn		= nft_chain_hash_obj,
 	.obj_cmpfn		= nft_chain_hash_cmp,
-	.locks_mul		= 1,
 	.automatic_shrinking	= true,
 };
 
-- 
cgit v1.2.3


From 149212f07856b25a9d342bfd6d736519b2ef66dc Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Tue, 2 Apr 2019 10:07:45 +1100
Subject: rhashtable: add lockdep tracking to bucket bit-spin-locks.

Native bit_spin_locks are not tracked by lockdep.

The bit_spin_locks used for rhashtable buckets are local
to the rhashtable implementation, so there is little opportunity
for the sort of misuse that lockdep might detect.
However locks are held while a hash function or compare
function is called, and if one of these took a lock,
a misbehaviour is possible.

As it is quite easy to add lockdep support this unlikely
possibility seems to be enough justification.

So create a lockdep class for bucket bit_spin_lock and attach
through a lockdep_map in each bucket_table.

Without the 'nested' annotation in rhashtable_rehash_one(), lockdep
correctly reports a possible problem as this lock is taken
while another bucket lock (in another table) is held.  This
confirms that the added support works.
With the correct nested annotation in place, lockdep reports
no problems.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 51 ++++++++++++++++++++++++++++++----------------
 lib/rhashtable.c           | 15 ++++++++------
 2 files changed, 43 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index ccbbafdf5547..460c0eaf6b96 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -82,6 +82,8 @@ struct bucket_table {
 
 	struct bucket_table __rcu *future_tbl;
 
+	struct lockdep_map	dep_map;
+
 	struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp;
 };
 
@@ -102,23 +104,38 @@ struct bucket_table {
  * this is safe.
  */
 
-static inline void rht_lock(struct rhash_lock_head **bkt)
+static inline void rht_lock(struct bucket_table *tbl,
+			    struct rhash_lock_head **bkt)
 {
 	local_bh_disable();
 	bit_spin_lock(1, (unsigned long *)bkt);
+	lock_map_acquire(&tbl->dep_map);
+}
+
+static inline void rht_lock_nested(struct bucket_table *tbl,
+				   struct rhash_lock_head **bucket,
+				   unsigned int subclass)
+{
+	local_bh_disable();
+	bit_spin_lock(1, (unsigned long *)bucket);
+	lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_);
 }
 
-static inline void rht_unlock(struct rhash_lock_head **bkt)
+static inline void rht_unlock(struct bucket_table *tbl,
+			      struct rhash_lock_head **bkt)
 {
+	lock_map_release(&tbl->dep_map);
 	bit_spin_unlock(1, (unsigned long *)bkt);
 	local_bh_enable();
 }
 
-static inline void rht_assign_unlock(struct rhash_lock_head **bkt,
+static inline void rht_assign_unlock(struct bucket_table *tbl,
+				     struct rhash_lock_head **bkt,
 				     struct rhash_head *obj)
 {
 	struct rhash_head **p = (struct rhash_head **)bkt;
 
+	lock_map_release(&tbl->dep_map);
 	rcu_assign_pointer(*p, obj);
 	preempt_enable();
 	__release(bitlock);
@@ -672,11 +689,11 @@ static inline void *__rhashtable_insert_fast(
 	if (!bkt)
 		goto out;
 	pprev = NULL;
-	rht_lock(bkt);
+	rht_lock(tbl, bkt);
 
 	if (unlikely(rcu_access_pointer(tbl->future_tbl))) {
 slow_path:
-		rht_unlock(bkt);
+		rht_unlock(tbl, bkt);
 		rcu_read_unlock();
 		return rhashtable_insert_slow(ht, key, obj);
 	}
@@ -708,9 +725,9 @@ slow_path:
 		RCU_INIT_POINTER(list->rhead.next, head);
 		if (pprev) {
 			rcu_assign_pointer(*pprev, obj);
-			rht_unlock(bkt);
+			rht_unlock(tbl, bkt);
 		} else
-			rht_assign_unlock(bkt, obj);
+			rht_assign_unlock(tbl, bkt, obj);
 		data = NULL;
 		goto out;
 	}
@@ -737,7 +754,7 @@ slow_path:
 	}
 
 	atomic_inc(&ht->nelems);
-	rht_assign_unlock(bkt, obj);
+	rht_assign_unlock(tbl, bkt, obj);
 
 	if (rht_grow_above_75(ht, tbl))
 		schedule_work(&ht->run_work);
@@ -749,7 +766,7 @@ out:
 	return data;
 
 out_unlock:
-	rht_unlock(bkt);
+	rht_unlock(tbl, bkt);
 	goto out;
 }
 
@@ -951,7 +968,7 @@ static inline int __rhashtable_remove_fast_one(
 	if (!bkt)
 		return -ENOENT;
 	pprev = NULL;
-	rht_lock(bkt);
+	rht_lock(tbl, bkt);
 
 	rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) {
 		struct rhlist_head *list;
@@ -995,14 +1012,14 @@ static inline int __rhashtable_remove_fast_one(
 
 		if (pprev) {
 			rcu_assign_pointer(*pprev, obj);
-			rht_unlock(bkt);
+			rht_unlock(tbl, bkt);
 		} else {
-			rht_assign_unlock(bkt, obj);
+			rht_assign_unlock(tbl, bkt, obj);
 		}
 		goto unlocked;
 	}
 
-	rht_unlock(bkt);
+	rht_unlock(tbl, bkt);
 unlocked:
 	if (err > 0) {
 		atomic_dec(&ht->nelems);
@@ -1110,7 +1127,7 @@ static inline int __rhashtable_replace_fast(
 		return -ENOENT;
 
 	pprev = NULL;
-	rht_lock(bkt);
+	rht_lock(tbl, bkt);
 
 	rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) {
 		if (he != obj_old) {
@@ -1121,15 +1138,15 @@ static inline int __rhashtable_replace_fast(
 		rcu_assign_pointer(obj_new->next, obj_old->next);
 		if (pprev) {
 			rcu_assign_pointer(*pprev, obj_new);
-			rht_unlock(bkt);
+			rht_unlock(tbl, bkt);
 		} else {
-			rht_assign_unlock(bkt, obj_new);
+			rht_assign_unlock(tbl, bkt, obj_new);
 		}
 		err = 0;
 		goto unlocked;
 	}
 
-	rht_unlock(bkt);
+	rht_unlock(tbl, bkt);
 
 unlocked:
 	return err;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index c5d0974467ee..a8583af43b59 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -173,6 +173,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 	struct bucket_table *tbl = NULL;
 	size_t size;
 	int i;
+	static struct lock_class_key __key;
 
 	size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
 	tbl = kvzalloc(size, gfp);
@@ -187,6 +188,8 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 	if (tbl == NULL)
 		return NULL;
 
+	lockdep_init_map(&tbl->dep_map, "rhashtable_bucket", &__key, 0);
+
 	tbl->size = size;
 
 	rcu_head_init(&tbl->rcu);
@@ -244,14 +247,14 @@ static int rhashtable_rehash_one(struct rhashtable *ht,
 
 	new_hash = head_hashfn(ht, new_tbl, entry);
 
-	rht_lock(&new_tbl->buckets[new_hash]);
+	rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING);
 
 	head = rht_ptr(rht_dereference_bucket(new_tbl->buckets[new_hash],
 					      new_tbl, new_hash));
 
 	RCU_INIT_POINTER(entry->next, head);
 
-	rht_assign_unlock(&new_tbl->buckets[new_hash], entry);
+	rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry);
 
 	if (pprev)
 		rcu_assign_pointer(*pprev, next);
@@ -272,14 +275,14 @@ static int rhashtable_rehash_chain(struct rhashtable *ht,
 
 	if (!bkt)
 		return 0;
-	rht_lock(bkt);
+	rht_lock(old_tbl, bkt);
 
 	while (!(err = rhashtable_rehash_one(ht, bkt, old_hash)))
 		;
 
 	if (err == -ENOENT)
 		err = 0;
-	rht_unlock(bkt);
+	rht_unlock(old_tbl, bkt);
 
 	return err;
 }
@@ -600,7 +603,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 			new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
 			data = ERR_PTR(-EAGAIN);
 		} else {
-			rht_lock(bkt);
+			rht_lock(tbl, bkt);
 			data = rhashtable_lookup_one(ht, bkt, tbl,
 						     hash, key, obj);
 			new_tbl = rhashtable_insert_one(ht, bkt, tbl,
@@ -608,7 +611,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 			if (PTR_ERR(new_tbl) != -EEXIST)
 				data = ERR_CAST(new_tbl);
 
-			rht_unlock(bkt);
+			rht_unlock(tbl, bkt);
 		}
 	} while (!IS_ERR_OR_NULL(new_tbl));
 
-- 
cgit v1.2.3


From b262a69582a4676c7378a73077b7bb186c7c5b2a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Mar 2019 21:16:22 +0100
Subject: xfrm: place af number into xfrm_mode struct

This will be useful to know if we're supposed to decode ipv4 or ipv6.

While at it, make the unregister function return void, all module_exit
functions did just BUG(); there is never a point in doing error checks
if there is no way to handle such error.

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h              |  9 +++++----
 net/ipv4/xfrm4_mode_beet.c      |  8 +++-----
 net/ipv4/xfrm4_mode_transport.c |  8 +++-----
 net/ipv4/xfrm4_mode_tunnel.c    |  8 +++-----
 net/ipv6/xfrm6_mode_beet.c      |  8 +++-----
 net/ipv6/xfrm6_mode_ro.c        |  8 +++-----
 net/ipv6/xfrm6_mode_transport.c |  8 +++-----
 net/ipv6/xfrm6_mode_tunnel.c    |  8 +++-----
 net/xfrm/xfrm_state.c           | 19 ++++++-------------
 9 files changed, 32 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 85386becbaea..9a155063c25f 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -482,8 +482,9 @@ struct xfrm_mode {
 
 	struct xfrm_state_afinfo *afinfo;
 	struct module *owner;
-	unsigned int encap;
-	int flags;
+	u8 encap;
+	u8 family;
+	u8 flags;
 };
 
 /* Flags for xfrm_mode. */
@@ -491,8 +492,8 @@ enum {
 	XFRM_MODE_FLAG_TUNNEL = 1,
 };
 
-int xfrm_register_mode(struct xfrm_mode *mode, int family);
-int xfrm_unregister_mode(struct xfrm_mode *mode, int family);
+int xfrm_register_mode(struct xfrm_mode *mode);
+void xfrm_unregister_mode(struct xfrm_mode *mode);
 
 static inline int xfrm_af2proto(unsigned int family)
 {
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
index 856d2dfdb44b..a2e3b52ae46c 100644
--- a/net/ipv4/xfrm4_mode_beet.c
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -134,19 +134,17 @@ static struct xfrm_mode xfrm4_beet_mode = {
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_BEET,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
+	.family = AF_INET,
 };
 
 static int __init xfrm4_beet_init(void)
 {
-	return xfrm_register_mode(&xfrm4_beet_mode, AF_INET);
+	return xfrm_register_mode(&xfrm4_beet_mode);
 }
 
 static void __exit xfrm4_beet_exit(void)
 {
-	int err;
-
-	err = xfrm_unregister_mode(&xfrm4_beet_mode, AF_INET);
-	BUG_ON(err);
+	xfrm_unregister_mode(&xfrm4_beet_mode);
 }
 
 module_init(xfrm4_beet_init);
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index 1ad2c2c4e250..7c5443f797cf 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -93,19 +93,17 @@ static struct xfrm_mode xfrm4_transport_mode = {
 	.xmit = xfrm4_transport_xmit,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TRANSPORT,
+	.family = AF_INET,
 };
 
 static int __init xfrm4_transport_init(void)
 {
-	return xfrm_register_mode(&xfrm4_transport_mode, AF_INET);
+	return xfrm_register_mode(&xfrm4_transport_mode);
 }
 
 static void __exit xfrm4_transport_exit(void)
 {
-	int err;
-
-	err = xfrm_unregister_mode(&xfrm4_transport_mode, AF_INET);
-	BUG_ON(err);
+	xfrm_unregister_mode(&xfrm4_transport_mode);
 }
 
 module_init(xfrm4_transport_init);
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 2a9764bd1719..cfc6b6d39755 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -131,19 +131,17 @@ static struct xfrm_mode xfrm4_tunnel_mode = {
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
+	.family = AF_INET,
 };
 
 static int __init xfrm4_mode_tunnel_init(void)
 {
-	return xfrm_register_mode(&xfrm4_tunnel_mode, AF_INET);
+	return xfrm_register_mode(&xfrm4_tunnel_mode);
 }
 
 static void __exit xfrm4_mode_tunnel_exit(void)
 {
-	int err;
-
-	err = xfrm_unregister_mode(&xfrm4_tunnel_mode, AF_INET);
-	BUG_ON(err);
+	xfrm_unregister_mode(&xfrm4_tunnel_mode);
 }
 
 module_init(xfrm4_mode_tunnel_init);
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
index 57fd314ec2b8..0d440e3a13f8 100644
--- a/net/ipv6/xfrm6_mode_beet.c
+++ b/net/ipv6/xfrm6_mode_beet.c
@@ -110,19 +110,17 @@ static struct xfrm_mode xfrm6_beet_mode = {
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_BEET,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
+	.family = AF_INET6,
 };
 
 static int __init xfrm6_beet_init(void)
 {
-	return xfrm_register_mode(&xfrm6_beet_mode, AF_INET6);
+	return xfrm_register_mode(&xfrm6_beet_mode);
 }
 
 static void __exit xfrm6_beet_exit(void)
 {
-	int err;
-
-	err = xfrm_unregister_mode(&xfrm6_beet_mode, AF_INET6);
-	BUG_ON(err);
+	xfrm_unregister_mode(&xfrm6_beet_mode);
 }
 
 module_init(xfrm6_beet_init);
diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c
index da28e4407b8f..0408547d01ab 100644
--- a/net/ipv6/xfrm6_mode_ro.c
+++ b/net/ipv6/xfrm6_mode_ro.c
@@ -64,19 +64,17 @@ static struct xfrm_mode xfrm6_ro_mode = {
 	.output = xfrm6_ro_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_ROUTEOPTIMIZATION,
+	.family = AF_INET6,
 };
 
 static int __init xfrm6_ro_init(void)
 {
-	return xfrm_register_mode(&xfrm6_ro_mode, AF_INET6);
+	return xfrm_register_mode(&xfrm6_ro_mode);
 }
 
 static void __exit xfrm6_ro_exit(void)
 {
-	int err;
-
-	err = xfrm_unregister_mode(&xfrm6_ro_mode, AF_INET6);
-	BUG_ON(err);
+	xfrm_unregister_mode(&xfrm6_ro_mode);
 }
 
 module_init(xfrm6_ro_init);
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 3c29da5defe6..66ae79218bdf 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -100,19 +100,17 @@ static struct xfrm_mode xfrm6_transport_mode = {
 	.xmit = xfrm6_transport_xmit,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TRANSPORT,
+	.family = AF_INET6,
 };
 
 static int __init xfrm6_transport_init(void)
 {
-	return xfrm_register_mode(&xfrm6_transport_mode, AF_INET6);
+	return xfrm_register_mode(&xfrm6_transport_mode);
 }
 
 static void __exit xfrm6_transport_exit(void)
 {
-	int err;
-
-	err = xfrm_unregister_mode(&xfrm6_transport_mode, AF_INET6);
-	BUG_ON(err);
+	xfrm_unregister_mode(&xfrm6_transport_mode);
 }
 
 module_init(xfrm6_transport_init);
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index de1b0b8c53b0..6cf12e961ea5 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -130,19 +130,17 @@ static struct xfrm_mode xfrm6_tunnel_mode = {
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
+	.family = AF_INET6,
 };
 
 static int __init xfrm6_mode_tunnel_init(void)
 {
-	return xfrm_register_mode(&xfrm6_tunnel_mode, AF_INET6);
+	return xfrm_register_mode(&xfrm6_tunnel_mode);
 }
 
 static void __exit xfrm6_mode_tunnel_exit(void)
 {
-	int err;
-
-	err = xfrm_unregister_mode(&xfrm6_tunnel_mode, AF_INET6);
-	BUG_ON(err);
+	xfrm_unregister_mode(&xfrm6_tunnel_mode);
 }
 
 module_init(xfrm6_mode_tunnel_init);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 1bb971f46fc6..c32394b59776 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -331,7 +331,7 @@ static void xfrm_put_type_offload(const struct xfrm_type_offload *type)
 }
 
 static DEFINE_SPINLOCK(xfrm_mode_lock);
-int xfrm_register_mode(struct xfrm_mode *mode, int family)
+int xfrm_register_mode(struct xfrm_mode *mode)
 {
 	struct xfrm_state_afinfo *afinfo;
 	struct xfrm_mode **modemap;
@@ -340,7 +340,7 @@ int xfrm_register_mode(struct xfrm_mode *mode, int family)
 	if (unlikely(mode->encap >= XFRM_MODE_MAX))
 		return -EINVAL;
 
-	afinfo = xfrm_state_get_afinfo(family);
+	afinfo = xfrm_state_get_afinfo(mode->family);
 	if (unlikely(afinfo == NULL))
 		return -EAFNOSUPPORT;
 
@@ -365,31 +365,24 @@ out:
 }
 EXPORT_SYMBOL(xfrm_register_mode);
 
-int xfrm_unregister_mode(struct xfrm_mode *mode, int family)
+void xfrm_unregister_mode(struct xfrm_mode *mode)
 {
 	struct xfrm_state_afinfo *afinfo;
 	struct xfrm_mode **modemap;
-	int err;
-
-	if (unlikely(mode->encap >= XFRM_MODE_MAX))
-		return -EINVAL;
 
-	afinfo = xfrm_state_get_afinfo(family);
-	if (unlikely(afinfo == NULL))
-		return -EAFNOSUPPORT;
+	afinfo = xfrm_state_get_afinfo(mode->family);
+	if (WARN_ON_ONCE(!afinfo))
+		return;
 
-	err = -ENOENT;
 	modemap = afinfo->mode_map;
 	spin_lock_bh(&xfrm_mode_lock);
 	if (likely(modemap[mode->encap] == mode)) {
 		modemap[mode->encap] = NULL;
 		module_put(mode->afinfo->owner);
-		err = 0;
 	}
 
 	spin_unlock_bh(&xfrm_mode_lock);
 	rcu_read_unlock();
-	return err;
 }
 EXPORT_SYMBOL(xfrm_unregister_mode);
 
-- 
cgit v1.2.3


From c2d305e51038167dd9de8d476c72f667d84cad8b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Mar 2019 21:16:24 +0100
Subject: xfrm: remove input indirection from xfrm_mode

No need for any indirection or abstraction here, both functions
are pretty much the same and quite small, they also have no external
dependencies.

xfrm_prepare_input can then be made static.

With allmodconfig build, size increase of vmlinux is 25 byte:

Before:
   text   data     bss     dec      filename
15730207  6936924 4046908 26714039  vmlinux

After:
15730208  6936948 4046908 26714064 vmlinux

v2: Fix INET_XFRM_MODE_TRANSPORT name in is-enabled test (Sabrina Dubroca)
    change copied comment to refer to transport and network header,
    not skb->{h,nh}, which don't exist anymore. (Sabrina)
    make xfrm_prepare_input static (Eyal Birger)

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h              | 11 ------
 net/ipv4/xfrm4_mode_beet.c      |  1 -
 net/ipv4/xfrm4_mode_transport.c | 23 -------------
 net/ipv4/xfrm4_mode_tunnel.c    |  1 -
 net/ipv6/xfrm6_mode_beet.c      |  1 -
 net/ipv6/xfrm6_mode_transport.c | 25 --------------
 net/ipv6/xfrm6_mode_tunnel.c    |  1 -
 net/xfrm/xfrm_input.c           | 75 +++++++++++++++++++++++++++++++++++++++--
 8 files changed, 72 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 9a155063c25f..2c5fc9cc367d 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -436,16 +436,6 @@ struct xfrm_mode {
 	 */
 	int (*input2)(struct xfrm_state *x, struct sk_buff *skb);
 
-	/*
-	 * This is the actual input entry point.
-	 *
-	 * For transport mode and equivalent this would be identical to
-	 * input2 (which does not need to be set).  While tunnel mode
-	 * and equivalent would set this to the tunnel encapsulation function
-	 * xfrm4_prepare_input that would in turn call input2.
-	 */
-	int (*input)(struct xfrm_state *x, struct sk_buff *skb);
-
 	/*
 	 * Add encapsulation header.
 	 *
@@ -1606,7 +1596,6 @@ int xfrm_init_replay(struct xfrm_state *x);
 int xfrm_state_mtu(struct xfrm_state *x, int mtu);
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload);
 int xfrm_init_state(struct xfrm_state *x);
-int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);
 int xfrm_input_resume(struct sk_buff *skb, int nexthdr);
 int xfrm_trans_queue(struct sk_buff *skb,
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
index a2e3b52ae46c..264c4c9e2473 100644
--- a/net/ipv4/xfrm4_mode_beet.c
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -128,7 +128,6 @@ out:
 
 static struct xfrm_mode xfrm4_beet_mode = {
 	.input2 = xfrm4_beet_input,
-	.input = xfrm_prepare_input,
 	.output2 = xfrm4_beet_output,
 	.output = xfrm4_prepare_output,
 	.owner = THIS_MODULE,
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index 7c5443f797cf..c943d710f302 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -35,28 +35,6 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 }
 
-/* Remove encapsulation header.
- *
- * The IP header will be moved over the top of the encapsulation header.
- *
- * On entry, skb->h shall point to where the IP header should be and skb->nh
- * shall be set to where the IP header currently is.  skb->data shall point
- * to the start of the payload.
- */
-static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
-{
-	int ihl = skb->data - skb_transport_header(skb);
-
-	if (skb->transport_header != skb->network_header) {
-		memmove(skb_transport_header(skb),
-			skb_network_header(skb), ihl);
-		skb->network_header = skb->transport_header;
-	}
-	ip_hdr(skb)->tot_len = htons(skb->len + ihl);
-	skb_reset_transport_header(skb);
-	return 0;
-}
-
 static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
 						   struct sk_buff *skb,
 						   netdev_features_t features)
@@ -87,7 +65,6 @@ static void xfrm4_transport_xmit(struct xfrm_state *x, struct sk_buff *skb)
 }
 
 static struct xfrm_mode xfrm4_transport_mode = {
-	.input = xfrm4_transport_input,
 	.output = xfrm4_transport_output,
 	.gso_segment = xfrm4_transport_gso_segment,
 	.xmit = xfrm4_transport_xmit,
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index cfc6b6d39755..678b91754b5e 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -123,7 +123,6 @@ static void xfrm4_mode_tunnel_xmit(struct xfrm_state *x, struct sk_buff *skb)
 
 static struct xfrm_mode xfrm4_tunnel_mode = {
 	.input2 = xfrm4_mode_tunnel_input,
-	.input = xfrm_prepare_input,
 	.output2 = xfrm4_mode_tunnel_output,
 	.output = xfrm4_prepare_output,
 	.gso_segment = xfrm4_mode_tunnel_gso_segment,
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
index 0d440e3a13f8..eadacaddfcae 100644
--- a/net/ipv6/xfrm6_mode_beet.c
+++ b/net/ipv6/xfrm6_mode_beet.c
@@ -104,7 +104,6 @@ out:
 
 static struct xfrm_mode xfrm6_beet_mode = {
 	.input2 = xfrm6_beet_input,
-	.input = xfrm_prepare_input,
 	.output2 = xfrm6_beet_output,
 	.output = xfrm6_prepare_output,
 	.owner = THIS_MODULE,
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 66ae79218bdf..4c306bb99284 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -40,29 +40,6 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 }
 
-/* Remove encapsulation header.
- *
- * The IP header will be moved over the top of the encapsulation header.
- *
- * On entry, skb->h shall point to where the IP header should be and skb->nh
- * shall be set to where the IP header currently is.  skb->data shall point
- * to the start of the payload.
- */
-static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
-{
-	int ihl = skb->data - skb_transport_header(skb);
-
-	if (skb->transport_header != skb->network_header) {
-		memmove(skb_transport_header(skb),
-			skb_network_header(skb), ihl);
-		skb->network_header = skb->transport_header;
-	}
-	ipv6_hdr(skb)->payload_len = htons(skb->len + ihl -
-					   sizeof(struct ipv6hdr));
-	skb_reset_transport_header(skb);
-	return 0;
-}
-
 static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
 						   struct sk_buff *skb,
 						   netdev_features_t features)
@@ -92,9 +69,7 @@ static void xfrm6_transport_xmit(struct xfrm_state *x, struct sk_buff *skb)
 	}
 }
 
-
 static struct xfrm_mode xfrm6_transport_mode = {
-	.input = xfrm6_transport_input,
 	.output = xfrm6_transport_output,
 	.gso_segment = xfrm4_transport_gso_segment,
 	.xmit = xfrm6_transport_xmit,
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 6cf12e961ea5..1e9677fd6559 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -122,7 +122,6 @@ static void xfrm6_mode_tunnel_xmit(struct xfrm_state *x, struct sk_buff *skb)
 
 static struct xfrm_mode xfrm6_tunnel_mode = {
 	.input2 = xfrm6_mode_tunnel_input,
-	.input = xfrm_prepare_input,
 	.output2 = xfrm6_mode_tunnel_output,
 	.output = xfrm6_prepare_output,
 	.gso_segment = xfrm6_mode_tunnel_gso_segment,
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index ea5ac053c15d..0edf3fb73585 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -166,7 +166,7 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq)
 }
 EXPORT_SYMBOL(xfrm_parse_spi);
 
-int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
+static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct xfrm_mode *inner_mode = x->inner_mode;
 	int err;
@@ -184,7 +184,76 @@ int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
 	skb->protocol = inner_mode->afinfo->eth_proto;
 	return inner_mode->input2(x, skb);
 }
-EXPORT_SYMBOL(xfrm_prepare_input);
+
+/* Remove encapsulation header.
+ *
+ * The IP header will be moved over the top of the encapsulation header.
+ *
+ * On entry, skb_transport_header() shall point to where the IP header
+ * should be and skb_network_header() shall be set to where the IP header
+ * currently is.  skb->data shall point to the start of the payload.
+ */
+static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_INET_XFRM_MODE_TRANSPORT)
+	int ihl = skb->data - skb_transport_header(skb);
+
+	if (skb->transport_header != skb->network_header) {
+		memmove(skb_transport_header(skb),
+			skb_network_header(skb), ihl);
+		skb->network_header = skb->transport_header;
+	}
+	ip_hdr(skb)->tot_len = htons(skb->len + ihl);
+	skb_reset_transport_header(skb);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_INET6_XFRM_MODE_TRANSPORT)
+	int ihl = skb->data - skb_transport_header(skb);
+
+	if (skb->transport_header != skb->network_header) {
+		memmove(skb_transport_header(skb),
+			skb_network_header(skb), ihl);
+		skb->network_header = skb->transport_header;
+	}
+	ipv6_hdr(skb)->payload_len = htons(skb->len + ihl -
+					   sizeof(struct ipv6hdr));
+	skb_reset_transport_header(skb);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int xfrm_inner_mode_input(struct xfrm_state *x,
+				 const struct xfrm_mode *inner_mode,
+				 struct sk_buff *skb)
+{
+	switch (inner_mode->encap) {
+	case XFRM_MODE_BEET:
+	case XFRM_MODE_TUNNEL:
+		return xfrm_prepare_input(x, skb);
+	case XFRM_MODE_TRANSPORT:
+		if (inner_mode->family == AF_INET)
+			return xfrm4_transport_input(x, skb);
+		if (inner_mode->family == AF_INET6)
+			return xfrm6_transport_input(x, skb);
+		break;
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+		WARN_ON_ONCE(1);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
 
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 {
@@ -410,7 +479,7 @@ resume:
 			}
 		}
 
-		if (inner_mode->input(x, skb)) {
+		if (xfrm_inner_mode_input(x, inner_mode, skb)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR);
 			goto drop;
 		}
-- 
cgit v1.2.3


From 0c620e97b3490890facbbe06d5deed9b024de255 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Mar 2019 21:16:25 +0100
Subject: xfrm: remove output indirection from xfrm_mode

Same is input indirection.  Only exception: we need to export
xfrm_outer_mode_output for pktgen.

Increases size of vmlinux by about 163 byte:
Before:
   text    data     bss     dec      filename
15730208  6936948 4046908 26714064   vmlinux

After:
15730311  6937008 4046908 26714227   vmlinux

xfrm_inner_extract_output has no more external callers, make it static.

v2: add IS_ENABLED(IPV6) guard in xfrm6_prepare_output
    add two missing breaks in xfrm_outer_mode_output (Sabrina Dubroca)
    add WARN_ON_ONCE for 'call AF_INET6 related output function, but
    CONFIG_IPV6=n' case.
    make xfrm_inner_extract_output static

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h              |  19 ++---
 net/core/pktgen.c               |   2 +-
 net/ipv4/xfrm4_mode_beet.c      |   1 -
 net/ipv4/xfrm4_mode_transport.c |  22 ------
 net/ipv4/xfrm4_mode_tunnel.c    |   1 -
 net/ipv4/xfrm4_output.c         |  15 ----
 net/ipv6/xfrm6_mode_beet.c      |   1 -
 net/ipv6/xfrm6_mode_ro.c        |  28 -------
 net/ipv6/xfrm6_mode_transport.c |  26 -------
 net/ipv6/xfrm6_mode_tunnel.c    |   1 -
 net/ipv6/xfrm6_output.c         |  15 ----
 net/xfrm/xfrm_output.c          | 166 +++++++++++++++++++++++++++++++++++++++-
 12 files changed, 169 insertions(+), 128 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 2c5fc9cc367d..01e7e9c0e8a9 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -449,17 +449,6 @@ struct xfrm_mode {
 	 */
 	int (*output2)(struct xfrm_state *x,struct sk_buff *skb);
 
-	/*
-	 * This is the actual output entry point.
-	 *
-	 * For transport mode and equivalent this would be identical to
-	 * output2 (which does not need to be set).  While tunnel mode
-	 * and equivalent would set this to a tunnel encapsulation function
-	 * (xfrm4_prepare_output or xfrm6_prepare_output) that would in turn
-	 * call output2.
-	 */
-	int (*output)(struct xfrm_state *x, struct sk_buff *skb);
-
 	/*
 	 * Adjust pointers into the packet and do GSO segmentation.
 	 */
@@ -1603,7 +1592,11 @@ int xfrm_trans_queue(struct sk_buff *skb,
 				   struct sk_buff *));
 int xfrm_output_resume(struct sk_buff *skb, int err);
 int xfrm_output(struct sock *sk, struct sk_buff *skb);
-int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
+
+#if IS_ENABLED(CONFIG_NET_PKTGEN)
+int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb);
+#endif
+
 void xfrm_local_error(struct sk_buff *skb, int mtu);
 int xfrm4_extract_header(struct sk_buff *skb);
 int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb);
@@ -1622,7 +1615,6 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
 }
 
 int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb);
-int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb);
 int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err);
@@ -1649,7 +1641,6 @@ int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family)
 __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr);
 __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr);
 int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb);
-int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb);
 int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f3f5a78cd062..319ad5490fb3 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2521,7 +2521,7 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev)
 		skb->_skb_refdst = (unsigned long)&pkt_dev->xdst.u.dst | SKB_DST_NOREF;
 
 	rcu_read_lock_bh();
-	err = x->outer_mode->output(x, skb);
+	err = pktgen_xfrm_outer_mode_output(x, skb);
 	rcu_read_unlock_bh();
 	if (err) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
index 264c4c9e2473..f02cc8237d54 100644
--- a/net/ipv4/xfrm4_mode_beet.c
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -129,7 +129,6 @@ out:
 static struct xfrm_mode xfrm4_beet_mode = {
 	.input2 = xfrm4_beet_input,
 	.output2 = xfrm4_beet_output,
-	.output = xfrm4_prepare_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_BEET,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index c943d710f302..6f8cf09ff0ef 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -14,27 +14,6 @@
 #include <net/xfrm.h>
 #include <net/protocol.h>
 
-/* Add encapsulation header.
- *
- * The IP header will be moved forward to make space for the encapsulation
- * header.
- */
-static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct iphdr *iph = ip_hdr(skb);
-	int ihl = iph->ihl * 4;
-
-	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
-
-	skb_set_network_header(skb, -x->props.header_len);
-	skb->mac_header = skb->network_header +
-			  offsetof(struct iphdr, protocol);
-	skb->transport_header = skb->network_header + ihl;
-	__skb_pull(skb, ihl);
-	memmove(skb_network_header(skb), iph, ihl);
-	return 0;
-}
-
 static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
 						   struct sk_buff *skb,
 						   netdev_features_t features)
@@ -65,7 +44,6 @@ static void xfrm4_transport_xmit(struct xfrm_state *x, struct sk_buff *skb)
 }
 
 static struct xfrm_mode xfrm4_transport_mode = {
-	.output = xfrm4_transport_output,
 	.gso_segment = xfrm4_transport_gso_segment,
 	.xmit = xfrm4_transport_xmit,
 	.owner = THIS_MODULE,
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 678b91754b5e..823bc54b47de 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -124,7 +124,6 @@ static void xfrm4_mode_tunnel_xmit(struct xfrm_state *x, struct sk_buff *skb)
 static struct xfrm_mode xfrm4_tunnel_mode = {
 	.input2 = xfrm4_mode_tunnel_input,
 	.output2 = xfrm4_mode_tunnel_output,
-	.output = xfrm4_prepare_output,
 	.gso_segment = xfrm4_mode_tunnel_gso_segment,
 	.xmit = xfrm4_mode_tunnel_xmit,
 	.owner = THIS_MODULE,
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index be980c195fc5..6802d1aee424 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -58,21 +58,6 @@ int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 	return xfrm4_extract_header(skb);
 }
 
-int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
-{
-	int err;
-
-	err = xfrm_inner_extract_output(x, skb);
-	if (err)
-		return err;
-
-	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
-	skb->protocol = htons(ETH_P_IP);
-
-	return x->outer_mode->output2(x, skb);
-}
-EXPORT_SYMBOL(xfrm4_prepare_output);
-
 int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
index eadacaddfcae..6f35e24f0077 100644
--- a/net/ipv6/xfrm6_mode_beet.c
+++ b/net/ipv6/xfrm6_mode_beet.c
@@ -105,7 +105,6 @@ out:
 static struct xfrm_mode xfrm6_beet_mode = {
 	.input2 = xfrm6_beet_input,
 	.output2 = xfrm6_beet_output,
-	.output = xfrm6_prepare_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_BEET,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c
index 0408547d01ab..d0a6a4dbd689 100644
--- a/net/ipv6/xfrm6_mode_ro.c
+++ b/net/ipv6/xfrm6_mode_ro.c
@@ -33,35 +33,7 @@
 #include <net/ipv6.h>
 #include <net/xfrm.h>
 
-/* Add route optimization header space.
- *
- * The IP header and mutable extension headers will be moved forward to make
- * space for the route optimization header.
- */
-static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct ipv6hdr *iph;
-	u8 *prevhdr;
-	int hdr_len;
-
-	iph = ipv6_hdr(skb);
-
-	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
-	if (hdr_len < 0)
-		return hdr_len;
-	skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
-	skb_set_network_header(skb, -x->props.header_len);
-	skb->transport_header = skb->network_header + hdr_len;
-	__skb_pull(skb, hdr_len);
-	memmove(ipv6_hdr(skb), iph, hdr_len);
-
-	x->lastused = ktime_get_real_seconds();
-
-	return 0;
-}
-
 static struct xfrm_mode xfrm6_ro_mode = {
-	.output = xfrm6_ro_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_ROUTEOPTIMIZATION,
 	.family = AF_INET6,
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 4c306bb99284..1e7165a8481a 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -15,31 +15,6 @@
 #include <net/xfrm.h>
 #include <net/protocol.h>
 
-/* Add encapsulation header.
- *
- * The IP header and mutable extension headers will be moved forward to make
- * space for the encapsulation header.
- */
-static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct ipv6hdr *iph;
-	u8 *prevhdr;
-	int hdr_len;
-
-	iph = ipv6_hdr(skb);
-	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
-
-	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
-	if (hdr_len < 0)
-		return hdr_len;
-	skb_set_mac_header(skb, (prevhdr - x->props.header_len) - skb->data);
-	skb_set_network_header(skb, -x->props.header_len);
-	skb->transport_header = skb->network_header + hdr_len;
-	__skb_pull(skb, hdr_len);
-	memmove(ipv6_hdr(skb), iph, hdr_len);
-	return 0;
-}
-
 static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
 						   struct sk_buff *skb,
 						   netdev_features_t features)
@@ -70,7 +45,6 @@ static void xfrm6_transport_xmit(struct xfrm_state *x, struct sk_buff *skb)
 }
 
 static struct xfrm_mode xfrm6_transport_mode = {
-	.output = xfrm6_transport_output,
 	.gso_segment = xfrm4_transport_gso_segment,
 	.xmit = xfrm6_transport_xmit,
 	.owner = THIS_MODULE,
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 1e9677fd6559..e1a129524dde 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -123,7 +123,6 @@ static void xfrm6_mode_tunnel_xmit(struct xfrm_state *x, struct sk_buff *skb)
 static struct xfrm_mode xfrm6_tunnel_mode = {
 	.input2 = xfrm6_mode_tunnel_input,
 	.output2 = xfrm6_mode_tunnel_output,
-	.output = xfrm6_prepare_output,
 	.gso_segment = xfrm6_mode_tunnel_gso_segment,
 	.xmit = xfrm6_mode_tunnel_xmit,
 	.owner = THIS_MODULE,
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 6a74080005cf..2b663d2ffdcd 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -111,21 +111,6 @@ int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 	return xfrm6_extract_header(skb);
 }
 
-int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
-{
-	int err;
-
-	err = xfrm_inner_extract_output(x, skb);
-	if (err)
-		return err;
-
-	skb->ignore_df = 1;
-	skb->protocol = htons(ETH_P_IPV6);
-
-	return x->outer_mode->output2(x, skb);
-}
-EXPORT_SYMBOL(xfrm6_prepare_output);
-
 int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb)
 {
 	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 9333153bafda..05926dcf5d17 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -20,6 +20,7 @@
 #include <net/xfrm.h>
 
 static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb);
+static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
 
 static int xfrm_skb_check_space(struct sk_buff *skb)
 {
@@ -50,6 +51,166 @@ static struct dst_entry *skb_dst_pop(struct sk_buff *skb)
 	return child;
 }
 
+/* Add encapsulation header.
+ *
+ * The IP header will be moved forward to make space for the encapsulation
+ * header.
+ */
+static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_INET_XFRM_MODE_TRANSPORT)
+	struct iphdr *iph = ip_hdr(skb);
+	int ihl = iph->ihl * 4;
+
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+	skb_set_network_header(skb, -x->props.header_len);
+	skb->mac_header = skb->network_header +
+			  offsetof(struct iphdr, protocol);
+	skb->transport_header = skb->network_header + ihl;
+	__skb_pull(skb, ihl);
+	memmove(skb_network_header(skb), iph, ihl);
+	return 0;
+#else
+	WARN_ON_ONCE(1);
+	return -EOPNOTSUPP;
+#endif
+}
+
+/* Add encapsulation header.
+ *
+ * The IP header and mutable extension headers will be moved forward to make
+ * space for the encapsulation header.
+ */
+static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_INET6_XFRM_MODE_TRANSPORT)
+	struct ipv6hdr *iph;
+	u8 *prevhdr;
+	int hdr_len;
+
+	iph = ipv6_hdr(skb);
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+	if (hdr_len < 0)
+		return hdr_len;
+	skb_set_mac_header(skb,
+			   (prevhdr - x->props.header_len) - skb->data);
+	skb_set_network_header(skb, -x->props.header_len);
+	skb->transport_header = skb->network_header + hdr_len;
+	__skb_pull(skb, hdr_len);
+	memmove(ipv6_hdr(skb), iph, hdr_len);
+	return 0;
+#else
+	WARN_ON_ONCE(1);
+	return -EOPNOTSUPP;
+#endif
+}
+
+/* Add route optimization header space.
+ *
+ * The IP header and mutable extension headers will be moved forward to make
+ * space for the route optimization header.
+ */
+static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION)
+	struct ipv6hdr *iph;
+	u8 *prevhdr;
+	int hdr_len;
+
+	iph = ipv6_hdr(skb);
+
+	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+	if (hdr_len < 0)
+		return hdr_len;
+	skb_set_mac_header(skb,
+			   (prevhdr - x->props.header_len) - skb->data);
+	skb_set_network_header(skb, -x->props.header_len);
+	skb->transport_header = skb->network_header + hdr_len;
+	__skb_pull(skb, hdr_len);
+	memmove(ipv6_hdr(skb), iph, hdr_len);
+
+	x->lastused = ktime_get_real_seconds();
+
+	return 0;
+#else
+	WARN_ON_ONCE(1);
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err;
+
+	err = xfrm_inner_extract_output(x, skb);
+	if (err)
+		return err;
+
+	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
+	skb->protocol = htons(ETH_P_IP);
+
+	return x->outer_mode->output2(x, skb);
+}
+
+static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	int err;
+
+	err = xfrm_inner_extract_output(x, skb);
+	if (err)
+		return err;
+
+	skb->ignore_df = 1;
+	skb->protocol = htons(ETH_P_IPV6);
+
+	return x->outer_mode->output2(x, skb);
+#else
+	WARN_ON_ONCE(1);
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	switch (x->outer_mode->encap) {
+	case XFRM_MODE_BEET:
+	case XFRM_MODE_TUNNEL:
+		if (x->outer_mode->family == AF_INET)
+			return xfrm4_prepare_output(x, skb);
+		if (x->outer_mode->family == AF_INET6)
+			return xfrm6_prepare_output(x, skb);
+		break;
+	case XFRM_MODE_TRANSPORT:
+		if (x->outer_mode->family == AF_INET)
+			return xfrm4_transport_output(x, skb);
+		if (x->outer_mode->family == AF_INET6)
+			return xfrm6_transport_output(x, skb);
+		break;
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+		if (x->outer_mode->family == AF_INET6)
+			return xfrm6_ro_output(x, skb);
+		WARN_ON_ONCE(1);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+#if IS_ENABLED(CONFIG_NET_PKTGEN)
+int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
+{
+	return xfrm_outer_mode_output(x, skb);
+}
+EXPORT_SYMBOL_GPL(pktgen_xfrm_outer_mode_output);
+#endif
+
 static int xfrm_output_one(struct sk_buff *skb, int err)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -68,7 +229,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 
 		skb->mark = xfrm_smark_get(skb->mark, x);
 
-		err = x->outer_mode->output(x, skb);
+		err = xfrm_outer_mode_output(x, skb);
 		if (err) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
 			goto error_nolock;
@@ -258,7 +419,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(xfrm_output);
 
-int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
+static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct xfrm_mode *inner_mode;
 	if (x->sel.family == AF_UNSPEC)
@@ -271,7 +432,6 @@ int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 		return -EAFNOSUPPORT;
 	return inner_mode->afinfo->extract_output(x, skb);
 }
-EXPORT_SYMBOL_GPL(xfrm_inner_extract_output);
 
 void xfrm_local_error(struct sk_buff *skb, int mtu)
 {
-- 
cgit v1.2.3


From 303c5fab1272888b22088fbdd08cb770205ccb7a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Mar 2019 21:16:26 +0100
Subject: xfrm: remove xmit indirection from xfrm_mode

There are only two versions (tunnel and transport). The ip/ipv6 versions
are only differ in sizeof(iphdr) vs ipv6hdr.

Place this in the core and use x->outer_mode->encap type to call the
correct adjustment helper.

Before:
   text   data    bss     dec      filename
15730311  6937008 4046908 26714227 vmlinux

After:
15730428  6937008 4046908 26714344 vmlinux

(about 117 byte increase)

v2: use family from x->outer_mode, not inner

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h              |  5 ----
 net/ipv4/xfrm4_mode_transport.c | 14 ----------
 net/ipv4/xfrm4_mode_tunnel.c    | 13 ---------
 net/ipv6/xfrm6_mode_transport.c | 14 ----------
 net/ipv6/xfrm6_mode_tunnel.c    | 12 ---------
 net/xfrm/xfrm_device.c          | 58 +++++++++++++++++++++++++++++++++++++++--
 6 files changed, 56 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 01e7e9c0e8a9..07966a27e4a4 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -454,11 +454,6 @@ struct xfrm_mode {
 	 */
 	struct sk_buff *(*gso_segment)(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features);
 
-	/*
-	 * Adjust pointers into the packet when IPsec is done at layer2.
-	 */
-	void (*xmit)(struct xfrm_state *x, struct sk_buff *skb);
-
 	struct xfrm_state_afinfo *afinfo;
 	struct module *owner;
 	u8 encap;
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index 6f8cf09ff0ef..d4b34bb2de00 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -30,22 +30,8 @@ static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
 	return segs;
 }
 
-static void xfrm4_transport_xmit(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct xfrm_offload *xo = xfrm_offload(skb);
-
-	skb_reset_mac_len(skb);
-	pskb_pull(skb, skb->mac_len + sizeof(struct iphdr) + x->props.header_len);
-
-	if (xo->flags & XFRM_GSO_SEGMENT) {
-		 skb_reset_transport_header(skb);
-		 skb->transport_header -= x->props.header_len;
-	}
-}
-
 static struct xfrm_mode xfrm4_transport_mode = {
 	.gso_segment = xfrm4_transport_gso_segment,
-	.xmit = xfrm4_transport_xmit,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TRANSPORT,
 	.family = AF_INET,
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 823bc54b47de..8bd5112b3ee3 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -109,23 +109,10 @@ static struct sk_buff *xfrm4_mode_tunnel_gso_segment(struct xfrm_state *x,
 	return skb_mac_gso_segment(skb, features);
 }
 
-static void xfrm4_mode_tunnel_xmit(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct xfrm_offload *xo = xfrm_offload(skb);
-
-	if (xo->flags & XFRM_GSO_SEGMENT)
-		skb->transport_header = skb->network_header +
-					sizeof(struct iphdr);
-
-	skb_reset_mac_len(skb);
-	pskb_pull(skb, skb->mac_len + x->props.header_len);
-}
-
 static struct xfrm_mode xfrm4_tunnel_mode = {
 	.input2 = xfrm4_mode_tunnel_input,
 	.output2 = xfrm4_mode_tunnel_output,
 	.gso_segment = xfrm4_mode_tunnel_gso_segment,
-	.xmit = xfrm4_mode_tunnel_xmit,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 1e7165a8481a..6a72ff39bc05 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -31,22 +31,8 @@ static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
 	return segs;
 }
 
-static void xfrm6_transport_xmit(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct xfrm_offload *xo = xfrm_offload(skb);
-
-	skb_reset_mac_len(skb);
-	pskb_pull(skb, skb->mac_len + sizeof(struct ipv6hdr) + x->props.header_len);
-
-	if (xo->flags & XFRM_GSO_SEGMENT) {
-		 skb_reset_transport_header(skb);
-		 skb->transport_header -= x->props.header_len;
-	}
-}
-
 static struct xfrm_mode xfrm6_transport_mode = {
 	.gso_segment = xfrm4_transport_gso_segment,
-	.xmit = xfrm6_transport_xmit,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TRANSPORT,
 	.family = AF_INET6,
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index e1a129524dde..7450dd87f27d 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -109,22 +109,10 @@ static struct sk_buff *xfrm6_mode_tunnel_gso_segment(struct xfrm_state *x,
 	return skb_mac_gso_segment(skb, features);
 }
 
-static void xfrm6_mode_tunnel_xmit(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct xfrm_offload *xo = xfrm_offload(skb);
-
-	if (xo->flags & XFRM_GSO_SEGMENT)
-		skb->transport_header = skb->network_header + sizeof(struct ipv6hdr);
-
-	skb_reset_mac_len(skb);
-	pskb_pull(skb, skb->mac_len + x->props.header_len);
-}
-
 static struct xfrm_mode xfrm6_tunnel_mode = {
 	.input2 = xfrm6_mode_tunnel_input,
 	.output2 = xfrm6_mode_tunnel_output,
 	.gso_segment = xfrm6_mode_tunnel_gso_segment,
-	.xmit = xfrm6_mode_tunnel_xmit,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index e437b60fba51..a20f376fe71f 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -23,6 +23,60 @@
 #include <linux/notifier.h>
 
 #ifdef CONFIG_XFRM_OFFLOAD
+static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb,
+				  unsigned int hsize)
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	skb_reset_mac_len(skb);
+	pskb_pull(skb, skb->mac_len + hsize + x->props.header_len);
+
+	if (xo->flags & XFRM_GSO_SEGMENT) {
+		skb_reset_transport_header(skb);
+		skb->transport_header -= x->props.header_len;
+	}
+}
+
+static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
+				    unsigned int hsize)
+
+{
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	if (xo->flags & XFRM_GSO_SEGMENT)
+		skb->transport_header = skb->network_header + hsize;
+
+	skb_reset_mac_len(skb);
+	pskb_pull(skb, skb->mac_len + x->props.header_len);
+}
+
+/* Adjust pointers into the packet when IPsec is done at layer2 */
+static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb)
+{
+	switch (x->outer_mode->encap) {
+	case XFRM_MODE_TUNNEL:
+		if (x->outer_mode->family == AF_INET)
+			return __xfrm_mode_tunnel_prep(x, skb,
+						       sizeof(struct iphdr));
+		if (x->outer_mode->family == AF_INET6)
+			return __xfrm_mode_tunnel_prep(x, skb,
+						       sizeof(struct ipv6hdr));
+		break;
+	case XFRM_MODE_TRANSPORT:
+		if (x->outer_mode->family == AF_INET)
+			return __xfrm_transport_prep(x, skb,
+						     sizeof(struct iphdr));
+		if (x->outer_mode->family == AF_INET6)
+			return __xfrm_transport_prep(x, skb,
+						     sizeof(struct ipv6hdr));
+		break;
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+	case XFRM_MODE_IN_TRIGGER:
+	case XFRM_MODE_BEET:
+		break;
+	}
+}
+
 struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again)
 {
 	int err;
@@ -79,7 +133,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 
 	if (!skb->next) {
 		esp_features |= skb->dev->gso_partial_features;
-		x->outer_mode->xmit(x, skb);
+		xfrm_outer_mode_prep(x, skb);
 
 		xo->flags |= XFRM_DEV_RESUME;
 
@@ -109,7 +163,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 		xo = xfrm_offload(skb2);
 		xo->flags |= XFRM_DEV_RESUME;
 
-		x->outer_mode->xmit(x, skb2);
+		xfrm_outer_mode_prep(x, skb2);
 
 		err = x->type_offload->xmit(x, skb2, esp_features);
 		if (!err) {
-- 
cgit v1.2.3


From 7613b92b1ae37141704948b77e8762c5de896510 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Mar 2019 21:16:27 +0100
Subject: xfrm: remove gso_segment indirection from xfrm_mode

These functions are small and we only have versions for tunnel
and transport mode for ipv4 and ipv6 respectively.

Just place the 'transport or tunnel' conditional in the protocol
specific function instead of using an indirection.

Before:
    3226       12       0     3238   net/ipv4/esp4_offload.o
    7004      492       0     7496   net/ipv4/ip_vti.o
    3339       12       0     3351   net/ipv6/esp6_offload.o
   11294      460       0    11754   net/ipv6/ip6_vti.o
    1180       72       0     1252   net/ipv4/xfrm4_mode_beet.o
     428       48       0      476   net/ipv4/xfrm4_mode_transport.o
    1271       48       0     1319   net/ipv4/xfrm4_mode_tunnel.o
    1083       60       0     1143   net/ipv6/xfrm6_mode_beet.o
     172       48       0      220   net/ipv6/xfrm6_mode_ro.o
     429       48       0      477   net/ipv6/xfrm6_mode_transport.o
    1164       48       0     1212   net/ipv6/xfrm6_mode_tunnel.o
15730428  6937008 4046908 26714344   vmlinux

After:
    3461       12       0     3473   net/ipv4/esp4_offload.o
    7000      492       0     7492   net/ipv4/ip_vti.o
    3574       12       0     3586   net/ipv6/esp6_offload.o
   11295      460       0    11755   net/ipv6/ip6_vti.o
    1180       64       0     1244   net/ipv4/xfrm4_mode_beet.o
     171       40       0      211   net/ipv4/xfrm4_mode_transport.o
    1163       40       0     1203   net/ipv4/xfrm4_mode_tunnel.o
    1083       52       0     1135   net/ipv6/xfrm6_mode_beet.o
     172       40       0      212   net/ipv6/xfrm6_mode_ro.o
     172       40       0      212   net/ipv6/xfrm6_mode_transport.o
    1056       40       0     1096   net/ipv6/xfrm6_mode_tunnel.o
15730424  6937008 4046908 26714340   vmlinux

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h              |  5 -----
 net/ipv4/esp4_offload.c         | 40 +++++++++++++++++++++++++++++++++++++++-
 net/ipv4/xfrm4_mode_transport.c | 17 -----------------
 net/ipv4/xfrm4_mode_tunnel.c    |  9 ---------
 net/ipv6/esp6_offload.c         | 40 +++++++++++++++++++++++++++++++++++++++-
 net/ipv6/xfrm6_mode_transport.c | 17 -----------------
 net/ipv6/xfrm6_mode_tunnel.c    |  8 --------
 7 files changed, 78 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 07966a27e4a4..de103a6d1ef8 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -449,11 +449,6 @@ struct xfrm_mode {
 	 */
 	int (*output2)(struct xfrm_state *x,struct sk_buff *skb);
 
-	/*
-	 * Adjust pointers into the packet and do GSO segmentation.
-	 */
-	struct sk_buff *(*gso_segment)(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features);
-
 	struct xfrm_state_afinfo *afinfo;
 	struct module *owner;
 	u8 encap;
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index c6c84f2bc41c..74d59e0177a7 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -107,6 +107,44 @@ static void esp4_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
 	xo->proto = proto;
 }
 
+static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x,
+						struct sk_buff *skb,
+						netdev_features_t features)
+{
+	__skb_push(skb, skb->mac_len);
+	return skb_mac_gso_segment(skb, features);
+}
+
+static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
+						   struct sk_buff *skb,
+						   netdev_features_t features)
+{
+	const struct net_offload *ops;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	skb->transport_header += x->props.header_len;
+	ops = rcu_dereference(inet_offloads[xo->proto]);
+	if (likely(ops && ops->callbacks.gso_segment))
+		segs = ops->callbacks.gso_segment(skb, features);
+
+	return segs;
+}
+
+static struct sk_buff *xfrm4_outer_mode_gso_segment(struct xfrm_state *x,
+						    struct sk_buff *skb,
+						    netdev_features_t features)
+{
+	switch (x->outer_mode->encap) {
+	case XFRM_MODE_TUNNEL:
+		return xfrm4_tunnel_gso_segment(x, skb, features);
+	case XFRM_MODE_TRANSPORT:
+		return xfrm4_transport_gso_segment(x, skb, features);
+	}
+
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
 				        netdev_features_t features)
 {
@@ -147,7 +185,7 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
 
 	xo->flags |= XFRM_GSO_SEGMENT;
 
-	return x->outer_mode->gso_segment(x, skb, esp_features);
+	return xfrm4_outer_mode_gso_segment(x, skb, esp_features);
 }
 
 static int esp_input_tail(struct xfrm_state *x, struct sk_buff *skb)
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index d4b34bb2de00..397863ea762b 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -14,24 +14,7 @@
 #include <net/xfrm.h>
 #include <net/protocol.h>
 
-static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
-						   struct sk_buff *skb,
-						   netdev_features_t features)
-{
-	const struct net_offload *ops;
-	struct sk_buff *segs = ERR_PTR(-EINVAL);
-	struct xfrm_offload *xo = xfrm_offload(skb);
-
-	skb->transport_header += x->props.header_len;
-	ops = rcu_dereference(inet_offloads[xo->proto]);
-	if (likely(ops && ops->callbacks.gso_segment))
-		segs = ops->callbacks.gso_segment(skb, features);
-
-	return segs;
-}
-
 static struct xfrm_mode xfrm4_transport_mode = {
-	.gso_segment = xfrm4_transport_gso_segment,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TRANSPORT,
 	.family = AF_INET,
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 8bd5112b3ee3..b5d4ba41758e 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -101,18 +101,9 @@ out:
 	return err;
 }
 
-static struct sk_buff *xfrm4_mode_tunnel_gso_segment(struct xfrm_state *x,
-						     struct sk_buff *skb,
-						     netdev_features_t features)
-{
-	__skb_push(skb, skb->mac_len);
-	return skb_mac_gso_segment(skb, features);
-}
-
 static struct xfrm_mode xfrm4_tunnel_mode = {
 	.input2 = xfrm4_mode_tunnel_input,
 	.output2 = xfrm4_mode_tunnel_output,
-	.gso_segment = xfrm4_mode_tunnel_gso_segment,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index d46b4eb645c2..c793a2ace77d 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -134,6 +134,44 @@ static void esp6_gso_encap(struct xfrm_state *x, struct sk_buff *skb)
 	xo->proto = proto;
 }
 
+static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x,
+						struct sk_buff *skb,
+						netdev_features_t features)
+{
+	__skb_push(skb, skb->mac_len);
+	return skb_mac_gso_segment(skb, features);
+}
+
+static struct sk_buff *xfrm6_transport_gso_segment(struct xfrm_state *x,
+						   struct sk_buff *skb,
+						   netdev_features_t features)
+{
+	const struct net_offload *ops;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct xfrm_offload *xo = xfrm_offload(skb);
+
+	skb->transport_header += x->props.header_len;
+	ops = rcu_dereference(inet6_offloads[xo->proto]);
+	if (likely(ops && ops->callbacks.gso_segment))
+		segs = ops->callbacks.gso_segment(skb, features);
+
+	return segs;
+}
+
+static struct sk_buff *xfrm6_outer_mode_gso_segment(struct xfrm_state *x,
+						    struct sk_buff *skb,
+						    netdev_features_t features)
+{
+	switch (x->outer_mode->encap) {
+	case XFRM_MODE_TUNNEL:
+		return xfrm6_tunnel_gso_segment(x, skb, features);
+	case XFRM_MODE_TRANSPORT:
+		return xfrm6_transport_gso_segment(x, skb, features);
+	}
+
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static struct sk_buff *esp6_gso_segment(struct sk_buff *skb,
 				        netdev_features_t features)
 {
@@ -172,7 +210,7 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb,
 
 	xo->flags |= XFRM_GSO_SEGMENT;
 
-	return x->outer_mode->gso_segment(x, skb, esp_features);
+	return xfrm6_outer_mode_gso_segment(x, skb, esp_features);
 }
 
 static int esp6_input_tail(struct xfrm_state *x, struct sk_buff *skb)
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 6a72ff39bc05..d90c934c2f1a 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -15,24 +15,7 @@
 #include <net/xfrm.h>
 #include <net/protocol.h>
 
-static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x,
-						   struct sk_buff *skb,
-						   netdev_features_t features)
-{
-	const struct net_offload *ops;
-	struct sk_buff *segs = ERR_PTR(-EINVAL);
-	struct xfrm_offload *xo = xfrm_offload(skb);
-
-	skb->transport_header += x->props.header_len;
-	ops = rcu_dereference(inet6_offloads[xo->proto]);
-	if (likely(ops && ops->callbacks.gso_segment))
-		segs = ops->callbacks.gso_segment(skb, features);
-
-	return segs;
-}
-
 static struct xfrm_mode xfrm6_transport_mode = {
-	.gso_segment = xfrm4_transport_gso_segment,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TRANSPORT,
 	.family = AF_INET6,
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 7450dd87f27d..8e23a2fba617 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -101,18 +101,10 @@ out:
 	return err;
 }
 
-static struct sk_buff *xfrm6_mode_tunnel_gso_segment(struct xfrm_state *x,
-						     struct sk_buff *skb,
-						     netdev_features_t features)
-{
-	__skb_push(skb, skb->mac_len);
-	return skb_mac_gso_segment(skb, features);
-}
 
 static struct xfrm_mode xfrm6_tunnel_mode = {
 	.input2 = xfrm6_mode_tunnel_input,
 	.output2 = xfrm6_mode_tunnel_output,
-	.gso_segment = xfrm6_mode_tunnel_gso_segment,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
-- 
cgit v1.2.3


From b3284df1c86f7ac078dcb8fb250fe3d6437e740c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Mar 2019 21:16:28 +0100
Subject: xfrm: remove input2 indirection from xfrm_mode

No external dependencies on any module, place this in the core.
Increase is about 1800 byte for xfrm_input.o.

The beet helpers get added to internal header, as they can be reused
from xfrm_output.c in the next patch (kernel contains several
copies of them in the xfrm{4,6}_mode_beet.c files).

Before:
   text    data     bss     dec filename
   5578     176    2364    8118 net/xfrm/xfrm_input.o
   1180      64       0    1244 net/ipv4/xfrm4_mode_beet.o
    171      40       0     211 net/ipv4/xfrm4_mode_transport.o
   1163      40       0    1203 net/ipv4/xfrm4_mode_tunnel.o
   1083      52       0    1135 net/ipv6/xfrm6_mode_beet.o
    172      40       0     212 net/ipv6/xfrm6_mode_ro.o
    172      40       0     212 net/ipv6/xfrm6_mode_transport.o
   1056      40       0    1096 net/ipv6/xfrm6_mode_tunnel.o

After:
   text    data     bss     dec filename
   7373     200    2364    9937 net/xfrm/xfrm_input.o
    587      44       0     631 net/ipv4/xfrm4_mode_beet.o
    171      32       0     203 net/ipv4/xfrm4_mode_transport.o
    649      32       0     681 net/ipv4/xfrm4_mode_tunnel.o
    625      44       0     669 net/ipv6/xfrm6_mode_beet.o
    172      32       0     204 net/ipv6/xfrm6_mode_ro.o
    172      32       0     204 net/ipv6/xfrm6_mode_transport.o
    599      32       0     631 net/ipv6/xfrm6_mode_tunnel.o

v2: pass inner_mode to xfrm_inner_mode_encap_remove to fix
    AF_UNSPEC selector breakage (bisected by Benedict Wong)

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h           |  13 ---
 net/ipv4/xfrm4_mode_beet.c   |  47 -----------
 net/ipv4/xfrm4_mode_tunnel.c |  39 ---------
 net/ipv6/xfrm6_mode_beet.c   |  27 -------
 net/ipv6/xfrm6_mode_tunnel.c |  46 -----------
 net/xfrm/xfrm_inout.h        |  38 +++++++++
 net/xfrm/xfrm_input.c        | 185 ++++++++++++++++++++++++++++++++++++++++++-
 7 files changed, 222 insertions(+), 173 deletions(-)
 create mode 100644 net/xfrm/xfrm_inout.h

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index de103a6d1ef8..bdda545cf740 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -423,19 +423,6 @@ int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned sh
 int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 
 struct xfrm_mode {
-	/*
-	 * Remove encapsulation header.
-	 *
-	 * The IP header will be moved over the top of the encapsulation
-	 * header.
-	 *
-	 * On entry, the transport header shall point to where the IP header
-	 * should be and the network header shall be set to where the IP
-	 * header currently is.  skb->data shall point to the start of the
-	 * payload.
-	 */
-	int (*input2)(struct xfrm_state *x, struct sk_buff *skb);
-
 	/*
 	 * Add encapsulation header.
 	 *
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
index f02cc8237d54..500960172933 100644
--- a/net/ipv4/xfrm4_mode_beet.c
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -80,54 +80,7 @@ static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 }
 
-static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct iphdr *iph;
-	int optlen = 0;
-	int err = -EINVAL;
-
-	if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) {
-		struct ip_beet_phdr *ph;
-		int phlen;
-
-		if (!pskb_may_pull(skb, sizeof(*ph)))
-			goto out;
-
-		ph = (struct ip_beet_phdr *)skb->data;
-
-		phlen = sizeof(*ph) + ph->padlen;
-		optlen = ph->hdrlen * 8 + (IPV4_BEET_PHMAXLEN - phlen);
-		if (optlen < 0 || optlen & 3 || optlen > 250)
-			goto out;
-
-		XFRM_MODE_SKB_CB(skb)->protocol = ph->nexthdr;
-
-		if (!pskb_may_pull(skb, phlen))
-			goto out;
-		__skb_pull(skb, phlen);
-	}
-
-	skb_push(skb, sizeof(*iph));
-	skb_reset_network_header(skb);
-	skb_mac_header_rebuild(skb);
-
-	xfrm4_beet_make_header(skb);
-
-	iph = ip_hdr(skb);
-
-	iph->ihl += optlen / 4;
-	iph->tot_len = htons(skb->len);
-	iph->daddr = x->sel.daddr.a4;
-	iph->saddr = x->sel.saddr.a4;
-	iph->check = 0;
-	iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
-	err = 0;
-out:
-	return err;
-}
-
 static struct xfrm_mode xfrm4_beet_mode = {
-	.input2 = xfrm4_beet_input,
 	.output2 = xfrm4_beet_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_BEET,
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index b5d4ba41758e..31645319aaeb 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -15,14 +15,6 @@
 #include <net/ip.h>
 #include <net/xfrm.h>
 
-static inline void ipip_ecn_decapsulate(struct sk_buff *skb)
-{
-	struct iphdr *inner_iph = ipip_hdr(skb);
-
-	if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
-		IP_ECN_set_ce(inner_iph);
-}
-
 /* Add encapsulation header.
  *
  * The top IP header will be constructed per RFC 2401.
@@ -71,38 +63,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 }
 
-static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
-{
-	int err = -EINVAL;
-
-	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
-		goto out;
-
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		goto out;
-
-	err = skb_unclone(skb, GFP_ATOMIC);
-	if (err)
-		goto out;
-
-	if (x->props.flags & XFRM_STATE_DECAP_DSCP)
-		ipv4_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipip_hdr(skb));
-	if (!(x->props.flags & XFRM_STATE_NOECN))
-		ipip_ecn_decapsulate(skb);
-
-	skb_reset_network_header(skb);
-	skb_mac_header_rebuild(skb);
-	if (skb->mac_len)
-		eth_hdr(skb)->h_proto = skb->protocol;
-
-	err = 0;
-
-out:
-	return err;
-}
-
 static struct xfrm_mode xfrm4_tunnel_mode = {
-	.input2 = xfrm4_mode_tunnel_input,
 	.output2 = xfrm4_mode_tunnel_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
index 6f35e24f0077..a0537b4f62f8 100644
--- a/net/ipv6/xfrm6_mode_beet.c
+++ b/net/ipv6/xfrm6_mode_beet.c
@@ -76,34 +76,7 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb)
 	top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
 	return 0;
 }
-
-static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct ipv6hdr *ip6h;
-	int size = sizeof(struct ipv6hdr);
-	int err;
-
-	err = skb_cow_head(skb, size + skb->mac_len);
-	if (err)
-		goto out;
-
-	__skb_push(skb, size);
-	skb_reset_network_header(skb);
-	skb_mac_header_rebuild(skb);
-
-	xfrm6_beet_make_header(skb);
-
-	ip6h = ipv6_hdr(skb);
-	ip6h->payload_len = htons(skb->len - size);
-	ip6h->daddr = x->sel.daddr.in6;
-	ip6h->saddr = x->sel.saddr.in6;
-	err = 0;
-out:
-	return err;
-}
-
 static struct xfrm_mode xfrm6_beet_mode = {
-	.input2 = xfrm6_beet_input,
 	.output2 = xfrm6_beet_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_BEET,
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 8e23a2fba617..79c57decb472 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -18,14 +18,6 @@
 #include <net/ipv6.h>
 #include <net/xfrm.h>
 
-static inline void ipip6_ecn_decapsulate(struct sk_buff *skb)
-{
-	struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
-
-	if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
-		IP6_ECN_set_ce(skb, inner_iph);
-}
-
 /* Add encapsulation header.
  *
  * The top IP header will be constructed per RFC 2401.
@@ -65,45 +57,7 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 }
 
-#define for_each_input_rcu(head, handler)	\
-	for (handler = rcu_dereference(head);	\
-	     handler != NULL;			\
-	     handler = rcu_dereference(handler->next))
-
-
-static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
-{
-	int err = -EINVAL;
-
-	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6)
-		goto out;
-	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
-		goto out;
-
-	err = skb_unclone(skb, GFP_ATOMIC);
-	if (err)
-		goto out;
-
-	if (x->props.flags & XFRM_STATE_DECAP_DSCP)
-		ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)),
-			       ipipv6_hdr(skb));
-	if (!(x->props.flags & XFRM_STATE_NOECN))
-		ipip6_ecn_decapsulate(skb);
-
-	skb_reset_network_header(skb);
-	skb_mac_header_rebuild(skb);
-	if (skb->mac_len)
-		eth_hdr(skb)->h_proto = skb->protocol;
-
-	err = 0;
-
-out:
-	return err;
-}
-
-
 static struct xfrm_mode xfrm6_tunnel_mode = {
-	.input2 = xfrm6_mode_tunnel_input,
 	.output2 = xfrm6_mode_tunnel_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
diff --git a/net/xfrm/xfrm_inout.h b/net/xfrm/xfrm_inout.h
new file mode 100644
index 000000000000..c7b0318938e2
--- /dev/null
+++ b/net/xfrm/xfrm_inout.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/ipv6.h>
+#include <net/dsfield.h>
+#include <net/xfrm.h>
+
+#ifndef XFRM_INOUT_H
+#define XFRM_INOUT_H 1
+
+static inline void xfrm6_beet_make_header(struct sk_buff *skb)
+{
+	struct ipv6hdr *iph = ipv6_hdr(skb);
+
+	iph->version = 6;
+
+	memcpy(iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
+	       sizeof(iph->flow_lbl));
+	iph->nexthdr = XFRM_MODE_SKB_CB(skb)->protocol;
+
+	ipv6_change_dsfield(iph, 0, XFRM_MODE_SKB_CB(skb)->tos);
+	iph->hop_limit = XFRM_MODE_SKB_CB(skb)->ttl;
+}
+
+static inline void xfrm4_beet_make_header(struct sk_buff *skb)
+{
+	struct iphdr *iph = ip_hdr(skb);
+
+	iph->ihl = 5;
+	iph->version = 4;
+
+	iph->protocol = XFRM_MODE_SKB_CB(skb)->protocol;
+	iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
+
+	iph->id = XFRM_MODE_SKB_CB(skb)->id;
+	iph->frag_off = XFRM_MODE_SKB_CB(skb)->frag_off;
+	iph->ttl = XFRM_MODE_SKB_CB(skb)->ttl;
+}
+
+#endif
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 0edf3fb73585..e0fd9561ffe5 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -21,6 +21,8 @@
 #include <net/ip_tunnels.h>
 #include <net/ip6_tunnel.h>
 
+#include "xfrm_inout.h"
+
 struct xfrm_trans_tasklet {
 	struct tasklet_struct tasklet;
 	struct sk_buff_head queue;
@@ -166,6 +168,187 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq)
 }
 EXPORT_SYMBOL(xfrm_parse_spi);
 
+static int xfrm4_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct iphdr *iph;
+	int optlen = 0;
+	int err = -EINVAL;
+
+	if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) {
+		struct ip_beet_phdr *ph;
+		int phlen;
+
+		if (!pskb_may_pull(skb, sizeof(*ph)))
+			goto out;
+
+		ph = (struct ip_beet_phdr *)skb->data;
+
+		phlen = sizeof(*ph) + ph->padlen;
+		optlen = ph->hdrlen * 8 + (IPV4_BEET_PHMAXLEN - phlen);
+		if (optlen < 0 || optlen & 3 || optlen > 250)
+			goto out;
+
+		XFRM_MODE_SKB_CB(skb)->protocol = ph->nexthdr;
+
+		if (!pskb_may_pull(skb, phlen))
+			goto out;
+		__skb_pull(skb, phlen);
+	}
+
+	skb_push(skb, sizeof(*iph));
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+
+	xfrm4_beet_make_header(skb);
+
+	iph = ip_hdr(skb);
+
+	iph->ihl += optlen / 4;
+	iph->tot_len = htons(skb->len);
+	iph->daddr = x->sel.daddr.a4;
+	iph->saddr = x->sel.saddr.a4;
+	iph->check = 0;
+	iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
+	err = 0;
+out:
+	return err;
+}
+
+static void ipip_ecn_decapsulate(struct sk_buff *skb)
+{
+	struct iphdr *inner_iph = ipip_hdr(skb);
+
+	if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
+		IP_ECN_set_ce(inner_iph);
+}
+
+static int xfrm4_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = -EINVAL;
+
+	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
+		goto out;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		goto out;
+
+	err = skb_unclone(skb, GFP_ATOMIC);
+	if (err)
+		goto out;
+
+	if (x->props.flags & XFRM_STATE_DECAP_DSCP)
+		ipv4_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipip_hdr(skb));
+	if (!(x->props.flags & XFRM_STATE_NOECN))
+		ipip_ecn_decapsulate(skb);
+
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+	if (skb->mac_len)
+		eth_hdr(skb)->h_proto = skb->protocol;
+
+	err = 0;
+
+out:
+	return err;
+}
+
+static void ipip6_ecn_decapsulate(struct sk_buff *skb)
+{
+	struct ipv6hdr *inner_iph = ipipv6_hdr(skb);
+
+	if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos))
+		IP6_ECN_set_ce(skb, inner_iph);
+}
+
+static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb)
+{
+	int err = -EINVAL;
+
+	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6)
+		goto out;
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+		goto out;
+
+	err = skb_unclone(skb, GFP_ATOMIC);
+	if (err)
+		goto out;
+
+	if (x->props.flags & XFRM_STATE_DECAP_DSCP)
+		ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)),
+			       ipipv6_hdr(skb));
+	if (!(x->props.flags & XFRM_STATE_NOECN))
+		ipip6_ecn_decapsulate(skb);
+
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+	if (skb->mac_len)
+		eth_hdr(skb)->h_proto = skb->protocol;
+
+	err = 0;
+
+out:
+	return err;
+}
+
+static int xfrm6_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ipv6hdr *ip6h;
+	int size = sizeof(struct ipv6hdr);
+	int err;
+
+	err = skb_cow_head(skb, size + skb->mac_len);
+	if (err)
+		goto out;
+
+	__skb_push(skb, size);
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+
+	xfrm6_beet_make_header(skb);
+
+	ip6h = ipv6_hdr(skb);
+	ip6h->payload_len = htons(skb->len - size);
+	ip6h->daddr = x->sel.daddr.in6;
+	ip6h->saddr = x->sel.saddr.in6;
+	err = 0;
+out:
+	return err;
+}
+
+/* Remove encapsulation header.
+ *
+ * The IP header will be moved over the top of the encapsulation
+ * header.
+ *
+ * On entry, the transport header shall point to where the IP header
+ * should be and the network header shall be set to where the IP
+ * header currently is.  skb->data shall point to the start of the
+ * payload.
+ */
+static int
+xfrm_inner_mode_encap_remove(struct xfrm_state *x,
+			     const struct xfrm_mode *inner_mode,
+			     struct sk_buff *skb)
+{
+	switch (inner_mode->encap) {
+	case XFRM_MODE_BEET:
+		if (inner_mode->family == AF_INET)
+			return xfrm4_remove_beet_encap(x, skb);
+		if (inner_mode->family == AF_INET6)
+			return xfrm6_remove_beet_encap(x, skb);
+		break;
+	case XFRM_MODE_TUNNEL:
+		if (inner_mode->family == AF_INET)
+			return xfrm4_remove_tunnel_encap(x, skb);
+		if (inner_mode->family == AF_INET6)
+			return xfrm6_remove_tunnel_encap(x, skb);
+		break;
+	}
+
+	WARN_ON_ONCE(1);
+	return -EOPNOTSUPP;
+}
+
 static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct xfrm_mode *inner_mode = x->inner_mode;
@@ -182,7 +365,7 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
 	}
 
 	skb->protocol = inner_mode->afinfo->eth_proto;
-	return inner_mode->input2(x, skb);
+	return xfrm_inner_mode_encap_remove(x, inner_mode, skb);
 }
 
 /* Remove encapsulation header.
-- 
cgit v1.2.3


From 1de70830066b72b6a8e259e5363f6c0bc4ba7bbc Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Mar 2019 21:16:29 +0100
Subject: xfrm: remove output2 indirection from xfrm_mode

similar to previous patch: no external module dependencies,
so we can avoid the indirection by placing this in the core.

This change removes the last indirection from xfrm_mode and the
xfrm4|6_mode_{beet,tunnel}.c modules contain (almost) no code anymore.

Before:
   text    data     bss     dec     hex filename
   3957     136       0    4093     ffd net/xfrm/xfrm_output.o
    587      44       0     631     277 net/ipv4/xfrm4_mode_beet.o
    649      32       0     681     2a9 net/ipv4/xfrm4_mode_tunnel.o
    625      44       0     669     29d net/ipv6/xfrm6_mode_beet.o
    599      32       0     631     277 net/ipv6/xfrm6_mode_tunnel.o
After:
   text    data     bss     dec     hex filename
   5359     184       0    5543    15a7 net/xfrm/xfrm_output.o
    171      24       0     195      c3 net/ipv4/xfrm4_mode_beet.o
    171      24       0     195      c3 net/ipv4/xfrm4_mode_tunnel.o
    172      24       0     196      c4 net/ipv6/xfrm6_mode_beet.o
    172      24       0     196      c4 net/ipv6/xfrm6_mode_tunnel.o

v2: fold the *encap_add functions into xfrm*_prepare_output
    preserve (move) output2 comment (Sabrina)
    use x->outer_mode->encap, not inner
    fix a build breakage on ppc (kbuild robot)

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h           |  13 ---
 net/ipv4/xfrm4_mode_beet.c   |  63 -------------
 net/ipv4/xfrm4_mode_tunnel.c |  49 ----------
 net/ipv6/xfrm6_mode_beet.c   |  58 ------------
 net/ipv6/xfrm6_mode_tunnel.c |  36 --------
 net/xfrm/xfrm_output.c       | 212 ++++++++++++++++++++++++++++++++++++++++++-
 6 files changed, 207 insertions(+), 224 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index bdda545cf740..4351444c10fc 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -423,19 +423,6 @@ int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned sh
 int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 
 struct xfrm_mode {
-	/*
-	 * Add encapsulation header.
-	 *
-	 * On exit, the transport header will be set to the start of the
-	 * encapsulation header to be filled in by x->type->output and
-	 * the mac header will be set to the nextheader (protocol for
-	 * IPv4) field of the extension header directly preceding the
-	 * encapsulation header, or in its absence, that of the top IP
-	 * header.  The value of the network header will always point
-	 * to the top IP header while skb->data will point to the payload.
-	 */
-	int (*output2)(struct xfrm_state *x,struct sk_buff *skb);
-
 	struct xfrm_state_afinfo *afinfo;
 	struct module *owner;
 	u8 encap;
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
index 500960172933..ba84b278e627 100644
--- a/net/ipv4/xfrm4_mode_beet.c
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -17,71 +17,8 @@
 #include <net/ip.h>
 #include <net/xfrm.h>
 
-static void xfrm4_beet_make_header(struct sk_buff *skb)
-{
-	struct iphdr *iph = ip_hdr(skb);
-
-	iph->ihl = 5;
-	iph->version = 4;
-
-	iph->protocol = XFRM_MODE_SKB_CB(skb)->protocol;
-	iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
-
-	iph->id = XFRM_MODE_SKB_CB(skb)->id;
-	iph->frag_off = XFRM_MODE_SKB_CB(skb)->frag_off;
-	iph->ttl = XFRM_MODE_SKB_CB(skb)->ttl;
-}
-
-/* Add encapsulation header.
- *
- * The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt.
- */
-static int xfrm4_beet_output(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct ip_beet_phdr *ph;
-	struct iphdr *top_iph;
-	int hdrlen, optlen;
-
-	hdrlen = 0;
-	optlen = XFRM_MODE_SKB_CB(skb)->optlen;
-	if (unlikely(optlen))
-		hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4);
-
-	skb_set_network_header(skb, -x->props.header_len -
-				    hdrlen + (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph)));
-	if (x->sel.family != AF_INET6)
-		skb->network_header += IPV4_BEET_PHMAXLEN;
-	skb->mac_header = skb->network_header +
-			  offsetof(struct iphdr, protocol);
-	skb->transport_header = skb->network_header + sizeof(*top_iph);
-
-	xfrm4_beet_make_header(skb);
-
-	ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen);
-
-	top_iph = ip_hdr(skb);
-
-	if (unlikely(optlen)) {
-		BUG_ON(optlen < 0);
-
-		ph->padlen = 4 - (optlen & 4);
-		ph->hdrlen = optlen / 8;
-		ph->nexthdr = top_iph->protocol;
-		if (ph->padlen)
-			memset(ph + 1, IPOPT_NOP, ph->padlen);
-
-		top_iph->protocol = IPPROTO_BEETPH;
-		top_iph->ihl = sizeof(struct iphdr) / 4;
-	}
-
-	top_iph->saddr = x->props.saddr.a4;
-	top_iph->daddr = x->id.daddr.a4;
-
-	return 0;
-}
 
 static struct xfrm_mode xfrm4_beet_mode = {
-	.output2 = xfrm4_beet_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_BEET,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 31645319aaeb..b2b132c800fc 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -15,56 +15,7 @@
 #include <net/ip.h>
 #include <net/xfrm.h>
 
-/* Add encapsulation header.
- *
- * The top IP header will be constructed per RFC 2401.
- */
-static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct dst_entry *dst = skb_dst(skb);
-	struct iphdr *top_iph;
-	int flags;
-
-	skb_set_inner_network_header(skb, skb_network_offset(skb));
-	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
-
-	skb_set_network_header(skb, -x->props.header_len);
-	skb->mac_header = skb->network_header +
-			  offsetof(struct iphdr, protocol);
-	skb->transport_header = skb->network_header + sizeof(*top_iph);
-	top_iph = ip_hdr(skb);
-
-	top_iph->ihl = 5;
-	top_iph->version = 4;
-
-	top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
-
-	/* DS disclosing depends on XFRM_SA_XFLAG_DONT_ENCAP_DSCP */
-	if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
-		top_iph->tos = 0;
-	else
-		top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
-	top_iph->tos = INET_ECN_encapsulate(top_iph->tos,
-					    XFRM_MODE_SKB_CB(skb)->tos);
-
-	flags = x->props.flags;
-	if (flags & XFRM_STATE_NOECN)
-		IP_ECN_clear(top_iph);
-
-	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
-		0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
-
-	top_iph->ttl = ip4_dst_hoplimit(xfrm_dst_child(dst));
-
-	top_iph->saddr = x->props.saddr.a4;
-	top_iph->daddr = x->id.daddr.a4;
-	ip_select_ident(dev_net(dst->dev), skb, NULL);
-
-	return 0;
-}
-
 static struct xfrm_mode xfrm4_tunnel_mode = {
-	.output2 = xfrm4_mode_tunnel_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
index a0537b4f62f8..1c4a76bdd889 100644
--- a/net/ipv6/xfrm6_mode_beet.c
+++ b/net/ipv6/xfrm6_mode_beet.c
@@ -19,65 +19,7 @@
 #include <net/ipv6.h>
 #include <net/xfrm.h>
 
-static void xfrm6_beet_make_header(struct sk_buff *skb)
-{
-	struct ipv6hdr *iph = ipv6_hdr(skb);
-
-	iph->version = 6;
-
-	memcpy(iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
-	       sizeof(iph->flow_lbl));
-	iph->nexthdr = XFRM_MODE_SKB_CB(skb)->protocol;
-
-	ipv6_change_dsfield(iph, 0, XFRM_MODE_SKB_CB(skb)->tos);
-	iph->hop_limit = XFRM_MODE_SKB_CB(skb)->ttl;
-}
-
-/* Add encapsulation header.
- *
- * The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt.
- */
-static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct ipv6hdr *top_iph;
-	struct ip_beet_phdr *ph;
-	int optlen, hdr_len;
-
-	hdr_len = 0;
-	optlen = XFRM_MODE_SKB_CB(skb)->optlen;
-	if (unlikely(optlen))
-		hdr_len += IPV4_BEET_PHMAXLEN - (optlen & 4);
-
-	skb_set_network_header(skb, -x->props.header_len - hdr_len);
-	if (x->sel.family != AF_INET6)
-		skb->network_header += IPV4_BEET_PHMAXLEN;
-	skb->mac_header = skb->network_header +
-			  offsetof(struct ipv6hdr, nexthdr);
-	skb->transport_header = skb->network_header + sizeof(*top_iph);
-	ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdr_len);
-
-	xfrm6_beet_make_header(skb);
-
-	top_iph = ipv6_hdr(skb);
-	if (unlikely(optlen)) {
-
-		BUG_ON(optlen < 0);
-
-		ph->padlen = 4 - (optlen & 4);
-		ph->hdrlen = optlen / 8;
-		ph->nexthdr = top_iph->nexthdr;
-		if (ph->padlen)
-			memset(ph + 1, IPOPT_NOP, ph->padlen);
-
-		top_iph->nexthdr = IPPROTO_BEETPH;
-	}
-
-	top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
-	top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
-	return 0;
-}
 static struct xfrm_mode xfrm6_beet_mode = {
-	.output2 = xfrm6_beet_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_BEET,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 79c57decb472..e5c928dd70e3 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -22,43 +22,7 @@
  *
  * The top IP header will be constructed per RFC 2401.
  */
-static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
-{
-	struct dst_entry *dst = skb_dst(skb);
-	struct ipv6hdr *top_iph;
-	int dsfield;
-
-	skb_set_inner_network_header(skb, skb_network_offset(skb));
-	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
-
-	skb_set_network_header(skb, -x->props.header_len);
-	skb->mac_header = skb->network_header +
-			  offsetof(struct ipv6hdr, nexthdr);
-	skb->transport_header = skb->network_header + sizeof(*top_iph);
-	top_iph = ipv6_hdr(skb);
-
-	top_iph->version = 6;
-
-	memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
-	       sizeof(top_iph->flow_lbl));
-	top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family);
-
-	if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
-		dsfield = 0;
-	else
-		dsfield = XFRM_MODE_SKB_CB(skb)->tos;
-	dsfield = INET_ECN_encapsulate(dsfield, XFRM_MODE_SKB_CB(skb)->tos);
-	if (x->props.flags & XFRM_STATE_NOECN)
-		dsfield &= ~INET_ECN_MASK;
-	ipv6_change_dsfield(top_iph, 0, dsfield);
-	top_iph->hop_limit = ip6_dst_hoplimit(xfrm_dst_child(dst));
-	top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
-	top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
-	return 0;
-}
-
 static struct xfrm_mode xfrm6_tunnel_mode = {
-	.output2 = xfrm6_mode_tunnel_output,
 	.owner = THIS_MODULE,
 	.encap = XFRM_MODE_TUNNEL,
 	.flags = XFRM_MODE_FLAG_TUNNEL,
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 05926dcf5d17..9bdf16f13606 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -17,8 +17,11 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <net/dst.h>
+#include <net/inet_ecn.h>
 #include <net/xfrm.h>
 
+#include "xfrm_inout.h"
+
 static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb);
 static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
 
@@ -141,6 +144,190 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
 #endif
 }
 
+/* Add encapsulation header.
+ *
+ * The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt.
+ */
+static int xfrm4_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ip_beet_phdr *ph;
+	struct iphdr *top_iph;
+	int hdrlen, optlen;
+
+	hdrlen = 0;
+	optlen = XFRM_MODE_SKB_CB(skb)->optlen;
+	if (unlikely(optlen))
+		hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4);
+
+	skb_set_network_header(skb, -x->props.header_len - hdrlen +
+			       (XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph)));
+	if (x->sel.family != AF_INET6)
+		skb->network_header += IPV4_BEET_PHMAXLEN;
+	skb->mac_header = skb->network_header +
+			  offsetof(struct iphdr, protocol);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
+
+	xfrm4_beet_make_header(skb);
+
+	ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen);
+
+	top_iph = ip_hdr(skb);
+
+	if (unlikely(optlen)) {
+		if (WARN_ON(optlen < 0))
+			return -EINVAL;
+
+		ph->padlen = 4 - (optlen & 4);
+		ph->hdrlen = optlen / 8;
+		ph->nexthdr = top_iph->protocol;
+		if (ph->padlen)
+			memset(ph + 1, IPOPT_NOP, ph->padlen);
+
+		top_iph->protocol = IPPROTO_BEETPH;
+		top_iph->ihl = sizeof(struct iphdr) / 4;
+	}
+
+	top_iph->saddr = x->props.saddr.a4;
+	top_iph->daddr = x->id.daddr.a4;
+
+	return 0;
+}
+
+/* Add encapsulation header.
+ *
+ * The top IP header will be constructed per RFC 2401.
+ */
+static int xfrm4_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct iphdr *top_iph;
+	int flags;
+
+	skb_set_inner_network_header(skb, skb_network_offset(skb));
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+	skb_set_network_header(skb, -x->props.header_len);
+	skb->mac_header = skb->network_header +
+			  offsetof(struct iphdr, protocol);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
+	top_iph = ip_hdr(skb);
+
+	top_iph->ihl = 5;
+	top_iph->version = 4;
+
+	top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
+
+	/* DS disclosing depends on XFRM_SA_XFLAG_DONT_ENCAP_DSCP */
+	if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
+		top_iph->tos = 0;
+	else
+		top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
+	top_iph->tos = INET_ECN_encapsulate(top_iph->tos,
+					    XFRM_MODE_SKB_CB(skb)->tos);
+
+	flags = x->props.flags;
+	if (flags & XFRM_STATE_NOECN)
+		IP_ECN_clear(top_iph);
+
+	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
+		0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
+
+	top_iph->ttl = ip4_dst_hoplimit(xfrm_dst_child(dst));
+
+	top_iph->saddr = x->props.saddr.a4;
+	top_iph->daddr = x->id.daddr.a4;
+	ip_select_ident(dev_net(dst->dev), skb, NULL);
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int xfrm6_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct ipv6hdr *top_iph;
+	int dsfield;
+
+	skb_set_inner_network_header(skb, skb_network_offset(skb));
+	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
+
+	skb_set_network_header(skb, -x->props.header_len);
+	skb->mac_header = skb->network_header +
+			  offsetof(struct ipv6hdr, nexthdr);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
+	top_iph = ipv6_hdr(skb);
+
+	top_iph->version = 6;
+
+	memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
+	       sizeof(top_iph->flow_lbl));
+	top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family);
+
+	if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
+		dsfield = 0;
+	else
+		dsfield = XFRM_MODE_SKB_CB(skb)->tos;
+	dsfield = INET_ECN_encapsulate(dsfield, XFRM_MODE_SKB_CB(skb)->tos);
+	if (x->props.flags & XFRM_STATE_NOECN)
+		dsfield &= ~INET_ECN_MASK;
+	ipv6_change_dsfield(top_iph, 0, dsfield);
+	top_iph->hop_limit = ip6_dst_hoplimit(xfrm_dst_child(dst));
+	top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
+	top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
+	return 0;
+}
+
+static int xfrm6_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb)
+{
+	struct ipv6hdr *top_iph;
+	struct ip_beet_phdr *ph;
+	int optlen, hdr_len;
+
+	hdr_len = 0;
+	optlen = XFRM_MODE_SKB_CB(skb)->optlen;
+	if (unlikely(optlen))
+		hdr_len += IPV4_BEET_PHMAXLEN - (optlen & 4);
+
+	skb_set_network_header(skb, -x->props.header_len - hdr_len);
+	if (x->sel.family != AF_INET6)
+		skb->network_header += IPV4_BEET_PHMAXLEN;
+	skb->mac_header = skb->network_header +
+			  offsetof(struct ipv6hdr, nexthdr);
+	skb->transport_header = skb->network_header + sizeof(*top_iph);
+	ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdr_len);
+
+	xfrm6_beet_make_header(skb);
+
+	top_iph = ipv6_hdr(skb);
+	if (unlikely(optlen)) {
+		if (WARN_ON(optlen < 0))
+			return -EINVAL;
+
+		ph->padlen = 4 - (optlen & 4);
+		ph->hdrlen = optlen / 8;
+		ph->nexthdr = top_iph->nexthdr;
+		if (ph->padlen)
+			memset(ph + 1, IPOPT_NOP, ph->padlen);
+
+		top_iph->nexthdr = IPPROTO_BEETPH;
+	}
+
+	top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
+	top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
+	return 0;
+}
+#endif
+
+/* Add encapsulation header.
+ *
+ * On exit, the transport header will be set to the start of the
+ * encapsulation header to be filled in by x->type->output and the mac
+ * header will be set to the nextheader (protocol for IPv4) field of the
+ * extension header directly preceding the encapsulation header, or in
+ * its absence, that of the top IP header.
+ * The value of the network header will always point to the top IP header
+ * while skb->data will point to the payload.
+ */
 static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
@@ -152,7 +339,15 @@ static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
 	skb->protocol = htons(ETH_P_IP);
 
-	return x->outer_mode->output2(x, skb);
+	switch (x->outer_mode->encap) {
+	case XFRM_MODE_BEET:
+		return xfrm4_beet_encap_add(x, skb);
+	case XFRM_MODE_TUNNEL:
+		return xfrm4_tunnel_encap_add(x, skb);
+	}
+
+	WARN_ON_ONCE(1);
+	return -EOPNOTSUPP;
 }
 
 static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
@@ -167,11 +362,18 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	skb->ignore_df = 1;
 	skb->protocol = htons(ETH_P_IPV6);
 
-	return x->outer_mode->output2(x, skb);
-#else
-	WARN_ON_ONCE(1);
-	return -EOPNOTSUPP;
+	switch (x->outer_mode->encap) {
+	case XFRM_MODE_BEET:
+		return xfrm6_beet_encap_add(x, skb);
+	case XFRM_MODE_TUNNEL:
+		return xfrm6_tunnel_encap_add(x, skb);
+	default:
+		WARN_ON_ONCE(1);
+		return -EOPNOTSUPP;
+	}
 #endif
+	WARN_ON_ONCE(1);
+	return -EAFNOSUPPORT;
 }
 
 static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
-- 
cgit v1.2.3


From 733a5fac2f15b55b9059230d098ed04341d2d884 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Mar 2019 21:16:30 +0100
Subject: xfrm: remove afinfo pointer from xfrm_mode

Adds an EXPORT_SYMBOL for afinfo_get_rcu, as it will now be called from
ipv6 in case of CONFIG_IPV6=m.

This change has virtually no effect on vmlinux size, but it reduces
afinfo size and allows followup patch to make xfrm modes const.

v2: mark if (afinfo) tests as likely (Sabrina)
    re-fetch afinfo according to inner_mode in xfrm_prepare_input().

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h      |  1 -
 net/ipv4/xfrm4_output.c | 12 +++++++++++-
 net/ipv6/xfrm6_output.c | 21 +++++++++++++++++++--
 net/xfrm/xfrm_input.c   | 34 ++++++++++++++++++++++++++++------
 net/xfrm/xfrm_output.c  | 12 +++++++++++-
 net/xfrm/xfrm_policy.c  | 10 +++++++++-
 net/xfrm/xfrm_state.c   |  4 ++--
 7 files changed, 80 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 4351444c10fc..8d1c9506bcf6 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -423,7 +423,6 @@ int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned sh
 int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 
 struct xfrm_mode {
-	struct xfrm_state_afinfo *afinfo;
 	struct module *owner;
 	u8 encap;
 	u8 family;
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 6802d1aee424..7c3df14daef3 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -72,6 +72,8 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
 static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct xfrm_state *x = skb_dst(skb)->xfrm;
+	const struct xfrm_state_afinfo *afinfo;
+	int ret = -EAFNOSUPPORT;
 
 #ifdef CONFIG_NETFILTER
 	if (!x) {
@@ -80,7 +82,15 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	}
 #endif
 
-	return x->outer_mode->afinfo->output_finish(sk, skb);
+	rcu_read_lock();
+	afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode->family);
+	if (likely(afinfo))
+		ret = afinfo->output_finish(sk, skb);
+	else
+		kfree_skb(skb);
+	rcu_read_unlock();
+
+	return ret;
 }
 
 int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 2b663d2ffdcd..455fbf3b91cf 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -122,11 +122,28 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb)
 	return xfrm_output(sk, skb);
 }
 
+static int __xfrm6_output_state_finish(struct xfrm_state *x, struct sock *sk,
+				       struct sk_buff *skb)
+{
+	const struct xfrm_state_afinfo *afinfo;
+	int ret = -EAFNOSUPPORT;
+
+	rcu_read_lock();
+	afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode->family);
+	if (likely(afinfo))
+		ret = afinfo->output_finish(sk, skb);
+	else
+		kfree_skb(skb);
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static int __xfrm6_output_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct xfrm_state *x = skb_dst(skb)->xfrm;
 
-	return x->outer_mode->afinfo->output_finish(sk, skb);
+	return __xfrm6_output_state_finish(x, sk, skb);
 }
 
 static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
@@ -168,7 +185,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 				    __xfrm6_output_finish);
 
 skip_frag:
-	return x->outer_mode->afinfo->output_finish(sk, skb);
+	return __xfrm6_output_state_finish(x, sk, skb);
 }
 
 int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index e0fd9561ffe5..74b53c13279b 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -352,19 +352,35 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x,
 static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
 {
 	struct xfrm_mode *inner_mode = x->inner_mode;
-	int err;
+	const struct xfrm_state_afinfo *afinfo;
+	int err = -EAFNOSUPPORT;
 
-	err = x->outer_mode->afinfo->extract_input(x, skb);
-	if (err)
+	rcu_read_lock();
+	afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode->family);
+	if (likely(afinfo))
+		err = afinfo->extract_input(x, skb);
+
+	if (err) {
+		rcu_read_unlock();
 		return err;
+	}
 
 	if (x->sel.family == AF_UNSPEC) {
 		inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
-		if (inner_mode == NULL)
+		if (!inner_mode) {
+			rcu_read_unlock();
 			return -EAFNOSUPPORT;
+		}
 	}
 
-	skb->protocol = inner_mode->afinfo->eth_proto;
+	afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
+	if (unlikely(!afinfo)) {
+		rcu_read_unlock();
+		return -EAFNOSUPPORT;
+	}
+
+	skb->protocol = afinfo->eth_proto;
+	rcu_read_unlock();
 	return xfrm_inner_mode_encap_remove(x, inner_mode, skb);
 }
 
@@ -440,6 +456,7 @@ static int xfrm_inner_mode_input(struct xfrm_state *x,
 
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 {
+	const struct xfrm_state_afinfo *afinfo;
 	struct net *net = dev_net(skb->dev);
 	int err;
 	__be32 seq;
@@ -705,7 +722,12 @@ resume:
 		if (xo)
 			xfrm_gro = xo->flags & XFRM_GRO;
 
-		err = x->inner_mode->afinfo->transport_finish(skb, xfrm_gro || async);
+		err = -EAFNOSUPPORT;
+		rcu_read_lock();
+		afinfo = xfrm_state_afinfo_get_rcu(x->inner_mode->family);
+		if (likely(afinfo))
+			err = afinfo->transport_finish(skb, xfrm_gro || async);
+		rcu_read_unlock();
 		if (xfrm_gro) {
 			sp = skb_sec_path(skb);
 			if (sp)
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 9bdf16f13606..17c4f58d28ea 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -623,7 +623,10 @@ EXPORT_SYMBOL_GPL(xfrm_output);
 
 static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 {
+	const struct xfrm_state_afinfo *afinfo;
 	struct xfrm_mode *inner_mode;
+	int err = -EAFNOSUPPORT;
+
 	if (x->sel.family == AF_UNSPEC)
 		inner_mode = xfrm_ip2inner_mode(x,
 				xfrm_af2proto(skb_dst(skb)->ops->family));
@@ -632,7 +635,14 @@ static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	if (inner_mode == NULL)
 		return -EAFNOSUPPORT;
-	return inner_mode->afinfo->extract_output(x, skb);
+
+	rcu_read_lock();
+	afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
+	if (likely(afinfo))
+		err = afinfo->extract_output(x, skb);
+	rcu_read_unlock();
+
+	return err;
 }
 
 void xfrm_local_error(struct sk_buff *skb, int mtu)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 8d1a898d0ba5..67122beb116c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2545,6 +2545,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 					    const struct flowi *fl,
 					    struct dst_entry *dst)
 {
+	const struct xfrm_state_afinfo *afinfo;
 	struct net *net = xp_net(policy);
 	unsigned long now = jiffies;
 	struct net_device *dev;
@@ -2622,7 +2623,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 		dst1->lastuse = now;
 
 		dst1->input = dst_discard;
-		dst1->output = inner_mode->afinfo->output;
+
+		rcu_read_lock();
+		afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
+		if (likely(afinfo))
+			dst1->output = afinfo->output;
+		else
+			dst1->output = dst_discard_out;
+		rcu_read_unlock();
 
 		xdst_prev = xdst;
 
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index c32394b59776..358b09f0d018 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -354,7 +354,6 @@ int xfrm_register_mode(struct xfrm_mode *mode)
 	if (!try_module_get(afinfo->owner))
 		goto out;
 
-	mode->afinfo = afinfo;
 	modemap[mode->encap] = mode;
 	err = 0;
 
@@ -378,7 +377,7 @@ void xfrm_unregister_mode(struct xfrm_mode *mode)
 	spin_lock_bh(&xfrm_mode_lock);
 	if (likely(modemap[mode->encap] == mode)) {
 		modemap[mode->encap] = NULL;
-		module_put(mode->afinfo->owner);
+		module_put(afinfo->owner);
 	}
 
 	spin_unlock_bh(&xfrm_mode_lock);
@@ -2188,6 +2187,7 @@ struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family)
 
 	return rcu_dereference(xfrm_state_afinfo[family]);
 }
+EXPORT_SYMBOL_GPL(xfrm_state_afinfo_get_rcu);
 
 struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
 {
-- 
cgit v1.2.3


From 4c145dce26013763490df88f2473714f5bc7857d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Mar 2019 21:16:31 +0100
Subject: xfrm: make xfrm modes builtin

after previous changes, xfrm_mode contains no function pointers anymore
and all modules defining such struct contain no code except an init/exit
functions to register the xfrm_mode struct with the xfrm core.

Just place the xfrm modes core and remove the modules,
the run-time xfrm_mode register/unregister functionality is removed.

Before:

    text    data     bss      dec filename
    7523     200    2364    10087 net/xfrm/xfrm_input.o
   40003     628     440    41071 net/xfrm/xfrm_state.o
15730338 6937080 4046908 26714326 vmlinux

    7389     200    2364    9953  net/xfrm/xfrm_input.o
   40574     656     440   41670  net/xfrm/xfrm_state.o
15730084 6937068 4046908 26714060 vmlinux

The xfrm*_mode_{transport,tunnel,beet} modules are gone.

v2: replace CONFIG_INET6_XFRM_MODE_* IS_ENABLED guards with CONFIG_IPV6
    ones rather than removing them.

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h                 |  13 +--
 net/ipv4/Kconfig                   |  29 +------
 net/ipv4/Makefile                  |   3 -
 net/ipv4/ip_vti.c                  |   2 +-
 net/ipv4/xfrm4_mode_beet.c         |  41 ----------
 net/ipv4/xfrm4_mode_transport.c    |  36 ---------
 net/ipv4/xfrm4_mode_tunnel.c       |  38 ---------
 net/ipv6/Kconfig                   |  35 +-------
 net/ipv6/Makefile                  |   4 -
 net/ipv6/ip6_vti.c                 |   2 +-
 net/ipv6/xfrm6_mode_beet.c         |  42 ----------
 net/ipv6/xfrm6_mode_ro.c           |  55 -------------
 net/ipv6/xfrm6_mode_transport.c    |  37 ---------
 net/ipv6/xfrm6_mode_tunnel.c       |  45 -----------
 net/xfrm/xfrm_input.c              |  13 ++-
 net/xfrm/xfrm_interface.c          |   2 +-
 net/xfrm/xfrm_output.c             |  15 ++--
 net/xfrm/xfrm_policy.c             |   2 +-
 net/xfrm/xfrm_state.c              | 158 ++++++++++++++-----------------------
 tools/testing/selftests/net/config |   2 -
 20 files changed, 81 insertions(+), 493 deletions(-)
 delete mode 100644 net/ipv4/xfrm4_mode_beet.c
 delete mode 100644 net/ipv4/xfrm4_mode_transport.c
 delete mode 100644 net/ipv4/xfrm4_mode_tunnel.c
 delete mode 100644 net/ipv6/xfrm6_mode_beet.c
 delete mode 100644 net/ipv6/xfrm6_mode_ro.c
 delete mode 100644 net/ipv6/xfrm6_mode_transport.c
 delete mode 100644 net/ipv6/xfrm6_mode_tunnel.c

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 8d1c9506bcf6..4ca79cdc3460 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -234,9 +234,9 @@ struct xfrm_state {
 	/* Reference to data common to all the instances of this
 	 * transformer. */
 	const struct xfrm_type	*type;
-	struct xfrm_mode	*inner_mode;
-	struct xfrm_mode	*inner_mode_iaf;
-	struct xfrm_mode	*outer_mode;
+	const struct xfrm_mode	*inner_mode;
+	const struct xfrm_mode	*inner_mode_iaf;
+	const struct xfrm_mode	*outer_mode;
 
 	const struct xfrm_type_offload	*type_offload;
 
@@ -347,7 +347,6 @@ struct xfrm_state_afinfo {
 	struct module			*owner;
 	const struct xfrm_type		*type_map[IPPROTO_MAX];
 	const struct xfrm_type_offload	*type_offload_map[IPPROTO_MAX];
-	struct xfrm_mode		*mode_map[XFRM_MODE_MAX];
 
 	int			(*init_flags)(struct xfrm_state *x);
 	void			(*init_tempsel)(struct xfrm_selector *sel,
@@ -423,7 +422,6 @@ int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned sh
 int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 
 struct xfrm_mode {
-	struct module *owner;
 	u8 encap;
 	u8 family;
 	u8 flags;
@@ -434,9 +432,6 @@ enum {
 	XFRM_MODE_FLAG_TUNNEL = 1,
 };
 
-int xfrm_register_mode(struct xfrm_mode *mode);
-void xfrm_unregister_mode(struct xfrm_mode *mode);
-
 static inline int xfrm_af2proto(unsigned int family)
 {
 	switch(family) {
@@ -449,7 +444,7 @@ static inline int xfrm_af2proto(unsigned int family)
 	}
 }
 
-static inline struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto)
+static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto)
 {
 	if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) ||
 	    (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6))
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 32cae39cdff6..8108e97d4285 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -304,7 +304,7 @@ config NET_IPVTI
 	tristate "Virtual (secure) IP: tunneling"
 	select INET_TUNNEL
 	select NET_IP_TUNNEL
-	depends on INET_XFRM_MODE_TUNNEL
+	select XFRM
 	---help---
 	  Tunneling means encapsulating data of one protocol type within
 	  another protocol and sending it over a channel that understands the
@@ -396,33 +396,6 @@ config INET_TUNNEL
 	tristate
 	default n
 
-config INET_XFRM_MODE_TRANSPORT
-	tristate "IP: IPsec transport mode"
-	default y
-	select XFRM
-	---help---
-	  Support for IPsec transport mode.
-
-	  If unsure, say Y.
-
-config INET_XFRM_MODE_TUNNEL
-	tristate "IP: IPsec tunnel mode"
-	default y
-	select XFRM
-	---help---
-	  Support for IPsec tunnel mode.
-
-	  If unsure, say Y.
-
-config INET_XFRM_MODE_BEET
-	tristate "IP: IPsec BEET mode"
-	default y
-	select XFRM
-	---help---
-	  Support for IPsec BEET mode.
-
-	  If unsure, say Y.
-
 config INET_DIAG
 	tristate "INET: socket monitoring interface"
 	default y
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 58629314eae9..000a61994c8f 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -37,10 +37,7 @@ obj-$(CONFIG_INET_ESP) += esp4.o
 obj-$(CONFIG_INET_ESP_OFFLOAD) += esp4_offload.o
 obj-$(CONFIG_INET_IPCOMP) += ipcomp.o
 obj-$(CONFIG_INET_XFRM_TUNNEL) += xfrm4_tunnel.o
-obj-$(CONFIG_INET_XFRM_MODE_BEET) += xfrm4_mode_beet.o
 obj-$(CONFIG_INET_TUNNEL) += tunnel4.o
-obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o
-obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o
 obj-$(CONFIG_IP_PNP) += ipconfig.o
 obj-$(CONFIG_NETFILTER)	+= netfilter.o netfilter/
 obj-$(CONFIG_INET_DIAG) += inet_diag.o
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 3f3f6d6be318..91926c9a3bc9 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -107,7 +107,7 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
 	struct net_device *dev;
 	struct pcpu_sw_netstats *tstats;
 	struct xfrm_state *x;
-	struct xfrm_mode *inner_mode;
+	const struct xfrm_mode *inner_mode;
 	struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
 	u32 orig_mark = skb->mark;
 	int ret;
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
deleted file mode 100644
index ba84b278e627..000000000000
--- a/net/ipv4/xfrm4_mode_beet.c
+++ /dev/null
@@ -1,41 +0,0 @@
-/*
- * xfrm4_mode_beet.c - BEET mode encapsulation for IPv4.
- *
- * Copyright (c) 2006 Diego Beltrami <diego.beltrami@gmail.com>
- *                    Miika Komu     <miika@iki.fi>
- *                    Herbert Xu     <herbert@gondor.apana.org.au>
- *                    Abhinav Pathak <abhinav.pathak@hiit.fi>
- *                    Jeff Ahrenholz <ahrenholz@gmail.com>
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/stringify.h>
-#include <net/dst.h>
-#include <net/ip.h>
-#include <net/xfrm.h>
-
-
-static struct xfrm_mode xfrm4_beet_mode = {
-	.owner = THIS_MODULE,
-	.encap = XFRM_MODE_BEET,
-	.flags = XFRM_MODE_FLAG_TUNNEL,
-	.family = AF_INET,
-};
-
-static int __init xfrm4_beet_init(void)
-{
-	return xfrm_register_mode(&xfrm4_beet_mode);
-}
-
-static void __exit xfrm4_beet_exit(void)
-{
-	xfrm_unregister_mode(&xfrm4_beet_mode);
-}
-
-module_init(xfrm4_beet_init);
-module_exit(xfrm4_beet_exit);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_XFRM_MODE(AF_INET, XFRM_MODE_BEET);
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
deleted file mode 100644
index 397863ea762b..000000000000
--- a/net/ipv4/xfrm4_mode_transport.c
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * xfrm4_mode_transport.c - Transport mode encapsulation for IPv4.
- *
- * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/stringify.h>
-#include <net/dst.h>
-#include <net/ip.h>
-#include <net/xfrm.h>
-#include <net/protocol.h>
-
-static struct xfrm_mode xfrm4_transport_mode = {
-	.owner = THIS_MODULE,
-	.encap = XFRM_MODE_TRANSPORT,
-	.family = AF_INET,
-};
-
-static int __init xfrm4_transport_init(void)
-{
-	return xfrm_register_mode(&xfrm4_transport_mode);
-}
-
-static void __exit xfrm4_transport_exit(void)
-{
-	xfrm_unregister_mode(&xfrm4_transport_mode);
-}
-
-module_init(xfrm4_transport_init);
-module_exit(xfrm4_transport_exit);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_XFRM_MODE(AF_INET, XFRM_MODE_TRANSPORT);
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
deleted file mode 100644
index b2b132c800fc..000000000000
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * xfrm4_mode_tunnel.c - Tunnel mode encapsulation for IPv4.
- *
- * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
- */
-
-#include <linux/gfp.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/stringify.h>
-#include <net/dst.h>
-#include <net/inet_ecn.h>
-#include <net/ip.h>
-#include <net/xfrm.h>
-
-static struct xfrm_mode xfrm4_tunnel_mode = {
-	.owner = THIS_MODULE,
-	.encap = XFRM_MODE_TUNNEL,
-	.flags = XFRM_MODE_FLAG_TUNNEL,
-	.family = AF_INET,
-};
-
-static int __init xfrm4_mode_tunnel_init(void)
-{
-	return xfrm_register_mode(&xfrm4_tunnel_mode);
-}
-
-static void __exit xfrm4_mode_tunnel_exit(void)
-{
-	xfrm_unregister_mode(&xfrm4_tunnel_mode);
-}
-
-module_init(xfrm4_mode_tunnel_init);
-module_exit(xfrm4_mode_tunnel_exit);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_XFRM_MODE(AF_INET, XFRM_MODE_TUNNEL);
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 613282c65a10..cd915e332c98 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -135,44 +135,11 @@ config INET6_TUNNEL
 	tristate
 	default n
 
-config INET6_XFRM_MODE_TRANSPORT
-	tristate "IPv6: IPsec transport mode"
-	default IPV6
-	select XFRM
-	---help---
-	  Support for IPsec transport mode.
-
-	  If unsure, say Y.
-
-config INET6_XFRM_MODE_TUNNEL
-	tristate "IPv6: IPsec tunnel mode"
-	default IPV6
-	select XFRM
-	---help---
-	  Support for IPsec tunnel mode.
-
-	  If unsure, say Y.
-
-config INET6_XFRM_MODE_BEET
-	tristate "IPv6: IPsec BEET mode"
-	default IPV6
-	select XFRM
-	---help---
-	  Support for IPsec BEET mode.
-
-	  If unsure, say Y.
-
-config INET6_XFRM_MODE_ROUTEOPTIMIZATION
-	tristate "IPv6: MIPv6 route optimization mode"
-	select XFRM
-	---help---
-	  Support for MIPv6 route optimization mode.
-
 config IPV6_VTI
 tristate "Virtual (secure) IPv6: tunneling"
 	select IPV6_TUNNEL
 	select NET_IP_TUNNEL
-	depends on INET6_XFRM_MODE_TUNNEL
+	select XFRM
 	---help---
 	Tunneling means encapsulating data of one protocol type within
 	another protocol and sending it over a channel that understands the
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index e0026fa1261b..8ccf35514015 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -35,10 +35,6 @@ obj-$(CONFIG_INET6_ESP_OFFLOAD) += esp6_offload.o
 obj-$(CONFIG_INET6_IPCOMP) += ipcomp6.o
 obj-$(CONFIG_INET6_XFRM_TUNNEL) += xfrm6_tunnel.o
 obj-$(CONFIG_INET6_TUNNEL) += tunnel6.o
-obj-$(CONFIG_INET6_XFRM_MODE_TRANSPORT) += xfrm6_mode_transport.o
-obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o
-obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o
-obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o
 obj-$(CONFIG_IPV6_MIP6) += mip6.o
 obj-$(CONFIG_IPV6_ILA) += ila/
 obj-$(CONFIG_NETFILTER)	+= netfilter/
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 369803c581b7..71ec5e60cf8f 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -342,7 +342,7 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
 	struct net_device *dev;
 	struct pcpu_sw_netstats *tstats;
 	struct xfrm_state *x;
-	struct xfrm_mode *inner_mode;
+	const struct xfrm_mode *inner_mode;
 	struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
 	u32 orig_mark = skb->mark;
 	int ret;
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
deleted file mode 100644
index 1c4a76bdd889..000000000000
--- a/net/ipv6/xfrm6_mode_beet.c
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * xfrm6_mode_beet.c - BEET mode encapsulation for IPv6.
- *
- * Copyright (c) 2006 Diego Beltrami <diego.beltrami@gmail.com>
- *                    Miika Komu     <miika@iki.fi>
- *                    Herbert Xu     <herbert@gondor.apana.org.au>
- *                    Abhinav Pathak <abhinav.pathak@hiit.fi>
- *                    Jeff Ahrenholz <ahrenholz@gmail.com>
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/stringify.h>
-#include <net/dsfield.h>
-#include <net/dst.h>
-#include <net/inet_ecn.h>
-#include <net/ipv6.h>
-#include <net/xfrm.h>
-
-static struct xfrm_mode xfrm6_beet_mode = {
-	.owner = THIS_MODULE,
-	.encap = XFRM_MODE_BEET,
-	.flags = XFRM_MODE_FLAG_TUNNEL,
-	.family = AF_INET6,
-};
-
-static int __init xfrm6_beet_init(void)
-{
-	return xfrm_register_mode(&xfrm6_beet_mode);
-}
-
-static void __exit xfrm6_beet_exit(void)
-{
-	xfrm_unregister_mode(&xfrm6_beet_mode);
-}
-
-module_init(xfrm6_beet_init);
-module_exit(xfrm6_beet_exit);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_BEET);
diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c
deleted file mode 100644
index d0a6a4dbd689..000000000000
--- a/net/ipv6/xfrm6_mode_ro.c
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * xfrm6_mode_ro.c - Route optimization mode for IPv6.
- *
- * Copyright (C)2003-2006 Helsinki University of Technology
- * Copyright (C)2003-2006 USAGI/WIDE Project
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-/*
- * Authors:
- *	Noriaki TAKAMIYA @USAGI
- *	Masahide NAKAMURA @USAGI
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/spinlock.h>
-#include <linux/stringify.h>
-#include <linux/time.h>
-#include <net/ipv6.h>
-#include <net/xfrm.h>
-
-static struct xfrm_mode xfrm6_ro_mode = {
-	.owner = THIS_MODULE,
-	.encap = XFRM_MODE_ROUTEOPTIMIZATION,
-	.family = AF_INET6,
-};
-
-static int __init xfrm6_ro_init(void)
-{
-	return xfrm_register_mode(&xfrm6_ro_mode);
-}
-
-static void __exit xfrm6_ro_exit(void)
-{
-	xfrm_unregister_mode(&xfrm6_ro_mode);
-}
-
-module_init(xfrm6_ro_init);
-module_exit(xfrm6_ro_exit);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_ROUTEOPTIMIZATION);
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
deleted file mode 100644
index d90c934c2f1a..000000000000
--- a/net/ipv6/xfrm6_mode_transport.c
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * xfrm6_mode_transport.c - Transport mode encapsulation for IPv6.
- *
- * Copyright (C) 2002 USAGI/WIDE Project
- * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/stringify.h>
-#include <net/dst.h>
-#include <net/ipv6.h>
-#include <net/xfrm.h>
-#include <net/protocol.h>
-
-static struct xfrm_mode xfrm6_transport_mode = {
-	.owner = THIS_MODULE,
-	.encap = XFRM_MODE_TRANSPORT,
-	.family = AF_INET6,
-};
-
-static int __init xfrm6_transport_init(void)
-{
-	return xfrm_register_mode(&xfrm6_transport_mode);
-}
-
-static void __exit xfrm6_transport_exit(void)
-{
-	xfrm_unregister_mode(&xfrm6_transport_mode);
-}
-
-module_init(xfrm6_transport_init);
-module_exit(xfrm6_transport_exit);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TRANSPORT);
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
deleted file mode 100644
index e5c928dd70e3..000000000000
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- * xfrm6_mode_tunnel.c - Tunnel mode encapsulation for IPv6.
- *
- * Copyright (C) 2002 USAGI/WIDE Project
- * Copyright (c) 2004-2006 Herbert Xu <herbert@gondor.apana.org.au>
- */
-
-#include <linux/gfp.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/stringify.h>
-#include <net/dsfield.h>
-#include <net/dst.h>
-#include <net/inet_ecn.h>
-#include <net/ip6_route.h>
-#include <net/ipv6.h>
-#include <net/xfrm.h>
-
-/* Add encapsulation header.
- *
- * The top IP header will be constructed per RFC 2401.
- */
-static struct xfrm_mode xfrm6_tunnel_mode = {
-	.owner = THIS_MODULE,
-	.encap = XFRM_MODE_TUNNEL,
-	.flags = XFRM_MODE_FLAG_TUNNEL,
-	.family = AF_INET6,
-};
-
-static int __init xfrm6_mode_tunnel_init(void)
-{
-	return xfrm_register_mode(&xfrm6_tunnel_mode);
-}
-
-static void __exit xfrm6_mode_tunnel_exit(void)
-{
-	xfrm_unregister_mode(&xfrm6_tunnel_mode);
-}
-
-module_init(xfrm6_mode_tunnel_init);
-module_exit(xfrm6_mode_tunnel_exit);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_XFRM_MODE(AF_INET6, XFRM_MODE_TUNNEL);
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 74b53c13279b..b5a31c8e2088 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -351,7 +351,7 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x,
 
 static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-	struct xfrm_mode *inner_mode = x->inner_mode;
+	const struct xfrm_mode *inner_mode = x->inner_mode;
 	const struct xfrm_state_afinfo *afinfo;
 	int err = -EAFNOSUPPORT;
 
@@ -394,7 +394,6 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
  */
 static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-#if IS_ENABLED(CONFIG_INET_XFRM_MODE_TRANSPORT)
 	int ihl = skb->data - skb_transport_header(skb);
 
 	if (skb->transport_header != skb->network_header) {
@@ -405,14 +404,11 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 	ip_hdr(skb)->tot_len = htons(skb->len + ihl);
 	skb_reset_transport_header(skb);
 	return 0;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
 static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-#if IS_ENABLED(CONFIG_INET6_XFRM_MODE_TRANSPORT)
+#if IS_ENABLED(CONFIG_IPV6)
 	int ihl = skb->data - skb_transport_header(skb);
 
 	if (skb->transport_header != skb->network_header) {
@@ -425,7 +421,8 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 	skb_reset_transport_header(skb);
 	return 0;
 #else
-	return -EOPNOTSUPP;
+	WARN_ON_ONCE(1);
+	return -EAFNOSUPPORT;
 #endif
 }
 
@@ -458,12 +455,12 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 {
 	const struct xfrm_state_afinfo *afinfo;
 	struct net *net = dev_net(skb->dev);
+	const struct xfrm_mode *inner_mode;
 	int err;
 	__be32 seq;
 	__be32 seq_hi;
 	struct xfrm_state *x = NULL;
 	xfrm_address_t *daddr;
-	struct xfrm_mode *inner_mode;
 	u32 mark = skb->mark;
 	unsigned int family = AF_UNSPEC;
 	int decaps = 0;
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 93efb0965e7d..4fc49dbf3edf 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -244,8 +244,8 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet)
 
 static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
 {
+	const struct xfrm_mode *inner_mode;
 	struct pcpu_sw_netstats *tstats;
-	struct xfrm_mode *inner_mode;
 	struct net_device *dev;
 	struct xfrm_state *x;
 	struct xfrm_if *xi;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 17c4f58d28ea..3cb2a328a8ab 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -61,7 +61,6 @@ static struct dst_entry *skb_dst_pop(struct sk_buff *skb)
  */
 static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 {
-#if IS_ENABLED(CONFIG_INET_XFRM_MODE_TRANSPORT)
 	struct iphdr *iph = ip_hdr(skb);
 	int ihl = iph->ihl * 4;
 
@@ -74,10 +73,6 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	__skb_pull(skb, ihl);
 	memmove(skb_network_header(skb), iph, ihl);
 	return 0;
-#else
-	WARN_ON_ONCE(1);
-	return -EOPNOTSUPP;
-#endif
 }
 
 /* Add encapsulation header.
@@ -87,7 +82,7 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
  */
 static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 {
-#if IS_ENABLED(CONFIG_INET6_XFRM_MODE_TRANSPORT)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct ipv6hdr *iph;
 	u8 *prevhdr;
 	int hdr_len;
@@ -107,7 +102,7 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 #else
 	WARN_ON_ONCE(1);
-	return -EOPNOTSUPP;
+	return -EAFNOSUPPORT;
 #endif
 }
 
@@ -118,7 +113,7 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
  */
 static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
 {
-#if IS_ENABLED(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct ipv6hdr *iph;
 	u8 *prevhdr;
 	int hdr_len;
@@ -140,7 +135,7 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 #else
 	WARN_ON_ONCE(1);
-	return -EOPNOTSUPP;
+	return -EAFNOSUPPORT;
 #endif
 }
 
@@ -624,7 +619,7 @@ EXPORT_SYMBOL_GPL(xfrm_output);
 static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	const struct xfrm_state_afinfo *afinfo;
-	struct xfrm_mode *inner_mode;
+	const struct xfrm_mode *inner_mode;
 	int err = -EAFNOSUPPORT;
 
 	if (x->sel.family == AF_UNSPEC)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 67122beb116c..1a5fd2296556 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2546,10 +2546,10 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 					    struct dst_entry *dst)
 {
 	const struct xfrm_state_afinfo *afinfo;
+	const struct xfrm_mode *inner_mode;
 	struct net *net = xp_net(policy);
 	unsigned long now = jiffies;
 	struct net_device *dev;
-	struct xfrm_mode *inner_mode;
 	struct xfrm_dst *xdst_prev = NULL;
 	struct xfrm_dst *xdst0 = NULL;
 	int i = 0;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 358b09f0d018..ace26f6dc790 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -330,92 +330,67 @@ static void xfrm_put_type_offload(const struct xfrm_type_offload *type)
 	module_put(type->owner);
 }
 
-static DEFINE_SPINLOCK(xfrm_mode_lock);
-int xfrm_register_mode(struct xfrm_mode *mode)
-{
-	struct xfrm_state_afinfo *afinfo;
-	struct xfrm_mode **modemap;
-	int err;
-
-	if (unlikely(mode->encap >= XFRM_MODE_MAX))
-		return -EINVAL;
-
-	afinfo = xfrm_state_get_afinfo(mode->family);
-	if (unlikely(afinfo == NULL))
-		return -EAFNOSUPPORT;
-
-	err = -EEXIST;
-	modemap = afinfo->mode_map;
-	spin_lock_bh(&xfrm_mode_lock);
-	if (modemap[mode->encap])
-		goto out;
-
-	err = -ENOENT;
-	if (!try_module_get(afinfo->owner))
-		goto out;
-
-	modemap[mode->encap] = mode;
-	err = 0;
-
-out:
-	spin_unlock_bh(&xfrm_mode_lock);
-	rcu_read_unlock();
-	return err;
-}
-EXPORT_SYMBOL(xfrm_register_mode);
-
-void xfrm_unregister_mode(struct xfrm_mode *mode)
-{
-	struct xfrm_state_afinfo *afinfo;
-	struct xfrm_mode **modemap;
-
-	afinfo = xfrm_state_get_afinfo(mode->family);
-	if (WARN_ON_ONCE(!afinfo))
-		return;
-
-	modemap = afinfo->mode_map;
-	spin_lock_bh(&xfrm_mode_lock);
-	if (likely(modemap[mode->encap] == mode)) {
-		modemap[mode->encap] = NULL;
-		module_put(afinfo->owner);
-	}
-
-	spin_unlock_bh(&xfrm_mode_lock);
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL(xfrm_unregister_mode);
-
-static struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
-{
-	struct xfrm_state_afinfo *afinfo;
-	struct xfrm_mode *mode;
-	int modload_attempted = 0;
+static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = {
+	[XFRM_MODE_BEET] = {
+		.encap = XFRM_MODE_BEET,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET,
+	},
+	[XFRM_MODE_TRANSPORT] = {
+		.encap = XFRM_MODE_TRANSPORT,
+		.family = AF_INET,
+	},
+	[XFRM_MODE_TUNNEL] = {
+		.encap = XFRM_MODE_TUNNEL,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET,
+	},
+};
+
+static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = {
+	[XFRM_MODE_BEET] = {
+		.encap = XFRM_MODE_BEET,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET6,
+	},
+	[XFRM_MODE_ROUTEOPTIMIZATION] = {
+		.encap = XFRM_MODE_ROUTEOPTIMIZATION,
+		.family = AF_INET6,
+	},
+	[XFRM_MODE_TRANSPORT] = {
+		.encap = XFRM_MODE_TRANSPORT,
+		.family = AF_INET6,
+	},
+	[XFRM_MODE_TUNNEL] = {
+		.encap = XFRM_MODE_TUNNEL,
+		.flags = XFRM_MODE_FLAG_TUNNEL,
+		.family = AF_INET6,
+	},
+};
+
+static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
+{
+	const struct xfrm_mode *mode;
 
 	if (unlikely(encap >= XFRM_MODE_MAX))
 		return NULL;
 
-retry:
-	afinfo = xfrm_state_get_afinfo(family);
-	if (unlikely(afinfo == NULL))
-		return NULL;
-
-	mode = READ_ONCE(afinfo->mode_map[encap]);
-	if (unlikely(mode && !try_module_get(mode->owner)))
-		mode = NULL;
-
-	rcu_read_unlock();
-	if (!mode && !modload_attempted) {
-		request_module("xfrm-mode-%d-%d", family, encap);
-		modload_attempted = 1;
-		goto retry;
+	switch (family) {
+	case AF_INET:
+		mode = &xfrm4_mode_map[encap];
+		if (mode->family == family)
+			return mode;
+		break;
+	case AF_INET6:
+		mode = &xfrm6_mode_map[encap];
+		if (mode->family == family)
+			return mode;
+		break;
+	default:
+		break;
 	}
 
-	return mode;
-}
-
-static void xfrm_put_mode(struct xfrm_mode *mode)
-{
-	module_put(mode->owner);
+	return NULL;
 }
 
 void xfrm_state_free(struct xfrm_state *x)
@@ -436,12 +411,6 @@ static void ___xfrm_state_destroy(struct xfrm_state *x)
 	kfree(x->coaddr);
 	kfree(x->replay_esn);
 	kfree(x->preplay_esn);
-	if (x->inner_mode)
-		xfrm_put_mode(x->inner_mode);
-	if (x->inner_mode_iaf)
-		xfrm_put_mode(x->inner_mode_iaf);
-	if (x->outer_mode)
-		xfrm_put_mode(x->outer_mode);
 	if (x->type_offload)
 		xfrm_put_type_offload(x->type_offload);
 	if (x->type) {
@@ -2235,8 +2204,8 @@ int xfrm_state_mtu(struct xfrm_state *x, int mtu)
 
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 {
-	struct xfrm_state_afinfo *afinfo;
-	struct xfrm_mode *inner_mode;
+	const struct xfrm_mode *inner_mode;
+	const struct xfrm_state_afinfo *afinfo;
 	int family = x->props.family;
 	int err;
 
@@ -2262,24 +2231,21 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 			goto error;
 
 		if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) &&
-		    family != x->sel.family) {
-			xfrm_put_mode(inner_mode);
+		    family != x->sel.family)
 			goto error;
-		}
 
 		x->inner_mode = inner_mode;
 	} else {
-		struct xfrm_mode *inner_mode_iaf;
+		const struct xfrm_mode *inner_mode_iaf;
 		int iafamily = AF_INET;
 
 		inner_mode = xfrm_get_mode(x->props.mode, x->props.family);
 		if (inner_mode == NULL)
 			goto error;
 
-		if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL)) {
-			xfrm_put_mode(inner_mode);
+		if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL))
 			goto error;
-		}
+
 		x->inner_mode = inner_mode;
 
 		if (x->props.family == AF_INET)
@@ -2289,8 +2255,6 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 		if (inner_mode_iaf) {
 			if (inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL)
 				x->inner_mode_iaf = inner_mode_iaf;
-			else
-				xfrm_put_mode(inner_mode_iaf);
 		}
 	}
 
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index e9c860d00416..474040448601 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -7,9 +7,7 @@ CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_IPV6=y
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_VETH=y
-CONFIG_INET_XFRM_MODE_TUNNEL=y
 CONFIG_NET_IPVTI=y
-CONFIG_INET6_XFRM_MODE_TUNNEL=y
 CONFIG_IPV6_VTI=y
 CONFIG_DUMMY=y
 CONFIG_BRIDGE=y
-- 
cgit v1.2.3


From c9500d7b7de8ff6ac88ee3e38b782889f1616593 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Mar 2019 21:16:32 +0100
Subject: xfrm: store xfrm_mode directly, not its address

This structure is now only 4 bytes, so its more efficient
to cache a copy rather than its address.

No significant size difference in allmodconfig vmlinux.

With non-modular kernel that has all XFRM options enabled, this
series reduces vmlinux image size by ~11kb. All xfrm_mode
indirections are gone and all modes are built-in.

before (ipsec-next master):
    text      data      bss         dec   filename
21071494   7233140 11104324    39408958   vmlinux.master

after this series:
21066448   7226772 11104324    39397544   vmlinux.patched

With allmodconfig kernel, the size increase is only 362 bytes,
even all the xfrm config options removed in this series are
modular.

before:
    text      data     bss      dec   filename
15731286   6936912 4046908 26715106   vmlinux.master

after this series:
15731492   6937068  4046908  26715468 vmlinux

Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h        | 34 +++++++++++++++++-----------------
 net/ipv4/esp4_offload.c   |  2 +-
 net/ipv4/ip_vti.c         |  2 +-
 net/ipv4/xfrm4_output.c   |  2 +-
 net/ipv6/esp6_offload.c   |  2 +-
 net/ipv6/ip6_vti.c        |  2 +-
 net/ipv6/xfrm6_output.c   |  2 +-
 net/xfrm/xfrm_device.c    | 10 +++++-----
 net/xfrm/xfrm_input.c     | 14 +++++++-------
 net/xfrm/xfrm_interface.c |  2 +-
 net/xfrm/xfrm_output.c    | 20 ++++++++++----------
 net/xfrm/xfrm_policy.c    |  2 +-
 net/xfrm/xfrm_state.c     | 16 ++++++++--------
 13 files changed, 55 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 4ca79cdc3460..77eb578a0384 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -132,6 +132,17 @@ struct xfrm_state_offload {
 	u8			flags;
 };
 
+struct xfrm_mode {
+	u8 encap;
+	u8 family;
+	u8 flags;
+};
+
+/* Flags for xfrm_mode. */
+enum {
+	XFRM_MODE_FLAG_TUNNEL = 1,
+};
+
 /* Full description of state of transformer. */
 struct xfrm_state {
 	possible_net_t		xs_net;
@@ -234,9 +245,9 @@ struct xfrm_state {
 	/* Reference to data common to all the instances of this
 	 * transformer. */
 	const struct xfrm_type	*type;
-	const struct xfrm_mode	*inner_mode;
-	const struct xfrm_mode	*inner_mode_iaf;
-	const struct xfrm_mode	*outer_mode;
+	struct xfrm_mode	inner_mode;
+	struct xfrm_mode	inner_mode_iaf;
+	struct xfrm_mode	outer_mode;
 
 	const struct xfrm_type_offload	*type_offload;
 
@@ -421,17 +432,6 @@ struct xfrm_type_offload {
 int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 
-struct xfrm_mode {
-	u8 encap;
-	u8 family;
-	u8 flags;
-};
-
-/* Flags for xfrm_mode. */
-enum {
-	XFRM_MODE_FLAG_TUNNEL = 1,
-};
-
 static inline int xfrm_af2proto(unsigned int family)
 {
 	switch(family) {
@@ -448,9 +448,9 @@ static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, i
 {
 	if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) ||
 	    (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6))
-		return x->inner_mode;
+		return &x->inner_mode;
 	else
-		return x->inner_mode_iaf;
+		return &x->inner_mode_iaf;
 }
 
 struct xfrm_tmpl {
@@ -1990,7 +1990,7 @@ static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
 			tunnel = true;
 		break;
 	}
-	if (tunnel && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL))
+	if (tunnel && !(x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL))
 		return -EINVAL;
 
 	return 0;
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 74d59e0177a7..b61a8ff558f9 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -135,7 +135,7 @@ static struct sk_buff *xfrm4_outer_mode_gso_segment(struct xfrm_state *x,
 						    struct sk_buff *skb,
 						    netdev_features_t features)
 {
-	switch (x->outer_mode->encap) {
+	switch (x->outer_mode.encap) {
 	case XFRM_MODE_TUNNEL:
 		return xfrm4_tunnel_gso_segment(x, skb, features);
 	case XFRM_MODE_TRANSPORT:
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 91926c9a3bc9..cc5d9c0a8a10 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -126,7 +126,7 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
 
 	x = xfrm_input_state(skb);
 
-	inner_mode = x->inner_mode;
+	inner_mode = &x->inner_mode;
 
 	if (x->sel.family == AF_UNSPEC) {
 		inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 7c3df14daef3..9bb8905088c7 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -83,7 +83,7 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 #endif
 
 	rcu_read_lock();
-	afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode->family);
+	afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode.family);
 	if (likely(afinfo))
 		ret = afinfo->output_finish(sk, skb);
 	else
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index c793a2ace77d..bff83279d76f 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -162,7 +162,7 @@ static struct sk_buff *xfrm6_outer_mode_gso_segment(struct xfrm_state *x,
 						    struct sk_buff *skb,
 						    netdev_features_t features)
 {
-	switch (x->outer_mode->encap) {
+	switch (x->outer_mode.encap) {
 	case XFRM_MODE_TUNNEL:
 		return xfrm6_tunnel_gso_segment(x, skb, features);
 	case XFRM_MODE_TRANSPORT:
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 71ec5e60cf8f..218a0dedc8f4 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -361,7 +361,7 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
 
 	x = xfrm_input_state(skb);
 
-	inner_mode = x->inner_mode;
+	inner_mode = &x->inner_mode;
 
 	if (x->sel.family == AF_UNSPEC) {
 		inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 455fbf3b91cf..8ad5e54eb8ca 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -129,7 +129,7 @@ static int __xfrm6_output_state_finish(struct xfrm_state *x, struct sock *sk,
 	int ret = -EAFNOSUPPORT;
 
 	rcu_read_lock();
-	afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode->family);
+	afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode.family);
 	if (likely(afinfo))
 		ret = afinfo->output_finish(sk, skb);
 	else
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index a20f376fe71f..b24cd86a02c3 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -53,20 +53,20 @@ static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
 /* Adjust pointers into the packet when IPsec is done at layer2 */
 static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb)
 {
-	switch (x->outer_mode->encap) {
+	switch (x->outer_mode.encap) {
 	case XFRM_MODE_TUNNEL:
-		if (x->outer_mode->family == AF_INET)
+		if (x->outer_mode.family == AF_INET)
 			return __xfrm_mode_tunnel_prep(x, skb,
 						       sizeof(struct iphdr));
-		if (x->outer_mode->family == AF_INET6)
+		if (x->outer_mode.family == AF_INET6)
 			return __xfrm_mode_tunnel_prep(x, skb,
 						       sizeof(struct ipv6hdr));
 		break;
 	case XFRM_MODE_TRANSPORT:
-		if (x->outer_mode->family == AF_INET)
+		if (x->outer_mode.family == AF_INET)
 			return __xfrm_transport_prep(x, skb,
 						     sizeof(struct iphdr));
-		if (x->outer_mode->family == AF_INET6)
+		if (x->outer_mode.family == AF_INET6)
 			return __xfrm_transport_prep(x, skb,
 						     sizeof(struct ipv6hdr));
 		break;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index b5a31c8e2088..314973aaa414 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -351,12 +351,12 @@ xfrm_inner_mode_encap_remove(struct xfrm_state *x,
 
 static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-	const struct xfrm_mode *inner_mode = x->inner_mode;
+	const struct xfrm_mode *inner_mode = &x->inner_mode;
 	const struct xfrm_state_afinfo *afinfo;
 	int err = -EAFNOSUPPORT;
 
 	rcu_read_lock();
-	afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode->family);
+	afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode.family);
 	if (likely(afinfo))
 		err = afinfo->extract_input(x, skb);
 
@@ -482,7 +482,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 			goto drop;
 		}
 
-		family = x->outer_mode->family;
+		family = x->outer_mode.family;
 
 		/* An encap_type of -1 indicates async resumption. */
 		if (encap_type == -1) {
@@ -666,7 +666,7 @@ resume:
 
 		XFRM_MODE_SKB_CB(skb)->protocol = nexthdr;
 
-		inner_mode = x->inner_mode;
+		inner_mode = &x->inner_mode;
 
 		if (x->sel.family == AF_UNSPEC) {
 			inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
@@ -681,7 +681,7 @@ resume:
 			goto drop;
 		}
 
-		if (x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) {
+		if (x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL) {
 			decaps = 1;
 			break;
 		}
@@ -691,7 +691,7 @@ resume:
 		 * transport mode so the outer address is identical.
 		 */
 		daddr = &x->id.daddr;
-		family = x->outer_mode->family;
+		family = x->outer_mode.family;
 
 		err = xfrm_parse_spi(skb, nexthdr, &spi, &seq);
 		if (err < 0) {
@@ -721,7 +721,7 @@ resume:
 
 		err = -EAFNOSUPPORT;
 		rcu_read_lock();
-		afinfo = xfrm_state_afinfo_get_rcu(x->inner_mode->family);
+		afinfo = xfrm_state_afinfo_get_rcu(x->inner_mode.family);
 		if (likely(afinfo))
 			err = afinfo->transport_finish(skb, xfrm_gro || async);
 		rcu_read_unlock();
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 4fc49dbf3edf..b9f118530db6 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -273,7 +273,7 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
 	xnet = !net_eq(xi->net, dev_net(skb->dev));
 
 	if (xnet) {
-		inner_mode = x->inner_mode;
+		inner_mode = &x->inner_mode;
 
 		if (x->sel.family == AF_UNSPEC) {
 			inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 3cb2a328a8ab..a55510f9ff35 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -334,7 +334,7 @@ static int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
 	skb->protocol = htons(ETH_P_IP);
 
-	switch (x->outer_mode->encap) {
+	switch (x->outer_mode.encap) {
 	case XFRM_MODE_BEET:
 		return xfrm4_beet_encap_add(x, skb);
 	case XFRM_MODE_TUNNEL:
@@ -357,7 +357,7 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	skb->ignore_df = 1;
 	skb->protocol = htons(ETH_P_IPV6);
 
-	switch (x->outer_mode->encap) {
+	switch (x->outer_mode.encap) {
 	case XFRM_MODE_BEET:
 		return xfrm6_beet_encap_add(x, skb);
 	case XFRM_MODE_TUNNEL:
@@ -373,22 +373,22 @@ static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 
 static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
 {
-	switch (x->outer_mode->encap) {
+	switch (x->outer_mode.encap) {
 	case XFRM_MODE_BEET:
 	case XFRM_MODE_TUNNEL:
-		if (x->outer_mode->family == AF_INET)
+		if (x->outer_mode.family == AF_INET)
 			return xfrm4_prepare_output(x, skb);
-		if (x->outer_mode->family == AF_INET6)
+		if (x->outer_mode.family == AF_INET6)
 			return xfrm6_prepare_output(x, skb);
 		break;
 	case XFRM_MODE_TRANSPORT:
-		if (x->outer_mode->family == AF_INET)
+		if (x->outer_mode.family == AF_INET)
 			return xfrm4_transport_output(x, skb);
-		if (x->outer_mode->family == AF_INET6)
+		if (x->outer_mode.family == AF_INET6)
 			return xfrm6_transport_output(x, skb);
 		break;
 	case XFRM_MODE_ROUTEOPTIMIZATION:
-		if (x->outer_mode->family == AF_INET6)
+		if (x->outer_mode.family == AF_INET6)
 			return xfrm6_ro_output(x, skb);
 		WARN_ON_ONCE(1);
 		break;
@@ -489,7 +489,7 @@ resume:
 		}
 		skb_dst_set(skb, dst);
 		x = dst->xfrm;
-	} while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL));
+	} while (x && !(x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL));
 
 	return 0;
 
@@ -626,7 +626,7 @@ static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 		inner_mode = xfrm_ip2inner_mode(x,
 				xfrm_af2proto(skb_dst(skb)->ops->family));
 	else
-		inner_mode = x->inner_mode;
+		inner_mode = &x->inner_mode;
 
 	if (inner_mode == NULL)
 		return -EAFNOSUPPORT;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 1a5fd2296556..16e70fc547b1 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2595,7 +2595,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 				goto put_states;
 			}
 		} else
-			inner_mode = xfrm[i]->inner_mode;
+			inner_mode = &xfrm[i]->inner_mode;
 
 		xdst->route = dst;
 		dst_copy_metrics(dst1, dst);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index ace26f6dc790..d3d87c409f44 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -551,8 +551,6 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 		x->lft.hard_packet_limit = XFRM_INF;
 		x->replay_maxage = 0;
 		x->replay_maxdiff = 0;
-		x->inner_mode = NULL;
-		x->inner_mode_iaf = NULL;
 		spin_lock_init(&x->lock);
 	}
 	return x;
@@ -2204,8 +2202,9 @@ int xfrm_state_mtu(struct xfrm_state *x, int mtu)
 
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 {
-	const struct xfrm_mode *inner_mode;
 	const struct xfrm_state_afinfo *afinfo;
+	const struct xfrm_mode *inner_mode;
+	const struct xfrm_mode *outer_mode;
 	int family = x->props.family;
 	int err;
 
@@ -2234,7 +2233,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 		    family != x->sel.family)
 			goto error;
 
-		x->inner_mode = inner_mode;
+		x->inner_mode = *inner_mode;
 	} else {
 		const struct xfrm_mode *inner_mode_iaf;
 		int iafamily = AF_INET;
@@ -2246,7 +2245,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 		if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL))
 			goto error;
 
-		x->inner_mode = inner_mode;
+		x->inner_mode = *inner_mode;
 
 		if (x->props.family == AF_INET)
 			iafamily = AF_INET6;
@@ -2254,7 +2253,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 		inner_mode_iaf = xfrm_get_mode(x->props.mode, iafamily);
 		if (inner_mode_iaf) {
 			if (inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL)
-				x->inner_mode_iaf = inner_mode_iaf;
+				x->inner_mode_iaf = *inner_mode_iaf;
 		}
 	}
 
@@ -2268,12 +2267,13 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 	if (err)
 		goto error;
 
-	x->outer_mode = xfrm_get_mode(x->props.mode, family);
-	if (x->outer_mode == NULL) {
+	outer_mode = xfrm_get_mode(x->props.mode, family);
+	if (!outer_mode) {
 		err = -EPROTONOSUPPORT;
 		goto error;
 	}
 
+	x->outer_mode = *outer_mode;
 	if (init_replay) {
 		err = xfrm_init_replay(x);
 		if (err)
-- 
cgit v1.2.3


From 1e1b11b6a1111cd9e8af1fd6ccda270a9fa3eacf Mon Sep 17 00:00:00 2001
From: vamsi krishna <vamsin@codeaurora.org>
Date: Fri, 1 Feb 2019 18:34:51 +0530
Subject: nl80211/cfg80211: Specify band specific min RSSI thresholds with
 sched scan

This commit adds the support to specify the RSSI thresholds per
band for each match set. This enhances the current behavior which
specifies a single rssi_threshold across all the bands by
introducing the rssi_threshold_per_band. These per band rssi
thresholds are referred through NL80211_BAND_* (enum nl80211_band)
variables  as attribute types. Such attributes/values per each
band are nested through NL80211_ATTR_SCHED_SCAN_MIN_RSSI.
These band specific rssi thresholds shall take precedence over
the current rssi_thold per match set.
Drivers indicate this support through
%NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD.
These per band rssi attributes/values does not specify
"default RSSI filter" as done by
NL80211_SCHED_SCAN_MATCH_ATTR_RSSI to stay backward compatible.
That said, these per band rssi values have to be specified for
the corresponding matchset.

Signed-off-by: vamsi krishna <vamsin@codeaurora.org>
Signed-off-by: Srinivas Dasari <dasaris@codeaurora.org>
[rebase on refactoring, add policy]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  8 +++++++
 include/uapi/linux/nl80211.h | 13 +++++++++++
 net/wireless/nl80211.c       | 53 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 74 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index bb307a11ee63..b13234a486e7 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1832,11 +1832,19 @@ static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask)
  * @bssid: BSSID to be matched; may be all-zero BSSID in case of SSID match
  *	or no match (RSSI only)
  * @rssi_thold: don't report scan results below this threshold (in s32 dBm)
+ * @per_band_rssi_thold: Minimum rssi threshold for each band to be applied
+ *	for filtering out scan results received. Drivers advertize this support
+ *	of band specific rssi based filtering through the feature capability
+ *	%NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD. These band
+ *	specific rssi thresholds take precedence over rssi_thold, if specified.
+ *	If not specified for any band, it will be assigned with rssi_thold of
+ *	corresponding matchset.
  */
 struct cfg80211_match_set {
 	struct cfg80211_ssid ssid;
 	u8 bssid[ETH_ALEN];
 	s32 rssi_thold;
+	s32 per_band_rssi_thold[NUM_NL80211_BANDS];
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index dd4f86ee286e..4a9404958fbe 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3638,6 +3638,14 @@ enum nl80211_reg_rule_attr {
  *	value as specified by &struct nl80211_bss_select_rssi_adjust.
  * @NL80211_SCHED_SCAN_MATCH_ATTR_BSSID: BSSID to be used for matching
  *	(this cannot be used together with SSID).
+ * @NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI: Nested attribute that carries the
+ *	band specific minimum rssi thresholds for the bands defined in
+ *	enum nl80211_band. The minimum rssi threshold value(s32) specific to a
+ *	band shall be encapsulated in attribute with type value equals to one
+ *	of the NL80211_BAND_* defined in enum nl80211_band. For example, the
+ *	minimum rssi threshold value for 2.4GHZ band shall be encapsulated
+ *	within an attribute of type NL80211_BAND_2GHZ. And one or more of such
+ *	attributes will be nested within this attribute.
  * @NL80211_SCHED_SCAN_MATCH_ATTR_MAX: highest scheduled scan filter
  *	attribute number currently defined
  * @__NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST: internal use
@@ -3650,6 +3658,7 @@ enum nl80211_sched_scan_match_attr {
 	NL80211_SCHED_SCAN_MATCH_ATTR_RELATIVE_RSSI,
 	NL80211_SCHED_SCAN_MATCH_ATTR_RSSI_ADJUST,
 	NL80211_SCHED_SCAN_MATCH_ATTR_BSSID,
+	NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI,
 
 	/* keep last */
 	__NL80211_SCHED_SCAN_MATCH_ATTR_AFTER_LAST,
@@ -5343,6 +5352,9 @@ enum nl80211_feature_flags {
  * @NL80211_EXT_FEATURE_AP_PMKSA_CACHING: Driver/device supports PMKSA caching
  *	(set/del PMKSA operations) in AP mode.
  *
+ * @NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD: Driver supports
+ *	filtering of sched scan results using band specific RSSI thresholds.
+ *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
  */
@@ -5384,6 +5396,7 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_ENABLE_FTM_RESPONDER,
 	NL80211_EXT_FEATURE_AIRTIME_FAIRNESS,
 	NL80211_EXT_FEATURE_AP_PMKSA_CACHING,
+	NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5c49d11fc477..62f96d6c02f0 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -617,12 +617,21 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = {
 	[NL80211_REKEY_DATA_REPLAY_CTR] = { .len = NL80211_REPLAY_CTR_LEN },
 };
 
+static const struct nla_policy
+nl80211_match_band_rssi_policy[NUM_NL80211_BANDS] = {
+	[NL80211_BAND_2GHZ] = { .type = NLA_S32 },
+	[NL80211_BAND_5GHZ] = { .type = NLA_S32 },
+	[NL80211_BAND_60GHZ] = { .type = NLA_S32 },
+};
+
 static const struct nla_policy
 nl80211_match_policy[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1] = {
 	[NL80211_SCHED_SCAN_MATCH_ATTR_SSID] = { .type = NLA_BINARY,
 						 .len = IEEE80211_MAX_SSID_LEN },
 	[NL80211_SCHED_SCAN_MATCH_ATTR_BSSID] = { .len = ETH_ALEN },
 	[NL80211_SCHED_SCAN_MATCH_ATTR_RSSI] = { .type = NLA_U32 },
+	[NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI] =
+		NLA_POLICY_NESTED(nl80211_match_band_rssi_policy),
 };
 
 static const struct nla_policy
@@ -7537,6 +7546,41 @@ nl80211_parse_sched_scan_plans(struct wiphy *wiphy, int n_plans,
 	return 0;
 }
 
+static int
+nl80211_parse_sched_scan_per_band_rssi(struct wiphy *wiphy,
+				       struct cfg80211_match_set *match_sets,
+				       struct nlattr *tb_band_rssi,
+				       s32 rssi_thold)
+{
+	struct nlattr *attr;
+	int i, tmp, ret = 0;
+
+	if (!wiphy_ext_feature_isset(wiphy,
+		    NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD)) {
+		if (tb_band_rssi)
+			ret = -EOPNOTSUPP;
+		else
+			for (i = 0; i < NUM_NL80211_BANDS; i++)
+				match_sets->per_band_rssi_thold[i] =
+					NL80211_SCAN_RSSI_THOLD_OFF;
+		return ret;
+	}
+
+	for (i = 0; i < NUM_NL80211_BANDS; i++)
+		match_sets->per_band_rssi_thold[i] = rssi_thold;
+
+	nla_for_each_nested(attr, tb_band_rssi, tmp) {
+		enum nl80211_band band = nla_type(attr);
+
+		if (band < 0 || band >= NUM_NL80211_BANDS)
+			return -EINVAL;
+
+		match_sets->per_band_rssi_thold[band] =	nla_get_s32(attr);
+	}
+
+	return 0;
+}
+
 static struct cfg80211_sched_scan_request *
 nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 			 struct nlattr **attrs, int max_match_sets)
@@ -7816,6 +7860,15 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 			if (rssi)
 				request->match_sets[i].rssi_thold =
 					nla_get_s32(rssi);
+
+			/* Parse per band RSSI attribute */
+			err = nl80211_parse_sched_scan_per_band_rssi(wiphy,
+				&request->match_sets[i],
+				tb[NL80211_SCHED_SCAN_MATCH_PER_BAND_RSSI],
+				request->match_sets[i].rssi_thold);
+			if (err)
+				goto out_free;
+
 			i++;
 		}
 
-- 
cgit v1.2.3


From ab60633c7136c300f15a390f3469d7c4be15a055 Mon Sep 17 00:00:00 2001
From: Narayanraddi Masti <team.nmasti@gmail.com>
Date: Thu, 7 Feb 2019 12:16:05 -0800
Subject: mac80211: Add support for NL80211_STA_INFO_AIRTIME_LINK_METRIC

Add support for mesh airtime link metric attribute
NL80211_STA_INFO_AIRTIME_LINK_METRIC.

Signed-off-by: Narayanraddi Masti <team.nmasti@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 3 +++
 include/uapi/linux/nl80211.h | 2 ++
 net/mac80211/mesh.h          | 2 ++
 net/mac80211/mesh_hwmp.c     | 4 ++--
 net/mac80211/sta_info.c      | 6 ++++++
 net/wireless/nl80211.c       | 1 +
 6 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index b13234a486e7..5859a5e02454 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1327,6 +1327,7 @@ struct cfg80211_tid_stats {
  * @fcs_err_count: number of packets (MPDUs) received from this station with
  *	an FCS error. This counter should be incremented only when TA of the
  *	received packet with an FCS error matches the peer MAC address.
+ * @airtime_link_metric: mesh airtime link metric.
  */
 struct station_info {
 	u64 filled;
@@ -1381,6 +1382,8 @@ struct station_info {
 
 	u32 rx_mpdu_count;
 	u32 fcs_err_count;
+
+	u32 airtime_link_metric;
 };
 
 #if IS_ENABLED(CONFIG_CFG80211)
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 4a9404958fbe..07457f4aea00 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3139,6 +3139,7 @@ enum nl80211_sta_bss_param {
  * @NL80211_STA_INFO_TX_DURATION: aggregate PPDU duration for all frames
  *	sent to the station (u64, usec)
  * @NL80211_STA_INFO_AIRTIME_WEIGHT: current airtime weight for station (u16)
+ * @NL80211_STA_INFO_AIRTIME_LINK_METRIC: airtime link metric for mesh station
  * @__NL80211_STA_INFO_AFTER_LAST: internal
  * @NL80211_STA_INFO_MAX: highest possible station info attribute
  */
@@ -3184,6 +3185,7 @@ enum nl80211_sta_info {
 	NL80211_STA_INFO_CONNECTED_TO_GATE,
 	NL80211_STA_INFO_TX_DURATION,
 	NL80211_STA_INFO_AIRTIME_WEIGHT,
+	NL80211_STA_INFO_AIRTIME_LINK_METRIC,
 
 	/* keep last */
 	__NL80211_STA_INFO_AFTER_LAST,
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index 574c3891c4b2..88535a2e62bc 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -278,6 +278,8 @@ mesh_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst);
 int mesh_path_add_gate(struct mesh_path *mpath);
 int mesh_path_send_to_gates(struct mesh_path *mpath);
 int mesh_gate_num(struct ieee80211_sub_if_data *sdata);
+u32 airtime_link_metric_get(struct ieee80211_local *local,
+			    struct sta_info *sta);
 
 /* Mesh plinks */
 void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index f7517668e77a..c694c0dd907e 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -318,8 +318,8 @@ void ieee80211s_update_metric(struct ieee80211_local *local,
 				  cfg80211_calculate_bitrate(&rinfo));
 }
 
-static u32 airtime_link_metric_get(struct ieee80211_local *local,
-				   struct sta_info *sta)
+u32 airtime_link_metric_get(struct ieee80211_local *local,
+			    struct sta_info *sta)
 {
 	/* This should be adjusted for each device */
 	int device_constant = 1 << ARITH_SHIFT;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 11f058987a54..a81e1279a76d 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -2373,6 +2373,12 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 		sinfo->filled |=
 			BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG);
 	}
+
+	if (ieee80211_vif_is_mesh(&sdata->vif)) {
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_LINK_METRIC);
+		sinfo->airtime_link_metric =
+			airtime_link_metric_get(local, sta);
+	}
 }
 
 u32 sta_get_expected_throughput(struct sta_info *sta)
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 62f96d6c02f0..7556c0479b3c 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4898,6 +4898,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	PUT_SINFO(TX_RETRIES, tx_retries, u32);
 	PUT_SINFO(TX_FAILED, tx_failed, u32);
 	PUT_SINFO(EXPECTED_THROUGHPUT, expected_throughput, u32);
+	PUT_SINFO(AIRTIME_LINK_METRIC, airtime_link_metric, u32);
 	PUT_SINFO(BEACON_LOSS, beacon_loss_count, u32);
 	PUT_SINFO(LOCAL_PM, local_pm, u32);
 	PUT_SINFO(PEER_PM, peer_pm, u32);
-- 
cgit v1.2.3


From cb74e9775871f8c82a1297cf76209f10ab5bbe3d Mon Sep 17 00:00:00 2001
From: Sunil Dutt <usdutt@codeaurora.org>
Date: Wed, 20 Feb 2019 16:18:07 +0530
Subject: cfg80211/nl80211: Offload OWE processing to user space in AP mode

This interface allows the host driver to offload OWE processing
to user space. This intends to support OWE (Opportunistic Wireless
Encryption) AKM by the drivers that implement SME but rely on the
user space for the cryptographic/OWE processing in AP mode. Such
drivers are not capable of processing/deriving the DH IE.

A new NL80211 command - NL80211_CMD_UPDATE_OWE_INFO is introduced
to send the request/event between the host driver and user space.

Driver shall provide the OWE info (MAC address and DH IE) of
the peer to user space for cryptographic processing of the DH IE
through the event. Accordingly, the user space shall update the
OWE info/DH IE to the driver.

Following is the sequence in AP mode for OWE authentication.

Driver passes the OWE info obtained from the peer in the
Association Request to the user space through the event
cfg80211_update_owe_info_event. User space shall process the
OWE info received and generate new OWE info. This OWE info is
passed to the driver through NL80211_CMD_UPDATE_OWE_INFO
request. Driver eventually uses this OWE info to send the
Association Response to the peer.

This OWE info in the command interface carries the IEs that include
PMKID of the peer if the PMKSA is still valid or an updated DH IE
for generating a new PMKSA with the peer.

Signed-off-by: Liangwei Dong <liangwei@codeaurora.org>
Signed-off-by: Sunil Dutt <usdutt@codeaurora.org>
Signed-off-by: Srinivas Dasari <dasaris@codeaurora.org>
[remove policy initialization - no longer exists]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 42 ++++++++++++++++++++++++++
 include/uapi/linux/nl80211.h |  7 +++++
 net/wireless/nl80211.c       | 72 ++++++++++++++++++++++++++++++++++++++++++++
 net/wireless/rdev-ops.h      | 13 ++++++++
 net/wireless/trace.h         | 38 +++++++++++++++++++++++
 5 files changed, 172 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 5859a5e02454..70432fd638af 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3110,6 +3110,32 @@ struct cfg80211_pmsr_request {
 	struct cfg80211_pmsr_request_peer peers[];
 };
 
+/**
+ * struct cfg80211_update_owe_info - OWE Information
+ *
+ * This structure provides information needed for the drivers to offload OWE
+ * (Opportunistic Wireless Encryption) processing to the user space.
+ *
+ * Commonly used across update_owe_info request and event interfaces.
+ *
+ * @peer: MAC address of the peer device for which the OWE processing
+ *	has to be done.
+ * @status: status code, %WLAN_STATUS_SUCCESS for successful OWE info
+ *	processing, use %WLAN_STATUS_UNSPECIFIED_FAILURE if user space
+ *	cannot give you the real status code for failures. Used only for
+ *	OWE update request command interface (user space to driver).
+ * @ie: IEs obtained from the peer or constructed by the user space. These are
+ *	the IEs of the remote peer in the event from the host driver and
+ *	the constructed IEs by the user space in the request interface.
+ * @ie_len: Length of IEs in octets.
+ */
+struct cfg80211_update_owe_info {
+	u8 peer[ETH_ALEN] __aligned(2);
+	u16 status;
+	const u8 *ie;
+	size_t ie_len;
+};
+
 /**
  * struct cfg80211_ops - backend description for wireless configuration
  *
@@ -3447,6 +3473,10 @@ struct cfg80211_pmsr_request {
  *	Statistics should be cumulative, currently no way to reset is provided.
  * @start_pmsr: start peer measurement (e.g. FTM)
  * @abort_pmsr: abort peer measurement
+ *
+ * @update_owe_info: Provide updated OWE info to driver. Driver implementing SME
+ *	but offloading OWE processing to the user space will get the updated
+ *	DH IE through this interface.
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -3761,6 +3791,8 @@ struct cfg80211_ops {
 			      struct cfg80211_pmsr_request *request);
 	void	(*abort_pmsr)(struct wiphy *wiphy, struct wireless_dev *wdev,
 			      struct cfg80211_pmsr_request *request);
+	int	(*update_owe_info)(struct wiphy *wiphy, struct net_device *dev,
+				   struct cfg80211_update_owe_info *owe_info);
 };
 
 /*
@@ -7219,4 +7251,14 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev,
 #define wiphy_WARN(wiphy, format, args...)			\
 	WARN(1, "wiphy: %s\n" format, wiphy_name(wiphy), ##args);
 
+/**
+ * cfg80211_update_owe_info_event - Notify the peer's OWE info to user space
+ * @netdev: network device
+ * @owe_info: peer's owe info
+ * @gfp: allocation flags
+ */
+void cfg80211_update_owe_info_event(struct net_device *netdev,
+				    struct cfg80211_update_owe_info *owe_info,
+				    gfp_t gfp);
+
 #endif /* __NET_CFG80211_H */
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 07457f4aea00..a99d75bef598 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1065,6 +1065,11 @@
  *	indicated by %NL80211_ATTR_WIPHY_FREQ and other attributes
  *	determining the width and type.
  *
+ * @NL80211_CMD_UPDATE_OWE_INFO: This interface allows the host driver to
+ *	offload OWE processing to user space. This intends to support
+ *	OWE AKM by the host drivers that implement SME but rely
+ *	on the user space for the cryptographic/DH IE processing in AP mode.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -1285,6 +1290,8 @@ enum nl80211_commands {
 
 	NL80211_CMD_NOTIFY_RADAR,
 
+	NL80211_CMD_UPDATE_OWE_INFO,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 7556c0479b3c..0124bab1f8a7 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -13316,6 +13316,31 @@ nla_put_failure:
 	return -ENOBUFS;
 }
 
+static int nl80211_update_owe_info(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct cfg80211_update_owe_info owe_info;
+	struct net_device *dev = info->user_ptr[1];
+
+	if (!rdev->ops->update_owe_info)
+		return -EOPNOTSUPP;
+
+	if (!info->attrs[NL80211_ATTR_STATUS_CODE] ||
+	    !info->attrs[NL80211_ATTR_MAC])
+		return -EINVAL;
+
+	memset(&owe_info, 0, sizeof(owe_info));
+	owe_info.status = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]);
+	nla_memcpy(owe_info.peer, info->attrs[NL80211_ATTR_MAC], ETH_ALEN);
+
+	if (info->attrs[NL80211_ATTR_IE]) {
+		owe_info.ie = nla_data(info->attrs[NL80211_ATTR_IE]);
+		owe_info.ie_len = nla_len(info->attrs[NL80211_ATTR_IE]);
+	}
+
+	return rdev_update_owe_info(rdev, dev, &owe_info);
+}
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -14146,6 +14171,13 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_UPDATE_OWE_INFO,
+		.doit = nl80211_update_owe_info,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 static struct genl_family nl80211_fam __ro_after_init = {
@@ -16318,6 +16350,46 @@ int cfg80211_external_auth_request(struct net_device *dev,
 }
 EXPORT_SYMBOL(cfg80211_external_auth_request);
 
+void cfg80211_update_owe_info_event(struct net_device *netdev,
+				    struct cfg80211_update_owe_info *owe_info,
+				    gfp_t gfp)
+{
+	struct wiphy *wiphy = netdev->ieee80211_ptr->wiphy;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+	struct sk_buff *msg;
+	void *hdr;
+
+	trace_cfg80211_update_owe_info_event(wiphy, netdev, owe_info);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp);
+	if (!msg)
+		return;
+
+	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_UPDATE_OWE_INFO);
+	if (!hdr)
+		goto nla_put_failure;
+
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
+	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) ||
+	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, owe_info->peer))
+		goto nla_put_failure;
+
+	if (!owe_info->ie_len ||
+	    nla_put(msg, NL80211_ATTR_IE, owe_info->ie_len, owe_info->ie))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
+				NL80211_MCGRP_MLME, gfp);
+	return;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	nlmsg_free(msg);
+}
+EXPORT_SYMBOL(cfg80211_update_owe_info_event);
+
 /* initialisation/exit functions */
 
 int __init nl80211_init(void)
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 5cb48d135fab..c1e3210b09e6 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -1272,4 +1272,17 @@ rdev_abort_pmsr(struct cfg80211_registered_device *rdev,
 	trace_rdev_return_void(&rdev->wiphy);
 }
 
+static inline int rdev_update_owe_info(struct cfg80211_registered_device *rdev,
+				       struct net_device *dev,
+				       struct cfg80211_update_owe_info *oweinfo)
+{
+	int ret = -EOPNOTSUPP;
+
+	trace_rdev_update_owe_info(&rdev->wiphy, dev, oweinfo);
+	if (rdev->ops->update_owe_info)
+		ret = rdev->ops->update_owe_info(&rdev->wiphy, dev, oweinfo);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 44b2ce1bb13a..2dda5291fc01 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -3362,6 +3362,44 @@ TRACE_EVENT(cfg80211_pmsr_complete,
 		  WIPHY_PR_ARG, WDEV_PR_ARG,
 		  (unsigned long long)__entry->cookie)
 );
+
+TRACE_EVENT(rdev_update_owe_info,
+	    TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		     struct cfg80211_update_owe_info *owe_info),
+	    TP_ARGS(wiphy, netdev, owe_info),
+	    TP_STRUCT__entry(WIPHY_ENTRY
+			     NETDEV_ENTRY
+			     MAC_ENTRY(peer)
+			     __field(u16, status)
+			     __dynamic_array(u8, ie, owe_info->ie_len)),
+	    TP_fast_assign(WIPHY_ASSIGN;
+			   NETDEV_ASSIGN;
+			   MAC_ASSIGN(peer, owe_info->peer);
+			   __entry->status = owe_info->status;
+			   memcpy(__get_dynamic_array(ie),
+				  owe_info->ie, owe_info->ie_len);),
+	    TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT
+		  " status %d", WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer),
+		  __entry->status)
+);
+
+TRACE_EVENT(cfg80211_update_owe_info_event,
+	    TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		     struct cfg80211_update_owe_info *owe_info),
+	    TP_ARGS(wiphy, netdev, owe_info),
+	    TP_STRUCT__entry(WIPHY_ENTRY
+			     NETDEV_ENTRY
+			     MAC_ENTRY(peer)
+			     __dynamic_array(u8, ie, owe_info->ie_len)),
+	    TP_fast_assign(WIPHY_ASSIGN;
+			   NETDEV_ASSIGN;
+			   MAC_ASSIGN(peer, owe_info->peer);
+			   memcpy(__get_dynamic_array(ie), owe_info->ie,
+				  owe_info->ie_len);),
+	    TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT,
+		      WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer))
+);
+
 #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
-- 
cgit v1.2.3


From fd69c399c7d6262086b6b820757c6aeaa71feeba Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 8 Apr 2019 10:15:59 +0200
Subject: datagram: remove rendundant 'peeked' argument

After commit a297569fe00a ("net/udp: do not touch skb->peeked unless
really needed") the 'peeked' argument of __skb_try_recv_datagram()
and friends is always equal to !!'flags & MSG_PEEK'.

Since such argument is really a boolean info, and the callers have
already 'flags & MSG_PEEK' handy, we can remove it and clean-up the
code a bit.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h |  6 +++---
 include/net/udp.h      |  6 +++---
 net/core/datagram.c    | 19 ++++++++-----------
 net/ipv4/udp.c         | 19 +++++++------------
 net/ipv6/udp.c         | 10 ++++------
 net/unix/af_unix.c     |  6 +++---
 6 files changed, 28 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 69b5538adcea..a06275a618f0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3370,17 +3370,17 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
 					  unsigned int flags,
 					  void (*destructor)(struct sock *sk,
 							   struct sk_buff *skb),
-					  int *peeked, int *off, int *err,
+					  int *off, int *err,
 					  struct sk_buff **last);
 struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags,
 					void (*destructor)(struct sock *sk,
 							   struct sk_buff *skb),
-					int *peeked, int *off, int *err,
+					int *off, int *err,
 					struct sk_buff **last);
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
 				    void (*destructor)(struct sock *sk,
 						       struct sk_buff *skb),
-				    int *peeked, int *off, int *err);
+				    int *off, int *err);
 struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock,
 				  int *err);
 __poll_t datagram_poll(struct file *file, struct socket *sock,
diff --git a/include/net/udp.h b/include/net/udp.h
index fd6d948755c8..d8ce937bc395 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -269,13 +269,13 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
 int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb);
 void udp_skb_destructor(struct sock *sk, struct sk_buff *skb);
 struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
-			       int noblock, int *peeked, int *off, int *err);
+			       int noblock, int *off, int *err);
 static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
 					   int noblock, int *err)
 {
-	int peeked, off = 0;
+	int off = 0;
 
-	return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err);
+	return __skb_recv_udp(sk, flags, noblock, &off, err);
 }
 
 int udp_v4_early_demux(struct sk_buff *skb);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 91bb5a083fee..45a162ef5e02 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -167,7 +167,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
 					  unsigned int flags,
 					  void (*destructor)(struct sock *sk,
 							   struct sk_buff *skb),
-					  int *peeked, int *off, int *err,
+					  int *off, int *err,
 					  struct sk_buff **last)
 {
 	bool peek_at_off = false;
@@ -194,7 +194,6 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
 					return NULL;
 				}
 			}
-			*peeked = 1;
 			refcount_inc(&skb->users);
 		} else {
 			__skb_unlink(skb, queue);
@@ -212,7 +211,6 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
  *	@sk: socket
  *	@flags: MSG\_ flags
  *	@destructor: invoked under the receive lock on successful dequeue
- *	@peeked: returns non-zero if this packet has been seen before
  *	@off: an offset in bytes to peek skb from. Returns an offset
  *	      within an skb where data actually starts
  *	@err: error code returned
@@ -246,7 +244,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk,
 struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 					void (*destructor)(struct sock *sk,
 							   struct sk_buff *skb),
-					int *peeked, int *off, int *err,
+					int *off, int *err,
 					struct sk_buff **last)
 {
 	struct sk_buff_head *queue = &sk->sk_receive_queue;
@@ -260,7 +258,6 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 	if (error)
 		goto no_packet;
 
-	*peeked = 0;
 	do {
 		/* Again only user level code calls this function, so nothing
 		 * interrupt level will suddenly eat the receive_queue.
@@ -270,7 +267,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 		 */
 		spin_lock_irqsave(&queue->lock, cpu_flags);
 		skb = __skb_try_recv_from_queue(sk, queue, flags, destructor,
-						peeked, off, &error, last);
+						off, &error, last);
 		spin_unlock_irqrestore(&queue->lock, cpu_flags);
 		if (error)
 			goto no_packet;
@@ -294,7 +291,7 @@ EXPORT_SYMBOL(__skb_try_recv_datagram);
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 				    void (*destructor)(struct sock *sk,
 						       struct sk_buff *skb),
-				    int *peeked, int *off, int *err)
+				    int *off, int *err)
 {
 	struct sk_buff *skb, *last;
 	long timeo;
@@ -302,8 +299,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
 	do {
-		skb = __skb_try_recv_datagram(sk, flags, destructor, peeked,
-					      off, err, &last);
+		skb = __skb_try_recv_datagram(sk, flags, destructor, off, err,
+					      &last);
 		if (skb)
 			return skb;
 
@@ -319,10 +316,10 @@ EXPORT_SYMBOL(__skb_recv_datagram);
 struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
 				  int noblock, int *err)
 {
-	int peeked, off = 0;
+	int off = 0;
 
 	return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
-				   NULL, &peeked, &off, err);
+				   NULL, &off, err);
 }
 EXPORT_SYMBOL(skb_recv_datagram);
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 372fdc5381a9..3c58ba02af7d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1631,7 +1631,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 EXPORT_SYMBOL(udp_ioctl);
 
 struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
-			       int noblock, int *peeked, int *off, int *err)
+			       int noblock, int *off, int *err)
 {
 	struct sk_buff_head *sk_queue = &sk->sk_receive_queue;
 	struct sk_buff_head *queue;
@@ -1650,13 +1650,11 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
 			break;
 
 		error = -EAGAIN;
-		*peeked = 0;
 		do {
 			spin_lock_bh(&queue->lock);
 			skb = __skb_try_recv_from_queue(sk, queue, flags,
 							udp_skb_destructor,
-							peeked, off, err,
-							&last);
+							off, err, &last);
 			if (skb) {
 				spin_unlock_bh(&queue->lock);
 				return skb;
@@ -1677,8 +1675,7 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
 
 			skb = __skb_try_recv_from_queue(sk, queue, flags,
 							udp_skb_dtor_locked,
-							peeked, off, err,
-							&last);
+							off, err, &last);
 			spin_unlock(&sk_queue->lock);
 			spin_unlock_bh(&queue->lock);
 			if (skb)
@@ -1713,8 +1710,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct sk_buff *skb;
 	unsigned int ulen, copied;
-	int peeked, peeking, off;
-	int err;
+	int off, err, peeking = flags & MSG_PEEK;
 	int is_udplite = IS_UDPLITE(sk);
 	bool checksum_valid = false;
 
@@ -1722,9 +1718,8 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 		return ip_recv_error(sk, msg, len, addr_len);
 
 try_again:
-	peeking = flags & MSG_PEEK;
 	off = sk_peek_offset(sk, flags);
-	skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
+	skb = __skb_recv_udp(sk, flags, noblock, &off, &err);
 	if (!skb)
 		return err;
 
@@ -1762,7 +1757,7 @@ try_again:
 	}
 
 	if (unlikely(err)) {
-		if (!peeked) {
+		if (!peeking) {
 			atomic_inc(&sk->sk_drops);
 			UDP_INC_STATS(sock_net(sk),
 				      UDP_MIB_INERRORS, is_udplite);
@@ -1771,7 +1766,7 @@ try_again:
 		return err;
 	}
 
-	if (!peeked)
+	if (!peeking)
 		UDP_INC_STATS(sock_net(sk),
 			      UDP_MIB_INDATAGRAMS, is_udplite);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index b444483cdb2b..d538fafaf4a9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -285,8 +285,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	struct inet_sock *inet = inet_sk(sk);
 	struct sk_buff *skb;
 	unsigned int ulen, copied;
-	int peeked, peeking, off;
-	int err;
+	int off, err, peeking = flags & MSG_PEEK;
 	int is_udplite = IS_UDPLITE(sk);
 	struct udp_mib __percpu *mib;
 	bool checksum_valid = false;
@@ -299,9 +298,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
 
 try_again:
-	peeking = flags & MSG_PEEK;
 	off = sk_peek_offset(sk, flags);
-	skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
+	skb = __skb_recv_udp(sk, flags, noblock, &off, &err);
 	if (!skb)
 		return err;
 
@@ -340,14 +338,14 @@ try_again:
 			goto csum_copy_err;
 	}
 	if (unlikely(err)) {
-		if (!peeked) {
+		if (!peeking) {
 			atomic_inc(&sk->sk_drops);
 			SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
 		}
 		kfree_skb(skb);
 		return err;
 	}
-	if (!peeked)
+	if (!peeking)
 		SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS);
 
 	sock_recv_ts_and_drops(msg, sk, skb);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ddb838a1b74c..e68d7454f2e3 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2040,8 +2040,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 	struct unix_sock *u = unix_sk(sk);
 	struct sk_buff *skb, *last;
 	long timeo;
+	int skip;
 	int err;
-	int peeked, skip;
 
 	err = -EOPNOTSUPP;
 	if (flags&MSG_OOB)
@@ -2053,8 +2053,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 		mutex_lock(&u->iolock);
 
 		skip = sk_peek_offset(sk, flags);
-		skb = __skb_try_recv_datagram(sk, flags, NULL, &peeked, &skip,
-					      &err, &last);
+		skb = __skb_try_recv_datagram(sk, flags, NULL, &skip, &err,
+					      &last);
 		if (skb)
 			break;
 
-- 
cgit v1.2.3


From 3b15d09f7e6db44065aaba5fd16dc7420035c5ad Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Thu, 28 Feb 2019 13:13:26 +0800
Subject: time: Introduce jiffies64_to_msecs()

there is a similar helper in net/netfilter/nf_tables_api.c,
this maybe become a common request someday, so move it to
time.c

Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Acked-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/jiffies.h       |  1 +
 kernel/time/time.c            | 10 ++++++++++
 net/netfilter/nf_tables_api.c |  4 +---
 3 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index fa928242567d..1b6d31da7cbc 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -297,6 +297,7 @@ static inline u64 jiffies_to_nsecs(const unsigned long j)
 }
 
 extern u64 jiffies64_to_nsecs(u64 j);
+extern u64 jiffies64_to_msecs(u64 j);
 
 extern unsigned long __msecs_to_jiffies(const unsigned int m);
 #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
diff --git a/kernel/time/time.c b/kernel/time/time.c
index c3f756f8534b..9e3f79d4f5a8 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -783,6 +783,16 @@ u64 jiffies64_to_nsecs(u64 j)
 }
 EXPORT_SYMBOL(jiffies64_to_nsecs);
 
+u64 jiffies64_to_msecs(const u64 j)
+{
+#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
+	return (MSEC_PER_SEC / HZ) * j;
+#else
+	return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN);
+#endif
+}
+EXPORT_SYMBOL(jiffies64_to_msecs);
+
 /**
  * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
  *
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 90e6b09ef2af..ee1b0d1445aa 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3193,9 +3193,7 @@ static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result)
 
 static __be64 nf_jiffies64_to_msecs(u64 input)
 {
-	u64 ms = jiffies64_to_nsecs(input);
-
-	return cpu_to_be64(div_u64(ms, NSEC_PER_MSEC));
+	return cpu_to_be64(jiffies64_to_msecs(input));
 }
 
 static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
-- 
cgit v1.2.3


From 84c0d5e96f3ae20344fb3a79161eab18905dae56 Mon Sep 17 00:00:00 2001
From: Jacky Hu <hengqing.hu@gmail.com>
Date: Tue, 26 Mar 2019 18:31:21 +0800
Subject: ipvs: allow tunneling with gue encapsulation

ipip packets are blocked in some public cloud environments, this patch
allows gue encapsulation with the tunneling method, which would make
tunneling working in those environments.

Signed-off-by: Jacky Hu <hengqing.hu@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/ip_vs.h             |  5 +++
 include/uapi/linux/ip_vs.h      | 11 ++++++
 net/netfilter/ipvs/ip_vs_ctl.c  | 35 ++++++++++++++++-
 net/netfilter/ipvs/ip_vs_xmit.c | 84 +++++++++++++++++++++++++++++++++++++++--
 4 files changed, 130 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 047f9a5ccaad..2ac40135b576 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -600,6 +600,9 @@ struct ip_vs_dest_user_kern {
 
 	/* Address family of addr */
 	u16			af;
+
+	u16			tun_type;	/* tunnel type */
+	__be16			tun_port;	/* tunnel port */
 };
 
 
@@ -660,6 +663,8 @@ struct ip_vs_dest {
 	atomic_t		conn_flags;	/* flags to copy to conn */
 	atomic_t		weight;		/* server weight */
 	atomic_t		last_weight;	/* server latest weight */
+	__u16			tun_type;	/* tunnel type */
+	__be16			tun_port;	/* tunnel port */
 
 	refcount_t		refcnt;		/* reference counter */
 	struct ip_vs_stats      stats;          /* statistics */
diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h
index 1c916b2f89dc..e34f436fc79d 100644
--- a/include/uapi/linux/ip_vs.h
+++ b/include/uapi/linux/ip_vs.h
@@ -124,6 +124,13 @@
 
 #define IP_VS_PEDATA_MAXLEN     255
 
+/* Tunnel types */
+enum {
+	IP_VS_CONN_F_TUNNEL_TYPE_IPIP = 0,	/* IPIP */
+	IP_VS_CONN_F_TUNNEL_TYPE_GUE,		/* GUE */
+	IP_VS_CONN_F_TUNNEL_TYPE_MAX,
+};
+
 /*
  *	The struct ip_vs_service_user and struct ip_vs_dest_user are
  *	used to set IPVS rules through setsockopt.
@@ -392,6 +399,10 @@ enum {
 
 	IPVS_DEST_ATTR_STATS64,		/* nested attribute for dest stats */
 
+	IPVS_DEST_ATTR_TUN_TYPE,	/* tunnel type */
+
+	IPVS_DEST_ATTR_TUN_PORT,	/* tunnel port */
+
 	__IPVS_DEST_ATTR_MAX,
 };
 
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 4b933669fd83..ab119a7540db 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -831,6 +831,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;
 	conn_flags |= IP_VS_CONN_F_INACTIVE;
 
+	/* set the tunnel info */
+	dest->tun_type = udest->tun_type;
+	dest->tun_port = udest->tun_port;
+
 	/* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */
 	if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) {
 		conn_flags |= IP_VS_CONN_F_NOOUTPUT;
@@ -987,6 +991,13 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 		return -ERANGE;
 	}
 
+	if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+		if (udest->tun_port == 0) {
+			pr_err("%s(): tunnel port is zero\n", __func__);
+			return -EINVAL;
+		}
+	}
+
 	ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
 
 	/* We use function that requires RCU lock */
@@ -1051,6 +1062,13 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
 		return -ERANGE;
 	}
 
+	if (udest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) {
+		if (udest->tun_port == 0) {
+			pr_err("%s(): tunnel port is zero\n", __func__);
+			return -EINVAL;
+		}
+	}
+
 	ip_vs_addr_copy(udest->af, &daddr, &udest->addr);
 
 	/* We use function that requires RCU lock */
@@ -2333,6 +2351,7 @@ static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest,
 	udest->u_threshold	= udest_compat->u_threshold;
 	udest->l_threshold	= udest_compat->l_threshold;
 	udest->af		= AF_INET;
+	udest->tun_type		= IP_VS_CONN_F_TUNNEL_TYPE_IPIP;
 }
 
 static int
@@ -2890,6 +2909,8 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = {
 	[IPVS_DEST_ATTR_PERSIST_CONNS]	= { .type = NLA_U32 },
 	[IPVS_DEST_ATTR_STATS]		= { .type = NLA_NESTED },
 	[IPVS_DEST_ATTR_ADDR_FAMILY]	= { .type = NLA_U16 },
+	[IPVS_DEST_ATTR_TUN_TYPE]	= { .type = NLA_U8 },
+	[IPVS_DEST_ATTR_TUN_PORT]	= { .type = NLA_U16 },
 };
 
 static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
@@ -3193,6 +3214,10 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
 			 IP_VS_CONN_F_FWD_MASK)) ||
 	    nla_put_u32(skb, IPVS_DEST_ATTR_WEIGHT,
 			atomic_read(&dest->weight)) ||
+	    nla_put_u8(skb, IPVS_DEST_ATTR_TUN_TYPE,
+		       dest->tun_type) ||
+	    nla_put_be16(skb, IPVS_DEST_ATTR_TUN_PORT,
+			 dest->tun_port) ||
 	    nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) ||
 	    nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) ||
 	    nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS,
@@ -3315,12 +3340,14 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
 	/* If a full entry was requested, check for the additional fields */
 	if (full_entry) {
 		struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh,
-			      *nla_l_thresh;
+			      *nla_l_thresh, *nla_tun_type, *nla_tun_port;
 
 		nla_fwd		= attrs[IPVS_DEST_ATTR_FWD_METHOD];
 		nla_weight	= attrs[IPVS_DEST_ATTR_WEIGHT];
 		nla_u_thresh	= attrs[IPVS_DEST_ATTR_U_THRESH];
 		nla_l_thresh	= attrs[IPVS_DEST_ATTR_L_THRESH];
+		nla_tun_type	= attrs[IPVS_DEST_ATTR_TUN_TYPE];
+		nla_tun_port	= attrs[IPVS_DEST_ATTR_TUN_PORT];
 
 		if (!(nla_fwd && nla_weight && nla_u_thresh && nla_l_thresh))
 			return -EINVAL;
@@ -3330,6 +3357,12 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
 		udest->weight = nla_get_u32(nla_weight);
 		udest->u_threshold = nla_get_u32(nla_u_thresh);
 		udest->l_threshold = nla_get_u32(nla_l_thresh);
+
+		if (nla_tun_type)
+			udest->tun_type = nla_get_u8(nla_tun_type);
+
+		if (nla_tun_port)
+			udest->tun_port = nla_get_be16(nla_tun_port);
 	}
 
 	return 0;
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 175349fcf91f..8d6f94b67772 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -32,6 +32,7 @@
 #include <linux/slab.h>
 #include <linux/tcp.h>                  /* for tcphdr */
 #include <net/ip.h>
+#include <net/gue.h>
 #include <net/tcp.h>                    /* for csum_tcpudp_magic */
 #include <net/udp.h>
 #include <net/icmp.h>                   /* for icmp_send */
@@ -382,6 +383,10 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 		mtu = dst_mtu(&rt->dst);
 	} else {
 		mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
+		if (!dest)
+			goto err_put;
+		if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+			mtu -= sizeof(struct udphdr) + sizeof(struct guehdr);
 		if (mtu < 68) {
 			IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
 			goto err_put;
@@ -533,6 +538,10 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 		mtu = dst_mtu(&rt->dst);
 	else {
 		mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
+		if (!dest)
+			goto err_put;
+		if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+			mtu -= sizeof(struct udphdr) + sizeof(struct guehdr);
 		if (mtu < IPV6_MIN_MTU) {
 			IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
 				     IPV6_MIN_MTU);
@@ -989,6 +998,41 @@ static inline int __tun_gso_type_mask(int encaps_af, int orig_af)
 	}
 }
 
+static int
+ipvs_gue_encap(struct net *net, struct sk_buff *skb,
+	       struct ip_vs_conn *cp, __u8 *next_protocol)
+{
+	__be16 dport;
+	__be16 sport = udp_flow_src_port(net, skb, 0, 0, false);
+	struct udphdr  *udph;	/* Our new UDP header */
+	struct guehdr  *gueh;	/* Our new GUE header */
+
+	skb_push(skb, sizeof(struct guehdr));
+
+	gueh = (struct guehdr *)skb->data;
+
+	gueh->control = 0;
+	gueh->version = 0;
+	gueh->hlen = 0;
+	gueh->flags = 0;
+	gueh->proto_ctype = *next_protocol;
+
+	skb_push(skb, sizeof(struct udphdr));
+	skb_reset_transport_header(skb);
+
+	udph = udp_hdr(skb);
+
+	dport = cp->dest->tun_port;
+	udph->dest = dport;
+	udph->source = sport;
+	udph->len = htons(skb->len);
+	udph->check = 0;
+
+	*next_protocol = IPPROTO_UDP;
+
+	return 0;
+}
+
 /*
  *   IP Tunneling transmitter
  *
@@ -1025,6 +1069,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	struct iphdr  *iph;			/* Our new IP header */
 	unsigned int max_headroom;		/* The extra header space needed */
 	int ret, local;
+	int tun_type, gso_type;
 
 	EnterFunction(10);
 
@@ -1046,6 +1091,11 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	 */
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
 
+	tun_type = cp->dest->tun_type;
+
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+		max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr);
+
 	/* We only care about the df field if sysctl_pmtu_disc(ipvs) is set */
 	dfp = sysctl_pmtu_disc(ipvs) ? &df : NULL;
 	skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
@@ -1054,11 +1104,20 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	if (IS_ERR(skb))
 		goto tx_error;
 
-	if (iptunnel_handle_offloads(skb, __tun_gso_type_mask(AF_INET, cp->af)))
+	gso_type = __tun_gso_type_mask(AF_INET, cp->af);
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+		gso_type |= SKB_GSO_UDP_TUNNEL;
+
+	if (iptunnel_handle_offloads(skb, gso_type))
 		goto tx_error;
 
 	skb->transport_header = skb->network_header;
 
+	skb_set_inner_ipproto(skb, next_protocol);
+
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+		ipvs_gue_encap(net, skb, cp, &next_protocol);
+
 	skb_push(skb, sizeof(struct iphdr));
 	skb_reset_network_header(skb);
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -1102,6 +1161,8 @@ int
 ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
 {
+	struct netns_ipvs *ipvs = cp->ipvs;
+	struct net *net = ipvs->net;
 	struct rt6_info *rt;		/* Route to the other host */
 	struct in6_addr saddr;		/* Source for tunnel */
 	struct net_device *tdev;	/* Device to other host */
@@ -1112,10 +1173,11 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	struct ipv6hdr  *iph;		/* Our new IP header */
 	unsigned int max_headroom;	/* The extra header space needed */
 	int ret, local;
+	int tun_type, gso_type;
 
 	EnterFunction(10);
 
-	local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest,
+	local = __ip_vs_get_out_rt_v6(ipvs, cp->af, skb, cp->dest,
 				      &cp->daddr.in6,
 				      &saddr, ipvsh, 1,
 				      IP_VS_RT_MODE_LOCAL |
@@ -1134,17 +1196,31 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	 */
 	max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr);
 
+	tun_type = cp->dest->tun_type;
+
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+		max_headroom += sizeof(struct udphdr) + sizeof(struct guehdr);
+
 	skb = ip_vs_prepare_tunneled_skb(skb, cp->af, max_headroom,
 					 &next_protocol, &payload_len,
 					 &dsfield, &ttl, NULL);
 	if (IS_ERR(skb))
 		goto tx_error;
 
-	if (iptunnel_handle_offloads(skb, __tun_gso_type_mask(AF_INET6, cp->af)))
+	gso_type = __tun_gso_type_mask(AF_INET6, cp->af);
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+		gso_type |= SKB_GSO_UDP_TUNNEL;
+
+	if (iptunnel_handle_offloads(skb, gso_type))
 		goto tx_error;
 
 	skb->transport_header = skb->network_header;
 
+	skb_set_inner_ipproto(skb, next_protocol);
+
+	if (tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE)
+		ipvs_gue_encap(net, skb, cp, &next_protocol);
+
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -1167,7 +1243,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 
 	ret = ip_vs_tunnel_xmit_prepare(skb, cp);
 	if (ret == NF_ACCEPT)
-		ip6_local_out(cp->ipvs->net, skb->sk, skb);
+		ip6_local_out(net, skb->sk, skb);
 	else if (ret == NF_DROP)
 		kfree_skb(skb);
 
-- 
cgit v1.2.3


From 01902f8c85bfde343a4c2b7428d18762442f3a25 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 26 Mar 2019 20:06:20 +0800
Subject: netfilter: optimize nf_inet_addr_cmp

optimize nf_inet_addr_cmp by 64bit xor computation
similar to ipv6_addr_equal()

Signed-off-by: Yuan Linsi <yuanlinsi01@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 72cb19c3db6a..4e0145ea033e 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -24,10 +24,17 @@ static inline int NF_DROP_GETERR(int verdict)
 static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1,
 				   const union nf_inet_addr *a2)
 {
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+	const unsigned long *ul1 = (const unsigned long *)a1;
+	const unsigned long *ul2 = (const unsigned long *)a2;
+
+	return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL;
+#else
 	return a1->all[0] == a2->all[0] &&
 	       a1->all[1] == a2->all[1] &&
 	       a1->all[2] == a2->all[2] &&
 	       a1->all[3] == a2->all[3];
+#endif
 }
 
 static inline void nf_inet_addr_mask(const union nf_inet_addr *a1,
-- 
cgit v1.2.3


From d164385ec572cbe3335a635ac308760e126d4ec0 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 27 Mar 2019 09:22:24 +0100
Subject: netfilter: nat: add inet family nat support

We need minimal support from the nat core for this, as we do not
want to register additional base hooks.

When an inet hook is registered, interally register ipv4 and ipv6
hooks for them and unregister those when inet hooks are removed.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat.h |  7 +++--
 net/netfilter/nf_nat_core.c    | 16 +++++-------
 net/netfilter/nf_nat_proto.c   | 43 ++++++++++++++++++++++++++-----
 net/netfilter/nft_chain_nat.c  | 36 ++++++++++++++++++++++++++
 net/netfilter/nft_nat.c        | 58 ++++++++++++++++++++++++++++++++++++++++--
 5 files changed, 141 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index cf332c4e0b32..423cda2c6542 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -69,9 +69,9 @@ static inline bool nf_nat_oif_changed(unsigned int hooknum,
 #endif
 }
 
-int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops,
+int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
 		       const struct nf_hook_ops *nat_ops, unsigned int ops_count);
-void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops,
+void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
 			  unsigned int ops_count);
 
 unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
@@ -98,6 +98,9 @@ void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops);
 int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops);
 void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops);
 
+int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops);
+void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops);
+
 unsigned int
 nf_nat_inet_fn(void *priv, struct sk_buff *skb,
 	       const struct nf_hook_state *state);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index af7dc6537758..a9ec49edd7f4 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1009,7 +1009,7 @@ static struct nf_ct_helper_expectfn follow_master_nat = {
 	.expectfn	= nf_nat_follow_master,
 };
 
-int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops,
+int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
 		       const struct nf_hook_ops *orig_nat_ops, unsigned int ops_count)
 {
 	struct nat_net *nat_net = net_generic(net, nat_net_id);
@@ -1019,14 +1019,12 @@ int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops,
 	struct nf_hook_ops *nat_ops;
 	int i, ret;
 
-	if (WARN_ON_ONCE(ops->pf >= ARRAY_SIZE(nat_net->nat_proto_net)))
+	if (WARN_ON_ONCE(pf >= ARRAY_SIZE(nat_net->nat_proto_net)))
 		return -EINVAL;
 
-	nat_proto_net = &nat_net->nat_proto_net[ops->pf];
+	nat_proto_net = &nat_net->nat_proto_net[pf];
 
 	for (i = 0; i < ops_count; i++) {
-		if (WARN_ON(orig_nat_ops[i].pf != ops->pf))
-			return -EINVAL;
 		if (orig_nat_ops[i].hooknum == hooknum) {
 			hooknum = i;
 			break;
@@ -1086,8 +1084,8 @@ int nf_nat_register_fn(struct net *net, const struct nf_hook_ops *ops,
 	return ret;
 }
 
-void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops,
-		          unsigned int ops_count)
+void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
+			  unsigned int ops_count)
 {
 	struct nat_net *nat_net = net_generic(net, nat_net_id);
 	struct nf_nat_hooks_net *nat_proto_net;
@@ -1096,10 +1094,10 @@ void nf_nat_unregister_fn(struct net *net, const struct nf_hook_ops *ops,
 	int hooknum = ops->hooknum;
 	int i;
 
-	if (ops->pf >= ARRAY_SIZE(nat_net->nat_proto_net))
+	if (pf >= ARRAY_SIZE(nat_net->nat_proto_net))
 		return;
 
-	nat_proto_net = &nat_net->nat_proto_net[ops->pf];
+	nat_proto_net = &nat_net->nat_proto_net[pf];
 
 	mutex_lock(&nf_nat_proto_mutex);
 	if (WARN_ON(nat_proto_net->users == 0))
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 62743da3004f..606d0a740615 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -725,7 +725,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
 	return ret;
 }
 
-static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
+const struct nf_hook_ops nf_nat_ipv4_ops[] = {
 	/* Before packet filtering, change destination */
 	{
 		.hook		= nf_nat_ipv4_in,
@@ -758,13 +758,14 @@ static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
 
 int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops)
 {
-	return nf_nat_register_fn(net, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+	return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv4_ops,
+				  ARRAY_SIZE(nf_nat_ipv4_ops));
 }
 EXPORT_SYMBOL_GPL(nf_nat_ipv4_register_fn);
 
 void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
 {
-	nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+	nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
 }
 EXPORT_SYMBOL_GPL(nf_nat_ipv4_unregister_fn);
 
@@ -977,7 +978,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
 	return ret;
 }
 
-static const struct nf_hook_ops nf_nat_ipv6_ops[] = {
+const struct nf_hook_ops nf_nat_ipv6_ops[] = {
 	/* Before packet filtering, change destination */
 	{
 		.hook		= nf_nat_ipv6_in,
@@ -1010,14 +1011,44 @@ static const struct nf_hook_ops nf_nat_ipv6_ops[] = {
 
 int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops)
 {
-	return nf_nat_register_fn(net, ops, nf_nat_ipv6_ops,
+	return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv6_ops,
 				  ARRAY_SIZE(nf_nat_ipv6_ops));
 }
 EXPORT_SYMBOL_GPL(nf_nat_ipv6_register_fn);
 
 void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
 {
-	nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
+	nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
 }
 EXPORT_SYMBOL_GPL(nf_nat_ipv6_unregister_fn);
 #endif /* CONFIG_IPV6 */
+
+#if defined(CONFIG_NF_TABLES_INET) && IS_ENABLED(CONFIG_NFT_NAT)
+int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops)
+{
+	int ret;
+
+	if (WARN_ON_ONCE(ops->pf != NFPROTO_INET))
+		return -EINVAL;
+
+	ret = nf_nat_register_fn(net, NFPROTO_IPV6, ops, nf_nat_ipv6_ops,
+				 ARRAY_SIZE(nf_nat_ipv6_ops));
+	if (ret)
+		return ret;
+
+	ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops,
+				 ARRAY_SIZE(nf_nat_ipv4_ops));
+	if (ret)
+		nf_nat_ipv6_unregister_fn(net, ops);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn);
+
+void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
+{
+	nf_nat_unregister_fn(net, NFPROTO_IPV4, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+	nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops));
+}
+EXPORT_SYMBOL_GPL(nf_nat_inet_unregister_fn);
+#endif /* NFT INET NAT */
diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c
index ee4852088d50..2f89bde3c61c 100644
--- a/net/netfilter/nft_chain_nat.c
+++ b/net/netfilter/nft_chain_nat.c
@@ -74,6 +74,36 @@ static const struct nft_chain_type nft_chain_nat_ipv6 = {
 };
 #endif
 
+#ifdef CONFIG_NF_TABLES_INET
+static int nft_nat_inet_reg(struct net *net, const struct nf_hook_ops *ops)
+{
+	return nf_nat_inet_register_fn(net, ops);
+}
+
+static void nft_nat_inet_unreg(struct net *net, const struct nf_hook_ops *ops)
+{
+	nf_nat_inet_unregister_fn(net, ops);
+}
+
+static const struct nft_chain_type nft_chain_nat_inet = {
+	.name		= "nat",
+	.type		= NFT_CHAIN_T_NAT,
+	.family		= NFPROTO_INET,
+	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_LOCAL_IN) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_POST_ROUTING),
+	.hooks		= {
+		[NF_INET_PRE_ROUTING]	= nft_nat_do_chain,
+		[NF_INET_LOCAL_IN]	= nft_nat_do_chain,
+		[NF_INET_LOCAL_OUT]	= nft_nat_do_chain,
+		[NF_INET_POST_ROUTING]	= nft_nat_do_chain,
+	},
+	.ops_register		= nft_nat_inet_reg,
+	.ops_unregister		= nft_nat_inet_unreg,
+};
+#endif
+
 static int __init nft_chain_nat_init(void)
 {
 #ifdef CONFIG_NF_TABLES_IPV6
@@ -82,6 +112,9 @@ static int __init nft_chain_nat_init(void)
 #ifdef CONFIG_NF_TABLES_IPV4
 	nft_register_chain_type(&nft_chain_nat_ipv4);
 #endif
+#ifdef CONFIG_NF_TABLES_INET
+	nft_register_chain_type(&nft_chain_nat_inet);
+#endif
 
 	return 0;
 }
@@ -94,6 +127,9 @@ static void __exit nft_chain_nat_exit(void)
 #ifdef CONFIG_NF_TABLES_IPV6
 	nft_unregister_chain_type(&nft_chain_nat_ipv6);
 #endif
+#ifdef CONFIG_NF_TABLES_INET
+	nft_unregister_chain_type(&nft_chain_nat_inet);
+#endif
 }
 
 module_init(nft_chain_nat_init);
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index e93aed9bda88..d90d421826aa 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -140,7 +140,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		return -EINVAL;
 
 	family = ntohl(nla_get_be32(tb[NFTA_NAT_FAMILY]));
-	if (family != ctx->family)
+	if (ctx->family != NFPROTO_INET && ctx->family != family)
 		return -EOPNOTSUPP;
 
 	switch (family) {
@@ -278,13 +278,67 @@ static struct nft_expr_type nft_nat_type __read_mostly = {
 	.owner          = THIS_MODULE,
 };
 
+#ifdef CONFIG_NF_TABLES_INET
+static void nft_nat_inet_eval(const struct nft_expr *expr,
+			      struct nft_regs *regs,
+			      const struct nft_pktinfo *pkt)
+{
+	const struct nft_nat *priv = nft_expr_priv(expr);
+
+	if (priv->family == nft_pf(pkt))
+		nft_nat_eval(expr, regs, pkt);
+}
+
+static const struct nft_expr_ops nft_nat_inet_ops = {
+	.type           = &nft_nat_type,
+	.size           = NFT_EXPR_SIZE(sizeof(struct nft_nat)),
+	.eval           = nft_nat_inet_eval,
+	.init           = nft_nat_init,
+	.destroy        = nft_nat_destroy,
+	.dump           = nft_nat_dump,
+	.validate	= nft_nat_validate,
+};
+
+static struct nft_expr_type nft_inet_nat_type __read_mostly = {
+	.name           = "nat",
+	.family		= NFPROTO_INET,
+	.ops            = &nft_nat_inet_ops,
+	.policy         = nft_nat_policy,
+	.maxattr        = NFTA_NAT_MAX,
+	.owner          = THIS_MODULE,
+};
+
+static int nft_nat_inet_module_init(void)
+{
+	return nft_register_expr(&nft_inet_nat_type);
+}
+
+static void nft_nat_inet_module_exit(void)
+{
+	nft_unregister_expr(&nft_inet_nat_type);
+}
+#else
+static int nft_nat_inet_module_init(void) { return 0; }
+static void nft_nat_inet_module_exit(void) { }
+#endif
+
 static int __init nft_nat_module_init(void)
 {
-	return nft_register_expr(&nft_nat_type);
+	int ret = nft_nat_inet_module_init();
+
+	if (ret)
+		return ret;
+
+	ret = nft_register_expr(&nft_nat_type);
+	if (ret)
+		nft_nat_inet_module_exit();
+
+	return ret;
 }
 
 static void __exit nft_nat_module_exit(void)
 {
+	nft_nat_inet_module_exit();
 	nft_unregister_expr(&nft_nat_type);
 }
 
-- 
cgit v1.2.3


From c1deb065cf3b5bcd483e3f03479f930edb151b99 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 27 Mar 2019 09:22:25 +0100
Subject: netfilter: nf_tables: merge route type into core

very little code, so it really doesn't make sense to have extra
modules or even a kconfig knob for this.

Merge them and make functionality available unconditionally.
The merge makes inet family route support trivial, so add it
as well here.

Before:
   text	   data	    bss	    dec	    hex	filename
    835	    832	      0	   1667	    683 nft_chain_route_ipv4.ko
    870	    832	      0	   1702	    6a6	nft_chain_route_ipv6.ko
 111568	   2556	    529	 114653	  1bfdd	nf_tables.ko

After:
   text	   data	    bss	    dec	    hex	filename
 113133	   2556	    529	 116218	  1c5fa	nf_tables.ko

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_ipv6.h            |  15 +++
 include/net/netfilter/nf_tables.h         |   2 +
 net/ipv4/netfilter/Kconfig                |   8 --
 net/ipv4/netfilter/Makefile               |   1 -
 net/ipv4/netfilter/nft_chain_route_ipv4.c |  89 ----------------
 net/ipv6/netfilter/Kconfig                |   8 --
 net/ipv6/netfilter/Makefile               |   1 -
 net/ipv6/netfilter/nft_chain_route_ipv6.c |  91 ----------------
 net/netfilter/Makefile                    |   3 +-
 net/netfilter/nf_nat_proto.c              |  16 +--
 net/netfilter/nf_tables_api.c             |   2 +
 net/netfilter/nft_chain_route.c           | 169 ++++++++++++++++++++++++++++++
 12 files changed, 191 insertions(+), 214 deletions(-)
 delete mode 100644 net/ipv4/netfilter/nft_chain_route_ipv4.c
 delete mode 100644 net/ipv6/netfilter/nft_chain_route_ipv6.c
 create mode 100644 net/netfilter/nft_chain_route.c

(limited to 'include')

diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 471e9467105b..12113e502656 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -87,6 +87,21 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst,
 }
 
 int ip6_route_me_harder(struct net *net, struct sk_buff *skb);
+
+static inline int nf_ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+{
+#if IS_MODULE(CONFIG_IPV6)
+	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
+
+	if (!v6_ops)
+		return -EHOSTUNREACH;
+
+	return v6_ops->route_me_harder(net, skb);
+#else
+	return ip6_route_me_harder(net, skb);
+#endif
+}
+
 __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
 			unsigned int dataoff, u_int8_t protocol);
 
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 3e9ab643eedf..55dff3ab44c7 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1411,4 +1411,6 @@ struct nft_trans_flowtable {
 int __init nft_chain_filter_init(void);
 void nft_chain_filter_fini(void);
 
+void __init nft_chain_route_init(void);
+void nft_chain_route_fini(void);
 #endif /* _NET_NF_TABLES_H */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index c98391d49200..ea688832fc4e 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -27,14 +27,6 @@ config NF_TABLES_IPV4
 
 if NF_TABLES_IPV4
 
-config NFT_CHAIN_ROUTE_IPV4
-	tristate "IPv4 nf_tables route chain support"
-	help
-	  This option enables the "route" chain for IPv4 in nf_tables. This
-	  chain type is used to force packet re-routing after mangling header
-	  fields such as the source, destination, type of service and
-	  the packet mark.
-
 config NFT_REJECT_IPV4
 	select NF_REJECT_IPV4
 	default NFT_REJECT
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index e241f5188ebe..2cfdda7b109f 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -24,7 +24,6 @@ nf_nat_snmp_basic-y := nf_nat_snmp_basic.asn1.o nf_nat_snmp_basic_main.o
 $(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h
 obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o
 
-obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
 obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o
 obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c
deleted file mode 100644
index 7d82934c46f4..000000000000
--- a/net/ipv4/netfilter/nft_chain_route_ipv4.c
+++ /dev/null
@@ -1,89 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_ipv4.h>
-#include <net/route.h>
-#include <net/ip.h>
-
-static unsigned int nf_route_table_hook(void *priv,
-					struct sk_buff *skb,
-					const struct nf_hook_state *state)
-{
-	unsigned int ret;
-	struct nft_pktinfo pkt;
-	u32 mark;
-	__be32 saddr, daddr;
-	u_int8_t tos;
-	const struct iphdr *iph;
-	int err;
-
-	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_ipv4(&pkt, skb);
-
-	mark = skb->mark;
-	iph = ip_hdr(skb);
-	saddr = iph->saddr;
-	daddr = iph->daddr;
-	tos = iph->tos;
-
-	ret = nft_do_chain(&pkt, priv);
-	if (ret != NF_DROP && ret != NF_STOLEN) {
-		iph = ip_hdr(skb);
-
-		if (iph->saddr != saddr ||
-		    iph->daddr != daddr ||
-		    skb->mark != mark ||
-		    iph->tos != tos) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
-			if (err < 0)
-				ret = NF_DROP_ERR(err);
-		}
-	}
-	return ret;
-}
-
-static const struct nft_chain_type nft_chain_route_ipv4 = {
-	.name		= "route",
-	.type		= NFT_CHAIN_T_ROUTE,
-	.family		= NFPROTO_IPV4,
-	.owner		= THIS_MODULE,
-	.hook_mask	= (1 << NF_INET_LOCAL_OUT),
-	.hooks		= {
-		[NF_INET_LOCAL_OUT]	= nf_route_table_hook,
-	},
-};
-
-static int __init nft_chain_route_init(void)
-{
-	nft_register_chain_type(&nft_chain_route_ipv4);
-
-	return 0;
-}
-
-static void __exit nft_chain_route_exit(void)
-{
-	nft_unregister_chain_type(&nft_chain_route_ipv4);
-}
-
-module_init(nft_chain_route_init);
-module_exit(nft_chain_route_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(AF_INET, "route");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index ddc99a1653aa..3de3adb1a0c9 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -23,14 +23,6 @@ config NF_TABLES_IPV6
 
 if NF_TABLES_IPV6
 
-config NFT_CHAIN_ROUTE_IPV6
-	tristate "IPv6 nf_tables route chain support"
-	help
-	  This option enables the "route" chain for IPv6 in nf_tables. This
-	  chain type is used to force packet re-routing after mangling header
-	  fields such as the source, destination, flowlabel, hop-limit and
-	  the packet mark.
-
 config NFT_REJECT_IPV6
 	select NF_REJECT_IPV6
 	default NFT_REJECT
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 3853c648ebaa..93aff604b243 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -27,7 +27,6 @@ obj-$(CONFIG_NF_REJECT_IPV6) += nf_reject_ipv6.o
 obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o
 
 # nf_tables
-obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
 obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
deleted file mode 100644
index da3f1f8cb325..000000000000
--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
+++ /dev/null
@@ -1,91 +0,0 @@
-/*
- * Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Development of this code funded by Astaro AG (http://www.astaro.com/)
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/netlink.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv6.h>
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_ipv6.h>
-#include <net/route.h>
-
-static unsigned int nf_route_table_hook(void *priv,
-					struct sk_buff *skb,
-					const struct nf_hook_state *state)
-{
-	unsigned int ret;
-	struct nft_pktinfo pkt;
-	struct in6_addr saddr, daddr;
-	u_int8_t hop_limit;
-	u32 mark, flowlabel;
-	int err;
-
-	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_ipv6(&pkt, skb);
-
-	/* save source/dest address, mark, hoplimit, flowlabel, priority */
-	memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
-	memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
-	mark = skb->mark;
-	hop_limit = ipv6_hdr(skb)->hop_limit;
-
-	/* flowlabel and prio (includes version, which shouldn't change either */
-	flowlabel = *((u32 *)ipv6_hdr(skb));
-
-	ret = nft_do_chain(&pkt, priv);
-	if (ret != NF_DROP && ret != NF_STOLEN &&
-	    (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
-	     memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
-	     skb->mark != mark ||
-	     ipv6_hdr(skb)->hop_limit != hop_limit ||
-	     flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
-		err = ip6_route_me_harder(state->net, skb);
-		if (err < 0)
-			ret = NF_DROP_ERR(err);
-	}
-
-	return ret;
-}
-
-static const struct nft_chain_type nft_chain_route_ipv6 = {
-	.name		= "route",
-	.type		= NFT_CHAIN_T_ROUTE,
-	.family		= NFPROTO_IPV6,
-	.owner		= THIS_MODULE,
-	.hook_mask	= (1 << NF_INET_LOCAL_OUT),
-	.hooks		= {
-		[NF_INET_LOCAL_OUT]	= nf_route_table_hook,
-	},
-};
-
-static int __init nft_chain_route_init(void)
-{
-	nft_register_chain_type(&nft_chain_route_ipv6);
-
-	return 0;
-}
-
-static void __exit nft_chain_route_exit(void)
-{
-	nft_unregister_chain_type(&nft_chain_route_ipv6);
-}
-
-module_init(nft_chain_route_init);
-module_exit(nft_chain_route_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(AF_INET6, "route");
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 4894a85cdd0b..afbf475e02b2 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -77,7 +77,8 @@ obj-$(CONFIG_NF_DUP_NETDEV)	+= nf_dup_netdev.o
 nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \
 		  nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \
 		  nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \
-		  nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o
+		  nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o \
+		  nft_chain_route.o
 
 nf_tables_set-objs := nf_tables_set_core.o \
 		      nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 606d0a740615..84f5c90a7f21 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -926,20 +926,6 @@ nf_nat_ipv6_out(void *priv, struct sk_buff *skb,
 	return ret;
 }
 
-static int nat_route_me_harder(struct net *net, struct sk_buff *skb)
-{
-#ifdef CONFIG_IPV6_MODULE
-	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
-
-	if (!v6_ops)
-		return -EHOSTUNREACH;
-
-	return v6_ops->route_me_harder(net, skb);
-#else
-	return ip6_route_me_harder(net, skb);
-#endif
-}
-
 static unsigned int
 nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
 		     const struct nf_hook_state *state)
@@ -959,7 +945,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
 
 		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
 				      &ct->tuplehash[!dir].tuple.src.u3)) {
-			err = nat_route_me_harder(state->net, skb);
+			err = nf_ip6_route_me_harder(state->net, skb);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 2d28b138ed18..a2bd439937e6 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7530,6 +7530,7 @@ static int __init nf_tables_module_init(void)
 	if (err < 0)
 		goto err5;
 
+	nft_chain_route_init();
 	return err;
 err5:
 	rhltable_destroy(&nft_objname_ht);
@@ -7549,6 +7550,7 @@ static void __exit nf_tables_module_exit(void)
 	nfnetlink_subsys_unregister(&nf_tables_subsys);
 	unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
 	nft_chain_filter_fini();
+	nft_chain_route_fini();
 	unregister_pernet_subsys(&nf_tables_net_ops);
 	cancel_work_sync(&trans_destroy_work);
 	rcu_barrier();
diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c
new file mode 100644
index 000000000000..8826bbe71136
--- /dev/null
+++ b/net/netfilter/nft_chain_route.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/skbuff.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv4.h>
+#include <net/netfilter/nf_tables_ipv6.h>
+#include <net/route.h>
+#include <net/ip.h>
+
+#ifdef CONFIG_NF_TABLES_IPV4
+static unsigned int nf_route_table_hook4(void *priv,
+					 struct sk_buff *skb,
+					 const struct nf_hook_state *state)
+{
+	const struct iphdr *iph;
+	struct nft_pktinfo pkt;
+	__be32 saddr, daddr;
+	unsigned int ret;
+	u32 mark;
+	int err;
+	u8 tos;
+
+	nft_set_pktinfo(&pkt, skb, state);
+	nft_set_pktinfo_ipv4(&pkt, skb);
+
+	mark = skb->mark;
+	iph = ip_hdr(skb);
+	saddr = iph->saddr;
+	daddr = iph->daddr;
+	tos = iph->tos;
+
+	ret = nft_do_chain(&pkt, priv);
+	if (ret == NF_ACCEPT) {
+		iph = ip_hdr(skb);
+
+		if (iph->saddr != saddr ||
+		    iph->daddr != daddr ||
+		    skb->mark != mark ||
+		    iph->tos != tos) {
+			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+	}
+	return ret;
+}
+
+static const struct nft_chain_type nft_chain_route_ipv4 = {
+	.name		= "route",
+	.type		= NFT_CHAIN_T_ROUTE,
+	.family		= NFPROTO_IPV4,
+	.hook_mask	= (1 << NF_INET_LOCAL_OUT),
+	.hooks		= {
+		[NF_INET_LOCAL_OUT]	= nf_route_table_hook4,
+	},
+};
+#endif
+
+#ifdef CONFIG_NF_TABLES_IPV6
+static unsigned int nf_route_table_hook6(void *priv,
+					 struct sk_buff *skb,
+					 const struct nf_hook_state *state)
+{
+	struct in6_addr saddr, daddr;
+	struct nft_pktinfo pkt;
+	u32 mark, flowlabel;
+	unsigned int ret;
+	u8 hop_limit;
+	int err;
+
+	nft_set_pktinfo(&pkt, skb, state);
+	nft_set_pktinfo_ipv6(&pkt, skb);
+
+	/* save source/dest address, mark, hoplimit, flowlabel, priority */
+	memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
+	memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
+	mark = skb->mark;
+	hop_limit = ipv6_hdr(skb)->hop_limit;
+
+	/* flowlabel and prio (includes version, which shouldn't change either)*/
+	flowlabel = *((u32 *)ipv6_hdr(skb));
+
+	ret = nft_do_chain(&pkt, priv);
+	if (ret == NF_ACCEPT &&
+	    (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
+	     memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
+	     skb->mark != mark ||
+	     ipv6_hdr(skb)->hop_limit != hop_limit ||
+	     flowlabel != *((u32 *)ipv6_hdr(skb)))) {
+		err = nf_ip6_route_me_harder(state->net, skb);
+		if (err < 0)
+			ret = NF_DROP_ERR(err);
+	}
+
+	return ret;
+}
+
+static const struct nft_chain_type nft_chain_route_ipv6 = {
+	.name		= "route",
+	.type		= NFT_CHAIN_T_ROUTE,
+	.family		= NFPROTO_IPV6,
+	.hook_mask	= (1 << NF_INET_LOCAL_OUT),
+	.hooks		= {
+		[NF_INET_LOCAL_OUT]	= nf_route_table_hook6,
+	},
+};
+#endif
+
+#ifdef CONFIG_NF_TABLES_INET
+static unsigned int nf_route_table_inet(void *priv,
+					struct sk_buff *skb,
+					const struct nf_hook_state *state)
+{
+	struct nft_pktinfo pkt;
+
+	switch (state->pf) {
+	case NFPROTO_IPV4:
+		return nf_route_table_hook4(priv, skb, state);
+	case NFPROTO_IPV6:
+		return nf_route_table_hook6(priv, skb, state);
+	default:
+		nft_set_pktinfo(&pkt, skb, state);
+		break;
+	}
+
+	return nft_do_chain(&pkt, priv);
+}
+
+static const struct nft_chain_type nft_chain_route_inet = {
+	.name		= "route",
+	.type		= NFT_CHAIN_T_ROUTE,
+	.family		= NFPROTO_INET,
+	.hook_mask	= (1 << NF_INET_LOCAL_OUT),
+	.hooks		= {
+		[NF_INET_LOCAL_OUT]	= nf_route_table_inet,
+	},
+};
+#endif
+
+void __init nft_chain_route_init(void)
+{
+#ifdef CONFIG_NF_TABLES_IPV6
+	nft_register_chain_type(&nft_chain_route_ipv6);
+#endif
+#ifdef CONFIG_NF_TABLES_IPV4
+	nft_register_chain_type(&nft_chain_route_ipv4);
+#endif
+#ifdef CONFIG_NF_TABLES_INET
+	nft_register_chain_type(&nft_chain_route_inet);
+#endif
+}
+
+void __exit nft_chain_route_fini(void)
+{
+#ifdef CONFIG_NF_TABLES_IPV6
+	nft_unregister_chain_type(&nft_chain_route_ipv6);
+#endif
+#ifdef CONFIG_NF_TABLES_IPV4
+	nft_unregister_chain_type(&nft_chain_route_ipv4);
+#endif
+#ifdef CONFIG_NF_TABLES_INET
+	nft_unregister_chain_type(&nft_chain_route_inet);
+#endif
+}
-- 
cgit v1.2.3


From 4806e975729f99c7908d1688a143f1e16d464e6c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 27 Mar 2019 09:22:26 +0100
Subject: netfilter: replace NF_NAT_NEEDED with IS_ENABLED(CONFIG_NF_NAT)

NF_NAT_NEEDED is true whenever nat support for either ipv4 or ipv6 is
enabled.  Now that the af-specific nat configuration switches have been
removed, IS_ENABLED(CONFIG_NF_NAT) has the same effect.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h                   |  2 +-
 include/net/netfilter/nf_conntrack_expect.h |  2 +-
 net/netfilter/Kconfig                       |  5 -----
 net/netfilter/nf_conntrack_expect.c         |  2 +-
 net/netfilter/nf_conntrack_netlink.c        | 16 ++++++++--------
 net/netfilter/nf_conntrack_sip.c            |  2 +-
 net/openvswitch/conntrack.c                 | 18 +++++++++---------
 7 files changed, 21 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 4e0145ea033e..a7252f3baeb0 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -367,7 +367,7 @@ extern struct nf_nat_hook __rcu *nf_nat_hook;
 static inline void
 nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 {
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	struct nf_nat_hook *nat_hook;
 
 	rcu_read_lock();
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 006e430d1cdf..93ce6b0daaba 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -48,7 +48,7 @@ struct nf_conntrack_expect {
 	/* Expectation class */
 	unsigned int class;
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	union nf_inet_addr saved_addr;
 	/* This is the original per-proto part, used to map the
 	 * expected connection the way the recipient expects. */
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 6548271209a0..f4384c096d0d 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -404,11 +404,6 @@ config NF_NAT
 	  forms of full Network Address Port Translation. This can be
 	  controlled by iptables, ip6tables or nft.
 
-config NF_NAT_NEEDED
-	bool
-	depends on NF_NAT
-	default y
-
 config NF_NAT_AMANDA
 	tristate
 	depends on NF_CONNTRACK && NF_NAT
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 334d6e5b7762..59c18804a10a 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -336,7 +336,7 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
 
 	exp->tuple.dst.u.all = *dst;
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	memset(&exp->saved_addr, 0, sizeof(exp->saved_addr));
 	memset(&exp->saved_proto, 0, sizeof(exp->saved_proto));
 #endif
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 66c596d287a5..32fe3060375a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -45,7 +45,7 @@
 #include <net/netfilter/nf_conntrack_timestamp.h>
 #include <net/netfilter/nf_conntrack_labels.h>
 #include <net/netfilter/nf_conntrack_synproxy.h>
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 #include <net/netfilter/nf_nat.h>
 #include <net/netfilter/nf_nat_helper.h>
 #endif
@@ -655,7 +655,7 @@ static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct)
 	       + nla_total_size(0) /* CTA_HELP */
 	       + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
 	       + ctnetlink_secctx_size(ct)
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	       + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
 	       + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
 #endif
@@ -1494,7 +1494,7 @@ static int ctnetlink_get_ct_unconfirmed(struct net *net, struct sock *ctnl,
 	return -EOPNOTSUPP;
 }
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 static int
 ctnetlink_parse_nat_setup(struct nf_conn *ct,
 			  enum nf_nat_manip_type manip,
@@ -1586,7 +1586,7 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[])
 static int
 ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
 {
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	int ret;
 
 	if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
@@ -2369,7 +2369,7 @@ ctnetlink_glue_build_size(const struct nf_conn *ct)
 	       + nla_total_size(0) /* CTA_HELP */
 	       + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
 	       + ctnetlink_secctx_size(ct)
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	       + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
 	       + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
 #endif
@@ -2699,7 +2699,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 	struct nf_conn *master = exp->master;
 	long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ;
 	struct nf_conn_help *help;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	struct nlattr *nest_parms;
 	struct nf_conntrack_tuple nat_tuple = {};
 #endif
@@ -2717,7 +2717,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 				 CTA_EXPECT_MASTER) < 0)
 		goto nla_put_failure;
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) ||
 	    exp->saved_proto.all) {
 		nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED);
@@ -3180,7 +3180,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr,
 			   struct nf_conntrack_expect *exp,
 			   u_int8_t u3)
 {
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	struct nlattr *tb[CTA_EXPECT_NAT_MAX+1];
 	struct nf_conntrack_tuple nat_tuple = {};
 	int err;
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index 39fcc1ed18f3..d5454d1031a3 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -928,7 +928,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 		    nfct_help(exp->master)->helper != nfct_help(ct)->helper ||
 		    exp->class != class)
 			break;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 		if (!direct_rtp &&
 		    (!nf_inet_addr_cmp(&exp->saved_addr, &exp->tuple.dst.u3) ||
 		     exp->saved_proto.udp.port != exp->tuple.dst.u.udp.port) &&
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 0be3ab5bde26..626629944450 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -29,7 +29,7 @@
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include <net/ipv6_frag.h>
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 #include <net/netfilter/nf_nat.h>
 #endif
 
@@ -75,7 +75,7 @@ struct ovs_conntrack_info {
 	struct md_mark mark;
 	struct md_labels labels;
 	char timeout[CTNL_TIMEOUT_NAME_MAX];
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	struct nf_nat_range2 range;  /* Only present for SRC NAT and DST NAT. */
 #endif
 };
@@ -721,7 +721,7 @@ static bool skb_nfct_cached(struct net *net,
 	return ct_executed;
 }
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 /* Modelled after nf_nat_ipv[46]_fn().
  * range is only used for new, uninitialized NAT state.
  * Returns either NF_ACCEPT or NF_DROP.
@@ -903,7 +903,7 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 
 	return err;
 }
-#else /* !CONFIG_NF_NAT_NEEDED */
+#else /* !CONFIG_NF_NAT */
 static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 		      const struct ovs_conntrack_info *info,
 		      struct sk_buff *skb, struct nf_conn *ct,
@@ -1330,7 +1330,7 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name,
 	return 0;
 }
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 static int parse_nat(const struct nlattr *attr,
 		     struct ovs_conntrack_info *info, bool log)
 {
@@ -1467,7 +1467,7 @@ static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = {
 				    .maxlen = sizeof(struct md_labels) },
 	[OVS_CT_ATTR_HELPER]	= { .minlen = 1,
 				    .maxlen = NF_CT_HELPER_NAME_LEN },
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	/* NAT length is checked when parsing the nested attributes. */
 	[OVS_CT_ATTR_NAT]	= { .minlen = 0, .maxlen = INT_MAX },
 #endif
@@ -1547,7 +1547,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
 				return -EINVAL;
 			}
 			break;
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 		case OVS_CT_ATTR_NAT: {
 			int err = parse_nat(a, info, log);
 
@@ -1677,7 +1677,7 @@ err_free_ct:
 	return err;
 }
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info,
 			       struct sk_buff *skb)
 {
@@ -1783,7 +1783,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
 			return -EMSGSIZE;
 	}
 
-#ifdef CONFIG_NF_NAT_NEEDED
+#if IS_ENABLED(CONFIG_NF_NAT)
 	if (ct_info->nat && !ovs_ct_nat_to_attr(ct_info, skb))
 		return -EMSGSIZE;
 #endif
-- 
cgit v1.2.3


From 22c7652cdaa8cd33ce78bacceb4e826a3f795873 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <ffmancera@riseup.net>
Date: Wed, 27 Mar 2019 11:36:26 +0100
Subject: netfilter: nft_osf: Add version option support

Add version option support to the nftables "osf" expression.

Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nfnetlink_osf.h  | 11 ++++++++---
 include/uapi/linux/netfilter/nf_tables.h |  6 ++++++
 net/netfilter/nfnetlink_osf.c            | 14 +++++++-------
 net/netfilter/nft_osf.c                  | 30 +++++++++++++++++++++++++-----
 4 files changed, 46 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h
index c6000046c966..788613f36935 100644
--- a/include/linux/netfilter/nfnetlink_osf.h
+++ b/include/linux/netfilter/nfnetlink_osf.h
@@ -21,13 +21,18 @@ struct nf_osf_finger {
 	struct nf_osf_user_finger	finger;
 };
 
+struct nf_osf_data {
+	const char *genre;
+	const char *version;
+};
+
 bool nf_osf_match(const struct sk_buff *skb, u_int8_t family,
 		  int hooknum, struct net_device *in, struct net_device *out,
 		  const struct nf_osf_info *info, struct net *net,
 		  const struct list_head *nf_osf_fingers);
 
-const char *nf_osf_find(const struct sk_buff *skb,
-			const struct list_head *nf_osf_fingers,
-			const int ttl_check);
+bool nf_osf_find(const struct sk_buff *skb,
+		 const struct list_head *nf_osf_fingers,
+		 const int ttl_check, struct nf_osf_data *data);
 
 #endif /* _NFOSF_H */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index a66c8de006cc..061bb3eb20c3 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1522,15 +1522,21 @@ enum nft_flowtable_hook_attributes {
  *
  * @NFTA_OSF_DREG: destination register (NLA_U32: nft_registers)
  * @NFTA_OSF_TTL: Value of the TTL osf option (NLA_U8)
+ * @NFTA_OSF_FLAGS: flags (NLA_U32)
  */
 enum nft_osf_attributes {
 	NFTA_OSF_UNSPEC,
 	NFTA_OSF_DREG,
 	NFTA_OSF_TTL,
+	NFTA_OSF_FLAGS,
 	__NFTA_OSF_MAX,
 };
 #define NFTA_OSF_MAX (__NFTA_OSF_MAX - 1)
 
+enum nft_osf_flags {
+	NFT_OSF_F_VERSION = (1 << 0),
+};
+
 /**
  * enum nft_device_attributes - nf_tables device netlink attributes
  *
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index 1f1d90c1716b..7b827bcb412c 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -255,9 +255,9 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family,
 }
 EXPORT_SYMBOL_GPL(nf_osf_match);
 
-const char *nf_osf_find(const struct sk_buff *skb,
-			const struct list_head *nf_osf_fingers,
-			const int ttl_check)
+bool nf_osf_find(const struct sk_buff *skb,
+		 const struct list_head *nf_osf_fingers,
+		 const int ttl_check, struct nf_osf_data *data)
 {
 	const struct iphdr *ip = ip_hdr(skb);
 	const struct nf_osf_user_finger *f;
@@ -265,24 +265,24 @@ const char *nf_osf_find(const struct sk_buff *skb,
 	const struct nf_osf_finger *kf;
 	struct nf_osf_hdr_ctx ctx;
 	const struct tcphdr *tcp;
-	const char *genre = NULL;
 
 	memset(&ctx, 0, sizeof(ctx));
 
 	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
 	if (!tcp)
-		return NULL;
+		return false;
 
 	list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) {
 		f = &kf->finger;
 		if (!nf_osf_match_one(skb, f, ttl_check, &ctx))
 			continue;
 
-		genre = f->genre;
+		data->genre = f->genre;
+		data->version = f->version;
 		break;
 	}
 
-	return genre;
+	return true;
 }
 EXPORT_SYMBOL_GPL(nf_osf_find);
 
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index b13618c764ec..87b60d6617ef 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -7,11 +7,13 @@
 struct nft_osf {
 	enum nft_registers	dreg:8;
 	u8			ttl;
+	u32			flags;
 };
 
 static const struct nla_policy nft_osf_policy[NFTA_OSF_MAX + 1] = {
 	[NFTA_OSF_DREG]		= { .type = NLA_U32 },
 	[NFTA_OSF_TTL]		= { .type = NLA_U8 },
+	[NFTA_OSF_FLAGS]	= { .type = NLA_U32 },
 };
 
 static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
@@ -20,9 +22,10 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	struct nft_osf *priv = nft_expr_priv(expr);
 	u32 *dest = &regs->data[priv->dreg];
 	struct sk_buff *skb = pkt->skb;
+	char os_match[NFT_OSF_MAXGENRELEN + 1];
 	const struct tcphdr *tcp;
+	struct nf_osf_data data;
 	struct tcphdr _tcph;
-	const char *os_name;
 
 	tcp = skb_header_pointer(skb, ip_hdrlen(skb),
 				 sizeof(struct tcphdr), &_tcph);
@@ -35,11 +38,17 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
 		return;
 	}
 
-	os_name = nf_osf_find(skb, nf_osf_fingers, priv->ttl);
-	if (!os_name)
+	if (!nf_osf_find(skb, nf_osf_fingers, priv->ttl, &data)) {
 		strncpy((char *)dest, "unknown", NFT_OSF_MAXGENRELEN);
-	else
-		strncpy((char *)dest, os_name, NFT_OSF_MAXGENRELEN);
+	} else {
+		if (priv->flags & NFT_OSF_F_VERSION)
+			snprintf(os_match, NFT_OSF_MAXGENRELEN, "%s:%s",
+				 data.genre, data.version);
+		else
+			strlcpy(os_match, data.genre, NFT_OSF_MAXGENRELEN);
+
+		strncpy((char *)dest, os_match, NFT_OSF_MAXGENRELEN);
+	}
 }
 
 static int nft_osf_init(const struct nft_ctx *ctx,
@@ -47,6 +56,7 @@ static int nft_osf_init(const struct nft_ctx *ctx,
 			const struct nlattr * const tb[])
 {
 	struct nft_osf *priv = nft_expr_priv(expr);
+	u32 flags;
 	int err;
 	u8 ttl;
 
@@ -57,6 +67,13 @@ static int nft_osf_init(const struct nft_ctx *ctx,
 		priv->ttl = ttl;
 	}
 
+	if (tb[NFTA_OSF_FLAGS]) {
+		flags = ntohl(nla_get_be32(tb[NFTA_OSF_FLAGS]));
+		if (flags != NFT_OSF_F_VERSION)
+			return -EINVAL;
+		priv->flags = flags;
+	}
+
 	priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]);
 	err = nft_validate_register_store(ctx, priv->dreg, NULL,
 					  NFT_DATA_VALUE, NFT_OSF_MAXGENRELEN);
@@ -73,6 +90,9 @@ static int nft_osf_dump(struct sk_buff *skb, const struct nft_expr *expr)
 	if (nla_put_u8(skb, NFTA_OSF_TTL, priv->ttl))
 		goto nla_put_failure;
 
+	if (nla_put_be32(skb, NFTA_OSF_FLAGS, ntohl(priv->flags)))
+		goto nla_put_failure;
+
 	if (nft_dump_register(skb, NFTA_OSF_DREG, priv->dreg))
 		goto nla_put_failure;
 
-- 
cgit v1.2.3


From 3b0a081db1f730373993c7a27936778402a3322c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 4 Apr 2019 10:58:20 +0200
Subject: netfilter: make two functions static

They have no external callers anymore.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/x_tables.h | 1 -
 include/net/netfilter/nf_tables.h  | 2 --
 net/netfilter/nf_tables_api.c      | 5 ++---
 net/netfilter/x_tables.c           | 3 +--
 4 files changed, 3 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index bf384b3eedb8..1f852ef7b098 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -317,7 +317,6 @@ struct xt_table_info *xt_replace_table(struct xt_table *table,
 				       int *error);
 
 struct xt_match *xt_find_match(u8 af, const char *name, u8 revision);
-struct xt_target *xt_find_target(u8 af, const char *name, u8 revision);
 struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision);
 struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision);
 int xt_find_revision(u8 af, const char *name, u8 revision, int target,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 55dff3ab44c7..2d5a0a1a87b8 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -475,8 +475,6 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
 			      enum nft_trans_phase phase);
 int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 		       struct nft_set_binding *binding);
-void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
-			  struct nft_set_binding *binding, bool commit);
 void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set);
 
 /**
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a2bd439937e6..e058273c5dde 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3782,8 +3782,8 @@ bind:
 }
 EXPORT_SYMBOL_GPL(nf_tables_bind_set);
 
-void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
-			  struct nft_set_binding *binding, bool event)
+static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
+				 struct nft_set_binding *binding, bool event)
 {
 	list_del_rcu(&binding->list);
 
@@ -3794,7 +3794,6 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 					     GFP_KERNEL);
 	}
 }
-EXPORT_SYMBOL_GPL(nf_tables_unbind_set);
 
 void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
 			      struct nft_set_binding *binding,
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index e5e5c64df8d1..0a6656ed1534 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -227,7 +227,7 @@ xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision)
 EXPORT_SYMBOL_GPL(xt_request_find_match);
 
 /* Find target, grabs ref.  Returns ERR_PTR() on error. */
-struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
+static struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
 {
 	struct xt_target *t;
 	int err = -ENOENT;
@@ -255,7 +255,6 @@ struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
 
 	return ERR_PTR(err);
 }
-EXPORT_SYMBOL(xt_find_target);
 
 struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision)
 {
-- 
cgit v1.2.3


From 3b8b11f96616c2e763ebcc093b778b309fc07a92 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 5 Apr 2019 21:23:13 +0200
Subject: net: phy: improve link partner capability detection

genphy_read_status() so far checks phydev->supported, not the actual
PHY capabilities. This can make a difference if the supported speeds
have been limited by of_set_phy_supported() or phy_set_max_speed().

It seems that this issue only affects the link partner advertisements
as displayed by ethtool. Also this patch wouldn't apply to older
kernels because linkmode bitmaps have been introduced recently.
Therefore net-next.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 12 ++++++++----
 include/linux/phy.h          |  2 ++
 2 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index f7a6d0ffb1ac..dab3ecbb452d 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1756,10 +1756,7 @@ int genphy_read_status(struct phy_device *phydev)
 	linkmode_zero(phydev->lp_advertising);
 
 	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) {
-		if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
-				      phydev->supported) ||
-		    linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
-				      phydev->supported)) {
+		if (phydev->is_gigabit_capable) {
 			lpagb = phy_read(phydev, MII_STAT1000);
 			if (lpagb < 0)
 				return lpagb;
@@ -2154,6 +2151,13 @@ static int phy_probe(struct device *dev)
 	if (err)
 		goto out;
 
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+			      phydev->supported))
+		phydev->is_gigabit_capable = 1;
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+			      phydev->supported))
+		phydev->is_gigabit_capable = 1;
+
 	of_set_phy_supported(phydev);
 	linkmode_copy(phydev->advertising, phydev->supported);
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index ab7439b3da2b..0f9552b17ee7 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -345,6 +345,7 @@ struct phy_c45_device_ids {
  * is_c45:  Set to true if this phy uses clause 45 addressing.
  * is_internal: Set to true if this phy is internal to a MAC.
  * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc.
+ * is_gigabit_capable: Set to true if PHY supports 1000Mbps
  * has_fixups: Set to true if this phy has fixups/quirks.
  * suspended: Set to true if this phy has been suspended successfully.
  * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal.
@@ -382,6 +383,7 @@ struct phy_device {
 	unsigned is_c45:1;
 	unsigned is_internal:1;
 	unsigned is_pseudo_fixed_link:1;
+	unsigned is_gigabit_capable:1;
 	unsigned has_fixups:1;
 	unsigned suspended:1;
 	unsigned sysfs_links:1;
-- 
cgit v1.2.3


From 1aefd3de7bc667115bb77cb0bc21e874c7e190fc Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:24 -0700
Subject: ipv6: Add fib6_nh_init and release to stubs

Add fib6_nh_init and fib6_nh_release to ipv6_stubs. If fib6_nh_init fails,
callers should not invoke fib6_nh_release, so there is no reason to have
a dummy stub for the IPv6 is not enabled case.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6_stubs.h | 6 ++++++
 net/ipv6/addrconf_core.c | 9 +++++++++
 net/ipv6/af_inet6.c      | 2 ++
 3 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index d8d9c0b0e8c0..453b55bf6723 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -12,6 +12,8 @@
 
 /* structs from net/ip6_fib.h */
 struct fib6_info;
+struct fib6_nh;
+struct fib6_config;
 
 /* This is ugly, ideally these symbols should be built
  * into the core kernel.
@@ -40,6 +42,10 @@ struct ipv6_stub {
 	u32 (*ip6_mtu_from_fib6)(struct fib6_info *f6i, struct in6_addr *daddr,
 				 struct in6_addr *saddr);
 
+	int (*fib6_nh_init)(struct net *net, struct fib6_nh *fib6_nh,
+			    struct fib6_config *cfg, gfp_t gfp_flags,
+			    struct netlink_ext_ack *extack);
+	void (*fib6_nh_release)(struct fib6_nh *fib6_nh);
 	void (*udpv6_encap_enable)(void);
 	void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr,
 			      const struct in6_addr *solicited_addr,
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 945b66e3008f..e37e4c5871f7 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -173,6 +173,14 @@ eafnosupport_ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
 	return 0;
 }
 
+static int eafnosupport_fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
+				     struct fib6_config *cfg, gfp_t gfp_flags,
+				     struct netlink_ext_ack *extack)
+{
+	NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel");
+	return -EAFNOSUPPORT;
+}
+
 const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 	.ipv6_dst_lookup   = eafnosupport_ipv6_dst_lookup,
 	.ipv6_route_input  = eafnosupport_ipv6_route_input,
@@ -181,6 +189,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 	.fib6_lookup       = eafnosupport_fib6_lookup,
 	.fib6_multipath_select = eafnosupport_fib6_multipath_select,
 	.ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6,
+	.fib6_nh_init	   = eafnosupport_fib6_nh_init,
 };
 EXPORT_SYMBOL_GPL(ipv6_stub);
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 1789bf99c419..1dac6ea6666a 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -919,6 +919,8 @@ static const struct ipv6_stub ipv6_stub_impl = {
 	.fib6_lookup       = fib6_lookup,
 	.fib6_multipath_select = fib6_multipath_select,
 	.ip6_mtu_from_fib6 = ip6_mtu_from_fib6,
+	.fib6_nh_init	   = fib6_nh_init,
+	.fib6_nh_release   = fib6_nh_release,
 	.udpv6_encap_enable = udpv6_encap_enable,
 	.ndisc_send_na = ndisc_send_na,
 	.nd_tbl	= &nd_tbl,
-- 
cgit v1.2.3


From 71df5777aaaeff673c242a49b945b1b96fe81718 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:25 -0700
Subject: ipv6: Add neighbor helpers that use the ipv6 stub

Add ipv6 helpers to handle ndisc references via the stub. Update
bpf_ipv6_fib_lookup to use __ipv6_neigh_lookup_noref_stub instead of
the open code ___neigh_lookup_noref with the stub.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ndisc.h | 40 ++++++++++++++++++++++++++++++++++++++++
 net/core/filter.c   |  6 ++----
 2 files changed, 42 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index ddfbb591e2c5..366150053043 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -2,6 +2,8 @@
 #ifndef _NDISC_H
 #define _NDISC_H
 
+#include <net/ipv6_stubs.h>
+
 /*
  *	ICMP codes for neighbour discovery messages
  */
@@ -379,6 +381,14 @@ static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev
 	return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev);
 }
 
+static inline
+struct neighbour *__ipv6_neigh_lookup_noref_stub(struct net_device *dev,
+						 const void *pkey)
+{
+	return ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
+				     ndisc_hashfn, pkey, dev);
+}
+
 static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey)
 {
 	struct neighbour *n;
@@ -409,6 +419,36 @@ static inline void __ipv6_confirm_neigh(struct net_device *dev,
 	rcu_read_unlock_bh();
 }
 
+static inline void __ipv6_confirm_neigh_stub(struct net_device *dev,
+					     const void *pkey)
+{
+	struct neighbour *n;
+
+	rcu_read_lock_bh();
+	n = __ipv6_neigh_lookup_noref_stub(dev, pkey);
+	if (n) {
+		unsigned long now = jiffies;
+
+		/* avoid dirtying neighbour */
+		if (n->confirmed != now)
+			n->confirmed = now;
+	}
+	rcu_read_unlock_bh();
+}
+
+/* uses ipv6_stub and is meant for use outside of IPv6 core */
+static inline struct neighbour *ip_neigh_gw6(struct net_device *dev,
+					     const void *addr)
+{
+	struct neighbour *neigh;
+
+	neigh = __ipv6_neigh_lookup_noref_stub(dev, addr);
+	if (unlikely(!neigh))
+		neigh = __neigh_create(ipv6_stub->nd_tbl, addr, dev, false);
+
+	return neigh;
+}
+
 int ndisc_init(void);
 int ndisc_late_init(void);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 8904e3407163..26d9cd785ae2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4759,11 +4759,9 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	params->rt_metric = f6i->fib6_metric;
 
 	/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
-	 * not needed here. Can not use __ipv6_neigh_lookup_noref here
-	 * because we need to get nd_tbl via the stub
+	 * not needed here.
 	 */
-	neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
-				      ndisc_hashfn, dst, dev);
+	neigh = __ipv6_neigh_lookup_noref_stub(dev, dst);
 	if (!neigh)
 		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-- 
cgit v1.2.3


From bdf004677107e3b847c5db09c9fbf8edefa24996 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:26 -0700
Subject: net: Replace nhc_has_gw with nhc_gw_family

Allow the gateway in a fib_nh_common to be from a different address
family than the outer fib{6}_nh. To that end, replace nhc_has_gw with
nhc_gw_family and update users of nhc_has_gw to check nhc_gw_family.
Now nhc_family is used to know if the nh_common is part of a fib_nh
or fib6_nh (used for container_of to get to route family specific data),
and nhc_gw_family represents the address family for the gateway.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  |  4 ++--
 include/net/ip6_route.h                            |  2 +-
 include/net/ip_fib.h                               |  7 +++---
 include/trace/events/fib.h                         |  4 ++--
 net/core/filter.c                                  |  4 ++--
 net/ipv4/fib_semantics.c                           | 25 ++++++++++------------
 net/ipv4/route.c                                   |  5 +++--
 net/ipv6/addrconf.c                                |  2 +-
 net/ipv6/ip6_fib.c                                 |  2 +-
 net/ipv6/route.c                                   | 18 ++++++++--------
 10 files changed, 35 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 0ba9daa05a52..772aa78cab51 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4915,7 +4915,7 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6)
 static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
 {
 	/* RTF_CACHE routes are ignored */
-	return !(rt->fib6_flags & RTF_ADDRCONF) && rt->fib6_nh.fib_nh_has_gw;
+	return !(rt->fib6_flags & RTF_ADDRCONF) && rt->fib6_nh.fib_nh_gw_family;
 }
 
 static struct fib6_info *
@@ -5055,7 +5055,7 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
 static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp,
 				    const struct fib6_info *rt)
 {
-	return rt->fib6_nh.fib_nh_has_gw ||
+	return rt->fib6_nh.fib_nh_gw_family ||
 	       mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL);
 }
 
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 342180a7285c..5909fc421305 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -69,7 +69,7 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
 static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i)
 {
 	return !(f6i->fib6_flags & (RTF_ADDRCONF|RTF_DYNAMIC)) &&
-		f6i->fib6_nh.fib_nh_has_gw;
+		f6i->fib6_nh.fib_nh_gw_family;
 }
 
 void ip6_route_input(struct sk_buff *skb);
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 3ce07841dc3b..c68a40435ee0 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -83,8 +83,8 @@ struct fib_nh_common {
 	struct lwtunnel_state	*nhc_lwtstate;
 	unsigned char		nhc_scope;
 	u8			nhc_family;
-	u8			nhc_has_gw:1,
-				unused:7;
+	u8			nhc_gw_family;
+
 	union {
 		__be32          ipv4;
 		struct in6_addr ipv6;
@@ -112,8 +112,7 @@ struct fib_nh {
 #define fib_nh_flags		nh_common.nhc_flags
 #define fib_nh_lws		nh_common.nhc_lwtstate
 #define fib_nh_scope		nh_common.nhc_scope
-#define fib_nh_family		nh_common.nhc_family
-#define fib_nh_has_gw		nh_common.nhc_has_gw
+#define fib_nh_gw_family	nh_common.nhc_gw_family
 #define fib_nh_gw4		nh_common.nhc_gw.ipv4
 #define fib_nh_gw6		nh_common.nhc_gw.ipv6
 #define fib_nh_weight		nh_common.nhc_weight
diff --git a/include/trace/events/fib.h b/include/trace/events/fib.h
index 7f83b6eafc5c..6f2a4dc35e37 100644
--- a/include/trace/events/fib.h
+++ b/include/trace/events/fib.h
@@ -69,13 +69,13 @@ TRACE_EVENT(fib_table_lookup,
 		__assign_str(name, dev ? dev->name : "-");
 
 		if (nhc) {
-			if (nhc->nhc_family == AF_INET) {
+			if (nhc->nhc_gw_family == AF_INET) {
 				p32 = (__be32 *) __entry->gw4;
 				*p32 = nhc->nhc_gw.ipv4;
 
 				in6 = (struct in6_addr *)__entry->gw6;
 				*in6 = in6_zero;
-			} else if (nhc->nhc_family == AF_INET6) {
+			} else if (nhc->nhc_gw_family == AF_INET6) {
 				p32 = (__be32 *) __entry->gw4;
 				*p32 = 0;
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 26d9cd785ae2..abd5b6ce031a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4639,7 +4639,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
 	dev = nhc->nhc_dev;
-	if (nhc->nhc_has_gw)
+	if (nhc->nhc_gw_family)
 		params->ipv4_dst = nhc->nhc_gw.ipv4;
 
 	params->rt_metric = res.fi->fib_priority;
@@ -4752,7 +4752,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (f6i->fib6_nh.fib_nh_lws)
 		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
-	if (f6i->fib6_nh.fib_nh_has_gw)
+	if (f6i->fib6_nh.fib_nh_gw_family)
 		*dst = f6i->fib6_nh.fib_nh_gw6;
 
 	dev = f6i->fib6_nh.fib_nh_dev;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 8e0cb1687a74..e11f78c6373f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -513,7 +513,7 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 	nh->fib_nh_oif = cfg->fc_oif;
 	if (cfg->fc_gw) {
 		nh->fib_nh_gw4 = cfg->fc_gw;
-		nh->fib_nh_has_gw = 1;
+		nh->fib_nh_gw_family = AF_INET;
 	}
 	nh->fib_nh_flags = cfg->fc_flags;
 
@@ -1238,7 +1238,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 				       "Route with host scope can not have multiple nexthops");
 			goto err_inval;
 		}
-		if (nh->fib_nh_gw4) {
+		if (nh->fib_nh_gw_family) {
 			NL_SET_ERR_MSG(extack,
 				       "Route with host scope can not have a gateway");
 			goto err_inval;
@@ -1341,18 +1341,15 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
 		rcu_read_unlock();
 	}
 
-	if (nhc->nhc_has_gw) {
-		switch (nhc->nhc_family) {
-		case AF_INET:
-			if (nla_put_in_addr(skb, RTA_GATEWAY, nhc->nhc_gw.ipv4))
-				goto nla_put_failure;
-			break;
-		case AF_INET6:
-			if (nla_put_in6_addr(skb, RTA_GATEWAY,
-					     &nhc->nhc_gw.ipv6) < 0)
-				goto nla_put_failure;
-			break;
-		}
+	switch (nhc->nhc_gw_family) {
+	case AF_INET:
+		if (nla_put_in_addr(skb, RTA_GATEWAY, nhc->nhc_gw.ipv4))
+			goto nla_put_failure;
+		break;
+	case AF_INET6:
+		if (nla_put_in6_addr(skb, RTA_GATEWAY, &nhc->nhc_gw.ipv6) < 0)
+			goto nla_put_failure;
+		break;
 	}
 
 	*flags |= (nhc->nhc_flags & RTNH_F_ONLINK);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f3f2adf630d4..e7338e421796 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1734,8 +1734,9 @@ static int __mkroute_input(struct sk_buff *skb,
 	do_cache = res->fi && !itag;
 	if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
 	    skb->protocol == htons(ETH_P_IP)) {
-		__be32 gw = nhc->nhc_family == AF_INET ? nhc->nhc_gw.ipv4 : 0;
+		__be32 gw;
 
+		gw = nhc->nhc_gw_family == AF_INET ? nhc->nhc_gw.ipv4 : 0;
 		if (IN_DEV_SHARED_MEDIA(out_dev) ||
 		    inet_addr_onlink(out_dev, saddr, gw))
 			IPCB(skb)->flags |= IPSKB_DOREDIRECT;
@@ -2284,7 +2285,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		} else {
 			if (unlikely(fl4->flowi4_flags &
 				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nhc->nhc_has_gw &&
+				     !(nhc->nhc_gw_family &&
 				       nhc->nhc_scope == RT_SCOPE_LINK))) {
 				do_cache = false;
 				goto add;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2e8d1d2d8d3d..340a0f06f974 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2421,7 +2421,7 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 	for_each_fib6_node_rt_rcu(fn) {
 		if (rt->fib6_nh.fib_nh_dev->ifindex != dev->ifindex)
 			continue;
-		if (no_gw && rt->fib6_nh.fib_nh_has_gw)
+		if (no_gw && rt->fib6_nh.fib_nh_gw_family)
 			continue;
 		if ((rt->fib6_flags & flags) != flags)
 			continue;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 8c00609a1513..46f54a5bb1f0 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2304,7 +2304,7 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 #else
 	seq_puts(seq, "00000000000000000000000000000000 00 ");
 #endif
-	if (rt->fib6_nh.fib_nh_has_gw) {
+	if (rt->fib6_nh.fib_nh_gw_family) {
 		flags |= RTF_GATEWAY;
 		seq_printf(seq, "%pi6", &rt->fib6_nh.fib_nh_gw6);
 	} else {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6e89151693d0..69f92d2b780e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -533,7 +533,7 @@ static void rt6_probe(struct fib6_info *rt)
 	 * Router Reachability Probe MUST be rate-limited
 	 * to no more than one per minute.
 	 */
-	if (!rt || !rt->fib6_nh.fib_nh_has_gw)
+	if (!rt || !rt->fib6_nh.fib_nh_gw_family)
 		return;
 
 	nh_gw = &rt->fib6_nh.fib_nh_gw6;
@@ -595,7 +595,7 @@ static inline enum rt6_nud_state rt6_check_neigh(struct fib6_info *rt)
 	struct neighbour *neigh;
 
 	if (rt->fib6_flags & RTF_NONEXTHOP ||
-	    !rt->fib6_nh.fib_nh_has_gw)
+	    !rt->fib6_nh.fib_nh_gw_family)
 		return RT6_NUD_SUCCEED;
 
 	rcu_read_lock_bh();
@@ -769,7 +769,7 @@ static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn,
 
 static bool rt6_is_gw_or_nonexthop(const struct fib6_info *rt)
 {
-	return (rt->fib6_flags & RTF_NONEXTHOP) || rt->fib6_nh.fib_nh_has_gw;
+	return (rt->fib6_flags & RTF_NONEXTHOP) || rt->fib6_nh.fib_nh_gw_family;
 }
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
@@ -975,7 +975,7 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
 	rt->rt6i_dst = ort->fib6_dst;
 	rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL;
 	rt->rt6i_flags = ort->fib6_flags;
-	if (ort->fib6_nh.fib_nh_has_gw) {
+	if (ort->fib6_nh.fib_nh_gw_family) {
 		rt->rt6i_gateway = ort->fib6_nh.fib_nh_gw6;
 		rt->rt6i_flags |= RTF_GATEWAY;
 	}
@@ -1860,7 +1860,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		rcu_read_unlock();
 		return rt;
 	} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
-			    !f6i->fib6_nh.fib_nh_has_gw)) {
+			    !f6i->fib6_nh.fib_nh_gw_family)) {
 		/* Create a RTF_CACHE clone which will not be
 		 * owned by the fib6 tree.  It is for the special case where
 		 * the daddr in the skb during the neighbor look-up is different
@@ -2430,7 +2430,7 @@ restart:
 			continue;
 		if (rt->fib6_flags & RTF_REJECT)
 			break;
-		if (!rt->fib6_nh.fib_nh_has_gw)
+		if (!rt->fib6_nh.fib_nh_gw_family)
 			continue;
 		if (fl6->flowi6_oif != rt->fib6_nh.fib_nh_dev->ifindex)
 			continue;
@@ -2964,7 +2964,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 			goto out;
 
 		fib6_nh->fib_nh_gw6 = cfg->fc_gateway;
-		fib6_nh->fib_nh_has_gw = 1;
+		fib6_nh->fib_nh_gw_family = AF_INET6;
 	}
 
 	err = -ENODEV;
@@ -3476,7 +3476,7 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 		if (rt->fib6_nh.fib_nh_dev->ifindex != ifindex)
 			continue;
 		if (!(rt->fib6_flags & RTF_ROUTEINFO) ||
-		    !rt->fib6_nh.fib_nh_has_gw)
+		    !rt->fib6_nh.fib_nh_gw_family)
 			continue;
 		if (!ipv6_addr_equal(&rt->fib6_nh.fib_nh_gw6, gwaddr))
 			continue;
@@ -3807,7 +3807,7 @@ static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
 	struct in6_addr *gateway = (struct in6_addr *)arg;
 
 	if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
-	    rt->fib6_nh.fib_nh_has_gw &&
+	    rt->fib6_nh.fib_nh_gw_family &&
 	    ipv6_addr_equal(gateway, &rt->fib6_nh.fib_nh_gw6)) {
 		return -1;
 	}
-- 
cgit v1.2.3


From 1550c171935d264f522581fd037db5e64a716bb6 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:27 -0700
Subject: ipv4: Prepare rtable for IPv6 gateway

To allow the gateway to be either an IPv4 or IPv6 address, remove
rt_uses_gateway from rtable and replace with rt_gw_family. If
rt_gw_family is set it implies rt_uses_gateway. Rename rt_gateway
to rt_gw4 to represent the IPv4 version.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/core/addr.c                     |  2 +-
 drivers/infiniband/hw/nes/nes_cm.c                 |  2 +-
 drivers/net/appletalk/ipddp.c                      |  6 ++-
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun.c    |  2 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_span.c    |  3 +-
 include/net/route.h                                |  8 ++--
 net/atm/clip.c                                     |  4 +-
 net/ipv4/inet_connection_sock.c                    |  4 +-
 net/ipv4/ip_forward.c                              |  2 +-
 net/ipv4/ip_output.c                               |  2 +-
 net/ipv4/route.c                                   | 51 ++++++++++++----------
 net/ipv4/xfrm4_policy.c                            |  5 ++-
 net/mpls/mpls_iptunnel.c                           | 11 +++--
 13 files changed, 57 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 2649e0f2ff65..f5ecb660fe7d 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -351,7 +351,7 @@ static bool has_gateway(const struct dst_entry *dst, sa_family_t family)
 
 	if (family == AF_INET) {
 		rt = container_of(dst, struct rtable, dst);
-		return rt->rt_uses_gateway;
+		return rt->rt_gw_family == AF_INET;
 	}
 
 	rt6 = container_of(dst, struct rt6_info, dst);
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 032883180f65..0010a3ed64f1 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -1407,7 +1407,7 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 		if (neigh->nud_state & NUD_VALID) {
 			nes_debug(NES_DBG_CM, "Neighbor MAC address for 0x%08X"
 				  " is %pM, Gateway is 0x%08X \n", dst_ip,
-				  neigh->ha, ntohl(rt->rt_gateway));
+				  neigh->ha, ntohl(rt->rt_gw4));
 
 			if (arpindex >= 0) {
 				if (ether_addr_equal(nesadapter->arp_table[arpindex].mac_addr, neigh->ha)) {
diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c
index 3d27616d9c85..51cf5eca9c7f 100644
--- a/drivers/net/appletalk/ipddp.c
+++ b/drivers/net/appletalk/ipddp.c
@@ -116,11 +116,15 @@ static struct net_device * __init ipddp_init(void)
  */
 static netdev_tx_t ipddp_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	__be32 paddr = skb_rtable(skb)->rt_gateway;
+        struct rtable *rtable = skb_rtable(skb);
+        __be32 paddr = 0;
         struct ddpehdr *ddp;
         struct ipddp_route *rt;
         struct atalk_addr *our_addr;
 
+	if (rtable->rt_gw_family == AF_INET)
+		paddr = rtable->rt_gw4;
+
 	spin_lock(&ipddp_route_lock);
 
 	/*
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 9ab3bd904295..b9d5830e8344 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -70,7 +70,7 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	if (ret)
 		return ret;
 
-	if (mlx5_lag_is_multipath(mdev) && !rt->rt_gateway)
+	if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET)
 		return -ENETUNREACH;
 #else
 	return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 536c23c578c3..133a497e3457 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -316,7 +316,8 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
 	dev = rt->dst.dev;
 	*saddrp = fl4.saddr;
-	*daddrp = rt->rt_gateway;
+	if (rt->rt_gw_family == AF_INET)
+		*daddrp = rt->rt_gw4;
 
 out:
 	ip_rt_put(rt);
diff --git a/include/net/route.h b/include/net/route.h
index 9883dc82f723..96912b099c08 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -55,12 +55,12 @@ struct rtable {
 	unsigned int		rt_flags;
 	__u16			rt_type;
 	__u8			rt_is_input;
-	__u8			rt_uses_gateway;
+	u8			rt_gw_family;
 
 	int			rt_iif;
 
 	/* Info on neighbour */
-	__be32			rt_gateway;
+	__be32			rt_gw4;
 
 	/* Miscellaneous cached information */
 	u32			rt_mtu_locked:1,
@@ -82,8 +82,8 @@ static inline bool rt_is_output_route(const struct rtable *rt)
 
 static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr)
 {
-	if (rt->rt_gateway)
-		return rt->rt_gateway;
+	if (rt->rt_gw_family == AF_INET)
+		return rt->rt_gw4;
 	return daddr;
 }
 
diff --git a/net/atm/clip.c b/net/atm/clip.c
index d795b9c5aea4..b9e67e589a7b 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -345,8 +345,8 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 	}
 	rt = (struct rtable *) dst;
-	if (rt->rt_gateway)
-		daddr = &rt->rt_gateway;
+	if (rt->rt_gw_family == AF_INET)
+		daddr = &rt->rt_gw4;
 	else
 		daddr = &ip_hdr(skb)->daddr;
 	n = dst_neigh_lookup(dst, daddr);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6ea523d71947..a175e3e7ae97 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -564,7 +564,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
+	if (opt && opt->opt.is_strictroute && rt->rt_gw_family)
 		goto route_err;
 	rcu_read_unlock();
 	return &rt->dst;
@@ -602,7 +602,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
+	if (opt && opt->opt.is_strictroute && rt->rt_gw_family)
 		goto route_err;
 	return &rt->dst;
 
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 00ec819f949b..06f6f280b9ff 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -123,7 +123,7 @@ int ip_forward(struct sk_buff *skb)
 
 	rt = skb_rtable(skb);
 
-	if (opt->is_strictroute && rt->rt_uses_gateway)
+	if (opt->is_strictroute && rt->rt_gw_family)
 		goto sr_failed;
 
 	IPCB(skb)->flags |= IPSKB_FORWARDED;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 10b35328cfbc..a2bd4a6d9e6b 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -472,7 +472,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 	skb_dst_set_noref(skb, &rt->dst);
 
 packet_routed:
-	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
+	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gw_family)
 		goto no_route;
 
 	/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e7338e421796..b77b4950d0c7 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -434,14 +434,13 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 					   struct sk_buff *skb,
 					   const void *daddr)
 {
+	const struct rtable *rt = container_of(dst, struct rtable, dst);
 	struct net_device *dev = dst->dev;
 	const __be32 *pkey = daddr;
-	const struct rtable *rt;
 	struct neighbour *n;
 
-	rt = (const struct rtable *) dst;
-	if (rt->rt_gateway)
-		pkey = (const __be32 *) &rt->rt_gateway;
+	if (rt->rt_gw_family == AF_INET)
+		pkey = (const __be32 *) &rt->rt_gw4;
 	else if (skb)
 		pkey = &ip_hdr(skb)->daddr;
 
@@ -453,13 +452,12 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 
 static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr)
 {
+	const struct rtable *rt = container_of(dst, struct rtable, dst);
 	struct net_device *dev = dst->dev;
 	const __be32 *pkey = daddr;
-	const struct rtable *rt;
 
-	rt = (const struct rtable *)dst;
-	if (rt->rt_gateway)
-		pkey = (const __be32 *)&rt->rt_gateway;
+	if (rt->rt_gw_family == AF_INET)
+		pkey = (const __be32 *)&rt->rt_gw4;
 	else if (!daddr ||
 		 (rt->rt_flags &
 		  (RTCF_MULTICAST | RTCF_BROADCAST | RTCF_LOCAL)))
@@ -629,8 +627,8 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh
 
 	if (fnhe->fnhe_gw) {
 		rt->rt_flags |= RTCF_REDIRECTED;
-		rt->rt_gateway = fnhe->fnhe_gw;
-		rt->rt_uses_gateway = 1;
+		rt->rt_gw_family = AF_INET;
+		rt->rt_gw4 = fnhe->fnhe_gw;
 	}
 }
 
@@ -747,7 +745,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 		return;
 	}
 
-	if (rt->rt_gateway != old_gw)
+	if (rt->rt_gw_family != AF_INET || rt->rt_gw4 != old_gw)
 		return;
 
 	in_dev = __in_dev_get_rcu(dev);
@@ -1282,7 +1280,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	mtu = READ_ONCE(dst->dev->mtu);
 
 	if (unlikely(ip_mtu_locked(dst))) {
-		if (rt->rt_uses_gateway && mtu > 576)
+		if (rt->rt_gw_family && mtu > 576)
 			mtu = 576;
 	}
 
@@ -1410,8 +1408,10 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 			orig = NULL;
 		}
 		fill_route_from_fnhe(rt, fnhe);
-		if (!rt->rt_gateway)
-			rt->rt_gateway = daddr;
+		if (!rt->rt_gw4) {
+			rt->rt_gw4 = daddr;
+			rt->rt_gw_family = AF_INET;
+		}
 
 		if (do_cache) {
 			dst_hold(&rt->dst);
@@ -1538,8 +1538,8 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 
 		if (nh->fib_nh_gw4 && nh->fib_nh_scope == RT_SCOPE_LINK) {
-			rt->rt_gateway = nh->fib_nh_gw4;
-			rt->rt_uses_gateway = 1;
+			rt->rt_gw4 = nh->fib_nh_gw4;
+			rt->rt_gw_family = AF_INET;
 		}
 		ip_dst_init_metrics(&rt->dst, fi->fib_metrics);
 
@@ -1557,8 +1557,10 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 			 * However, if we are unsuccessful at storing this
 			 * route into the cache we really need to set it.
 			 */
-			if (!rt->rt_gateway)
-				rt->rt_gateway = daddr;
+			if (!rt->rt_gw4) {
+				rt->rt_gw_family = AF_INET;
+				rt->rt_gw4 = daddr;
+			}
 			rt_add_uncached_list(rt);
 		}
 	} else
@@ -1591,8 +1593,8 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 		rt->rt_iif = 0;
 		rt->rt_pmtu = 0;
 		rt->rt_mtu_locked = 0;
-		rt->rt_gateway = 0;
-		rt->rt_uses_gateway = 0;
+		rt->rt_gw_family = 0;
+		rt->rt_gw4 = 0;
 		INIT_LIST_HEAD(&rt->rt_uncached);
 
 		rt->dst.output = ip_output;
@@ -2595,8 +2597,9 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		rt->rt_genid = rt_genid_ipv4(net);
 		rt->rt_flags = ort->rt_flags;
 		rt->rt_type = ort->rt_type;
-		rt->rt_gateway = ort->rt_gateway;
-		rt->rt_uses_gateway = ort->rt_uses_gateway;
+		rt->rt_gw_family = ort->rt_gw_family;
+		if (rt->rt_gw_family == AF_INET)
+			rt->rt_gw4 = ort->rt_gw4;
 
 		INIT_LIST_HEAD(&rt->rt_uncached);
 	}
@@ -2675,8 +2678,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 		if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr))
 			goto nla_put_failure;
 	}
-	if (rt->rt_uses_gateway &&
-	    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gateway))
+	if (rt->rt_gw_family == AF_INET &&
+	    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4))
 		goto nla_put_failure;
 
 	expires = rt->dst.expires;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index d73a6d6652f6..ee53a91526e5 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -97,8 +97,9 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
 					      RTCF_LOCAL);
 	xdst->u.rt.rt_type = rt->rt_type;
-	xdst->u.rt.rt_gateway = rt->rt_gateway;
-	xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
+	xdst->u.rt.rt_gw_family = rt->rt_gw_family;
+	if (rt->rt_gw_family == AF_INET)
+		xdst->u.rt.rt_gw4 = rt->rt_gw4;
 	xdst->u.rt.rt_pmtu = rt->rt_pmtu;
 	xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked;
 	INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index f3a8557494d6..1f61b4e53686 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -137,10 +137,13 @@ static int mpls_xmit(struct sk_buff *skb)
 
 	mpls_stats_inc_outucastpkts(out_dev, skb);
 
-	if (rt)
-		err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway,
-				 skb);
-	else if (rt6) {
+	if (rt) {
+		if (rt->rt_gw_family == AF_INET)
+			err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gw4,
+					 skb);
+		else
+			err = -EAFNOSUPPORT;
+	} else if (rt6) {
 		if (ipv6_addr_v4mapped(&rt6->rt6i_gateway)) {
 			/* 6PE (RFC 4798) */
 			err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt6->rt6i_gateway.s6_addr32[3],
-- 
cgit v1.2.3


From f35b794b3b405e2478654ea875bc0b29fe1a1bc5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:28 -0700
Subject: ipv4: Prepare fib_config for IPv6 gateway

Similar to rtable, fib_config needs to allow the gateway to be either an
IPv4 or an IPv6 address. To that end, rename fc_gw to fc_gw4 to mean an
IPv4 address and add fc_gw_family. Checks on 'is a gateway set' are changed
to see if fc_gw_family is set. In the process prepare the code for a
fc_gw_family == AF_INET6.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  5 +++--
 net/ipv4/fib_frontend.c  |  8 +++++---
 net/ipv4/fib_semantics.c | 40 ++++++++++++++++++++++++++--------------
 3 files changed, 34 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index c68a40435ee0..1f72ad553c31 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -32,10 +32,11 @@ struct fib_config {
 	u8			fc_protocol;
 	u8			fc_scope;
 	u8			fc_type;
-	/* 3 bytes unused */
+	u8			fc_gw_family;
+	/* 2 bytes unused */
 	u32			fc_table;
 	__be32			fc_dst;
-	__be32			fc_gw;
+	__be32			fc_gw4;
 	int			fc_oif;
 	u32			fc_flags;
 	u32			fc_priority;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 15f779bd26b3..f99a2ec32505 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -558,7 +558,8 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
 	if (rt->rt_gateway.sa_family == AF_INET && addr) {
 		unsigned int addr_type;
 
-		cfg->fc_gw = addr;
+		cfg->fc_gw4 = addr;
+		cfg->fc_gw_family = AF_INET;
 		addr_type = inet_addr_type_table(net, addr, cfg->fc_table);
 		if (rt->rt_flags & RTF_GATEWAY &&
 		    addr_type == RTN_UNICAST)
@@ -568,7 +569,7 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
 	if (cmd == SIOCDELRT)
 		return 0;
 
-	if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw)
+	if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family)
 		return -EINVAL;
 
 	if (cfg->fc_scope == RT_SCOPE_NOWHERE)
@@ -708,7 +709,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			cfg->fc_oif = nla_get_u32(attr);
 			break;
 		case RTA_GATEWAY:
-			cfg->fc_gw = nla_get_be32(attr);
+			cfg->fc_gw_family = AF_INET;
+			cfg->fc_gw4 = nla_get_be32(attr);
 			break;
 		case RTA_VIA:
 			NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute");
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e11f78c6373f..d3e26e55f2e1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -511,8 +511,8 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 		goto init_failure;
 
 	nh->fib_nh_oif = cfg->fc_oif;
-	if (cfg->fc_gw) {
-		nh->fib_nh_gw4 = cfg->fc_gw;
+	if (cfg->fc_gw_family == AF_INET) {
+		nh->fib_nh_gw4 = cfg->fc_gw4;
 		nh->fib_nh_gw_family = AF_INET;
 	}
 	nh->fib_nh_flags = cfg->fc_flags;
@@ -589,8 +589,10 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
-			if (nla)
-				fib_cfg.fc_gw = nla_get_in_addr(nla);
+			if (nla) {
+				fib_cfg.fc_gw_family = AF_INET;
+				fib_cfg.fc_gw4 = nla_get_in_addr(nla);
+			}
 
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
 			if (nla)
@@ -616,10 +618,14 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 			       "Nexthop device index does not match RTA_OIF");
 		goto errout;
 	}
-	if (cfg->fc_gw && fi->fib_nh->fib_nh_gw4 != cfg->fc_gw) {
-		NL_SET_ERR_MSG(extack,
-			       "Nexthop gateway does not match RTA_GATEWAY");
-		goto errout;
+	if (cfg->fc_gw_family) {
+		if (cfg->fc_gw_family != fi->fib_nh->fib_nh_gw_family ||
+		    (cfg->fc_gw_family == AF_INET &&
+		     fi->fib_nh->fib_nh_gw4 != cfg->fc_gw4)) {
+			NL_SET_ERR_MSG(extack,
+				       "Nexthop gateway does not match RTA_GATEWAY");
+			goto errout;
+		}
 	}
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) {
@@ -719,7 +725,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 	if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
 		return 1;
 
-	if (cfg->fc_oif || cfg->fc_gw) {
+	if (cfg->fc_oif || cfg->fc_gw_family) {
 		if (cfg->fc_encap) {
 			if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap,
 					    fi->fib_nh, cfg, extack))
@@ -730,10 +736,16 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 		    cfg->fc_flow != fi->fib_nh->nh_tclassid)
 			return 1;
 #endif
-		if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->fib_nh_oif) &&
-		    (!cfg->fc_gw  || cfg->fc_gw == fi->fib_nh->fib_nh_gw4))
-			return 0;
-		return 1;
+		if ((cfg->fc_oif && cfg->fc_oif != fi->fib_nh->fib_nh_oif) ||
+		    (cfg->fc_gw_family &&
+		     cfg->fc_gw_family != fi->fib_nh->fib_nh_gw_family))
+			return 1;
+
+		if (cfg->fc_gw_family == AF_INET &&
+		    cfg->fc_gw4 != fi->fib_nh->fib_nh_gw4)
+			return 1;
+
+		return 0;
 	}
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -1204,7 +1216,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 		goto failure;
 
 	if (fib_props[cfg->fc_type].error) {
-		if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp) {
+		if (cfg->fc_gw_family || cfg->fc_oif || cfg->fc_mp) {
 			NL_SET_ERR_MSG(extack,
 				       "Gateway, device and multipath can not be specified for this route type");
 			goto err_inval;
-- 
cgit v1.2.3


From 0f5f7d7bf6e6bda4dffe7b42812a16ada6ea9816 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:29 -0700
Subject: ipv4: Add support to rtable for ipv6 gateway

Add support for an IPv6 gateway to rtable. Since a gateway is either
IPv4 or IPv6, make it a union with rt_gw4 where rt_gw_family decides
which address is in use.

When dumping the route data, encode an ipv6 nexthop using RTA_VIA.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_span.c    |  3 +++
 include/net/route.h                                |  5 +++-
 net/ipv4/route.c                                   | 31 ++++++++++++++++++----
 net/ipv4/xfrm4_policy.c                            |  2 ++
 net/mpls/mpls_iptunnel.c                           |  5 ++--
 5 files changed, 38 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 133a497e3457..560a60e522f9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -318,6 +318,9 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 	*saddrp = fl4.saddr;
 	if (rt->rt_gw_family == AF_INET)
 		*daddrp = rt->rt_gw4;
+	/* can not offload if route has an IPv6 gateway */
+	else if (rt->rt_gw_family == AF_INET6)
+		dev = NULL;
 
 out:
 	ip_rt_put(rt);
diff --git a/include/net/route.h b/include/net/route.h
index 96912b099c08..5d28a2509b58 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -60,7 +60,10 @@ struct rtable {
 	int			rt_iif;
 
 	/* Info on neighbour */
-	__be32			rt_gw4;
+	union {
+		__be32		rt_gw4;
+		struct in6_addr	rt_gw6;
+	};
 
 	/* Miscellaneous cached information */
 	u32			rt_mtu_locked:1,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b77b4950d0c7..6e58acf0a87b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1535,14 +1535,20 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 
 	if (fi) {
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
-		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
+		struct fib_nh *nh;
 
-		if (nh->fib_nh_gw4 && nh->fib_nh_scope == RT_SCOPE_LINK) {
-			rt->rt_gw4 = nh->fib_nh_gw4;
-			rt->rt_gw_family = AF_INET;
+		if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) {
+			rt->rt_gw_family = nhc->nhc_gw_family;
+			/* only INET and INET6 are supported */
+			if (likely(nhc->nhc_gw_family == AF_INET))
+				rt->rt_gw4 = nhc->nhc_gw.ipv4;
+			else
+				rt->rt_gw6 = nhc->nhc_gw.ipv6;
 		}
+
 		ip_dst_init_metrics(&rt->dst, fi->fib_metrics);
 
+		nh = container_of(nhc, struct fib_nh, nh_common);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
 #endif
@@ -2600,6 +2606,8 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		rt->rt_gw_family = ort->rt_gw_family;
 		if (rt->rt_gw_family == AF_INET)
 			rt->rt_gw4 = ort->rt_gw4;
+		else if (rt->rt_gw_family == AF_INET6)
+			rt->rt_gw6 = ort->rt_gw6;
 
 		INIT_LIST_HEAD(&rt->rt_uncached);
 	}
@@ -2679,8 +2687,21 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 			goto nla_put_failure;
 	}
 	if (rt->rt_gw_family == AF_INET &&
-	    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4))
+	    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) {
 		goto nla_put_failure;
+	} else if (rt->rt_gw_family == AF_INET6) {
+		int alen = sizeof(struct in6_addr);
+		struct nlattr *nla;
+		struct rtvia *via;
+
+		nla = nla_reserve(skb, RTA_VIA, alen + 2);
+		if (!nla)
+			goto nla_put_failure;
+
+		via = nla_data(nla);
+		via->rtvia_family = AF_INET6;
+		memcpy(via->rtvia_addr, &rt->rt_gw6, alen);
+	}
 
 	expires = rt->dst.expires;
 	if (expires) {
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index ee53a91526e5..72d19b1838ed 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -100,6 +100,8 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	xdst->u.rt.rt_gw_family = rt->rt_gw_family;
 	if (rt->rt_gw_family == AF_INET)
 		xdst->u.rt.rt_gw4 = rt->rt_gw4;
+	else if (rt->rt_gw_family == AF_INET6)
+		xdst->u.rt.rt_gw6 = rt->rt_gw6;
 	xdst->u.rt.rt_pmtu = rt->rt_pmtu;
 	xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked;
 	INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 1f61b4e53686..2619c2fbea93 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -141,8 +141,9 @@ static int mpls_xmit(struct sk_buff *skb)
 		if (rt->rt_gw_family == AF_INET)
 			err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gw4,
 					 skb);
-		else
-			err = -EAFNOSUPPORT;
+		else if (rt->rt_gw_family == AF_INET6)
+			err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt->rt_gw6,
+					 skb);
 	} else if (rt6) {
 		if (ipv6_addr_v4mapped(&rt6->rt6i_gateway)) {
 			/* 6PE (RFC 4798) */
-- 
cgit v1.2.3


From a4ea5d43c807be28545625c1e0641905022fa0d1 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:30 -0700
Subject: ipv4: Add support to fib_config for IPv6 gateway

Add support for an IPv6 gateway to fib_config. Since a gateway is either
IPv4 or IPv6, make it a union with fc_gw4 where fc_gw_family decides
which address is in use. Update current checks on family and gw4 to
handle ipv6 as well.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  5 ++++-
 net/ipv4/fib_semantics.c | 29 +++++++++++++++++++++++------
 2 files changed, 27 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 1f72ad553c31..f1c452f618a9 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -36,7 +36,10 @@ struct fib_config {
 	/* 2 bytes unused */
 	u32			fc_table;
 	__be32			fc_dst;
-	__be32			fc_gw4;
+	union {
+		__be32		fc_gw4;
+		struct in6_addr	fc_gw6;
+	};
 	int			fc_oif;
 	u32			fc_flags;
 	u32			fc_priority;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index d3e26e55f2e1..680b5a9a911a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -276,7 +276,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
 
 	for_nexthops(fi) {
 		if (nh->fib_nh_oif != onh->fib_nh_oif ||
-		    nh->fib_nh_gw4 != onh->fib_nh_gw4 ||
+		    nh->fib_nh_gw_family != onh->fib_nh_gw_family ||
 		    nh->fib_nh_scope != onh->fib_nh_scope ||
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 		    nh->fib_nh_weight != onh->fib_nh_weight ||
@@ -287,6 +287,15 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
 		    lwtunnel_cmp_encap(nh->fib_nh_lws, onh->fib_nh_lws) ||
 		    ((nh->fib_nh_flags ^ onh->fib_nh_flags) & ~RTNH_COMPARE_MASK))
 			return -1;
+
+		if (nh->fib_nh_gw_family == AF_INET &&
+		    nh->fib_nh_gw4 != onh->fib_nh_gw4)
+			return -1;
+
+		if (nh->fib_nh_gw_family == AF_INET6 &&
+		    ipv6_addr_cmp(&nh->fib_nh_gw6, &onh->fib_nh_gw6))
+			return -1;
+
 		onh++;
 	} endfor_nexthops(fi);
 	return 0;
@@ -511,10 +520,12 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 		goto init_failure;
 
 	nh->fib_nh_oif = cfg->fc_oif;
-	if (cfg->fc_gw_family == AF_INET) {
+	nh->fib_nh_gw_family = cfg->fc_gw_family;
+	if (cfg->fc_gw_family == AF_INET)
 		nh->fib_nh_gw4 = cfg->fc_gw4;
-		nh->fib_nh_gw_family = AF_INET;
-	}
+	else if (cfg->fc_gw_family == AF_INET6)
+		nh->fib_nh_gw6 = cfg->fc_gw6;
+
 	nh->fib_nh_flags = cfg->fc_flags;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -621,9 +632,11 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 	if (cfg->fc_gw_family) {
 		if (cfg->fc_gw_family != fi->fib_nh->fib_nh_gw_family ||
 		    (cfg->fc_gw_family == AF_INET &&
-		     fi->fib_nh->fib_nh_gw4 != cfg->fc_gw4)) {
+		     fi->fib_nh->fib_nh_gw4 != cfg->fc_gw4) ||
+		    (cfg->fc_gw_family == AF_INET6 &&
+		     ipv6_addr_cmp(&fi->fib_nh->fib_nh_gw6, &cfg->fc_gw6))) {
 			NL_SET_ERR_MSG(extack,
-				       "Nexthop gateway does not match RTA_GATEWAY");
+				       "Nexthop gateway does not match RTA_GATEWAY or RTA_VIA");
 			goto errout;
 		}
 	}
@@ -745,6 +758,10 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 		    cfg->fc_gw4 != fi->fib_nh->fib_nh_gw4)
 			return 1;
 
+		if (cfg->fc_gw_family == AF_INET6 &&
+		    ipv6_addr_cmp(&cfg->fc_gw6, &fi->fib_nh->fib_nh_gw6))
+			return 1;
+
 		return 0;
 	}
 
-- 
cgit v1.2.3


From 0353f28231c79416191326810e7fe656b69c63b7 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:33 -0700
Subject: neighbor: Add skip_cache argument to neigh_output

A later patch allows an IPv6 gateway with an IPv4 route. The neighbor
entry will exist in the v6 ndisc table and the cached header will contain
the ipv6 protocol which is wrong for an IPv4 packet. For an IPv4 packet to
use the v6 neighbor entry, neigh_output needs to skip the cached header
and just use the output callback for the neigh entry.

A future patchset can look at expanding the hh_cache to handle 2
protocols. For now, IPv6 gateways with an IPv4 route will take the
extra overhead of generating the header.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c       | 4 ++--
 include/net/neighbour.h | 5 +++--
 net/ipv4/ip_output.c    | 2 +-
 net/ipv6/ip6_output.c   | 2 +-
 4 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 6d1a1abbed27..fd1337736aa0 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -370,7 +370,7 @@ static int vrf_finish_output6(struct net *net, struct sock *sk,
 		neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
 	if (!IS_ERR(neigh)) {
 		sock_confirm_neigh(skb, neigh);
-		ret = neigh_output(neigh, skb);
+		ret = neigh_output(neigh, skb, false);
 		rcu_read_unlock_bh();
 		return ret;
 	}
@@ -578,7 +578,7 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 		neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
 	if (!IS_ERR(neigh)) {
 		sock_confirm_neigh(skb, neigh);
-		ret = neigh_output(neigh, skb);
+		ret = neigh_output(neigh, skb, false);
 		rcu_read_unlock_bh();
 		return ret;
 	}
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 7c1ab9edba03..3e5438bd0101 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -498,11 +498,12 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb
 	return dev_queue_xmit(skb);
 }
 
-static inline int neigh_output(struct neighbour *n, struct sk_buff *skb)
+static inline int neigh_output(struct neighbour *n, struct sk_buff *skb,
+			       bool skip_cache)
 {
 	const struct hh_cache *hh = &n->hh;
 
-	if ((n->nud_state & NUD_CONNECTED) && hh->hh_len)
+	if ((n->nud_state & NUD_CONNECTED) && hh->hh_len && !skip_cache)
 		return neigh_hh_output(hh, skb);
 	else
 		return n->output(n, skb);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a2bd4a6d9e6b..cca4892b8cb2 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -226,7 +226,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
 		int res;
 
 		sock_confirm_neigh(skb, neigh);
-		res = neigh_output(neigh, skb);
+		res = neigh_output(neigh, skb, false);
 
 		rcu_read_unlock_bh();
 		return res;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index e51f3c648b09..adef2236abe2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -117,7 +117,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 		neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
 	if (!IS_ERR(neigh)) {
 		sock_confirm_neigh(skb, neigh);
-		ret = neigh_output(neigh, skb);
+		ret = neigh_output(neigh, skb, false);
 		rcu_read_unlock_bh();
 		return ret;
 	}
-- 
cgit v1.2.3


From 5c9f7c1dfc2e0776551ef1ceb335187c6698d1ff Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:34 -0700
Subject: ipv4: Add helpers for neigh lookup for nexthop

A common theme in the output path is looking up a neigh entry for a
nexthop, either the gateway in an rtable or a fallback to the daddr
in the skb:

        nexthop = (__force u32)rt_nexthop(rt, ip_hdr(skb)->daddr);
        neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
        if (unlikely(!neigh))
                neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);

To allow the nexthop to be an IPv6 address we need to consider the
family of the nexthop and then call __ipv{4,6}_neigh_lookup_noref based
on it.

To make this simpler, add a ip_neigh_gw4 helper similar to ip_neigh_gw6
added in an earlier patch which handles:

        neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
        if (unlikely(!neigh))
                neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);

And then add a second one, ip_neigh_for_gw, that calls either
ip_neigh_gw4 or ip_neigh_gw6 based on the address family of the gateway.

Update the output paths in the VRF driver and core v4 code to use
ip_neigh_for_gw simplifying the family based lookup and making both
ready for a v6 nexthop.

ipv4_neigh_lookup has a different need - the potential to resolve a
passed in address in addition to any gateway in the rtable or skb. Since
this is a one-off, add ip_neigh_gw4 and ip_neigh_gw6 diectly. The
difference between __neigh_create used by the helpers and neigh_create
called by ipv4_neigh_lookup is taking a refcount, so add rcu_read_lock_bh
and bump the refcnt on the neigh entry.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c    | 10 ++++------
 include/net/route.h  | 32 ++++++++++++++++++++++++++++++++
 net/ipv4/ip_output.c | 11 ++++-------
 net/ipv4/route.c     | 29 +++++++++++++++++++----------
 4 files changed, 59 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index fd1337736aa0..18d752ae554f 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -549,7 +549,7 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	struct net_device *dev = dst->dev;
 	unsigned int hh_len = LL_RESERVED_SPACE(dev);
 	struct neighbour *neigh;
-	u32 nexthop;
+	bool is_v6gw = false;
 	int ret = -EINVAL;
 
 	nf_reset(skb);
@@ -572,13 +572,11 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 
 	rcu_read_lock_bh();
 
-	nexthop = (__force u32)rt_nexthop(rt, ip_hdr(skb)->daddr);
-	neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
-	if (unlikely(!neigh))
-		neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
+	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
 	if (!IS_ERR(neigh)) {
 		sock_confirm_neigh(skb, neigh);
-		ret = neigh_output(neigh, skb, false);
+		/* if crossing protocols, can not use the cached header */
+		ret = neigh_output(neigh, skb, is_v6gw);
 		rcu_read_unlock_bh();
 		return ret;
 	}
diff --git a/include/net/route.h b/include/net/route.h
index 5d28a2509b58..96f6c9ae33c2 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -29,6 +29,8 @@
 #include <net/flow.h>
 #include <net/inet_sock.h>
 #include <net/ip_fib.h>
+#include <net/arp.h>
+#include <net/ndisc.h>
 #include <linux/in_route.h>
 #include <linux/rtnetlink.h>
 #include <linux/rcupdate.h>
@@ -350,4 +352,34 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
 	return hoplimit;
 }
 
+static inline struct neighbour *ip_neigh_gw4(struct net_device *dev,
+					     __be32 daddr)
+{
+	struct neighbour *neigh;
+
+	neigh = __ipv4_neigh_lookup_noref(dev, daddr);
+	if (unlikely(!neigh))
+		neigh = __neigh_create(&arp_tbl, &daddr, dev, false);
+
+	return neigh;
+}
+
+static inline struct neighbour *ip_neigh_for_gw(struct rtable *rt,
+						struct sk_buff *skb,
+						bool *is_v6gw)
+{
+	struct net_device *dev = rt->dst.dev;
+	struct neighbour *neigh;
+
+	if (likely(rt->rt_gw_family == AF_INET)) {
+		neigh = ip_neigh_gw4(dev, rt->rt_gw4);
+	} else if (rt->rt_gw_family == AF_INET6) {
+		neigh = ip_neigh_gw6(dev, &rt->rt_gw6);
+		*is_v6gw = true;
+	} else {
+		neigh = ip_neigh_gw4(dev, ip_hdr(skb)->daddr);
+	}
+	return neigh;
+}
+
 #endif	/* _ROUTE_H */
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index cca4892b8cb2..4e42c1974ba2 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -188,7 +188,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
 	struct net_device *dev = dst->dev;
 	unsigned int hh_len = LL_RESERVED_SPACE(dev);
 	struct neighbour *neigh;
-	u32 nexthop;
+	bool is_v6gw = false;
 
 	if (rt->rt_type == RTN_MULTICAST) {
 		IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len);
@@ -218,16 +218,13 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
 	}
 
 	rcu_read_lock_bh();
-	nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
-	neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
-	if (unlikely(!neigh))
-		neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
+	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
 	if (!IS_ERR(neigh)) {
 		int res;
 
 		sock_confirm_neigh(skb, neigh);
-		res = neigh_output(neigh, skb, false);
-
+		/* if crossing protocols, can not use the cached header */
+		res = neigh_output(neigh, skb, is_v6gw);
 		rcu_read_unlock_bh();
 		return res;
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6e58acf0a87b..32ecb4c1c7e3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -436,18 +436,27 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 {
 	const struct rtable *rt = container_of(dst, struct rtable, dst);
 	struct net_device *dev = dst->dev;
-	const __be32 *pkey = daddr;
 	struct neighbour *n;
 
-	if (rt->rt_gw_family == AF_INET)
-		pkey = (const __be32 *) &rt->rt_gw4;
-	else if (skb)
-		pkey = &ip_hdr(skb)->daddr;
-
-	n = __ipv4_neigh_lookup(dev, *(__force u32 *)pkey);
-	if (n)
-		return n;
-	return neigh_create(&arp_tbl, pkey, dev);
+	rcu_read_lock_bh();
+
+	if (likely(rt->rt_gw_family == AF_INET)) {
+		n = ip_neigh_gw4(dev, rt->rt_gw4);
+	} else if (rt->rt_gw_family == AF_INET6) {
+		n = ip_neigh_gw6(dev, &rt->rt_gw6);
+        } else {
+		__be32 pkey;
+
+		pkey = skb ? ip_hdr(skb)->daddr : *((__be32 *) daddr);
+		n = ip_neigh_gw4(dev, pkey);
+	}
+
+	if (n && !refcount_inc_not_zero(&n->refcnt))
+		n = NULL;
+
+	rcu_read_unlock_bh();
+
+	return n;
 }
 
 static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr)
-- 
cgit v1.2.3


From 19a9d136f198cd7c4e26ea6897a0cf067d3f7ecb Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:39 -0700
Subject: ipv4: Flag fib_info with a fib_nh using IPv6 gateway

Until support is added to the offload drivers, they need to be able to
reject routes with an IPv6 gateway. To that end add a flag to fib_info
that indicates if any fib_nh has a v6 gateway. The flag allows the drivers
to efficiently know the use of a v6 gateway without walking all fib_nh
tied to a fib_info each time a route is added.

Update mlxsw and rocker to reject the routes with extack message as to why.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 8 ++++++++
 drivers/net/ethernet/rocker/rocker_main.c             | 9 +++++++++
 include/net/ip_fib.h                                  | 1 +
 net/ipv4/fib_semantics.c                              | 2 ++
 4 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 772aa78cab51..5f05723011b4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6092,6 +6092,14 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 			NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route");
 			return notifier_from_errno(-EINVAL);
 		}
+		if (info->family == AF_INET) {
+			struct fib_entry_notifier_info *fen_info = ptr;
+
+			if (fen_info->fi->fib_nh_is_v6) {
+				NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported");
+				return notifier_from_errno(-EINVAL);
+			}
+		}
 		break;
 	}
 
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index a71c900ca04f..7ae6c124bfe9 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2207,6 +2207,15 @@ static int rocker_router_fib_event(struct notifier_block *nb,
 	switch (event) {
 	case FIB_EVENT_ENTRY_ADD: /* fall through */
 	case FIB_EVENT_ENTRY_DEL:
+		if (info->family == AF_INET) {
+			struct fib_entry_notifier_info *fen_info = ptr;
+
+			if (fen_info->fi->fib_nh_is_v6) {
+				NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported");
+				return notifier_from_errno(-EINVAL);
+			}
+		}
+
 		memcpy(&fib_work->fen_info, ptr, sizeof(fib_work->fen_info));
 		/* Take referece on fib_info to prevent it from being
 		 * freed while work is queued. Release it afterwards.
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index f1c452f618a9..337106469ec5 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -147,6 +147,7 @@ struct fib_info {
 #define fib_rtt fib_metrics->metrics[RTAX_RTT-1]
 #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1]
 	int			fib_nhs;
+	bool			fib_nh_is_v6;
 	struct rcu_head		rcu;
 	struct fib_nh		fib_nh[0];
 #define fib_dev		fib_nh[0].fib_nh_dev
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c1ea138335a2..4a968e24507b 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1349,6 +1349,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 
 	change_nexthops(fi) {
 		fib_info_update_nh_saddr(net, nexthop_nh);
+		if (nexthop_nh->fib_nh_gw_family == AF_INET6)
+			fi->fib_nh_is_v6 = true;
 	} endfor_nexthops(fi)
 
 	fib_rebalance(fi);
-- 
cgit v1.2.3


From d15662682db232da77136cd348f4c9df312ca6f9 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 5 Apr 2019 16:30:40 -0700
Subject: ipv4: Allow ipv6 gateway with ipv4 routes

Add support for RTA_VIA and allow an IPv6 nexthop for v4 routes:
   $ ip ro add 172.16.1.0/24 via inet6 2001:db8::1 dev eth0
   $ ip ro ls
   ...
   172.16.1.0/24 via inet6 2001:db8::1 dev eth0

For convenience and simplicity, userspace can use RTA_VIA to specify
AF_INET or AF_INET6 gateway.

The common fib_nexthop_info dump function compares the gateway address
family to the nh_common family to know if the gateway should be encoded
as RTA_VIA or RTA_GATEWAY.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  2 ++
 net/ipv4/fib_frontend.c  | 60 ++++++++++++++++++++++++++++++++++++++---
 net/ipv4/fib_semantics.c | 69 ++++++++++++++++++++++++++++++++++++++++++++----
 3 files changed, 123 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 337106469ec5..d8195c77e247 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -401,6 +401,8 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net,
 /* Exported by fib_frontend.c */
 extern const struct nla_policy rtm_ipv4_policy[];
 void ip_fib_init(void);
+int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
+		    struct netlink_ext_ack *extack);
 __be32 fib_compute_spec_dst(struct sk_buff *skb);
 bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev);
 int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index f99a2ec32505..310060e67790 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -665,10 +665,55 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
 	[RTA_DPORT]		= { .type = NLA_U16 },
 };
 
+int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
+		    struct netlink_ext_ack *extack)
+{
+	struct rtvia *via;
+	int alen;
+
+	if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) {
+		NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA");
+		return -EINVAL;
+	}
+
+	via = nla_data(nla);
+	alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr);
+
+	switch (via->rtvia_family) {
+	case AF_INET:
+		if (alen != sizeof(__be32)) {
+			NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA");
+			return -EINVAL;
+		}
+		cfg->fc_gw_family = AF_INET;
+		cfg->fc_gw4 = *((__be32 *)via->rtvia_addr);
+		break;
+	case AF_INET6:
+#ifdef CONFIG_IPV6
+		if (alen != sizeof(struct in6_addr)) {
+			NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA");
+			return -EINVAL;
+		}
+		cfg->fc_gw_family = AF_INET6;
+		cfg->fc_gw6 = *((struct in6_addr *)via->rtvia_addr);
+#else
+		NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel");
+		return -EINVAL;
+#endif
+		break;
+	default:
+		NL_SET_ERR_MSG(extack, "Unsupported address family in RTA_VIA");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			     struct nlmsghdr *nlh, struct fib_config *cfg,
 			     struct netlink_ext_ack *extack)
 {
+	bool has_gw = false, has_via = false;
 	struct nlattr *attr;
 	int err, remaining;
 	struct rtmsg *rtm;
@@ -709,13 +754,16 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			cfg->fc_oif = nla_get_u32(attr);
 			break;
 		case RTA_GATEWAY:
+			has_gw = true;
 			cfg->fc_gw_family = AF_INET;
 			cfg->fc_gw4 = nla_get_be32(attr);
 			break;
 		case RTA_VIA:
-			NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute");
-			err = -EINVAL;
-			goto errout;
+			has_via = true;
+			err = fib_gw_from_via(cfg, attr, extack);
+			if (err)
+				goto errout;
+			break;
 		case RTA_PRIORITY:
 			cfg->fc_priority = nla_get_u32(attr);
 			break;
@@ -754,6 +802,12 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		}
 	}
 
+	if (has_gw && has_via) {
+		NL_SET_ERR_MSG(extack,
+			       "Nexthop configuration can not contain both GATEWAY and VIA");
+		goto errout;
+	}
+
 	return 0;
 errout:
 	return err;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 4a968e24507b..017273885eee 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -606,12 +606,22 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
-			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+			struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+			nlav = nla_find(attrs, attrlen, RTA_VIA);
+			if (nla && nlav) {
+				NL_SET_ERR_MSG(extack,
+					       "Nexthop configuration can not contain both GATEWAY and VIA");
+				return -EINVAL;
+			}
 			if (nla) {
 				fib_cfg.fc_gw_family = AF_INET;
 				fib_cfg.fc_gw4 = nla_get_in_addr(nla);
+			} else if (nlav) {
+				ret = fib_gw_from_via(&fib_cfg, nlav, extack);
+				if (ret)
+					goto errout;
 			}
 
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
@@ -792,11 +802,43 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
-			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+			struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
-			if (nla && nla_get_in_addr(nla) != nh->fib_nh_gw4)
-				return 1;
+			nlav = nla_find(attrs, attrlen, RTA_VIA);
+			if (nla && nlav) {
+				NL_SET_ERR_MSG(extack,
+					       "Nexthop configuration can not contain both GATEWAY and VIA");
+				return -EINVAL;
+			}
+
+			if (nla) {
+				if (nh->fib_nh_gw_family != AF_INET ||
+				    nla_get_in_addr(nla) != nh->fib_nh_gw4)
+					return 1;
+			} else if (nlav) {
+				struct fib_config cfg2;
+				int err;
+
+				err = fib_gw_from_via(&cfg2, nlav, extack);
+				if (err)
+					return err;
+
+				switch (nh->fib_nh_gw_family) {
+				case AF_INET:
+					if (cfg2.fc_gw_family != AF_INET ||
+					    cfg2.fc_gw4 != nh->fib_nh_gw4)
+						return 1;
+					break;
+				case AF_INET6:
+					if (cfg2.fc_gw_family != AF_INET6 ||
+					    ipv6_addr_cmp(&cfg2.fc_gw6,
+							  &nh->fib_nh_gw6))
+						return 1;
+					break;
+				}
+			}
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
 			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
@@ -1429,8 +1471,25 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
 			goto nla_put_failure;
 		break;
 	case AF_INET6:
-		if (nla_put_in6_addr(skb, RTA_GATEWAY, &nhc->nhc_gw.ipv6) < 0)
+		/* if gateway family does not match nexthop family
+		 * gateway is encoded as RTA_VIA
+		 */
+		if (nhc->nhc_gw_family != nhc->nhc_family) {
+			int alen = sizeof(struct in6_addr);
+			struct nlattr *nla;
+			struct rtvia *via;
+
+			nla = nla_reserve(skb, RTA_VIA, alen + 2);
+			if (!nla)
+				goto nla_put_failure;
+
+			via = nla_data(nla);
+			via->rtvia_family = AF_INET6;
+			memcpy(via->rtvia_addr, &nhc->nhc_gw.ipv6, alen);
+		} else if (nla_put_in6_addr(skb, RTA_GATEWAY,
+					    &nhc->nhc_gw.ipv6) < 0) {
 			goto nla_put_failure;
+		}
 		break;
 	}
 
-- 
cgit v1.2.3


From d8eca5bbb2be9bc7546f9e733786fa2f1a594c67 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 9 Apr 2019 23:20:03 +0200
Subject: bpf: implement lookup-free direct value access for maps

This generic extension to BPF maps allows for directly loading
an address residing inside a BPF map value as a single BPF
ldimm64 instruction!

The idea is similar to what BPF_PSEUDO_MAP_FD does today, which
is a special src_reg flag for ldimm64 instruction that indicates
that inside the first part of the double insns's imm field is a
file descriptor which the verifier then replaces as a full 64bit
address of the map into both imm parts. For the newly added
BPF_PSEUDO_MAP_VALUE src_reg flag, the idea is the following:
the first part of the double insns's imm field is again a file
descriptor corresponding to the map, and the second part of the
imm field is an offset into the value. The verifier will then
replace both imm parts with an address that points into the BPF
map value at the given value offset for maps that support this
operation. Currently supported is array map with single entry.
It is possible to support more than just single map element by
reusing both 16bit off fields of the insns as a map index, so
full array map lookup could be expressed that way. It hasn't
been implemented here due to lack of concrete use case, but
could easily be done so in future in a compatible way, since
both off fields right now have to be 0 and would correctly
denote a map index 0.

The BPF_PSEUDO_MAP_VALUE is a distinct flag as otherwise with
BPF_PSEUDO_MAP_FD we could not differ offset 0 between load of
map pointer versus load of map's value at offset 0, and changing
BPF_PSEUDO_MAP_FD's encoding into off by one to differ between
regular map pointer and map value pointer would add unnecessary
complexity and increases barrier for debugability thus less
suitable. Using the second part of the imm field as an offset
into the value does /not/ come with limitations since maximum
possible value size is in u32 universe anyway.

This optimization allows for efficiently retrieving an address
to a map value memory area without having to issue a helper call
which needs to prepare registers according to calling convention,
etc, without needing the extra NULL test, and without having to
add the offset in an additional instruction to the value base
pointer. The verifier then treats the destination register as
PTR_TO_MAP_VALUE with constant reg->off from the user passed
offset from the second imm field, and guarantees that this is
within bounds of the map value. Any subsequent operations are
normally treated as typical map value handling without anything
extra needed from verification side.

The two map operations for direct value access have been added to
array map for now. In future other types could be supported as
well depending on the use case. The main use case for this commit
is to allow for BPF loader support for global variables that
reside in .data/.rodata/.bss sections such that we can directly
load the address of them with minimal additional infrastructure
required. Loader support has been added in subsequent commits for
libbpf library.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h               |  6 +++
 include/linux/bpf_verifier.h      |  4 ++
 include/uapi/linux/bpf.h          | 13 +++++-
 kernel/bpf/arraymap.c             | 32 +++++++++++++++
 kernel/bpf/core.c                 |  3 +-
 kernel/bpf/disasm.c               |  5 ++-
 kernel/bpf/syscall.c              | 28 +++++++++----
 kernel/bpf/verifier.c             | 86 ++++++++++++++++++++++++++++++---------
 tools/bpf/bpftool/xlated_dumper.c |  3 ++
 9 files changed, 149 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a445194b5fb6..bd93a592dd29 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -57,6 +57,12 @@ struct bpf_map_ops {
 			     const struct btf *btf,
 			     const struct btf_type *key_type,
 			     const struct btf_type *value_type);
+
+	/* Direct value access helpers. */
+	int (*map_direct_value_addr)(const struct bpf_map *map,
+				     u64 *imm, u32 off);
+	int (*map_direct_value_meta)(const struct bpf_map *map,
+				     u64 imm, u32 *off);
 };
 
 struct bpf_map {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index fc8254d6b569..b3ab61fe1932 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -224,6 +224,10 @@ struct bpf_insn_aux_data {
 		unsigned long map_state;	/* pointer/poison value for maps */
 		s32 call_imm;			/* saved imm field of call insn */
 		u32 alu_limit;			/* limit for add/sub register with pointer */
+		struct {
+			u32 map_index;		/* index into used_maps[] */
+			u32 map_off;		/* offset from value base address */
+		};
 	};
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
 	int sanitize_stack_off; /* stack slot to be cleared */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 837024512baf..26cfb5b2c964 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -255,8 +255,19 @@ enum bpf_attach_type {
  */
 #define BPF_F_ANY_ALIGNMENT	(1U << 1)
 
-/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
+/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
+ * two extensions:
+ *
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm:      map fd              map fd
+ * insn[1].imm:      0                   offset into value
+ * insn[0].off:      0                   0
+ * insn[1].off:      0                   0
+ * ldimm64 rewrite:  address of map      address of map[0]+offset
+ * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
+ */
 #define BPF_PSEUDO_MAP_FD	1
+#define BPF_PSEUDO_MAP_VALUE	2
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index c72e0d8e1e65..1a6e9861d554 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -160,6 +160,36 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
 	return array->value + array->elem_size * (index & array->index_mask);
 }
 
+static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm,
+				       u32 off)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+
+	if (map->max_entries != 1)
+		return -ENOTSUPP;
+	if (off >= map->value_size)
+		return -EINVAL;
+
+	*imm = (unsigned long)array->value;
+	return 0;
+}
+
+static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm,
+				       u32 *off)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u64 base = (unsigned long)array->value;
+	u64 range = array->elem_size;
+
+	if (map->max_entries != 1)
+		return -ENOTSUPP;
+	if (imm < base || imm >= base + range)
+		return -ENOENT;
+
+	*off = imm - base;
+	return 0;
+}
+
 /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
 static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
@@ -419,6 +449,8 @@ const struct bpf_map_ops array_map_ops = {
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
 	.map_gen_lookup = array_map_gen_lookup,
+	.map_direct_value_addr = array_map_direct_value_addr,
+	.map_direct_value_meta = array_map_direct_value_meta,
 	.map_seq_show_elem = array_map_seq_show_elem,
 	.map_check_btf = array_map_check_btf,
 };
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2966cb368bf4..ace8c22c8b0e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -292,7 +292,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 		dst[i] = fp->insnsi[i];
 		if (!was_ld_map &&
 		    dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
-		    dst[i].src_reg == BPF_PSEUDO_MAP_FD) {
+		    (dst[i].src_reg == BPF_PSEUDO_MAP_FD ||
+		     dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) {
 			was_ld_map = true;
 			dst[i].imm = 0;
 		} else if (was_ld_map &&
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index de73f55e42fd..d9ce383c0f9c 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -205,10 +205,11 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 			 * part of the ldimm64 insn is accessible.
 			 */
 			u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
-			bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+			bool is_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD ||
+				      insn->src_reg == BPF_PSEUDO_MAP_VALUE;
 			char tmp[64];
 
-			if (map_ptr && !allow_ptr_leaks)
+			if (is_ptr && !allow_ptr_leaks)
 				imm = 0;
 
 			verbose(cbs->private_data, "(%02x) r%d = %s\n",
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1d65e56594db..828518bb947b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2072,13 +2072,26 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
 }
 
 static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
-					      unsigned long addr)
+					      unsigned long addr, u32 *off,
+					      u32 *type)
 {
+	const struct bpf_map *map;
 	int i;
 
-	for (i = 0; i < prog->aux->used_map_cnt; i++)
-		if (prog->aux->used_maps[i] == (void *)addr)
-			return prog->aux->used_maps[i];
+	for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) {
+		map = prog->aux->used_maps[i];
+		if (map == (void *)addr) {
+			*type = BPF_PSEUDO_MAP_FD;
+			return map;
+		}
+		if (!map->ops->map_direct_value_meta)
+			continue;
+		if (!map->ops->map_direct_value_meta(map, addr, off)) {
+			*type = BPF_PSEUDO_MAP_VALUE;
+			return map;
+		}
+	}
+
 	return NULL;
 }
 
@@ -2086,6 +2099,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
 {
 	const struct bpf_map *map;
 	struct bpf_insn *insns;
+	u32 off, type;
 	u64 imm;
 	int i;
 
@@ -2113,11 +2127,11 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
 			continue;
 
 		imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm;
-		map = bpf_map_from_imm(prog, imm);
+		map = bpf_map_from_imm(prog, imm, &off, &type);
 		if (map) {
-			insns[i].src_reg = BPF_PSEUDO_MAP_FD;
+			insns[i].src_reg = type;
 			insns[i].imm = map->id;
-			insns[i + 1].imm = 0;
+			insns[i + 1].imm = off;
 			continue;
 		}
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 48718e1da16d..6ab7a23fc924 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5056,18 +5056,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	return 0;
 }
 
-/* return the map pointer stored inside BPF_LD_IMM64 instruction */
-static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
-{
-	u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;
-
-	return (struct bpf_map *) (unsigned long) imm64;
-}
-
 /* verify BPF_LD_IMM64 instruction */
 static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 {
+	struct bpf_insn_aux_data *aux = cur_aux(env);
 	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_map *map;
 	int err;
 
 	if (BPF_SIZE(insn->code) != BPF_DW) {
@@ -5091,11 +5085,22 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return 0;
 	}
 
-	/* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
-	BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);
+	map = env->used_maps[aux->map_index];
+	mark_reg_known_zero(env, regs, insn->dst_reg);
+	regs[insn->dst_reg].map_ptr = map;
+
+	if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
+		regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
+		regs[insn->dst_reg].off = aux->map_off;
+		if (map_value_has_spin_lock(map))
+			regs[insn->dst_reg].id = ++env->id_gen;
+	} else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+		regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
+	} else {
+		verbose(env, "bpf verifier is misconfigured\n");
+		return -EINVAL;
+	}
 
-	regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
-	regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
 	return 0;
 }
 
@@ -6803,8 +6808,10 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 		}
 
 		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
+			struct bpf_insn_aux_data *aux;
 			struct bpf_map *map;
 			struct fd f;
+			u64 addr;
 
 			if (i == insn_cnt - 1 || insn[1].code != 0 ||
 			    insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
@@ -6813,13 +6820,19 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 				return -EINVAL;
 			}
 
-			if (insn->src_reg == 0)
+			if (insn[0].src_reg == 0)
 				/* valid generic load 64-bit imm */
 				goto next_insn;
 
-			if (insn[0].src_reg != BPF_PSEUDO_MAP_FD ||
-			    insn[1].imm != 0) {
-				verbose(env, "unrecognized bpf_ld_imm64 insn\n");
+			/* In final convert_pseudo_ld_imm64() step, this is
+			 * converted into regular 64-bit imm load insn.
+			 */
+			if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD &&
+			     insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) ||
+			    (insn[0].src_reg == BPF_PSEUDO_MAP_FD &&
+			     insn[1].imm != 0)) {
+				verbose(env,
+					"unrecognized bpf_ld_imm64 insn\n");
 				return -EINVAL;
 			}
 
@@ -6837,16 +6850,47 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 				return err;
 			}
 
-			/* store map pointer inside BPF_LD_IMM64 instruction */
-			insn[0].imm = (u32) (unsigned long) map;
-			insn[1].imm = ((u64) (unsigned long) map) >> 32;
+			aux = &env->insn_aux_data[i];
+			if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+				addr = (unsigned long)map;
+			} else {
+				u32 off = insn[1].imm;
+
+				if (off >= BPF_MAX_VAR_OFF) {
+					verbose(env, "direct value offset of %u is not allowed\n", off);
+					fdput(f);
+					return -EINVAL;
+				}
+
+				if (!map->ops->map_direct_value_addr) {
+					verbose(env, "no direct value access support for this map type\n");
+					fdput(f);
+					return -EINVAL;
+				}
+
+				err = map->ops->map_direct_value_addr(map, &addr, off);
+				if (err) {
+					verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n",
+						map->value_size, off);
+					fdput(f);
+					return err;
+				}
+
+				aux->map_off = off;
+				addr += off;
+			}
+
+			insn[0].imm = (u32)addr;
+			insn[1].imm = addr >> 32;
 
 			/* check whether we recorded this map already */
-			for (j = 0; j < env->used_map_cnt; j++)
+			for (j = 0; j < env->used_map_cnt; j++) {
 				if (env->used_maps[j] == map) {
+					aux->map_index = j;
 					fdput(f);
 					goto next_insn;
 				}
+			}
 
 			if (env->used_map_cnt >= MAX_USED_MAPS) {
 				fdput(f);
@@ -6863,6 +6907,8 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 				fdput(f);
 				return PTR_ERR(map);
 			}
+
+			aux->map_index = env->used_map_cnt;
 			env->used_maps[env->used_map_cnt++] = map;
 
 			if (bpf_map_is_cgroup_storage(map) &&
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 7073dbe1ff27..0bb17bf88b18 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -195,6 +195,9 @@ static const char *print_imm(void *private_data,
 	if (insn->src_reg == BPF_PSEUDO_MAP_FD)
 		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
 			 "map[id:%u]", insn->imm);
+	else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE)
+		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
+			 "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm);
 	else
 		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
 			 "0x%llx", (unsigned long long)full_imm);
-- 
cgit v1.2.3


From 591fe9888d7809d9ee5c828020b6c6ae27c37229 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 9 Apr 2019 23:20:05 +0200
Subject: bpf: add program side {rd, wr}only support for maps

This work adds two new map creation flags BPF_F_RDONLY_PROG
and BPF_F_WRONLY_PROG in order to allow for read-only or
write-only BPF maps from a BPF program side.

Today we have BPF_F_RDONLY and BPF_F_WRONLY, but this only
applies to system call side, meaning the BPF program has full
read/write access to the map as usual while bpf(2) calls with
map fd can either only read or write into the map depending
on the flags. BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG allows
for the exact opposite such that verifier is going to reject
program loads if write into a read-only map or a read into a
write-only map is detected. For read-only map case also some
helpers are forbidden for programs that would alter the map
state such as map deletion, update, etc. As opposed to the two
BPF_F_RDONLY / BPF_F_WRONLY flags, BPF_F_RDONLY_PROG as well
as BPF_F_WRONLY_PROG really do correspond to the map lifetime.

We've enabled this generic map extension to various non-special
maps holding normal user data: array, hash, lru, lpm, local
storage, queue and stack. Further generic map types could be
followed up in future depending on use-case. Main use case
here is to forbid writes into .rodata map values from verifier
side.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h           | 29 +++++++++++++++++++++++++++
 include/uapi/linux/bpf.h      |  6 +++++-
 kernel/bpf/arraymap.c         |  6 +++++-
 kernel/bpf/hashtab.c          |  6 +++---
 kernel/bpf/local_storage.c    |  6 +++---
 kernel/bpf/lpm_trie.c         |  3 ++-
 kernel/bpf/queue_stack_maps.c |  6 +++---
 kernel/bpf/syscall.c          |  2 ++
 kernel/bpf/verifier.c         | 46 +++++++++++++++++++++++++++++++++++++++++--
 9 files changed, 96 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bd93a592dd29..be20804631b5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -430,6 +430,35 @@ struct bpf_array {
 #define BPF_COMPLEXITY_LIMIT_INSNS      1000000 /* yes. 1M insns */
 #define MAX_TAIL_CALL_CNT 32
 
+#define BPF_F_ACCESS_MASK	(BPF_F_RDONLY |		\
+				 BPF_F_RDONLY_PROG |	\
+				 BPF_F_WRONLY |		\
+				 BPF_F_WRONLY_PROG)
+
+#define BPF_MAP_CAN_READ	BIT(0)
+#define BPF_MAP_CAN_WRITE	BIT(1)
+
+static inline u32 bpf_map_flags_to_cap(struct bpf_map *map)
+{
+	u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
+
+	/* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is
+	 * not possible.
+	 */
+	if (access_flags & BPF_F_RDONLY_PROG)
+		return BPF_MAP_CAN_READ;
+	else if (access_flags & BPF_F_WRONLY_PROG)
+		return BPF_MAP_CAN_WRITE;
+	else
+		return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE;
+}
+
+static inline bool bpf_map_flags_access_ok(u32 access_flags)
+{
+	return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) !=
+	       (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
+}
+
 struct bpf_event_entry {
 	struct perf_event *event;
 	struct file *perf_file;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 26cfb5b2c964..d275446d807c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -294,7 +294,7 @@ enum bpf_attach_type {
 
 #define BPF_OBJ_NAME_LEN 16U
 
-/* Flags for accessing BPF object */
+/* Flags for accessing BPF object from syscall side. */
 #define BPF_F_RDONLY		(1U << 3)
 #define BPF_F_WRONLY		(1U << 4)
 
@@ -304,6 +304,10 @@ enum bpf_attach_type {
 /* Zero-initialize hash function seed. This should only be used for testing. */
 #define BPF_F_ZERO_SEED		(1U << 6)
 
+/* Flags for accessing BPF object from program side. */
+#define BPF_F_RDONLY_PROG	(1U << 7)
+#define BPF_F_WRONLY_PROG	(1U << 8)
+
 /* flags for BPF_PROG_QUERY */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 1a6e9861d554..217b10bd9f48 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -22,7 +22,7 @@
 #include "map_in_map.h"
 
 #define ARRAY_CREATE_FLAG_MASK \
-	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
 
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
@@ -63,6 +63,7 @@ int array_map_alloc_check(union bpf_attr *attr)
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size == 0 ||
 	    attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags) ||
 	    (percpu && numa_node != NUMA_NO_NODE))
 		return -EINVAL;
 
@@ -472,6 +473,9 @@ static int fd_array_map_alloc_check(union bpf_attr *attr)
 	/* only file descriptors can be stored in this type of map */
 	if (attr->value_size != sizeof(u32))
 		return -EINVAL;
+	/* Program read-only/write-only not supported for special maps yet. */
+	if (attr->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG))
+		return -EINVAL;
 	return array_map_alloc_check(attr);
 }
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fed15cf94dca..192d32e77db3 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -23,7 +23,7 @@
 
 #define HTAB_CREATE_FLAG_MASK						\
 	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE |	\
-	 BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED)
+	 BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED)
 
 struct bucket {
 	struct hlist_nulls_head head;
@@ -262,8 +262,8 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 		/* Guard against local DoS, and discourage production use. */
 		return -EPERM;
 
-	if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
-		/* reserved bits should not be used */
+	if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags))
 		return -EINVAL;
 
 	if (!lru && percpu_lru)
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 6b572e2de7fb..980e8f1f6cb5 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -14,7 +14,7 @@ DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STO
 #ifdef CONFIG_CGROUP_BPF
 
 #define LOCAL_STORAGE_CREATE_FLAG_MASK					\
-	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
 
 struct bpf_cgroup_storage_map {
 	struct bpf_map map;
@@ -282,8 +282,8 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 	if (attr->value_size > PAGE_SIZE)
 		return ERR_PTR(-E2BIG);
 
-	if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK)
-		/* reserved bits should not be used */
+	if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags))
 		return ERR_PTR(-EINVAL);
 
 	if (attr->max_entries)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 93a5cbbde421..e61630c2e50b 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -538,7 +538,7 @@ out:
 #define LPM_KEY_SIZE_MIN	LPM_KEY_SIZE(LPM_DATA_SIZE_MIN)
 
 #define LPM_CREATE_FLAG_MASK	(BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE |	\
-				 BPF_F_RDONLY | BPF_F_WRONLY)
+				 BPF_F_ACCESS_MASK)
 
 static struct bpf_map *trie_alloc(union bpf_attr *attr)
 {
@@ -553,6 +553,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 	if (attr->max_entries == 0 ||
 	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
 	    attr->map_flags & ~LPM_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags) ||
 	    attr->key_size < LPM_KEY_SIZE_MIN ||
 	    attr->key_size > LPM_KEY_SIZE_MAX ||
 	    attr->value_size < LPM_VAL_SIZE_MIN ||
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index b384ea9f3254..0b140d236889 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -11,8 +11,7 @@
 #include "percpu_freelist.h"
 
 #define QUEUE_STACK_CREATE_FLAG_MASK \
-	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
-
+	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
 
 struct bpf_queue_stack {
 	struct bpf_map map;
@@ -52,7 +51,8 @@ static int queue_stack_map_alloc_check(union bpf_attr *attr)
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 0 ||
 	    attr->value_size == 0 ||
-	    attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
+	    attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags))
 		return -EINVAL;
 
 	if (attr->value_size > KMALLOC_MAX_SIZE)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 56b4b0e08b3b..0c9276b54c88 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -501,6 +501,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	map->spin_lock_off = btf_find_spin_lock(btf, value_type);
 
 	if (map_value_has_spin_lock(map)) {
+		if (map->map_flags & BPF_F_RDONLY_PROG)
+			return -EACCES;
 		if (map->map_type != BPF_MAP_TYPE_HASH &&
 		    map->map_type != BPF_MAP_TYPE_ARRAY &&
 		    map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6ab7a23fc924..b747434df89c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1439,6 +1439,28 @@ static int check_stack_access(struct bpf_verifier_env *env,
 	return 0;
 }
 
+static int check_map_access_type(struct bpf_verifier_env *env, u32 regno,
+				 int off, int size, enum bpf_access_type type)
+{
+	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_map *map = regs[regno].map_ptr;
+	u32 cap = bpf_map_flags_to_cap(map);
+
+	if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) {
+		verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n",
+			map->value_size, off, size);
+		return -EACCES;
+	}
+
+	if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) {
+		verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n",
+			map->value_size, off, size);
+		return -EACCES;
+	}
+
+	return 0;
+}
+
 /* check read/write into map element returned by bpf_map_lookup_elem() */
 static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
 			      int size, bool zero_size_allowed)
@@ -2024,7 +2046,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			verbose(env, "R%d leaks addr into map\n", value_regno);
 			return -EACCES;
 		}
-
+		err = check_map_access_type(env, regno, off, size, t);
+		if (err)
+			return err;
 		err = check_map_access(env, regno, off, size, false);
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
@@ -2327,6 +2351,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 		return check_packet_access(env, regno, reg->off, access_size,
 					   zero_size_allowed);
 	case PTR_TO_MAP_VALUE:
+		if (check_map_access_type(env, regno, reg->off, access_size,
+					  meta && meta->raw_mode ? BPF_WRITE :
+					  BPF_READ))
+			return -EACCES;
 		return check_map_access(env, regno, reg->off, access_size,
 					zero_size_allowed);
 	default: /* scalar_value|ptr_to_stack or invalid ptr */
@@ -3059,6 +3087,7 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 		int func_id, int insn_idx)
 {
 	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
+	struct bpf_map *map = meta->map_ptr;
 
 	if (func_id != BPF_FUNC_tail_call &&
 	    func_id != BPF_FUNC_map_lookup_elem &&
@@ -3069,11 +3098,24 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	    func_id != BPF_FUNC_map_peek_elem)
 		return 0;
 
-	if (meta->map_ptr == NULL) {
+	if (map == NULL) {
 		verbose(env, "kernel subsystem misconfigured verifier\n");
 		return -EINVAL;
 	}
 
+	/* In case of read-only, some additional restrictions
+	 * need to be applied in order to prevent altering the
+	 * state of the map from program side.
+	 */
+	if ((map->map_flags & BPF_F_RDONLY_PROG) &&
+	    (func_id == BPF_FUNC_map_delete_elem ||
+	     func_id == BPF_FUNC_map_update_elem ||
+	     func_id == BPF_FUNC_map_push_elem ||
+	     func_id == BPF_FUNC_map_pop_elem)) {
+		verbose(env, "write into map forbidden\n");
+		return -EACCES;
+	}
+
 	if (!BPF_MAP_PTR(aux->map_state))
 		bpf_map_ptr_store(aux, meta->map_ptr,
 				  meta->map_ptr->unpriv_array);
-- 
cgit v1.2.3


From 87df15de441bd4add7876ef584da8cabdd9a042a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 9 Apr 2019 23:20:06 +0200
Subject: bpf: add syscall side map freeze support

This patch adds a new BPF_MAP_FREEZE command which allows to
"freeze" the map globally as read-only / immutable from syscall
side.

Map permission handling has been refactored into map_get_sys_perms()
and drops FMODE_CAN_WRITE in case of locked map. Main use case is
to allow for setting up .rodata sections from the BPF ELF which
are loaded into the kernel, meaning BPF loader first allocates
map, sets up map value by copying .rodata section into it and once
complete, it calls BPF_MAP_FREEZE on the map fd to prevent further
modifications.

Right now BPF_MAP_FREEZE only takes map fd as argument while remaining
bpf_attr members are required to be zero. I didn't add write-only
locking here as counterpart since I don't have a concrete use-case
for it on my side, and I think it makes probably more sense to wait
once there is actually one. In that case bpf_attr can be extended
as usual with a flag field and/or others where flag 0 means that
we lock the map read-only hence this doesn't prevent to add further
extensions to BPF_MAP_FREEZE upon need.

A map creation flag like BPF_F_WRONCE was not considered for couple
of reasons: i) in case of a generic implementation, a map can consist
of more than just one element, thus there could be multiple map
updates needed to set the map into a state where it can then be
made immutable, ii) WRONCE indicates exact one-time write before
it is then set immutable. A generic implementation would set a bit
atomically on map update entry (if unset), indicating that every
subsequent update from then onwards will need to bail out there.
However, map updates can fail, so upon failure that flag would need
to be unset again and the update attempt would need to be repeated
for it to be eventually made immutable. While this can be made
race-free, this approach feels less clean and in combination with
reason i), it's not generic enough. A dedicated BPF_MAP_FREEZE
command directly sets the flag and caller has the guarantee that
map is immutable from syscall side upon successful return for any
future syscall invocations that would alter the map state, which
is also more intuitive from an API point of view. A command name
such as BPF_MAP_LOCK has been avoided as it's too close with BPF
map spin locks (which already has BPF_F_LOCK flag). BPF_MAP_FREEZE
is so far only enabled for privileged users.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h      |  3 ++-
 include/uapi/linux/bpf.h |  1 +
 kernel/bpf/syscall.c     | 66 +++++++++++++++++++++++++++++++++++++++---------
 3 files changed, 57 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index be20804631b5..65f7094c40b4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -87,7 +87,8 @@ struct bpf_map {
 	struct btf *btf;
 	u32 pages;
 	bool unpriv_array;
-	/* 51 bytes hole */
+	bool frozen; /* write-once */
+	/* 48 bytes hole */
 
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d275446d807c..af1cbd951f26 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -105,6 +105,7 @@ enum bpf_cmd {
 	BPF_BTF_GET_FD_BY_ID,
 	BPF_TASK_FD_QUERY,
 	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
+	BPF_MAP_FREEZE,
 };
 
 enum bpf_map_type {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0c9276b54c88..b3ce516e5a20 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -355,6 +355,18 @@ static int bpf_map_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f)
+{
+	fmode_t mode = f.file->f_mode;
+
+	/* Our file permissions may have been overridden by global
+	 * map permissions facing syscall side.
+	 */
+	if (READ_ONCE(map->frozen))
+		mode &= ~FMODE_CAN_WRITE;
+	return mode;
+}
+
 #ifdef CONFIG_PROC_FS
 static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 {
@@ -376,14 +388,16 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   "max_entries:\t%u\n"
 		   "map_flags:\t%#x\n"
 		   "memlock:\t%llu\n"
-		   "map_id:\t%u\n",
+		   "map_id:\t%u\n"
+		   "frozen:\t%u\n",
 		   map->map_type,
 		   map->key_size,
 		   map->value_size,
 		   map->max_entries,
 		   map->map_flags,
 		   map->pages * 1ULL << PAGE_SHIFT,
-		   map->id);
+		   map->id,
+		   READ_ONCE(map->frozen));
 
 	if (owner_prog_type) {
 		seq_printf(m, "owner_prog_type:\t%u\n",
@@ -727,8 +741,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if (!(f.file->f_mode & FMODE_CAN_READ)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -857,8 +870,7 @@ static int map_update_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -969,8 +981,7 @@ static int map_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1021,8 +1032,7 @@ static int map_get_next_key(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if (!(f.file->f_mode & FMODE_CAN_READ)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1089,8 +1099,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1132,6 +1141,36 @@ err_put:
 	return err;
 }
 
+#define BPF_MAP_FREEZE_LAST_FIELD map_fd
+
+static int map_freeze(const union bpf_attr *attr)
+{
+	int err = 0, ufd = attr->map_fd;
+	struct bpf_map *map;
+	struct fd f;
+
+	if (CHECK_ATTR(BPF_MAP_FREEZE))
+		return -EINVAL;
+
+	f = fdget(ufd);
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+	if (READ_ONCE(map->frozen)) {
+		err = -EBUSY;
+		goto err_put;
+	}
+	if (!capable(CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
+	WRITE_ONCE(map->frozen, true);
+err_put:
+	fdput(f);
+	return err;
+}
+
 static const struct bpf_prog_ops * const bpf_prog_types[] = {
 #define BPF_PROG_TYPE(_id, _name) \
 	[_id] = & _name ## _prog_ops,
@@ -2735,6 +2774,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_MAP_GET_NEXT_KEY:
 		err = map_get_next_key(&attr);
 		break;
+	case BPF_MAP_FREEZE:
+		err = map_freeze(&attr);
+		break;
 	case BPF_PROG_LOAD:
 		err = bpf_prog_load(&attr, uattr);
 		break;
-- 
cgit v1.2.3


From f063c889c9458354a92b235a51cbb60d30321070 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 9 Apr 2019 23:20:08 +0200
Subject: bpf: add specification for BTF Var and DataSec kinds

This adds the BTF specification and UAPI bits for supporting BTF Var
and DataSec kinds. This is following LLVM upstream commit ac4082b77e07
("[BPF] Add BTF Var and DataSec Support") which has been merged recently.
Var itself is for describing a global variable and DataSec to describe
ELF sections e.g. data/bss/rodata sections that hold one or multiple
global variables.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/bpf/btf.rst | 57 +++++++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/btf.h  | 32 ++++++++++++++++++++++----
 2 files changed, 85 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst
index 9a60a5d60e38..60d87d7363ec 100644
--- a/Documentation/bpf/btf.rst
+++ b/Documentation/bpf/btf.rst
@@ -82,6 +82,8 @@ sequentially and type id is assigned to each recognized type starting from id
     #define BTF_KIND_RESTRICT       11      /* Restrict     */
     #define BTF_KIND_FUNC           12      /* Function     */
     #define BTF_KIND_FUNC_PROTO     13      /* Function Proto       */
+    #define BTF_KIND_VAR            14      /* Variable     */
+    #define BTF_KIND_DATASEC        15      /* Section      */
 
 Note that the type section encodes debug info, not just pure types.
 ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram.
@@ -393,6 +395,61 @@ refers to parameter type.
 If the function has variable arguments, the last parameter is encoded with
 ``name_off = 0`` and ``type = 0``.
 
+2.2.14 BTF_KIND_VAR
+~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+  * ``name_off``: offset to a valid C identifier
+  * ``info.kind_flag``: 0
+  * ``info.kind``: BTF_KIND_VAR
+  * ``info.vlen``: 0
+  * ``type``: the type of the variable
+
+``btf_type`` is followed by a single ``struct btf_variable`` with the
+following data::
+
+    struct btf_var {
+        __u32   linkage;
+    };
+
+``struct btf_var`` encoding:
+  * ``linkage``: currently only static variable 0, or globally allocated
+                 variable in ELF sections 1
+
+Not all type of global variables are supported by LLVM at this point.
+The following is currently available:
+
+  * static variables with or without section attributes
+  * global variables with section attributes
+
+The latter is for future extraction of map key/value type id's from a
+map definition.
+
+2.2.15 BTF_KIND_DATASEC
+~~~~~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+  * ``name_off``: offset to a valid name associated with a variable or
+                  one of .data/.bss/.rodata
+  * ``info.kind_flag``: 0
+  * ``info.kind``: BTF_KIND_DATASEC
+  * ``info.vlen``: # of variables
+  * ``size``: total section size in bytes (0 at compilation time, patched
+              to actual size by BPF loaders such as libbpf)
+
+``btf_type`` is followed by ``info.vlen`` number of ``struct btf_var_secinfo``.::
+
+    struct btf_var_secinfo {
+        __u32   type;
+        __u32   offset;
+        __u32   size;
+    };
+
+``struct btf_var_secinfo`` encoding:
+  * ``type``: the type of the BTF_KIND_VAR variable
+  * ``offset``: the in-section offset of the variable
+  * ``size``: the size of the variable in bytes
+
 3. BTF Kernel API
 *****************
 
diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index 7b7475ef2f17..9310652ca4f9 100644
--- a/include/uapi/linux/btf.h
+++ b/include/uapi/linux/btf.h
@@ -39,11 +39,11 @@ struct btf_type {
 	 *             struct, union and fwd
 	 */
 	__u32 info;
-	/* "size" is used by INT, ENUM, STRUCT and UNION.
+	/* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC and FUNC_PROTO.
+	 * FUNC, FUNC_PROTO and VAR.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -70,8 +70,10 @@ struct btf_type {
 #define BTF_KIND_RESTRICT	11	/* Restrict	*/
 #define BTF_KIND_FUNC		12	/* Function	*/
 #define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
-#define BTF_KIND_MAX		13
-#define NR_BTF_KINDS		14
+#define BTF_KIND_VAR		14	/* Variable	*/
+#define BTF_KIND_DATASEC	15	/* Section	*/
+#define BTF_KIND_MAX		BTF_KIND_DATASEC
+#define NR_BTF_KINDS		(BTF_KIND_MAX + 1)
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -138,4 +140,26 @@ struct btf_param {
 	__u32	type;
 };
 
+enum {
+	BTF_VAR_STATIC = 0,
+	BTF_VAR_GLOBAL_ALLOCATED,
+};
+
+/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
+ * additional information related to the variable such as its linkage.
+ */
+struct btf_var {
+	__u32	linkage;
+};
+
+/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo"
+ * to describe all BTF_KIND_VAR types it contains along with it's
+ * in-section offset as well as size.
+ */
+struct btf_var_secinfo {
+	__u32	type;
+	__u32	offset;
+	__u32	size;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */
-- 
cgit v1.2.3


From 2824ecb7010f6a20e9a4140512b798469ab066cc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 9 Apr 2019 23:20:10 +0200
Subject: bpf: allow for key-less BTF in array map

Given we'll be reusing BPF array maps for global data/bss/rodata
sections, we need a way to associate BTF DataSec type as its map
value type. In usual cases we have this ugly BPF_ANNOTATE_KV_PAIR()
macro hack e.g. via 38d5d3b3d5db ("bpf: Introduce BPF_ANNOTATE_KV_PAIR")
to get initial map to type association going. While more use cases
for it are discouraged, this also won't work for global data since
the use of array map is a BPF loader detail and therefore unknown
at compilation time. For array maps with just a single entry we make
an exception in terms of BTF in that key type is declared optional
if value type is of DataSec type. The latter LLVM is guaranteed to
emit and it also aligns with how we regard global data maps as just
a plain buffer area reusing existing map facilities for allowing
things like introspection with existing tools.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf.h   |  1 +
 kernel/bpf/arraymap.c | 15 ++++++++++++++-
 kernel/bpf/btf.c      |  2 +-
 kernel/bpf/syscall.c  | 15 +++++++++++----
 4 files changed, 27 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 455d31b55828..64cdf2a23d42 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -51,6 +51,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
 int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
+bool btf_type_is_void(const struct btf_type *t);
 
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 217b10bd9f48..584636c9e2eb 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -391,7 +391,8 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key,
 		return;
 	}
 
-	seq_printf(m, "%u: ", *(u32 *)key);
+	if (map->btf_key_type_id)
+		seq_printf(m, "%u: ", *(u32 *)key);
 	btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
 	seq_puts(m, "\n");
 
@@ -428,6 +429,18 @@ static int array_map_check_btf(const struct bpf_map *map,
 {
 	u32 int_data;
 
+	/* One exception for keyless BTF: .bss/.data/.rodata map */
+	if (btf_type_is_void(key_type)) {
+		if (map->map_type != BPF_MAP_TYPE_ARRAY ||
+		    map->max_entries != 1)
+			return -EINVAL;
+
+		if (BTF_INFO_KIND(value_type->info) != BTF_KIND_DATASEC)
+			return -EINVAL;
+
+		return 0;
+	}
+
 	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
 		return -EINVAL;
 
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 0cecf6bab61b..cad09858a5f2 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -326,7 +326,7 @@ static bool btf_type_is_modifier(const struct btf_type *t)
 	return false;
 }
 
-static bool btf_type_is_void(const struct btf_type *t)
+bool btf_type_is_void(const struct btf_type *t)
 {
 	return t == &btf_void;
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 198c9680bf0d..438199e2eca4 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -504,9 +504,16 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	u32 key_size, value_size;
 	int ret = 0;
 
-	key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
-	if (!key_type || key_size != map->key_size)
-		return -EINVAL;
+	/* Some maps allow key to be unspecified. */
+	if (btf_key_id) {
+		key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+		if (!key_type || key_size != map->key_size)
+			return -EINVAL;
+	} else {
+		key_type = btf_type_by_id(btf, 0);
+		if (!map->ops->map_check_btf)
+			return -EINVAL;
+	}
 
 	value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
 	if (!value_type || value_size != map->value_size)
@@ -573,7 +580,7 @@ static int map_create(union bpf_attr *attr)
 	if (attr->btf_key_type_id || attr->btf_value_type_id) {
 		struct btf *btf;
 
-		if (!attr->btf_key_type_id || !attr->btf_value_type_id) {
+		if (!attr->btf_value_type_id) {
 			err = -EINVAL;
 			goto free_map_nouncharge;
 		}
-- 
cgit v1.2.3


From b6d9ccb1125049941590ea895c38e1167badba5f Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Thu, 28 Mar 2019 15:27:31 +0200
Subject: net/mlx5: E-Switch, don't use hardcoded values for FDB prios

When creating the FDB prios, use the enum values already defined and not
the hardcoded values.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 5 -----
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c          | 5 +++--
 include/linux/mlx5/fs.h                                    | 5 +++++
 3 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 1496e82b5108..8a214ada2424 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -41,11 +41,6 @@
 #include "fs_core.h"
 #include "lib/devcom.h"
 
-enum {
-	FDB_FAST_PATH = 0,
-	FDB_SLOW_PATH
-};
-
 /* There are two match-all miss flows, one for unicast dst mac and
  * one for multicast.
  */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 8d199c5e7c81..8b96f71332d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2479,7 +2479,8 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 		return -ENOMEM;
 
 	levels = 2 * FDB_MAX_PRIO * (FDB_MAX_CHAIN + 1);
-	maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns, 0,
+	maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns,
+					  FDB_FAST_PATH,
 					  levels);
 	if (IS_ERR(maj_prio)) {
 		err = PTR_ERR(maj_prio);
@@ -2504,7 +2505,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 		steering->fdb_sub_ns[chain] = ns;
 	}
 
-	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, 1, 1);
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_SLOW_PATH, 1);
 	if (IS_ERR(maj_prio)) {
 		err = PTR_ERR(maj_prio);
 		goto out_err;
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 9df51da04621..3eeb04154317 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -75,6 +75,11 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_EGRESS,
 };
 
+enum {
+	FDB_FAST_PATH,
+	FDB_SLOW_PATH,
+};
+
 struct mlx5_flow_table;
 struct mlx5_flow_group;
 struct mlx5_flow_namespace;
-- 
cgit v1.2.3


From d9cb06759eca5a420072b937d2a2a670db474008 Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Thu, 28 Mar 2019 15:27:32 +0200
Subject: net/mlx5: E-Switch, add a new prio to be used by the RDMA side

Create a new prio in the FDB, it will be used when inserting steering rules
into the FDB from the RDMA side. We create a new PRIO so rules from the
net side and rules from the RDMA side won't be inserted to the same PRIO,
each side has it's own sandbox to play in.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 7 +++++++
 include/linux/mlx5/fs.h                           | 1 +
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 8b96f71332d8..72d42cc3487a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2478,6 +2478,13 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 	if (!steering->fdb_sub_ns)
 		return -ENOMEM;
 
+	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BYPASS_PATH,
+				  1);
+	if (IS_ERR(maj_prio)) {
+		err = PTR_ERR(maj_prio);
+		goto out_err;
+	}
+
 	levels = 2 * FDB_MAX_PRIO * (FDB_MAX_CHAIN + 1);
 	maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns,
 					  FDB_FAST_PATH,
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 3eeb04154317..fd91df3a4e09 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -76,6 +76,7 @@ enum mlx5_flow_namespace_type {
 };
 
 enum {
+	FDB_BYPASS_PATH,
 	FDB_FAST_PATH,
 	FDB_SLOW_PATH,
 };
-- 
cgit v1.2.3


From 1f5e6fdd6aec7929e67afad1e42e35d894a119ae Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 10 Apr 2019 14:32:38 +0200
Subject: net: sched: prefer qdisc_is_empty() over direct qlen access

When checking for root qdisc queue length, do not access directly q.qlen.
In the following patches we will move back qlen accounting to per CPU
values for NOLOCK qdiscs.

Instead, prefer the qdisc_is_empty() helper usage.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 0aea0e262452..7ecb6127e980 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -747,7 +747,7 @@ static inline bool qdisc_all_tx_empty(const struct net_device *dev)
 		struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
 		const struct Qdisc *q = rcu_dereference(txq->qdisc);
 
-		if (q->q.qlen) {
+		if (!qdisc_is_empty(q)) {
 			rcu_read_unlock();
 			return false;
 		}
-- 
cgit v1.2.3


From 9c01c9f1f2a3ddbddbf3b233cc6bfa86f5a59af0 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 10 Apr 2019 14:32:39 +0200
Subject: net: sched: always do stats accounting according to TCQ_F_CPUSTATS

The core sched implementation checks independently for NOLOCK flag
to acquire/release the root spin lock and for qdisc_is_percpu_stats()
to account per CPU values in many places.

This change update the last few places checking the TCQ_F_NOLOCK to
do per CPU stats accounting according to qdisc_is_percpu_stats()
value.

The above allows to clean dev_requeue_skb() implementation a bit
and makes stats update always consistent with a single flag.

v1 -> v2:
 - do not move qdisc_is_empty definition, fix build issue

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 23 +++++++++++++---------
 net/sched/sch_generic.c   | 50 ++++++++++++++++-------------------------------
 2 files changed, 31 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 7ecb6127e980..ed56474cfe3b 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -146,9 +146,14 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc)
 	return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
 }
 
+static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
+{
+	return q->flags & TCQ_F_CPUSTATS;
+}
+
 static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
 {
-	if (qdisc->flags & TCQ_F_NOLOCK)
+	if (qdisc_is_percpu_stats(qdisc))
 		return qdisc->empty;
 	return !qdisc->q.qlen;
 }
@@ -490,7 +495,7 @@ static inline u32 qdisc_qlen_sum(const struct Qdisc *q)
 {
 	u32 qlen = q->qstats.qlen;
 
-	if (q->flags & TCQ_F_NOLOCK)
+	if (qdisc_is_percpu_stats(q))
 		qlen += atomic_read(&q->q.atomic_qlen);
 	else
 		qlen += q->q.qlen;
@@ -817,11 +822,6 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	return sch->enqueue(skb, sch, to_free);
 }
 
-static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
-{
-	return q->flags & TCQ_F_CPUSTATS;
-}
-
 static inline void _bstats_update(struct gnet_stats_basic_packed *bstats,
 				  __u64 bytes, __u32 packets)
 {
@@ -1113,8 +1113,13 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
 
 	if (skb) {
 		skb = __skb_dequeue(&sch->gso_skb);
-		qdisc_qstats_backlog_dec(sch, skb);
-		sch->q.qlen--;
+		if (qdisc_is_percpu_stats(sch)) {
+			qdisc_qstats_cpu_backlog_dec(sch, skb);
+			qdisc_qstats_atomic_qlen_dec(sch);
+		} else {
+			qdisc_qstats_backlog_dec(sch, skb);
+			sch->q.qlen--;
+		}
 	} else {
 		skb = sch->dequeue(sch);
 	}
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 81356ef38d1d..ddff2952be87 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -118,52 +118,36 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q,
 		spin_unlock(lock);
 }
 
-static inline int __dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
+static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 {
-	while (skb) {
-		struct sk_buff *next = skb->next;
-
-		__skb_queue_tail(&q->gso_skb, skb);
-		q->qstats.requeues++;
-		qdisc_qstats_backlog_inc(q, skb);
-		q->q.qlen++;	/* it's still part of the queue */
+	spinlock_t *lock = NULL;
 
-		skb = next;
+	if (q->flags & TCQ_F_NOLOCK) {
+		lock = qdisc_lock(q);
+		spin_lock(lock);
 	}
-	__netif_schedule(q);
-
-	return 0;
-}
 
-static inline int dev_requeue_skb_locked(struct sk_buff *skb, struct Qdisc *q)
-{
-	spinlock_t *lock = qdisc_lock(q);
-
-	spin_lock(lock);
 	while (skb) {
 		struct sk_buff *next = skb->next;
 
 		__skb_queue_tail(&q->gso_skb, skb);
 
-		qdisc_qstats_cpu_requeues_inc(q);
-		qdisc_qstats_cpu_backlog_inc(q, skb);
-		qdisc_qstats_atomic_qlen_inc(q);
+		/* it's still part of the queue */
+		if (qdisc_is_percpu_stats(q)) {
+			qdisc_qstats_cpu_requeues_inc(q);
+			qdisc_qstats_cpu_backlog_inc(q, skb);
+			qdisc_qstats_atomic_qlen_inc(q);
+		} else {
+			q->qstats.requeues++;
+			qdisc_qstats_backlog_inc(q, skb);
+			q->q.qlen++;
+		}
 
 		skb = next;
 	}
-	spin_unlock(lock);
-
+	if (lock)
+		spin_unlock(lock);
 	__netif_schedule(q);
-
-	return 0;
-}
-
-static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
-{
-	if (q->flags & TCQ_F_NOLOCK)
-		return dev_requeue_skb_locked(skb, q);
-	else
-		return __dev_requeue_skb(skb, q);
 }
 
 static void try_bulk_dequeue_skb(struct Qdisc *q,
-- 
cgit v1.2.3


From 8a53e616de294873fec1a75ddb77ecb3d225cee0 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 10 Apr 2019 14:32:40 +0200
Subject: net: sched: when clearing NOLOCK, clear TCQ_F_CPUSTATS, too

Since stats updating is always consistent with TCQ_F_CPUSTATS flag,
we can disable it at qdisc creation time flipping such bit.

In my experiments, if the NOLOCK flag is cleared, per CPU stats
accounting does not give any measurable performance gain, but it
waste some memory.

Let's clear TCQ_F_CPUSTATS together with NOLOCK, when enslaving
a NOLOCK qdisc to 'lock' one.

Use stats update helper inside pfifo_fast, to cope correctly with
TCQ_F_CPUSTATS flag change.

As a side effect, q.qlen value for any child qdiscs is always
consistent for all lock classfull qdiscs.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 26 ++++++++++++++++++++++++++
 net/sched/sch_api.c       | 15 ++++++++++++++-
 net/sched/sch_generic.c   | 10 ++--------
 3 files changed, 42 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index ed56474cfe3b..f069011524ba 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1106,6 +1106,32 @@ static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch)
 	return skb;
 }
 
+static inline void qdisc_update_stats_at_dequeue(struct Qdisc *sch,
+						 struct sk_buff *skb)
+{
+	if (qdisc_is_percpu_stats(sch)) {
+		qdisc_qstats_cpu_backlog_dec(sch, skb);
+		qdisc_bstats_cpu_update(sch, skb);
+		qdisc_qstats_atomic_qlen_dec(sch);
+	} else {
+		qdisc_qstats_backlog_dec(sch, skb);
+		qdisc_bstats_update(sch, skb);
+		sch->q.qlen--;
+	}
+}
+
+static inline void qdisc_update_stats_at_enqueue(struct Qdisc *sch,
+						 unsigned int pkt_len)
+{
+	if (qdisc_is_percpu_stats(sch)) {
+		qdisc_qstats_atomic_qlen_inc(sch);
+		this_cpu_add(sch->cpu_qstats->backlog, pkt_len);
+	} else {
+		sch->qstats.backlog += pkt_len;
+		sch->q.qlen++;
+	}
+}
+
 /* use instead of qdisc->dequeue() for all qdiscs queried with ->peek() */
 static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
 {
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index fb8f138b9776..c126b9f78d6e 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -998,6 +998,19 @@ static void notify_and_destroy(struct net *net, struct sk_buff *skb,
 		qdisc_put(old);
 }
 
+static void qdisc_clear_nolock(struct Qdisc *sch)
+{
+	sch->flags &= ~TCQ_F_NOLOCK;
+	if (!(sch->flags & TCQ_F_CPUSTATS))
+		return;
+
+	free_percpu(sch->cpu_bstats);
+	free_percpu(sch->cpu_qstats);
+	sch->cpu_bstats = NULL;
+	sch->cpu_qstats = NULL;
+	sch->flags &= ~TCQ_F_CPUSTATS;
+}
+
 /* Graft qdisc "new" to class "classid" of qdisc "parent" or
  * to device "dev".
  *
@@ -1076,7 +1089,7 @@ skip:
 		/* Only support running class lockless if parent is lockless */
 		if (new && (new->flags & TCQ_F_NOLOCK) &&
 		    parent && !(parent->flags & TCQ_F_NOLOCK))
-			new->flags &= ~TCQ_F_NOLOCK;
+			qdisc_clear_nolock(new);
 
 		if (!cops || !cops->graft)
 			return -EOPNOTSUPP;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index ddff2952be87..12a6e1a39fa0 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -629,11 +629,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
 	if (unlikely(err))
 		return qdisc_drop_cpu(skb, qdisc, to_free);
 
-	qdisc_qstats_atomic_qlen_inc(qdisc);
-	/* Note: skb can not be used after skb_array_produce(),
-	 * so we better not use qdisc_qstats_cpu_backlog_inc()
-	 */
-	this_cpu_add(qdisc->cpu_qstats->backlog, pkt_len);
+	qdisc_update_stats_at_enqueue(qdisc, pkt_len);
 	return NET_XMIT_SUCCESS;
 }
 
@@ -652,9 +648,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 		skb = __skb_array_consume(q);
 	}
 	if (likely(skb)) {
-		qdisc_qstats_cpu_backlog_dec(qdisc, skb);
-		qdisc_bstats_cpu_update(qdisc, skb);
-		qdisc_qstats_atomic_qlen_dec(qdisc);
+		qdisc_update_stats_at_dequeue(qdisc, skb);
 	} else {
 		qdisc->empty = true;
 	}
-- 
cgit v1.2.3


From 73eb628ddfd3884d1e58a8022de2e78de7807fc6 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Wed, 10 Apr 2019 14:32:41 +0200
Subject: Revert: "net: sched: put back q.qlen into a single location"

This revert commit 46b1c18f9deb ("net: sched: put back q.qlen into
a single location").
After the previous patch, when a NOLOCK qdisc is enslaved to a
locking qdisc it switches to global stats accounting. As a consequence,
when a classful qdisc accesses directly a child qdisc's qlen, such
qdisc is not doing per CPU accounting and qlen value is consistent.

In the control path nobody uses directly qlen since commit
e5f0e8f8e45 ("net: sched: introduce and use qdisc tree flush/purge
helpers"), so we can remove the contented atomic ops from the
datapath.

v1 -> v2:
 - complete the qdisc_qstats_atomic_qlen_dec() ->
   qdisc_qstats_cpu_qlen_dec() replacement, fix build issue
 - more descriptive commit message

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 37 +++++++++++++++++++++----------------
 net/core/gen_stats.c      |  2 ++
 net/sched/sch_generic.c   |  9 +++++----
 3 files changed, 28 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index f069011524ba..e8f85cd2afce 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -52,10 +52,7 @@ struct qdisc_size_table {
 struct qdisc_skb_head {
 	struct sk_buff	*head;
 	struct sk_buff	*tail;
-	union {
-		u32		qlen;
-		atomic_t	atomic_qlen;
-	};
+	__u32		qlen;
 	spinlock_t	lock;
 };
 
@@ -486,19 +483,27 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 	BUILD_BUG_ON(sizeof(qcb->data) < sz);
 }
 
+static inline int qdisc_qlen_cpu(const struct Qdisc *q)
+{
+	return this_cpu_ptr(q->cpu_qstats)->qlen;
+}
+
 static inline int qdisc_qlen(const struct Qdisc *q)
 {
 	return q->q.qlen;
 }
 
-static inline u32 qdisc_qlen_sum(const struct Qdisc *q)
+static inline int qdisc_qlen_sum(const struct Qdisc *q)
 {
-	u32 qlen = q->qstats.qlen;
+	__u32 qlen = q->qstats.qlen;
+	int i;
 
-	if (qdisc_is_percpu_stats(q))
-		qlen += atomic_read(&q->q.atomic_qlen);
-	else
+	if (qdisc_is_percpu_stats(q)) {
+		for_each_possible_cpu(i)
+			qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen;
+	} else {
 		qlen += q->q.qlen;
+	}
 
 	return qlen;
 }
@@ -889,14 +894,14 @@ static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch,
 	this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb));
 }
 
-static inline void qdisc_qstats_atomic_qlen_inc(struct Qdisc *sch)
+static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch)
 {
-	atomic_inc(&sch->q.atomic_qlen);
+	this_cpu_inc(sch->cpu_qstats->qlen);
 }
 
-static inline void qdisc_qstats_atomic_qlen_dec(struct Qdisc *sch)
+static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch)
 {
-	atomic_dec(&sch->q.atomic_qlen);
+	this_cpu_dec(sch->cpu_qstats->qlen);
 }
 
 static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch)
@@ -1112,7 +1117,7 @@ static inline void qdisc_update_stats_at_dequeue(struct Qdisc *sch,
 	if (qdisc_is_percpu_stats(sch)) {
 		qdisc_qstats_cpu_backlog_dec(sch, skb);
 		qdisc_bstats_cpu_update(sch, skb);
-		qdisc_qstats_atomic_qlen_dec(sch);
+		qdisc_qstats_cpu_qlen_dec(sch);
 	} else {
 		qdisc_qstats_backlog_dec(sch, skb);
 		qdisc_bstats_update(sch, skb);
@@ -1124,7 +1129,7 @@ static inline void qdisc_update_stats_at_enqueue(struct Qdisc *sch,
 						 unsigned int pkt_len)
 {
 	if (qdisc_is_percpu_stats(sch)) {
-		qdisc_qstats_atomic_qlen_inc(sch);
+		qdisc_qstats_cpu_qlen_inc(sch);
 		this_cpu_add(sch->cpu_qstats->backlog, pkt_len);
 	} else {
 		sch->qstats.backlog += pkt_len;
@@ -1141,7 +1146,7 @@ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
 		skb = __skb_dequeue(&sch->gso_skb);
 		if (qdisc_is_percpu_stats(sch)) {
 			qdisc_qstats_cpu_backlog_dec(sch, skb);
-			qdisc_qstats_atomic_qlen_dec(sch);
+			qdisc_qstats_cpu_qlen_dec(sch);
 		} else {
 			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index ac679f74ba47..9bf1b9ad1780 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -291,6 +291,7 @@ __gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats,
 	for_each_possible_cpu(i) {
 		const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i);
 
+		qstats->qlen = 0;
 		qstats->backlog += qcpu->backlog;
 		qstats->drops += qcpu->drops;
 		qstats->requeues += qcpu->requeues;
@@ -306,6 +307,7 @@ void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats,
 	if (cpu) {
 		__gnet_stats_copy_queue_cpu(qstats, cpu);
 	} else {
+		qstats->qlen = q->qlen;
 		qstats->backlog = q->backlog;
 		qstats->drops = q->drops;
 		qstats->requeues = q->requeues;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 12a6e1a39fa0..848aab3693bd 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -68,7 +68,7 @@ static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
 			skb = __skb_dequeue(&q->skb_bad_txq);
 			if (qdisc_is_percpu_stats(q)) {
 				qdisc_qstats_cpu_backlog_dec(q, skb);
-				qdisc_qstats_atomic_qlen_dec(q);
+				qdisc_qstats_cpu_qlen_dec(q);
 			} else {
 				qdisc_qstats_backlog_dec(q, skb);
 				q->q.qlen--;
@@ -108,7 +108,7 @@ static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q,
 
 	if (qdisc_is_percpu_stats(q)) {
 		qdisc_qstats_cpu_backlog_inc(q, skb);
-		qdisc_qstats_atomic_qlen_inc(q);
+		qdisc_qstats_cpu_qlen_inc(q);
 	} else {
 		qdisc_qstats_backlog_inc(q, skb);
 		q->q.qlen++;
@@ -136,7 +136,7 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 		if (qdisc_is_percpu_stats(q)) {
 			qdisc_qstats_cpu_requeues_inc(q);
 			qdisc_qstats_cpu_backlog_inc(q, skb);
-			qdisc_qstats_atomic_qlen_inc(q);
+			qdisc_qstats_cpu_qlen_inc(q);
 		} else {
 			q->qstats.requeues++;
 			qdisc_qstats_backlog_inc(q, skb);
@@ -236,7 +236,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 			skb = __skb_dequeue(&q->gso_skb);
 			if (qdisc_is_percpu_stats(q)) {
 				qdisc_qstats_cpu_backlog_dec(q, skb);
-				qdisc_qstats_atomic_qlen_dec(q);
+				qdisc_qstats_cpu_qlen_dec(q);
 			} else {
 				qdisc_qstats_backlog_dec(q, skb);
 				q->q.qlen--;
@@ -694,6 +694,7 @@ static void pfifo_fast_reset(struct Qdisc *qdisc)
 		struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i);
 
 		q->backlog = 0;
+		q->qlen = 0;
 	}
 }
 
-- 
cgit v1.2.3


From b0b9395d865e3060d97658fbc9ba3f77fecc8da1 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Tue, 9 Apr 2019 11:49:09 -0700
Subject: bpf: support input __sk_buff context in BPF_PROG_TEST_RUN

Add new set of arguments to bpf_attr for BPF_PROG_TEST_RUN:
* ctx_in/ctx_size_in - input context
* ctx_out/ctx_size_out - output context

The intended use case is to pass some meta data to the test runs that
operate on skb (this has being brought up on recent LPC).

For programs that use bpf_prog_test_run_skb, support __sk_buff input and
output. Initially, from input __sk_buff, copy _only_ cb and priority into
skb, all other non-zero fields are prohibited (with EINVAL).
If the user has set ctx_out/ctx_size_out, copy the potentially modified
__sk_buff back to the userspace.

We require all fields of input __sk_buff except the ones we explicitly
support to be set to zero. The expectation is that in the future we might
add support for more fields and we want to fail explicitly if the user
runs the program on the kernel where we don't yet support them.

The API is intentionally vague (i.e. we don't explicitly add __sk_buff
to bpf_attr, but ctx_in) to potentially let other test_run types use
this interface in the future (this can be xdp_md for xdp types for
example).

v4:
  * don't copy more than allowed in bpf_ctx_init [Martin]

v3:
  * handle case where ctx_in is NULL, but ctx_out is not [Martin]
  * convert size==0 checks to ptr==NULL checks and add some extra ptr
    checks [Martin]

v2:
  * Addressed comments from Martin Lau

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h |   7 +++
 kernel/bpf/syscall.c     |  10 +++-
 net/bpf/test_run.c       | 143 ++++++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 151 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index af1cbd951f26..31a27dd337dc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -412,6 +412,13 @@ union bpf_attr {
 		__aligned_u64	data_out;
 		__u32		repeat;
 		__u32		duration;
+		__u32		ctx_size_in;	/* input: len of ctx_in */
+		__u32		ctx_size_out;	/* input/output: len of ctx_out
+						 *   returns ENOSPC if ctx_out
+						 *   is too small.
+						 */
+		__aligned_u64	ctx_in;
+		__aligned_u64	ctx_out;
 	} test;
 
 	struct { /* anonymous struct used by BPF_*_GET_*_ID */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 438199e2eca4..d995eedfdd16 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2009,7 +2009,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	return cgroup_bpf_prog_query(attr, uattr);
 }
 
-#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out
 
 static int bpf_prog_test_run(const union bpf_attr *attr,
 			     union bpf_attr __user *uattr)
@@ -2022,6 +2022,14 @@ static int bpf_prog_test_run(const union bpf_attr *attr,
 	if (CHECK_ATTR(BPF_PROG_TEST_RUN))
 		return -EINVAL;
 
+	if ((attr->test.ctx_size_in && !attr->test.ctx_in) ||
+	    (!attr->test.ctx_size_in && attr->test.ctx_in))
+		return -EINVAL;
+
+	if ((attr->test.ctx_size_out && !attr->test.ctx_out) ||
+	    (!attr->test.ctx_size_out && attr->test.ctx_out))
+		return -EINVAL;
+
 	prog = bpf_prog_get(attr->test.prog_fd);
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index fab142b796ef..cbd4fb65aa4f 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -123,12 +123,126 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
 	return data;
 }
 
+static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
+{
+	void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in);
+	void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
+	u32 size = kattr->test.ctx_size_in;
+	void *data;
+	int err;
+
+	if (!data_in && !data_out)
+		return NULL;
+
+	data = kzalloc(max_size, GFP_USER);
+	if (!data)
+		return ERR_PTR(-ENOMEM);
+
+	if (data_in) {
+		err = bpf_check_uarg_tail_zero(data_in, max_size, size);
+		if (err) {
+			kfree(data);
+			return ERR_PTR(err);
+		}
+
+		size = min_t(u32, max_size, size);
+		if (copy_from_user(data, data_in, size)) {
+			kfree(data);
+			return ERR_PTR(-EFAULT);
+		}
+	}
+	return data;
+}
+
+static int bpf_ctx_finish(const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr, const void *data,
+			  u32 size)
+{
+	void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
+	int err = -EFAULT;
+	u32 copy_size = size;
+
+	if (!data || !data_out)
+		return 0;
+
+	if (copy_size > kattr->test.ctx_size_out) {
+		copy_size = kattr->test.ctx_size_out;
+		err = -ENOSPC;
+	}
+
+	if (copy_to_user(data_out, data, copy_size))
+		goto out;
+	if (copy_to_user(&uattr->test.ctx_size_out, &size, sizeof(size)))
+		goto out;
+	if (err != -ENOSPC)
+		err = 0;
+out:
+	return err;
+}
+
+/**
+ * range_is_zero - test whether buffer is initialized
+ * @buf: buffer to check
+ * @from: check from this position
+ * @to: check up until (excluding) this position
+ *
+ * This function returns true if the there is a non-zero byte
+ * in the buf in the range [from,to).
+ */
+static inline bool range_is_zero(void *buf, size_t from, size_t to)
+{
+	return !memchr_inv((u8 *)buf + from, 0, to - from);
+}
+
+static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
+{
+	struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
+
+	if (!__skb)
+		return 0;
+
+	/* make sure the fields we don't use are zeroed */
+	if (!range_is_zero(__skb, 0, offsetof(struct __sk_buff, priority)))
+		return -EINVAL;
+
+	/* priority is allowed */
+
+	if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) +
+			   FIELD_SIZEOF(struct __sk_buff, priority),
+			   offsetof(struct __sk_buff, cb)))
+		return -EINVAL;
+
+	/* cb is allowed */
+
+	if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) +
+			   FIELD_SIZEOF(struct __sk_buff, cb),
+			   sizeof(struct __sk_buff)))
+		return -EINVAL;
+
+	skb->priority = __skb->priority;
+	memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN);
+
+	return 0;
+}
+
+static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb)
+{
+	struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
+
+	if (!__skb)
+		return;
+
+	__skb->priority = skb->priority;
+	memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN);
+}
+
 int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr)
 {
 	bool is_l2 = false, is_direct_pkt_access = false;
 	u32 size = kattr->test.data_size_in;
 	u32 repeat = kattr->test.repeat;
+	struct __sk_buff *ctx = NULL;
 	u32 retval, duration;
 	int hh_len = ETH_HLEN;
 	struct sk_buff *skb;
@@ -141,6 +255,12 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
+	ctx = bpf_ctx_init(kattr, sizeof(struct __sk_buff));
+	if (IS_ERR(ctx)) {
+		kfree(data);
+		return PTR_ERR(ctx);
+	}
+
 	switch (prog->type) {
 	case BPF_PROG_TYPE_SCHED_CLS:
 	case BPF_PROG_TYPE_SCHED_ACT:
@@ -158,6 +278,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	sk = kzalloc(sizeof(struct sock), GFP_USER);
 	if (!sk) {
 		kfree(data);
+		kfree(ctx);
 		return -ENOMEM;
 	}
 	sock_net_set(sk, current->nsproxy->net_ns);
@@ -166,6 +287,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	skb = build_skb(data, 0);
 	if (!skb) {
 		kfree(data);
+		kfree(ctx);
 		kfree(sk);
 		return -ENOMEM;
 	}
@@ -180,32 +302,37 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		__skb_push(skb, hh_len);
 	if (is_direct_pkt_access)
 		bpf_compute_data_pointers(skb);
+	ret = convert___skb_to_skb(skb, ctx);
+	if (ret)
+		goto out;
 	ret = bpf_test_run(prog, skb, repeat, &retval, &duration);
-	if (ret) {
-		kfree_skb(skb);
-		kfree(sk);
-		return ret;
-	}
+	if (ret)
+		goto out;
 	if (!is_l2) {
 		if (skb_headroom(skb) < hh_len) {
 			int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
 
 			if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
-				kfree_skb(skb);
-				kfree(sk);
-				return -ENOMEM;
+				ret = -ENOMEM;
+				goto out;
 			}
 		}
 		memset(__skb_push(skb, hh_len), 0, hh_len);
 	}
+	convert_skb_to___skb(skb, ctx);
 
 	size = skb->len;
 	/* bpf program can never convert linear skb to non-linear */
 	if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
 		size = skb_headlen(skb);
 	ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
+	if (!ret)
+		ret = bpf_ctx_finish(kattr, uattr, ctx,
+				     sizeof(struct __sk_buff));
+out:
 	kfree_skb(skb);
 	kfree(sk);
+	kfree(ctx);
 	return ret;
 }
 
-- 
cgit v1.2.3


From bf8981a2aa082d9d64771b47c8a1c9c388d8cd40 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 9 Apr 2019 10:44:06 +0200
Subject: netfilter: nf_nat: merge ip/ip6 masquerade headers

Both are now implemented by nf_nat_masquerade.c, so no need to keep
different headers.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv4/nf_nat_masquerade.h | 15 ---------------
 include/net/netfilter/ipv6/nf_nat_masquerade.h | 11 -----------
 include/net/netfilter/nf_nat_masquerade.h      | 21 +++++++++++++++++++++
 net/ipv4/netfilter/ipt_MASQUERADE.c            |  2 +-
 net/ipv6/netfilter/ip6t_MASQUERADE.c           |  2 +-
 net/netfilter/nf_nat_masquerade.c              |  3 +--
 net/netfilter/nft_masq.c                       |  3 +--
 7 files changed, 25 insertions(+), 32 deletions(-)
 delete mode 100644 include/net/netfilter/ipv4/nf_nat_masquerade.h
 delete mode 100644 include/net/netfilter/ipv6/nf_nat_masquerade.h
 create mode 100644 include/net/netfilter/nf_nat_masquerade.h

(limited to 'include')

diff --git a/include/net/netfilter/ipv4/nf_nat_masquerade.h b/include/net/netfilter/ipv4/nf_nat_masquerade.h
deleted file mode 100644
index 13d55206bb9f..000000000000
--- a/include/net/netfilter/ipv4/nf_nat_masquerade.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NF_NAT_MASQUERADE_IPV4_H_
-#define _NF_NAT_MASQUERADE_IPV4_H_
-
-#include <net/netfilter/nf_nat.h>
-
-unsigned int
-nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
-		       const struct nf_nat_range2 *range,
-		       const struct net_device *out);
-
-int nf_nat_masquerade_ipv4_register_notifier(void);
-void nf_nat_masquerade_ipv4_unregister_notifier(void);
-
-#endif /*_NF_NAT_MASQUERADE_IPV4_H_ */
diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h
deleted file mode 100644
index 2917bf95c437..000000000000
--- a/include/net/netfilter/ipv6/nf_nat_masquerade.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NF_NAT_MASQUERADE_IPV6_H_
-#define _NF_NAT_MASQUERADE_IPV6_H_
-
-unsigned int
-nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
-		       const struct net_device *out);
-int nf_nat_masquerade_ipv6_register_notifier(void);
-void nf_nat_masquerade_ipv6_unregister_notifier(void);
-
-#endif /* _NF_NAT_MASQUERADE_IPV6_H_ */
diff --git a/include/net/netfilter/nf_nat_masquerade.h b/include/net/netfilter/nf_nat_masquerade.h
new file mode 100644
index 000000000000..cafe71822a53
--- /dev/null
+++ b/include/net/netfilter/nf_nat_masquerade.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NF_NAT_MASQUERADE_H_
+#define _NF_NAT_MASQUERADE_H_
+
+#include <net/netfilter/nf_nat.h>
+
+unsigned int
+nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
+		       const struct nf_nat_range2 *range,
+		       const struct net_device *out);
+
+int nf_nat_masquerade_ipv4_register_notifier(void);
+void nf_nat_masquerade_ipv4_unregister_notifier(void);
+
+unsigned int
+nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
+		       const struct net_device *out);
+int nf_nat_masquerade_ipv6_register_notifier(void);
+void nf_nat_masquerade_ipv6_unregister_notifier(void);
+
+#endif /*_NF_NAT_MASQUERADE_H_ */
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index fd3f9e8a74da..0a2bffb6a0ad 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -22,7 +22,7 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter/x_tables.h>
 #include <net/netfilter/nf_nat.h>
-#include <net/netfilter/ipv4/nf_nat_masquerade.h>
+#include <net/netfilter/nf_nat_masquerade.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 29c7f1915a96..4a22343ed67a 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -19,7 +19,7 @@
 #include <net/netfilter/nf_nat.h>
 #include <net/addrconf.h>
 #include <net/ipv6.h>
-#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+#include <net/netfilter/nf_nat_masquerade.h>
 
 static unsigned int
 masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c
index d85c4d902e7b..10053e70f69d 100644
--- a/net/netfilter/nf_nat_masquerade.c
+++ b/net/netfilter/nf_nat_masquerade.c
@@ -7,8 +7,7 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_ipv6.h>
 
-#include <net/netfilter/ipv4/nf_nat_masquerade.h>
-#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+#include <net/netfilter/nf_nat_masquerade.h>
 
 static DEFINE_MUTEX(masq_mutex);
 static unsigned int masq_refcnt4 __read_mostly;
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index 35a1794acf4c..0783a3e99bd7 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -14,8 +14,7 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_nat.h>
-#include <net/netfilter/ipv4/nf_nat_masquerade.h>
-#include <net/netfilter/ipv6/nf_nat_masquerade.h>
+#include <net/netfilter/nf_nat_masquerade.h>
 
 struct nft_masq {
 	u32			flags;
-- 
cgit v1.2.3


From 610a43149cabd0c7aa7bed19cbcf05a0249ab32a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 9 Apr 2019 10:44:08 +0200
Subject: netfilter: nf_nat_masquerade: unify ipv4/6 notifier registration

Only reason for having two different register functions was because of
ipt_MASQUERADE and ip6t_MASQUERADE being two different modules.

Previous patch merged those into xt_MASQUERADE, so we can merge this too.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_nat_masquerade.h |   6 +-
 net/netfilter/nf_nat_masquerade.c         | 101 +++++++++++-------------------
 net/netfilter/nft_masq.c                  |  16 +----
 net/netfilter/xt_MASQUERADE.c             |  16 +----
 4 files changed, 44 insertions(+), 95 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_nat_masquerade.h b/include/net/netfilter/nf_nat_masquerade.h
index cafe71822a53..54a14d643c34 100644
--- a/include/net/netfilter/nf_nat_masquerade.h
+++ b/include/net/netfilter/nf_nat_masquerade.h
@@ -9,13 +9,11 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
 		       const struct nf_nat_range2 *range,
 		       const struct net_device *out);
 
-int nf_nat_masquerade_ipv4_register_notifier(void);
-void nf_nat_masquerade_ipv4_unregister_notifier(void);
+int nf_nat_masquerade_inet_register_notifiers(void);
+void nf_nat_masquerade_inet_unregister_notifiers(void);
 
 unsigned int
 nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
 		       const struct net_device *out);
-int nf_nat_masquerade_ipv6_register_notifier(void);
-void nf_nat_masquerade_ipv6_unregister_notifier(void);
 
 #endif /*_NF_NAT_MASQUERADE_H_ */
diff --git a/net/netfilter/nf_nat_masquerade.c b/net/netfilter/nf_nat_masquerade.c
index 10053e70f69d..8e8a65d46345 100644
--- a/net/netfilter/nf_nat_masquerade.c
+++ b/net/netfilter/nf_nat_masquerade.c
@@ -10,8 +10,7 @@
 #include <net/netfilter/nf_nat_masquerade.h>
 
 static DEFINE_MUTEX(masq_mutex);
-static unsigned int masq_refcnt4 __read_mostly;
-static unsigned int masq_refcnt6 __read_mostly;
+static unsigned int masq_refcnt __read_mostly;
 
 unsigned int
 nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
@@ -136,56 +135,6 @@ static struct notifier_block masq_inet_notifier = {
 	.notifier_call	= masq_inet_event,
 };
 
-int nf_nat_masquerade_ipv4_register_notifier(void)
-{
-	int ret = 0;
-
-	mutex_lock(&masq_mutex);
-	if (WARN_ON_ONCE(masq_refcnt4 == UINT_MAX)) {
-		ret = -EOVERFLOW;
-		goto out_unlock;
-	}
-
-	/* check if the notifier was already set */
-	if (++masq_refcnt4 > 1)
-		goto out_unlock;
-
-	/* Register for device down reports */
-	ret = register_netdevice_notifier(&masq_dev_notifier);
-	if (ret)
-		goto err_dec;
-	/* Register IP address change reports */
-	ret = register_inetaddr_notifier(&masq_inet_notifier);
-	if (ret)
-		goto err_unregister;
-
-	mutex_unlock(&masq_mutex);
-	return ret;
-
-err_unregister:
-	unregister_netdevice_notifier(&masq_dev_notifier);
-err_dec:
-	masq_refcnt4--;
-out_unlock:
-	mutex_unlock(&masq_mutex);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
-
-void nf_nat_masquerade_ipv4_unregister_notifier(void)
-{
-	mutex_lock(&masq_mutex);
-	/* check if the notifier still has clients */
-	if (--masq_refcnt4 > 0)
-		goto out_unlock;
-
-	unregister_netdevice_notifier(&masq_dev_notifier);
-	unregister_inetaddr_notifier(&masq_inet_notifier);
-out_unlock:
-	mutex_unlock(&masq_mutex);
-}
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
-
 #if IS_ENABLED(CONFIG_IPV6)
 static atomic_t v6_worker_count __read_mostly;
 
@@ -321,44 +270,68 @@ static struct notifier_block masq_inet6_notifier = {
 	.notifier_call	= masq_inet6_event,
 };
 
-int nf_nat_masquerade_ipv6_register_notifier(void)
+static int nf_nat_masquerade_ipv6_register_notifier(void)
+{
+	return register_inet6addr_notifier(&masq_inet6_notifier);
+}
+#else
+static inline int nf_nat_masquerade_ipv6_register_notifier(void) { return 0; }
+#endif
+
+int nf_nat_masquerade_inet_register_notifiers(void)
 {
 	int ret = 0;
 
 	mutex_lock(&masq_mutex);
-	if (WARN_ON_ONCE(masq_refcnt6 == UINT_MAX)) {
+	if (WARN_ON_ONCE(masq_refcnt == UINT_MAX)) {
 		ret = -EOVERFLOW;
 		goto out_unlock;
 	}
 
-	/* check if the notifier is already set */
-	if (++masq_refcnt6 > 1)
+	/* check if the notifier was already set */
+	if (++masq_refcnt > 1)
 		goto out_unlock;
 
-	ret = register_inet6addr_notifier(&masq_inet6_notifier);
+	/* Register for device down reports */
+	ret = register_netdevice_notifier(&masq_dev_notifier);
 	if (ret)
 		goto err_dec;
+	/* Register IP address change reports */
+	ret = register_inetaddr_notifier(&masq_inet_notifier);
+	if (ret)
+		goto err_unregister;
+
+	ret = nf_nat_masquerade_ipv6_register_notifier();
+	if (ret)
+		goto err_unreg_inet;
 
 	mutex_unlock(&masq_mutex);
 	return ret;
+err_unreg_inet:
+	unregister_inetaddr_notifier(&masq_inet_notifier);
+err_unregister:
+	unregister_netdevice_notifier(&masq_dev_notifier);
 err_dec:
-	masq_refcnt6--;
+	masq_refcnt--;
 out_unlock:
 	mutex_unlock(&masq_mutex);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_register_notifiers);
 
-void nf_nat_masquerade_ipv6_unregister_notifier(void)
+void nf_nat_masquerade_inet_unregister_notifiers(void)
 {
 	mutex_lock(&masq_mutex);
-	/* check if the notifier still has clients */
-	if (--masq_refcnt6 > 0)
+	/* check if the notifiers still have clients */
+	if (--masq_refcnt > 0)
 		goto out_unlock;
 
+	unregister_netdevice_notifier(&masq_dev_notifier);
+	unregister_inetaddr_notifier(&masq_inet_notifier);
+#if IS_ENABLED(CONFIG_IPV6)
 	unregister_inet6addr_notifier(&masq_inet6_notifier);
+#endif
 out_unlock:
 	mutex_unlock(&masq_mutex);
 }
-EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
-#endif
+EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_unregister_notifiers);
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index 0783a3e99bd7..86fd90085eaf 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -195,22 +195,12 @@ static struct nft_expr_type nft_masq_ipv6_type __read_mostly = {
 
 static int __init nft_masq_module_init_ipv6(void)
 {
-	int ret = nft_register_expr(&nft_masq_ipv6_type);
-
-	if (ret)
-		return ret;
-
-	ret = nf_nat_masquerade_ipv6_register_notifier();
-	if (ret < 0)
-		nft_unregister_expr(&nft_masq_ipv6_type);
-
-	return ret;
+	return nft_register_expr(&nft_masq_ipv6_type);
 }
 
 static void nft_masq_module_exit_ipv6(void)
 {
 	nft_unregister_expr(&nft_masq_ipv6_type);
-	nf_nat_masquerade_ipv6_unregister_notifier();
 }
 #else
 static inline int nft_masq_module_init_ipv6(void) { return 0; }
@@ -293,7 +283,7 @@ static int __init nft_masq_module_init(void)
 		return ret;
 	}
 
-	ret = nf_nat_masquerade_ipv4_register_notifier();
+	ret = nf_nat_masquerade_inet_register_notifiers();
 	if (ret < 0) {
 		nft_masq_module_exit_ipv6();
 		nft_masq_module_exit_inet();
@@ -309,7 +299,7 @@ static void __exit nft_masq_module_exit(void)
 	nft_masq_module_exit_ipv6();
 	nft_masq_module_exit_inet();
 	nft_unregister_expr(&nft_masq_ipv4_type);
-	nf_nat_masquerade_ipv4_unregister_notifier();
+	nf_nat_masquerade_inet_unregister_notifiers();
 }
 
 module_init(nft_masq_module_init);
diff --git a/net/netfilter/xt_MASQUERADE.c b/net/netfilter/xt_MASQUERADE.c
index 96d884718749..ece20d832adc 100644
--- a/net/netfilter/xt_MASQUERADE.c
+++ b/net/netfilter/xt_MASQUERADE.c
@@ -107,32 +107,20 @@ static int __init masquerade_tg_init(void)
 	if (ret)
 		return ret;
 
-	ret = nf_nat_masquerade_ipv4_register_notifier();
+	ret = nf_nat_masquerade_inet_register_notifiers();
 	if (ret) {
 		xt_unregister_targets(masquerade_tg_reg,
 				      ARRAY_SIZE(masquerade_tg_reg));
 		return ret;
 	}
 
-#if IS_ENABLED(CONFIG_IPV6)
-	ret = nf_nat_masquerade_ipv6_register_notifier();
-	if (ret) {
-		xt_unregister_targets(masquerade_tg_reg,
-				      ARRAY_SIZE(masquerade_tg_reg));
-		nf_nat_masquerade_ipv4_unregister_notifier();
-		return ret;
-	}
-#endif
 	return ret;
 }
 
 static void __exit masquerade_tg_exit(void)
 {
 	xt_unregister_targets(masquerade_tg_reg, ARRAY_SIZE(masquerade_tg_reg));
-	nf_nat_masquerade_ipv4_unregister_notifier();
-#if IS_ENABLED(CONFIG_IPV6)
-	nf_nat_masquerade_ipv6_unregister_notifier();
-#endif
+	nf_nat_masquerade_inet_unregister_notifiers();
 }
 
 module_init(masquerade_tg_init);
-- 
cgit v1.2.3


From c695865c5c9803f14eef2c99d8a49d9ad60a3383 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Thu, 11 Apr 2019 09:12:02 -0700
Subject: bpf: fix missing bpf_check_uarg_tail_zero in BPF_PROG_TEST_RUN
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit b0b9395d865e ("bpf: support input __sk_buff context in
BPF_PROG_TEST_RUN") started using bpf_check_uarg_tail_zero in
BPF_PROG_TEST_RUN. However, bpf_check_uarg_tail_zero is not defined
for !CONFIG_BPF_SYSCALL:

net/bpf/test_run.c: In function ‘bpf_ctx_init’:
net/bpf/test_run.c:142:9: error: implicit declaration of function ‘bpf_check_uarg_tail_zero’ [-Werror=implicit-function-declaration]
   err = bpf_check_uarg_tail_zero(data_in, max_size, size);
         ^~~~~~~~~~~~~~~~~~~~~~~~

Let's not build net/bpf/test_run.c when CONFIG_BPF_SYSCALL is not set.

Reported-by: kbuild test robot <lkp@intel.com>
Fixes: b0b9395d865e ("bpf: support input __sk_buff context in BPF_PROG_TEST_RUN")
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h | 36 ++++++++++++++++++++++++++++--------
 net/bpf/Makefile    |  2 +-
 2 files changed, 29 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 65f7094c40b4..e4d4c1771ab0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -483,14 +483,6 @@ typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type,
 u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
 
-int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
-			  union bpf_attr __user *uattr);
-int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
-			  union bpf_attr __user *uattr);
-int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
-				     const union bpf_attr *kattr,
-				     union bpf_attr __user *uattr);
-
 /* an array of programs to be executed under rcu_lock.
  *
  * Typical usage:
@@ -681,6 +673,13 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
 struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type);
 int array_map_alloc_check(union bpf_attr *attr);
 
+int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr);
+int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr);
+int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
+				     const union bpf_attr *kattr,
+				     union bpf_attr __user *uattr);
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
@@ -792,6 +791,27 @@ static inline struct bpf_prog *bpf_prog_get_type_path(const char *name,
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
+
+static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog,
+					const union bpf_attr *kattr,
+					union bpf_attr __user *uattr)
+{
+	return -ENOTSUPP;
+}
+
+static inline int bpf_prog_test_run_skb(struct bpf_prog *prog,
+					const union bpf_attr *kattr,
+					union bpf_attr __user *uattr)
+{
+	return -ENOTSUPP;
+}
+
+static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
+						   const union bpf_attr *kattr,
+						   union bpf_attr __user *uattr)
+{
+	return -ENOTSUPP;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
diff --git a/net/bpf/Makefile b/net/bpf/Makefile
index 27b2992a0692..b0ca361742e4 100644
--- a/net/bpf/Makefile
+++ b/net/bpf/Makefile
@@ -1 +1 @@
-obj-y	:= test_run.o
+obj-$(CONFIG_BPF_SYSCALL)	:= test_run.o
-- 
cgit v1.2.3


From 58dfc900faff6db7eb9bf01555622e0b6c74c262 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Tue, 9 Apr 2019 15:06:41 +0100
Subject: bpf: add layer 2 encap support to bpf_skb_adjust_room

commit 868d523535c2 ("bpf: add bpf_skb_adjust_room encap flags")
introduced support to bpf_skb_adjust_room for GSO-friendly GRE
and UDP encapsulation.

For GSO to work for skbs, the inner headers (mac and network) need to
be marked.  For L3 encapsulation using bpf_skb_adjust_room, the mac
and network headers are identical.  Here we provide a way of specifying
the inner mac header length for cases where L2 encap is desired.  Such
an approach can support encapsulated ethernet headers, MPLS headers etc.
For example to convert from a packet of form [eth][ip][tcp] to
[eth][ip][udp][inner mac][ip][tcp], something like the following could
be done:

	headroom = sizeof(iph) + sizeof(struct udphdr) + inner_maclen;

	ret = bpf_skb_adjust_room(skb, headroom, BPF_ADJ_ROOM_MAC,
				  BPF_F_ADJ_ROOM_ENCAP_L4_UDP |
				  BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 |
				  BPF_F_ADJ_ROOM_ENCAP_L2(inner_maclen));

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h | 10 ++++++++++
 net/core/filter.c        | 12 ++++++++----
 2 files changed, 18 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 31a27dd337dc..2e96d0b4bf65 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1523,6 +1523,10 @@ union bpf_attr {
  *		* **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **:
  *		  Use with ENCAP_L3 flags to further specify the tunnel type.
  *
+ *		* **BPF_F_ADJ_ROOM_ENCAP_L2(len) **:
+ *		  Use with ENCAP_L3/L4 flags to further specify the tunnel
+ *		  type; **len** is the length of the inner MAC header.
+ *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
  * 		previously done by the verifier are invalidated and must be
@@ -2664,10 +2668,16 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_adjust_room flags. */
 #define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
 
+#define	BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
+#define	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
+
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
+#define	BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
+					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
diff --git a/net/core/filter.c b/net/core/filter.c
index 22eb2edf5573..a1654ef62533 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2969,11 +2969,14 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 #define BPF_F_ADJ_ROOM_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO | \
 					 BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
 					 BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
-					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
+					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \
+					 BPF_F_ADJ_ROOM_ENCAP_L2( \
+					  BPF_ADJ_ROOM_ENCAP_L2_MASK))
 
 static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			    u64 flags)
 {
+	u8 inner_mac_len = flags >> BPF_ADJ_ROOM_ENCAP_L2_SHIFT;
 	bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK;
 	u16 mac_len = 0, inner_net = 0, inner_trans = 0;
 	unsigned int gso_type = SKB_GSO_DODGY;
@@ -3008,6 +3011,8 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 
 		mac_len = skb->network_header - skb->mac_header;
 		inner_net = skb->network_header;
+		if (inner_mac_len > len_diff)
+			return -EINVAL;
 		inner_trans = skb->transport_header;
 	}
 
@@ -3016,8 +3021,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 		return ret;
 
 	if (encap) {
-		/* inner mac == inner_net on l3 encap */
-		skb->inner_mac_header = inner_net;
+		skb->inner_mac_header = inner_net - inner_mac_len;
 		skb->inner_network_header = inner_net;
 		skb->inner_transport_header = inner_trans;
 		skb_set_inner_protocol(skb, skb->protocol);
@@ -3031,7 +3035,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			gso_type |= SKB_GSO_GRE;
 		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
 			gso_type |= SKB_GSO_IPXIP6;
-		else
+		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4)
 			gso_type |= SKB_GSO_IPXIP4;
 
 		if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE ||
-- 
cgit v1.2.3


From cc3a86c802f0ba9a2627aef256d95ae3b3fa6e91 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 9 Apr 2019 14:41:12 -0700
Subject: ipv6: Change rt6_probe to take a fib6_nh

rt6_probe sends probes for gateways in a nexthop. As such it really
depends on a fib6_nh, not a fib entry. Move last_probe to fib6_nh and
update rt6_probe to a fib6_nh struct.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  8 ++++----
 net/ipv6/route.c      | 16 ++++++++--------
 2 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 58dbb4e82908..2e9235adfa0d 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -127,6 +127,10 @@ struct rt6_exception {
 
 struct fib6_nh {
 	struct fib_nh_common	nh_common;
+
+#ifdef CONFIG_IPV6_ROUTER_PREF
+	unsigned long		last_probe;
+#endif
 };
 
 struct fib6_info {
@@ -155,10 +159,6 @@ struct fib6_info {
 	struct rt6_info * __percpu	*rt6i_pcpu;
 	struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
 
-#ifdef CONFIG_IPV6_ROUTER_PREF
-	unsigned long			last_probe;
-#endif
-
 	u32				fib6_metric;
 	u8				fib6_protocol;
 	u8				fib6_type;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9630339d4b76..c2b0d6f049e3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -517,7 +517,7 @@ static void rt6_probe_deferred(struct work_struct *w)
 	kfree(work);
 }
 
-static void rt6_probe(struct fib6_info *rt)
+static void rt6_probe(struct fib6_nh *fib6_nh)
 {
 	struct __rt6_probe_work *work = NULL;
 	const struct in6_addr *nh_gw;
@@ -533,11 +533,11 @@ static void rt6_probe(struct fib6_info *rt)
 	 * Router Reachability Probe MUST be rate-limited
 	 * to no more than one per minute.
 	 */
-	if (!rt || !rt->fib6_nh.fib_nh_gw_family)
+	if (fib6_nh->fib_nh_gw_family)
 		return;
 
-	nh_gw = &rt->fib6_nh.fib_nh_gw6;
-	dev = rt->fib6_nh.fib_nh_dev;
+	nh_gw = &fib6_nh->fib_nh_gw6;
+	dev = fib6_nh->fib_nh_dev;
 	rcu_read_lock_bh();
 	idev = __in6_dev_get(dev);
 	neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
@@ -554,13 +554,13 @@ static void rt6_probe(struct fib6_info *rt)
 				__neigh_set_probe_once(neigh);
 		}
 		write_unlock(&neigh->lock);
-	} else if (time_after(jiffies, rt->last_probe +
+	} else if (time_after(jiffies, fib6_nh->last_probe +
 				       idev->cnf.rtr_probe_interval)) {
 		work = kmalloc(sizeof(*work), GFP_ATOMIC);
 	}
 
 	if (work) {
-		rt->last_probe = jiffies;
+		fib6_nh->last_probe = jiffies;
 		INIT_WORK(&work->work, rt6_probe_deferred);
 		work->target = *nh_gw;
 		dev_hold(dev);
@@ -572,7 +572,7 @@ out:
 	rcu_read_unlock_bh();
 }
 #else
-static inline void rt6_probe(struct fib6_info *rt)
+static inline void rt6_probe(struct fib6_nh *fib6_nh)
 {
 }
 #endif
@@ -657,7 +657,7 @@ static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict,
 	}
 
 	if (strict & RT6_LOOKUP_F_REACHABLE)
-		rt6_probe(rt);
+		rt6_probe(&rt->fib6_nh);
 
 	/* note that m can be RT6_NUD_FAIL_PROBE at this point */
 	if (m > *mpri) {
-- 
cgit v1.2.3


From 971502d77faa50a37c89bc6d172450294ad9a5fd Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 11 Apr 2019 16:36:41 +0200
Subject: bridge: netfilter: unroll NF_HOOK helper in bridge input path

Replace NF_HOOK() based invocation of the netfilter hooks with a private
copy of nf_hook_slow().

This copy has one difference: it can return the rx handler value expected
by the stack, i.e. RX_HANDLER_CONSUMED or RX_HANDLER_PASS.

This is needed by the next patch to invoke the ebtables
"broute" table via the standard netfilter hooks rather than the custom
"br_should_route_hook" indirection that is used now.

When the skb is to be "brouted", we must return RX_HANDLER_PASS from the
bridge rx input handler, but there is no way to indicate this via
NF_HOOK(), unless perhaps by some hack such as exposing bridge_cb in the
netfilter core or a percpu flag.

  text    data     bss     dec   filename
  3369      56       0    3425   net/bridge/br_input.o.before
  3458      40       0    3498   net/bridge/br_input.o.after

This allows removal of the "br_should_route_hook" in the next patch.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_queue.h |  3 +++
 net/bridge/br_input.c            | 55 +++++++++++++++++++++++++++++++++++++---
 net/netfilter/core.c             |  1 +
 net/netfilter/nf_internals.h     |  3 ---
 net/netfilter/nf_queue.c         |  1 +
 5 files changed, 56 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h
index a50a69f5334c..7239105d9d2e 100644
--- a/include/net/netfilter/nf_queue.h
+++ b/include/net/netfilter/nf_queue.h
@@ -119,4 +119,7 @@ nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family,
 	return queue;
 }
 
+int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
+	     const struct nf_hook_entries *entries, unsigned int index,
+	     unsigned int verdict);
 #endif /* _NF_QUEUE_H */
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index e2f93e5c72da..4ac34fb5f943 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -16,6 +16,7 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/netfilter_bridge.h>
+#include <net/netfilter/nf_queue.h>
 #include <linux/neighbour.h>
 #include <net/arp.h>
 #include <linux/export.h>
@@ -206,6 +207,55 @@ static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_bu
 	return 0;
 }
 
+static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb)
+{
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+	struct nf_hook_entries *e = NULL;
+	struct nf_hook_state state;
+	unsigned int verdict, i;
+	struct net *net;
+	int ret;
+
+	net = dev_net(skb->dev);
+#ifdef HAVE_JUMP_LABEL
+	if (!static_key_false(&nf_hooks_needed[NFPROTO_BRIDGE][NF_BR_PRE_ROUTING]))
+		goto frame_finish;
+#endif
+
+	e = rcu_dereference(net->nf.hooks_bridge[NF_BR_PRE_ROUTING]);
+	if (!e)
+		goto frame_finish;
+
+	nf_hook_state_init(&state, NF_BR_PRE_ROUTING,
+			   NFPROTO_BRIDGE, skb->dev, NULL, NULL,
+			   net, br_handle_frame_finish);
+
+	for (i = 0; i < e->num_hook_entries; i++) {
+		verdict = nf_hook_entry_hookfn(&e->hooks[i], skb, &state);
+		switch (verdict & NF_VERDICT_MASK) {
+		case NF_ACCEPT:
+			break;
+		case NF_DROP:
+			kfree_skb(skb);
+			return RX_HANDLER_CONSUMED;
+		case NF_QUEUE:
+			ret = nf_queue(skb, &state, e, i, verdict);
+			if (ret == 1)
+				continue;
+			return RX_HANDLER_CONSUMED;
+		default: /* STOLEN */
+			return RX_HANDLER_CONSUMED;
+		}
+	}
+frame_finish:
+	net = dev_net(skb->dev);
+	br_handle_frame_finish(net, NULL, skb);
+#else
+	br_handle_frame_finish(dev_net(skb->dev), NULL, skb);
+#endif
+	return RX_HANDLER_CONSUMED;
+}
+
 /*
  * Return NULL if skb is handled
  * note: already called with rcu_read_lock
@@ -304,10 +354,7 @@ forward:
 		if (ether_addr_equal(p->br->dev->dev_addr, dest))
 			skb->pkt_type = PACKET_HOST;
 
-		NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING,
-			dev_net(skb->dev), NULL, skb, skb->dev, NULL,
-			br_handle_frame_finish);
-		break;
+		return nf_hook_bridge_pre(skb, pskb);
 	default:
 drop:
 		kfree_skb(skb);
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 93aaec3a54ec..71f06900473e 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -23,6 +23,7 @@
 #include <linux/mm.h>
 #include <linux/rcupdate.h>
 #include <net/net_namespace.h>
+#include <net/netfilter/nf_queue.h>
 #include <net/sock.h>
 
 #include "nf_internals.h"
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index e15779fd58e3..d6c43902ebd7 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -7,9 +7,6 @@
 #include <linux/netdevice.h>
 
 /* nf_queue.c */
-int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
-	     const struct nf_hook_entries *entries, unsigned int index,
-	     unsigned int verdict);
 void nf_queue_nf_hook_drop(struct net *net);
 
 /* nf_log.c */
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index a36a77bae1d6..9dc1d6e04946 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -240,6 +240,7 @@ int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nf_queue);
 
 static unsigned int nf_iterate(struct sk_buff *skb,
 			       struct nf_hook_state *state,
-- 
cgit v1.2.3


From 223fd0adfa8af36d5d9b5d38016e579ee052f367 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 11 Apr 2019 16:36:42 +0200
Subject: bridge: broute: make broute a real ebtables table

This makes broute a normal ebtables table, hooking at PREROUTING.
The broute hook is removed.

It uses skb->cb to signal to bridge rx handler that the skb should be
routed instead of being bridged.

This change is backwards compatible with ebtables as no userspace visible
parts are changed.

This means we can also remove the !ops test in ebt_register_table,
it was only there for broute table sake.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/if_bridge.h             |  3 --
 net/bridge/br_input.c                 | 18 +++-------
 net/bridge/br_private.h               |  3 ++
 net/bridge/netfilter/ebtable_broute.c | 63 ++++++++++++++++++++++++-----------
 net/bridge/netfilter/ebtables.c       |  7 +---
 5 files changed, 52 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 627b788ba0ff..ef0819ced0fc 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -56,9 +56,6 @@ struct br_ip_list {
 
 extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
 
-typedef int br_should_route_hook_t(struct sk_buff *skb);
-extern br_should_route_hook_t __rcu *br_should_route_hook;
-
 #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
 int br_multicast_list_adjacent(struct net_device *dev,
 			       struct list_head *br_ip_list);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 4ac34fb5f943..e0aacfedcfe1 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -24,10 +24,6 @@
 #include "br_private.h"
 #include "br_private_tunnel.h"
 
-/* Hook for brouter */
-br_should_route_hook_t __rcu *br_should_route_hook __read_mostly;
-EXPORT_SYMBOL(br_should_route_hook);
-
 static int
 br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
@@ -234,6 +230,10 @@ static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb)
 		verdict = nf_hook_entry_hookfn(&e->hooks[i], skb, &state);
 		switch (verdict & NF_VERDICT_MASK) {
 		case NF_ACCEPT:
+			if (BR_INPUT_SKB_CB(skb)->br_netfilter_broute) {
+				*pskb = skb;
+				return RX_HANDLER_PASS;
+			}
 			break;
 		case NF_DROP:
 			kfree_skb(skb);
@@ -265,7 +265,6 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 	struct net_bridge_port *p;
 	struct sk_buff *skb = *pskb;
 	const unsigned char *dest = eth_hdr(skb)->h_dest;
-	br_should_route_hook_t *rhook;
 
 	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
 		return RX_HANDLER_PASS;
@@ -341,15 +340,6 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 forward:
 	switch (p->state) {
 	case BR_STATE_FORWARDING:
-		rhook = rcu_dereference(br_should_route_hook);
-		if (rhook) {
-			if ((*rhook)(skb)) {
-				*pskb = skb;
-				return RX_HANDLER_PASS;
-			}
-			dest = eth_hdr(skb)->h_dest;
-		}
-		/* fall through */
 	case BR_STATE_LEARNING:
 		if (ether_addr_equal(p->br->dev->dev_addr, dest))
 			skb->pkt_type = PACKET_HOST;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e7110a6e2b7e..4bea2f11da9b 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -433,6 +433,9 @@ struct br_input_skb_cb {
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
 	u8 vlan_filtered:1;
 #endif
+#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE
+	u8 br_netfilter_broute:1;
+#endif
 
 #ifdef CONFIG_NET_SWITCHDEV
 	int offload_fwd_mark;
diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c
index 276b60262981..ec2652a459da 100644
--- a/net/bridge/netfilter/ebtable_broute.c
+++ b/net/bridge/netfilter/ebtable_broute.c
@@ -15,6 +15,8 @@
 #include <linux/module.h>
 #include <linux/if_bridge.h>
 
+#include "../br_private.h"
+
 /* EBT_ACCEPT means the frame will be bridged
  * EBT_DROP means the frame will be routed
  */
@@ -48,30 +50,63 @@ static const struct ebt_table broute_table = {
 	.me		= THIS_MODULE,
 };
 
-static int ebt_broute(struct sk_buff *skb)
+static unsigned int ebt_broute(void *priv, struct sk_buff *skb,
+			       const struct nf_hook_state *s)
 {
+	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
 	struct nf_hook_state state;
+	unsigned char *dest;
 	int ret;
 
+	if (!p || p->state != BR_STATE_FORWARDING)
+		return NF_ACCEPT;
+
 	nf_hook_state_init(&state, NF_BR_BROUTING,
-			   NFPROTO_BRIDGE, skb->dev, NULL, NULL,
-			   dev_net(skb->dev), NULL);
+			   NFPROTO_BRIDGE, s->in, NULL, NULL,
+			   s->net, NULL);
 
 	ret = ebt_do_table(skb, &state, state.net->xt.broute_table);
-	if (ret == NF_DROP)
-		return 1; /* route it */
-	return 0; /* bridge it */
+
+	if (ret != NF_DROP)
+		return ret;
+
+	/* DROP in ebtables -t broute means that the
+	 * skb should be routed, not bridged.
+	 * This is awkward, but can't be changed for compatibility
+	 * reasons.
+	 *
+	 * We map DROP to ACCEPT and set the ->br_netfilter_broute flag.
+	 */
+	BR_INPUT_SKB_CB(skb)->br_netfilter_broute = 1;
+
+	/* undo PACKET_HOST mangling done in br_input in case the dst
+	 * address matches the logical bridge but not the port.
+	 */
+	dest = eth_hdr(skb)->h_dest;
+	if (skb->pkt_type == PACKET_HOST &&
+	    !ether_addr_equal(skb->dev->dev_addr, dest) &&
+	     ether_addr_equal(p->br->dev->dev_addr, dest))
+		skb->pkt_type = PACKET_OTHERHOST;
+
+	return NF_ACCEPT;
 }
 
+static const struct nf_hook_ops ebt_ops_broute = {
+	.hook		= ebt_broute,
+	.pf		= NFPROTO_BRIDGE,
+	.hooknum	= NF_BR_PRE_ROUTING,
+	.priority	= NF_BR_PRI_FIRST,
+};
+
 static int __net_init broute_net_init(struct net *net)
 {
-	return ebt_register_table(net, &broute_table, NULL,
+	return ebt_register_table(net, &broute_table, &ebt_ops_broute,
 				  &net->xt.broute_table);
 }
 
 static void __net_exit broute_net_exit(struct net *net)
 {
-	ebt_unregister_table(net, net->xt.broute_table, NULL);
+	ebt_unregister_table(net, net->xt.broute_table, &ebt_ops_broute);
 }
 
 static struct pernet_operations broute_net_ops = {
@@ -81,21 +116,11 @@ static struct pernet_operations broute_net_ops = {
 
 static int __init ebtable_broute_init(void)
 {
-	int ret;
-
-	ret = register_pernet_subsys(&broute_net_ops);
-	if (ret < 0)
-		return ret;
-	/* see br_input.c */
-	RCU_INIT_POINTER(br_should_route_hook,
-			   (br_should_route_hook_t *)ebt_broute);
-	return 0;
+	return register_pernet_subsys(&broute_net_ops);
 }
 
 static void __exit ebtable_broute_fini(void)
 {
-	RCU_INIT_POINTER(br_should_route_hook, NULL);
-	synchronize_net();
 	unregister_pernet_subsys(&broute_net_ops);
 }
 
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index eb15891f8b9f..383f0328ff68 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1221,10 +1221,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
 	mutex_unlock(&ebt_mutex);
 
 	WRITE_ONCE(*res, table);
-
-	if (!ops)
-		return 0;
-
 	ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
 	if (ret) {
 		__ebt_unregister_table(net, table);
@@ -1248,8 +1244,7 @@ out:
 void ebt_unregister_table(struct net *net, struct ebt_table *table,
 			  const struct nf_hook_ops *ops)
 {
-	if (ops)
-		nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+	nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
 	__ebt_unregister_table(net, table);
 }
 
-- 
cgit v1.2.3


From 013b96ec64616b57fc631b304dfcecc5bc288f90 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Thu, 11 Apr 2019 15:02:07 -0700
Subject: sctp: Pass sk_buff_head explicitly to sctp_ulpq_tail_event().

Now the SKB list implementation assumption can be removed.

And now that we know that the list head is always non-NULL
we can remove the code blocks dealing with that as well.

Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/ulpqueue.h  |  2 +-
 net/sctp/stream_interleave.c |  2 +-
 net/sctp/ulpqueue.c          | 29 +++++++++++------------------
 3 files changed, 13 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/ulpqueue.h b/include/net/sctp/ulpqueue.h
index bb0ecba3db2b..f4ac7117ff29 100644
--- a/include/net/sctp/ulpqueue.h
+++ b/include/net/sctp/ulpqueue.h
@@ -59,7 +59,7 @@ void sctp_ulpq_free(struct sctp_ulpq *);
 int sctp_ulpq_tail_data(struct sctp_ulpq *, struct sctp_chunk *, gfp_t);
 
 /* Add a new event for propagation to the ULP. */
-int sctp_ulpq_tail_event(struct sctp_ulpq *, struct sctp_ulpevent *ev);
+int sctp_ulpq_tail_event(struct sctp_ulpq *, struct sk_buff_head *skb_list);
 
 /* Renege previously received chunks.  */
 void sctp_ulpq_renege(struct sctp_ulpq *, struct sctp_chunk *, gfp_t);
diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c
index 2c50627bdfdb..25e0b7e5189c 100644
--- a/net/sctp/stream_interleave.c
+++ b/net/sctp/stream_interleave.c
@@ -1317,7 +1317,7 @@ static int do_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *even
 
 	skb_queue_head_init(&temp);
 	__skb_queue_tail(&temp, sctp_event2skb(event));
-	return sctp_ulpq_tail_event(ulpq, event);
+	return sctp_ulpq_tail_event(ulpq, &temp);
 }
 
 static struct sctp_stream_interleave sctp_stream_interleave_0 = {
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index a698f1a509bf..7cdc3623fa35 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -130,7 +130,7 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 	 */
 	if (event) {
 		event_eor = (event->msg_flags & MSG_EOR) ? 1 : 0;
-		sctp_ulpq_tail_event(ulpq, event);
+		sctp_ulpq_tail_event(ulpq, &temp);
 	}
 
 	return event_eor;
@@ -194,18 +194,17 @@ static int sctp_ulpq_clear_pd(struct sctp_ulpq *ulpq)
 	return sctp_clear_pd(ulpq->asoc->base.sk, ulpq->asoc);
 }
 
-/* If the SKB of 'event' is on a list, it is the first such member
- * of that list.
- */
-int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
+int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sk_buff_head *skb_list)
 {
 	struct sock *sk = ulpq->asoc->base.sk;
 	struct sctp_sock *sp = sctp_sk(sk);
-	struct sk_buff_head *queue, *skb_list;
-	struct sk_buff *skb = sctp_event2skb(event);
+	struct sctp_ulpevent *event;
+	struct sk_buff_head *queue;
+	struct sk_buff *skb;
 	int clear_pd = 0;
 
-	skb_list = (struct sk_buff_head *) skb->prev;
+	skb = __skb_peek(skb_list);
+	event = sctp_skb2event(skb);
 
 	/* If the socket is just going to throw this away, do not
 	 * even try to deliver it.
@@ -258,13 +257,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		}
 	}
 
-	/* If we are harvesting multiple skbs they will be
-	 * collected on a list.
-	 */
-	if (skb_list)
-		skb_queue_splice_tail_init(skb_list, queue);
-	else
-		__skb_queue_tail(queue, skb);
+	skb_queue_splice_tail_init(skb_list, queue);
 
 	/* Did we just complete partial delivery and need to get
 	 * rolling again?  Move pending data to the receive
@@ -757,7 +750,7 @@ static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq)
 		 * sctp_ulpevent for  very first SKB on the  temp' list.
 		 */
 		if (event)
-			sctp_ulpq_tail_event(ulpq, event);
+			sctp_ulpq_tail_event(ulpq, &temp);
 	}
 }
 
@@ -957,7 +950,7 @@ static void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid)
 	if (event) {
 		/* see if we have more ordered that we can deliver */
 		sctp_ulpq_retrieve_ordered(ulpq, event);
-		sctp_ulpq_tail_event(ulpq, event);
+		sctp_ulpq_tail_event(ulpq, &temp);
 	}
 }
 
@@ -1087,7 +1080,7 @@ void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq,
 
 			skb_queue_head_init(&temp);
 			__skb_queue_tail(&temp, sctp_event2skb(event));
-			sctp_ulpq_tail_event(ulpq, event);
+			sctp_ulpq_tail_event(ulpq, &temp);
 			sctp_ulpq_set_pd(ulpq);
 			return;
 		}
-- 
cgit v1.2.3


From 7b146cebe30cb481b0f70d85779da938da818637 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 27 Feb 2019 12:59:24 -0800
Subject: bpf: Sysctl hook

Containerized applications may run as root and it may create problems
for whole host. Specifically such applications may change a sysctl and
affect applications in other containers.

Furthermore in existing infrastructure it may not be possible to just
completely disable writing to sysctl, instead such a process should be
gradual with ability to log what sysctl are being changed by a
container, investigate, limit the set of writable sysctl to currently
used ones (so that new ones can not be changed) and eventually reduce
this set to zero.

The patch introduces new program type BPF_PROG_TYPE_CGROUP_SYSCTL and
attach type BPF_CGROUP_SYSCTL to solve these problems on cgroup basis.

New program type has access to following minimal context:
	struct bpf_sysctl {
		__u32	write;
	};

Where @write indicates whether sysctl is being read (= 0) or written (=
1).

Helpers to access sysctl name and value will be introduced separately.

BPF_CGROUP_SYSCTL attach point is added to sysctl code right before
passing control to ctl_table->proc_handler so that BPF program can
either allow or deny access to sysctl.

Suggested-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 fs/proc/proc_sysctl.c      |  5 +++
 include/linux/bpf-cgroup.h | 18 +++++++++
 include/linux/bpf_types.h  |  1 +
 include/linux/filter.h     |  8 ++++
 include/uapi/linux/bpf.h   |  9 +++++
 kernel/bpf/cgroup.c        | 92 ++++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c       |  7 ++++
 kernel/bpf/verifier.c      |  1 +
 8 files changed, 141 insertions(+)

(limited to 'include')

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index d65390727541..e01b02150340 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -13,6 +13,7 @@
 #include <linux/namei.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/bpf-cgroup.h>
 #include "internal.h"
 
 static const struct dentry_operations proc_sys_dentry_operations;
@@ -588,6 +589,10 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
 	if (!table->proc_handler)
 		goto out;
 
+	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write);
+	if (error)
+		goto out;
+
 	/* careful: calling conventions are nasty here */
 	res = count;
 	error = table->proc_handler(table, write, buf, &res, ppos);
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index a4c644c1c091..b1c45da20a26 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -17,6 +17,8 @@ struct bpf_map;
 struct bpf_prog;
 struct bpf_sock_ops_kern;
 struct bpf_cgroup_storage;
+struct ctl_table;
+struct ctl_table_header;
 
 #ifdef CONFIG_CGROUP_BPF
 
@@ -109,6 +111,10 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 				      short access, enum bpf_attach_type type);
 
+int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
+				   struct ctl_table *table, int write,
+				   enum bpf_attach_type type);
+
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
 {
@@ -253,6 +259,17 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 									      \
 	__ret;								      \
 })
+
+
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write)			       \
+({									       \
+	int __ret = 0;							       \
+	if (cgroup_bpf_enabled)						       \
+		__ret = __cgroup_bpf_run_filter_sysctl(head, table, write,     \
+						       BPF_CGROUP_SYSCTL);     \
+	__ret;								       \
+})
+
 int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 			   enum bpf_prog_type ptype, struct bpf_prog *prog);
 int cgroup_bpf_prog_detach(const union bpf_attr *attr,
@@ -321,6 +338,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write) ({ 0; })
 
 #define for_each_cgroup_storage_type(stype) for (; false; )
 
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 08bf2f1fe553..d26991a16894 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -28,6 +28,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
 #endif
 #ifdef CONFIG_CGROUP_BPF
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl)
 #endif
 #ifdef CONFIG_BPF_LIRC_MODE2
 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 6074aa064b54..a17732057880 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -33,6 +33,8 @@ struct bpf_prog_aux;
 struct xdp_rxq_info;
 struct xdp_buff;
 struct sock_reuseport;
+struct ctl_table;
+struct ctl_table_header;
 
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function
@@ -1177,4 +1179,10 @@ struct bpf_sock_ops_kern {
 					 */
 };
 
+struct bpf_sysctl_kern {
+	struct ctl_table_header *head;
+	struct ctl_table *table;
+	int write;
+};
+
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2e96d0b4bf65..cc2a2466d5f3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -167,6 +167,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LIRC_MODE2,
 	BPF_PROG_TYPE_SK_REUSEPORT,
 	BPF_PROG_TYPE_FLOW_DISSECTOR,
+	BPF_PROG_TYPE_CGROUP_SYSCTL,
 };
 
 enum bpf_attach_type {
@@ -188,6 +189,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_UDP6_SENDMSG,
 	BPF_LIRC_MODE2,
 	BPF_FLOW_DISSECTOR,
+	BPF_CGROUP_SYSCTL,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -3308,4 +3310,11 @@ struct bpf_line_info {
 struct bpf_spin_lock {
 	__u32	val;
 };
+
+struct bpf_sysctl {
+	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
+				 * Allows 1,2,4-byte read, but no write.
+				 */
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index f6cd38746df2..610491b5f0aa 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -11,7 +11,9 @@
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 #include <linux/cgroup.h>
+#include <linux/filter.h>
 #include <linux/slab.h>
+#include <linux/sysctl.h>
 #include <linux/bpf.h>
 #include <linux/bpf-cgroup.h>
 #include <net/sock.h>
@@ -768,3 +770,93 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
 	.get_func_proto		= cgroup_dev_func_proto,
 	.is_valid_access	= cgroup_dev_is_valid_access,
 };
+
+/**
+ * __cgroup_bpf_run_filter_sysctl - Run a program on sysctl
+ *
+ * @head: sysctl table header
+ * @table: sysctl table
+ * @write: sysctl is being read (= 0) or written (= 1)
+ * @type: type of program to be executed
+ *
+ * Program is run when sysctl is being accessed, either read or written, and
+ * can allow or deny such access.
+ *
+ * This function will return %-EPERM if an attached program is found and
+ * returned value != 1 during execution. In all other cases 0 is returned.
+ */
+int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
+				   struct ctl_table *table, int write,
+				   enum bpf_attach_type type)
+{
+	struct bpf_sysctl_kern ctx = {
+		.head = head,
+		.table = table,
+		.write = write,
+	};
+	struct cgroup *cgrp;
+	int ret;
+
+	rcu_read_lock();
+	cgrp = task_dfl_cgroup(current);
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);
+	rcu_read_unlock();
+
+	return ret == 1 ? 0 : -EPERM;
+}
+EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
+
+static const struct bpf_func_proto *
+sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	return cgroup_base_func_proto(func_id, prog);
+}
+
+static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,
+				   const struct bpf_prog *prog,
+				   struct bpf_insn_access_aux *info)
+{
+	const int size_default = sizeof(__u32);
+
+	if (off < 0 || off + size > sizeof(struct bpf_sysctl) ||
+	    off % size || type != BPF_READ)
+		return false;
+
+	switch (off) {
+	case offsetof(struct bpf_sysctl, write):
+		bpf_ctx_record_field_size(info, size_default);
+		return bpf_ctx_narrow_access_ok(off, size, size_default);
+	default:
+		return false;
+	}
+}
+
+static u32 sysctl_convert_ctx_access(enum bpf_access_type type,
+				     const struct bpf_insn *si,
+				     struct bpf_insn *insn_buf,
+				     struct bpf_prog *prog, u32 *target_size)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct bpf_sysctl, write):
+		*insn++ = BPF_LDX_MEM(
+			BPF_SIZE(si->code), si->dst_reg, si->src_reg,
+			bpf_target_off(struct bpf_sysctl_kern, write,
+				       FIELD_SIZEOF(struct bpf_sysctl_kern,
+						    write),
+				       target_size));
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
+const struct bpf_verifier_ops cg_sysctl_verifier_ops = {
+	.get_func_proto		= sysctl_func_proto,
+	.is_valid_access	= sysctl_is_valid_access,
+	.convert_ctx_access	= sysctl_convert_ctx_access,
+};
+
+const struct bpf_prog_ops cg_sysctl_prog_ops = {
+};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d995eedfdd16..92c9b8a32b50 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1888,6 +1888,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	case BPF_FLOW_DISSECTOR:
 		ptype = BPF_PROG_TYPE_FLOW_DISSECTOR;
 		break;
+	case BPF_CGROUP_SYSCTL:
+		ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1966,6 +1969,9 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		return lirc_prog_detach(attr);
 	case BPF_FLOW_DISSECTOR:
 		return skb_flow_dissector_bpf_prog_detach(attr);
+	case BPF_CGROUP_SYSCTL:
+		ptype = BPF_PROG_TYPE_CGROUP_SYSCTL;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1999,6 +2005,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_UDP6_SENDMSG:
 	case BPF_CGROUP_SOCK_OPS:
 	case BPF_CGROUP_DEVICE:
+	case BPF_CGROUP_SYSCTL:
 		break;
 	case BPF_LIRC_MODE2:
 		return lirc_prog_query(attr, uattr);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f25b7c9c20ba..20808e3c95a8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5267,6 +5267,7 @@ static int check_return_code(struct bpf_verifier_env *env)
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 	case BPF_PROG_TYPE_SOCK_OPS:
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
+	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 		break;
 	default:
 		return 0;
-- 
cgit v1.2.3


From 808649fb787d918a48a360a668ee4ee9023f0c11 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 27 Feb 2019 13:28:48 -0800
Subject: bpf: Introduce bpf_sysctl_get_name helper

Add bpf_sysctl_get_name() helper to copy sysctl name (/proc/sys/ entry)
into provided by BPF_PROG_TYPE_CGROUP_SYSCTL program buffer.

By default full name (w/o /proc/sys/) is copied, e.g. "net/ipv4/tcp_mem".

If BPF_F_SYSCTL_BASE_NAME flag is set, only base name will be copied,
e.g. "tcp_mem".

Documentation for the new helper is provided in bpf.h UAPI.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h | 22 ++++++++++++++-
 kernel/bpf/cgroup.c      | 70 +++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 90 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index cc2a2466d5f3..9c8a2f3ccb9b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2506,6 +2506,22 @@ union bpf_attr {
  * 	Return
  * 		0 if iph and th are a valid SYN cookie ACK, or a negative error
  * 		otherwise.
+ *
+ * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags)
+ *	Description
+ *		Get name of sysctl in /proc/sys/ and copy it into provided by
+ *		program buffer *buf* of size *buf_len*.
+ *
+ *		The buffer is always NUL terminated, unless it's zero-sized.
+ *
+ *		If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is
+ *		copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name
+ *		only (e.g. "tcp_mem").
+ *	Return
+ *		Number of character copied (not including the trailing NUL).
+ *
+ *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ *		truncated name in this case).
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2608,7 +2624,8 @@ union bpf_attr {
 	FN(skb_ecn_set_ce),		\
 	FN(get_listener_sock),		\
 	FN(skc_lookup_tcp),		\
-	FN(tcp_check_syncookie),
+	FN(tcp_check_syncookie),	\
+	FN(sysctl_get_name),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2681,6 +2698,9 @@ enum bpf_func_id {
 					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
 					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
+/* BPF_FUNC_sysctl_get_name flags. */
+#define BPF_F_SYSCTL_BASE_NAME		(1ULL << 0)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 610491b5f0aa..a68387043244 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -14,6 +14,7 @@
 #include <linux/filter.h>
 #include <linux/slab.h>
 #include <linux/sysctl.h>
+#include <linux/string.h>
 #include <linux/bpf.h>
 #include <linux/bpf-cgroup.h>
 #include <net/sock.h>
@@ -806,10 +807,77 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
 
+static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,
+			      size_t *lenp)
+{
+	ssize_t tmp_ret = 0, ret;
+
+	if (dir->header.parent) {
+		tmp_ret = sysctl_cpy_dir(dir->header.parent, bufp, lenp);
+		if (tmp_ret < 0)
+			return tmp_ret;
+	}
+
+	ret = strscpy(*bufp, dir->header.ctl_table[0].procname, *lenp);
+	if (ret < 0)
+		return ret;
+	*bufp += ret;
+	*lenp -= ret;
+	ret += tmp_ret;
+
+	/* Avoid leading slash. */
+	if (!ret)
+		return ret;
+
+	tmp_ret = strscpy(*bufp, "/", *lenp);
+	if (tmp_ret < 0)
+		return tmp_ret;
+	*bufp += tmp_ret;
+	*lenp -= tmp_ret;
+
+	return ret + tmp_ret;
+}
+
+BPF_CALL_4(bpf_sysctl_get_name, struct bpf_sysctl_kern *, ctx, char *, buf,
+	   size_t, buf_len, u64, flags)
+{
+	ssize_t tmp_ret = 0, ret;
+
+	if (!buf)
+		return -EINVAL;
+
+	if (!(flags & BPF_F_SYSCTL_BASE_NAME)) {
+		if (!ctx->head)
+			return -EINVAL;
+		tmp_ret = sysctl_cpy_dir(ctx->head->parent, &buf, &buf_len);
+		if (tmp_ret < 0)
+			return tmp_ret;
+	}
+
+	ret = strscpy(buf, ctx->table->procname, buf_len);
+
+	return ret < 0 ? ret : tmp_ret + ret;
+}
+
+static const struct bpf_func_proto bpf_sysctl_get_name_proto = {
+	.func		= bpf_sysctl_get_name,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
-	return cgroup_base_func_proto(func_id, prog);
+	switch (func_id) {
+	case BPF_FUNC_sysctl_get_name:
+		return &bpf_sysctl_get_name_proto;
+	default:
+		return cgroup_base_func_proto(func_id, prog);
+	}
 }
 
 static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,
-- 
cgit v1.2.3


From 1d11b3016cec4ed9770b98e82a61708c8f4926e7 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Thu, 28 Feb 2019 19:22:15 -0800
Subject: bpf: Introduce bpf_sysctl_get_current_value helper

Add bpf_sysctl_get_current_value() helper to copy current sysctl value
into provided by BPF_PROG_TYPE_CGROUP_SYSCTL program buffer.

It provides same string as user space can see by reading corresponding
file in /proc/sys/, including new line, etc.

Documentation for the new helper is provided in bpf.h UAPI.

Since current value is kept in ctl_table->data in a parsed form,
ctl_table->proc_handler() with write=0 is called to read that data and
convert it to a string. Such a string can later be parsed by a program
using helpers that will be introduced separately.

Unfortunately it's not trivial to provide API to access parsed data due to
variety of data representations (string, intvec, uintvec, ulongvec,
custom structures, even NULL, etc). Instead it's assumed that user know
how to handle specific sysctl they're interested in and appropriate
helpers can be used.

Since ctl_table->proc_handler() expects __user buffer, conversion to
__user happens for kernel allocated one where the value is stored.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/filter.h   |  2 ++
 include/uapi/linux/bpf.h | 22 +++++++++++++++-
 kernel/bpf/cgroup.c      | 65 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 88 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index a17732057880..f254ff92819f 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1182,6 +1182,8 @@ struct bpf_sock_ops_kern {
 struct bpf_sysctl_kern {
 	struct ctl_table_header *head;
 	struct ctl_table *table;
+	void *cur_val;
+	size_t cur_len;
 	int write;
 };
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9c8a2f3ccb9b..063543afa359 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2522,6 +2522,25 @@ union bpf_attr {
  *
  *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
  *		truncated name in this case).
+ *
+ * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ *	Description
+ *		Get current value of sysctl as it is presented in /proc/sys
+ *		(incl. newline, etc), and copy it as a string into provided
+ *		by program buffer *buf* of size *buf_len*.
+ *
+ *		The whole value is copied, no matter what file position user
+ *		space issued e.g. sys_read at.
+ *
+ *		The buffer is always NUL terminated, unless it's zero-sized.
+ *	Return
+ *		Number of character copied (not including the trailing NUL).
+ *
+ *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ *		truncated name in this case).
+ *
+ *		**-EINVAL** if current value was unavailable, e.g. because
+ *		sysctl is uninitialized and read returns -EIO for it.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2625,7 +2644,8 @@ union bpf_attr {
 	FN(get_listener_sock),		\
 	FN(skc_lookup_tcp),		\
 	FN(tcp_check_syncookie),	\
-	FN(sysctl_get_name),
+	FN(sysctl_get_name),		\
+	FN(sysctl_get_current_value),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index a68387043244..c6b2cf29a54b 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -794,15 +794,37 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 		.head = head,
 		.table = table,
 		.write = write,
+		.cur_val = NULL,
+		.cur_len = PAGE_SIZE,
 	};
 	struct cgroup *cgrp;
 	int ret;
 
+	ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL);
+	if (ctx.cur_val) {
+		mm_segment_t old_fs;
+		loff_t pos = 0;
+
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		if (table->proc_handler(table, 0, (void __user *)ctx.cur_val,
+					&ctx.cur_len, &pos)) {
+			/* Let BPF program decide how to proceed. */
+			ctx.cur_len = 0;
+		}
+		set_fs(old_fs);
+	} else {
+		/* Let BPF program decide how to proceed. */
+		ctx.cur_len = 0;
+	}
+
 	rcu_read_lock();
 	cgrp = task_dfl_cgroup(current);
 	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);
 	rcu_read_unlock();
 
+	kfree(ctx.cur_val);
+
 	return ret == 1 ? 0 : -EPERM;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
@@ -869,12 +891,55 @@ static const struct bpf_func_proto bpf_sysctl_get_name_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+static int copy_sysctl_value(char *dst, size_t dst_len, char *src,
+			     size_t src_len)
+{
+	if (!dst)
+		return -EINVAL;
+
+	if (!dst_len)
+		return -E2BIG;
+
+	if (!src || !src_len) {
+		memset(dst, 0, dst_len);
+		return -EINVAL;
+	}
+
+	memcpy(dst, src, min(dst_len, src_len));
+
+	if (dst_len > src_len) {
+		memset(dst + src_len, '\0', dst_len - src_len);
+		return src_len;
+	}
+
+	dst[dst_len - 1] = '\0';
+
+	return -E2BIG;
+}
+
+BPF_CALL_3(bpf_sysctl_get_current_value, struct bpf_sysctl_kern *, ctx,
+	   char *, buf, size_t, buf_len)
+{
+	return copy_sysctl_value(buf, buf_len, ctx->cur_val, ctx->cur_len);
+}
+
+static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = {
+	.func		= bpf_sysctl_get_current_value,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *
 sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_sysctl_get_name:
 		return &bpf_sysctl_get_name_proto;
+	case BPF_FUNC_sysctl_get_current_value:
+		return &bpf_sysctl_get_current_value_proto;
 	default:
 		return cgroup_base_func_proto(func_id, prog);
 	}
-- 
cgit v1.2.3


From 4e63acdff864654cee0ac5aaeda3913798ee78f6 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Thu, 7 Mar 2019 18:38:43 -0800
Subject: bpf: Introduce bpf_sysctl_{get,set}_new_value helpers

Add helpers to work with new value being written to sysctl by user
space.

bpf_sysctl_get_new_value() copies value being written to sysctl into
provided buffer.

bpf_sysctl_set_new_value() overrides new value being written by user
space with a one from provided buffer. Buffer should contain string
representation of the value, similar to what can be seen in /proc/sys/.

Both helpers can be used only on sysctl write.

File position matters and can be managed by an interface that will be
introduced separately. E.g. if user space calls sys_write to a file in
/proc/sys/ at file position = X, where X > 0, then the value set by
bpf_sysctl_set_new_value() will be written starting from X. If program
wants to override whole value with specified buffer, file position has
to be set to zero.

Documentation for the new helpers is provided in bpf.h UAPI.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 fs/proc/proc_sysctl.c      | 22 ++++++++++---
 include/linux/bpf-cgroup.h |  8 +++--
 include/linux/filter.h     |  3 ++
 include/uapi/linux/bpf.h   | 38 +++++++++++++++++++++-
 kernel/bpf/cgroup.c        | 81 +++++++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 142 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index e01b02150340..023101c6f0d7 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -570,8 +570,8 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
 	struct inode *inode = file_inode(filp);
 	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+	void *new_buf = NULL;
 	ssize_t error;
-	size_t res;
 
 	if (IS_ERR(head))
 		return PTR_ERR(head);
@@ -589,15 +589,27 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
 	if (!table->proc_handler)
 		goto out;
 
-	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write);
+	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count,
+					   &new_buf);
 	if (error)
 		goto out;
 
 	/* careful: calling conventions are nasty here */
-	res = count;
-	error = table->proc_handler(table, write, buf, &res, ppos);
+	if (new_buf) {
+		mm_segment_t old_fs;
+
+		old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		error = table->proc_handler(table, write, (void __user *)new_buf,
+					    &count, ppos);
+		set_fs(old_fs);
+		kfree(new_buf);
+	} else {
+		error = table->proc_handler(table, write, buf, &count, ppos);
+	}
+
 	if (!error)
-		error = res;
+		error = count;
 out:
 	sysctl_head_finish(head);
 
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index b1c45da20a26..1e97271f9a10 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -113,7 +113,8 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   enum bpf_attach_type type);
+				   void __user *buf, size_t *pcount,
+				   void **new_buf, enum bpf_attach_type type);
 
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
@@ -261,11 +262,12 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 })
 
 
-#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write)			       \
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, nbuf)       \
 ({									       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled)						       \
 		__ret = __cgroup_bpf_run_filter_sysctl(head, table, write,     \
+						       buf, count, nbuf,       \
 						       BPF_CGROUP_SYSCTL);     \
 	__ret;								       \
 })
@@ -338,7 +340,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,nbuf) ({ 0; })
 
 #define for_each_cgroup_storage_type(stype) for (; false; )
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index f254ff92819f..a23653f9460c 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1184,6 +1184,9 @@ struct bpf_sysctl_kern {
 	struct ctl_table *table;
 	void *cur_val;
 	size_t cur_len;
+	void *new_val;
+	size_t new_len;
+	int new_updated;
 	int write;
 };
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 063543afa359..547b8258d731 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2541,6 +2541,40 @@ union bpf_attr {
  *
  *		**-EINVAL** if current value was unavailable, e.g. because
  *		sysctl is uninitialized and read returns -EIO for it.
+ *
+ * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len)
+ *	Description
+ *		Get new value being written by user space to sysctl (before
+ *		the actual write happens) and copy it as a string into
+ *		provided by program buffer *buf* of size *buf_len*.
+ *
+ *		User space may write new value at file position > 0.
+ *
+ *		The buffer is always NUL terminated, unless it's zero-sized.
+ *	Return
+ *		Number of character copied (not including the trailing NUL).
+ *
+ *		**-E2BIG** if the buffer wasn't big enough (*buf* will contain
+ *		truncated name in this case).
+ *
+ *		**-EINVAL** if sysctl is being read.
+ *
+ * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len)
+ *	Description
+ *		Override new value being written by user space to sysctl with
+ *		value provided by program in buffer *buf* of size *buf_len*.
+ *
+ *		*buf* should contain a string in same form as provided by user
+ *		space on sysctl write.
+ *
+ *		User space may write new value at file position > 0. To override
+ *		the whole sysctl value file position should be set to zero.
+ *	Return
+ *		0 on success.
+ *
+ *		**-E2BIG** if the *buf_len* is too big.
+ *
+ *		**-EINVAL** if sysctl is being read.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2645,7 +2679,9 @@ union bpf_attr {
 	FN(skc_lookup_tcp),		\
 	FN(tcp_check_syncookie),	\
 	FN(sysctl_get_name),		\
-	FN(sysctl_get_current_value),
+	FN(sysctl_get_current_value),	\
+	FN(sysctl_get_new_value),	\
+	FN(sysctl_set_new_value),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index c6b2cf29a54b..ba4e21986760 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -778,6 +778,13 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  * @head: sysctl table header
  * @table: sysctl table
  * @write: sysctl is being read (= 0) or written (= 1)
+ * @buf: pointer to buffer passed by user space
+ * @pcount: value-result argument: value is size of buffer pointed to by @buf,
+ *	result is size of @new_buf if program set new value, initial value
+ *	otherwise
+ * @new_buf: pointer to pointer to new buffer that will be allocated if program
+ *	overrides new value provided by user space on sysctl write
+ *	NOTE: it's caller responsibility to free *new_buf if it was set
  * @type: type of program to be executed
  *
  * Program is run when sysctl is being accessed, either read or written, and
@@ -788,7 +795,8 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  */
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
-				   enum bpf_attach_type type)
+				   void __user *buf, size_t *pcount,
+				   void **new_buf, enum bpf_attach_type type)
 {
 	struct bpf_sysctl_kern ctx = {
 		.head = head,
@@ -796,6 +804,9 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 		.write = write,
 		.cur_val = NULL,
 		.cur_len = PAGE_SIZE,
+		.new_val = NULL,
+		.new_len = 0,
+		.new_updated = 0,
 	};
 	struct cgroup *cgrp;
 	int ret;
@@ -818,6 +829,18 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 		ctx.cur_len = 0;
 	}
 
+	if (write && buf && *pcount) {
+		/* BPF program should be able to override new value with a
+		 * buffer bigger than provided by user.
+		 */
+		ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL);
+		ctx.new_len = min(PAGE_SIZE, *pcount);
+		if (!ctx.new_val ||
+		    copy_from_user(ctx.new_val, buf, ctx.new_len))
+			/* Let BPF program decide how to proceed. */
+			ctx.new_len = 0;
+	}
+
 	rcu_read_lock();
 	cgrp = task_dfl_cgroup(current);
 	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);
@@ -825,6 +848,13 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 
 	kfree(ctx.cur_val);
 
+	if (ret == 1 && ctx.new_updated) {
+		*new_buf = ctx.new_val;
+		*pcount = ctx.new_len;
+	} else {
+		kfree(ctx.new_val);
+	}
+
 	return ret == 1 ? 0 : -EPERM;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl);
@@ -932,6 +962,51 @@ static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = {
 	.arg3_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_3(bpf_sysctl_get_new_value, struct bpf_sysctl_kern *, ctx, char *, buf,
+	   size_t, buf_len)
+{
+	if (!ctx->write) {
+		if (buf && buf_len)
+			memset(buf, '\0', buf_len);
+		return -EINVAL;
+	}
+	return copy_sysctl_value(buf, buf_len, ctx->new_val, ctx->new_len);
+}
+
+static const struct bpf_func_proto bpf_sysctl_get_new_value_proto = {
+	.func		= bpf_sysctl_get_new_value,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_3(bpf_sysctl_set_new_value, struct bpf_sysctl_kern *, ctx,
+	   const char *, buf, size_t, buf_len)
+{
+	if (!ctx->write || !ctx->new_val || !ctx->new_len || !buf || !buf_len)
+		return -EINVAL;
+
+	if (buf_len > PAGE_SIZE - 1)
+		return -E2BIG;
+
+	memcpy(ctx->new_val, buf, buf_len);
+	ctx->new_len = buf_len;
+	ctx->new_updated = 1;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = {
+	.func		= bpf_sysctl_set_new_value,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+};
+
 static const struct bpf_func_proto *
 sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -940,6 +1015,10 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sysctl_get_name_proto;
 	case BPF_FUNC_sysctl_get_current_value:
 		return &bpf_sysctl_get_current_value_proto;
+	case BPF_FUNC_sysctl_get_new_value:
+		return &bpf_sysctl_get_new_value_proto;
+	case BPF_FUNC_sysctl_set_new_value:
+		return &bpf_sysctl_set_new_value_proto;
 	default:
 		return cgroup_base_func_proto(func_id, prog);
 	}
-- 
cgit v1.2.3


From e1550bfe0de47e30484ba91de1e50a91ec1c31f5 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Thu, 7 Mar 2019 18:50:52 -0800
Subject: bpf: Add file_pos field to bpf_sysctl ctx

Add file_pos field to bpf_sysctl context to read and write sysctl file
position at which sysctl is being accessed (read or written).

The field can be used to e.g. override whole sysctl value on write to
sysctl even when sys_write is called by user space with file_pos > 0. Or
BPF program may reject such accesses.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 fs/proc/proc_sysctl.c      |  2 +-
 include/linux/bpf-cgroup.h |  9 ++++----
 include/linux/filter.h     |  3 +++
 include/uapi/linux/bpf.h   |  3 +++
 kernel/bpf/cgroup.c        | 54 +++++++++++++++++++++++++++++++++++++++++++---
 5 files changed, 63 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 023101c6f0d7..2d61e5e8c863 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -590,7 +590,7 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
 		goto out;
 
 	error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, &count,
-					   &new_buf);
+					   ppos, &new_buf);
 	if (error)
 		goto out;
 
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 1e97271f9a10..cb3c6b3b89c8 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -114,7 +114,8 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
 				   void __user *buf, size_t *pcount,
-				   void **new_buf, enum bpf_attach_type type);
+				   loff_t *ppos, void **new_buf,
+				   enum bpf_attach_type type);
 
 static inline enum bpf_cgroup_storage_type cgroup_storage_type(
 	struct bpf_map *map)
@@ -262,12 +263,12 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key,
 })
 
 
-#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, nbuf)       \
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, buf, count, pos, nbuf)  \
 ({									       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled)						       \
 		__ret = __cgroup_bpf_run_filter_sysctl(head, table, write,     \
-						       buf, count, nbuf,       \
+						       buf, count, pos, nbuf,  \
 						       BPF_CGROUP_SYSCTL);     \
 	__ret;								       \
 })
@@ -340,7 +341,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,nbuf) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; })
 
 #define for_each_cgroup_storage_type(stype) for (; false; )
 
diff --git a/include/linux/filter.h b/include/linux/filter.h
index a23653f9460c..fb0edad75971 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1188,6 +1188,9 @@ struct bpf_sysctl_kern {
 	size_t new_len;
 	int new_updated;
 	int write;
+	loff_t *ppos;
+	/* Temporary "register" for indirect stores to ppos. */
+	u64 tmp_reg;
 };
 
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 547b8258d731..89976de909af 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3391,6 +3391,9 @@ struct bpf_sysctl {
 	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
 				 * Allows 1,2,4-byte read, but no write.
 				 */
+	__u32	file_pos;	/* Sysctl file position to read from, write to.
+				 * Allows 1,2,4-byte read an 4-byte write.
+				 */
 };
 
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ba4e21986760..b2adf22139b3 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -782,6 +782,9 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  * @pcount: value-result argument: value is size of buffer pointed to by @buf,
  *	result is size of @new_buf if program set new value, initial value
  *	otherwise
+ * @ppos: value-result argument: value is position at which read from or write
+ *	to sysctl is happening, result is new position if program overrode it,
+ *	initial value otherwise
  * @new_buf: pointer to pointer to new buffer that will be allocated if program
  *	overrides new value provided by user space on sysctl write
  *	NOTE: it's caller responsibility to free *new_buf if it was set
@@ -796,12 +799,14 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
 				   struct ctl_table *table, int write,
 				   void __user *buf, size_t *pcount,
-				   void **new_buf, enum bpf_attach_type type)
+				   loff_t *ppos, void **new_buf,
+				   enum bpf_attach_type type)
 {
 	struct bpf_sysctl_kern ctx = {
 		.head = head,
 		.table = table,
 		.write = write,
+		.ppos = ppos,
 		.cur_val = NULL,
 		.cur_len = PAGE_SIZE,
 		.new_val = NULL,
@@ -1030,14 +1035,22 @@ static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,
 {
 	const int size_default = sizeof(__u32);
 
-	if (off < 0 || off + size > sizeof(struct bpf_sysctl) ||
-	    off % size || type != BPF_READ)
+	if (off < 0 || off + size > sizeof(struct bpf_sysctl) || off % size)
 		return false;
 
 	switch (off) {
 	case offsetof(struct bpf_sysctl, write):
+		if (type != BPF_READ)
+			return false;
 		bpf_ctx_record_field_size(info, size_default);
 		return bpf_ctx_narrow_access_ok(off, size, size_default);
+	case offsetof(struct bpf_sysctl, file_pos):
+		if (type == BPF_READ) {
+			bpf_ctx_record_field_size(info, size_default);
+			return bpf_ctx_narrow_access_ok(off, size, size_default);
+		} else {
+			return size == size_default;
+		}
 	default:
 		return false;
 	}
@@ -1059,6 +1072,41 @@ static u32 sysctl_convert_ctx_access(enum bpf_access_type type,
 						    write),
 				       target_size));
 		break;
+	case offsetof(struct bpf_sysctl, file_pos):
+		/* ppos is a pointer so it should be accessed via indirect
+		 * loads and stores. Also for stores additional temporary
+		 * register is used since neither src_reg nor dst_reg can be
+		 * overridden.
+		 */
+		if (type == BPF_WRITE) {
+			int treg = BPF_REG_9;
+
+			if (si->src_reg == treg || si->dst_reg == treg)
+				--treg;
+			if (si->src_reg == treg || si->dst_reg == treg)
+				--treg;
+			*insn++ = BPF_STX_MEM(
+				BPF_DW, si->dst_reg, treg,
+				offsetof(struct bpf_sysctl_kern, tmp_reg));
+			*insn++ = BPF_LDX_MEM(
+				BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
+				treg, si->dst_reg,
+				offsetof(struct bpf_sysctl_kern, ppos));
+			*insn++ = BPF_STX_MEM(
+				BPF_SIZEOF(u32), treg, si->src_reg, 0);
+			*insn++ = BPF_LDX_MEM(
+				BPF_DW, treg, si->dst_reg,
+				offsetof(struct bpf_sysctl_kern, tmp_reg));
+		} else {
+			*insn++ = BPF_LDX_MEM(
+				BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos),
+				si->dst_reg, si->src_reg,
+				offsetof(struct bpf_sysctl_kern, ppos));
+			*insn++ = BPF_LDX_MEM(
+				BPF_SIZE(si->code), si->dst_reg, si->dst_reg, 0);
+		}
+		*target_size = sizeof(u32);
+		break;
 	}
 
 	return insn - insn_buf;
-- 
cgit v1.2.3


From 57c3bb725a3dd97d960d7e1cd0845d88de53217f Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Mon, 18 Mar 2019 16:57:10 -0700
Subject: bpf: Introduce ARG_PTR_TO_{INT,LONG} arg types

Currently the way to pass result from BPF helper to BPF program is to
provide memory area defined by pointer and size: func(void *, size_t).

It works great for generic use-case, but for simple types, such as int,
it's overkill and consumes two arguments when it could use just one.

Introduce new argument types ARG_PTR_TO_INT and ARG_PTR_TO_LONG to be
able to pass result from helper to program via pointer to int and long
correspondingly: func(int *) or func(long *).

New argument types are similar to ARG_PTR_TO_MEM with the following
differences:
* they don't require corresponding ARG_CONST_SIZE argument, predefined
  access sizes are used instead (32bit for int, 64bit for long);
* it's possible to use more than one such an argument in a helper;
* provided pointers have to be aligned.

It's easy to introduce similar ARG_PTR_TO_CHAR and ARG_PTR_TO_SHORT
argument types. It's not done due to lack of use-case though.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h   |  2 ++
 kernel/bpf/verifier.c | 29 +++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e4d4c1771ab0..fd06ada941ad 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -202,6 +202,8 @@ enum bpf_arg_type {
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
+	ARG_PTR_TO_INT,		/* pointer to int */
+	ARG_PTR_TO_LONG,	/* pointer to long */
 };
 
 /* type of values returned from helper functions */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 20808e3c95a8..15ab6fa817ce 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2462,6 +2462,22 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type)
 	       type == ARG_CONST_SIZE_OR_ZERO;
 }
 
+static bool arg_type_is_int_ptr(enum bpf_arg_type type)
+{
+	return type == ARG_PTR_TO_INT ||
+	       type == ARG_PTR_TO_LONG;
+}
+
+static int int_ptr_type_to_size(enum bpf_arg_type type)
+{
+	if (type == ARG_PTR_TO_INT)
+		return sizeof(u32);
+	else if (type == ARG_PTR_TO_LONG)
+		return sizeof(u64);
+
+	return -EINVAL;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			  enum bpf_arg_type arg_type,
 			  struct bpf_call_arg_meta *meta)
@@ -2554,6 +2570,12 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			 type != expected_type)
 			goto err_type;
 		meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
+	} else if (arg_type_is_int_ptr(arg_type)) {
+		expected_type = PTR_TO_STACK;
+		if (!type_is_pkt_pointer(type) &&
+		    type != PTR_TO_MAP_VALUE &&
+		    type != expected_type)
+			goto err_type;
 	} else {
 		verbose(env, "unsupported arg_type %d\n", arg_type);
 		return -EFAULT;
@@ -2635,6 +2657,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		err = check_helper_mem_access(env, regno - 1,
 					      reg->umax_value,
 					      zero_size_allowed, meta);
+	} else if (arg_type_is_int_ptr(arg_type)) {
+		int size = int_ptr_type_to_size(arg_type);
+
+		err = check_helper_mem_access(env, regno, size, false, meta);
+		if (err)
+			return err;
+		err = check_ptr_alignment(env, reg, 0, size, true);
 	}
 
 	return err;
-- 
cgit v1.2.3


From d7a4cb9b6705a89937d12c8158a35a3145dc967a Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Mon, 18 Mar 2019 17:55:26 -0700
Subject: bpf: Introduce bpf_strtol and bpf_strtoul helpers

Add bpf_strtol and bpf_strtoul to convert a string to long and unsigned
long correspondingly. It's similar to user space strtol(3) and
strtoul(3) with a few changes to the API:

* instead of NUL-terminated C string the helpers expect buffer and
  buffer length;

* resulting long or unsigned long is returned in a separate
  result-argument;

* return value is used to indicate success or failure, on success number
  of consumed bytes is returned that can be used to identify position to
  read next if the buffer is expected to contain multiple integers;

* instead of *base* argument, *flags* is used that provides base in 5
  LSB, other bits are reserved for future use;

* number of supported bases is limited.

Documentation for the new helpers is provided in bpf.h UAPI.

The helpers are made available to BPF_PROG_TYPE_CGROUP_SYSCTL programs to
be able to convert string input to e.g. "ulongvec" output.

E.g. "net/ipv4/tcp_mem" consists of three ulong integers. They can be
parsed by calling to bpf_strtoul three times.

Implementation notes:

Implementation includes "../../lib/kstrtox.h" to reuse integer parsing
functions. It's done exactly same way as fs/proc/base.c already does.

Unfortunately existing kstrtoX function can't be used directly since
they fail if any invalid character is present right after integer in the
string. Existing simple_strtoX functions can't be used either since
they're obsolete and don't handle overflow properly.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h      |   2 +
 include/uapi/linux/bpf.h |  51 +++++++++++++++++-
 kernel/bpf/cgroup.c      |   4 ++
 kernel/bpf/helpers.c     | 131 +++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 187 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index fd06ada941ad..f15432d90728 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -989,6 +989,8 @@ extern const struct bpf_func_proto bpf_sk_redirect_map_proto;
 extern const struct bpf_func_proto bpf_spin_lock_proto;
 extern const struct bpf_func_proto bpf_spin_unlock_proto;
 extern const struct bpf_func_proto bpf_get_local_storage_proto;
+extern const struct bpf_func_proto bpf_strtol_proto;
+extern const struct bpf_func_proto bpf_strtoul_proto;
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 89976de909af..c26be24fd5e2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2575,6 +2575,53 @@ union bpf_attr {
  *		**-E2BIG** if the *buf_len* is too big.
  *
  *		**-EINVAL** if sysctl is being read.
+ *
+ * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res)
+ *	Description
+ *		Convert the initial part of the string from buffer *buf* of
+ *		size *buf_len* to a long integer according to the given base
+ *		and save the result in *res*.
+ *
+ *		The string may begin with an arbitrary amount of white space
+ *		(as determined by isspace(3)) followed by a single optional '-'
+ *		sign.
+ *
+ *		Five least significant bits of *flags* encode base, other bits
+ *		are currently unused.
+ *
+ *		Base must be either 8, 10, 16 or 0 to detect it automatically
+ *		similar to user space strtol(3).
+ *	Return
+ *		Number of characters consumed on success. Must be positive but
+ *		no more than buf_len.
+ *
+ *		**-EINVAL** if no valid digits were found or unsupported base
+ *		was provided.
+ *
+ *		**-ERANGE** if resulting value was out of range.
+ *
+ * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res)
+ *	Description
+ *		Convert the initial part of the string from buffer *buf* of
+ *		size *buf_len* to an unsigned long integer according to the
+ *		given base and save the result in *res*.
+ *
+ *		The string may begin with an arbitrary amount of white space
+ *		(as determined by isspace(3)).
+ *
+ *		Five least significant bits of *flags* encode base, other bits
+ *		are currently unused.
+ *
+ *		Base must be either 8, 10, 16 or 0 to detect it automatically
+ *		similar to user space strtoul(3).
+ *	Return
+ *		Number of characters consumed on success. Must be positive but
+ *		no more than buf_len.
+ *
+ *		**-EINVAL** if no valid digits were found or unsupported base
+ *		was provided.
+ *
+ *		**-ERANGE** if resulting value was out of range.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2681,7 +2728,9 @@ union bpf_attr {
 	FN(sysctl_get_name),		\
 	FN(sysctl_get_current_value),	\
 	FN(sysctl_get_new_value),	\
-	FN(sysctl_set_new_value),
+	FN(sysctl_set_new_value),	\
+	FN(strtol),			\
+	FN(strtoul),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index b2adf22139b3..789d4ab2336e 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1016,6 +1016,10 @@ static const struct bpf_func_proto *
 sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
+	case BPF_FUNC_strtol:
+		return &bpf_strtol_proto;
+	case BPF_FUNC_strtoul:
+		return &bpf_strtoul_proto;
 	case BPF_FUNC_sysctl_get_name:
 		return &bpf_sysctl_get_name_proto;
 	case BPF_FUNC_sysctl_get_current_value:
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index a411fc17d265..4266ffde07ca 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -18,6 +18,9 @@
 #include <linux/sched.h>
 #include <linux/uidgid.h>
 #include <linux/filter.h>
+#include <linux/ctype.h>
+
+#include "../../lib/kstrtox.h"
 
 /* If kernel subsystem is allowing eBPF programs to call this function,
  * inside its own verifier_ops->get_func_proto() callback it should return
@@ -363,4 +366,132 @@ const struct bpf_func_proto bpf_get_local_storage_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 #endif
+
+#define BPF_STRTOX_BASE_MASK 0x1F
+
+static int __bpf_strtoull(const char *buf, size_t buf_len, u64 flags,
+			  unsigned long long *res, bool *is_negative)
+{
+	unsigned int base = flags & BPF_STRTOX_BASE_MASK;
+	const char *cur_buf = buf;
+	size_t cur_len = buf_len;
+	unsigned int consumed;
+	size_t val_len;
+	char str[64];
+
+	if (!buf || !buf_len || !res || !is_negative)
+		return -EINVAL;
+
+	if (base != 0 && base != 8 && base != 10 && base != 16)
+		return -EINVAL;
+
+	if (flags & ~BPF_STRTOX_BASE_MASK)
+		return -EINVAL;
+
+	while (cur_buf < buf + buf_len && isspace(*cur_buf))
+		++cur_buf;
+
+	*is_negative = (cur_buf < buf + buf_len && *cur_buf == '-');
+	if (*is_negative)
+		++cur_buf;
+
+	consumed = cur_buf - buf;
+	cur_len -= consumed;
+	if (!cur_len)
+		return -EINVAL;
+
+	cur_len = min(cur_len, sizeof(str) - 1);
+	memcpy(str, cur_buf, cur_len);
+	str[cur_len] = '\0';
+	cur_buf = str;
+
+	cur_buf = _parse_integer_fixup_radix(cur_buf, &base);
+	val_len = _parse_integer(cur_buf, base, res);
+
+	if (val_len & KSTRTOX_OVERFLOW)
+		return -ERANGE;
+
+	if (val_len == 0)
+		return -EINVAL;
+
+	cur_buf += val_len;
+	consumed += cur_buf - str;
+
+	return consumed;
+}
+
+static int __bpf_strtoll(const char *buf, size_t buf_len, u64 flags,
+			 long long *res)
+{
+	unsigned long long _res;
+	bool is_negative;
+	int err;
+
+	err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative);
+	if (err < 0)
+		return err;
+	if (is_negative) {
+		if ((long long)-_res > 0)
+			return -ERANGE;
+		*res = -_res;
+	} else {
+		if ((long long)_res < 0)
+			return -ERANGE;
+		*res = _res;
+	}
+	return err;
+}
+
+BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags,
+	   long *, res)
+{
+	long long _res;
+	int err;
+
+	err = __bpf_strtoll(buf, buf_len, flags, &_res);
+	if (err < 0)
+		return err;
+	if (_res != (long)_res)
+		return -ERANGE;
+	*res = _res;
+	return err;
+}
+
+const struct bpf_func_proto bpf_strtol_proto = {
+	.func		= bpf_strtol,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_LONG,
+};
+
+BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags,
+	   unsigned long *, res)
+{
+	unsigned long long _res;
+	bool is_negative;
+	int err;
+
+	err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative);
+	if (err < 0)
+		return err;
+	if (is_negative)
+		return -EINVAL;
+	if (_res != (unsigned long)_res)
+		return -ERANGE;
+	*res = _res;
+	return err;
+}
+
+const struct bpf_func_proto bpf_strtoul_proto = {
+	.func		= bpf_strtoul,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_LONG,
+};
 #endif
-- 
cgit v1.2.3


From e4edbe3c1f44c84f319149aeb998e7e36b3b897f Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Fri, 12 Apr 2019 11:52:07 +1000
Subject: rhashtable: fix some __rcu annotation errors

With these annotations, the rhashtable now gets no
warnings when compiled with "C=1" for sparse checking.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 11 ++++++-----
 lib/rhashtable.c           |  4 ++--
 2 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 460c0eaf6b96..2711cbf01b64 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -40,7 +40,7 @@
  * the chain.  To avoid dereferencing this pointer without clearing
  * the bit first, we use an opaque 'struct rhash_lock_head *' for the
  * pointer stored in the bucket.  This struct needs to be defined so
- * that rcu_derefernce() works on it, but it has no content so a
+ * that rcu_dereference() works on it, but it has no content so a
  * cast is needed for it to be useful.  This ensures it isn't
  * used by mistake with clearing the lock bit first.
  */
@@ -130,10 +130,10 @@ static inline void rht_unlock(struct bucket_table *tbl,
 }
 
 static inline void rht_assign_unlock(struct bucket_table *tbl,
-				     struct rhash_lock_head **bkt,
+				     struct rhash_lock_head __rcu **bkt,
 				     struct rhash_head *obj)
 {
-	struct rhash_head **p = (struct rhash_head **)bkt;
+	struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
 
 	lock_map_release(&tbl->dep_map);
 	rcu_assign_pointer(*p, obj);
@@ -556,6 +556,7 @@ static inline struct rhash_head *__rhashtable_lookup(
 	};
 	struct rhash_lock_head __rcu * const *bkt;
 	struct bucket_table *tbl;
+	struct rhash_head __rcu *head;
 	struct rhash_head *he;
 	unsigned int hash;
 
@@ -564,8 +565,8 @@ restart:
 	hash = rht_key_hashfn(ht, tbl, key, params);
 	bkt = rht_bucket(tbl, hash);
 	do {
-		he = rht_ptr(rht_dereference_bucket_rcu(*bkt, tbl, hash));
-		rht_for_each_rcu_from(he, he, tbl, hash) {
+		head = rht_ptr(rht_dereference_bucket_rcu(*bkt, tbl, hash));
+		rht_for_each_rcu_from(he, head, tbl, hash) {
 			if (params.obj_cmpfn ?
 			    params.obj_cmpfn(&arg, rht_obj(ht, he)) :
 			    rhashtable_compare(&arg, rht_obj(ht, he)))
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 9c84f5cef69c..e387ceb00e86 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -223,7 +223,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht,
 	struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl);
 	int err = -EAGAIN;
 	struct rhash_head *head, *next, *entry;
-	struct rhash_head **pprev = NULL;
+	struct rhash_head __rcu **pprev = NULL;
 	unsigned int new_hash;
 
 	if (new_tbl->nest)
@@ -486,7 +486,7 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 		.ht = ht,
 		.key = key,
 	};
-	struct rhash_head **pprev = NULL;
+	struct rhash_head __rcu **pprev = NULL;
 	struct rhash_head *head;
 	int elasticity;
 
-- 
cgit v1.2.3


From c5783311a1248c437614d438b69c5f31fe483ecb Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Fri, 12 Apr 2019 11:52:08 +1000
Subject: rhashtable: reorder some inline functions and macros.

This patch only moves some code around, it doesn't
change the code at all.
A subsequent patch will benefit from this as it needs
to add calls to functions which are now defined before the
call-site, but weren't before.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 142 ++++++++++++++++++++++-----------------------
 1 file changed, 71 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 2711cbf01b64..c504cd820736 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -87,77 +87,6 @@ struct bucket_table {
 	struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp;
 };
 
-/*
- * We lock a bucket by setting BIT(1) in the pointer - this is always
- * zero in real pointers and in the nulls marker.
- * bit_spin_locks do not handle contention well, but the whole point
- * of the hashtable design is to achieve minimum per-bucket contention.
- * A nested hash table might not have a bucket pointer.  In that case
- * we cannot get a lock.  For remove and replace the bucket cannot be
- * interesting and doesn't need locking.
- * For insert we allocate the bucket if this is the last bucket_table,
- * and then take the lock.
- * Sometimes we unlock a bucket by writing a new pointer there.  In that
- * case we don't need to unlock, but we do need to reset state such as
- * local_bh. For that we have rht_assign_unlock().  As rcu_assign_pointer()
- * provides the same release semantics that bit_spin_unlock() provides,
- * this is safe.
- */
-
-static inline void rht_lock(struct bucket_table *tbl,
-			    struct rhash_lock_head **bkt)
-{
-	local_bh_disable();
-	bit_spin_lock(1, (unsigned long *)bkt);
-	lock_map_acquire(&tbl->dep_map);
-}
-
-static inline void rht_lock_nested(struct bucket_table *tbl,
-				   struct rhash_lock_head **bucket,
-				   unsigned int subclass)
-{
-	local_bh_disable();
-	bit_spin_lock(1, (unsigned long *)bucket);
-	lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_);
-}
-
-static inline void rht_unlock(struct bucket_table *tbl,
-			      struct rhash_lock_head **bkt)
-{
-	lock_map_release(&tbl->dep_map);
-	bit_spin_unlock(1, (unsigned long *)bkt);
-	local_bh_enable();
-}
-
-static inline void rht_assign_unlock(struct bucket_table *tbl,
-				     struct rhash_lock_head __rcu **bkt,
-				     struct rhash_head *obj)
-{
-	struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
-
-	lock_map_release(&tbl->dep_map);
-	rcu_assign_pointer(*p, obj);
-	preempt_enable();
-	__release(bitlock);
-	local_bh_enable();
-}
-
-/*
- * If 'p' is a bucket head and might be locked:
- *   rht_ptr() returns the address without the lock bit.
- *   rht_ptr_locked() returns the address WITH the lock bit.
- */
-static inline struct rhash_head __rcu *rht_ptr(const struct rhash_lock_head *p)
-{
-	return (void *)(((unsigned long)p) & ~BIT(1));
-}
-
-static inline struct rhash_lock_head __rcu *rht_ptr_locked(const
-							   struct rhash_head *p)
-{
-	return (void *)(((unsigned long)p) | BIT(1));
-}
-
 /*
  * NULLS_MARKER() expects a hash value with the low
  * bits mostly likely to be significant, and it discards
@@ -372,6 +301,77 @@ static inline struct rhash_lock_head __rcu **rht_bucket_insert(
 				     &tbl->buckets[hash];
 }
 
+/*
+ * We lock a bucket by setting BIT(1) in the pointer - this is always
+ * zero in real pointers and in the nulls marker.
+ * bit_spin_locks do not handle contention well, but the whole point
+ * of the hashtable design is to achieve minimum per-bucket contention.
+ * A nested hash table might not have a bucket pointer.  In that case
+ * we cannot get a lock.  For remove and replace the bucket cannot be
+ * interesting and doesn't need locking.
+ * For insert we allocate the bucket if this is the last bucket_table,
+ * and then take the lock.
+ * Sometimes we unlock a bucket by writing a new pointer there.  In that
+ * case we don't need to unlock, but we do need to reset state such as
+ * local_bh. For that we have rht_assign_unlock().  As rcu_assign_pointer()
+ * provides the same release semantics that bit_spin_unlock() provides,
+ * this is safe.
+ */
+
+static inline void rht_lock(struct bucket_table *tbl,
+			    struct rhash_lock_head **bkt)
+{
+	local_bh_disable();
+	bit_spin_lock(1, (unsigned long *)bkt);
+	lock_map_acquire(&tbl->dep_map);
+}
+
+static inline void rht_lock_nested(struct bucket_table *tbl,
+				   struct rhash_lock_head **bucket,
+				   unsigned int subclass)
+{
+	local_bh_disable();
+	bit_spin_lock(1, (unsigned long *)bucket);
+	lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_);
+}
+
+static inline void rht_unlock(struct bucket_table *tbl,
+			      struct rhash_lock_head **bkt)
+{
+	lock_map_release(&tbl->dep_map);
+	bit_spin_unlock(1, (unsigned long *)bkt);
+	local_bh_enable();
+}
+
+/*
+ * If 'p' is a bucket head and might be locked:
+ *   rht_ptr() returns the address without the lock bit.
+ *   rht_ptr_locked() returns the address WITH the lock bit.
+ */
+static inline struct rhash_head __rcu *rht_ptr(const struct rhash_lock_head *p)
+{
+	return (void *)(((unsigned long)p) & ~BIT(1));
+}
+
+static inline struct rhash_lock_head __rcu *rht_ptr_locked(const
+							   struct rhash_head *p)
+{
+	return (void *)(((unsigned long)p) | BIT(1));
+}
+
+static inline void rht_assign_unlock(struct bucket_table *tbl,
+				     struct rhash_lock_head __rcu **bkt,
+				     struct rhash_head *obj)
+{
+	struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
+
+	lock_map_release(&tbl->dep_map);
+	rcu_assign_pointer(*p, obj);
+	preempt_enable();
+	__release(bitlock);
+	local_bh_enable();
+}
+
 /**
  * rht_for_each_from - iterate over hash chain from given head
  * @pos:	the &struct rhash_head to use as a loop cursor.
-- 
cgit v1.2.3


From adc6a3ab192eb40fb9d8b093c87d9aa785af4513 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Fri, 12 Apr 2019 11:52:08 +1000
Subject: rhashtable: move dereference inside rht_ptr()

Rather than dereferencing a pointer to a bucket and then passing the
result to rht_ptr(), we now pass in the pointer and do the dereference
in rht_ptr().

This requires that we pass in the tbl and hash as well to support RCU
checks, and means that the various rht_for_each functions can expect a
pointer that can be dereferenced without further care.

There are two places where we dereference a bucket pointer
where there is no testable protection - in each case we know
that we much have exclusive access without having taken a lock.
The previous code used rht_dereference() to pretend that holding
the mutex provided protects, but holding the mutex never provides
protection for accessing buckets.

So instead introduce rht_ptr_exclusive() that can be used when
there is known to be exclusive access without holding any locks.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 69 ++++++++++++++++++++++++++++------------------
 lib/rhashtable.c           | 12 ++++----
 lib/test_rhashtable.c      |  2 +-
 3 files changed, 49 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index c504cd820736..b54e6436547e 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -344,12 +344,28 @@ static inline void rht_unlock(struct bucket_table *tbl,
 }
 
 /*
- * If 'p' is a bucket head and might be locked:
- *   rht_ptr() returns the address without the lock bit.
- *   rht_ptr_locked() returns the address WITH the lock bit.
+ * Where 'bkt' is a bucket and might be locked:
+ *   rht_ptr() dereferences that pointer and clears the lock bit.
+ *   rht_ptr_exclusive() dereferences in a context where exclusive
+ *            access is guaranteed, such as when destroying the table.
  */
-static inline struct rhash_head __rcu *rht_ptr(const struct rhash_lock_head *p)
+static inline struct rhash_head *rht_ptr(
+	struct rhash_lock_head __rcu * const *bkt,
+	struct bucket_table *tbl,
+	unsigned int hash)
 {
+	const struct rhash_lock_head *p =
+		rht_dereference_bucket_rcu(*bkt, tbl, hash);
+
+	return (void *)(((unsigned long)p) & ~BIT(1));
+}
+
+static inline struct rhash_head *rht_ptr_exclusive(
+	struct rhash_lock_head __rcu * const *bkt)
+{
+	const struct rhash_lock_head *p =
+		rcu_dereference_protected(*bkt, 1);
+
 	return (void *)(((unsigned long)p) & ~BIT(1));
 }
 
@@ -380,8 +396,8 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
  * @hash:	the hash value / bucket index
  */
 #define rht_for_each_from(pos, head, tbl, hash) \
-	for (pos = rht_dereference_bucket(head, tbl, hash); \
-	     !rht_is_a_nulls(pos); \
+	for (pos = head;			\
+	     !rht_is_a_nulls(pos);		\
 	     pos = rht_dereference_bucket((pos)->next, tbl, hash))
 
 /**
@@ -391,7 +407,8 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
  * @hash:	the hash value / bucket index
  */
 #define rht_for_each(pos, tbl, hash) \
-	rht_for_each_from(pos, rht_ptr(*rht_bucket(tbl, hash)), tbl, hash)
+	rht_for_each_from(pos, rht_ptr(rht_bucket(tbl, hash), tbl, hash),  \
+			  tbl, hash)
 
 /**
  * rht_for_each_entry_from - iterate over hash chain from given head
@@ -403,7 +420,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
  * @member:	name of the &struct rhash_head within the hashable struct.
  */
 #define rht_for_each_entry_from(tpos, pos, head, tbl, hash, member)	\
-	for (pos = rht_dereference_bucket(head, tbl, hash);		\
+	for (pos = head;						\
 	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	\
 	     pos = rht_dereference_bucket((pos)->next, tbl, hash))
 
@@ -416,8 +433,9 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
  * @member:	name of the &struct rhash_head within the hashable struct.
  */
 #define rht_for_each_entry(tpos, pos, tbl, hash, member)		\
-	rht_for_each_entry_from(tpos, pos, rht_ptr(*rht_bucket(tbl, hash)), \
-				    tbl, hash, member)
+	rht_for_each_entry_from(tpos, pos,				\
+				rht_ptr(rht_bucket(tbl, hash), tbl, hash), \
+				tbl, hash, member)
 
 /**
  * rht_for_each_entry_safe - safely iterate over hash chain of given type
@@ -432,8 +450,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
  * remove the loop cursor from the list.
  */
 #define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member)	      \
-	for (pos = rht_dereference_bucket(rht_ptr(*rht_bucket(tbl, hash)),    \
-					  tbl, hash),			      \
+	for (pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash),		      \
 	     next = !rht_is_a_nulls(pos) ?				      \
 		       rht_dereference_bucket(pos->next, tbl, hash) : NULL;   \
 	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	      \
@@ -454,7 +471,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
  */
 #define rht_for_each_rcu_from(pos, head, tbl, hash)			\
 	for (({barrier(); }),						\
-	     pos = rht_dereference_bucket_rcu(head, tbl, hash);		\
+	     pos = head;						\
 	     !rht_is_a_nulls(pos);					\
 	     pos = rcu_dereference_raw(pos->next))
 
@@ -469,10 +486,9 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
  * traversal is guarded by rcu_read_lock().
  */
 #define rht_for_each_rcu(pos, tbl, hash)			\
-	for (({barrier(); }),						\
-	     pos = rht_ptr(rht_dereference_bucket_rcu(			\
-				   *rht_bucket(tbl, hash), tbl, hash));	\
-	     !rht_is_a_nulls(pos);					\
+	for (({barrier(); }),					\
+	     pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash);	\
+	     !rht_is_a_nulls(pos);				\
 	     pos = rcu_dereference_raw(pos->next))
 
 /**
@@ -490,7 +506,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
  */
 #define rht_for_each_entry_rcu_from(tpos, pos, head, tbl, hash, member) \
 	for (({barrier(); }),						    \
-	     pos = rht_dereference_bucket_rcu(head, tbl, hash);		    \
+	     pos = head;						    \
 	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	    \
 	     pos = rht_dereference_bucket_rcu(pos->next, tbl, hash))
 
@@ -508,8 +524,9 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
  */
 #define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member)		   \
 	rht_for_each_entry_rcu_from(tpos, pos,				   \
-					rht_ptr(*rht_bucket(tbl, hash)),   \
-					tbl, hash, member)
+				    rht_ptr(rht_bucket(tbl, hash),	   \
+					    tbl, hash),			   \
+				    tbl, hash, member)
 
 /**
  * rhl_for_each_rcu - iterate over rcu hash table list
@@ -556,7 +573,6 @@ static inline struct rhash_head *__rhashtable_lookup(
 	};
 	struct rhash_lock_head __rcu * const *bkt;
 	struct bucket_table *tbl;
-	struct rhash_head __rcu *head;
 	struct rhash_head *he;
 	unsigned int hash;
 
@@ -565,8 +581,7 @@ restart:
 	hash = rht_key_hashfn(ht, tbl, key, params);
 	bkt = rht_bucket(tbl, hash);
 	do {
-		head = rht_ptr(rht_dereference_bucket_rcu(*bkt, tbl, hash));
-		rht_for_each_rcu_from(he, head, tbl, hash) {
+		rht_for_each_rcu_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) {
 			if (params.obj_cmpfn ?
 			    params.obj_cmpfn(&arg, rht_obj(ht, he)) :
 			    rhashtable_compare(&arg, rht_obj(ht, he)))
@@ -699,7 +714,7 @@ slow_path:
 		return rhashtable_insert_slow(ht, key, obj);
 	}
 
-	rht_for_each_from(head, rht_ptr(*bkt), tbl, hash) {
+	rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) {
 		struct rhlist_head *plist;
 		struct rhlist_head *list;
 
@@ -744,7 +759,7 @@ slow_path:
 		goto slow_path;
 
 	/* Inserting at head of list makes unlocking free. */
-	head = rht_ptr(rht_dereference_bucket(*bkt, tbl, hash));
+	head = rht_ptr(bkt, tbl, hash);
 
 	RCU_INIT_POINTER(obj->next, head);
 	if (rhlist) {
@@ -971,7 +986,7 @@ static inline int __rhashtable_remove_fast_one(
 	pprev = NULL;
 	rht_lock(tbl, bkt);
 
-	rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) {
+	rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) {
 		struct rhlist_head *list;
 
 		list = container_of(he, struct rhlist_head, rhead);
@@ -1130,7 +1145,7 @@ static inline int __rhashtable_replace_fast(
 	pprev = NULL;
 	rht_lock(tbl, bkt);
 
-	rht_for_each_from(he, rht_ptr(*bkt), tbl, hash) {
+	rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) {
 		if (he != obj_old) {
 			pprev = &he->next;
 			continue;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index e387ceb00e86..237368ea98c5 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -231,7 +231,8 @@ static int rhashtable_rehash_one(struct rhashtable *ht,
 
 	err = -ENOENT;
 
-	rht_for_each_from(entry, rht_ptr(*bkt), old_tbl, old_hash) {
+	rht_for_each_from(entry, rht_ptr(bkt, old_tbl, old_hash),
+			  old_tbl, old_hash) {
 		err = 0;
 		next = rht_dereference_bucket(entry->next, old_tbl, old_hash);
 
@@ -248,8 +249,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht,
 
 	rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING);
 
-	head = rht_ptr(rht_dereference_bucket(new_tbl->buckets[new_hash],
-					      new_tbl, new_hash));
+	head = rht_ptr(new_tbl->buckets + new_hash, new_tbl, new_hash);
 
 	RCU_INIT_POINTER(entry->next, head);
 
@@ -491,7 +491,7 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 	int elasticity;
 
 	elasticity = RHT_ELASTICITY;
-	rht_for_each_from(head, rht_ptr(*bkt), tbl, hash) {
+	rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) {
 		struct rhlist_head *list;
 		struct rhlist_head *plist;
 
@@ -557,7 +557,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
 	if (unlikely(rht_grow_above_100(ht, tbl)))
 		return ERR_PTR(-EAGAIN);
 
-	head = rht_ptr(rht_dereference_bucket(*bkt, tbl, hash));
+	head = rht_ptr(bkt, tbl, hash);
 
 	RCU_INIT_POINTER(obj->next, head);
 	if (ht->rhlist) {
@@ -1139,7 +1139,7 @@ restart:
 			struct rhash_head *pos, *next;
 
 			cond_resched();
-			for (pos = rht_ptr(rht_dereference(*rht_bucket(tbl, i), ht)),
+			for (pos = rht_ptr_exclusive(rht_bucket(tbl, i)),
 			     next = !rht_is_a_nulls(pos) ?
 					rht_dereference(pos->next, ht) : NULL;
 			     !rht_is_a_nulls(pos);
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 02592c2a249c..084fe5a6ac57 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -500,7 +500,7 @@ static unsigned int __init print_ht(struct rhltable *rhlt)
 		struct rhash_head *pos, *next;
 		struct test_obj_rhl *p;
 
-		pos = rht_ptr(rht_dereference(tbl->buckets[i], ht));
+		pos = rht_ptr_exclusive(tbl->buckets + i);
 		next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL;
 
 		if (!rht_is_a_nulls(pos)) {
-- 
cgit v1.2.3


From f4712b46a529ca2da078c82d5d99d367c7ebf82b Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Fri, 12 Apr 2019 11:52:08 +1000
Subject: rhashtable: replace rht_ptr_locked() with rht_assign_locked()

The only times rht_ptr_locked() is used, it is to store a new
value in a bucket-head.  This is the only time it makes sense
to use it too.  So replace it by a function which does the
whole task:  Sets the lock bit and assigns to a bucket head.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 9 ++++++---
 lib/rhashtable.c           | 6 +++---
 2 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index b54e6436547e..882bc0fcea4b 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -316,6 +316,7 @@ static inline struct rhash_lock_head __rcu **rht_bucket_insert(
  * local_bh. For that we have rht_assign_unlock().  As rcu_assign_pointer()
  * provides the same release semantics that bit_spin_unlock() provides,
  * this is safe.
+ * When we write to a bucket without unlocking, we use rht_assign_locked().
  */
 
 static inline void rht_lock(struct bucket_table *tbl,
@@ -369,10 +370,12 @@ static inline struct rhash_head *rht_ptr_exclusive(
 	return (void *)(((unsigned long)p) & ~BIT(1));
 }
 
-static inline struct rhash_lock_head __rcu *rht_ptr_locked(const
-							   struct rhash_head *p)
+static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt,
+				     struct rhash_head *obj)
 {
-	return (void *)(((unsigned long)p) | BIT(1));
+	struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
+
+	rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(1)));
 }
 
 static inline void rht_assign_unlock(struct bucket_table *tbl,
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 237368ea98c5..ef5378efdef3 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -259,7 +259,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht,
 		rcu_assign_pointer(*pprev, next);
 	else
 		/* Need to preserved the bit lock. */
-		rcu_assign_pointer(*bkt, rht_ptr_locked(next));
+		rht_assign_locked(bkt, next);
 
 out:
 	return err;
@@ -517,7 +517,7 @@ static void *rhashtable_lookup_one(struct rhashtable *ht,
 			rcu_assign_pointer(*pprev, obj);
 		else
 			/* Need to preserve the bit lock */
-			rcu_assign_pointer(*bkt, rht_ptr_locked(obj));
+			rht_assign_locked(bkt, obj);
 
 		return NULL;
 	}
@@ -570,7 +570,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
 	/* bkt is always the head of the list, so it holds
 	 * the lock, which we need to preserve
 	 */
-	rcu_assign_pointer(*bkt, rht_ptr_locked(obj));
+	rht_assign_locked(bkt, obj);
 
 	atomic_inc(&ht->nelems);
 	if (rht_grow_above_75(ht, tbl))
-- 
cgit v1.2.3


From ca0b709d1a07b1fe1fb356d8d58f220287f85672 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Fri, 12 Apr 2019 11:52:08 +1000
Subject: rhashtable: use BIT(0) for locking.

As reported by Guenter Roeck, the new bit-locking using
BIT(1) doesn't work on the m68k architecture.  m68k only requires
2-byte alignment for words and longwords, so there is only one
unused bit in pointers to structs - We current use two, one for the
NULLS marker at the end of the linked list, and one for the bit-lock
in the head of the list.

The two uses don't need to conflict as we never need the head of the
list to be a NULLS marker - the marker is only needed to check if an
object has moved to a different table, and the bucket head cannot
move.  The NULLS marker is only needed in a ->next pointer.

As we already have different types for the bucket head pointer (struct
rhash_lock_head) and the ->next pointers (struct rhash_head), it is
fairly easy to treat the lsb differently in each.

So: Initialize buckets heads to NULL, and use the lsb for locking.
When loading the pointer from the bucket head, if it is NULL (ignoring
the lock big), report as being the expected NULLS marker.
When storing a value into a bucket head, if it is a NULLS marker,
store NULL instead.

And convert all places that used bit 1 for locking, to use bit 0.

Fixes: 8f0db018006a ("rhashtable: use bit_spin_locks to protect hash bucket.")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 35 ++++++++++++++++++++++++-----------
 lib/rhashtable.c           |  2 +-
 2 files changed, 25 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 882bc0fcea4b..f7714d3b46bd 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -35,7 +35,7 @@
  * the least significant bit set but otherwise stores the address of
  * the hash bucket.  This allows us to be be sure we've found the end
  * of the right list.
- * The value stored in the hash bucket has BIT(2) used as a lock bit.
+ * The value stored in the hash bucket has BIT(0) used as a lock bit.
  * This bit must be atomically set before any changes are made to
  * the chain.  To avoid dereferencing this pointer without clearing
  * the bit first, we use an opaque 'struct rhash_lock_head *' for the
@@ -91,15 +91,19 @@ struct bucket_table {
  * NULLS_MARKER() expects a hash value with the low
  * bits mostly likely to be significant, and it discards
  * the msb.
- * We git it an address, in which the bottom 2 bits are
+ * We give it an address, in which the bottom bit is
  * always 0, and the msb might be significant.
  * So we shift the address down one bit to align with
  * expectations and avoid losing a significant bit.
+ *
+ * We never store the NULLS_MARKER in the hash table
+ * itself as we need the lsb for locking.
+ * Instead we store a NULL
  */
 #define	RHT_NULLS_MARKER(ptr)	\
 	((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1))
 #define INIT_RHT_NULLS_HEAD(ptr)	\
-	((ptr) = RHT_NULLS_MARKER(&(ptr)))
+	((ptr) = NULL)
 
 static inline bool rht_is_a_nulls(const struct rhash_head *ptr)
 {
@@ -302,8 +306,9 @@ static inline struct rhash_lock_head __rcu **rht_bucket_insert(
 }
 
 /*
- * We lock a bucket by setting BIT(1) in the pointer - this is always
- * zero in real pointers and in the nulls marker.
+ * We lock a bucket by setting BIT(0) in the pointer - this is always
+ * zero in real pointers.  The NULLS mark is never stored in the bucket,
+ * rather we store NULL if the bucket is empty.
  * bit_spin_locks do not handle contention well, but the whole point
  * of the hashtable design is to achieve minimum per-bucket contention.
  * A nested hash table might not have a bucket pointer.  In that case
@@ -323,7 +328,7 @@ static inline void rht_lock(struct bucket_table *tbl,
 			    struct rhash_lock_head **bkt)
 {
 	local_bh_disable();
-	bit_spin_lock(1, (unsigned long *)bkt);
+	bit_spin_lock(0, (unsigned long *)bkt);
 	lock_map_acquire(&tbl->dep_map);
 }
 
@@ -332,7 +337,7 @@ static inline void rht_lock_nested(struct bucket_table *tbl,
 				   unsigned int subclass)
 {
 	local_bh_disable();
-	bit_spin_lock(1, (unsigned long *)bucket);
+	bit_spin_lock(0, (unsigned long *)bucket);
 	lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_);
 }
 
@@ -340,7 +345,7 @@ static inline void rht_unlock(struct bucket_table *tbl,
 			      struct rhash_lock_head **bkt)
 {
 	lock_map_release(&tbl->dep_map);
-	bit_spin_unlock(1, (unsigned long *)bkt);
+	bit_spin_unlock(0, (unsigned long *)bkt);
 	local_bh_enable();
 }
 
@@ -358,7 +363,9 @@ static inline struct rhash_head *rht_ptr(
 	const struct rhash_lock_head *p =
 		rht_dereference_bucket_rcu(*bkt, tbl, hash);
 
-	return (void *)(((unsigned long)p) & ~BIT(1));
+	if ((((unsigned long)p) & ~BIT(0)) == 0)
+		return RHT_NULLS_MARKER(bkt);
+	return (void *)(((unsigned long)p) & ~BIT(0));
 }
 
 static inline struct rhash_head *rht_ptr_exclusive(
@@ -367,7 +374,9 @@ static inline struct rhash_head *rht_ptr_exclusive(
 	const struct rhash_lock_head *p =
 		rcu_dereference_protected(*bkt, 1);
 
-	return (void *)(((unsigned long)p) & ~BIT(1));
+	if (!p)
+		return RHT_NULLS_MARKER(bkt);
+	return (void *)(((unsigned long)p) & ~BIT(0));
 }
 
 static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt,
@@ -375,7 +384,9 @@ static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt,
 {
 	struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
 
-	rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(1)));
+	if (rht_is_a_nulls(obj))
+		obj = NULL;
+	rcu_assign_pointer(*p, (void *)((unsigned long)obj | BIT(0)));
 }
 
 static inline void rht_assign_unlock(struct bucket_table *tbl,
@@ -384,6 +395,8 @@ static inline void rht_assign_unlock(struct bucket_table *tbl,
 {
 	struct rhash_head __rcu **p = (struct rhash_head __rcu **)bkt;
 
+	if (rht_is_a_nulls(obj))
+		obj = NULL;
 	lock_map_release(&tbl->dep_map);
 	rcu_assign_pointer(*p, obj);
 	preempt_enable();
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index ef5378efdef3..6529fe1b45c1 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -59,7 +59,7 @@ int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash)
 		return 1;
 	if (unlikely(tbl->nest))
 		return 1;
-	return bit_spin_is_locked(1, (unsigned long *)&tbl->buckets[hash]);
+	return bit_spin_is_locked(0, (unsigned long *)&tbl->buckets[hash]);
 }
 EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
 #else
-- 
cgit v1.2.3


From 9dde27de3e5efa0d032f3c891a0ca833a0d31911 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 15 Apr 2019 17:15:07 +0800
Subject: sctp: implement memory accounting on rx path

sk_forward_alloc's updating is also done on rx path, but to be consistent
we change to use sk_mem_charge() in sctp_skb_set_owner_r().

In sctp_eat_data(), it's not enough to check sctp_memory_pressure only,
which doesn't work for mem_cgroup_sockets_enabled, so we change to use
sk_under_memory_pressure().

When it's under memory pressure, sk_mem_reclaim() and sk_rmem_schedule()
should be called on both RENEGE or CHUNK DELIVERY path exit the memory
pressure status as soon as possible.

Note that sk_rmem_schedule() is using datalen to make things easy there.

Reported-by: Matteo Croce <mcroce@redhat.com>
Tested-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sctp.h |  2 +-
 net/sctp/sm_statefuns.c |  6 ++++--
 net/sctp/ulpevent.c     | 19 ++++++++-----------
 net/sctp/ulpqueue.c     |  3 ++-
 4 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 1d13ec3f2707..eefdfa5abf6e 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -421,7 +421,7 @@ static inline void sctp_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	/*
 	 * This mimics the behavior of skb_set_owner_r
 	 */
-	sk->sk_forward_alloc -= event->rmem_len;
+	sk_mem_charge(sk, event->rmem_len);
 }
 
 /* Tests if the list has one and only one entry. */
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index c9ae3404b1bb..7dfc34b28f4f 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -6412,13 +6412,15 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	 * in sctp_ulpevent_make_rcvmsg will drop the frame if we grow our
 	 * memory usage too much
 	 */
-	if (*sk->sk_prot_creator->memory_pressure) {
+	if (sk_under_memory_pressure(sk)) {
 		if (sctp_tsnmap_has_gap(map) &&
 		    (sctp_tsnmap_get_ctsn(map) + 1) == tsn) {
 			pr_debug("%s: under pressure, reneging for tsn:%u\n",
 				 __func__, tsn);
 			deliver = SCTP_CMD_RENEGE;
-		 }
+		} else {
+			sk_mem_reclaim(sk);
+		}
 	}
 
 	/*
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 8cb7d9858270..c2a7478587ab 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -634,8 +634,9 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 						gfp_t gfp)
 {
 	struct sctp_ulpevent *event = NULL;
-	struct sk_buff *skb;
-	size_t padding, len;
+	struct sk_buff *skb = chunk->skb;
+	struct sock *sk = asoc->base.sk;
+	size_t padding, datalen;
 	int rx_count;
 
 	/*
@@ -646,15 +647,12 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 	if (asoc->ep->rcvbuf_policy)
 		rx_count = atomic_read(&asoc->rmem_alloc);
 	else
-		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
+		rx_count = atomic_read(&sk->sk_rmem_alloc);
 
-	if (rx_count >= asoc->base.sk->sk_rcvbuf) {
+	datalen = ntohs(chunk->chunk_hdr->length);
 
-		if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) ||
-		    (!sk_rmem_schedule(asoc->base.sk, chunk->skb,
-				       chunk->skb->truesize)))
-			goto fail;
-	}
+	if (rx_count >= sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, datalen))
+		goto fail;
 
 	/* Clone the original skb, sharing the data.  */
 	skb = skb_clone(chunk->skb, gfp);
@@ -681,8 +679,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc,
 	 * The sender should never pad with more than 3 bytes.  The receiver
 	 * MUST ignore the padding bytes.
 	 */
-	len = ntohs(chunk->chunk_hdr->length);
-	padding = SCTP_PAD4(len) - len;
+	padding = SCTP_PAD4(datalen) - datalen;
 
 	/* Fixup cloned skb with just this chunks data.  */
 	skb_trim(skb, chunk->chunk_end - padding - skb->data);
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 7cdc3623fa35..a212fe079c07 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -1104,7 +1104,8 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk,
 			freed += sctp_ulpq_renege_frags(ulpq, needed - freed);
 	}
 	/* If able to free enough room, accept this chunk. */
-	if (freed >= needed) {
+	if (sk_rmem_schedule(asoc->base.sk, chunk->skb, needed) &&
+	    freed >= needed) {
 		int retval = sctp_ulpq_tail_data(ulpq, chunk, gfp);
 		/*
 		 * Enter partial delivery if chunk has not been
-- 
cgit v1.2.3


From bfb35c27c65fce60a12e188135ae1344d1b89e24 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Fri, 12 Apr 2019 12:27:34 +0100
Subject: bpf: fix whitespace for ENCAP_L2 defines in bpf.h

replace tab after #define with space in line with rest of definitions

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h       | 6 +++---
 tools/include/uapi/linux/bpf.h | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c26be24fd5e2..704bb69514a2 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2792,14 +2792,14 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_adjust_room flags. */
 #define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
 
-#define	BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
-#define	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
+#define BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
+#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
 
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
-#define	BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
 					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
 					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c26be24fd5e2..704bb69514a2 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2792,14 +2792,14 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_adjust_room flags. */
 #define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
 
-#define	BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
-#define	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
+#define BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
+#define BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
 
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
-#define	BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
 					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
 					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
-- 
cgit v1.2.3


From 725721a6506eea53bfde81a34e91a06d6162c216 Mon Sep 17 00:00:00 2001
From: Viet Hoang Tran <hoang.tran@uclouvain.be>
Date: Mon, 15 Apr 2019 09:54:55 +0000
Subject: bpf: allow clearing all sock_ops callback flags

The helper function bpf_sock_ops_cb_flags_set() can be used to both
set and clear the sock_ops callback flags. However, its current
behavior is not consistent. BPF program may clear a flag if more than
one were set, or replace a flag with another one, but cannot clear all
flags.

This patch also updates the documentation to clarify the ability to
clear flags of this helper function.

Signed-off-by: Hoang Tran <hoang.tran@uclouvain.be>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/uapi/linux/bpf.h | 9 ++++++++-
 net/core/filter.c        | 3 +--
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 704bb69514a2..eaf2d3284248 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1737,12 +1737,19 @@ union bpf_attr {
  * 		error if an eBPF program tries to set a callback that is not
  * 		supported in the current kernel.
  *
- * 		The supported callback values that *argval* can combine are:
+ * 		*argval* is a flag array which can combine these flags:
  *
  * 		* **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out)
  * 		* **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission)
  * 		* **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change)
  *
+ * 		Therefore, this function can be used to clear a callback flag by
+ * 		setting the appropriate bit to zero. e.g. to disable the RTO
+ * 		callback:
+ *
+ * 		**bpf_sock_ops_cb_flags_set(bpf_sock,**
+ * 			**bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)**
+ *
  * 		Here are some examples of where one could call such eBPF
  * 		program:
  *
diff --git a/net/core/filter.c b/net/core/filter.c
index bd1f51907b83..1833926a63fc 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4437,8 +4437,7 @@ BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock,
 	if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk))
 		return -EINVAL;
 
-	if (val)
-		tcp_sk(sk)->bpf_sock_ops_cb_flags = val;
+	tcp_sk(sk)->bpf_sock_ops_cb_flags = val;
 
 	return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS);
 }
-- 
cgit v1.2.3


From ba0509b6881efd0c8b26c36490cba87d8fb324c0 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 12 Apr 2019 17:07:37 +0200
Subject: net: core: introduce build_skb_around

The function build_skb() also have the responsibility to allocate and clear
the SKB structure. Introduce a new function build_skb_around(), that moves
the responsibility of allocation and clearing to the caller. This allows
caller to use kmem_cache (slab/slub) bulk allocation API.

Next patch use this function combined with kmem_cache_alloc_bulk.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/skbuff.h |  2 ++
 net/core/skbuff.c      | 71 ++++++++++++++++++++++++++++++++++++--------------
 2 files changed, 54 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a06275a618f0..e81f2b0e8a83 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1042,6 +1042,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags,
 			    int node);
 struct sk_buff *__build_skb(void *data, unsigned int frag_size);
 struct sk_buff *build_skb(void *data, unsigned int frag_size);
+struct sk_buff *build_skb_around(struct sk_buff *skb,
+				 void *data, unsigned int frag_size);
 
 /**
  * alloc_skb - allocate a network buffer
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9901f5322852..087622298d77 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -258,6 +258,33 @@ nodata:
 }
 EXPORT_SYMBOL(__alloc_skb);
 
+/* Caller must provide SKB that is memset cleared */
+static struct sk_buff *__build_skb_around(struct sk_buff *skb,
+					  void *data, unsigned int frag_size)
+{
+	struct skb_shared_info *shinfo;
+	unsigned int size = frag_size ? : ksize(data);
+
+	size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	/* Assumes caller memset cleared SKB */
+	skb->truesize = SKB_TRUESIZE(size);
+	refcount_set(&skb->users, 1);
+	skb->head = data;
+	skb->data = data;
+	skb_reset_tail_pointer(skb);
+	skb->end = skb->tail + size;
+	skb->mac_header = (typeof(skb->mac_header))~0U;
+	skb->transport_header = (typeof(skb->transport_header))~0U;
+
+	/* make sure we initialize shinfo sequentially */
+	shinfo = skb_shinfo(skb);
+	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
+	atomic_set(&shinfo->dataref, 1);
+
+	return skb;
+}
+
 /**
  * __build_skb - build a network buffer
  * @data: data buffer provided by caller
@@ -279,32 +306,15 @@ EXPORT_SYMBOL(__alloc_skb);
  */
 struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
-	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
-	unsigned int size = frag_size ? : ksize(data);
 
 	skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
-	if (!skb)
+	if (unlikely(!skb))
 		return NULL;
 
-	size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
 	memset(skb, 0, offsetof(struct sk_buff, tail));
-	skb->truesize = SKB_TRUESIZE(size);
-	refcount_set(&skb->users, 1);
-	skb->head = data;
-	skb->data = data;
-	skb_reset_tail_pointer(skb);
-	skb->end = skb->tail + size;
-	skb->mac_header = (typeof(skb->mac_header))~0U;
-	skb->transport_header = (typeof(skb->transport_header))~0U;
 
-	/* make sure we initialize shinfo sequentially */
-	shinfo = skb_shinfo(skb);
-	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
-	atomic_set(&shinfo->dataref, 1);
-
-	return skb;
+	return __build_skb_around(skb, data, frag_size);
 }
 
 /* build_skb() is wrapper over __build_skb(), that specifically
@@ -325,6 +335,29 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 }
 EXPORT_SYMBOL(build_skb);
 
+/**
+ * build_skb_around - build a network buffer around provided skb
+ * @skb: sk_buff provide by caller, must be memset cleared
+ * @data: data buffer provided by caller
+ * @frag_size: size of data, or 0 if head was kmalloced
+ */
+struct sk_buff *build_skb_around(struct sk_buff *skb,
+				 void *data, unsigned int frag_size)
+{
+	if (unlikely(!skb))
+		return NULL;
+
+	skb = __build_skb_around(skb, data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (page_is_pfmemalloc(virt_to_head_page(data)))
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
+EXPORT_SYMBOL(build_skb_around);
+
 #define NAPI_SKB_CACHE_SIZE	64
 
 struct napi_alloc_cache {
-- 
cgit v1.2.3


From b1d40991506aa9f1de310a2e74ef8e3bec6ba215 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 16 Apr 2019 14:35:59 -0700
Subject: ipv6: Rename fib6_multipath_select and pass fib6_result

Add 'struct fib6_result' to hold the fib entry and fib6_nh from a fib
lookup as separate entries, similar to what IPv4 now has with fib_result.

Rename fib6_multipath_select to fib6_select_path, pass fib6_result to
it, and set f6i and nh in the result once a path selection is done.
Call fib6_select_path unconditionally for path selection which means
moving the sibling and oif check to fib6_select_path. To handle the two
different call paths (2 only call multipath_select if flowi6_oif == 0 and
the other always calls it), add a new have_oif_match that controls the
sibling walk if relevant.

Update callers of fib6_multipath_select accordingly and have them use the
fib6_info and fib6_nh from the result.

This is needed for multipath nexthop objects where a single f6i can
point to multiple fib6_nh (similar to IPv4).

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h    | 13 ++++++----
 include/net/ipv6_stubs.h |  9 +++----
 net/core/filter.c        | 34 +++++++++++++-------------
 net/ipv6/addrconf_core.c | 11 ++++-----
 net/ipv6/af_inet6.c      |  2 +-
 net/ipv6/route.c         | 63 +++++++++++++++++++++++++-----------------------
 6 files changed, 68 insertions(+), 64 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 2e9235adfa0d..c4d818041663 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -190,6 +190,11 @@ struct rt6_info {
 	unsigned short			rt6i_nfheader_len;
 };
 
+struct fib6_result {
+	struct fib6_nh		*nh;
+	struct fib6_info	*f6i;
+};
+
 #define for_each_fib6_node_rt_rcu(fn)					\
 	for (rt = rcu_dereference((fn)->leaf); rt;			\
 	     rt = rcu_dereference(rt->fib6_next))
@@ -391,11 +396,9 @@ struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
 struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
 				    int oif, struct flowi6 *fl6, int strict);
 
-struct fib6_info *fib6_multipath_select(const struct net *net,
-					struct fib6_info *match,
-					struct flowi6 *fl6, int oif,
-					const struct sk_buff *skb, int strict);
-
+void fib6_select_path(const struct net *net, struct fib6_result *res,
+		      struct flowi6 *fl6, int oif, bool have_oif_match,
+		      const struct sk_buff *skb, int strict);
 struct fib6_node *fib6_node_lookup(struct fib6_node *root,
 				   const struct in6_addr *daddr,
 				   const struct in6_addr *saddr);
diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index 453b55bf6723..5df36d6a2613 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -14,6 +14,7 @@
 struct fib6_info;
 struct fib6_nh;
 struct fib6_config;
+struct fib6_result;
 
 /* This is ugly, ideally these symbols should be built
  * into the core kernel.
@@ -34,11 +35,9 @@ struct ipv6_stub {
 					      struct fib6_table *table,
 					      int oif, struct flowi6 *fl6,
 					      int flags);
-	struct fib6_info *(*fib6_multipath_select)(const struct net *net,
-						   struct fib6_info *f6i,
-						   struct flowi6 *fl6, int oif,
-						   const struct sk_buff *skb,
-						   int strict);
+	void (*fib6_select_path)(const struct net *net, struct fib6_result *res,
+				 struct flowi6 *fl6, int oif, bool oif_match,
+				 const struct sk_buff *skb, int strict);
 	u32 (*ip6_mtu_from_fib6)(struct fib6_info *f6i, struct in6_addr *daddr,
 				 struct in6_addr *saddr);
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 07687e2a2e66..c8dcce205872 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4679,9 +4679,9 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	struct in6_addr *src = (struct in6_addr *) params->ipv6_src;
 	struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst;
 	struct neighbour *neigh;
+	struct fib6_result res;
 	struct net_device *dev;
 	struct inet6_dev *idev;
-	struct fib6_info *f6i;
 	struct flowi6 fl6;
 	int strict = 0;
 	int oif;
@@ -4726,21 +4726,23 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		if (unlikely(!tb))
 			return BPF_FIB_LKUP_RET_NOT_FWDED;
 
-		f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
+		res.f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6,
+						       strict);
 	} else {
 		fl6.flowi6_mark = 0;
 		fl6.flowi6_secid = 0;
 		fl6.flowi6_tun_key.tun_id = 0;
 		fl6.flowi6_uid = sock_net_uid(net, NULL);
 
-		f6i = ipv6_stub->fib6_lookup(net, oif, &fl6, strict);
+		res.f6i = ipv6_stub->fib6_lookup(net, oif, &fl6, strict);
 	}
 
-	if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
+	if (unlikely(IS_ERR_OR_NULL(res.f6i) ||
+		     res.f6i == net->ipv6.fib6_null_entry))
 		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
-	if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
-		switch (f6i->fib6_type) {
+	if (unlikely(res.f6i->fib6_flags & RTF_REJECT)) {
+		switch (res.f6i->fib6_type) {
 		case RTN_BLACKHOLE:
 			return BPF_FIB_LKUP_RET_BLACKHOLE;
 		case RTN_UNREACHABLE:
@@ -4752,28 +4754,26 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		}
 	}
 
-	if (f6i->fib6_type != RTN_UNICAST)
+	if (res.f6i->fib6_type != RTN_UNICAST)
 		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
-	if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
-		f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
-						       fl6.flowi6_oif, NULL,
-						       strict);
+	ipv6_stub->fib6_select_path(net, &res, &fl6, fl6.flowi6_oif,
+				    fl6.flowi6_oif != 0, NULL, strict);
 
 	if (check_mtu) {
-		mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
+		mtu = ipv6_stub->ip6_mtu_from_fib6(res.f6i, dst, src);
 		if (params->tot_len > mtu)
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
-	if (f6i->fib6_nh.fib_nh_lws)
+	if (res.nh->fib_nh_lws)
 		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
-	if (f6i->fib6_nh.fib_nh_gw_family)
-		*dst = f6i->fib6_nh.fib_nh_gw6;
+	if (res.nh->fib_nh_gw_family)
+		*dst = res.nh->fib_nh_gw6;
 
-	dev = f6i->fib6_nh.fib_nh_dev;
-	params->rt_metric = f6i->fib6_metric;
+	dev = res.nh->fib_nh_dev;
+	params->rt_metric = res.f6i->fib6_metric;
 
 	/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
 	 * not needed here.
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index e37e4c5871f7..b11fa0aa18a0 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -158,12 +158,11 @@ eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
 	return NULL;
 }
 
-static struct fib6_info *
-eafnosupport_fib6_multipath_select(const struct net *net, struct fib6_info *f6i,
-				   struct flowi6 *fl6, int oif,
-				   const struct sk_buff *skb, int strict)
+static void
+eafnosupport_fib6_select_path(const struct net *net, struct fib6_result *res,
+			      struct flowi6 *fl6, int oif, bool have_oif_match,
+			      const struct sk_buff *skb, int strict)
 {
-	return f6i;
 }
 
 static u32
@@ -187,7 +186,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 	.fib6_get_table    = eafnosupport_fib6_get_table,
 	.fib6_table_lookup = eafnosupport_fib6_table_lookup,
 	.fib6_lookup       = eafnosupport_fib6_lookup,
-	.fib6_multipath_select = eafnosupport_fib6_multipath_select,
+	.fib6_select_path  = eafnosupport_fib6_select_path,
 	.ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6,
 	.fib6_nh_init	   = eafnosupport_fib6_nh_init,
 };
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 1dac6ea6666a..d8587ca4fbeb 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -917,7 +917,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
 	.fib6_get_table	   = fib6_get_table,
 	.fib6_table_lookup = fib6_table_lookup,
 	.fib6_lookup       = fib6_lookup,
-	.fib6_multipath_select = fib6_multipath_select,
+	.fib6_select_path  = fib6_select_path,
 	.ip6_mtu_from_fib6 = ip6_mtu_from_fib6,
 	.fib6_nh_init	   = fib6_nh_init,
 	.fib6_nh_release   = fib6_nh_release,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9ece8067a59b..0ad77b62da7c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -428,13 +428,15 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 	return false;
 }
 
-struct fib6_info *fib6_multipath_select(const struct net *net,
-					struct fib6_info *match,
-					struct flowi6 *fl6, int oif,
-					const struct sk_buff *skb,
-					int strict)
+void fib6_select_path(const struct net *net, struct fib6_result *res,
+		      struct flowi6 *fl6, int oif, bool have_oif_match,
+		      const struct sk_buff *skb, int strict)
 {
 	struct fib6_info *sibling, *next_sibling;
+	struct fib6_info *match = res->f6i;
+
+	if (!match->fib6_nsiblings || have_oif_match)
+		goto out;
 
 	/* We might have already computed the hash for ICMPv6 errors. In such
 	 * case it will always be non-zero. Otherwise now is the time to do it.
@@ -443,7 +445,7 @@ struct fib6_info *fib6_multipath_select(const struct net *net,
 		fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
 
 	if (fl6->mp_hash <= atomic_read(&match->fib6_nh.fib_nh_upper_bound))
-		return match;
+		goto out;
 
 	list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
 				 fib6_siblings) {
@@ -459,7 +461,9 @@ struct fib6_info *fib6_multipath_select(const struct net *net,
 		break;
 	}
 
-	return match;
+out:
+	res->f6i = match;
+	res->nh = &match->fib6_nh;
 }
 
 /*
@@ -1063,7 +1067,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 					     const struct sk_buff *skb,
 					     int flags)
 {
-	struct fib6_info *f6i;
+	struct fib6_result res = {};
 	struct fib6_node *fn;
 	struct rt6_info *rt;
 
@@ -1073,14 +1077,14 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 	rcu_read_lock();
 	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
-	f6i = rcu_dereference(fn->leaf);
-	if (!f6i)
-		f6i = net->ipv6.fib6_null_entry;
+	res.f6i = rcu_dereference(fn->leaf);
+	if (!res.f6i)
+		res.f6i = net->ipv6.fib6_null_entry;
 	else
-		f6i = rt6_device_match(net, f6i, &fl6->saddr,
-				      fl6->flowi6_oif, flags);
+		res.f6i = rt6_device_match(net, res.f6i, &fl6->saddr,
+					   fl6->flowi6_oif, flags);
 
-	if (f6i == net->ipv6.fib6_null_entry) {
+	if (res.f6i == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
 			goto restart;
@@ -1090,20 +1094,20 @@ restart:
 		goto out;
 	}
 
-	if (f6i->fib6_nsiblings && fl6->flowi6_oif == 0)
-		f6i = fib6_multipath_select(net, f6i, fl6, fl6->flowi6_oif, skb,
-					    flags);
+	fib6_select_path(net, &res, fl6, fl6->flowi6_oif,
+			 fl6->flowi6_oif != 0, skb, flags);
+
 	/* Search through exception table */
-	rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+	rt = rt6_find_cached_rt(res.f6i, &fl6->daddr, &fl6->saddr);
 	if (rt) {
 		if (ip6_hold_safe(net, &rt))
 			dst_use_noref(&rt->dst, jiffies);
 	} else {
-		rt = ip6_create_rt_rcu(f6i);
+		rt = ip6_create_rt_rcu(res.f6i);
 	}
 
 out:
-	trace_fib6_table_lookup(net, f6i, table, fl6);
+	trace_fib6_table_lookup(net, res.f6i, table, fl6);
 
 	rcu_read_unlock();
 
@@ -1843,7 +1847,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 			       int oif, struct flowi6 *fl6,
 			       const struct sk_buff *skb, int flags)
 {
-	struct fib6_info *f6i;
+	struct fib6_result res = {};
 	struct rt6_info *rt;
 	int strict = 0;
 
@@ -1854,19 +1858,18 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 
 	rcu_read_lock();
 
-	f6i = fib6_table_lookup(net, table, oif, fl6, strict);
-	if (f6i == net->ipv6.fib6_null_entry) {
+	res.f6i = fib6_table_lookup(net, table, oif, fl6, strict);
+	if (res.f6i == net->ipv6.fib6_null_entry) {
 		rt = net->ipv6.ip6_null_entry;
 		rcu_read_unlock();
 		dst_hold(&rt->dst);
 		return rt;
 	}
 
-	if (f6i->fib6_nsiblings)
-		f6i = fib6_multipath_select(net, f6i, fl6, oif, skb, strict);
+	fib6_select_path(net, &res, fl6, oif, false, skb, strict);
 
 	/*Search through exception table */
-	rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+	rt = rt6_find_cached_rt(res.f6i, &fl6->daddr, &fl6->saddr);
 	if (rt) {
 		if (ip6_hold_safe(net, &rt))
 			dst_use_noref(&rt->dst, jiffies);
@@ -1874,7 +1877,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		rcu_read_unlock();
 		return rt;
 	} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
-			    !f6i->fib6_nh.fib_nh_gw_family)) {
+			    !res.nh->fib_nh_gw_family)) {
 		/* Create a RTF_CACHE clone which will not be
 		 * owned by the fib6 tree.  It is for the special case where
 		 * the daddr in the skb during the neighbor look-up is different
@@ -1882,7 +1885,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		 */
 		struct rt6_info *uncached_rt;
 
-		uncached_rt = ip6_rt_cache_alloc(f6i, &fl6->daddr, NULL);
+		uncached_rt = ip6_rt_cache_alloc(res.f6i, &fl6->daddr, NULL);
 
 		rcu_read_unlock();
 
@@ -1904,10 +1907,10 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		struct rt6_info *pcpu_rt;
 
 		local_bh_disable();
-		pcpu_rt = rt6_get_pcpu_route(f6i);
+		pcpu_rt = rt6_get_pcpu_route(res.f6i);
 
 		if (!pcpu_rt)
-			pcpu_rt = rt6_make_pcpu_route(net, f6i);
+			pcpu_rt = rt6_make_pcpu_route(net, res.f6i);
 
 		local_bh_enable();
 		rcu_read_unlock();
-- 
cgit v1.2.3


From b748f26092626332f73e71d75e4390de6b8bdf9b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 16 Apr 2019 14:36:06 -0700
Subject: ipv6: Pass fib6_result to ip6_mtu_from_fib6 and fib6_mtu

Change ip6_mtu_from_fib6 and fib6_mtu to take a fib6_result over a
fib6_info. Update both to use the fib6_nh from fib6_result.

Since the signature of ip6_mtu_from_fib6 is already changing, add const
to daddr and saddr.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h  |  5 +++--
 include/net/ipv6_stubs.h |  5 +++--
 net/core/filter.c        |  2 +-
 net/ipv6/addrconf_core.c |  5 +++--
 net/ipv6/route.c         | 26 +++++++++++++++-----------
 5 files changed, 25 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 5909fc421305..46bbd8ff9cc6 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -302,8 +302,9 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
 	return mtu;
 }
 
-u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
-		      struct in6_addr *saddr);
+u32 ip6_mtu_from_fib6(const struct fib6_result *res,
+		      const struct in6_addr *daddr,
+		      const struct in6_addr *saddr);
 
 struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
 				   struct net_device *dev, struct sk_buff *skb,
diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index 5df36d6a2613..0d16b9ec0485 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -38,8 +38,9 @@ struct ipv6_stub {
 	void (*fib6_select_path)(const struct net *net, struct fib6_result *res,
 				 struct flowi6 *fl6, int oif, bool oif_match,
 				 const struct sk_buff *skb, int strict);
-	u32 (*ip6_mtu_from_fib6)(struct fib6_info *f6i, struct in6_addr *daddr,
-				 struct in6_addr *saddr);
+	u32 (*ip6_mtu_from_fib6)(const struct fib6_result *res,
+				 const struct in6_addr *daddr,
+				 const struct in6_addr *saddr);
 
 	int (*fib6_nh_init)(struct net *net, struct fib6_nh *fib6_nh,
 			    struct fib6_config *cfg, gfp_t gfp_flags,
diff --git a/net/core/filter.c b/net/core/filter.c
index c8dcce205872..bb8fb2d58fd4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4761,7 +4761,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 				    fl6.flowi6_oif != 0, NULL, strict);
 
 	if (check_mtu) {
-		mtu = ipv6_stub->ip6_mtu_from_fib6(res.f6i, dst, src);
+		mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src);
 		if (params->tot_len > mtu)
 			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index b11fa0aa18a0..c4c0203d6836 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -166,8 +166,9 @@ eafnosupport_fib6_select_path(const struct net *net, struct fib6_result *res,
 }
 
 static u32
-eafnosupport_ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
-			       struct in6_addr *saddr)
+eafnosupport_ip6_mtu_from_fib6(const struct fib6_result *res,
+			       const struct in6_addr *daddr,
+			       const struct in6_addr *saddr)
 {
 	return 0;
 }
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 39d1a7a4d704..85799a09e144 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1417,14 +1417,15 @@ __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket,
 	return NULL;
 }
 
-static unsigned int fib6_mtu(const struct fib6_info *rt)
+static unsigned int fib6_mtu(const struct fib6_result *res)
 {
+	const struct fib6_nh *nh = res->nh;
 	unsigned int mtu;
 
-	if (rt->fib6_pmtu) {
-		mtu = rt->fib6_pmtu;
+	if (res->f6i->fib6_pmtu) {
+		mtu = res->f6i->fib6_pmtu;
 	} else {
-		struct net_device *dev = fib6_info_nh_dev(rt);
+		struct net_device *dev = nh->fib_nh_dev;
 		struct inet6_dev *idev;
 
 		rcu_read_lock();
@@ -1435,7 +1436,7 @@ static unsigned int fib6_mtu(const struct fib6_info *rt)
 
 	mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
 
-	return mtu - lwtunnel_headroom(rt->fib6_nh.fib_nh_lws, mtu);
+	return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
 }
 
 static int rt6_insert_exception(struct rt6_info *nrt,
@@ -1481,7 +1482,7 @@ static int rt6_insert_exception(struct rt6_info *nrt,
 	 * Only insert this exception route if its mtu
 	 * is less than f6i's mtu value.
 	 */
-	if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(res->f6i)) {
+	if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(res)) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -2640,12 +2641,15 @@ out:
  * based on ip6_dst_mtu_forward and exception logic of
  * rt6_find_cached_rt; called with rcu_read_lock
  */
-u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
-		      struct in6_addr *saddr)
+u32 ip6_mtu_from_fib6(const struct fib6_result *res,
+		      const struct in6_addr *daddr,
+		      const struct in6_addr *saddr)
 {
 	struct rt6_exception_bucket *bucket;
+	const struct fib6_nh *nh = res->nh;
+	struct fib6_info *f6i = res->f6i;
+	const struct in6_addr *src_key;
 	struct rt6_exception *rt6_ex;
-	struct in6_addr *src_key;
 	struct inet6_dev *idev;
 	u32 mtu = 0;
 
@@ -2667,7 +2671,7 @@ u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
 		mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU);
 
 	if (likely(!mtu)) {
-		struct net_device *dev = fib6_info_nh_dev(f6i);
+		struct net_device *dev = nh->fib_nh_dev;
 
 		mtu = IPV6_MIN_MTU;
 		idev = __in6_dev_get(dev);
@@ -2677,7 +2681,7 @@ u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
 
 	mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
 out:
-	return mtu - lwtunnel_headroom(fib6_info_nh_lwt(f6i), mtu);
+	return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
 }
 
 struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
-- 
cgit v1.2.3


From 8ff2e5b26cb84b1b0f502c0b7a3c62e4c4d86acc Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 16 Apr 2019 14:36:09 -0700
Subject: ipv6: Pass fib6_result to fib6_table_lookup tracepoint

Change fib6_table_lookup tracepoint to take the fib6_result and use
the fib6_info and fib6_nh from it.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/fib6.h | 16 ++++++++--------
 net/ipv6/route.c            |  6 +++---
 2 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/fib6.h b/include/trace/events/fib6.h
index 6d05ebdd669c..70e252d926ea 100644
--- a/include/trace/events/fib6.h
+++ b/include/trace/events/fib6.h
@@ -12,10 +12,10 @@
 
 TRACE_EVENT(fib6_table_lookup,
 
-	TP_PROTO(const struct net *net, const struct fib6_info *f6i,
+	TP_PROTO(const struct net *net, const struct fib6_result *res,
 		 struct fib6_table *table, const struct flowi6 *flp),
 
-	TP_ARGS(net, f6i, table, flp),
+	TP_ARGS(net, res, table, flp),
 
 	TP_STRUCT__entry(
 		__field(	u32,	tb_id		)
@@ -39,7 +39,7 @@ TRACE_EVENT(fib6_table_lookup,
 		struct in6_addr *in6;
 
 		__entry->tb_id = table->tb6_id;
-		__entry->err = ip6_rt_type_to_error(f6i->fib6_type);
+		__entry->err = ip6_rt_type_to_error(res->f6i->fib6_type);
 		__entry->oif = flp->flowi6_oif;
 		__entry->iif = flp->flowi6_iif;
 		__entry->tos = ip6_tclass(flp->flowlabel);
@@ -62,20 +62,20 @@ TRACE_EVENT(fib6_table_lookup,
 			__entry->dport = 0;
 		}
 
-		if (f6i->fib6_nh.fib_nh_dev) {
-			__assign_str(name, f6i->fib6_nh.fib_nh_dev);
+		if (res->nh && res->nh->fib_nh_dev) {
+			__assign_str(name, res->nh->fib_nh_dev);
 		} else {
 			__assign_str(name, "-");
 		}
-		if (f6i == net->ipv6.fib6_null_entry) {
+		if (res->f6i == net->ipv6.fib6_null_entry) {
 			struct in6_addr in6_zero = {};
 
 			in6 = (struct in6_addr *)__entry->gw;
 			*in6 = in6_zero;
 
-		} else if (f6i) {
+		} else if (res->nh) {
 			in6 = (struct in6_addr *)__entry->gw;
-			*in6 = f6i->fib6_nh.fib_nh_gw6;
+			*in6 = res->nh->fib_nh_gw6;
 		}
 	),
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a466e2e478e8..405e0784d13b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1130,7 +1130,7 @@ restart:
 	}
 
 out:
-	trace_fib6_table_lookup(net, res.f6i, table, fl6);
+	trace_fib6_table_lookup(net, &res, table, fl6);
 
 	rcu_read_unlock();
 
@@ -1865,7 +1865,7 @@ redo_rt6_select:
 		}
 	}
 
-	trace_fib6_table_lookup(net, res.f6i, table, fl6);
+	trace_fib6_table_lookup(net, &res, table, fl6);
 
 	return res.f6i;
 }
@@ -2538,7 +2538,7 @@ out:
 
 	rcu_read_unlock();
 
-	trace_fib6_table_lookup(net, rt, table, fl6);
+	trace_fib6_table_lookup(net, &res, table, fl6);
 	return ret;
 };
 
-- 
cgit v1.2.3


From effda4dd97e878ab83336bec7411cc41b5cc6d37 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 16 Apr 2019 14:36:10 -0700
Subject: ipv6: Pass fib6_result to fib lookups

Change fib6_lookup and fib6_table_lookup to take a fib6_result and set
f6i and nh rather than returning a fib6_info. For now both always
return 0.

A later patch set can make these more like the IPv4 counterparts and
return EINVAL, EACCESS, etc based on fib6_type.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h    |  9 +++++----
 include/net/ipv6_stubs.h | 11 +++++------
 net/core/filter.c        | 10 +++++-----
 net/ipv6/addrconf_core.c | 13 +++++++------
 net/ipv6/fib6_rules.c    | 34 +++++++++++++---------------------
 net/ipv6/ip6_fib.c       |  7 ++++---
 net/ipv6/route.c         | 15 +++++++--------
 7 files changed, 46 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index c4d818041663..cb3277cd1413 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -389,12 +389,13 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 /* called with rcu lock held; can return error pointer
  * caller needs to select path
  */
-struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
-			      int flags);
+int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+		struct fib6_result *res, int flags);
 
 /* called with rcu lock held; caller needs to select path */
-struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
-				    int oif, struct flowi6 *fl6, int strict);
+int fib6_table_lookup(struct net *net, struct fib6_table *table,
+		      int oif, struct flowi6 *fl6, struct fib6_result *res,
+		      int strict);
 
 void fib6_select_path(const struct net *net, struct fib6_result *res,
 		      struct flowi6 *fl6, int oif, bool have_oif_match,
diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index 0d16b9ec0485..6c0c4fde16f8 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -29,12 +29,11 @@ struct ipv6_stub {
 	int (*ipv6_route_input)(struct sk_buff *skb);
 
 	struct fib6_table *(*fib6_get_table)(struct net *net, u32 id);
-	struct fib6_info *(*fib6_lookup)(struct net *net, int oif,
-					 struct flowi6 *fl6, int flags);
-	struct fib6_info *(*fib6_table_lookup)(struct net *net,
-					      struct fib6_table *table,
-					      int oif, struct flowi6 *fl6,
-					      int flags);
+	int (*fib6_lookup)(struct net *net, int oif, struct flowi6 *fl6,
+			   struct fib6_result *res, int flags);
+	int (*fib6_table_lookup)(struct net *net, struct fib6_table *table,
+				 int oif, struct flowi6 *fl6,
+				 struct fib6_result *res, int flags);
 	void (*fib6_select_path)(const struct net *net, struct fib6_result *res,
 				 struct flowi6 *fl6, int oif, bool oif_match,
 				 const struct sk_buff *skb, int strict);
diff --git a/net/core/filter.c b/net/core/filter.c
index bb8fb2d58fd4..d17347cbeb1e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4684,7 +4684,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	struct inet6_dev *idev;
 	struct flowi6 fl6;
 	int strict = 0;
-	int oif;
+	int oif, err;
 	u32 mtu;
 
 	/* link local addresses are never forwarded */
@@ -4726,18 +4726,18 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		if (unlikely(!tb))
 			return BPF_FIB_LKUP_RET_NOT_FWDED;
 
-		res.f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6,
-						       strict);
+		err = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, &res,
+						   strict);
 	} else {
 		fl6.flowi6_mark = 0;
 		fl6.flowi6_secid = 0;
 		fl6.flowi6_tun_key.tun_id = 0;
 		fl6.flowi6_uid = sock_net_uid(net, NULL);
 
-		res.f6i = ipv6_stub->fib6_lookup(net, oif, &fl6, strict);
+		err = ipv6_stub->fib6_lookup(net, oif, &fl6, &res, strict);
 	}
 
-	if (unlikely(IS_ERR_OR_NULL(res.f6i) ||
+	if (unlikely(err || IS_ERR_OR_NULL(res.f6i) ||
 		     res.f6i == net->ipv6.fib6_null_entry))
 		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index c4c0203d6836..763a947e0d14 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -144,18 +144,19 @@ static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id)
 	return NULL;
 }
 
-static struct fib6_info *
+static int
 eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table,
-			       int oif, struct flowi6 *fl6, int flags)
+			       int oif, struct flowi6 *fl6,
+			       struct fib6_result *res, int flags)
 {
-	return NULL;
+	return -EAFNOSUPPORT;
 }
 
-static struct fib6_info *
+static int
 eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
-			 int flags)
+			 struct fib6_result *res, int flags)
 {
-	return NULL;
+	return -EAFNOSUPPORT;
 }
 
 static void
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index f590446595d8..ab5ac643bae8 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -61,16 +61,16 @@ unsigned int fib6_rules_seq_read(struct net *net)
 }
 
 /* called with rcu lock held; no reference taken on fib6_info */
-struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
-			      int flags)
+int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+		struct fib6_result *res, int flags)
 {
-	struct fib6_info *f6i;
 	int err;
 
 	if (net->ipv6.fib6_has_custom_rules) {
 		struct fib_lookup_arg arg = {
 			.lookup_ptr = fib6_table_lookup,
 			.lookup_data = &oif,
+			.result = res,
 			.flags = FIB_LOOKUP_NOREF,
 		};
 
@@ -78,19 +78,15 @@ struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
 
 		err = fib_rules_lookup(net->ipv6.fib6_rules_ops,
 				       flowi6_to_flowi(fl6), flags, &arg);
-		if (err)
-			return ERR_PTR(err);
-
-		f6i = arg.result ? : net->ipv6.fib6_null_entry;
 	} else {
-		f6i = fib6_table_lookup(net, net->ipv6.fib6_local_tbl,
-					oif, fl6, flags);
-		if (!f6i || f6i == net->ipv6.fib6_null_entry)
-			f6i = fib6_table_lookup(net, net->ipv6.fib6_main_tbl,
-						oif, fl6, flags);
+		err = fib6_table_lookup(net, net->ipv6.fib6_local_tbl, oif,
+					fl6, res, flags);
+		if (err || res->f6i == net->ipv6.fib6_null_entry)
+			err = fib6_table_lookup(net, net->ipv6.fib6_main_tbl,
+						oif, fl6, res, flags);
 	}
 
-	return f6i;
+	return err;
 }
 
 struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
@@ -157,10 +153,10 @@ static int fib6_rule_saddr(struct net *net, struct fib_rule *rule, int flags,
 static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp,
 				int flags, struct fib_lookup_arg *arg)
 {
+	struct fib6_result *res = arg->result;
 	struct flowi6 *flp6 = &flp->u.ip6;
 	struct net *net = rule->fr_net;
 	struct fib6_table *table;
-	struct fib6_info *f6i;
 	int err = -EAGAIN, *oif;
 	u32 tb_id;
 
@@ -182,14 +178,10 @@ static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp,
 		return -EAGAIN;
 
 	oif = (int *)arg->lookup_data;
-	f6i = fib6_table_lookup(net, table, *oif, flp6, flags);
-	if (f6i != net->ipv6.fib6_null_entry) {
+	err = fib6_table_lookup(net, table, *oif, flp6, res, flags);
+	if (!err && res->f6i != net->ipv6.fib6_null_entry)
 		err = fib6_rule_saddr(net, rule, flags, flp6,
-				      fib6_info_nh_dev(f6i));
-
-		if (likely(!err))
-			arg->result = f6i;
-	}
+				      res->nh->fib_nh_dev);
 
 	return err;
 }
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 46f54a5bb1f0..b47e15df9769 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -354,10 +354,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 }
 
 /* called with rcu lock held; no reference taken on fib6_info */
-struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
-			      int flags)
+int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+		struct fib6_result *res, int flags)
 {
-	return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, flags);
+	return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6,
+				 res, flags);
 }
 
 static void __net_init fib6_tables_init(struct net *net)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 405e0784d13b..5a1e1176c33c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1839,11 +1839,10 @@ void rt6_age_exceptions(struct fib6_info *rt,
 }
 
 /* must be called with rcu lock held */
-struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
-				    int oif, struct flowi6 *fl6, int strict)
+int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif,
+		      struct flowi6 *fl6, struct fib6_result *res, int strict)
 {
 	struct fib6_node *fn, *saved_fn;
-	struct fib6_result res;
 
 	fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 	saved_fn = fn;
@@ -1852,8 +1851,8 @@ struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
 		oif = 0;
 
 redo_rt6_select:
-	rt6_select(net, fn, oif, &res, strict);
-	if (res.f6i == net->ipv6.fib6_null_entry) {
+	rt6_select(net, fn, oif, res, strict);
+	if (res->f6i == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)
 			goto redo_rt6_select;
@@ -1865,9 +1864,9 @@ redo_rt6_select:
 		}
 	}
 
-	trace_fib6_table_lookup(net, &res, table, fl6);
+	trace_fib6_table_lookup(net, res, table, fl6);
 
-	return res.f6i;
+	return 0;
 }
 
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
@@ -1885,7 +1884,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 
 	rcu_read_lock();
 
-	res.f6i = fib6_table_lookup(net, table, oif, fl6, strict);
+	fib6_table_lookup(net, table, oif, fl6, &res, strict);
 	if (res.f6i == net->ipv6.fib6_null_entry) {
 		rt = net->ipv6.ip6_null_entry;
 		rcu_read_unlock();
-- 
cgit v1.2.3


From 7d21fec90438941b44b699ae73673d2f8a3a9d76 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 16 Apr 2019 14:36:11 -0700
Subject: ipv6: Add fib6_type and fib6_flags to fib6_result

Add the fib6_flags and fib6_type to fib6_result. Update the lookup helpers
to set them and update post fib lookup users to use the version from the
result.

This allows nexthop objects to have blackhole nexthop.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h       |  2 ++
 include/trace/events/fib6.h |  2 +-
 net/core/filter.c           | 26 +++++++++----------
 net/ipv6/route.c            | 61 +++++++++++++++++++++++++++------------------
 4 files changed, 52 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index cb3277cd1413..6b7557b71c8c 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -193,6 +193,8 @@ struct rt6_info {
 struct fib6_result {
 	struct fib6_nh		*nh;
 	struct fib6_info	*f6i;
+	u32			fib6_flags;
+	u8			fib6_type;
 };
 
 #define for_each_fib6_node_rt_rcu(fn)					\
diff --git a/include/trace/events/fib6.h b/include/trace/events/fib6.h
index 70e252d926ea..c6abdcc77c12 100644
--- a/include/trace/events/fib6.h
+++ b/include/trace/events/fib6.h
@@ -39,7 +39,7 @@ TRACE_EVENT(fib6_table_lookup,
 		struct in6_addr *in6;
 
 		__entry->tb_id = table->tb6_id;
-		__entry->err = ip6_rt_type_to_error(res->f6i->fib6_type);
+		__entry->err = ip6_rt_type_to_error(res->fib6_type);
 		__entry->oif = flp->flowi6_oif;
 		__entry->iif = flp->flowi6_iif;
 		__entry->tos = ip6_tclass(flp->flowlabel);
diff --git a/net/core/filter.c b/net/core/filter.c
index d17347cbeb1e..1644a16afcec 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4741,21 +4741,19 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		     res.f6i == net->ipv6.fib6_null_entry))
 		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
-	if (unlikely(res.f6i->fib6_flags & RTF_REJECT)) {
-		switch (res.f6i->fib6_type) {
-		case RTN_BLACKHOLE:
-			return BPF_FIB_LKUP_RET_BLACKHOLE;
-		case RTN_UNREACHABLE:
-			return BPF_FIB_LKUP_RET_UNREACHABLE;
-		case RTN_PROHIBIT:
-			return BPF_FIB_LKUP_RET_PROHIBIT;
-		default:
-			return BPF_FIB_LKUP_RET_NOT_FWDED;
-		}
-	}
-
-	if (res.f6i->fib6_type != RTN_UNICAST)
+	switch (res.fib6_type) {
+	/* only unicast is forwarded */
+	case RTN_UNICAST:
+		break;
+	case RTN_BLACKHOLE:
+		return BPF_FIB_LKUP_RET_BLACKHOLE;
+	case RTN_UNREACHABLE:
+		return BPF_FIB_LKUP_RET_UNREACHABLE;
+	case RTN_PROHIBIT:
+		return BPF_FIB_LKUP_RET_PROHIBIT;
+	default:
 		return BPF_FIB_LKUP_RET_NOT_FWDED;
+	}
 
 	ipv6_stub->fib6_select_path(net, &res, &fl6, fl6.flowi6_oif,
 				    fl6.flowi6_oif != 0, NULL, strict);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5a1e1176c33c..e8c73b7782cd 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -500,31 +500,33 @@ static void rt6_device_match(struct net *net, struct fib6_result *res,
 
 	if (!oif && ipv6_addr_any(saddr)) {
 		nh = &f6i->fib6_nh;
-		if (!(nh->fib_nh_flags & RTNH_F_DEAD)) {
-			res->nh = nh;
-			return;
-		}
+		if (!(nh->fib_nh_flags & RTNH_F_DEAD))
+			goto out;
 	}
 
 	for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) {
 		nh = &spf6i->fib6_nh;
 		if (__rt6_device_match(net, nh, saddr, oif, flags)) {
 			res->f6i = spf6i;
-			res->nh = nh;
+			goto out;
 		}
 	}
 
 	if (oif && flags & RT6_LOOKUP_F_IFACE) {
 		res->f6i = net->ipv6.fib6_null_entry;
-		res->nh = &res->f6i->fib6_nh;
-		return;
+		nh = &res->f6i->fib6_nh;
+		goto out;
 	}
 
-	res->nh = &f6i->fib6_nh;
-	if (res->nh->fib_nh_flags & RTNH_F_DEAD) {
+	nh = &f6i->fib6_nh;
+	if (nh->fib_nh_flags & RTNH_F_DEAD) {
 		res->f6i = net->ipv6.fib6_null_entry;
-		res->nh = &res->f6i->fib6_nh;
+		nh = &res->f6i->fib6_nh;
 	}
+out:
+	res->nh = nh;
+	res->fib6_type = res->f6i->fib6_type;
+	res->fib6_flags = res->f6i->fib6_flags;
 }
 
 #ifdef CONFIG_IPV6_ROUTER_PREF
@@ -719,6 +721,8 @@ static void __find_rr_leaf(struct fib6_info *f6i_start,
 		if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) {
 			res->f6i = f6i;
 			res->nh = nh;
+			res->fib6_flags = f6i->fib6_flags;
+			res->fib6_type = f6i->fib6_type;
 		}
 	}
 }
@@ -796,6 +800,8 @@ out:
 	if (!res->f6i) {
 		res->f6i = net->ipv6.fib6_null_entry;
 		res->nh = &res->f6i->fib6_nh;
+		res->fib6_flags = res->f6i->fib6_flags;
+		res->fib6_type = res->f6i->fib6_type;
 	}
 }
 
@@ -889,15 +895,14 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
 static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res)
 {
 	struct net_device *dev = res->nh->fib_nh_dev;
-	const struct fib6_info *f6i = res->f6i;
 
-	if (f6i->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) {
+	if (res->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) {
 		/* for copies of local routes, dst->dev needs to be the
 		 * device if it is a master device, the master device if
 		 * device is enslaved, and the loopback as the default
 		 */
 		if (netif_is_l3_slave(dev) &&
-		    !rt6_need_strict(&f6i->fib6_dst.addr))
+		    !rt6_need_strict(&res->f6i->fib6_dst.addr))
 			dev = l3mdev_master_dev_rcu(dev);
 		else if (!netif_is_l3_master(dev))
 			dev = dev_net(dev)->loopback_dev;
@@ -943,11 +948,11 @@ static unsigned short fib6_info_dst_flags(struct fib6_info *rt)
 	return flags;
 }
 
-static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort)
+static void ip6_rt_init_dst_reject(struct rt6_info *rt, u8 fib6_type)
 {
-	rt->dst.error = ip6_rt_type_to_error(ort->fib6_type);
+	rt->dst.error = ip6_rt_type_to_error(fib6_type);
 
-	switch (ort->fib6_type) {
+	switch (fib6_type) {
 	case RTN_BLACKHOLE:
 		rt->dst.output = dst_discard_out;
 		rt->dst.input = dst_discard;
@@ -967,19 +972,19 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort)
 
 static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res)
 {
-	struct fib6_info *ort = res->f6i;
+	struct fib6_info *f6i = res->f6i;
 
-	if (ort->fib6_flags & RTF_REJECT) {
-		ip6_rt_init_dst_reject(rt, ort);
+	if (res->fib6_flags & RTF_REJECT) {
+		ip6_rt_init_dst_reject(rt, res->fib6_type);
 		return;
 	}
 
 	rt->dst.error = 0;
 	rt->dst.output = ip6_output;
 
-	if (ort->fib6_type == RTN_LOCAL || ort->fib6_type == RTN_ANYCAST) {
+	if (res->fib6_type == RTN_LOCAL || res->fib6_type == RTN_ANYCAST) {
 		rt->dst.input = ip6_input;
-	} else if (ipv6_addr_type(&ort->fib6_dst.addr) & IPV6_ADDR_MULTICAST) {
+	} else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) {
 		rt->dst.input = ip6_mc_input;
 	} else {
 		rt->dst.input = ip6_forward;
@@ -1012,7 +1017,7 @@ static void ip6_rt_copy_init(struct rt6_info *rt, const struct fib6_result *res)
 
 	rt->rt6i_dst = f6i->fib6_dst;
 	rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL;
-	rt->rt6i_flags = f6i->fib6_flags;
+	rt->rt6i_flags = res->fib6_flags;
 	if (nh->fib_nh_gw_family) {
 		rt->rt6i_gateway = nh->fib_nh_gw6;
 		rt->rt6i_flags |= RTF_GATEWAY;
@@ -2365,6 +2370,9 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 			return;
 		}
 		res.nh = &res.f6i->fib6_nh;
+		res.fib6_flags = res.f6i->fib6_flags;
+		res.fib6_type = res.f6i->fib6_type;
+
 		nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr);
 		if (nrt6) {
 			rt6_do_update_pmtu(nrt6, mtu);
@@ -2530,10 +2538,13 @@ restart:
 	res.f6i = rt;
 	res.nh = &rt->fib6_nh;
 out:
-	if (ret)
+	if (ret) {
 		ip6_hold_safe(net, &ret);
-	else
+	} else {
+		res.fib6_flags = res.f6i->fib6_flags;
+		res.fib6_type = res.f6i->fib6_type;
 		ret = ip6_create_rt_rcu(&res);
+	}
 
 	rcu_read_unlock();
 
@@ -3491,6 +3502,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	rcu_read_unlock();
 
 	res.nh = &res.f6i->fib6_nh;
+	res.fib6_flags = res.f6i->fib6_flags;
+	res.fib6_type = res.f6i->fib6_type;
 	nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL);
 	if (!nrt)
 		goto out;
-- 
cgit v1.2.3


From b8fb1ab46169ac016a8552a6455bb0bfc401f8e2 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 16 Apr 2019 17:31:43 -0700
Subject: net ipv6: Prevent neighbor add if protocol is disabled on device

Disabling IPv6 on an interface removes existing entries but nothing prevents
new entries from being manually added. To that end, add a new neigh_table
operation, allow_add, that is called on RTM_NEWNEIGH to see if neighbor
entries are allowed on a given device. If IPv6 is disabled on the device,
allow_add returns false and passes a message back to the user via extack.

  $ echo 1 > /proc/sys/net/ipv6/conf/eth1/disable_ipv6
  $ ip -6 neigh add fe80::4c88:bff:fe21:2704 dev eth1 lladdr de:ad:be:ef:01:01
  Error: IPv6 is disabled on this device.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/neighbour.h |  2 ++
 net/core/neighbour.c    |  5 +++++
 net/ipv6/ndisc.c        | 17 +++++++++++++++++
 3 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 3e5438bd0101..50a67bd6a434 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -205,6 +205,8 @@ struct neigh_table {
 	int			(*pconstructor)(struct pneigh_entry *);
 	void			(*pdestructor)(struct pneigh_entry *);
 	void			(*proxy_redo)(struct sk_buff *skb);
+	bool			(*allow_add)(const struct net_device *dev,
+					     struct netlink_ext_ack *extack);
 	char			*id;
 	struct neigh_parms	parms;
 	struct list_head	parms_list;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 30f6fd8f68e0..997cfa8f99ba 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1920,6 +1920,11 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 	}
 
+	if (tbl->allow_add && !tbl->allow_add(dev, extack)) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	neigh = neigh_lookup(tbl, dst, dev);
 	if (neigh == NULL) {
 		bool exempt_from_gc;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 66c8b294e02b..4c8e2ea8bf19 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -77,6 +77,8 @@ static u32 ndisc_hash(const void *pkey,
 		      const struct net_device *dev,
 		      __u32 *hash_rnd);
 static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey);
+static bool ndisc_allow_add(const struct net_device *dev,
+			    struct netlink_ext_ack *extack);
 static int ndisc_constructor(struct neighbour *neigh);
 static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
 static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
@@ -117,6 +119,7 @@ struct neigh_table nd_tbl = {
 	.pconstructor =	pndisc_constructor,
 	.pdestructor =	pndisc_destructor,
 	.proxy_redo =	pndisc_redo,
+	.allow_add  =   ndisc_allow_add,
 	.id =		"ndisc_cache",
 	.parms = {
 		.tbl			= &nd_tbl,
@@ -392,6 +395,20 @@ static void pndisc_destructor(struct pneigh_entry *n)
 	ipv6_dev_mc_dec(dev, &maddr);
 }
 
+/* called with rtnl held */
+static bool ndisc_allow_add(const struct net_device *dev,
+			    struct netlink_ext_ack *extack)
+{
+	struct inet6_dev *idev = __in6_dev_get(dev);
+
+	if (!idev || idev->cnf.disable_ipv6) {
+		NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device");
+		return false;
+	}
+
+	return true;
+}
+
 static struct sk_buff *ndisc_alloc_skb(struct net_device *dev,
 				       int len)
 {
-- 
cgit v1.2.3


From 0bc199854405543b0debe67c735c0aae94f1d319 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Wed, 17 Apr 2019 16:35:49 -0400
Subject: ipv6: Add rate limit mask for ICMPv6 messages

To make ICMPv6 closer to ICMPv4, add ratemask parameter. Since the ICMP
message types use larger numeric values, a simple bitmask doesn't fit.
I use large bitmap. The input and output are the in form of list of
ranges. Set the default to rate limit all error messages but Packet Too
Big. For Packet Too Big, use ratemask instead of hard-coded.

There are functions where icmpv6_xrlim_allow() and icmpv6_global_allow()
aren't called. This patch only adds them to icmpv6_echo_reply().

Rate limiting error messages is mandated by RFC 4443 but RFC 4890 says
that it is also acceptable to rate limit informational messages. Thus,
I removed the current hard-coded behavior of icmpv6_mask_allow() that
doesn't rate limit informational messages.

v2: Add dummy function proc_do_large_bitmap() if CONFIG_PROC_SYSCTL
    isn't defined, expand the description in ip-sysctl.txt and remove
    unnecessary conditional before kfree().
v3: Inline the bitmap instead of dynamically allocated. Still is a
    pointer to it is needed because of the way proc_do_large_bitmap work.

Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 17 ++++++++++++++++-
 include/net/netns/ipv6.h               |  3 +++
 include/uapi/linux/icmpv6.h            |  4 ++++
 kernel/sysctl.c                        |  6 ++++++
 net/ipv6/af_inet6.c                    |  9 +++++++++
 net/ipv6/icmp.c                        | 31 ++++++++++++++++++++++---------
 6 files changed, 60 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 5eedc6941ce5..8a5e59ba223f 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1913,11 +1913,26 @@ enhanced_dad - BOOLEAN
 
 icmp/*:
 ratelimit - INTEGER
-	Limit the maximal rates for sending ICMPv6 packets.
+	Limit the maximal rates for sending ICMPv6 messages.
 	0 to disable any limiting,
 	otherwise the minimal space between responses in milliseconds.
 	Default: 1000
 
+ratemask - list of comma separated ranges
+	For ICMPv6 message types matching the ranges in the ratemask, limit
+	the sending of the message according to ratelimit parameter.
+
+	The format used for both input and output is a comma separated
+	list of ranges (e.g. "0-127,129" for ICMPv6 message type 0 to 127 and
+	129). Writing to the file will clear all previous ranges of ICMPv6
+	message types and update the current list with the input.
+
+	Refer to: https://www.iana.org/assignments/icmpv6-parameters/icmpv6-parameters.xhtml
+	for numerical values of ICMPv6 message types, e.g. echo request is 128
+	and echo reply is 129.
+
+	Default: 0-1,3-127 (rate limit ICMPv6 errors except Packet Too Big)
+
 echo_ignore_all - BOOLEAN
 	If set non-zero, then the kernel will ignore all ICMP ECHO
 	requests sent to it over the IPv6 protocol.
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 64e29b58bb5e..5e61b5a8635d 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -8,6 +8,7 @@
 #ifndef __NETNS_IPV6_H__
 #define __NETNS_IPV6_H__
 #include <net/dst_ops.h>
+#include <uapi/linux/icmpv6.h>
 
 struct ctl_table_header;
 
@@ -35,6 +36,8 @@ struct netns_sysctl_ipv6 {
 	int icmpv6_echo_ignore_all;
 	int icmpv6_echo_ignore_multicast;
 	int icmpv6_echo_ignore_anycast;
+	DECLARE_BITMAP(icmpv6_ratemask, ICMPV6_MSG_MAX + 1);
+	unsigned long *icmpv6_ratemask_ptr;
 	int anycast_src_echo_reply;
 	int ip_nonlocal_bind;
 	int fwmark_reflect;
diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h
index 325395f56bfa..2622b5a3e616 100644
--- a/include/uapi/linux/icmpv6.h
+++ b/include/uapi/linux/icmpv6.h
@@ -90,6 +90,8 @@ struct icmp6hdr {
 #define ICMPV6_TIME_EXCEED		3
 #define ICMPV6_PARAMPROB		4
 
+#define ICMPV6_ERRMSG_MAX       127
+
 #define ICMPV6_INFOMSG_MASK		0x80
 
 #define ICMPV6_ECHO_REQUEST		128
@@ -110,6 +112,8 @@ struct icmp6hdr {
 
 #define ICMPV6_MRDISC_ADV		151
 
+#define ICMPV6_MSG_MAX          255
+
 /*
  *	Codes for Destination Unreachable
  */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c9ec050bcf46..599510a3355e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -3326,6 +3326,11 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
     return -ENOSYS;
 }
 
+int proc_do_large_bitmap(struct ctl_table *table, int write,
+			 void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	return -ENOSYS;
+}
 
 #endif /* CONFIG_PROC_SYSCTL */
 
@@ -3366,3 +3371,4 @@ EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
 EXPORT_SYMBOL(proc_dostring);
 EXPORT_SYMBOL(proc_doulongvec_minmax);
 EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
+EXPORT_SYMBOL(proc_do_large_bitmap);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d8587ca4fbeb..3d1de28aaa9e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -850,6 +850,15 @@ static int __net_init inet6_net_init(struct net *net)
 	net->ipv6.sysctl.icmpv6_echo_ignore_all = 0;
 	net->ipv6.sysctl.icmpv6_echo_ignore_multicast = 0;
 	net->ipv6.sysctl.icmpv6_echo_ignore_anycast = 0;
+
+	/* By default, rate limit error messages.
+	 * Except for pmtu discovery, it would break it.
+	 * proc_do_large_bitmap needs pointer to the bitmap.
+	 */
+	bitmap_set(net->ipv6.sysctl.icmpv6_ratemask, 0, ICMPV6_ERRMSG_MAX + 1);
+	bitmap_clear(net->ipv6.sysctl.icmpv6_ratemask, ICMPV6_PKT_TOOBIG, 1);
+	net->ipv6.sysctl.icmpv6_ratemask_ptr = net->ipv6.sysctl.icmpv6_ratemask;
+
 	net->ipv6.sysctl.flowlabel_consistency = 1;
 	net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS;
 	net->ipv6.sysctl.idgen_retries = 3;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index cc14b9998941..afb915807cd0 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -168,22 +168,21 @@ static bool is_ineligible(const struct sk_buff *skb)
 	return false;
 }
 
-static bool icmpv6_mask_allow(int type)
+static bool icmpv6_mask_allow(struct net *net, int type)
 {
-	/* Informational messages are not limited. */
-	if (type & ICMPV6_INFOMSG_MASK)
+	if (type > ICMPV6_MSG_MAX)
 		return true;
 
-	/* Do not limit pmtu discovery, it would break it. */
-	if (type == ICMPV6_PKT_TOOBIG)
+	/* Limit if icmp type is set in ratemask. */
+	if (!test_bit(type, net->ipv6.sysctl.icmpv6_ratemask))
 		return true;
 
 	return false;
 }
 
-static bool icmpv6_global_allow(int type)
+static bool icmpv6_global_allow(struct net *net, int type)
 {
-	if (icmpv6_mask_allow(type))
+	if (icmpv6_mask_allow(net, type))
 		return true;
 
 	if (icmp_global_allow())
@@ -202,7 +201,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	struct dst_entry *dst;
 	bool res = false;
 
-	if (icmpv6_mask_allow(type))
+	if (icmpv6_mask_allow(net, type))
 		return true;
 
 	/*
@@ -511,7 +510,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	local_bh_disable();
 
 	/* Check global sysctl_icmp_msgs_per_sec ratelimit */
-	if (!(skb->dev->flags&IFF_LOOPBACK) && !icmpv6_global_allow(type))
+	if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type))
 		goto out_bh_enable;
 
 	mip6_addr_swap(skb);
@@ -731,6 +730,11 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	if (IS_ERR(dst))
 		goto out;
 
+	/* Check the ratelimit */
+	if ((!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY)) ||
+	    !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6))
+		goto out_dst_release;
+
 	idev = __in6_dev_get(skb->dev);
 
 	msg.skb = skb;
@@ -751,6 +755,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 		icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
 					   skb->len + sizeof(struct icmp6hdr));
 	}
+out_dst_release:
 	dst_release(dst);
 out:
 	icmpv6_xmit_unlock(sk);
@@ -1137,6 +1142,13 @@ static struct ctl_table ipv6_icmp_table_template[] = {
 		.mode		= 0644,
 		.proc_handler = proc_dointvec,
 	},
+	{
+		.procname	= "ratemask",
+		.data		= &init_net.ipv6.sysctl.icmpv6_ratemask_ptr,
+		.maxlen		= ICMPV6_MSG_MAX + 1,
+		.mode		= 0644,
+		.proc_handler = proc_do_large_bitmap,
+	},
 	{ },
 };
 
@@ -1153,6 +1165,7 @@ struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
 		table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all;
 		table[2].data = &net->ipv6.sysctl.icmpv6_echo_ignore_multicast;
 		table[3].data = &net->ipv6.sysctl.icmpv6_echo_ignore_anycast;
+		table[4].data = &net->ipv6.sysctl.icmpv6_ratemask_ptr;
 	}
 	return table;
 }
-- 
cgit v1.2.3


From a06eaaf7913cab9dd6cb8ece4f78cfd7a802872a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 17 Apr 2019 13:51:59 -0700
Subject: net: skb: remove unused asserts

We are discouraging the use of BUG() these days, remove the
unused ASSERT macros from skbuff.h.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a06275a618f0..e4ee92089dd6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2100,8 +2100,6 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size,
 			  unsigned int truesize);
 
-#define SKB_PAGE_ASSERT(skb) 	BUG_ON(skb_shinfo(skb)->nr_frags)
-#define SKB_FRAG_ASSERT(skb) 	BUG_ON(skb_has_frag_list(skb))
 #define SKB_LINEAR_ASSERT(skb)  BUG_ON(skb_is_nonlinear(skb))
 
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
-- 
cgit v1.2.3


From 71dd6c0dff51b5f1fef2e9dfa6f6a948aac975f3 Mon Sep 17 00:00:00 2001
From: David Bauer <mail@david-bauer.net>
Date: Wed, 17 Apr 2019 23:59:21 +0200
Subject: net: phy: add support for reset-controller

This commit adds support for PHY reset pins handled by a reset controller.

Signed-off-by: David Bauer <mail@david-bauer.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c    | 27 +++++++++++++++++++++++++--
 drivers/net/phy/mdio_device.c | 13 +++++++++++--
 include/linux/mdio.h          |  1 +
 3 files changed, 37 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 4be4cc09eb90..ba3d2523808b 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -24,6 +24,7 @@
 #include <linux/of_gpio.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
+#include <linux/reset.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
 #include <linux/mm.h>
@@ -57,8 +58,23 @@ static int mdiobus_register_gpiod(struct mdio_device *mdiodev)
 
 	mdiodev->reset = gpiod;
 
-	/* Assert the reset signal again */
-	mdio_device_reset(mdiodev, 1);
+	return 0;
+}
+
+static int mdiobus_register_reset(struct mdio_device *mdiodev)
+{
+	struct reset_control *reset = NULL;
+
+	if (mdiodev->dev.of_node)
+		reset = devm_reset_control_get_exclusive(&mdiodev->dev,
+							 "phy");
+	if (PTR_ERR(reset) == -ENOENT ||
+	    PTR_ERR(reset) == -ENOTSUPP)
+		reset = NULL;
+	else if (IS_ERR(reset))
+		return PTR_ERR(reset);
+
+	mdiodev->reset_ctrl = reset;
 
 	return 0;
 }
@@ -74,6 +90,13 @@ int mdiobus_register_device(struct mdio_device *mdiodev)
 		err = mdiobus_register_gpiod(mdiodev);
 		if (err)
 			return err;
+
+		err = mdiobus_register_reset(mdiodev);
+		if (err)
+			return err;
+
+		/* Assert the reset signal */
+		mdio_device_reset(mdiodev, 1);
 	}
 
 	mdiodev->bus->mdio_map[mdiodev->addr] = mdiodev;
diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index 887076292e50..57668e0f9256 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -16,6 +16,7 @@
 #include <linux/mii.h>
 #include <linux/module.h>
 #include <linux/phy.h>
+#include <linux/reset.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/unistd.h>
@@ -116,10 +117,18 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value)
 {
 	unsigned int d;
 
-	if (!mdiodev->reset)
+	if (!mdiodev->reset && !mdiodev->reset_ctrl)
 		return;
 
-	gpiod_set_value(mdiodev->reset, value);
+	if (mdiodev->reset)
+		gpiod_set_value(mdiodev->reset, value);
+
+	if (mdiodev->reset_ctrl) {
+		if (value)
+			reset_control_assert(mdiodev->reset_ctrl);
+		else
+			reset_control_deassert(mdiodev->reset_ctrl);
+	}
 
 	d = value ? mdiodev->reset_assert_delay : mdiodev->reset_deassert_delay;
 	if (d)
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 3e99ae3ed87f..6eaf71500ef6 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -40,6 +40,7 @@ struct mdio_device {
 	int addr;
 	int flags;
 	struct gpio_desc *reset;
+	struct reset_control *reset_ctrl;
 	unsigned int reset_assert_delay;
 	unsigned int reset_deassert_delay;
 };
-- 
cgit v1.2.3


From 6110ed2db3a41f3b9d676e58ac3d4637c2b497c4 Mon Sep 17 00:00:00 2001
From: David Bauer <mail@david-bauer.net>
Date: Wed, 17 Apr 2019 23:59:22 +0200
Subject: net: mdio: rename mdio_device reset to reset_gpio

This renames the GPIO reset of mdio devices from 'reset' to
'reset_gpio' to better differentiate between GPIO and
reset-controller driven reset line.

Signed-off-by: David Bauer <mail@david-bauer.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c      | 2 +-
 drivers/net/phy/mdio_bus.c    | 6 +++---
 drivers/net/phy/mdio_device.c | 6 +++---
 include/linux/mdio.h          | 2 +-
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 406111753f7c..222ccd9ecfce 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -331,7 +331,7 @@ static void at803x_link_change_notify(struct phy_device *phydev)
 	 * in the FIFO. In such cases, the FIFO enters an error mode it
 	 * cannot recover from by software.
 	 */
-	if (phydev->state == PHY_NOLINK && phydev->mdio.reset) {
+	if (phydev->state == PHY_NOLINK && phydev->mdio.reset_gpio) {
 		struct at803x_context context;
 
 		at803x_context_save(phydev, &context);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index ba3d2523808b..bd04fe762056 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -56,7 +56,7 @@ static int mdiobus_register_gpiod(struct mdio_device *mdiodev)
 			return PTR_ERR(gpiod);
 	}
 
-	mdiodev->reset = gpiod;
+	mdiodev->reset_gpio = gpiod;
 
 	return 0;
 }
@@ -469,8 +469,8 @@ void mdiobus_unregister(struct mii_bus *bus)
 		if (!mdiodev)
 			continue;
 
-		if (mdiodev->reset)
-			gpiod_put(mdiodev->reset);
+		if (mdiodev->reset_gpio)
+			gpiod_put(mdiodev->reset_gpio);
 
 		mdiodev->device_remove(mdiodev);
 		mdiodev->device_free(mdiodev);
diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index 57668e0f9256..e282600bd83e 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -117,11 +117,11 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value)
 {
 	unsigned int d;
 
-	if (!mdiodev->reset && !mdiodev->reset_ctrl)
+	if (!mdiodev->reset_gpio && !mdiodev->reset_ctrl)
 		return;
 
-	if (mdiodev->reset)
-		gpiod_set_value(mdiodev->reset, value);
+	if (mdiodev->reset_gpio)
+		gpiod_set_value(mdiodev->reset_gpio, value);
 
 	if (mdiodev->reset_ctrl) {
 		if (value)
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 6eaf71500ef6..9dc16d5705a1 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -39,7 +39,7 @@ struct mdio_device {
 	/* Bus address of the MDIO device (0-31) */
 	int addr;
 	int flags;
-	struct gpio_desc *reset;
+	struct gpio_desc *reset_gpio;
 	struct reset_control *reset_ctrl;
 	unsigned int reset_assert_delay;
 	unsigned int reset_deassert_delay;
-- 
cgit v1.2.3


From 8c8b3458d0b91b2230f76fbe1b0280568f10d19f Mon Sep 17 00:00:00 2001
From: Mike Manning <mmanning@vyatta.att-mail.com>
Date: Thu, 18 Apr 2019 18:35:31 +0100
Subject: vlan: support binding link state to vlan member bridge ports

In the case of vlan filtering on bridges, the bridge may also have the
corresponding vlan devices as upper devices. Currently the link state
of vlan devices is transferred from the lower device. So this is up if
the bridge is in admin up state and there is at least one bridge port
that is up, regardless of the vlan that the port is a member of.

The link state of the vlan device may need to track only the state of
the subset of ports that are also members of the corresponding vlan,
rather than that of all ports.

Add a flag to specify a vlan bridge binding mode, by which the link
state is no longer automatically transferred from the lower device,
but is instead determined by the bridge ports that are members of the
vlan.

Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Acked-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_vlan.h | 9 +++++----
 net/8021q/vlan_dev.c         | 3 ++-
 net/8021q/vlan_netlink.c     | 3 ++-
 3 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_vlan.h b/include/uapi/linux/if_vlan.h
index 7a0e8bd65b6b..90a2c89afc8f 100644
--- a/include/uapi/linux/if_vlan.h
+++ b/include/uapi/linux/if_vlan.h
@@ -32,10 +32,11 @@ enum vlan_ioctl_cmds {
 };
 
 enum vlan_flags {
-	VLAN_FLAG_REORDER_HDR	= 0x1,
-	VLAN_FLAG_GVRP		= 0x2,
-	VLAN_FLAG_LOOSE_BINDING	= 0x4,
-	VLAN_FLAG_MVRP		= 0x8,
+	VLAN_FLAG_REORDER_HDR		= 0x1,
+	VLAN_FLAG_GVRP			= 0x2,
+	VLAN_FLAG_LOOSE_BINDING		= 0x4,
+	VLAN_FLAG_MVRP			= 0x8,
+	VLAN_FLAG_BRIDGE_BINDING	= 0x10,
 };
 
 enum vlan_name_types {
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 8d77b6ee4477..ed996b500b10 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -223,7 +223,8 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask)
 	u32 old_flags = vlan->flags;
 
 	if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP |
-		     VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP))
+		     VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP |
+		     VLAN_FLAG_BRIDGE_BINDING))
 		return -EINVAL;
 
 	vlan->flags = (old_flags & ~mask) | (flags & mask);
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 9b60c1e399e2..a624dccf68fd 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -84,7 +84,8 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[],
 		flags = nla_data(data[IFLA_VLAN_FLAGS]);
 		if ((flags->flags & flags->mask) &
 		    ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP |
-		      VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP)) {
+		      VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP |
+		      VLAN_FLAG_BRIDGE_BINDING)) {
 			NL_SET_ERR_MSG_MOD(extack, "Invalid VLAN flags");
 			return -EINVAL;
 		}
-- 
cgit v1.2.3


From c7cbdbf29f488a19982cd9f4a109887f18028bbb Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 17 Apr 2019 22:51:48 +0200
Subject: net: rework SIOCGSTAMP ioctl handling

The SIOCGSTAMP/SIOCGSTAMPNS ioctl commands are implemented by many
socket protocol handlers, and all of those end up calling the same
sock_get_timestamp()/sock_get_timestampns() helper functions, which
results in a lot of duplicate code.

With the introduction of 64-bit time_t on 32-bit architectures, this
gets worse, as we then need four different ioctl commands in each
socket protocol implementation.

To simplify that, let's add a new .gettstamp() operation in
struct proto_ops, and move ioctl implementation into the common
sock_ioctl()/compat_sock_ioctl_trans() functions that these all go
through.

We can reuse the sock_get_timestamp() implementation, but generalize
it so it can deal with both native and compat mode, as well as
timeval and timespec structures.

Acked-by: Stefan Schmidt <stefan@datenfreihafen.org>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://lore.kernel.org/lkml/CAK8P3a038aDQQotzua_QtKGhq8O9n+rdiz2=WDCp82ys8eUT+A@mail.gmail.com/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h          |  2 ++
 include/net/compat.h         |  3 ---
 include/net/sock.h           |  4 ++--
 net/appletalk/ddp.c          |  7 +-----
 net/atm/ioctl.c              | 16 -------------
 net/atm/pvc.c                |  1 +
 net/atm/svc.c                |  1 +
 net/ax25/af_ax25.c           |  9 +------
 net/bluetooth/af_bluetooth.c |  8 -------
 net/bluetooth/l2cap_sock.c   |  1 +
 net/bluetooth/rfcomm/sock.c  |  1 +
 net/bluetooth/sco.c          |  1 +
 net/can/af_can.c             |  6 -----
 net/can/bcm.c                |  1 +
 net/can/raw.c                |  1 +
 net/compat.c                 | 57 --------------------------------------------
 net/core/sock.c              | 51 +++++++++++++++++++++------------------
 net/dccp/ipv4.c              |  1 +
 net/dccp/ipv6.c              |  1 +
 net/ieee802154/socket.c      |  6 ++---
 net/ipv4/af_inet.c           |  9 +++----
 net/ipv6/af_inet6.c          |  8 ++-----
 net/ipv6/raw.c               |  1 +
 net/l2tp/l2tp_ip.c           |  1 +
 net/l2tp/l2tp_ip6.c          |  1 +
 net/netrom/af_netrom.c       | 14 +----------
 net/packet/af_packet.c       |  7 ++----
 net/qrtr/qrtr.c              |  4 +---
 net/rose/af_rose.c           |  7 +-----
 net/sctp/ipv6.c              |  1 +
 net/sctp/protocol.c          |  1 +
 net/socket.c                 | 48 +++++++++++--------------------------
 net/x25/af_x25.c             | 27 +--------------------
 33 files changed, 75 insertions(+), 232 deletions(-)

(limited to 'include')

diff --git a/include/linux/net.h b/include/linux/net.h
index c606c72311d0..50bf5206ead6 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -161,6 +161,8 @@ struct proto_ops {
 	int	 	(*compat_ioctl) (struct socket *sock, unsigned int cmd,
 				      unsigned long arg);
 #endif
+	int		(*gettstamp) (struct socket *sock, void __user *userstamp,
+				      bool timeval, bool time32);
 	int		(*listen)    (struct socket *sock, int len);
 	int		(*shutdown)  (struct socket *sock, int flags);
 	int		(*setsockopt)(struct socket *sock, int level,
diff --git a/include/net/compat.h b/include/net/compat.h
index 4c6d75612b6c..f277653c7e17 100644
--- a/include/net/compat.h
+++ b/include/net/compat.h
@@ -30,9 +30,6 @@ struct compat_cmsghdr {
 	compat_int_t	cmsg_type;
 };
 
-int compat_sock_get_timestamp(struct sock *, struct timeval __user *);
-int compat_sock_get_timestampns(struct sock *, struct timespec __user *);
-
 #else /* defined(CONFIG_COMPAT) */
 /*
  * To avoid compiler warnings:
diff --git a/include/net/sock.h b/include/net/sock.h
index bdd77bbce7d8..784cd19d5ff7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1614,6 +1614,8 @@ int sock_setsockopt(struct socket *sock, int level, int op,
 
 int sock_getsockopt(struct socket *sock, int level, int op,
 		    char __user *optval, int __user *optlen);
+int sock_gettstamp(struct socket *sock, void __user *userstamp,
+		   bool timeval, bool time32);
 struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
 				    int noblock, int *errcode);
 struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
@@ -2503,8 +2505,6 @@ static inline bool sk_listener(const struct sock *sk)
 }
 
 void sock_enable_timestamp(struct sock *sk, int flag);
-int sock_get_timestamp(struct sock *, struct timeval __user *);
-int sock_get_timestampns(struct sock *, struct timespec __user *);
 int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
 		       int type);
 
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 709d2542f729..e2511027d19b 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1806,12 +1806,6 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		rc = put_user(amount, (int __user *)argp);
 		break;
 	}
-	case SIOCGSTAMP:
-		rc = sock_get_timestamp(sk, argp);
-		break;
-	case SIOCGSTAMPNS:
-		rc = sock_get_timestampns(sk, argp);
-		break;
 	/* Routing */
 	case SIOCADDRT:
 	case SIOCDELRT:
@@ -1871,6 +1865,7 @@ static const struct proto_ops atalk_dgram_ops = {
 	.getname	= atalk_getname,
 	.poll		= datagram_poll,
 	.ioctl		= atalk_ioctl,
+	.gettstamp	= sock_gettstamp,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= atalk_compat_ioctl,
 #endif
diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c
index 2ff0e5e470e3..d955b683aa7c 100644
--- a/net/atm/ioctl.c
+++ b/net/atm/ioctl.c
@@ -81,22 +81,6 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd,
 				 (int __user *)argp) ? -EFAULT : 0;
 		goto done;
 	}
-	case SIOCGSTAMP: /* borrowed from IP */
-#ifdef CONFIG_COMPAT
-		if (compat)
-			error = compat_sock_get_timestamp(sk, argp);
-		else
-#endif
-			error = sock_get_timestamp(sk, argp);
-		goto done;
-	case SIOCGSTAMPNS: /* borrowed from IP */
-#ifdef CONFIG_COMPAT
-		if (compat)
-			error = compat_sock_get_timestampns(sk, argp);
-		else
-#endif
-			error = sock_get_timestampns(sk, argp);
-		goto done;
 	case ATM_SETSC:
 		net_warn_ratelimited("ATM_SETSC is obsolete; used by %s:%d\n",
 				     current->comm, task_pid_nr(current));
diff --git a/net/atm/pvc.c b/net/atm/pvc.c
index 2cb10af16afc..02bd2a436bdf 100644
--- a/net/atm/pvc.c
+++ b/net/atm/pvc.c
@@ -118,6 +118,7 @@ static const struct proto_ops pvc_proto_ops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = vcc_compat_ioctl,
 #endif
+	.gettstamp =	sock_gettstamp,
 	.listen =	sock_no_listen,
 	.shutdown =	pvc_shutdown,
 	.setsockopt =	pvc_setsockopt,
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 2f91b766ac42..908cbb8654f5 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -641,6 +641,7 @@ static const struct proto_ops svc_proto_ops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl =	svc_compat_ioctl,
 #endif
+	.gettstamp =	sock_gettstamp,
 	.listen =	svc_listen,
 	.shutdown =	svc_shutdown,
 	.setsockopt =	svc_setsockopt,
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 5d01edf8d819..449e7b7190c1 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1714,14 +1714,6 @@ static int ax25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		break;
 	}
 
-	case SIOCGSTAMP:
-		res = sock_get_timestamp(sk, argp);
-		break;
-
-	case SIOCGSTAMPNS:
-		res = sock_get_timestampns(sk, argp);
-		break;
-
 	case SIOCAX25ADDUID:	/* Add a uid to the uid/call map table */
 	case SIOCAX25DELUID:	/* Delete a uid from the uid/call map table */
 	case SIOCAX25GETUID: {
@@ -1950,6 +1942,7 @@ static const struct proto_ops ax25_proto_ops = {
 	.getname	= ax25_getname,
 	.poll		= datagram_poll,
 	.ioctl		= ax25_ioctl,
+	.gettstamp	= sock_gettstamp,
 	.listen		= ax25_listen,
 	.shutdown	= ax25_shutdown,
 	.setsockopt	= ax25_setsockopt,
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 8d12198eaa94..94ddf19998c7 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -521,14 +521,6 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		err = put_user(amount, (int __user *) arg);
 		break;
 
-	case SIOCGSTAMP:
-		err = sock_get_timestamp(sk, (struct timeval __user *) arg);
-		break;
-
-	case SIOCGSTAMPNS:
-		err = sock_get_timestampns(sk, (struct timespec __user *) arg);
-		break;
-
 	default:
 		err = -ENOIOCTLCMD;
 		break;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index a3a2cd55e23a..dcb14abebeba 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1655,6 +1655,7 @@ static const struct proto_ops l2cap_sock_ops = {
 	.recvmsg	= l2cap_sock_recvmsg,
 	.poll		= bt_sock_poll,
 	.ioctl		= bt_sock_ioctl,
+	.gettstamp	= sock_gettstamp,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,
 	.shutdown	= l2cap_sock_shutdown,
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index b1f49fcc0478..90bb53aa4bee 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -1039,6 +1039,7 @@ static const struct proto_ops rfcomm_sock_ops = {
 	.setsockopt	= rfcomm_sock_setsockopt,
 	.getsockopt	= rfcomm_sock_getsockopt,
 	.ioctl		= rfcomm_sock_ioctl,
+	.gettstamp	= sock_gettstamp,
 	.poll		= bt_sock_poll,
 	.socketpair	= sock_no_socketpair,
 	.mmap		= sock_no_mmap
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index d892b7c3cc42..b91d6b440fdf 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1190,6 +1190,7 @@ static const struct proto_ops sco_sock_ops = {
 	.recvmsg	= sco_sock_recvmsg,
 	.poll		= bt_sock_poll,
 	.ioctl		= bt_sock_ioctl,
+	.gettstamp	= sock_gettstamp,
 	.mmap		= sock_no_mmap,
 	.socketpair	= sock_no_socketpair,
 	.shutdown	= sco_sock_shutdown,
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 1684ba5b51eb..e8fd5dc1780a 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -89,13 +89,7 @@ static atomic_t skbcounter = ATOMIC_INIT(0);
 
 int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
-	struct sock *sk = sock->sk;
-
 	switch (cmd) {
-
-	case SIOCGSTAMP:
-		return sock_get_timestamp(sk, (struct timeval __user *)arg);
-
 	default:
 		return -ENOIOCTLCMD;
 	}
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 79bb8afa9c0c..a34ee52f19ea 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1689,6 +1689,7 @@ static const struct proto_ops bcm_ops = {
 	.getname       = sock_no_getname,
 	.poll          = datagram_poll,
 	.ioctl         = can_ioctl,	/* use can_ioctl() from af_can.c */
+	.gettstamp     = sock_gettstamp,
 	.listen        = sock_no_listen,
 	.shutdown      = sock_no_shutdown,
 	.setsockopt    = sock_no_setsockopt,
diff --git a/net/can/raw.c b/net/can/raw.c
index c70207537488..afcbff063a67 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -846,6 +846,7 @@ static const struct proto_ops raw_ops = {
 	.getname       = raw_getname,
 	.poll          = datagram_poll,
 	.ioctl         = can_ioctl,	/* use can_ioctl() from af_can.c */
+	.gettstamp     = sock_gettstamp,
 	.listen        = sock_no_listen,
 	.shutdown      = sock_no_shutdown,
 	.setsockopt    = raw_setsockopt,
diff --git a/net/compat.c b/net/compat.c
index eeea5eb71639..a031bd333092 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -395,63 +395,6 @@ COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname,
 	return __compat_sys_setsockopt(fd, level, optname, optval, optlen);
 }
 
-int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
-{
-	struct compat_timeval __user *ctv;
-	int err;
-	struct timeval tv;
-
-	if (COMPAT_USE_64BIT_TIME)
-		return sock_get_timestamp(sk, userstamp);
-
-	ctv = (struct compat_timeval __user *) userstamp;
-	err = -ENOENT;
-	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	tv = ktime_to_timeval(sock_read_timestamp(sk));
-
-	if (tv.tv_sec == -1)
-		return err;
-	if (tv.tv_sec == 0) {
-		ktime_t kt = ktime_get_real();
-		sock_write_timestamp(sk, kt);
-		tv = ktime_to_timeval(kt);
-	}
-	err = 0;
-	if (put_user(tv.tv_sec, &ctv->tv_sec) ||
-			put_user(tv.tv_usec, &ctv->tv_usec))
-		err = -EFAULT;
-	return err;
-}
-EXPORT_SYMBOL(compat_sock_get_timestamp);
-
-int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
-{
-	struct compat_timespec __user *ctv;
-	int err;
-	struct timespec ts;
-
-	if (COMPAT_USE_64BIT_TIME)
-		return sock_get_timestampns (sk, userstamp);
-
-	ctv = (struct compat_timespec __user *) userstamp;
-	err = -ENOENT;
-	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	ts = ktime_to_timespec(sock_read_timestamp(sk));
-	if (ts.tv_sec == -1)
-		return err;
-	if (ts.tv_sec == 0) {
-		ktime_t kt = ktime_get_real();
-		sock_write_timestamp(sk, kt);
-		ts = ktime_to_timespec(kt);
-	}
-	err = 0;
-	if (put_user(ts.tv_sec, &ctv->tv_sec) ||
-			put_user(ts.tv_nsec, &ctv->tv_nsec))
-		err = -EFAULT;
-	return err;
-}
-EXPORT_SYMBOL(compat_sock_get_timestampns);
-
 static int __compat_sys_getsockopt(int fd, int level, int optname,
 				   char __user *optval,
 				   int __user *optlen)
diff --git a/net/core/sock.c b/net/core/sock.c
index 067878a1e4c5..443b98d05f1e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2977,39 +2977,44 @@ bool lock_sock_fast(struct sock *sk)
 }
 EXPORT_SYMBOL(lock_sock_fast);
 
-int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
+int sock_gettstamp(struct socket *sock, void __user *userstamp,
+		   bool timeval, bool time32)
 {
-	struct timeval tv;
+	struct sock *sk = sock->sk;
+	struct timespec64 ts;
 
 	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	tv = ktime_to_timeval(sock_read_timestamp(sk));
-	if (tv.tv_sec == -1)
+	ts = ktime_to_timespec64(sock_read_timestamp(sk));
+	if (ts.tv_sec == -1)
 		return -ENOENT;
-	if (tv.tv_sec == 0) {
+	if (ts.tv_sec == 0) {
 		ktime_t kt = ktime_get_real();
-		sock_write_timestamp(sk, kt);
-		tv = ktime_to_timeval(kt);
+		sock_write_timestamp(sk, kt);;
+		ts = ktime_to_timespec64(kt);
 	}
-	return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0;
-}
-EXPORT_SYMBOL(sock_get_timestamp);
 
-int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
-{
-	struct timespec ts;
+	if (timeval)
+		ts.tv_nsec /= 1000;
 
-	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
-	ts = ktime_to_timespec(sock_read_timestamp(sk));
-	if (ts.tv_sec == -1)
-		return -ENOENT;
-	if (ts.tv_sec == 0) {
-		ktime_t kt = ktime_get_real();
-		sock_write_timestamp(sk, kt);
-		ts = ktime_to_timespec(sk->sk_stamp);
+#ifdef CONFIG_COMPAT_32BIT_TIME
+	if (time32)
+		return put_old_timespec32(&ts, userstamp);
+#endif
+#ifdef CONFIG_SPARC64
+	/* beware of padding in sparc64 timeval */
+	if (timeval && !in_compat_syscall()) {
+		struct __kernel_old_timeval __user tv = {
+			.tv_sec = ts.tv_sec;
+			.tv_usec = ts.tv_nsec;
+		};
+		if (copy_to_user(userstamp, &tv, sizeof(tv))
+			return -EFAULT;
+		return 0;
 	}
-	return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0;
+#endif
+	return put_timespec64(&ts, userstamp);
 }
-EXPORT_SYMBOL(sock_get_timestampns);
+EXPORT_SYMBOL(sock_gettstamp);
 
 void sock_enable_timestamp(struct sock *sk, int flag)
 {
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 26a21d97b6b0..004535e4c070 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -991,6 +991,7 @@ static const struct proto_ops inet_dccp_ops = {
 	/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
 	.poll		   = dccp_poll,
 	.ioctl		   = inet_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	/* FIXME: work on inet_listen to rename it to sock_common_listen */
 	.listen		   = inet_dccp_listen,
 	.shutdown	   = inet_shutdown,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 57d84e9b7b6f..c4e4d1301062 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -1075,6 +1075,7 @@ static const struct proto_ops inet6_dccp_ops = {
 	.getname	   = inet6_getname,
 	.poll		   = dccp_poll,
 	.ioctl		   = inet6_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = inet_dccp_listen,
 	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index bc6b912603f1..ce2dfb997537 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -164,10 +164,6 @@ static int ieee802154_sock_ioctl(struct socket *sock, unsigned int cmd,
 	struct sock *sk = sock->sk;
 
 	switch (cmd) {
-	case SIOCGSTAMP:
-		return sock_get_timestamp(sk, (struct timeval __user *)arg);
-	case SIOCGSTAMPNS:
-		return sock_get_timestampns(sk, (struct timespec __user *)arg);
 	case SIOCGIFADDR:
 	case SIOCSIFADDR:
 		return ieee802154_dev_ioctl(sk, (struct ifreq __user *)arg,
@@ -426,6 +422,7 @@ static const struct proto_ops ieee802154_raw_ops = {
 	.getname	   = sock_no_getname,
 	.poll		   = datagram_poll,
 	.ioctl		   = ieee802154_sock_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sock_no_listen,
 	.shutdown	   = sock_no_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
@@ -988,6 +985,7 @@ static const struct proto_ops ieee802154_dgram_ops = {
 	.getname	   = sock_no_getname,
 	.poll		   = datagram_poll,
 	.ioctl		   = ieee802154_sock_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sock_no_listen,
 	.shutdown	   = sock_no_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 08a8430f5647..5183a2daba64 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -915,12 +915,6 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	struct rtentry rt;
 
 	switch (cmd) {
-	case SIOCGSTAMP:
-		err = sock_get_timestamp(sk, (struct timeval __user *)arg);
-		break;
-	case SIOCGSTAMPNS:
-		err = sock_get_timestampns(sk, (struct timespec __user *)arg);
-		break;
 	case SIOCADDRT:
 	case SIOCDELRT:
 		if (copy_from_user(&rt, p, sizeof(struct rtentry)))
@@ -992,6 +986,7 @@ const struct proto_ops inet_stream_ops = {
 	.getname	   = inet_getname,
 	.poll		   = tcp_poll,
 	.ioctl		   = inet_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = inet_listen,
 	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
@@ -1027,6 +1022,7 @@ const struct proto_ops inet_dgram_ops = {
 	.getname	   = inet_getname,
 	.poll		   = udp_poll,
 	.ioctl		   = inet_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
@@ -1059,6 +1055,7 @@ static const struct proto_ops inet_sockraw_ops = {
 	.getname	   = inet_getname,
 	.poll		   = datagram_poll,
 	.ioctl		   = inet_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3d1de28aaa9e..c04ae282f4e4 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -547,12 +547,6 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	struct net *net = sock_net(sk);
 
 	switch (cmd) {
-	case SIOCGSTAMP:
-		return sock_get_timestamp(sk, (struct timeval __user *)arg);
-
-	case SIOCGSTAMPNS:
-		return sock_get_timestampns(sk, (struct timespec __user *)arg);
-
 	case SIOCADDRT:
 	case SIOCDELRT:
 
@@ -585,6 +579,7 @@ const struct proto_ops inet6_stream_ops = {
 	.getname	   = inet6_getname,
 	.poll		   = tcp_poll,			/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = inet_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
 	.setsockopt	   = sock_common_setsockopt,	/* ok		*/
@@ -618,6 +613,7 @@ const struct proto_ops inet6_dgram_ops = {
 	.getname	   = inet6_getname,
 	.poll		   = udp_poll,			/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sock_no_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
 	.setsockopt	   = sock_common_setsockopt,	/* ok		*/
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5a426226c762..84dbe21b71e5 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1356,6 +1356,7 @@ const struct proto_ops inet6_sockraw_ops = {
 	.getname	   = inet6_getname,
 	.poll		   = datagram_poll,		/* ok		*/
 	.ioctl		   = inet6_ioctl,		/* must change  */
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sock_no_listen,		/* ok		*/
 	.shutdown	   = inet_shutdown,		/* ok		*/
 	.setsockopt	   = sock_common_setsockopt,	/* ok		*/
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index d4c60523c549..2cac910c1cd4 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -618,6 +618,7 @@ static const struct proto_ops l2tp_ip_ops = {
 	.getname	   = l2tp_ip_getname,
 	.poll		   = datagram_poll,
 	.ioctl		   = inet_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 37a69df17cab..4ec546cc1dd6 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -752,6 +752,7 @@ static const struct proto_ops l2tp_ip6_ops = {
 	.getname	   = l2tp_ip6_getname,
 	.poll		   = datagram_poll,
 	.ioctl		   = inet6_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sock_no_listen,
 	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 71ffd1a6dc7c..167c09e1ea90 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1199,7 +1199,6 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
 	struct sock *sk = sock->sk;
 	void __user *argp = (void __user *)arg;
-	int ret;
 
 	switch (cmd) {
 	case TIOCOUTQ: {
@@ -1225,18 +1224,6 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		return put_user(amount, (int __user *)argp);
 	}
 
-	case SIOCGSTAMP:
-		lock_sock(sk);
-		ret = sock_get_timestamp(sk, argp);
-		release_sock(sk);
-		return ret;
-
-	case SIOCGSTAMPNS:
-		lock_sock(sk);
-		ret = sock_get_timestampns(sk, argp);
-		release_sock(sk);
-		return ret;
-
 	case SIOCGIFADDR:
 	case SIOCSIFADDR:
 	case SIOCGIFDSTADDR:
@@ -1362,6 +1349,7 @@ static const struct proto_ops nr_proto_ops = {
 	.getname	=	nr_getname,
 	.poll		=	datagram_poll,
 	.ioctl		=	nr_ioctl,
+	.gettstamp	=	sock_gettstamp,
 	.listen		=	nr_listen,
 	.shutdown	=	sock_no_shutdown,
 	.setsockopt	=	nr_setsockopt,
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 08fe8b79c0bf..5c4a118d6f96 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4075,11 +4075,6 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd,
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		return put_user(amount, (int __user *)arg);
 	}
-	case SIOCGSTAMP:
-		return sock_get_timestamp(sk, (struct timeval __user *)arg);
-	case SIOCGSTAMPNS:
-		return sock_get_timestampns(sk, (struct timespec __user *)arg);
-
 #ifdef CONFIG_INET
 	case SIOCADDRT:
 	case SIOCDELRT:
@@ -4455,6 +4450,7 @@ static const struct proto_ops packet_ops_spkt = {
 	.getname =	packet_getname_spkt,
 	.poll =		datagram_poll,
 	.ioctl =	packet_ioctl,
+	.gettstamp =	sock_gettstamp,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
 	.setsockopt =	sock_no_setsockopt,
@@ -4476,6 +4472,7 @@ static const struct proto_ops packet_ops = {
 	.getname =	packet_getname,
 	.poll =		packet_poll,
 	.ioctl =	packet_ioctl,
+	.gettstamp =	sock_gettstamp,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
 	.setsockopt =	packet_setsockopt,
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index b37e6e0a1026..7c5e8292cc0a 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -968,9 +968,6 @@ static int qrtr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 			break;
 		}
 		break;
-	case SIOCGSTAMP:
-		rc = sock_get_timestamp(sk, argp);
-		break;
 	case SIOCADDRT:
 	case SIOCDELRT:
 	case SIOCSIFADDR:
@@ -1033,6 +1030,7 @@ static const struct proto_ops qrtr_proto_ops = {
 	.recvmsg	= qrtr_recvmsg,
 	.getname	= qrtr_getname,
 	.ioctl		= qrtr_ioctl,
+	.gettstamp	= sock_gettstamp,
 	.poll		= datagram_poll,
 	.shutdown	= sock_no_shutdown,
 	.setsockopt	= sock_no_setsockopt,
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index c96f63ffe31e..e274bc6e1458 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1301,12 +1301,6 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		return put_user(amount, (unsigned int __user *) argp);
 	}
 
-	case SIOCGSTAMP:
-		return sock_get_timestamp(sk, (struct timeval __user *) argp);
-
-	case SIOCGSTAMPNS:
-		return sock_get_timestampns(sk, (struct timespec __user *) argp);
-
 	case SIOCGIFADDR:
 	case SIOCSIFADDR:
 	case SIOCGIFDSTADDR:
@@ -1474,6 +1468,7 @@ static const struct proto_ops rose_proto_ops = {
 	.getname	=	rose_getname,
 	.poll		=	datagram_poll,
 	.ioctl		=	rose_ioctl,
+	.gettstamp	=	sock_gettstamp,
 	.listen		=	rose_listen,
 	.shutdown	=	sock_no_shutdown,
 	.setsockopt	=	rose_setsockopt,
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 6200cd2b4b99..188c47eb206e 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -1030,6 +1030,7 @@ static const struct proto_ops inet6_seqpacket_ops = {
 	.getname	   = sctp_getname,
 	.poll		   = sctp_poll,
 	.ioctl		   = inet6_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sctp_inet_listen,
 	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 951afdeea5e9..f0631bf486b6 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1026,6 +1026,7 @@ static const struct proto_ops inet_seqpacket_ops = {
 	.getname	   = inet_getname,	/* Semantics are different.  */
 	.poll		   = sctp_poll,
 	.ioctl		   = inet_ioctl,
+	.gettstamp	   = sock_gettstamp,
 	.listen		   = sctp_inet_listen,
 	.shutdown	   = inet_shutdown,	/* Looks harmless.  */
 	.setsockopt	   = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */
diff --git a/net/socket.c b/net/socket.c
index 8255f5bda0aa..ab624d42ead5 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1164,6 +1164,15 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 
 			err = open_related_ns(&net->ns, get_net_ns);
 			break;
+		case SIOCGSTAMP:
+		case SIOCGSTAMPNS:
+			if (!sock->ops->gettstamp) {
+				err = -ENOIOCTLCMD;
+				break;
+			}
+			err = sock->ops->gettstamp(sock, argp,
+						   cmd == SIOCGSTAMP, false);
+			break;
 		default:
 			err = sock_do_ioctl(net, sock, cmd, arg);
 			break;
@@ -2916,38 +2925,6 @@ void socket_seq_show(struct seq_file *seq)
 #endif				/* CONFIG_PROC_FS */
 
 #ifdef CONFIG_COMPAT
-static int do_siocgstamp(struct net *net, struct socket *sock,
-			 unsigned int cmd, void __user *up)
-{
-	mm_segment_t old_fs = get_fs();
-	struct timeval ktv;
-	int err;
-
-	set_fs(KERNEL_DS);
-	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
-	set_fs(old_fs);
-	if (!err)
-		err = compat_put_timeval(&ktv, up);
-
-	return err;
-}
-
-static int do_siocgstampns(struct net *net, struct socket *sock,
-			   unsigned int cmd, void __user *up)
-{
-	mm_segment_t old_fs = get_fs();
-	struct timespec kts;
-	int err;
-
-	set_fs(KERNEL_DS);
-	err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
-	set_fs(old_fs);
-	if (!err)
-		err = compat_put_timespec(&kts, up);
-
-	return err;
-}
-
 static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32)
 {
 	struct compat_ifconf ifc32;
@@ -3348,9 +3325,12 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCDELRT:
 		return routing_ioctl(net, sock, cmd, argp);
 	case SIOCGSTAMP:
-		return do_siocgstamp(net, sock, cmd, argp);
 	case SIOCGSTAMPNS:
-		return do_siocgstampns(net, sock, cmd, argp);
+		if (!sock->ops->gettstamp)
+			return -ENOIOCTLCMD;
+		return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP,
+					    !COMPAT_USE_64BIT_TIME);
+
 	case SIOCBONDSLAVEINFOQUERY:
 	case SIOCBONDINFOQUERY:
 	case SIOCSHWTSTAMP:
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 20a511398389..0ea48a52ce79 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1398,18 +1398,6 @@ static int x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		break;
 	}
 
-	case SIOCGSTAMP:
-		rc = -EINVAL;
-		if (sk)
-			rc = sock_get_timestamp(sk,
-						(struct timeval __user *)argp);
-		break;
-	case SIOCGSTAMPNS:
-		rc = -EINVAL;
-		if (sk)
-			rc = sock_get_timestampns(sk,
-					(struct timespec __user *)argp);
-		break;
 	case SIOCGIFADDR:
 	case SIOCSIFADDR:
 	case SIOCGIFDSTADDR:
@@ -1681,8 +1669,6 @@ static int compat_x25_ioctl(struct socket *sock, unsigned int cmd,
 				unsigned long arg)
 {
 	void __user *argp = compat_ptr(arg);
-	struct sock *sk = sock->sk;
-
 	int rc = -ENOIOCTLCMD;
 
 	switch(cmd) {
@@ -1690,18 +1676,6 @@ static int compat_x25_ioctl(struct socket *sock, unsigned int cmd,
 	case TIOCINQ:
 		rc = x25_ioctl(sock, cmd, (unsigned long)argp);
 		break;
-	case SIOCGSTAMP:
-		rc = -EINVAL;
-		if (sk)
-			rc = compat_sock_get_timestamp(sk,
-					(struct timeval __user*)argp);
-		break;
-	case SIOCGSTAMPNS:
-		rc = -EINVAL;
-		if (sk)
-			rc = compat_sock_get_timestampns(sk,
-					(struct timespec __user*)argp);
-		break;
 	case SIOCGIFADDR:
 	case SIOCSIFADDR:
 	case SIOCGIFDSTADDR:
@@ -1765,6 +1739,7 @@ static const struct proto_ops x25_proto_ops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = compat_x25_ioctl,
 #endif
+	.gettstamp =	sock_gettstamp,
 	.listen =	x25_listen,
 	.shutdown =	sock_no_shutdown,
 	.setsockopt =	x25_setsockopt,
-- 
cgit v1.2.3


From 0768e17073dc527ccd18ed5f96ce85f9985e9115 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 17 Apr 2019 22:56:11 +0200
Subject: net: socket: implement 64-bit timestamps

The 'timeval' and 'timespec' data structures used for socket timestamps
are going to be redefined in user space based on 64-bit time_t in future
versions of the C library to deal with the y2038 overflow problem,
which breaks the ABI definition.

Unlike many modern ioctl commands, SIOCGSTAMP and SIOCGSTAMPNS do not
use the _IOR() macro to encode the size of the transferred data, so it
remains ambiguous whether the application uses the old or new layout.

The best workaround I could find is rather ugly: we redefine the command
code based on the size of the respective data structure with a ternary
operator. This lets it get evaluated as late as possible, hopefully after
that structure is visible to the caller. We cannot use an #ifdef here,
because inux/sockios.h might have been included before any libc header
that could determine the size of time_t.

The ioctl implementation now interprets the new command codes as always
referring to the 64-bit structure on all architectures, while the old
architecture specific command code still refers to the old architecture
specific layout. The new command number is only used when they are
actually different.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/alpha/include/uapi/asm/sockios.h  |  4 ++--
 arch/mips/include/uapi/asm/sockios.h   |  4 ++--
 arch/sh/include/uapi/asm/sockios.h     |  5 +++--
 arch/xtensa/include/uapi/asm/sockios.h |  4 ++--
 include/uapi/asm-generic/sockios.h     |  4 ++--
 include/uapi/linux/sockios.h           | 21 +++++++++++++++++++++
 net/socket.c                           | 24 ++++++++++++++++++------
 7 files changed, 50 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/include/uapi/asm/sockios.h b/arch/alpha/include/uapi/asm/sockios.h
index ba287e4b01bf..af92bc27c3be 100644
--- a/arch/alpha/include/uapi/asm/sockios.h
+++ b/arch/alpha/include/uapi/asm/sockios.h
@@ -11,7 +11,7 @@
 #define SIOCSPGRP	_IOW('s', 8, pid_t)
 #define SIOCGPGRP	_IOR('s', 9, pid_t)
 
-#define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
-#define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
+#define SIOCGSTAMP_OLD	0x8906		/* Get stamp (timeval) */
+#define SIOCGSTAMPNS_OLD 0x8907		/* Get stamp (timespec) */
 
 #endif /* _ASM_ALPHA_SOCKIOS_H */
diff --git a/arch/mips/include/uapi/asm/sockios.h b/arch/mips/include/uapi/asm/sockios.h
index 5b40a88593fa..66f60234f290 100644
--- a/arch/mips/include/uapi/asm/sockios.h
+++ b/arch/mips/include/uapi/asm/sockios.h
@@ -21,7 +21,7 @@
 #define SIOCSPGRP	_IOW('s', 8, pid_t)
 #define SIOCGPGRP	_IOR('s', 9, pid_t)
 
-#define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
-#define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
+#define SIOCGSTAMP_OLD	0x8906		/* Get stamp (timeval) */
+#define SIOCGSTAMPNS_OLD 0x8907		/* Get stamp (timespec) */
 
 #endif /* _ASM_SOCKIOS_H */
diff --git a/arch/sh/include/uapi/asm/sockios.h b/arch/sh/include/uapi/asm/sockios.h
index 17313d2c3527..ef18a668456d 100644
--- a/arch/sh/include/uapi/asm/sockios.h
+++ b/arch/sh/include/uapi/asm/sockios.h
@@ -10,6 +10,7 @@
 #define SIOCSPGRP	_IOW('s', 8, pid_t)
 #define SIOCGPGRP	_IOR('s', 9, pid_t)
 
-#define SIOCGSTAMP	_IOR('s', 100, struct timeval) /* Get stamp (timeval) */
-#define SIOCGSTAMPNS	_IOR('s', 101, struct timespec) /* Get stamp (timespec) */
+#define SIOCGSTAMP_OLD	_IOR('s', 100, struct timeval) /* Get stamp (timeval) */
+#define SIOCGSTAMPNS_OLD _IOR('s', 101, struct timespec) /* Get stamp (timespec) */
+
 #endif /* __ASM_SH_SOCKIOS_H */
diff --git a/arch/xtensa/include/uapi/asm/sockios.h b/arch/xtensa/include/uapi/asm/sockios.h
index fb8ac3607189..1a1f58f4b75a 100644
--- a/arch/xtensa/include/uapi/asm/sockios.h
+++ b/arch/xtensa/include/uapi/asm/sockios.h
@@ -26,7 +26,7 @@
 #define SIOCSPGRP	_IOW('s', 8, pid_t)
 #define SIOCGPGRP	_IOR('s', 9, pid_t)
 
-#define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
-#define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
+#define SIOCGSTAMP_OLD	0x8906		/* Get stamp (timeval) */
+#define SIOCGSTAMPNS_OLD 0x8907		/* Get stamp (timespec) */
 
 #endif	/* _XTENSA_SOCKIOS_H */
diff --git a/include/uapi/asm-generic/sockios.h b/include/uapi/asm-generic/sockios.h
index 64f658c7cec2..44fa3ed70483 100644
--- a/include/uapi/asm-generic/sockios.h
+++ b/include/uapi/asm-generic/sockios.h
@@ -8,7 +8,7 @@
 #define FIOGETOWN	0x8903
 #define SIOCGPGRP	0x8904
 #define SIOCATMARK	0x8905
-#define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
-#define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
+#define SIOCGSTAMP_OLD	0x8906		/* Get stamp (timeval) */
+#define SIOCGSTAMPNS_OLD 0x8907		/* Get stamp (timespec) */
 
 #endif /* __ASM_GENERIC_SOCKIOS_H */
diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h
index d393e9ed3964..7d1bccbbef78 100644
--- a/include/uapi/linux/sockios.h
+++ b/include/uapi/linux/sockios.h
@@ -19,6 +19,7 @@
 #ifndef _LINUX_SOCKIOS_H
 #define _LINUX_SOCKIOS_H
 
+#include <asm/bitsperlong.h>
 #include <asm/sockios.h>
 
 /* Linux-specific socket ioctls */
@@ -27,6 +28,26 @@
 
 #define SOCK_IOC_TYPE	0x89
 
+/*
+ * the timeval/timespec data structure layout is defined by libc,
+ * so we need to cover both possible versions on 32-bit.
+ */
+/* Get stamp (timeval) */
+#define SIOCGSTAMP_NEW	 _IOR(SOCK_IOC_TYPE, 0x06, long long[2])
+/* Get stamp (timespec) */
+#define SIOCGSTAMPNS_NEW _IOR(SOCK_IOC_TYPE, 0x07, long long[2])
+
+#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
+/* on 64-bit and x32, avoid the ?: operator */
+#define SIOCGSTAMP	SIOCGSTAMP_OLD
+#define SIOCGSTAMPNS	SIOCGSTAMPNS_OLD
+#else
+#define SIOCGSTAMP	((sizeof(struct timeval))  == 8 ? \
+			 SIOCGSTAMP_OLD   : SIOCGSTAMP_NEW)
+#define SIOCGSTAMPNS	((sizeof(struct timespec)) == 8 ? \
+			 SIOCGSTAMPNS_OLD : SIOCGSTAMPNS_NEW)
+#endif
+
 /* Routing table calls. */
 #define SIOCADDRT	0x890B		/* add routing table entry	*/
 #define SIOCDELRT	0x890C		/* delete routing table entry	*/
diff --git a/net/socket.c b/net/socket.c
index ab624d42ead5..8d9d4fc7d962 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1164,14 +1164,24 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 
 			err = open_related_ns(&net->ns, get_net_ns);
 			break;
-		case SIOCGSTAMP:
-		case SIOCGSTAMPNS:
+		case SIOCGSTAMP_OLD:
+		case SIOCGSTAMPNS_OLD:
 			if (!sock->ops->gettstamp) {
 				err = -ENOIOCTLCMD;
 				break;
 			}
 			err = sock->ops->gettstamp(sock, argp,
-						   cmd == SIOCGSTAMP, false);
+						   cmd == SIOCGSTAMP_OLD,
+						   !IS_ENABLED(CONFIG_64BIT));
+		case SIOCGSTAMP_NEW:
+		case SIOCGSTAMPNS_NEW:
+			if (!sock->ops->gettstamp) {
+				err = -ENOIOCTLCMD;
+				break;
+			}
+			err = sock->ops->gettstamp(sock, argp,
+						   cmd == SIOCGSTAMP_NEW,
+						   false);
 			break;
 		default:
 			err = sock_do_ioctl(net, sock, cmd, arg);
@@ -3324,11 +3334,11 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCADDRT:
 	case SIOCDELRT:
 		return routing_ioctl(net, sock, cmd, argp);
-	case SIOCGSTAMP:
-	case SIOCGSTAMPNS:
+	case SIOCGSTAMP_OLD:
+	case SIOCGSTAMPNS_OLD:
 		if (!sock->ops->gettstamp)
 			return -ENOIOCTLCMD;
-		return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP,
+		return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD,
 					    !COMPAT_USE_64BIT_TIME);
 
 	case SIOCBONDSLAVEINFOQUERY:
@@ -3348,6 +3358,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCADDDLCI:
 	case SIOCDELDLCI:
 	case SIOCGSKNS:
+	case SIOCGSTAMP_NEW:
+	case SIOCGSTAMPNS_NEW:
 		return sock_ioctl(file, cmd, arg);
 
 	case SIOCGIFFLAGS:
-- 
cgit v1.2.3


From 42e5425aa0dfd8a6cdd7e177cfd9703df05c7411 Mon Sep 17 00:00:00 2001
From: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Date: Thu, 18 Apr 2019 21:02:19 +0700
Subject: tipc: introduce new socket option TIPC_SOCK_RECVQ_USED

When using TIPC_SOCK_RECVQ_DEPTH for getsockopt(), it returns the
number of buffers in receive socket buffer which is not so helpful
for user space applications.

This commit introduces the new option TIPC_SOCK_RECVQ_USED which
returns the current allocated bytes of the receive socket buffer.
This helps user space applications dimension its buffer usage to
avoid buffer overload issue.

Signed-off-by: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc.h | 1 +
 net/tipc/socket.c         | 3 +++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h
index 6b2fd4d9655f..7df026ea6aff 100644
--- a/include/uapi/linux/tipc.h
+++ b/include/uapi/linux/tipc.h
@@ -190,6 +190,7 @@ struct sockaddr_tipc {
 #define TIPC_MCAST_REPLICAST    134     /* Default: TIPC selects. No arg */
 #define TIPC_GROUP_JOIN         135     /* Takes struct tipc_group_req* */
 #define TIPC_GROUP_LEAVE        136     /* No argument */
+#define TIPC_SOCK_RECVQ_USED    137     /* Default: none (read only) */
 
 /*
  * Flag values
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 8ac8ddf1e324..1385207a301f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -3070,6 +3070,9 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
 	case TIPC_SOCK_RECVQ_DEPTH:
 		value = skb_queue_len(&sk->sk_receive_queue);
 		break;
+	case TIPC_SOCK_RECVQ_USED:
+		value = sk_rmem_alloc_get(sk);
+		break;
 	case TIPC_GROUP_JOIN:
 		seq.type = 0;
 		if (tsk->group)
-- 
cgit v1.2.3


From 4e54507ab1a9da05238b986292f6cb702e6696c7 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 21 Apr 2019 08:49:01 -0700
Subject: ipv6: Simplify rt6_qualify_for_ecmp

After commit c7a1ce397ada ("ipv6: Change addrconf_f6i_alloc to use
ip6_route_info_create"), the gateway is no longer filled in for fib6_nh
structs in a prefix route. Accordingly, the RTF_ADDRCONF flag check can
be dropped from the 'rt6_qualify_for_ecmp'.

Further, RTF_DYNAMIC is only set in rt6_info instances, so it can be
removed from the check as well.

This reduces rt6_qualify_for_ecmp and the mlxsw version to just checking
if the nexthop has a gateway which is the real indication of whether
entries can be coalesced into a multipath route.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +-
 include/net/ip6_route.h                               | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 8f31c2ddc538..34d9053e5cf0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4928,7 +4928,7 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6)
 static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
 {
 	/* RTF_CACHE routes are ignored */
-	return !(rt->fib6_flags & RTF_ADDRCONF) && rt->fib6_nh.fib_nh_gw_family;
+	return rt->fib6_nh.fib_nh_gw_family;
 }
 
 static struct fib6_info *
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 46bbd8ff9cc6..518d97fbe074 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -68,8 +68,7 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
 
 static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i)
 {
-	return !(f6i->fib6_flags & (RTF_ADDRCONF|RTF_DYNAMIC)) &&
-		f6i->fib6_nh.fib_nh_gw_family;
+	return f6i->fib6_nh.fib_nh_gw_family;
 }
 
 void ip6_route_input(struct sk_buff *skb);
-- 
cgit v1.2.3


From be659b8d3c79afc54e087ebf8d849685d7b0d395 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 21 Apr 2019 17:39:18 -0700
Subject: ipv6: Restore RTF_ADDRCONF check in rt6_qualify_for_ecmp

The RTF_ADDRCONF flag filters out routes added by RA's in determining
which routes can be appended to an existing one to create a multipath
route. Restore the flag check and add a comment to document the RA piece.

Fixes: 4e54507ab1a9 ("ipv6: Simplify rt6_qualify_for_ecmp")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 2 +-
 include/net/ip6_route.h                               | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 34d9053e5cf0..8f31c2ddc538 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4928,7 +4928,7 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6)
 static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
 {
 	/* RTF_CACHE routes are ignored */
-	return rt->fib6_nh.fib_nh_gw_family;
+	return !(rt->fib6_flags & RTF_ADDRCONF) && rt->fib6_nh.fib_nh_gw_family;
 }
 
 static struct fib6_info *
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 518d97fbe074..df9cebc2b20c 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -68,7 +68,9 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
 
 static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i)
 {
-	return f6i->fib6_nh.fib_nh_gw_family;
+	/* the RTF_ADDRCONF flag filters out RA's */
+	return !(f6i->fib6_flags & RTF_ADDRCONF) &&
+		f6i->fib6_nh.fib_nh_gw_family;
 }
 
 void ip6_route_input(struct sk_buff *skb);
-- 
cgit v1.2.3


From 7df737e991069d75eec1ded1c8b37e81b8c54df9 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Fri, 19 Apr 2019 07:44:54 -0700
Subject: bpf: remove global variables

Move three global variables protected by bpf_verifier_lock into
'struct bpf_verifier_env' to allow parallel verification.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf_verifier.h |  5 +++++
 kernel/bpf/verifier.c        | 25 +++++++++++++------------
 2 files changed, 18 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index b3ab61fe1932..1305ccbd8fe6 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -295,6 +295,11 @@ struct bpf_verifier_env {
 	const struct bpf_line_info *prev_linfo;
 	struct bpf_verifier_log log;
 	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
+	struct {
+		int *insn_state;
+		int *insn_stack;
+		int cur_stack;
+	} cfg;
 	u32 subprog_cnt;
 	/* number of instructions analyzed by the verifier */
 	u32 insn_processed;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index db301e9b5295..5f0eb5bd5589 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5369,10 +5369,6 @@ enum {
 
 #define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L)
 
-static int *insn_stack;	/* stack of insns to process */
-static int cur_stack;	/* current stack index */
-static int *insn_state;
-
 /* t, w, e - match pseudo-code above:
  * t - index of current instruction
  * w - next instruction
@@ -5380,6 +5376,9 @@ static int *insn_state;
  */
 static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 {
+	int *insn_stack = env->cfg.insn_stack;
+	int *insn_state = env->cfg.insn_state;
+
 	if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
 		return 0;
 
@@ -5400,9 +5399,9 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
 		/* tree-edge */
 		insn_state[t] = DISCOVERED | e;
 		insn_state[w] = DISCOVERED;
-		if (cur_stack >= env->prog->len)
+		if (env->cfg.cur_stack >= env->prog->len)
 			return -E2BIG;
-		insn_stack[cur_stack++] = w;
+		insn_stack[env->cfg.cur_stack++] = w;
 		return 1;
 	} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
 		verbose_linfo(env, t, "%d: ", t);
@@ -5426,14 +5425,15 @@ static int check_cfg(struct bpf_verifier_env *env)
 {
 	struct bpf_insn *insns = env->prog->insnsi;
 	int insn_cnt = env->prog->len;
+	int *insn_stack, *insn_state;
 	int ret = 0;
 	int i, t;
 
-	insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+	insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
 	if (!insn_state)
 		return -ENOMEM;
 
-	insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+	insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
 	if (!insn_stack) {
 		kvfree(insn_state);
 		return -ENOMEM;
@@ -5441,12 +5441,12 @@ static int check_cfg(struct bpf_verifier_env *env)
 
 	insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */
 	insn_stack[0] = 0; /* 0 is the first instruction */
-	cur_stack = 1;
+	env->cfg.cur_stack = 1;
 
 peek_stack:
-	if (cur_stack == 0)
+	if (env->cfg.cur_stack == 0)
 		goto check_state;
-	t = insn_stack[cur_stack - 1];
+	t = insn_stack[env->cfg.cur_stack - 1];
 
 	if (BPF_CLASS(insns[t].code) == BPF_JMP ||
 	    BPF_CLASS(insns[t].code) == BPF_JMP32) {
@@ -5515,7 +5515,7 @@ peek_stack:
 
 mark_explored:
 	insn_state[t] = EXPLORED;
-	if (cur_stack-- <= 0) {
+	if (env->cfg.cur_stack-- <= 0) {
 		verbose(env, "pop stack internal bug\n");
 		ret = -EFAULT;
 		goto err_free;
@@ -5535,6 +5535,7 @@ check_state:
 err_free:
 	kvfree(insn_state);
 	kvfree(insn_stack);
+	env->cfg.insn_state = env->cfg.insn_stack = NULL;
 	return ret;
 }
 
-- 
cgit v1.2.3


From 0b13c9bb96f6edf03018030f07929a16b4dd77a6 Mon Sep 17 00:00:00 2001
From: "Daniel T. Lee" <danieltimlee@gmail.com>
Date: Sun, 21 Apr 2019 00:50:42 +0900
Subject: include/net/tcp.h: whitespace cleanup at tcp_v4_check

This patch makes trivial whitespace fix to the function
tcp_v4_check at include/net/tcp.h file.

It has stylistic issue, which is "space required after that ','"
and it can be confirmed with ./scripts/checkpatch.pl tool.

    ERROR: space required after that ',' (ctx:VxV)
    #29: FILE: include/net/tcp.h:1317:
    +	        return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
         	                              ^

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 68ee02523b87..7cf1181630a3 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1314,7 +1314,7 @@ static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq)
 static inline __sum16 tcp_v4_check(int len, __be32 saddr,
 				   __be32 daddr, __wsum base)
 {
-	return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
+	return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_TCP, base);
 }
 
 static inline bool tcp_checksum_complete(struct sk_buff *skb)
-- 
cgit v1.2.3


From 7e5f4cdb284be5ff862f84ccda084e2847f73fbb Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sat, 20 Apr 2019 09:27:27 -0700
Subject: ipv6: Remove fib6_info_nh_lwt

fib6_info_nh_lwt is no longer used; remove it.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 6b7557b71c8c..352f767bea81 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -450,12 +450,6 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 		 struct netlink_ext_ack *extack);
 void fib6_nh_release(struct fib6_nh *fib6_nh);
 
-static inline
-struct lwtunnel_state *fib6_info_nh_lwt(const struct fib6_info *f6i)
-{
-	return f6i->fib6_nh.fib_nh_lws;
-}
-
 void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		     unsigned int flags);
 
-- 
cgit v1.2.3


From 3c618c1dbb8859625c643121ac80af9a6723533f Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sat, 20 Apr 2019 09:28:20 -0700
Subject: net: Rename net/nexthop.h net/rtnh.h

The header contains rtnh_ macros so rename the file accordingly.
Allows a later patch to use the nexthop.h name for the new
nexthop code.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/nexthop.h    | 34 ----------------------------------
 include/net/rtnh.h       | 34 ++++++++++++++++++++++++++++++++++
 net/core/lwtunnel.c      |  2 +-
 net/decnet/dn_fib.c      |  2 +-
 net/ipv4/fib_semantics.c |  2 +-
 net/ipv4/ipmr.c          |  2 +-
 net/ipv6/route.c         |  2 +-
 net/mpls/af_mpls.c       |  2 +-
 8 files changed, 40 insertions(+), 40 deletions(-)
 delete mode 100644 include/net/nexthop.h
 create mode 100644 include/net/rtnh.h

(limited to 'include')

diff --git a/include/net/nexthop.h b/include/net/nexthop.h
deleted file mode 100644
index 902ff382a6dc..000000000000
--- a/include/net/nexthop.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __NET_NEXTHOP_H
-#define __NET_NEXTHOP_H
-
-#include <linux/rtnetlink.h>
-#include <net/netlink.h>
-
-static inline int rtnh_ok(const struct rtnexthop *rtnh, int remaining)
-{
-	return remaining >= (int)sizeof(*rtnh) &&
-	       rtnh->rtnh_len >= sizeof(*rtnh) &&
-	       rtnh->rtnh_len <= remaining;
-}
-
-static inline struct rtnexthop *rtnh_next(const struct rtnexthop *rtnh,
-                                         int *remaining)
-{
-	int totlen = NLA_ALIGN(rtnh->rtnh_len);
-
-	*remaining -= totlen;
-	return (struct rtnexthop *) ((char *) rtnh + totlen);
-}
-
-static inline struct nlattr *rtnh_attrs(const struct rtnexthop *rtnh)
-{
-	return (struct nlattr *) ((char *) rtnh + NLA_ALIGN(sizeof(*rtnh)));
-}
-
-static inline int rtnh_attrlen(const struct rtnexthop *rtnh)
-{
-	return rtnh->rtnh_len - NLA_ALIGN(sizeof(*rtnh));
-}
-
-#endif
diff --git a/include/net/rtnh.h b/include/net/rtnh.h
new file mode 100644
index 000000000000..aa2cfc508f7c
--- /dev/null
+++ b/include/net/rtnh.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_RTNH_H
+#define __NET_RTNH_H
+
+#include <linux/rtnetlink.h>
+#include <net/netlink.h>
+
+static inline int rtnh_ok(const struct rtnexthop *rtnh, int remaining)
+{
+	return remaining >= (int)sizeof(*rtnh) &&
+	       rtnh->rtnh_len >= sizeof(*rtnh) &&
+	       rtnh->rtnh_len <= remaining;
+}
+
+static inline struct rtnexthop *rtnh_next(const struct rtnexthop *rtnh,
+                                         int *remaining)
+{
+	int totlen = NLA_ALIGN(rtnh->rtnh_len);
+
+	*remaining -= totlen;
+	return (struct rtnexthop *) ((char *) rtnh + totlen);
+}
+
+static inline struct nlattr *rtnh_attrs(const struct rtnexthop *rtnh)
+{
+	return (struct nlattr *) ((char *) rtnh + NLA_ALIGN(sizeof(*rtnh)));
+}
+
+static inline int rtnh_attrlen(const struct rtnexthop *rtnh)
+{
+	return rtnh->rtnh_len - NLA_ALIGN(sizeof(*rtnh));
+}
+
+#endif
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 19b557bd294b..a8018aa5b798 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -26,7 +26,7 @@
 #include <net/lwtunnel.h>
 #include <net/rtnetlink.h>
 #include <net/ip6_fib.h>
-#include <net/nexthop.h>
+#include <net/rtnh.h>
 
 #ifdef CONFIG_MODULES
 
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 6cd3737593a6..7e47ffdd1412 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -42,7 +42,7 @@
 #include <net/dn_fib.h>
 #include <net/dn_neigh.h>
 #include <net/dn_dev.h>
-#include <net/nexthop.h>
+#include <net/rtnh.h>
 
 #define RT_MIN_TABLE 1
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 779d2be2b135..b5230c4a1c16 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -43,7 +43,7 @@
 #include <net/ip_fib.h>
 #include <net/ip6_fib.h>
 #include <net/netlink.h>
-#include <net/nexthop.h>
+#include <net/rtnh.h>
 #include <net/lwtunnel.h>
 #include <net/fib_notifier.h>
 #include <net/addrconf.h>
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9a3f13edc98e..a8eb97777c0a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -66,7 +66,7 @@
 #include <net/netlink.h>
 #include <net/fib_rules.h>
 #include <linux/netconf.h>
-#include <net/nexthop.h>
+#include <net/rtnh.h>
 
 #include <linux/nospec.h>
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e8c73b7782cd..844b16d8d6e8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -59,7 +59,7 @@
 #include <net/xfrm.h>
 #include <net/netevent.h>
 #include <net/netlink.h>
-#include <net/nexthop.h>
+#include <net/rtnh.h>
 #include <net/lwtunnel.h>
 #include <net/ip_tunnels.h>
 #include <net/l3mdev.h>
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 8120e04f15e4..e321a5fafb87 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -23,7 +23,7 @@
 #include <net/ipv6.h>
 #endif
 #include <net/ipv6_stubs.h>
-#include <net/nexthop.h>
+#include <net/rtnh.h>
 #include "internal.h"
 
 /* max memory we will use for mpls_route */
-- 
cgit v1.2.3


From a79eda3aaf30bc73752487fff5160cf67e99e313 Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Sat, 20 Apr 2019 23:29:42 -0400
Subject: net: psample: drop include of module.h from psample.h

Ideally, header files under include/linux shouldn't be adding
includes of other headers, in anticipation of their consumers,
but just the headers needed for the header itself to pass
parsing with CPP.

The module.h is particularly bad in this sense, as it itself does
include a whole bunch of other headers, due to the complexity of
module support.

There doesn't appear to be anything in psample.h that is module
related, and build coverage doesn't appear to show any other
files/drivers relying implicitly on getting it from here.

So it appears we are simply free to just remove it in this case.

Cc: Yotam Gigi <yotam.gi@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/psample.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/psample.h b/include/net/psample.h
index 9b80f814ab04..37a4df2325b2 100644
--- a/include/net/psample.h
+++ b/include/net/psample.h
@@ -3,7 +3,6 @@
 #define __NET_PSAMPLE_H
 
 #include <uapi/linux/psample.h>
-#include <linux/module.h>
 #include <linux/list.h>
 
 struct psample_group {
-- 
cgit v1.2.3


From c517796ea91d11dd3f0ae7ff61a12fe5d4941eb0 Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Sat, 20 Apr 2019 23:29:43 -0400
Subject: net: ife: drop include of module.h from net/ife.h

Ideally, header files under include/linux shouldn't be adding
includes of other headers, in anticipation of their consumers,
but just the headers needed for the header itself to pass
parsing with CPP.

The module.h is particularly bad in this sense, as it itself does
include a whole bunch of other headers, due to the complexity of
module support.

There doesn't appear to be anything in net/ife.h that is module
related, and build coverage doesn't appear to show any other
files/drivers relying implicitly on getting it from here.

So it appears we are simply free to just remove it in this case.

Cc: Yotam Gigi <yotam.gi@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ife.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ife.h b/include/net/ife.h
index e117617e3c34..7e2538d8585b 100644
--- a/include/net/ife.h
+++ b/include/net/ife.h
@@ -4,7 +4,6 @@
 
 #include <linux/etherdevice.h>
 #include <linux/rtnetlink.h>
-#include <linux/module.h>
 #include <uapi/linux/ife.h>
 
 #if IS_ENABLED(CONFIG_NET_IFE)
-- 
cgit v1.2.3


From 113e63286697893127c3ee83471b45ad0cf8d75f Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Sat, 20 Apr 2019 23:29:44 -0400
Subject: net: fib: drop include of module.h from fib_notifier.h

Ideally, header files under include/linux shouldn't be adding
includes of other headers, in anticipation of their consumers,
but just the headers needed for the header itself to pass
parsing with CPP.

The module.h is particularly bad in this sense, as it itself does
include a whole bunch of other headers, due to the complexity of
module support.

Since fib_notifier.h is not going into a module struct looking for
specific fields, we can just let it know that module is a struct,
just like about 60 other include/linux headers already do.

Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/fib_notifier.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h
index c91ec732afd6..c49d7bfb5c30 100644
--- a/include/net/fib_notifier.h
+++ b/include/net/fib_notifier.h
@@ -2,10 +2,11 @@
 #define __NET_FIB_NOTIFIER_H
 
 #include <linux/types.h>
-#include <linux/module.h>
 #include <linux/notifier.h>
 #include <net/net_namespace.h>
 
+struct module;
+
 struct fib_notifier_info {
 	struct net *net;
 	int family;
-- 
cgit v1.2.3


From a130f9b27545f56880034c345da9a4efc2ba2b24 Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Sat, 20 Apr 2019 23:29:45 -0400
Subject: net: tc_act: drop include of module.h from tc_ife.h

Ideally, header files under include/linux shouldn't be adding
includes of other headers, in anticipation of their consumers,
but just the headers needed for the header itself to pass
parsing with CPP.

The module.h is particularly bad in this sense, as it itself does
include a whole bunch of other headers, due to the complexity of
module support.

Since tc_ife.h is not going into a module struct looking for
specific fields, we can just let it know that module is a struct,
just like about 60 other include/linux headers already do.

Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tc_act/tc_ife.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h
index 86d13b01b39d..c7f24a2da1ca 100644
--- a/include/net/tc_act/tc_ife.h
+++ b/include/net/tc_act/tc_ife.h
@@ -5,7 +5,8 @@
 #include <net/act_api.h>
 #include <linux/etherdevice.h>
 #include <linux/rtnetlink.h>
-#include <linux/module.h>
+
+struct module;
 
 struct tcf_ife_params {
 	u8 eth_dst[ETH_ALEN];
-- 
cgit v1.2.3


From f2ad1a522e9817fba7799008e0a8dc6f8a32bf7d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Mon, 22 Apr 2019 12:08:39 +0000
Subject: net: devlink: Add extack to shared buffer operations

Add extack to shared buffer set operations, so that meaningful error
messages could be propagated to the user.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c       |  9 ++++++---
 drivers/net/ethernet/netronome/nfp/nfp_devlink.c |  3 ++-
 include/net/devlink.h                            |  8 +++++---
 net/core/devlink.c                               | 22 +++++++++++++---------
 4 files changed, 26 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 9e8e3e92f369..a6533d42b285 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -781,7 +781,8 @@ mlxsw_devlink_sb_pool_get(struct devlink *devlink,
 static int
 mlxsw_devlink_sb_pool_set(struct devlink *devlink,
 			  unsigned int sb_index, u16 pool_index, u32 size,
-			  enum devlink_sb_threshold_type threshold_type)
+			  enum devlink_sb_threshold_type threshold_type,
+			  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
 	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
@@ -829,7 +830,8 @@ static int mlxsw_devlink_sb_port_pool_get(struct devlink_port *devlink_port,
 
 static int mlxsw_devlink_sb_port_pool_set(struct devlink_port *devlink_port,
 					  unsigned int sb_index, u16 pool_index,
-					  u32 threshold)
+					  u32 threshold,
+					  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
 	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
@@ -864,7 +866,8 @@ static int
 mlxsw_devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
 				  unsigned int sb_index, u16 tc_index,
 				  enum devlink_sb_pool_type pool_type,
-				  u16 pool_index, u32 threshold)
+				  u16 pool_index, u32 threshold,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_core *mlxsw_core = devlink_priv(devlink_port->devlink);
 	struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index 8e7591241e7c..c50fce42f473 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -144,7 +144,8 @@ nfp_devlink_sb_pool_get(struct devlink *devlink, unsigned int sb_index,
 static int
 nfp_devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index,
 			u16 pool_index,
-			u32 size, enum devlink_sb_threshold_type threshold_type)
+			u32 size, enum devlink_sb_threshold_type threshold_type,
+			struct netlink_ext_ack *extack)
 {
 	struct nfp_pf *pf = devlink_priv(devlink);
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 70c7d1ac8344..4f5e41613503 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -491,13 +491,14 @@ struct devlink_ops {
 			   struct devlink_sb_pool_info *pool_info);
 	int (*sb_pool_set)(struct devlink *devlink, unsigned int sb_index,
 			   u16 pool_index, u32 size,
-			   enum devlink_sb_threshold_type threshold_type);
+			   enum devlink_sb_threshold_type threshold_type,
+			   struct netlink_ext_ack *extack);
 	int (*sb_port_pool_get)(struct devlink_port *devlink_port,
 				unsigned int sb_index, u16 pool_index,
 				u32 *p_threshold);
 	int (*sb_port_pool_set)(struct devlink_port *devlink_port,
 				unsigned int sb_index, u16 pool_index,
-				u32 threshold);
+				u32 threshold, struct netlink_ext_ack *extack);
 	int (*sb_tc_pool_bind_get)(struct devlink_port *devlink_port,
 				   unsigned int sb_index,
 				   u16 tc_index,
@@ -507,7 +508,8 @@ struct devlink_ops {
 				   unsigned int sb_index,
 				   u16 tc_index,
 				   enum devlink_sb_pool_type pool_type,
-				   u16 pool_index, u32 threshold);
+				   u16 pool_index, u32 threshold,
+				   struct netlink_ext_ack *extack);
 	int (*sb_occ_snapshot)(struct devlink *devlink,
 			       unsigned int sb_index);
 	int (*sb_occ_max_clear)(struct devlink *devlink,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index b2715a187a11..7b91605e75d6 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1047,14 +1047,15 @@ out:
 
 static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index,
 			       u16 pool_index, u32 size,
-			       enum devlink_sb_threshold_type threshold_type)
+			       enum devlink_sb_threshold_type threshold_type,
+			       struct netlink_ext_ack *extack)
 
 {
 	const struct devlink_ops *ops = devlink->ops;
 
 	if (ops->sb_pool_set)
 		return ops->sb_pool_set(devlink, sb_index, pool_index,
-					size, threshold_type);
+					size, threshold_type, extack);
 	return -EOPNOTSUPP;
 }
 
@@ -1082,7 +1083,8 @@ static int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb,
 
 	size = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_POOL_SIZE]);
 	return devlink_sb_pool_set(devlink, devlink_sb->index,
-				   pool_index, size, threshold_type);
+				   pool_index, size, threshold_type,
+				   info->extack);
 }
 
 static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg,
@@ -1243,14 +1245,15 @@ out:
 
 static int devlink_sb_port_pool_set(struct devlink_port *devlink_port,
 				    unsigned int sb_index, u16 pool_index,
-				    u32 threshold)
+				    u32 threshold,
+				    struct netlink_ext_ack *extack)
 
 {
 	const struct devlink_ops *ops = devlink_port->devlink->ops;
 
 	if (ops->sb_port_pool_set)
 		return ops->sb_port_pool_set(devlink_port, sb_index,
-					     pool_index, threshold);
+					     pool_index, threshold, extack);
 	return -EOPNOTSUPP;
 }
 
@@ -1273,7 +1276,7 @@ static int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb,
 
 	threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]);
 	return devlink_sb_port_pool_set(devlink_port, devlink_sb->index,
-					pool_index, threshold);
+					pool_index, threshold, info->extack);
 }
 
 static int
@@ -1472,7 +1475,8 @@ out:
 static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
 				       unsigned int sb_index, u16 tc_index,
 				       enum devlink_sb_pool_type pool_type,
-				       u16 pool_index, u32 threshold)
+				       u16 pool_index, u32 threshold,
+				       struct netlink_ext_ack *extack)
 
 {
 	const struct devlink_ops *ops = devlink_port->devlink->ops;
@@ -1480,7 +1484,7 @@ static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port,
 	if (ops->sb_tc_pool_bind_set)
 		return ops->sb_tc_pool_bind_set(devlink_port, sb_index,
 						tc_index, pool_type,
-						pool_index, threshold);
+						pool_index, threshold, extack);
 	return -EOPNOTSUPP;
 }
 
@@ -1515,7 +1519,7 @@ static int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb,
 	threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]);
 	return devlink_sb_tc_pool_bind_set(devlink_port, devlink_sb->index,
 					   tc_index, pool_type,
-					   pool_index, threshold);
+					   pool_index, threshold, info->extack);
 }
 
 static int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb,
-- 
cgit v1.2.3


From f24ea52873c726bf7b54318f00ec45050222b367 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 16 Apr 2019 16:44:37 +0200
Subject: xfrm: remove tos indirection from afinfo_policy

Only used by ipv4, we can read the fl4 tos value directly instead.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h      |  1 -
 net/ipv4/xfrm4_policy.c |  6 ------
 net/ipv6/xfrm6_policy.c |  6 ------
 net/xfrm/xfrm_policy.c  | 14 +++-----------
 4 files changed, 3 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 77eb578a0384..652da5861772 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -329,7 +329,6 @@ struct xfrm_policy_afinfo {
 	void			(*decode_session)(struct sk_buff *skb,
 						  struct flowi *fl,
 						  int reverse);
-	int			(*get_tos)(const struct flowi *fl);
 	int			(*init_path)(struct xfrm_dst *path,
 					     struct dst_entry *dst,
 					     int nfheader_len);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index d73a6d6652f6..244d26baa3af 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -69,11 +69,6 @@ static int xfrm4_get_saddr(struct net *net, int oif,
 	return 0;
 }
 
-static int xfrm4_get_tos(const struct flowi *fl)
-{
-	return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos; /* Strip ECN bits */
-}
-
 static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
 			   int nfheader_len)
 {
@@ -272,7 +267,6 @@ static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.dst_lookup =		xfrm4_dst_lookup,
 	.get_saddr =		xfrm4_get_saddr,
 	.decode_session =	_decode_session4,
-	.get_tos =		xfrm4_get_tos,
 	.init_path =		xfrm4_init_path,
 	.fill_dst =		xfrm4_fill_dst,
 	.blackhole_route =	ipv4_blackhole_route,
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 769f8f78d3b8..0e92fa2f9678 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -71,11 +71,6 @@ static int xfrm6_get_saddr(struct net *net, int oif,
 	return 0;
 }
 
-static int xfrm6_get_tos(const struct flowi *fl)
-{
-	return 0;
-}
-
 static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
 			   int nfheader_len)
 {
@@ -292,7 +287,6 @@ static const struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.dst_lookup =		xfrm6_dst_lookup,
 	.get_saddr =		xfrm6_get_saddr,
 	.decode_session =	_decode_session6,
-	.get_tos =		xfrm6_get_tos,
 	.init_path =		xfrm6_init_path,
 	.fill_dst =		xfrm6_fill_dst,
 	.blackhole_route =	ip6_blackhole_route,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 16e70fc547b1..1d1335eab76c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2450,18 +2450,10 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl,
 
 static int xfrm_get_tos(const struct flowi *fl, int family)
 {
-	const struct xfrm_policy_afinfo *afinfo;
-	int tos;
-
-	afinfo = xfrm_policy_get_afinfo(family);
-	if (!afinfo)
-		return 0;
-
-	tos = afinfo->get_tos(fl);
+	if (family == AF_INET)
+		return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos;
 
-	rcu_read_unlock();
-
-	return tos;
+	return 0;
 }
 
 static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
-- 
cgit v1.2.3


From 2e8b4aa816eaaf480fe68b1086614259caf1bf3c Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 16 Apr 2019 16:44:38 +0200
Subject: xfrm: remove init_path indirection from afinfo_policy

handle this directly, its only used by ipv6.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h      |  3 ---
 net/ipv4/xfrm4_policy.c |  7 -------
 net/ipv6/xfrm6_policy.c | 14 --------------
 net/xfrm/xfrm_policy.c  | 21 +++++++--------------
 4 files changed, 7 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 652da5861772..b8de1622141a 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -329,9 +329,6 @@ struct xfrm_policy_afinfo {
 	void			(*decode_session)(struct sk_buff *skb,
 						  struct flowi *fl,
 						  int reverse);
-	int			(*init_path)(struct xfrm_dst *path,
-					     struct dst_entry *dst,
-					     int nfheader_len);
 	int			(*fill_dst)(struct xfrm_dst *xdst,
 					    struct net_device *dev,
 					    const struct flowi *fl);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 244d26baa3af..6e89378668ae 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -69,12 +69,6 @@ static int xfrm4_get_saddr(struct net *net, int oif,
 	return 0;
 }
 
-static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
-			   int nfheader_len)
-{
-	return 0;
-}
-
 static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 			  const struct flowi *fl)
 {
@@ -267,7 +261,6 @@ static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.dst_lookup =		xfrm4_dst_lookup,
 	.get_saddr =		xfrm4_get_saddr,
 	.decode_session =	_decode_session4,
-	.init_path =		xfrm4_init_path,
 	.fill_dst =		xfrm4_fill_dst,
 	.blackhole_route =	ipv4_blackhole_route,
 };
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 0e92fa2f9678..358e834fedce 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -71,19 +71,6 @@ static int xfrm6_get_saddr(struct net *net, int oif,
 	return 0;
 }
 
-static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
-			   int nfheader_len)
-{
-	if (dst->ops->family == AF_INET6) {
-		struct rt6_info *rt = (struct rt6_info *)dst;
-		path->path_cookie = rt6_get_cookie(rt);
-	}
-
-	path->u.rt6.rt6i_nfheader_len = nfheader_len;
-
-	return 0;
-}
-
 static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 			  const struct flowi *fl)
 {
@@ -287,7 +274,6 @@ static const struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.dst_lookup =		xfrm6_dst_lookup,
 	.get_saddr =		xfrm6_get_saddr,
 	.decode_session =	_decode_session6,
-	.init_path =		xfrm6_init_path,
 	.fill_dst =		xfrm6_fill_dst,
 	.blackhole_route =	ip6_blackhole_route,
 };
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 1d1335eab76c..5359c312f016 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2491,21 +2491,14 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 	return xdst;
 }
 
-static inline int xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
-				 int nfheader_len)
+static void xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
+			   int nfheader_len)
 {
-	const struct xfrm_policy_afinfo *afinfo =
-		xfrm_policy_get_afinfo(dst->ops->family);
-	int err;
-
-	if (!afinfo)
-		return -EINVAL;
-
-	err = afinfo->init_path(path, dst, nfheader_len);
-
-	rcu_read_unlock();
-
-	return err;
+	if (dst->ops->family == AF_INET6) {
+		struct rt6_info *rt = (struct rt6_info *)dst;
+		path->path_cookie = rt6_get_cookie(rt);
+		path->u.rt6.rt6i_nfheader_len = nfheader_len;
+	}
 }
 
 static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
-- 
cgit v1.2.3


From c53ac41e3720926301c623d6682bb87ce992a3b3 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 16 Apr 2019 16:44:39 +0200
Subject: xfrm: remove decode_session indirection from afinfo_policy

No external dependencies, might as well handle this directly.
xfrm_afinfo_policy is now 40 bytes on x86_64.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h      |   3 -
 net/ipv4/xfrm4_policy.c | 114 ------------------------
 net/ipv6/xfrm6_policy.c | 106 ----------------------
 net/xfrm/xfrm_policy.c  | 231 ++++++++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 222 insertions(+), 232 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b8de1622141a..18d6b33501b9 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -326,9 +326,6 @@ struct xfrm_policy_afinfo {
 					     xfrm_address_t *saddr,
 					     xfrm_address_t *daddr,
 					     u32 mark);
-	void			(*decode_session)(struct sk_buff *skb,
-						  struct flowi *fl,
-						  int reverse);
 	int			(*fill_dst)(struct xfrm_dst *xdst,
 					    struct net_device *dev,
 					    const struct flowi *fl);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 6e89378668ae..414ab0420604 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -12,7 +12,6 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/inetdevice.h>
-#include <linux/if_tunnel.h>
 #include <net/dst.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
@@ -96,118 +95,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	return 0;
 }
 
-static void
-_decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
-{
-	const struct iphdr *iph = ip_hdr(skb);
-	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
-	struct flowi4 *fl4 = &fl->u.ip4;
-	int oif = 0;
-
-	if (skb_dst(skb))
-		oif = skb_dst(skb)->dev->ifindex;
-
-	memset(fl4, 0, sizeof(struct flowi4));
-	fl4->flowi4_mark = skb->mark;
-	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
-
-	if (!ip_is_fragment(iph)) {
-		switch (iph->protocol) {
-		case IPPROTO_UDP:
-		case IPPROTO_UDPLITE:
-		case IPPROTO_TCP:
-		case IPPROTO_SCTP:
-		case IPPROTO_DCCP:
-			if (xprth + 4 < skb->data ||
-			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				__be16 *ports;
-
-				xprth = skb_network_header(skb) + iph->ihl * 4;
-				ports = (__be16 *)xprth;
-
-				fl4->fl4_sport = ports[!!reverse];
-				fl4->fl4_dport = ports[!reverse];
-			}
-			break;
-
-		case IPPROTO_ICMP:
-			if (xprth + 2 < skb->data ||
-			    pskb_may_pull(skb, xprth + 2 - skb->data)) {
-				u8 *icmp;
-
-				xprth = skb_network_header(skb) + iph->ihl * 4;
-				icmp = xprth;
-
-				fl4->fl4_icmp_type = icmp[0];
-				fl4->fl4_icmp_code = icmp[1];
-			}
-			break;
-
-		case IPPROTO_ESP:
-			if (xprth + 4 < skb->data ||
-			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				__be32 *ehdr;
-
-				xprth = skb_network_header(skb) + iph->ihl * 4;
-				ehdr = (__be32 *)xprth;
-
-				fl4->fl4_ipsec_spi = ehdr[0];
-			}
-			break;
-
-		case IPPROTO_AH:
-			if (xprth + 8 < skb->data ||
-			    pskb_may_pull(skb, xprth + 8 - skb->data)) {
-				__be32 *ah_hdr;
-
-				xprth = skb_network_header(skb) + iph->ihl * 4;
-				ah_hdr = (__be32 *)xprth;
-
-				fl4->fl4_ipsec_spi = ah_hdr[1];
-			}
-			break;
-
-		case IPPROTO_COMP:
-			if (xprth + 4 < skb->data ||
-			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
-				__be16 *ipcomp_hdr;
-
-				xprth = skb_network_header(skb) + iph->ihl * 4;
-				ipcomp_hdr = (__be16 *)xprth;
-
-				fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
-			}
-			break;
-
-		case IPPROTO_GRE:
-			if (xprth + 12 < skb->data ||
-			    pskb_may_pull(skb, xprth + 12 - skb->data)) {
-				__be16 *greflags;
-				__be32 *gre_hdr;
-
-				xprth = skb_network_header(skb) + iph->ihl * 4;
-				greflags = (__be16 *)xprth;
-				gre_hdr = (__be32 *)xprth;
-
-				if (greflags[0] & GRE_KEY) {
-					if (greflags[0] & GRE_CSUM)
-						gre_hdr++;
-					fl4->fl4_gre_key = gre_hdr[1];
-				}
-			}
-			break;
-
-		default:
-			fl4->fl4_ipsec_spi = 0;
-			break;
-		}
-	}
-	fl4->flowi4_proto = iph->protocol;
-	fl4->daddr = reverse ? iph->saddr : iph->daddr;
-	fl4->saddr = reverse ? iph->daddr : iph->saddr;
-	fl4->flowi4_tos = iph->tos;
-}
-
 static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
 			      struct sk_buff *skb, u32 mtu)
 {
@@ -260,7 +147,6 @@ static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
 	.dst_ops =		&xfrm4_dst_ops_template,
 	.dst_lookup =		xfrm4_dst_lookup,
 	.get_saddr =		xfrm4_get_saddr,
-	.decode_session =	_decode_session4,
 	.fill_dst =		xfrm4_fill_dst,
 	.blackhole_route =	ipv4_blackhole_route,
 };
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 358e834fedce..699e0730ce8e 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -22,9 +22,6 @@
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
 #include <net/l3mdev.h>
-#if IS_ENABLED(CONFIG_IPV6_MIP6)
-#include <net/mip6.h>
-#endif
 
 static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif,
 					  const xfrm_address_t *saddr,
@@ -100,108 +97,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	return 0;
 }
 
-static inline void
-_decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
-{
-	struct flowi6 *fl6 = &fl->u.ip6;
-	int onlyproto = 0;
-	const struct ipv6hdr *hdr = ipv6_hdr(skb);
-	u32 offset = sizeof(*hdr);
-	struct ipv6_opt_hdr *exthdr;
-	const unsigned char *nh = skb_network_header(skb);
-	u16 nhoff = IP6CB(skb)->nhoff;
-	int oif = 0;
-	u8 nexthdr;
-
-	if (!nhoff)
-		nhoff = offsetof(struct ipv6hdr, nexthdr);
-
-	nexthdr = nh[nhoff];
-
-	if (skb_dst(skb))
-		oif = skb_dst(skb)->dev->ifindex;
-
-	memset(fl6, 0, sizeof(struct flowi6));
-	fl6->flowi6_mark = skb->mark;
-	fl6->flowi6_oif = reverse ? skb->skb_iif : oif;
-
-	fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
-	fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
-
-	while (nh + offset + sizeof(*exthdr) < skb->data ||
-	       pskb_may_pull(skb, nh + offset + sizeof(*exthdr) - skb->data)) {
-		nh = skb_network_header(skb);
-		exthdr = (struct ipv6_opt_hdr *)(nh + offset);
-
-		switch (nexthdr) {
-		case NEXTHDR_FRAGMENT:
-			onlyproto = 1;
-			/* fall through */
-		case NEXTHDR_ROUTING:
-		case NEXTHDR_HOP:
-		case NEXTHDR_DEST:
-			offset += ipv6_optlen(exthdr);
-			nexthdr = exthdr->nexthdr;
-			exthdr = (struct ipv6_opt_hdr *)(nh + offset);
-			break;
-
-		case IPPROTO_UDP:
-		case IPPROTO_UDPLITE:
-		case IPPROTO_TCP:
-		case IPPROTO_SCTP:
-		case IPPROTO_DCCP:
-			if (!onlyproto && (nh + offset + 4 < skb->data ||
-			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
-				__be16 *ports;
-
-				nh = skb_network_header(skb);
-				ports = (__be16 *)(nh + offset);
-				fl6->fl6_sport = ports[!!reverse];
-				fl6->fl6_dport = ports[!reverse];
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
-
-		case IPPROTO_ICMPV6:
-			if (!onlyproto && (nh + offset + 2 < skb->data ||
-			    pskb_may_pull(skb, nh + offset + 2 - skb->data))) {
-				u8 *icmp;
-
-				nh = skb_network_header(skb);
-				icmp = (u8 *)(nh + offset);
-				fl6->fl6_icmp_type = icmp[0];
-				fl6->fl6_icmp_code = icmp[1];
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
-
-#if IS_ENABLED(CONFIG_IPV6_MIP6)
-		case IPPROTO_MH:
-			offset += ipv6_optlen(exthdr);
-			if (!onlyproto && (nh + offset + 3 < skb->data ||
-			    pskb_may_pull(skb, nh + offset + 3 - skb->data))) {
-				struct ip6_mh *mh;
-
-				nh = skb_network_header(skb);
-				mh = (struct ip6_mh *)(nh + offset);
-				fl6->fl6_mh_type = mh->ip6mh_type;
-			}
-			fl6->flowi6_proto = nexthdr;
-			return;
-#endif
-
-		/* XXX Why are there these headers? */
-		case IPPROTO_AH:
-		case IPPROTO_ESP:
-		case IPPROTO_COMP:
-		default:
-			fl6->fl6_ipsec_spi = 0;
-			fl6->flowi6_proto = nexthdr;
-			return;
-		}
-	}
-}
-
 static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
 			      struct sk_buff *skb, u32 mtu)
 {
@@ -273,7 +168,6 @@ static const struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.dst_ops =		&xfrm6_dst_ops_template,
 	.dst_lookup =		xfrm6_dst_lookup,
 	.get_saddr =		xfrm6_get_saddr,
-	.decode_session =	_decode_session6,
 	.fill_dst =		xfrm6_fill_dst,
 	.blackhole_route =	ip6_blackhole_route,
 };
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5359c312f016..03b6bf85d70b 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -27,10 +27,14 @@
 #include <linux/cpu.h>
 #include <linux/audit.h>
 #include <linux/rhashtable.h>
+#include <linux/if_tunnel.h>
 #include <net/dst.h>
 #include <net/flow.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+#include <net/mip6.h>
+#endif
 #ifdef CONFIG_XFRM_STATISTICS
 #include <net/snmp.h>
 #endif
@@ -3256,20 +3260,229 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star
 	return start;
 }
 
+static void
+decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
+	struct flowi4 *fl4 = &fl->u.ip4;
+	int oif = 0;
+
+	if (skb_dst(skb))
+		oif = skb_dst(skb)->dev->ifindex;
+
+	memset(fl4, 0, sizeof(struct flowi4));
+	fl4->flowi4_mark = skb->mark;
+	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
+
+	if (!ip_is_fragment(iph)) {
+		switch (iph->protocol) {
+		case IPPROTO_UDP:
+		case IPPROTO_UDPLITE:
+		case IPPROTO_TCP:
+		case IPPROTO_SCTP:
+		case IPPROTO_DCCP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be16 *ports;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ports = (__be16 *)xprth;
+
+				fl4->fl4_sport = ports[!!reverse];
+				fl4->fl4_dport = ports[!reverse];
+			}
+			break;
+		case IPPROTO_ICMP:
+			if (xprth + 2 < skb->data ||
+			    pskb_may_pull(skb, xprth + 2 - skb->data)) {
+				u8 *icmp;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				icmp = xprth;
+
+				fl4->fl4_icmp_type = icmp[0];
+				fl4->fl4_icmp_code = icmp[1];
+			}
+			break;
+		case IPPROTO_ESP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be32 *ehdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ehdr = (__be32 *)xprth;
+
+				fl4->fl4_ipsec_spi = ehdr[0];
+			}
+			break;
+		case IPPROTO_AH:
+			if (xprth + 8 < skb->data ||
+			    pskb_may_pull(skb, xprth + 8 - skb->data)) {
+				__be32 *ah_hdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ah_hdr = (__be32 *)xprth;
+
+				fl4->fl4_ipsec_spi = ah_hdr[1];
+			}
+			break;
+		case IPPROTO_COMP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be16 *ipcomp_hdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ipcomp_hdr = (__be16 *)xprth;
+
+				fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
+			}
+			break;
+		case IPPROTO_GRE:
+			if (xprth + 12 < skb->data ||
+			    pskb_may_pull(skb, xprth + 12 - skb->data)) {
+				__be16 *greflags;
+				__be32 *gre_hdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				greflags = (__be16 *)xprth;
+				gre_hdr = (__be32 *)xprth;
+
+				if (greflags[0] & GRE_KEY) {
+					if (greflags[0] & GRE_CSUM)
+						gre_hdr++;
+					fl4->fl4_gre_key = gre_hdr[1];
+				}
+			}
+			break;
+		default:
+			fl4->fl4_ipsec_spi = 0;
+			break;
+		}
+	}
+	fl4->flowi4_proto = iph->protocol;
+	fl4->daddr = reverse ? iph->saddr : iph->daddr;
+	fl4->saddr = reverse ? iph->daddr : iph->saddr;
+	fl4->flowi4_tos = iph->tos;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static void
+decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
+{
+	struct flowi6 *fl6 = &fl->u.ip6;
+	int onlyproto = 0;
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
+	u32 offset = sizeof(*hdr);
+	struct ipv6_opt_hdr *exthdr;
+	const unsigned char *nh = skb_network_header(skb);
+	u16 nhoff = IP6CB(skb)->nhoff;
+	int oif = 0;
+	u8 nexthdr;
+
+	if (!nhoff)
+		nhoff = offsetof(struct ipv6hdr, nexthdr);
+
+	nexthdr = nh[nhoff];
+
+	if (skb_dst(skb))
+		oif = skb_dst(skb)->dev->ifindex;
+
+	memset(fl6, 0, sizeof(struct flowi6));
+	fl6->flowi6_mark = skb->mark;
+	fl6->flowi6_oif = reverse ? skb->skb_iif : oif;
+
+	fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
+	fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
+
+	while (nh + offset + sizeof(*exthdr) < skb->data ||
+	       pskb_may_pull(skb, nh + offset + sizeof(*exthdr) - skb->data)) {
+		nh = skb_network_header(skb);
+		exthdr = (struct ipv6_opt_hdr *)(nh + offset);
+
+		switch (nexthdr) {
+		case NEXTHDR_FRAGMENT:
+			onlyproto = 1;
+			/* fall through */
+		case NEXTHDR_ROUTING:
+		case NEXTHDR_HOP:
+		case NEXTHDR_DEST:
+			offset += ipv6_optlen(exthdr);
+			nexthdr = exthdr->nexthdr;
+			exthdr = (struct ipv6_opt_hdr *)(nh + offset);
+			break;
+		case IPPROTO_UDP:
+		case IPPROTO_UDPLITE:
+		case IPPROTO_TCP:
+		case IPPROTO_SCTP:
+		case IPPROTO_DCCP:
+			if (!onlyproto && (nh + offset + 4 < skb->data ||
+			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
+				__be16 *ports;
+
+				nh = skb_network_header(skb);
+				ports = (__be16 *)(nh + offset);
+				fl6->fl6_sport = ports[!!reverse];
+				fl6->fl6_dport = ports[!reverse];
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+		case IPPROTO_ICMPV6:
+			if (!onlyproto && (nh + offset + 2 < skb->data ||
+			    pskb_may_pull(skb, nh + offset + 2 - skb->data))) {
+				u8 *icmp;
+
+				nh = skb_network_header(skb);
+				icmp = (u8 *)(nh + offset);
+				fl6->fl6_icmp_type = icmp[0];
+				fl6->fl6_icmp_code = icmp[1];
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+		case IPPROTO_MH:
+			offset += ipv6_optlen(exthdr);
+			if (!onlyproto && (nh + offset + 3 < skb->data ||
+			    pskb_may_pull(skb, nh + offset + 3 - skb->data))) {
+				struct ip6_mh *mh;
+
+				nh = skb_network_header(skb);
+				mh = (struct ip6_mh *)(nh + offset);
+				fl6->fl6_mh_type = mh->ip6mh_type;
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+#endif
+		/* XXX Why are there these headers? */
+		case IPPROTO_AH:
+		case IPPROTO_ESP:
+		case IPPROTO_COMP:
+		default:
+			fl6->fl6_ipsec_spi = 0;
+			fl6->flowi6_proto = nexthdr;
+			return;
+		}
+	}
+}
+#endif
+
 int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
 			  unsigned int family, int reverse)
 {
-	const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
-	int err;
-
-	if (unlikely(afinfo == NULL))
+	switch (family) {
+	case AF_INET:
+		decode_session4(skb, fl, reverse);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		decode_session6(skb, fl, reverse);
+		break;
+#endif
+	default:
 		return -EAFNOSUPPORT;
+	}
 
-	afinfo->decode_session(skb, fl, reverse);
-
-	err = security_xfrm_decode_session(skb, &fl->flowi_secid);
-	rcu_read_unlock();
-	return err;
+	return security_xfrm_decode_session(skb, &fl->flowi_secid);
 }
 EXPORT_SYMBOL(__xfrm_decode_session);
 
-- 
cgit v1.2.3


From bb9cd077e216b886438c5698e1cd75f762ecd3c9 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 17 Apr 2019 11:45:13 +0200
Subject: xfrm: remove unneeded export_symbols

None of them have any external callers, make them static.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h        | 2 --
 net/ipv4/xfrm4_protocol.c | 3 +--
 net/ipv6/xfrm6_protocol.c | 3 +--
 net/xfrm/xfrm_state.c     | 5 ++---
 4 files changed, 4 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 18d6b33501b9..eb5018b1cf9c 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1568,7 +1568,6 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
 int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb);
 int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb);
-int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err);
 int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol);
 int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol);
 int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family);
@@ -1584,7 +1583,6 @@ int xfrm6_rcv(struct sk_buff *skb);
 int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
 		     xfrm_address_t *saddr, u8 proto);
 void xfrm6_local_error(struct sk_buff *skb, u32 mtu);
-int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err);
 int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol);
 int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol);
 int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family);
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index 35c54865dc42..bcab48944c15 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/net/ipv4/xfrm4_protocol.c
@@ -46,7 +46,7 @@ static inline struct xfrm4_protocol __rcu **proto_handlers(u8 protocol)
 	     handler != NULL;				\
 	     handler = rcu_dereference(handler->next))	\
 
-int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
+static int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
 {
 	int ret;
 	struct xfrm4_protocol *handler;
@@ -61,7 +61,6 @@ int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
 
 	return 0;
 }
-EXPORT_SYMBOL(xfrm4_rcv_cb);
 
 int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
 		    int encap_type)
diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c
index cc979b702c89..aaacac7fdbce 100644
--- a/net/ipv6/xfrm6_protocol.c
+++ b/net/ipv6/xfrm6_protocol.c
@@ -46,7 +46,7 @@ static inline struct xfrm6_protocol __rcu **proto_handlers(u8 protocol)
 	     handler != NULL;				\
 	     handler = rcu_dereference(handler->next))	\
 
-int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
+static int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
 {
 	int ret;
 	struct xfrm6_protocol *handler;
@@ -61,7 +61,6 @@ int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
 
 	return 0;
 }
-EXPORT_SYMBOL(xfrm6_rcv_cb);
 
 static int xfrm6_esp_rcv(struct sk_buff *skb)
 {
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index d3d87c409f44..ed25eb81aabe 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -173,7 +173,7 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock);
 int __xfrm_state_delete(struct xfrm_state *x);
 
 int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol);
-bool km_is_alive(const struct km_event *c);
+static bool km_is_alive(const struct km_event *c);
 void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
 
 static DEFINE_SPINLOCK(xfrm_type_lock);
@@ -2025,7 +2025,7 @@ int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address
 }
 EXPORT_SYMBOL(km_report);
 
-bool km_is_alive(const struct km_event *c)
+static bool km_is_alive(const struct km_event *c)
 {
 	struct xfrm_mgr *km;
 	bool is_alive = false;
@@ -2041,7 +2041,6 @@ bool km_is_alive(const struct km_event *c)
 
 	return is_alive;
 }
-EXPORT_SYMBOL(km_is_alive);
 
 int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
 {
-- 
cgit v1.2.3


From 756e161993824961fad4ba62c40045d9ab65bdb8 Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Fri, 8 Mar 2019 09:15:43 +0800
Subject: mmc: add SDIO identifiers for MediaTek Bluetooth devices

The SDIO identifier for MediaTek Bluetooth devices were defined in the
MediaTek Bluetooth driver. Moving the definitions in MMC header file
seems common sense.

Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/mmc/sdio_ids.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index 4332199c71c2..d1a5d5df02f5 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -59,6 +59,8 @@
 #define SDIO_DEVICE_ID_MARVELL_8797_F0		0x9128
 #define SDIO_DEVICE_ID_MARVELL_8887WLAN	0x9134
 
+#define SDIO_VENDOR_ID_MEDIATEK			0x037a
+
 #define SDIO_VENDOR_ID_SIANO			0x039a
 #define SDIO_DEVICE_ID_SIANO_NOVA_B0		0x0201
 #define SDIO_DEVICE_ID_SIANO_NICE		0x0202
-- 
cgit v1.2.3


From db0a390835209c1c5dce7669de3d23a8cba10f34 Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Thu, 14 Mar 2019 05:01:58 +0800
Subject: mmc: sdio: Add helper macro for sdio_driver boilerplate

This patch introduces the module_sdio_driver macro which is a convenience
macro for SDIO driver modules similar to module_usb_driver. It is intended
to be used by drivers which init/exit section does nothing but register/
unregister the SDIO driver. By using this macro it is possible to eliminate
a few lines of boilerplate code per SDIO driver.

Suggested-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/mmc/sdio_func.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h
index 97ca105347a6..5685805533b5 100644
--- a/include/linux/mmc/sdio_func.h
+++ b/include/linux/mmc/sdio_func.h
@@ -111,6 +111,18 @@ struct sdio_driver {
 extern int sdio_register_driver(struct sdio_driver *);
 extern void sdio_unregister_driver(struct sdio_driver *);
 
+/**
+ * module_sdio_driver() - Helper macro for registering a SDIO driver
+ * @__sdio_driver: sdio_driver struct
+ *
+ * Helper macro for SDIO drivers which do not do anything special in module
+ * init/exit. This eliminates a lot of boilerplate. Each module may only
+ * use this macro once, and calling it replaces module_init() and module_exit()
+ */
+#define module_sdio_driver(__sdio_driver) \
+	module_driver(__sdio_driver, sdio_register_driver, \
+		      sdio_unregister_driver)
+
 /*
  * SDIO I/O operations
  */
-- 
cgit v1.2.3


From 089b19a9204fc090793d389a265f54124eacb05d Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 22 Apr 2019 08:55:44 -0700
Subject: flow_dissector: switch kernel context to struct bpf_flow_dissector

struct bpf_flow_dissector has a small subset of sk_buff fields that
flow dissector BPF program is allowed to access and an optional
pointer to real skb. Real skb is used only in bpf_skb_load_bytes
helper to read non-linear data.

The real motivation for this is to be able to call flow dissector
from eth_get_headlen context where we don't have an skb and need
to dissect raw bytes.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/skbuff.h       |   4 ++
 include/net/flow_dissector.h |   7 +++
 include/net/sch_generic.h    |  11 ++---
 net/bpf/test_run.c           |   4 --
 net/core/filter.c            | 105 +++++++++++++++++++++++++++++++++----------
 net/core/flow_dissector.c    |  45 +++++++++----------
 6 files changed, 117 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6f42942a443b..2b7b8228c5c3 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1275,6 +1275,10 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr)
 }
 #endif
 
+struct bpf_flow_dissector;
+bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
+		      __be16 proto, int nhoff, int hlen);
+
 struct bpf_flow_keys;
 bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
 			    const struct sk_buff *skb,
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 2b26979efb48..7c5a8d9a8d2a 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -305,4 +305,11 @@ static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissec
 	return ((char *)target_container) + flow_dissector->offset[key_id];
 }
 
+struct bpf_flow_dissector {
+	struct bpf_flow_keys	*flow_keys;
+	const struct sk_buff	*skb;
+	void			*data;
+	void			*data_end;
+};
+
 #endif
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index e8f85cd2afce..21f434f3ac9e 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -364,13 +364,10 @@ struct tcf_proto {
 };
 
 struct qdisc_skb_cb {
-	union {
-		struct {
-			unsigned int		pkt_len;
-			u16			slave_dev_queue_mapping;
-			u16			tc_classid;
-		};
-		struct bpf_flow_keys *flow_keys;
+	struct {
+		unsigned int		pkt_len;
+		u16			slave_dev_queue_mapping;
+		u16			tc_classid;
 	};
 #define QDISC_CB_PRIV_LEN 20
 	unsigned char		data[QDISC_CB_PRIV_LEN];
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 2221573dacdb..006ad865f7fb 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -382,7 +382,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	u32 repeat = kattr->test.repeat;
 	struct bpf_flow_keys flow_keys;
 	u64 time_start, time_spent = 0;
-	struct bpf_skb_data_end *cb;
 	u32 retval, duration;
 	struct sk_buff *skb;
 	struct sock *sk;
@@ -423,9 +422,6 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 				       current->nsproxy->net_ns->loopback_dev);
 	skb_reset_network_header(skb);
 
-	cb = (struct bpf_skb_data_end *)skb->cb;
-	cb->qdisc_cb.flow_keys = &flow_keys;
-
 	if (!repeat)
 		repeat = 1;
 
diff --git a/net/core/filter.c b/net/core/filter.c
index fa8fb0548217..edb3a7c22f6c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1730,6 +1730,40 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_4(bpf_flow_dissector_load_bytes,
+	   const struct bpf_flow_dissector *, ctx, u32, offset,
+	   void *, to, u32, len)
+{
+	void *ptr;
+
+	if (unlikely(offset > 0xffff))
+		goto err_clear;
+
+	if (unlikely(!ctx->skb))
+		goto err_clear;
+
+	ptr = skb_header_pointer(ctx->skb, offset, len, to);
+	if (unlikely(!ptr))
+		goto err_clear;
+	if (ptr != to)
+		memcpy(to, ptr, len);
+
+	return 0;
+err_clear:
+	memset(to, 0, len);
+	return -EFAULT;
+}
+
+static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = {
+	.func		= bpf_flow_dissector_load_bytes,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
 BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb,
 	   u32, offset, void *, to, u32, len, u32, start_header)
 {
@@ -6121,7 +6155,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
 	case BPF_FUNC_skb_load_bytes:
-		return &bpf_skb_load_bytes_proto;
+		return &bpf_flow_dissector_load_bytes_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6248,9 +6282,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
 			return false;
 		break;
 	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
-		if (size != sizeof(__u64))
-			return false;
-		break;
+		return false;
 	case bpf_ctx_range(struct __sk_buff, tstamp):
 		if (size != sizeof(__u64))
 			return false;
@@ -6285,7 +6317,6 @@ static bool sk_filter_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, data_end):
-	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 	case bpf_ctx_range(struct __sk_buff, tstamp):
 	case bpf_ctx_range(struct __sk_buff, wire_len):
@@ -6312,7 +6343,6 @@ static bool cg_skb_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
@@ -6358,7 +6388,6 @@ static bool lwt_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range(struct __sk_buff, tstamp):
 	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
@@ -6601,7 +6630,6 @@ static bool tc_cls_act_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_end):
 		info->reg_type = PTR_TO_PACKET_END;
 		break;
-	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
 		return false;
 	}
@@ -6803,7 +6831,6 @@ static bool sk_skb_is_valid_access(int off, int size,
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, tc_classid):
 	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 	case bpf_ctx_range(struct __sk_buff, tstamp):
 	case bpf_ctx_range(struct __sk_buff, wire_len):
 		return false;
@@ -6877,24 +6904,65 @@ static bool flow_dissector_is_valid_access(int off, int size,
 					   const struct bpf_prog *prog,
 					   struct bpf_insn_access_aux *info)
 {
+	const int size_default = sizeof(__u32);
+
+	if (off < 0 || off >= sizeof(struct __sk_buff))
+		return false;
+
 	if (type == BPF_WRITE)
 		return false;
 
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, data):
+		if (size != size_default)
+			return false;
 		info->reg_type = PTR_TO_PACKET;
-		break;
+		return true;
 	case bpf_ctx_range(struct __sk_buff, data_end):
+		if (size != size_default)
+			return false;
 		info->reg_type = PTR_TO_PACKET_END;
-		break;
+		return true;
 	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
+		if (size != sizeof(__u64))
+			return false;
 		info->reg_type = PTR_TO_FLOW_KEYS;
-		break;
+		return true;
 	default:
 		return false;
 	}
+}
 
-	return bpf_skb_is_valid_access(off, size, type, prog, info);
+static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type,
+					     const struct bpf_insn *si,
+					     struct bpf_insn *insn_buf,
+					     struct bpf_prog *prog,
+					     u32 *target_size)
+
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct __sk_buff, data):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_flow_dissector, data));
+		break;
+
+	case offsetof(struct __sk_buff, data_end):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data_end),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_flow_dissector, data_end));
+		break;
+
+	case offsetof(struct __sk_buff, flow_keys):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, flow_keys),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_flow_dissector, flow_keys));
+		break;
+	}
+
+	return insn - insn_buf;
 }
 
 static u32 bpf_convert_ctx_access(enum bpf_access_type type,
@@ -7201,15 +7269,6 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 						     skc_num, 2, target_size));
 		break;
 
-	case offsetof(struct __sk_buff, flow_keys):
-		off  = si->off;
-		off -= offsetof(struct __sk_buff, flow_keys);
-		off += offsetof(struct sk_buff, cb);
-		off += offsetof(struct qdisc_skb_cb, flow_keys);
-		*insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg,
-				      si->src_reg, off);
-		break;
-
 	case offsetof(struct __sk_buff, tstamp):
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8);
 
@@ -8214,7 +8273,7 @@ const struct bpf_prog_ops sk_msg_prog_ops = {
 const struct bpf_verifier_ops flow_dissector_verifier_ops = {
 	.get_func_proto		= flow_dissector_func_proto,
 	.is_valid_access	= flow_dissector_is_valid_access,
-	.convert_ctx_access	= bpf_convert_ctx_access,
+	.convert_ctx_access	= flow_dissector_convert_ctx_access,
 };
 
 const struct bpf_prog_ops flow_dissector_prog_ops = {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 795449713ba4..ef6d9443cc75 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -688,39 +688,34 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
 			    struct flow_dissector *flow_dissector,
 			    struct bpf_flow_keys *flow_keys)
 {
-	struct bpf_skb_data_end cb_saved;
-	struct bpf_skb_data_end *cb;
-	u32 result;
-
-	/* Note that even though the const qualifier is discarded
-	 * throughout the execution of the BPF program, all changes(the
-	 * control block) are reverted after the BPF program returns.
-	 * Therefore, __skb_flow_dissect does not alter the skb.
-	 */
-
-	cb = (struct bpf_skb_data_end *)skb->cb;
+	struct bpf_flow_dissector ctx = {
+		.flow_keys = flow_keys,
+		.skb = skb,
+		.data = skb->data,
+		.data_end = skb->data + skb_headlen(skb),
+	};
+
+	return bpf_flow_dissect(prog, &ctx, skb->protocol,
+				skb_network_offset(skb), skb_headlen(skb));
+}
 
-	/* Save Control Block */
-	memcpy(&cb_saved, cb, sizeof(cb_saved));
-	memset(cb, 0, sizeof(*cb));
+bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
+		      __be16 proto, int nhoff, int hlen)
+{
+	struct bpf_flow_keys *flow_keys = ctx->flow_keys;
+	u32 result;
 
 	/* Pass parameters to the BPF program */
 	memset(flow_keys, 0, sizeof(*flow_keys));
-	cb->qdisc_cb.flow_keys = flow_keys;
-	flow_keys->n_proto = skb->protocol;
-	flow_keys->nhoff = skb_network_offset(skb);
+	flow_keys->n_proto = proto;
+	flow_keys->nhoff = nhoff;
 	flow_keys->thoff = flow_keys->nhoff;
 
-	bpf_compute_data_pointers((struct sk_buff *)skb);
-	result = BPF_PROG_RUN(prog, skb);
-
-	/* Restore state */
-	memcpy(cb, &cb_saved, sizeof(cb_saved));
+	result = BPF_PROG_RUN(prog, ctx);
 
-	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff,
-				   skb_network_offset(skb), skb->len);
+	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen);
 	flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
-				   flow_keys->nhoff, skb->len);
+				   flow_keys->nhoff, hlen);
 
 	return result == BPF_OK;
 }
-- 
cgit v1.2.3


From 3cbf4ffba5eeec60f82868a5facc1962d8a44d00 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 22 Apr 2019 08:55:46 -0700
Subject: net: plumb network namespace into __skb_flow_dissect

This new argument will be used in the next patches for the
eth_get_headlen use case. eth_get_headlen calls flow dissector
with only data (without skb) so there is currently no way to
pull attached BPF flow dissector program. With this new argument,
we can amend the callers to explicitly pass network namespace
so we can use attached BPF program.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/skbuff.h    | 19 +++++++++++--------
 net/core/flow_dissector.c | 27 +++++++++++++++++----------
 net/ethernet/eth.c        |  5 +++--
 3 files changed, 31 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2b7b8228c5c3..b466fbface2e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1284,7 +1284,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
 			    const struct sk_buff *skb,
 			    struct flow_dissector *flow_dissector,
 			    struct bpf_flow_keys *flow_keys);
-bool __skb_flow_dissect(const struct sk_buff *skb,
+bool __skb_flow_dissect(const struct net *net,
+			const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
 			void *target_container,
 			void *data, __be16 proto, int nhoff, int hlen,
@@ -1294,8 +1295,8 @@ static inline bool skb_flow_dissect(const struct sk_buff *skb,
 				    struct flow_dissector *flow_dissector,
 				    void *target_container, unsigned int flags)
 {
-	return __skb_flow_dissect(skb, flow_dissector, target_container,
-				  NULL, 0, 0, 0, flags);
+	return __skb_flow_dissect(NULL, skb, flow_dissector,
+				  target_container, NULL, 0, 0, 0, flags);
 }
 
 static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
@@ -1303,18 +1304,19 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb,
 					      unsigned int flags)
 {
 	memset(flow, 0, sizeof(*flow));
-	return __skb_flow_dissect(skb, &flow_keys_dissector, flow,
-				  NULL, 0, 0, 0, flags);
+	return __skb_flow_dissect(NULL, skb, &flow_keys_dissector,
+				  flow, NULL, 0, 0, 0, flags);
 }
 
 static inline bool
-skb_flow_dissect_flow_keys_basic(const struct sk_buff *skb,
+skb_flow_dissect_flow_keys_basic(const struct net *net,
+				 const struct sk_buff *skb,
 				 struct flow_keys_basic *flow, void *data,
 				 __be16 proto, int nhoff, int hlen,
 				 unsigned int flags)
 {
 	memset(flow, 0, sizeof(*flow));
-	return __skb_flow_dissect(skb, &flow_keys_basic_dissector, flow,
+	return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow,
 				  data, proto, nhoff, hlen, flags);
 }
 
@@ -2492,7 +2494,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb)
 	if (skb_transport_header_was_set(skb))
 		return;
 
-	if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0))
+	if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
+					     NULL, 0, 0, 0, 0))
 		skb_set_transport_header(skb, keys.control.thoff);
 }
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index ef6d9443cc75..f32c7e737fc6 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -722,6 +722,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
 
 /**
  * __skb_flow_dissect - extract the flow_keys struct and return it
+ * @net: associated network namespace, derived from @skb if NULL
  * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
  * @flow_dissector: list of keys to dissect
  * @target_container: target structure to put dissected values into
@@ -738,7 +739,8 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
  *
  * Caller must take care of zeroing target container memory.
  */
-bool __skb_flow_dissect(const struct sk_buff *skb,
+bool __skb_flow_dissect(const struct net *net,
+			const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
 			void *target_container,
 			void *data, __be16 proto, int nhoff, int hlen,
@@ -797,13 +799,17 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 		struct bpf_prog *attached = NULL;
 
 		rcu_read_lock();
+		if (!net) {
+			if (skb->dev)
+				net = dev_net(skb->dev);
+			else if (skb->sk)
+				net = sock_net(skb->sk);
+			else
+				WARN_ON_ONCE(1);
+		}
 
-		if (skb->dev)
-			attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog);
-		else if (skb->sk)
-			attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog);
-		else
-			WARN_ON_ONCE(1);
+		if (net)
+			attached = rcu_dereference(net->flow_dissector_prog);
 
 		if (attached) {
 			ret = __skb_flow_bpf_dissect(attached, skb,
@@ -1405,8 +1411,8 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
 	__flow_hash_secret_init();
 
 	memset(&keys, 0, sizeof(keys));
-	__skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys,
-			   NULL, 0, 0, 0,
+	__skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric,
+			   &keys, NULL, 0, 0, 0,
 			   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
 
 	return __flow_hash_from_keys(&keys, hashrnd);
@@ -1507,7 +1513,8 @@ u32 skb_get_poff(const struct sk_buff *skb)
 {
 	struct flow_keys_basic keys;
 
-	if (!skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0))
+	if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
+					      NULL, 0, 0, 0, 0))
 		return 0;
 
 	return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index f7a3d7a171c7..1e439549c419 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -136,8 +136,9 @@ u32 eth_get_headlen(void *data, unsigned int len)
 		return len;
 
 	/* parse any remaining L2/L3 headers, check for L4 */
-	if (!skb_flow_dissect_flow_keys_basic(NULL, &keys, data, eth->h_proto,
-					      sizeof(*eth), len, flags))
+	if (!skb_flow_dissect_flow_keys_basic(NULL, NULL, &keys, data,
+					      eth->h_proto, sizeof(*eth),
+					      len, flags))
 		return max_t(u32, keys.control.thoff, sizeof(*eth));
 
 	/* parse for any L4 headers */
-- 
cgit v1.2.3


From 9b52e3f267a6835efd50ed9002d530666d16a411 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 22 Apr 2019 08:55:47 -0700
Subject: flow_dissector: handle no-skb use case

When called without skb, gather all required data from the
__skb_flow_dissect's arguments and use recently introduces
no-skb mode of bpf flow dissector.

Note: WARN_ON_ONCE(!net) will now trigger for eth_get_headlen users.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/skbuff.h    |  5 -----
 net/core/flow_dissector.c | 52 +++++++++++++++++++++++------------------------
 2 files changed, 25 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b466fbface2e..998256c2820b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1279,11 +1279,6 @@ struct bpf_flow_dissector;
 bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
 		      __be16 proto, int nhoff, int hlen);
 
-struct bpf_flow_keys;
-bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
-			    const struct sk_buff *skb,
-			    struct flow_dissector *flow_dissector,
-			    struct bpf_flow_keys *flow_keys);
 bool __skb_flow_dissect(const struct net *net,
 			const struct sk_buff *skb,
 			struct flow_dissector *flow_dissector,
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index f32c7e737fc6..fac712cee9d5 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -683,22 +683,6 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys,
 	}
 }
 
-bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
-			    const struct sk_buff *skb,
-			    struct flow_dissector *flow_dissector,
-			    struct bpf_flow_keys *flow_keys)
-{
-	struct bpf_flow_dissector ctx = {
-		.flow_keys = flow_keys,
-		.skb = skb,
-		.data = skb->data,
-		.data_end = skb->data + skb_headlen(skb),
-	};
-
-	return bpf_flow_dissect(prog, &ctx, skb->protocol,
-				skb_network_offset(skb), skb_headlen(skb));
-}
-
 bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx,
 		      __be16 proto, int nhoff, int hlen)
 {
@@ -753,6 +737,7 @@ bool __skb_flow_dissect(const struct net *net,
 	struct flow_dissector_key_icmp *key_icmp;
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
+	struct bpf_prog *attached = NULL;
 	enum flow_dissect_ret fdret;
 	enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
 	int num_hdrs = 0;
@@ -795,26 +780,39 @@ bool __skb_flow_dissect(const struct net *net,
 					      target_container);
 
 	if (skb) {
-		struct bpf_flow_keys flow_keys;
-		struct bpf_prog *attached = NULL;
-
-		rcu_read_lock();
 		if (!net) {
 			if (skb->dev)
 				net = dev_net(skb->dev);
 			else if (skb->sk)
 				net = sock_net(skb->sk);
-			else
-				WARN_ON_ONCE(1);
 		}
+	}
 
-		if (net)
-			attached = rcu_dereference(net->flow_dissector_prog);
+	WARN_ON_ONCE(!net);
+	if (net) {
+		rcu_read_lock();
+		attached = rcu_dereference(net->flow_dissector_prog);
 
 		if (attached) {
-			ret = __skb_flow_bpf_dissect(attached, skb,
-						     flow_dissector,
-						     &flow_keys);
+			struct bpf_flow_keys flow_keys;
+			struct bpf_flow_dissector ctx = {
+				.flow_keys = &flow_keys,
+				.data = data,
+				.data_end = data + hlen,
+			};
+			__be16 n_proto = proto;
+
+			if (skb) {
+				ctx.skb = skb;
+				/* we can't use 'proto' in the skb case
+				 * because it might be set to skb->vlan_proto
+				 * which has been pulled from the data
+				 */
+				n_proto = skb->protocol;
+			}
+
+			ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff,
+					       hlen);
 			__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
 						 target_container);
 			rcu_read_unlock();
-- 
cgit v1.2.3


From c43f1255b866b423d2381f77eaa2cbc64a9c49aa Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Mon, 22 Apr 2019 08:55:48 -0700
Subject: net: pass net_device argument to the eth_get_headlen

Update all users of eth_get_headlen to pass network device, fetch
network namespace from it and pass it down to the flow dissector.
This commit is a noop until administrator inserts BPF flow dissector
program.

Cc: Maxim Krasnyansky <maxk@qti.qualcomm.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: intel-wired-lan@lists.osuosl.org
Cc: Yisen Zhuang <yisen.zhuang@huawei.com>
Cc: Salil Mehta <salil.mehta@huawei.com>
Cc: Michael Chan <michael.chan@broadcom.com>
Cc: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c  | 3 ++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 2 +-
 drivers/net/ethernet/hisilicon/hns/hns_enet.c     | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c   | 2 +-
 drivers/net/ethernet/intel/fm10k/fm10k_main.c     | 2 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.c       | 3 ++-
 drivers/net/ethernet/intel/iavf/iavf_txrx.c       | 2 +-
 drivers/net/ethernet/intel/ice/ice_txrx.c         | 2 +-
 drivers/net/ethernet/intel/igb/igb_main.c         | 2 +-
 drivers/net/ethernet/intel/igc/igc_main.c         | 2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c     | 2 +-
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c   | 2 +-
 drivers/net/tun.c                                 | 3 ++-
 include/linux/etherdevice.h                       | 2 +-
 net/ethernet/eth.c                                | 5 +++--
 16 files changed, 22 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index c64e2fb5a4f1..350e385528fd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -354,7 +354,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 
 			hdr_len = buff->len;
 			if (hdr_len > AQ_CFG_RX_HDR_SIZE)
-				hdr_len = eth_get_headlen(aq_buf_vaddr(&buff->rxdata),
+				hdr_len = eth_get_headlen(skb->dev,
+							  aq_buf_vaddr(&buff->rxdata),
 							  AQ_CFG_RX_HDR_SIZE);
 
 			memcpy(__skb_put(skb, hdr_len), aq_buf_vaddr(&buff->rxdata),
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6528a597367b..526f36dcb204 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -899,7 +899,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp,
 			     DMA_ATTR_WEAK_ORDERING);
 
 	if (unlikely(!payload))
-		payload = eth_get_headlen(data_ptr, len);
+		payload = eth_get_headlen(bp->dev, data_ptr, len);
 
 	skb = napi_alloc_skb(&rxr->bnapi->napi, payload);
 	if (!skb) {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 297b95c1b3c1..65b985acae38 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -598,7 +598,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
 	} else {
 		ring->stats.seg_pkt_cnt++;
 
-		pull_len = eth_get_headlen(va, HNS_RX_HEAD_SIZE);
+		pull_len = eth_get_headlen(ndev, va, HNS_RX_HEAD_SIZE);
 		memcpy(__skb_put(skb, pull_len), va,
 		       ALIGN(pull_len, sizeof(long)));
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 176d4b965709..5f7b51c6ee91 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2580,7 +2580,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length,
 	ring->stats.seg_pkt_cnt++;
 	u64_stats_update_end(&ring->syncp);
 
-	ring->pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE);
+	ring->pull_len = eth_get_headlen(netdev, va, HNS3_RX_HEAD_SIZE);
 	__skb_put(skb, ring->pull_len);
 	hns3_nic_reuse_page(skb, ring->frag_num++, ring, ring->pull_len,
 			    desc_cb);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 2325cee76211..b4d970e44163 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -280,7 +280,7 @@ static bool fm10k_add_rx_frag(struct fm10k_rx_buffer *rx_buffer,
 	/* we need the header to contain the greater of either ETH_HLEN or
 	 * 60 bytes if the skb->len is less than 60 for skb_pad.
 	 */
-	pull_len = eth_get_headlen(va, FM10K_RX_HDR_LEN);
+	pull_len = eth_get_headlen(skb->dev, va, FM10K_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 1a95223c9f99..e1931701cd7e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2035,7 +2035,8 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > I40E_RX_HDR_SIZE)
-		headlen = eth_get_headlen(xdp->data, I40E_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, xdp->data,
+					  I40E_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), xdp->data,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index b64187753ad6..cf8be63a8a4f 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -1315,7 +1315,7 @@ static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IAVF_RX_HDR_SIZE)
-		headlen = eth_get_headlen(va, IAVF_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, va, IAVF_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 79043fec0187..259f118c7d8b 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -699,7 +699,7 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > ICE_RX_HDR_SIZE)
-		headlen = eth_get_headlen(va, ICE_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, va, ICE_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index acbb5b4f333d..9b8a4bb25327 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -8051,7 +8051,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IGB_RX_HDR_LEN)
-		headlen = eth_get_headlen(va, IGB_RX_HDR_LEN);
+		headlen = eth_get_headlen(skb->dev, va, IGB_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index f79728381e8a..e58a6e0dc4d9 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1199,7 +1199,7 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IGC_RX_HDR_LEN)
-		headlen = eth_get_headlen(va, IGC_RX_HDR_LEN);
+		headlen = eth_get_headlen(skb->dev, va, IGC_RX_HDR_LEN);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 60cec3540dd7..7b903206b534 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1800,7 +1800,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
 	 * we need the header to contain the greater of either ETH_HLEN or
 	 * 60 bytes if the skb->len is less than 60 for skb_pad.
 	 */
-	pull_len = eth_get_headlen(va, IXGBE_RX_HDR_SIZE);
+	pull_len = eth_get_headlen(skb->dev, va, IXGBE_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 49e23afa05a2..d189ed247665 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -895,7 +895,8 @@ struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring,
 	/* Determine available headroom for copy */
 	headlen = size;
 	if (headlen > IXGBEVF_RX_HDR_SIZE)
-		headlen = eth_get_headlen(xdp->data, IXGBEVF_RX_HDR_SIZE);
+		headlen = eth_get_headlen(skb->dev, xdp->data,
+					  IXGBEVF_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	memcpy(__skb_put(skb, headlen), xdp->data,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 40f3f98aa279..7b61126fcec9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -163,7 +163,7 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
 	case MLX5_INLINE_MODE_NONE:
 		return 0;
 	case MLX5_INLINE_MODE_TCP_UDP:
-		hlen = eth_get_headlen(skb->data, skb_headlen(skb));
+		hlen = eth_get_headlen(skb->dev, skb->data, skb_headlen(skb));
 		if (hlen == ETH_HLEN && !skb_vlan_tag_present(skb))
 			hlen += VLAN_HLEN;
 		break;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 24d0220b9ba0..9d72f8c76c15 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1965,7 +1965,8 @@ drop:
 
 	if (frags) {
 		/* Exercise flow dissector code path. */
-		u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb));
+		u32 headlen = eth_get_headlen(tun->dev, skb->data,
+					      skb_headlen(skb));
 
 		if (unlikely(headlen > skb_headlen(skb))) {
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index e2f3b21cd72a..c6c1930e28a0 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -33,7 +33,7 @@ struct device;
 int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr);
 unsigned char *arch_get_platform_mac_address(void);
 int nvmem_get_mac_address(struct device *dev, void *addrbuf);
-u32 eth_get_headlen(void *data, unsigned int max_len);
+u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len);
 __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
 extern const struct header_ops eth_header_ops;
 
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 1e439549c419..0f9863dc4d44 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -119,13 +119,14 @@ EXPORT_SYMBOL(eth_header);
 
 /**
  * eth_get_headlen - determine the length of header for an ethernet frame
+ * @dev: pointer to network device
  * @data: pointer to start of frame
  * @len: total length of frame
  *
  * Make a best effort attempt to pull the length for all of the headers for
  * a given frame in a linear buffer.
  */
-u32 eth_get_headlen(void *data, unsigned int len)
+u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len)
 {
 	const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
 	const struct ethhdr *eth = (const struct ethhdr *)data;
@@ -136,7 +137,7 @@ u32 eth_get_headlen(void *data, unsigned int len)
 		return len;
 
 	/* parse any remaining L2/L3 headers, check for L4 */
-	if (!skb_flow_dissect_flow_keys_basic(NULL, NULL, &keys, data,
+	if (!skb_flow_dissect_flow_keys_basic(dev_net(dev), NULL, &keys, data,
 					      eth->h_proto, sizeof(*eth),
 					      len, flags))
 		return max_t(u32, keys.control.thoff, sizeof(*eth));
-- 
cgit v1.2.3


From a93f7fe134543649cf2e2d8fc2c50a8f4d742915 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Mon, 22 Apr 2019 21:52:23 +0800
Subject: net: phy: marvell: add new default led configure for m88e151x

The default m88e151x LED configuration is 0x1177, used LED[0]
for 1000M link, LED[1] for 100M link, and LED[2] for active.
But for some boards, which use LED[0] for link, and LED[1] for
active, prefer to be 0x1040. To be compatible with this case,
this patch defines a new dev_flag, and set it before connect
phy in HNS3 driver. When phy initializing, using the new
LED configuration if this dev_flag is set.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c | 3 +++
 drivers/net/phy/marvell.c                               | 6 +++++-
 include/linux/marvell_phy.h                             | 1 +
 3 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 12be4e293fcf..1e8134892d77 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -3,6 +3,7 @@
 
 #include <linux/etherdevice.h>
 #include <linux/kernel.h>
+#include <linux/marvell_phy.h>
 
 #include "hclge_cmd.h"
 #include "hclge_main.h"
@@ -209,6 +210,8 @@ int hclge_mac_connect_phy(struct hnae3_handle *handle)
 
 	linkmode_clear_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phydev->supported);
 
+	phydev->dev_flags |= MARVELL_PHY_LED0_LINK_LED1_ACTIVE;
+
 	ret = phy_connect_direct(netdev, phydev,
 				 hclge_mac_adjust_link,
 				 PHY_INTERFACE_MODE_SGMII);
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 8754cb883d02..a7e8c8113d97 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -137,6 +137,7 @@
 #define MII_PHY_LED_CTRL	        16
 #define MII_88E1121_PHY_LED_DEF		0x0030
 #define MII_88E1510_PHY_LED_DEF		0x1177
+#define MII_88E1510_PHY_LED0_LINK_LED1_ACTIVE	0x1040
 
 #define MII_M1011_PHY_STATUS		0x11
 #define MII_M1011_PHY_STATUS_1000	0x8000
@@ -633,7 +634,10 @@ static void marvell_config_led(struct phy_device *phydev)
 	 * LED[2] .. Blink, Activity
 	 */
 	case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1510):
-		def_config = MII_88E1510_PHY_LED_DEF;
+		if (phydev->dev_flags & MARVELL_PHY_LED0_LINK_LED1_ACTIVE)
+			def_config = MII_88E1510_PHY_LED0_LINK_LED1_ACTIVE;
+		else
+			def_config = MII_88E1510_PHY_LED_DEF;
 		break;
 	default:
 		return;
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index 73d04743a2bb..af6b11d4d673 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -34,5 +34,6 @@
 /* struct phy_device dev_flags definitions */
 #define MARVELL_PHY_M1145_FLAGS_RESISTANCE	0x00000001
 #define MARVELL_PHY_M1118_DNS323_LEDS		0x00000002
+#define MARVELL_PHY_LED0_LINK_LED1_ACTIVE	0x00000004
 
 #endif /* _MARVELL_PHY_H */
-- 
cgit v1.2.3


From c2273219baa5097a4d7c1c162b992623534f34c1 Mon Sep 17 00:00:00 2001
From: Shay Agroskin <shayag@mellanox.com>
Date: Thu, 14 Mar 2019 14:54:07 +0200
Subject: net/mlx5e: XDP, Inline small packets into the TX MPWQE in XDP xmit
 flow

Upon high packet rate with multiple CPUs TX workloads, much of the HCA's
resources are spent on prefetching TX descriptors, thus affecting
transmission rates.
This patch comes to mitigate this problem by moving some workload to the
CPU and reducing the HW data prefetch overhead for small packets (<= 256B).

When forwarding packets with XDP, a packet that is smaller
than a certain size (set to ~256 bytes) would be sent inline within
its WQE TX descrptor (mem-copied), when the hardware tx queue is congested
beyond a pre-defined water-mark.

This is added to better utilize the HW resources (which now makes
one less packet data prefetch) and allow better scalability, on the
account of CPU usage (which now 'memcpy's the packet into the WQE).

To load balance between HW and CPU and get max packet rate, we use
watermarks to detect how much the HW is congested and move the work
loads back and forth between HW and CPU.

Performance:
Tested packet rate for UDP 64Byte multi-stream
over two dual port ConnectX-5 100Gbps NICs.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz

* Tested with hyper-threading disabled

XDP_TX:

|          | before | after   |       |
| 24 rings | 51Mpps | 116Mpps | +126% |
| 1 ring   | 12Mpps | 12Mpps  | same  |

XDP_REDIRECT:

** Below is the transmit rate, not the redirection rate
which might be larger, and is not affected by this patch.

|          | before  | after   |      |
| 32 rings | 64Mpps  | 92Mpps  | +43% |
| 1 ring   | 6.4Mpps | 6.4Mpps | same |

As we can see, feature significantly improves scaling, without
hurting single ring performance.

Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  5 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   | 22 +++++----
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h   | 57 ++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c |  8 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h |  3 ++
 include/linux/mlx5/qp.h                            |  1 +
 7 files changed, 83 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index a3700c57b073..c190061763fd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -409,14 +409,17 @@ struct mlx5e_xdp_info_fifo {
 
 struct mlx5e_xdp_wqe_info {
 	u8 num_wqebbs;
-	u8 num_ds;
+	u8 num_pkts;
 };
 
 struct mlx5e_xdp_mpwqe {
 	/* Current MPWQE session */
 	struct mlx5e_tx_wqe *wqe;
 	u8                   ds_count;
+	u8                   pkt_count;
 	u8                   max_ds_count;
+	u8                   complete;
+	u8                   inline_on;
 };
 
 struct mlx5e_xdpsq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index a9075b526ab9..c3d4efbf60ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -113,7 +113,9 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 	mlx5e_xdpsq_fetch_wqe(sq, &session->wqe);
 
 	prefetchw(session->wqe->data);
-	session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	session->ds_count  = MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	session->pkt_count = 0;
+	session->complete  = 0;
 
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
@@ -132,6 +134,9 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 		       MLX5E_XDP_MPW_MAX_WQEBBS);
 
 	session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs;
+
+	mlx5e_xdp_update_inline_state(sq);
+
 	stats->mpwqe++;
 }
 
@@ -149,7 +154,7 @@ static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
 	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_count);
 
 	wi->num_wqebbs = DIV_ROUND_UP(ds_count, MLX5_SEND_WQEBB_NUM_DS);
-	wi->num_ds     = ds_count - MLX5E_XDP_TX_EMPTY_DS_COUNT;
+	wi->num_pkts   = session->pkt_count;
 
 	sq->pc += wi->num_wqebbs;
 
@@ -164,11 +169,9 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 
-	dma_addr_t dma_addr    = xdpi->dma_addr;
 	struct xdp_frame *xdpf = xdpi->xdpf;
-	unsigned int dma_len   = xdpf->len;
 
-	if (unlikely(sq->hw_mtu < dma_len)) {
+	if (unlikely(sq->hw_mtu < xdpf->len)) {
 		stats->err++;
 		return false;
 	}
@@ -185,9 +188,10 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
 		mlx5e_xdp_mpwqe_session_start(sq);
 	}
 
-	mlx5e_xdp_mpwqe_add_dseg(sq, dma_addr, dma_len);
+	mlx5e_xdp_mpwqe_add_dseg(sq, xdpi, stats);
 
-	if (unlikely(session->ds_count == session->max_ds_count))
+	if (unlikely(session->complete ||
+		     session->ds_count == session->max_ds_count))
 		mlx5e_xdp_mpwqe_complete(sq);
 
 	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
@@ -301,7 +305,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 
 			sqcc += wi->num_wqebbs;
 
-			for (j = 0; j < wi->num_ds; j++) {
+			for (j = 0; j < wi->num_pkts; j++) {
 				struct mlx5e_xdp_info xdpi =
 					mlx5e_xdpi_fifo_pop(xdpi_fifo);
 
@@ -342,7 +346,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 
 		sq->cc += wi->num_wqebbs;
 
-		for (i = 0; i < wi->num_ds; i++) {
+		for (i = 0; i < wi->num_pkts; i++) {
 			struct mlx5e_xdp_info xdpi =
 				mlx5e_xdpi_fifo_pop(xdpi_fifo);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index ee27a7c8cd87..858e7a2a13ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -75,16 +75,68 @@ static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 	}
 }
 
+/* Enable inline WQEs to shift some load from a congested HCA (HW) to
+ * a less congested cpu (SW).
+ */
+static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq)
+{
+	u16 outstanding = sq->xdpi_fifo_pc - sq->xdpi_fifo_cc;
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+
+#define MLX5E_XDP_INLINE_WATERMARK_LOW	10
+#define MLX5E_XDP_INLINE_WATERMARK_HIGH 128
+
+	if (session->inline_on) {
+		if (outstanding <= MLX5E_XDP_INLINE_WATERMARK_LOW)
+			session->inline_on = 0;
+		return;
+	}
+
+	/* inline is false */
+	if (outstanding >= MLX5E_XDP_INLINE_WATERMARK_HIGH)
+		session->inline_on = 1;
+}
+
 static inline void
-mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, dma_addr_t dma_addr, u16 dma_len)
+mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi,
+			 struct mlx5e_xdpsq_stats *stats)
 {
 	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	dma_addr_t dma_addr    = xdpi->dma_addr;
+	struct xdp_frame *xdpf = xdpi->xdpf;
 	struct mlx5_wqe_data_seg *dseg =
-		(struct mlx5_wqe_data_seg *)session->wqe + session->ds_count++;
+		(struct mlx5_wqe_data_seg *)session->wqe + session->ds_count;
+	u16 dma_len = xdpf->len;
 
+	session->pkt_count++;
+
+#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg))
+
+	if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) {
+		struct mlx5_wqe_inline_seg *inline_dseg =
+			(struct mlx5_wqe_inline_seg *)dseg;
+		u16 ds_len = sizeof(*inline_dseg) + dma_len;
+		u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS);
+
+		if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) {
+			/* Not enough space for inline wqe, send with memory pointer */
+			session->complete = true;
+			goto no_inline;
+		}
+
+		inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG);
+		memcpy(inline_dseg->data, xdpf->data, dma_len);
+
+		session->ds_count += ds_cnt;
+		stats->inlnw++;
+		return;
+	}
+
+no_inline:
 	dseg->addr       = cpu_to_be64(dma_addr);
 	dseg->byte_count = cpu_to_be32(dma_len);
 	dseg->lkey       = sq->mkey_be;
+	session->ds_count++;
 }
 
 static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq,
@@ -111,5 +163,4 @@ mlx5e_xdpi_fifo_pop(struct mlx5e_xdp_info_fifo *fifo)
 {
 	return fifo->xi[(*fifo->cc)++ & fifo->mask];
 }
-
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7ab195ac7299..23df6f486c6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1532,7 +1532,7 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 			dseg->lkey = sq->mkey_be;
 
 			wi->num_wqebbs = 1;
-			wi->num_ds     = 1;
+			wi->num_pkts   = 1;
 		}
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 80ee48dcc0a3..ca0ff3b3fbd1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -66,6 +66,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_mpwqe) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_inlnw) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
@@ -81,6 +82,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_mpwqe) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_inlnw) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) },
@@ -163,6 +165,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_xdp_redirect += rq_stats->xdp_redirect;
 		s->rx_xdp_tx_xmit  += xdpsq_stats->xmit;
 		s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe;
+		s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw;
 		s->rx_xdp_tx_full  += xdpsq_stats->full;
 		s->rx_xdp_tx_err   += xdpsq_stats->err;
 		s->rx_xdp_tx_cqe   += xdpsq_stats->cqes;
@@ -188,7 +191,8 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->ch_eq_rearm    += ch_stats->eq_rearm;
 		/* xdp redirect */
 		s->tx_xdp_xmit    += xdpsq_red_stats->xmit;
-		s->tx_xdp_mpwqe += xdpsq_red_stats->mpwqe;
+		s->tx_xdp_mpwqe   += xdpsq_red_stats->mpwqe;
+		s->tx_xdp_inlnw   += xdpsq_red_stats->inlnw;
 		s->tx_xdp_full    += xdpsq_red_stats->full;
 		s->tx_xdp_err     += xdpsq_red_stats->err;
 		s->tx_xdp_cqes    += xdpsq_red_stats->cqes;
@@ -1250,6 +1254,7 @@ static const struct counter_desc sq_stats_desc[] = {
 static const struct counter_desc rq_xdpsq_stats_desc[] = {
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
@@ -1258,6 +1263,7 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = {
 static const struct counter_desc xdpsq_stats_desc[] = {
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
 	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 1f05ffa086b1..ac3c7c2a0964 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -78,6 +78,7 @@ struct mlx5e_sw_stats {
 	u64 rx_xdp_redirect;
 	u64 rx_xdp_tx_xmit;
 	u64 rx_xdp_tx_mpwqe;
+	u64 rx_xdp_tx_inlnw;
 	u64 rx_xdp_tx_full;
 	u64 rx_xdp_tx_err;
 	u64 rx_xdp_tx_cqe;
@@ -93,6 +94,7 @@ struct mlx5e_sw_stats {
 	u64 tx_cqe_err;
 	u64 tx_xdp_xmit;
 	u64 tx_xdp_mpwqe;
+	u64 tx_xdp_inlnw;
 	u64 tx_xdp_full;
 	u64 tx_xdp_err;
 	u64 tx_xdp_cqes;
@@ -244,6 +246,7 @@ struct mlx5e_sq_stats {
 struct mlx5e_xdpsq_stats {
 	u64 xmit;
 	u64 mpwqe;
+	u64 inlnw;
 	u64 full;
 	u64 err;
 	/* dirtied @completion */
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 0343c81d4c5f..3ba4edbd17a6 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -395,6 +395,7 @@ struct mlx5_wqe_signature_seg {
 
 struct mlx5_wqe_inline_seg {
 	__be32	byte_count;
+	__be32	data[0];
 };
 
 enum mlx5_sig_type {
-- 
cgit v1.2.3


From f05713e0916ca46f127641b6afa74bd1a0772423 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 22 Apr 2019 18:35:03 -0700
Subject: ipv6: convert fib6_ref to refcount_t

We suspect some issues involving fib6_ref 0 -> 1 transitions might
cause strange syzbot reports.

Lets convert fib6_ref to refcount_t to catch them earlier.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Wei Wang <weiwan@google.com>
Acked-by: Wei Wang <weiwan@google.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 8 ++++----
 net/ipv6/ip6_fib.c    | 6 +++---
 net/ipv6/route.c      | 2 +-
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 352f767bea81..5a4a67b38712 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -146,7 +146,7 @@ struct fib6_info {
 	struct list_head		fib6_siblings;
 	unsigned int			fib6_nsiblings;
 
-	atomic_t			fib6_ref;
+	refcount_t			fib6_ref;
 	unsigned long			expires;
 	struct dst_metrics		*fib6_metrics;
 #define fib6_pmtu		fib6_metrics->metrics[RTAX_MTU-1]
@@ -284,17 +284,17 @@ void fib6_info_destroy_rcu(struct rcu_head *head);
 
 static inline void fib6_info_hold(struct fib6_info *f6i)
 {
-	atomic_inc(&f6i->fib6_ref);
+	refcount_inc(&f6i->fib6_ref);
 }
 
 static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
 {
-	return atomic_inc_not_zero(&f6i->fib6_ref);
+	return refcount_inc_not_zero(&f6i->fib6_ref);
 }
 
 static inline void fib6_info_release(struct fib6_info *f6i)
 {
-	if (f6i && atomic_dec_and_test(&f6i->fib6_ref))
+	if (f6i && refcount_dec_and_test(&f6i->fib6_ref))
 		call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
 }
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index a5e83593e0e4..a8919c217cc2 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -162,7 +162,7 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags)
 	}
 
 	INIT_LIST_HEAD(&f6i->fib6_siblings);
-	atomic_set(&f6i->fib6_ref, 1);
+	refcount_set(&f6i->fib6_ref, 1);
 
 	return f6i;
 }
@@ -929,7 +929,7 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 {
 	struct fib6_table *table = rt->fib6_table;
 
-	if (atomic_read(&rt->fib6_ref) != 1) {
+	if (refcount_read(&rt->fib6_ref) != 1) {
 		/* This route is used as dummy address holder in some split
 		 * nodes. It is not leaked, but it still holds other resources,
 		 * which must be released in time. So, scan ascendant nodes
@@ -2311,7 +2311,7 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 
 	dev = rt->fib6_nh.fib_nh_dev;
 	seq_printf(seq, " %08x %08x %08x %08x %8s\n",
-		   rt->fib6_metric, atomic_read(&rt->fib6_ref), 0,
+		   rt->fib6_metric, refcount_read(&rt->fib6_ref), 0,
 		   flags, dev ? dev->name : "");
 	iter->w.leaf = NULL;
 	return 0;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 844b16d8d6e8..923af51890ca 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -296,7 +296,7 @@ static const struct fib6_info fib6_null_entry_template = {
 	.fib6_flags	= (RTF_REJECT | RTF_NONEXTHOP),
 	.fib6_protocol  = RTPROT_KERNEL,
 	.fib6_metric	= ~(u32)0,
-	.fib6_ref	= ATOMIC_INIT(1),
+	.fib6_ref	= REFCOUNT_INIT(1),
 	.fib6_type	= RTN_UNREACHABLE,
 	.fib6_metrics	= (struct dst_metrics *)&dst_default_metrics,
 };
-- 
cgit v1.2.3


From ffa8ce54be3aaf6b15abae3bbd08282b867d3a4f Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 23 Apr 2019 08:23:41 -0700
Subject: lwtunnel: Pass encap and encap type attributes to lwtunnel_fill_encap

Currently, lwtunnel_fill_encap hardcodes the encap and encap type
attributes as RTA_ENCAP and RTA_ENCAP_TYPE, respectively. The nexthop
objects want to re-use this code but the encap attributes passed to
userspace as NHA_ENCAP and NHA_ENCAP_TYPE. Since that is the only
difference, change lwtunnel_fill_encap to take the attribute type as
an input.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/lwtunnel.h   | 7 ++++---
 net/core/lwtunnel.c      | 7 ++++---
 net/ipv4/fib_semantics.c | 3 ++-
 3 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 671113bcb2cc..5d6c5b1fc695 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -118,8 +118,8 @@ int lwtunnel_build_state(u16 encap_type,
 			 unsigned int family, const void *cfg,
 			 struct lwtunnel_state **lws,
 			 struct netlink_ext_ack *extack);
-int lwtunnel_fill_encap(struct sk_buff *skb,
-			struct lwtunnel_state *lwtstate);
+int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate,
+			int encap_attr, int encap_type_attr);
 int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate);
 struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len);
 int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b);
@@ -219,7 +219,8 @@ static inline int lwtunnel_build_state(u16 encap_type,
 }
 
 static inline int lwtunnel_fill_encap(struct sk_buff *skb,
-				      struct lwtunnel_state *lwtstate)
+				      struct lwtunnel_state *lwtstate,
+				      int encap_attr, int encap_type_attr)
 {
 	return 0;
 }
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index a8018aa5b798..94749e0e2cfd 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -223,7 +223,8 @@ void lwtstate_free(struct lwtunnel_state *lws)
 }
 EXPORT_SYMBOL_GPL(lwtstate_free);
 
-int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
+int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate,
+			int encap_attr, int encap_type_attr)
 {
 	const struct lwtunnel_encap_ops *ops;
 	struct nlattr *nest;
@@ -236,7 +237,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
 	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
 		return 0;
 
-	nest = nla_nest_start(skb, RTA_ENCAP);
+	nest = nla_nest_start(skb, encap_attr);
 	if (!nest)
 		return -EMSGSIZE;
 
@@ -250,7 +251,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate)
 	if (ret)
 		goto nla_put_failure;
 	nla_nest_end(skb, nest);
-	ret = nla_put_u16(skb, RTA_ENCAP_TYPE, lwtstate->type);
+	ret = nla_put_u16(skb, encap_type_attr, lwtstate->type);
 	if (ret)
 		goto nla_put_failure;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b5230c4a1c16..c695e629fac2 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1503,7 +1503,8 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
 		goto nla_put_failure;
 
 	if (nhc->nhc_lwtstate &&
-	    lwtunnel_fill_encap(skb, nhc->nhc_lwtstate) < 0)
+	    lwtunnel_fill_encap(skb, nhc->nhc_lwtstate,
+				RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
 		goto nla_put_failure;
 
 	return 0;
-- 
cgit v1.2.3


From ecc5663cce8c7d7e4eba32af4e1e3cab296c64b9 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 23 Apr 2019 08:48:09 -0700
Subject: net: Change nhc_flags to unsigned char

nhc_flags holds the RTNH_F flags for a given nexthop (fib{6}_nh).
All of the RTNH_F_ flags fit in an unsigned char, and since the API to
userspace (rtnh_flags and lower byte of rtm_flags) is 1 byte it can not
grow. Make nhc_flags in fib_nh_common an unsigned char and shrink the
size of the struct by 8, from 56 to 48 bytes.

Update the flags arguments for up netdevice events and fib_nexthop_info
which determines the RTNH_F flags to return on a dump/event. The RTNH_F
flags are passed in the lower byte of rtm_flags which is an unsigned int
so use a temp variable for the flags to fib_nexthop_info and combine
with rtm_flags in the caller.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_route.h  |  2 +-
 include/net/ip_fib.h     |  8 ++++----
 net/ipv4/fib_semantics.c |  8 ++++----
 net/ipv6/route.c         | 12 ++++++++----
 4 files changed, 17 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index df9cebc2b20c..4790beaa86e0 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -182,7 +182,7 @@ int rt6_dump_route(struct fib6_info *f6i, void *p_arg);
 void rt6_mtu_change(struct net_device *dev, unsigned int mtu);
 void rt6_remove_prefsrc(struct inet6_ifaddr *ifp);
 void rt6_clean_tohost(struct net *net, struct in6_addr *gateway);
-void rt6_sync_up(struct net_device *dev, unsigned int nh_flags);
+void rt6_sync_up(struct net_device *dev, unsigned char nh_flags);
 void rt6_disable_ip(struct net_device *dev, unsigned long event);
 void rt6_sync_down_dev(struct net_device *dev, unsigned long event);
 void rt6_multipath_rebalance(struct fib6_info *f6i);
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index d8195c77e247..772a9e61bd84 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -83,11 +83,11 @@ struct fnhe_hash_bucket {
 struct fib_nh_common {
 	struct net_device	*nhc_dev;
 	int			nhc_oif;
-	unsigned int		nhc_flags;
-	struct lwtunnel_state	*nhc_lwtstate;
 	unsigned char		nhc_scope;
 	u8			nhc_family;
 	u8			nhc_gw_family;
+	unsigned char		nhc_flags;
+	struct lwtunnel_state	*nhc_lwtstate;
 
 	union {
 		__be32          ipv4;
@@ -425,7 +425,7 @@ int fib_unmerge(struct net *net);
 int ip_fib_check_default(__be32 gw, struct net_device *dev);
 int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
 int fib_sync_down_addr(struct net_device *dev, __be32 local);
-int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
+int fib_sync_up(struct net_device *dev, unsigned char nh_flags);
 void fib_sync_mtu(struct net_device *dev, u32 orig_mtu);
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
@@ -500,7 +500,7 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 			  struct netlink_callback *cb);
 
 int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh,
-		     unsigned int *flags, bool skip_oif);
+		     unsigned char *flags, bool skip_oif);
 int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh,
 		    int nh_weight);
 #endif  /* _NET_FIB_H */
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c695e629fac2..4336f1ec8ab0 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1444,7 +1444,7 @@ failure:
 }
 
 int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
-		     unsigned int *flags, bool skip_oif)
+		     unsigned char *flags, bool skip_oif)
 {
 	if (nhc->nhc_flags & RTNH_F_DEAD)
 		*flags |= RTNH_F_DEAD;
@@ -1520,7 +1520,7 @@ int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc,
 {
 	const struct net_device *dev = nhc->nhc_dev;
 	struct rtnexthop *rtnh;
-	unsigned int flags = 0;
+	unsigned char flags = 0;
 
 	rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
 	if (!rtnh)
@@ -1619,7 +1619,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		goto nla_put_failure;
 	if (fi->fib_nhs == 1) {
 		struct fib_nh *nh = &fi->fib_nh[0];
-		unsigned int flags = 0;
+		unsigned char flags = 0;
 
 		if (fib_nexthop_info(skb, &nh->nh_common, &flags, false) < 0)
 			goto nla_put_failure;
@@ -1902,7 +1902,7 @@ out:
  * Dead device goes up. We wake up dead nexthops.
  * It takes sense only on multipath routes.
  */
-int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
+int fib_sync_up(struct net_device *dev, unsigned char nh_flags)
 {
 	struct fib_info *prev_fi;
 	unsigned int hash;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 923af51890ca..9c0127a44f9f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3912,7 +3912,7 @@ void rt6_clean_tohost(struct net *net, struct in6_addr *gateway)
 struct arg_netdev_event {
 	const struct net_device *dev;
 	union {
-		unsigned int nh_flags;
+		unsigned char nh_flags;
 		unsigned long event;
 	};
 };
@@ -4025,7 +4025,7 @@ static int fib6_ifup(struct fib6_info *rt, void *p_arg)
 	return 0;
 }
 
-void rt6_sync_up(struct net_device *dev, unsigned int nh_flags)
+void rt6_sync_up(struct net_device *dev, unsigned char nh_flags)
 {
 	struct arg_netdev_event arg = {
 		.dev = dev,
@@ -4082,7 +4082,7 @@ static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt,
 
 static void rt6_multipath_nh_flags_set(struct fib6_info *rt,
 				       const struct net_device *dev,
-				       unsigned int nh_flags)
+				       unsigned char nh_flags)
 {
 	struct fib6_info *iter;
 
@@ -4794,9 +4794,13 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 
 		nla_nest_end(skb, mp);
 	} else {
+		unsigned char nh_flags = 0;
+
 		if (fib_nexthop_info(skb, &rt->fib6_nh.nh_common,
-				     &rtm->rtm_flags, false) < 0)
+				     &nh_flags, false) < 0)
 			goto nla_put_failure;
+
+		rtm->rtm_flags |= nh_flags;
 	}
 
 	if (rt6_flags & RTF_EXPIRES) {
-- 
cgit v1.2.3


From a65120bae4b7425a39c5783aa3d4fc29677eef0e Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 23 Apr 2019 18:05:33 -0700
Subject: ipv6: Use result arg in fib_lookup_arg consistently

arg.result is sometimes used as fib6_result and sometimes used to
hold the rt6_info. Add rt6_info to fib6_result and make the use
of arg.result consistent through ipv6 rules.

The rt6 entry is filled in for lookups returning a dst_entry, but not
for direct fib_lookups that just want a fib6_info.

Fixes: effda4dd97e8 ("ipv6: Pass fib6_result to fib lookups")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h |  1 +
 net/ipv6/fib6_rules.c | 15 +++++++++++----
 2 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 5a4a67b38712..40105738e2f6 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -195,6 +195,7 @@ struct fib6_result {
 	struct fib6_info	*f6i;
 	u32			fib6_flags;
 	u8			fib6_type;
+	struct rt6_info		*rt6;
 };
 
 #define for_each_fib6_node_rt_rcu(fn)					\
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index dbedbe655c91..06d1b7763600 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -94,9 +94,11 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 				   int flags, pol_lookup_t lookup)
 {
 	if (net->ipv6.fib6_has_custom_rules) {
+		struct fib6_result res = {};
 		struct fib_lookup_arg arg = {
 			.lookup_ptr = lookup,
 			.lookup_data = skb,
+			.result = &res,
 			.flags = FIB_LOOKUP_NOREF,
 		};
 
@@ -106,8 +108,8 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 		fib_rules_lookup(net->ipv6.fib6_rules_ops,
 				 flowi6_to_flowi(fl6), flags, &arg);
 
-		if (arg.result)
-			return arg.result;
+		if (res.rt6)
+			return &res.rt6->dst;
 	} else {
 		struct rt6_info *rt;
 
@@ -191,6 +193,7 @@ static int fib6_rule_action_alt(struct fib_rule *rule, struct flowi *flp,
 static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 			      int flags, struct fib_lookup_arg *arg)
 {
+	struct fib6_result *res = arg->result;
 	struct flowi6 *flp6 = &flp->u.ip6;
 	struct rt6_info *rt = NULL;
 	struct fib6_table *table;
@@ -245,7 +248,7 @@ again:
 discard_pkt:
 	dst_hold(&rt->dst);
 out:
-	arg->result = rt;
+	res->rt6 = rt;
 	return err;
 }
 
@@ -260,9 +263,13 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 
 static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
 {
-	struct rt6_info *rt = (struct rt6_info *) arg->result;
+	struct fib6_result *res = arg->result;
+	struct rt6_info *rt = res->rt6;
 	struct net_device *dev = NULL;
 
+	if (!rt)
+		return false;
+
 	if (rt->rt6i_idev)
 		dev = rt->rt6i_idev->dev;
 
-- 
cgit v1.2.3


From 9fba2b9b4f1566213a4f0cec658479d8915086fa Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Sun, 31 Mar 2019 19:44:43 +0300
Subject: net/mlx5: Expose SW ICM related device memory capabilities

Add SW ICM related fields to the device memory capabilities
structure and sw ownership capability in flow table properties.

The currently supported SW ICM types are steering and header modify
and the changes exposes the device memory capabilities for each
of these two types.

SW ICM memory can be allocated by SW and then be accessed by RDMA
operations for direct management of the HW packet handling tables.

Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 45 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 43 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 11e498442134..d96eb0916a44 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -80,6 +80,14 @@ enum {
 	MLX5_SHARED_RESOURCE_UID = 0xffff,
 };
 
+enum {
+	MLX5_OBJ_TYPE_SW_ICM = 0x0008,
+};
+
+enum {
+	MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM),
+};
+
 enum {
 	MLX5_CMD_OP_QUERY_HCA_CAP                 = 0x100,
 	MLX5_CMD_OP_QUERY_ADAPTER                 = 0x101,
@@ -357,7 +365,8 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         pop_vlan_2[0x1];
 	u8         push_vlan_2[0x1];
 	u8	   reformat_and_vlan_action[0x1];
-	u8	   reserved_at_10[0x2];
+	u8	   reserved_at_10[0x1];
+	u8         sw_owner[0x1];
 	u8	   reformat_l3_tunnel_to_l2[0x1];
 	u8	   reformat_l2_to_l3_tunnel[0x1];
 	u8	   reformat_and_modify_action[0x1];
@@ -770,7 +779,19 @@ struct mlx5_ifc_device_mem_cap_bits {
 
 	u8         max_memic_size[0x20];
 
-	u8         reserved_at_c0[0x740];
+	u8         steering_sw_icm_start_address[0x40];
+
+	u8         reserved_at_100[0x8];
+	u8         log_header_modify_sw_icm_size[0x8];
+	u8         reserved_at_110[0x2];
+	u8         log_sw_icm_alloc_granularity[0x6];
+	u8         log_steering_sw_icm_size[0x8];
+
+	u8         reserved_at_120[0x20];
+
+	u8         header_modify_sw_icm_start_address[0x40];
+
+	u8         reserved_at_180[0x680];
 };
 
 enum {
@@ -919,6 +940,7 @@ enum {
 
 enum {
 	MLX5_UCTX_CAP_RAW_TX = 1UL << 0,
+	MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1,
 };
 
 struct mlx5_ifc_cmd_hca_cap_bits {
@@ -2920,6 +2942,7 @@ enum {
 	MLX5_MKC_ACCESS_MODE_MTT   = 0x1,
 	MLX5_MKC_ACCESS_MODE_KLMS  = 0x2,
 	MLX5_MKC_ACCESS_MODE_KSM   = 0x3,
+	MLX5_MKC_ACCESS_MODE_SW_ICM = 0x4,
 	MLX5_MKC_ACCESS_MODE_MEMIC = 0x5,
 };
 
@@ -9491,6 +9514,19 @@ struct mlx5_ifc_uctx_bits {
 	u8         reserved_at_20[0x160];
 };
 
+struct mlx5_ifc_sw_icm_bits {
+	u8         modify_field_select[0x40];
+
+	u8	   reserved_at_40[0x18];
+	u8         log_sw_icm_size[0x8];
+
+	u8         reserved_at_60[0x20];
+
+	u8         sw_icm_start_addr[0x40];
+
+	u8         reserved_at_c0[0x140];
+};
+
 struct mlx5_ifc_create_umem_in_bits {
 	u8         opcode[0x10];
 	u8         uid[0x10];
@@ -9528,6 +9564,11 @@ struct mlx5_ifc_destroy_uctx_in_bits {
 	u8         reserved_at_60[0x20];
 };
 
+struct mlx5_ifc_create_sw_icm_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits   hdr;
+	struct mlx5_ifc_sw_icm_bits		      sw_icm;
+};
+
 struct mlx5_ifc_mtrc_string_db_param_bits {
 	u8         string_db_base_address[0x20];
 
-- 
cgit v1.2.3


From 3e07047021d36674d9051e76454e8b6a3b599036 Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Sun, 31 Mar 2019 19:44:48 +0300
Subject: net/mlx5: Expose TIR ICM address in command outbox

Adding the TIR ICM address to the create_tir command outbox
through which the device reports the ICM address of the newly
created TIR.

The TIR address can be used for direct attachment to a steering
rule in SW managed steering mode.

Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index d96eb0916a44..4b37519bd6a5 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -6897,14 +6897,14 @@ struct mlx5_ifc_create_tis_in_bits {
 
 struct mlx5_ifc_create_tir_out_bits {
 	u8         status[0x8];
-	u8         reserved_at_8[0x18];
+	u8         icm_address_63_40[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_at_40[0x8];
+	u8         icm_address_39_32[0x8];
 	u8         tirn[0x18];
 
-	u8         reserved_at_60[0x20];
+	u8         icm_address_31_0[0x20];
 };
 
 struct mlx5_ifc_create_tir_in_bits {
-- 
cgit v1.2.3


From 96780e4f46b2fc0fc5ae2b95957002e2c42b11d3 Mon Sep 17 00:00:00 2001
From: Ariel Levkovich <lariel@mellanox.com>
Date: Sun, 31 Mar 2019 19:44:49 +0300
Subject: net/mlx5: Introduce new TIR creation core API

Introducing new TIR creation core API which allows caller
to receive back from the call the full command outbox.

This comes as a preparation for the next patch that will
retrieve the TIR ICM address from the command outbox.

Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/transobj.c | 18 +++++++++++++-----
 include/linux/mlx5/transobj.h                      |  3 +++
 2 files changed, 16 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index c4d4b76096dc..b1068500f1df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -182,16 +182,24 @@ out:
 }
 EXPORT_SYMBOL_GPL(mlx5_core_query_sq_state);
 
+int mlx5_core_create_tir_out(struct mlx5_core_dev *dev,
+			     u32 *in, int inlen,
+			     u32 *out, int outlen)
+{
+	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
+
+	return mlx5_cmd_exec(dev, in, inlen, out, outlen);
+}
+EXPORT_SYMBOL(mlx5_core_create_tir_out);
+
 int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *tirn)
 {
-	u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(create_tir_out)] = {};
 	int err;
 
-	MLX5_SET(create_tir_in, in, opcode, MLX5_CMD_OP_CREATE_TIR);
-
-	memset(out, 0, sizeof(out));
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	err = mlx5_core_create_tir_out(dev, in, inlen,
+				       out, sizeof(out));
 	if (!err)
 		*tirn = MLX5_GET(create_tir_out, out, tirn);
 
diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h
index a261d5528ff7..dc6b1e7cb8c4 100644
--- a/include/linux/mlx5/transobj.h
+++ b/include/linux/mlx5/transobj.h
@@ -50,6 +50,9 @@ int mlx5_core_query_sq(struct mlx5_core_dev *dev, u32 sqn, u32 *out);
 int mlx5_core_query_sq_state(struct mlx5_core_dev *dev, u32 sqn, u8 *state);
 int mlx5_core_create_tir(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *tirn);
+int mlx5_core_create_tir_out(struct mlx5_core_dev *dev,
+			     u32 *in, int inlen,
+			     u32 *out, int outlen);
 int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in,
 			 int inlen);
 void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn);
-- 
cgit v1.2.3


From d5bb334a8e171b262e48f378bd2096c0ea458265 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Wed, 24 Apr 2019 22:19:17 +0200
Subject: Bluetooth: Align minimum encryption key size for LE and BR/EDR
 connections

The minimum encryption key size for LE connections is 56 bits and to
align LE with BR/EDR, enforce 56 bits of minimum encryption key size for
BR/EDR connections as well.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Cc: stable@vger.kernel.org
---
 include/net/bluetooth/hci_core.h | 3 +++
 net/bluetooth/hci_conn.c         | 8 ++++++++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 094e61e07030..05b1b96f4d9e 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -190,6 +190,9 @@ struct adv_info {
 
 #define HCI_MAX_SHORT_NAME_LENGTH	10
 
+/* Min encryption key size to match with SMP */
+#define HCI_MIN_ENC_KEY_SIZE		7
+
 /* Default LE RPA expiry time, 15 minutes */
 #define HCI_DEFAULT_RPA_TIMEOUT		(15 * 60)
 
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index bd4978ce8c45..3cf0764d5793 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1276,6 +1276,14 @@ int hci_conn_check_link_mode(struct hci_conn *conn)
 	    !test_bit(HCI_CONN_ENCRYPT, &conn->flags))
 		return 0;
 
+	/* The minimum encryption key size needs to be enforced by the
+	 * host stack before establishing any L2CAP connections. The
+	 * specification in theory allows a minimum of 1, but to align
+	 * BR/EDR and LE transports, a minimum of 7 is chosen.
+	 */
+	if (conn->enc_key_size < HCI_MIN_ENC_KEY_SIZE)
+		return 0;
+
 	return 1;
 }
 
-- 
cgit v1.2.3


From 118c8e9ae629d35fa9b3d27a7b9d59298b1b4183 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Thu, 25 Apr 2019 14:37:23 -0700
Subject: bpf: support BPF_PROG_QUERY for BPF_FLOW_DISSECTOR attach_type

target_fd is target namespace. If there is a flow dissector BPF program
attached to that namespace, its (single) id is returned.

v5:
* drop net ref right after rcu unlock (Daniel Borkmann)

v4:
* add missing put_net (Jann Horn)

v3:
* add missing inline to skb_flow_dissector_prog_query static def
  (kbuild test robot <lkp@intel.com>)

v2:
* don't sleep in rcu critical section (Jakub Kicinski)
* check input prog_cnt (exit early)

Cc: Jann Horn <jannh@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/skbuff.h    |  8 ++++++++
 kernel/bpf/syscall.c      |  2 ++
 net/core/flow_dissector.c | 39 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 49 insertions(+)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 998256c2820b..6d58fa8a65fd 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1258,11 +1258,19 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 			     unsigned int key_count);
 
 #ifdef CONFIG_NET
+int skb_flow_dissector_prog_query(const union bpf_attr *attr,
+				  union bpf_attr __user *uattr);
 int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 				       struct bpf_prog *prog);
 
 int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr);
 #else
+static inline int skb_flow_dissector_prog_query(const union bpf_attr *attr,
+						union bpf_attr __user *uattr)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 						     struct bpf_prog *prog)
 {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 92c9b8a32b50..b0de49598341 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2009,6 +2009,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
 		break;
 	case BPF_LIRC_MODE2:
 		return lirc_prog_query(attr, uattr);
+	case BPF_FLOW_DISSECTOR:
+		return skb_flow_dissector_prog_query(attr, uattr);
 	default:
 		return -EINVAL;
 	}
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index fac712cee9d5..9ca784c592ac 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -65,6 +65,45 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 }
 EXPORT_SYMBOL(skb_flow_dissector_init);
 
+int skb_flow_dissector_prog_query(const union bpf_attr *attr,
+				  union bpf_attr __user *uattr)
+{
+	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+	u32 prog_id, prog_cnt = 0, flags = 0;
+	struct bpf_prog *attached;
+	struct net *net;
+
+	if (attr->query.query_flags)
+		return -EINVAL;
+
+	net = get_net_ns_by_fd(attr->query.target_fd);
+	if (IS_ERR(net))
+		return PTR_ERR(net);
+
+	rcu_read_lock();
+	attached = rcu_dereference(net->flow_dissector_prog);
+	if (attached) {
+		prog_cnt = 1;
+		prog_id = attached->aux->id;
+	}
+	rcu_read_unlock();
+
+	put_net(net);
+
+	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+		return -EFAULT;
+	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
+		return -EFAULT;
+
+	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
+		return 0;
+
+	if (copy_to_user(prog_ids, &prog_id, sizeof(u32)))
+		return -EFAULT;
+
+	return 0;
+}
+
 int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr,
 				       struct bpf_prog *prog)
 {
-- 
cgit v1.2.3


From 1d9373329bcbe0cfbb9af1738139292a9b10fe6a Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Fri, 15 Mar 2019 17:38:58 +0200
Subject: nl80211: increase NL80211_MAX_SUPP_REG_RULES

The iwlwifi driver creates one rule per channel, thus it needs more
rules than normal.  To solve this, increase NL80211_MAX_SUPP_REG_RULES
so iwlwifi can also fit UHB (ultra high band) channels.

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index a99d75bef598..f00dbd82149e 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -11,7 +11,7 @@
  * Copyright 2008 Jouni Malinen <jouni.malinen@atheros.com>
  * Copyright 2008 Colin McCabe <colin@cozybit.com>
  * Copyright 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018 Intel Corporation
+ * Copyright (C) 2018-2019 Intel Corporation
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -2809,7 +2809,7 @@ enum nl80211_attrs {
 
 #define NL80211_MAX_SUPP_RATES			32
 #define NL80211_MAX_SUPP_HT_RATES		77
-#define NL80211_MAX_SUPP_REG_RULES		64
+#define NL80211_MAX_SUPP_REG_RULES		128
 #define NL80211_TKIP_DATA_OFFSET_ENCR_KEY	0
 #define NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY	16
 #define NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY	24
-- 
cgit v1.2.3


From f7dacfb11475ba777e1e84ccec2e14b0ba5a17a3 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Fri, 15 Mar 2019 17:39:03 +0200
Subject: cfg80211: support non-inheritance element

Subelement profile may specify element IDs it doesn't inherit
from the management frame. Support it.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h |  1 +
 include/net/cfg80211.h    |  8 +++++++
 net/wireless/scan.c       | 61 ++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 69 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 48703ec60d06..522881f31938 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2487,6 +2487,7 @@ enum ieee80211_eid_ext {
 	WLAN_EID_EXT_HE_MU_EDCA = 38,
 	WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME = 52,
 	WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION = 55,
+	WLAN_EID_EXT_NON_INHERITANCE = 56,
 };
 
 /* Action category code */
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 70432fd638af..777c4f021610 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5534,6 +5534,14 @@ static inline void cfg80211_gen_new_bssid(const u8 *bssid, u8 max_bssid,
 	u64_to_ether_addr(new_bssid_u64, new_bssid);
 }
 
+/**
+ * cfg80211_is_element_inherited - returns if element ID should be inherited
+ * @element: element to check
+ * @non_inherit_element: non inheritance element
+ */
+bool cfg80211_is_element_inherited(const struct element *element,
+				   const struct element *non_inherit_element);
+
 /**
  * enum cfg80211_bss_frame_type - frame type that the BSS data came from
  * @CFG80211_BSS_FTYPE_UNKNOWN: driver doesn't know whether the data is
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 49f700a1460b..bda9114ded77 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -179,12 +179,63 @@ static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *rdev,
 	return true;
 }
 
+bool cfg80211_is_element_inherited(const struct element *elem,
+				   const struct element *non_inherit_elem)
+{
+	u8 id_len, ext_id_len, i, loop_len, id;
+	const u8 *list;
+
+	if (elem->id == WLAN_EID_MULTIPLE_BSSID)
+		return false;
+
+	if (!non_inherit_elem || non_inherit_elem->datalen < 2)
+		return true;
+
+	/*
+	 * non inheritance element format is:
+	 * ext ID (56) | IDs list len | list | extension IDs list len | list
+	 * Both lists are optional. Both lengths are mandatory.
+	 * This means valid length is:
+	 * elem_len = 1 (extension ID) + 2 (list len fields) + list lengths
+	 */
+	id_len = non_inherit_elem->data[1];
+	if (non_inherit_elem->datalen < 3 + id_len)
+		return true;
+
+	ext_id_len = non_inherit_elem->data[2 + id_len];
+	if (non_inherit_elem->datalen < 3 + id_len + ext_id_len)
+		return true;
+
+	if (elem->id == WLAN_EID_EXTENSION) {
+		if (!ext_id_len)
+			return true;
+		loop_len = ext_id_len;
+		list = &non_inherit_elem->data[3 + id_len];
+		id = elem->data[0];
+	} else {
+		if (!id_len)
+			return true;
+		loop_len = id_len;
+		list = &non_inherit_elem->data[2];
+		id = elem->id;
+	}
+
+	for (i = 0; i < loop_len; i++) {
+		if (list[i] == id)
+			return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL(cfg80211_is_element_inherited);
+
 static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
 				  const u8 *subelement, size_t subie_len,
 				  u8 *new_ie, gfp_t gfp)
 {
 	u8 *pos, *tmp;
 	const u8 *tmp_old, *tmp_new;
+	const struct element *non_inherit_elem;
 	u8 *sub_copy;
 
 	/* copy subelement as we need to change its content to
@@ -204,6 +255,11 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
 		pos += (tmp_new[1] + 2);
 	}
 
+	/* get non inheritance list if exists */
+	non_inherit_elem =
+		cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
+				       sub_copy, subie_len);
+
 	/* go through IEs in ie (skip SSID) and subelement,
 	 * merge them into new_ie
 	 */
@@ -224,8 +280,11 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
 						     subie_len);
 
 		if (!tmp) {
+			const struct element *old_elem = (void *)tmp_old;
+
 			/* ie in old ie but not in subelement */
-			if (tmp_old[0] != WLAN_EID_MULTIPLE_BSSID) {
+			if (cfg80211_is_element_inherited(old_elem,
+							  non_inherit_elem)) {
 				memcpy(pos, tmp_old, tmp_old[1] + 2);
 				pos += tmp_old[1] + 2;
 			}
-- 
cgit v1.2.3


From fe806e4992c9047affd263bcc13b2c047029a726 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Fri, 15 Mar 2019 17:39:05 +0200
Subject: cfg80211: support profile split between elements

Since an element is limited to 255 octets, a profile may be split
split to several elements. Support the split as defined in the 11ax
draft 3. Detect legacy split and print a net-rate limited warning,
since there is no ROI in supporting this probably non-existent
split.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  14 +++++++
 net/wireless/scan.c    | 109 ++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 117 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 777c4f021610..f6665f8eba5a 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5542,6 +5542,20 @@ static inline void cfg80211_gen_new_bssid(const u8 *bssid, u8 max_bssid,
 bool cfg80211_is_element_inherited(const struct element *element,
 				   const struct element *non_inherit_element);
 
+/**
+ * cfg80211_merge_profile - merges a MBSSID profile if it is split between IEs
+ * @ie: ies
+ * @ielen: length of IEs
+ * @mbssid_elem: current MBSSID element
+ * @sub_elem: current MBSSID subelement (profile)
+ * @merged_ie: location of the merged profile
+ * @max_copy_len: max merged profile length
+ */
+size_t cfg80211_merge_profile(const u8 *ie, size_t ielen,
+			      const struct element *mbssid_elem,
+			      const struct element *sub_elem,
+			      u8 **merged_ie, size_t max_copy_len);
+
 /**
  * enum cfg80211_bss_frame_type - frame type that the BSS data came from
  * @CFG80211_BSS_FTYPE_UNKNOWN: driver doesn't know whether the data is
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index bda9114ded77..878c867f3f7d 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1456,6 +1456,78 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
 	return &res->pub;
 }
 
+static const struct element
+*cfg80211_get_profile_continuation(const u8 *ie, size_t ielen,
+				   const struct element *mbssid_elem,
+				   const struct element *sub_elem)
+{
+	const u8 *mbssid_end = mbssid_elem->data + mbssid_elem->datalen;
+	const struct element *next_mbssid;
+	const struct element *next_sub;
+
+	next_mbssid = cfg80211_find_elem(WLAN_EID_MULTIPLE_BSSID,
+					 mbssid_end,
+					 ielen - (mbssid_end - ie));
+
+	/*
+	 * If is is not the last subelement in current MBSSID IE or there isn't
+	 * a next MBSSID IE - profile is complete.
+	*/
+	if ((sub_elem->data + sub_elem->datalen < mbssid_end - 1) ||
+	    !next_mbssid)
+		return NULL;
+
+	/* For any length error, just return NULL */
+
+	if (next_mbssid->datalen < 4)
+		return NULL;
+
+	next_sub = (void *)&next_mbssid->data[1];
+
+	if (next_mbssid->data + next_mbssid->datalen <
+	    next_sub->data + next_sub->datalen)
+		return NULL;
+
+	if (next_sub->id != 0 || next_sub->datalen < 2)
+		return NULL;
+
+	/*
+	 * Check if the first element in the next sub element is a start
+	 * of a new profile
+	 */
+	return next_sub->data[0] == WLAN_EID_NON_TX_BSSID_CAP ?
+	       NULL : next_mbssid;
+}
+
+size_t cfg80211_merge_profile(const u8 *ie, size_t ielen,
+			      const struct element *mbssid_elem,
+			      const struct element *sub_elem,
+			      u8 **merged_ie, size_t max_copy_len)
+{
+	size_t copied_len = sub_elem->datalen;
+	const struct element *next_mbssid;
+
+	if (sub_elem->datalen > max_copy_len)
+		return 0;
+
+	memcpy(*merged_ie, sub_elem->data, sub_elem->datalen);
+
+	while ((next_mbssid = cfg80211_get_profile_continuation(ie, ielen,
+								mbssid_elem,
+								sub_elem))) {
+		const struct element *next_sub = (void *)&next_mbssid->data[1];
+
+		if (copied_len + next_sub->datalen > max_copy_len)
+			break;
+		memcpy(*merged_ie + copied_len, next_sub->data,
+		       next_sub->datalen);
+		copied_len += next_sub->datalen;
+	}
+
+	return copied_len;
+}
+EXPORT_SYMBOL(cfg80211_merge_profile);
+
 static void cfg80211_parse_mbssid_data(struct wiphy *wiphy,
 				       struct cfg80211_inform_bss *data,
 				       enum cfg80211_bss_frame_type ftype,
@@ -1469,7 +1541,8 @@ static void cfg80211_parse_mbssid_data(struct wiphy *wiphy,
 	const struct element *elem, *sub;
 	size_t new_ie_len;
 	u8 new_bssid[ETH_ALEN];
-	u8 *new_ie;
+	u8 *new_ie, *profile;
+	u64 seen_indices = 0;
 	u16 capability;
 	struct cfg80211_bss *bss;
 
@@ -1487,10 +1560,16 @@ static void cfg80211_parse_mbssid_data(struct wiphy *wiphy,
 	if (!new_ie)
 		return;
 
+	profile = kmalloc(ielen, gfp);
+	if (!profile)
+		goto out;
+
 	for_each_element_id(elem, WLAN_EID_MULTIPLE_BSSID, ie, ielen) {
 		if (elem->datalen < 4)
 			continue;
 		for_each_element(sub, elem->data + 1, elem->datalen - 1) {
+			u8 profile_len;
+
 			if (sub->id != 0 || sub->datalen < 4) {
 				/* not a valid BSS profile */
 				continue;
@@ -1505,16 +1584,31 @@ static void cfg80211_parse_mbssid_data(struct wiphy *wiphy,
 				continue;
 			}
 
+			memset(profile, 0, ielen);
+			profile_len = cfg80211_merge_profile(ie, ielen,
+							     elem,
+							     sub,
+							     &profile,
+							     ielen);
+
 			/* found a Nontransmitted BSSID Profile */
 			mbssid_index_ie = cfg80211_find_ie
 				(WLAN_EID_MULTI_BSSID_IDX,
-				 sub->data, sub->datalen);
+				 profile, profile_len);
 			if (!mbssid_index_ie || mbssid_index_ie[1] < 1 ||
-			    mbssid_index_ie[2] == 0) {
+			    mbssid_index_ie[2] == 0 ||
+			    mbssid_index_ie[2] > 46) {
 				/* No valid Multiple BSSID-Index element */
 				continue;
 			}
 
+			if (seen_indices & BIT(mbssid_index_ie[2]))
+				/* We don't support legacy split of a profile */
+				net_dbg_ratelimited("Partial info for BSSID index %d\n",
+						    mbssid_index_ie[2]);
+
+			seen_indices |= BIT(mbssid_index_ie[2]);
+
 			non_tx_data->bssid_index = mbssid_index_ie[2];
 			non_tx_data->max_bssid_indicator = elem->data[0];
 
@@ -1523,13 +1617,14 @@ static void cfg80211_parse_mbssid_data(struct wiphy *wiphy,
 					       non_tx_data->bssid_index,
 					       new_bssid);
 			memset(new_ie, 0, IEEE80211_MAX_DATA_LEN);
-			new_ie_len = cfg80211_gen_new_ie(ie, ielen, sub->data,
-							 sub->datalen, new_ie,
+			new_ie_len = cfg80211_gen_new_ie(ie, ielen,
+							 profile,
+							 profile_len, new_ie,
 							 gfp);
 			if (!new_ie_len)
 				continue;
 
-			capability = get_unaligned_le16(sub->data + 2);
+			capability = get_unaligned_le16(profile + 2);
 			bss = cfg80211_inform_single_bss_data(wiphy, data,
 							      ftype,
 							      new_bssid, tsf,
@@ -1545,7 +1640,9 @@ static void cfg80211_parse_mbssid_data(struct wiphy *wiphy,
 		}
 	}
 
+out:
 	kfree(new_ie);
+	kfree(profile);
 }
 
 struct cfg80211_bss *
-- 
cgit v1.2.3


From abaea61c79ea7a03fde7db5b48414143546b07c4 Mon Sep 17 00:00:00 2001
From: Liad Kaufman <liad.kaufman@intel.com>
Date: Fri, 15 Mar 2019 17:39:07 +0200
Subject: ieee80211: update HE IEs to D4.0 spec

Update the out-dated comments as well, and have them point to
the correct sections in the D4.0 spec.

Signed-off-by: Liad Kaufman <liad.kaufman@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 522881f31938..61f0a316c6ac 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1557,7 +1557,7 @@ struct ieee80211_vht_operation {
  * struct ieee80211_he_cap_elem - HE capabilities element
  *
  * This structure is the "HE capabilities element" fixed fields as
- * described in P802.11ax_D3.0 section 9.4.2.237.2 and 9.4.2.237.3
+ * described in P802.11ax_D4.0 section 9.4.2.242.2 and 9.4.2.242.3
  */
 struct ieee80211_he_cap_elem {
 	u8 mac_cap_info[6];
@@ -1619,12 +1619,12 @@ struct ieee80211_he_mcs_nss_supp {
  * struct ieee80211_he_operation - HE capabilities element
  *
  * This structure is the "HE operation element" fields as
- * described in P802.11ax_D3.0 section 9.4.2.238
+ * described in P802.11ax_D4.0 section 9.4.2.243
  */
 struct ieee80211_he_operation {
 	__le32 he_oper_params;
 	__le16 he_mcs_nss_set;
-	/* Optional 0,1,3 or 4 bytes: depends on @he_oper_params */
+	/* Optional 0,1,3,4,5,7 or 8 bytes: depends on @he_oper_params */
 	u8 optional[0];
 } __packed;
 
@@ -1632,7 +1632,7 @@ struct ieee80211_he_operation {
  * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field
  *
  * This structure is the "MU AC Parameter Record" fields as
- * described in P802.11ax_D2.0 section 9.4.2.240
+ * described in P802.11ax_D4.0 section 9.4.2.245
  */
 struct ieee80211_he_mu_edca_param_ac_rec {
 	u8 aifsn;
@@ -1644,7 +1644,7 @@ struct ieee80211_he_mu_edca_param_ac_rec {
  * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element
  *
  * This structure is the "MU EDCA Parameter Set element" fields as
- * described in P802.11ax_D2.0 section 9.4.2.240
+ * described in P802.11ax_D4.0 section 9.4.2.245
  */
 struct ieee80211_mu_edca_param_set {
 	u8 mu_qos_info;
@@ -2026,6 +2026,7 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info)
 #define IEEE80211_HE_OPERATION_VHT_OPER_INFO			0x00004000
 #define IEEE80211_HE_OPERATION_CO_HOSTED_BSS			0x00008000
 #define IEEE80211_HE_OPERATION_ER_SU_DISABLE			0x00010000
+#define IEEE80211_HE_OPERATION_6GHZ_OP_INFO			0x00020000
 #define IEEE80211_HE_OPERATION_BSS_COLOR_MASK			0x3f000000
 #define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET		24
 #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR		0x40000000
@@ -2056,6 +2057,8 @@ ieee80211_he_oper_size(const u8 *he_oper_ie)
 		oper_len += 3;
 	if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS)
 		oper_len++;
+	if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)
+		oper_len += 4;
 
 	/* Add the first byte (extension ID) to the total length */
 	oper_len++;
-- 
cgit v1.2.3


From f2af2df800d3648b1d68e02d5b8a5d77cfee8970 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Sat, 16 Mar 2019 18:06:32 +0100
Subject: mac80211: calculate hash for fq without holding fq->lock in itxq
 enqueue
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reduces lock contention on enqueue/dequeue of iTXQ packets

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/fq_impl.h | 18 ++++++++++--------
 net/mac80211/tx.c     | 15 ++++++++++-----
 2 files changed, 20 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h
index be7c0fab3478..2caa86660ab0 100644
--- a/include/net/fq_impl.h
+++ b/include/net/fq_impl.h
@@ -107,21 +107,23 @@ begin:
 	return skb;
 }
 
+static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb)
+{
+	u32 hash = skb_get_hash_perturb(skb, fq->perturbation);
+
+	return reciprocal_scale(hash, fq->flows_cnt);
+}
+
 static struct fq_flow *fq_flow_classify(struct fq *fq,
-					struct fq_tin *tin,
+					struct fq_tin *tin, u32 idx,
 					struct sk_buff *skb,
 					fq_flow_get_default_t get_default_func)
 {
 	struct fq_flow *flow;
-	u32 hash;
-	u32 idx;
 
 	lockdep_assert_held(&fq->lock);
 
-	hash = skb_get_hash_perturb(skb, fq->perturbation);
-	idx = reciprocal_scale(hash, fq->flows_cnt);
 	flow = &fq->flows[idx];
-
 	if (flow->tin && flow->tin != tin) {
 		flow = get_default_func(fq, tin, idx, skb);
 		tin->collisions++;
@@ -153,7 +155,7 @@ static void fq_recalc_backlog(struct fq *fq,
 }
 
 static void fq_tin_enqueue(struct fq *fq,
-			   struct fq_tin *tin,
+			   struct fq_tin *tin, u32 idx,
 			   struct sk_buff *skb,
 			   fq_skb_free_t free_func,
 			   fq_flow_get_default_t get_default_func)
@@ -163,7 +165,7 @@ static void fq_tin_enqueue(struct fq *fq,
 
 	lockdep_assert_held(&fq->lock);
 
-	flow = fq_flow_classify(fq, tin, skb, get_default_func);
+	flow = fq_flow_classify(fq, tin, idx, skb, get_default_func);
 
 	flow->tin = tin;
 	flow->backlog += skb->len;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 8a49a74c0a37..2c0fec888021 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1399,11 +1399,15 @@ static void ieee80211_txq_enqueue(struct ieee80211_local *local,
 {
 	struct fq *fq = &local->fq;
 	struct fq_tin *tin = &txqi->tin;
+	u32 flow_idx = fq_flow_idx(fq, skb);
 
 	ieee80211_set_skb_enqueue_time(skb);
-	fq_tin_enqueue(fq, tin, skb,
+
+	spin_lock_bh(&fq->lock);
+	fq_tin_enqueue(fq, tin, flow_idx, skb,
 		       fq_skb_free_func,
 		       fq_flow_get_default_func);
+	spin_unlock_bh(&fq->lock);
 }
 
 static bool fq_vlan_filter_func(struct fq *fq, struct fq_tin *tin,
@@ -1590,7 +1594,6 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local,
 				struct sta_info *sta,
 				struct sk_buff *skb)
 {
-	struct fq *fq = &local->fq;
 	struct ieee80211_vif *vif;
 	struct txq_info *txqi;
 
@@ -1608,9 +1611,7 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local,
 	if (!txqi)
 		return false;
 
-	spin_lock_bh(&fq->lock);
 	ieee80211_txq_enqueue(local, txqi, skb);
-	spin_unlock_bh(&fq->lock);
 
 	schedule_and_wake_txq(local, txqi);
 
@@ -3221,6 +3222,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	u8 max_subframes = sta->sta.max_amsdu_subframes;
 	int max_frags = local->hw.max_tx_fragments;
 	int max_amsdu_len = sta->sta.max_amsdu_len;
+	u32 flow_idx;
 	__be16 len;
 	void *data;
 	bool ret = false;
@@ -3249,6 +3251,8 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 		max_amsdu_len = min_t(int, max_amsdu_len,
 				      sta->sta.max_tid_amsdu_len[tid]);
 
+	flow_idx = fq_flow_idx(fq, skb);
+
 	spin_lock_bh(&fq->lock);
 
 	/* TODO: Ideally aggregation should be done on dequeue to remain
@@ -3256,7 +3260,8 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	 */
 
 	tin = &txqi->tin;
-	flow = fq_flow_classify(fq, tin, skb, fq_flow_get_default_func);
+	flow = fq_flow_classify(fq, tin, flow_idx, skb,
+				fq_flow_get_default_func);
 	head = skb_peek_tail(&flow->queue);
 	if (!head || skb_is_gso(head))
 		goto out;
-- 
cgit v1.2.3


From 6cdd3979a2bdc16116c5b2eb09475abf54ba9e70 Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <alexander@wetzel-home.de>
Date: Tue, 19 Mar 2019 21:34:07 +0100
Subject: nl80211/cfg80211: Extended Key ID support

Add support for IEEE 802.11-2016 "Extended Key ID for Individually
Addressed Frames".

Extend cfg80211 and nl80211 to allow pairwise keys to be installed for
Rx only, enable Tx separately and allow Key ID 1 for pairwise keys.

Signed-off-by: Alexander Wetzel <alexander@wetzel-home.de>
[use NLA_POLICY_RANGE() for NL80211_KEY_MODE]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  2 ++
 include/uapi/linux/nl80211.h | 28 ++++++++++++++++++++++++++++
 net/wireless/nl80211.c       | 32 ++++++++++++++++++++++++++++----
 net/wireless/rdev-ops.h      |  3 ++-
 net/wireless/trace.h         | 31 ++++++++++++++++++++++++++-----
 net/wireless/util.c          | 21 +++++++++++++++------
 6 files changed, 101 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index f6665f8eba5a..2b039802ae2e 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -485,6 +485,7 @@ struct vif_params {
  *	with the get_key() callback, must be in little endian,
  *	length given by @seq_len.
  * @seq_len: length of @seq.
+ * @mode: key install mode (RX_TX, NO_TX or SET_TX)
  */
 struct key_params {
 	const u8 *key;
@@ -492,6 +493,7 @@ struct key_params {
 	int key_len;
 	int seq_len;
 	u32 cipher;
+	enum nl80211_key_mode mode;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index f00dbd82149e..e75615bf4453 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -4152,6 +4152,27 @@ enum nl80211_channel_type {
 	NL80211_CHAN_HT40PLUS
 };
 
+/**
+ * enum nl80211_key_mode - Key mode
+ *
+ * @NL80211_KEY_RX_TX: (Default)
+ *	Key can be used for Rx and Tx immediately
+ *
+ * The following modes can only be selected for unicast keys and when the
+ * driver supports @NL80211_EXT_FEATURE_EXT_KEY_ID:
+ *
+ * @NL80211_KEY_NO_TX: Only allowed in combination with @NL80211_CMD_NEW_KEY:
+ *	Unicast key can only be used for Rx, Tx not allowed, yet
+ * @NL80211_KEY_SET_TX: Only allowed in combination with @NL80211_CMD_SET_KEY:
+ *	The unicast key identified by idx and mac is cleared for Tx and becomes
+ *	the preferred Tx key for the station.
+ */
+enum nl80211_key_mode {
+	NL80211_KEY_RX_TX,
+	NL80211_KEY_NO_TX,
+	NL80211_KEY_SET_TX
+};
+
 /**
  * enum nl80211_chan_width - channel width definitions
  *
@@ -4395,6 +4416,9 @@ enum nl80211_key_default_types {
  * @NL80211_KEY_DEFAULT_TYPES: A nested attribute containing flags
  *	attributes, specifying what a key should be set as default as.
  *	See &enum nl80211_key_default_types.
+ * @NL80211_KEY_MODE: the mode from enum nl80211_key_mode.
+ *	Defaults to @NL80211_KEY_RX_TX.
+ *
  * @__NL80211_KEY_AFTER_LAST: internal
  * @NL80211_KEY_MAX: highest key attribute
  */
@@ -4408,6 +4432,7 @@ enum nl80211_key_attributes {
 	NL80211_KEY_DEFAULT_MGMT,
 	NL80211_KEY_TYPE,
 	NL80211_KEY_DEFAULT_TYPES,
+	NL80211_KEY_MODE,
 
 	/* keep last */
 	__NL80211_KEY_AFTER_LAST,
@@ -5353,6 +5378,8 @@ enum nl80211_feature_flags {
  *      able to rekey an in-use key correctly. Userspace must not rekey PTK keys
  *      if this flag is not set. Ignoring this can leak clear text packets and/or
  *      freeze the connection.
+ * @NL80211_EXT_FEATURE_EXT_KEY_ID: Driver supports "Extended Key ID for
+ *      Individually Addressed Frames" from IEEE802.11-2016.
  *
  * @NL80211_EXT_FEATURE_AIRTIME_FAIRNESS: Driver supports getting airtime
  *	fairness for transmitted packets and has enabled airtime fairness
@@ -5406,6 +5433,7 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_AIRTIME_FAIRNESS,
 	NL80211_EXT_FEATURE_AP_PMKSA_CACHING,
 	NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD,
+	NL80211_EXT_FEATURE_EXT_KEY_ID,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0124bab1f8a7..ab9b095f6094 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -553,6 +553,7 @@ static const struct nla_policy nl80211_key_policy[NL80211_KEY_MAX + 1] = {
 	[NL80211_KEY_DEFAULT_MGMT] = { .type = NLA_FLAG },
 	[NL80211_KEY_TYPE] = NLA_POLICY_MAX(NLA_U32, NUM_NL80211_KEYTYPES - 1),
 	[NL80211_KEY_DEFAULT_TYPES] = { .type = NLA_NESTED },
+	[NL80211_KEY_MODE] = NLA_POLICY_RANGE(NLA_U8, 0, NL80211_KEY_SET_TX),
 };
 
 /* policy for the key default flags */
@@ -967,6 +968,9 @@ static int nl80211_parse_key_new(struct genl_info *info, struct nlattr *key,
 		k->def_multi = kdt[NL80211_KEY_DEFAULT_TYPE_MULTICAST];
 	}
 
+	if (tb[NL80211_KEY_MODE])
+		k->p.mode = nla_get_u8(tb[NL80211_KEY_MODE]);
+
 	return 0;
 }
 
@@ -3643,8 +3647,11 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info)
 	if (key.idx < 0)
 		return -EINVAL;
 
-	/* only support setting default key */
-	if (!key.def && !key.defmgmt)
+	/* Only support setting default key and
+	 * Extended Key ID action NL80211_KEY_SET_TX.
+	 */
+	if (!key.def && !key.defmgmt &&
+	    !(key.p.mode == NL80211_KEY_SET_TX))
 		return -EINVAL;
 
 	wdev_lock(dev->ieee80211_ptr);
@@ -3668,7 +3675,7 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info)
 #ifdef CONFIG_CFG80211_WEXT
 		dev->ieee80211_ptr->wext.default_key = key.idx;
 #endif
-	} else {
+	} else if (key.defmgmt) {
 		if (key.def_uni || !key.def_multi) {
 			err = -EINVAL;
 			goto out;
@@ -3690,8 +3697,25 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info)
 #ifdef CONFIG_CFG80211_WEXT
 		dev->ieee80211_ptr->wext.default_mgmt_key = key.idx;
 #endif
-	}
+	} else if (key.p.mode == NL80211_KEY_SET_TX &&
+		   wiphy_ext_feature_isset(&rdev->wiphy,
+					   NL80211_EXT_FEATURE_EXT_KEY_ID)) {
+		u8 *mac_addr = NULL;
 
+		if (info->attrs[NL80211_ATTR_MAC])
+			mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]);
+
+		if (!mac_addr || key.idx < 0 || key.idx > 1) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		err = rdev_add_key(rdev, dev, key.idx,
+				   NL80211_KEYTYPE_PAIRWISE,
+				   mac_addr, &key.p);
+	} else {
+		err = -EINVAL;
+	}
  out:
 	wdev_unlock(dev->ieee80211_ptr);
 
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index c1e3210b09e6..18437a9deb54 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -77,7 +77,8 @@ static inline int rdev_add_key(struct cfg80211_registered_device *rdev,
 			       struct key_params *params)
 {
 	int ret;
-	trace_rdev_add_key(&rdev->wiphy, netdev, key_index, pairwise, mac_addr);
+	trace_rdev_add_key(&rdev->wiphy, netdev, key_index, pairwise,
+			   mac_addr, params->mode);
 	ret = rdev->ops->add_key(&rdev->wiphy, netdev, key_index, pairwise,
 				  mac_addr, params);
 	trace_rdev_return_int(&rdev->wiphy, ret);
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 2dda5291fc01..488ef2ce8231 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -430,22 +430,43 @@ DECLARE_EVENT_CLASS(key_handle,
 		  BOOL_TO_STR(__entry->pairwise), MAC_PR_ARG(mac_addr))
 );
 
-DEFINE_EVENT(key_handle, rdev_add_key,
+DEFINE_EVENT(key_handle, rdev_get_key,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index,
 		 bool pairwise, const u8 *mac_addr),
 	TP_ARGS(wiphy, netdev, key_index, pairwise, mac_addr)
 );
 
-DEFINE_EVENT(key_handle, rdev_get_key,
+DEFINE_EVENT(key_handle, rdev_del_key,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index,
 		 bool pairwise, const u8 *mac_addr),
 	TP_ARGS(wiphy, netdev, key_index, pairwise, mac_addr)
 );
 
-DEFINE_EVENT(key_handle, rdev_del_key,
+TRACE_EVENT(rdev_add_key,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index,
-		 bool pairwise, const u8 *mac_addr),
-	TP_ARGS(wiphy, netdev, key_index, pairwise, mac_addr)
+		 bool pairwise, const u8 *mac_addr, u8 mode),
+	TP_ARGS(wiphy, netdev, key_index, pairwise, mac_addr, mode),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(mac_addr)
+		__field(u8, key_index)
+		__field(bool, pairwise)
+		__field(u8, mode)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(mac_addr, mac_addr);
+		__entry->key_index = key_index;
+		__entry->pairwise = pairwise;
+		__entry->mode = mode;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", key_index: %u, "
+		  "mode: %u, pairwise: %s, mac addr: " MAC_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->key_index,
+		  __entry->mode, BOOL_TO_STR(__entry->pairwise),
+		  MAC_PR_ARG(mac_addr))
 );
 
 TRACE_EVENT(rdev_set_default_key,
diff --git a/net/wireless/util.c b/net/wireless/util.c
index e4b8db5e81ec..6c02c9cf7aa9 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -237,14 +237,23 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
-		/* Disallow pairwise keys with non-zero index unless it's WEP
-		 * or a vendor specific cipher (because current deployments use
-		 * pairwise WEP keys with non-zero indices and for vendor
-		 * specific ciphers this should be validated in the driver or
-		 * hardware level - but 802.11i clearly specifies to use zero)
+		/* IEEE802.11-2016 allows only 0 and - when using Extended Key
+		 * ID - 1 as index for pairwise keys.
+		 * @NL80211_KEY_NO_TX is only allowed for pairwise keys when
+		 * the driver supports Extended Key ID.
+		 * @NL80211_KEY_SET_TX can't be set when installing and
+		 * validating a key.
 		 */
-		if (pairwise && key_idx)
+		if (params->mode == NL80211_KEY_NO_TX) {
+			if (!wiphy_ext_feature_isset(&rdev->wiphy,
+						     NL80211_EXT_FEATURE_EXT_KEY_ID))
+				return -EINVAL;
+			else if (!pairwise || key_idx < 0 || key_idx > 1)
+				return -EINVAL;
+		} else if ((pairwise && key_idx) ||
+			   params->mode == NL80211_KEY_SET_TX) {
 			return -EINVAL;
+		}
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
-- 
cgit v1.2.3


From 96fc6efb9ad9d0cd8cbb4462f0eb2a07092649e6 Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <alexander@wetzel-home.de>
Date: Tue, 19 Mar 2019 21:34:08 +0100
Subject: mac80211: IEEE 802.11 Extended Key ID support

Add support for Extended Key ID as defined in IEEE 802.11-2016.

 - Implement the nl80211 API for Extended Key ID
 - Extend mac80211 API to allow drivers to support Extended Key ID
 - Enable Extended Key ID by default for drivers only supporting SW
   crypto (e.g. mac80211_hwsim)
 - Allow unicast Tx usage to be supressed (IEEE80211_KEY_FLAG_NO_AUTO_TX)
 - Select the decryption key based on the MPDU keyid
 - Enforce existing assumptions in the code that rekeys don't change the
   cipher

Signed-off-by: Alexander Wetzel <alexander@wetzel-home.de>
[remove module parameter]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  6 ++++
 net/mac80211/cfg.c         | 36 ++++++++++++++++++++++
 net/mac80211/debugfs.c     |  1 +
 net/mac80211/ieee80211_i.h |  2 +-
 net/mac80211/key.c         | 63 ++++++++++++++++++++++++++++++---------
 net/mac80211/key.h         |  2 ++
 net/mac80211/main.c        |  5 ++++
 net/mac80211/rx.c          | 74 ++++++++++++++++++++++++----------------------
 net/mac80211/sta_info.c    |  9 ++++++
 net/mac80211/tx.c          | 13 ++------
 10 files changed, 151 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index ac2ed8ec662b..c10abca55fde 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1697,6 +1697,7 @@ struct wireless_dev *ieee80211_vif_to_wdev(struct ieee80211_vif *vif);
  * @IEEE80211_KEY_FLAG_PUT_MIC_SPACE: This flag should be set by the driver for
  *	a TKIP key if it only requires MIC space. Do not set together with
  *	@IEEE80211_KEY_FLAG_GENERATE_MMIC on the same key.
+ * @IEEE80211_KEY_FLAG_NO_AUTO_TX: Key needs explicit Tx activation.
  */
 enum ieee80211_key_flags {
 	IEEE80211_KEY_FLAG_GENERATE_IV_MGMT	= BIT(0),
@@ -1708,6 +1709,7 @@ enum ieee80211_key_flags {
 	IEEE80211_KEY_FLAG_RX_MGMT		= BIT(6),
 	IEEE80211_KEY_FLAG_RESERVE_TAILROOM	= BIT(7),
 	IEEE80211_KEY_FLAG_PUT_MIC_SPACE	= BIT(8),
+	IEEE80211_KEY_FLAG_NO_AUTO_TX		= BIT(9),
 };
 
 /**
@@ -2243,6 +2245,9 @@ struct ieee80211_txq {
  * @IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID: Hardware supports multi BSSID
  *	only for HE APs. Applies if @IEEE80211_HW_SUPPORTS_MULTI_BSSID is set.
  *
+ * @IEEE80211_HW_EXT_KEY_ID_NATIVE: Driver and hardware are supporting Extended
+ *	Key ID and can handle two unicast keys per station for Rx and Tx.
+ *
  * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
  */
 enum ieee80211_hw_flags {
@@ -2294,6 +2299,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN,
 	IEEE80211_HW_SUPPORTS_MULTI_BSSID,
 	IEEE80211_HW_SUPPORTS_ONLY_HE_MULTI_BSSID,
+	IEEE80211_HW_EXT_KEY_ID_NATIVE,
 
 	/* keep last, obviously */
 	NUM_IEEE80211_HW_FLAGS
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 09dd1c2860fc..14bbb7e8ad0e 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -351,6 +351,36 @@ static int ieee80211_set_noack_map(struct wiphy *wiphy,
 	return 0;
 }
 
+static int ieee80211_set_tx(struct ieee80211_sub_if_data *sdata,
+			    const u8 *mac_addr, u8 key_idx)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_key *key;
+	struct sta_info *sta;
+	int ret = -EINVAL;
+
+	if (!wiphy_ext_feature_isset(local->hw.wiphy,
+				     NL80211_EXT_FEATURE_EXT_KEY_ID))
+		return -EINVAL;
+
+	sta = sta_info_get_bss(sdata, mac_addr);
+
+	if (!sta)
+		return -EINVAL;
+
+	if (sta->ptk_idx == key_idx)
+		return 0;
+
+	mutex_lock(&local->key_mtx);
+	key = key_mtx_dereference(local, sta->ptk[key_idx]);
+
+	if (key && key->conf.flags & IEEE80211_KEY_FLAG_NO_AUTO_TX)
+		ret = ieee80211_set_tx_key(key);
+
+	mutex_unlock(&local->key_mtx);
+	return ret;
+}
+
 static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 			     u8 key_idx, bool pairwise, const u8 *mac_addr,
 			     struct key_params *params)
@@ -365,6 +395,9 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 	if (!ieee80211_sdata_running(sdata))
 		return -ENETDOWN;
 
+	if (pairwise && params->mode == NL80211_KEY_SET_TX)
+		return ieee80211_set_tx(sdata, mac_addr, key_idx);
+
 	/* reject WEP and TKIP keys if WEP failed to initialize */
 	switch (params->cipher) {
 	case WLAN_CIPHER_SUITE_WEP40:
@@ -396,6 +429,9 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 	if (pairwise)
 		key->conf.flags |= IEEE80211_KEY_FLAG_PAIRWISE;
 
+	if (params->mode == NL80211_KEY_NO_TX)
+		key->conf.flags |= IEEE80211_KEY_FLAG_NO_AUTO_TX;
+
 	mutex_lock(&local->sta_mtx);
 
 	if (mac_addr) {
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 2d43bc127043..aa6f23e1a457 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -221,6 +221,7 @@ static const char *hw_flag_names[] = {
 	FLAG(TX_STATUS_NO_AMPDU_LEN),
 	FLAG(SUPPORTS_MULTI_BSSID),
 	FLAG(SUPPORTS_ONLY_HE_MULTI_BSSID),
+	FLAG(EXT_KEY_ID_NATIVE),
 #undef FLAG
 };
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index c5708f8a7401..32094e2ac0cb 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1269,7 +1269,7 @@ struct ieee80211_local {
 
 	/*
 	 * Key mutex, protects sdata's key_list and sta_info's
-	 * key pointers (write access, they're RCU.)
+	 * key pointers and ptk_idx (write access, they're RCU.)
 	 */
 	struct mutex key_mtx;
 
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 41b8db37c7c1..42d52cded4c1 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -265,9 +265,24 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key)
 			  sta ? sta->sta.addr : bcast_addr, ret);
 }
 
+int ieee80211_set_tx_key(struct ieee80211_key *key)
+{
+	struct sta_info *sta = key->sta;
+	struct ieee80211_local *local = key->local;
+	struct ieee80211_key *old;
+
+	assert_key_lock(local);
+
+	old = key_mtx_dereference(local, sta->ptk[sta->ptk_idx]);
+	sta->ptk_idx = key->conf.keyidx;
+	ieee80211_check_fast_xmit(sta);
+
+	return 0;
+}
+
 static int ieee80211_hw_key_replace(struct ieee80211_key *old_key,
 				    struct ieee80211_key *new_key,
-				    bool ptk0rekey)
+				    bool pairwise)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct ieee80211_local *local;
@@ -284,8 +299,9 @@ static int ieee80211_hw_key_replace(struct ieee80211_key *old_key,
 	assert_key_lock(old_key->local);
 	sta = old_key->sta;
 
-	/* PTK only using key ID 0 needs special handling on rekey */
-	if (new_key && sta && ptk0rekey) {
+	/* Unicast rekey without Extended Key ID needs special handling */
+	if (new_key && sta && pairwise &&
+	    rcu_access_pointer(sta->ptk[sta->ptk_idx]) == old_key) {
 		local = old_key->local;
 		sdata = old_key->sdata;
 
@@ -401,10 +417,6 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata,
 
 	if (old) {
 		idx = old->conf.keyidx;
-		/* TODO: proper implement and test "Extended Key ID for
-		 * Individually Addressed Frames" from IEEE 802.11-2016.
-		 * Till then always assume only key ID 0 is used for
-		 * pairwise keys.*/
 		ret = ieee80211_hw_key_replace(old, new, pairwise);
 	} else {
 		/* new must be provided in case old is not */
@@ -421,15 +433,20 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata,
 	if (sta) {
 		if (pairwise) {
 			rcu_assign_pointer(sta->ptk[idx], new);
-			sta->ptk_idx = idx;
-			if (new) {
+			if (new &&
+			    !(new->conf.flags & IEEE80211_KEY_FLAG_NO_AUTO_TX)) {
+				sta->ptk_idx = idx;
 				clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
 				ieee80211_check_fast_xmit(sta);
 			}
 		} else {
 			rcu_assign_pointer(sta->gtk[idx], new);
 		}
-		if (new)
+		/* Only needed for transition from no key -> key.
+		 * Still triggers unnecessary when using Extended Key ID
+		 * and installing the second key ID the first time.
+		 */
+		if (new && !old)
 			ieee80211_check_fast_rx(sta);
 	} else {
 		defunikey = old &&
@@ -745,16 +762,34 @@ int ieee80211_key_link(struct ieee80211_key *key,
 	 * can cause warnings to appear.
 	 */
 	bool delay_tailroom = sdata->vif.type == NL80211_IFTYPE_STATION;
-	int ret;
+	int ret = -EOPNOTSUPP;
 
 	mutex_lock(&sdata->local->key_mtx);
 
-	if (sta && pairwise)
+	if (sta && pairwise) {
+		struct ieee80211_key *alt_key;
+
 		old_key = key_mtx_dereference(sdata->local, sta->ptk[idx]);
-	else if (sta)
+		alt_key = key_mtx_dereference(sdata->local, sta->ptk[idx ^ 1]);
+
+		/* The rekey code assumes that the old and new key are using
+		 * the same cipher. Enforce the assumption for pairwise keys.
+		 */
+		if (key &&
+		    ((alt_key && alt_key->conf.cipher != key->conf.cipher) ||
+		     (old_key && old_key->conf.cipher != key->conf.cipher)))
+			goto out;
+	} else if (sta) {
 		old_key = key_mtx_dereference(sdata->local, sta->gtk[idx]);
-	else
+	} else {
 		old_key = key_mtx_dereference(sdata->local, sdata->keys[idx]);
+	}
+
+	/* Non-pairwise keys must also not switch the cipher on rekey */
+	if (!pairwise) {
+		if (key && old_key && old_key->conf.cipher != key->conf.cipher)
+			goto out;
+	}
 
 	/*
 	 * Silently accept key re-installation without really installing the
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index ebdb80b85dc3..f06fbd03d235 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -18,6 +18,7 @@
 
 #define NUM_DEFAULT_KEYS 4
 #define NUM_DEFAULT_MGMT_KEYS 2
+#define INVALID_PTK_KEYIDX 2 /* Keyidx always pointing to a NULL key for PTK */
 
 struct ieee80211_local;
 struct ieee80211_sub_if_data;
@@ -146,6 +147,7 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 int ieee80211_key_link(struct ieee80211_key *key,
 		       struct ieee80211_sub_if_data *sdata,
 		       struct sta_info *sta);
+int ieee80211_set_tx_key(struct ieee80211_key *key);
 void ieee80211_key_free(struct ieee80211_key *key, bool delay_tailroom);
 void ieee80211_key_free_unused(struct ieee80211_key *key);
 void ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, int idx,
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 800e67615e2a..5d6b93050c0b 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1051,6 +1051,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		}
 	}
 
+	if (!local->ops->set_key ||
+	    ieee80211_hw_check(&local->hw, EXT_KEY_ID_NATIVE))
+		wiphy_ext_feature_set(local->hw.wiphy,
+				      NL80211_EXT_FEATURE_EXT_KEY_ID);
+
 	/*
 	 * Calculate scan IE length -- we need this to alloc
 	 * memory and to subtract from the driver limit. It
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 7f8d93401ce0..4a03c18b39a8 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1005,23 +1005,43 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb)
 	return -1;
 }
 
-static int ieee80211_get_cs_keyid(const struct ieee80211_cipher_scheme *cs,
-				  struct sk_buff *skb)
+static int ieee80211_get_keyid(struct sk_buff *skb,
+			       const struct ieee80211_cipher_scheme *cs)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	__le16 fc;
 	int hdrlen;
+	int minlen;
+	u8 key_idx_off;
+	u8 key_idx_shift;
 	u8 keyid;
 
 	fc = hdr->frame_control;
 	hdrlen = ieee80211_hdrlen(fc);
 
-	if (skb->len < hdrlen + cs->hdr_len)
+	if (cs) {
+		minlen = hdrlen + cs->hdr_len;
+		key_idx_off = hdrlen + cs->key_idx_off;
+		key_idx_shift = cs->key_idx_shift;
+	} else {
+		/* WEP, TKIP, CCMP and GCMP */
+		minlen = hdrlen + IEEE80211_WEP_IV_LEN;
+		key_idx_off = hdrlen + 3;
+		key_idx_shift = 6;
+	}
+
+	if (unlikely(skb->len < minlen))
 		return -EINVAL;
 
-	skb_copy_bits(skb, hdrlen + cs->key_idx_off, &keyid, 1);
-	keyid &= cs->key_idx_mask;
-	keyid >>= cs->key_idx_shift;
+	skb_copy_bits(skb, key_idx_off, &keyid, 1);
+
+	if (cs)
+		keyid &= cs->key_idx_mask;
+	keyid >>= key_idx_shift;
+
+	/* cs could use more than the usual two bits for the keyid */
+	if (unlikely(keyid >= NUM_DEFAULT_KEYS))
+		return -EINVAL;
 
 	return keyid;
 }
@@ -1852,9 +1872,9 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	int keyidx;
-	int hdrlen;
 	ieee80211_rx_result result = RX_DROP_UNUSABLE;
 	struct ieee80211_key *sta_ptk = NULL;
+	struct ieee80211_key *ptk_idx = NULL;
 	int mmie_keyidx = -1;
 	__le16 fc;
 	const struct ieee80211_cipher_scheme *cs = NULL;
@@ -1892,21 +1912,24 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 
 	if (rx->sta) {
 		int keyid = rx->sta->ptk_idx;
+		sta_ptk = rcu_dereference(rx->sta->ptk[keyid]);
 
-		if (ieee80211_has_protected(fc) && rx->sta->cipher_scheme) {
+		if (ieee80211_has_protected(fc)) {
 			cs = rx->sta->cipher_scheme;
-			keyid = ieee80211_get_cs_keyid(cs, rx->skb);
+			keyid = ieee80211_get_keyid(rx->skb, cs);
+
 			if (unlikely(keyid < 0))
 				return RX_DROP_UNUSABLE;
+
+			ptk_idx = rcu_dereference(rx->sta->ptk[keyid]);
 		}
-		sta_ptk = rcu_dereference(rx->sta->ptk[keyid]);
 	}
 
 	if (!ieee80211_has_protected(fc))
 		mmie_keyidx = ieee80211_get_mmie_keyidx(rx->skb);
 
 	if (!is_multicast_ether_addr(hdr->addr1) && sta_ptk) {
-		rx->key = sta_ptk;
+		rx->key = ptk_idx ? ptk_idx : sta_ptk;
 		if ((status->flag & RX_FLAG_DECRYPTED) &&
 		    (status->flag & RX_FLAG_IV_STRIPPED))
 			return RX_CONTINUE;
@@ -1966,8 +1989,6 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 		}
 		return RX_CONTINUE;
 	} else {
-		u8 keyid;
-
 		/*
 		 * The device doesn't give us the IV so we won't be
 		 * able to look up the key. That's ok though, we
@@ -1981,23 +2002,10 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 		    (status->flag & RX_FLAG_IV_STRIPPED))
 			return RX_CONTINUE;
 
-		hdrlen = ieee80211_hdrlen(fc);
-
-		if (cs) {
-			keyidx = ieee80211_get_cs_keyid(cs, rx->skb);
+		keyidx = ieee80211_get_keyid(rx->skb, cs);
 
-			if (unlikely(keyidx < 0))
-				return RX_DROP_UNUSABLE;
-		} else {
-			if (rx->skb->len < 8 + hdrlen)
-				return RX_DROP_UNUSABLE; /* TODO: count this? */
-			/*
-			 * no need to call ieee80211_wep_get_keyidx,
-			 * it verifies a bunch of things we've done already
-			 */
-			skb_copy_bits(rx->skb, hdrlen + 3, &keyid, 1);
-			keyidx = keyid >> 6;
-		}
+		if (unlikely(keyidx < 0))
+			return RX_DROP_UNUSABLE;
 
 		/* check per-station GTK first, if multicast packet */
 		if (is_multicast_ether_addr(hdr->addr1) && rx->sta)
@@ -4042,12 +4050,8 @@ void ieee80211_check_fast_rx(struct sta_info *sta)
 		case WLAN_CIPHER_SUITE_GCMP_256:
 			break;
 		default:
-			/* we also don't want to deal with WEP or cipher scheme
-			 * since those require looking up the key idx in the
-			 * frame, rather than assuming the PTK is used
-			 * (we need to revisit this once we implement the real
-			 * PTK index, which is now valid in the spec, but we
-			 * haven't implemented that part yet)
+			/* We also don't want to deal with
+			 * WEP or cipher scheme.
 			 */
 			goto clear_rcu;
 		}
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index a81e1279a76d..a4932ee3595c 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -347,6 +347,15 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	sta->sta.max_rx_aggregation_subframes =
 		local->hw.max_rx_aggregation_subframes;
 
+	/* Extended Key ID needs to install keys for keyid 0 and 1 Rx-only.
+	 * The Tx path starts to use a key as soon as the key slot ptk_idx
+	 * references to is not NULL. To not use the initial Rx-only key
+	 * prematurely for Tx initialize ptk_idx to an impossible PTK keyid
+	 * which always will refer to a NULL key.
+	 */
+	BUILD_BUG_ON(ARRAY_SIZE(sta->ptk) <= INVALID_PTK_KEYIDX);
+	sta->ptk_idx = INVALID_PTK_KEYIDX;
+
 	sta->local = local;
 	sta->sdata = sdata;
 	sta->rx_stats.last_rx = jiffies;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index a3c6053cdffe..c49fd1e961d0 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3001,23 +3001,15 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
 		switch (build.key->conf.cipher) {
 		case WLAN_CIPHER_SUITE_CCMP:
 		case WLAN_CIPHER_SUITE_CCMP_256:
-			/* add fixed key ID */
-			if (gen_iv) {
-				(build.hdr + build.hdr_len)[3] =
-					0x20 | (build.key->conf.keyidx << 6);
+			if (gen_iv)
 				build.pn_offs = build.hdr_len;
-			}
 			if (gen_iv || iv_spc)
 				build.hdr_len += IEEE80211_CCMP_HDR_LEN;
 			break;
 		case WLAN_CIPHER_SUITE_GCMP:
 		case WLAN_CIPHER_SUITE_GCMP_256:
-			/* add fixed key ID */
-			if (gen_iv) {
-				(build.hdr + build.hdr_len)[3] =
-					0x20 | (build.key->conf.keyidx << 6);
+			if (gen_iv)
 				build.pn_offs = build.hdr_len;
-			}
 			if (gen_iv || iv_spc)
 				build.hdr_len += IEEE80211_GCMP_HDR_LEN;
 			break;
@@ -3388,6 +3380,7 @@ static void ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata,
 			pn = atomic64_inc_return(&key->conf.tx_pn);
 			crypto_hdr[0] = pn;
 			crypto_hdr[1] = pn >> 8;
+			crypto_hdr[3] = 0x20 | (key->conf.keyidx << 6);
 			crypto_hdr[4] = pn >> 16;
 			crypto_hdr[5] = pn >> 24;
 			crypto_hdr[6] = pn >> 32;
-- 
cgit v1.2.3


From e96d1cd2635c05efdd01b4eafcfc50c22c40751f Mon Sep 17 00:00:00 2001
From: Ashok Raj Nagarajan <arnagara@codeaurora.org>
Date: Fri, 29 Mar 2019 16:18:21 +0530
Subject: cfg80211: Add support to set tx power for a station associated

This patch adds support to set transmit power setting type and transmit
power level attributes to NL80211_CMD_SET_STATION in order to facilitate
adjusting the transmit power level of a station associated to the AP.

The added attributes allow selection of automatic and limited transmit
power level, with the level defined in dBm format.

Co-developed-by: Balaji Pothunoori <bpothuno@codeaurora.org>
Signed-off-by: Ashok Raj Nagarajan <arnagara@codeaurora.org>
Signed-off-by: Balaji Pothunoori <bpothuno@codeaurora.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 22 ++++++++++++++++++++++
 include/uapi/linux/nl80211.h | 15 +++++++++++++++
 net/wireless/nl80211.c       | 43 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 80 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 2b039802ae2e..2ea04e94b522 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -975,6 +975,27 @@ enum station_parameters_apply_mask {
 	STATION_PARAM_APPLY_UAPSD = BIT(0),
 	STATION_PARAM_APPLY_CAPABILITY = BIT(1),
 	STATION_PARAM_APPLY_PLINK_STATE = BIT(2),
+	STATION_PARAM_APPLY_STA_TXPOWER = BIT(3),
+};
+
+/**
+ * struct sta_txpwr - station txpower configuration
+ *
+ * Used to configure txpower for station.
+ *
+ * @power: tx power (in dBm) to be used for sending data traffic. If tx power
+ *	is not provided, the default per-interface tx power setting will be
+ *	overriding. Driver should be picking up the lowest tx power, either tx
+ *	power per-interface or per-station.
+ * @type: In particular if TPC %type is NL80211_TX_POWER_LIMITED then tx power
+ *	will be less than or equal to specified from userspace, whereas if TPC
+ *	%type is NL80211_TX_POWER_AUTOMATIC then it indicates default tx power.
+ *	NL80211_TX_POWER_FIXED is not a valid configuration option for
+ *	per peer TPC.
+ */
+struct sta_txpwr {
+	s16 power;
+	enum nl80211_tx_power_setting type;
 };
 
 /**
@@ -1049,6 +1070,7 @@ struct station_parameters {
 	const struct ieee80211_he_cap_elem *he_capa;
 	u8 he_capa_len;
 	u16 airtime_weight;
+	struct sta_txpwr txpwr;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index e75615bf4453..25f70dd2b583 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2315,6 +2315,15 @@ enum nl80211_commands {
  * @NL80211_ATTR_AIRTIME_WEIGHT: Station's weight when scheduled by the airtime
  *	scheduler.
  *
+ * @NL80211_ATTR_STA_TX_POWER_SETTING: Transmit power setting type (u8) for
+ *	station associated with the AP. See &enum nl80211_tx_power_setting for
+ *	possible values.
+ * @NL80211_ATTR_STA_TX_POWER: Transmit power level (s16) in dBm units. This
+ *	allows to set Tx power for a station. If this attribute is not included,
+ *	the default per-interface tx power setting will be overriding. Driver
+ *	should be picking up the lowest tx power, either tx power per-interface
+ *	or per-station.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2765,6 +2774,8 @@ enum nl80211_attrs {
 	NL80211_ATTR_PEER_MEASUREMENTS,
 
 	NL80211_ATTR_AIRTIME_WEIGHT,
+	NL80211_ATTR_STA_TX_POWER_SETTING,
+	NL80211_ATTR_STA_TX_POWER,
 
 	/* add attributes here, update the policy in nl80211.c */
 
@@ -5391,6 +5402,9 @@ enum nl80211_feature_flags {
  * @NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD: Driver supports
  *	filtering of sched scan results using band specific RSSI thresholds.
  *
+ * @NL80211_EXT_FEATURE_STA_TX_PWR: This driver supports controlling tx power
+ *	to a station.
+ *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
  */
@@ -5434,6 +5448,7 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_AP_PMKSA_CACHING,
 	NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD,
 	NL80211_EXT_FEATURE_EXT_KEY_ID,
+	NL80211_EXT_FEATURE_STA_TX_PWR,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 64f191244c67..0524a6fb84ad 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -331,6 +331,11 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 					       .len = NL80211_MAX_SUPP_RATES },
 	[NL80211_ATTR_STA_PLINK_ACTION] =
 		NLA_POLICY_MAX(NLA_U8, NUM_NL80211_PLINK_ACTIONS - 1),
+	[NL80211_ATTR_STA_TX_POWER_SETTING] =
+		NLA_POLICY_RANGE(NLA_U8,
+				 NL80211_TX_POWER_AUTOMATIC,
+				 NL80211_TX_POWER_FIXED),
+	[NL80211_ATTR_STA_TX_POWER] = { .type = NLA_S16 },
 	[NL80211_ATTR_STA_VLAN] = { .type = NLA_U32 },
 	[NL80211_ATTR_MNTR_FLAGS] = { /* NLA_NESTED can't be empty */ },
 	[NL80211_ATTR_MESH_ID] = { .type = NLA_BINARY,
@@ -5420,6 +5425,36 @@ static int nl80211_set_station_tdls(struct genl_info *info,
 	return nl80211_parse_sta_wme(info, params);
 }
 
+static int nl80211_parse_sta_txpower_setting(struct genl_info *info,
+					     struct station_parameters *params)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	int idx;
+
+	if (info->attrs[NL80211_ATTR_STA_TX_POWER_SETTING]) {
+		if (!rdev->ops->set_tx_power ||
+		    !wiphy_ext_feature_isset(&rdev->wiphy,
+					 NL80211_EXT_FEATURE_STA_TX_PWR))
+			return -EOPNOTSUPP;
+
+		idx = NL80211_ATTR_STA_TX_POWER_SETTING;
+		params->txpwr.type = nla_get_u8(info->attrs[idx]);
+
+		if (params->txpwr.type == NL80211_TX_POWER_LIMITED) {
+			idx = NL80211_ATTR_STA_TX_POWER;
+
+			if (info->attrs[idx])
+				params->txpwr.power =
+					nla_get_s16(info->attrs[idx]);
+			else
+				return -EINVAL;
+		}
+		params->sta_modify_mask |= STATION_PARAM_APPLY_STA_TXPOWER;
+	}
+
+	return 0;
+}
+
 static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -5513,6 +5548,10 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info)
 				     NL80211_EXT_FEATURE_AIRTIME_FAIRNESS))
 		return -EOPNOTSUPP;
 
+	err = nl80211_parse_sta_txpower_setting(info, &params);
+	if (err)
+		return err;
+
 	/* Include parameters for TDLS peer (will check later) */
 	err = nl80211_set_station_tdls(info, &params);
 	if (err)
@@ -5650,6 +5689,10 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 				     NL80211_EXT_FEATURE_AIRTIME_FAIRNESS))
 		return -EOPNOTSUPP;
 
+	err = nl80211_parse_sta_txpower_setting(info, &params);
+	if (err)
+		return err;
+
 	err = nl80211_parse_sta_channel_info(info, &params);
 	if (err)
 		return err;
-- 
cgit v1.2.3


From ba905bf432f662cb907fd692a4f160e612c0408b Mon Sep 17 00:00:00 2001
From: Ashok Raj Nagarajan <arnagara@codeaurora.org>
Date: Fri, 29 Mar 2019 16:19:09 +0530
Subject: mac80211: store tx power value from user to station

This patch introduce a new driver callback drv_sta_set_txpwr. This API will
copy the transmit power value passed from user space and call the driver
callback to set the tx power for the station.

Co-developed-by: Balaji Pothunoori <bpothuno@codeaurora.org>
Signed-off-by: Ashok Raj Nagarajan <arnagara@codeaurora.org>
Signed-off-by: Balaji Pothunoori <bpothuno@codeaurora.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    | 22 ++++++++++++++++++++++
 net/mac80211/cfg.c        |  9 +++++++++
 net/mac80211/driver-ops.c | 21 +++++++++++++++++++++
 net/mac80211/driver-ops.h |  5 +++++
 net/mac80211/trace.h      | 30 ++++++++++++++++++++++++++++++
 5 files changed, 87 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index c10abca55fde..d66fbfe8d55d 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1889,6 +1889,24 @@ struct ieee80211_sta_rates {
 	} rate[IEEE80211_TX_RATE_TABLE_SIZE];
 };
 
+/**
+ * struct ieee80211_sta_txpwr - station txpower configuration
+ *
+ * Used to configure txpower for station.
+ *
+ * @power: indicates the tx power, in dBm, to be used when sending data frames
+ *	to the STA.
+ * @type: In particular if TPC %type is NL80211_TX_POWER_LIMITED then tx power
+ *	will be less than or equal to specified from userspace, whereas if TPC
+ *	%type is NL80211_TX_POWER_AUTOMATIC then it indicates default tx power.
+ *	NL80211_TX_POWER_FIXED is not a valid configuration option for
+ *	per peer TPC.
+ */
+struct ieee80211_sta_txpwr {
+	s16 power;
+	enum nl80211_tx_power_setting type;
+};
+
 /**
  * struct ieee80211_sta - station table entry
  *
@@ -1975,6 +1993,7 @@ struct ieee80211_sta {
 	bool support_p2p_ps;
 	u16 max_rc_amsdu_len;
 	u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS];
+	struct ieee80211_sta_txpwr txpwr;
 
 	struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1];
 
@@ -3800,6 +3819,9 @@ struct ieee80211_ops {
 #endif
 	void (*sta_notify)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			enum sta_notify_cmd, struct ieee80211_sta *sta);
+	int (*sta_set_txpwr)(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_sta *sta);
 	int (*sta_state)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			 struct ieee80211_sta *sta,
 			 enum ieee80211_sta_state old_state,
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 14bbb7e8ad0e..ba6e4080d63d 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1457,6 +1457,15 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 	if (params->listen_interval >= 0)
 		sta->listen_interval = params->listen_interval;
 
+	if (params->sta_modify_mask & STATION_PARAM_APPLY_STA_TXPOWER) {
+		sta->sta.txpwr.type = params->txpwr.type;
+		if (params->txpwr.type == NL80211_TX_POWER_LIMITED)
+			sta->sta.txpwr.power = params->txpwr.power;
+		ret = drv_sta_set_txpwr(local, sdata, sta);
+		if (ret)
+			return ret;
+	}
+
 	if (params->supported_rates) {
 		ieee80211_parse_bitrates(&sdata->vif.bss_conf.chandef,
 					 sband, params->supported_rates,
diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index bb886e7db47f..839c0022a29c 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -138,6 +138,27 @@ int drv_sta_state(struct ieee80211_local *local,
 	return ret;
 }
 
+__must_check
+int drv_sta_set_txpwr(struct ieee80211_local *local,
+		      struct ieee80211_sub_if_data *sdata,
+		      struct sta_info *sta)
+{
+	int ret = -EOPNOTSUPP;
+
+	might_sleep();
+
+	sdata = get_bss_sdata(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
+
+	trace_drv_sta_set_txpwr(local, sdata, &sta->sta);
+	if (local->ops->sta_set_txpwr)
+		ret = local->ops->sta_set_txpwr(&local->hw, &sdata->vif,
+						&sta->sta);
+	trace_drv_return_int(local, ret);
+	return ret;
+}
+
 void drv_sta_rc_update(struct ieee80211_local *local,
 		       struct ieee80211_sub_if_data *sdata,
 		       struct ieee80211_sta *sta, u32 changed)
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 28d022a3eee3..62edfa6a73ed 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -529,6 +529,11 @@ int drv_sta_state(struct ieee80211_local *local,
 		  enum ieee80211_sta_state old_state,
 		  enum ieee80211_sta_state new_state);
 
+__must_check
+int drv_sta_set_txpwr(struct ieee80211_local *local,
+		      struct ieee80211_sub_if_data *sdata,
+		      struct sta_info *sta);
+
 void drv_sta_rc_update(struct ieee80211_local *local,
 		       struct ieee80211_sub_if_data *sdata,
 		       struct ieee80211_sta *sta, u32 changed);
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 8ba70d26b82e..3bb4459b52c7 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -828,6 +828,36 @@ TRACE_EVENT(drv_sta_state,
 	)
 );
 
+TRACE_EVENT(drv_sta_set_txpwr,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta),
+
+	TP_ARGS(local, sdata, sta),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		STA_ENTRY
+		__field(s16, txpwr)
+		__field(u8, type)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_ASSIGN;
+		__entry->txpwr = sta->txpwr.power;
+		__entry->type = sta->txpwr.type;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT  VIF_PR_FMT  STA_PR_FMT " txpwr: %d type %d",
+		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG,
+		__entry->txpwr,  __entry->type
+	)
+);
+
 TRACE_EVENT(drv_sta_rc_update,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
-- 
cgit v1.2.3


From 5809a5d54bb9eda3a388b5a712657970c2cb9f8e Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 11 Apr 2019 11:59:50 +0300
Subject: cfg80211: don't pass pointer to pointer unnecessarily

The cfg80211_merge_profile() and ieee802_11_find_bssid_profile() are
a bit cleaner if we just pass the merged_ie pointer instead of a pointer
to the pointer.

This isn't a functional change, it's just a clean up.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 2 +-
 net/mac80211/util.c    | 8 ++++----
 net/wireless/scan.c    | 8 ++++----
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 2ea04e94b522..944de1802210 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5578,7 +5578,7 @@ bool cfg80211_is_element_inherited(const struct element *element,
 size_t cfg80211_merge_profile(const u8 *ie, size_t ielen,
 			      const struct element *mbssid_elem,
 			      const struct element *sub_elem,
-			      u8 **merged_ie, size_t max_copy_len);
+			      u8 *merged_ie, size_t max_copy_len);
 
 /**
  * enum cfg80211_bss_frame_type - frame type that the BSS data came from
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 99dd58454592..cba4633cd6cf 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1258,7 +1258,7 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len,
 					    struct ieee802_11_elems *elems,
 					    u8 *transmitter_bssid,
 					    u8 *bss_bssid,
-					    u8 **nontransmitted_profile)
+					    u8 *nontransmitted_profile)
 {
 	const struct element *elem, *sub;
 	size_t profile_len = 0;
@@ -1290,7 +1290,7 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len,
 				continue;
 			}
 
-			memset(*nontransmitted_profile, 0, len);
+			memset(nontransmitted_profile, 0, len);
 			profile_len = cfg80211_merge_profile(start, len,
 							     elem,
 							     sub,
@@ -1299,7 +1299,7 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len,
 
 			/* found a Nontransmitted BSSID Profile */
 			index = cfg80211_find_ie(WLAN_EID_MULTI_BSSID_IDX,
-						 *nontransmitted_profile,
+						 nontransmitted_profile,
 						 profile_len);
 			if (!index || index[1] < 1 || index[2] == 0) {
 				/* Invalid MBSSID Index element */
@@ -1341,7 +1341,7 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 			ieee802_11_find_bssid_profile(start, len, elems,
 						      transmitter_bssid,
 						      bss_bssid,
-						      &nontransmitted_profile);
+						      nontransmitted_profile);
 		non_inherit =
 			cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
 					       nontransmitted_profile,
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 878c867f3f7d..85dd3342d2c4 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1502,7 +1502,7 @@ static const struct element
 size_t cfg80211_merge_profile(const u8 *ie, size_t ielen,
 			      const struct element *mbssid_elem,
 			      const struct element *sub_elem,
-			      u8 **merged_ie, size_t max_copy_len)
+			      u8 *merged_ie, size_t max_copy_len)
 {
 	size_t copied_len = sub_elem->datalen;
 	const struct element *next_mbssid;
@@ -1510,7 +1510,7 @@ size_t cfg80211_merge_profile(const u8 *ie, size_t ielen,
 	if (sub_elem->datalen > max_copy_len)
 		return 0;
 
-	memcpy(*merged_ie, sub_elem->data, sub_elem->datalen);
+	memcpy(merged_ie, sub_elem->data, sub_elem->datalen);
 
 	while ((next_mbssid = cfg80211_get_profile_continuation(ie, ielen,
 								mbssid_elem,
@@ -1519,7 +1519,7 @@ size_t cfg80211_merge_profile(const u8 *ie, size_t ielen,
 
 		if (copied_len + next_sub->datalen > max_copy_len)
 			break;
-		memcpy(*merged_ie + copied_len, next_sub->data,
+		memcpy(merged_ie + copied_len, next_sub->data,
 		       next_sub->datalen);
 		copied_len += next_sub->datalen;
 	}
@@ -1588,7 +1588,7 @@ static void cfg80211_parse_mbssid_data(struct wiphy *wiphy,
 			profile_len = cfg80211_merge_profile(ie, ielen,
 							     elem,
 							     sub,
-							     &profile,
+							     profile,
 							     ielen);
 
 			/* found a Nontransmitted BSSID Profile */
-- 
cgit v1.2.3


From 5ab92e7fe49ad74293b50fb9e6f25be5521e2f68 Mon Sep 17 00:00:00 2001
From: Rajkumar Manoharan <rmanohar@codeaurora.org>
Date: Thu, 11 Apr 2019 13:47:24 -0700
Subject: cfg80211: add support to probe unexercised mesh link

Adding support to allow mesh HWMP to measure link metrics on unexercised
direct mesh path by sending some data frames to other mesh points which
are not currently selected as a primary traffic path but only 1 hop away.
The absence of the primary path to the chosen node makes it necessary to
apply some form of marking on a chosen packet stream so that the packets
can be properly steered to the selected node for testing, and not by the
regular mesh path lookup.

Tested-by: Pradeep Kumar Chitrapu <pradeepc@codeaurora.org>
Signed-off-by: Rajkumar Manoharan <rmanohar@codeaurora.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  5 +++++
 include/uapi/linux/nl80211.h | 17 ++++++++++++++++
 net/wireless/nl80211.c       | 48 ++++++++++++++++++++++++++++++++++++++++++++
 net/wireless/rdev-ops.h      | 13 ++++++++++++
 net/wireless/trace.h         | 18 +++++++++++++++++
 5 files changed, 101 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 944de1802210..298301525f9f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3501,6 +3501,9 @@ struct cfg80211_update_owe_info {
  * @update_owe_info: Provide updated OWE info to driver. Driver implementing SME
  *	but offloading OWE processing to the user space will get the updated
  *	DH IE through this interface.
+ *
+ * @probe_mesh_link: Probe direct Mesh peer's link quality by sending data frame
+ *	and overrule HWMP path selection algorithm.
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -3817,6 +3820,8 @@ struct cfg80211_ops {
 			      struct cfg80211_pmsr_request *request);
 	int	(*update_owe_info)(struct wiphy *wiphy, struct net_device *dev,
 				   struct cfg80211_update_owe_info *owe_info);
+	int	(*probe_mesh_link)(struct wiphy *wiphy, struct net_device *dev,
+				   const u8 *buf, size_t len);
 };
 
 /*
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 25f70dd2b583..6f09d1500960 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1070,6 +1070,21 @@
  *	OWE AKM by the host drivers that implement SME but rely
  *	on the user space for the cryptographic/DH IE processing in AP mode.
  *
+ * @NL80211_CMD_PROBE_MESH_LINK: The requirement for mesh link metric
+ *	refreshing, is that from one mesh point we be able to send some data
+ *	frames to other mesh points which are not currently selected as a
+ *	primary traffic path, but which are only 1 hop away. The absence of
+ *	the primary path to the chosen node makes it necessary to apply some
+ *	form of marking on a chosen packet stream so that the packets can be
+ *	properly steered to the selected node for testing, and not by the
+ *	regular mesh path lookup. Further, the packets must be of type data
+ *	so that the rate control (often embedded in firmware) is used for
+ *	rate selection.
+ *
+ *	Here attribute %NL80211_ATTR_MAC is used to specify connected mesh
+ *	peer MAC address and %NL80211_ATTR_FRAME is used to specify the frame
+ *	content. The frame is ethernet data.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -1292,6 +1307,8 @@ enum nl80211_commands {
 
 	NL80211_CMD_UPDATE_OWE_INFO,
 
+	NL80211_CMD_PROBE_MESH_LINK,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5dfc4dba9e56..3aecdd3d5b07 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -13404,6 +13404,47 @@ static int nl80211_update_owe_info(struct sk_buff *skb, struct genl_info *info)
 	return rdev_update_owe_info(rdev, dev, &owe_info);
 }
 
+static int nl80211_probe_mesh_link(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct station_info sinfo = {};
+	const u8 *buf;
+	size_t len;
+	u8 *dest;
+	int err;
+
+	if (!rdev->ops->probe_mesh_link || !rdev->ops->get_station)
+		return -EOPNOTSUPP;
+
+	if (!info->attrs[NL80211_ATTR_MAC] ||
+	    !info->attrs[NL80211_ATTR_FRAME]) {
+		GENL_SET_ERR_MSG(info, "Frame or MAC missing");
+		return -EINVAL;
+	}
+
+	if (wdev->iftype != NL80211_IFTYPE_MESH_POINT)
+		return -EOPNOTSUPP;
+
+	dest = nla_data(info->attrs[NL80211_ATTR_MAC]);
+	buf = nla_data(info->attrs[NL80211_ATTR_FRAME]);
+	len = nla_len(info->attrs[NL80211_ATTR_FRAME]);
+
+	if (len < sizeof(struct ethhdr))
+		return -EINVAL;
+
+	if (!ether_addr_equal(buf, dest) || is_multicast_ether_addr(buf) ||
+	    !ether_addr_equal(buf + ETH_ALEN, dev->dev_addr))
+		return -EINVAL;
+
+	err = rdev_get_station(rdev, dev, dest, &sinfo);
+	if (err)
+		return err;
+
+	return rdev_probe_mesh_link(rdev, dev, dest, buf, len);
+}
+
 #define NL80211_FLAG_NEED_WIPHY		0x01
 #define NL80211_FLAG_NEED_NETDEV	0x02
 #define NL80211_FLAG_NEED_RTNL		0x04
@@ -14241,6 +14282,13 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_PROBE_MESH_LINK,
+		.doit = nl80211_probe_mesh_link,
+		.flags = GENL_UNS_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 static struct genl_family nl80211_fam __ro_after_init = {
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 18437a9deb54..e853a4fe6f97 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -1286,4 +1286,17 @@ static inline int rdev_update_owe_info(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int
+rdev_probe_mesh_link(struct cfg80211_registered_device *rdev,
+		     struct net_device *dev, const u8 *dest,
+		     const void *buf, size_t len)
+{
+	int ret;
+
+	trace_rdev_probe_mesh_link(&rdev->wiphy, dev, dest, buf, len);
+	ret = rdev->ops->probe_mesh_link(&rdev->wiphy, dev, buf, len);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+	return ret;
+}
+
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 488ef2ce8231..2abfff925aac 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -3421,6 +3421,24 @@ TRACE_EVENT(cfg80211_update_owe_info_event,
 		      WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer))
 );
 
+TRACE_EVENT(rdev_probe_mesh_link,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 const u8 *dest, const u8 *buf, size_t len),
+	TP_ARGS(wiphy, netdev, dest, buf, len),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		MAC_ENTRY(dest)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		MAC_ASSIGN(dest, dest);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(dest))
+);
+
 #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
-- 
cgit v1.2.3


From 8828f81ad4a2f4e89ebe6e7793c06ed767c31d53 Mon Sep 17 00:00:00 2001
From: Rajkumar Manoharan <rmanohar@codeaurora.org>
Date: Thu, 11 Apr 2019 13:47:26 -0700
Subject: mac80211: probe unexercised mesh links

The requirement for mesh link metric refreshing, is that from one
mesh point we be able to send some data frames to other mesh points
which are not currently selected as a primary traffic path, but which
are only 1 hop away. The absence of the primary path to the chosen node
makes it necessary to apply some form of marking on a chosen packet
stream so that the packets can be properly steered to the selected node
for testing, and not by the regular mesh path lookup.

Tested-by: Pradeep Kumar Chitrapu <pradeepc@codeaurora.org>
Signed-off-by: Rajkumar Manoharan <rmanohar@codeaurora.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  2 ++
 net/mac80211/cfg.c         |  1 +
 net/mac80211/ieee80211_i.h |  2 ++
 net/mac80211/mesh_hwmp.c   |  4 ++++
 net/mac80211/tx.c          | 36 ++++++++++++++++++++++++++++++++++++
 5 files changed, 45 insertions(+)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d66fbfe8d55d..76a443f32fc8 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -807,6 +807,7 @@ enum mac80211_tx_info_flags {
  * @IEEE80211_TX_CTRL_RATE_INJECT: This frame is injected with rate information
  * @IEEE80211_TX_CTRL_AMSDU: This frame is an A-MSDU frame
  * @IEEE80211_TX_CTRL_FAST_XMIT: This frame is going through the fast_xmit path
+ * @IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP: This frame skips mesh path lookup
  *
  * These flags are used in tx_info->control.flags.
  */
@@ -816,6 +817,7 @@ enum mac80211_tx_control_flags {
 	IEEE80211_TX_CTRL_RATE_INJECT		= BIT(2),
 	IEEE80211_TX_CTRL_AMSDU			= BIT(3),
 	IEEE80211_TX_CTRL_FAST_XMIT		= BIT(4),
+	IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP	= BIT(5),
 };
 
 /*
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index ba6e4080d63d..52e6a091b7e4 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -4035,4 +4035,5 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.get_ftm_responder_stats = ieee80211_get_ftm_responder_stats,
 	.start_pmsr = ieee80211_start_pmsr,
 	.abort_pmsr = ieee80211_abort_pmsr,
+	.probe_mesh_link = ieee80211_probe_mesh_link,
 };
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 9b0190eaff1e..073a8235ae1b 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1779,6 +1779,8 @@ void ieee80211_clear_fast_xmit(struct sta_info *sta);
 int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 			      const u8 *buf, size_t len,
 			      const u8 *dest, __be16 proto, bool unencrypted);
+int ieee80211_probe_mesh_link(struct wiphy *wiphy, struct net_device *dev,
+			      const u8 *buf, size_t len);
 
 /* HT */
 void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 2c5929c0fa62..bf8e13cd5fd1 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -1135,6 +1135,10 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata,
 	if (ieee80211_is_qos_nullfunc(hdr->frame_control))
 		return 0;
 
+	/* Allow injected packets to bypass mesh routing */
+	if (info->control.flags & IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP)
+		return 0;
+
 	if (!mesh_nexthop_lookup(sdata, skb))
 		return 0;
 
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 9e3678675f3b..8037384fc06e 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2607,6 +2607,13 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 			goto free;
 		}
 		band = chanctx_conf->def.chan->band;
+
+		/* For injected frames, fill RA right away as nexthop lookup
+		 * will be skipped.
+		 */
+		if ((ctrl_flags & IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP) &&
+		    is_zero_ether_addr(hdr.addr1))
+			memcpy(hdr.addr1, skb->data, ETH_ALEN);
 		break;
 #endif
 	case NL80211_IFTYPE_STATION:
@@ -5091,3 +5098,32 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 
 	return 0;
 }
+
+int ieee80211_probe_mesh_link(struct wiphy *wiphy, struct net_device *dev,
+			      const u8 *buf, size_t len)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+	struct sk_buff *skb;
+
+	skb = dev_alloc_skb(local->hw.extra_tx_headroom + len +
+			    30 + /* header size */
+			    18); /* 11s header size */
+	if (!skb)
+		return -ENOMEM;
+
+	skb_reserve(skb, local->hw.extra_tx_headroom);
+	skb_put_data(skb, buf, len);
+
+	skb->dev = dev;
+	skb->protocol = htons(ETH_P_802_3);
+	skb_reset_network_header(skb);
+	skb_reset_mac_header(skb);
+
+	local_bh_disable();
+	__ieee80211_subif_start_xmit(skb, skb->dev, 0,
+				     IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP);
+	local_bh_enable();
+
+	return 0;
+}
-- 
cgit v1.2.3


From 9df1c28bb75217b244257152ab7d788bb2a386d0 Mon Sep 17 00:00:00 2001
From: Matt Mullins <mmullins@fb.com>
Date: Fri, 26 Apr 2019 11:49:47 -0700
Subject: bpf: add writable context for raw tracepoints

This is an opt-in interface that allows a tracepoint to provide a safe
buffer that can be written from a BPF_PROG_TYPE_RAW_TRACEPOINT program.
The size of the buffer must be a compile-time constant, and is checked
before allowing a BPF program to attach to a tracepoint that uses this
feature.

The pointer to this buffer will be the first argument of tracepoints
that opt in; the pointer is valid and can be bpf_probe_read() by both
BPF_PROG_TYPE_RAW_TRACEPOINT and BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE
programs that attach to such a tracepoint, but the buffer to which it
points may only be written by the latter.

Signed-off-by: Matt Mullins <mmullins@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h             |  2 ++
 include/linux/bpf_types.h       |  1 +
 include/linux/tracepoint-defs.h |  1 +
 include/trace/bpf_probe.h       | 27 +++++++++++++++++++++++++--
 include/uapi/linux/bpf.h        |  1 +
 kernel/bpf/syscall.c            |  8 ++++++--
 kernel/bpf/verifier.c           | 31 +++++++++++++++++++++++++++++++
 kernel/trace/bpf_trace.c        | 24 ++++++++++++++++++++++++
 8 files changed, 91 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f15432d90728..cd6341eabd74 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -272,6 +272,7 @@ enum bpf_reg_type {
 	PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */
 	PTR_TO_TCP_SOCK,	 /* reg points to struct tcp_sock */
 	PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
+	PTR_TO_TP_BUFFER,	 /* reg points to a writable raw tp's buffer */
 };
 
 /* The information passed from prog-specific *_is_valid_access
@@ -361,6 +362,7 @@ struct bpf_prog_aux {
 	u32 used_map_cnt;
 	u32 max_ctx_offset;
 	u32 max_pkt_offset;
+	u32 max_tp_access;
 	u32 stack_depth;
 	u32 id;
 	u32 func_cnt; /* used by non-func prog as the number of func progs */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index d26991a16894..a10d37bce364 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -25,6 +25,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
 BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
 BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
 BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
+BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable)
 #endif
 #ifdef CONFIG_CGROUP_BPF
 BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h
index 49ba9cde7e4b..b29950a19205 100644
--- a/include/linux/tracepoint-defs.h
+++ b/include/linux/tracepoint-defs.h
@@ -45,6 +45,7 @@ struct bpf_raw_event_map {
 	struct tracepoint	*tp;
 	void			*bpf_func;
 	u32			num_args;
+	u32			writable_size;
 } __aligned(32);
 
 #endif
diff --git a/include/trace/bpf_probe.h b/include/trace/bpf_probe.h
index 505dae0bed80..d6e556c0a085 100644
--- a/include/trace/bpf_probe.h
+++ b/include/trace/bpf_probe.h
@@ -69,8 +69,7 @@ __bpf_trace_##call(void *__data, proto)					\
  * to make sure that if the tracepoint handling changes, the
  * bpf probe will fail to compile unless it too is updated.
  */
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, call, proto, args)			\
+#define __DEFINE_EVENT(template, call, proto, args, size)		\
 static inline void bpf_test_probe_##call(void)				\
 {									\
 	check_trace_callback_type_##call(__bpf_trace_##template);	\
@@ -81,12 +80,36 @@ __bpf_trace_tp_map_##call = {						\
 	.tp		= &__tracepoint_##call,				\
 	.bpf_func	= (void *)__bpf_trace_##template,		\
 	.num_args	= COUNT_ARGS(args),				\
+	.writable_size	= size,						\
 };
 
+#define FIRST(x, ...) x
+
+#undef DEFINE_EVENT_WRITABLE
+#define DEFINE_EVENT_WRITABLE(template, call, proto, args, size)	\
+static inline void bpf_test_buffer_##call(void)				\
+{									\
+	/* BUILD_BUG_ON() is ignored if the code is completely eliminated, but \
+	 * BUILD_BUG_ON_ZERO() uses a different mechanism that is not	\
+	 * dead-code-eliminated.					\
+	 */								\
+	FIRST(proto);							\
+	(void)BUILD_BUG_ON_ZERO(size != sizeof(*FIRST(args)));		\
+}									\
+__DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), size)
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args)			\
+	__DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args), 0)
 
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
 	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef DEFINE_EVENT_WRITABLE
+#undef __DEFINE_EVENT
+#undef FIRST
+
 #endif /* CONFIG_BPF_EVENTS */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index eaf2d3284248..f7fa7a34a62d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -168,6 +168,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SK_REUSEPORT,
 	BPF_PROG_TYPE_FLOW_DISSECTOR,
 	BPF_PROG_TYPE_CGROUP_SYSCTL,
+	BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
 };
 
 enum bpf_attach_type {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b0de49598341..ae141e745f92 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1789,12 +1789,16 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 	}
 	raw_tp->btp = btp;
 
-	prog = bpf_prog_get_type(attr->raw_tracepoint.prog_fd,
-				 BPF_PROG_TYPE_RAW_TRACEPOINT);
+	prog = bpf_prog_get(attr->raw_tracepoint.prog_fd);
 	if (IS_ERR(prog)) {
 		err = PTR_ERR(prog);
 		goto out_free_tp;
 	}
+	if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT &&
+	    prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
+		err = -EINVAL;
+		goto out_put_prog;
+	}
 
 	err = bpf_probe_register(raw_tp->btp, prog);
 	if (err)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 423f242a5efb..2ef442c62c0e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -405,6 +405,7 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
 	[PTR_TO_TCP_SOCK]	= "tcp_sock",
 	[PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
+	[PTR_TO_TP_BUFFER]	= "tp_buffer",
 };
 
 static char slot_type_char[] = {
@@ -1993,6 +1994,32 @@ static int check_ctx_reg(struct bpf_verifier_env *env,
 	return 0;
 }
 
+static int check_tp_buffer_access(struct bpf_verifier_env *env,
+				  const struct bpf_reg_state *reg,
+				  int regno, int off, int size)
+{
+	if (off < 0) {
+		verbose(env,
+			"R%d invalid tracepoint buffer access: off=%d, size=%d",
+			regno, off, size);
+		return -EACCES;
+	}
+	if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+		char tn_buf[48];
+
+		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+		verbose(env,
+			"R%d invalid variable buffer offset: off=%d, var_off=%s",
+			regno, off, tn_buf);
+		return -EACCES;
+	}
+	if (off + size > env->prog->aux->max_tp_access)
+		env->prog->aux->max_tp_access = off + size;
+
+	return 0;
+}
+
+
 /* truncate register to smaller size (in bytes)
  * must be called with size < BPF_REG_SIZE
  */
@@ -2137,6 +2164,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		err = check_sock_access(env, insn_idx, regno, off, size, t);
 		if (!err && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
+	} else if (reg->type == PTR_TO_TP_BUFFER) {
+		err = check_tp_buffer_access(env, reg, regno, off, size);
+		if (!err && t == BPF_READ && value_regno >= 0)
+			mark_reg_unknown(env, regs, value_regno);
 	} else {
 		verbose(env, "R%d invalid mem access '%s'\n", regno,
 			reg_type_str[reg->type]);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 91800be0c8eb..8607aba1d882 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -915,6 +915,27 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = {
 const struct bpf_prog_ops raw_tracepoint_prog_ops = {
 };
 
+static bool raw_tp_writable_prog_is_valid_access(int off, int size,
+						 enum bpf_access_type type,
+						 const struct bpf_prog *prog,
+						 struct bpf_insn_access_aux *info)
+{
+	if (off == 0) {
+		if (size != sizeof(u64) || type != BPF_READ)
+			return false;
+		info->reg_type = PTR_TO_TP_BUFFER;
+	}
+	return raw_tp_prog_is_valid_access(off, size, type, prog, info);
+}
+
+const struct bpf_verifier_ops raw_tracepoint_writable_verifier_ops = {
+	.get_func_proto  = raw_tp_prog_func_proto,
+	.is_valid_access = raw_tp_writable_prog_is_valid_access,
+};
+
+const struct bpf_prog_ops raw_tracepoint_writable_prog_ops = {
+};
+
 static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type,
 				    const struct bpf_prog *prog,
 				    struct bpf_insn_access_aux *info)
@@ -1204,6 +1225,9 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *
 	if (prog->aux->max_ctx_offset > btp->num_args * sizeof(u64))
 		return -EINVAL;
 
+	if (prog->aux->max_tp_access > btp->writable_size)
+		return -EINVAL;
+
 	return tracepoint_probe_register(tp, (void *)btp->bpf_func, prog);
 }
 
-- 
cgit v1.2.3


From ea106722c76f08002b69a6983ed84dc18958ba48 Mon Sep 17 00:00:00 2001
From: Matt Mullins <mmullins@fb.com>
Date: Fri, 26 Apr 2019 11:49:48 -0700
Subject: nbd: trace sending nbd requests

This adds a tracepoint that can both observe the nbd request being sent
to the server, as well as modify that request , e.g., setting a flag in
the request that will cause the server to collect detailed tracing data.

The struct request * being handled is included to permit correlation
with the block tracepoints.

Signed-off-by: Matt Mullins <mmullins@fb.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 MAINTAINERS                |  1 +
 drivers/block/nbd.c        |  5 +++++
 include/trace/events/nbd.h | 56 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 62 insertions(+)
 create mode 100644 include/trace/events/nbd.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 72dfb80e8721..025c6d27789e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10741,6 +10741,7 @@ L:	linux-block@vger.kernel.org
 L:	nbd@other.debian.org
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
+F:	include/trace/events/nbd.h
 F:	include/uapi/linux/nbd.h
 
 NETWORK DROP MONITOR
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 92b8aafb8bb4..24cc10d1f0b4 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -44,6 +44,9 @@
 #include <linux/nbd-netlink.h>
 #include <net/genetlink.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/nbd.h>
+
 static DEFINE_IDR(nbd_index_idr);
 static DEFINE_MUTEX(nbd_index_mutex);
 static int nbd_total_devices = 0;
@@ -526,6 +529,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	handle = nbd_cmd_handle(cmd);
 	memcpy(request.handle, &handle, sizeof(handle));
 
+	trace_nbd_send_request(&request, nbd->index, blk_mq_rq_from_pdu(cmd));
+
 	dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
 		req, nbdcmd_to_ascii(type),
 		(unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req));
diff --git a/include/trace/events/nbd.h b/include/trace/events/nbd.h
new file mode 100644
index 000000000000..5928255ed02e
--- /dev/null
+++ b/include/trace/events/nbd.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM nbd
+
+#if !defined(_TRACE_NBD_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NBD_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(nbd_send_request,
+
+	TP_PROTO(struct nbd_request *nbd_request, int index,
+		 struct request *rq),
+
+	TP_ARGS(nbd_request, index, rq),
+
+	TP_STRUCT__entry(
+		__field(struct nbd_request *, nbd_request)
+		__field(u64, dev_index)
+		__field(struct request *, request)
+	),
+
+	TP_fast_assign(
+		__entry->nbd_request = 0;
+		__entry->dev_index = index;
+		__entry->request = rq;
+	),
+
+	TP_printk("nbd%lld: request %p", __entry->dev_index, __entry->request)
+);
+
+#ifdef DEFINE_EVENT_WRITABLE
+#undef NBD_DEFINE_EVENT
+#define NBD_DEFINE_EVENT(template, call, proto, args, size)		\
+	DEFINE_EVENT_WRITABLE(template, call, PARAMS(proto),		\
+			      PARAMS(args), size)
+#else
+#undef NBD_DEFINE_EVENT
+#define NBD_DEFINE_EVENT(template, call, proto, args, size)		\
+	DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args))
+#endif
+
+NBD_DEFINE_EVENT(nbd_send_request, nbd_send_request,
+
+	TP_PROTO(struct nbd_request *nbd_request, int index,
+		 struct request *rq),
+
+	TP_ARGS(nbd_request, index, rq),
+
+	sizeof(struct nbd_request)
+);
+
+#endif
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
-- 
cgit v1.2.3


From 2abd2de712cd891321a06b0890a85aef1e506cb5 Mon Sep 17 00:00:00 2001
From: Andrew Hall <hall@fb.com>
Date: Fri, 26 Apr 2019 11:49:49 -0700
Subject: nbd: add tracepoints for send/receive timing

This adds four tracepoints to nbd, enabling separate tracing of payload
and header sending/receipt.

In the send path for headers that have already been sent, we also
explicitly initialize the handle so it can be referenced by the later
tracepoint.

Signed-off-by: Andrew Hall <hall@fb.com>
Signed-off-by: Matt Mullins <mmullins@fb.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 drivers/block/nbd.c        |  8 ++++++++
 include/trace/events/nbd.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)

(limited to 'include')

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 24cc10d1f0b4..3e6c3d5dadc8 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -513,6 +513,10 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	if (sent) {
 		if (sent >= sizeof(request)) {
 			skip = sent - sizeof(request);
+
+			/* initialize handle for tracing purposes */
+			handle = nbd_cmd_handle(cmd);
+
 			goto send_pages;
 		}
 		iov_iter_advance(&from, sent);
@@ -536,6 +540,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		(unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req));
 	result = sock_xmit(nbd, index, 1, &from,
 			(type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent);
+	trace_nbd_header_sent(req, handle);
 	if (result <= 0) {
 		if (was_interrupted(result)) {
 			/* If we havne't sent anything we can just return BUSY,
@@ -608,6 +613,7 @@ send_pages:
 		bio = next;
 	}
 out:
+	trace_nbd_payload_sent(req, handle);
 	nsock->pending = NULL;
 	nsock->sent = 0;
 	return 0;
@@ -655,6 +661,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 			tag, req);
 		return ERR_PTR(-ENOENT);
 	}
+	trace_nbd_header_received(req, handle);
 	cmd = blk_mq_rq_to_pdu(req);
 
 	mutex_lock(&cmd->lock);
@@ -708,6 +715,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		}
 	}
 out:
+	trace_nbd_payload_received(req, handle);
 	mutex_unlock(&cmd->lock);
 	return ret ? ERR_PTR(ret) : cmd;
 }
diff --git a/include/trace/events/nbd.h b/include/trace/events/nbd.h
index 5928255ed02e..9849956f34d8 100644
--- a/include/trace/events/nbd.h
+++ b/include/trace/events/nbd.h
@@ -7,6 +7,57 @@
 
 #include <linux/tracepoint.h>
 
+DECLARE_EVENT_CLASS(nbd_transport_event,
+
+	TP_PROTO(struct request *req, u64 handle),
+
+	TP_ARGS(req, handle),
+
+	TP_STRUCT__entry(
+		__field(struct request *, req)
+		__field(u64, handle)
+	),
+
+	TP_fast_assign(
+		__entry->req = req;
+		__entry->handle = handle;
+	),
+
+	TP_printk(
+		"nbd transport event: request %p, handle 0x%016llx",
+		__entry->req,
+		__entry->handle
+	)
+);
+
+DEFINE_EVENT(nbd_transport_event, nbd_header_sent,
+
+	TP_PROTO(struct request *req, u64 handle),
+
+	TP_ARGS(req, handle)
+);
+
+DEFINE_EVENT(nbd_transport_event, nbd_payload_sent,
+
+	TP_PROTO(struct request *req, u64 handle),
+
+	TP_ARGS(req, handle)
+);
+
+DEFINE_EVENT(nbd_transport_event, nbd_header_received,
+
+	TP_PROTO(struct request *req, u64 handle),
+
+	TP_ARGS(req, handle)
+);
+
+DEFINE_EVENT(nbd_transport_event, nbd_payload_received,
+
+	TP_PROTO(struct request *req, u64 handle),
+
+	TP_ARGS(req, handle)
+);
+
 DECLARE_EVENT_CLASS(nbd_send_request,
 
 	TP_PROTO(struct nbd_request *nbd_request, int index,
-- 
cgit v1.2.3


From e950e843367d7990b9d7ea964e3c33876d477c4b Mon Sep 17 00:00:00 2001
From: Matt Mullins <mmullins@fb.com>
Date: Fri, 26 Apr 2019 11:49:51 -0700
Subject: selftests: bpf: test writable buffers in raw tps

This tests that:
  * a BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE cannot be attached if it
    uses either:
    * a variable offset to the tracepoint buffer, or
    * an offset beyond the size of the tracepoint buffer
  * a tracer can modify the buffer provided when attached to a writable
    tracepoint in bpf_prog_test_run

Signed-off-by: Matt Mullins <mmullins@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/trace/events/bpf_test_run.h                | 50 ++++++++++++++
 net/bpf/test_run.c                                 |  4 ++
 .../raw_tp_writable_reject_nbd_invalid.c           | 42 ++++++++++++
 .../bpf/prog_tests/raw_tp_writable_test_run.c      | 80 ++++++++++++++++++++++
 .../selftests/bpf/verifier/raw_tp_writable.c       | 34 +++++++++
 5 files changed, 210 insertions(+)
 create mode 100644 include/trace/events/bpf_test_run.h
 create mode 100644 tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c
 create mode 100644 tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
 create mode 100644 tools/testing/selftests/bpf/verifier/raw_tp_writable.c

(limited to 'include')

diff --git a/include/trace/events/bpf_test_run.h b/include/trace/events/bpf_test_run.h
new file mode 100644
index 000000000000..265447e3f71a
--- /dev/null
+++ b/include/trace/events/bpf_test_run.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM bpf_test_run
+
+#if !defined(_TRACE_BPF_TEST_RUN_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BPF_TEST_RUN_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(bpf_test_finish,
+
+	TP_PROTO(int *err),
+
+	TP_ARGS(err),
+
+	TP_STRUCT__entry(
+		__field(int, err)
+	),
+
+	TP_fast_assign(
+		__entry->err = *err;
+	),
+
+	TP_printk("bpf_test_finish with err=%d", __entry->err)
+);
+
+#ifdef DEFINE_EVENT_WRITABLE
+#undef BPF_TEST_RUN_DEFINE_EVENT
+#define BPF_TEST_RUN_DEFINE_EVENT(template, call, proto, args, size)	\
+	DEFINE_EVENT_WRITABLE(template, call, PARAMS(proto),		\
+			      PARAMS(args), size)
+#else
+#undef BPF_TEST_RUN_DEFINE_EVENT
+#define BPF_TEST_RUN_DEFINE_EVENT(template, call, proto, args, size)	\
+	DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args))
+#endif
+
+BPF_TEST_RUN_DEFINE_EVENT(bpf_test_finish, bpf_test_finish,
+
+	TP_PROTO(int *err),
+
+	TP_ARGS(err),
+
+	sizeof(int)
+);
+
+#endif
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 8606e5aef0b6..6c4694ae4241 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -13,6 +13,9 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/bpf_test_run.h>
+
 static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 			u32 *retval, u32 *time)
 {
@@ -100,6 +103,7 @@ static int bpf_test_finish(const union bpf_attr *kattr,
 	if (err != -ENOSPC)
 		err = 0;
 out:
+	trace_bpf_test_finish(&err);
 	return err;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c
new file mode 100644
index 000000000000..9807336a3016
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include <linux/nbd.h>
+
+void test_raw_tp_writable_reject_nbd_invalid(void)
+{
+	__u32 duration = 0;
+	char error[4096];
+	int bpf_fd = -1, tp_fd = -1;
+
+	const struct bpf_insn program[] = {
+		/* r6 is our tp buffer */
+		BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+		/* one byte beyond the end of the nbd_request struct */
+		BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6,
+			    sizeof(struct nbd_request)),
+		BPF_EXIT_INSN(),
+	};
+
+	struct bpf_load_program_attr load_attr = {
+		.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+		.license = "GPL v2",
+		.insns = program,
+		.insns_cnt = sizeof(program) / sizeof(struct bpf_insn),
+		.log_level = 2,
+	};
+
+	bpf_fd = bpf_load_program_xattr(&load_attr, error, sizeof(error));
+	if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable load",
+		  "failed: %d errno %d\n", bpf_fd, errno))
+		return;
+
+	tp_fd = bpf_raw_tracepoint_open("nbd_send_request", bpf_fd);
+	if (CHECK(tp_fd >= 0, "bpf_raw_tracepoint_writable open",
+		  "erroneously succeeded\n"))
+		goto out_bpffd;
+
+	close(tp_fd);
+out_bpffd:
+	close(bpf_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
new file mode 100644
index 000000000000..5c45424cac5f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include <linux/nbd.h>
+
+void test_raw_tp_writable_test_run(void)
+{
+	__u32 duration = 0;
+	char error[4096];
+
+	const struct bpf_insn trace_program[] = {
+		BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 42),
+		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+
+	struct bpf_load_program_attr load_attr = {
+		.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+		.license = "GPL v2",
+		.insns = trace_program,
+		.insns_cnt = sizeof(trace_program) / sizeof(struct bpf_insn),
+		.log_level = 2,
+	};
+
+	int bpf_fd = bpf_load_program_xattr(&load_attr, error, sizeof(error));
+	if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable loaded",
+		  "failed: %d errno %d\n", bpf_fd, errno))
+		return;
+
+	const struct bpf_insn skb_program[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+
+	struct bpf_load_program_attr skb_load_attr = {
+		.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+		.license = "GPL v2",
+		.insns = skb_program,
+		.insns_cnt = sizeof(skb_program) / sizeof(struct bpf_insn),
+	};
+
+	int filter_fd =
+		bpf_load_program_xattr(&skb_load_attr, error, sizeof(error));
+	if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n",
+		  filter_fd, errno))
+		goto out_bpffd;
+
+	int tp_fd = bpf_raw_tracepoint_open("bpf_test_finish", bpf_fd);
+	if (CHECK(tp_fd < 0, "bpf_raw_tracepoint_writable opened",
+		  "failed: %d errno %d\n", tp_fd, errno))
+		goto out_filterfd;
+
+	char test_skb[128] = {
+		0,
+	};
+
+	__u32 prog_ret;
+	int err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0,
+				    0, &prog_ret, 0);
+	CHECK(err != 42, "test_run",
+	      "tracepoint did not modify return value\n");
+	CHECK(prog_ret != 0, "test_run_ret",
+	      "socket_filter did not return 0\n");
+
+	close(tp_fd);
+
+	err = bpf_prog_test_run(filter_fd, 1, test_skb, sizeof(test_skb), 0, 0,
+				&prog_ret, 0);
+	CHECK(err != 0, "test_run_notrace",
+	      "test_run failed with %d errno %d\n", err, errno);
+	CHECK(prog_ret != 0, "test_run_ret_notrace",
+	      "socket_filter did not return 0\n");
+
+out_filterfd:
+	close(filter_fd);
+out_bpffd:
+	close(bpf_fd);
+}
diff --git a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c
new file mode 100644
index 000000000000..95b5d70a1dc1
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c
@@ -0,0 +1,34 @@
+{
+	"raw_tracepoint_writable: reject variable offset",
+	.insns = {
+		/* r6 is our tp buffer */
+		BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
+
+		BPF_LD_MAP_FD(BPF_REG_1, 0),
+		/* move the key (== 0) to r10-8 */
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+		BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+		/* lookup in the map */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_map_lookup_elem),
+
+		/* exit clean if null */
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+		BPF_EXIT_INSN(),
+
+		/* shift the buffer pointer to a variable location */
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
+		BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_0),
+		/* clobber whatever's there */
+		BPF_MOV64_IMM(BPF_REG_7, 4242),
+		BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, 0),
+
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_8b = { 1, },
+	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
+	.errstr = "R6 invalid variable buffer offset: off=0, var_off=(0x0; 0xffffffff)",
+},
-- 
cgit v1.2.3


From 6ac99e8f23d4b10258406ca0dd7bffca5f31da9d Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 26 Apr 2019 16:39:39 -0700
Subject: bpf: Introduce bpf sk local storage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After allowing a bpf prog to
- directly read the skb->sk ptr
- get the fullsock bpf_sock by "bpf_sk_fullsock()"
- get the bpf_tcp_sock by "bpf_tcp_sock()"
- get the listener sock by "bpf_get_listener_sock()"
- avoid duplicating the fields of "(bpf_)sock" and "(bpf_)tcp_sock"
  into different bpf running context.

this patch is another effort to make bpf's network programming
more intuitive to do (together with memory and performance benefit).

When bpf prog needs to store data for a sk, the current practice is to
define a map with the usual 4-tuples (src/dst ip/port) as the key.
If multiple bpf progs require to store different sk data, multiple maps
have to be defined.  Hence, wasting memory to store the duplicated
keys (i.e. 4 tuples here) in each of the bpf map.
[ The smallest key could be the sk pointer itself which requires
  some enhancement in the verifier and it is a separate topic. ]

Also, the bpf prog needs to clean up the elem when sk is freed.
Otherwise, the bpf map will become full and un-usable quickly.
The sk-free tracking currently could be done during sk state
transition (e.g. BPF_SOCK_OPS_STATE_CB).

The size of the map needs to be predefined which then usually ended-up
with an over-provisioned map in production.  Even the map was re-sizable,
while the sk naturally come and go away already, this potential re-size
operation is arguably redundant if the data can be directly connected
to the sk itself instead of proxy-ing through a bpf map.

This patch introduces sk->sk_bpf_storage to provide local storage space
at sk for bpf prog to use.  The space will be allocated when the first bpf
prog has created data for this particular sk.

The design optimizes the bpf prog's lookup (and then optionally followed by
an inline update).  bpf_spin_lock should be used if the inline update needs
to be protected.

BPF_MAP_TYPE_SK_STORAGE:
-----------------------
To define a bpf "sk-local-storage", a BPF_MAP_TYPE_SK_STORAGE map (new in
this patch) needs to be created.  Multiple BPF_MAP_TYPE_SK_STORAGE maps can
be created to fit different bpf progs' needs.  The map enforces
BTF to allow printing the sk-local-storage during a system-wise
sk dump (e.g. "ss -ta") in the future.

The purpose of a BPF_MAP_TYPE_SK_STORAGE map is not for lookup/update/delete
a "sk-local-storage" data from a particular sk.
Think of the map as a meta-data (or "type") of a "sk-local-storage".  This
particular "type" of "sk-local-storage" data can then be stored in any sk.

The main purposes of this map are mostly:
1. Define the size of a "sk-local-storage" type.
2. Provide a similar syscall userspace API as the map (e.g. lookup/update,
   map-id, map-btf...etc.)
3. Keep track of all sk's storages of this "type" and clean them up
   when the map is freed.

sk->sk_bpf_storage:
------------------
The main lookup/update/delete is done on sk->sk_bpf_storage (which
is a "struct bpf_sk_storage").  When doing a lookup,
the "map" pointer is now used as the "key" to search on the
sk_storage->list.  The "map" pointer is actually serving
as the "type" of the "sk-local-storage" that is being
requested.

To allow very fast lookup, it should be as fast as looking up an
array at a stable-offset.  At the same time, it is not ideal to
set a hard limit on the number of sk-local-storage "type" that the
system can have.  Hence, this patch takes a cache approach.
The last search result from sk_storage->list is cached in
sk_storage->cache[] which is a stable sized array.  Each
"sk-local-storage" type has a stable offset to the cache[] array.
In the future, a map's flag could be introduced to do cache
opt-out/enforcement if it became necessary.

The cache size is 16 (i.e. 16 types of "sk-local-storage").
Programs can share map.  On the program side, having a few bpf_progs
running in the networking hotpath is already a lot.  The bpf_prog
should have already consolidated the existing sock-key-ed map usage
to minimize the map lookup penalty.  16 has enough runway to grow.

All sk-local-storage data will be removed from sk->sk_bpf_storage
during sk destruction.

bpf_sk_storage_get() and bpf_sk_storage_delete():
------------------------------------------------
Instead of using bpf_map_(lookup|update|delete)_elem(),
the bpf prog needs to use the new helper bpf_sk_storage_get() and
bpf_sk_storage_delete().  The verifier can then enforce the
ARG_PTR_TO_SOCKET argument.  The bpf_sk_storage_get() also allows to
"create" new elem if one does not exist in the sk.  It is done by
the new BPF_SK_STORAGE_GET_F_CREATE flag.  An optional value can also be
provided as the initial value during BPF_SK_STORAGE_GET_F_CREATE.
The BPF_MAP_TYPE_SK_STORAGE also supports bpf_spin_lock.  Together,
it has eliminated the potential use cases for an equivalent
bpf_map_update_elem() API (for bpf_prog) in this patch.

Misc notes:
----------
1. map_get_next_key is not supported.  From the userspace syscall
   perspective,  the map has the socket fd as the key while the map
   can be shared by pinned-file or map-id.

   Since btf is enforced, the existing "ss" could be enhanced to pretty
   print the local-storage.

   Supporting a kernel defined btf with 4 tuples as the return key could
   be explored later also.

2. The sk->sk_lock cannot be acquired.  Atomic operations is used instead.
   e.g. cmpxchg is done on the sk->sk_bpf_storage ptr.
   Please refer to the source code comments for the details in
   synchronization cases and considerations.

3. The mem is charged to the sk->sk_omem_alloc as the sk filter does.

Benchmark:
---------
Here is the benchmark data collected by turning on
the "kernel.bpf_stats_enabled" sysctl.
Two bpf progs are tested:

One bpf prog with the usual bpf hashmap (max_entries = 8192) with the
sk ptr as the key. (verifier is modified to support sk ptr as the key
That should have shortened the key lookup time.)

Another bpf prog is with the new BPF_MAP_TYPE_SK_STORAGE.

Both are storing a "u32 cnt", do a lookup on "egress_skb/cgroup" for
each egress skb and then bump the cnt.  netperf is used to drive
data with 4096 connected UDP sockets.

BPF_MAP_TYPE_HASH with a modifier verifier (152ns per bpf run)
27: cgroup_skb  name egress_sk_map  tag 74f56e832918070b run_time_ns 58280107540 run_cnt 381347633
    loaded_at 2019-04-15T13:46:39-0700  uid 0
    xlated 344B  jited 258B  memlock 4096B  map_ids 16
    btf_id 5

BPF_MAP_TYPE_SK_STORAGE in this patch (66ns per bpf run)
30: cgroup_skb  name egress_sk_stora  tag d4aa70984cc7bbf6 run_time_ns 25617093319 run_cnt 390989739
    loaded_at 2019-04-15T13:47:54-0700  uid 0
    xlated 168B  jited 156B  memlock 4096B  map_ids 17
    btf_id 6

Here is a high-level picture on how are the objects organized:

       sk
    ┌──────┐
    │      │
    │      │
    │      │
    │*sk_bpf_storage─────▶ bpf_sk_storage
    └──────┘                 ┌───────┐
                 ┌───────────┤ list  │
                 │           │       │
                 │           │       │
                 │           │       │
                 │           └───────┘
                 │
                 │     elem
                 │  ┌────────┐
                 ├─▶│ snode  │
                 │  ├────────┤
                 │  │  data  │          bpf_map
                 │  ├────────┤        ┌─────────┐
                 │  │map_node│◀─┬─────┤  list   │
                 │  └────────┘  │     │         │
                 │              │     │         │
                 │     elem     │     │         │
                 │  ┌────────┐  │     └─────────┘
                 └─▶│ snode  │  │
                    ├────────┤  │
   bpf_map          │  data  │  │
 ┌─────────┐        ├────────┤  │
 │  list   ├───────▶│map_node│  │
 │         │        └────────┘  │
 │         │                    │
 │         │           elem     │
 └─────────┘        ┌────────┐  │
                 ┌─▶│ snode  │  │
                 │  ├────────┤  │
                 │  │  data  │  │
                 │  ├────────┤  │
                 │  │map_node│◀─┘
                 │  └────────┘
                 │
                 │
                 │          ┌───────┐
     sk          └──────────│ list  │
  ┌──────┐                  │       │
  │      │                  │       │
  │      │                  │       │
  │      │                  └───────┘
  │*sk_bpf_storage───────▶bpf_sk_storage
  └──────┘

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h          |   2 +
 include/linux/bpf_types.h    |   1 +
 include/net/bpf_sk_storage.h |  13 +
 include/net/sock.h           |   5 +
 include/uapi/linux/bpf.h     |  44 ++-
 kernel/bpf/syscall.c         |   3 +-
 kernel/bpf/verifier.c        |  27 +-
 net/bpf/test_run.c           |   2 +
 net/core/Makefile            |   1 +
 net/core/bpf_sk_storage.c    | 804 +++++++++++++++++++++++++++++++++++++++++++
 net/core/filter.c            |  12 +
 net/core/sock.c              |   5 +
 12 files changed, 914 insertions(+), 5 deletions(-)
 create mode 100644 include/net/bpf_sk_storage.h
 create mode 100644 net/core/bpf_sk_storage.c

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cd6341eabd74..9a21848fdb07 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -184,6 +184,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_MAP_KEY,	/* pointer to stack used as map key */
 	ARG_PTR_TO_MAP_VALUE,	/* pointer to stack used as map value */
 	ARG_PTR_TO_UNINIT_MAP_VALUE,	/* pointer to valid memory used to store a map value */
+	ARG_PTR_TO_MAP_VALUE_OR_NULL,	/* pointer to stack used as map value or NULL */
 
 	/* the following constraints used to prototype bpf_memcmp() and other
 	 * functions that access data on eBPF program stack
@@ -204,6 +205,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
 	ARG_PTR_TO_INT,		/* pointer to int */
 	ARG_PTR_TO_LONG,	/* pointer to long */
+	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock (fullsock) */
 };
 
 /* type of values returned from helper functions */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index a10d37bce364..5a9975678d6f 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -61,6 +61,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
 #ifdef CONFIG_NET
 BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
 #if defined(CONFIG_BPF_STREAM_PARSER)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKHASH, sock_hash_ops)
diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
new file mode 100644
index 000000000000..b9dcb02e756b
--- /dev/null
+++ b/include/net/bpf_sk_storage.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Facebook */
+#ifndef _BPF_SK_STORAGE_H
+#define _BPF_SK_STORAGE_H
+
+struct sock;
+
+void bpf_sk_storage_free(struct sock *sk);
+
+extern const struct bpf_func_proto bpf_sk_storage_get_proto;
+extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
+
+#endif /* _BPF_SK_STORAGE_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 784cd19d5ff7..4d208c0f9c14 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -236,6 +236,8 @@ struct sock_common {
 	/* public: */
 };
 
+struct bpf_sk_storage;
+
 /**
   *	struct sock - network layer representation of sockets
   *	@__sk_common: shared layout with inet_timewait_sock
@@ -510,6 +512,9 @@ struct sock {
 #endif
 	void                    (*sk_destruct)(struct sock *sk);
 	struct sock_reuseport __rcu	*sk_reuseport_cb;
+#ifdef CONFIG_BPF_SYSCALL
+	struct bpf_sk_storage __rcu	*sk_bpf_storage;
+#endif
 	struct rcu_head		sk_rcu;
 };
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f7fa7a34a62d..72336bac7573 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -133,6 +133,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
 	BPF_MAP_TYPE_QUEUE,
 	BPF_MAP_TYPE_STACK,
+	BPF_MAP_TYPE_SK_STORAGE,
 };
 
 /* Note that tracing related programs such as
@@ -2630,6 +2631,42 @@ union bpf_attr {
  *		was provided.
  *
  *		**-ERANGE** if resulting value was out of range.
+ *
+ * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags)
+ *	Description
+ *		Get a bpf-local-storage from a sk.
+ *
+ *		Logically, it could be thought of getting the value from
+ *		a *map* with *sk* as the **key**.  From this
+ *		perspective,  the usage is not much different from
+ *		**bpf_map_lookup_elem(map, &sk)** except this
+ *		helper enforces the key must be a **bpf_fullsock()**
+ *		and the map must be a BPF_MAP_TYPE_SK_STORAGE also.
+ *
+ *		Underneath, the value is stored locally at *sk* instead of
+ *		the map.  The *map* is used as the bpf-local-storage **type**.
+ *		The bpf-local-storage **type** (i.e. the *map*) is searched
+ *		against all bpf-local-storages residing at sk.
+ *
+ *		An optional *flags* (BPF_SK_STORAGE_GET_F_CREATE) can be
+ *		used such that a new bpf-local-storage will be
+ *		created if one does not exist.  *value* can be used
+ *		together with BPF_SK_STORAGE_GET_F_CREATE to specify
+ *		the initial value of a bpf-local-storage.  If *value* is
+ *		NULL, the new bpf-local-storage will be zero initialized.
+ *	Return
+ *		A bpf-local-storage pointer is returned on success.
+ *
+ *		**NULL** if not found or there was an error in adding
+ *		a new bpf-local-storage.
+ *
+ * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk)
+ *	Description
+ *		Delete a bpf-local-storage from a sk.
+ *	Return
+ *		0 on success.
+ *
+ *		**-ENOENT** if the bpf-local-storage cannot be found.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2738,7 +2775,9 @@ union bpf_attr {
 	FN(sysctl_get_new_value),	\
 	FN(sysctl_set_new_value),	\
 	FN(strtol),			\
-	FN(strtoul),
+	FN(strtoul),			\
+	FN(sk_storage_get),		\
+	FN(sk_storage_delete),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2814,6 +2853,9 @@ enum bpf_func_id {
 /* BPF_FUNC_sysctl_get_name flags. */
 #define BPF_F_SYSCTL_BASE_NAME		(1ULL << 0)
 
+/* BPF_FUNC_sk_storage_get flags */
+#define BPF_SK_STORAGE_GET_F_CREATE	(1ULL << 0)
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ae141e745f92..ad3ccf82f31d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -526,7 +526,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 			return -EACCES;
 		if (map->map_type != BPF_MAP_TYPE_HASH &&
 		    map->map_type != BPF_MAP_TYPE_ARRAY &&
-		    map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+		    map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
+		    map->map_type != BPF_MAP_TYPE_SK_STORAGE)
 			return -ENOTSUPP;
 		if (map->spin_lock_off + sizeof(struct bpf_spin_lock) >
 		    map->value_size) {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2ef442c62c0e..271717246af3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2543,10 +2543,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 
 	if (arg_type == ARG_PTR_TO_MAP_KEY ||
 	    arg_type == ARG_PTR_TO_MAP_VALUE ||
-	    arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
+	    arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
+	    arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
 		expected_type = PTR_TO_STACK;
-		if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
-		    type != expected_type)
+		if (register_is_null(reg) &&
+		    arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL)
+			/* final test in check_stack_boundary() */;
+		else if (!type_is_pkt_pointer(type) &&
+			 type != PTR_TO_MAP_VALUE &&
+			 type != expected_type)
 			goto err_type;
 	} else if (arg_type == ARG_CONST_SIZE ||
 		   arg_type == ARG_CONST_SIZE_OR_ZERO) {
@@ -2578,6 +2583,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 			}
 			meta->ref_obj_id = reg->ref_obj_id;
 		}
+	} else if (arg_type == ARG_PTR_TO_SOCKET) {
+		expected_type = PTR_TO_SOCKET;
+		if (type != expected_type)
+			goto err_type;
 	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
 		if (meta->func_id == BPF_FUNC_spin_lock) {
 			if (process_spin_lock(env, regno, true))
@@ -2635,6 +2644,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 					      meta->map_ptr->key_size, false,
 					      NULL);
 	} else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
+		   (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL &&
+		    !register_is_null(reg)) ||
 		   arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
 		/* bpf_map_xxx(..., map_ptr, ..., value) call:
 		 * check [value, value + map->value_size) validity
@@ -2784,6 +2795,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_map_push_elem)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_SK_STORAGE:
+		if (func_id != BPF_FUNC_sk_storage_get &&
+		    func_id != BPF_FUNC_sk_storage_delete)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -2847,6 +2863,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    map->map_type != BPF_MAP_TYPE_STACK)
 			goto error;
 		break;
+	case BPF_FUNC_sk_storage_get:
+	case BPF_FUNC_sk_storage_delete:
+		if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
+			goto error;
+		break;
 	default:
 		break;
 	}
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 6c4694ae4241..33e0dc168c16 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -10,6 +10,7 @@
 #include <linux/etherdevice.h>
 #include <linux/filter.h>
 #include <linux/sched/signal.h>
+#include <net/bpf_sk_storage.h>
 #include <net/sock.h>
 #include <net/tcp.h>
 
@@ -335,6 +336,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 				     sizeof(struct __sk_buff));
 out:
 	kfree_skb(skb);
+	bpf_sk_storage_free(sk);
 	kfree(sk);
 	kfree(ctx);
 	return ret;
diff --git a/net/core/Makefile b/net/core/Makefile
index f97d6254e564..a104dc8faafc 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -34,3 +34,4 @@ obj-$(CONFIG_HWBM) += hwbm.o
 obj-$(CONFIG_NET_DEVLINK) += devlink.o
 obj-$(CONFIG_GRO_CELLS) += gro_cells.o
 obj-$(CONFIG_FAILOVER) += failover.o
+obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
new file mode 100644
index 000000000000..a8e9ac71b22d
--- /dev/null
+++ b/net/core/bpf_sk_storage.c
@@ -0,0 +1,804 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook  */
+#include <linux/rculist.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bpf.h>
+#include <net/bpf_sk_storage.h>
+#include <net/sock.h>
+#include <uapi/linux/btf.h>
+
+static atomic_t cache_idx;
+
+struct bucket {
+	struct hlist_head list;
+	raw_spinlock_t lock;
+};
+
+/* Thp map is not the primary owner of a bpf_sk_storage_elem.
+ * Instead, the sk->sk_bpf_storage is.
+ *
+ * The map (bpf_sk_storage_map) is for two purposes
+ * 1. Define the size of the "sk local storage".  It is
+ *    the map's value_size.
+ *
+ * 2. Maintain a list to keep track of all elems such
+ *    that they can be cleaned up during the map destruction.
+ *
+ * When a bpf local storage is being looked up for a
+ * particular sk,  the "bpf_map" pointer is actually used
+ * as the "key" to search in the list of elem in
+ * sk->sk_bpf_storage.
+ *
+ * Hence, consider sk->sk_bpf_storage is the mini-map
+ * with the "bpf_map" pointer as the searching key.
+ */
+struct bpf_sk_storage_map {
+	struct bpf_map map;
+	/* Lookup elem does not require accessing the map.
+	 *
+	 * Updating/Deleting requires a bucket lock to
+	 * link/unlink the elem from the map.  Having
+	 * multiple buckets to improve contention.
+	 */
+	struct bucket *buckets;
+	u32 bucket_log;
+	u16 elem_size;
+	u16 cache_idx;
+};
+
+struct bpf_sk_storage_data {
+	/* smap is used as the searching key when looking up
+	 * from sk->sk_bpf_storage.
+	 *
+	 * Put it in the same cacheline as the data to minimize
+	 * the number of cachelines access during the cache hit case.
+	 */
+	struct bpf_sk_storage_map __rcu *smap;
+	u8 data[0] __aligned(8);
+};
+
+/* Linked to bpf_sk_storage and bpf_sk_storage_map */
+struct bpf_sk_storage_elem {
+	struct hlist_node map_node;	/* Linked to bpf_sk_storage_map */
+	struct hlist_node snode;	/* Linked to bpf_sk_storage */
+	struct bpf_sk_storage __rcu *sk_storage;
+	struct rcu_head rcu;
+	/* 8 bytes hole */
+	/* The data is stored in aother cacheline to minimize
+	 * the number of cachelines access during a cache hit.
+	 */
+	struct bpf_sk_storage_data sdata ____cacheline_aligned;
+};
+
+#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata)
+#define SDATA(_SELEM) (&(_SELEM)->sdata)
+#define BPF_SK_STORAGE_CACHE_SIZE	16
+
+struct bpf_sk_storage {
+	struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE];
+	struct hlist_head list;	/* List of bpf_sk_storage_elem */
+	struct sock *sk;	/* The sk that owns the the above "list" of
+				 * bpf_sk_storage_elem.
+				 */
+	struct rcu_head rcu;
+	raw_spinlock_t lock;	/* Protect adding/removing from the "list" */
+};
+
+static struct bucket *select_bucket(struct bpf_sk_storage_map *smap,
+				    struct bpf_sk_storage_elem *selem)
+{
+	return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
+}
+
+static int omem_charge(struct sock *sk, unsigned int size)
+{
+	/* same check as in sock_kmalloc() */
+	if (size <= sysctl_optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+		atomic_add(size, &sk->sk_omem_alloc);
+		return 0;
+	}
+
+	return -ENOMEM;
+}
+
+static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem)
+{
+	return !hlist_unhashed(&selem->snode);
+}
+
+static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem)
+{
+	return !hlist_unhashed(&selem->map_node);
+}
+
+static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap,
+					       struct sock *sk, void *value,
+					       bool charge_omem)
+{
+	struct bpf_sk_storage_elem *selem;
+
+	if (charge_omem && omem_charge(sk, smap->elem_size))
+		return NULL;
+
+	selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+	if (selem) {
+		if (value)
+			memcpy(SDATA(selem)->data, value, smap->map.value_size);
+		return selem;
+	}
+
+	if (charge_omem)
+		atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
+
+	return NULL;
+}
+
+/* sk_storage->lock must be held and selem->sk_storage == sk_storage.
+ * The caller must ensure selem->smap is still valid to be
+ * dereferenced for its smap->elem_size and smap->cache_idx.
+ */
+static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage,
+			      struct bpf_sk_storage_elem *selem,
+			      bool uncharge_omem)
+{
+	struct bpf_sk_storage_map *smap;
+	bool free_sk_storage;
+	struct sock *sk;
+
+	smap = rcu_dereference(SDATA(selem)->smap);
+	sk = sk_storage->sk;
+
+	/* All uncharging on sk->sk_omem_alloc must be done first.
+	 * sk may be freed once the last selem is unlinked from sk_storage.
+	 */
+	if (uncharge_omem)
+		atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
+
+	free_sk_storage = hlist_is_singular_node(&selem->snode,
+						 &sk_storage->list);
+	if (free_sk_storage) {
+		atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc);
+		sk_storage->sk = NULL;
+		/* After this RCU_INIT, sk may be freed and cannot be used */
+		RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);
+
+		/* sk_storage is not freed now.  sk_storage->lock is
+		 * still held and raw_spin_unlock_bh(&sk_storage->lock)
+		 * will be done by the caller.
+		 *
+		 * Although the unlock will be done under
+		 * rcu_read_lock(),  it is more intutivie to
+		 * read if kfree_rcu(sk_storage, rcu) is done
+		 * after the raw_spin_unlock_bh(&sk_storage->lock).
+		 *
+		 * Hence, a "bool free_sk_storage" is returned
+		 * to the caller which then calls the kfree_rcu()
+		 * after unlock.
+		 */
+	}
+	hlist_del_init_rcu(&selem->snode);
+	if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) ==
+	    SDATA(selem))
+		RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL);
+
+	kfree_rcu(selem, rcu);
+
+	return free_sk_storage;
+}
+
+static void selem_unlink_sk(struct bpf_sk_storage_elem *selem)
+{
+	struct bpf_sk_storage *sk_storage;
+	bool free_sk_storage = false;
+
+	if (unlikely(!selem_linked_to_sk(selem)))
+		/* selem has already been unlinked from sk */
+		return;
+
+	sk_storage = rcu_dereference(selem->sk_storage);
+	raw_spin_lock_bh(&sk_storage->lock);
+	if (likely(selem_linked_to_sk(selem)))
+		free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
+	raw_spin_unlock_bh(&sk_storage->lock);
+
+	if (free_sk_storage)
+		kfree_rcu(sk_storage, rcu);
+}
+
+/* sk_storage->lock must be held and sk_storage->list cannot be empty */
+static void __selem_link_sk(struct bpf_sk_storage *sk_storage,
+			    struct bpf_sk_storage_elem *selem)
+{
+	RCU_INIT_POINTER(selem->sk_storage, sk_storage);
+	hlist_add_head(&selem->snode, &sk_storage->list);
+}
+
+static void selem_unlink_map(struct bpf_sk_storage_elem *selem)
+{
+	struct bpf_sk_storage_map *smap;
+	struct bucket *b;
+
+	if (unlikely(!selem_linked_to_map(selem)))
+		/* selem has already be unlinked from smap */
+		return;
+
+	smap = rcu_dereference(SDATA(selem)->smap);
+	b = select_bucket(smap, selem);
+	raw_spin_lock_bh(&b->lock);
+	if (likely(selem_linked_to_map(selem)))
+		hlist_del_init_rcu(&selem->map_node);
+	raw_spin_unlock_bh(&b->lock);
+}
+
+static void selem_link_map(struct bpf_sk_storage_map *smap,
+			   struct bpf_sk_storage_elem *selem)
+{
+	struct bucket *b = select_bucket(smap, selem);
+
+	raw_spin_lock_bh(&b->lock);
+	RCU_INIT_POINTER(SDATA(selem)->smap, smap);
+	hlist_add_head_rcu(&selem->map_node, &b->list);
+	raw_spin_unlock_bh(&b->lock);
+}
+
+static void selem_unlink(struct bpf_sk_storage_elem *selem)
+{
+	/* Always unlink from map before unlinking from sk_storage
+	 * because selem will be freed after successfully unlinked from
+	 * the sk_storage.
+	 */
+	selem_unlink_map(selem);
+	selem_unlink_sk(selem);
+}
+
+static struct bpf_sk_storage_data *
+__sk_storage_lookup(struct bpf_sk_storage *sk_storage,
+		    struct bpf_sk_storage_map *smap,
+		    bool cacheit_lockit)
+{
+	struct bpf_sk_storage_data *sdata;
+	struct bpf_sk_storage_elem *selem;
+
+	/* Fast path (cache hit) */
+	sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]);
+	if (sdata && rcu_access_pointer(sdata->smap) == smap)
+		return sdata;
+
+	/* Slow path (cache miss) */
+	hlist_for_each_entry_rcu(selem, &sk_storage->list, snode)
+		if (rcu_access_pointer(SDATA(selem)->smap) == smap)
+			break;
+
+	if (!selem)
+		return NULL;
+
+	sdata = SDATA(selem);
+	if (cacheit_lockit) {
+		/* spinlock is needed to avoid racing with the
+		 * parallel delete.  Otherwise, publishing an already
+		 * deleted sdata to the cache will become a use-after-free
+		 * problem in the next __sk_storage_lookup().
+		 */
+		raw_spin_lock_bh(&sk_storage->lock);
+		if (selem_linked_to_sk(selem))
+			rcu_assign_pointer(sk_storage->cache[smap->cache_idx],
+					   sdata);
+		raw_spin_unlock_bh(&sk_storage->lock);
+	}
+
+	return sdata;
+}
+
+static struct bpf_sk_storage_data *
+sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
+{
+	struct bpf_sk_storage *sk_storage;
+	struct bpf_sk_storage_map *smap;
+
+	sk_storage = rcu_dereference(sk->sk_bpf_storage);
+	if (!sk_storage)
+		return NULL;
+
+	smap = (struct bpf_sk_storage_map *)map;
+	return __sk_storage_lookup(sk_storage, smap, cacheit_lockit);
+}
+
+static int check_flags(const struct bpf_sk_storage_data *old_sdata,
+		       u64 map_flags)
+{
+	if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
+		/* elem already exists */
+		return -EEXIST;
+
+	if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
+		/* elem doesn't exist, cannot update it */
+		return -ENOENT;
+
+	return 0;
+}
+
+static int sk_storage_alloc(struct sock *sk,
+			    struct bpf_sk_storage_map *smap,
+			    struct bpf_sk_storage_elem *first_selem)
+{
+	struct bpf_sk_storage *prev_sk_storage, *sk_storage;
+	int err;
+
+	err = omem_charge(sk, sizeof(*sk_storage));
+	if (err)
+		return err;
+
+	sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN);
+	if (!sk_storage) {
+		err = -ENOMEM;
+		goto uncharge;
+	}
+	INIT_HLIST_HEAD(&sk_storage->list);
+	raw_spin_lock_init(&sk_storage->lock);
+	sk_storage->sk = sk;
+
+	__selem_link_sk(sk_storage, first_selem);
+	selem_link_map(smap, first_selem);
+	/* Publish sk_storage to sk.  sk->sk_lock cannot be acquired.
+	 * Hence, atomic ops is used to set sk->sk_bpf_storage
+	 * from NULL to the newly allocated sk_storage ptr.
+	 *
+	 * From now on, the sk->sk_bpf_storage pointer is protected
+	 * by the sk_storage->lock.  Hence,  when freeing
+	 * the sk->sk_bpf_storage, the sk_storage->lock must
+	 * be held before setting sk->sk_bpf_storage to NULL.
+	 */
+	prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage,
+				  NULL, sk_storage);
+	if (unlikely(prev_sk_storage)) {
+		selem_unlink_map(first_selem);
+		err = -EAGAIN;
+		goto uncharge;
+
+		/* Note that even first_selem was linked to smap's
+		 * bucket->list, first_selem can be freed immediately
+		 * (instead of kfree_rcu) because
+		 * bpf_sk_storage_map_free() does a
+		 * synchronize_rcu() before walking the bucket->list.
+		 * Hence, no one is accessing selem from the
+		 * bucket->list under rcu_read_lock().
+		 */
+	}
+
+	return 0;
+
+uncharge:
+	kfree(sk_storage);
+	atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc);
+	return err;
+}
+
+/* sk cannot be going away because it is linking new elem
+ * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0).
+ * Otherwise, it will become a leak (and other memory issues
+ * during map destruction).
+ */
+static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
+						     struct bpf_map *map,
+						     void *value,
+						     u64 map_flags)
+{
+	struct bpf_sk_storage_data *old_sdata = NULL;
+	struct bpf_sk_storage_elem *selem;
+	struct bpf_sk_storage *sk_storage;
+	struct bpf_sk_storage_map *smap;
+	int err;
+
+	/* BPF_EXIST and BPF_NOEXIST cannot be both set */
+	if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
+	    /* BPF_F_LOCK can only be used in a value with spin_lock */
+	    unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
+		return ERR_PTR(-EINVAL);
+
+	smap = (struct bpf_sk_storage_map *)map;
+	sk_storage = rcu_dereference(sk->sk_bpf_storage);
+	if (!sk_storage || hlist_empty(&sk_storage->list)) {
+		/* Very first elem for this sk */
+		err = check_flags(NULL, map_flags);
+		if (err)
+			return ERR_PTR(err);
+
+		selem = selem_alloc(smap, sk, value, true);
+		if (!selem)
+			return ERR_PTR(-ENOMEM);
+
+		err = sk_storage_alloc(sk, smap, selem);
+		if (err) {
+			kfree(selem);
+			atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
+			return ERR_PTR(err);
+		}
+
+		return SDATA(selem);
+	}
+
+	if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) {
+		/* Hoping to find an old_sdata to do inline update
+		 * such that it can avoid taking the sk_storage->lock
+		 * and changing the lists.
+		 */
+		old_sdata = __sk_storage_lookup(sk_storage, smap, false);
+		err = check_flags(old_sdata, map_flags);
+		if (err)
+			return ERR_PTR(err);
+		if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) {
+			copy_map_value_locked(map, old_sdata->data,
+					      value, false);
+			return old_sdata;
+		}
+	}
+
+	raw_spin_lock_bh(&sk_storage->lock);
+
+	/* Recheck sk_storage->list under sk_storage->lock */
+	if (unlikely(hlist_empty(&sk_storage->list))) {
+		/* A parallel del is happening and sk_storage is going
+		 * away.  It has just been checked before, so very
+		 * unlikely.  Return instead of retry to keep things
+		 * simple.
+		 */
+		err = -EAGAIN;
+		goto unlock_err;
+	}
+
+	old_sdata = __sk_storage_lookup(sk_storage, smap, false);
+	err = check_flags(old_sdata, map_flags);
+	if (err)
+		goto unlock_err;
+
+	if (old_sdata && (map_flags & BPF_F_LOCK)) {
+		copy_map_value_locked(map, old_sdata->data, value, false);
+		selem = SELEM(old_sdata);
+		goto unlock;
+	}
+
+	/* sk_storage->lock is held.  Hence, we are sure
+	 * we can unlink and uncharge the old_sdata successfully
+	 * later.  Hence, instead of charging the new selem now
+	 * and then uncharge the old selem later (which may cause
+	 * a potential but unnecessary charge failure),  avoid taking
+	 * a charge at all here (the "!old_sdata" check) and the
+	 * old_sdata will not be uncharged later during __selem_unlink_sk().
+	 */
+	selem = selem_alloc(smap, sk, value, !old_sdata);
+	if (!selem) {
+		err = -ENOMEM;
+		goto unlock_err;
+	}
+
+	/* First, link the new selem to the map */
+	selem_link_map(smap, selem);
+
+	/* Second, link (and publish) the new selem to sk_storage */
+	__selem_link_sk(sk_storage, selem);
+
+	/* Third, remove old selem, SELEM(old_sdata) */
+	if (old_sdata) {
+		selem_unlink_map(SELEM(old_sdata));
+		__selem_unlink_sk(sk_storage, SELEM(old_sdata), false);
+	}
+
+unlock:
+	raw_spin_unlock_bh(&sk_storage->lock);
+	return SDATA(selem);
+
+unlock_err:
+	raw_spin_unlock_bh(&sk_storage->lock);
+	return ERR_PTR(err);
+}
+
+static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
+{
+	struct bpf_sk_storage_data *sdata;
+
+	sdata = sk_storage_lookup(sk, map, false);
+	if (!sdata)
+		return -ENOENT;
+
+	selem_unlink(SELEM(sdata));
+
+	return 0;
+}
+
+/* Called by __sk_destruct() */
+void bpf_sk_storage_free(struct sock *sk)
+{
+	struct bpf_sk_storage_elem *selem;
+	struct bpf_sk_storage *sk_storage;
+	bool free_sk_storage = false;
+	struct hlist_node *n;
+
+	rcu_read_lock();
+	sk_storage = rcu_dereference(sk->sk_bpf_storage);
+	if (!sk_storage) {
+		rcu_read_unlock();
+		return;
+	}
+
+	/* Netiher the bpf_prog nor the bpf-map's syscall
+	 * could be modifying the sk_storage->list now.
+	 * Thus, no elem can be added-to or deleted-from the
+	 * sk_storage->list by the bpf_prog or by the bpf-map's syscall.
+	 *
+	 * It is racing with bpf_sk_storage_map_free() alone
+	 * when unlinking elem from the sk_storage->list and
+	 * the map's bucket->list.
+	 */
+	raw_spin_lock_bh(&sk_storage->lock);
+	hlist_for_each_entry_safe(selem, n, &sk_storage->list, snode) {
+		/* Always unlink from map before unlinking from
+		 * sk_storage.
+		 */
+		selem_unlink_map(selem);
+		free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
+	}
+	raw_spin_unlock_bh(&sk_storage->lock);
+	rcu_read_unlock();
+
+	if (free_sk_storage)
+		kfree_rcu(sk_storage, rcu);
+}
+
+static void bpf_sk_storage_map_free(struct bpf_map *map)
+{
+	struct bpf_sk_storage_elem *selem;
+	struct bpf_sk_storage_map *smap;
+	struct bucket *b;
+	unsigned int i;
+
+	smap = (struct bpf_sk_storage_map *)map;
+
+	synchronize_rcu();
+
+	/* bpf prog and the userspace can no longer access this map
+	 * now.  No new selem (of this map) can be added
+	 * to the sk->sk_bpf_storage or to the map bucket's list.
+	 *
+	 * The elem of this map can be cleaned up here
+	 * or
+	 * by bpf_sk_storage_free() during __sk_destruct().
+	 */
+	for (i = 0; i < (1U << smap->bucket_log); i++) {
+		b = &smap->buckets[i];
+
+		rcu_read_lock();
+		/* No one is adding to b->list now */
+		while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)),
+						 struct bpf_sk_storage_elem,
+						 map_node))) {
+			selem_unlink(selem);
+			cond_resched_rcu();
+		}
+		rcu_read_unlock();
+	}
+
+	/* bpf_sk_storage_free() may still need to access the map.
+	 * e.g. bpf_sk_storage_free() has unlinked selem from the map
+	 * which then made the above while((selem = ...)) loop
+	 * exited immediately.
+	 *
+	 * However, the bpf_sk_storage_free() still needs to access
+	 * the smap->elem_size to do the uncharging in
+	 * __selem_unlink_sk().
+	 *
+	 * Hence, wait another rcu grace period for the
+	 * bpf_sk_storage_free() to finish.
+	 */
+	synchronize_rcu();
+
+	kvfree(smap->buckets);
+	kfree(map);
+}
+
+static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
+{
+	if (attr->map_flags != BPF_F_NO_PREALLOC || attr->max_entries ||
+	    attr->key_size != sizeof(int) || !attr->value_size ||
+	    /* Enforce BTF for userspace sk dumping */
+	    !attr->btf_key_type_id || !attr->btf_value_type_id)
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (attr->value_size >= KMALLOC_MAX_SIZE -
+	    MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem) ||
+	    /* U16_MAX is much more than enough for sk local storage
+	     * considering a tcp_sock is ~2k.
+	     */
+	    attr->value_size > U16_MAX - sizeof(struct bpf_sk_storage_elem))
+		return -E2BIG;
+
+	return 0;
+}
+
+static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_sk_storage_map *smap;
+	unsigned int i;
+	u32 nbuckets;
+	u64 cost;
+
+	smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
+	if (!smap)
+		return ERR_PTR(-ENOMEM);
+	bpf_map_init_from_attr(&smap->map, attr);
+
+	smap->bucket_log = ilog2(roundup_pow_of_two(num_possible_cpus()));
+	nbuckets = 1U << smap->bucket_log;
+	smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
+				 GFP_USER | __GFP_NOWARN);
+	if (!smap->buckets) {
+		kfree(smap);
+		return ERR_PTR(-ENOMEM);
+	}
+	cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
+
+	for (i = 0; i < nbuckets; i++) {
+		INIT_HLIST_HEAD(&smap->buckets[i].list);
+		raw_spin_lock_init(&smap->buckets[i].lock);
+	}
+
+	smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size;
+	smap->cache_idx = (unsigned int)atomic_inc_return(&cache_idx) %
+		BPF_SK_STORAGE_CACHE_SIZE;
+	smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	return &smap->map;
+}
+
+static int notsupp_get_next_key(struct bpf_map *map, void *key,
+				void *next_key)
+{
+	return -ENOTSUPP;
+}
+
+static int bpf_sk_storage_map_check_btf(const struct bpf_map *map,
+					const struct btf *btf,
+					const struct btf_type *key_type,
+					const struct btf_type *value_type)
+{
+	u32 int_data;
+
+	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+		return -EINVAL;
+
+	int_data = *(u32 *)(key_type + 1);
+	if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_sk_storage_data *sdata;
+	struct socket *sock;
+	int fd, err;
+
+	fd = *(int *)key;
+	sock = sockfd_lookup(fd, &err);
+	if (sock) {
+		sdata = sk_storage_lookup(sock->sk, map, true);
+		sockfd_put(sock);
+		return sdata ? sdata->data : NULL;
+	}
+
+	return ERR_PTR(err);
+}
+
+static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key,
+					 void *value, u64 map_flags)
+{
+	struct bpf_sk_storage_data *sdata;
+	struct socket *sock;
+	int fd, err;
+
+	fd = *(int *)key;
+	sock = sockfd_lookup(fd, &err);
+	if (sock) {
+		sdata = sk_storage_update(sock->sk, map, value, map_flags);
+		sockfd_put(sock);
+		return IS_ERR(sdata) ? PTR_ERR(sdata) : 0;
+	}
+
+	return err;
+}
+
+static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
+{
+	struct socket *sock;
+	int fd, err;
+
+	fd = *(int *)key;
+	sock = sockfd_lookup(fd, &err);
+	if (sock) {
+		err = sk_storage_delete(sock->sk, map);
+		sockfd_put(sock);
+		return err;
+	}
+
+	return err;
+}
+
+BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
+	   void *, value, u64, flags)
+{
+	struct bpf_sk_storage_data *sdata;
+
+	if (flags > BPF_SK_STORAGE_GET_F_CREATE)
+		return (unsigned long)NULL;
+
+	sdata = sk_storage_lookup(sk, map, true);
+	if (sdata)
+		return (unsigned long)sdata->data;
+
+	if (flags == BPF_SK_STORAGE_GET_F_CREATE &&
+	    /* Cannot add new elem to a going away sk.
+	     * Otherwise, the new elem may become a leak
+	     * (and also other memory issues during map
+	     *  destruction).
+	     */
+	    refcount_inc_not_zero(&sk->sk_refcnt)) {
+		sdata = sk_storage_update(sk, map, value, BPF_NOEXIST);
+		/* sk must be a fullsock (guaranteed by verifier),
+		 * so sock_gen_put() is unnecessary.
+		 */
+		sock_put(sk);
+		return IS_ERR(sdata) ?
+			(unsigned long)NULL : (unsigned long)sdata->data;
+	}
+
+	return (unsigned long)NULL;
+}
+
+BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
+{
+	if (refcount_inc_not_zero(&sk->sk_refcnt)) {
+		int err;
+
+		err = sk_storage_delete(sk, map);
+		sock_put(sk);
+		return err;
+	}
+
+	return -ENOENT;
+}
+
+const struct bpf_map_ops sk_storage_map_ops = {
+	.map_alloc_check = bpf_sk_storage_map_alloc_check,
+	.map_alloc = bpf_sk_storage_map_alloc,
+	.map_free = bpf_sk_storage_map_free,
+	.map_get_next_key = notsupp_get_next_key,
+	.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
+	.map_update_elem = bpf_fd_sk_storage_update_elem,
+	.map_delete_elem = bpf_fd_sk_storage_delete_elem,
+	.map_check_btf = bpf_sk_storage_map_check_btf,
+};
+
+const struct bpf_func_proto bpf_sk_storage_get_proto = {
+	.func		= bpf_sk_storage_get,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_SOCKET,
+	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+const struct bpf_func_proto bpf_sk_storage_delete_proto = {
+	.func		= bpf_sk_storage_delete,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_SOCKET,
+};
diff --git a/net/core/filter.c b/net/core/filter.c
index 2f88baf39cc2..27b0dc01dc3f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -75,6 +75,7 @@
 #include <net/seg6_local.h>
 #include <net/lwtunnel.h>
 #include <net/ipv6_stubs.h>
+#include <net/bpf_sk_storage.h>
 
 /**
  *	sk_filter_trim_cap - run a packet through a socket filter
@@ -5903,6 +5904,9 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	}
 }
 
+const struct bpf_func_proto bpf_sk_storage_get_proto __weak;
+const struct bpf_func_proto bpf_sk_storage_delete_proto __weak;
+
 static const struct bpf_func_proto *
 cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -5911,6 +5915,10 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_sk_fullsock:
 		return &bpf_sk_fullsock_proto;
+	case BPF_FUNC_sk_storage_get:
+		return &bpf_sk_storage_get_proto;
+	case BPF_FUNC_sk_storage_delete:
+		return &bpf_sk_storage_delete_proto;
 #ifdef CONFIG_INET
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
@@ -5992,6 +6000,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skb_fib_lookup_proto;
 	case BPF_FUNC_sk_fullsock:
 		return &bpf_sk_fullsock_proto;
+	case BPF_FUNC_sk_storage_get:
+		return &bpf_sk_storage_get_proto;
+	case BPF_FUNC_sk_storage_delete:
+		return &bpf_sk_storage_delete_proto;
 #ifdef CONFIG_XFRM
 	case BPF_FUNC_skb_get_xfrm_state:
 		return &bpf_skb_get_xfrm_state_proto;
diff --git a/net/core/sock.c b/net/core/sock.c
index 443b98d05f1e..9773be724aa9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -137,6 +137,7 @@
 
 #include <linux/filter.h>
 #include <net/sock_reuseport.h>
+#include <net/bpf_sk_storage.h>
 
 #include <trace/events/sock.h>
 
@@ -1709,6 +1710,10 @@ static void __sk_destruct(struct rcu_head *head)
 
 	sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
 
+#ifdef CONFIG_BPF_SYSCALL
+	bpf_sk_storage_free(sk);
+#endif
+
 	if (atomic_read(&sk->sk_omem_alloc))
 		pr_debug("%s: optmem leakage (%d bytes) detected\n",
 			 __func__, atomic_read(&sk->sk_omem_alloc));
-- 
cgit v1.2.3


From 9e9957973c7785b1f8fa77f099cac661cc5e7e5b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 25 Apr 2019 12:32:02 -0700
Subject: net/tls: remove old exports of sk_destruct functions

tls_device_sk_destruct being set on a socket used to indicate
that socket is a kTLS device one.  That is no longer true -
now we use sk_validate_xmit_skb pointer for that purpose.
Remove the export.  tls_device_attach() needs to be moved.

While at it, remove the dead declaration of tls_sk_destruct().

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h    |  2 --
 net/tls/tls_device.c | 35 +++++++++++++++++------------------
 2 files changed, 17 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/tls.h b/include/net/tls.h
index d9d0ac66f040..20196cb31ecc 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -317,7 +317,6 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx);
 int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tls_device_sendpage(struct sock *sk, struct page *page,
 			int offset, size_t size, int flags);
-void tls_device_sk_destruct(struct sock *sk);
 void tls_device_free_resources_tx(struct sock *sk);
 void tls_device_init(void);
 void tls_device_cleanup(void);
@@ -336,7 +335,6 @@ static inline u32 tls_record_start_seq(struct tls_record_info *rec)
 	return rec->end_seq - rec->len;
 }
 
-void tls_sk_destruct(struct sock *sk, struct tls_context *ctx);
 int tls_push_sg(struct sock *sk, struct tls_context *ctx,
 		struct scatterlist *sg, u16 first_offset,
 		int flags);
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 87e6cad7bace..79475b102cca 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -89,22 +89,6 @@ static void tls_device_gc_task(struct work_struct *work)
 	}
 }
 
-static void tls_device_attach(struct tls_context *ctx, struct sock *sk,
-			      struct net_device *netdev)
-{
-	if (sk->sk_destruct != tls_device_sk_destruct) {
-		refcount_set(&ctx->refcount, 1);
-		dev_hold(netdev);
-		ctx->netdev = netdev;
-		spin_lock_irq(&tls_device_lock);
-		list_add_tail(&ctx->list, &tls_device_list);
-		spin_unlock_irq(&tls_device_lock);
-
-		ctx->sk_destruct = sk->sk_destruct;
-		sk->sk_destruct = tls_device_sk_destruct;
-	}
-}
-
 static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
 {
 	unsigned long flags;
@@ -199,7 +183,7 @@ static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq)
  * socket and no in-flight SKBs associated with this
  * socket, so it is safe to free all the resources.
  */
-void tls_device_sk_destruct(struct sock *sk)
+static void tls_device_sk_destruct(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
@@ -217,7 +201,6 @@ void tls_device_sk_destruct(struct sock *sk)
 	if (refcount_dec_and_test(&tls_ctx->refcount))
 		tls_device_queue_ctx_destruction(tls_ctx);
 }
-EXPORT_SYMBOL(tls_device_sk_destruct);
 
 void tls_device_free_resources_tx(struct sock *sk)
 {
@@ -682,6 +665,22 @@ int tls_device_decrypted(struct sock *sk, struct sk_buff *skb)
 		tls_device_reencrypt(sk, skb);
 }
 
+static void tls_device_attach(struct tls_context *ctx, struct sock *sk,
+			      struct net_device *netdev)
+{
+	if (sk->sk_destruct != tls_device_sk_destruct) {
+		refcount_set(&ctx->refcount, 1);
+		dev_hold(netdev);
+		ctx->netdev = netdev;
+		spin_lock_irq(&tls_device_lock);
+		list_add_tail(&ctx->list, &tls_device_list);
+		spin_unlock_irq(&tls_device_lock);
+
+		ctx->sk_destruct = sk->sk_destruct;
+		sk->sk_destruct = tls_device_sk_destruct;
+	}
+}
+
 int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 {
 	u16 nonce_size, tag_size, iv_size, rec_seq_size;
-- 
cgit v1.2.3


From da68b4ad02343862fee1e3e8c6315984f16a4778 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 25 Apr 2019 12:32:03 -0700
Subject: net/tls: move definition of tls ops into net/tls.h

There seems to be no reason for tls_ops to be defined in netdevice.h
which is included in a lot of places.  Don't wrap the struct/enum
declaration in ifdefs, it trickles down unnecessary ifdefs into
driver code.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 23 +----------------------
 include/net/tls.h         | 17 +++++++++++++++++
 2 files changed, 18 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c46d218a0456..44b47e9df94a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -914,34 +914,13 @@ struct xfrmdev_ops {
 };
 #endif
 
-#if IS_ENABLED(CONFIG_TLS_DEVICE)
-enum tls_offload_ctx_dir {
-	TLS_OFFLOAD_CTX_DIR_RX,
-	TLS_OFFLOAD_CTX_DIR_TX,
-};
-
-struct tls_crypto_info;
-struct tls_context;
-
-struct tlsdev_ops {
-	int (*tls_dev_add)(struct net_device *netdev, struct sock *sk,
-			   enum tls_offload_ctx_dir direction,
-			   struct tls_crypto_info *crypto_info,
-			   u32 start_offload_tcp_sn);
-	void (*tls_dev_del)(struct net_device *netdev,
-			    struct tls_context *ctx,
-			    enum tls_offload_ctx_dir direction);
-	void (*tls_dev_resync_rx)(struct net_device *netdev,
-				  struct sock *sk, u32 seq, u64 rcd_sn);
-};
-#endif
-
 struct dev_ifalias {
 	struct rcu_head rcuhead;
 	char ifalias[];
 };
 
 struct devlink;
+struct tlsdev_ops;
 
 /*
  * This structure defines the management hooks for network devices.
diff --git a/include/net/tls.h b/include/net/tls.h
index 20196cb31ecc..41a2ee643fc5 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -277,6 +277,23 @@ struct tls_context {
 	void (*unhash)(struct sock *sk);
 };
 
+enum tls_offload_ctx_dir {
+	TLS_OFFLOAD_CTX_DIR_RX,
+	TLS_OFFLOAD_CTX_DIR_TX,
+};
+
+struct tlsdev_ops {
+	int (*tls_dev_add)(struct net_device *netdev, struct sock *sk,
+			   enum tls_offload_ctx_dir direction,
+			   struct tls_crypto_info *crypto_info,
+			   u32 start_offload_tcp_sn);
+	void (*tls_dev_del)(struct net_device *netdev,
+			    struct tls_context *ctx,
+			    enum tls_offload_ctx_dir direction);
+	void (*tls_dev_resync_rx)(struct net_device *netdev,
+				  struct sock *sk, u32 seq, u64 rcd_sn);
+};
+
 struct tls_offload_context_rx {
 	/* sw must be the first member of tls_offload_context_rx */
 	struct tls_sw_context_rx sw;
-- 
cgit v1.2.3


From 63a1c95f3fe48b4e9fe0c261b376e5e527b71b25 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 25 Apr 2019 12:32:04 -0700
Subject: net/tls: byte swap device req TCP seq no upon setting

To avoid a sparse warning byteswap the be32 sequence number
before it's stored in the atomic value.  While at it drop
unnecessary brackets and use kernel's u64 type.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h    | 2 +-
 net/tls/tls_device.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/tls.h b/include/net/tls.h
index 41a2ee643fc5..39ea62f0c1f6 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -562,7 +562,7 @@ static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq)
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
 
-	atomic64_set(&rx_ctx->resync_req, ((((uint64_t)seq) << 32) | 1));
+	atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | 1);
 }
 
 
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 79475b102cca..26f26e71ef3f 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -567,7 +567,7 @@ void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
 
 	rx_ctx = tls_offload_ctx_rx(tls_ctx);
 	resync_req = atomic64_read(&rx_ctx->resync_req);
-	req_seq = ntohl(resync_req >> 32) - ((u32)TLS_HEADER_SIZE - 1);
+	req_seq = (resync_req >> 32) - ((u32)TLS_HEADER_SIZE - 1);
 	is_req_pending = resync_req;
 
 	if (unlikely(is_req_pending) && req_seq == seq &&
-- 
cgit v1.2.3


From ae0be8de9a53cda3505865c11826d8ff0640237c Mon Sep 17 00:00:00 2001
From: Michal Kubecek <mkubecek@suse.cz>
Date: Fri, 26 Apr 2019 11:13:06 +0200
Subject: netlink: make nla_nest_start() add NLA_F_NESTED flag

Even if the NLA_F_NESTED flag was introduced more than 11 years ago, most
netlink based interfaces (including recently added ones) are still not
setting it in kernel generated messages. Without the flag, message parsers
not aware of attribute semantics (e.g. wireshark dissector or libmnl's
mnl_nlmsg_fprintf()) cannot recognize nested attributes and won't display
the structure of their contents.

Unfortunately we cannot just add the flag everywhere as there may be
userspace applications which check nlattr::nla_type directly rather than
through a helper masking out the flags. Therefore the patch renames
nla_nest_start() to nla_nest_start_noflag() and introduces nla_nest_start()
as a wrapper adding NLA_F_NESTED. The calls which add NLA_F_NESTED manually
are rewritten to use nla_nest_start().

Except for changes in include/net/netlink.h, the patch was generated using
this semantic patch:

@@ expression E1, E2; @@
-nla_nest_start(E1, E2)
+nla_nest_start_noflag(E1, E2)

@@ expression E1, E2; @@
-nla_nest_start_noflag(E1, E2 | NLA_F_NESTED)
+nla_nest_start(E1, E2)

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/drbd/drbd_nl.c                |   8 +-
 drivers/block/nbd.c                         |   4 +-
 drivers/infiniband/core/nldev.c             |   9 +-
 drivers/infiniband/hw/cxgb4/restrack.c      |   8 +-
 drivers/net/bonding/bond_netlink.c          |   8 +-
 drivers/net/ieee802154/mac802154_hwsim.c    |   6 +-
 drivers/net/macsec.c                        |  27 ++--
 drivers/net/macvlan.c                       |   2 +-
 drivers/net/team/team.c                     |   8 +-
 drivers/net/wireless/ath/wil6210/cfg80211.c |   4 +-
 include/linux/netfilter/ipset/ip_set.h      |   2 +-
 include/net/netlink.h                       |  26 +++-
 kernel/taskstats.c                          |   2 +-
 net/8021q/vlan_netlink.c                    |   4 +-
 net/bridge/br_mdb.c                         |  17 +--
 net/bridge/br_netlink.c                     |   6 +-
 net/bridge/br_netlink_tunnel.c              |   2 +-
 net/core/devlink.c                          |  78 ++++++-----
 net/core/lwt_bpf.c                          |   2 +-
 net/core/lwtunnel.c                         |   2 +-
 net/core/neighbour.c                        |   2 +-
 net/core/rtnetlink.c                        |  48 +++----
 net/dcb/dcbnl.c                             |  40 +++---
 net/decnet/dn_table.c                       |   2 +-
 net/ieee802154/nl802154.c                   |  34 ++---
 net/ipv4/fib_semantics.c                    |   2 +-
 net/ipv4/ipmr.c                             |   6 +-
 net/ipv4/ipmr_base.c                        |   2 +-
 net/ipv4/tcp_metrics.c                      |   2 +-
 net/ipv6/addrconf.c                         |   2 +-
 net/ipv6/route.c                            |   2 +-
 net/ipv6/seg6_local.c                       |   2 +-
 net/l2tp/l2tp_netlink.c                     |   4 +-
 net/mpls/af_mpls.c                          |   2 +-
 net/ncsi/ncsi-netlink.c                     |  12 +-
 net/netfilter/ipvs/ip_vs_ctl.c              |  10 +-
 net/netfilter/nf_conntrack_netlink.c        |  40 +++---
 net/netfilter/nf_conntrack_proto_dccp.c     |   2 +-
 net/netfilter/nf_conntrack_proto_sctp.c     |   2 +-
 net/netfilter/nf_conntrack_proto_tcp.c      |   2 +-
 net/netfilter/nf_tables_api.c               |  29 +++--
 net/netfilter/nfnetlink_cthelper.c          |   7 +-
 net/netfilter/nfnetlink_cttimeout.c         |   4 +-
 net/netfilter/nfnetlink_queue.c             |   2 +-
 net/netfilter/nft_ct.c                      |   2 +-
 net/netfilter/nft_tunnel.c                  |   6 +-
 net/netlabel/netlabel_cipso_v4.c            |  14 +-
 net/netlabel/netlabel_mgmt.c                |   8 +-
 net/netlink/genetlink.c                     |  12 +-
 net/nfc/netlink.c                           |   4 +-
 net/openvswitch/conntrack.c                 |   6 +-
 net/openvswitch/datapath.c                  |   7 +-
 net/openvswitch/flow_netlink.c              |  33 ++---
 net/openvswitch/meter.c                     |   8 +-
 net/openvswitch/vport-vxlan.c               |   2 +-
 net/openvswitch/vport.c                     |   2 +-
 net/packet/diag.c                           |   2 +-
 net/sched/act_api.c                         |  14 +-
 net/sched/act_ife.c                         |   2 +-
 net/sched/act_pedit.c                       |   5 +-
 net/sched/act_tunnel_key.c                  |   4 +-
 net/sched/cls_api.c                         |   4 +-
 net/sched/cls_basic.c                       |   2 +-
 net/sched/cls_bpf.c                         |   2 +-
 net/sched/cls_cgroup.c                      |   2 +-
 net/sched/cls_flow.c                        |   2 +-
 net/sched/cls_flower.c                      |   8 +-
 net/sched/cls_fw.c                          |   2 +-
 net/sched/cls_matchall.c                    |   2 +-
 net/sched/cls_route.c                       |   2 +-
 net/sched/cls_rsvp.h                        |   2 +-
 net/sched/cls_tcindex.c                     |   2 +-
 net/sched/cls_u32.c                         |   2 +-
 net/sched/ematch.c                          |   4 +-
 net/sched/sch_api.c                         |   2 +-
 net/sched/sch_atm.c                         |   2 +-
 net/sched/sch_cake.c                        |  10 +-
 net/sched/sch_cbq.c                         |   4 +-
 net/sched/sch_cbs.c                         |   2 +-
 net/sched/sch_choke.c                       |   2 +-
 net/sched/sch_codel.c                       |   2 +-
 net/sched/sch_drr.c                         |   2 +-
 net/sched/sch_dsmark.c                      |   4 +-
 net/sched/sch_etf.c                         |   2 +-
 net/sched/sch_fq.c                          |   2 +-
 net/sched/sch_fq_codel.c                    |   2 +-
 net/sched/sch_gred.c                        |   8 +-
 net/sched/sch_hfsc.c                        |   2 +-
 net/sched/sch_hhf.c                         |   2 +-
 net/sched/sch_htb.c                         |   4 +-
 net/sched/sch_ingress.c                     |   2 +-
 net/sched/sch_mqprio.c                      |   4 +-
 net/sched/sch_netem.c                       |   2 +-
 net/sched/sch_pie.c                         |   2 +-
 net/sched/sch_qfq.c                         |   2 +-
 net/sched/sch_red.c                         |   2 +-
 net/sched/sch_sfb.c                         |   2 +-
 net/sched/sch_taprio.c                      |   7 +-
 net/sched/sch_tbf.c                         |   2 +-
 net/tipc/bearer.c                           |   8 +-
 net/tipc/group.c                            |   2 +-
 net/tipc/link.c                             |  12 +-
 net/tipc/monitor.c                          |   4 +-
 net/tipc/name_table.c                       |   4 +-
 net/tipc/net.c                              |   2 +-
 net/tipc/netlink_compat.c                   |  24 ++--
 net/tipc/node.c                             |   4 +-
 net/tipc/socket.c                           |  10 +-
 net/tipc/udp_media.c                        |   2 +-
 net/wireless/nl80211.c                      | 192 +++++++++++++++-------------
 net/wireless/pmsr.c                         |  12 +-
 111 files changed, 539 insertions(+), 466 deletions(-)

(limited to 'include')

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index f2471172a961..1cb5a0b85fd9 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -114,7 +114,7 @@ static int drbd_msg_put_info(struct sk_buff *skb, const char *info)
 	if (!info || !info[0])
 		return 0;
 
-	nla = nla_nest_start(skb, DRBD_NLA_CFG_REPLY);
+	nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_REPLY);
 	if (!nla)
 		return err;
 
@@ -135,7 +135,7 @@ static int drbd_msg_sprintf_info(struct sk_buff *skb, const char *fmt, ...)
 	int err = -EMSGSIZE;
 	int len;
 
-	nla = nla_nest_start(skb, DRBD_NLA_CFG_REPLY);
+	nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_REPLY);
 	if (!nla)
 		return err;
 
@@ -3269,7 +3269,7 @@ static int nla_put_drbd_cfg_context(struct sk_buff *skb,
 				    struct drbd_device *device)
 {
 	struct nlattr *nla;
-	nla = nla_nest_start(skb, DRBD_NLA_CFG_CONTEXT);
+	nla = nla_nest_start_noflag(skb, DRBD_NLA_CFG_CONTEXT);
 	if (!nla)
 		goto nla_put_failure;
 	if (device &&
@@ -3837,7 +3837,7 @@ static int nla_put_status_info(struct sk_buff *skb, struct drbd_device *device,
 	if (err)
 		goto nla_put_failure;
 
-	nla = nla_nest_start(skb, DRBD_NLA_STATE_INFO);
+	nla = nla_nest_start_noflag(skb, DRBD_NLA_STATE_INFO);
 	if (!nla)
 		goto nla_put_failure;
 	if (nla_put_u32(skb, T_sib_reason, sib ? sib->sib_reason : SIB_GET_STATUS_REPLY) ||
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 92b8aafb8bb4..cd27f236431d 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -2047,7 +2047,7 @@ static int populate_nbd_status(struct nbd_device *nbd, struct sk_buff *reply)
 	 */
 	if (refcount_read(&nbd->config_refs))
 		connected = 1;
-	dev_opt = nla_nest_start(reply, NBD_DEVICE_ITEM);
+	dev_opt = nla_nest_start_noflag(reply, NBD_DEVICE_ITEM);
 	if (!dev_opt)
 		return -EMSGSIZE;
 	ret = nla_put_u32(reply, NBD_DEVICE_INDEX, nbd->index);
@@ -2095,7 +2095,7 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 	}
 
-	dev_list = nla_nest_start(reply, NBD_ATTR_DEVICE_LIST);
+	dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST);
 	if (index == -1) {
 		ret = idr_for_each(&nbd_index_idr, &status_cb, reply);
 		if (ret) {
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 11ed58d3fce5..ad189a29cc67 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -292,7 +292,8 @@ static int fill_res_info_entry(struct sk_buff *msg,
 {
 	struct nlattr *entry_attr;
 
-	entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY);
+	entry_attr = nla_nest_start_noflag(msg,
+					   RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY);
 	if (!entry_attr)
 		return -EMSGSIZE;
 
@@ -327,7 +328,7 @@ static int fill_res_info(struct sk_buff *msg, struct ib_device *device)
 	if (fill_nldev_handle(msg, device))
 		return -EMSGSIZE;
 
-	table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_SUMMARY);
+	table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_RES_SUMMARY);
 	if (!table_attr)
 		return -EMSGSIZE;
 
@@ -1108,7 +1109,7 @@ static int res_get_common_dumpit(struct sk_buff *skb,
 		goto err;
 	}
 
-	table_attr = nla_nest_start(skb, fe->nldev_attr);
+	table_attr = nla_nest_start_noflag(skb, fe->nldev_attr);
 	if (!table_attr) {
 		ret = -EMSGSIZE;
 		goto err;
@@ -1134,7 +1135,7 @@ static int res_get_common_dumpit(struct sk_buff *skb,
 
 		filled = true;
 
-		entry_attr = nla_nest_start(skb, fe->entry);
+		entry_attr = nla_nest_start_noflag(skb, fe->entry);
 		if (!entry_attr) {
 			ret = -EMSGSIZE;
 			rdma_restrack_put(res);
diff --git a/drivers/infiniband/hw/cxgb4/restrack.c b/drivers/infiniband/hw/cxgb4/restrack.c
index 9a7520ee41e0..f82d46ed969d 100644
--- a/drivers/infiniband/hw/cxgb4/restrack.c
+++ b/drivers/infiniband/hw/cxgb4/restrack.c
@@ -149,7 +149,7 @@ static int fill_res_qp_entry(struct sk_buff *msg,
 	if (qhp->ucontext)
 		return 0;
 
-	table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_DRIVER);
+	table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_DRIVER);
 	if (!table_attr)
 		goto err;
 
@@ -216,7 +216,7 @@ static int fill_res_ep_entry(struct sk_buff *msg,
 	if (!uep)
 		return 0;
 
-	table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_DRIVER);
+	table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_DRIVER);
 	if (!table_attr)
 		goto err_free_uep;
 
@@ -387,7 +387,7 @@ static int fill_res_cq_entry(struct sk_buff *msg,
 	if (ibcq->uobject)
 		return 0;
 
-	table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_DRIVER);
+	table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_DRIVER);
 	if (!table_attr)
 		goto err;
 
@@ -447,7 +447,7 @@ static int fill_res_mr_entry(struct sk_buff *msg,
 	if (!stag)
 		return 0;
 
-	table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_DRIVER);
+	table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_DRIVER);
 	if (!table_attr)
 		goto err;
 
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index b286f591242e..022044b59d6a 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -546,7 +546,7 @@ static int bond_fill_info(struct sk_buff *skb,
 	if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval))
 		goto nla_put_failure;
 
-	targets = nla_nest_start(skb, IFLA_BOND_ARP_IP_TARGET);
+	targets = nla_nest_start_noflag(skb, IFLA_BOND_ARP_IP_TARGET);
 	if (!targets)
 		goto nla_put_failure;
 
@@ -644,7 +644,7 @@ static int bond_fill_info(struct sk_buff *skb,
 		if (!bond_3ad_get_active_agg_info(bond, &info)) {
 			struct nlattr *nest;
 
-			nest = nla_nest_start(skb, IFLA_BOND_AD_INFO);
+			nest = nla_nest_start_noflag(skb, IFLA_BOND_AD_INFO);
 			if (!nest)
 				goto nla_put_failure;
 
@@ -711,7 +711,7 @@ static int bond_fill_linkxstats(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-	nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BOND);
+	nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BOND);
 	if (!nest)
 		return -EMSGSIZE;
 	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
@@ -722,7 +722,7 @@ static int bond_fill_linkxstats(struct sk_buff *skb,
 		else
 			stats = &BOND_AD_INFO(bond).stats;
 
-		nest2 = nla_nest_start(skb, BOND_XSTATS_3AD);
+		nest2 = nla_nest_start_noflag(skb, BOND_XSTATS_3AD);
 		if (!nest2) {
 			nla_nest_end(skb, nest);
 			return -EMSGSIZE;
diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index 707285953750..80ca300aba04 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -227,14 +227,16 @@ static int append_radio_msg(struct sk_buff *skb, struct hwsim_phy *phy)
 		return 0;
 	}
 
-	nl_edges = nla_nest_start(skb, MAC802154_HWSIM_ATTR_RADIO_EDGES);
+	nl_edges = nla_nest_start_noflag(skb,
+					 MAC802154_HWSIM_ATTR_RADIO_EDGES);
 	if (!nl_edges) {
 		rcu_read_unlock();
 		return -ENOBUFS;
 	}
 
 	list_for_each_entry_rcu(e, &phy->edges, list) {
-		nl_edge = nla_nest_start(skb, MAC802154_HWSIM_ATTR_RADIO_EDGE);
+		nl_edge = nla_nest_start_noflag(skb,
+						MAC802154_HWSIM_ATTR_RADIO_EDGE);
 		if (!nl_edge) {
 			rcu_read_unlock();
 			nla_nest_cancel(skb, nl_edges);
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 263bfafdb004..8dedb9a9781e 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2365,7 +2365,8 @@ copy_secy_stats(struct sk_buff *skb, struct pcpu_secy_stats __percpu *pstats)
 static int nla_put_secy(struct macsec_secy *secy, struct sk_buff *skb)
 {
 	struct macsec_tx_sc *tx_sc = &secy->tx_sc;
-	struct nlattr *secy_nest = nla_nest_start(skb, MACSEC_ATTR_SECY);
+	struct nlattr *secy_nest = nla_nest_start_noflag(skb,
+							 MACSEC_ATTR_SECY);
 	u64 csid;
 
 	if (!secy_nest)
@@ -2435,7 +2436,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 	if (nla_put_secy(secy, skb))
 		goto nla_put_failure;
 
-	attr = nla_nest_start(skb, MACSEC_ATTR_TXSC_STATS);
+	attr = nla_nest_start_noflag(skb, MACSEC_ATTR_TXSC_STATS);
 	if (!attr)
 		goto nla_put_failure;
 	if (copy_tx_sc_stats(skb, tx_sc->stats)) {
@@ -2444,7 +2445,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 	}
 	nla_nest_end(skb, attr);
 
-	attr = nla_nest_start(skb, MACSEC_ATTR_SECY_STATS);
+	attr = nla_nest_start_noflag(skb, MACSEC_ATTR_SECY_STATS);
 	if (!attr)
 		goto nla_put_failure;
 	if (copy_secy_stats(skb, macsec_priv(dev)->stats)) {
@@ -2453,7 +2454,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 	}
 	nla_nest_end(skb, attr);
 
-	txsa_list = nla_nest_start(skb, MACSEC_ATTR_TXSA_LIST);
+	txsa_list = nla_nest_start_noflag(skb, MACSEC_ATTR_TXSA_LIST);
 	if (!txsa_list)
 		goto nla_put_failure;
 	for (i = 0, j = 1; i < MACSEC_NUM_AN; i++) {
@@ -2463,7 +2464,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 		if (!tx_sa)
 			continue;
 
-		txsa_nest = nla_nest_start(skb, j++);
+		txsa_nest = nla_nest_start_noflag(skb, j++);
 		if (!txsa_nest) {
 			nla_nest_cancel(skb, txsa_list);
 			goto nla_put_failure;
@@ -2478,7 +2479,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 			goto nla_put_failure;
 		}
 
-		attr = nla_nest_start(skb, MACSEC_SA_ATTR_STATS);
+		attr = nla_nest_start_noflag(skb, MACSEC_SA_ATTR_STATS);
 		if (!attr) {
 			nla_nest_cancel(skb, txsa_nest);
 			nla_nest_cancel(skb, txsa_list);
@@ -2496,7 +2497,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 	}
 	nla_nest_end(skb, txsa_list);
 
-	rxsc_list = nla_nest_start(skb, MACSEC_ATTR_RXSC_LIST);
+	rxsc_list = nla_nest_start_noflag(skb, MACSEC_ATTR_RXSC_LIST);
 	if (!rxsc_list)
 		goto nla_put_failure;
 
@@ -2504,7 +2505,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 	for_each_rxsc_rtnl(secy, rx_sc) {
 		int k;
 		struct nlattr *rxsa_list;
-		struct nlattr *rxsc_nest = nla_nest_start(skb, j++);
+		struct nlattr *rxsc_nest = nla_nest_start_noflag(skb, j++);
 
 		if (!rxsc_nest) {
 			nla_nest_cancel(skb, rxsc_list);
@@ -2519,7 +2520,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 			goto nla_put_failure;
 		}
 
-		attr = nla_nest_start(skb, MACSEC_RXSC_ATTR_STATS);
+		attr = nla_nest_start_noflag(skb, MACSEC_RXSC_ATTR_STATS);
 		if (!attr) {
 			nla_nest_cancel(skb, rxsc_nest);
 			nla_nest_cancel(skb, rxsc_list);
@@ -2533,7 +2534,8 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 		}
 		nla_nest_end(skb, attr);
 
-		rxsa_list = nla_nest_start(skb, MACSEC_RXSC_ATTR_SA_LIST);
+		rxsa_list = nla_nest_start_noflag(skb,
+						  MACSEC_RXSC_ATTR_SA_LIST);
 		if (!rxsa_list) {
 			nla_nest_cancel(skb, rxsc_nest);
 			nla_nest_cancel(skb, rxsc_list);
@@ -2547,7 +2549,7 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 			if (!rx_sa)
 				continue;
 
-			rxsa_nest = nla_nest_start(skb, k++);
+			rxsa_nest = nla_nest_start_noflag(skb, k++);
 			if (!rxsa_nest) {
 				nla_nest_cancel(skb, rxsa_list);
 				nla_nest_cancel(skb, rxsc_nest);
@@ -2555,7 +2557,8 @@ dump_secy(struct macsec_secy *secy, struct net_device *dev,
 				goto nla_put_failure;
 			}
 
-			attr = nla_nest_start(skb, MACSEC_SA_ATTR_STATS);
+			attr = nla_nest_start_noflag(skb,
+						     MACSEC_SA_ATTR_STATS);
 			if (!attr) {
 				nla_nest_cancel(skb, rxsa_list);
 				nla_nest_cancel(skb, rxsc_nest);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 4a6be8fab884..b395423b19bc 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1624,7 +1624,7 @@ static int macvlan_fill_info(struct sk_buff *skb,
 	if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count))
 		goto nla_put_failure;
 	if (vlan->macaddr_count > 0) {
-		nest = nla_nest_start(skb, IFLA_MACVLAN_MACADDR_DATA);
+		nest = nla_nest_start_noflag(skb, IFLA_MACVLAN_MACADDR_DATA);
 		if (nest == NULL)
 			goto nla_put_failure;
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index eb4711bfc52a..6306897c147f 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2290,7 +2290,7 @@ static int team_nl_fill_one_option_get(struct sk_buff *skb, struct team *team,
 	if (err)
 		return err;
 
-	option_item = nla_nest_start(skb, TEAM_ATTR_ITEM_OPTION);
+	option_item = nla_nest_start_noflag(skb, TEAM_ATTR_ITEM_OPTION);
 	if (!option_item)
 		return -EMSGSIZE;
 
@@ -2404,7 +2404,7 @@ start_again:
 
 	if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex))
 		goto nla_put_failure;
-	option_list = nla_nest_start(skb, TEAM_ATTR_LIST_OPTION);
+	option_list = nla_nest_start_noflag(skb, TEAM_ATTR_LIST_OPTION);
 	if (!option_list)
 		goto nla_put_failure;
 
@@ -2626,7 +2626,7 @@ static int team_nl_fill_one_port_get(struct sk_buff *skb,
 {
 	struct nlattr *port_item;
 
-	port_item = nla_nest_start(skb, TEAM_ATTR_ITEM_PORT);
+	port_item = nla_nest_start_noflag(skb, TEAM_ATTR_ITEM_PORT);
 	if (!port_item)
 		goto nest_cancel;
 	if (nla_put_u32(skb, TEAM_ATTR_PORT_IFINDEX, port->dev->ifindex))
@@ -2681,7 +2681,7 @@ start_again:
 
 	if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex))
 		goto nla_put_failure;
-	port_list = nla_nest_start(skb, TEAM_ATTR_LIST_PORT);
+	port_list = nla_nest_start_noflag(skb, TEAM_ATTR_LIST_PORT);
 	if (!port_list)
 		goto nla_put_failure;
 
diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index a1e226652b4a..cac18e61474e 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -2679,13 +2679,13 @@ static int wil_rf_sector_get_cfg(struct wiphy *wiphy,
 			      QCA_ATTR_PAD))
 		goto nla_put_failure;
 
-	nl_cfgs = nla_nest_start(msg, QCA_ATTR_DMG_RF_SECTOR_CFG);
+	nl_cfgs = nla_nest_start_noflag(msg, QCA_ATTR_DMG_RF_SECTOR_CFG);
 	if (!nl_cfgs)
 		goto nla_put_failure;
 	for (i = 0; i < WMI_MAX_RF_MODULES_NUM; i++) {
 		if (!(rf_modules_vec & BIT(i)))
 			continue;
-		nl_cfg = nla_nest_start(msg, i);
+		nl_cfg = nla_nest_start_noflag(msg, i);
 		if (!nl_cfg)
 			goto nla_put_failure;
 		si = &reply.evt.sectors_info[i];
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index f2e1e6b13ca4..965dc6c6653e 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -401,7 +401,7 @@ ip_set_get_h16(const struct nlattr *attr)
 	return ntohs(nla_get_be16(attr));
 }
 
-#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr | NLA_F_NESTED)
+#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr)
 #define ipset_nest_end(skb, start)  nla_nest_end(skb, start)
 
 static inline int nla_put_ipaddr4(struct sk_buff *skb, int type, __be32 ipaddr)
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 23f27b0b3cef..1f18b47f41b4 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1415,13 +1415,18 @@ static inline void *nla_memdup(const struct nlattr *src, gfp_t gfp)
 }
 
 /**
- * nla_nest_start - Start a new level of nested attributes
+ * nla_nest_start_noflag - Start a new level of nested attributes
  * @skb: socket buffer to add attributes to
  * @attrtype: attribute type of container
  *
- * Returns the container attribute
+ * This function exists for backward compatibility to use in APIs which never
+ * marked their nest attributes with NLA_F_NESTED flag. New APIs should use
+ * nla_nest_start() which sets the flag.
+ *
+ * Returns the container attribute or NULL on error
  */
-static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype)
+static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb,
+						   int attrtype)
 {
 	struct nlattr *start = (struct nlattr *)skb_tail_pointer(skb);
 
@@ -1431,6 +1436,21 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype)
 	return start;
 }
 
+/**
+ * nla_nest_start - Start a new level of nested attributes, with NLA_F_NESTED
+ * @skb: socket buffer to add attributes to
+ * @attrtype: attribute type of container
+ *
+ * Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED
+ * flag. This is the preferred function to use in new code.
+ *
+ * Returns the container attribute or NULL on error
+ */
+static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype)
+{
+	return nla_nest_start_noflag(skb, attrtype | NLA_F_NESTED);
+}
+
 /**
  * nla_nest_end - Finalize nesting of attributes
  * @skb: socket buffer the attributes are stored in
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 1b942a7caf26..ef4f9cd980fd 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -375,7 +375,7 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
 			? TASKSTATS_TYPE_AGGR_PID
 			: TASKSTATS_TYPE_AGGR_TGID;
 
-	na = nla_nest_start(skb, aggr);
+	na = nla_nest_start_noflag(skb, aggr);
 	if (!na)
 		goto err;
 
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index a624dccf68fd..ab4921e7797b 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -227,7 +227,7 @@ static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			goto nla_put_failure;
 	}
 	if (vlan->nr_ingress_mappings) {
-		nest = nla_nest_start(skb, IFLA_VLAN_INGRESS_QOS);
+		nest = nla_nest_start_noflag(skb, IFLA_VLAN_INGRESS_QOS);
 		if (nest == NULL)
 			goto nla_put_failure;
 
@@ -245,7 +245,7 @@ static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	}
 
 	if (vlan->nr_egress_mappings) {
-		nest = nla_nest_start(skb, IFLA_VLAN_EGRESS_QOS);
+		nest = nla_nest_start_noflag(skb, IFLA_VLAN_EGRESS_QOS);
 		if (nest == NULL)
 			goto nla_put_failure;
 
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index f69c8d91dc81..3619c1a12a77 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -26,14 +26,14 @@ static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 	if (!br->multicast_router || hlist_empty(&br->router_list))
 		return 0;
 
-	nest = nla_nest_start(skb, MDBA_ROUTER);
+	nest = nla_nest_start_noflag(skb, MDBA_ROUTER);
 	if (nest == NULL)
 		return -EMSGSIZE;
 
 	hlist_for_each_entry_rcu(p, &br->router_list, rlist) {
 		if (!p)
 			continue;
-		port_nest = nla_nest_start(skb, MDBA_ROUTER_PORT);
+		port_nest = nla_nest_start_noflag(skb, MDBA_ROUTER_PORT);
 		if (!port_nest)
 			goto fail;
 		if (nla_put_nohdr(skb, sizeof(u32), &p->dev->ifindex) ||
@@ -86,7 +86,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED))
 		return 0;
 
-	nest = nla_nest_start(skb, MDBA_MDB);
+	nest = nla_nest_start_noflag(skb, MDBA_MDB);
 	if (nest == NULL)
 		return -EMSGSIZE;
 
@@ -98,7 +98,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 		if (idx < s_idx)
 			goto skip;
 
-		nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
+		nest2 = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY);
 		if (!nest2) {
 			err = -EMSGSIZE;
 			break;
@@ -124,7 +124,8 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 				e.addr.u.ip6 = p->addr.u.ip6;
 #endif
 			e.addr.proto = p->addr.proto;
-			nest_ent = nla_nest_start(skb, MDBA_MDB_ENTRY_INFO);
+			nest_ent = nla_nest_start_noflag(skb,
+							 MDBA_MDB_ENTRY_INFO);
 			if (!nest_ent) {
 				nla_nest_cancel(skb, nest2);
 				err = -EMSGSIZE;
@@ -248,10 +249,10 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb,
 	memset(bpm, 0, sizeof(*bpm));
 	bpm->family  = AF_BRIDGE;
 	bpm->ifindex = dev->ifindex;
-	nest = nla_nest_start(skb, MDBA_MDB);
+	nest = nla_nest_start_noflag(skb, MDBA_MDB);
 	if (nest == NULL)
 		goto cancel;
-	nest2 = nla_nest_start(skb, MDBA_MDB_ENTRY);
+	nest2 = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY);
 	if (nest2 == NULL)
 		goto end;
 
@@ -444,7 +445,7 @@ static int nlmsg_populate_rtr_fill(struct sk_buff *skb,
 	memset(bpm, 0, sizeof(*bpm));
 	bpm->family = AF_BRIDGE;
 	bpm->ifindex = dev->ifindex;
-	nest = nla_nest_start(skb, MDBA_ROUTER);
+	nest = nla_nest_start_noflag(skb, MDBA_ROUTER);
 	if (!nest)
 		goto cancel;
 
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 8dfcc2d285d8..0914477c4719 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -414,7 +414,7 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 
 	if (event == RTM_NEWLINK && port) {
 		struct nlattr *nest
-			= nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
+			= nla_nest_start(skb, IFLA_PROTINFO);
 
 		if (nest == NULL || br_port_fill_attrs(skb, port) < 0)
 			goto nla_put_failure;
@@ -439,7 +439,7 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 			rcu_read_unlock();
 			goto done;
 		}
-		af = nla_nest_start(skb, IFLA_AF_SPEC);
+		af = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
 		if (!af) {
 			rcu_read_unlock();
 			goto nla_put_failure;
@@ -1569,7 +1569,7 @@ static int br_fill_linkxstats(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-	nest = nla_nest_start(skb, LINK_XSTATS_TYPE_BRIDGE);
+	nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BRIDGE);
 	if (!nest)
 		return -EMSGSIZE;
 
diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c
index da8cb99fd259..787e140dc4b5 100644
--- a/net/bridge/br_netlink_tunnel.c
+++ b/net/bridge/br_netlink_tunnel.c
@@ -97,7 +97,7 @@ static int br_fill_vlan_tinfo(struct sk_buff *skb, u16 vid,
 	__be32 tid = tunnel_id_to_key32(tunnel_id);
 	struct nlattr *tmap;
 
-	tmap = nla_nest_start(skb, IFLA_BRIDGE_VLAN_TUNNEL_INFO);
+	tmap = nla_nest_start_noflag(skb, IFLA_BRIDGE_VLAN_TUNNEL_INFO);
 	if (!tmap)
 		return -EMSGSIZE;
 	if (nla_put_u32(skb, IFLA_BRIDGE_VLAN_TUNNEL_ID,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 7b91605e75d6..b94f326f5f06 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1671,7 +1671,7 @@ int devlink_dpipe_match_put(struct sk_buff *skb,
 	struct devlink_dpipe_field *field = &header->fields[match->field_id];
 	struct nlattr *match_attr;
 
-	match_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_MATCH);
+	match_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_MATCH);
 	if (!match_attr)
 		return -EMSGSIZE;
 
@@ -1696,7 +1696,8 @@ static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table,
 {
 	struct nlattr *matches_attr;
 
-	matches_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_MATCHES);
+	matches_attr = nla_nest_start_noflag(skb,
+					     DEVLINK_ATTR_DPIPE_TABLE_MATCHES);
 	if (!matches_attr)
 		return -EMSGSIZE;
 
@@ -1718,7 +1719,7 @@ int devlink_dpipe_action_put(struct sk_buff *skb,
 	struct devlink_dpipe_field *field = &header->fields[action->field_id];
 	struct nlattr *action_attr;
 
-	action_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ACTION);
+	action_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ACTION);
 	if (!action_attr)
 		return -EMSGSIZE;
 
@@ -1743,7 +1744,8 @@ static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table,
 {
 	struct nlattr *actions_attr;
 
-	actions_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_ACTIONS);
+	actions_attr = nla_nest_start_noflag(skb,
+					     DEVLINK_ATTR_DPIPE_TABLE_ACTIONS);
 	if (!actions_attr)
 		return -EMSGSIZE;
 
@@ -1765,7 +1767,7 @@ static int devlink_dpipe_table_put(struct sk_buff *skb,
 	u64 table_size;
 
 	table_size = table->table_ops->size_get(table->priv);
-	table_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE);
+	table_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLE);
 	if (!table_attr)
 		return -EMSGSIZE;
 
@@ -1845,7 +1847,7 @@ start_again:
 
 	if (devlink_nl_put_handle(skb, devlink))
 		goto nla_put_failure;
-	tables_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLES);
+	tables_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_TABLES);
 	if (!tables_attr)
 		goto nla_put_failure;
 
@@ -1946,8 +1948,8 @@ static int devlink_dpipe_action_values_put(struct sk_buff *skb,
 	int err;
 
 	for (i = 0; i < values_count; i++) {
-		action_attr = nla_nest_start(skb,
-					     DEVLINK_ATTR_DPIPE_ACTION_VALUE);
+		action_attr = nla_nest_start_noflag(skb,
+						    DEVLINK_ATTR_DPIPE_ACTION_VALUE);
 		if (!action_attr)
 			return -EMSGSIZE;
 		err = devlink_dpipe_action_value_put(skb, &values[i]);
@@ -1983,8 +1985,8 @@ static int devlink_dpipe_match_values_put(struct sk_buff *skb,
 	int err;
 
 	for (i = 0; i < values_count; i++) {
-		match_attr = nla_nest_start(skb,
-					    DEVLINK_ATTR_DPIPE_MATCH_VALUE);
+		match_attr = nla_nest_start_noflag(skb,
+						   DEVLINK_ATTR_DPIPE_MATCH_VALUE);
 		if (!match_attr)
 			return -EMSGSIZE;
 		err = devlink_dpipe_match_value_put(skb, &values[i]);
@@ -2005,7 +2007,7 @@ static int devlink_dpipe_entry_put(struct sk_buff *skb,
 	struct nlattr *entry_attr, *matches_attr, *actions_attr;
 	int err;
 
-	entry_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ENTRY);
+	entry_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_ENTRY);
 	if (!entry_attr)
 		return  -EMSGSIZE;
 
@@ -2017,8 +2019,8 @@ static int devlink_dpipe_entry_put(struct sk_buff *skb,
 				      entry->counter, DEVLINK_ATTR_PAD))
 			goto nla_put_failure;
 
-	matches_attr = nla_nest_start(skb,
-				      DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES);
+	matches_attr = nla_nest_start_noflag(skb,
+					     DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES);
 	if (!matches_attr)
 		goto nla_put_failure;
 
@@ -2030,8 +2032,8 @@ static int devlink_dpipe_entry_put(struct sk_buff *skb,
 	}
 	nla_nest_end(skb, matches_attr);
 
-	actions_attr = nla_nest_start(skb,
-				      DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES);
+	actions_attr = nla_nest_start_noflag(skb,
+					     DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES);
 	if (!actions_attr)
 		goto nla_put_failure;
 
@@ -2088,8 +2090,8 @@ int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx)
 	devlink = dump_ctx->info->user_ptr[0];
 	if (devlink_nl_put_handle(dump_ctx->skb, devlink))
 		goto nla_put_failure;
-	dump_ctx->nest = nla_nest_start(dump_ctx->skb,
-					DEVLINK_ATTR_DPIPE_ENTRIES);
+	dump_ctx->nest = nla_nest_start_noflag(dump_ctx->skb,
+					       DEVLINK_ATTR_DPIPE_ENTRIES);
 	if (!dump_ctx->nest)
 		goto nla_put_failure;
 	return 0;
@@ -2199,7 +2201,8 @@ static int devlink_dpipe_fields_put(struct sk_buff *skb,
 
 	for (i = 0; i < header->fields_count; i++) {
 		field = &header->fields[i];
-		field_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_FIELD);
+		field_attr = nla_nest_start_noflag(skb,
+						   DEVLINK_ATTR_DPIPE_FIELD);
 		if (!field_attr)
 			return -EMSGSIZE;
 		if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) ||
@@ -2222,7 +2225,7 @@ static int devlink_dpipe_header_put(struct sk_buff *skb,
 	struct nlattr *fields_attr, *header_attr;
 	int err;
 
-	header_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER);
+	header_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADER);
 	if (!header_attr)
 		return -EMSGSIZE;
 
@@ -2231,7 +2234,8 @@ static int devlink_dpipe_header_put(struct sk_buff *skb,
 	    nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global))
 		goto nla_put_failure;
 
-	fields_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER_FIELDS);
+	fields_attr = nla_nest_start_noflag(skb,
+					    DEVLINK_ATTR_DPIPE_HEADER_FIELDS);
 	if (!fields_attr)
 		goto nla_put_failure;
 
@@ -2278,7 +2282,7 @@ start_again:
 
 	if (devlink_nl_put_handle(skb, devlink))
 		goto nla_put_failure;
-	headers_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADERS);
+	headers_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_DPIPE_HEADERS);
 	if (!headers_attr)
 		goto nla_put_failure;
 
@@ -2502,7 +2506,7 @@ static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb,
 	struct nlattr *child_resource_attr;
 	struct nlattr *resource_attr;
 
-	resource_attr = nla_nest_start(skb, DEVLINK_ATTR_RESOURCE);
+	resource_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_RESOURCE);
 	if (!resource_attr)
 		return -EMSGSIZE;
 
@@ -2526,7 +2530,8 @@ static int devlink_resource_put(struct devlink *devlink, struct sk_buff *skb,
 		       resource->size_valid))
 		goto nla_put_failure;
 
-	child_resource_attr = nla_nest_start(skb, DEVLINK_ATTR_RESOURCE_LIST);
+	child_resource_attr = nla_nest_start_noflag(skb,
+						    DEVLINK_ATTR_RESOURCE_LIST);
 	if (!child_resource_attr)
 		goto nla_put_failure;
 
@@ -2577,7 +2582,8 @@ start_again:
 	if (devlink_nl_put_handle(skb, devlink))
 		goto nla_put_failure;
 
-	resources_attr = nla_nest_start(skb, DEVLINK_ATTR_RESOURCE_LIST);
+	resources_attr = nla_nest_start_noflag(skb,
+					       DEVLINK_ATTR_RESOURCE_LIST);
 	if (!resources_attr)
 		goto nla_put_failure;
 
@@ -2831,7 +2837,8 @@ devlink_nl_param_value_fill_one(struct sk_buff *msg,
 {
 	struct nlattr *param_value_attr;
 
-	param_value_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM_VALUE);
+	param_value_attr = nla_nest_start_noflag(msg,
+						 DEVLINK_ATTR_PARAM_VALUE);
 	if (!param_value_attr)
 		goto nla_put_failure;
 
@@ -2922,7 +2929,7 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
 		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index))
 			goto genlmsg_cancel;
 
-	param_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM);
+	param_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_PARAM);
 	if (!param_attr)
 		goto genlmsg_cancel;
 	if (nla_put_string(msg, DEVLINK_ATTR_PARAM_NAME, param->name))
@@ -2936,7 +2943,8 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type))
 		goto param_nest_cancel;
 
-	param_values_list = nla_nest_start(msg, DEVLINK_ATTR_PARAM_VALUES_LIST);
+	param_values_list = nla_nest_start_noflag(msg,
+						  DEVLINK_ATTR_PARAM_VALUES_LIST);
 	if (!param_values_list)
 		goto param_nest_cancel;
 
@@ -3336,7 +3344,7 @@ static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg,
 	struct nlattr *snap_attr;
 	int err;
 
-	snap_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOT);
+	snap_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOT);
 	if (!snap_attr)
 		return -EINVAL;
 
@@ -3360,7 +3368,8 @@ static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg,
 	struct nlattr *snapshots_attr;
 	int err;
 
-	snapshots_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOTS);
+	snapshots_attr = nla_nest_start_noflag(msg,
+					       DEVLINK_ATTR_REGION_SNAPSHOTS);
 	if (!snapshots_attr)
 		return -EINVAL;
 
@@ -3576,7 +3585,7 @@ static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg,
 	struct nlattr *chunk_attr;
 	int err;
 
-	chunk_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_CHUNK);
+	chunk_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_CHUNK);
 	if (!chunk_attr)
 		return -EINVAL;
 
@@ -3709,7 +3718,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 	if (err)
 		goto nla_put_failure;
 
-	chunks_attr = nla_nest_start(skb, DEVLINK_ATTR_REGION_CHUNKS);
+	chunks_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_REGION_CHUNKS);
 	if (!chunks_attr) {
 		err = -EMSGSIZE;
 		goto nla_put_failure;
@@ -3785,7 +3794,7 @@ static int devlink_info_version_put(struct devlink_info_req *req, int attr,
 	struct nlattr *nest;
 	int err;
 
-	nest = nla_nest_start(req->msg, attr);
+	nest = nla_nest_start_noflag(req->msg, attr);
 	if (!nest)
 		return -EMSGSIZE;
 
@@ -4313,7 +4322,7 @@ devlink_fmsg_prepare_skb(struct devlink_fmsg *fmsg, struct sk_buff *skb,
 	int i = 0;
 	int err;
 
-	fmsg_nlattr = nla_nest_start(skb, DEVLINK_ATTR_FMSG);
+	fmsg_nlattr = nla_nest_start_noflag(skb, DEVLINK_ATTR_FMSG);
 	if (!fmsg_nlattr)
 		return -EMSGSIZE;
 
@@ -4665,7 +4674,8 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg,
 	if (devlink_nl_put_handle(msg, devlink))
 		goto genlmsg_cancel;
 
-	reporter_attr = nla_nest_start(msg, DEVLINK_ATTR_HEALTH_REPORTER);
+	reporter_attr = nla_nest_start_noflag(msg,
+					      DEVLINK_ATTR_HEALTH_REPORTER);
 	if (!reporter_attr)
 		goto genlmsg_cancel;
 	if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME,
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 3c5c24a5d9f5..bbdfc8db1960 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -453,7 +453,7 @@ static int bpf_fill_lwt_prog(struct sk_buff *skb, int attr,
 	if (!prog->prog)
 		return 0;
 
-	nest = nla_nest_start(skb, attr);
+	nest = nla_nest_start_noflag(skb, attr);
 	if (!nest)
 		return -EMSGSIZE;
 
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 94749e0e2cfd..69e249fbc02f 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -237,7 +237,7 @@ int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate,
 	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
 		return 0;
 
-	nest = nla_nest_start(skb, encap_attr);
+	nest = nla_nest_start_noflag(skb, encap_attr);
 	if (!nest)
 		return -EMSGSIZE;
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 997cfa8f99ba..efd0b53d9ca4 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1979,7 +1979,7 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
 {
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, NDTA_PARMS);
+	nest = nla_nest_start_noflag(skb, NDTA_PARMS);
 	if (nest == NULL)
 		return -ENOBUFS;
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5fa5bf3e9945..8ad44b299e72 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -634,7 +634,7 @@ static int rtnl_link_slave_info_fill(struct sk_buff *skb,
 	if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0)
 		return -EMSGSIZE;
 	if (ops->fill_slave_info) {
-		slave_data = nla_nest_start(skb, IFLA_INFO_SLAVE_DATA);
+		slave_data = nla_nest_start_noflag(skb, IFLA_INFO_SLAVE_DATA);
 		if (!slave_data)
 			return -EMSGSIZE;
 		err = ops->fill_slave_info(skb, master_dev, dev);
@@ -666,7 +666,7 @@ static int rtnl_link_info_fill(struct sk_buff *skb,
 			return err;
 	}
 	if (ops->fill_info) {
-		data = nla_nest_start(skb, IFLA_INFO_DATA);
+		data = nla_nest_start_noflag(skb, IFLA_INFO_DATA);
 		if (data == NULL)
 			return -EMSGSIZE;
 		err = ops->fill_info(skb, dev);
@@ -686,7 +686,7 @@ static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev)
 	struct nlattr *linkinfo;
 	int err = -EMSGSIZE;
 
-	linkinfo = nla_nest_start(skb, IFLA_LINKINFO);
+	linkinfo = nla_nest_start_noflag(skb, IFLA_LINKINFO);
 	if (linkinfo == NULL)
 		goto out;
 
@@ -755,7 +755,7 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
 	struct nlattr *mx;
 	int i, valid = 0;
 
-	mx = nla_nest_start(skb, RTA_METRICS);
+	mx = nla_nest_start_noflag(skb, RTA_METRICS);
 	if (mx == NULL)
 		return -ENOBUFS;
 
@@ -1036,12 +1036,12 @@ static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
 	int vf;
 	int err;
 
-	vf_ports = nla_nest_start(skb, IFLA_VF_PORTS);
+	vf_ports = nla_nest_start_noflag(skb, IFLA_VF_PORTS);
 	if (!vf_ports)
 		return -EMSGSIZE;
 
 	for (vf = 0; vf < dev_num_vf(dev->dev.parent); vf++) {
-		vf_port = nla_nest_start(skb, IFLA_VF_PORT);
+		vf_port = nla_nest_start_noflag(skb, IFLA_VF_PORT);
 		if (!vf_port)
 			goto nla_put_failure;
 		if (nla_put_u32(skb, IFLA_PORT_VF, vf))
@@ -1070,7 +1070,7 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev)
 	struct nlattr *port_self;
 	int err;
 
-	port_self = nla_nest_start(skb, IFLA_PORT_SELF);
+	port_self = nla_nest_start_noflag(skb, IFLA_PORT_SELF);
 	if (!port_self)
 		return -EMSGSIZE;
 
@@ -1247,7 +1247,7 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	vf_linkstate.link_state = ivi.linkstate;
 	vf_rss_query_en.setting = ivi.rss_query_en;
 	vf_trust.setting = ivi.trusted;
-	vf = nla_nest_start(skb, IFLA_VF_INFO);
+	vf = nla_nest_start_noflag(skb, IFLA_VF_INFO);
 	if (!vf)
 		goto nla_put_vfinfo_failure;
 	if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) ||
@@ -1266,7 +1266,7 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	    nla_put(skb, IFLA_VF_TRUST,
 		    sizeof(vf_trust), &vf_trust))
 		goto nla_put_vf_failure;
-	vfvlanlist = nla_nest_start(skb, IFLA_VF_VLAN_LIST);
+	vfvlanlist = nla_nest_start_noflag(skb, IFLA_VF_VLAN_LIST);
 	if (!vfvlanlist)
 		goto nla_put_vf_failure;
 	if (nla_put(skb, IFLA_VF_VLAN_INFO, sizeof(vf_vlan_info),
@@ -1279,7 +1279,7 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	if (dev->netdev_ops->ndo_get_vf_stats)
 		dev->netdev_ops->ndo_get_vf_stats(dev, vfs_num,
 						&vf_stats);
-	vfstats = nla_nest_start(skb, IFLA_VF_STATS);
+	vfstats = nla_nest_start_noflag(skb, IFLA_VF_STATS);
 	if (!vfstats)
 		goto nla_put_vf_failure;
 	if (nla_put_u64_64bit(skb, IFLA_VF_STATS_RX_PACKETS,
@@ -1329,7 +1329,7 @@ static noinline_for_stack int rtnl_fill_vf(struct sk_buff *skb,
 	if (!dev->netdev_ops->ndo_get_vf_config)
 		return 0;
 
-	vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST);
+	vfinfo = nla_nest_start_noflag(skb, IFLA_VFINFO_LIST);
 	if (!vfinfo)
 		return -EMSGSIZE;
 
@@ -1414,7 +1414,7 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 	int err;
 	u8 mode;
 
-	xdp = nla_nest_start(skb, IFLA_XDP);
+	xdp = nla_nest_start_noflag(skb, IFLA_XDP);
 	if (!xdp)
 		return -EMSGSIZE;
 
@@ -1541,7 +1541,7 @@ static int rtnl_fill_link_af(struct sk_buff *skb,
 	const struct rtnl_af_ops *af_ops;
 	struct nlattr *af_spec;
 
-	af_spec = nla_nest_start(skb, IFLA_AF_SPEC);
+	af_spec = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
 	if (!af_spec)
 		return -EMSGSIZE;
 
@@ -1552,7 +1552,7 @@ static int rtnl_fill_link_af(struct sk_buff *skb,
 		if (!af_ops->fill_link_af)
 			continue;
 
-		af = nla_nest_start(skb, af_ops->family);
+		af = nla_nest_start_noflag(skb, af_ops->family);
 		if (!af)
 			return -EMSGSIZE;
 
@@ -4273,7 +4273,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	     nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))))
 		goto nla_put_failure;
 
-	br_afspec = nla_nest_start(skb, IFLA_AF_SPEC);
+	br_afspec = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
 	if (!br_afspec)
 		goto nla_put_failure;
 
@@ -4297,7 +4297,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	}
 	nla_nest_end(skb, br_afspec);
 
-	protinfo = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED);
+	protinfo = nla_nest_start(skb, IFLA_PROTINFO);
 	if (!protinfo)
 		goto nla_put_failure;
 
@@ -4776,8 +4776,8 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
 
 		if (ops && ops->fill_linkxstats) {
 			*idxattr = IFLA_STATS_LINK_XSTATS;
-			attr = nla_nest_start(skb,
-					      IFLA_STATS_LINK_XSTATS);
+			attr = nla_nest_start_noflag(skb,
+						     IFLA_STATS_LINK_XSTATS);
 			if (!attr)
 				goto nla_put_failure;
 
@@ -4799,8 +4799,8 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
 			ops = master->rtnl_link_ops;
 		if (ops && ops->fill_linkxstats) {
 			*idxattr = IFLA_STATS_LINK_XSTATS_SLAVE;
-			attr = nla_nest_start(skb,
-					      IFLA_STATS_LINK_XSTATS_SLAVE);
+			attr = nla_nest_start_noflag(skb,
+						     IFLA_STATS_LINK_XSTATS_SLAVE);
 			if (!attr)
 				goto nla_put_failure;
 
@@ -4815,7 +4815,8 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
 	if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_OFFLOAD_XSTATS,
 			     *idxattr)) {
 		*idxattr = IFLA_STATS_LINK_OFFLOAD_XSTATS;
-		attr = nla_nest_start(skb, IFLA_STATS_LINK_OFFLOAD_XSTATS);
+		attr = nla_nest_start_noflag(skb,
+					     IFLA_STATS_LINK_OFFLOAD_XSTATS);
 		if (!attr)
 			goto nla_put_failure;
 
@@ -4834,7 +4835,7 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
 		struct rtnl_af_ops *af_ops;
 
 		*idxattr = IFLA_STATS_AF_SPEC;
-		attr = nla_nest_start(skb, IFLA_STATS_AF_SPEC);
+		attr = nla_nest_start_noflag(skb, IFLA_STATS_AF_SPEC);
 		if (!attr)
 			goto nla_put_failure;
 
@@ -4844,7 +4845,8 @@ static int rtnl_fill_statsinfo(struct sk_buff *skb, struct net_device *dev,
 				struct nlattr *af;
 				int err;
 
-				af = nla_nest_start(skb, af_ops->family);
+				af = nla_nest_start_noflag(skb,
+							   af_ops->family);
 				if (!af) {
 					rcu_read_unlock();
 					goto nla_put_failure;
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index a556cd708885..3fd3aa7348bd 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -246,7 +246,7 @@ static int dcbnl_getpfccfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (ret)
 		return ret;
 
-	nest = nla_nest_start(skb, DCB_ATTR_PFC_CFG);
+	nest = nla_nest_start_noflag(skb, DCB_ATTR_PFC_CFG);
 	if (!nest)
 		return -EMSGSIZE;
 
@@ -304,7 +304,7 @@ static int dcbnl_getcap(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (ret)
 		return ret;
 
-	nest = nla_nest_start(skb, DCB_ATTR_CAP);
+	nest = nla_nest_start_noflag(skb, DCB_ATTR_CAP);
 	if (!nest)
 		return -EMSGSIZE;
 
@@ -348,7 +348,7 @@ static int dcbnl_getnumtcs(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (ret)
 		return ret;
 
-	nest = nla_nest_start(skb, DCB_ATTR_NUMTCS);
+	nest = nla_nest_start_noflag(skb, DCB_ATTR_NUMTCS);
 	if (!nest)
 		return -EMSGSIZE;
 
@@ -479,7 +479,7 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh,
 		up = dcb_getapp(netdev, &app);
 	}
 
-	app_nest = nla_nest_start(skb, DCB_ATTR_APP);
+	app_nest = nla_nest_start_noflag(skb, DCB_ATTR_APP);
 	if (!app_nest)
 		return -EMSGSIZE;
 
@@ -578,7 +578,7 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (ret)
 		return ret;
 
-	pg_nest = nla_nest_start(skb, DCB_ATTR_PG_CFG);
+	pg_nest = nla_nest_start_noflag(skb, DCB_ATTR_PG_CFG);
 	if (!pg_nest)
 		return -EMSGSIZE;
 
@@ -598,7 +598,7 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 		if (ret)
 			goto err_pg;
 
-		param_nest = nla_nest_start(skb, i);
+		param_nest = nla_nest_start_noflag(skb, i);
 		if (!param_nest)
 			goto err_pg;
 
@@ -889,7 +889,7 @@ static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (ret)
 		return ret;
 
-	bcn_nest = nla_nest_start(skb, DCB_ATTR_BCN);
+	bcn_nest = nla_nest_start_noflag(skb, DCB_ATTR_BCN);
 	if (!bcn_nest)
 		return -EMSGSIZE;
 
@@ -1002,7 +1002,7 @@ static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb,
 		 */
 		err = -EMSGSIZE;
 
-		app = nla_nest_start(skb, app_nested_type);
+		app = nla_nest_start_noflag(skb, app_nested_type);
 		if (!app)
 			goto nla_put_failure;
 
@@ -1036,7 +1036,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev)
 	if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name))
 		return -EMSGSIZE;
 
-	ieee = nla_nest_start(skb, DCB_ATTR_IEEE);
+	ieee = nla_nest_start_noflag(skb, DCB_ATTR_IEEE);
 	if (!ieee)
 		return -EMSGSIZE;
 
@@ -1106,7 +1106,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev)
 			return -EMSGSIZE;
 	}
 
-	app = nla_nest_start(skb, DCB_ATTR_IEEE_APP_TABLE);
+	app = nla_nest_start_noflag(skb, DCB_ATTR_IEEE_APP_TABLE);
 	if (!app)
 		return -EMSGSIZE;
 
@@ -1174,13 +1174,13 @@ static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev,
 	u8 pgid, up_map, prio, tc_pct;
 	const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops;
 	int i = dir ? DCB_ATTR_CEE_TX_PG : DCB_ATTR_CEE_RX_PG;
-	struct nlattr *pg = nla_nest_start(skb, i);
+	struct nlattr *pg = nla_nest_start_noflag(skb, i);
 
 	if (!pg)
 		return -EMSGSIZE;
 
 	for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) {
-		struct nlattr *tc_nest = nla_nest_start(skb, i);
+		struct nlattr *tc_nest = nla_nest_start_noflag(skb, i);
 
 		if (!tc_nest)
 			return -EMSGSIZE;
@@ -1231,7 +1231,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev)
 
 	if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name))
 		goto nla_put_failure;
-	cee = nla_nest_start(skb, DCB_ATTR_CEE);
+	cee = nla_nest_start_noflag(skb, DCB_ATTR_CEE);
 	if (!cee)
 		goto nla_put_failure;
 
@@ -1250,7 +1250,8 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev)
 
 	/* local pfc */
 	if (ops->getpfccfg) {
-		struct nlattr *pfc_nest = nla_nest_start(skb, DCB_ATTR_CEE_PFC);
+		struct nlattr *pfc_nest = nla_nest_start_noflag(skb,
+								DCB_ATTR_CEE_PFC);
 
 		if (!pfc_nest)
 			goto nla_put_failure;
@@ -1265,14 +1266,14 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev)
 
 	/* local app */
 	spin_lock_bh(&dcb_lock);
-	app = nla_nest_start(skb, DCB_ATTR_CEE_APP_TABLE);
+	app = nla_nest_start_noflag(skb, DCB_ATTR_CEE_APP_TABLE);
 	if (!app)
 		goto dcb_unlock;
 
 	list_for_each_entry(itr, &dcb_app_list, list) {
 		if (itr->ifindex == netdev->ifindex) {
-			struct nlattr *app_nest = nla_nest_start(skb,
-								 DCB_ATTR_APP);
+			struct nlattr *app_nest = nla_nest_start_noflag(skb,
+									DCB_ATTR_APP);
 			if (!app_nest)
 				goto dcb_unlock;
 
@@ -1305,7 +1306,8 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev)
 
 	/* features flags */
 	if (ops->getfeatcfg) {
-		struct nlattr *feat = nla_nest_start(skb, DCB_ATTR_CEE_FEAT);
+		struct nlattr *feat = nla_nest_start_noflag(skb,
+							    DCB_ATTR_CEE_FEAT);
 		if (!feat)
 			goto nla_put_failure;
 
@@ -1607,7 +1609,7 @@ static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (ret)
 		return ret;
 
-	nest = nla_nest_start(skb, DCB_ATTR_FEATCFG);
+	nest = nla_nest_start_noflag(skb, DCB_ATTR_FEATCFG);
 	if (!nest)
 		return -EMSGSIZE;
 
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index f0710b5d037d..2fb764321b97 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -348,7 +348,7 @@ static int dn_fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		struct rtnexthop *nhp;
 		struct nlattr *mp_head;
 
-		if (!(mp_head = nla_nest_start(skb, RTA_MULTIPATH)))
+		if (!(mp_head = nla_nest_start_noflag(skb, RTA_MULTIPATH)))
 			goto errout;
 
 		for_nexthops(fi) {
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 308370cfd668..1a002eb85096 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -312,7 +312,7 @@ static inline void *nl802154hdr_put(struct sk_buff *skb, u32 portid, u32 seq,
 static int
 nl802154_put_flags(struct sk_buff *msg, int attr, u32 mask)
 {
-	struct nlattr *nl_flags = nla_nest_start(msg, attr);
+	struct nlattr *nl_flags = nla_nest_start_noflag(msg, attr);
 	int i;
 
 	if (!nl_flags)
@@ -338,7 +338,7 @@ nl802154_send_wpan_phy_channels(struct cfg802154_registered_device *rdev,
 	struct nlattr *nl_page;
 	unsigned long page;
 
-	nl_page = nla_nest_start(msg, NL802154_ATTR_CHANNELS_SUPPORTED);
+	nl_page = nla_nest_start_noflag(msg, NL802154_ATTR_CHANNELS_SUPPORTED);
 	if (!nl_page)
 		return -ENOBUFS;
 
@@ -360,11 +360,11 @@ nl802154_put_capabilities(struct sk_buff *msg,
 	struct nlattr *nl_caps, *nl_channels;
 	int i;
 
-	nl_caps = nla_nest_start(msg, NL802154_ATTR_WPAN_PHY_CAPS);
+	nl_caps = nla_nest_start_noflag(msg, NL802154_ATTR_WPAN_PHY_CAPS);
 	if (!nl_caps)
 		return -ENOBUFS;
 
-	nl_channels = nla_nest_start(msg, NL802154_CAP_ATTR_CHANNELS);
+	nl_channels = nla_nest_start_noflag(msg, NL802154_CAP_ATTR_CHANNELS);
 	if (!nl_channels)
 		return -ENOBUFS;
 
@@ -380,8 +380,8 @@ nl802154_put_capabilities(struct sk_buff *msg,
 	if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_CCA_ED_LEVEL) {
 		struct nlattr *nl_ed_lvls;
 
-		nl_ed_lvls = nla_nest_start(msg,
-					    NL802154_CAP_ATTR_CCA_ED_LEVELS);
+		nl_ed_lvls = nla_nest_start_noflag(msg,
+						   NL802154_CAP_ATTR_CCA_ED_LEVELS);
 		if (!nl_ed_lvls)
 			return -ENOBUFS;
 
@@ -396,7 +396,8 @@ nl802154_put_capabilities(struct sk_buff *msg,
 	if (rdev->wpan_phy.flags & WPAN_PHY_FLAG_TXPOWER) {
 		struct nlattr *nl_tx_pwrs;
 
-		nl_tx_pwrs = nla_nest_start(msg, NL802154_CAP_ATTR_TX_POWERS);
+		nl_tx_pwrs = nla_nest_start_noflag(msg,
+						   NL802154_CAP_ATTR_TX_POWERS);
 		if (!nl_tx_pwrs)
 			return -ENOBUFS;
 
@@ -504,7 +505,7 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev,
 	if (nl802154_put_capabilities(msg, rdev))
 		goto nla_put_failure;
 
-	nl_cmds = nla_nest_start(msg, NL802154_ATTR_SUPPORTED_COMMANDS);
+	nl_cmds = nla_nest_start_noflag(msg, NL802154_ATTR_SUPPORTED_COMMANDS);
 	if (!nl_cmds)
 		goto nla_put_failure;
 
@@ -693,7 +694,8 @@ ieee802154_llsec_send_key_id(struct sk_buff *msg,
 
 	switch (desc->mode) {
 	case NL802154_KEY_ID_MODE_IMPLICIT:
-		nl_dev_addr = nla_nest_start(msg, NL802154_KEY_ID_ATTR_IMPLICIT);
+		nl_dev_addr = nla_nest_start_noflag(msg,
+						    NL802154_KEY_ID_ATTR_IMPLICIT);
 		if (!nl_dev_addr)
 			return -ENOBUFS;
 
@@ -768,7 +770,7 @@ static int nl802154_get_llsec_params(struct sk_buff *msg,
 			 params.frame_counter))
 		return -ENOBUFS;
 
-	nl_key_id = nla_nest_start(msg, NL802154_ATTR_SEC_OUT_KEY_ID);
+	nl_key_id = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_OUT_KEY_ID);
 	if (!nl_key_id)
 		return -ENOBUFS;
 
@@ -1455,11 +1457,11 @@ static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid,
 	if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
 
-	nl_key = nla_nest_start(msg, NL802154_ATTR_SEC_KEY);
+	nl_key = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_KEY);
 	if (!nl_key)
 		goto nla_put_failure;
 
-	nl_key_id = nla_nest_start(msg, NL802154_KEY_ATTR_ID);
+	nl_key_id = nla_nest_start_noflag(msg, NL802154_KEY_ATTR_ID);
 	if (!nl_key_id)
 		goto nla_put_failure;
 
@@ -1639,7 +1641,7 @@ static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid,
 	if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
 
-	nl_device = nla_nest_start(msg, NL802154_ATTR_SEC_DEVICE);
+	nl_device = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_DEVICE);
 	if (!nl_device)
 		goto nla_put_failure;
 
@@ -1808,7 +1810,7 @@ static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid,
 	if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
 
-	nl_devkey = nla_nest_start(msg, NL802154_ATTR_SEC_DEVKEY);
+	nl_devkey = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_DEVKEY);
 	if (!nl_devkey)
 		goto nla_put_failure;
 
@@ -1818,7 +1820,7 @@ static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid,
 			devkey->frame_counter))
 		goto nla_put_failure;
 
-	nl_key_id = nla_nest_start(msg, NL802154_DEVKEY_ATTR_ID);
+	nl_key_id = nla_nest_start_noflag(msg, NL802154_DEVKEY_ATTR_ID);
 	if (!nl_key_id)
 		goto nla_put_failure;
 
@@ -1976,7 +1978,7 @@ static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid,
 	if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
 
-	nl_seclevel = nla_nest_start(msg, NL802154_ATTR_SEC_LEVEL);
+	nl_seclevel = nla_nest_start_noflag(msg, NL802154_ATTR_SEC_LEVEL);
 	if (!nl_seclevel)
 		goto nla_put_failure;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 4336f1ec8ab0..71c2165a2ce3 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1550,7 +1550,7 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi)
 {
 	struct nlattr *mp;
 
-	mp = nla_nest_start(skb, RTA_MULTIPATH);
+	mp = nla_nest_start_noflag(skb, RTA_MULTIPATH);
 	if (!mp)
 		goto nla_put_failure;
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a8eb97777c0a..1322573b8228 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2783,7 +2783,7 @@ static bool ipmr_fill_vif(struct mr_table *mrt, u32 vifid, struct sk_buff *skb)
 		return true;
 
 	vif = &mrt->vif_table[vifid];
-	vif_nest = nla_nest_start(skb, IPMRA_VIF);
+	vif_nest = nla_nest_start_noflag(skb, IPMRA_VIF);
 	if (!vif_nest)
 		return false;
 	if (nla_put_u32(skb, IPMRA_VIFA_IFINDEX, vif->dev->ifindex) ||
@@ -2867,7 +2867,7 @@ static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb)
 		memset(hdr, 0, sizeof(*hdr));
 		hdr->ifi_family = RTNL_FAMILY_IPMR;
 
-		af = nla_nest_start(skb, IFLA_AF_SPEC);
+		af = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
 		if (!af) {
 			nlmsg_cancel(skb, nlh);
 			goto out;
@@ -2878,7 +2878,7 @@ static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb)
 			goto out;
 		}
 
-		vifs = nla_nest_start(skb, IPMRA_TABLE_VIFS);
+		vifs = nla_nest_start_noflag(skb, IPMRA_TABLE_VIFS);
 		if (!vifs) {
 			nla_nest_end(skb, af);
 			nlmsg_end(skb, nlh);
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index 3e614cc824f7..278834d4babc 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -228,7 +228,7 @@ int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 	if (c->mfc_flags & MFC_OFFLOAD)
 		rtm->rtm_flags |= RTNH_F_OFFLOAD;
 
-	mp_attr = nla_nest_start(skb, RTA_MULTIPATH);
+	mp_attr = nla_nest_start_noflag(skb, RTA_MULTIPATH);
 	if (!mp_attr)
 		return -EMSGSIZE;
 
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 4ccec4c705f7..9a08bfb0672c 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -658,7 +658,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 	{
 		int n = 0;
 
-		nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS);
+		nest = nla_nest_start_noflag(msg, TCP_METRICS_ATTR_VALS);
 		if (!nest)
 			goto nla_put_failure;
 		for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) {
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 340a0f06f974..01f081aa718c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5752,7 +5752,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
 	    nla_put_u8(skb, IFLA_OPERSTATE,
 		       netif_running(dev) ? dev->operstate : IF_OPER_DOWN))
 		goto nla_put_failure;
-	protoinfo = nla_nest_start(skb, IFLA_PROTINFO);
+	protoinfo = nla_nest_start_noflag(skb, IFLA_PROTINFO);
 	if (!protoinfo)
 		goto nla_put_failure;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9c0127a44f9f..e2b47f47de92 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4777,7 +4777,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		struct fib6_info *sibling, *next_sibling;
 		struct nlattr *mp;
 
-		mp = nla_nest_start(skb, RTA_MULTIPATH);
+		mp = nla_nest_start_noflag(skb, RTA_MULTIPATH);
 		if (!mp)
 			goto nla_put_failure;
 
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 60325dbfe88b..67005ac71341 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -853,7 +853,7 @@ static int put_nla_bpf(struct sk_buff *skb, struct seg6_local_lwt *slwt)
 	if (!slwt->bpf.prog)
 		return 0;
 
-	nest = nla_nest_start(skb, SEG6_LOCAL_BPF);
+	nest = nla_nest_start_noflag(skb, SEG6_LOCAL_BPF);
 	if (!nest)
 		return -EMSGSIZE;
 
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 77595fcc9f75..c31b50cc48d9 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -345,7 +345,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	    nla_put_u16(skb, L2TP_ATTR_ENCAP_TYPE, tunnel->encap))
 		goto nla_put_failure;
 
-	nest = nla_nest_start(skb, L2TP_ATTR_STATS);
+	nest = nla_nest_start_noflag(skb, L2TP_ATTR_STATS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
@@ -742,7 +742,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 			   session->reorder_timeout, L2TP_ATTR_PAD)))
 		goto nla_put_failure;
 
-	nest = nla_nest_start(skb, L2TP_ATTR_STATS);
+	nest = nla_nest_start_noflag(skb, L2TP_ATTR_STATS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index e321a5fafb87..01f8a4f97872 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -2017,7 +2017,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		u8 linkdown = 0;
 		u8 dead = 0;
 
-		mp = nla_nest_start(skb, RTA_MULTIPATH);
+		mp = nla_nest_start_noflag(skb, RTA_MULTIPATH);
 		if (!mp)
 			goto nla_put_failure;
 
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 367b2f6513e0..672ed56b5ef0 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -79,7 +79,7 @@ static int ncsi_write_channel_info(struct sk_buff *skb,
 	nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.alpha2);
 	nla_put_string(skb, NCSI_CHANNEL_ATTR_VERSION_STR, nc->version.fw_name);
 
-	vid_nest = nla_nest_start(skb, NCSI_CHANNEL_ATTR_VLAN_LIST);
+	vid_nest = nla_nest_start_noflag(skb, NCSI_CHANNEL_ATTR_VLAN_LIST);
 	if (!vid_nest)
 		return -ENOMEM;
 	ncf = &nc->vlan_filter;
@@ -113,19 +113,19 @@ static int ncsi_write_package_info(struct sk_buff *skb,
 	NCSI_FOR_EACH_PACKAGE(ndp, np) {
 		if (np->id != id)
 			continue;
-		pnest = nla_nest_start(skb, NCSI_PKG_ATTR);
+		pnest = nla_nest_start_noflag(skb, NCSI_PKG_ATTR);
 		if (!pnest)
 			return -ENOMEM;
 		nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id);
 		if ((0x1 << np->id) == ndp->package_whitelist)
 			nla_put_flag(skb, NCSI_PKG_ATTR_FORCED);
-		cnest = nla_nest_start(skb, NCSI_PKG_ATTR_CHANNEL_LIST);
+		cnest = nla_nest_start_noflag(skb, NCSI_PKG_ATTR_CHANNEL_LIST);
 		if (!cnest) {
 			nla_nest_cancel(skb, pnest);
 			return -ENOMEM;
 		}
 		NCSI_FOR_EACH_CHANNEL(np, nc) {
-			nest = nla_nest_start(skb, NCSI_CHANNEL_ATTR);
+			nest = nla_nest_start_noflag(skb, NCSI_CHANNEL_ATTR);
 			if (!nest) {
 				nla_nest_cancel(skb, cnest);
 				nla_nest_cancel(skb, pnest);
@@ -187,7 +187,7 @@ static int ncsi_pkg_info_nl(struct sk_buff *msg, struct genl_info *info)
 
 	package_id = nla_get_u32(info->attrs[NCSI_ATTR_PACKAGE_ID]);
 
-	attr = nla_nest_start(skb, NCSI_ATTR_PACKAGE_LIST);
+	attr = nla_nest_start_noflag(skb, NCSI_ATTR_PACKAGE_LIST);
 	if (!attr) {
 		kfree_skb(skb);
 		return -EMSGSIZE;
@@ -250,7 +250,7 @@ static int ncsi_pkg_info_all_nl(struct sk_buff *skb,
 		goto err;
 	}
 
-	attr = nla_nest_start(skb, NCSI_ATTR_PACKAGE_LIST);
+	attr = nla_nest_start_noflag(skb, NCSI_ATTR_PACKAGE_LIST);
 	if (!attr) {
 		rc = -EMSGSIZE;
 		goto err;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ab119a7540db..39892e5d38a2 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2916,7 +2916,7 @@ static const struct nla_policy ip_vs_dest_policy[IPVS_DEST_ATTR_MAX + 1] = {
 static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type,
 				 struct ip_vs_kstats *kstats)
 {
-	struct nlattr *nl_stats = nla_nest_start(skb, container_type);
+	struct nlattr *nl_stats = nla_nest_start_noflag(skb, container_type);
 
 	if (!nl_stats)
 		return -EMSGSIZE;
@@ -2946,7 +2946,7 @@ nla_put_failure:
 static int ip_vs_genl_fill_stats64(struct sk_buff *skb, int container_type,
 				   struct ip_vs_kstats *kstats)
 {
-	struct nlattr *nl_stats = nla_nest_start(skb, container_type);
+	struct nlattr *nl_stats = nla_nest_start_noflag(skb, container_type);
 
 	if (!nl_stats)
 		return -EMSGSIZE;
@@ -2992,7 +2992,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb,
 	struct ip_vs_kstats kstats;
 	char *sched_name;
 
-	nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE);
+	nl_service = nla_nest_start_noflag(skb, IPVS_CMD_ATTR_SERVICE);
 	if (!nl_service)
 		return -EMSGSIZE;
 
@@ -3203,7 +3203,7 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
 	struct nlattr *nl_dest;
 	struct ip_vs_kstats kstats;
 
-	nl_dest = nla_nest_start(skb, IPVS_CMD_ATTR_DEST);
+	nl_dest = nla_nest_start_noflag(skb, IPVS_CMD_ATTR_DEST);
 	if (!nl_dest)
 		return -EMSGSIZE;
 
@@ -3373,7 +3373,7 @@ static int ip_vs_genl_fill_daemon(struct sk_buff *skb, __u32 state,
 {
 	struct nlattr *nl_daemon;
 
-	nl_daemon = nla_nest_start(skb, IPVS_CMD_ATTR_DAEMON);
+	nl_daemon = nla_nest_start_noflag(skb, IPVS_CMD_ATTR_DAEMON);
 	if (!nl_daemon)
 		return -EMSGSIZE;
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index d547a777192f..148b99a15b21 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -63,7 +63,7 @@ static int ctnetlink_dump_tuples_proto(struct sk_buff *skb,
 	int ret = 0;
 	struct nlattr *nest_parms;
 
-	nest_parms = nla_nest_start(skb, CTA_TUPLE_PROTO | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TUPLE_PROTO);
 	if (!nest_parms)
 		goto nla_put_failure;
 	if (nla_put_u8(skb, CTA_PROTO_NUM, tuple->dst.protonum))
@@ -104,7 +104,7 @@ static int ctnetlink_dump_tuples_ip(struct sk_buff *skb,
 	int ret = 0;
 	struct nlattr *nest_parms;
 
-	nest_parms = nla_nest_start(skb, CTA_TUPLE_IP | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TUPLE_IP);
 	if (!nest_parms)
 		goto nla_put_failure;
 
@@ -187,7 +187,7 @@ static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct)
 	if (!l4proto->to_nlattr)
 		return 0;
 
-	nest_proto = nla_nest_start(skb, CTA_PROTOINFO | NLA_F_NESTED);
+	nest_proto = nla_nest_start(skb, CTA_PROTOINFO);
 	if (!nest_proto)
 		goto nla_put_failure;
 
@@ -215,7 +215,7 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb,
 	if (!helper)
 		goto out;
 
-	nest_helper = nla_nest_start(skb, CTA_HELP | NLA_F_NESTED);
+	nest_helper = nla_nest_start(skb, CTA_HELP);
 	if (!nest_helper)
 		goto nla_put_failure;
 	if (nla_put_string(skb, CTA_HELP_NAME, helper->name))
@@ -249,7 +249,7 @@ dump_counters(struct sk_buff *skb, struct nf_conn_acct *acct,
 		bytes = atomic64_read(&counter[dir].bytes);
 	}
 
-	nest_count = nla_nest_start(skb, attr | NLA_F_NESTED);
+	nest_count = nla_nest_start(skb, attr);
 	if (!nest_count)
 		goto nla_put_failure;
 
@@ -293,7 +293,7 @@ ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct)
 	if (!tstamp)
 		return 0;
 
-	nest_count = nla_nest_start(skb, CTA_TIMESTAMP | NLA_F_NESTED);
+	nest_count = nla_nest_start(skb, CTA_TIMESTAMP);
 	if (!nest_count)
 		goto nla_put_failure;
 
@@ -337,7 +337,7 @@ static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct)
 		return 0;
 
 	ret = -1;
-	nest_secctx = nla_nest_start(skb, CTA_SECCTX | NLA_F_NESTED);
+	nest_secctx = nla_nest_start(skb, CTA_SECCTX);
 	if (!nest_secctx)
 		goto nla_put_failure;
 
@@ -397,7 +397,7 @@ static int ctnetlink_dump_master(struct sk_buff *skb, const struct nf_conn *ct)
 	if (!(ct->status & IPS_EXPECTED))
 		return 0;
 
-	nest_parms = nla_nest_start(skb, CTA_TUPLE_MASTER | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TUPLE_MASTER);
 	if (!nest_parms)
 		goto nla_put_failure;
 	if (ctnetlink_dump_tuples(skb, master_tuple(ct)) < 0)
@@ -415,7 +415,7 @@ dump_ct_seq_adj(struct sk_buff *skb, const struct nf_ct_seqadj *seq, int type)
 {
 	struct nlattr *nest_parms;
 
-	nest_parms = nla_nest_start(skb, type | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, type);
 	if (!nest_parms)
 		goto nla_put_failure;
 
@@ -467,7 +467,7 @@ static int ctnetlink_dump_ct_synproxy(struct sk_buff *skb, struct nf_conn *ct)
 	if (!synproxy)
 		return 0;
 
-	nest_parms = nla_nest_start(skb, CTA_SYNPROXY | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_SYNPROXY);
 	if (!nest_parms)
 		goto nla_put_failure;
 
@@ -528,7 +528,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 
 	zone = nf_ct_zone(ct);
 
-	nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG);
 	if (!nest_parms)
 		goto nla_put_failure;
 	if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
@@ -538,7 +538,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 		goto nla_put_failure;
 	nla_nest_end(skb, nest_parms);
 
-	nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY);
 	if (!nest_parms)
 		goto nla_put_failure;
 	if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0)
@@ -720,7 +720,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 
 	zone = nf_ct_zone(ct);
 
-	nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG);
 	if (!nest_parms)
 		goto nla_put_failure;
 	if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
@@ -730,7 +730,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 		goto nla_put_failure;
 	nla_nest_end(skb, nest_parms);
 
-	nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY);
 	if (!nest_parms)
 		goto nla_put_failure;
 	if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0)
@@ -2400,7 +2400,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct)
 
 	zone = nf_ct_zone(ct);
 
-	nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG);
 	if (!nest_parms)
 		goto nla_put_failure;
 	if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
@@ -2410,7 +2410,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct)
 		goto nla_put_failure;
 	nla_nest_end(skb, nest_parms);
 
-	nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY);
 	if (!nest_parms)
 		goto nla_put_failure;
 	if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0)
@@ -2472,7 +2472,7 @@ ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct,
 {
 	struct nlattr *nest_parms;
 
-	nest_parms = nla_nest_start(skb, ct_attr | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, ct_attr);
 	if (!nest_parms)
 		goto nla_put_failure;
 
@@ -2644,7 +2644,7 @@ static int ctnetlink_exp_dump_tuple(struct sk_buff *skb,
 {
 	struct nlattr *nest_parms;
 
-	nest_parms = nla_nest_start(skb, type | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, type);
 	if (!nest_parms)
 		goto nla_put_failure;
 	if (ctnetlink_dump_tuples(skb, tuple) < 0)
@@ -2671,7 +2671,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb,
 	m.src.u.all = mask->src.u.all;
 	m.dst.protonum = tuple->dst.protonum;
 
-	nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK);
 	if (!nest_parms)
 		goto nla_put_failure;
 
@@ -2743,7 +2743,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 #if IS_ENABLED(CONFIG_NF_NAT)
 	if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) ||
 	    exp->saved_proto.all) {
-		nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED);
+		nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT);
 		if (!nest_parms)
 			goto nla_put_failure;
 
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 6fca80587505..a4deddebec0a 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -598,7 +598,7 @@ static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
 	struct nlattr *nest_parms;
 
 	spin_lock_bh(&ct->lock);
-	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP);
 	if (!nest_parms)
 		goto nla_put_failure;
 	if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state) ||
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index a7818101ad80..8cf36b684400 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -520,7 +520,7 @@ static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
 	struct nlattr *nest_parms;
 
 	spin_lock_bh(&ct->lock);
-	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_SCTP | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_SCTP);
 	if (!nest_parms)
 		goto nla_put_failure;
 
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index a06875a466a4..ec6c3618333d 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1192,7 +1192,7 @@ static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
 	struct nf_ct_tcp_flags tmp = {};
 
 	spin_lock_bh(&ct->lock);
-	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP);
 	if (!nest_parms)
 		goto nla_put_failure;
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9d888dc6be38..2b79c250ecb4 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1200,7 +1200,7 @@ static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats)
 		total.pkts += pkts;
 		total.bytes += bytes;
 	}
-	nest = nla_nest_start(skb, NFTA_CHAIN_COUNTERS);
+	nest = nla_nest_start_noflag(skb, NFTA_CHAIN_COUNTERS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
@@ -1248,7 +1248,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 		const struct nf_hook_ops *ops = &basechain->ops;
 		struct nlattr *nest;
 
-		nest = nla_nest_start(skb, NFTA_CHAIN_HOOK);
+		nest = nla_nest_start_noflag(skb, NFTA_CHAIN_HOOK);
 		if (nest == NULL)
 			goto nla_put_failure;
 		if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum)))
@@ -2059,7 +2059,8 @@ static int nf_tables_fill_expr_info(struct sk_buff *skb,
 		goto nla_put_failure;
 
 	if (expr->ops->dump) {
-		struct nlattr *data = nla_nest_start(skb, NFTA_EXPR_DATA);
+		struct nlattr *data = nla_nest_start_noflag(skb,
+							    NFTA_EXPR_DATA);
 		if (data == NULL)
 			goto nla_put_failure;
 		if (expr->ops->dump(skb, expr) < 0)
@@ -2078,7 +2079,7 @@ int nft_expr_dump(struct sk_buff *skb, unsigned int attr,
 {
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, attr);
+	nest = nla_nest_start_noflag(skb, attr);
 	if (!nest)
 		goto nla_put_failure;
 	if (nf_tables_fill_expr_info(skb, expr) < 0)
@@ -2289,7 +2290,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
 			goto nla_put_failure;
 	}
 
-	list = nla_nest_start(skb, NFTA_RULE_EXPRESSIONS);
+	list = nla_nest_start_noflag(skb, NFTA_RULE_EXPRESSIONS);
 	if (list == NULL)
 		goto nla_put_failure;
 	nft_rule_for_each_expr(expr, next, rule) {
@@ -3258,7 +3259,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 	if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata))
 		goto nla_put_failure;
 
-	desc = nla_nest_start(skb, NFTA_SET_DESC);
+	desc = nla_nest_start_noflag(skb, NFTA_SET_DESC);
 	if (desc == NULL)
 		goto nla_put_failure;
 	if (set->size &&
@@ -3908,7 +3909,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, NFTA_LIST_ELEM);
+	nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM);
 	if (nest == NULL)
 		goto nla_put_failure;
 
@@ -4052,7 +4053,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	if (nla_put_string(skb, NFTA_SET_ELEM_LIST_SET, set->name))
 		goto nla_put_failure;
 
-	nest = nla_nest_start(skb, NFTA_SET_ELEM_LIST_ELEMENTS);
+	nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_LIST_ELEMENTS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
@@ -4124,7 +4125,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
 	if (nla_put_string(skb, NFTA_SET_NAME, set->name))
 		goto nla_put_failure;
 
-	nest = nla_nest_start(skb, NFTA_SET_ELEM_LIST_ELEMENTS);
+	nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_LIST_ELEMENTS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
@@ -5014,7 +5015,7 @@ static int nft_object_dump(struct sk_buff *skb, unsigned int attr,
 {
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, attr);
+	nest = nla_nest_start_noflag(skb, attr);
 	if (!nest)
 		goto nla_put_failure;
 	if (obj->ops->dump(skb, obj, reset) < 0)
@@ -5831,14 +5832,14 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 			 NFTA_FLOWTABLE_PAD))
 		goto nla_put_failure;
 
-	nest = nla_nest_start(skb, NFTA_FLOWTABLE_HOOK);
+	nest = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK);
 	if (!nest)
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_NUM, htonl(flowtable->hooknum)) ||
 	    nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->priority)))
 		goto nla_put_failure;
 
-	nest_devs = nla_nest_start(skb, NFTA_FLOWTABLE_HOOK_DEVS);
+	nest_devs = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK_DEVS);
 	if (!nest_devs)
 		goto nla_put_failure;
 
@@ -7264,7 +7265,7 @@ int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v)
 {
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, type);
+	nest = nla_nest_start_noflag(skb, type);
 	if (!nest)
 		goto nla_put_failure;
 
@@ -7377,7 +7378,7 @@ int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data,
 	struct nlattr *nest;
 	int err;
 
-	nest = nla_nest_start(skb, attr);
+	nest = nla_nest_start_noflag(skb, attr);
 	if (nest == NULL)
 		return -1;
 
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index e5d27b2e4eba..74c9794d28d6 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -462,7 +462,7 @@ nfnl_cthelper_dump_tuple(struct sk_buff *skb,
 {
 	struct nlattr *nest_parms;
 
-	nest_parms = nla_nest_start(skb, NFCTH_TUPLE | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, NFCTH_TUPLE);
 	if (nest_parms == NULL)
 		goto nla_put_failure;
 
@@ -487,7 +487,7 @@ nfnl_cthelper_dump_policy(struct sk_buff *skb,
 	int i;
 	struct nlattr *nest_parms1, *nest_parms2;
 
-	nest_parms1 = nla_nest_start(skb, NFCTH_POLICY | NLA_F_NESTED);
+	nest_parms1 = nla_nest_start(skb, NFCTH_POLICY);
 	if (nest_parms1 == NULL)
 		goto nla_put_failure;
 
@@ -496,8 +496,7 @@ nfnl_cthelper_dump_policy(struct sk_buff *skb,
 		goto nla_put_failure;
 
 	for (i = 0; i < helper->expect_class_max + 1; i++) {
-		nest_parms2 = nla_nest_start(skb,
-				(NFCTH_POLICY_SET+i) | NLA_F_NESTED);
+		nest_parms2 = nla_nest_start(skb, (NFCTH_POLICY_SET + i));
 		if (nest_parms2 == NULL)
 			goto nla_put_failure;
 
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index c69b11ca5aad..572cb42e1ee1 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -184,7 +184,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 			 htonl(refcount_read(&timeout->refcnt))))
 		goto nla_put_failure;
 
-	nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA);
 	if (!nest_parms)
 		goto nla_put_failure;
 
@@ -401,7 +401,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
 	    nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto))
 		goto nla_put_failure;
 
-	nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA | NLA_F_NESTED);
+	nest_parms = nla_nest_start(skb, CTA_TIMEOUT_DATA);
 	if (!nest_parms)
 		goto nla_put_failure;
 
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index e057b2961d31..be7d53943e2d 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -351,7 +351,7 @@ static int nfqnl_put_bridge(struct nf_queue_entry *entry, struct sk_buff *skb)
 	if (skb_vlan_tag_present(entskb)) {
 		struct nlattr *nest;
 
-		nest = nla_nest_start(skb, NFQA_VLAN | NLA_F_NESTED);
+		nest = nla_nest_start(skb, NFQA_VLAN);
 		if (!nest)
 			goto nla_put_failure;
 
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 7b717fad6cdc..1738ef6dcb56 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -928,7 +928,7 @@ static int nft_ct_timeout_obj_dump(struct sk_buff *skb,
 	    nla_put_be16(skb, NFTA_CT_TIMEOUT_L3PROTO, htons(timeout->l3num)))
 		return -1;
 
-	nest_params = nla_nest_start(skb, NFTA_CT_TIMEOUT_DATA | NLA_F_NESTED);
+	nest_params = nla_nest_start(skb, NFTA_CT_TIMEOUT_DATA);
 	if (!nest_params)
 		return -1;
 
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index b113fcac94e1..66b52d015763 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -437,7 +437,7 @@ static int nft_tunnel_ip_dump(struct sk_buff *skb, struct ip_tunnel_info *info)
 	struct nlattr *nest;
 
 	if (info->mode & IP_TUNNEL_INFO_IPV6) {
-		nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_IP6);
+		nest = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_IP6);
 		if (!nest)
 			return -1;
 
@@ -448,7 +448,7 @@ static int nft_tunnel_ip_dump(struct sk_buff *skb, struct ip_tunnel_info *info)
 
 		nla_nest_end(skb, nest);
 	} else {
-		nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_IP);
+		nest = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_IP);
 		if (!nest)
 			return -1;
 
@@ -468,7 +468,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb,
 	struct nft_tunnel_opts *opts = &priv->opts;
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_OPTS);
+	nest = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS);
 	if (!nest)
 		return -1;
 
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index ba7800f94ccc..c9775658fb98 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -498,7 +498,7 @@ list_start:
 	if (ret_val != 0)
 		goto list_failure_lock;
 
-	nla_a = nla_nest_start(ans_skb, NLBL_CIPSOV4_A_TAGLST);
+	nla_a = nla_nest_start_noflag(ans_skb, NLBL_CIPSOV4_A_TAGLST);
 	if (nla_a == NULL) {
 		ret_val = -ENOMEM;
 		goto list_failure_lock;
@@ -517,7 +517,8 @@ list_start:
 
 	switch (doi_def->type) {
 	case CIPSO_V4_MAP_TRANS:
-		nla_a = nla_nest_start(ans_skb, NLBL_CIPSOV4_A_MLSLVLLST);
+		nla_a = nla_nest_start_noflag(ans_skb,
+					      NLBL_CIPSOV4_A_MLSLVLLST);
 		if (nla_a == NULL) {
 			ret_val = -ENOMEM;
 			goto list_failure_lock;
@@ -529,7 +530,8 @@ list_start:
 			    CIPSO_V4_INV_LVL)
 				continue;
 
-			nla_b = nla_nest_start(ans_skb, NLBL_CIPSOV4_A_MLSLVL);
+			nla_b = nla_nest_start_noflag(ans_skb,
+						      NLBL_CIPSOV4_A_MLSLVL);
 			if (nla_b == NULL) {
 				ret_val = -ENOMEM;
 				goto list_retry;
@@ -548,7 +550,8 @@ list_start:
 		}
 		nla_nest_end(ans_skb, nla_a);
 
-		nla_a = nla_nest_start(ans_skb, NLBL_CIPSOV4_A_MLSCATLST);
+		nla_a = nla_nest_start_noflag(ans_skb,
+					      NLBL_CIPSOV4_A_MLSCATLST);
 		if (nla_a == NULL) {
 			ret_val = -ENOMEM;
 			goto list_retry;
@@ -560,7 +563,8 @@ list_start:
 			    CIPSO_V4_INV_CAT)
 				continue;
 
-			nla_b = nla_nest_start(ans_skb, NLBL_CIPSOV4_A_MLSCAT);
+			nla_b = nla_nest_start_noflag(ans_skb,
+						      NLBL_CIPSOV4_A_MLSCAT);
 			if (nla_b == NULL) {
 				ret_val = -ENOMEM;
 				goto list_retry;
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index a16eacfb2236..c6c8a101f2ff 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -315,7 +315,7 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb,
 
 	switch (entry->def.type) {
 	case NETLBL_NLTYPE_ADDRSELECT:
-		nla_a = nla_nest_start(skb, NLBL_MGMT_A_SELECTORLIST);
+		nla_a = nla_nest_start_noflag(skb, NLBL_MGMT_A_SELECTORLIST);
 		if (nla_a == NULL)
 			return -ENOMEM;
 
@@ -323,7 +323,8 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb,
 			struct netlbl_domaddr4_map *map4;
 			struct in_addr addr_struct;
 
-			nla_b = nla_nest_start(skb, NLBL_MGMT_A_ADDRSELECTOR);
+			nla_b = nla_nest_start_noflag(skb,
+						      NLBL_MGMT_A_ADDRSELECTOR);
 			if (nla_b == NULL)
 				return -ENOMEM;
 
@@ -357,7 +358,8 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb,
 		netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) {
 			struct netlbl_domaddr6_map *map6;
 
-			nla_b = nla_nest_start(skb, NLBL_MGMT_A_ADDRSELECTOR);
+			nla_b = nla_nest_start_noflag(skb,
+						      NLBL_MGMT_A_ADDRSELECTOR);
 			if (nla_b == NULL)
 				return -ENOMEM;
 
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 288456090710..83e876591f6c 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -665,7 +665,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 		struct nlattr *nla_ops;
 		int i;
 
-		nla_ops = nla_nest_start(skb, CTRL_ATTR_OPS);
+		nla_ops = nla_nest_start_noflag(skb, CTRL_ATTR_OPS);
 		if (nla_ops == NULL)
 			goto nla_put_failure;
 
@@ -681,7 +681,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 			if (family->policy)
 				op_flags |= GENL_CMD_CAP_HASPOL;
 
-			nest = nla_nest_start(skb, i + 1);
+			nest = nla_nest_start_noflag(skb, i + 1);
 			if (nest == NULL)
 				goto nla_put_failure;
 
@@ -699,7 +699,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 		struct nlattr *nla_grps;
 		int i;
 
-		nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
+		nla_grps = nla_nest_start_noflag(skb, CTRL_ATTR_MCAST_GROUPS);
 		if (nla_grps == NULL)
 			goto nla_put_failure;
 
@@ -709,7 +709,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 
 			grp = &family->mcgrps[i];
 
-			nest = nla_nest_start(skb, i + 1);
+			nest = nla_nest_start_noflag(skb, i + 1);
 			if (nest == NULL)
 				goto nla_put_failure;
 
@@ -749,11 +749,11 @@ static int ctrl_fill_mcgrp_info(const struct genl_family *family,
 	    nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id))
 		goto nla_put_failure;
 
-	nla_grps = nla_nest_start(skb, CTRL_ATTR_MCAST_GROUPS);
+	nla_grps = nla_nest_start_noflag(skb, CTRL_ATTR_MCAST_GROUPS);
 	if (nla_grps == NULL)
 		goto nla_put_failure;
 
-	nest = nla_nest_start(skb, 1);
+	nest = nla_nest_start_noflag(skb, 1);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 4d9f3ac8d562..f91ce7c82746 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -392,7 +392,7 @@ int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list)
 	if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx))
 		goto nla_put_failure;
 
-	sdp_attr = nla_nest_start(msg, NFC_ATTR_LLC_SDP);
+	sdp_attr = nla_nest_start_noflag(msg, NFC_ATTR_LLC_SDP);
 	if (sdp_attr == NULL) {
 		rc = -ENOMEM;
 		goto nla_put_failure;
@@ -402,7 +402,7 @@ int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list)
 	hlist_for_each_entry_safe(sdres, n, sdres_list, node) {
 		pr_debug("uri: %s, sap: %d\n", sdres->uri, sdres->sap);
 
-		uri_attr = nla_nest_start(msg, i++);
+		uri_attr = nla_nest_start_noflag(msg, i++);
 		if (uri_attr == NULL) {
 			rc = -ENOMEM;
 			goto nla_put_failure;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 626629944450..ff8baf810bb3 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1683,7 +1683,7 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info,
 {
 	struct nlattr *start;
 
-	start = nla_nest_start(skb, OVS_CT_ATTR_NAT);
+	start = nla_nest_start_noflag(skb, OVS_CT_ATTR_NAT);
 	if (!start)
 		return false;
 
@@ -1750,7 +1750,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
 {
 	struct nlattr *start;
 
-	start = nla_nest_start(skb, OVS_ACTION_ATTR_CT);
+	start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CT);
 	if (!start)
 		return -EMSGSIZE;
 
@@ -2160,7 +2160,7 @@ static int ovs_ct_limit_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	if (IS_ERR(reply))
 		return PTR_ERR(reply);
 
-	nla_reply = nla_nest_start(reply, OVS_CT_LIMIT_ATTR_ZONE_LIMIT);
+	nla_reply = nla_nest_start_noflag(reply, OVS_CT_LIMIT_ATTR_ZONE_LIMIT);
 
 	if (a[OVS_CT_LIMIT_ATTR_ZONE_LIMIT]) {
 		err = ovs_ct_limit_get_zone_limit(
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index a64d3eb1f9a9..356677c3a0c2 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -463,7 +463,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 			  nla_data(upcall_info->userdata));
 
 	if (upcall_info->egress_tun_info) {
-		nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY);
+		nla = nla_nest_start_noflag(user_skb,
+					    OVS_PACKET_ATTR_EGRESS_TUN_KEY);
 		if (!nla) {
 			err = -EMSGSIZE;
 			goto out;
@@ -475,7 +476,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	}
 
 	if (upcall_info->actions_len) {
-		nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_ACTIONS);
+		nla = nla_nest_start_noflag(user_skb, OVS_PACKET_ATTR_ACTIONS);
 		if (!nla) {
 			err = -EMSGSIZE;
 			goto out;
@@ -776,7 +777,7 @@ static int ovs_flow_cmd_fill_actions(const struct sw_flow *flow,
 	 * This can only fail for dump operations because the skb is always
 	 * properly sized for single flows.
 	 */
-	start = nla_nest_start(skb, OVS_FLOW_ATTR_ACTIONS);
+	start = nla_nest_start_noflag(skb, OVS_FLOW_ATTR_ACTIONS);
 	if (start) {
 		const struct sw_flow_actions *sf_acts;
 
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 3563acd5f92e..2427b672107a 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -856,7 +856,7 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb,
 	const struct vxlan_metadata *opts = tun_opts;
 	struct nlattr *nla;
 
-	nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS);
+	nla = nla_nest_start_noflag(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS);
 	if (!nla)
 		return -EMSGSIZE;
 
@@ -948,7 +948,7 @@ static int ip_tun_to_nlattr(struct sk_buff *skb,
 	struct nlattr *nla;
 	int err;
 
-	nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL);
+	nla = nla_nest_start_noflag(skb, OVS_KEY_ATTR_TUNNEL);
 	if (!nla)
 		return -EMSGSIZE;
 
@@ -1957,7 +1957,7 @@ static int nsh_key_to_nlattr(const struct ovs_key_nsh *nsh, bool is_mask,
 {
 	struct nlattr *start;
 
-	start = nla_nest_start(skb, OVS_KEY_ATTR_NSH);
+	start = nla_nest_start_noflag(skb, OVS_KEY_ATTR_NSH);
 	if (!start)
 		return -EMSGSIZE;
 
@@ -2040,14 +2040,15 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
 		if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) {
 			if (ovs_nla_put_vlan(skb, &output->eth.vlan, is_mask))
 				goto nla_put_failure;
-			encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
+			encap = nla_nest_start_noflag(skb, OVS_KEY_ATTR_ENCAP);
 			if (!swkey->eth.vlan.tci)
 				goto unencap;
 
 			if (swkey->eth.cvlan.tci || eth_type_vlan(swkey->eth.type)) {
 				if (ovs_nla_put_vlan(skb, &output->eth.cvlan, is_mask))
 					goto nla_put_failure;
-				in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
+				in_encap = nla_nest_start_noflag(skb,
+								 OVS_KEY_ATTR_ENCAP);
 				if (!swkey->eth.cvlan.tci)
 					goto unencap;
 			}
@@ -2226,7 +2227,7 @@ int ovs_nla_put_key(const struct sw_flow_key *swkey,
 	int err;
 	struct nlattr *nla;
 
-	nla = nla_nest_start(skb, attr);
+	nla = nla_nest_start_noflag(skb, attr);
 	if (!nla)
 		return -EMSGSIZE;
 	err = __ovs_nla_put_key(swkey, output, is_mask, skb);
@@ -3252,7 +3253,7 @@ static int sample_action_to_attr(const struct nlattr *attr,
 	const struct sample_arg *arg;
 	struct nlattr *actions;
 
-	start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE);
+	start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_SAMPLE);
 	if (!start)
 		return -EMSGSIZE;
 
@@ -3265,7 +3266,7 @@ static int sample_action_to_attr(const struct nlattr *attr,
 		goto out;
 	}
 
-	ac_start = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
+	ac_start = nla_nest_start_noflag(skb, OVS_SAMPLE_ATTR_ACTIONS);
 	if (!ac_start) {
 		err = -EMSGSIZE;
 		goto out;
@@ -3291,7 +3292,7 @@ static int clone_action_to_attr(const struct nlattr *attr,
 	struct nlattr *start;
 	int err = 0, rem = nla_len(attr);
 
-	start = nla_nest_start(skb, OVS_ACTION_ATTR_CLONE);
+	start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CLONE);
 	if (!start)
 		return -EMSGSIZE;
 
@@ -3313,7 +3314,7 @@ static int check_pkt_len_action_to_attr(const struct nlattr *attr,
 	const struct nlattr *a, *cpl_arg;
 	int err = 0, rem = nla_len(attr);
 
-	start = nla_nest_start(skb, OVS_ACTION_ATTR_CHECK_PKT_LEN);
+	start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CHECK_PKT_LEN);
 	if (!start)
 		return -EMSGSIZE;
 
@@ -3332,8 +3333,8 @@ static int check_pkt_len_action_to_attr(const struct nlattr *attr,
 	 * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
 	 */
 	a = nla_next(cpl_arg, &rem);
-	ac_start =  nla_nest_start(skb,
-		OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL);
+	ac_start =  nla_nest_start_noflag(skb,
+					  OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL);
 	if (!ac_start) {
 		err = -EMSGSIZE;
 		goto out;
@@ -3351,8 +3352,8 @@ static int check_pkt_len_action_to_attr(const struct nlattr *attr,
 	 * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER.
 	 */
 	a = nla_next(a, &rem);
-	ac_start =  nla_nest_start(skb,
-				   OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER);
+	ac_start =  nla_nest_start_noflag(skb,
+					  OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER);
 	if (!ac_start) {
 		err = -EMSGSIZE;
 		goto out;
@@ -3386,7 +3387,7 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 		struct ovs_tunnel_info *ovs_tun = nla_data(ovs_key);
 		struct ip_tunnel_info *tun_info = &ovs_tun->tun_dst->u.tun_info;
 
-		start = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
+		start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_SET);
 		if (!start)
 			return -EMSGSIZE;
 
@@ -3418,7 +3419,7 @@ static int masked_set_action_to_set_action_attr(const struct nlattr *a,
 	/* Revert the conversion we did from a non-masked set action to
 	 * masked set action.
 	 */
-	nla = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
+	nla = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_SET);
 	if (!nla)
 		return -EMSGSIZE;
 
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 0be3d097ae01..fdc8be7fd8f3 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -127,7 +127,7 @@ static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id,
 			      OVS_METER_ATTR_PAD))
 		goto error;
 
-	nla = nla_nest_start(reply, OVS_METER_ATTR_BANDS);
+	nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS);
 	if (!nla)
 		goto error;
 
@@ -136,7 +136,7 @@ static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id,
 	for (i = 0; i < meter->n_bands; ++i, ++band) {
 		struct nlattr *band_nla;
 
-		band_nla = nla_nest_start(reply, OVS_BAND_ATTR_UNSPEC);
+		band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC);
 		if (!band_nla || nla_put(reply, OVS_BAND_ATTR_STATS,
 					 sizeof(struct ovs_flow_stats),
 					 &band->stats))
@@ -166,11 +166,11 @@ static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info)
 	    nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS))
 		goto nla_put_failure;
 
-	nla = nla_nest_start(reply, OVS_METER_ATTR_BANDS);
+	nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS);
 	if (!nla)
 		goto nla_put_failure;
 
-	band_nla = nla_nest_start(reply, OVS_BAND_ATTR_UNSPEC);
+	band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC);
 	if (!band_nla)
 		goto nla_put_failure;
 	/* Currently only DROP band type is supported. */
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 8f16f11f7ad3..54965ff8cc66 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -43,7 +43,7 @@ static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
 	if (vxlan->cfg.flags & VXLAN_F_GBP) {
 		struct nlattr *exts;
 
-		exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION);
+		exts = nla_nest_start_noflag(skb, OVS_TUNNEL_ATTR_EXTENSION);
 		if (!exts)
 			return -EMSGSIZE;
 
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 19f6765566e7..258ce3b7b452 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -319,7 +319,7 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
 	if (!vport->ops->get_options)
 		return 0;
 
-	nla = nla_nest_start(skb, OVS_VPORT_ATTR_OPTIONS);
+	nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_OPTIONS);
 	if (!nla)
 		return -EMSGSIZE;
 
diff --git a/net/packet/diag.c b/net/packet/diag.c
index 7ef1c881ae74..98abfd8644a4 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -39,7 +39,7 @@ static int pdiag_put_mclist(const struct packet_sock *po, struct sk_buff *nlskb)
 	struct nlattr *mca;
 	struct packet_mclist *ml;
 
-	mca = nla_nest_start(nlskb, PACKET_DIAG_MCLIST);
+	mca = nla_nest_start_noflag(nlskb, PACKET_DIAG_MCLIST);
 	if (!mca)
 		return -EMSGSIZE;
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 5a87e271d35a..641ad7575f24 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -242,7 +242,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 			       (unsigned long)p->tcfa_tm.lastuse))
 			continue;
 
-		nest = nla_nest_start(skb, n_i);
+		nest = nla_nest_start_noflag(skb, n_i);
 		if (!nest) {
 			index--;
 			goto nla_put_failure;
@@ -299,7 +299,7 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 	struct tc_action *p;
 	unsigned long id = 1;
 
-	nest = nla_nest_start(skb, 0);
+	nest = nla_nest_start_noflag(skb, 0);
 	if (nest == NULL)
 		goto nla_put_failure;
 	if (nla_put_string(skb, TCA_KIND, ops->kind))
@@ -776,7 +776,7 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 	}
 	rcu_read_unlock();
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 	err = tcf_action_dump_old(skb, a, bind, ref);
@@ -800,7 +800,7 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[],
 
 	for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
 		a = actions[i];
-		nest = nla_nest_start(skb, a->order);
+		nest = nla_nest_start_noflag(skb, a->order);
 		if (nest == NULL)
 			goto nla_put_failure;
 		err = tcf_action_dump_1(skb, a, bind, ref);
@@ -1052,7 +1052,7 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[],
 	t->tca__pad1 = 0;
 	t->tca__pad2 = 0;
 
-	nest = nla_nest_start(skb, TCA_ACT_TAB);
+	nest = nla_nest_start_noflag(skb, TCA_ACT_TAB);
 	if (!nest)
 		goto out_nlmsg_trim;
 
@@ -1176,7 +1176,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 	t->tca__pad1 = 0;
 	t->tca__pad2 = 0;
 
-	nest = nla_nest_start(skb, TCA_ACT_TAB);
+	nest = nla_nest_start_noflag(skb, TCA_ACT_TAB);
 	if (!nest) {
 		NL_SET_ERR_MSG(extack, "Failed to add new netlink message");
 		goto out_module_put;
@@ -1508,7 +1508,7 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
 	if (!count_attr)
 		goto out_module_put;
 
-	nest = nla_nest_start(skb, TCA_ACT_TAB);
+	nest = nla_nest_start_noflag(skb, TCA_ACT_TAB);
 	if (nest == NULL)
 		goto out_module_put;
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 31c6ffb6abe7..7a87ce2e5a76 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -387,7 +387,7 @@ static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife)
 	if (list_empty(&ife->metalist))
 		return 0;
 
-	nest = nla_nest_start(skb, TCA_IFE_METALST);
+	nest = nla_nest_start_noflag(skb, TCA_IFE_METALST);
 	if (!nest)
 		goto out_nlmsg_trim;
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 287793abfaf9..ce4b54fa7834 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -108,14 +108,15 @@ err_out:
 static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
 				 struct tcf_pedit_key_ex *keys_ex, int n)
 {
-	struct nlattr *keys_start = nla_nest_start(skb, TCA_PEDIT_KEYS_EX);
+	struct nlattr *keys_start = nla_nest_start_noflag(skb,
+							  TCA_PEDIT_KEYS_EX);
 
 	if (!keys_start)
 		goto nla_failure;
 	for (; n > 0; n--) {
 		struct nlattr *key_start;
 
-		key_start = nla_nest_start(skb, TCA_PEDIT_KEY_EX);
+		key_start = nla_nest_start_noflag(skb, TCA_PEDIT_KEY_EX);
 		if (!key_start)
 			goto nla_failure;
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index d5aaf90a3971..45c0c253c7e8 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -426,7 +426,7 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
 	u8 *src = (u8 *)(info + 1);
 	struct nlattr *start;
 
-	start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE);
+	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE);
 	if (!start)
 		return -EMSGSIZE;
 
@@ -460,7 +460,7 @@ static int tunnel_key_opts_dump(struct sk_buff *skb,
 	if (!info->options_len)
 		return 0;
 
-	start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS);
+	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS);
 	if (!start)
 		return -EMSGSIZE;
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 9115f053883f..78de717afddf 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -3111,7 +3111,7 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
 		 * tc data even if iproute2  was newer - jhs
 		 */
 		if (exts->type != TCA_OLD_COMPAT) {
-			nest = nla_nest_start(skb, exts->action);
+			nest = nla_nest_start_noflag(skb, exts->action);
 			if (nest == NULL)
 				goto nla_put_failure;
 
@@ -3120,7 +3120,7 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
 			nla_nest_end(skb, nest);
 		} else if (exts->police) {
 			struct tc_action *act = tcf_exts_first_act(exts);
-			nest = nla_nest_start(skb, exts->police);
+			nest = nla_nest_start_noflag(skb, exts->police);
 			if (nest == NULL || !act)
 				goto nla_put_failure;
 			if (tcf_action_dump_old(skb, act, 0, 0) < 0)
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 687b0af67878..dd5fdb62c6df 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -288,7 +288,7 @@ static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh,
 
 	t->tcm_handle = f->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index b4ac58039cb1..6fd569c5a036 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -591,7 +591,7 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh,
 
 	cls_bpf_offload_update_stats(tp, prog);
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 4c1567854f95..b680dd684282 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -176,7 +176,7 @@ static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, void *fh,
 
 	t->tcm_handle = head->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index eece1ee26930..cb29fe7d5ed3 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -629,7 +629,7 @@ static int flow_dump(struct net *net, struct tcf_proto *tp, void *fh,
 
 	t->tcm_handle = f->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 0d8968803e98..8d4f7a672f14 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -2051,7 +2051,7 @@ static int fl_dump_key_geneve_opt(struct sk_buff *skb,
 	struct nlattr *nest;
 	int opt_off = 0;
 
-	nest = nla_nest_start(skb, TCA_FLOWER_KEY_ENC_OPTS_GENEVE);
+	nest = nla_nest_start_noflag(skb, TCA_FLOWER_KEY_ENC_OPTS_GENEVE);
 	if (!nest)
 		goto nla_put_failure;
 
@@ -2087,7 +2087,7 @@ static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
 	if (!enc_opts->len)
 		return 0;
 
-	nest = nla_nest_start(skb, enc_opt_type);
+	nest = nla_nest_start_noflag(skb, enc_opt_type);
 	if (!nest)
 		goto nla_put_failure;
 
@@ -2333,7 +2333,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 
 	t->tcm_handle = f->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (!nest)
 		goto nla_put_failure;
 
@@ -2384,7 +2384,7 @@ static int fl_tmplt_dump(struct sk_buff *skb, struct net *net, void *tmplt_priv)
 	struct fl_flow_key *key, *mask;
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (!nest)
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index ad036b00427d..3fcc1d51b9d7 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -402,7 +402,7 @@ static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	if (!f->res.classid && !tcf_exts_has_actions(&f->exts))
 		return skb->len;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index a13bc351a414..d54fa8e11b9e 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -303,7 +303,7 @@ static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,
 
 	t->tcm_handle = head->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (!nest)
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index f006af23b64a..b3b9b151a61d 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -607,7 +607,7 @@ static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh,
 
 	t->tcm_handle = f->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 0719a21d9c41..fa059cf934a6 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -706,7 +706,7 @@ static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh,
 
 	t->tcm_handle = f->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 24e0a62a65cc..1a2e7d5a8776 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -601,7 +601,7 @@ static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh,
 		 tp, fh, skb, t, p, r);
 	pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h);
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 48e76a3acf8a..499477058b2d 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -1294,7 +1294,7 @@ static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh,
 
 	t->tcm_handle = n->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 1331a4c2d8ff..6f2d6a761dbe 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -440,14 +440,14 @@ int tcf_em_tree_dump(struct sk_buff *skb, struct tcf_ematch_tree *tree, int tlv)
 	struct nlattr *top_start;
 	struct nlattr *list_start;
 
-	top_start = nla_nest_start(skb, tlv);
+	top_start = nla_nest_start_noflag(skb, tlv);
 	if (top_start == NULL)
 		goto nla_put_failure;
 
 	if (nla_put(skb, TCA_EMATCH_TREE_HDR, sizeof(tree->hdr), &tree->hdr))
 		goto nla_put_failure;
 
-	list_start = nla_nest_start(skb, TCA_EMATCH_TREE_LIST);
+	list_start = nla_nest_start_noflag(skb, TCA_EMATCH_TREE_LIST);
 	if (list_start == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index c126b9f78d6e..6c81b22d214f 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -542,7 +542,7 @@ static int qdisc_dump_stab(struct sk_buff *skb, struct qdisc_size_table *stab)
 {
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, TCA_STAB);
+	nest = nla_nest_start_noflag(skb, TCA_STAB);
 	if (nest == NULL)
 		goto nla_put_failure;
 	if (nla_put(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts))
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index d714d3747bcb..c36aa57eb4af 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -609,7 +609,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl,
 	tcm->tcm_handle = flow->common.classid;
 	tcm->tcm_info = flow->q->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 259d97bc2abd..50db72fe44de 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -2735,7 +2735,7 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct cake_sched_data *q = qdisc_priv(sch);
 	struct nlattr *opts;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (!opts)
 		goto nla_put_failure;
 
@@ -2806,7 +2806,7 @@ nla_put_failure:
 
 static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 {
-	struct nlattr *stats = nla_nest_start(d->skb, TCA_STATS_APP);
+	struct nlattr *stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP);
 	struct cake_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tstats, *ts;
 	int i;
@@ -2836,7 +2836,7 @@ static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 #undef PUT_STAT_U32
 #undef PUT_STAT_U64
 
-	tstats = nla_nest_start(d->skb, TCA_CAKE_STATS_TIN_STATS);
+	tstats = nla_nest_start_noflag(d->skb, TCA_CAKE_STATS_TIN_STATS);
 	if (!tstats)
 		goto nla_put_failure;
 
@@ -2853,7 +2853,7 @@ static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 	for (i = 0; i < q->tin_cnt; i++) {
 		struct cake_tin_data *b = &q->tins[q->tin_order[i]];
 
-		ts = nla_nest_start(d->skb, i + 1);
+		ts = nla_nest_start_noflag(d->skb, i + 1);
 		if (!ts)
 			goto nla_put_failure;
 
@@ -2973,7 +2973,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	if (flow) {
 		ktime_t now = ktime_get();
 
-		stats = nla_nest_start(d->skb, TCA_STATS_APP);
+		stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP);
 		if (!stats)
 			return -1;
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 114b9048ea7e..243bce4b888b 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1305,7 +1305,7 @@ static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 	if (cbq_dump_attr(skb, &q->link) < 0)
@@ -1340,7 +1340,7 @@ cbq_dump_class(struct Qdisc *sch, unsigned long arg,
 	tcm->tcm_handle = cl->common.classid;
 	tcm->tcm_info = cl->q->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 	if (cbq_dump_attr(skb, cl) < 0)
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index f68fd7a0e038..adffc6d68c06 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -449,7 +449,7 @@ static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct tc_cbs_qopt opt = { };
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (!nest)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index eafc0d17d174..eda21dc94bde 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -452,7 +452,7 @@ static int choke_dump(struct Qdisc *sch, struct sk_buff *skb)
 		.Scell_log	= q->parms.Scell_log,
 	};
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 17cd81f84b5d..60ac4e61ce3a 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -217,7 +217,7 @@ static int codel_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *opts;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 430df9a55ec4..022db73fd5a9 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -244,7 +244,7 @@ static int drr_dump_class(struct Qdisc *sch, unsigned long arg,
 	tcm->tcm_handle	= cl->common.classid;
 	tcm->tcm_info	= cl->qdisc->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 	if (nla_put_u32(skb, TCA_DRR_QUANTUM, cl->quantum))
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 42471464ded3..cdf744e710f1 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -432,7 +432,7 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl,
 	tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1);
 	tcm->tcm_info = p->q->handle;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
 	if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) ||
@@ -451,7 +451,7 @@ static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct dsmark_qdisc_data *p = qdisc_priv(sch);
 	struct nlattr *opts = NULL;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
 	if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices))
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 1150f22983df..67107caa287c 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -460,7 +460,7 @@ static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct tc_etf_qopt opt = { };
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (!nest)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 1a662f2bb7bb..5ca370e78d3a 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -823,7 +823,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	u64 ce_threshold = q->ce_threshold;
 	struct nlattr *opts;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index cd04d40c30b6..825a933b019a 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -527,7 +527,7 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *opts;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 234afbf9115b..9bfa15e12d23 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -772,7 +772,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (gred_offload_dump_stats(sch))
 		goto nla_put_failure;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
 	if (nla_put(skb, TCA_GRED_DPS, sizeof(sopt), &sopt))
@@ -790,7 +790,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
 		goto nla_put_failure;
 
 	/* Old style all-in-one dump of VQs */
-	parms = nla_nest_start(skb, TCA_GRED_PARMS);
+	parms = nla_nest_start_noflag(skb, TCA_GRED_PARMS);
 	if (parms == NULL)
 		goto nla_put_failure;
 
@@ -841,7 +841,7 @@ append_opt:
 	nla_nest_end(skb, parms);
 
 	/* Dump the VQs again, in more structured way */
-	vqs = nla_nest_start(skb, TCA_GRED_VQ_LIST);
+	vqs = nla_nest_start_noflag(skb, TCA_GRED_VQ_LIST);
 	if (!vqs)
 		goto nla_put_failure;
 
@@ -852,7 +852,7 @@ append_opt:
 		if (!q)
 			continue;
 
-		vq = nla_nest_start(skb, TCA_GRED_VQ_ENTRY);
+		vq = nla_nest_start_noflag(skb, TCA_GRED_VQ_ENTRY);
 		if (!vq)
 			goto nla_put_failure;
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index d2ab463f22ae..97d2fb91c39f 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1300,7 +1300,7 @@ hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb,
 	if (cl->level == 0)
 		tcm->tcm_info = cl->qdisc->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 	if (hfsc_dump_curves(skb, cl) < 0)
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 9d6a47697406..43bc159c4f7c 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -654,7 +654,7 @@ static int hhf_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	struct nlattr *opts;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 2f9883b196e8..64010aec5437 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1057,7 +1057,7 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb)
 	gopt.defcls = q->defcls;
 	gopt.debug = 0;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 	if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) ||
@@ -1086,7 +1086,7 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg,
 	if (!cl->level && cl->leaf.q)
 		tcm->tcm_info = cl->leaf.q->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index ce3f55259d0d..0bac926b46c7 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -106,7 +106,7 @@ static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index ea0dc112b38d..7afefed72d35 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -349,7 +349,7 @@ static int dump_rates(struct mqprio_sched *priv,
 	int i;
 
 	if (priv->flags & TC_MQPRIO_F_MIN_RATE) {
-		nest = nla_nest_start(skb, TCA_MQPRIO_MIN_RATE64);
+		nest = nla_nest_start_noflag(skb, TCA_MQPRIO_MIN_RATE64);
 		if (!nest)
 			goto nla_put_failure;
 
@@ -363,7 +363,7 @@ static int dump_rates(struct mqprio_sched *priv,
 	}
 
 	if (priv->flags & TC_MQPRIO_F_MAX_RATE) {
-		nest = nla_nest_start(skb, TCA_MQPRIO_MAX_RATE64);
+		nest = nla_nest_start_noflag(skb, TCA_MQPRIO_MAX_RATE64);
 		if (!nest)
 			goto nla_put_failure;
 
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index cc9d8133afcd..0242c0d4a2d0 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -1079,7 +1079,7 @@ static int dump_loss_model(const struct netem_sched_data *q,
 {
 	struct nlattr *nest;
 
-	nest = nla_nest_start(skb, TCA_NETEM_LOSS);
+	nest = nla_nest_start_noflag(skb, TCA_NETEM_LOSS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 1cc0c7b74aa3..9bf41f4a2312 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -491,7 +491,7 @@ static int pie_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct pie_sched_data *q = qdisc_priv(sch);
 	struct nlattr *opts;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (!opts)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 1589364b54da..bab2d4026e8b 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -619,7 +619,7 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg,
 	tcm->tcm_handle	= cl->common.classid;
 	tcm->tcm_info	= cl->qdisc->handle;
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 	if (nla_put_u32(skb, TCA_QFQ_WEIGHT, cl->agg->class_weight) ||
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 4e8c0abf6194..b9f34e057e87 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -318,7 +318,7 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (err)
 		goto nla_put_failure;
 
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
 	if (nla_put(skb, TCA_RED_PARMS, sizeof(opt), &opt) ||
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 2419fdb75966..f54b00a431a3 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -580,7 +580,7 @@ static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb)
 	};
 
 	sch->qstats.backlog = q->qdisc->qstats.backlog;
-	opts = nla_nest_start(skb, TCA_OPTIONS);
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (opts == NULL)
 		goto nla_put_failure;
 	if (nla_put(skb, TCA_SFB_PARMS, sizeof(opt), &opt))
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index df848a36b222..e016ee07dd1f 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -841,7 +841,7 @@ static int dump_entry(struct sk_buff *msg,
 {
 	struct nlattr *item;
 
-	item = nla_nest_start(msg, TCA_TAPRIO_SCHED_ENTRY);
+	item = nla_nest_start_noflag(msg, TCA_TAPRIO_SCHED_ENTRY);
 	if (!item)
 		return -ENOSPC;
 
@@ -883,7 +883,7 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 		opt.offset[i] = dev->tc_to_txq[i].offset;
 	}
 
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (!nest)
 		return -ENOSPC;
 
@@ -897,7 +897,8 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid))
 		goto options_error;
 
-	entry_list = nla_nest_start(skb, TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST);
+	entry_list = nla_nest_start_noflag(skb,
+					   TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST);
 	if (!entry_list)
 		goto options_error;
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index f71578dbb9e3..3ae5a29eeab3 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -448,7 +448,7 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct tc_tbf_qopt opt;
 
 	sch->qstats.backlog = q->qdisc->qstats.backlog;
-	nest = nla_nest_start(skb, TCA_OPTIONS);
+	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index d27f30a9a01d..fd8e4e83f5e0 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -687,14 +687,14 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg,
 	if (!hdr)
 		return -EMSGSIZE;
 
-	attrs = nla_nest_start(msg->skb, TIPC_NLA_BEARER);
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER);
 	if (!attrs)
 		goto msg_full;
 
 	if (nla_put_string(msg->skb, TIPC_NLA_BEARER_NAME, bearer->name))
 		goto attr_msg_full;
 
-	prop = nla_nest_start(msg->skb, TIPC_NLA_BEARER_PROP);
+	prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_PROP);
 	if (!prop)
 		goto prop_msg_full;
 	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, bearer->priority))
@@ -1033,14 +1033,14 @@ static int __tipc_nl_add_media(struct tipc_nl_msg *msg,
 	if (!hdr)
 		return -EMSGSIZE;
 
-	attrs = nla_nest_start(msg->skb, TIPC_NLA_MEDIA);
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA);
 	if (!attrs)
 		goto msg_full;
 
 	if (nla_put_string(msg->skb, TIPC_NLA_MEDIA_NAME, media->name))
 		goto attr_msg_full;
 
-	prop = nla_nest_start(msg->skb, TIPC_NLA_MEDIA_PROP);
+	prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_MEDIA_PROP);
 	if (!prop)
 		goto prop_msg_full;
 	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, media->priority))
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 63f39201e41e..992be6113676 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -917,7 +917,7 @@ void tipc_group_member_evt(struct tipc_group *grp,
 
 int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb)
 {
-	struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP);
+	struct nlattr *group = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_GROUP);
 
 	if (!group)
 		return -EMSGSIZE;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 6053489c8063..0327c8ff8d48 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -2228,7 +2228,7 @@ static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s)
 			(s->accu_queue_sz / s->queue_sz_counts) : 0}
 	};
 
-	stats = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
+	stats = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS);
 	if (!stats)
 		return -EMSGSIZE;
 
@@ -2260,7 +2260,7 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg,
 	if (!hdr)
 		return -EMSGSIZE;
 
-	attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK);
 	if (!attrs)
 		goto msg_full;
 
@@ -2282,7 +2282,7 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg,
 		if (nla_put_flag(msg->skb, TIPC_NLA_LINK_ACTIVE))
 			goto attr_msg_full;
 
-	prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP);
+	prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP);
 	if (!prop)
 		goto attr_msg_full;
 	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_PRIO, link->priority))
@@ -2349,7 +2349,7 @@ static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb,
 			(stats->accu_queue_sz / stats->queue_sz_counts) : 0}
 	};
 
-	nest = nla_nest_start(skb, TIPC_NLA_LINK_STATS);
+	nest = nla_nest_start_noflag(skb, TIPC_NLA_LINK_STATS);
 	if (!nest)
 		return -EMSGSIZE;
 
@@ -2389,7 +2389,7 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
 		return -EMSGSIZE;
 	}
 
-	attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK);
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK);
 	if (!attrs)
 		goto msg_full;
 
@@ -2406,7 +2406,7 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg)
 	if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, 0))
 		goto attr_msg_full;
 
-	prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP);
+	prop = nla_nest_start_noflag(msg->skb, TIPC_NLA_LINK_PROP);
 	if (!prop)
 		goto attr_msg_full;
 	if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bcl->window))
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 67f69389ec17..6a6eae88442f 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -696,7 +696,7 @@ static int __tipc_nl_add_monitor_peer(struct tipc_peer *peer,
 	if (!hdr)
 		return -EMSGSIZE;
 
-	attrs = nla_nest_start(msg->skb, TIPC_NLA_MON_PEER);
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON_PEER);
 	if (!attrs)
 		goto msg_full;
 
@@ -785,7 +785,7 @@ int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg,
 	if (!hdr)
 		return -EMSGSIZE;
 
-	attrs = nla_nest_start(msg->skb, TIPC_NLA_MON);
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON);
 	if (!attrs)
 		goto msg_full;
 
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 89993afe0fbd..66a65c2cdb23 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -829,11 +829,11 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg,
 		if (!hdr)
 			return -EMSGSIZE;
 
-		attrs = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE);
+		attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NAME_TABLE);
 		if (!attrs)
 			goto msg_full;
 
-		b = nla_nest_start(msg->skb, TIPC_NLA_NAME_TABLE_PUBL);
+		b = nla_nest_start_noflag(msg->skb, TIPC_NLA_NAME_TABLE_PUBL);
 		if (!b)
 			goto attr_msg_full;
 
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 7ce1e86b024f..0bba4e6b005c 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -187,7 +187,7 @@ static int __tipc_nl_add_net(struct net *net, struct tipc_nl_msg *msg)
 	if (!hdr)
 		return -EMSGSIZE;
 
-	attrs = nla_nest_start(msg->skb, TIPC_NLA_NET);
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NET);
 	if (!attrs)
 		goto msg_full;
 
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 340a6e7c43a7..36fe2dbb6d87 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -399,7 +399,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd,
 
 	b = (struct tipc_bearer_config *)TLV_DATA(msg->req);
 
-	bearer = nla_nest_start(skb, TIPC_NLA_BEARER);
+	bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER);
 	if (!bearer)
 		return -EMSGSIZE;
 
@@ -419,7 +419,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd,
 		return -EMSGSIZE;
 
 	if (ntohl(b->priority) <= TIPC_MAX_LINK_PRI) {
-		prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP);
+		prop = nla_nest_start_noflag(skb, TIPC_NLA_BEARER_PROP);
 		if (!prop)
 			return -EMSGSIZE;
 		if (nla_put_u32(skb, TIPC_NLA_PROP_PRIO, ntohl(b->priority)))
@@ -441,7 +441,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd,
 
 	name = (char *)TLV_DATA(msg->req);
 
-	bearer = nla_nest_start(skb, TIPC_NLA_BEARER);
+	bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER);
 	if (!bearer)
 		return -EMSGSIZE;
 
@@ -685,7 +685,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb,
 
 	lc = (struct tipc_link_config *)TLV_DATA(msg->req);
 
-	media = nla_nest_start(skb, TIPC_NLA_MEDIA);
+	media = nla_nest_start_noflag(skb, TIPC_NLA_MEDIA);
 	if (!media)
 		return -EMSGSIZE;
 
@@ -696,7 +696,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb,
 	if (nla_put_string(skb, TIPC_NLA_MEDIA_NAME, lc->name))
 		return -EMSGSIZE;
 
-	prop = nla_nest_start(skb, TIPC_NLA_MEDIA_PROP);
+	prop = nla_nest_start_noflag(skb, TIPC_NLA_MEDIA_PROP);
 	if (!prop)
 		return -EMSGSIZE;
 
@@ -717,7 +717,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb,
 
 	lc = (struct tipc_link_config *)TLV_DATA(msg->req);
 
-	bearer = nla_nest_start(skb, TIPC_NLA_BEARER);
+	bearer = nla_nest_start_noflag(skb, TIPC_NLA_BEARER);
 	if (!bearer)
 		return -EMSGSIZE;
 
@@ -728,7 +728,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb,
 	if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, lc->name))
 		return -EMSGSIZE;
 
-	prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP);
+	prop = nla_nest_start_noflag(skb, TIPC_NLA_BEARER_PROP);
 	if (!prop)
 		return -EMSGSIZE;
 
@@ -748,14 +748,14 @@ static int __tipc_nl_compat_link_set(struct sk_buff *skb,
 
 	lc = (struct tipc_link_config *)TLV_DATA(msg->req);
 
-	link = nla_nest_start(skb, TIPC_NLA_LINK);
+	link = nla_nest_start_noflag(skb, TIPC_NLA_LINK);
 	if (!link)
 		return -EMSGSIZE;
 
 	if (nla_put_string(skb, TIPC_NLA_LINK_NAME, lc->name))
 		return -EMSGSIZE;
 
-	prop = nla_nest_start(skb, TIPC_NLA_LINK_PROP);
+	prop = nla_nest_start_noflag(skb, TIPC_NLA_LINK_PROP);
 	if (!prop)
 		return -EMSGSIZE;
 
@@ -811,7 +811,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd,
 
 	name = (char *)TLV_DATA(msg->req);
 
-	link = nla_nest_start(skb, TIPC_NLA_LINK);
+	link = nla_nest_start_noflag(skb, TIPC_NLA_LINK);
 	if (!link)
 		return -EMSGSIZE;
 
@@ -973,7 +973,7 @@ static int tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, u32 sock)
 		return -EMSGSIZE;
 	}
 
-	nest = nla_nest_start(args, TIPC_NLA_SOCK);
+	nest = nla_nest_start_noflag(args, TIPC_NLA_SOCK);
 	if (!nest) {
 		kfree_skb(args);
 		return -EMSGSIZE;
@@ -1100,7 +1100,7 @@ static int tipc_nl_compat_net_set(struct tipc_nl_compat_cmd_doit *cmd,
 
 	val = ntohl(*(__be32 *)TLV_DATA(msg->req));
 
-	net = nla_nest_start(skb, TIPC_NLA_NET);
+	net = nla_nest_start_noflag(skb, TIPC_NLA_NET);
 	if (!net)
 		return -EMSGSIZE;
 
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 7478e2d4ec02..3777254a508f 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1359,7 +1359,7 @@ static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node)
 	if (!hdr)
 		return -EMSGSIZE;
 
-	attrs = nla_nest_start(msg->skb, TIPC_NLA_NODE);
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_NODE);
 	if (!attrs)
 		goto msg_full;
 
@@ -2353,7 +2353,7 @@ static int __tipc_nl_add_monitor_prop(struct net *net, struct tipc_nl_msg *msg)
 	if (!hdr)
 		return -EMSGSIZE;
 
-	attrs = nla_nest_start(msg->skb, TIPC_NLA_MON);
+	attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON);
 	if (!attrs)
 		goto msg_full;
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 1385207a301f..7918f4763fdc 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -3273,7 +3273,7 @@ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk)
 	peer_node = tsk_peer_node(tsk);
 	peer_port = tsk_peer_port(tsk);
 
-	nest = nla_nest_start(skb, TIPC_NLA_SOCK_CON);
+	nest = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_CON);
 	if (!nest)
 		return -EMSGSIZE;
 
@@ -3332,7 +3332,7 @@ static int __tipc_nl_add_sk(struct sk_buff *skb, struct netlink_callback *cb,
 	if (!hdr)
 		goto msg_cancel;
 
-	attrs = nla_nest_start(skb, TIPC_NLA_SOCK);
+	attrs = nla_nest_start_noflag(skb, TIPC_NLA_SOCK);
 	if (!attrs)
 		goto genlmsg_cancel;
 
@@ -3437,7 +3437,7 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb,
 	if (!(sk_filter_state & (1 << sk->sk_state)))
 		return 0;
 
-	attrs = nla_nest_start(skb, TIPC_NLA_SOCK);
+	attrs = nla_nest_start_noflag(skb, TIPC_NLA_SOCK);
 	if (!attrs)
 		goto msg_cancel;
 
@@ -3455,7 +3455,7 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb,
 			      TIPC_NLA_SOCK_PAD))
 		goto attr_msg_cancel;
 
-	stat = nla_nest_start(skb, TIPC_NLA_SOCK_STAT);
+	stat = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_STAT);
 	if (!stat)
 		goto attr_msg_cancel;
 
@@ -3512,7 +3512,7 @@ static int __tipc_nl_add_sk_publ(struct sk_buff *skb,
 	if (!hdr)
 		goto msg_cancel;
 
-	attrs = nla_nest_start(skb, TIPC_NLA_PUBL);
+	attrs = nla_nest_start_noflag(skb, TIPC_NLA_PUBL);
 	if (!attrs)
 		goto genlmsg_cancel;
 
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 0884a1b8ad12..24d7c79598bb 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -523,7 +523,7 @@ int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b)
 	if (!ub)
 		return -ENODEV;
 
-	nest = nla_nest_start(msg->skb, TIPC_NLA_BEARER_UDP_OPTS);
+	nest = nla_nest_start_noflag(msg->skb, TIPC_NLA_BEARER_UDP_OPTS);
 	if (!nest)
 		goto msg_full;
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e74d21f4108a..0bcd5ea4b4f2 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -755,13 +755,13 @@ static int nl80211_msg_put_wmm_rules(struct sk_buff *msg,
 {
 	int j;
 	struct nlattr *nl_wmm_rules =
-		nla_nest_start(msg, NL80211_FREQUENCY_ATTR_WMM);
+		nla_nest_start_noflag(msg, NL80211_FREQUENCY_ATTR_WMM);
 
 	if (!nl_wmm_rules)
 		goto nla_put_failure;
 
 	for (j = 0; j < IEEE80211_NUM_ACS; j++) {
-		struct nlattr *nl_wmm_rule = nla_nest_start(msg, j);
+		struct nlattr *nl_wmm_rule = nla_nest_start_noflag(msg, j);
 
 		if (!nl_wmm_rule)
 			goto nla_put_failure;
@@ -890,7 +890,7 @@ static bool nl80211_put_txq_stats(struct sk_buff *msg,
 		return false;						  \
 	} while (0)
 
-	txqattr = nla_nest_start(msg, attrtype);
+	txqattr = nla_nest_start_noflag(msg, attrtype);
 	if (!txqattr)
 		return false;
 
@@ -1205,7 +1205,7 @@ static struct ieee80211_channel *nl80211_get_valid_chan(struct wiphy *wiphy,
 
 static int nl80211_put_iftypes(struct sk_buff *msg, u32 attr, u16 ifmodes)
 {
-	struct nlattr *nl_modes = nla_nest_start(msg, attr);
+	struct nlattr *nl_modes = nla_nest_start_noflag(msg, attr);
 	int i;
 
 	if (!nl_modes)
@@ -1233,8 +1233,8 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy,
 	struct nlattr *nl_combis;
 	int i, j;
 
-	nl_combis = nla_nest_start(msg,
-				NL80211_ATTR_INTERFACE_COMBINATIONS);
+	nl_combis = nla_nest_start_noflag(msg,
+					  NL80211_ATTR_INTERFACE_COMBINATIONS);
 	if (!nl_combis)
 		goto nla_put_failure;
 
@@ -1244,18 +1244,19 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy,
 
 		c = &wiphy->iface_combinations[i];
 
-		nl_combi = nla_nest_start(msg, i + 1);
+		nl_combi = nla_nest_start_noflag(msg, i + 1);
 		if (!nl_combi)
 			goto nla_put_failure;
 
-		nl_limits = nla_nest_start(msg, NL80211_IFACE_COMB_LIMITS);
+		nl_limits = nla_nest_start_noflag(msg,
+						  NL80211_IFACE_COMB_LIMITS);
 		if (!nl_limits)
 			goto nla_put_failure;
 
 		for (j = 0; j < c->n_limits; j++) {
 			struct nlattr *nl_limit;
 
-			nl_limit = nla_nest_start(msg, j + 1);
+			nl_limit = nla_nest_start_noflag(msg, j + 1);
 			if (!nl_limit)
 				goto nla_put_failure;
 			if (nla_put_u32(msg, NL80211_IFACE_LIMIT_MAX,
@@ -1308,7 +1309,8 @@ static int nl80211_send_wowlan_tcp_caps(struct cfg80211_registered_device *rdev,
 	if (!tcp)
 		return 0;
 
-	nl_tcp = nla_nest_start(msg, NL80211_WOWLAN_TRIG_TCP_CONNECTION);
+	nl_tcp = nla_nest_start_noflag(msg,
+				       NL80211_WOWLAN_TRIG_TCP_CONNECTION);
 	if (!nl_tcp)
 		return -ENOBUFS;
 
@@ -1348,7 +1350,8 @@ static int nl80211_send_wowlan(struct sk_buff *msg,
 	if (!rdev->wiphy.wowlan)
 		return 0;
 
-	nl_wowlan = nla_nest_start(msg, NL80211_ATTR_WOWLAN_TRIGGERS_SUPPORTED);
+	nl_wowlan = nla_nest_start_noflag(msg,
+					  NL80211_ATTR_WOWLAN_TRIGGERS_SUPPORTED);
 	if (!nl_wowlan)
 		return -ENOBUFS;
 
@@ -1477,7 +1480,8 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg,
 
 	if (sband->n_iftype_data) {
 		struct nlattr *nl_iftype_data =
-			nla_nest_start(msg, NL80211_BAND_ATTR_IFTYPE_DATA);
+			nla_nest_start_noflag(msg,
+					      NL80211_BAND_ATTR_IFTYPE_DATA);
 		int err;
 
 		if (!nl_iftype_data)
@@ -1486,7 +1490,7 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg,
 		for (i = 0; i < sband->n_iftype_data; i++) {
 			struct nlattr *iftdata;
 
-			iftdata = nla_nest_start(msg, i + 1);
+			iftdata = nla_nest_start_noflag(msg, i + 1);
 			if (!iftdata)
 				return -ENOBUFS;
 
@@ -1502,12 +1506,12 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg,
 	}
 
 	/* add bitrates */
-	nl_rates = nla_nest_start(msg, NL80211_BAND_ATTR_RATES);
+	nl_rates = nla_nest_start_noflag(msg, NL80211_BAND_ATTR_RATES);
 	if (!nl_rates)
 		return -ENOBUFS;
 
 	for (i = 0; i < sband->n_bitrates; i++) {
-		nl_rate = nla_nest_start(msg, i);
+		nl_rate = nla_nest_start_noflag(msg, i);
 		if (!nl_rate)
 			return -ENOBUFS;
 
@@ -1540,12 +1544,12 @@ nl80211_send_mgmt_stypes(struct sk_buff *msg,
 	if (!mgmt_stypes)
 		return 0;
 
-	nl_ifs = nla_nest_start(msg, NL80211_ATTR_TX_FRAME_TYPES);
+	nl_ifs = nla_nest_start_noflag(msg, NL80211_ATTR_TX_FRAME_TYPES);
 	if (!nl_ifs)
 		return -ENOBUFS;
 
 	for (ift = 0; ift < NUM_NL80211_IFTYPES; ift++) {
-		nl_ftypes = nla_nest_start(msg, ift);
+		nl_ftypes = nla_nest_start_noflag(msg, ift);
 		if (!nl_ftypes)
 			return -ENOBUFS;
 		i = 0;
@@ -1563,12 +1567,12 @@ nl80211_send_mgmt_stypes(struct sk_buff *msg,
 
 	nla_nest_end(msg, nl_ifs);
 
-	nl_ifs = nla_nest_start(msg, NL80211_ATTR_RX_FRAME_TYPES);
+	nl_ifs = nla_nest_start_noflag(msg, NL80211_ATTR_RX_FRAME_TYPES);
 	if (!nl_ifs)
 		return -ENOBUFS;
 
 	for (ift = 0; ift < NUM_NL80211_IFTYPES; ift++) {
-		nl_ftypes = nla_nest_start(msg, ift);
+		nl_ftypes = nla_nest_start_noflag(msg, ift);
 		if (!nl_ftypes)
 			return -ENOBUFS;
 		i = 0;
@@ -1686,7 +1690,7 @@ nl80211_send_pmsr_ftm_capa(const struct cfg80211_pmsr_capabilities *cap,
 	if (!cap->ftm.supported)
 		return 0;
 
-	ftm = nla_nest_start(msg, NL80211_PMSR_TYPE_FTM);
+	ftm = nla_nest_start_noflag(msg, NL80211_PMSR_TYPE_FTM);
 	if (!ftm)
 		return -ENOBUFS;
 
@@ -1734,7 +1738,7 @@ static int nl80211_send_pmsr_capa(struct cfg80211_registered_device *rdev,
 	 * will genlmsg_cancel() if we fail
 	 */
 
-	pmsr = nla_nest_start(msg, NL80211_ATTR_PEER_MEASUREMENTS);
+	pmsr = nla_nest_start_noflag(msg, NL80211_ATTR_PEER_MEASUREMENTS);
 	if (!pmsr)
 		return -ENOBUFS;
 
@@ -1749,7 +1753,7 @@ static int nl80211_send_pmsr_capa(struct cfg80211_registered_device *rdev,
 	    nla_put_flag(msg, NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR))
 		return -ENOBUFS;
 
-	caps = nla_nest_start(msg, NL80211_PMSR_ATTR_TYPE_CAPA);
+	caps = nla_nest_start_noflag(msg, NL80211_PMSR_ATTR_TYPE_CAPA);
 	if (!caps)
 		return -ENOBUFS;
 
@@ -1910,7 +1914,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			break;
 		/* fall through */
 	case 3:
-		nl_bands = nla_nest_start(msg, NL80211_ATTR_WIPHY_BANDS);
+		nl_bands = nla_nest_start_noflag(msg,
+						 NL80211_ATTR_WIPHY_BANDS);
 		if (!nl_bands)
 			goto nla_put_failure;
 
@@ -1923,7 +1928,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			if (!sband)
 				continue;
 
-			nl_band = nla_nest_start(msg, band);
+			nl_band = nla_nest_start_noflag(msg, band);
 			if (!nl_band)
 				goto nla_put_failure;
 
@@ -1937,15 +1942,16 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 				/* fall through */
 			default:
 				/* add frequencies */
-				nl_freqs = nla_nest_start(
-					msg, NL80211_BAND_ATTR_FREQS);
+				nl_freqs = nla_nest_start_noflag(msg,
+								 NL80211_BAND_ATTR_FREQS);
 				if (!nl_freqs)
 					goto nla_put_failure;
 
 				for (i = state->chan_start - 1;
 				     i < sband->n_channels;
 				     i++) {
-					nl_freq = nla_nest_start(msg, i);
+					nl_freq = nla_nest_start_noflag(msg,
+									i);
 					if (!nl_freq)
 						goto nla_put_failure;
 
@@ -1990,7 +1996,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			break;
 		/* fall through */
 	case 4:
-		nl_cmds = nla_nest_start(msg, NL80211_ATTR_SUPPORTED_COMMANDS);
+		nl_cmds = nla_nest_start_noflag(msg,
+						NL80211_ATTR_SUPPORTED_COMMANDS);
 		if (!nl_cmds)
 			goto nla_put_failure;
 
@@ -2138,7 +2145,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			const struct nl80211_vendor_cmd_info *info;
 			struct nlattr *nested;
 
-			nested = nla_nest_start(msg, NL80211_ATTR_VENDOR_DATA);
+			nested = nla_nest_start_noflag(msg,
+						       NL80211_ATTR_VENDOR_DATA);
 			if (!nested)
 				goto nla_put_failure;
 
@@ -2154,8 +2162,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			const struct nl80211_vendor_cmd_info *info;
 			struct nlattr *nested;
 
-			nested = nla_nest_start(msg,
-						NL80211_ATTR_VENDOR_EVENTS);
+			nested = nla_nest_start_noflag(msg,
+						       NL80211_ATTR_VENDOR_EVENTS);
 			if (!nested)
 				goto nla_put_failure;
 
@@ -2192,7 +2200,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			struct nlattr *nested;
 			u32 bss_select_support = rdev->wiphy.bss_select_support;
 
-			nested = nla_nest_start(msg, NL80211_ATTR_BSS_SELECT);
+			nested = nla_nest_start_noflag(msg,
+						       NL80211_ATTR_BSS_SELECT);
 			if (!nested)
 				goto nla_put_failure;
 
@@ -2214,8 +2223,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		    rdev->wiphy.iftype_ext_capab) {
 			struct nlattr *nested_ext_capab, *nested;
 
-			nested = nla_nest_start(msg,
-						NL80211_ATTR_IFTYPE_EXT_CAPA);
+			nested = nla_nest_start_noflag(msg,
+						       NL80211_ATTR_IFTYPE_EXT_CAPA);
 			if (!nested)
 				goto nla_put_failure;
 
@@ -2225,7 +2234,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 
 				capab = &rdev->wiphy.iftype_ext_capab[i];
 
-				nested_ext_capab = nla_nest_start(msg, i);
+				nested_ext_capab = nla_nest_start_noflag(msg,
+									 i);
 				if (!nested_ext_capab ||
 				    nla_put_u32(msg, NL80211_ATTR_IFTYPE,
 						capab->iftype) ||
@@ -3539,7 +3549,7 @@ static void get_key_callback(void *c, struct key_params *params)
 			 params->cipher)))
 		goto nla_put_failure;
 
-	key = nla_nest_start(cookie->msg, NL80211_ATTR_KEY);
+	key = nla_nest_start_noflag(cookie->msg, NL80211_ATTR_KEY);
 	if (!key)
 		goto nla_put_failure;
 
@@ -4723,7 +4733,7 @@ bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info, int attr)
 	u16 bitrate_compat;
 	enum nl80211_rate_info rate_flg;
 
-	rate = nla_nest_start(msg, attr);
+	rate = nla_nest_start_noflag(msg, attr);
 	if (!rate)
 		return false;
 
@@ -4810,7 +4820,7 @@ static bool nl80211_put_signal(struct sk_buff *msg, u8 mask, s8 *signal,
 	if (!mask)
 		return true;
 
-	attr = nla_nest_start(msg, id);
+	attr = nla_nest_start_noflag(msg, id);
 	if (!attr)
 		return false;
 
@@ -4845,7 +4855,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	    nla_put_u32(msg, NL80211_ATTR_GENERATION, sinfo->generation))
 		goto nla_put_failure;
 
-	sinfoattr = nla_nest_start(msg, NL80211_ATTR_STA_INFO);
+	sinfoattr = nla_nest_start_noflag(msg, NL80211_ATTR_STA_INFO);
 	if (!sinfoattr)
 		goto nla_put_failure;
 
@@ -4934,7 +4944,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	PUT_SINFO(CONNECTED_TO_GATE, connected_to_gate, u8);
 
 	if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_BSS_PARAM)) {
-		bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM);
+		bss_param = nla_nest_start_noflag(msg,
+						  NL80211_STA_INFO_BSS_PARAM);
 		if (!bss_param)
 			goto nla_put_failure;
 
@@ -4977,7 +4988,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 		struct nlattr *tidsattr;
 		int tid;
 
-		tidsattr = nla_nest_start(msg, NL80211_STA_INFO_TID_STATS);
+		tidsattr = nla_nest_start_noflag(msg,
+						 NL80211_STA_INFO_TID_STATS);
 		if (!tidsattr)
 			goto nla_put_failure;
 
@@ -4990,7 +5002,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 			if (!tidstats->filled)
 				continue;
 
-			tidattr = nla_nest_start(msg, tid + 1);
+			tidattr = nla_nest_start_noflag(msg, tid + 1);
 			if (!tidattr)
 				goto nla_put_failure;
 
@@ -5875,7 +5887,7 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq,
 	    nla_put_u32(msg, NL80211_ATTR_GENERATION, pinfo->generation))
 		goto nla_put_failure;
 
-	pinfoattr = nla_nest_start(msg, NL80211_ATTR_MPATH_INFO);
+	pinfoattr = nla_nest_start_noflag(msg, NL80211_ATTR_MPATH_INFO);
 	if (!pinfoattr)
 		goto nla_put_failure;
 	if ((pinfo->filled & MPATH_INFO_FRAME_QLEN) &&
@@ -6326,7 +6338,7 @@ static int nl80211_get_mesh_config(struct sk_buff *skb,
 			     NL80211_CMD_GET_MESH_CONFIG);
 	if (!hdr)
 		goto out;
-	pinfoattr = nla_nest_start(msg, NL80211_ATTR_MESH_CONFIG);
+	pinfoattr = nla_nest_start_noflag(msg, NL80211_ATTR_MESH_CONFIG);
 	if (!pinfoattr)
 		goto nla_put_failure;
 	if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
@@ -6705,7 +6717,7 @@ static int nl80211_put_regdom(const struct ieee80211_regdomain *regdom,
 	     nla_put_u8(msg, NL80211_ATTR_DFS_REGION, regdom->dfs_region)))
 		goto nla_put_failure;
 
-	nl_reg_rules = nla_nest_start(msg, NL80211_ATTR_REG_RULES);
+	nl_reg_rules = nla_nest_start_noflag(msg, NL80211_ATTR_REG_RULES);
 	if (!nl_reg_rules)
 		goto nla_put_failure;
 
@@ -6720,7 +6732,7 @@ static int nl80211_put_regdom(const struct ieee80211_regdomain *regdom,
 		freq_range = &reg_rule->freq_range;
 		power_rule = &reg_rule->power_rule;
 
-		nl_reg_rule = nla_nest_start(msg, i);
+		nl_reg_rule = nla_nest_start_noflag(msg, i);
 		if (!nl_reg_rule)
 			goto nla_put_failure;
 
@@ -8389,7 +8401,7 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 			      NL80211_ATTR_PAD))
 		goto nla_put_failure;
 
-	bss = nla_nest_start(msg, NL80211_ATTR_BSS);
+	bss = nla_nest_start_noflag(msg, NL80211_ATTR_BSS);
 	if (!bss)
 		goto nla_put_failure;
 	if ((!is_zero_ether_addr(res->bssid) &&
@@ -8566,7 +8578,7 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 	if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
 
-	infoattr = nla_nest_start(msg, NL80211_ATTR_SURVEY_INFO);
+	infoattr = nla_nest_start_noflag(msg, NL80211_ATTR_SURVEY_INFO);
 	if (!infoattr)
 		goto nla_put_failure;
 
@@ -9407,7 +9419,7 @@ __cfg80211_alloc_vendor_skb(struct cfg80211_registered_device *rdev,
 			goto nla_put_failure;
 	}
 
-	data = nla_nest_start(skb, attr);
+	data = nla_nest_start_noflag(skb, attr);
 	if (!data)
 		goto nla_put_failure;
 
@@ -9581,7 +9593,7 @@ static int nl80211_testmode_dump(struct sk_buff *skb,
 			break;
 		}
 
-		tmdata = nla_nest_start(skb, NL80211_ATTR_TESTDATA);
+		tmdata = nla_nest_start_noflag(skb, NL80211_ATTR_TESTDATA);
 		if (!tmdata) {
 			genlmsg_cancel(skb, hdr);
 			break;
@@ -10859,12 +10871,12 @@ static int nl80211_send_wowlan_patterns(struct sk_buff *msg,
 	if (!wowlan->n_patterns)
 		return 0;
 
-	nl_pats = nla_nest_start(msg, NL80211_WOWLAN_TRIG_PKT_PATTERN);
+	nl_pats = nla_nest_start_noflag(msg, NL80211_WOWLAN_TRIG_PKT_PATTERN);
 	if (!nl_pats)
 		return -ENOBUFS;
 
 	for (i = 0; i < wowlan->n_patterns; i++) {
-		nl_pat = nla_nest_start(msg, i + 1);
+		nl_pat = nla_nest_start_noflag(msg, i + 1);
 		if (!nl_pat)
 			return -ENOBUFS;
 		pat_len = wowlan->patterns[i].pattern_len;
@@ -10890,7 +10902,8 @@ static int nl80211_send_wowlan_tcp(struct sk_buff *msg,
 	if (!tcp)
 		return 0;
 
-	nl_tcp = nla_nest_start(msg, NL80211_WOWLAN_TRIG_TCP_CONNECTION);
+	nl_tcp = nla_nest_start_noflag(msg,
+				       NL80211_WOWLAN_TRIG_TCP_CONNECTION);
 	if (!nl_tcp)
 		return -ENOBUFS;
 
@@ -10934,7 +10947,7 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg,
 	if (!req)
 		return 0;
 
-	nd = nla_nest_start(msg, NL80211_WOWLAN_TRIG_NET_DETECT);
+	nd = nla_nest_start_noflag(msg, NL80211_WOWLAN_TRIG_NET_DETECT);
 	if (!nd)
 		return -ENOBUFS;
 
@@ -10960,7 +10973,7 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg,
 			return -ENOBUFS;
 	}
 
-	freqs = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES);
+	freqs = nla_nest_start_noflag(msg, NL80211_ATTR_SCAN_FREQUENCIES);
 	if (!freqs)
 		return -ENOBUFS;
 
@@ -10972,12 +10985,13 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg,
 	nla_nest_end(msg, freqs);
 
 	if (req->n_match_sets) {
-		matches = nla_nest_start(msg, NL80211_ATTR_SCHED_SCAN_MATCH);
+		matches = nla_nest_start_noflag(msg,
+						NL80211_ATTR_SCHED_SCAN_MATCH);
 		if (!matches)
 			return -ENOBUFS;
 
 		for (i = 0; i < req->n_match_sets; i++) {
-			match = nla_nest_start(msg, i);
+			match = nla_nest_start_noflag(msg, i);
 			if (!match)
 				return -ENOBUFS;
 
@@ -10990,12 +11004,12 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg,
 		nla_nest_end(msg, matches);
 	}
 
-	scan_plans = nla_nest_start(msg, NL80211_ATTR_SCHED_SCAN_PLANS);
+	scan_plans = nla_nest_start_noflag(msg, NL80211_ATTR_SCHED_SCAN_PLANS);
 	if (!scan_plans)
 		return -ENOBUFS;
 
 	for (i = 0; i < req->n_scan_plans; i++) {
-		scan_plan = nla_nest_start(msg, i + 1);
+		scan_plan = nla_nest_start_noflag(msg, i + 1);
 		if (!scan_plan)
 			return -ENOBUFS;
 
@@ -11044,7 +11058,8 @@ static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info)
 	if (rdev->wiphy.wowlan_config) {
 		struct nlattr *nl_wowlan;
 
-		nl_wowlan = nla_nest_start(msg, NL80211_ATTR_WOWLAN_TRIGGERS);
+		nl_wowlan = nla_nest_start_noflag(msg,
+						  NL80211_ATTR_WOWLAN_TRIGGERS);
 		if (!nl_wowlan)
 			goto nla_put_failure;
 
@@ -11478,12 +11493,12 @@ static int nl80211_send_coalesce_rules(struct sk_buff *msg,
 	if (!rdev->coalesce->n_rules)
 		return 0;
 
-	nl_rules = nla_nest_start(msg, NL80211_ATTR_COALESCE_RULE);
+	nl_rules = nla_nest_start_noflag(msg, NL80211_ATTR_COALESCE_RULE);
 	if (!nl_rules)
 		return -ENOBUFS;
 
 	for (i = 0; i < rdev->coalesce->n_rules; i++) {
-		nl_rule = nla_nest_start(msg, i + 1);
+		nl_rule = nla_nest_start_noflag(msg, i + 1);
 		if (!nl_rule)
 			return -ENOBUFS;
 
@@ -11496,13 +11511,13 @@ static int nl80211_send_coalesce_rules(struct sk_buff *msg,
 				rule->condition))
 			return -ENOBUFS;
 
-		nl_pats = nla_nest_start(msg,
-				NL80211_ATTR_COALESCE_RULE_PKT_PATTERN);
+		nl_pats = nla_nest_start_noflag(msg,
+						NL80211_ATTR_COALESCE_RULE_PKT_PATTERN);
 		if (!nl_pats)
 			return -ENOBUFS;
 
 		for (j = 0; j < rule->n_patterns; j++) {
-			nl_pat = nla_nest_start(msg, j + 1);
+			nl_pat = nla_nest_start_noflag(msg, j + 1);
 			if (!nl_pat)
 				return -ENOBUFS;
 			pat_len = rule->patterns[j].pattern_len;
@@ -12254,7 +12269,7 @@ out:
 			      NL80211_ATTR_PAD))
 		goto nla_put_failure;
 
-	func_attr = nla_nest_start(msg, NL80211_ATTR_NAN_FUNC);
+	func_attr = nla_nest_start_noflag(msg, NL80211_ATTR_NAN_FUNC);
 	if (!func_attr)
 		goto nla_put_failure;
 
@@ -12371,11 +12386,12 @@ void cfg80211_nan_match(struct wireless_dev *wdev,
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, match->addr))
 		goto nla_put_failure;
 
-	match_attr = nla_nest_start(msg, NL80211_ATTR_NAN_MATCH);
+	match_attr = nla_nest_start_noflag(msg, NL80211_ATTR_NAN_MATCH);
 	if (!match_attr)
 		goto nla_put_failure;
 
-	local_func_attr = nla_nest_start(msg, NL80211_NAN_MATCH_FUNC_LOCAL);
+	local_func_attr = nla_nest_start_noflag(msg,
+						NL80211_NAN_MATCH_FUNC_LOCAL);
 	if (!local_func_attr)
 		goto nla_put_failure;
 
@@ -12384,7 +12400,8 @@ void cfg80211_nan_match(struct wireless_dev *wdev,
 
 	nla_nest_end(msg, local_func_attr);
 
-	peer_func_attr = nla_nest_start(msg, NL80211_NAN_MATCH_FUNC_PEER);
+	peer_func_attr = nla_nest_start_noflag(msg,
+					       NL80211_NAN_MATCH_FUNC_PEER);
 	if (!peer_func_attr)
 		goto nla_put_failure;
 
@@ -12450,7 +12467,7 @@ void cfg80211_nan_func_terminated(struct wireless_dev *wdev,
 			      NL80211_ATTR_PAD))
 		goto nla_put_failure;
 
-	func_attr = nla_nest_start(msg, NL80211_ATTR_NAN_FUNC);
+	func_attr = nla_nest_start_noflag(msg, NL80211_ATTR_NAN_FUNC);
 	if (!func_attr)
 		goto nla_put_failure;
 
@@ -12799,7 +12816,8 @@ static int nl80211_vendor_cmd_dump(struct sk_buff *skb,
 			break;
 		}
 
-		vendor_data = nla_nest_start(skb, NL80211_ATTR_VENDOR_DATA);
+		vendor_data = nla_nest_start_noflag(skb,
+						    NL80211_ATTR_VENDOR_DATA);
 		if (!vendor_data) {
 			genlmsg_cancel(skb, hdr);
 			break;
@@ -13343,7 +13361,8 @@ static int nl80211_get_ftm_responder_stats(struct sk_buff *skb,
 	if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
 
-	ftm_stats_attr = nla_nest_start(msg, NL80211_ATTR_FTM_RESPONDER_STATS);
+	ftm_stats_attr = nla_nest_start_noflag(msg,
+					       NL80211_ATTR_FTM_RESPONDER_STATS);
 	if (!ftm_stats_attr)
 		goto nla_put_failure;
 
@@ -14366,7 +14385,7 @@ static int nl80211_add_scan_req(struct sk_buff *msg,
 	if (WARN_ON(!req))
 		return 0;
 
-	nest = nla_nest_start(msg, NL80211_ATTR_SCAN_SSIDS);
+	nest = nla_nest_start_noflag(msg, NL80211_ATTR_SCAN_SSIDS);
 	if (!nest)
 		goto nla_put_failure;
 	for (i = 0; i < req->n_ssids; i++) {
@@ -14375,7 +14394,7 @@ static int nl80211_add_scan_req(struct sk_buff *msg,
 	}
 	nla_nest_end(msg, nest);
 
-	nest = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES);
+	nest = nla_nest_start_noflag(msg, NL80211_ATTR_SCAN_FREQUENCIES);
 	if (!nest)
 		goto nla_put_failure;
 	for (i = 0; i < req->n_channels; i++) {
@@ -14637,7 +14656,7 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev,
 
 	if (uapsd_queues >= 0) {
 		struct nlattr *nla_wmm =
-			nla_nest_start(msg, NL80211_ATTR_STA_WME);
+			nla_nest_start_noflag(msg, NL80211_ATTR_STA_WME);
 		if (!nla_wmm)
 			goto nla_put_failure;
 
@@ -15078,7 +15097,7 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy,
 		goto nla_put_failure;
 
 	/* Before */
-	nl_freq = nla_nest_start(msg, NL80211_ATTR_FREQ_BEFORE);
+	nl_freq = nla_nest_start_noflag(msg, NL80211_ATTR_FREQ_BEFORE);
 	if (!nl_freq)
 		goto nla_put_failure;
 
@@ -15087,7 +15106,7 @@ void nl80211_send_beacon_hint_event(struct wiphy *wiphy,
 	nla_nest_end(msg, nl_freq);
 
 	/* After */
-	nl_freq = nla_nest_start(msg, NL80211_ATTR_FREQ_AFTER);
+	nl_freq = nla_nest_start_noflag(msg, NL80211_ATTR_FREQ_AFTER);
 	if (!nl_freq)
 		goto nla_put_failure;
 
@@ -15521,7 +15540,7 @@ static struct sk_buff *cfg80211_prepare_cqm(struct net_device *dev,
 	if (mac && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac))
 		goto nla_put_failure;
 
-	cb[1] = nla_nest_start(msg, NL80211_ATTR_CQM);
+	cb[1] = nla_nest_start_noflag(msg, NL80211_ATTR_CQM);
 	if (!cb[1])
 		goto nla_put_failure;
 
@@ -15682,7 +15701,7 @@ static void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev,
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid))
 		goto nla_put_failure;
 
-	rekey_attr = nla_nest_start(msg, NL80211_ATTR_REKEY_DATA);
+	rekey_attr = nla_nest_start_noflag(msg, NL80211_ATTR_REKEY_DATA);
 	if (!rekey_attr)
 		goto nla_put_failure;
 
@@ -15737,7 +15756,7 @@ nl80211_pmksa_candidate_notify(struct cfg80211_registered_device *rdev,
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex))
 		goto nla_put_failure;
 
-	attr = nla_nest_start(msg, NL80211_ATTR_PMKSA_CANDIDATE);
+	attr = nla_nest_start_noflag(msg, NL80211_ATTR_PMKSA_CANDIDATE);
 	if (!attr)
 		goto nla_put_failure;
 
@@ -16047,15 +16066,15 @@ static int cfg80211_net_detect_results(struct sk_buff *msg,
 	struct nlattr *nl_results, *nl_match, *nl_freqs;
 	int i, j;
 
-	nl_results = nla_nest_start(
-		msg, NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS);
+	nl_results = nla_nest_start_noflag(msg,
+					   NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS);
 	if (!nl_results)
 		return -EMSGSIZE;
 
 	for (i = 0; i < nd->n_matches; i++) {
 		struct cfg80211_wowlan_nd_match *match = nd->matches[i];
 
-		nl_match = nla_nest_start(msg, i);
+		nl_match = nla_nest_start_noflag(msg, i);
 		if (!nl_match)
 			break;
 
@@ -16073,8 +16092,8 @@ static int cfg80211_net_detect_results(struct sk_buff *msg,
 		}
 
 		if (match->n_channels) {
-			nl_freqs = nla_nest_start(
-				msg, NL80211_ATTR_SCAN_FREQUENCIES);
+			nl_freqs = nla_nest_start_noflag(msg,
+							 NL80211_ATTR_SCAN_FREQUENCIES);
 			if (!nl_freqs) {
 				nla_nest_cancel(msg, nl_match);
 				goto out;
@@ -16133,7 +16152,8 @@ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev,
 	if (wakeup) {
 		struct nlattr *reasons;
 
-		reasons = nla_nest_start(msg, NL80211_ATTR_WOWLAN_TRIGGERS);
+		reasons = nla_nest_start_noflag(msg,
+						NL80211_ATTR_WOWLAN_TRIGGERS);
 		if (!reasons)
 			goto free_msg;
 
diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c
index 5e2ab01d325c..5c80bccc8b3c 100644
--- a/net/wireless/pmsr.c
+++ b/net/wireless/pmsr.c
@@ -420,22 +420,22 @@ static int nl80211_pmsr_send_result(struct sk_buff *msg,
 {
 	struct nlattr *pmsr, *peers, *peer, *resp, *data, *typedata;
 
-	pmsr = nla_nest_start(msg, NL80211_ATTR_PEER_MEASUREMENTS);
+	pmsr = nla_nest_start_noflag(msg, NL80211_ATTR_PEER_MEASUREMENTS);
 	if (!pmsr)
 		goto error;
 
-	peers = nla_nest_start(msg, NL80211_PMSR_ATTR_PEERS);
+	peers = nla_nest_start_noflag(msg, NL80211_PMSR_ATTR_PEERS);
 	if (!peers)
 		goto error;
 
-	peer = nla_nest_start(msg, 1);
+	peer = nla_nest_start_noflag(msg, 1);
 	if (!peer)
 		goto error;
 
 	if (nla_put(msg, NL80211_PMSR_PEER_ATTR_ADDR, ETH_ALEN, res->addr))
 		goto error;
 
-	resp = nla_nest_start(msg, NL80211_PMSR_PEER_ATTR_RESP);
+	resp = nla_nest_start_noflag(msg, NL80211_PMSR_PEER_ATTR_RESP);
 	if (!resp)
 		goto error;
 
@@ -452,11 +452,11 @@ static int nl80211_pmsr_send_result(struct sk_buff *msg,
 	if (res->final && nla_put_flag(msg, NL80211_PMSR_RESP_ATTR_FINAL))
 		goto error;
 
-	data = nla_nest_start(msg, NL80211_PMSR_RESP_ATTR_DATA);
+	data = nla_nest_start_noflag(msg, NL80211_PMSR_RESP_ATTR_DATA);
 	if (!data)
 		goto error;
 
-	typedata = nla_nest_start(msg, res->type);
+	typedata = nla_nest_start_noflag(msg, res->type);
 	if (!typedata)
 		goto error;
 
-- 
cgit v1.2.3


From 12ad5f65f030ae7b8a2425f6f79137c4217e30d4 Mon Sep 17 00:00:00 2001
From: Michal Kubecek <mkubecek@suse.cz>
Date: Fri, 26 Apr 2019 11:13:09 +0200
Subject: ipset: drop ipset_nest_start() and ipset_nest_end()

After the previous commit, both ipset_nest_start() and ipset_nest_end() are
just aliases for nla_nest_start() and nla_nest_end() so that there is no
need to keep them.

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Acked-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netfilter/ipset/ip_set.h  | 11 ++++-------
 net/netfilter/ipset/ip_set_bitmap_gen.h | 14 +++++++-------
 net/netfilter/ipset/ip_set_hash_gen.h   | 14 +++++++-------
 net/netfilter/ipset/ip_set_list_set.c   | 14 +++++++-------
 4 files changed, 25 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 965dc6c6653e..e499d170f12d 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -401,33 +401,30 @@ ip_set_get_h16(const struct nlattr *attr)
 	return ntohs(nla_get_be16(attr));
 }
 
-#define ipset_nest_start(skb, attr) nla_nest_start(skb, attr)
-#define ipset_nest_end(skb, start)  nla_nest_end(skb, start)
-
 static inline int nla_put_ipaddr4(struct sk_buff *skb, int type, __be32 ipaddr)
 {
-	struct nlattr *__nested = ipset_nest_start(skb, type);
+	struct nlattr *__nested = nla_nest_start(skb, type);
 	int ret;
 
 	if (!__nested)
 		return -EMSGSIZE;
 	ret = nla_put_in_addr(skb, IPSET_ATTR_IPADDR_IPV4, ipaddr);
 	if (!ret)
-		ipset_nest_end(skb, __nested);
+		nla_nest_end(skb, __nested);
 	return ret;
 }
 
 static inline int nla_put_ipaddr6(struct sk_buff *skb, int type,
 				  const struct in6_addr *ipaddrptr)
 {
-	struct nlattr *__nested = ipset_nest_start(skb, type);
+	struct nlattr *__nested = nla_nest_start(skb, type);
 	int ret;
 
 	if (!__nested)
 		return -EMSGSIZE;
 	ret = nla_put_in6_addr(skb, IPSET_ATTR_IPADDR_IPV6, ipaddrptr);
 	if (!ret)
-		ipset_nest_end(skb, __nested);
+		nla_nest_end(skb, __nested);
 	return ret;
 }
 
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
index 257ca393e6f2..38ef2ea838cb 100644
--- a/net/netfilter/ipset/ip_set_bitmap_gen.h
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -99,7 +99,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	struct nlattr *nested;
 	size_t memsize = mtype_memsize(map, set->dsize) + set->ext_size;
 
-	nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+	nested = nla_nest_start(skb, IPSET_ATTR_DATA);
 	if (!nested)
 		goto nla_put_failure;
 	if (mtype_do_head(skb, map) ||
@@ -109,7 +109,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 		goto nla_put_failure;
 	if (unlikely(ip_set_put_flags(skb, set)))
 		goto nla_put_failure;
-	ipset_nest_end(skb, nested);
+	nla_nest_end(skb, nested);
 
 	return 0;
 nla_put_failure:
@@ -213,7 +213,7 @@ mtype_list(const struct ip_set *set,
 	u32 id, first = cb->args[IPSET_CB_ARG0];
 	int ret = 0;
 
-	adt = ipset_nest_start(skb, IPSET_ATTR_ADT);
+	adt = nla_nest_start(skb, IPSET_ATTR_ADT);
 	if (!adt)
 		return -EMSGSIZE;
 	/* Extensions may be replaced */
@@ -230,7 +230,7 @@ mtype_list(const struct ip_set *set,
 #endif
 		     ip_set_timeout_expired(ext_timeout(x, set))))
 			continue;
-		nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+		nested = nla_nest_start(skb, IPSET_ATTR_DATA);
 		if (!nested) {
 			if (id == first) {
 				nla_nest_cancel(skb, adt);
@@ -244,9 +244,9 @@ mtype_list(const struct ip_set *set,
 			goto nla_put_failure;
 		if (ip_set_put_extensions(skb, set, x, mtype_is_filled(x)))
 			goto nla_put_failure;
-		ipset_nest_end(skb, nested);
+		nla_nest_end(skb, nested);
 	}
-	ipset_nest_end(skb, adt);
+	nla_nest_end(skb, adt);
 
 	/* Set listing finished */
 	cb->args[IPSET_CB_ARG0] = 0;
@@ -259,7 +259,7 @@ nla_put_failure:
 		cb->args[IPSET_CB_ARG0] = 0;
 		ret = -EMSGSIZE;
 	}
-	ipset_nest_end(skb, adt);
+	nla_nest_end(skb, adt);
 out:
 	rcu_read_unlock();
 	return ret;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 2c9609929c71..01d51f775f12 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -1057,7 +1057,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	htable_bits = t->htable_bits;
 	rcu_read_unlock_bh();
 
-	nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+	nested = nla_nest_start(skb, IPSET_ATTR_DATA);
 	if (!nested)
 		goto nla_put_failure;
 	if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE,
@@ -1079,7 +1079,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 		goto nla_put_failure;
 	if (unlikely(ip_set_put_flags(skb, set)))
 		goto nla_put_failure;
-	ipset_nest_end(skb, nested);
+	nla_nest_end(skb, nested);
 
 	return 0;
 nla_put_failure:
@@ -1124,7 +1124,7 @@ mtype_list(const struct ip_set *set,
 	void *incomplete;
 	int i, ret = 0;
 
-	atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
+	atd = nla_nest_start(skb, IPSET_ATTR_ADT);
 	if (!atd)
 		return -EMSGSIZE;
 
@@ -1150,7 +1150,7 @@ mtype_list(const struct ip_set *set,
 				continue;
 			pr_debug("list hash %lu hbucket %p i %u, data %p\n",
 				 cb->args[IPSET_CB_ARG0], n, i, e);
-			nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+			nested = nla_nest_start(skb, IPSET_ATTR_DATA);
 			if (!nested) {
 				if (cb->args[IPSET_CB_ARG0] == first) {
 					nla_nest_cancel(skb, atd);
@@ -1163,10 +1163,10 @@ mtype_list(const struct ip_set *set,
 				goto nla_put_failure;
 			if (ip_set_put_extensions(skb, set, e, true))
 				goto nla_put_failure;
-			ipset_nest_end(skb, nested);
+			nla_nest_end(skb, nested);
 		}
 	}
-	ipset_nest_end(skb, atd);
+	nla_nest_end(skb, atd);
 	/* Set listing finished */
 	cb->args[IPSET_CB_ARG0] = 0;
 
@@ -1180,7 +1180,7 @@ nla_put_failure:
 		cb->args[IPSET_CB_ARG0] = 0;
 		ret = -EMSGSIZE;
 	} else {
-		ipset_nest_end(skb, atd);
+		nla_nest_end(skb, atd);
 	}
 out:
 	rcu_read_unlock();
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 8da228da53ae..4f894165cdcd 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -466,7 +466,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb)
 	struct nlattr *nested;
 	size_t memsize = list_set_memsize(map, set->dsize) + set->ext_size;
 
-	nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+	nested = nla_nest_start(skb, IPSET_ATTR_DATA);
 	if (!nested)
 		goto nla_put_failure;
 	if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) ||
@@ -476,7 +476,7 @@ list_set_head(struct ip_set *set, struct sk_buff *skb)
 		goto nla_put_failure;
 	if (unlikely(ip_set_put_flags(skb, set)))
 		goto nla_put_failure;
-	ipset_nest_end(skb, nested);
+	nla_nest_end(skb, nested);
 
 	return 0;
 nla_put_failure:
@@ -494,7 +494,7 @@ list_set_list(const struct ip_set *set,
 	struct set_elem *e;
 	int ret = 0;
 
-	atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
+	atd = nla_nest_start(skb, IPSET_ATTR_ADT);
 	if (!atd)
 		return -EMSGSIZE;
 
@@ -506,7 +506,7 @@ list_set_list(const struct ip_set *set,
 			i++;
 			continue;
 		}
-		nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+		nested = nla_nest_start(skb, IPSET_ATTR_DATA);
 		if (!nested)
 			goto nla_put_failure;
 		ip_set_name_byindex(map->net, e->id, name);
@@ -514,11 +514,11 @@ list_set_list(const struct ip_set *set,
 			goto nla_put_failure;
 		if (ip_set_put_extensions(skb, set, e, true))
 			goto nla_put_failure;
-		ipset_nest_end(skb, nested);
+		nla_nest_end(skb, nested);
 		i++;
 	}
 
-	ipset_nest_end(skb, atd);
+	nla_nest_end(skb, atd);
 	/* Set listing finished */
 	cb->args[IPSET_CB_ARG0] = 0;
 	goto out;
@@ -531,7 +531,7 @@ nla_put_failure:
 		ret = -EMSGSIZE;
 	} else {
 		cb->args[IPSET_CB_ARG0] = i;
-		ipset_nest_end(skb, atd);
+		nla_nest_end(skb, atd);
 	}
 out:
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 6f455f5f4e9c28aefaefbe18ce7304b499645d75 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 26 Apr 2019 14:07:27 +0200
Subject: netlink: add NLA_MIN_LEN

Rather than using NLA_UNSPEC for this type of thing, use NLA_MIN_LEN
so we can make NLA_UNSPEC be NLA_REJECT under certain conditions for
future attributes.

While at it, also use NLA_EXACT_LEN for the struct example.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h | 6 +++++-
 lib/nlattr.c          | 9 ++++++++-
 2 files changed, 13 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 1f18b47f41b4..c77ed51c18f1 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -183,6 +183,7 @@ enum {
 	NLA_REJECT,
 	NLA_EXACT_LEN,
 	NLA_EXACT_LEN_WARN,
+	NLA_MIN_LEN,
 	__NLA_TYPE_MAX,
 };
 
@@ -212,6 +213,7 @@ enum nla_policy_validation {
  *    NLA_NUL_STRING       Maximum length of string (excluding NUL)
  *    NLA_FLAG             Unused
  *    NLA_BINARY           Maximum length of attribute payload
+ *    NLA_MIN_LEN          Minimum length of attribute payload
  *    NLA_NESTED,
  *    NLA_NESTED_ARRAY     Length verification is done by checking len of
  *                         nested header (or empty); len field is used if
@@ -230,6 +232,7 @@ enum nla_policy_validation {
  *                         it is rejected.
  *    NLA_EXACT_LEN_WARN   Attribute should have exactly this length, a warning
  *                         is logged if it is longer, shorter is rejected.
+ *    NLA_MIN_LEN          Minimum length of attribute payload
  *    All other            Minimum length of attribute payload
  *
  * Meaning of `validation_data' field:
@@ -281,7 +284,7 @@ enum nla_policy_validation {
  * static const struct nla_policy my_policy[ATTR_MAX+1] = {
  * 	[ATTR_FOO] = { .type = NLA_U16 },
  *	[ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ },
- *	[ATTR_BAZ] = { .len = sizeof(struct mystruct) },
+ *	[ATTR_BAZ] = { .type = NLA_EXACT_LEN, .len = sizeof(struct mystruct) },
  *	[ATTR_GOO] = { .type = NLA_BITFIELD32, .validation_data = &myvalidflags },
  * };
  */
@@ -302,6 +305,7 @@ struct nla_policy {
 #define NLA_POLICY_EXACT_LEN(_len)	{ .type = NLA_EXACT_LEN, .len = _len }
 #define NLA_POLICY_EXACT_LEN_WARN(_len)	{ .type = NLA_EXACT_LEN_WARN, \
 					  .len = _len }
+#define NLA_POLICY_MIN_LEN(_len)	{ .type = NLA_MIN_LEN, .len = _len }
 
 #define NLA_POLICY_ETH_ADDR		NLA_POLICY_EXACT_LEN(ETH_ALEN)
 #define NLA_POLICY_ETH_ADDR_COMPAT	NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN)
diff --git a/lib/nlattr.c b/lib/nlattr.c
index d26de6156b97..465c9e8ef8a5 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -278,10 +278,17 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 			}
 		}
 		break;
+
+	case NLA_UNSPEC:
+	case NLA_MIN_LEN:
+		if (attrlen < pt->len)
+			goto out_err;
+		break;
+
 	default:
 		if (pt->len)
 			minlen = pt->len;
-		else if (pt->type != NLA_UNSPEC)
+		else
 			minlen = nla_attr_minlen[pt->type];
 
 		if (attrlen < minlen)
-- 
cgit v1.2.3


From 8cb081746c031fb164089322e2336a0bf5b3070c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 26 Apr 2019 14:07:28 +0200
Subject: netlink: make validation more configurable for future strictness

We currently have two levels of strict validation:

 1) liberal (default)
     - undefined (type >= max) & NLA_UNSPEC attributes accepted
     - attribute length >= expected accepted
     - garbage at end of message accepted
 2) strict (opt-in)
     - NLA_UNSPEC attributes accepted
     - attribute length >= expected accepted

Split out parsing strictness into four different options:
 * TRAILING     - check that there's no trailing data after parsing
                  attributes (in message or nested)
 * MAXTYPE      - reject attrs > max known type
 * UNSPEC       - reject attributes with NLA_UNSPEC policy entries
 * STRICT_ATTRS - strictly validate attribute size

The default for future things should be *everything*.
The current *_strict() is a combination of TRAILING and MAXTYPE,
and is renamed to _deprecated_strict().
The current regular parsing has none of this, and is renamed to
*_parse_deprecated().

Additionally it allows us to selectively set one of the new flags
even on old policies. Notably, the UNSPEC flag could be useful in
this case, since it can be arranged (by filling in the policy) to
not be an incompatible userspace ABI change, but would then going
forward prevent forgetting attribute entries. Similar can apply
to the POLICY flag.

We end up with the following renames:
 * nla_parse           -> nla_parse_deprecated
 * nla_parse_strict    -> nla_parse_deprecated_strict
 * nlmsg_parse         -> nlmsg_parse_deprecated
 * nlmsg_parse_strict  -> nlmsg_parse_deprecated_strict
 * nla_parse_nested    -> nla_parse_nested_deprecated
 * nla_validate_nested -> nla_validate_nested_deprecated

Using spatch, of course:
    @@
    expression TB, MAX, HEAD, LEN, POL, EXT;
    @@
    -nla_parse(TB, MAX, HEAD, LEN, POL, EXT)
    +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT)

    @@
    expression NLH, HDRLEN, TB, MAX, POL, EXT;
    @@
    -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT)
    +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT)

    @@
    expression NLH, HDRLEN, TB, MAX, POL, EXT;
    @@
    -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT)
    +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT)

    @@
    expression TB, MAX, NLA, POL, EXT;
    @@
    -nla_parse_nested(TB, MAX, NLA, POL, EXT)
    +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT)

    @@
    expression START, MAX, POL, EXT;
    @@
    -nla_validate_nested(START, MAX, POL, EXT)
    +nla_validate_nested_deprecated(START, MAX, POL, EXT)

    @@
    expression NLH, HDRLEN, MAX, POL, EXT;
    @@
    -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT)
    +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT)

For this patch, don't actually add the strict, non-renamed versions
yet so that it breaks compile if I get it wrong.

Also, while at it, make nla_validate and nla_parse go down to a
common __nla_validate_parse() function to avoid code duplication.

Ultimately, this allows us to have very strict validation for every
new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the
next patch, while existing things will continue to work as is.

In effect then, this adds fully strict validation for any new command.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 crypto/crypto_user_base.c                         |   4 +-
 drivers/block/drbd/drbd_nla.c                     |   3 +-
 drivers/block/nbd.c                               |  12 +-
 drivers/infiniband/core/addr.c                    |   4 +-
 drivers/infiniband/core/iwpm_util.c               |   8 +-
 drivers/infiniband/core/nldev.c                   |  36 ++--
 drivers/infiniband/core/sa_query.c                |   8 +-
 drivers/net/ieee802154/mac802154_hwsim.c          |  12 +-
 drivers/net/macsec.c                              |   8 +-
 drivers/net/team/team.c                           |   8 +-
 drivers/net/wireless/ath/ath10k/testmode.c        |   4 +-
 drivers/net/wireless/ath/ath6kl/testmode.c        |   4 +-
 drivers/net/wireless/ath/wcn36xx/testmode.c       |   4 +-
 drivers/net/wireless/ath/wil6210/cfg80211.c       |  24 ++-
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c |   4 +-
 drivers/net/wireless/mac80211_hwsim.c             |   8 +-
 drivers/net/wireless/marvell/mwifiex/cfg80211.c   |   4 +-
 drivers/net/wireless/ti/wlcore/testmode.c         |   4 +-
 drivers/net/wireless/ti/wlcore/vendor_cmd.c       |   8 +-
 include/net/genetlink.h                           |  16 +-
 include/net/netlink.h                             | 238 +++++++++++++++++-----
 kernel/taskstats.c                                |   5 +-
 lib/nlattr.c                                      | 171 ++++++++--------
 net/8021q/vlan_netlink.c                          |   4 +-
 net/bridge/br_mdb.c                               |   4 +-
 net/bridge/br_netlink.c                           |   6 +-
 net/bridge/br_netlink_tunnel.c                    |   4 +-
 net/can/gw.c                                      |   4 +-
 net/core/devlink.c                                |   7 +-
 net/core/fib_rules.c                              |   6 +-
 net/core/lwt_bpf.c                                |   7 +-
 net/core/neighbour.c                              |  25 ++-
 net/core/net_namespace.c                          |  19 +-
 net/core/rtnetlink.c                              | 107 ++++++----
 net/dcb/dcbnl.c                                   |  90 ++++----
 net/decnet/dn_dev.c                               |   8 +-
 net/decnet/dn_fib.c                               |   8 +-
 net/decnet/dn_route.c                             |   4 +-
 net/ieee802154/nl802154.c                         |  46 ++---
 net/ipv4/devinet.c                                |  27 +--
 net/ipv4/fib_frontend.c                           |   8 +-
 net/ipv4/ip_tunnel_core.c                         |   8 +-
 net/ipv4/ipmr.c                                   |  12 +-
 net/ipv4/route.c                                  |   8 +-
 net/ipv6/addrconf.c                               |  36 ++--
 net/ipv6/addrlabel.c                              |  12 +-
 net/ipv6/ila/ila_lwt.c                            |   3 +-
 net/ipv6/route.c                                  |  12 +-
 net/ipv6/seg6_iptunnel.c                          |   4 +-
 net/ipv6/seg6_local.c                             |   9 +-
 net/mpls/af_mpls.c                                |  26 +--
 net/mpls/mpls_iptunnel.c                          |   4 +-
 net/ncsi/ncsi-netlink.c                           |   4 +-
 net/netfilter/ipset/ip_set_core.c                 |  36 ++--
 net/netfilter/ipvs/ip_vs_ctl.c                    |  13 +-
 net/netfilter/nf_conntrack_netlink.c              |  45 ++--
 net/netfilter/nf_conntrack_proto_dccp.c           |   4 +-
 net/netfilter/nf_conntrack_proto_sctp.c           |   4 +-
 net/netfilter/nf_conntrack_proto_tcp.c            |   4 +-
 net/netfilter/nf_nat_core.c                       |   7 +-
 net/netfilter/nf_tables_api.c                     |  48 +++--
 net/netfilter/nfnetlink.c                         |  15 +-
 net/netfilter/nfnetlink_acct.c                    |   4 +-
 net/netfilter/nfnetlink_cthelper.c                |  22 +-
 net/netfilter/nfnetlink_cttimeout.c               |   7 +-
 net/netfilter/nfnetlink_queue.c                   |   5 +-
 net/netfilter/nft_compat.c                        |   4 +-
 net/netfilter/nft_ct.c                            |   8 +-
 net/netfilter/nft_tunnel.c                        |  21 +-
 net/netlabel/netlabel_cipso_v4.c                  |  36 ++--
 net/netlink/genetlink.c                           |   5 +-
 net/nfc/netlink.c                                 |  12 +-
 net/openvswitch/datapath.c                        |   4 +-
 net/openvswitch/flow_netlink.c                    |   9 +-
 net/openvswitch/meter.c                           |   6 +-
 net/openvswitch/vport-vxlan.c                     |   4 +-
 net/phonet/pn_netlink.c                           |   8 +-
 net/qrtr/qrtr.c                                   |   3 +-
 net/sched/act_api.c                               |  26 +--
 net/sched/act_bpf.c                               |   3 +-
 net/sched/act_connmark.c                          |   4 +-
 net/sched/act_csum.c                              |   3 +-
 net/sched/act_gact.c                              |   3 +-
 net/sched/act_ife.c                               |   8 +-
 net/sched/act_ipt.c                               |   3 +-
 net/sched/act_mirred.c                            |   3 +-
 net/sched/act_nat.c                               |   3 +-
 net/sched/act_pedit.c                             |   8 +-
 net/sched/act_police.c                            |   3 +-
 net/sched/act_sample.c                            |   3 +-
 net/sched/act_simple.c                            |   3 +-
 net/sched/act_skbedit.c                           |   3 +-
 net/sched/act_skbmod.c                            |   3 +-
 net/sched/act_tunnel_key.c                        |  13 +-
 net/sched/act_vlan.c                              |   3 +-
 net/sched/cls_api.c                               |  20 +-
 net/sched/cls_basic.c                             |   4 +-
 net/sched/cls_bpf.c                               |   4 +-
 net/sched/cls_cgroup.c                            |   5 +-
 net/sched/cls_flow.c                              |   3 +-
 net/sched/cls_flower.c                            |  25 +--
 net/sched/cls_fw.c                                |   3 +-
 net/sched/cls_matchall.c                          |   4 +-
 net/sched/cls_route.c                             |   3 +-
 net/sched/cls_rsvp.h                              |   3 +-
 net/sched/cls_tcindex.c                           |   3 +-
 net/sched/cls_u32.c                               |   3 +-
 net/sched/em_ipt.c                                |   4 +-
 net/sched/em_meta.c                               |   3 +-
 net/sched/ematch.c                                |   3 +-
 net/sched/sch_api.c                               |  19 +-
 net/sched/sch_atm.c                               |   3 +-
 net/sched/sch_cake.c                              |   3 +-
 net/sched/sch_cbq.c                               |   6 +-
 net/sched/sch_cbs.c                               |   3 +-
 net/sched/sch_choke.c                             |   3 +-
 net/sched/sch_codel.c                             |   3 +-
 net/sched/sch_drr.c                               |   3 +-
 net/sched/sch_dsmark.c                            |   6 +-
 net/sched/sch_etf.c                               |   3 +-
 net/sched/sch_fq.c                                |   3 +-
 net/sched/sch_fq_codel.c                          |   4 +-
 net/sched/sch_gred.c                              |  17 +-
 net/sched/sch_hfsc.c                              |   3 +-
 net/sched/sch_hhf.c                               |   3 +-
 net/sched/sch_htb.c                               |   6 +-
 net/sched/sch_mqprio.c                            |   5 +-
 net/sched/sch_netem.c                             |   5 +-
 net/sched/sch_pie.c                               |   3 +-
 net/sched/sch_qfq.c                               |   4 +-
 net/sched/sch_red.c                               |   3 +-
 net/sched/sch_sfb.c                               |   3 +-
 net/sched/sch_taprio.c                            |  19 +-
 net/sched/sch_tbf.c                               |   3 +-
 net/tipc/bearer.c                                 |  42 ++--
 net/tipc/link.c                                   |   4 +-
 net/tipc/net.c                                    |   6 +-
 net/tipc/netlink.c                                |   4 +-
 net/tipc/netlink_compat.c                         |  63 +++---
 net/tipc/node.c                                   |  38 ++--
 net/tipc/socket.c                                 |   6 +-
 net/tipc/udp_media.c                              |  13 +-
 net/wireless/nl80211.c                            | 191 +++++++++--------
 net/wireless/pmsr.c                               |  18 +-
 net/xfrm/xfrm_user.c                              |  10 +-
 145 files changed, 1233 insertions(+), 933 deletions(-)

(limited to 'include')

diff --git a/crypto/crypto_user_base.c b/crypto/crypto_user_base.c
index f25d3f32c9c2..e48da3b75c71 100644
--- a/crypto/crypto_user_base.c
+++ b/crypto/crypto_user_base.c
@@ -465,8 +465,8 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return err;
 	}
 
-	err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX,
-			  crypto_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, crypto_msg_min[type], attrs,
+				     CRYPTOCFGA_MAX, crypto_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/drivers/block/drbd/drbd_nla.c b/drivers/block/drbd/drbd_nla.c
index 8e261cb5198b..6a09b0b98018 100644
--- a/drivers/block/drbd/drbd_nla.c
+++ b/drivers/block/drbd/drbd_nla.c
@@ -35,7 +35,8 @@ int drbd_nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
 
 	err = drbd_nla_check_mandatory(maxtype, nla);
 	if (!err)
-		err = nla_parse_nested(tb, maxtype, nla, policy, NULL);
+		err = nla_parse_nested_deprecated(tb, maxtype, nla, policy,
+						  NULL);
 
 	return err;
 }
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index cd27f236431d..69dc11f907a3 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1797,8 +1797,10 @@ again:
 				ret = -EINVAL;
 				goto out;
 			}
-			ret = nla_parse_nested(socks, NBD_SOCK_MAX, attr,
-					       nbd_sock_policy, info->extack);
+			ret = nla_parse_nested_deprecated(socks, NBD_SOCK_MAX,
+							  attr,
+							  nbd_sock_policy,
+							  info->extack);
 			if (ret != 0) {
 				printk(KERN_ERR "nbd: error processing sock list\n");
 				ret = -EINVAL;
@@ -1968,8 +1970,10 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
 				ret = -EINVAL;
 				goto out;
 			}
-			ret = nla_parse_nested(socks, NBD_SOCK_MAX, attr,
-					       nbd_sock_policy, info->extack);
+			ret = nla_parse_nested_deprecated(socks, NBD_SOCK_MAX,
+							  attr,
+							  nbd_sock_policy,
+							  info->extack);
 			if (ret != 0) {
 				printk(KERN_ERR "nbd: error processing sock list\n");
 				ret = -EINVAL;
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index f5ecb660fe7d..744b6ec0acb0 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -86,8 +86,8 @@ static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh)
 	if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR)
 		return false;
 
-	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
-			nlmsg_len(nlh), ib_nl_addr_policy, NULL);
+	ret = nla_parse_deprecated(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
+				   nlmsg_len(nlh), ib_nl_addr_policy, NULL);
 	if (ret)
 		return false;
 
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index a5d2a20ee697..41929bb83739 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -506,14 +506,14 @@ int iwpm_parse_nlmsg(struct netlink_callback *cb, int policy_max,
 	int ret;
 	const char *err_str = "";
 
-	ret = nlmsg_validate(cb->nlh, nlh_len, policy_max - 1, nlmsg_policy,
-			     NULL);
+	ret = nlmsg_validate_deprecated(cb->nlh, nlh_len, policy_max - 1,
+					nlmsg_policy, NULL);
 	if (ret) {
 		err_str = "Invalid attribute";
 		goto parse_nlmsg_error;
 	}
-	ret = nlmsg_parse(cb->nlh, nlh_len, nltb, policy_max - 1,
-			  nlmsg_policy, NULL);
+	ret = nlmsg_parse_deprecated(cb->nlh, nlh_len, nltb, policy_max - 1,
+				     nlmsg_policy, NULL);
 	if (ret) {
 		err_str = "Unable to parse the nlmsg";
 		goto parse_nlmsg_error;
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index ad189a29cc67..85324012bf07 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -608,8 +608,8 @@ static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u32 index;
 	int err;
 
-	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
-			  nldev_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+				     nldev_policy, extack);
 	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
 		return -EINVAL;
 
@@ -653,8 +653,8 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u32 index;
 	int err;
 
-	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+				     nldev_policy, extack);
 	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
 		return -EINVAL;
 
@@ -722,8 +722,8 @@ static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u32 port;
 	int err;
 
-	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
-			  nldev_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+				     nldev_policy, extack);
 	if (err ||
 	    !tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
 	    !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
@@ -778,8 +778,8 @@ static int nldev_port_get_dumpit(struct sk_buff *skb,
 	int err;
 	unsigned int p;
 
-	err = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
-			  nldev_policy, NULL);
+	err = nlmsg_parse_deprecated(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+				     nldev_policy, NULL);
 	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
 		return -EINVAL;
 
@@ -833,8 +833,8 @@ static int nldev_res_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u32 index;
 	int ret;
 
-	ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
-			  nldev_policy, extack);
+	ret = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+				     nldev_policy, extack);
 	if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
 		return -EINVAL;
 
@@ -982,8 +982,8 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct sk_buff *msg;
 	int ret;
 
-	ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
-			  nldev_policy, extack);
+	ret = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+				     nldev_policy, extack);
 	if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !fe->id || !tb[fe->id])
 		return -EINVAL;
 
@@ -1071,8 +1071,8 @@ static int res_get_common_dumpit(struct sk_buff *skb,
 	u32 index, port = 0;
 	bool filled = false;
 
-	err = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
-			  nldev_policy, NULL);
+	err = nlmsg_parse_deprecated(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+				     nldev_policy, NULL);
 	/*
 	 * Right now, we are expecting the device index to get res information,
 	 * but it is possible to extend this code to return all devices in
@@ -1250,8 +1250,8 @@ static int nldev_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	char type[IFNAMSIZ];
 	int err;
 
-	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
-			  nldev_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+				     nldev_policy, extack);
 	if (err || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
 	    !tb[RDMA_NLDEV_ATTR_LINK_TYPE] || !tb[RDMA_NLDEV_ATTR_NDEV_NAME])
 		return -EINVAL;
@@ -1294,8 +1294,8 @@ static int nldev_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u32 index;
 	int err;
 
-	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
-			  nldev_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+				     nldev_policy, extack);
 	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
 		return -EINVAL;
 
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 7925e45ea88a..bb534959abf0 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1028,8 +1028,8 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb,
 	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
-	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
-			nlmsg_len(nlh), ib_nl_policy, NULL);
+	ret = nla_parse_deprecated(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
+				   nlmsg_len(nlh), ib_nl_policy, NULL);
 	attr = (const struct nlattr *)tb[LS_NLA_TYPE_TIMEOUT];
 	if (ret || !attr)
 		goto settimeout_out;
@@ -1080,8 +1080,8 @@ static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
 	if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR)
 		return 0;
 
-	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
-			nlmsg_len(nlh), ib_nl_policy, NULL);
+	ret = nla_parse_deprecated(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
+				   nlmsg_len(nlh), ib_nl_policy, NULL);
 	if (ret)
 		return 0;
 
diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index 80ca300aba04..486a3a3bf35b 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -430,9 +430,7 @@ static int hwsim_new_edge_nl(struct sk_buff *msg, struct genl_info *info)
 	    !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE])
 		return -EINVAL;
 
-	if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX,
-			     info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE],
-			     hwsim_edge_policy, NULL))
+	if (nla_parse_nested_deprecated(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX, info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE], hwsim_edge_policy, NULL))
 		return -EINVAL;
 
 	if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID])
@@ -494,9 +492,7 @@ static int hwsim_del_edge_nl(struct sk_buff *msg, struct genl_info *info)
 	    !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE])
 		return -EINVAL;
 
-	if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX,
-			     info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE],
-			     hwsim_edge_policy, NULL))
+	if (nla_parse_nested_deprecated(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX, info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE], hwsim_edge_policy, NULL))
 		return -EINVAL;
 
 	if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID])
@@ -544,9 +540,7 @@ static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info)
 	    !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE])
 		return -EINVAL;
 
-	if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX,
-			     info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE],
-			     hwsim_edge_policy, NULL))
+	if (nla_parse_nested_deprecated(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX, info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE], hwsim_edge_policy, NULL))
 		return -EINVAL;
 
 	if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID] &&
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 8dedb9a9781e..c3fa3d8da8f3 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1611,9 +1611,7 @@ static int parse_sa_config(struct nlattr **attrs, struct nlattr **tb_sa)
 	if (!attrs[MACSEC_ATTR_SA_CONFIG])
 		return -EINVAL;
 
-	if (nla_parse_nested(tb_sa, MACSEC_SA_ATTR_MAX,
-			     attrs[MACSEC_ATTR_SA_CONFIG],
-			     macsec_genl_sa_policy, NULL))
+	if (nla_parse_nested_deprecated(tb_sa, MACSEC_SA_ATTR_MAX, attrs[MACSEC_ATTR_SA_CONFIG], macsec_genl_sa_policy, NULL))
 		return -EINVAL;
 
 	return 0;
@@ -1624,9 +1622,7 @@ static int parse_rxsc_config(struct nlattr **attrs, struct nlattr **tb_rxsc)
 	if (!attrs[MACSEC_ATTR_RXSC_CONFIG])
 		return -EINVAL;
 
-	if (nla_parse_nested(tb_rxsc, MACSEC_RXSC_ATTR_MAX,
-			     attrs[MACSEC_ATTR_RXSC_CONFIG],
-			     macsec_genl_rxsc_policy, NULL))
+	if (nla_parse_nested_deprecated(tb_rxsc, MACSEC_RXSC_ATTR_MAX, attrs[MACSEC_ATTR_RXSC_CONFIG], macsec_genl_rxsc_policy, NULL))
 		return -EINVAL;
 
 	return 0;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 6306897c147f..be58445afbbc 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2510,9 +2510,11 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 			err = -EINVAL;
 			goto team_put;
 		}
-		err = nla_parse_nested(opt_attrs, TEAM_ATTR_OPTION_MAX,
-				       nl_option, team_nl_option_policy,
-				       info->extack);
+		err = nla_parse_nested_deprecated(opt_attrs,
+						  TEAM_ATTR_OPTION_MAX,
+						  nl_option,
+						  team_nl_option_policy,
+						  info->extack);
 		if (err)
 			goto team_put;
 		if (!opt_attrs[TEAM_ATTR_OPTION_NAME] ||
diff --git a/drivers/net/wireless/ath/ath10k/testmode.c b/drivers/net/wireless/ath/ath10k/testmode.c
index 6433ff10d80e..a29cfb9c72c2 100644
--- a/drivers/net/wireless/ath/ath10k/testmode.c
+++ b/drivers/net/wireless/ath/ath10k/testmode.c
@@ -416,8 +416,8 @@ int ath10k_tm_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct nlattr *tb[ATH10K_TM_ATTR_MAX + 1];
 	int ret;
 
-	ret = nla_parse(tb, ATH10K_TM_ATTR_MAX, data, len, ath10k_tm_policy,
-			NULL);
+	ret = nla_parse_deprecated(tb, ATH10K_TM_ATTR_MAX, data, len,
+				   ath10k_tm_policy, NULL);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/ath/ath6kl/testmode.c b/drivers/net/wireless/ath/ath6kl/testmode.c
index d8dcacda9add..f3906dbe5495 100644
--- a/drivers/net/wireless/ath/ath6kl/testmode.c
+++ b/drivers/net/wireless/ath/ath6kl/testmode.c
@@ -74,8 +74,8 @@ int ath6kl_tm_cmd(struct wiphy *wiphy, struct wireless_dev *wdev,
 	int err, buf_len;
 	void *buf;
 
-	err = nla_parse(tb, ATH6KL_TM_ATTR_MAX, data, len, ath6kl_tm_policy,
-			NULL);
+	err = nla_parse_deprecated(tb, ATH6KL_TM_ATTR_MAX, data, len,
+				   ath6kl_tm_policy, NULL);
 	if (err)
 		return err;
 
diff --git a/drivers/net/wireless/ath/wcn36xx/testmode.c b/drivers/net/wireless/ath/wcn36xx/testmode.c
index 51a038022c8b..7ae14b4d2d0e 100644
--- a/drivers/net/wireless/ath/wcn36xx/testmode.c
+++ b/drivers/net/wireless/ath/wcn36xx/testmode.c
@@ -132,8 +132,8 @@ int wcn36xx_tm_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	unsigned short attr;
 
 	wcn36xx_dbg_dump(WCN36XX_DBG_TESTMODE_DUMP, "Data:", data, len);
-	ret = nla_parse(tb, WCN36XX_TM_ATTR_MAX, data, len,
-			wcn36xx_tm_policy, NULL);
+	ret = nla_parse_deprecated(tb, WCN36XX_TM_ATTR_MAX, data, len,
+				   wcn36xx_tm_policy, NULL);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index cac18e61474e..9a67ad2a589c 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -2620,8 +2620,8 @@ static int wil_rf_sector_get_cfg(struct wiphy *wiphy,
 	if (!test_bit(WMI_FW_CAPABILITY_RF_SECTORS, wil->fw_capabilities))
 		return -EOPNOTSUPP;
 
-	rc = nla_parse(tb, QCA_ATTR_DMG_RF_SECTOR_MAX, data, data_len,
-		       wil_rf_sector_policy, NULL);
+	rc = nla_parse_deprecated(tb, QCA_ATTR_DMG_RF_SECTOR_MAX, data,
+				  data_len, wil_rf_sector_policy, NULL);
 	if (rc) {
 		wil_err(wil, "Invalid rf sector ATTR\n");
 		return rc;
@@ -2740,8 +2740,8 @@ static int wil_rf_sector_set_cfg(struct wiphy *wiphy,
 	if (!test_bit(WMI_FW_CAPABILITY_RF_SECTORS, wil->fw_capabilities))
 		return -EOPNOTSUPP;
 
-	rc = nla_parse(tb, QCA_ATTR_DMG_RF_SECTOR_MAX, data, data_len,
-		       wil_rf_sector_policy, NULL);
+	rc = nla_parse_deprecated(tb, QCA_ATTR_DMG_RF_SECTOR_MAX, data,
+				  data_len, wil_rf_sector_policy, NULL);
 	if (rc) {
 		wil_err(wil, "Invalid rf sector ATTR\n");
 		return rc;
@@ -2773,9 +2773,11 @@ static int wil_rf_sector_set_cfg(struct wiphy *wiphy,
 	cmd.sector_type = sector_type;
 	nla_for_each_nested(nl_cfg, tb[QCA_ATTR_DMG_RF_SECTOR_CFG],
 			    tmp) {
-		rc = nla_parse_nested(tb2, QCA_ATTR_DMG_RF_SECTOR_CFG_MAX,
-				      nl_cfg, wil_rf_sector_cfg_policy,
-				      NULL);
+		rc = nla_parse_nested_deprecated(tb2,
+						 QCA_ATTR_DMG_RF_SECTOR_CFG_MAX,
+						 nl_cfg,
+						 wil_rf_sector_cfg_policy,
+						 NULL);
 		if (rc) {
 			wil_err(wil, "invalid sector cfg\n");
 			return -EINVAL;
@@ -2847,8 +2849,8 @@ static int wil_rf_sector_get_selected(struct wiphy *wiphy,
 	if (!test_bit(WMI_FW_CAPABILITY_RF_SECTORS, wil->fw_capabilities))
 		return -EOPNOTSUPP;
 
-	rc = nla_parse(tb, QCA_ATTR_DMG_RF_SECTOR_MAX, data, data_len,
-		       wil_rf_sector_policy, NULL);
+	rc = nla_parse_deprecated(tb, QCA_ATTR_DMG_RF_SECTOR_MAX, data,
+				  data_len, wil_rf_sector_policy, NULL);
 	if (rc) {
 		wil_err(wil, "Invalid rf sector ATTR\n");
 		return rc;
@@ -2955,8 +2957,8 @@ static int wil_rf_sector_set_selected(struct wiphy *wiphy,
 	if (!test_bit(WMI_FW_CAPABILITY_RF_SECTORS, wil->fw_capabilities))
 		return -EOPNOTSUPP;
 
-	rc = nla_parse(tb, QCA_ATTR_DMG_RF_SECTOR_MAX, data, data_len,
-		       wil_rf_sector_policy, NULL);
+	rc = nla_parse_deprecated(tb, QCA_ATTR_DMG_RF_SECTOR_MAX, data,
+				  data_len, wil_rf_sector_policy, NULL);
 	if (rc) {
 		wil_err(wil, "Invalid rf sector ATTR\n");
 		return rc;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index d4c7f08f08e3..5c52469288be 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -4465,8 +4465,8 @@ static int __iwl_mvm_mac_testmode_cmd(struct iwl_mvm *mvm,
 	int err;
 	u32 noa_duration;
 
-	err = nla_parse(tb, IWL_MVM_TM_ATTR_MAX, data, len, iwl_mvm_tm_policy,
-			NULL);
+	err = nla_parse_deprecated(tb, IWL_MVM_TM_ATTR_MAX, data, len,
+				   iwl_mvm_tm_policy, NULL);
 	if (err)
 		return err;
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 4c2145ba87a0..2a1aa2f6e7dc 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -409,8 +409,8 @@ static int mac80211_hwsim_vendor_cmd_test(struct wiphy *wiphy,
 	int err;
 	u32 val;
 
-	err = nla_parse(tb, QCA_WLAN_VENDOR_ATTR_MAX, data, data_len,
-			hwsim_vendor_test_policy, NULL);
+	err = nla_parse_deprecated(tb, QCA_WLAN_VENDOR_ATTR_MAX, data,
+				   data_len, hwsim_vendor_test_policy, NULL);
 	if (err)
 		return err;
 	if (!tb[QCA_WLAN_VENDOR_ATTR_TEST])
@@ -1936,8 +1936,8 @@ static int mac80211_hwsim_testmode_cmd(struct ieee80211_hw *hw,
 	struct sk_buff *skb;
 	int err, ps;
 
-	err = nla_parse(tb, HWSIM_TM_ATTR_MAX, data, len,
-			hwsim_testmode_policy, NULL);
+	err = nla_parse_deprecated(tb, HWSIM_TM_ATTR_MAX, data, len,
+				   hwsim_testmode_policy, NULL);
 	if (err)
 		return err;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index e582d9b3e50c..e11a4bb67172 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -4059,8 +4059,8 @@ static int mwifiex_tm_cmd(struct wiphy *wiphy, struct wireless_dev *wdev,
 	if (!priv)
 		return -EINVAL;
 
-	err = nla_parse(tb, MWIFIEX_TM_ATTR_MAX, data, len, mwifiex_tm_policy,
-			NULL);
+	err = nla_parse_deprecated(tb, MWIFIEX_TM_ATTR_MAX, data, len,
+				   mwifiex_tm_policy, NULL);
 	if (err)
 		return err;
 
diff --git a/drivers/net/wireless/ti/wlcore/testmode.c b/drivers/net/wireless/ti/wlcore/testmode.c
index dcb2c8b0feb6..affefaaea1ea 100644
--- a/drivers/net/wireless/ti/wlcore/testmode.c
+++ b/drivers/net/wireless/ti/wlcore/testmode.c
@@ -372,8 +372,8 @@ int wl1271_tm_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	u32 nla_cmd;
 	int err;
 
-	err = nla_parse(tb, WL1271_TM_ATTR_MAX, data, len, wl1271_tm_policy,
-			NULL);
+	err = nla_parse_deprecated(tb, WL1271_TM_ATTR_MAX, data, len,
+				   wl1271_tm_policy, NULL);
 	if (err)
 		return err;
 
diff --git a/drivers/net/wireless/ti/wlcore/vendor_cmd.c b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
index 7f34ec077ee5..75756fb8e7b0 100644
--- a/drivers/net/wireless/ti/wlcore/vendor_cmd.c
+++ b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
@@ -41,8 +41,8 @@ wlcore_vendor_cmd_smart_config_start(struct wiphy *wiphy,
 	if (!data)
 		return -EINVAL;
 
-	ret = nla_parse(tb, MAX_WLCORE_VENDOR_ATTR, data, data_len,
-			wlcore_vendor_attr_policy, NULL);
+	ret = nla_parse_deprecated(tb, MAX_WLCORE_VENDOR_ATTR, data, data_len,
+				   wlcore_vendor_attr_policy, NULL);
 	if (ret)
 		return ret;
 
@@ -122,8 +122,8 @@ wlcore_vendor_cmd_smart_config_set_group_key(struct wiphy *wiphy,
 	if (!data)
 		return -EINVAL;
 
-	ret = nla_parse(tb, MAX_WLCORE_VENDOR_ATTR, data, data_len,
-			wlcore_vendor_attr_policy, NULL);
+	ret = nla_parse_deprecated(tb, MAX_WLCORE_VENDOR_ATTR, data, data_len,
+				   wlcore_vendor_attr_policy, NULL);
 	if (ret)
 		return ret;
 
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 6850c7b1a3a6..897cdba13569 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -165,7 +165,7 @@ static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr)
 }
 
 /**
- * genlmsg_parse - parse attributes of a genetlink message
+ * genlmsg_parse_deprecated - parse attributes of a genetlink message
  * @nlh: netlink message header
  * @family: genetlink message family
  * @tb: destination array with maxtype+1 elements
@@ -173,14 +173,14 @@ static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr)
  * @policy: validation policy
  * @extack: extended ACK report struct
  */
-static inline int genlmsg_parse(const struct nlmsghdr *nlh,
-				const struct genl_family *family,
-				struct nlattr *tb[], int maxtype,
-				const struct nla_policy *policy,
-				struct netlink_ext_ack *extack)
+static inline int genlmsg_parse_deprecated(const struct nlmsghdr *nlh,
+					   const struct genl_family *family,
+					   struct nlattr *tb[], int maxtype,
+					   const struct nla_policy *policy,
+					   struct netlink_ext_ack *extack)
 {
-	return nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype,
-			   policy, extack);
+	return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype,
+			     policy, NL_VALIDATE_LIBERAL, extack);
 }
 
 /**
diff --git a/include/net/netlink.h b/include/net/netlink.h
index c77ed51c18f1..ab26a5e3558b 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -369,21 +369,48 @@ struct nl_info {
 	bool			skip_notify;
 };
 
+/**
+ * enum netlink_validation - netlink message/attribute validation levels
+ * @NL_VALIDATE_LIBERAL: Old-style "be liberal" validation, not caring about
+ *	extra data at the end of the message, attributes being longer than
+ *	they should be, or unknown attributes being present.
+ * @NL_VALIDATE_TRAILING: Reject junk data encountered after attribute parsing.
+ * @NL_VALIDATE_MAXTYPE: Reject attributes > max type; Together with _TRAILING
+ *	this is equivalent to the old nla_parse_strict()/nlmsg_parse_strict().
+ * @NL_VALIDATE_UNSPEC: Reject attributes with NLA_UNSPEC in the policy.
+ *	This can safely be set by the kernel when the given policy has no
+ *	NLA_UNSPEC anymore, and can thus be used to ensure policy entries
+ *	are enforced going forward.
+ * @NL_VALIDATE_STRICT_ATTRS: strict attribute policy parsing (e.g.
+ *	U8, U16, U32 must have exact size, etc.)
+ */
+enum netlink_validation {
+	NL_VALIDATE_LIBERAL = 0,
+	NL_VALIDATE_TRAILING = BIT(0),
+	NL_VALIDATE_MAXTYPE = BIT(1),
+	NL_VALIDATE_UNSPEC = BIT(2),
+	NL_VALIDATE_STRICT_ATTRS = BIT(3),
+};
+
+#define NL_VALIDATE_DEPRECATED_STRICT (NL_VALIDATE_TRAILING |\
+				       NL_VALIDATE_MAXTYPE)
+#define NL_VALIDATE_STRICT (NL_VALIDATE_TRAILING |\
+			    NL_VALIDATE_MAXTYPE |\
+			    NL_VALIDATE_UNSPEC |\
+			    NL_VALIDATE_STRICT_ATTRS)
+
 int netlink_rcv_skb(struct sk_buff *skb,
 		    int (*cb)(struct sk_buff *, struct nlmsghdr *,
 			      struct netlink_ext_ack *));
 int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid,
 		 unsigned int group, int report, gfp_t flags);
 
-int nla_validate(const struct nlattr *head, int len, int maxtype,
-		 const struct nla_policy *policy,
-		 struct netlink_ext_ack *extack);
-int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
-	      int len, const struct nla_policy *policy,
-	      struct netlink_ext_ack *extack);
-int nla_parse_strict(struct nlattr **tb, int maxtype, const struct nlattr *head,
-		     int len, const struct nla_policy *policy,
-		     struct netlink_ext_ack *extack);
+int __nla_validate(const struct nlattr *head, int len, int maxtype,
+		   const struct nla_policy *policy, unsigned int validate,
+		   struct netlink_ext_ack *extack);
+int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
+		int len, const struct nla_policy *policy, unsigned int validate,
+		struct netlink_ext_ack *extack);
 int nla_policy_len(const struct nla_policy *, int);
 struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype);
 size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize);
@@ -512,42 +539,121 @@ nlmsg_next(const struct nlmsghdr *nlh, int *remaining)
 }
 
 /**
- * nlmsg_parse - parse attributes of a netlink message
+ * nla_parse_deprecated - Parse a stream of attributes into a tb buffer
+ * @tb: destination array with maxtype+1 elements
+ * @maxtype: maximum attribute type to be expected
+ * @head: head of attribute stream
+ * @len: length of attribute stream
+ * @policy: validation policy
+ * @extack: extended ACK pointer
+ *
+ * Parses a stream of attributes and stores a pointer to each attribute in
+ * the tb array accessible via the attribute type. Attributes with a type
+ * exceeding maxtype will be ignored and attributes from the policy are not
+ * always strictly validated (only for new attributes).
+ *
+ * Returns 0 on success or a negative error code.
+ */
+static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype,
+				       const struct nlattr *head, int len,
+				       const struct nla_policy *policy,
+				       struct netlink_ext_ack *extack)
+{
+	return __nla_parse(tb, maxtype, head, len, policy,
+			   NL_VALIDATE_LIBERAL, extack);
+}
+
+/**
+ * nla_parse_deprecated_strict - Parse a stream of attributes into a tb buffer
+ * @tb: destination array with maxtype+1 elements
+ * @maxtype: maximum attribute type to be expected
+ * @head: head of attribute stream
+ * @len: length of attribute stream
+ * @policy: validation policy
+ * @extack: extended ACK pointer
+ *
+ * Parses a stream of attributes and stores a pointer to each attribute in
+ * the tb array accessible via the attribute type. Attributes with a type
+ * exceeding maxtype will be rejected as well as trailing data, but the
+ * policy is not completely strictly validated (only for new attributes).
+ *
+ * Returns 0 on success or a negative error code.
+ */
+static inline int nla_parse_deprecated_strict(struct nlattr **tb, int maxtype,
+					      const struct nlattr *head,
+					      int len,
+					      const struct nla_policy *policy,
+					      struct netlink_ext_ack *extack)
+{
+	return __nla_parse(tb, maxtype, head, len, policy,
+			   NL_VALIDATE_DEPRECATED_STRICT, extack);
+}
+
+/**
+ * __nlmsg_parse - parse attributes of a netlink message
  * @nlh: netlink message header
  * @hdrlen: length of family specific header
  * @tb: destination array with maxtype+1 elements
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
+ * @validate: validation strictness
  * @extack: extended ACK report struct
  *
  * See nla_parse()
  */
-static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
-			      struct nlattr *tb[], int maxtype,
-			      const struct nla_policy *policy,
-			      struct netlink_ext_ack *extack)
+static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
+				struct nlattr *tb[], int maxtype,
+				const struct nla_policy *policy,
+				unsigned int validate,
+				struct netlink_ext_ack *extack)
 {
 	if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) {
 		NL_SET_ERR_MSG(extack, "Invalid header length");
 		return -EINVAL;
 	}
 
-	return nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
-			 nlmsg_attrlen(nlh, hdrlen), policy, extack);
+	return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
+			   nlmsg_attrlen(nlh, hdrlen), policy, validate,
+			   extack);
 }
 
-static inline int nlmsg_parse_strict(const struct nlmsghdr *nlh, int hdrlen,
-				     struct nlattr *tb[], int maxtype,
-				     const struct nla_policy *policy,
-				     struct netlink_ext_ack *extack)
+/**
+ * nlmsg_parse_deprecated - parse attributes of a netlink message
+ * @nlh: netlink message header
+ * @hdrlen: length of family specific header
+ * @tb: destination array with maxtype+1 elements
+ * @maxtype: maximum attribute type to be expected
+ * @extack: extended ACK report struct
+ *
+ * See nla_parse_deprecated()
+ */
+static inline int nlmsg_parse_deprecated(const struct nlmsghdr *nlh, int hdrlen,
+					 struct nlattr *tb[], int maxtype,
+					 const struct nla_policy *policy,
+					 struct netlink_ext_ack *extack)
 {
-	if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) {
-		NL_SET_ERR_MSG(extack, "Invalid header length");
-		return -EINVAL;
-	}
+	return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy,
+			     NL_VALIDATE_LIBERAL, extack);
+}
 
-	return nla_parse_strict(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
-				nlmsg_attrlen(nlh, hdrlen), policy, extack);
+/**
+ * nlmsg_parse_deprecated_strict - parse attributes of a netlink message
+ * @nlh: netlink message header
+ * @hdrlen: length of family specific header
+ * @tb: destination array with maxtype+1 elements
+ * @maxtype: maximum attribute type to be expected
+ * @extack: extended ACK report struct
+ *
+ * See nla_parse_deprecated_strict()
+ */
+static inline int
+nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen,
+			      struct nlattr *tb[], int maxtype,
+			      const struct nla_policy *policy,
+			      struct netlink_ext_ack *extack)
+{
+	return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy,
+			     NL_VALIDATE_DEPRECATED_STRICT, extack);
 }
 
 /**
@@ -566,26 +672,53 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh,
 }
 
 /**
- * nlmsg_validate - validate a netlink message including attributes
+ * nla_validate_deprecated - Validate a stream of attributes
+ * @head: head of attribute stream
+ * @len: length of attribute stream
+ * @maxtype: maximum attribute type to be expected
+ * @policy: validation policy
+ * @validate: validation strictness
+ * @extack: extended ACK report struct
+ *
+ * Validates all attributes in the specified attribute stream against the
+ * specified policy. Validation is done in liberal mode.
+ * See documenation of struct nla_policy for more details.
+ *
+ * Returns 0 on success or a negative error code.
+ */
+static inline int nla_validate_deprecated(const struct nlattr *head, int len,
+					  int maxtype,
+					  const struct nla_policy *policy,
+					  struct netlink_ext_ack *extack)
+{
+	return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_LIBERAL,
+			      extack);
+}
+
+
+/**
+ * nlmsg_validate_deprecated - validate a netlink message including attributes
  * @nlh: netlinket message header
  * @hdrlen: length of familiy specific header
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
  * @extack: extended ACK report struct
  */
-static inline int nlmsg_validate(const struct nlmsghdr *nlh,
-				 int hdrlen, int maxtype,
-				 const struct nla_policy *policy,
-				 struct netlink_ext_ack *extack)
+static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh,
+					    int hdrlen, int maxtype,
+					    const struct nla_policy *policy,
+					    struct netlink_ext_ack *extack)
 {
 	if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
 		return -EINVAL;
 
-	return nla_validate(nlmsg_attrdata(nlh, hdrlen),
-			    nlmsg_attrlen(nlh, hdrlen), maxtype, policy,
-			    extack);
+	return __nla_validate(nlmsg_attrdata(nlh, hdrlen),
+			      nlmsg_attrlen(nlh, hdrlen), maxtype,
+			      policy, NL_VALIDATE_LIBERAL, extack);
 }
 
+
+
 /**
  * nlmsg_report - need to report back to application?
  * @nlh: netlink message header
@@ -899,22 +1032,22 @@ nla_find_nested(const struct nlattr *nla, int attrtype)
 }
 
 /**
- * nla_parse_nested - parse nested attributes
+ * nla_parse_nested_deprecated - parse nested attributes
  * @tb: destination array with maxtype+1 elements
  * @maxtype: maximum attribute type to be expected
  * @nla: attribute containing the nested attributes
  * @policy: validation policy
  * @extack: extended ACK report struct
  *
- * See nla_parse()
+ * See nla_parse_deprecated()
  */
-static inline int nla_parse_nested(struct nlattr *tb[], int maxtype,
-				   const struct nlattr *nla,
-				   const struct nla_policy *policy,
-				   struct netlink_ext_ack *extack)
+static inline int nla_parse_nested_deprecated(struct nlattr *tb[], int maxtype,
+					      const struct nlattr *nla,
+					      const struct nla_policy *policy,
+					      struct netlink_ext_ack *extack)
 {
-	return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy,
-			 extack);
+	return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy,
+			   NL_VALIDATE_LIBERAL, extack);
 }
 
 /**
@@ -1489,6 +1622,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
  * @start: container attribute
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
+ * @validate: validation strictness
  * @extack: extended ACK report struct
  *
  * Validates all attributes in the nested attribute stream against the
@@ -1497,12 +1631,22 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
  *
  * Returns 0 on success or a negative error code.
  */
-static inline int nla_validate_nested(const struct nlattr *start, int maxtype,
-				      const struct nla_policy *policy,
-				      struct netlink_ext_ack *extack)
+static inline int __nla_validate_nested(const struct nlattr *start, int maxtype,
+					const struct nla_policy *policy,
+					unsigned int validate,
+					struct netlink_ext_ack *extack)
+{
+	return __nla_validate(nla_data(start), nla_len(start), maxtype, policy,
+			      validate, extack);
+}
+
+static inline int
+nla_validate_nested_deprecated(const struct nlattr *start, int maxtype,
+			       const struct nla_policy *policy,
+			       struct netlink_ext_ack *extack)
 {
-	return nla_validate(nla_data(start), nla_len(start), maxtype, policy,
-			    extack);
+	return __nla_validate_nested(start, maxtype, policy,
+				     NL_VALIDATE_LIBERAL, extack);
 }
 
 /**
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index ef4f9cd980fd..0e347f1c7800 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -677,8 +677,9 @@ static int taskstats_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-	return nlmsg_validate(info->nlhdr, GENL_HDRLEN, TASKSTATS_CMD_ATTR_MAX,
-			      policy, info->extack);
+	return nlmsg_validate_deprecated(info->nlhdr, GENL_HDRLEN,
+					 TASKSTATS_CMD_ATTR_MAX, policy,
+					 info->extack);
 }
 
 static struct genl_family family __ro_after_init = {
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 465c9e8ef8a5..af0f8b0309c6 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -69,7 +69,8 @@ static int validate_nla_bitfield32(const struct nlattr *nla,
 
 static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
 			      const struct nla_policy *policy,
-			      struct netlink_ext_ack *extack)
+			      struct netlink_ext_ack *extack,
+			      unsigned int validate)
 {
 	const struct nlattr *entry;
 	int rem;
@@ -86,8 +87,8 @@ static int nla_validate_array(const struct nlattr *head, int len, int maxtype,
 			return -ERANGE;
 		}
 
-		ret = nla_validate(nla_data(entry), nla_len(entry),
-				   maxtype, policy, extack);
+		ret = __nla_validate(nla_data(entry), nla_len(entry),
+				     maxtype, policy, validate, extack);
 		if (ret < 0)
 			return ret;
 	}
@@ -154,7 +155,7 @@ static int nla_validate_int_range(const struct nla_policy *pt,
 }
 
 static int validate_nla(const struct nlattr *nla, int maxtype,
-			const struct nla_policy *policy,
+			const struct nla_policy *policy, unsigned int validate,
 			struct netlink_ext_ack *extack)
 {
 	const struct nla_policy *pt;
@@ -172,6 +173,11 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 	    (pt->type == NLA_EXACT_LEN_WARN && attrlen != pt->len)) {
 		pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n",
 				    current->comm, type);
+		if (validate & NL_VALIDATE_STRICT_ATTRS) {
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "invalid attribute length");
+			return -EINVAL;
+		}
 	}
 
 	switch (pt->type) {
@@ -244,8 +250,9 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 		if (attrlen < NLA_HDRLEN)
 			goto out_err;
 		if (pt->validation_data) {
-			err = nla_validate(nla_data(nla), nla_len(nla), pt->len,
-					   pt->validation_data, extack);
+			err = __nla_validate(nla_data(nla), nla_len(nla), pt->len,
+					     pt->validation_data, validate,
+					     extack);
 			if (err < 0) {
 				/*
 				 * return directly to preserve the inner
@@ -268,7 +275,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 
 			err = nla_validate_array(nla_data(nla), nla_len(nla),
 						 pt->len, pt->validation_data,
-						 extack);
+						 extack, validate);
 			if (err < 0) {
 				/*
 				 * return directly to preserve the inner
@@ -280,6 +287,12 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 		break;
 
 	case NLA_UNSPEC:
+		if (validate & NL_VALIDATE_UNSPEC) {
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "Unsupported attribute");
+			return -EINVAL;
+		}
+		/* fall through */
 	case NLA_MIN_LEN:
 		if (attrlen < pt->len)
 			goto out_err;
@@ -322,37 +335,75 @@ out_err:
 	return err;
 }
 
+static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype,
+				const struct nla_policy *policy,
+				unsigned int validate,
+				struct netlink_ext_ack *extack,
+				struct nlattr **tb)
+{
+	const struct nlattr *nla;
+	int rem;
+
+	if (tb)
+		memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
+
+	nla_for_each_attr(nla, head, len, rem) {
+		u16 type = nla_type(nla);
+
+		if (type == 0 || type > maxtype) {
+			if (validate & NL_VALIDATE_MAXTYPE) {
+				NL_SET_ERR_MSG(extack, "Unknown attribute type");
+				return -EINVAL;
+			}
+			continue;
+		}
+		if (policy) {
+			int err = validate_nla(nla, maxtype, policy,
+					       validate, extack);
+
+			if (err < 0)
+				return err;
+		}
+
+		if (tb)
+			tb[type] = (struct nlattr *)nla;
+	}
+
+	if (unlikely(rem > 0)) {
+		pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
+				    rem, current->comm);
+		NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes");
+		if (validate & NL_VALIDATE_TRAILING)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
- * nla_validate - Validate a stream of attributes
+ * __nla_validate - Validate a stream of attributes
  * @head: head of attribute stream
  * @len: length of attribute stream
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
+ * @validate: validation strictness
  * @extack: extended ACK report struct
  *
  * Validates all attributes in the specified attribute stream against the
- * specified policy. Attributes with a type exceeding maxtype will be
- * ignored. See documenation of struct nla_policy for more details.
+ * specified policy. Validation depends on the validate flags passed, see
+ * &enum netlink_validation for more details on that.
+ * See documenation of struct nla_policy for more details.
  *
  * Returns 0 on success or a negative error code.
  */
-int nla_validate(const struct nlattr *head, int len, int maxtype,
-		 const struct nla_policy *policy,
-		 struct netlink_ext_ack *extack)
+int __nla_validate(const struct nlattr *head, int len, int maxtype,
+		   const struct nla_policy *policy, unsigned int validate,
+		   struct netlink_ext_ack *extack)
 {
-	const struct nlattr *nla;
-	int rem;
-
-	nla_for_each_attr(nla, head, len, rem) {
-		int err = validate_nla(nla, maxtype, policy, extack);
-
-		if (err < 0)
-			return err;
-	}
-
-	return 0;
+	return __nla_validate_parse(head, len, maxtype, policy, validate,
+				    extack, NULL);
 }
-EXPORT_SYMBOL(nla_validate);
+EXPORT_SYMBOL(__nla_validate);
 
 /**
  * nla_policy_len - Determin the max. length of a policy
@@ -384,76 +435,30 @@ nla_policy_len(const struct nla_policy *p, int n)
 EXPORT_SYMBOL(nla_policy_len);
 
 /**
- * nla_parse - Parse a stream of attributes into a tb buffer
+ * __nla_parse - Parse a stream of attributes into a tb buffer
  * @tb: destination array with maxtype+1 elements
  * @maxtype: maximum attribute type to be expected
  * @head: head of attribute stream
  * @len: length of attribute stream
  * @policy: validation policy
+ * @validate: validation strictness
+ * @extack: extended ACK pointer
  *
  * Parses a stream of attributes and stores a pointer to each attribute in
- * the tb array accessible via the attribute type. Attributes with a type
- * exceeding maxtype will be silently ignored for backwards compatibility
- * reasons. policy may be set to NULL if no validation is required.
+ * the tb array accessible via the attribute type.
+ * Validation is controlled by the @validate parameter.
  *
  * Returns 0 on success or a negative error code.
  */
-static int __nla_parse(struct nlattr **tb, int maxtype,
-		       const struct nlattr *head, int len,
-		       bool strict, const struct nla_policy *policy,
-		       struct netlink_ext_ack *extack)
-{
-	const struct nlattr *nla;
-	int rem;
-
-	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
-
-	nla_for_each_attr(nla, head, len, rem) {
-		u16 type = nla_type(nla);
-
-		if (type == 0 || type > maxtype) {
-			if (strict) {
-				NL_SET_ERR_MSG(extack, "Unknown attribute type");
-				return -EINVAL;
-			}
-			continue;
-		}
-		if (policy) {
-			int err = validate_nla(nla, maxtype, policy, extack);
-
-			if (err < 0)
-				return err;
-		}
-
-		tb[type] = (struct nlattr *)nla;
-	}
-
-	if (unlikely(rem > 0)) {
-		pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
-				    rem, current->comm);
-		NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes");
-		if (strict)
-			return -EINVAL;
-	}
-
-	return 0;
-}
-
-int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
-	      int len, const struct nla_policy *policy,
-	      struct netlink_ext_ack *extack)
-{
-	return __nla_parse(tb, maxtype, head, len, false, policy, extack);
-}
-EXPORT_SYMBOL(nla_parse);
-
-int nla_parse_strict(struct nlattr **tb, int maxtype, const struct nlattr *head,
-		     int len, const struct nla_policy *policy,
-		     struct netlink_ext_ack *extack)
+int __nla_parse(struct nlattr **tb, int maxtype,
+		const struct nlattr *head, int len,
+		const struct nla_policy *policy, unsigned int validate,
+		struct netlink_ext_ack *extack)
 {
-	return __nla_parse(tb, maxtype, head, len, true, policy, extack);
+	return __nla_validate_parse(head, len, maxtype, policy, validate,
+				    extack, tb);
 }
-EXPORT_SYMBOL(nla_parse_strict);
+EXPORT_SYMBOL(__nla_parse);
 
 /**
  * nla_find - Find a specific attribute in a stream of attributes
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index ab4921e7797b..24eebbc92364 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -35,8 +35,8 @@ static inline int vlan_validate_qos_map(struct nlattr *attr)
 {
 	if (!attr)
 		return 0;
-	return nla_validate_nested(attr, IFLA_VLAN_QOS_MAX, vlan_map_policy,
-				   NULL);
+	return nla_validate_nested_deprecated(attr, IFLA_VLAN_QOS_MAX,
+					      vlan_map_policy, NULL);
 }
 
 static int vlan_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 3619c1a12a77..bf6acd34234d 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -530,8 +530,8 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net_device *dev;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY_MAX, NULL,
-			  NULL);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb,
+				     MDBA_SET_ENTRY_MAX, NULL, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 348ddb6d09bb..a5acad29cd4f 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -880,8 +880,10 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags,
 
 	if (p && protinfo) {
 		if (protinfo->nla_type & NLA_F_NESTED) {
-			err = nla_parse_nested(tb, IFLA_BRPORT_MAX, protinfo,
-					       br_port_policy, NULL);
+			err = nla_parse_nested_deprecated(tb, IFLA_BRPORT_MAX,
+							  protinfo,
+							  br_port_policy,
+							  NULL);
 			if (err)
 				return err;
 
diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c
index 787e140dc4b5..34629d558709 100644
--- a/net/bridge/br_netlink_tunnel.c
+++ b/net/bridge/br_netlink_tunnel.c
@@ -230,8 +230,8 @@ int br_parse_vlan_tunnel_info(struct nlattr *attr,
 
 	memset(tinfo, 0, sizeof(*tinfo));
 
-	err = nla_parse_nested(tb, IFLA_BRIDGE_VLAN_TUNNEL_MAX, attr,
-			       vlan_tunnel_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, IFLA_BRIDGE_VLAN_TUNNEL_MAX,
+					  attr, vlan_tunnel_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/can/gw.c b/net/can/gw.c
index 53859346dc9a..5275ddf580bc 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -662,8 +662,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod,
 	/* initialize modification & checksum data space */
 	memset(mod, 0, sizeof(*mod));
 
-	err = nlmsg_parse(nlh, sizeof(struct rtcanmsg), tb, CGW_MAX,
-			  cgw_policy, NULL);
+	err = nlmsg_parse_deprecated(nlh, sizeof(struct rtcanmsg), tb,
+				     CGW_MAX, cgw_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index b94f326f5f06..b020d182c9fc 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3674,9 +3674,10 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 	if (!attrs)
 		return -ENOMEM;
 
-	err = nlmsg_parse(cb->nlh, GENL_HDRLEN + devlink_nl_family.hdrsize,
-			  attrs, DEVLINK_ATTR_MAX, devlink_nl_family.policy,
-			  cb->extack);
+	err = nlmsg_parse_deprecated(cb->nlh,
+				     GENL_HDRLEN + devlink_nl_family.hdrsize,
+				     attrs, DEVLINK_ATTR_MAX,
+				     devlink_nl_family.policy, cb->extack);
 	if (err)
 		goto out_free;
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index ffbb827723a2..18f8dd8329ed 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -746,7 +746,8 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 	}
 
-	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX,
+				     ops->policy, extack);
 	if (err < 0) {
 		NL_SET_ERR_MSG(extack, "Error parsing msg");
 		goto errout;
@@ -853,7 +854,8 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 	}
 
-	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX,
+				     ops->policy, extack);
 	if (err < 0) {
 		NL_SET_ERR_MSG(extack, "Error parsing msg");
 		goto errout;
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index bbdfc8db1960..1c94f529f4a1 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -343,8 +343,8 @@ static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog,
 	int ret;
 	u32 fd;
 
-	ret = nla_parse_nested(tb, LWT_BPF_PROG_MAX, attr, bpf_prog_policy,
-			       NULL);
+	ret = nla_parse_nested_deprecated(tb, LWT_BPF_PROG_MAX, attr,
+					  bpf_prog_policy, NULL);
 	if (ret < 0)
 		return ret;
 
@@ -385,7 +385,8 @@ static int bpf_build_state(struct nlattr *nla,
 	if (family != AF_INET && family != AF_INET6)
 		return -EAFNOSUPPORT;
 
-	ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, extack);
+	ret = nla_parse_nested_deprecated(tb, LWT_BPF_MAX, nla, bpf_nl_policy,
+					  extack);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index efd0b53d9ca4..e73bfc63e473 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1862,7 +1862,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err;
 
 	ASSERT_RTNL();
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, nda_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX,
+				     nda_policy, extack);
 	if (err < 0)
 		goto out;
 
@@ -2181,8 +2182,8 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh,
 	bool found = false;
 	int err, tidx;
 
-	err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
-			  nl_neightbl_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
+				     nl_neightbl_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -2219,8 +2220,9 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct neigh_parms *p;
 		int i, ifindex = 0;
 
-		err = nla_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS],
-				       nl_ntbl_parm_policy, extack);
+		err = nla_parse_nested_deprecated(tbp, NDTPA_MAX,
+						  tb[NDTA_PARMS],
+						  nl_ntbl_parm_policy, extack);
 		if (err < 0)
 			goto errout_tbl_lock;
 
@@ -2660,11 +2662,12 @@ static int neigh_valid_dump_req(const struct nlmsghdr *nlh,
 			return -EINVAL;
 		}
 
-		err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
-					 nda_policy, extack);
+		err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct ndmsg),
+						    tb, NDA_MAX, nda_policy,
+						    extack);
 	} else {
-		err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
-				  nda_policy, extack);
+		err = nlmsg_parse_deprecated(nlh, sizeof(struct ndmsg), tb,
+					     NDA_MAX, nda_policy, extack);
 	}
 	if (err < 0)
 		return err;
@@ -2764,8 +2767,8 @@ static int neigh_valid_get_req(const struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
-				 nda_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct ndmsg), tb,
+					    NDA_MAX, nda_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index ebb5b6d21a13..711b161505ac 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -682,8 +682,8 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *peer;
 	int nsid, err;
 
-	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
-			  rtnl_net_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb,
+				     NETNSA_MAX, rtnl_net_policy, extack);
 	if (err < 0)
 		return err;
 	if (!tb[NETNSA_NSID]) {
@@ -787,11 +787,13 @@ static int rtnl_net_valid_getid_req(struct sk_buff *skb,
 	int i, err;
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
-				   rtnl_net_policy, extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg),
+					      tb, NETNSA_MAX, rtnl_net_policy,
+					      extack);
 
-	err = nlmsg_parse_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
-				 rtnl_net_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb,
+					    NETNSA_MAX, rtnl_net_policy,
+					    extack);
 	if (err)
 		return err;
 
@@ -929,8 +931,9 @@ static int rtnl_valid_dump_net_req(const struct nlmsghdr *nlh, struct sock *sk,
 	struct nlattr *tb[NETNSA_MAX + 1];
 	int err, i;
 
-	err = nlmsg_parse_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
-				 rtnl_net_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb,
+					    NETNSA_MAX, rtnl_net_policy,
+					    extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 8ad44b299e72..2bd12afb9297 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1797,8 +1797,7 @@ static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla
 	const struct rtnl_link_ops *ops = NULL;
 	struct nlattr *linfo[IFLA_INFO_MAX + 1];
 
-	if (nla_parse_nested(linfo, IFLA_INFO_MAX, nla,
-			     ifla_info_policy, NULL) < 0)
+	if (nla_parse_nested_deprecated(linfo, IFLA_INFO_MAX, nla, ifla_info_policy, NULL) < 0)
 		return NULL;
 
 	if (linfo[IFLA_INFO_KIND]) {
@@ -1897,8 +1896,9 @@ static int rtnl_valid_dump_ifinfo_req(const struct nlmsghdr *nlh,
 			return -EINVAL;
 		}
 
-		return nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFLA_MAX,
-					  ifla_policy, extack);
+		return nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb,
+						     IFLA_MAX, ifla_policy,
+						     extack);
 	}
 
 	/* A hack to preserve kernel<->userspace interface.
@@ -1911,7 +1911,8 @@ static int rtnl_valid_dump_ifinfo_req(const struct nlmsghdr *nlh,
 	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
 		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	return nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy, extack);
+	return nlmsg_parse_deprecated(nlh, hdrlen, tb, IFLA_MAX, ifla_policy,
+				      extack);
 }
 
 static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
@@ -2019,7 +2020,8 @@ out_err:
 int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len,
 			struct netlink_ext_ack *exterr)
 {
-	return nla_parse(tb, IFLA_MAX, head, len, ifla_policy, exterr);
+	return nla_parse_deprecated(tb, IFLA_MAX, head, len, ifla_policy,
+				    exterr);
 }
 EXPORT_SYMBOL(rtnl_nla_parse_ifla);
 
@@ -2564,8 +2566,10 @@ static int do_setlink(const struct sk_buff *skb,
 				err = -EINVAL;
 				goto errout;
 			}
-			err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
-					       ifla_vf_policy, NULL);
+			err = nla_parse_nested_deprecated(vfinfo, IFLA_VF_MAX,
+							  attr,
+							  ifla_vf_policy,
+							  NULL);
 			if (err < 0)
 				goto errout;
 			err = do_setvfinfo(dev, vfinfo);
@@ -2592,8 +2596,10 @@ static int do_setlink(const struct sk_buff *skb,
 				err = -EINVAL;
 				goto errout;
 			}
-			err = nla_parse_nested(port, IFLA_PORT_MAX, attr,
-					       ifla_port_policy, NULL);
+			err = nla_parse_nested_deprecated(port, IFLA_PORT_MAX,
+							  attr,
+							  ifla_port_policy,
+							  NULL);
 			if (err < 0)
 				goto errout;
 			if (!port[IFLA_PORT_VF]) {
@@ -2612,9 +2618,9 @@ static int do_setlink(const struct sk_buff *skb,
 	if (tb[IFLA_PORT_SELF]) {
 		struct nlattr *port[IFLA_PORT_MAX+1];
 
-		err = nla_parse_nested(port, IFLA_PORT_MAX,
-				       tb[IFLA_PORT_SELF], ifla_port_policy,
-				       NULL);
+		err = nla_parse_nested_deprecated(port, IFLA_PORT_MAX,
+						  tb[IFLA_PORT_SELF],
+						  ifla_port_policy, NULL);
 		if (err < 0)
 			goto errout;
 
@@ -2661,8 +2667,9 @@ static int do_setlink(const struct sk_buff *skb,
 		struct nlattr *xdp[IFLA_XDP_MAX + 1];
 		u32 xdp_flags = 0;
 
-		err = nla_parse_nested(xdp, IFLA_XDP_MAX, tb[IFLA_XDP],
-				       ifla_xdp_policy, NULL);
+		err = nla_parse_nested_deprecated(xdp, IFLA_XDP_MAX,
+						  tb[IFLA_XDP],
+						  ifla_xdp_policy, NULL);
 		if (err < 0)
 			goto errout;
 
@@ -2716,8 +2723,8 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct nlattr *tb[IFLA_MAX+1];
 	char ifname[IFNAMSIZ];
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFLA_MAX,
+				     ifla_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -2813,7 +2820,8 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err;
 	int netnsid = -1;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFLA_MAX,
+				     ifla_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2990,7 +2998,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 #ifdef CONFIG_MODULES
 replay:
 #endif
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFLA_MAX,
+				     ifla_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -3024,9 +3033,9 @@ replay:
 		return err;
 
 	if (tb[IFLA_LINKINFO]) {
-		err = nla_parse_nested(linkinfo, IFLA_INFO_MAX,
-				       tb[IFLA_LINKINFO], ifla_info_policy,
-				       NULL);
+		err = nla_parse_nested_deprecated(linkinfo, IFLA_INFO_MAX,
+						  tb[IFLA_LINKINFO],
+						  ifla_info_policy, NULL);
 		if (err < 0)
 			return err;
 	} else
@@ -3046,9 +3055,9 @@ replay:
 			return -EINVAL;
 
 		if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
-			err = nla_parse_nested(attr, ops->maxtype,
-					       linkinfo[IFLA_INFO_DATA],
-					       ops->policy, extack);
+			err = nla_parse_nested_deprecated(attr, ops->maxtype,
+							  linkinfo[IFLA_INFO_DATA],
+							  ops->policy, extack);
 			if (err < 0)
 				return err;
 			data = attr;
@@ -3067,9 +3076,11 @@ replay:
 
 		if (m_ops->slave_maxtype &&
 		    linkinfo[IFLA_INFO_SLAVE_DATA]) {
-			err = nla_parse_nested(slave_attr, m_ops->slave_maxtype,
-					       linkinfo[IFLA_INFO_SLAVE_DATA],
-					       m_ops->slave_policy, extack);
+			err = nla_parse_nested_deprecated(slave_attr,
+							  m_ops->slave_maxtype,
+							  linkinfo[IFLA_INFO_SLAVE_DATA],
+							  m_ops->slave_policy,
+							  extack);
 			if (err < 0)
 				return err;
 			slave_data = slave_attr;
@@ -3250,8 +3261,8 @@ static int rtnl_valid_getlink_req(struct sk_buff *skb,
 	}
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy,
-				   extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFLA_MAX,
+					      ifla_policy, extack);
 
 	ifm = nlmsg_data(nlh);
 	if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
@@ -3260,8 +3271,8 @@ static int rtnl_valid_getlink_req(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy,
-				 extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFLA_MAX,
+					    ifla_policy, extack);
 	if (err)
 		return err;
 
@@ -3366,7 +3377,7 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
 		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) {
+	if (nlmsg_parse_deprecated(nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 	}
@@ -3639,7 +3650,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u16 vid;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX, NULL,
+				     extack);
 	if (err < 0)
 		return err;
 
@@ -3749,7 +3761,8 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL, extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX, NULL,
+				     extack);
 	if (err < 0)
 		return err;
 
@@ -3898,8 +3911,8 @@ static int valid_fdb_dump_strict(const struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
-				 NULL, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct ndmsg), tb,
+					    NDA_MAX, NULL, extack);
 	if (err < 0)
 		return err;
 
@@ -3951,8 +3964,9 @@ static int valid_fdb_dump_legacy(const struct nlmsghdr *nlh,
 	     nla_attr_size(sizeof(u32)))) {
 		struct ifinfomsg *ifm;
 
-		err = nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-				  ifla_policy, extack);
+		err = nlmsg_parse_deprecated(nlh, sizeof(struct ifinfomsg),
+					     tb, IFLA_MAX, ifla_policy,
+					     extack);
 		if (err < 0) {
 			return -EINVAL;
 		} else if (err == 0) {
@@ -4091,8 +4105,8 @@ static int valid_fdb_get_strict(const struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
-				 nda_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct ndmsg), tb,
+					    NDA_MAX, nda_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -4354,11 +4368,14 @@ static int valid_bridge_getlink_req(const struct nlmsghdr *nlh,
 			return -EINVAL;
 		}
 
-		err = nlmsg_parse_strict(nlh, sizeof(struct ifinfomsg), tb,
-					 IFLA_MAX, ifla_policy, extack);
+		err = nlmsg_parse_deprecated_strict(nlh,
+						    sizeof(struct ifinfomsg),
+						    tb, IFLA_MAX, ifla_policy,
+						    extack);
 	} else {
-		err = nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb,
-				  IFLA_MAX, ifla_policy, extack);
+		err = nlmsg_parse_deprecated(nlh, sizeof(struct ifinfomsg),
+					     tb, IFLA_MAX, ifla_policy,
+					     extack);
 	}
 	if (err < 0)
 		return err;
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 3fd3aa7348bd..ceff9d22deea 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -241,8 +241,9 @@ static int dcbnl_getpfccfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!netdev->dcbnl_ops->getpfccfg)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX,
-			       tb[DCB_ATTR_PFC_CFG], dcbnl_pfc_up_nest, NULL);
+	ret = nla_parse_nested_deprecated(data, DCB_PFC_UP_ATTR_MAX,
+					  tb[DCB_ATTR_PFC_CFG],
+					  dcbnl_pfc_up_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -299,8 +300,9 @@ static int dcbnl_getcap(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!netdev->dcbnl_ops->getcap)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(data, DCB_CAP_ATTR_MAX, tb[DCB_ATTR_CAP],
-			       dcbnl_cap_nest, NULL);
+	ret = nla_parse_nested_deprecated(data, DCB_CAP_ATTR_MAX,
+					  tb[DCB_ATTR_CAP], dcbnl_cap_nest,
+					  NULL);
 	if (ret)
 		return ret;
 
@@ -343,8 +345,9 @@ static int dcbnl_getnumtcs(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!netdev->dcbnl_ops->getnumtcs)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
-			       dcbnl_numtcs_nest, NULL);
+	ret = nla_parse_nested_deprecated(data, DCB_NUMTCS_ATTR_MAX,
+					  tb[DCB_ATTR_NUMTCS],
+					  dcbnl_numtcs_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -388,8 +391,9 @@ static int dcbnl_setnumtcs(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!netdev->dcbnl_ops->setnumtcs)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
-			       dcbnl_numtcs_nest, NULL);
+	ret = nla_parse_nested_deprecated(data, DCB_NUMTCS_ATTR_MAX,
+					  tb[DCB_ATTR_NUMTCS],
+					  dcbnl_numtcs_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -447,8 +451,9 @@ static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!tb[DCB_ATTR_APP])
 		return -EINVAL;
 
-	ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
-			       dcbnl_app_nest, NULL);
+	ret = nla_parse_nested_deprecated(app_tb, DCB_APP_ATTR_MAX,
+					  tb[DCB_ATTR_APP], dcbnl_app_nest,
+					  NULL);
 	if (ret)
 		return ret;
 
@@ -515,8 +520,9 @@ static int dcbnl_setapp(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!tb[DCB_ATTR_APP])
 		return -EINVAL;
 
-	ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
-			       dcbnl_app_nest, NULL);
+	ret = nla_parse_nested_deprecated(app_tb, DCB_APP_ATTR_MAX,
+					  tb[DCB_ATTR_APP], dcbnl_app_nest,
+					  NULL);
 	if (ret)
 		return ret;
 
@@ -573,8 +579,9 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	    !netdev->dcbnl_ops->getpgbwgcfgrx)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX, tb[DCB_ATTR_PG_CFG],
-			       dcbnl_pg_nest, NULL);
+	ret = nla_parse_nested_deprecated(pg_tb, DCB_PG_ATTR_MAX,
+					  tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest,
+					  NULL);
 	if (ret)
 		return ret;
 
@@ -593,8 +600,9 @@ static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 			data = pg_tb[DCB_PG_ATTR_TC_ALL];
 		else
 			data = pg_tb[i];
-		ret = nla_parse_nested(param_tb, DCB_TC_ATTR_PARAM_MAX, data,
-				       dcbnl_tc_param_nest, NULL);
+		ret = nla_parse_nested_deprecated(param_tb,
+						  DCB_TC_ATTR_PARAM_MAX, data,
+						  dcbnl_tc_param_nest, NULL);
 		if (ret)
 			goto err_pg;
 
@@ -730,8 +738,9 @@ static int dcbnl_setpfccfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!netdev->dcbnl_ops->setpfccfg)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX,
-			       tb[DCB_ATTR_PFC_CFG], dcbnl_pfc_up_nest, NULL);
+	ret = nla_parse_nested_deprecated(data, DCB_PFC_UP_ATTR_MAX,
+					  tb[DCB_ATTR_PFC_CFG],
+					  dcbnl_pfc_up_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -786,8 +795,9 @@ static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	    !netdev->dcbnl_ops->setpgbwgcfgrx)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX, tb[DCB_ATTR_PG_CFG],
-			       dcbnl_pg_nest, NULL);
+	ret = nla_parse_nested_deprecated(pg_tb, DCB_PG_ATTR_MAX,
+					  tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest,
+					  NULL);
 	if (ret)
 		return ret;
 
@@ -795,8 +805,10 @@ static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 		if (!pg_tb[i])
 			continue;
 
-		ret = nla_parse_nested(param_tb, DCB_TC_ATTR_PARAM_MAX,
-				       pg_tb[i], dcbnl_tc_param_nest, NULL);
+		ret = nla_parse_nested_deprecated(param_tb,
+						  DCB_TC_ATTR_PARAM_MAX,
+						  pg_tb[i],
+						  dcbnl_tc_param_nest, NULL);
 		if (ret)
 			return ret;
 
@@ -884,8 +896,9 @@ static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	    !netdev->dcbnl_ops->getbcncfg)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(bcn_tb, DCB_BCN_ATTR_MAX, tb[DCB_ATTR_BCN],
-			       dcbnl_bcn_nest, NULL);
+	ret = nla_parse_nested_deprecated(bcn_tb, DCB_BCN_ATTR_MAX,
+					  tb[DCB_ATTR_BCN], dcbnl_bcn_nest,
+					  NULL);
 	if (ret)
 		return ret;
 
@@ -943,8 +956,9 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	    !netdev->dcbnl_ops->setbcnrp)
 		return -EOPNOTSUPP;
 
-	ret = nla_parse_nested(data, DCB_BCN_ATTR_MAX, tb[DCB_ATTR_BCN],
-			       dcbnl_pfc_up_nest, NULL);
+	ret = nla_parse_nested_deprecated(data, DCB_BCN_ATTR_MAX,
+					  tb[DCB_ATTR_BCN], dcbnl_pfc_up_nest,
+					  NULL);
 	if (ret)
 		return ret;
 
@@ -1431,8 +1445,9 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!tb[DCB_ATTR_IEEE])
 		return -EINVAL;
 
-	err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX, tb[DCB_ATTR_IEEE],
-			       dcbnl_ieee_policy, NULL);
+	err = nla_parse_nested_deprecated(ieee, DCB_ATTR_IEEE_MAX,
+					  tb[DCB_ATTR_IEEE],
+					  dcbnl_ieee_policy, NULL);
 	if (err)
 		return err;
 
@@ -1531,8 +1546,9 @@ static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!tb[DCB_ATTR_IEEE])
 		return -EINVAL;
 
-	err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX, tb[DCB_ATTR_IEEE],
-			       dcbnl_ieee_policy, NULL);
+	err = nla_parse_nested_deprecated(ieee, DCB_ATTR_IEEE_MAX,
+					  tb[DCB_ATTR_IEEE],
+					  dcbnl_ieee_policy, NULL);
 	if (err)
 		return err;
 
@@ -1604,8 +1620,9 @@ static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!tb[DCB_ATTR_FEATCFG])
 		return -EINVAL;
 
-	ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX,
-			       tb[DCB_ATTR_FEATCFG], dcbnl_featcfg_nest, NULL);
+	ret = nla_parse_nested_deprecated(data, DCB_FEATCFG_ATTR_MAX,
+					  tb[DCB_ATTR_FEATCFG],
+					  dcbnl_featcfg_nest, NULL);
 	if (ret)
 		return ret;
 
@@ -1648,8 +1665,9 @@ static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh,
 	if (!tb[DCB_ATTR_FEATCFG])
 		return -EINVAL;
 
-	ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX,
-			       tb[DCB_ATTR_FEATCFG], dcbnl_featcfg_nest, NULL);
+	ret = nla_parse_nested_deprecated(data, DCB_FEATCFG_ATTR_MAX,
+					  tb[DCB_ATTR_FEATCFG],
+					  dcbnl_featcfg_nest, NULL);
 
 	if (ret)
 		goto err;
@@ -1738,8 +1756,8 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX,
-			  dcbnl_rtnl_policy, extack);
+	ret = nlmsg_parse_deprecated(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX,
+				     dcbnl_rtnl_policy, extack);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 0962f9201baa..cca7ae712995 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -583,8 +583,8 @@ static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!net_eq(net, &init_net))
 		goto errout;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+				     dn_ifa_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -629,8 +629,8 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!net_eq(net, &init_net))
 		return -EINVAL;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+				     dn_ifa_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index 7e47ffdd1412..77fbf8e9df4b 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -517,8 +517,8 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!net_eq(net, &init_net))
 		return -EINVAL;
 
-	err = nlmsg_parse(nlh, sizeof(*r), attrs, RTA_MAX, rtm_dn_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*r), attrs, RTA_MAX,
+				     rtm_dn_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -544,8 +544,8 @@ static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!net_eq(net, &init_net))
 		return -EINVAL;
 
-	err = nlmsg_parse(nlh, sizeof(*r), attrs, RTA_MAX, rtm_dn_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*r), attrs, RTA_MAX,
+				     rtm_dn_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 950613ee7881..664584763c36 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1651,8 +1651,8 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	if (!net_eq(net, &init_net))
 		return -EINVAL;
 
-	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_dn_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
+				     rtm_dn_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 1a002eb85096..4218304cb201 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -247,9 +247,11 @@ nl802154_prepare_wpan_dev_dump(struct sk_buff *skb,
 	rtnl_lock();
 
 	if (!cb->args[0]) {
-		err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl802154_fam.hdrsize,
-				  genl_family_attrbuf(&nl802154_fam),
-				  nl802154_fam.maxattr, nl802154_policy, NULL);
+		err = nlmsg_parse_deprecated(cb->nlh,
+					     GENL_HDRLEN + nl802154_fam.hdrsize,
+					     genl_family_attrbuf(&nl802154_fam),
+					     nl802154_fam.maxattr,
+					     nl802154_policy, NULL);
 		if (err)
 			goto out_unlock;
 
@@ -562,8 +564,10 @@ static int nl802154_dump_wpan_phy_parse(struct sk_buff *skb,
 					struct nl802154_dump_wpan_phy_state *state)
 {
 	struct nlattr **tb = genl_family_attrbuf(&nl802154_fam);
-	int ret = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl802154_fam.hdrsize, tb,
-			      nl802154_fam.maxattr, nl802154_policy, NULL);
+	int ret = nlmsg_parse_deprecated(cb->nlh,
+					 GENL_HDRLEN + nl802154_fam.hdrsize,
+					 tb, nl802154_fam.maxattr,
+					 nl802154_policy, NULL);
 
 	/* TODO check if we can handle error here,
 	 * we have no backward compatibility
@@ -1308,8 +1312,7 @@ ieee802154_llsec_parse_dev_addr(struct nlattr *nla,
 {
 	struct nlattr *attrs[NL802154_DEV_ADDR_ATTR_MAX + 1];
 
-	if (!nla || nla_parse_nested(attrs, NL802154_DEV_ADDR_ATTR_MAX, nla,
-				     nl802154_dev_addr_policy, NULL))
+	if (!nla || nla_parse_nested_deprecated(attrs, NL802154_DEV_ADDR_ATTR_MAX, nla, nl802154_dev_addr_policy, NULL))
 		return -EINVAL;
 
 	if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] ||
@@ -1348,8 +1351,7 @@ ieee802154_llsec_parse_key_id(struct nlattr *nla,
 {
 	struct nlattr *attrs[NL802154_KEY_ID_ATTR_MAX + 1];
 
-	if (!nla || nla_parse_nested(attrs, NL802154_KEY_ID_ATTR_MAX, nla,
-				     nl802154_key_id_policy, NULL))
+	if (!nla || nla_parse_nested_deprecated(attrs, NL802154_KEY_ID_ATTR_MAX, nla, nl802154_key_id_policy, NULL))
 		return -EINVAL;
 
 	if (!attrs[NL802154_KEY_ID_ATTR_MODE])
@@ -1564,9 +1566,7 @@ static int nl802154_add_llsec_key(struct sk_buff *skb, struct genl_info *info)
 	struct ieee802154_llsec_key_id id = { };
 	u32 commands[NL802154_CMD_FRAME_NR_IDS / 32] = { };
 
-	if (nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX,
-			     info->attrs[NL802154_ATTR_SEC_KEY],
-			     nl802154_key_policy, info->extack))
+	if (nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
 		return -EINVAL;
 
 	if (!attrs[NL802154_KEY_ATTR_USAGE_FRAMES] ||
@@ -1614,9 +1614,7 @@ static int nl802154_del_llsec_key(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1];
 	struct ieee802154_llsec_key_id id;
 
-	if (nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX,
-			     info->attrs[NL802154_ATTR_SEC_KEY],
-			     nl802154_key_policy, info->extack))
+	if (nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
 		return -EINVAL;
 
 	if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0)
@@ -1730,8 +1728,7 @@ ieee802154_llsec_parse_device(struct nlattr *nla,
 {
 	struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1];
 
-	if (!nla || nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX,
-				     nla, nl802154_dev_policy, NULL))
+	if (!nla || nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, nla, nl802154_dev_policy, NULL))
 		return -EINVAL;
 
 	memset(dev, 0, sizeof(*dev));
@@ -1782,9 +1779,7 @@ static int nl802154_del_llsec_dev(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1];
 	__le64 extended_addr;
 
-	if (nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX,
-			     info->attrs[NL802154_ATTR_SEC_DEVICE],
-			     nl802154_dev_policy, info->extack))
+	if (nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack))
 		return -EINVAL;
 
 	if (!attrs[NL802154_DEV_ATTR_EXTENDED_ADDR])
@@ -1910,9 +1905,7 @@ static int nl802154_add_llsec_devkey(struct sk_buff *skb, struct genl_info *info
 	__le64 extended_addr;
 
 	if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] ||
-	    nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX,
-			     info->attrs[NL802154_ATTR_SEC_DEVKEY],
-			     nl802154_devkey_policy, info->extack) < 0)
+	    nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack) < 0)
 		return -EINVAL;
 
 	if (!attrs[NL802154_DEVKEY_ATTR_FRAME_COUNTER] ||
@@ -1942,9 +1935,7 @@ static int nl802154_del_llsec_devkey(struct sk_buff *skb, struct genl_info *info
 	struct ieee802154_llsec_device_key key;
 	__le64 extended_addr;
 
-	if (nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX,
-			     info->attrs[NL802154_ATTR_SEC_DEVKEY],
-			     nl802154_devkey_policy, info->extack))
+	if (nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack))
 		return -EINVAL;
 
 	if (!attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR])
@@ -2064,8 +2055,7 @@ llsec_parse_seclevel(struct nlattr *nla, struct ieee802154_llsec_seclevel *sl)
 {
 	struct nlattr *attrs[NL802154_SECLEVEL_ATTR_MAX + 1];
 
-	if (!nla || nla_parse_nested(attrs, NL802154_SECLEVEL_ATTR_MAX,
-				     nla, nl802154_seclevel_policy, NULL))
+	if (!nla || nla_parse_nested_deprecated(attrs, NL802154_SECLEVEL_ATTR_MAX, nla, nl802154_seclevel_policy, NULL))
 		return -EINVAL;
 
 	memset(sl, 0, sizeof(*sl));
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index eb514f312e6f..701c5d113a34 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -621,8 +621,8 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	ASSERT_RTNL();
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+				     ifa_ipv4_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -793,8 +793,8 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 	struct in_device *in_dev;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+				     ifa_ipv4_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -1689,8 +1689,8 @@ static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
 		fillargs->flags |= NLM_F_DUMP_FILTERED;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
-				 ifa_ipv4_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
+					    ifa_ipv4_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -1906,7 +1906,8 @@ static int inet_validate_link_af(const struct net_device *dev,
 	if (dev && !__in_dev_get_rcu(dev))
 		return -EAFNOSUPPORT;
 
-	err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla,
+					  inet_af_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1934,7 +1935,7 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla)
 	if (!in_dev)
 		return -EAFNOSUPPORT;
 
-	if (nla_parse_nested(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0)
+	if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0)
 		BUG();
 
 	if (tb[IFLA_INET_CONF]) {
@@ -2076,11 +2077,13 @@ static int inet_netconf_valid_get_req(struct sk_buff *skb,
 	}
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(struct netconfmsg), tb,
-				   NETCONFA_MAX, devconf_ipv4_policy, extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg),
+					      tb, NETCONFA_MAX,
+					      devconf_ipv4_policy, extack);
 
-	err = nlmsg_parse_strict(nlh, sizeof(struct netconfmsg), tb,
-				 NETCONFA_MAX, devconf_ipv4_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg),
+					    tb, NETCONFA_MAX,
+					    devconf_ipv4_policy, extack);
 	if (err)
 		return err;
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index d4b63f94f7be..b298255f6fdb 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -718,8 +718,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 	int err, remaining;
 	struct rtmsg *rtm;
 
-	err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy,
-			     extack);
+	err = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX,
+					rtm_ipv4_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -896,8 +896,8 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 	filter->rt_type  = rtm->rtm_type;
 	filter->table_id = rtm->rtm_table;
 
-	err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
-				 rtm_ipv4_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
+					    rtm_ipv4_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index c3f3d28d1087..30c1c264bdfc 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -239,8 +239,8 @@ static int ip_tun_build_state(struct nlattr *attr,
 	struct nlattr *tb[LWTUNNEL_IP_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy,
-			       extack);
+	err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_MAX, attr,
+					  ip_tun_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -356,8 +356,8 @@ static int ip6_tun_build_state(struct nlattr *attr,
 	struct nlattr *tb[LWTUNNEL_IP6_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy,
-			       extack);
+	err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP6_MAX, attr,
+					  ip6_tun_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 1322573b8228..2c61e10a60e3 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2498,8 +2498,8 @@ static int ipmr_rtm_valid_getroute_req(struct sk_buff *skb,
 	}
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX,
-				   rtm_ipv4_policy, extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
+					      rtm_ipv4_policy, extack);
 
 	rtm = nlmsg_data(nlh);
 	if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) ||
@@ -2510,8 +2510,8 @@ static int ipmr_rtm_valid_getroute_req(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
-				 rtm_ipv4_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
+					    rtm_ipv4_policy, extack);
 	if (err)
 		return err;
 
@@ -2674,8 +2674,8 @@ static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh,
 	struct rtmsg *rtm;
 	int ret, rem;
 
-	ret = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipmr_policy,
-			     extack);
+	ret = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX,
+					rtm_ipmr_policy, extack);
 	if (ret < 0)
 		goto out;
 	rtm = nlmsg_data(nlh);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 4950adeb05c0..795aed6e4720 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2877,8 +2877,8 @@ static int inet_rtm_valid_getroute_req(struct sk_buff *skb,
 	}
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX,
-				   rtm_ipv4_policy, extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
+					      rtm_ipv4_policy, extack);
 
 	rtm = nlmsg_data(nlh);
 	if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) ||
@@ -2896,8 +2896,8 @@ static int inet_rtm_valid_getroute_req(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
-				 rtm_ipv4_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
+					    rtm_ipv4_policy, extack);
 	if (err)
 		return err;
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 01f081aa718c..f96d1de79509 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -611,11 +611,13 @@ static int inet6_netconf_valid_get_req(struct sk_buff *skb,
 	}
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(struct netconfmsg), tb,
-				   NETCONFA_MAX, devconf_ipv6_policy, extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg),
+					      tb, NETCONFA_MAX,
+					      devconf_ipv6_policy, extack);
 
-	err = nlmsg_parse_strict(nlh, sizeof(struct netconfmsg), tb,
-				 NETCONFA_MAX, devconf_ipv6_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg),
+					    tb, NETCONFA_MAX,
+					    devconf_ipv6_policy, extack);
 	if (err)
 		return err;
 
@@ -4565,8 +4567,8 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u32 ifa_flags;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+				     ifa_ipv6_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -4729,8 +4731,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct ifa6_config cfg;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+				     ifa_ipv6_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -5086,8 +5088,8 @@ static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
 		fillargs->flags |= NLM_F_DUMP_FILTERED;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
-				 ifa_ipv6_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
+					    ifa_ipv6_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -5237,11 +5239,11 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb,
 	}
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX,
-				   ifa_ipv6_policy, extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+					      ifa_ipv6_policy, extack);
 
-	err = nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
-				 ifa_ipv6_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
+					    ifa_ipv6_policy, extack);
 	if (err)
 		return err;
 
@@ -5667,8 +5669,8 @@ static int inet6_validate_link_af(const struct net_device *dev,
 	if (dev && !__in6_dev_get(dev))
 		return -EAFNOSUPPORT;
 
-	return nla_parse_nested(tb, IFLA_INET6_MAX, nla, inet6_af_policy,
-				NULL);
+	return nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla,
+					   inet6_af_policy, NULL);
 }
 
 static int check_addr_gen_mode(int mode)
@@ -5700,7 +5702,7 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
 	if (!idev)
 		return -EAFNOSUPPORT;
 
-	if (nla_parse_nested(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0)
+	if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0)
 		BUG();
 
 	if (tb[IFLA_INET6_TOKEN]) {
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 1766325423b5..642fc6ac13d2 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -383,8 +383,8 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh,
 	u32 label;
 	int err = 0;
 
-	err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifal), tb, IFAL_MAX,
+				     ifal_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -537,8 +537,8 @@ static int ip6addrlbl_valid_get_req(struct sk_buff *skb,
 	}
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX,
-				   ifal_policy, extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(*ifal), tb,
+					      IFAL_MAX, ifal_policy, extack);
 
 	ifal = nlmsg_data(nlh);
 	if (ifal->__ifal_reserved || ifal->ifal_flags || ifal->ifal_seq) {
@@ -546,8 +546,8 @@ static int ip6addrlbl_valid_get_req(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(*ifal), tb, IFAL_MAX,
-				 ifal_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifal), tb, IFAL_MAX,
+					    ifal_policy, extack);
 	if (err)
 		return err;
 
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index 3d56a2fb6f86..422dcc691f71 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -146,7 +146,8 @@ static int ila_build_state(struct nlattr *nla,
 	if (family != AF_INET6)
 		return -EINVAL;
 
-	ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack);
+	ret = nla_parse_nested_deprecated(tb, ILA_ATTR_MAX, nla,
+					  ila_nl_policy, extack);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index e2b47f47de92..b18e85cd7587 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4239,8 +4239,8 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int pref;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
+				     rtm_ipv6_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -4886,8 +4886,8 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
 	}
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX,
-				   rtm_ipv6_policy, extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
+					      rtm_ipv6_policy, extack);
 
 	rtm = nlmsg_data(nlh);
 	if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) ||
@@ -4903,8 +4903,8 @@ static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
-				 rtm_ipv6_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
+					    rtm_ipv6_policy, extack);
 	if (err)
 		return err;
 
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index ee5403cbe655..7a525fda8978 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -396,8 +396,8 @@ static int seg6_build_state(struct nlattr *nla,
 	if (family != AF_INET && family != AF_INET6)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla,
-			       seg6_iptunnel_policy, extack);
+	err = nla_parse_nested_deprecated(tb, SEG6_IPTUNNEL_MAX, nla,
+					  seg6_iptunnel_policy, extack);
 
 	if (err < 0)
 		return err;
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index 67005ac71341..78155fdb8c36 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -823,8 +823,9 @@ static int parse_nla_bpf(struct nlattr **attrs, struct seg6_local_lwt *slwt)
 	int ret;
 	u32 fd;
 
-	ret = nla_parse_nested(tb, SEG6_LOCAL_BPF_PROG_MAX,
-			       attrs[SEG6_LOCAL_BPF], bpf_prog_policy, NULL);
+	ret = nla_parse_nested_deprecated(tb, SEG6_LOCAL_BPF_PROG_MAX,
+					  attrs[SEG6_LOCAL_BPF],
+					  bpf_prog_policy, NULL);
 	if (ret < 0)
 		return ret;
 
@@ -959,8 +960,8 @@ static int seg6_local_build_state(struct nlattr *nla, unsigned int family,
 	if (family != AF_INET6)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, SEG6_LOCAL_MAX, nla, seg6_local_policy,
-			       extack);
+	err = nla_parse_nested_deprecated(tb, SEG6_LOCAL_MAX, nla,
+					  seg6_local_policy, extack);
 
 	if (err < 0)
 		return err;
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 01f8a4f97872..baa098291fb0 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1223,11 +1223,13 @@ static int mpls_netconf_valid_get_req(struct sk_buff *skb,
 	}
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(struct netconfmsg), tb,
-				   NETCONFA_MAX, devconf_mpls_policy, extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg),
+					      tb, NETCONFA_MAX,
+					      devconf_mpls_policy, extack);
 
-	err = nlmsg_parse_strict(nlh, sizeof(struct netconfmsg), tb,
-				 NETCONFA_MAX, devconf_mpls_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg),
+					    tb, NETCONFA_MAX,
+					    devconf_mpls_policy, extack);
 	if (err)
 		return err;
 
@@ -1788,8 +1790,8 @@ static int rtm_to_route_config(struct sk_buff *skb,
 	int index;
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
+				     rtm_mpls_policy, extack);
 	if (err < 0)
 		goto errout;
 
@@ -2106,8 +2108,8 @@ static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 		cb->answer_flags = NLM_F_DUMP_FILTERED;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
-				 rtm_mpls_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
+					    rtm_mpls_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2290,8 +2292,8 @@ static int mpls_valid_getroute_req(struct sk_buff *skb,
 	}
 
 	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX,
-				   rtm_mpls_policy, extack);
+		return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
+					      rtm_mpls_policy, extack);
 
 	rtm = nlmsg_data(nlh);
 	if ((rtm->rtm_dst_len && rtm->rtm_dst_len != 20) ||
@@ -2306,8 +2308,8 @@ static int mpls_valid_getroute_req(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-	err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
-				 rtm_mpls_policy, extack);
+	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
+					    rtm_mpls_policy, extack);
 	if (err)
 		return err;
 
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 2619c2fbea93..951b52d5835b 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -178,8 +178,8 @@ static int mpls_build_state(struct nlattr *nla,
 	u8 n_labels;
 	int ret;
 
-	ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla,
-			       mpls_iptunnel_policy, extack);
+	ret = nla_parse_nested_deprecated(tb, MPLS_IPTUNNEL_MAX, nla,
+					  mpls_iptunnel_policy, extack);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 672ed56b5ef0..37759c88ef02 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -220,8 +220,8 @@ static int ncsi_pkg_info_all_nl(struct sk_buff *skb,
 	void *hdr;
 	int rc;
 
-	rc = genlmsg_parse(cb->nlh, &ncsi_genl_family, attrs, NCSI_ATTR_MAX,
-			   ncsi_genl_policy, NULL);
+	rc = genlmsg_parse_deprecated(cb->nlh, &ncsi_genl_family, attrs, NCSI_ATTR_MAX,
+				      ncsi_genl_policy, NULL);
 	if (rc)
 		return rc;
 
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 45a257695bef..3f4a4936f63c 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -299,8 +299,7 @@ ip_set_get_ipaddr4(struct nlattr *nla,  __be32 *ipaddr)
 
 	if (unlikely(!flag_nested(nla)))
 		return -IPSET_ERR_PROTOCOL;
-	if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla,
-			     ipaddr_policy, NULL))
+	if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL))
 		return -IPSET_ERR_PROTOCOL;
 	if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV4)))
 		return -IPSET_ERR_PROTOCOL;
@@ -318,8 +317,7 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
 	if (unlikely(!flag_nested(nla)))
 		return -IPSET_ERR_PROTOCOL;
 
-	if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla,
-			     ipaddr_policy, NULL))
+	if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL))
 		return -IPSET_ERR_PROTOCOL;
 	if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV6)))
 		return -IPSET_ERR_PROTOCOL;
@@ -939,8 +937,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
 
 	/* Without holding any locks, create private part. */
 	if (attr[IPSET_ATTR_DATA] &&
-	    nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA],
-			     set->type->create_policy, NULL)) {
+	    nla_parse_nested_deprecated(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], set->type->create_policy, NULL)) {
 		ret = -IPSET_ERR_PROTOCOL;
 		goto put_out;
 	}
@@ -1298,8 +1295,9 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
 	ip_set_id_t index;
 
 	/* Second pass, so parser can't fail */
-	nla_parse(cda, IPSET_ATTR_CMD_MAX, attr, nlh->nlmsg_len - min_len,
-		  ip_set_setname_policy, NULL);
+	nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, attr,
+			     nlh->nlmsg_len - min_len, ip_set_setname_policy,
+			     NULL);
 
 	cb->args[IPSET_CB_PROTO] = nla_get_u8(cda[IPSET_ATTR_PROTOCOL]);
 	if (cda[IPSET_ATTR_SETNAME]) {
@@ -1546,8 +1544,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
 		memcpy(&errmsg->msg, nlh, nlh->nlmsg_len);
 		cmdattr = (void *)&errmsg->msg + min_len;
 
-		nla_parse(cda, IPSET_ATTR_CMD_MAX, cmdattr,
-			  nlh->nlmsg_len - min_len, ip_set_adt_policy, NULL);
+		nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, cmdattr,
+				     nlh->nlmsg_len - min_len,
+				     ip_set_adt_policy, NULL);
 
 		errline = nla_data(cda[IPSET_ATTR_LINENO]);
 
@@ -1592,9 +1591,7 @@ static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 
 	use_lineno = !!attr[IPSET_ATTR_LINENO];
 	if (attr[IPSET_ATTR_DATA]) {
-		if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX,
-				     attr[IPSET_ATTR_DATA],
-				     set->type->adt_policy, NULL))
+		if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL))
 			return -IPSET_ERR_PROTOCOL;
 		ret = call_ad(ctnl, skb, set, tb, IPSET_ADD, flags,
 			      use_lineno);
@@ -1605,8 +1602,7 @@ static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 			memset(tb, 0, sizeof(tb));
 			if (nla_type(nla) != IPSET_ATTR_DATA ||
 			    !flag_nested(nla) ||
-			    nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla,
-					     set->type->adt_policy, NULL))
+			    nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, nla, set->type->adt_policy, NULL))
 				return -IPSET_ERR_PROTOCOL;
 			ret = call_ad(ctnl, skb, set, tb, IPSET_ADD,
 				      flags, use_lineno);
@@ -1647,9 +1643,7 @@ static int ip_set_udel(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 
 	use_lineno = !!attr[IPSET_ATTR_LINENO];
 	if (attr[IPSET_ATTR_DATA]) {
-		if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX,
-				     attr[IPSET_ATTR_DATA],
-				     set->type->adt_policy, NULL))
+		if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL))
 			return -IPSET_ERR_PROTOCOL;
 		ret = call_ad(ctnl, skb, set, tb, IPSET_DEL, flags,
 			      use_lineno);
@@ -1660,8 +1654,7 @@ static int ip_set_udel(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 			memset(tb, 0, sizeof(*tb));
 			if (nla_type(nla) != IPSET_ATTR_DATA ||
 			    !flag_nested(nla) ||
-			    nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla,
-					     set->type->adt_policy, NULL))
+			    nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, nla, set->type->adt_policy, NULL))
 				return -IPSET_ERR_PROTOCOL;
 			ret = call_ad(ctnl, skb, set, tb, IPSET_DEL,
 				      flags, use_lineno);
@@ -1692,8 +1685,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	if (!set)
 		return -ENOENT;
 
-	if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA],
-			     set->type->adt_policy, NULL))
+	if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL))
 		return -IPSET_ERR_PROTOCOL;
 
 	rcu_read_lock_bh();
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 39892e5d38a2..24bb1a7b590c 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3116,8 +3116,7 @@ static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs,
 
 	/* Parse mandatory identifying service fields first */
 	if (nla == NULL ||
-	    nla_parse_nested(attrs, IPVS_SVC_ATTR_MAX, nla,
-			     ip_vs_svc_policy, NULL))
+	    nla_parse_nested_deprecated(attrs, IPVS_SVC_ATTR_MAX, nla, ip_vs_svc_policy, NULL))
 		return -EINVAL;
 
 	nla_af		= attrs[IPVS_SVC_ATTR_AF];
@@ -3279,8 +3278,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
 	mutex_lock(&__ip_vs_mutex);
 
 	/* Try to find the service for which to dump destinations */
-	if (nlmsg_parse(cb->nlh, GENL_HDRLEN, attrs, IPVS_CMD_ATTR_MAX,
-			ip_vs_cmd_policy, cb->extack))
+	if (nlmsg_parse_deprecated(cb->nlh, GENL_HDRLEN, attrs, IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy, cb->extack))
 		goto out_err;
 
 
@@ -3316,8 +3314,7 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
 
 	/* Parse mandatory identifying destination fields first */
 	if (nla == NULL ||
-	    nla_parse_nested(attrs, IPVS_DEST_ATTR_MAX, nla,
-			     ip_vs_dest_policy, NULL))
+	    nla_parse_nested_deprecated(attrs, IPVS_DEST_ATTR_MAX, nla, ip_vs_dest_policy, NULL))
 		return -EINVAL;
 
 	nla_addr	= attrs[IPVS_DEST_ATTR_ADDR];
@@ -3561,9 +3558,7 @@ static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info)
 		struct nlattr *daemon_attrs[IPVS_DAEMON_ATTR_MAX + 1];
 
 		if (!info->attrs[IPVS_CMD_ATTR_DAEMON] ||
-		    nla_parse_nested(daemon_attrs, IPVS_DAEMON_ATTR_MAX,
-				     info->attrs[IPVS_CMD_ATTR_DAEMON],
-				     ip_vs_daemon_policy, info->extack))
+		    nla_parse_nested_deprecated(daemon_attrs, IPVS_DAEMON_ATTR_MAX, info->attrs[IPVS_CMD_ATTR_DAEMON], ip_vs_daemon_policy, info->extack))
 			goto out;
 
 		if (cmd == IPVS_CMD_NEW_DAEMON)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 148b99a15b21..8dcc064d518d 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1020,12 +1020,12 @@ static int ctnetlink_parse_tuple_ip(struct nlattr *attr,
 	struct nlattr *tb[CTA_IP_MAX+1];
 	int ret = 0;
 
-	ret = nla_parse_nested(tb, CTA_IP_MAX, attr, NULL, NULL);
+	ret = nla_parse_nested_deprecated(tb, CTA_IP_MAX, attr, NULL, NULL);
 	if (ret < 0)
 		return ret;
 
-	ret = nla_validate_nested(attr, CTA_IP_MAX,
-				  cta_ip_nla_policy, NULL);
+	ret = nla_validate_nested_deprecated(attr, CTA_IP_MAX,
+					     cta_ip_nla_policy, NULL);
 	if (ret)
 		return ret;
 
@@ -1052,8 +1052,8 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr,
 	struct nlattr *tb[CTA_PROTO_MAX+1];
 	int ret = 0;
 
-	ret = nla_parse_nested(tb, CTA_PROTO_MAX, attr, proto_nla_policy,
-			       NULL);
+	ret = nla_parse_nested_deprecated(tb, CTA_PROTO_MAX, attr,
+					  proto_nla_policy, NULL);
 	if (ret < 0)
 		return ret;
 
@@ -1065,8 +1065,9 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr,
 	l4proto = nf_ct_l4proto_find(tuple->dst.protonum);
 
 	if (likely(l4proto->nlattr_to_tuple)) {
-		ret = nla_validate_nested(attr, CTA_PROTO_MAX,
-					  l4proto->nla_policy, NULL);
+		ret = nla_validate_nested_deprecated(attr, CTA_PROTO_MAX,
+						     l4proto->nla_policy,
+						     NULL);
 		if (ret == 0)
 			ret = l4proto->nlattr_to_tuple(tb, tuple);
 	}
@@ -1129,8 +1130,8 @@ ctnetlink_parse_tuple(const struct nlattr * const cda[],
 
 	memset(tuple, 0, sizeof(*tuple));
 
-	err = nla_parse_nested(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy,
-			       NULL);
+	err = nla_parse_nested_deprecated(tb, CTA_TUPLE_MAX, cda[type],
+					  tuple_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1180,7 +1181,8 @@ static int ctnetlink_parse_help(const struct nlattr *attr, char **helper_name,
 	int err;
 	struct nlattr *tb[CTA_HELP_MAX+1];
 
-	err = nla_parse_nested(tb, CTA_HELP_MAX, attr, help_nla_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, CTA_HELP_MAX, attr,
+					  help_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1721,8 +1723,8 @@ static int ctnetlink_change_protoinfo(struct nf_conn *ct,
 	struct nlattr *tb[CTA_PROTOINFO_MAX+1];
 	int err = 0;
 
-	err = nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy,
-			       NULL);
+	err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_MAX, attr,
+					  protoinfo_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1745,7 +1747,8 @@ static int change_seq_adj(struct nf_ct_seqadj *seq,
 	int err;
 	struct nlattr *cda[CTA_SEQADJ_MAX+1];
 
-	err = nla_parse_nested(cda, CTA_SEQADJ_MAX, attr, seqadj_policy, NULL);
+	err = nla_parse_nested_deprecated(cda, CTA_SEQADJ_MAX, attr,
+					  seqadj_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -1822,8 +1825,9 @@ static int ctnetlink_change_synproxy(struct nf_conn *ct,
 	if (!synproxy)
 		return 0;
 
-	err = nla_parse_nested(tb, CTA_SYNPROXY_MAX, cda[CTA_SYNPROXY],
-			       synproxy_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, CTA_SYNPROXY_MAX,
+					  cda[CTA_SYNPROXY], synproxy_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
@@ -2553,7 +2557,8 @@ ctnetlink_glue_parse(const struct nlattr *attr, struct nf_conn *ct)
 	struct nlattr *cda[CTA_MAX+1];
 	int ret;
 
-	ret = nla_parse_nested(cda, CTA_MAX, attr, ct_nla_policy, NULL);
+	ret = nla_parse_nested_deprecated(cda, CTA_MAX, attr, ct_nla_policy,
+					  NULL);
 	if (ret < 0)
 		return ret;
 
@@ -2586,8 +2591,8 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct,
 	struct nf_conntrack_expect *exp;
 	int err;
 
-	err = nla_parse_nested(cda, CTA_EXPECT_MAX, attr, exp_nla_policy,
-			       NULL);
+	err = nla_parse_nested_deprecated(cda, CTA_EXPECT_MAX, attr,
+					  exp_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -3209,8 +3214,8 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr,
 	struct nf_conntrack_tuple nat_tuple = {};
 	int err;
 
-	err = nla_parse_nested(tb, CTA_EXPECT_NAT_MAX, attr,
-			       exp_nat_nla_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, CTA_EXPECT_NAT_MAX, attr,
+					  exp_nat_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index a4deddebec0a..7491aa4c3566 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -639,8 +639,8 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
 	if (!attr)
 		return 0;
 
-	err = nla_parse_nested(tb, CTA_PROTOINFO_DCCP_MAX, attr,
-			       dccp_nla_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_DCCP_MAX, attr,
+					  dccp_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 8cf36b684400..5b8dde266412 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -563,8 +563,8 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct)
 	if (!attr)
 		return 0;
 
-	err = nla_parse_nested(tb, CTA_PROTOINFO_SCTP_MAX, attr,
-			       sctp_nla_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_SCTP_MAX, attr,
+					  sctp_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index ec6c3618333d..7ba01d8ee165 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1248,8 +1248,8 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
 	if (!pattr)
 		return 0;
 
-	err = nla_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, pattr,
-			       tcp_nla_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_TCP_MAX, pattr,
+					  tcp_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 715e3d4d761b..cd94481e6c07 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -890,8 +890,8 @@ static int nfnetlink_parse_nat_proto(struct nlattr *attr,
 	struct nlattr *tb[CTA_PROTONAT_MAX+1];
 	int err;
 
-	err = nla_parse_nested(tb, CTA_PROTONAT_MAX, attr,
-			       protonat_nla_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, CTA_PROTONAT_MAX, attr,
+					  protonat_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -949,7 +949,8 @@ nfnetlink_parse_nat(const struct nlattr *nat,
 
 	memset(range, 0, sizeof(*range));
 
-	err = nla_parse_nested(tb, CTA_NAT_MAX, nat, nat_nla_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, CTA_NAT_MAX, nat,
+					  nat_nla_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 2b79c250ecb4..d98416e83d4e 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1420,8 +1420,8 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr)
 	struct nft_stats *stats;
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy,
-			       NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_COUNTER_MAX, attr,
+					  nft_counter_policy, NULL);
 	if (err < 0)
 		return ERR_PTR(err);
 
@@ -1525,8 +1525,9 @@ static int nft_chain_parse_hook(struct net *net,
 	lockdep_assert_held(&net->nft.commit_mutex);
 	lockdep_nfnl_nft_mutex_not_held();
 
-	err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK],
-			       nft_hook_policy, NULL);
+	err = nla_parse_nested_deprecated(ha, NFTA_HOOK_MAX,
+					  nla[NFTA_CHAIN_HOOK],
+					  nft_hook_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -2105,7 +2106,8 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
 	struct nlattr *tb[NFTA_EXPR_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_EXPR_MAX, nla, nft_expr_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_EXPR_MAX, nla,
+					  nft_expr_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -2114,8 +2116,9 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
 		return PTR_ERR(type);
 
 	if (tb[NFTA_EXPR_DATA]) {
-		err = nla_parse_nested(info->tb, type->maxattr,
-				       tb[NFTA_EXPR_DATA], type->policy, NULL);
+		err = nla_parse_nested_deprecated(info->tb, type->maxattr,
+						  tb[NFTA_EXPR_DATA],
+						  type->policy, NULL);
 		if (err < 0)
 			goto err1;
 	} else
@@ -3443,8 +3446,8 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc,
 	struct nlattr *da[NFTA_SET_DESC_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(da, NFTA_SET_DESC_MAX, nla,
-			       nft_set_desc_policy, NULL);
+	err = nla_parse_nested_deprecated(da, NFTA_SET_DESC_MAX, nla,
+					  nft_set_desc_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -4170,8 +4173,8 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	void *priv;
 	int err;
 
-	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
-			       nft_set_elem_policy, NULL);
+	err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr,
+					  nft_set_elem_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -4402,8 +4405,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	u8 ulen;
 	int err;
 
-	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
-			       nft_set_elem_policy, NULL);
+	err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr,
+					  nft_set_elem_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -4696,8 +4699,8 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 	void *priv;
 	int err;
 
-	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
-			       nft_set_elem_policy, NULL);
+	err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr,
+					  nft_set_elem_policy, NULL);
 	if (err < 0)
 		goto err1;
 
@@ -4971,8 +4974,8 @@ static struct nft_object *nft_obj_init(const struct nft_ctx *ctx,
 		goto err1;
 
 	if (attr) {
-		err = nla_parse_nested(tb, type->maxattr, attr, type->policy,
-				       NULL);
+		err = nla_parse_nested_deprecated(tb, type->maxattr, attr,
+						  type->policy, NULL);
 		if (err < 0)
 			goto err2;
 	} else {
@@ -5548,8 +5551,8 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx,
 	int hooknum, priority;
 	int err, n = 0, i;
 
-	err = nla_parse_nested(tb, NFTA_FLOWTABLE_HOOK_MAX, attr,
-			       nft_flowtable_hook_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_FLOWTABLE_HOOK_MAX, attr,
+					  nft_flowtable_hook_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -7206,8 +7209,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 	struct nft_chain *chain;
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_VERDICT_MAX, nla, nft_verdict_policy,
-			       NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_VERDICT_MAX, nla,
+					  nft_verdict_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -7337,7 +7340,8 @@ int nft_data_init(const struct nft_ctx *ctx,
 	struct nlattr *tb[NFTA_DATA_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_DATA_MAX, nla, nft_data_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_DATA_MAX, nla,
+					  nft_data_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 916913454624..92077d459109 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -206,8 +206,9 @@ replay:
 			return -ENOMEM;
 		}
 
-		err = nla_parse(cda, ss->cb[cb_id].attr_count, attr, attrlen,
-				ss->cb[cb_id].policy, extack);
+		err = nla_parse_deprecated(cda, ss->cb[cb_id].attr_count,
+					   attr, attrlen,
+					   ss->cb[cb_id].policy, extack);
 		if (err < 0) {
 			rcu_read_unlock();
 			return err;
@@ -421,8 +422,10 @@ replay:
 				goto ack;
 			}
 
-			err = nla_parse(cda, ss->cb[cb_id].attr_count, attr,
-					attrlen, ss->cb[cb_id].policy, NULL);
+			err = nla_parse_deprecated(cda,
+						   ss->cb[cb_id].attr_count,
+						   attr, attrlen,
+						   ss->cb[cb_id].policy, NULL);
 			if (err < 0)
 				goto ack;
 
@@ -520,8 +523,8 @@ static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg))
 		return;
 
-	err = nla_parse(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy,
-			NULL);
+	err = nla_parse_deprecated(cda, NFNL_BATCH_MAX, attr, attrlen,
+				   nfnl_batch_policy, NULL);
 	if (err < 0) {
 		netlink_ack(skb, nlh, err, NULL);
 		return;
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 8fa8bf7c48e6..02c877432d71 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -248,8 +248,8 @@ static int nfnl_acct_start(struct netlink_callback *cb)
 	if (!attr)
 		return 0;
 
-	err = nla_parse_nested(tb, NFACCT_FILTER_MAX, attr, filter_policy,
-			       NULL);
+	err = nla_parse_nested_deprecated(tb, NFACCT_FILTER_MAX, attr,
+					  filter_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 74c9794d28d6..17eb473a626b 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -78,8 +78,8 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 	int err;
 	struct nlattr *tb[NFCTH_TUPLE_MAX+1];
 
-	err = nla_parse_nested(tb, NFCTH_TUPLE_MAX, attr,
-			       nfnl_cthelper_tuple_pol, NULL);
+	err = nla_parse_nested_deprecated(tb, NFCTH_TUPLE_MAX, attr,
+					  nfnl_cthelper_tuple_pol, NULL);
 	if (err < 0)
 		return err;
 
@@ -139,8 +139,8 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy,
 	int err;
 	struct nlattr *tb[NFCTH_POLICY_MAX+1];
 
-	err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr,
-			       nfnl_cthelper_expect_pol, NULL);
+	err = nla_parse_nested_deprecated(tb, NFCTH_POLICY_MAX, attr,
+					  nfnl_cthelper_expect_pol, NULL);
 	if (err < 0)
 		return err;
 
@@ -176,8 +176,9 @@ nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
 	struct nlattr *tb[NFCTH_POLICY_SET_MAX+1];
 	unsigned int class_max;
 
-	ret = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
-			       nfnl_cthelper_expect_policy_set, NULL);
+	ret = nla_parse_nested_deprecated(tb, NFCTH_POLICY_SET_MAX, attr,
+					  nfnl_cthelper_expect_policy_set,
+					  NULL);
 	if (ret < 0)
 		return ret;
 
@@ -289,8 +290,8 @@ nfnl_cthelper_update_policy_one(const struct nf_conntrack_expect_policy *policy,
 	struct nlattr *tb[NFCTH_POLICY_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr,
-			       nfnl_cthelper_expect_pol, NULL);
+	err = nla_parse_nested_deprecated(tb, NFCTH_POLICY_MAX, attr,
+					  nfnl_cthelper_expect_pol, NULL);
 	if (err < 0)
 		return err;
 
@@ -361,8 +362,9 @@ static int nfnl_cthelper_update_policy(struct nf_conntrack_helper *helper,
 	unsigned int class_max;
 	int err;
 
-	err = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
-			       nfnl_cthelper_expect_policy_set, NULL);
+	err = nla_parse_nested_deprecated(tb, NFCTH_POLICY_SET_MAX, attr,
+					  nfnl_cthelper_expect_policy_set,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 572cb42e1ee1..427b411c5739 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -59,8 +59,11 @@ ctnl_timeout_parse_policy(void *timeout,
 	if (!tb)
 		return -ENOMEM;
 
-	ret = nla_parse_nested(tb, l4proto->ctnl_timeout.nlattr_max, attr,
-			       l4proto->ctnl_timeout.nla_policy, NULL);
+	ret = nla_parse_nested_deprecated(tb,
+					  l4proto->ctnl_timeout.nlattr_max,
+					  attr,
+					  l4proto->ctnl_timeout.nla_policy,
+					  NULL);
 	if (ret < 0)
 		goto err;
 
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index be7d53943e2d..27dac47b29c2 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1139,8 +1139,9 @@ static int nfqa_parse_bridge(struct nf_queue_entry *entry,
 		struct nlattr *tb[NFQA_VLAN_MAX + 1];
 		int err;
 
-		err = nla_parse_nested(tb, NFQA_VLAN_MAX, nfqa[NFQA_VLAN],
-				       nfqa_vlan_policy, NULL);
+		err = nla_parse_nested_deprecated(tb, NFQA_VLAN_MAX,
+						  nfqa[NFQA_VLAN],
+						  nfqa_vlan_policy, NULL);
 		if (err < 0)
 			return err;
 
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 469f9da5073b..276f1f2d6de1 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -198,8 +198,8 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 	u32 flags;
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_RULE_COMPAT_MAX, attr,
-			       nft_rule_compat_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_RULE_COMPAT_MAX, attr,
+					  nft_rule_compat_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 1738ef6dcb56..b422b74bfe08 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -797,9 +797,11 @@ nft_ct_timeout_parse_policy(void *timeouts,
 	if (!tb)
 		return -ENOMEM;
 
-	ret = nla_parse_nested(tb, l4proto->ctnl_timeout.nlattr_max,
-			       attr, l4proto->ctnl_timeout.nla_policy,
-			       NULL);
+	ret = nla_parse_nested_deprecated(tb,
+					  l4proto->ctnl_timeout.nlattr_max,
+					  attr,
+					  l4proto->ctnl_timeout.nla_policy,
+					  NULL);
 	if (ret < 0)
 		goto err;
 
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 66b52d015763..3d4c2ae605a8 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -166,8 +166,8 @@ static int nft_tunnel_obj_ip_init(const struct nft_ctx *ctx,
 	struct nlattr *tb[NFTA_TUNNEL_KEY_IP_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_IP_MAX, attr,
-			       nft_tunnel_ip_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_TUNNEL_KEY_IP_MAX, attr,
+					  nft_tunnel_ip_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -195,8 +195,8 @@ static int nft_tunnel_obj_ip6_init(const struct nft_ctx *ctx,
 	struct nlattr *tb[NFTA_TUNNEL_KEY_IP6_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_IP6_MAX, attr,
-			       nft_tunnel_ip6_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_TUNNEL_KEY_IP6_MAX, attr,
+					  nft_tunnel_ip6_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -231,8 +231,8 @@ static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr,
 	struct nlattr *tb[NFTA_TUNNEL_KEY_VXLAN_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_VXLAN_MAX, attr,
-			       nft_tunnel_opts_vxlan_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_TUNNEL_KEY_VXLAN_MAX, attr,
+					  nft_tunnel_opts_vxlan_policy, NULL);
 	if (err < 0)
 		return err;
 
@@ -260,8 +260,9 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr,
 	uint8_t hwid, dir;
 	int err, version;
 
-	err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_ERSPAN_MAX, attr,
-			       nft_tunnel_opts_erspan_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_TUNNEL_KEY_ERSPAN_MAX,
+					  attr, nft_tunnel_opts_erspan_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
@@ -309,8 +310,8 @@ static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx,
 	struct nlattr *tb[NFTA_TUNNEL_KEY_OPTS_MAX + 1];
 	int err;
 
-	err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_OPTS_MAX, attr,
-			       nft_tunnel_opts_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, NFTA_TUNNEL_KEY_OPTS_MAX, attr,
+					  nft_tunnel_opts_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index c9775658fb98..8d401df65928 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -99,9 +99,10 @@ static int netlbl_cipsov4_add_common(struct genl_info *info,
 
 	doi_def->doi = nla_get_u32(info->attrs[NLBL_CIPSOV4_A_DOI]);
 
-	if (nla_validate_nested(info->attrs[NLBL_CIPSOV4_A_TAGLST],
-				NLBL_CIPSOV4_A_MAX,
-				netlbl_cipsov4_genl_policy, NULL) != 0)
+	if (nla_validate_nested_deprecated(info->attrs[NLBL_CIPSOV4_A_TAGLST],
+					   NLBL_CIPSOV4_A_MAX,
+					   netlbl_cipsov4_genl_policy,
+					   NULL) != 0)
 		return -EINVAL;
 
 	nla_for_each_nested(nla, info->attrs[NLBL_CIPSOV4_A_TAGLST], nla_rem)
@@ -146,9 +147,10 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
 	    !info->attrs[NLBL_CIPSOV4_A_MLSLVLLST])
 		return -EINVAL;
 
-	if (nla_validate_nested(info->attrs[NLBL_CIPSOV4_A_MLSLVLLST],
-				NLBL_CIPSOV4_A_MAX,
-				netlbl_cipsov4_genl_policy, NULL) != 0)
+	if (nla_validate_nested_deprecated(info->attrs[NLBL_CIPSOV4_A_MLSLVLLST],
+					   NLBL_CIPSOV4_A_MAX,
+					   netlbl_cipsov4_genl_policy,
+					   NULL) != 0)
 		return -EINVAL;
 
 	doi_def = kmalloc(sizeof(*doi_def), GFP_KERNEL);
@@ -170,9 +172,10 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
 			    info->attrs[NLBL_CIPSOV4_A_MLSLVLLST],
 			    nla_a_rem)
 		if (nla_type(nla_a) == NLBL_CIPSOV4_A_MLSLVL) {
-			if (nla_validate_nested(nla_a, NLBL_CIPSOV4_A_MAX,
-						netlbl_cipsov4_genl_policy,
-						NULL) != 0)
+			if (nla_validate_nested_deprecated(nla_a,
+							   NLBL_CIPSOV4_A_MAX,
+							   netlbl_cipsov4_genl_policy,
+							   NULL) != 0)
 				goto add_std_failure;
 			nla_for_each_nested(nla_b, nla_a, nla_b_rem)
 				switch (nla_type(nla_b)) {
@@ -234,19 +237,20 @@ static int netlbl_cipsov4_add_std(struct genl_info *info,
 		}
 
 	if (info->attrs[NLBL_CIPSOV4_A_MLSCATLST]) {
-		if (nla_validate_nested(info->attrs[NLBL_CIPSOV4_A_MLSCATLST],
-					NLBL_CIPSOV4_A_MAX,
-					netlbl_cipsov4_genl_policy, NULL) != 0)
+		if (nla_validate_nested_deprecated(info->attrs[NLBL_CIPSOV4_A_MLSCATLST],
+						   NLBL_CIPSOV4_A_MAX,
+						   netlbl_cipsov4_genl_policy,
+						   NULL) != 0)
 			goto add_std_failure;
 
 		nla_for_each_nested(nla_a,
 				    info->attrs[NLBL_CIPSOV4_A_MLSCATLST],
 				    nla_a_rem)
 			if (nla_type(nla_a) == NLBL_CIPSOV4_A_MLSCAT) {
-				if (nla_validate_nested(nla_a,
-							NLBL_CIPSOV4_A_MAX,
-							netlbl_cipsov4_genl_policy,
-							NULL) != 0)
+				if (nla_validate_nested_deprecated(nla_a,
+								   NLBL_CIPSOV4_A_MAX,
+								   netlbl_cipsov4_genl_policy,
+								   NULL) != 0)
 					goto add_std_failure;
 				nla_for_each_nested(nla_b, nla_a, nla_b_rem)
 					switch (nla_type(nla_b)) {
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 83e876591f6c..994d9aff2093 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -577,8 +577,9 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 		attrbuf = family->attrbuf;
 
 	if (attrbuf) {
-		err = nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr,
-				  family->policy, extack);
+		err = nlmsg_parse_deprecated(nlh, hdrlen, attrbuf,
+					     family->maxattr, family->policy,
+					     extack);
 		if (err < 0)
 			goto out;
 	}
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index f91ce7c82746..c6ba308cede7 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -119,9 +119,10 @@ static struct nfc_dev *__get_device_from_cb(struct netlink_callback *cb)
 	int rc;
 	u32 idx;
 
-	rc = nlmsg_parse(cb->nlh, GENL_HDRLEN + nfc_genl_family.hdrsize,
-			 attrbuf, nfc_genl_family.maxattr, nfc_genl_policy,
-			 NULL);
+	rc = nlmsg_parse_deprecated(cb->nlh,
+				    GENL_HDRLEN + nfc_genl_family.hdrsize,
+				    attrbuf, nfc_genl_family.maxattr,
+				    nfc_genl_policy, NULL);
 	if (rc < 0)
 		return ERR_PTR(rc);
 
@@ -1177,8 +1178,9 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
 	tlvs_len = 0;
 
 	nla_for_each_nested(attr, info->attrs[NFC_ATTR_LLC_SDP], rem) {
-		rc = nla_parse_nested(sdp_attrs, NFC_SDP_ATTR_MAX, attr,
-				      nfc_sdp_genl_policy, info->extack);
+		rc = nla_parse_nested_deprecated(sdp_attrs, NFC_SDP_ATTR_MAX,
+						 attr, nfc_sdp_genl_policy,
+						 info->extack);
 
 		if (rc != 0) {
 			rc = -EINVAL;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 356677c3a0c2..3b99fc3de9ac 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1375,8 +1375,8 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	u32 ufid_flags;
 	int err;
 
-	err = genlmsg_parse(cb->nlh, &dp_flow_genl_family, a,
-			    OVS_FLOW_ATTR_MAX, flow_policy, NULL);
+	err = genlmsg_parse_deprecated(cb->nlh, &dp_flow_genl_family, a,
+				       OVS_FLOW_ATTR_MAX, flow_policy, NULL);
 	if (err)
 		return err;
 	ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 2427b672107a..54eb80dd2dc6 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2854,8 +2854,8 @@ static int validate_userspace(const struct nlattr *attr)
 	struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
 	int error;
 
-	error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX, attr,
-				 userspace_policy, NULL);
+	error = nla_parse_nested_deprecated(a, OVS_USERSPACE_ATTR_MAX, attr,
+					    userspace_policy, NULL);
 	if (error)
 		return error;
 
@@ -2885,8 +2885,9 @@ static int validate_and_copy_check_pkt_len(struct net *net,
 	int nested_acts_start;
 	int start, err;
 
-	err = nla_parse_strict(a, OVS_CHECK_PKT_LEN_ATTR_MAX, nla_data(attr),
-			       nla_len(attr), cpl_policy, NULL);
+	err = nla_parse_deprecated_strict(a, OVS_CHECK_PKT_LEN_ATTR_MAX,
+					  nla_data(attr), nla_len(attr),
+					  cpl_policy, NULL);
 	if (err)
 		return err;
 
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index fdc8be7fd8f3..9c89e8539a5a 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -227,9 +227,9 @@ static struct dp_meter *dp_meter_create(struct nlattr **a)
 		struct nlattr *attr[OVS_BAND_ATTR_MAX + 1];
 		u32 band_max_delta_t;
 
-		err = nla_parse((struct nlattr **)&attr, OVS_BAND_ATTR_MAX,
-				nla_data(nla), nla_len(nla), band_policy,
-				NULL);
+		err = nla_parse_deprecated((struct nlattr **)&attr,
+					   OVS_BAND_ATTR_MAX, nla_data(nla),
+					   nla_len(nla), band_policy, NULL);
 		if (err)
 			goto exit_free_meter;
 
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 54965ff8cc66..f3c54871f9e1 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -70,8 +70,8 @@ static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr,
 	if (nla_len(attr) < sizeof(struct nlattr))
 		return -EINVAL;
 
-	err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy,
-			       NULL);
+	err = nla_parse_nested_deprecated(exts, OVS_VXLAN_EXT_MAX, attr,
+					  exts_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index 871eaf2cb85e..be92d936b5d5 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -79,8 +79,8 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	ASSERT_RTNL();
 
-	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_phonet_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+				     ifa_phonet_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -246,8 +246,8 @@ static int route_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	ASSERT_RTNL();
 
-	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_phonet_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX,
+				     rtm_phonet_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 7c5e8292cc0a..dd0e97f4f6c0 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -1091,7 +1091,8 @@ static int qrtr_addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	ASSERT_RTNL();
 
-	rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, qrtr_policy, extack);
+	rc = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+				    qrtr_policy, extack);
 	if (rc < 0)
 		return rc;
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 641ad7575f24..683fcc00da49 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -849,7 +849,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	int err;
 
 	if (name == NULL) {
-		err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack);
+		err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL,
+						  extack);
 		if (err < 0)
 			goto err_out;
 		err = -EINVAL;
@@ -964,7 +965,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 	int err;
 	int i;
 
-	err = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX_PRIO, nla, NULL,
+					  extack);
 	if (err < 0)
 		return err;
 
@@ -1099,7 +1101,7 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla,
 	int index;
 	int err;
 
-	err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, extack);
 	if (err < 0)
 		goto err_out;
 
@@ -1153,7 +1155,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
 
 	b = skb_tail_pointer(skb);
 
-	err = nla_parse_nested(tb, TCA_ACT_MAX, nla, NULL, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_ACT_MAX, nla, NULL, extack);
 	if (err < 0)
 		goto err_out;
 
@@ -1282,7 +1284,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	size_t attr_size = 0;
 	struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
 
-	ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack);
+	ret = nla_parse_nested_deprecated(tb, TCA_ACT_MAX_PRIO, nla, NULL,
+					  extack);
 	if (ret < 0)
 		return ret;
 
@@ -1384,8 +1387,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ROOT_MAX, NULL,
-			  extack);
+	ret = nlmsg_parse_deprecated(n, sizeof(struct tcamsg), tca,
+				     TCA_ROOT_MAX, NULL, extack);
 	if (ret < 0)
 		return ret;
 
@@ -1436,13 +1439,12 @@ static struct nlattr *find_dump_kind(struct nlattr **nla)
 	if (tb1 == NULL)
 		return NULL;
 
-	if (nla_parse(tb, TCA_ACT_MAX_PRIO, nla_data(tb1),
-		      NLMSG_ALIGN(nla_len(tb1)), NULL, NULL) < 0)
+	if (nla_parse_deprecated(tb, TCA_ACT_MAX_PRIO, nla_data(tb1), NLMSG_ALIGN(nla_len(tb1)), NULL, NULL) < 0)
 		return NULL;
 
 	if (tb[1] == NULL)
 		return NULL;
-	if (nla_parse_nested(tb2, TCA_ACT_MAX, tb[1], NULL, NULL) < 0)
+	if (nla_parse_nested_deprecated(tb2, TCA_ACT_MAX, tb[1], NULL, NULL) < 0)
 		return NULL;
 	kind = tb2[TCA_ACT_KIND];
 
@@ -1466,8 +1468,8 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
 	u32 msecs_since = 0;
 	u32 act_count = 0;
 
-	ret = nlmsg_parse(cb->nlh, sizeof(struct tcamsg), tb, TCA_ROOT_MAX,
-			  tcaa_policy, cb->extack);
+	ret = nlmsg_parse_deprecated(cb->nlh, sizeof(struct tcamsg), tb,
+				     TCA_ROOT_MAX, tcaa_policy, cb->extack);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 3841156aa09f..a0c77faca04b 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -293,7 +293,8 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	if (!nla)
 		return -EINVAL;
 
-	ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy, NULL);
+	ret = nla_parse_nested_deprecated(tb, TCA_ACT_BPF_MAX, nla,
+					  act_bpf_policy, NULL);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 32ae0cd6e31c..8838575cd536 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -111,8 +111,8 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	if (!nla)
 		return -EINVAL;
 
-	ret = nla_parse_nested(tb, TCA_CONNMARK_MAX, nla, connmark_policy,
-			       NULL);
+	ret = nla_parse_nested_deprecated(tb, TCA_CONNMARK_MAX, nla,
+					  connmark_policy, NULL);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 0c77e7bdf6d5..14bb525e355e 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -61,7 +61,8 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_CSUM_MAX, nla, csum_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_CSUM_MAX, nla, csum_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index e540e31069d7..75492b07f324 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -74,7 +74,8 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_GACT_MAX, nla, gact_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_GACT_MAX, nla, gact_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 7a87ce2e5a76..12489f60a979 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -486,7 +486,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	int ret = 0;
 	int err;
 
-	err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
@@ -567,8 +568,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		INIT_LIST_HEAD(&ife->metalist);
 
 	if (tb[TCA_IFE_METALST]) {
-		err = nla_parse_nested(tb2, IFE_META_MAX, tb[TCA_IFE_METALST],
-				       NULL, NULL);
+		err = nla_parse_nested_deprecated(tb2, IFE_META_MAX,
+						  tb[TCA_IFE_METALST], NULL,
+						  NULL);
 		if (err)
 			goto metadata_parse_err;
 		err = populate_metalist(ife, tb2, exists, rtnl_held);
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 04a0b5c61194..ae6e28ab1cd7 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -113,7 +113,8 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_IPT_MAX, nla, ipt_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_IPT_MAX, nla, ipt_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 17cc6bd4c57c..c329390342f4 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -111,7 +111,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed");
 		return -EINVAL;
 	}
-	ret = nla_parse_nested(tb, TCA_MIRRED_MAX, nla, mirred_policy, extack);
+	ret = nla_parse_nested_deprecated(tb, TCA_MIRRED_MAX, nla,
+					  mirred_policy, extack);
 	if (ret < 0)
 		return ret;
 	if (!tb[TCA_MIRRED_PARMS]) {
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index e91bb8eb81ec..51bd1ba02380 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -52,7 +52,8 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_NAT_MAX, nla, nat_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_NAT_MAX, nla, nat_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index ce4b54fa7834..d790c02b9c6c 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -70,8 +70,9 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla,
 			goto err_out;
 		}
 
-		err = nla_parse_nested(tb, TCA_PEDIT_KEY_EX_MAX, ka,
-				       pedit_key_ex_policy, NULL);
+		err = nla_parse_nested_deprecated(tb, TCA_PEDIT_KEY_EX_MAX,
+						  ka, pedit_key_ex_policy,
+						  NULL);
 		if (err)
 			goto err_out;
 
@@ -158,7 +159,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb, TCA_PEDIT_MAX, nla, pedit_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_PEDIT_MAX, nla,
+					  pedit_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 2b8581f6ab51..b48e40c69ad0 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -100,7 +100,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_POLICE_MAX, nla, police_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_POLICE_MAX, nla,
+					  police_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 0f82d50ea232..b2faa43c1ac7 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -53,7 +53,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 
 	if (!nla)
 		return -EINVAL;
-	ret = nla_parse_nested(tb, TCA_SAMPLE_MAX, nla, sample_policy, NULL);
+	ret = nla_parse_nested_deprecated(tb, TCA_SAMPLE_MAX, nla,
+					  sample_policy, NULL);
 	if (ret < 0)
 		return ret;
 	if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] ||
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 23c8ca5615e5..ead480e6014c 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -104,7 +104,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_DEF_MAX, nla, simple_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_DEF_MAX, nla, simple_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 7e1d261a31d2..7ec159b95364 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -114,7 +114,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 	if (nla == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_SKBEDIT_MAX, nla, skbedit_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_SKBEDIT_MAX, nla,
+					  skbedit_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 1d4c324d0a42..186ef98c828f 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -102,7 +102,8 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	if (!nla)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_SKBMOD_MAX, nla, skbmod_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_SKBMOD_MAX, nla,
+					  skbmod_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 45c0c253c7e8..6a9070511ee8 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -76,8 +76,9 @@ tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len,
 	int err, data_len, opt_len;
 	u8 *data;
 
-	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX,
-			       nla, geneve_opt_policy, extack);
+	err = nla_parse_nested_deprecated(tb,
+					  TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX,
+					  nla, geneve_opt_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -125,8 +126,8 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
 	int err, rem, opt_len, len = nla_len(nla), opts_len = 0;
 	const struct nlattr *attr, *head = nla_data(nla);
 
-	err = nla_validate(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX,
-			   enc_opts_policy, extack);
+	err = nla_validate_deprecated(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX,
+				      enc_opts_policy, extack);
 	if (err)
 		return err;
 
@@ -235,8 +236,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy,
-			       extack);
+	err = nla_parse_nested_deprecated(tb, TCA_TUNNEL_KEY_MAX, nla,
+					  tunnel_key_policy, extack);
 	if (err < 0) {
 		NL_SET_ERR_MSG(extack, "Failed to parse nested tunnel key attributes");
 		return err;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 0f40d0a74423..39bd9fa3e455 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -124,7 +124,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	if (!nla)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_VLAN_MAX, nla, vlan_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_VLAN_MAX, nla, vlan_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 78de717afddf..263c2ec082c9 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2006,7 +2006,8 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 replay:
 	tp_created = 0;
 
-	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
+	err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
+				     rtm_tca_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2217,7 +2218,8 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
+	err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
+				     rtm_tca_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2366,7 +2368,8 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	int err;
 	bool rtnl_held = false;
 
-	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
+	err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
+				     rtm_tca_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2558,8 +2561,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
 	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
 		return skb->len;
 
-	err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL,
-			  cb->extack);
+	err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX,
+				     NULL, cb->extack);
 	if (err)
 		return err;
 
@@ -2806,7 +2809,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
 		return -EPERM;
 
 replay:
-	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack);
+	err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX,
+				     rtm_tca_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -2937,8 +2941,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
 		return skb->len;
 
-	err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy,
-			  cb->extack);
+	err = nlmsg_parse_deprecated(cb->nlh, sizeof(*tcm), tca, TCA_MAX,
+				     rtm_tca_policy, cb->extack);
 	if (err)
 		return err;
 
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index dd5fdb62c6df..923863f3b0d8 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -185,8 +185,8 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 	if (tca[TCA_OPTIONS] == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_BASIC_MAX, tca[TCA_OPTIONS],
-			       basic_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_BASIC_MAX, tca[TCA_OPTIONS],
+					  basic_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 6fd569c5a036..9bcf499cce0c 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -468,8 +468,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 	if (tca[TCA_OPTIONS] == NULL)
 		return -EINVAL;
 
-	ret = nla_parse_nested(tb, TCA_BPF_MAX, tca[TCA_OPTIONS], bpf_policy,
-			       NULL);
+	ret = nla_parse_nested_deprecated(tb, TCA_BPF_MAX, tca[TCA_OPTIONS],
+					  bpf_policy, NULL);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index b680dd684282..037d128c2851 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -104,8 +104,9 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 		goto errout;
 	new->handle = handle;
 	new->tp = tp;
-	err = nla_parse_nested(tb, TCA_CGROUP_MAX, tca[TCA_OPTIONS],
-			       cgroup_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_CGROUP_MAX,
+					  tca[TCA_OPTIONS], cgroup_policy,
+					  NULL);
 	if (err < 0)
 		goto errout;
 
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index cb29fe7d5ed3..7bb79ec5b176 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -408,7 +408,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_FLOW_MAX, opt, flow_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_FLOW_MAX, opt, flow_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 8d4f7a672f14..f6685fc53119 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -884,8 +884,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key,
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
-			       nla, geneve_opt_policy, extack);
+	err = nla_parse_nested_deprecated(tb,
+					  TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+					  nla, geneve_opt_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -947,18 +948,18 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 	const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL;
 	int err, option_len, key_depth, msk_depth = 0;
 
-	err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS],
-				  TCA_FLOWER_KEY_ENC_OPTS_MAX,
-				  enc_opts_policy, extack);
+	err = nla_validate_nested_deprecated(tb[TCA_FLOWER_KEY_ENC_OPTS],
+					     TCA_FLOWER_KEY_ENC_OPTS_MAX,
+					     enc_opts_policy, extack);
 	if (err)
 		return err;
 
 	nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]);
 
 	if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) {
-		err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK],
-					  TCA_FLOWER_KEY_ENC_OPTS_MAX,
-					  enc_opts_policy, extack);
+		err = nla_validate_nested_deprecated(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK],
+						     TCA_FLOWER_KEY_ENC_OPTS_MAX,
+						     enc_opts_policy, extack);
 		if (err)
 			return err;
 
@@ -1513,8 +1514,8 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 		goto errout_mask_alloc;
 	}
 
-	err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS],
-			       fl_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_FLOWER_MAX,
+					  tca[TCA_OPTIONS], fl_policy, NULL);
 	if (err < 0)
 		goto errout_tb;
 
@@ -1852,8 +1853,8 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
 	tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
 	if (!tb)
 		return ERR_PTR(-ENOBUFS);
-	err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS],
-			       fl_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_FLOWER_MAX,
+					  tca[TCA_OPTIONS], fl_policy, NULL);
 	if (err)
 		goto errout_tb;
 
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 3fcc1d51b9d7..1d0b39c3932f 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -263,7 +263,8 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	if (!opt)
 		return handle ? -EINVAL : 0; /* Succeed if it is old method. */
 
-	err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_FW_MAX, opt, fw_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index d54fa8e11b9e..46982b4ea70a 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -181,8 +181,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 	if (head)
 		return -EEXIST;
 
-	err = nla_parse_nested(tb, TCA_MATCHALL_MAX, tca[TCA_OPTIONS],
-			       mall_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_MATCHALL_MAX,
+					  tca[TCA_OPTIONS], mall_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index b3b9b151a61d..eeff5bbfb912 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -484,7 +484,8 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 	if (opt == NULL)
 		return handle ? -EINVAL : 0;
 
-	err = nla_parse_nested(tb, TCA_ROUTE4_MAX, opt, route4_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_ROUTE4_MAX, opt,
+					  route4_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index fa059cf934a6..a4688bb92f43 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -497,7 +497,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
 	if (opt == NULL)
 		return handle ? -EINVAL : 0;
 
-	err = nla_parse_nested(tb, TCA_RSVP_MAX, opt, rsvp_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_RSVP_MAX, opt, rsvp_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 1a2e7d5a8776..9f4f4203c388 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -510,7 +510,8 @@ tcindex_change(struct net *net, struct sk_buff *in_skb,
 	if (!opt)
 		return 0;
 
-	err = nla_parse_nested(tb, TCA_TCINDEX_MAX, opt, tcindex_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_TCINDEX_MAX, opt,
+					  tcindex_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 499477058b2d..04e9ef088535 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -884,7 +884,8 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		}
 	}
 
-	err = nla_parse_nested(tb, TCA_U32_MAX, opt, u32_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_U32_MAX, opt, u32_policy,
+					  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c
index a5f34e930eff..60c26b8294b5 100644
--- a/net/sched/em_ipt.c
+++ b/net/sched/em_ipt.c
@@ -120,8 +120,8 @@ static int em_ipt_change(struct net *net, void *data, int data_len,
 	struct xt_match *match;
 	int mdata_len, ret;
 
-	ret = nla_parse(tb, TCA_EM_IPT_MAX, data, data_len, em_ipt_policy,
-			NULL);
+	ret = nla_parse_deprecated(tb, TCA_EM_IPT_MAX, data, data_len,
+				   em_ipt_policy, NULL);
 	if (ret < 0)
 		return ret;
 
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index d6e97115500b..28dfa8f2a4ea 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -912,7 +912,8 @@ static int em_meta_change(struct net *net, void *data, int len,
 	struct tcf_meta_hdr *hdr;
 	struct meta_match *meta = NULL;
 
-	err = nla_parse(tb, TCA_EM_META_MAX, data, len, meta_policy, NULL);
+	err = nla_parse_deprecated(tb, TCA_EM_META_MAX, data, len,
+				   meta_policy, NULL);
 	if (err < 0)
 		goto errout;
 
diff --git a/net/sched/ematch.c b/net/sched/ematch.c
index 6f2d6a761dbe..7b86c2a44746 100644
--- a/net/sched/ematch.c
+++ b/net/sched/ematch.c
@@ -314,7 +314,8 @@ int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla,
 	if (!nla)
 		return 0;
 
-	err = nla_parse_nested(tb, TCA_EMATCH_TREE_MAX, nla, em_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_EMATCH_TREE_MAX, nla,
+					  em_policy, NULL);
 	if (err < 0)
 		goto errout;
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 6c81b22d214f..607e84d67c33 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -479,7 +479,8 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt,
 	u16 *tab = NULL;
 	int err;
 
-	err = nla_parse_nested(tb, TCA_STAB_MAX, opt, stab_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_STAB_MAX, opt, stab_policy,
+					  extack);
 	if (err < 0)
 		return ERR_PTR(err);
 	if (!tb[TCA_STAB_BASE]) {
@@ -1423,8 +1424,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX,
+				     rtm_tca_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -1508,8 +1509,8 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 
 replay:
 	/* Reinit, just in case something touches this. */
-	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX,
+				     rtm_tca_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -1743,8 +1744,8 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
 	idx = 0;
 	ASSERT_RTNL();
 
-	err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX,
-			  rtm_tca_policy, cb->extack);
+	err = nlmsg_parse_deprecated(nlh, sizeof(struct tcmsg), tca, TCA_MAX,
+				     rtm_tca_policy, cb->extack);
 	if (err < 0)
 		return err;
 
@@ -1972,8 +1973,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy,
-			  extack);
+	err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX,
+				     rtm_tca_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index c36aa57eb4af..ae506c7906cd 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -223,7 +223,8 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent,
 	if (opt == NULL)
 		return -EINVAL;
 
-	error = nla_parse_nested(tb, TCA_ATM_MAX, opt, atm_policy, NULL);
+	error = nla_parse_nested_deprecated(tb, TCA_ATM_MAX, opt, atm_policy,
+					    NULL);
 	if (error < 0)
 		return error;
 
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 50db72fe44de..53a80bc6b13a 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -2531,7 +2531,8 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_CAKE_MAX, opt, cake_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_CAKE_MAX, opt, cake_policy,
+					  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 243bce4b888b..ba4b33b74dd8 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1149,7 +1149,8 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt,
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy,
+					  extack);
 	if (err < 0)
 		return err;
 
@@ -1473,7 +1474,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy,
+					  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index adffc6d68c06..8077c846f5bf 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -358,7 +358,8 @@ static int cbs_change(struct Qdisc *sch, struct nlattr *opt,
 	struct tc_cbs_qopt *qopt;
 	int err;
 
-	err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_CBS_MAX, opt, cbs_policy,
+					  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index eda21dc94bde..370dbcf49e8b 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -358,7 +358,8 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt,
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_CHOKE_MAX, opt, choke_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_CHOKE_MAX, opt,
+					  choke_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 60ac4e61ce3a..25ef172c23df 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -141,7 +141,8 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_CODEL_MAX, opt, codel_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_CODEL_MAX, opt,
+					  codel_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 022db73fd5a9..ffcd6654c39d 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -70,7 +70,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb, TCA_DRR_MAX, opt, drr_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_DRR_MAX, opt, drr_policy,
+					  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index cdf744e710f1..3deeb06eaecf 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -132,7 +132,8 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent,
 	if (!opt)
 		goto errout;
 
-	err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt,
+					  dsmark_policy, NULL);
 	if (err < 0)
 		goto errout;
 
@@ -353,7 +354,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt,
 	if (err)
 		return err;
 
-	err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt,
+					  dsmark_policy, NULL);
 	if (err < 0)
 		goto errout;
 
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 67107caa287c..db0c2ba1d156 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -351,7 +351,8 @@ static int etf_init(struct Qdisc *sch, struct nlattr *opt,
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb, TCA_ETF_MAX, opt, etf_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_ETF_MAX, opt, etf_policy,
+					  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 5ca370e78d3a..d107c74767cd 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -684,7 +684,8 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_FQ_MAX, opt, fq_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_FQ_MAX, opt, fq_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 825a933b019a..08d85370b97c 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -387,8 +387,8 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_FQ_CODEL_MAX, opt, fq_codel_policy,
-			       NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_FQ_CODEL_MAX, opt,
+					  fq_codel_policy, NULL);
 	if (err < 0)
 		return err;
 	if (tb[TCA_FQ_CODEL_FLOWS]) {
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 9bfa15e12d23..dfa657da100f 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -538,7 +538,8 @@ static void gred_vq_apply(struct gred_sched *table, const struct nlattr *entry)
 	struct nlattr *tb[TCA_GRED_VQ_MAX + 1];
 	u32 dp;
 
-	nla_parse_nested(tb, TCA_GRED_VQ_MAX, entry, gred_vq_policy, NULL);
+	nla_parse_nested_deprecated(tb, TCA_GRED_VQ_MAX, entry,
+				    gred_vq_policy, NULL);
 
 	dp = nla_get_u32(tb[TCA_GRED_VQ_DP]);
 
@@ -568,8 +569,8 @@ static int gred_vq_validate(struct gred_sched *table, u32 cdp,
 	int err;
 	u32 dp;
 
-	err = nla_parse_nested(tb, TCA_GRED_VQ_MAX, entry, gred_vq_policy,
-			       extack);
+	err = nla_parse_nested_deprecated(tb, TCA_GRED_VQ_MAX, entry,
+					  gred_vq_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -610,8 +611,8 @@ static int gred_vqs_validate(struct gred_sched *table, u32 cdp,
 	const struct nlattr *attr;
 	int rem, err;
 
-	err = nla_validate_nested(vqs, TCA_GRED_VQ_ENTRY_MAX,
-				  gred_vqe_policy, extack);
+	err = nla_validate_nested_deprecated(vqs, TCA_GRED_VQ_ENTRY_MAX,
+					     gred_vqe_policy, extack);
 	if (err < 0)
 		return err;
 
@@ -650,7 +651,8 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_GRED_MAX, opt, gred_policy,
+					  extack);
 	if (err < 0)
 		return err;
 
@@ -737,7 +739,8 @@ static int gred_init(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_GRED_MAX, opt, gred_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_GRED_MAX, opt, gred_policy,
+					  extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 97d2fb91c39f..433f2190960f 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -926,7 +926,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_HFSC_MAX, opt, hfsc_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_HFSC_MAX, opt, hfsc_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 43bc159c4f7c..a28e09b1609c 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -518,7 +518,8 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_HHF_MAX, opt, hhf_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_HHF_MAX, opt, hhf_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 64010aec5437..d27d9bc9d010 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1012,7 +1012,8 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt,
 	if (err)
 		return err;
 
-	err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_HTB_MAX, opt, htb_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
@@ -1310,7 +1311,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 	if (!opt)
 		goto failure;
 
-	err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_HTB_MAX, opt, htb_policy,
+					  NULL);
 	if (err < 0)
 		goto failure;
 
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 7afefed72d35..d05086dc3866 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -125,8 +125,9 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
 	int nested_len = nla_len(nla) - NLA_ALIGN(len);
 
 	if (nested_len >= nla_attr_size(0))
-		return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len),
-				 nested_len, policy, NULL);
+		return nla_parse_deprecated(tb, maxtype,
+					    nla_data(nla) + NLA_ALIGN(len),
+					    nested_len, policy, NULL);
 
 	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
 	return 0;
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 0242c0d4a2d0..78aa76b0da2e 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -935,8 +935,9 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
 	}
 
 	if (nested_len >= nla_attr_size(0))
-		return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len),
-				 nested_len, policy, NULL);
+		return nla_parse_deprecated(tb, maxtype,
+					    nla_data(nla) + NLA_ALIGN(len),
+					    nested_len, policy, NULL);
 
 	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
 	return 0;
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 9bf41f4a2312..8fa129d3943e 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -216,7 +216,8 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_PIE_MAX, opt, pie_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_PIE_MAX, opt, pie_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index bab2d4026e8b..3f9e8b425ac6 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -410,8 +410,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], qfq_policy,
-			       NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS],
+					  qfq_policy, NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index b9f34e057e87..1e68a13bb66b 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -205,7 +205,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
 	if (opt == NULL)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, TCA_RED_MAX, opt, red_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_RED_MAX, opt, red_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index f54b00a431a3..b245d6a2068d 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -499,7 +499,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt,
 	int err;
 
 	if (opt) {
-		err = nla_parse_nested(tb, TCA_SFB_MAX, opt, sfb_policy, NULL);
+		err = nla_parse_nested_deprecated(tb, TCA_SFB_MAX, opt,
+						  sfb_policy, NULL);
 		if (err < 0)
 			return -EINVAL;
 
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index e016ee07dd1f..09563c245473 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -310,8 +310,8 @@ static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry,
 	struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { };
 	int err;
 
-	err = nla_parse_nested(tb, TCA_TAPRIO_SCHED_ENTRY_MAX, n,
-			       entry_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_SCHED_ENTRY_MAX, n,
+					  entry_policy, NULL);
 	if (err < 0) {
 		NL_SET_ERR_MSG(extack, "Could not parse nested entry");
 		return -EINVAL;
@@ -334,8 +334,8 @@ static int parse_sched_single_entry(struct nlattr *n,
 	u32 index;
 	int err;
 
-	err = nla_parse_nested(tb_list, TCA_TAPRIO_SCHED_MAX,
-			       n, entry_list_policy, NULL);
+	err = nla_parse_nested_deprecated(tb_list, TCA_TAPRIO_SCHED_MAX, n,
+					  entry_list_policy, NULL);
 	if (err < 0) {
 		NL_SET_ERR_MSG(extack, "Could not parse nested entry");
 		return -EINVAL;
@@ -346,9 +346,10 @@ static int parse_sched_single_entry(struct nlattr *n,
 		return -EINVAL;
 	}
 
-	err = nla_parse_nested(tb_entry, TCA_TAPRIO_SCHED_ENTRY_MAX,
-			       tb_list[TCA_TAPRIO_SCHED_ENTRY],
-			       entry_policy, NULL);
+	err = nla_parse_nested_deprecated(tb_entry,
+					  TCA_TAPRIO_SCHED_ENTRY_MAX,
+					  tb_list[TCA_TAPRIO_SCHED_ENTRY],
+					  entry_policy, NULL);
 	if (err < 0) {
 		NL_SET_ERR_MSG(extack, "Could not parse nested entry");
 		return -EINVAL;
@@ -644,8 +645,8 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	int i, err, size;
 	ktime_t start;
 
-	err = nla_parse_nested(tb, TCA_TAPRIO_ATTR_MAX, opt,
-			       taprio_policy, extack);
+	err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_ATTR_MAX, opt,
+					  taprio_policy, extack);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 3ae5a29eeab3..c09c0d855846 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -308,7 +308,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 	s64 buffer, mtu;
 	u64 rate64 = 0, prate64 = 0;
 
-	err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, TCA_TBF_MAX, opt, tbf_policy,
+					  NULL);
 	if (err < 0)
 		return err;
 
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index fd8e4e83f5e0..2bed6589f41e 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -776,9 +776,9 @@ int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_BEARER])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
-			       info->attrs[TIPC_NLA_BEARER],
-			       tipc_nl_bearer_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
+					  info->attrs[TIPC_NLA_BEARER],
+					  tipc_nl_bearer_policy, info->extack);
 	if (err)
 		return err;
 
@@ -825,9 +825,9 @@ int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_BEARER])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
-			       info->attrs[TIPC_NLA_BEARER],
-			       tipc_nl_bearer_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
+					  info->attrs[TIPC_NLA_BEARER],
+					  tipc_nl_bearer_policy, info->extack);
 	if (err)
 		return err;
 
@@ -870,9 +870,9 @@ int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_BEARER])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
-			       info->attrs[TIPC_NLA_BEARER],
-			       tipc_nl_bearer_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
+					  info->attrs[TIPC_NLA_BEARER],
+					  tipc_nl_bearer_policy, info->extack);
 	if (err)
 		return err;
 
@@ -921,9 +921,9 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_BEARER])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
-			       info->attrs[TIPC_NLA_BEARER],
-			       tipc_nl_bearer_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
+					  info->attrs[TIPC_NLA_BEARER],
+					  tipc_nl_bearer_policy, info->extack);
 	if (err)
 		return err;
 
@@ -964,9 +964,9 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_BEARER])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_BEARER_MAX,
-			       info->attrs[TIPC_NLA_BEARER],
-			       tipc_nl_bearer_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_BEARER_MAX,
+					  info->attrs[TIPC_NLA_BEARER],
+					  tipc_nl_bearer_policy, info->extack);
 	if (err)
 		return err;
 
@@ -1107,9 +1107,9 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_MEDIA])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX,
-			       info->attrs[TIPC_NLA_MEDIA],
-			       tipc_nl_media_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX,
+					  info->attrs[TIPC_NLA_MEDIA],
+					  tipc_nl_media_policy, info->extack);
 	if (err)
 		return err;
 
@@ -1155,9 +1155,9 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_MEDIA])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_MEDIA_MAX,
-			       info->attrs[TIPC_NLA_MEDIA],
-			       tipc_nl_media_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MEDIA_MAX,
+					  info->attrs[TIPC_NLA_MEDIA],
+					  tipc_nl_media_policy, info->extack);
 
 	if (!attrs[TIPC_NLA_MEDIA_NAME])
 		return -EINVAL;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 0327c8ff8d48..1c514b64a0a9 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -2148,8 +2148,8 @@ int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[])
 {
 	int err;
 
-	err = nla_parse_nested(props, TIPC_NLA_PROP_MAX, prop,
-			       tipc_nl_prop_policy, NULL);
+	err = nla_parse_nested_deprecated(props, TIPC_NLA_PROP_MAX, prop,
+					  tipc_nl_prop_policy, NULL);
 	if (err)
 		return err;
 
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 0bba4e6b005c..85707c185360 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -245,9 +245,9 @@ int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_NET])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX,
-			       info->attrs[TIPC_NLA_NET], tipc_nl_net_policy,
-			       info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_NET_MAX,
+					  info->attrs[TIPC_NLA_NET],
+					  tipc_nl_net_policy, info->extack);
 
 	if (err)
 		return err;
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 2d178df0a89f..3d5d0fb5b37c 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -255,8 +255,8 @@ int tipc_nlmsg_parse(const struct nlmsghdr *nlh, struct nlattr ***attr)
 	if (!*attr)
 		return -EOPNOTSUPP;
 
-	return nlmsg_parse(nlh, GENL_HDRLEN, *attr, maxattr, tipc_nl_policy,
-			   NULL);
+	return nlmsg_parse_deprecated(nlh, GENL_HDRLEN, *attr, maxattr,
+				      tipc_nl_policy, NULL);
 }
 
 int __init tipc_netlink_start(void)
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 36fe2dbb6d87..f7269ce934b5 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -328,9 +328,9 @@ static int __tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
 	if (err)
 		goto doit_out;
 
-	err = nla_parse(attrbuf, tipc_genl_family.maxattr,
-			(const struct nlattr *)trans_buf->data,
-			trans_buf->len, NULL, NULL);
+	err = nla_parse_deprecated(attrbuf, tipc_genl_family.maxattr,
+				   (const struct nlattr *)trans_buf->data,
+				   trans_buf->len, NULL, NULL);
 	if (err)
 		goto doit_out;
 
@@ -378,8 +378,8 @@ static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg,
 	if (!attrs[TIPC_NLA_BEARER])
 		return -EINVAL;
 
-	err = nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX,
-			       attrs[TIPC_NLA_BEARER], NULL, NULL);
+	err = nla_parse_nested_deprecated(bearer, TIPC_NLA_BEARER_MAX,
+					  attrs[TIPC_NLA_BEARER], NULL, NULL);
 	if (err)
 		return err;
 
@@ -514,24 +514,26 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 	if (!attrs[TIPC_NLA_LINK])
 		return -EINVAL;
 
-	err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK],
-			       NULL, NULL);
+	err = nla_parse_nested_deprecated(link, TIPC_NLA_LINK_MAX,
+					  attrs[TIPC_NLA_LINK], NULL, NULL);
 	if (err)
 		return err;
 
 	if (!link[TIPC_NLA_LINK_PROP])
 		return -EINVAL;
 
-	err = nla_parse_nested(prop, TIPC_NLA_PROP_MAX,
-			       link[TIPC_NLA_LINK_PROP], NULL, NULL);
+	err = nla_parse_nested_deprecated(prop, TIPC_NLA_PROP_MAX,
+					  link[TIPC_NLA_LINK_PROP], NULL,
+					  NULL);
 	if (err)
 		return err;
 
 	if (!link[TIPC_NLA_LINK_STATS])
 		return -EINVAL;
 
-	err = nla_parse_nested(stats, TIPC_NLA_STATS_MAX,
-			       link[TIPC_NLA_LINK_STATS], NULL, NULL);
+	err = nla_parse_nested_deprecated(stats, TIPC_NLA_STATS_MAX,
+					  link[TIPC_NLA_LINK_STATS], NULL,
+					  NULL);
 	if (err)
 		return err;
 
@@ -645,8 +647,8 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
 	if (!attrs[TIPC_NLA_LINK])
 		return -EINVAL;
 
-	err = nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK],
-			       NULL, NULL);
+	err = nla_parse_nested_deprecated(link, TIPC_NLA_LINK_MAX,
+					  attrs[TIPC_NLA_LINK], NULL, NULL);
 	if (err)
 		return err;
 
@@ -869,16 +871,18 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg,
 	if (!attrs[TIPC_NLA_NAME_TABLE])
 		return -EINVAL;
 
-	err = nla_parse_nested(nt, TIPC_NLA_NAME_TABLE_MAX,
-			       attrs[TIPC_NLA_NAME_TABLE], NULL, NULL);
+	err = nla_parse_nested_deprecated(nt, TIPC_NLA_NAME_TABLE_MAX,
+					  attrs[TIPC_NLA_NAME_TABLE], NULL,
+					  NULL);
 	if (err)
 		return err;
 
 	if (!nt[TIPC_NLA_NAME_TABLE_PUBL])
 		return -EINVAL;
 
-	err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX,
-			       nt[TIPC_NLA_NAME_TABLE_PUBL], NULL, NULL);
+	err = nla_parse_nested_deprecated(publ, TIPC_NLA_PUBL_MAX,
+					  nt[TIPC_NLA_NAME_TABLE_PUBL], NULL,
+					  NULL);
 	if (err)
 		return err;
 
@@ -937,8 +941,8 @@ static int __tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg,
 	if (!attrs[TIPC_NLA_PUBL])
 		return -EINVAL;
 
-	err = nla_parse_nested(publ, TIPC_NLA_PUBL_MAX, attrs[TIPC_NLA_PUBL],
-			       NULL, NULL);
+	err = nla_parse_nested_deprecated(publ, TIPC_NLA_PUBL_MAX,
+					  attrs[TIPC_NLA_PUBL], NULL, NULL);
 	if (err)
 		return err;
 
@@ -1007,8 +1011,8 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
 	if (!attrs[TIPC_NLA_SOCK])
 		return -EINVAL;
 
-	err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK],
-			       NULL, NULL);
+	err = nla_parse_nested_deprecated(sock, TIPC_NLA_SOCK_MAX,
+					  attrs[TIPC_NLA_SOCK], NULL, NULL);
 	if (err)
 		return err;
 
@@ -1019,8 +1023,9 @@ static int tipc_nl_compat_sk_dump(struct tipc_nl_compat_msg *msg,
 		u32 node;
 		struct nlattr *con[TIPC_NLA_CON_MAX + 1];
 
-		err = nla_parse_nested(con, TIPC_NLA_CON_MAX,
-				       sock[TIPC_NLA_SOCK_CON], NULL, NULL);
+		err = nla_parse_nested_deprecated(con, TIPC_NLA_CON_MAX,
+						  sock[TIPC_NLA_SOCK_CON],
+						  NULL, NULL);
 
 		if (err)
 			return err;
@@ -1059,8 +1064,8 @@ static int tipc_nl_compat_media_dump(struct tipc_nl_compat_msg *msg,
 	if (!attrs[TIPC_NLA_MEDIA])
 		return -EINVAL;
 
-	err = nla_parse_nested(media, TIPC_NLA_MEDIA_MAX,
-			       attrs[TIPC_NLA_MEDIA], NULL, NULL);
+	err = nla_parse_nested_deprecated(media, TIPC_NLA_MEDIA_MAX,
+					  attrs[TIPC_NLA_MEDIA], NULL, NULL);
 	if (err)
 		return err;
 
@@ -1079,8 +1084,8 @@ static int tipc_nl_compat_node_dump(struct tipc_nl_compat_msg *msg,
 	if (!attrs[TIPC_NLA_NODE])
 		return -EINVAL;
 
-	err = nla_parse_nested(node, TIPC_NLA_NODE_MAX, attrs[TIPC_NLA_NODE],
-			       NULL, NULL);
+	err = nla_parse_nested_deprecated(node, TIPC_NLA_NODE_MAX,
+					  attrs[TIPC_NLA_NODE], NULL, NULL);
 	if (err)
 		return err;
 
@@ -1126,8 +1131,8 @@ static int tipc_nl_compat_net_dump(struct tipc_nl_compat_msg *msg,
 	if (!attrs[TIPC_NLA_NET])
 		return -EINVAL;
 
-	err = nla_parse_nested(net, TIPC_NLA_NET_MAX, attrs[TIPC_NLA_NET],
-			       NULL, NULL);
+	err = nla_parse_nested_deprecated(net, TIPC_NLA_NET_MAX,
+					  attrs[TIPC_NLA_NET], NULL, NULL);
 	if (err)
 		return err;
 
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 3777254a508f..0eb1bf850219 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1885,9 +1885,9 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_NET])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_NET_MAX,
-			       info->attrs[TIPC_NLA_NET], tipc_nl_net_policy,
-			       info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_NET_MAX,
+					  info->attrs[TIPC_NLA_NET],
+					  tipc_nl_net_policy, info->extack);
 	if (err)
 		return err;
 
@@ -2043,9 +2043,9 @@ int tipc_nl_node_set_link(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_LINK])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
-			       info->attrs[TIPC_NLA_LINK],
-			       tipc_nl_link_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_LINK_MAX,
+					  info->attrs[TIPC_NLA_LINK],
+					  tipc_nl_link_policy, info->extack);
 	if (err)
 		return err;
 
@@ -2119,9 +2119,9 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_LINK])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
-			       info->attrs[TIPC_NLA_LINK],
-			       tipc_nl_link_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_LINK_MAX,
+					  info->attrs[TIPC_NLA_LINK],
+					  tipc_nl_link_policy, info->extack);
 	if (err)
 		return err;
 
@@ -2184,9 +2184,9 @@ int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_LINK])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX,
-			       info->attrs[TIPC_NLA_LINK],
-			       tipc_nl_link_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_LINK_MAX,
+					  info->attrs[TIPC_NLA_LINK],
+					  tipc_nl_link_policy, info->extack);
 	if (err)
 		return err;
 
@@ -2324,9 +2324,10 @@ int tipc_nl_node_set_monitor(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[TIPC_NLA_MON])
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, TIPC_NLA_MON_MAX,
-			       info->attrs[TIPC_NLA_MON],
-			       tipc_nl_monitor_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, TIPC_NLA_MON_MAX,
+					  info->attrs[TIPC_NLA_MON],
+					  tipc_nl_monitor_policy,
+					  info->extack);
 	if (err)
 		return err;
 
@@ -2444,9 +2445,10 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb,
 		if (!attrs[TIPC_NLA_MON])
 			return -EINVAL;
 
-		err = nla_parse_nested(mon, TIPC_NLA_MON_MAX,
-				       attrs[TIPC_NLA_MON],
-				       tipc_nl_monitor_policy, NULL);
+		err = nla_parse_nested_deprecated(mon, TIPC_NLA_MON_MAX,
+						  attrs[TIPC_NLA_MON],
+						  tipc_nl_monitor_policy,
+						  NULL);
 		if (err)
 			return err;
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7918f4763fdc..145e4decb0c9 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -3599,9 +3599,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (!attrs[TIPC_NLA_SOCK])
 			return -EINVAL;
 
-		err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX,
-				       attrs[TIPC_NLA_SOCK],
-				       tipc_nl_sock_policy, NULL);
+		err = nla_parse_nested_deprecated(sock, TIPC_NLA_SOCK_MAX,
+						  attrs[TIPC_NLA_SOCK],
+						  tipc_nl_sock_policy, NULL);
 		if (err)
 			return err;
 
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 24d7c79598bb..7fc02d84c4f1 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -447,9 +447,9 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb)
 		if (!attrs[TIPC_NLA_BEARER])
 			return -EINVAL;
 
-		err = nla_parse_nested(battrs, TIPC_NLA_BEARER_MAX,
-				       attrs[TIPC_NLA_BEARER],
-				       tipc_nl_bearer_policy, NULL);
+		err = nla_parse_nested_deprecated(battrs, TIPC_NLA_BEARER_MAX,
+						  attrs[TIPC_NLA_BEARER],
+						  tipc_nl_bearer_policy, NULL);
 		if (err)
 			return err;
 
@@ -601,8 +601,7 @@ int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr)
 	struct nlattr *opts[TIPC_NLA_UDP_MAX + 1];
 	struct udp_media_addr *dst;
 
-	if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX, attr,
-			     tipc_nl_udp_policy, NULL))
+	if (nla_parse_nested_deprecated(opts, TIPC_NLA_UDP_MAX, attr, tipc_nl_udp_policy, NULL))
 		return -EINVAL;
 
 	if (!opts[TIPC_NLA_UDP_REMOTE])
@@ -655,9 +654,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 	if (!attrs[TIPC_NLA_BEARER_UDP_OPTS])
 		goto err;
 
-	if (nla_parse_nested(opts, TIPC_NLA_UDP_MAX,
-			     attrs[TIPC_NLA_BEARER_UDP_OPTS],
-			     tipc_nl_udp_policy, NULL))
+	if (nla_parse_nested_deprecated(opts, TIPC_NLA_UDP_MAX, attrs[TIPC_NLA_BEARER_UDP_OPTS], tipc_nl_udp_policy, NULL))
 		goto err;
 
 	if (!opts[TIPC_NLA_UDP_LOCAL] || !opts[TIPC_NLA_UDP_REMOTE]) {
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0bcd5ea4b4f2..782c8225a90a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -703,9 +703,11 @@ int nl80211_prepare_wdev_dump(struct netlink_callback *cb,
 	int err;
 
 	if (!cb->args[0]) {
-		err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
-				  genl_family_attrbuf(&nl80211_fam),
-				  nl80211_fam.maxattr, nl80211_policy, NULL);
+		err = nlmsg_parse_deprecated(cb->nlh,
+					     GENL_HDRLEN + nl80211_fam.hdrsize,
+					     genl_family_attrbuf(&nl80211_fam),
+					     nl80211_fam.maxattr,
+					     nl80211_policy, NULL);
 		if (err)
 			return err;
 
@@ -925,8 +927,9 @@ static int nl80211_parse_key_new(struct genl_info *info, struct nlattr *key,
 				 struct key_parse *k)
 {
 	struct nlattr *tb[NL80211_KEY_MAX + 1];
-	int err = nla_parse_nested(tb, NL80211_KEY_MAX, key,
-				   nl80211_key_policy, info->extack);
+	int err = nla_parse_nested_deprecated(tb, NL80211_KEY_MAX, key,
+					      nl80211_key_policy,
+					      info->extack);
 	if (err)
 		return err;
 
@@ -962,10 +965,11 @@ static int nl80211_parse_key_new(struct genl_info *info, struct nlattr *key,
 	if (tb[NL80211_KEY_DEFAULT_TYPES]) {
 		struct nlattr *kdt[NUM_NL80211_KEY_DEFAULT_TYPES];
 
-		err = nla_parse_nested(kdt, NUM_NL80211_KEY_DEFAULT_TYPES - 1,
-				       tb[NL80211_KEY_DEFAULT_TYPES],
-				       nl80211_key_default_policy,
-				       info->extack);
+		err = nla_parse_nested_deprecated(kdt,
+						  NUM_NL80211_KEY_DEFAULT_TYPES - 1,
+						  tb[NL80211_KEY_DEFAULT_TYPES],
+						  nl80211_key_default_policy,
+						  info->extack);
 		if (err)
 			return err;
 
@@ -1012,11 +1016,11 @@ static int nl80211_parse_key_old(struct genl_info *info, struct key_parse *k)
 
 	if (info->attrs[NL80211_ATTR_KEY_DEFAULT_TYPES]) {
 		struct nlattr *kdt[NUM_NL80211_KEY_DEFAULT_TYPES];
-		int err = nla_parse_nested(kdt,
-					   NUM_NL80211_KEY_DEFAULT_TYPES - 1,
-					   info->attrs[NL80211_ATTR_KEY_DEFAULT_TYPES],
-					   nl80211_key_default_policy,
-					   info->extack);
+		int err = nla_parse_nested_deprecated(kdt,
+						      NUM_NL80211_KEY_DEFAULT_TYPES - 1,
+						      info->attrs[NL80211_ATTR_KEY_DEFAULT_TYPES],
+						      nl80211_key_default_policy,
+						      info->extack);
 		if (err)
 			return err;
 
@@ -2317,8 +2321,10 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb,
 				    struct nl80211_dump_wiphy_state *state)
 {
 	struct nlattr **tb = genl_family_attrbuf(&nl80211_fam);
-	int ret = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, tb,
-			      nl80211_fam.maxattr, nl80211_policy, NULL);
+	int ret = nlmsg_parse_deprecated(cb->nlh,
+					 GENL_HDRLEN + nl80211_fam.hdrsize,
+					 tb, nl80211_fam.maxattr,
+					 nl80211_policy, NULL);
 	/* ignore parse errors for backward compatibility */
 	if (ret)
 		return 0;
@@ -2761,10 +2767,11 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 		nla_for_each_nested(nl_txq_params,
 				    info->attrs[NL80211_ATTR_WIPHY_TXQ_PARAMS],
 				    rem_txq_params) {
-			result = nla_parse_nested(tb, NL80211_TXQ_ATTR_MAX,
-						  nl_txq_params,
-						  txq_params_policy,
-						  info->extack);
+			result = nla_parse_nested_deprecated(tb,
+							     NL80211_TXQ_ATTR_MAX,
+							     nl_txq_params,
+							     txq_params_policy,
+							     info->extack);
 			if (result)
 				return result;
 			result = parse_txq_params(tb, &txq_params);
@@ -3221,8 +3228,7 @@ static int parse_monitor_flags(struct nlattr *nla, u32 *mntrflags)
 	if (!nla)
 		return -EINVAL;
 
-	if (nla_parse_nested(flags, NL80211_MNTR_FLAG_MAX, nla,
-			     mntr_flags_policy, NULL))
+	if (nla_parse_nested_deprecated(flags, NL80211_MNTR_FLAG_MAX, nla, mntr_flags_policy, NULL))
 		return -EINVAL;
 
 	for (flag = 1; flag <= NL80211_MNTR_FLAG_MAX; flag++)
@@ -4101,8 +4107,10 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 		sband = rdev->wiphy.bands[band];
 		if (sband == NULL)
 			return -EINVAL;
-		err = nla_parse_nested(tb, NL80211_TXRATE_MAX, tx_rates,
-				       nl80211_txattr_policy, info->extack);
+		err = nla_parse_nested_deprecated(tb, NL80211_TXRATE_MAX,
+						  tx_rates,
+						  nl80211_txattr_policy,
+						  info->extack);
 		if (err)
 			return err;
 		if (tb[NL80211_TXRATE_LEGACY]) {
@@ -4270,9 +4278,10 @@ static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev,
 	if (attrs[NL80211_ATTR_FTM_RESPONDER]) {
 		struct nlattr *tb[NL80211_FTM_RESP_ATTR_MAX + 1];
 
-		err = nla_parse_nested(tb, NL80211_FTM_RESP_ATTR_MAX,
-				       attrs[NL80211_ATTR_FTM_RESPONDER],
-				       NULL, NULL);
+		err = nla_parse_nested_deprecated(tb,
+						  NL80211_FTM_RESP_ATTR_MAX,
+						  attrs[NL80211_ATTR_FTM_RESPONDER],
+						  NULL, NULL);
 		if (err)
 			return err;
 
@@ -4680,8 +4689,7 @@ static int parse_station_flags(struct genl_info *info,
 	if (!nla)
 		return 0;
 
-	if (nla_parse_nested(flags, NL80211_STA_FLAG_MAX, nla,
-			     sta_flags_policy, info->extack))
+	if (nla_parse_nested_deprecated(flags, NL80211_STA_FLAG_MAX, nla, sta_flags_policy, info->extack))
 		return -EINVAL;
 
 	/*
@@ -5350,8 +5358,9 @@ static int nl80211_parse_sta_wme(struct genl_info *info,
 		return 0;
 
 	nla = info->attrs[NL80211_ATTR_STA_WME];
-	err = nla_parse_nested(tb, NL80211_STA_WME_MAX, nla,
-			       nl80211_sta_wme_policy, info->extack);
+	err = nla_parse_nested_deprecated(tb, NL80211_STA_WME_MAX, nla,
+					  nl80211_sta_wme_policy,
+					  info->extack);
 	if (err)
 		return err;
 
@@ -6491,9 +6500,7 @@ do {									\
 
 	if (!info->attrs[NL80211_ATTR_MESH_CONFIG])
 		return -EINVAL;
-	if (nla_parse_nested(tb, NL80211_MESHCONF_ATTR_MAX,
-			     info->attrs[NL80211_ATTR_MESH_CONFIG],
-			     nl80211_meshconf_params_policy, info->extack))
+	if (nla_parse_nested_deprecated(tb, NL80211_MESHCONF_ATTR_MAX, info->attrs[NL80211_ATTR_MESH_CONFIG], nl80211_meshconf_params_policy, info->extack))
 		return -EINVAL;
 
 	/* This makes sure that there aren't more than 32 mesh config
@@ -6626,9 +6633,7 @@ static int nl80211_parse_mesh_setup(struct genl_info *info,
 
 	if (!info->attrs[NL80211_ATTR_MESH_SETUP])
 		return -EINVAL;
-	if (nla_parse_nested(tb, NL80211_MESH_SETUP_ATTR_MAX,
-			     info->attrs[NL80211_ATTR_MESH_SETUP],
-			     nl80211_mesh_setup_params_policy, info->extack))
+	if (nla_parse_nested_deprecated(tb, NL80211_MESH_SETUP_ATTR_MAX, info->attrs[NL80211_ATTR_MESH_SETUP], nl80211_mesh_setup_params_policy, info->extack))
 		return -EINVAL;
 
 	if (tb[NL80211_MESH_SETUP_ENABLE_VENDOR_SYNC])
@@ -7012,9 +7017,9 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info)
 
 	nla_for_each_nested(nl_reg_rule, info->attrs[NL80211_ATTR_REG_RULES],
 			    rem_reg_rules) {
-		r = nla_parse_nested(tb, NL80211_REG_RULE_ATTR_MAX,
-				     nl_reg_rule, reg_rule_policy,
-				     info->extack);
+		r = nla_parse_nested_deprecated(tb, NL80211_REG_RULE_ATTR_MAX,
+						nl_reg_rule, reg_rule_policy,
+						info->extack);
 		if (r)
 			goto bad_reg;
 		r = parse_reg_rule(tb, &rd->reg_rules[rule_idx]);
@@ -7085,8 +7090,9 @@ static int parse_bss_select(struct nlattr *nla, struct wiphy *wiphy,
 	if (!nla_ok(nest, nla_len(nest)))
 		return -EINVAL;
 
-	err = nla_parse_nested(attr, NL80211_BSS_SELECT_ATTR_MAX, nest,
-			       nl80211_bss_select_policy, NULL);
+	err = nla_parse_nested_deprecated(attr, NL80211_BSS_SELECT_ATTR_MAX,
+					  nest, nl80211_bss_select_policy,
+					  NULL);
 	if (err)
 		return err;
 
@@ -7579,8 +7585,10 @@ nl80211_parse_sched_scan_plans(struct wiphy *wiphy, int n_plans,
 		if (WARN_ON(i >= n_plans))
 			return -EINVAL;
 
-		err = nla_parse_nested(plan, NL80211_SCHED_SCAN_PLAN_MAX,
-				       attr, nl80211_plan_policy, NULL);
+		err = nla_parse_nested_deprecated(plan,
+						  NL80211_SCHED_SCAN_PLAN_MAX,
+						  attr, nl80211_plan_policy,
+						  NULL);
 		if (err)
 			return err;
 
@@ -7701,10 +7709,11 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 				    tmp) {
 			struct nlattr *rssi;
 
-			err = nla_parse_nested(tb,
-					       NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
-					       attr, nl80211_match_policy,
-					       NULL);
+			err = nla_parse_nested_deprecated(tb,
+							  NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
+							  attr,
+							  nl80211_match_policy,
+							  NULL);
 			if (err)
 				return ERR_PTR(err);
 
@@ -7888,10 +7897,11 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 				    tmp) {
 			struct nlattr *ssid, *bssid, *rssi;
 
-			err = nla_parse_nested(tb,
-					       NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
-					       attr, nl80211_match_policy,
-					       NULL);
+			err = nla_parse_nested_deprecated(tb,
+							  NL80211_SCHED_SCAN_MATCH_ATTR_MAX,
+							  attr,
+							  nl80211_match_policy,
+							  NULL);
 			if (err)
 				goto out_free;
 			ssid = tb[NL80211_SCHED_SCAN_MATCH_ATTR_SSID];
@@ -8275,9 +8285,9 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 
-	err = nla_parse_nested(csa_attrs, NL80211_ATTR_MAX,
-			       info->attrs[NL80211_ATTR_CSA_IES],
-			       nl80211_policy, info->extack);
+	err = nla_parse_nested_deprecated(csa_attrs, NL80211_ATTR_MAX,
+					  info->attrs[NL80211_ATTR_CSA_IES],
+					  nl80211_policy, info->extack);
 	if (err)
 		return err;
 
@@ -9552,9 +9562,10 @@ static int nl80211_testmode_dump(struct sk_buff *skb,
 	} else {
 		struct nlattr **attrbuf = genl_family_attrbuf(&nl80211_fam);
 
-		err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize,
-				  attrbuf, nl80211_fam.maxattr,
-				  nl80211_policy, NULL);
+		err = nlmsg_parse_deprecated(cb->nlh,
+					     GENL_HDRLEN + nl80211_fam.hdrsize,
+					     attrbuf, nl80211_fam.maxattr,
+					     nl80211_policy, NULL);
 		if (err)
 			goto out_err;
 
@@ -10678,8 +10689,9 @@ static int nl80211_set_cqm(struct sk_buff *skb, struct genl_info *info)
 	if (!cqm)
 		return -EINVAL;
 
-	err = nla_parse_nested(attrs, NL80211_ATTR_CQM_MAX, cqm,
-			       nl80211_attr_cqm_policy, info->extack);
+	err = nla_parse_nested_deprecated(attrs, NL80211_ATTR_CQM_MAX, cqm,
+					  nl80211_attr_cqm_policy,
+					  info->extack);
 	if (err)
 		return err;
 
@@ -11117,8 +11129,8 @@ static int nl80211_parse_wowlan_tcp(struct cfg80211_registered_device *rdev,
 	if (!rdev->wiphy.wowlan->tcp)
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, MAX_NL80211_WOWLAN_TCP, attr,
-			       nl80211_wowlan_tcp_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, MAX_NL80211_WOWLAN_TCP, attr,
+					  nl80211_wowlan_tcp_policy, NULL);
 	if (err)
 		return err;
 
@@ -11263,8 +11275,8 @@ static int nl80211_parse_wowlan_nd(struct cfg80211_registered_device *rdev,
 		goto out;
 	}
 
-	err = nla_parse_nested(tb, NL80211_ATTR_MAX, attr, nl80211_policy,
-			       NULL);
+	err = nla_parse_nested_deprecated(tb, NL80211_ATTR_MAX, attr,
+					  nl80211_policy, NULL);
 	if (err)
 		goto out;
 
@@ -11299,9 +11311,9 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 		goto set_wakeup;
 	}
 
-	err = nla_parse_nested(tb, MAX_NL80211_WOWLAN_TRIG,
-			       info->attrs[NL80211_ATTR_WOWLAN_TRIGGERS],
-			       nl80211_wowlan_policy, info->extack);
+	err = nla_parse_nested_deprecated(tb, MAX_NL80211_WOWLAN_TRIG,
+					  info->attrs[NL80211_ATTR_WOWLAN_TRIGGERS],
+					  nl80211_wowlan_policy, info->extack);
 	if (err)
 		return err;
 
@@ -11383,9 +11395,11 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 				    rem) {
 			u8 *mask_pat;
 
-			err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
-					       nl80211_packet_pattern_policy,
-					       info->extack);
+			err = nla_parse_nested_deprecated(pat_tb,
+							  MAX_NL80211_PKTPAT,
+							  pat,
+							  nl80211_packet_pattern_policy,
+							  info->extack);
 			if (err)
 				goto error;
 
@@ -11598,8 +11612,8 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
 	int rem, pat_len, mask_len, pkt_offset, n_patterns = 0;
 	struct nlattr *pat_tb[NUM_NL80211_PKTPAT];
 
-	err = nla_parse_nested(tb, NL80211_ATTR_COALESCE_RULE_MAX, rule,
-			       nl80211_coalesce_policy, NULL);
+	err = nla_parse_nested_deprecated(tb, NL80211_ATTR_COALESCE_RULE_MAX,
+					  rule, nl80211_coalesce_policy, NULL);
 	if (err)
 		return err;
 
@@ -11634,8 +11648,10 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
 			    rem) {
 		u8 *mask_pat;
 
-		err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
-				       nl80211_packet_pattern_policy, NULL);
+		err = nla_parse_nested_deprecated(pat_tb, MAX_NL80211_PKTPAT,
+						  pat,
+						  nl80211_packet_pattern_policy,
+						  NULL);
 		if (err)
 			return err;
 
@@ -11757,9 +11773,9 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[NL80211_ATTR_REKEY_DATA])
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, MAX_NL80211_REKEY_DATA,
-			       info->attrs[NL80211_ATTR_REKEY_DATA],
-			       nl80211_rekey_policy, info->extack);
+	err = nla_parse_nested_deprecated(tb, MAX_NL80211_REKEY_DATA,
+					  info->attrs[NL80211_ATTR_REKEY_DATA],
+					  nl80211_rekey_policy, info->extack);
 	if (err)
 		return err;
 
@@ -12071,9 +12087,10 @@ static int nl80211_nan_add_func(struct sk_buff *skb,
 	if (!info->attrs[NL80211_ATTR_NAN_FUNC])
 		return -EINVAL;
 
-	err = nla_parse_nested(tb, NL80211_NAN_FUNC_ATTR_MAX,
-			       info->attrs[NL80211_ATTR_NAN_FUNC],
-			       nl80211_nan_func_policy, info->extack);
+	err = nla_parse_nested_deprecated(tb, NL80211_NAN_FUNC_ATTR_MAX,
+					  info->attrs[NL80211_ATTR_NAN_FUNC],
+					  nl80211_nan_func_policy,
+					  info->extack);
 	if (err)
 		return err;
 
@@ -12169,9 +12186,11 @@ static int nl80211_nan_add_func(struct sk_buff *skb,
 	if (tb[NL80211_NAN_FUNC_SRF]) {
 		struct nlattr *srf_tb[NUM_NL80211_NAN_SRF_ATTR];
 
-		err = nla_parse_nested(srf_tb, NL80211_NAN_SRF_ATTR_MAX,
-				       tb[NL80211_NAN_FUNC_SRF],
-				       nl80211_nan_srf_policy, info->extack);
+		err = nla_parse_nested_deprecated(srf_tb,
+						  NL80211_NAN_SRF_ATTR_MAX,
+						  tb[NL80211_NAN_FUNC_SRF],
+						  nl80211_nan_srf_policy,
+						  info->extack);
 		if (err)
 			goto out;
 
@@ -12704,8 +12723,10 @@ static int nl80211_prepare_vendor_dump(struct sk_buff *skb,
 		return 0;
 	}
 
-	err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, attrbuf,
-			  nl80211_fam.maxattr, nl80211_policy, NULL);
+	err = nlmsg_parse_deprecated(cb->nlh,
+				     GENL_HDRLEN + nl80211_fam.hdrsize,
+				     attrbuf, nl80211_fam.maxattr,
+				     nl80211_policy, NULL);
 	if (err)
 		return err;
 
diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c
index 5c80bccc8b3c..1b190475359a 100644
--- a/net/wireless/pmsr.c
+++ b/net/wireless/pmsr.c
@@ -25,7 +25,8 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev,
 	}
 
 	/* no validation needed - was already done via nested policy */
-	nla_parse_nested(tb, NL80211_PMSR_FTM_REQ_ATTR_MAX, ftmreq, NULL, NULL);
+	nla_parse_nested_deprecated(tb, NL80211_PMSR_FTM_REQ_ATTR_MAX, ftmreq,
+				    NULL, NULL);
 
 	if (tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE])
 		preamble = nla_get_u32(tb[NL80211_PMSR_FTM_REQ_ATTR_PREAMBLE]);
@@ -139,7 +140,8 @@ static int pmsr_parse_peer(struct cfg80211_registered_device *rdev,
 	int err, rem;
 
 	/* no validation needed - was already done via nested policy */
-	nla_parse_nested(tb, NL80211_PMSR_PEER_ATTR_MAX, peer, NULL, NULL);
+	nla_parse_nested_deprecated(tb, NL80211_PMSR_PEER_ATTR_MAX, peer,
+				    NULL, NULL);
 
 	if (!tb[NL80211_PMSR_PEER_ATTR_ADDR] ||
 	    !tb[NL80211_PMSR_PEER_ATTR_CHAN] ||
@@ -154,9 +156,9 @@ static int pmsr_parse_peer(struct cfg80211_registered_device *rdev,
 	/* reuse info->attrs */
 	memset(info->attrs, 0, sizeof(*info->attrs) * (NL80211_ATTR_MAX + 1));
 	/* need to validate here, we don't want to have validation recursion */
-	err = nla_parse_nested(info->attrs, NL80211_ATTR_MAX,
-			       tb[NL80211_PMSR_PEER_ATTR_CHAN],
-			       nl80211_policy, info->extack);
+	err = nla_parse_nested_deprecated(info->attrs, NL80211_ATTR_MAX,
+					  tb[NL80211_PMSR_PEER_ATTR_CHAN],
+					  nl80211_policy, info->extack);
 	if (err)
 		return err;
 
@@ -165,9 +167,9 @@ static int pmsr_parse_peer(struct cfg80211_registered_device *rdev,
 		return err;
 
 	/* no validation needed - was already done via nested policy */
-	nla_parse_nested(req, NL80211_PMSR_REQ_ATTR_MAX,
-			 tb[NL80211_PMSR_PEER_ATTR_REQ],
-			 NULL, NULL);
+	nla_parse_nested_deprecated(req, NL80211_PMSR_REQ_ATTR_MAX,
+				    tb[NL80211_PMSR_PEER_ATTR_REQ], NULL,
+				    NULL);
 
 	if (!req[NL80211_PMSR_REQ_ATTR_DATA]) {
 		NL_SET_ERR_MSG_ATTR(info->extack,
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index a131f9ff979e..d7cb16f0df5b 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1006,8 +1006,8 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
 		u8 proto = 0;
 		int err;
 
-		err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX, xfrma_policy,
-				  cb->extack);
+		err = nlmsg_parse_deprecated(cb->nlh, 0, attrs, XFRMA_MAX,
+					     xfrma_policy, cb->extack);
 		if (err < 0)
 			return err;
 
@@ -2656,9 +2656,9 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		}
 	}
 
-	err = nlmsg_parse(nlh, xfrm_msg_min[type], attrs,
-			  link->nla_max ? : XFRMA_MAX,
-			  link->nla_pol ? : xfrma_policy, extack);
+	err = nlmsg_parse_deprecated(nlh, xfrm_msg_min[type], attrs,
+				     link->nla_max ? : XFRMA_MAX,
+				     link->nla_pol ? : xfrma_policy, extack);
 	if (err < 0)
 		return err;
 
-- 
cgit v1.2.3


From 3de644035446567017e952f16da2594d6bd195fc Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 26 Apr 2019 14:07:29 +0200
Subject: netlink: re-add parse/validate functions in strict mode

This re-adds the parse and validate functions like nla_parse()
that are now actually strict after the previous rename and were
just split out to make sure everything is converted (and if not
compilation of the previous patch would fail.)

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 19 +++++++++++
 include/net/netlink.h   | 87 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 106 insertions(+)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 897cdba13569..68de579cfe5e 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -183,6 +183,25 @@ static inline int genlmsg_parse_deprecated(const struct nlmsghdr *nlh,
 			     policy, NL_VALIDATE_LIBERAL, extack);
 }
 
+/**
+ * genlmsg_parse - parse attributes of a genetlink message
+ * @nlh: netlink message header
+ * @family: genetlink message family
+ * @tb: destination array with maxtype+1 elements
+ * @maxtype: maximum attribute type to be expected
+ * @policy: validation policy
+ * @extack: extended ACK report struct
+ */
+static inline int genlmsg_parse(const struct nlmsghdr *nlh,
+				const struct genl_family *family,
+				struct nlattr *tb[], int maxtype,
+				const struct nla_policy *policy,
+				struct netlink_ext_ack *extack)
+{
+	return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype,
+			     policy, NL_VALIDATE_STRICT, extack);
+}
+
 /**
  * genl_dump_check_consistent - check if sequence is consistent and advertise if not
  * @cb: netlink callback structure that stores the sequence number
diff --git a/include/net/netlink.h b/include/net/netlink.h
index ab26a5e3558b..e4dd874412bf 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -538,6 +538,31 @@ nlmsg_next(const struct nlmsghdr *nlh, int *remaining)
 	return (struct nlmsghdr *) ((unsigned char *) nlh + totlen);
 }
 
+/**
+ * nla_parse - Parse a stream of attributes into a tb buffer
+ * @tb: destination array with maxtype+1 elements
+ * @maxtype: maximum attribute type to be expected
+ * @head: head of attribute stream
+ * @len: length of attribute stream
+ * @policy: validation policy
+ * @extack: extended ACK pointer
+ *
+ * Parses a stream of attributes and stores a pointer to each attribute in
+ * the tb array accessible via the attribute type. Attributes with a type
+ * exceeding maxtype will be rejected, policy must be specified, attributes
+ * will be validated in the strictest way possible.
+ *
+ * Returns 0 on success or a negative error code.
+ */
+static inline int nla_parse(struct nlattr **tb, int maxtype,
+			    const struct nlattr *head, int len,
+			    const struct nla_policy *policy,
+			    struct netlink_ext_ack *extack)
+{
+	return __nla_parse(tb, maxtype, head, len, policy,
+			   NL_VALIDATE_STRICT, extack);
+}
+
 /**
  * nla_parse_deprecated - Parse a stream of attributes into a tb buffer
  * @tb: destination array with maxtype+1 elements
@@ -617,6 +642,27 @@ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
 			   extack);
 }
 
+/**
+ * nlmsg_parse - parse attributes of a netlink message
+ * @nlh: netlink message header
+ * @hdrlen: length of family specific header
+ * @tb: destination array with maxtype+1 elements
+ * @maxtype: maximum attribute type to be expected
+ * @validate: validation strictness
+ * @extack: extended ACK report struct
+ *
+ * See nla_parse()
+ */
+static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
+			      struct nlattr *tb[], int maxtype,
+			      const struct nla_policy *policy,
+			      struct netlink_ext_ack *extack)
+{
+	return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
+			   nlmsg_attrlen(nlh, hdrlen), policy,
+			   NL_VALIDATE_STRICT, extack);
+}
+
 /**
  * nlmsg_parse_deprecated - parse attributes of a netlink message
  * @nlh: netlink message header
@@ -695,6 +741,28 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len,
 			      extack);
 }
 
+/**
+ * nla_validate - Validate a stream of attributes
+ * @head: head of attribute stream
+ * @len: length of attribute stream
+ * @maxtype: maximum attribute type to be expected
+ * @policy: validation policy
+ * @validate: validation strictness
+ * @extack: extended ACK report struct
+ *
+ * Validates all attributes in the specified attribute stream against the
+ * specified policy. Validation is done in strict mode.
+ * See documenation of struct nla_policy for more details.
+ *
+ * Returns 0 on success or a negative error code.
+ */
+static inline int nla_validate(const struct nlattr *head, int len, int maxtype,
+			       const struct nla_policy *policy,
+			       struct netlink_ext_ack *extack)
+{
+	return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_STRICT,
+			      extack);
+}
 
 /**
  * nlmsg_validate_deprecated - validate a netlink message including attributes
@@ -1031,6 +1099,25 @@ nla_find_nested(const struct nlattr *nla, int attrtype)
 	return nla_find(nla_data(nla), nla_len(nla), attrtype);
 }
 
+/**
+ * nla_parse_nested - parse nested attributes
+ * @tb: destination array with maxtype+1 elements
+ * @maxtype: maximum attribute type to be expected
+ * @nla: attribute containing the nested attributes
+ * @policy: validation policy
+ * @extack: extended ACK report struct
+ *
+ * See nla_parse()
+ */
+static inline int nla_parse_nested(struct nlattr *tb[], int maxtype,
+				   const struct nlattr *nla,
+				   const struct nla_policy *policy,
+				   struct netlink_ext_ack *extack)
+{
+	return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy,
+			   NL_VALIDATE_STRICT, extack);
+}
+
 /**
  * nla_parse_nested_deprecated - parse nested attributes
  * @tb: destination array with maxtype+1 elements
-- 
cgit v1.2.3


From 56738f460841761abc70347c919d5c45f6f05a42 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 26 Apr 2019 14:07:30 +0200
Subject: netlink: add strict parsing for future attributes

Unfortunately, we cannot add strict parsing for all attributes, as
that would break existing userspace. We currently warn about it, but
that's about all we can do.

For new attributes, however, the story is better: nobody is using
them, so we can reject bad sizes.

Also, for new attributes, we need not accept them when the policy
doesn't declare their usage.

David Ahern and I went back and forth on how to best encode this, and
the best way we found was to have a "boundary type", from which point
on new attributes have all possible validation applied, and NLA_UNSPEC
is rejected.

As we didn't want to add another argument to all functions that get a
netlink policy, the workaround is to encode that boundary in the first
entry of the policy array (which is for type 0 and thus probably not
really valid anyway). I put it into the validation union for the rare
possibility that somebody is actually using attribute 0, which would
continue to work fine unless they tried to use the extended validation,
which isn't likely. We also didn't find any in-tree users with type 0.

The reason for setting the "start strict here" attribute is that we
never really need to start strict from 0, which is invalid anyway (or
in legacy families where that isn't true, it cannot be set to strict),
so we can thus reserve the value 0 for "don't do this check" and don't
have to add the tag to all policies right now.

Thus, policies can now opt in to this validation, which we should do
for all existing policies, at least when adding new attributes.

Note that entirely *new* policies won't need to set it, as the use
of that should be using nla_parse()/nlmsg_parse() etc. which anyway
do fully strict validation now, regardless of this.

So in effect, this patch only covers the "existing command with new
attribute" case.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h | 18 ++++++++++++++++++
 lib/nlattr.c          |  4 ++++
 2 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index e4dd874412bf..679f649748d4 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -299,6 +299,24 @@ struct nla_policy {
 		};
 		int (*validate)(const struct nlattr *attr,
 				struct netlink_ext_ack *extack);
+		/* This entry is special, and used for the attribute at index 0
+		 * only, and specifies special data about the policy, namely it
+		 * specifies the "boundary type" where strict length validation
+		 * starts for any attribute types >= this value, also, strict
+		 * nesting validation starts here.
+		 *
+		 * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT
+		 * for any types >= this, so need to use NLA_MIN_LEN to get the
+		 * previous pure { .len = xyz } behaviour. The advantage of this
+		 * is that types not specified in the policy will be rejected.
+		 *
+		 * For completely new families it should be set to 1 so that the
+		 * validation is enforced for all attributes. For existing ones
+		 * it should be set at least when new attributes are added to
+		 * the enum used by the policy, and be set to the new value that
+		 * was added to enforce strict validation from thereon.
+		 */
+		u16 strict_start_type;
 	};
 };
 
diff --git a/lib/nlattr.c b/lib/nlattr.c
index af0f8b0309c6..29f6336e2422 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -158,10 +158,14 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 			const struct nla_policy *policy, unsigned int validate,
 			struct netlink_ext_ack *extack)
 {
+	u16 strict_start_type = policy[0].strict_start_type;
 	const struct nla_policy *pt;
 	int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla);
 	int err = -ERANGE;
 
+	if (strict_start_type && type >= strict_start_type)
+		validate |= NL_VALIDATE_STRICT;
+
 	if (type <= 0 || type > maxtype)
 		return 0;
 
-- 
cgit v1.2.3


From ef6243acb4782df587a4d7d6c310fa5b5d82684b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 26 Apr 2019 14:07:31 +0200
Subject: genetlink: optionally validate strictly/dumps

Add options to strictly validate messages and dump messages,
sometimes perhaps validating dump messages non-strictly may
be required, so add an option for that as well.

Since none of this can really be applied to existing commands,
set the options everwhere using the following spatch:

    @@
    identifier ops;
    expression X;
    @@
    struct genl_ops ops[] = {
    ...,
     {
            .cmd = X,
    +       .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
            ...
     },
    ...
    };

For new commands one should just not copy the .validate 'opt-out'
flags and thus get strict validation.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/nbd.c                      |   4 ++
 drivers/net/gtp.c                        |   3 +
 drivers/net/ieee802154/mac802154_hwsim.c |   6 ++
 drivers/net/macsec.c                     |  10 +++
 drivers/net/team/team.c                  |   4 ++
 drivers/net/wireless/mac80211_hwsim.c    |   6 ++
 drivers/target/target_core_user.c        |   4 ++
 fs/dlm/netlink.c                         |   1 +
 include/net/genetlink.h                  |   7 +++
 kernel/taskstats.c                       |   2 +
 net/batman-adv/netlink.c                 |  18 ++++++
 net/core/devlink.c                       |  38 +++++++++++
 net/core/drop_monitor.c                  |   3 +
 net/hsr/hsr_netlink.c                    |   2 +
 net/ieee802154/nl802154.c                |  29 +++++++++
 net/ipv4/fou.c                           |   3 +
 net/ipv4/tcp_metrics.c                   |   2 +
 net/ipv6/ila/ila_main.c                  |   4 ++
 net/ipv6/seg6.c                          |   4 ++
 net/l2tp/l2tp_netlink.c                  |   9 +++
 net/ncsi/ncsi-netlink.c                  |   6 ++
 net/netfilter/ipvs/ip_vs_ctl.c           |  16 +++++
 net/netlabel/netlabel_calipso.c          |   4 ++
 net/netlabel/netlabel_cipso_v4.c         |   4 ++
 net/netlabel/netlabel_mgmt.c             |   8 +++
 net/netlabel/netlabel_unlabeled.c        |   8 +++
 net/netlink/genetlink.c                  |  29 ++++++++-
 net/nfc/netlink.c                        |  19 ++++++
 net/openvswitch/conntrack.c              |   3 +
 net/openvswitch/datapath.c               |  13 ++++
 net/openvswitch/meter.c                  |   4 ++
 net/psample/psample.c                    |   1 +
 net/smc/smc_pnet.c                       |   4 ++
 net/tipc/netlink.c                       |  21 +++++++
 net/tipc/netlink_compat.c                |   1 +
 net/wimax/stack.c                        |   4 ++
 net/wireless/nl80211.c                   | 104 +++++++++++++++++++++++++++++++
 37 files changed, 405 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 69dc11f907a3..6c2dd268e603 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -2003,18 +2003,22 @@ out:
 static const struct genl_ops nbd_connect_genl_ops[] = {
 	{
 		.cmd	= NBD_CMD_CONNECT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= nbd_genl_connect,
 	},
 	{
 		.cmd	= NBD_CMD_DISCONNECT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= nbd_genl_disconnect,
 	},
 	{
 		.cmd	= NBD_CMD_RECONFIGURE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= nbd_genl_reconfigure,
 	},
 	{
 		.cmd	= NBD_CMD_STATUS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= nbd_genl_status,
 	},
 };
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index c06e31747288..eaf4311b4004 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1270,16 +1270,19 @@ static const struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
 static const struct genl_ops gtp_genl_ops[] = {
 	{
 		.cmd = GTP_CMD_NEWPDP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = gtp_genl_new_pdp,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = GTP_CMD_DELPDP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = gtp_genl_del_pdp,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = GTP_CMD_GETPDP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = gtp_genl_get_pdp,
 		.dumpit = gtp_genl_dump_pdp,
 		.flags = GENL_ADMIN_PERM,
diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index 486a3a3bf35b..b187ae1a6bd6 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -594,31 +594,37 @@ static const struct nla_policy hwsim_genl_policy[MAC802154_HWSIM_ATTR_MAX + 1] =
 static const struct genl_ops hwsim_nl_ops[] = {
 	{
 		.cmd = MAC802154_HWSIM_CMD_NEW_RADIO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_new_radio_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = MAC802154_HWSIM_CMD_DEL_RADIO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_del_radio_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = MAC802154_HWSIM_CMD_GET_RADIO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_get_radio_nl,
 		.dumpit = hwsim_dump_radio_nl,
 	},
 	{
 		.cmd = MAC802154_HWSIM_CMD_NEW_EDGE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_new_edge_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = MAC802154_HWSIM_CMD_DEL_EDGE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_del_edge_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = MAC802154_HWSIM_CMD_SET_EDGE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_set_edge_lqi,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index c3fa3d8da8f3..009b2902c9d3 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -2637,50 +2637,60 @@ done:
 static const struct genl_ops macsec_genl_ops[] = {
 	{
 		.cmd = MACSEC_CMD_GET_TXSC,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit = macsec_dump_txsc,
 	},
 	{
 		.cmd = MACSEC_CMD_ADD_RXSC,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = macsec_add_rxsc,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_DEL_RXSC,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = macsec_del_rxsc,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_UPD_RXSC,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = macsec_upd_rxsc,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_ADD_TXSA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = macsec_add_txsa,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_DEL_TXSA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = macsec_del_txsa,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_UPD_TXSA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = macsec_upd_txsa,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_ADD_RXSA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = macsec_add_rxsa,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_DEL_RXSA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = macsec_del_rxsa,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = MACSEC_CMD_UPD_RXSA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = macsec_upd_rxsa,
 		.flags = GENL_ADMIN_PERM,
 	},
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index be58445afbbc..2106045b3e16 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -2757,20 +2757,24 @@ static int team_nl_cmd_port_list_get(struct sk_buff *skb,
 static const struct genl_ops team_nl_ops[] = {
 	{
 		.cmd = TEAM_CMD_NOOP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = team_nl_cmd_noop,
 	},
 	{
 		.cmd = TEAM_CMD_OPTIONS_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = team_nl_cmd_options_set,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = TEAM_CMD_OPTIONS_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = team_nl_cmd_options_get,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = TEAM_CMD_PORT_LIST_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = team_nl_cmd_port_list_get,
 		.flags = GENL_ADMIN_PERM,
 	},
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 2a1aa2f6e7dc..0dcb511f44e2 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -3637,29 +3637,35 @@ done:
 static const struct genl_ops hwsim_ops[] = {
 	{
 		.cmd = HWSIM_CMD_REGISTER,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_register_received_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = HWSIM_CMD_FRAME,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_cloned_frame_received_nl,
 	},
 	{
 		.cmd = HWSIM_CMD_TX_INFO_FRAME,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_tx_info_frame_received_nl,
 	},
 	{
 		.cmd = HWSIM_CMD_NEW_RADIO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_new_radio_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = HWSIM_CMD_DEL_RADIO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_del_radio_nl,
 		.flags = GENL_UNS_ADMIN_PERM,
 	},
 	{
 		.cmd = HWSIM_CMD_GET_RADIO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = hwsim_get_radio_nl,
 		.dumpit = hwsim_dump_radio_nl,
 	},
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 481d371c4b01..40b29ca5a98d 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -441,21 +441,25 @@ static int tcmu_genl_set_features(struct sk_buff *skb, struct genl_info *info)
 static const struct genl_ops tcmu_genl_ops[] = {
 	{
 		.cmd	= TCMU_CMD_SET_FEATURES,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= tcmu_genl_set_features,
 	},
 	{
 		.cmd	= TCMU_CMD_ADDED_DEVICE_DONE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= tcmu_genl_add_dev_done,
 	},
 	{
 		.cmd	= TCMU_CMD_REMOVED_DEVICE_DONE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= tcmu_genl_rm_dev_done,
 	},
 	{
 		.cmd	= TCMU_CMD_RECONFIG_DEVICE_DONE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= tcmu_genl_reconfig_dev_done,
 	},
diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c
index 43a96c330570..d8e27defa89f 100644
--- a/fs/dlm/netlink.c
+++ b/fs/dlm/netlink.c
@@ -68,6 +68,7 @@ static int user_cmd(struct sk_buff *skb, struct genl_info *info)
 static const struct genl_ops dlm_nl_ops[] = {
 	{
 		.cmd	= DLM_CMD_HELLO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= user_cmd,
 	},
 };
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 68de579cfe5e..9292f1c588b7 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -121,6 +121,12 @@ static inline int genl_err_attr(struct genl_info *info, int err,
 	return err;
 }
 
+enum genl_validate_flags {
+	GENL_DONT_VALIDATE_STRICT		= BIT(0),
+	GENL_DONT_VALIDATE_DUMP			= BIT(1),
+	GENL_DONT_VALIDATE_DUMP_STRICT		= BIT(2),
+};
+
 /**
  * struct genl_ops - generic netlink operations
  * @cmd: command identifier
@@ -141,6 +147,7 @@ struct genl_ops {
 	u8			cmd;
 	u8			internal_flags;
 	u8			flags;
+	u8			validate;
 };
 
 int genl_register_family(struct genl_family *family);
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 0e347f1c7800..5f852b8f59f7 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -649,12 +649,14 @@ err:
 static const struct genl_ops taskstats_ops[] = {
 	{
 		.cmd		= TASKSTATS_CMD_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit		= taskstats_user_cmd,
 		/* policy enforced later */
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_HASPOL,
 	},
 	{
 		.cmd		= CGROUPSTATS_CMD_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit		= cgroupstats_user_cmd,
 		/* policy enforced later */
 		.flags		= GENL_CMD_CAP_HASPOL,
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index e7907308b331..a67720fad46c 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -1343,29 +1343,34 @@ static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
 static const struct genl_ops batadv_netlink_ops[] = {
 	{
 		.cmd = BATADV_CMD_GET_MESH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		/* can be retrieved by unprivileged users */
 		.doit = batadv_netlink_get_mesh,
 		.internal_flags = BATADV_FLAG_NEED_MESH,
 	},
 	{
 		.cmd = BATADV_CMD_TP_METER,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = batadv_netlink_tp_meter_start,
 		.internal_flags = BATADV_FLAG_NEED_MESH,
 	},
 	{
 		.cmd = BATADV_CMD_TP_METER_CANCEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = batadv_netlink_tp_meter_cancel,
 		.internal_flags = BATADV_FLAG_NEED_MESH,
 	},
 	{
 		.cmd = BATADV_CMD_GET_ROUTING_ALGOS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.dumpit = batadv_algo_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_HARDIF,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		/* can be retrieved by unprivileged users */
 		.dumpit = batadv_netlink_dump_hardif,
 		.doit = batadv_netlink_get_hardif,
@@ -1374,57 +1379,68 @@ static const struct genl_ops batadv_netlink_ops[] = {
 	},
 	{
 		.cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.dumpit = batadv_tt_local_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_TRANSTABLE_GLOBAL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.dumpit = batadv_tt_global_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_ORIGINATORS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.dumpit = batadv_orig_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_NEIGHBORS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.dumpit = batadv_hardif_neigh_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_GATEWAYS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.dumpit = batadv_gw_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_BLA_CLAIM,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.dumpit = batadv_bla_claim_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_BLA_BACKBONE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.dumpit = batadv_bla_backbone_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_DAT_CACHE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.dumpit = batadv_dat_cache_dump,
 	},
 	{
 		.cmd = BATADV_CMD_GET_MCAST_FLAGS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.dumpit = batadv_mcast_flags_dump,
 	},
 	{
 		.cmd = BATADV_CMD_SET_MESH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = batadv_netlink_set_mesh,
 		.internal_flags = BATADV_FLAG_NEED_MESH,
 	},
 	{
 		.cmd = BATADV_CMD_SET_HARDIF,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = batadv_netlink_set_hardif,
 		.internal_flags = BATADV_FLAG_NEED_MESH |
@@ -1432,6 +1448,7 @@ static const struct genl_ops batadv_netlink_ops[] = {
 	},
 	{
 		.cmd = BATADV_CMD_GET_VLAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		/* can be retrieved by unprivileged users */
 		.doit = batadv_netlink_get_vlan,
 		.internal_flags = BATADV_FLAG_NEED_MESH |
@@ -1439,6 +1456,7 @@ static const struct genl_ops batadv_netlink_ops[] = {
 	},
 	{
 		.cmd = BATADV_CMD_SET_VLAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = batadv_netlink_set_vlan,
 		.internal_flags = BATADV_FLAG_NEED_MESH |
diff --git a/net/core/devlink.c b/net/core/devlink.c
index b020d182c9fc..4e28d04c0165 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4948,6 +4948,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 static const struct genl_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_get_doit,
 		.dumpit = devlink_nl_cmd_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
@@ -4955,6 +4956,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_PORT_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_port_get_doit,
 		.dumpit = devlink_nl_cmd_port_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
@@ -4962,12 +4964,14 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_PORT_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_port_set_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
 	{
 		.cmd = DEVLINK_CMD_PORT_SPLIT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_port_split_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -4975,6 +4979,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_PORT_UNSPLIT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_port_unsplit_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -4982,6 +4987,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_sb_get_doit,
 		.dumpit = devlink_nl_cmd_sb_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -4990,6 +4996,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_POOL_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_sb_pool_get_doit,
 		.dumpit = devlink_nl_cmd_sb_pool_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -4998,6 +5005,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_POOL_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_sb_pool_set_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -5005,6 +5013,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_PORT_POOL_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_sb_port_pool_get_doit,
 		.dumpit = devlink_nl_cmd_sb_port_pool_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
@@ -5013,6 +5022,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_PORT_POOL_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_sb_port_pool_set_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
@@ -5020,6 +5030,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit,
 		.dumpit = devlink_nl_cmd_sb_tc_pool_bind_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
@@ -5028,6 +5039,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT |
@@ -5035,6 +5047,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_sb_occ_snapshot_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -5042,6 +5055,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_sb_occ_max_clear_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -5049,12 +5063,14 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_ESWITCH_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_eswitch_get_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_ESWITCH_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_eswitch_set_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -5062,42 +5078,49 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_DPIPE_TABLE_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_dpipe_table_get,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_dpipe_entries_get,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_DPIPE_HEADERS_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_dpipe_headers_get,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_dpipe_table_counters_set,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_RESOURCE_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_resource_set,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_RESOURCE_DUMP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_resource_dump,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = DEVLINK_CMD_RELOAD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_reload,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -5105,6 +5128,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_PARAM_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_param_get_doit,
 		.dumpit = devlink_nl_cmd_param_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
@@ -5112,12 +5136,14 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_PARAM_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_param_set_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_PORT_PARAM_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_port_param_get_doit,
 		.dumpit = devlink_nl_cmd_port_param_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
@@ -5125,12 +5151,14 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_PORT_PARAM_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_port_param_set_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
 	{
 		.cmd = DEVLINK_CMD_REGION_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_region_get_doit,
 		.dumpit = devlink_nl_cmd_region_get_dumpit,
 		.flags = GENL_ADMIN_PERM,
@@ -5138,18 +5166,21 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_REGION_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_region_del,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_REGION_READ,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit = devlink_nl_cmd_region_read_dumpit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_INFO_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_info_get_doit,
 		.dumpit = devlink_nl_cmd_info_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
@@ -5157,6 +5188,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_health_reporter_get_doit,
 		.dumpit = devlink_nl_cmd_health_reporter_get_dumpit,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
@@ -5164,24 +5196,28 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_health_reporter_set_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_health_reporter_recover_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_health_reporter_diagnose_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_health_reporter_dump_get_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -5189,6 +5225,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_health_reporter_dump_clear_doit,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
@@ -5196,6 +5233,7 @@ static const struct genl_ops devlink_nl_ops[] = {
 	},
 	{
 		.cmd = DEVLINK_CMD_FLASH_UPDATE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_flash_update,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index c7785efeea57..d4ce0542acfa 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -355,14 +355,17 @@ out:
 static const struct genl_ops dropmon_ops[] = {
 	{
 		.cmd = NET_DM_CMD_CONFIG,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = net_dm_cmd_config,
 	},
 	{
 		.cmd = NET_DM_CMD_START,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = net_dm_cmd_trace,
 	},
 	{
 		.cmd = NET_DM_CMD_STOP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = net_dm_cmd_trace,
 	},
 };
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index c2d5a368d6d8..8f8337f893ba 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -437,12 +437,14 @@ fail:
 static const struct genl_ops hsr_ops[] = {
 	{
 		.cmd = HSR_C_GET_NODE_STATUS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = 0,
 		.doit = hsr_get_node_status,
 		.dumpit = NULL,
 	},
 	{
 		.cmd = HSR_C_GET_NODE_LIST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = 0,
 		.doit = hsr_get_node_list,
 		.dumpit = NULL,
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 4218304cb201..e4c4174f9efb 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -2209,6 +2209,7 @@ static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
 static const struct genl_ops nl802154_ops[] = {
 	{
 		.cmd = NL802154_CMD_GET_WPAN_PHY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_get_wpan_phy,
 		.dumpit = nl802154_dump_wpan_phy,
 		.done = nl802154_dump_wpan_phy_done,
@@ -2218,6 +2219,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_GET_INTERFACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_get_interface,
 		.dumpit = nl802154_dump_interface,
 		/* can be retrieved by unprivileged users */
@@ -2226,6 +2228,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_NEW_INTERFACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_new_interface,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
@@ -2233,6 +2236,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_DEL_INTERFACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_del_interface,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_DEV |
@@ -2240,6 +2244,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_CHANNEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_channel,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
@@ -2247,6 +2252,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_CCA_MODE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_cca_mode,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
@@ -2254,6 +2260,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_CCA_ED_LEVEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_cca_ed_level,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
@@ -2261,6 +2268,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_TX_POWER,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_tx_power,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
@@ -2268,6 +2276,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_WPAN_PHY_NETNS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_wpan_phy_netns,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
@@ -2275,6 +2284,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_PAN_ID,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_pan_id,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2282,6 +2292,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_SHORT_ADDR,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_short_addr,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2289,6 +2300,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_BACKOFF_EXPONENT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_backoff_exponent,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2296,6 +2308,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_MAX_CSMA_BACKOFFS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_max_csma_backoffs,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2303,6 +2316,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_MAX_FRAME_RETRIES,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_max_frame_retries,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2310,6 +2324,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_LBT_MODE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_lbt_mode,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2317,6 +2332,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_SET_ACKREQ_DEFAULT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_ackreq_default,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2325,6 +2341,7 @@ static const struct genl_ops nl802154_ops[] = {
 #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
 	{
 		.cmd = NL802154_CMD_SET_SEC_PARAMS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_set_llsec_params,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2332,6 +2349,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_GET_SEC_KEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		/* TODO .doit by matching key id? */
 		.dumpit = nl802154_dump_llsec_key,
 		.flags = GENL_ADMIN_PERM,
@@ -2340,6 +2358,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_NEW_SEC_KEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_add_llsec_key,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2347,6 +2366,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_DEL_SEC_KEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_del_llsec_key,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2355,6 +2375,7 @@ static const struct genl_ops nl802154_ops[] = {
 	/* TODO unique identifier must short+pan OR extended_addr */
 	{
 		.cmd = NL802154_CMD_GET_SEC_DEV,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		/* TODO .doit by matching extended_addr? */
 		.dumpit = nl802154_dump_llsec_dev,
 		.flags = GENL_ADMIN_PERM,
@@ -2363,6 +2384,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_NEW_SEC_DEV,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_add_llsec_dev,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2370,6 +2392,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_DEL_SEC_DEV,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_del_llsec_dev,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2378,6 +2401,7 @@ static const struct genl_ops nl802154_ops[] = {
 	/* TODO remove complete devkey, put it as nested? */
 	{
 		.cmd = NL802154_CMD_GET_SEC_DEVKEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		/* TODO doit by matching ??? */
 		.dumpit = nl802154_dump_llsec_devkey,
 		.flags = GENL_ADMIN_PERM,
@@ -2386,6 +2410,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_NEW_SEC_DEVKEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_add_llsec_devkey,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2393,6 +2418,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_DEL_SEC_DEVKEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_del_llsec_devkey,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2400,6 +2426,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_GET_SEC_LEVEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		/* TODO .doit by matching frame_type? */
 		.dumpit = nl802154_dump_llsec_seclevel,
 		.flags = GENL_ADMIN_PERM,
@@ -2408,6 +2435,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_NEW_SEC_LEVEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl802154_add_llsec_seclevel,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL802154_FLAG_NEED_NETDEV |
@@ -2415,6 +2443,7 @@ static const struct genl_ops nl802154_ops[] = {
 	},
 	{
 		.cmd = NL802154_CMD_DEL_SEC_LEVEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		/* TODO match frame_type only? */
 		.doit = nl802154_del_llsec_seclevel,
 		.flags = GENL_ADMIN_PERM,
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 1ca1586a7e46..ca95051317ed 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -913,16 +913,19 @@ static int fou_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 static const struct genl_ops fou_nl_ops[] = {
 	{
 		.cmd = FOU_CMD_ADD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = fou_nl_cmd_add_port,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = FOU_CMD_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = fou_nl_cmd_rm_port,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = FOU_CMD_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = fou_nl_cmd_get_port,
 		.dumpit = fou_nl_dump,
 	},
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 9a08bfb0672c..f262f2cace29 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -951,11 +951,13 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
 static const struct genl_ops tcp_metrics_nl_ops[] = {
 	{
 		.cmd = TCP_METRICS_CMD_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = tcp_metrics_nl_cmd_get,
 		.dumpit = tcp_metrics_nl_dump,
 	},
 	{
 		.cmd = TCP_METRICS_CMD_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = tcp_metrics_nl_cmd_del,
 		.flags = GENL_ADMIN_PERM,
 	},
diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c
index 8d31a5066d0c..257d2b681246 100644
--- a/net/ipv6/ila/ila_main.c
+++ b/net/ipv6/ila/ila_main.c
@@ -16,21 +16,25 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = {
 static const struct genl_ops ila_nl_ops[] = {
 	{
 		.cmd = ILA_CMD_ADD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = ila_xlat_nl_cmd_add_mapping,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = ILA_CMD_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = ila_xlat_nl_cmd_del_mapping,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = ILA_CMD_FLUSH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = ila_xlat_nl_cmd_flush,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = ILA_CMD_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = ila_xlat_nl_cmd_get_mapping,
 		.start = ila_xlat_nl_dump_start,
 		.dumpit = ila_xlat_nl_dump,
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index ceff773471e7..0c5479ef9b38 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -398,11 +398,13 @@ static struct pernet_operations ip6_segments_ops = {
 static const struct genl_ops seg6_genl_ops[] = {
 	{
 		.cmd	= SEG6_CMD_SETHMAC,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= seg6_genl_sethmac,
 		.flags	= GENL_ADMIN_PERM,
 	},
 	{
 		.cmd	= SEG6_CMD_DUMPHMAC,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.start	= seg6_genl_dumphmac_start,
 		.dumpit	= seg6_genl_dumphmac,
 		.done	= seg6_genl_dumphmac_done,
@@ -410,11 +412,13 @@ static const struct genl_ops seg6_genl_ops[] = {
 	},
 	{
 		.cmd	= SEG6_CMD_SET_TUNSRC,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= seg6_genl_set_tunsrc,
 		.flags	= GENL_ADMIN_PERM,
 	},
 	{
 		.cmd	= SEG6_CMD_GET_TUNSRC,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= seg6_genl_get_tunsrc,
 		.flags	= GENL_ADMIN_PERM,
 	},
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index c31b50cc48d9..6acc7f869b0c 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -915,47 +915,56 @@ static const struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = {
 static const struct genl_ops l2tp_nl_ops[] = {
 	{
 		.cmd = L2TP_CMD_NOOP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_noop,
 		/* can be retrieved by unprivileged users */
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_CREATE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_create,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_DELETE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_delete,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_MODIFY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_modify,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_TUNNEL_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_tunnel_get,
 		.dumpit = l2tp_nl_cmd_tunnel_dump,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_CREATE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_create,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_DELETE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_delete,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_MODIFY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_modify,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = L2TP_CMD_SESSION_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = l2tp_nl_cmd_session_get,
 		.dumpit = l2tp_nl_cmd_session_dump,
 		.flags = GENL_ADMIN_PERM,
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 37759c88ef02..7fc4feddafa3 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -723,32 +723,38 @@ static int ncsi_set_channel_mask_nl(struct sk_buff *msg,
 static const struct genl_ops ncsi_ops[] = {
 	{
 		.cmd = NCSI_CMD_PKG_INFO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = ncsi_pkg_info_nl,
 		.dumpit = ncsi_pkg_info_all_nl,
 		.flags = 0,
 	},
 	{
 		.cmd = NCSI_CMD_SET_INTERFACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = ncsi_set_interface_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NCSI_CMD_CLEAR_INTERFACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = ncsi_clear_interface_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NCSI_CMD_SEND_CMD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = ncsi_send_cmd_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NCSI_CMD_SET_PACKAGE_MASK,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = ncsi_set_package_mask_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NCSI_CMD_SET_CHANNEL_MASK,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = ncsi_set_channel_mask_nl,
 		.flags = GENL_ADMIN_PERM,
 	},
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 24bb1a7b590c..0e887159425c 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3802,82 +3802,98 @@ out:
 static const struct genl_ops ip_vs_genl_ops[] = {
 	{
 		.cmd	= IPVS_CMD_NEW_SERVICE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_SET_SERVICE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_DEL_SERVICE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_GET_SERVICE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_get_cmd,
 		.dumpit	= ip_vs_genl_dump_services,
 	},
 	{
 		.cmd	= IPVS_CMD_NEW_DEST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_SET_DEST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_DEL_DEST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_GET_DEST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.dumpit	= ip_vs_genl_dump_dests,
 	},
 	{
 		.cmd	= IPVS_CMD_NEW_DAEMON,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_daemon,
 	},
 	{
 		.cmd	= IPVS_CMD_DEL_DAEMON,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_daemon,
 	},
 	{
 		.cmd	= IPVS_CMD_GET_DAEMON,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.dumpit	= ip_vs_genl_dump_daemons,
 	},
 	{
 		.cmd	= IPVS_CMD_SET_CONFIG,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_GET_CONFIG,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_get_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_GET_INFO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_get_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_ZERO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_cmd,
 	},
 	{
 		.cmd	= IPVS_CMD_FLUSH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags	= GENL_ADMIN_PERM,
 		.doit	= ip_vs_genl_set_cmd,
 	},
diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c
index 80184513b2b2..1de87172885d 100644
--- a/net/netlabel/netlabel_calipso.c
+++ b/net/netlabel/netlabel_calipso.c
@@ -321,24 +321,28 @@ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info)
 static const struct genl_ops netlbl_calipso_ops[] = {
 	{
 	.cmd = NLBL_CALIPSO_C_ADD,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_calipso_add,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CALIPSO_C_REMOVE,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_calipso_remove,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CALIPSO_C_LIST,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = netlbl_calipso_list,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CALIPSO_C_LISTALL,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = NULL,
 	.dumpit = netlbl_calipso_listall,
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 8d401df65928..5d1121981d0b 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -741,24 +741,28 @@ static int netlbl_cipsov4_remove(struct sk_buff *skb, struct genl_info *info)
 static const struct genl_ops netlbl_cipsov4_ops[] = {
 	{
 	.cmd = NLBL_CIPSOV4_C_ADD,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_cipsov4_add,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CIPSOV4_C_REMOVE,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_cipsov4_remove,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CIPSOV4_C_LIST,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = netlbl_cipsov4_list,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_CIPSOV4_C_LISTALL,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = NULL,
 	.dumpit = netlbl_cipsov4_listall,
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index c6c8a101f2ff..cae04f207782 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -774,48 +774,56 @@ version_failure:
 static const struct genl_ops netlbl_mgmt_genl_ops[] = {
 	{
 	.cmd = NLBL_MGMT_C_ADD,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_mgmt_add,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_MGMT_C_REMOVE,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_mgmt_remove,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_MGMT_C_LISTALL,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = NULL,
 	.dumpit = netlbl_mgmt_listall,
 	},
 	{
 	.cmd = NLBL_MGMT_C_ADDDEF,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_mgmt_adddef,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_MGMT_C_REMOVEDEF,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_mgmt_removedef,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_MGMT_C_LISTDEF,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = netlbl_mgmt_listdef,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_MGMT_C_PROTOCOLS,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = NULL,
 	.dumpit = netlbl_mgmt_protocols,
 	},
 	{
 	.cmd = NLBL_MGMT_C_VERSION,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = netlbl_mgmt_version,
 	.dumpit = NULL,
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index 6b1b6c2b5141..b87dd34e1835 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -1317,48 +1317,56 @@ unlabel_staticlistdef_return:
 static const struct genl_ops netlbl_unlabel_genl_ops[] = {
 	{
 	.cmd = NLBL_UNLABEL_C_STATICADD,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_unlabel_staticadd,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_STATICREMOVE,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_unlabel_staticremove,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_STATICLIST,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = NULL,
 	.dumpit = netlbl_unlabel_staticlist,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_STATICADDDEF,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_unlabel_staticadddef,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_STATICREMOVEDEF,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_unlabel_staticremovedef,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_STATICLISTDEF,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = NULL,
 	.dumpit = netlbl_unlabel_staticlistdef,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_ACCEPT,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = GENL_ADMIN_PERM,
 	.doit = netlbl_unlabel_accept,
 	.dumpit = NULL,
 	},
 	{
 	.cmd = NLBL_UNLABEL_C_LIST,
+	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	.flags = 0,
 	.doit = netlbl_unlabel_list,
 	.dumpit = NULL,
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 994d9aff2093..72668759cd2b 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -536,6 +536,24 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 		if (ops->dumpit == NULL)
 			return -EOPNOTSUPP;
 
+		if (!(ops->validate & GENL_DONT_VALIDATE_DUMP)) {
+			unsigned int validate = NL_VALIDATE_STRICT;
+			int hdrlen = GENL_HDRLEN + family->hdrsize;
+
+			if (ops->validate & GENL_DONT_VALIDATE_DUMP_STRICT)
+				validate = NL_VALIDATE_LIBERAL;
+
+			if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
+				return -EINVAL;
+
+			rc = __nla_validate(nlmsg_attrdata(nlh, hdrlen),
+					    nlmsg_attrlen(nlh, hdrlen),
+					    family->maxattr, family->policy,
+					    validate, extack);
+			if (rc)
+				return rc;
+		}
+
 		if (!family->parallel_ops) {
 			struct netlink_dump_control c = {
 				.module = family->module,
@@ -577,9 +595,13 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 		attrbuf = family->attrbuf;
 
 	if (attrbuf) {
-		err = nlmsg_parse_deprecated(nlh, hdrlen, attrbuf,
-					     family->maxattr, family->policy,
-					     extack);
+		enum netlink_validation validate = NL_VALIDATE_STRICT;
+
+		if (ops->validate & GENL_DONT_VALIDATE_STRICT)
+			validate = NL_VALIDATE_LIBERAL;
+
+		err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr,
+				    family->policy, validate, extack);
 		if (err < 0)
 			goto out;
 	}
@@ -939,6 +961,7 @@ static int genl_ctrl_event(int event, const struct genl_family *family,
 static const struct genl_ops genl_ctrl_ops[] = {
 	{
 		.cmd		= CTRL_CMD_GETFAMILY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit		= ctrl_getfamily,
 		.dumpit		= ctrl_dumpfamily,
 	},
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index c6ba308cede7..04a8e47674ec 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1669,82 +1669,101 @@ EXPORT_SYMBOL(nfc_vendor_cmd_reply);
 static const struct genl_ops nfc_genl_ops[] = {
 	{
 		.cmd = NFC_CMD_GET_DEVICE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_get_device,
 		.dumpit = nfc_genl_dump_devices,
 		.done = nfc_genl_dump_devices_done,
 	},
 	{
 		.cmd = NFC_CMD_DEV_UP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_dev_up,
 	},
 	{
 		.cmd = NFC_CMD_DEV_DOWN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_dev_down,
 	},
 	{
 		.cmd = NFC_CMD_START_POLL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_start_poll,
 	},
 	{
 		.cmd = NFC_CMD_STOP_POLL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_stop_poll,
 	},
 	{
 		.cmd = NFC_CMD_DEP_LINK_UP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_dep_link_up,
 	},
 	{
 		.cmd = NFC_CMD_DEP_LINK_DOWN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_dep_link_down,
 	},
 	{
 		.cmd = NFC_CMD_GET_TARGET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit = nfc_genl_dump_targets,
 		.done = nfc_genl_dump_targets_done,
 	},
 	{
 		.cmd = NFC_CMD_LLC_GET_PARAMS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_llc_get_params,
 	},
 	{
 		.cmd = NFC_CMD_LLC_SET_PARAMS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_llc_set_params,
 	},
 	{
 		.cmd = NFC_CMD_LLC_SDREQ,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_llc_sdreq,
 	},
 	{
 		.cmd = NFC_CMD_FW_DOWNLOAD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_fw_download,
 	},
 	{
 		.cmd = NFC_CMD_ENABLE_SE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_enable_se,
 	},
 	{
 		.cmd = NFC_CMD_DISABLE_SE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_disable_se,
 	},
 	{
 		.cmd = NFC_CMD_GET_SE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit = nfc_genl_dump_ses,
 		.done = nfc_genl_dump_ses_done,
 	},
 	{
 		.cmd = NFC_CMD_SE_IO,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_se_io,
 	},
 	{
 		.cmd = NFC_CMD_ACTIVATE_TARGET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_activate_target,
 	},
 	{
 		.cmd = NFC_CMD_VENDOR,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_vendor_cmd,
 	},
 	{
 		.cmd = NFC_CMD_DEACTIVATE_TARGET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nfc_genl_deactivate_target,
 	},
 };
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index ff8baf810bb3..bded32144619 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -2186,16 +2186,19 @@ exit_err:
 
 static struct genl_ops ct_limit_genl_ops[] = {
 	{ .cmd = OVS_CT_LIMIT_CMD_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
 					   * privilege. */
 		.doit = ovs_ct_limit_cmd_set,
 	},
 	{ .cmd = OVS_CT_LIMIT_CMD_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
 					   * privilege. */
 		.doit = ovs_ct_limit_cmd_del,
 	},
 	{ .cmd = OVS_CT_LIMIT_CMD_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = 0,		  /* OK for unprivileged users. */
 		.doit = ovs_ct_limit_cmd_get,
 	},
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 3b99fc3de9ac..b95015c7e999 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -639,6 +639,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
 
 static const struct genl_ops dp_packet_genl_ops[] = {
 	{ .cmd = OVS_PACKET_CMD_EXECUTE,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .doit = ovs_packet_cmd_execute
 	}
@@ -1424,19 +1425,23 @@ static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
 
 static const struct genl_ops dp_flow_genl_ops[] = {
 	{ .cmd = OVS_FLOW_CMD_NEW,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .doit = ovs_flow_cmd_new
 	},
 	{ .cmd = OVS_FLOW_CMD_DEL,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .doit = ovs_flow_cmd_del
 	},
 	{ .cmd = OVS_FLOW_CMD_GET,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = 0,		    /* OK for unprivileged users. */
 	  .doit = ovs_flow_cmd_get,
 	  .dumpit = ovs_flow_cmd_dump
 	},
 	{ .cmd = OVS_FLOW_CMD_SET,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .doit = ovs_flow_cmd_set,
 	},
@@ -1814,19 +1819,23 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
 
 static const struct genl_ops dp_datapath_genl_ops[] = {
 	{ .cmd = OVS_DP_CMD_NEW,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .doit = ovs_dp_cmd_new
 	},
 	{ .cmd = OVS_DP_CMD_DEL,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .doit = ovs_dp_cmd_del
 	},
 	{ .cmd = OVS_DP_CMD_GET,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = 0,		    /* OK for unprivileged users. */
 	  .doit = ovs_dp_cmd_get,
 	  .dumpit = ovs_dp_cmd_dump
 	},
 	{ .cmd = OVS_DP_CMD_SET,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .doit = ovs_dp_cmd_set,
 	},
@@ -2254,19 +2263,23 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 
 static const struct genl_ops dp_vport_genl_ops[] = {
 	{ .cmd = OVS_VPORT_CMD_NEW,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .doit = ovs_vport_cmd_new
 	},
 	{ .cmd = OVS_VPORT_CMD_DEL,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .doit = ovs_vport_cmd_del
 	},
 	{ .cmd = OVS_VPORT_CMD_GET,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = 0,		    /* OK for unprivileged users. */
 	  .doit = ovs_vport_cmd_get,
 	  .dumpit = ovs_vport_cmd_dump
 	},
 	{ .cmd = OVS_VPORT_CMD_SET,
+	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .doit = ovs_vport_cmd_set,
 	},
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 9c89e8539a5a..bb67238f0340 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -526,20 +526,24 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
 
 static struct genl_ops dp_meter_genl_ops[] = {
 	{ .cmd = OVS_METER_CMD_FEATURES,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = 0,		  /* OK for unprivileged users. */
 		.doit = ovs_meter_cmd_features
 	},
 	{ .cmd = OVS_METER_CMD_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
 					   *  privilege.
 					   */
 		.doit = ovs_meter_cmd_set,
 	},
 	{ .cmd = OVS_METER_CMD_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = 0,		  /* OK for unprivileged users. */
 		.doit = ovs_meter_cmd_get,
 	},
 	{ .cmd = OVS_METER_CMD_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
 					   *  privilege.
 					   */
diff --git a/net/psample/psample.c b/net/psample/psample.c
index 64f95624f219..a107b2405668 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -100,6 +100,7 @@ static int psample_nl_cmd_get_group_dumpit(struct sk_buff *msg,
 static const struct genl_ops psample_nl_ops[] = {
 	{
 		.cmd = PSAMPLE_CMD_GET_GROUP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit = psample_nl_cmd_get_group_dumpit,
 		/* can be retrieved by unprivileged users */
 	}
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 9f5d8f36f2d7..bab2da8cf17a 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -612,6 +612,7 @@ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info)
 static const struct genl_ops smc_pnet_ops[] = {
 	{
 		.cmd = SMC_PNETID_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = smc_pnet_get,
 		.dumpit = smc_pnet_dump,
@@ -619,16 +620,19 @@ static const struct genl_ops smc_pnet_ops[] = {
 	},
 	{
 		.cmd = SMC_PNETID_ADD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = smc_pnet_add
 	},
 	{
 		.cmd = SMC_PNETID_DEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = smc_pnet_del
 	},
 	{
 		.cmd = SMC_PNETID_FLUSH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = smc_pnet_flush
 	}
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index 3d5d0fb5b37c..99bd166bccec 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -143,93 +143,114 @@ const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = {
 static const struct genl_ops tipc_genl_v2_ops[] = {
 	{
 		.cmd	= TIPC_NL_BEARER_DISABLE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_bearer_disable,
 	},
 	{
 		.cmd	= TIPC_NL_BEARER_ENABLE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_bearer_enable,
 	},
 	{
 		.cmd	= TIPC_NL_BEARER_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_bearer_get,
 		.dumpit	= tipc_nl_bearer_dump,
 	},
 	{
 		.cmd	= TIPC_NL_BEARER_ADD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_bearer_add,
 	},
 	{
 		.cmd	= TIPC_NL_BEARER_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_bearer_set,
 	},
 	{
 		.cmd	= TIPC_NL_SOCK_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.start = tipc_dump_start,
 		.dumpit	= tipc_nl_sk_dump,
 		.done	= tipc_dump_done,
 	},
 	{
 		.cmd	= TIPC_NL_PUBL_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit	= tipc_nl_publ_dump,
 	},
 	{
 		.cmd	= TIPC_NL_LINK_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit   = tipc_nl_node_get_link,
 		.dumpit	= tipc_nl_node_dump_link,
 	},
 	{
 		.cmd	= TIPC_NL_LINK_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_node_set_link,
 	},
 	{
 		.cmd	= TIPC_NL_LINK_RESET_STATS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit   = tipc_nl_node_reset_link_stats,
 	},
 	{
 		.cmd	= TIPC_NL_MEDIA_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_media_get,
 		.dumpit	= tipc_nl_media_dump,
 	},
 	{
 		.cmd	= TIPC_NL_MEDIA_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_media_set,
 	},
 	{
 		.cmd	= TIPC_NL_NODE_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit	= tipc_nl_node_dump,
 	},
 	{
 		.cmd	= TIPC_NL_NET_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit	= tipc_nl_net_dump,
 	},
 	{
 		.cmd	= TIPC_NL_NET_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_net_set,
 	},
 	{
 		.cmd	= TIPC_NL_NAME_TABLE_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit	= tipc_nl_name_table_dump,
 	},
 	{
 		.cmd	= TIPC_NL_MON_SET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_node_set_monitor,
 	},
 	{
 		.cmd	= TIPC_NL_MON_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_node_get_monitor,
 		.dumpit	= tipc_nl_node_dump_monitor,
 	},
 	{
 		.cmd	= TIPC_NL_MON_PEER_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit	= tipc_nl_node_dump_monitor_peer,
 	},
 	{
 		.cmd	= TIPC_NL_PEER_REMOVE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit	= tipc_nl_peer_rm,
 	},
 #ifdef CONFIG_TIPC_MEDIA_UDP
 	{
 		.cmd	= TIPC_NL_UDP_GET_REMOTEIP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit	= tipc_udp_nl_dump_remoteip,
 	},
 #endif
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index f7269ce934b5..c6a04c09d075 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -1305,6 +1305,7 @@ send:
 static const struct genl_ops tipc_genl_compat_ops[] = {
 	{
 		.cmd		= TIPC_GENL_CMD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit		= tipc_nl_compat_recv,
 	},
 };
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
index b7f571e55448..4969de672886 100644
--- a/net/wimax/stack.c
+++ b/net/wimax/stack.c
@@ -419,21 +419,25 @@ static const struct nla_policy wimax_gnl_policy[WIMAX_GNL_ATTR_MAX + 1] = {
 static const struct genl_ops wimax_gnl_ops[] = {
 	{
 		.cmd = WIMAX_GNL_OP_MSG_FROM_USER,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = wimax_gnl_doit_msg_from_user,
 	},
 	{
 		.cmd = WIMAX_GNL_OP_RESET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = wimax_gnl_doit_reset,
 	},
 	{
 		.cmd = WIMAX_GNL_OP_RFKILL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = wimax_gnl_doit_rfkill,
 	},
 	{
 		.cmd = WIMAX_GNL_OP_STATE_GET,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM,
 		.doit = wimax_gnl_doit_state_get,
 	},
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 782c8225a90a..fffe4b371e23 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -13591,6 +13591,7 @@ static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
 static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_GET_WIPHY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_wiphy,
 		.dumpit = nl80211_dump_wiphy,
 		.done = nl80211_dump_wiphy_done,
@@ -13600,12 +13601,14 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_WIPHY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_wiphy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_GET_INTERFACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_interface,
 		.dumpit = nl80211_dump_interface,
 		/* can be retrieved by unprivileged users */
@@ -13614,6 +13617,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_INTERFACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_interface,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -13621,6 +13625,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_NEW_INTERFACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_new_interface,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
@@ -13628,6 +13633,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DEL_INTERFACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_del_interface,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
@@ -13635,6 +13641,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_KEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_key,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13642,6 +13649,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_KEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_key,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13650,6 +13658,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_NEW_KEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_new_key,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13658,6 +13667,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DEL_KEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_del_key,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13665,6 +13675,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_BEACON,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_set_beacon,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13672,6 +13683,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_START_AP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_start_ap,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13679,6 +13691,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_STOP_AP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.doit = nl80211_stop_ap,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13686,6 +13699,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_STATION,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_station,
 		.dumpit = nl80211_dump_station,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -13693,6 +13707,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_STATION,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_station,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13700,6 +13715,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_NEW_STATION,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_new_station,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13707,6 +13723,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DEL_STATION,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_del_station,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13714,6 +13731,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_MPATH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_mpath,
 		.dumpit = nl80211_dump_mpath,
 		.flags = GENL_UNS_ADMIN_PERM,
@@ -13722,6 +13740,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_MPP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_mpp,
 		.dumpit = nl80211_dump_mpp,
 		.flags = GENL_UNS_ADMIN_PERM,
@@ -13730,6 +13749,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_MPATH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_mpath,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13737,6 +13757,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_NEW_MPATH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_new_mpath,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13744,6 +13765,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DEL_MPATH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_del_mpath,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13751,6 +13773,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_BSS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_bss,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13758,6 +13781,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_REG,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_reg_do,
 		.dumpit = nl80211_get_reg_dump,
 		.internal_flags = NL80211_FLAG_NEED_RTNL,
@@ -13766,6 +13790,7 @@ static const struct genl_ops nl80211_ops[] = {
 #ifdef CONFIG_CFG80211_CRDA_SUPPORT
 	{
 		.cmd = NL80211_CMD_SET_REG,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_reg,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_RTNL,
@@ -13773,16 +13798,19 @@ static const struct genl_ops nl80211_ops[] = {
 #endif
 	{
 		.cmd = NL80211_CMD_REQ_SET_REG,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_req_set_reg,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NL80211_CMD_RELOAD_REGDB,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_reload_regdb,
 		.flags = GENL_ADMIN_PERM,
 	},
 	{
 		.cmd = NL80211_CMD_GET_MESH_CONFIG,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_mesh_config,
 		/* can be retrieved by unprivileged users */
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13790,6 +13818,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_MESH_CONFIG,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_update_mesh_config,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13797,6 +13826,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_TRIGGER_SCAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_trigger_scan,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -13804,6 +13834,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_ABORT_SCAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_abort_scan,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -13811,10 +13842,12 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_SCAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit = nl80211_dump_scan,
 	},
 	{
 		.cmd = NL80211_CMD_START_SCHED_SCAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_start_sched_scan,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13822,6 +13855,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_STOP_SCHED_SCAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_stop_sched_scan,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13829,6 +13863,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_AUTHENTICATE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_authenticate,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13837,6 +13872,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_ASSOCIATE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_associate,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13845,6 +13881,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DEAUTHENTICATE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_deauthenticate,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13852,6 +13889,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DISASSOCIATE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_disassociate,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13859,6 +13897,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_JOIN_IBSS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_join_ibss,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13866,6 +13905,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_LEAVE_IBSS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_leave_ibss,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13874,6 +13914,7 @@ static const struct genl_ops nl80211_ops[] = {
 #ifdef CONFIG_NL80211_TESTMODE
 	{
 		.cmd = NL80211_CMD_TESTMODE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_testmode_do,
 		.dumpit = nl80211_testmode_dump,
 		.flags = GENL_UNS_ADMIN_PERM,
@@ -13883,6 +13924,7 @@ static const struct genl_ops nl80211_ops[] = {
 #endif
 	{
 		.cmd = NL80211_CMD_CONNECT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_connect,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13891,6 +13933,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_update_connect_params,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13899,6 +13942,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DISCONNECT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_disconnect,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13906,6 +13950,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_WIPHY_NETNS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_wiphy_netns,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
@@ -13913,10 +13958,12 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_SURVEY,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.dumpit = nl80211_dump_survey,
 	},
 	{
 		.cmd = NL80211_CMD_SET_PMKSA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_setdel_pmksa,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13925,6 +13972,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DEL_PMKSA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_setdel_pmksa,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13932,6 +13980,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_FLUSH_PMKSA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_flush_pmksa,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -13939,6 +13988,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_REMAIN_ON_CHANNEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_remain_on_channel,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -13946,6 +13996,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_cancel_remain_on_channel,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -13953,6 +14004,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_TX_BITRATE_MASK,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_tx_bitrate_mask,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -13960,6 +14012,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_REGISTER_FRAME,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_register_mgmt,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
@@ -13967,6 +14020,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_FRAME,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_tx_mgmt,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -13974,6 +14028,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_FRAME_WAIT_CANCEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_tx_mgmt_cancel_wait,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -13981,6 +14036,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_POWER_SAVE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_power_save,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -13988,6 +14044,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_POWER_SAVE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_power_save,
 		/* can be retrieved by unprivileged users */
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -13995,6 +14052,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_CQM,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_cqm,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -14002,6 +14060,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_CHANNEL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_channel,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -14009,6 +14068,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_WDS_PEER,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_wds_peer,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -14016,6 +14076,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_JOIN_MESH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_join_mesh,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14023,6 +14084,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_LEAVE_MESH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_leave_mesh,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14030,6 +14092,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_JOIN_OCB,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_join_ocb,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14037,6 +14100,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_LEAVE_OCB,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_leave_ocb,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14045,6 +14109,7 @@ static const struct genl_ops nl80211_ops[] = {
 #ifdef CONFIG_PM
 	{
 		.cmd = NL80211_CMD_GET_WOWLAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_wowlan,
 		/* can be retrieved by unprivileged users */
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
@@ -14052,6 +14117,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_WOWLAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_wowlan,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
@@ -14060,6 +14126,7 @@ static const struct genl_ops nl80211_ops[] = {
 #endif
 	{
 		.cmd = NL80211_CMD_SET_REKEY_OFFLOAD,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_rekey_data,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14068,6 +14135,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_TDLS_MGMT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_tdls_mgmt,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14075,6 +14143,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_TDLS_OPER,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_tdls_oper,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14082,6 +14151,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_UNEXPECTED_FRAME,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_register_unexpected_frame,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -14089,6 +14159,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_PROBE_CLIENT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_probe_client,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14096,6 +14167,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_REGISTER_BEACONS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_register_beacons,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
@@ -14103,6 +14175,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_NOACK_MAP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_noack_map,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -14110,6 +14183,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_START_P2P_DEVICE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_start_p2p_device,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
@@ -14117,6 +14191,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_STOP_P2P_DEVICE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_stop_p2p_device,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -14124,6 +14199,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_START_NAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_start_nan,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV |
@@ -14131,6 +14207,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_STOP_NAN,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_stop_nan,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -14138,6 +14215,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_ADD_NAN_FUNCTION,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_nan_add_func,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -14145,6 +14223,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DEL_NAN_FUNCTION,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_nan_del_func,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -14152,6 +14231,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_CHANGE_NAN_CONFIG,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_nan_change_config,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -14159,6 +14239,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_MCAST_RATE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_mcast_rate,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -14166,6 +14247,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_MAC_ACL,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_mac_acl,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -14173,6 +14255,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_RADAR_DETECT,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_start_radar_detection,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14180,10 +14263,12 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_PROTOCOL_FEATURES,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_protocol_features,
 	},
 	{
 		.cmd = NL80211_CMD_UPDATE_FT_IES,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_update_ft_ies,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14191,6 +14276,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_CRIT_PROTOCOL_START,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_crit_protocol_start,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -14198,6 +14284,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_CRIT_PROTOCOL_STOP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_crit_protocol_stop,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -14205,12 +14292,14 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_COALESCE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_coalesce,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_SET_COALESCE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_coalesce,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
@@ -14218,6 +14307,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_CHANNEL_SWITCH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_channel_switch,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14225,6 +14315,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_VENDOR,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_vendor_cmd,
 		.dumpit = nl80211_vendor_cmd_dump,
 		.flags = GENL_UNS_ADMIN_PERM,
@@ -14234,6 +14325,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_QOS_MAP,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_qos_map,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14241,6 +14333,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_ADD_TX_TS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_add_tx_ts,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14248,6 +14341,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DEL_TX_TS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_del_tx_ts,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14255,6 +14349,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_TDLS_CHANNEL_SWITCH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_tdls_channel_switch,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14262,6 +14357,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_tdls_cancel_channel_switch,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14269,6 +14365,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_MULTICAST_TO_UNICAST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_multicast_to_unicast,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
@@ -14276,6 +14373,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_SET_PMK,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_set_pmk,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL |
@@ -14283,12 +14381,14 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_DEL_PMK,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_del_pmk,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_EXTERNAL_AUTH,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_external_auth,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14296,6 +14396,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_CONTROL_PORT_FRAME,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_tx_control_port,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
@@ -14303,12 +14404,14 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_FTM_RESPONDER_STATS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_get_ftm_responder_stats,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
 		.cmd = NL80211_CMD_PEER_MEASUREMENT_START,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_pmsr_start,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WDEV_UP |
@@ -14316,6 +14419,7 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_NOTIFY_RADAR,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_notify_radar_detection,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
-- 
cgit v1.2.3


From 875138f81d71af3cfa80df57e32fe9efbc4f95bc Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 28 Apr 2019 19:37:11 +0200
Subject: dsa: Move tagger name into its ops structure

Rather than keep a list to map a tagger ops to a name, place the name
into the ops structure. This removes the hard coded list, a step
towards making the taggers more dynamic.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>

v2:
Move name to end of structure, keeping the hot entries at the beginning.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h     |  1 +
 net/dsa/dsa.c         | 45 ++-------------------------------------------
 net/dsa/tag_brcm.c    |  2 ++
 net/dsa/tag_dsa.c     |  1 +
 net/dsa/tag_edsa.c    |  1 +
 net/dsa/tag_gswip.c   |  1 +
 net/dsa/tag_ksz.c     |  2 ++
 net/dsa/tag_lan9303.c |  1 +
 net/dsa/tag_mtk.c     |  1 +
 net/dsa/tag_qca.c     |  1 +
 net/dsa/tag_trailer.c |  1 +
 11 files changed, 14 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 0cfc2f828b87..801346e31e9b 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -56,6 +56,7 @@ struct dsa_device_ops {
 	int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto,
 			    int *offset);
 	unsigned int overhead;
+	const char *name;
 };
 
 struct dsa_switch_tree {
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 36de4f2a3366..92b3cd129eb7 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -35,6 +35,7 @@ static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb,
 }
 
 static const struct dsa_device_ops none_ops = {
+	.name	= "none",
 	.xmit	= dsa_slave_notag_xmit,
 	.rcv	= NULL,
 };
@@ -76,49 +77,7 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
 
 const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops)
 {
-	const char *protocol_name[DSA_TAG_LAST] = {
-#ifdef CONFIG_NET_DSA_TAG_BRCM
-		[DSA_TAG_PROTO_BRCM] = "brcm",
-#endif
-#ifdef CONFIG_NET_DSA_TAG_BRCM_PREPEND
-		[DSA_TAG_PROTO_BRCM_PREPEND] = "brcm-prepend",
-#endif
-#ifdef CONFIG_NET_DSA_TAG_DSA
-		[DSA_TAG_PROTO_DSA] = "dsa",
-#endif
-#ifdef CONFIG_NET_DSA_TAG_EDSA
-		[DSA_TAG_PROTO_EDSA] = "edsa",
-#endif
-#ifdef CONFIG_NET_DSA_TAG_GSWIP
-		[DSA_TAG_PROTO_GSWIP] = "gswip",
-#endif
-#ifdef CONFIG_NET_DSA_TAG_KSZ9477
-		[DSA_TAG_PROTO_KSZ9477] = "ksz9477",
-		[DSA_TAG_PROTO_KSZ9893] = "ksz9893",
-#endif
-#ifdef CONFIG_NET_DSA_TAG_LAN9303
-		[DSA_TAG_PROTO_LAN9303] = "lan9303",
-#endif
-#ifdef CONFIG_NET_DSA_TAG_MTK
-		[DSA_TAG_PROTO_MTK] = "mtk",
-#endif
-#ifdef CONFIG_NET_DSA_TAG_QCA
-		[DSA_TAG_PROTO_QCA] = "qca",
-#endif
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
-		[DSA_TAG_PROTO_TRAILER] = "trailer",
-#endif
-		[DSA_TAG_PROTO_NONE] = "none",
-	};
-	unsigned int i;
-
-	BUILD_BUG_ON(ARRAY_SIZE(protocol_name) != DSA_TAG_LAST);
-
-	for (i = 0; i < ARRAY_SIZE(dsa_device_ops); i++)
-		if (ops == dsa_device_ops[i])
-			return protocol_name[i];
-
-	return protocol_name[DSA_TAG_PROTO_NONE];
+	return ops->name;
 };
 
 const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol)
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index b3063e7adb73..1b7dfbe6b3ae 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -168,6 +168,7 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 }
 
 const struct dsa_device_ops brcm_netdev_ops = {
+	.name	= "brcm",
 	.xmit	= brcm_tag_xmit,
 	.rcv	= brcm_tag_rcv,
 	.overhead = BRCM_TAG_LEN,
@@ -191,6 +192,7 @@ static struct sk_buff *brcm_tag_rcv_prepend(struct sk_buff *skb,
 }
 
 const struct dsa_device_ops brcm_prepend_netdev_ops = {
+	.name	= "brcm-prepend",
 	.xmit	= brcm_tag_xmit_prepend,
 	.rcv	= brcm_tag_rcv_prepend,
 	.overhead = BRCM_TAG_LEN,
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index fdaf850831e2..e1c90709de6c 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -151,6 +151,7 @@ static int dsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 }
 
 const struct dsa_device_ops dsa_netdev_ops = {
+	.name	= "dsa",
 	.xmit	= dsa_xmit,
 	.rcv	= dsa_rcv,
 	.flow_dissect   = dsa_tag_flow_dissect,
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index df879445f658..b936b4660b71 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -170,6 +170,7 @@ static int edsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 }
 
 const struct dsa_device_ops edsa_netdev_ops = {
+	.name	= "edsa",
 	.xmit	= edsa_xmit,
 	.rcv	= edsa_rcv,
 	.flow_dissect   = edsa_tag_flow_dissect,
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index cb6f82ffe5eb..d1c1e7db87b6 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -104,6 +104,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb,
 }
 
 const struct dsa_device_ops gswip_netdev_ops = {
+	.name = "gwsip",
 	.xmit = gswip_tag_xmit,
 	.rcv = gswip_tag_rcv,
 	.overhead = GSWIP_RX_HEADER_LEN,
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 12b2f58786ee..631094599514 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -134,6 +134,7 @@ static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev,
 }
 
 const struct dsa_device_ops ksz9477_netdev_ops = {
+	.name	= "ksz9477",
 	.xmit	= ksz9477_xmit,
 	.rcv	= ksz9477_rcv,
 	.overhead = KSZ9477_INGRESS_TAG_LEN,
@@ -167,6 +168,7 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb,
 }
 
 const struct dsa_device_ops ksz9893_netdev_ops = {
+	.name	= "ksz9893",
 	.xmit	= ksz9893_xmit,
 	.rcv	= ksz9477_rcv,
 	.overhead = KSZ_INGRESS_TAG_LEN,
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index 7bfd3165e46e..67d70339536d 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -129,6 +129,7 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev,
 }
 
 const struct dsa_device_ops lan9303_netdev_ops = {
+	.name = "lan9303",
 	.xmit = lan9303_xmit,
 	.rcv = lan9303_rcv,
 	.overhead = LAN9303_TAG_LEN,
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index 6e06fa621bbc..dc537d9a18c0 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -99,6 +99,7 @@ static int mtk_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 }
 
 const struct dsa_device_ops mtk_netdev_ops = {
+	.name		= "mtk",
 	.xmit		= mtk_tag_xmit,
 	.rcv		= mtk_tag_rcv,
 	.flow_dissect	= mtk_tag_flow_dissect,
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index de3eb1022e21..f62296ffc5b7 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -100,6 +100,7 @@ static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 }
 
 const struct dsa_device_ops qca_netdev_ops = {
+	.name	= "qca",
 	.xmit	= qca_tag_xmit,
 	.rcv	= qca_tag_rcv,
 	.flow_dissect = qca_tag_flow_dissect,
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 492a30046281..20ee7f84fe4d 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -78,6 +78,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
 }
 
 const struct dsa_device_ops trailer_netdev_ops = {
+	.name	= "trailer",
 	.xmit	= trailer_xmit,
 	.rcv	= trailer_rcv,
 	.overhead = 4,
-- 
cgit v1.2.3


From 0b42f03363706609d621c31324fae5c1250f579f Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 28 Apr 2019 19:37:12 +0200
Subject: dsa: Add MODULE_ALIAS to taggers in preparation to become modules

When the tag drivers become modules, we will need to dynamically load
them based on what the switch drivers need. Add aliases to map between
the TAG protocol and the driver.

In order to do this, we need the tag protocol number as something
which the C pre-processor can stringinfy. Only the compiler knows the
value of an enum, CPP cannot use them. So add #defines.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h     | 43 ++++++++++++++++++++++++++++++-------------
 net/dsa/tag_brcm.c    |  4 ++++
 net/dsa/tag_dsa.c     |  2 ++
 net/dsa/tag_edsa.c    |  2 ++
 net/dsa/tag_gswip.c   |  2 ++
 net/dsa/tag_ksz.c     |  4 ++++
 net/dsa/tag_lan9303.c |  2 ++
 net/dsa/tag_mtk.c     |  2 ++
 net/dsa/tag_qca.c     |  2 ++
 net/dsa/tag_trailer.c |  2 ++
 10 files changed, 52 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 801346e31e9b..8f3d5e0825a2 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -30,20 +30,33 @@ struct phy_device;
 struct fixed_phy_status;
 struct phylink_link_state;
 
+#define DSA_TAG_PROTO_NONE_VALUE		0
+#define DSA_TAG_PROTO_BRCM_VALUE		1
+#define DSA_TAG_PROTO_BRCM_PREPEND_VALUE	2
+#define DSA_TAG_PROTO_DSA_VALUE			3
+#define DSA_TAG_PROTO_EDSA_VALUE		4
+#define DSA_TAG_PROTO_GSWIP_VALUE		5
+#define DSA_TAG_PROTO_KSZ9477_VALUE		6
+#define DSA_TAG_PROTO_KSZ9893_VALUE		7
+#define DSA_TAG_PROTO_LAN9303_VALUE		8
+#define DSA_TAG_PROTO_MTK_VALUE			9
+#define DSA_TAG_PROTO_QCA_VALUE			10
+#define DSA_TAG_PROTO_TRAILER_VALUE		11
+
 enum dsa_tag_protocol {
-	DSA_TAG_PROTO_NONE = 0,
-	DSA_TAG_PROTO_BRCM,
-	DSA_TAG_PROTO_BRCM_PREPEND,
-	DSA_TAG_PROTO_DSA,
-	DSA_TAG_PROTO_EDSA,
-	DSA_TAG_PROTO_GSWIP,
-	DSA_TAG_PROTO_KSZ9477,
-	DSA_TAG_PROTO_KSZ9893,
-	DSA_TAG_PROTO_LAN9303,
-	DSA_TAG_PROTO_MTK,
-	DSA_TAG_PROTO_QCA,
-	DSA_TAG_PROTO_TRAILER,
-	DSA_TAG_LAST,		/* MUST BE LAST */
+	DSA_TAG_PROTO_NONE		= DSA_TAG_PROTO_NONE_VALUE,
+	DSA_TAG_PROTO_BRCM		= DSA_TAG_PROTO_BRCM_VALUE,
+	DSA_TAG_PROTO_BRCM_PREPEND	= DSA_TAG_PROTO_BRCM_PREPEND_VALUE,
+	DSA_TAG_PROTO_DSA		= DSA_TAG_PROTO_DSA_VALUE,
+	DSA_TAG_PROTO_EDSA		= DSA_TAG_PROTO_EDSA_VALUE,
+	DSA_TAG_PROTO_GSWIP		= DSA_TAG_PROTO_GSWIP_VALUE,
+	DSA_TAG_PROTO_KSZ9477		= DSA_TAG_PROTO_KSZ9477_VALUE,
+	DSA_TAG_PROTO_KSZ9893		= DSA_TAG_PROTO_KSZ9893_VALUE,
+	DSA_TAG_PROTO_LAN9303		= DSA_TAG_PROTO_LAN9303_VALUE,
+	DSA_TAG_PROTO_MTK		= DSA_TAG_PROTO_MTK_VALUE,
+	DSA_TAG_PROTO_QCA		= DSA_TAG_PROTO_QCA_VALUE,
+	DSA_TAG_PROTO_TRAILER		= DSA_TAG_PROTO_TRAILER_VALUE,
+	DSA_TAG_LAST,			/* MUST BE LAST */
 };
 
 struct packet_type;
@@ -59,6 +72,10 @@ struct dsa_device_ops {
 	const char *name;
 };
 
+#define DSA_TAG_DRIVER_ALIAS "dsa_tag-"
+#define MODULE_ALIAS_DSA_TAG_DRIVER(__proto)				\
+	MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __stringify(__proto##_VALUE))
+
 struct dsa_switch_tree {
 	struct list_head	list;
 
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 1b7dfbe6b3ae..24d8f45a7e6f 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -173,6 +173,8 @@ const struct dsa_device_ops brcm_netdev_ops = {
 	.rcv	= brcm_tag_rcv,
 	.overhead = BRCM_TAG_LEN,
 };
+
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM);
 #endif
 
 #ifdef CONFIG_NET_DSA_TAG_BRCM_PREPEND
@@ -198,3 +200,5 @@ const struct dsa_device_ops brcm_prepend_netdev_ops = {
 	.overhead = BRCM_TAG_LEN,
 };
 #endif
+
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_PREPEND);
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index e1c90709de6c..8aefaf96c1ca 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -157,3 +157,5 @@ const struct dsa_device_ops dsa_netdev_ops = {
 	.flow_dissect   = dsa_tag_flow_dissect,
 	.overhead = DSA_HLEN,
 };
+
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_DSA);
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index b936b4660b71..bad12e760f3d 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -176,3 +176,5 @@ const struct dsa_device_ops edsa_netdev_ops = {
 	.flow_dissect   = edsa_tag_flow_dissect,
 	.overhead = EDSA_HLEN,
 };
+
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA);
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index d1c1e7db87b6..30bf7036620f 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -109,3 +109,5 @@ const struct dsa_device_ops gswip_netdev_ops = {
 	.rcv = gswip_tag_rcv,
 	.overhead = GSWIP_RX_HEADER_LEN,
 };
+
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_GSWIP);
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 631094599514..9be0f5f12afb 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -140,6 +140,8 @@ const struct dsa_device_ops ksz9477_netdev_ops = {
 	.overhead = KSZ9477_INGRESS_TAG_LEN,
 };
 
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9477);
+
 #define KSZ9893_TAIL_TAG_OVERRIDE	BIT(5)
 #define KSZ9893_TAIL_TAG_LOOKUP		BIT(6)
 
@@ -173,3 +175,5 @@ const struct dsa_device_ops ksz9893_netdev_ops = {
 	.rcv	= ksz9477_rcv,
 	.overhead = KSZ_INGRESS_TAG_LEN,
 };
+
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9893);
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index 67d70339536d..48bca20024d4 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -134,3 +134,5 @@ const struct dsa_device_ops lan9303_netdev_ops = {
 	.rcv = lan9303_rcv,
 	.overhead = LAN9303_TAG_LEN,
 };
+
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_LAN9303);
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index dc537d9a18c0..23210a65cbed 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -105,3 +105,5 @@ const struct dsa_device_ops mtk_netdev_ops = {
 	.flow_dissect	= mtk_tag_flow_dissect,
 	.overhead	= MTK_HDR_LEN,
 };
+
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_MTK);
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index f62296ffc5b7..7d9cb178da3d 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -106,3 +106,5 @@ const struct dsa_device_ops qca_netdev_ops = {
 	.flow_dissect = qca_tag_flow_dissect,
 	.overhead = QCA_HDR_LEN,
 };
+
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_QCA);
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 20ee7f84fe4d..00d521cf9c48 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -83,3 +83,5 @@ const struct dsa_device_ops trailer_netdev_ops = {
 	.rcv	= trailer_rcv,
 	.overhead = 4,
 };
+
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_TRAILER);
-- 
cgit v1.2.3


From 056eed2fb071c11535527fc792bdfb985a9a3e26 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 28 Apr 2019 19:37:14 +0200
Subject: dsa: Add TAG protocol to tag ops

In order that we can match the tagging protocol a switch driver
request to the tagger, we need to know what protocol the tagger
supports. Add this information to the ops structure.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>

v2
More tag protocol to end of structure to keep hot members at the beginning.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h     | 1 +
 net/dsa/dsa.c         | 1 +
 net/dsa/tag_brcm.c    | 2 ++
 net/dsa/tag_dsa.c     | 1 +
 net/dsa/tag_edsa.c    | 1 +
 net/dsa/tag_gswip.c   | 1 +
 net/dsa/tag_ksz.c     | 2 ++
 net/dsa/tag_lan9303.c | 1 +
 net/dsa/tag_mtk.c     | 1 +
 net/dsa/tag_qca.c     | 1 +
 net/dsa/tag_trailer.c | 1 +
 11 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 8f3d5e0825a2..720036f48fb3 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -70,6 +70,7 @@ struct dsa_device_ops {
 			    int *offset);
 	unsigned int overhead;
 	const char *name;
+	enum dsa_tag_protocol proto;
 };
 
 #define DSA_TAG_DRIVER_ALIAS "dsa_tag-"
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 92b3cd129eb7..2da733dff86b 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -36,6 +36,7 @@ static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb,
 
 static const struct dsa_device_ops none_ops = {
 	.name	= "none",
+	.proto	= DSA_TAG_PROTO_NONE,
 	.xmit	= dsa_slave_notag_xmit,
 	.rcv	= NULL,
 };
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 59421f9e96de..39b380485e5a 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -169,6 +169,7 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 
 const struct dsa_device_ops brcm_netdev_ops = {
 	.name	= "brcm",
+	.proto	= DSA_TAG_PROTO_BRCM,
 	.xmit	= brcm_tag_xmit,
 	.rcv	= brcm_tag_rcv,
 	.overhead = BRCM_TAG_LEN,
@@ -195,6 +196,7 @@ static struct sk_buff *brcm_tag_rcv_prepend(struct sk_buff *skb,
 
 const struct dsa_device_ops brcm_prepend_netdev_ops = {
 	.name	= "brcm-prepend",
+	.proto	= DSA_TAG_PROTO_BRCM_PREPEND,
 	.xmit	= brcm_tag_xmit_prepend,
 	.rcv	= brcm_tag_rcv_prepend,
 	.overhead = BRCM_TAG_LEN,
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index b8f3236db877..ec9b66c11219 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -152,6 +152,7 @@ static int dsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 
 const struct dsa_device_ops dsa_netdev_ops = {
 	.name	= "dsa",
+	.proto	= DSA_TAG_PROTO_DSA,
 	.xmit	= dsa_xmit,
 	.rcv	= dsa_rcv,
 	.flow_dissect   = dsa_tag_flow_dissect,
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index c4fddf7292cf..866d4e684511 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -171,6 +171,7 @@ static int edsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 
 const struct dsa_device_ops edsa_netdev_ops = {
 	.name	= "edsa",
+	.proto	= DSA_TAG_PROTO_EDSA,
 	.xmit	= edsa_xmit,
 	.rcv	= edsa_rcv,
 	.flow_dissect   = edsa_tag_flow_dissect,
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index 6a7ff063b6e0..192156373108 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -105,6 +105,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb,
 
 const struct dsa_device_ops gswip_netdev_ops = {
 	.name = "gwsip",
+	.proto	= DSA_TAG_PROTO_GSWIP,
 	.xmit = gswip_tag_xmit,
 	.rcv = gswip_tag_rcv,
 	.overhead = GSWIP_RX_HEADER_LEN,
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 6d78d88270fc..5f5c8f9a6141 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -135,6 +135,7 @@ static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev,
 
 const struct dsa_device_ops ksz9477_netdev_ops = {
 	.name	= "ksz9477",
+	.proto	= DSA_TAG_PROTO_KSZ9477,
 	.xmit	= ksz9477_xmit,
 	.rcv	= ksz9477_rcv,
 	.overhead = KSZ9477_INGRESS_TAG_LEN,
@@ -171,6 +172,7 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb,
 
 const struct dsa_device_ops ksz9893_netdev_ops = {
 	.name	= "ksz9893",
+	.proto	= DSA_TAG_PROTO_KSZ9893,
 	.xmit	= ksz9893_xmit,
 	.rcv	= ksz9477_rcv,
 	.overhead = KSZ_INGRESS_TAG_LEN,
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index 1f5819e4e687..b6ef1e1a6673 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -130,6 +130,7 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev,
 
 const struct dsa_device_ops lan9303_netdev_ops = {
 	.name = "lan9303",
+	.proto	= DSA_TAG_PROTO_LAN9303,
 	.xmit = lan9303_xmit,
 	.rcv = lan9303_rcv,
 	.overhead = LAN9303_TAG_LEN,
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index 7ecafb569f74..ca02ab3dcd80 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -100,6 +100,7 @@ static int mtk_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 
 const struct dsa_device_ops mtk_netdev_ops = {
 	.name		= "mtk",
+	.proto		= DSA_TAG_PROTO_MTK,
 	.xmit		= mtk_tag_xmit,
 	.rcv		= mtk_tag_rcv,
 	.flow_dissect	= mtk_tag_flow_dissect,
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index f3fdeafef1fe..1ff65c2e0cb4 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -101,6 +101,7 @@ static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 
 const struct dsa_device_ops qca_netdev_ops = {
 	.name	= "qca",
+	.proto	= DSA_TAG_PROTO_QCA,
 	.xmit	= qca_tag_xmit,
 	.rcv	= qca_tag_rcv,
 	.flow_dissect = qca_tag_flow_dissect,
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 9ec6aa7938cc..628ab1a44ed7 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -79,6 +79,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
 
 const struct dsa_device_ops trailer_netdev_ops = {
 	.name	= "trailer",
+	.proto	= DSA_TAG_PROTO_TRAILER,
 	.xmit	= trailer_xmit,
 	.rcv	= trailer_rcv,
 	.overhead = 4,
-- 
cgit v1.2.3


From d3b8c04988ca1685700e345a82a1396df79e6291 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 28 Apr 2019 19:37:15 +0200
Subject: dsa: Add boilerplate helper to register DSA tag driver modules

A DSA tag driver module will need to register the tag protocols it
implements with the DSA core. Add macros containing this boiler plate.

The registration/unregistration code is currently just a stub. A Later
patch will add the real implementation.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>

v2
Fix indent of #endif
Rewrite to move list pointer into a new structure
v3
Move kdoc next to macro
Fix THIS_MODULE indentation

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h     | 66 +++++++++++++++++++++++++++++++++++++++++++++++++++
 net/dsa/dsa.c         | 12 ++++++++++
 net/dsa/tag_brcm.c    | 16 ++++++++++++-
 net/dsa/tag_dsa.c     |  2 ++
 net/dsa/tag_edsa.c    |  2 ++
 net/dsa/tag_gswip.c   |  2 ++
 net/dsa/tag_ksz.c     | 12 +++++++++-
 net/dsa/tag_lan9303.c |  2 ++
 net/dsa/tag_mtk.c     |  2 ++
 net/dsa/tag_qca.c     |  2 ++
 net/dsa/tag_trailer.c |  2 ++
 11 files changed, 118 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 720036f48fb3..08ac05c014e3 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -594,4 +594,70 @@ int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data);
 int dsa_port_get_phy_sset_count(struct dsa_port *dp);
 void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up);
 
+struct dsa_tag_driver {
+	const struct dsa_device_ops *ops;
+	struct list_head list;
+	struct module *owner;
+};
+
+void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[],
+			      unsigned int count,
+			      struct module *owner);
+void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[],
+				unsigned int count);
+
+#define dsa_tag_driver_module_drivers(__dsa_tag_drivers_array, __count)	\
+static int __init dsa_tag_driver_module_init(void)			\
+{									\
+	dsa_tag_drivers_register(__dsa_tag_drivers_array, __count,	\
+				 THIS_MODULE);				\
+	return 0;							\
+}									\
+module_init(dsa_tag_driver_module_init);				\
+									\
+static void __exit dsa_tag_driver_module_exit(void)			\
+{									\
+	dsa_tag_drivers_unregister(__dsa_tag_drivers_array, __count);	\
+}									\
+module_exit(dsa_tag_driver_module_exit)
+
+/**
+ * module_dsa_tag_drivers() - Helper macro for registering DSA tag
+ * drivers
+ * @__ops_array: Array of tag driver strucutres
+ *
+ * Helper macro for DSA tag drivers which do not do anything special
+ * in module init/exit. Each module may only use this macro once, and
+ * calling it replaces module_init() and module_exit().
+ */
+#define module_dsa_tag_drivers(__ops_array)				\
+dsa_tag_driver_module_drivers(__ops_array, ARRAY_SIZE(__ops_array))
+
+#define DSA_TAG_DRIVER_NAME(__ops) dsa_tag_driver ## _ ## __ops
+
+/* Create a static structure we can build a linked list of dsa_tag
+ * drivers
+ */
+#define DSA_TAG_DRIVER(__ops)						\
+static struct dsa_tag_driver DSA_TAG_DRIVER_NAME(__ops) = {		\
+	.ops = &__ops,							\
+}
+
+/**
+ * module_dsa_tag_driver() - Helper macro for registering a single DSA tag
+ * driver
+ * @__ops: Single tag driver structures
+ *
+ * Helper macro for DSA tag drivers which do not do anything special
+ * in module init/exit. Each module may only use this macro once, and
+ * calling it replaces module_init() and module_exit().
+ */
+#define module_dsa_tag_driver(__ops)					\
+DSA_TAG_DRIVER(__ops);							\
+									\
+static struct dsa_tag_driver *dsa_tag_driver_array[] =	{		\
+	&DSA_TAG_DRIVER_NAME(__ops)					\
+};									\
+module_dsa_tag_drivers(dsa_tag_driver_array)
 #endif
+
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 2da733dff86b..34becafbd37b 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -76,6 +76,18 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
 	[DSA_TAG_PROTO_NONE] = &none_ops,
 };
 
+void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[],
+			      unsigned int count, struct module *owner)
+{
+}
+EXPORT_SYMBOL_GPL(dsa_tag_drivers_register);
+
+void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[],
+				unsigned int count)
+{
+}
+EXPORT_SYMBOL_GPL(dsa_tag_drivers_unregister);
+
 const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops)
 {
 	return ops->name;
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 39b380485e5a..63c8c6645a05 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -175,6 +175,7 @@ const struct dsa_device_ops brcm_netdev_ops = {
 	.overhead = BRCM_TAG_LEN,
 };
 
+DSA_TAG_DRIVER(brcm_netdev_ops);
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM);
 #endif
 
@@ -203,5 +204,18 @@ const struct dsa_device_ops brcm_prepend_netdev_ops = {
 };
 #endif
 
-MODULE_LICENSE("GPL");
+DSA_TAG_DRIVER(brcm_prepend_netdev_ops);
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_PREPEND);
+
+static struct dsa_tag_driver *dsa_tag_driver_array[] =	{
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM)
+	&DSA_TAG_DRIVER_NAME(brcm_netdev_ops),
+#endif
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_PREPEND)
+	&DSA_TAG_DRIVER_NAME(brcm_prepend_netdev_ops),
+#endif
+};
+
+module_dsa_tag_drivers(dsa_tag_driver_array);
+
+MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index ec9b66c11219..96b5147b6f3e 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -161,3 +161,5 @@ const struct dsa_device_ops dsa_netdev_ops = {
 
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_DSA);
+
+module_dsa_tag_driver(dsa_netdev_ops);
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 866d4e684511..76bf3db4e9d4 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -180,3 +180,5 @@ const struct dsa_device_ops edsa_netdev_ops = {
 
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA);
+
+module_dsa_tag_driver(edsa_netdev_ops);
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index 192156373108..ee5167180e79 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -113,3 +113,5 @@ const struct dsa_device_ops gswip_netdev_ops = {
 
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_GSWIP);
+
+module_dsa_tag_driver(gswip_netdev_ops);
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 5f5c8f9a6141..02689ac6f9da 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -141,6 +141,7 @@ const struct dsa_device_ops ksz9477_netdev_ops = {
 	.overhead = KSZ9477_INGRESS_TAG_LEN,
 };
 
+DSA_TAG_DRIVER(ksz9477_netdev_ops);
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9477);
 
 #define KSZ9893_TAIL_TAG_OVERRIDE	BIT(5)
@@ -178,5 +179,14 @@ const struct dsa_device_ops ksz9893_netdev_ops = {
 	.overhead = KSZ_INGRESS_TAG_LEN,
 };
 
-MODULE_LICENSE("GPL");
+DSA_TAG_DRIVER(ksz9893_netdev_ops);
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9893);
+
+static struct dsa_tag_driver *dsa_tag_driver_array[] = {
+	&DSA_TAG_DRIVER_NAME(ksz9477_netdev_ops),
+	&DSA_TAG_DRIVER_NAME(ksz9893_netdev_ops),
+};
+
+module_dsa_tag_drivers(dsa_tag_driver_array);
+
+MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index b6ef1e1a6673..609a2405abd8 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -138,3 +138,5 @@ const struct dsa_device_ops lan9303_netdev_ops = {
 
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_LAN9303);
+
+module_dsa_tag_driver(lan9303_netdev_ops);
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index ca02ab3dcd80..a4d2dcdb7102 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -109,3 +109,5 @@ const struct dsa_device_ops mtk_netdev_ops = {
 
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_MTK);
+
+module_dsa_tag_driver(mtk_netdev_ops);
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 1ff65c2e0cb4..552ddfbbf5ec 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -110,3 +110,5 @@ const struct dsa_device_ops qca_netdev_ops = {
 
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_QCA);
+
+module_dsa_tag_driver(qca_netdev_ops);
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 628ab1a44ed7..807cc2dff052 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -87,3 +87,5 @@ const struct dsa_device_ops trailer_netdev_ops = {
 
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_TRAILER);
+
+module_dsa_tag_driver(trailer_netdev_ops);
-- 
cgit v1.2.3


From f81a43e8da07ccd91c4d923a44ffffaeee39dcc8 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 28 Apr 2019 19:37:21 +0200
Subject: dsa: Cleanup unneeded table and make tag structures static

Now that tag drivers dynamically register, we don't need the static
table. Remove it. This also means the tag driver structures can be
made static.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h     |  1 -
 net/dsa/dsa.c         | 35 -----------------------------------
 net/dsa/dsa_priv.h    | 30 ------------------------------
 net/dsa/tag_brcm.c    |  4 ++--
 net/dsa/tag_dsa.c     |  2 +-
 net/dsa/tag_edsa.c    |  2 +-
 net/dsa/tag_gswip.c   |  2 +-
 net/dsa/tag_ksz.c     |  4 ++--
 net/dsa/tag_lan9303.c |  2 +-
 net/dsa/tag_mtk.c     |  2 +-
 net/dsa/tag_qca.c     |  2 +-
 net/dsa/tag_trailer.c |  2 +-
 12 files changed, 11 insertions(+), 77 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 08ac05c014e3..b550f7bb5314 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -56,7 +56,6 @@ enum dsa_tag_protocol {
 	DSA_TAG_PROTO_MTK		= DSA_TAG_PROTO_MTK_VALUE,
 	DSA_TAG_PROTO_QCA		= DSA_TAG_PROTO_QCA_VALUE,
 	DSA_TAG_PROTO_TRAILER		= DSA_TAG_PROTO_TRAILER_VALUE,
-	DSA_TAG_LAST,			/* MUST BE LAST */
 };
 
 struct packet_type;
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 67d21647c500..ba04c78633be 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -46,41 +46,6 @@ static const struct dsa_device_ops none_ops = {
 
 DSA_TAG_DRIVER(none_ops);
 
-const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = {
-#ifdef CONFIG_NET_DSA_TAG_BRCM
-	[DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops,
-#endif
-#ifdef CONFIG_NET_DSA_TAG_BRCM_PREPEND
-	[DSA_TAG_PROTO_BRCM_PREPEND] = &brcm_prepend_netdev_ops,
-#endif
-#ifdef CONFIG_NET_DSA_TAG_DSA
-	[DSA_TAG_PROTO_DSA] = &dsa_netdev_ops,
-#endif
-#ifdef CONFIG_NET_DSA_TAG_EDSA
-	[DSA_TAG_PROTO_EDSA] = &edsa_netdev_ops,
-#endif
-#ifdef CONFIG_NET_DSA_TAG_GSWIP
-	[DSA_TAG_PROTO_GSWIP] = &gswip_netdev_ops,
-#endif
-#ifdef CONFIG_NET_DSA_TAG_KSZ9477
-	[DSA_TAG_PROTO_KSZ9477] = &ksz9477_netdev_ops,
-	[DSA_TAG_PROTO_KSZ9893] = &ksz9893_netdev_ops,
-#endif
-#ifdef CONFIG_NET_DSA_TAG_LAN9303
-	[DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops,
-#endif
-#ifdef CONFIG_NET_DSA_TAG_MTK
-	[DSA_TAG_PROTO_MTK] = &mtk_netdev_ops,
-#endif
-#ifdef CONFIG_NET_DSA_TAG_QCA
-	[DSA_TAG_PROTO_QCA] = &qca_netdev_ops,
-#endif
-#ifdef CONFIG_NET_DSA_TAG_TRAILER
-	[DSA_TAG_PROTO_TRAILER] = &trailer_netdev_ops,
-#endif
-	[DSA_TAG_PROTO_NONE] = &none_ops,
-};
-
 static void dsa_tag_driver_register(struct dsa_tag_driver *dsa_tag_driver,
 				    struct module *owner)
 {
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index ea482e88f7b8..e860512d673a 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -202,34 +202,4 @@ dsa_slave_to_master(const struct net_device *dev)
 /* switch.c */
 int dsa_switch_register_notifier(struct dsa_switch *ds);
 void dsa_switch_unregister_notifier(struct dsa_switch *ds);
-
-/* tag_brcm.c */
-extern const struct dsa_device_ops brcm_netdev_ops;
-extern const struct dsa_device_ops brcm_prepend_netdev_ops;
-
-/* tag_dsa.c */
-extern const struct dsa_device_ops dsa_netdev_ops;
-
-/* tag_edsa.c */
-extern const struct dsa_device_ops edsa_netdev_ops;
-
-/* tag_gswip.c */
-extern const struct dsa_device_ops gswip_netdev_ops;
-
-/* tag_ksz.c */
-extern const struct dsa_device_ops ksz9477_netdev_ops;
-extern const struct dsa_device_ops ksz9893_netdev_ops;
-
-/* tag_lan9303.c */
-extern const struct dsa_device_ops lan9303_netdev_ops;
-
-/* tag_mtk.c */
-extern const struct dsa_device_ops mtk_netdev_ops;
-
-/* tag_qca.c */
-extern const struct dsa_device_ops qca_netdev_ops;
-
-/* tag_trailer.c */
-extern const struct dsa_device_ops trailer_netdev_ops;
-
 #endif
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index 63c8c6645a05..9890097a85d9 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -167,7 +167,7 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	return nskb;
 }
 
-const struct dsa_device_ops brcm_netdev_ops = {
+static const struct dsa_device_ops brcm_netdev_ops = {
 	.name	= "brcm",
 	.proto	= DSA_TAG_PROTO_BRCM,
 	.xmit	= brcm_tag_xmit,
@@ -195,7 +195,7 @@ static struct sk_buff *brcm_tag_rcv_prepend(struct sk_buff *skb,
 	return brcm_tag_rcv_ll(skb, dev, pt, ETH_HLEN);
 }
 
-const struct dsa_device_ops brcm_prepend_netdev_ops = {
+static const struct dsa_device_ops brcm_prepend_netdev_ops = {
 	.name	= "brcm-prepend",
 	.proto	= DSA_TAG_PROTO_BRCM_PREPEND,
 	.xmit	= brcm_tag_xmit_prepend,
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 96b5147b6f3e..7ddec9794477 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -150,7 +150,7 @@ static int dsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 	return 0;
 }
 
-const struct dsa_device_ops dsa_netdev_ops = {
+static const struct dsa_device_ops dsa_netdev_ops = {
 	.name	= "dsa",
 	.proto	= DSA_TAG_PROTO_DSA,
 	.xmit	= dsa_xmit,
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 76bf3db4e9d4..e8eaa804ccb9 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -169,7 +169,7 @@ static int edsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 	return 0;
 }
 
-const struct dsa_device_ops edsa_netdev_ops = {
+static const struct dsa_device_ops edsa_netdev_ops = {
 	.name	= "edsa",
 	.proto	= DSA_TAG_PROTO_EDSA,
 	.xmit	= edsa_xmit,
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index ee5167180e79..b678160bbd66 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -103,7 +103,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb,
 	return skb;
 }
 
-const struct dsa_device_ops gswip_netdev_ops = {
+static const struct dsa_device_ops gswip_netdev_ops = {
 	.name = "gwsip",
 	.proto	= DSA_TAG_PROTO_GSWIP,
 	.xmit = gswip_tag_xmit,
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 02689ac6f9da..b4872b87d4a6 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -133,7 +133,7 @@ static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev,
 	return ksz_common_rcv(skb, dev, port, len);
 }
 
-const struct dsa_device_ops ksz9477_netdev_ops = {
+static const struct dsa_device_ops ksz9477_netdev_ops = {
 	.name	= "ksz9477",
 	.proto	= DSA_TAG_PROTO_KSZ9477,
 	.xmit	= ksz9477_xmit,
@@ -171,7 +171,7 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb,
 	return nskb;
 }
 
-const struct dsa_device_ops ksz9893_netdev_ops = {
+static const struct dsa_device_ops ksz9893_netdev_ops = {
 	.name	= "ksz9893",
 	.proto	= DSA_TAG_PROTO_KSZ9893,
 	.xmit	= ksz9893_xmit,
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index 609a2405abd8..eb0e7a32e53d 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -128,7 +128,7 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-const struct dsa_device_ops lan9303_netdev_ops = {
+static const struct dsa_device_ops lan9303_netdev_ops = {
 	.name = "lan9303",
 	.proto	= DSA_TAG_PROTO_LAN9303,
 	.xmit = lan9303_xmit,
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index a4d2dcdb7102..b5705cba8318 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -98,7 +98,7 @@ static int mtk_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 	return 0;
 }
 
-const struct dsa_device_ops mtk_netdev_ops = {
+static const struct dsa_device_ops mtk_netdev_ops = {
 	.name		= "mtk",
 	.proto		= DSA_TAG_PROTO_MTK,
 	.xmit		= mtk_tag_xmit,
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 552ddfbbf5ec..c95885215525 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -99,7 +99,7 @@ static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
 	return 0;
 }
 
-const struct dsa_device_ops qca_netdev_ops = {
+static const struct dsa_device_ops qca_netdev_ops = {
 	.name	= "qca",
 	.proto	= DSA_TAG_PROTO_QCA,
 	.xmit	= qca_tag_xmit,
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 807cc2dff052..4f8ab62f0208 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -77,7 +77,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-const struct dsa_device_ops trailer_netdev_ops = {
+static const struct dsa_device_ops trailer_netdev_ops = {
 	.name	= "trailer",
 	.proto	= DSA_TAG_PROTO_TRAILER,
 	.xmit	= trailer_xmit,
-- 
cgit v1.2.3


From 316793fb2d907d4726b4977b6be26ec653827774 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr@mellanox.com>
Date: Mon, 29 Apr 2019 18:14:01 +0000
Subject: net/mlx5: E-Switch: Introduce prio tag mode

Current ConnectX HW is unable to perform VLAN pop in TX path and VLAN
push on RX path. To workaround that limitation untagged packets will be
tagged with VLAN ID 0x000 (priority tag) and pop/push actions will be
replaced by VLAN re-write actions (which are supported by the HW).
Introduce prio tag mode as a pre-step to controlling the workaround
behavior.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 4b37519bd6a5..eeedf3f53ed3 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -951,7 +951,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         log_max_srq_sz[0x8];
 	u8         log_max_qp_sz[0x8];
-	u8         reserved_at_90[0xb];
+	u8         reserved_at_90[0x8];
+	u8         prio_tag_required[0x1];
+	u8         reserved_at_99[0x2];
 	u8         log_max_qp[0x5];
 
 	u8         reserved_at_a0[0xb];
-- 
cgit v1.2.3


From 27b942fbbd3107d4e969ece133925cd646239ef4 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Mon, 29 Apr 2019 18:14:02 +0000
Subject: net/mlx5: Get rid of storing copy of device name

Currently mlx5 core stores copy of the PCI device name in a
mlx5_priv structure and uses pr_warn, pr_err helpers.

Get rid of the copy of this name; instead store the parent device
pointer that contains name as well as dma specific parameters.
This also allows to use kernel's well defined dev_warn, dev_err, dev_dbg
device specific print routines.

This is also a preparation patch to access non PCI parent device in
future.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c      |  2 +-
 .../mellanox/mlx5/core/diag/fw_tracer_tracepoint.h |  5 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |  5 +-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  8 +--
 drivers/net/ethernet/mellanox/mlx5/core/health.c   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     | 15 +++--
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    | 65 ++++++++++++----------
 .../net/ethernet/mellanox/mlx5/core/pagealloc.c    |  5 +-
 include/linux/mlx5/driver.h                        |  3 +-
 9 files changed, 57 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 0a2ffe794a54..779fa1e9ee4e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1347,7 +1347,7 @@ static void set_wqname(struct mlx5_core_dev *dev)
 	struct mlx5_cmd *cmd = &dev->cmd;
 
 	snprintf(cmd->wq_name, sizeof(cmd->wq_name), "mlx5_cmd_%s",
-		 dev->priv.name);
+		 dev_name(dev->device));
 }
 
 static void clean_debug_files(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
index 7b5901d42994..3038be575923 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
@@ -47,7 +47,7 @@ TRACE_EVENT(mlx5_fw,
 	TP_ARGS(tracer, trace_timestamp, lost, event_id, msg),
 
 	TP_STRUCT__entry(
-		__string(dev_name, tracer->dev->priv.name)
+		__string(dev_name, dev_name(tracer->dev->device))
 		__field(u64, trace_timestamp)
 		__field(bool, lost)
 		__field(u8, event_id)
@@ -55,7 +55,8 @@ TRACE_EVENT(mlx5_fw,
 	),
 
 	TP_fast_assign(
-		__assign_str(dev_name, tracer->dev->priv.name);
+		__assign_str(dev_name,
+			     dev_name(tracer->dev->device));
 		__entry->trace_timestamp = trace_timestamp;
 		__entry->lost = lost;
 		__entry->event_id = event_id;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b4967a0ff8c7..a40e801cf713 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -663,7 +663,8 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 	}
 
 	netdev_dbg(priv->netdev, "add hairpin: tirn %x rqn %x peer %s sqn %x prio %d (log) data %d packets %d\n",
-		   hp->tirn, hp->pair->rqn[0], hp->pair->peer_mdev->priv.name,
+		   hp->tirn, hp->pair->rqn[0],
+		   dev_name(hp->pair->peer_mdev->device),
 		   hp->pair->sqn[0], match_prio, params.log_data_size, params.log_num_packets);
 
 	hpe->hp = hp;
@@ -700,7 +701,7 @@ static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv,
 		hpe = list_entry(next, struct mlx5e_hairpin_entry, flows);
 
 		netdev_dbg(priv->netdev, "del hairpin: peer %s\n",
-			   hpe->hp->pair->peer_mdev->priv.name);
+			   dev_name(hpe->hp->pair->peer_mdev->device));
 
 		mlx5e_hairpin_destroy(hpe->hp);
 		hash_del(&hpe->hairpin_hlist);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 3f3cd32ae60a..c1d6bb90cf04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -376,11 +376,11 @@ bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 
 #define MLX5_DEBUG_ESWITCH_MASK BIT(3)
 
-#define esw_info(dev, format, ...)				\
-	pr_info("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
+#define esw_info(__dev, format, ...)			\
+	dev_info((__dev)->device, "E-Switch: " format, ##__VA_ARGS__)
 
-#define esw_warn(dev, format, ...)				\
-	pr_warn("(%s): E-Switch: " format, (dev)->priv.name, ##__VA_ARGS__)
+#define esw_warn(__dev, format, ...)			\
+	dev_warn((__dev)->device, "E-Switch: " format, ##__VA_ARGS__)
 
 #define esw_debug(dev, format, ...)				\
 	mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 3b98fcdd7d0e..a2656f4008d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -380,7 +380,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 
 	strcpy(name, "mlx5_health");
-	strcat(name, dev->priv.name);
+	strcat(name, dev_name(dev->device));
 	health->wq = create_singlethread_workqueue(name);
 	kfree(name);
 	if (!health->wq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index b200a29d1420..bedf809737b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -741,7 +741,6 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 	struct mlx5_priv *priv = &dev->priv;
 	int err = 0;
 
-	dev->pdev = pdev;
 	priv->pci_dev_data = id->driver_data;
 
 	pci_set_drvdata(dev->pdev, dev);
@@ -1242,14 +1241,11 @@ static const struct devlink_ops mlx5_devlink_ops = {
 #endif
 };
 
-static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char *name)
+static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	int err;
 
-	strncpy(priv->name, name, MLX5_MAX_NAME_LEN);
-	priv->name[MLX5_MAX_NAME_LEN - 1] = 0;
-
 	dev->profile = &profile[profile_idx];
 
 	INIT_LIST_HEAD(&priv->ctx_list);
@@ -1267,9 +1263,10 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx, const char
 	INIT_LIST_HEAD(&priv->pgdir_list);
 	spin_lock_init(&priv->mkey_lock);
 
-	priv->dbg_root = debugfs_create_dir(name, mlx5_debugfs_root);
+	priv->dbg_root = debugfs_create_dir(dev_name(dev->device),
+					    mlx5_debugfs_root);
 	if (!priv->dbg_root) {
-		pr_err("mlx5_core: %s error, Cannot create debugfs dir, aborting\n", name);
+		dev_err(dev->device, "mlx5_core: error, Cannot create debugfs dir, aborting\n");
 		return -ENOMEM;
 	}
 
@@ -1312,8 +1309,10 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	dev = devlink_priv(devlink);
+	dev->device = &pdev->dev;
+	dev->pdev = pdev;
 
-	err = mlx5_mdev_init(dev, prof_sel, dev_name(&pdev->dev));
+	err = mlx5_mdev_init(dev, prof_sel);
 	if (err)
 		goto mdev_init_err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index d66f4f082ef7..0e111b70c178 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -41,6 +41,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/fs.h>
+#include <linux/mlx5/driver.h>
 
 #define DRIVER_NAME "mlx5_core"
 #define DRIVER_VERSION "5.0-0"
@@ -48,53 +49,57 @@
 extern uint mlx5_core_debug_mask;
 
 #define mlx5_core_dbg(__dev, format, ...)				\
-	pr_debug("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,      \
+	dev_dbg((__dev)->device, "%s:%d:(pid %d): " format,		\
 		 __func__, __LINE__, current->pid,			\
 		 ##__VA_ARGS__)
 
-#define mlx5_core_dbg_once(__dev, format, ...)				\
-	pr_debug_once("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
-		     __func__, __LINE__, current->pid,			\
+#define mlx5_core_dbg_once(__dev, format, ...)		\
+	dev_dbg_once((__dev)->device,		\
+		     "%s:%d:(pid %d): " format,		\
+		     __func__, __LINE__, current->pid,	\
 		     ##__VA_ARGS__)
 
-#define mlx5_core_dbg_mask(__dev, mask, format, ...)			\
-do {									\
-	if ((mask) & mlx5_core_debug_mask)				\
-		mlx5_core_dbg(__dev, format, ##__VA_ARGS__);		\
+#define mlx5_core_dbg_mask(__dev, mask, format, ...)		\
+do {								\
+	if ((mask) & mlx5_core_debug_mask)			\
+		mlx5_core_dbg(__dev, format, ##__VA_ARGS__);	\
 } while (0)
 
-#define mlx5_core_err(__dev, format, ...)				\
-	pr_err("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,        \
-		__func__, __LINE__, current->pid,	\
+#define mlx5_core_err(__dev, format, ...)			\
+	dev_err((__dev)->device, "%s:%d:(pid %d): " format,	\
+		__func__, __LINE__, current->pid,		\
 	       ##__VA_ARGS__)
 
-#define mlx5_core_err_rl(__dev, format, ...)				     \
-	pr_err_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
-			   __func__, __LINE__, current->pid,		     \
-			   ##__VA_ARGS__)
+#define mlx5_core_err_rl(__dev, format, ...)			\
+	dev_err_ratelimited((__dev)->device,			\
+			    "%s:%d:(pid %d): " format,		\
+			    __func__, __LINE__, current->pid,	\
+			    ##__VA_ARGS__)
 
-#define mlx5_core_warn(__dev, format, ...)				\
-	pr_warn("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,       \
-		 __func__, __LINE__, current->pid,			\
-		##__VA_ARGS__)
+#define mlx5_core_warn(__dev, format, ...)			\
+	dev_warn((__dev)->device, "%s:%d:(pid %d): " format,	\
+		 __func__, __LINE__, current->pid,		\
+		 ##__VA_ARGS__)
 
 #define mlx5_core_warn_once(__dev, format, ...)				\
-	pr_warn_once("%s:%s:%d:(pid %d): " format, (__dev)->priv.name,  \
+	dev_warn_once((__dev)->device, "%s:%d:(pid %d): " format,	\
 		      __func__, __LINE__, current->pid,			\
 		      ##__VA_ARGS__)
 
-#define mlx5_core_warn_rl(__dev, format, ...)				      \
-	pr_warn_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
-			   __func__, __LINE__, current->pid,		      \
-			   ##__VA_ARGS__)
+#define mlx5_core_warn_rl(__dev, format, ...)			\
+	dev_warn_ratelimited((__dev)->device,			\
+			     "%s:%d:(pid %d): " format,		\
+			     __func__, __LINE__, current->pid,	\
+			     ##__VA_ARGS__)
 
-#define mlx5_core_info(__dev, format, ...)				\
-	pr_info("%s " format, (__dev)->priv.name, ##__VA_ARGS__)
+#define mlx5_core_info(__dev, format, ...)		\
+	dev_info((__dev)->device, format, ##__VA_ARGS__)
 
-#define mlx5_core_info_rl(__dev, format, ...)				      \
-	pr_info_ratelimited("%s:%s:%d:(pid %d): " format, (__dev)->priv.name, \
-			   __func__, __LINE__, current->pid,		      \
-			   ##__VA_ARGS__)
+#define mlx5_core_info_rl(__dev, format, ...)			\
+	dev_info_ratelimited((__dev)->device,			\
+			     "%s:%d:(pid %d): " format,		\
+			     __func__, __LINE__, current->pid,	\
+			     ##__VA_ARGS__)
 
 enum {
 	MLX5_CMD_DATA, /* print command payload only */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 41025387ff2c..d87d42f4f6dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -600,8 +600,7 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages)
 		return 0;
 	}
 
-	mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_pages,
-		      dev->priv.name);
+	mlx5_core_dbg(dev, "Waiting for %d pages\n", prev_pages);
 	while (*pages) {
 		if (time_after(jiffies, end)) {
 			mlx5_core_warn(dev, "aborting while there are %d pending pages\n", *pages);
@@ -614,6 +613,6 @@ int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages)
 		msleep(50);
 	}
 
-	mlx5_core_dbg(dev, "All pages received from %s\n", dev->priv.name);
+	mlx5_core_dbg(dev, "All pages received\n");
 	return 0;
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 6c43191c0186..582a9680b182 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -56,7 +56,6 @@
 
 enum {
 	MLX5_BOARD_ID_LEN = 64,
-	MLX5_MAX_NAME_LEN = 16,
 };
 
 enum {
@@ -514,7 +513,6 @@ struct mlx5_rl_table {
 };
 
 struct mlx5_priv {
-	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	*eq_table;
 
 	/* pages stuff */
@@ -641,6 +639,7 @@ struct mlx5_fw_tracer;
 struct mlx5_vxlan;
 
 struct mlx5_core_dev {
+	struct device *device;
 	struct pci_dev	       *pdev;
 	/* sync pci state */
 	struct mutex		pci_status_mutex;
-- 
cgit v1.2.3


From d83eb50e29de36ddc819863ab7b9d2da58bccbd0 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Mon, 29 Apr 2019 18:14:12 +0000
Subject: net/mlx5: Add support in RDMA RX steering

Add new flow steering namespace - MLX5_FLOW_NAMESPACE_RDMA_RX.
Flow steering rules in this namespace are used to filter
RDMA traffic.

Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c  |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 27 +++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h |  2 ++
 include/linux/mlx5/device.h                       |  6 +++++
 include/linux/mlx5/fs.h                           |  1 +
 include/linux/mlx5/mlx5_ifc.h                     |  2 +-
 6 files changed, 38 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index e89555da485e..629c5ab1c0d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -854,6 +854,7 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ
 	case FS_FT_SNIFFER_RX:
 	case FS_FT_SNIFFER_TX:
 	case FS_FT_NIC_TX:
+	case FS_FT_RDMA_RX:
 		return mlx5_fs_cmd_get_fw_cmds();
 	default:
 		return mlx5_fs_cmd_get_stub_cmds();
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 6024df821734..3c2302a2b9d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2054,6 +2054,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		if (steering->sniffer_tx_root_ns)
 			return &steering->sniffer_tx_root_ns->ns;
 		return NULL;
+	case MLX5_FLOW_NAMESPACE_RDMA_RX:
+		if (steering->rdma_rx_root_ns)
+			return &steering->rdma_rx_root_ns->ns;
+		return NULL;
 	default:
 		break;
 	}
@@ -2450,6 +2454,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 	steering->fdb_sub_ns = NULL;
 	cleanup_root_ns(steering->sniffer_rx_root_ns);
 	cleanup_root_ns(steering->sniffer_tx_root_ns);
+	cleanup_root_ns(steering->rdma_rx_root_ns);
 	cleanup_root_ns(steering->egress_root_ns);
 	mlx5_cleanup_fc_stats(dev);
 	kmem_cache_destroy(steering->ftes_cache);
@@ -2491,6 +2496,22 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering)
 	return 0;
 }
 
+static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct fs_prio *prio;
+
+	steering->rdma_rx_root_ns = create_root_ns(steering, FS_FT_RDMA_RX);
+	if (!steering->rdma_rx_root_ns)
+		return -ENOMEM;
+
+	/* Create single prio */
+	prio = fs_create_prio(&steering->rdma_rx_root_ns->ns, 0, 1);
+	if (IS_ERR(prio)) {
+		cleanup_root_ns(steering->rdma_rx_root_ns);
+		return PTR_ERR(prio);
+	}
+	return 0;
+}
 static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
 {
 	struct mlx5_flow_namespace *ns;
@@ -2727,6 +2748,12 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
+	if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support)) {
+		err = init_rdma_rx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
 	if (MLX5_IPSEC_DEV(dev) || MLX5_CAP_FLOWTABLE_NIC_TX(dev, ft_support)) {
 		err = init_egress_root_ns(steering);
 		if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 87de0e4d9124..e43c6f6d46a7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -67,6 +67,7 @@ enum fs_flow_table_type {
 	FS_FT_FDB             = 0X4,
 	FS_FT_SNIFFER_RX	= 0X5,
 	FS_FT_SNIFFER_TX	= 0X6,
+	FS_FT_RDMA_RX		= 0X7,
 	FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX,
 };
 
@@ -90,6 +91,7 @@ struct mlx5_flow_steering {
 	struct mlx5_flow_root_namespace **esw_ingress_root_ns;
 	struct mlx5_flow_root_namespace	*sniffer_tx_root_ns;
 	struct mlx5_flow_root_namespace	*sniffer_rx_root_ns;
+	struct mlx5_flow_root_namespace	*rdma_rx_root_ns;
 	struct mlx5_flow_root_namespace	*egress_root_ns;
 };
 
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index f93a5598b942..28ebb6c93542 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1166,6 +1166,12 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_FLOWTABLE_SNIFFER_TX_MAX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_sniffer.cap)
 
+#define MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) \
+	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_rdma.cap)
+
+#define MLX5_CAP_FLOWTABLE_RDMA_RX_MAX(mdev, cap) \
+	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_rdma.cap)
+
 #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
 		 mdev->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index fd91df3a4e09..e690ba0f965c 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -73,6 +73,7 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_SNIFFER_RX,
 	MLX5_FLOW_NAMESPACE_SNIFFER_TX,
 	MLX5_FLOW_NAMESPACE_EGRESS,
+	MLX5_FLOW_NAMESPACE_RDMA_RX,
 };
 
 enum {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index eeedf3f53ed3..89e7194b3d97 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -598,7 +598,7 @@ struct mlx5_ifc_flow_table_nic_cap_bits {
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive;
 
-	u8         reserved_at_400[0x200];
+	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_rdma;
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_sniffer;
 
-- 
cgit v1.2.3


From f6f7d6b5bd818cc84eebb55ba6bcba38cfd3b385 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Mon, 29 Apr 2019 18:14:14 +0000
Subject: net/mlx5: Add new miss flow table action

Flow table supports three types of miss action:
1. Default miss action - go to default miss table according to table.
2. Go to specific table.
3. Switch domain - go to the root table of an alternative steering
   table domain.

New table miss action was added - switch_domain.
The next domain for RDMA_RX namespace is the NIC RX domain.

Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c  | 13 ++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c |  6 +++++-
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h |  1 +
 include/linux/mlx5/mlx5_ifc.h                     | 10 +++++++++-
 4 files changed, 25 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 629c5ab1c0d1..013b1ca4a791 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -172,9 +172,14 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns,
 	case FS_FT_OP_MOD_NORMAL:
 		if (next_ft) {
 			MLX5_SET(create_flow_table_in, in,
-				 flow_table_context.table_miss_action, 1);
+				 flow_table_context.table_miss_action,
+				 MLX5_FLOW_TABLE_MISS_ACTION_FWD);
 			MLX5_SET(create_flow_table_in, in,
 				 flow_table_context.table_miss_id, next_ft->id);
+		} else {
+			MLX5_SET(create_flow_table_in, in,
+				 flow_table_context.table_miss_action,
+				 ns->def_miss_action);
 		}
 		break;
 
@@ -246,13 +251,15 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns,
 			 MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID);
 		if (next_ft) {
 			MLX5_SET(modify_flow_table_in, in,
-				 flow_table_context.table_miss_action, 1);
+				 flow_table_context.table_miss_action,
+				 MLX5_FLOW_TABLE_MISS_ACTION_FWD);
 			MLX5_SET(modify_flow_table_in, in,
 				 flow_table_context.table_miss_id,
 				 next_ft->id);
 		} else {
 			MLX5_SET(modify_flow_table_in, in,
-				 flow_table_context.table_miss_action, 0);
+				 flow_table_context.table_miss_action,
+				 ns->def_miss_action);
 		}
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 3c2302a2b9d4..fb5b61727ee7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2504,6 +2504,9 @@ static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering)
 	if (!steering->rdma_rx_root_ns)
 		return -ENOMEM;
 
+	steering->rdma_rx_root_ns->def_miss_action =
+		MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN;
+
 	/* Create single prio */
 	prio = fs_create_prio(&steering->rdma_rx_root_ns->ns, 0, 1);
 	if (IS_ERR(prio)) {
@@ -2748,7 +2751,8 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
-	if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support)) {
+	if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) &&
+	    MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) {
 		err = init_rdma_rx_root_ns(steering);
 		if (err)
 			goto err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index e43c6f6d46a7..0c6c5fef4548 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -218,6 +218,7 @@ struct mlx5_flow_root_namespace {
 	struct mutex			chain_lock;
 	struct list_head		underlay_qpns;
 	const struct mlx5_flow_cmds	*cmds;
+	enum mlx5_flow_table_miss_action def_miss_action;
 };
 
 int mlx5_init_fc_stats(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 89e7194b3d97..7d9264b282d1 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -370,7 +370,9 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8	   reformat_l3_tunnel_to_l2[0x1];
 	u8	   reformat_l2_to_l3_tunnel[0x1];
 	u8	   reformat_and_modify_action[0x1];
-	u8         reserved_at_15[0xb];
+	u8         reserved_at_15[0x2];
+	u8	   table_miss_action_domain[0x1];
+	u8         reserved_at_18[0x8];
 	u8         reserved_at_20[0x2];
 	u8         log_max_ft_size[0x6];
 	u8         log_max_modify_header_context[0x8];
@@ -1284,6 +1286,12 @@ enum mlx5_flow_destination_type {
 	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM = 0x101,
 };
 
+enum mlx5_flow_table_miss_action {
+	MLX5_FLOW_TABLE_MISS_ACTION_DEF,
+	MLX5_FLOW_TABLE_MISS_ACTION_FWD,
+	MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN,
+};
+
 struct mlx5_ifc_dest_format_struct_bits {
 	u8         destination_type[0x8];
 	u8         destination_id[0x18];
-- 
cgit v1.2.3


From 80f09dfc237f181e92968a72d97b7a4202baa453 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@mellanox.com>
Date: Mon, 29 Apr 2019 18:14:16 +0000
Subject: net/mlx5: Eswitch, enable RoCE loopback traffic

When in switchdev mode, we would like to treat loopback RoCE
traffic (on eswitch manager) as RDMA and not as regular
Ethernet traffic
In order to enable it we add flow steering rule that forward RoCE
loopback traffic to the HW RoCE filter (by adding allow rule).
In addition we add RoCE address in GID index 0, which will be
set in the RoCE loopback packet.

Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Acked-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c |   4 +
 drivers/net/ethernet/mellanox/mlx5/core/rdma.c     | 182 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/rdma.h     |  20 +++
 include/linux/mlx5/driver.h                        |   7 +
 5 files changed, 214 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/rdma.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/rdma.h

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 1a16f6d73cbc..5f0be9b36a04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -35,7 +35,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tu
 #
 # Core extra
 #
-mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o ecpf.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o ecpf.o rdma.o
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 6c8a17ca236e..9a1598bca4d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -37,6 +37,7 @@
 #include <linux/mlx5/fs.h>
 #include "mlx5_core.h"
 #include "eswitch.h"
+#include "rdma.h"
 #include "en.h"
 #include "fs_core.h"
 #include "lib/devcom.h"
@@ -1713,6 +1714,8 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
 		esw->host_info.num_vfs = vf_nvports;
 	}
 
+	mlx5_rdma_enable_roce(esw->dev);
+
 	return 0;
 
 err_reps:
@@ -1751,6 +1754,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 		num_vfs = esw->dev->priv.sriov.num_vfs;
 	}
 
+	mlx5_rdma_disable_roce(esw->dev);
 	esw_offloads_devcom_cleanup(esw);
 	esw_offloads_unload_all_reps(esw, num_vfs);
 	esw_offloads_steering_cleanup(esw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
new file mode 100644
index 000000000000..86f77456f873
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#include <linux/mlx5/vport.h>
+#include <rdma/ib_verbs.h>
+#include <net/addrconf.h>
+
+#include "lib/mlx5.h"
+#include "eswitch.h"
+#include "fs_core.h"
+#include "rdma.h"
+
+static void mlx5_rdma_disable_roce_steering(struct mlx5_core_dev *dev)
+{
+	struct mlx5_core_roce *roce = &dev->priv.roce;
+
+	if (!roce->ft)
+		return;
+
+	mlx5_del_flow_rules(roce->allow_rule);
+	mlx5_destroy_flow_group(roce->fg);
+	mlx5_destroy_flow_table(roce->ft);
+}
+
+static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_core_roce *roce = &dev->priv.roce;
+	struct mlx5_flow_handle *flow_rule = NULL;
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_namespace *ns = NULL;
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_spec *spec;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	void *match_criteria;
+	u32 *flow_group_in;
+	void *misc;
+	int err;
+
+	if (!(MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) &&
+	      MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)))
+		return -EOPNOTSUPP;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec) {
+		kvfree(flow_group_in);
+		return -ENOMEM;
+	}
+
+	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX);
+	if (!ns) {
+		mlx5_core_err(dev, "Failed to get RDMA RX namespace");
+		err = -EOPNOTSUPP;
+		goto free;
+	}
+
+	ft_attr.max_fte = 1;
+	ft = mlx5_create_flow_table(ns, &ft_attr);
+	if (IS_ERR(ft)) {
+		mlx5_core_err(dev, "Failed to create RDMA RX flow table");
+		err = PTR_ERR(ft);
+		goto free;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS);
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+				      match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters.source_port);
+
+	fg = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		mlx5_core_err(dev, "Failed to create RDMA RX flow group err(%d)\n", err);
+		goto destroy_flow_table;
+	}
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			    misc_parameters);
+	MLX5_SET(fte_match_set_misc, misc, source_port,
+		 dev->priv.eswitch->manager_vport);
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			    misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	flow_rule = mlx5_add_flow_rules(ft, spec, &flow_act, NULL, 0);
+	if (IS_ERR(flow_rule)) {
+		err = PTR_ERR(flow_rule);
+		mlx5_core_err(dev, "Failed to add RoCE allow rule, err=%d\n",
+			      err);
+		goto destroy_flow_group;
+	}
+
+	kvfree(spec);
+	kvfree(flow_group_in);
+	roce->ft = ft;
+	roce->fg = fg;
+	roce->allow_rule = flow_rule;
+
+	return 0;
+
+destroy_flow_table:
+	mlx5_destroy_flow_table(ft);
+destroy_flow_group:
+	mlx5_destroy_flow_group(fg);
+free:
+	kvfree(spec);
+	kvfree(flow_group_in);
+	return err;
+}
+
+static void mlx5_rdma_del_roce_addr(struct mlx5_core_dev *dev)
+{
+	mlx5_core_roce_gid_set(dev, 0, 0, 0,
+			       NULL, NULL, false, 0, 0);
+}
+
+static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *gid)
+{
+	u8 hw_id[ETH_ALEN];
+
+	mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
+	gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
+	addrconf_addr_eui48(&gid->raw[8], hw_id);
+}
+
+static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
+{
+	union ib_gid gid;
+	u8 mac[ETH_ALEN];
+
+	mlx5_rdma_make_default_gid(dev, &gid);
+	return mlx5_core_roce_gid_set(dev, 0,
+				      MLX5_ROCE_VERSION_1,
+				      0, gid.raw, mac,
+				      false, 0, 1);
+}
+
+void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
+{
+	mlx5_rdma_disable_roce_steering(dev);
+	mlx5_rdma_del_roce_addr(dev);
+	mlx5_nic_vport_disable_roce(dev);
+}
+
+void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_nic_vport_enable_roce(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to enable RoCE: %d\n", err);
+		return;
+	}
+
+	err = mlx5_rdma_add_roce_addr(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to add RoCE address: %d\n", err);
+		goto disable_roce;
+	}
+
+	err = mlx5_rdma_enable_roce_steering(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to enable RoCE steering: %d\n", err);
+		goto del_roce_addr;
+	}
+
+	return;
+
+del_roce_addr:
+	mlx5_rdma_del_roce_addr(dev);
+disable_roce:
+	mlx5_nic_vport_disable_roce(dev);
+	return;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.h b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
new file mode 100644
index 000000000000..750cff2a71a4
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_RDMA_H__
+#define __MLX5_RDMA_H__
+
+#include "mlx5_core.h"
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev);
+void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev);
+
+#else /* CONFIG_MLX5_ESWITCH */
+
+static inline void mlx5_rdma_enable_roce(struct mlx5_core_dev *dev) {}
+static inline void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) {}
+
+#endif /* CONFIG_MLX5_ESWITCH */
+#endif /* __MLX5_RDMA_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 582a9680b182..7fa95270dd59 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -512,6 +512,12 @@ struct mlx5_rl_table {
 	struct mlx5_rl_entry   *rl_entry;
 };
 
+struct mlx5_core_roce {
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	struct mlx5_flow_handle *allow_rule;
+};
+
 struct mlx5_priv {
 	struct mlx5_eq_table	*eq_table;
 
@@ -565,6 +571,7 @@ struct mlx5_priv {
 	struct mlx5_lag		*lag;
 	struct mlx5_devcom	*devcom;
 	unsigned long		pci_dev_data;
+	struct mlx5_core_roce	roce;
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;
 
-- 
cgit v1.2.3


From 75d90e7def8e20b57c1de9e2b672c3bf9249da83 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@mellanox.com>
Date: Mon, 29 Apr 2019 18:14:18 +0000
Subject: net/mlx5: Geneve, Add basic Geneve encap/decap flow table
 capabilities

Introduce support for Geneve flow specification and allow
the creation of rules that are matching on basic Geneve
protocol fields: VNI, OAM bit, protocol type, options length.

Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 7d9264b282d1..268ac126b3bb 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -307,7 +307,11 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         outer_gre_protocol[0x1];
 	u8         outer_gre_key[0x1];
 	u8         outer_vxlan_vni[0x1];
-	u8         reserved_at_1a[0x5];
+	u8         outer_geneve_vni[0x1];
+	u8         outer_geneve_oam[0x1];
+	u8         outer_geneve_protocol_type[0x1];
+	u8         outer_geneve_opt_len[0x1];
+	u8         reserved_at_1e[0x1];
 	u8         source_eswitch_port[0x1];
 
 	u8         inner_dmac[0x1];
@@ -480,7 +484,9 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 	u8         vxlan_vni[0x18];
 	u8         reserved_at_b8[0x8];
 
-	u8         reserved_at_c0[0x20];
+	u8         geneve_vni[0x18];
+	u8         reserved_at_d8[0x7];
+	u8         geneve_oam[0x1];
 
 	u8         reserved_at_e0[0xc];
 	u8         outer_ipv6_flow_label[0x14];
@@ -488,7 +494,11 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 	u8         reserved_at_100[0xc];
 	u8         inner_ipv6_flow_label[0x14];
 
-	u8         reserved_at_120[0x28];
+	u8         reserved_at_120[0xa];
+	u8         geneve_opt_len[0x6];
+	u8         geneve_protocol_type[0x10];
+
+	u8         reserved_at_140[0x8];
 	u8         bth_dst_qp[0x18];
 	u8	   reserved_at_160[0x20];
 	u8	   outer_esp_spi[0x20];
-- 
cgit v1.2.3


From b169e64a24442e02cafee1586f17fcb713fe65a6 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@mellanox.com>
Date: Mon, 29 Apr 2019 18:14:20 +0000
Subject: net/mlx5: Geneve, Add flow table capabilities for Geneve decap with
 TLV options

Introduce specification for Geneve decap flow with encapsulation options
and allow creation of rules that are matching on Geneve TLV options.

Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h |  2 +-
 include/linux/mlx5/device.h                       |  4 +-
 include/linux/mlx5/mlx5_ifc.h                     | 50 ++++++++++++++++++++---
 3 files changed, 49 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 0c6c5fef4548..a08c3d09a50f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -152,7 +152,7 @@ struct mlx5_ft_underlay_qp {
 	u32 qpn;
 };
 
-#define MLX5_FTE_MATCH_PARAM_RESERVED	reserved_at_800
+#define MLX5_FTE_MATCH_PARAM_RESERVED	reserved_at_a00
 /* Calculate the fte_match_param length and without the reserved length.
  * Make sure the reserved field is the last.
  */
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 28ebb6c93542..4ab801040e98 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1001,7 +1001,8 @@ enum {
 	MLX5_MATCH_OUTER_HEADERS	= 1 << 0,
 	MLX5_MATCH_MISC_PARAMETERS	= 1 << 1,
 	MLX5_MATCH_INNER_HEADERS	= 1 << 2,
-
+	MLX5_MATCH_MISC_PARAMETERS_2	= 1 << 3,
+	MLX5_MATCH_MISC_PARAMETERS_3	= 1 << 4,
 };
 
 enum {
@@ -1045,6 +1046,7 @@ enum mlx5_mpls_supported_fields {
 };
 
 enum mlx5_flex_parser_protos {
+	MLX5_FLEX_PROTO_GENEVE	      = 1 << 3,
 	MLX5_FLEX_PROTO_CW_MPLS_GRE   = 1 << 4,
 	MLX5_FLEX_PROTO_CW_MPLS_UDP   = 1 << 5,
 };
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 268ac126b3bb..6a7fc18a9fe3 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -86,6 +86,11 @@ enum {
 
 enum {
 	MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM),
+	MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11),
+};
+
+enum {
+	MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b,
 };
 
 enum {
@@ -339,7 +344,8 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 	u8         inner_tcp_flags[0x1];
 	u8         reserved_at_37[0x9];
 
-	u8         reserved_at_40[0x5];
+	u8         geneve_tlv_option_0_data[0x1];
+	u8         reserved_at_41[0x4];
 	u8         outer_first_mpls_over_udp[0x4];
 	u8         outer_first_mpls_over_gre[0x4];
 	u8         inner_first_mpls[0x4];
@@ -528,6 +534,12 @@ struct mlx5_ifc_fte_match_set_misc2_bits {
 	u8         reserved_at_1a0[0x60];
 };
 
+struct mlx5_ifc_fte_match_set_misc3_bits {
+	u8         reserved_at_0[0x120];
+	u8         geneve_tlv_option_0_data[0x20];
+	u8         reserved_at_140[0xc0];
+};
+
 struct mlx5_ifc_cmd_pas_bits {
 	u8         pa_h[0x20];
 
@@ -1247,9 +1259,13 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   num_of_uars_per_page[0x20];
 
 	u8         flex_parser_protocols[0x20];
-	u8         reserved_at_560[0x20];
 
-	u8         reserved_at_580[0x3c];
+	u8         max_geneve_tlv_options[0x8];
+	u8         reserved_at_568[0x3];
+	u8         max_geneve_tlv_option_data_len[0x5];
+	u8         reserved_at_570[0x10];
+
+	u8         reserved_at_580[0x1c];
 	u8         mini_cqe_resp_stride_index[0x1];
 	u8         cqe_128_always[0x1];
 	u8         cqe_compression_128[0x1];
@@ -1283,7 +1299,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         uctx_cap[0x20];
 
-	u8	   reserved_at_6c0[0x140];
+	u8         reserved_at_6c0[0x4];
+	u8         flex_parser_id_geneve_tlv_option_0[0x4];
+	u8         reserved_at_6c8[0x138];
 };
 
 enum mlx5_flow_destination_type {
@@ -1341,7 +1359,9 @@ struct mlx5_ifc_fte_match_param_bits {
 
 	struct mlx5_ifc_fte_match_set_misc2_bits misc_parameters_2;
 
-	u8         reserved_at_800[0x800];
+	struct mlx5_ifc_fte_match_set_misc3_bits misc_parameters_3;
+
+	u8         reserved_at_a00[0x600];
 };
 
 enum {
@@ -4850,6 +4870,7 @@ enum {
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS  = 0x1,
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_INNER_HEADERS    = 0x2,
 	MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3,
+	MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_3 = 0x4,
 };
 
 struct mlx5_ifc_query_flow_group_out_bits {
@@ -9545,6 +9566,20 @@ struct mlx5_ifc_sw_icm_bits {
 	u8         sw_icm_start_addr[0x40];
 
 	u8         reserved_at_c0[0x140];
+}; 
+
+struct mlx5_ifc_geneve_tlv_option_bits {
+	u8         modify_field_select[0x40];
+
+	u8         reserved_at_40[0x18];
+	u8         geneve_option_fte_index[0x8];
+
+	u8         option_class[0x10];
+	u8         option_type[0x8];
+	u8         reserved_at_78[0x3];
+	u8         option_data_length[0x5];
+
+	u8         reserved_at_80[0x180];
 };
 
 struct mlx5_ifc_create_umem_in_bits {
@@ -9589,6 +9624,11 @@ struct mlx5_ifc_create_sw_icm_in_bits {
 	struct mlx5_ifc_sw_icm_bits		      sw_icm;
 };
 
+struct mlx5_ifc_create_geneve_tlv_option_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits   hdr;
+	struct mlx5_ifc_geneve_tlv_option_bits        geneve_tlv_opt;
+};
+
 struct mlx5_ifc_mtrc_string_db_param_bits {
 	u8         string_db_base_address[0x20];
 
-- 
cgit v1.2.3


From f1f86d09ca7e35fb161a47bc54ec9cb2f4fe42d8 Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Mon, 15 Apr 2019 16:43:14 -0400
Subject: netfilter: nf_tables: relocate header content to consumer

The nf_tables.h header is used in a lot of files, but it turns out
that there is only one actual user of nft_expr_clone().

Hence we relocate that function to be with the one consumer of it
and avoid having to process it with CPP for all the other files.

This will also enable a reduction in the other headers that the
nf_tables.h itself has to include just to be stand-alone, hence
a pending further significant reduction in the CPP content that
needs to get processed for each netfilter file.

Note that the explicit "inline" has been dropped as part of this
relocation.  In similar changes to this, I believe Dave has asked
this be done, so we free up gcc to make the choice of whether to
inline or not.

Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 17 -----------------
 net/netfilter/nft_dynset.c        | 17 +++++++++++++++++
 2 files changed, 17 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 2d5a0a1a87b8..706f744f7308 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -806,23 +806,6 @@ void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr);
 int nft_expr_dump(struct sk_buff *skb, unsigned int attr,
 		  const struct nft_expr *expr);
 
-static inline int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src)
-{
-	int err;
-
-	if (src->ops->clone) {
-		dst->ops = src->ops;
-		err = src->ops->clone(dst, src);
-		if (err < 0)
-			return err;
-	} else {
-		memcpy(dst, src, src->ops->size);
-	}
-
-	__module_get(src->ops->type->owner);
-	return 0;
-}
-
 /**
  *	struct nft_rule - nf_tables rule
  *
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index e461007558e8..8394560aa695 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -28,6 +28,23 @@ struct nft_dynset {
 	struct nft_set_binding		binding;
 };
 
+static int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src)
+{
+	int err;
+
+	if (src->ops->clone) {
+		dst->ops = src->ops;
+		err = src->ops->clone(dst, src);
+		if (err < 0)
+			return err;
+	} else {
+		memcpy(dst, src, src->ops->size);
+	}
+
+	__module_get(src->ops->type->owner);
+	return 0;
+}
+
 static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr,
 			    struct nft_regs *regs)
 {
-- 
cgit v1.2.3


From a4cb98f32c9046fea28bcb4979182f2ff731a27a Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Mon, 15 Apr 2019 16:43:16 -0400
Subject: netfilter: nf_tables: drop include of module.h from nf_tables.h

Ideally, header files under include/linux shouldn't be adding
includes of other headers, in anticipation of their consumers,
but just the headers needed for the header itself to pass
parsing with CPP.

The module.h is particularly bad in this sense, as it itself does
include a whole bunch of other headers, due to the complexity of
module support.

Since nf_tables.h is not going into a module struct looking for
specific fields, we can just let it know that module is a struct,
just like about 60 other include/linux headers already do.

Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 706f744f7308..5b8624ae4a27 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -2,7 +2,6 @@
 #ifndef _NET_NF_TABLES_H
 #define _NET_NF_TABLES_H
 
-#include <linux/module.h>
 #include <linux/list.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nfnetlink.h>
@@ -13,6 +12,8 @@
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netlink.h>
 
+struct module;
+
 #define NFT_JUMP_STACK_SIZE	16
 
 struct nft_pktinfo {
-- 
cgit v1.2.3


From 8f14c99c7edaaba9c0bb1727d44db6ebf157cc61 Mon Sep 17 00:00:00 2001
From: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Date: Sun, 7 Apr 2019 08:14:20 -0700
Subject: netfilter: conntrack: limit sysctl setting for boolean options

We use the zero and one to limit the boolean options setting.
After this patch we only set 0 or 1 to boolean options for nf
conntrack sysctl.

Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netns/conntrack.h           |  6 ++---
 net/netfilter/nf_conntrack_standalone.c | 48 ++++++++++++++++++++++-----------
 2 files changed, 36 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index f19b53130bf7..806454e767bf 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -24,9 +24,9 @@ struct nf_generic_net {
 
 struct nf_tcp_net {
 	unsigned int timeouts[TCP_CONNTRACK_TIMEOUT_MAX];
-	unsigned int tcp_loose;
-	unsigned int tcp_be_liberal;
-	unsigned int tcp_max_retrans;
+	int tcp_loose;
+	int tcp_be_liberal;
+	int tcp_max_retrans;
 };
 
 enum udp_conntrack {
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index c2ae14c720b4..e0d392cb3075 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -511,6 +511,8 @@ static void nf_conntrack_standalone_fini_proc(struct net *net)
 /* Log invalid packets of a given protocol */
 static int log_invalid_proto_min __read_mostly;
 static int log_invalid_proto_max __read_mostly = 255;
+static int zero;
+static int one = 1;
 
 /* size the user *wants to set */
 static unsigned int nf_conntrack_htable_size_user __read_mostly;
@@ -624,9 +626,11 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 	[NF_SYSCTL_CT_CHECKSUM] = {
 		.procname	= "nf_conntrack_checksum",
 		.data		= &init_net.ct.sysctl_checksum,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1 	= &zero,
+		.extra2 	= &one,
 	},
 	[NF_SYSCTL_CT_LOG_INVALID] = {
 		.procname	= "nf_conntrack_log_invalid",
@@ -647,33 +651,41 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 	[NF_SYSCTL_CT_ACCT] = {
 		.procname	= "nf_conntrack_acct",
 		.data		= &init_net.ct.sysctl_acct,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1 	= &zero,
+		.extra2 	= &one,
 	},
 	[NF_SYSCTL_CT_HELPER] = {
 		.procname	= "nf_conntrack_helper",
 		.data		= &init_net.ct.sysctl_auto_assign_helper,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1 	= &zero,
+		.extra2 	= &one,
 	},
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 	[NF_SYSCTL_CT_EVENTS] = {
 		.procname	= "nf_conntrack_events",
 		.data		= &init_net.ct.sysctl_events,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1 	= &zero,
+		.extra2 	= &one,
 	},
 #endif
 #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
 	[NF_SYSCTL_CT_TIMESTAMP] = {
 		.procname	= "nf_conntrack_timestamp",
 		.data		= &init_net.ct.sysctl_tstamp,
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1 	= &zero,
+		.extra2 	= &one,
 	},
 #endif
 	[NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC] = {
@@ -744,15 +756,19 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 	},
 	[NF_SYSCTL_CT_PROTO_TCP_LOOSE] = {
 		.procname	= "nf_conntrack_tcp_loose",
-		.maxlen		= sizeof(unsigned int),
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1 	= &zero,
+		.extra2 	= &one,
 	},
 	[NF_SYSCTL_CT_PROTO_TCP_LIBERAL] = {
 		.procname       = "nf_conntrack_tcp_be_liberal",
-		.maxlen         = sizeof(unsigned int),
+		.maxlen         = sizeof(int),
 		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1 	= &zero,
+		.extra2 	= &one,
 	},
 	[NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = {
 		.procname	= "nf_conntrack_tcp_max_retrans",
@@ -887,7 +903,9 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.procname	= "nf_conntrack_dccp_loose",
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1 	= &zero,
+		.extra2 	= &one,
 	},
 #endif
 #ifdef CONFIG_NF_CT_PROTO_GRE
-- 
cgit v1.2.3


From e1f172e162c0a11721f1188f12e5b4c3f9f80de6 Mon Sep 17 00:00:00 2001
From: Flavio Leitner <fbl@redhat.com>
Date: Wed, 17 Apr 2019 11:46:14 -0300
Subject: netfilter: use macros to create module aliases.

Each NAT helper creates a module alias which follows a pattern.
Use macros for consistency.

Signed-off-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_helper.h | 4 ++++
 net/ipv4/netfilter/nf_nat_h323.c            | 2 +-
 net/ipv4/netfilter/nf_nat_pptp.c            | 2 +-
 net/netfilter/nf_nat_amanda.c               | 2 +-
 net/netfilter/nf_nat_ftp.c                  | 2 +-
 net/netfilter/nf_nat_irc.c                  | 2 +-
 net/netfilter/nf_nat_sip.c                  | 2 +-
 net/netfilter/nf_nat_tftp.c                 | 2 +-
 8 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index ec52a8dc32fd..28bd4569aa64 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -15,6 +15,10 @@
 #include <net/netfilter/nf_conntrack_extend.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 
+#define NF_NAT_HELPER_NAME(name)	"ip_nat_" name
+#define MODULE_ALIAS_NF_NAT_HELPER(name) \
+	MODULE_ALIAS(NF_NAT_HELPER_NAME(name))
+
 struct module;
 
 enum nf_ct_helper_flags {
diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c
index 4e6b53ab6c33..7875c98072eb 100644
--- a/net/ipv4/netfilter/nf_nat_h323.c
+++ b/net/ipv4/netfilter/nf_nat_h323.c
@@ -631,4 +631,4 @@ module_exit(fini);
 MODULE_AUTHOR("Jing Min Zhao <zhaojingmin@users.sourceforge.net>");
 MODULE_DESCRIPTION("H.323 NAT helper");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("ip_nat_h323");
+MODULE_ALIAS_NF_NAT_HELPER("h323");
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 68b4d450391b..e17b4ee7604c 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -37,7 +37,7 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>");
 MODULE_DESCRIPTION("Netfilter NAT helper module for PPTP");
-MODULE_ALIAS("ip_nat_pptp");
+MODULE_ALIAS_NF_NAT_HELPER("pptp");
 
 static void pptp_nat_expected(struct nf_conn *ct,
 			      struct nf_conntrack_expect *exp)
diff --git a/net/netfilter/nf_nat_amanda.c b/net/netfilter/nf_nat_amanda.c
index e4d61a7a5258..6b729a897c5f 100644
--- a/net/netfilter/nf_nat_amanda.c
+++ b/net/netfilter/nf_nat_amanda.c
@@ -22,7 +22,7 @@
 MODULE_AUTHOR("Brian J. Murrell <netfilter@interlinx.bc.ca>");
 MODULE_DESCRIPTION("Amanda NAT helper");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("ip_nat_amanda");
+MODULE_ALIAS_NF_NAT_HELPER("amanda");
 
 static unsigned int help(struct sk_buff *skb,
 			 enum ip_conntrack_info ctinfo,
diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c
index 5063cbf1689c..0e93b1f19432 100644
--- a/net/netfilter/nf_nat_ftp.c
+++ b/net/netfilter/nf_nat_ftp.c
@@ -24,7 +24,7 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>");
 MODULE_DESCRIPTION("ftp NAT helper");
-MODULE_ALIAS("ip_nat_ftp");
+MODULE_ALIAS_NF_NAT_HELPER("ftp");
 
 /* FIXME: Time out? --RR */
 
diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c
index 3aa35a43100d..6c06e997395f 100644
--- a/net/netfilter/nf_nat_irc.c
+++ b/net/netfilter/nf_nat_irc.c
@@ -26,7 +26,7 @@
 MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>");
 MODULE_DESCRIPTION("IRC (DCC) NAT helper");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("ip_nat_irc");
+MODULE_ALIAS_NF_NAT_HELPER("irc");
 
 static unsigned int help(struct sk_buff *skb,
 			 enum ip_conntrack_info ctinfo,
diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c
index aa1be643d7a0..f1f007d9484c 100644
--- a/net/netfilter/nf_nat_sip.c
+++ b/net/netfilter/nf_nat_sip.c
@@ -27,7 +27,7 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Christian Hentschel <chentschel@arnet.com.ar>");
 MODULE_DESCRIPTION("SIP NAT helper");
-MODULE_ALIAS("ip_nat_sip");
+MODULE_ALIAS_NF_NAT_HELPER("sip");
 
 
 static unsigned int mangle_packet(struct sk_buff *skb, unsigned int protoff,
diff --git a/net/netfilter/nf_nat_tftp.c b/net/netfilter/nf_nat_tftp.c
index 7f67e1d5310d..dd3a835c111d 100644
--- a/net/netfilter/nf_nat_tftp.c
+++ b/net/netfilter/nf_nat_tftp.c
@@ -16,7 +16,7 @@
 MODULE_AUTHOR("Magnus Boden <mb@ozaba.mine.nu>");
 MODULE_DESCRIPTION("TFTP NAT helper");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("ip_nat_tftp");
+MODULE_ALIAS_NF_NAT_HELPER("tftp");
 
 static unsigned int help(struct sk_buff *skb,
 			 enum ip_conntrack_info ctinfo,
-- 
cgit v1.2.3


From 08010a21602678932894c5e87014a282af0079cf Mon Sep 17 00:00:00 2001
From: Flavio Leitner <fbl@redhat.com>
Date: Wed, 17 Apr 2019 11:46:15 -0300
Subject: netfilter: add API to manage NAT helpers.

The API allows a conntrack helper to indicate its corresponding
NAT helper which then can be loaded and reference counted.

Signed-off-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_helper.h | 22 +++++++-
 net/netfilter/nf_conntrack_amanda.c         |  8 ++-
 net/netfilter/nf_conntrack_ftp.c            | 18 +++---
 net/netfilter/nf_conntrack_helper.c         | 86 +++++++++++++++++++++++++++++
 net/netfilter/nf_conntrack_irc.c            |  6 +-
 net/netfilter/nf_conntrack_sane.c           | 12 ++--
 net/netfilter/nf_conntrack_sip.c            | 28 +++++-----
 net/netfilter/nf_conntrack_tftp.c           | 18 +++---
 8 files changed, 161 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 28bd4569aa64..44b5a00a9c64 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -15,7 +15,8 @@
 #include <net/netfilter/nf_conntrack_extend.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 
-#define NF_NAT_HELPER_NAME(name)	"ip_nat_" name
+#define NF_NAT_HELPER_PREFIX		"ip_nat_"
+#define NF_NAT_HELPER_NAME(name)	NF_NAT_HELPER_PREFIX name
 #define MODULE_ALIAS_NF_NAT_HELPER(name) \
 	MODULE_ALIAS(NF_NAT_HELPER_NAME(name))
 
@@ -58,6 +59,8 @@ struct nf_conntrack_helper {
 	unsigned int queue_num;
 	/* length of userspace private data stored in nf_conn_help->data */
 	u16 data_len;
+	/* name of NAT helper module */
+	char nat_mod_name[NF_CT_HELPER_NAME_LEN];
 };
 
 /* Must be kept in sync with the classes defined by helpers */
@@ -157,4 +160,21 @@ nf_ct_helper_expectfn_find_by_symbol(const void *symbol);
 extern struct hlist_head *nf_ct_helper_hash;
 extern unsigned int nf_ct_helper_hsize;
 
+struct nf_conntrack_nat_helper {
+	struct list_head list;
+	char mod_name[NF_CT_HELPER_NAME_LEN];	/* module name */
+	struct module *module;			/* pointer to self */
+};
+
+#define NF_CT_NAT_HELPER_INIT(name) \
+	{ \
+	.mod_name = NF_NAT_HELPER_NAME(name), \
+	.module = THIS_MODULE \
+	}
+
+void nf_nat_helper_register(struct nf_conntrack_nat_helper *nat);
+void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat);
+int nf_nat_helper_try_module_get(const char *name, u16 l3num,
+				 u8 protonum);
+void nf_nat_helper_put(struct nf_conntrack_helper *helper);
 #endif /*_NF_CONNTRACK_HELPER_H*/
diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c
index f2681ec5b5f6..dbec6fca0d9e 100644
--- a/net/netfilter/nf_conntrack_amanda.c
+++ b/net/netfilter/nf_conntrack_amanda.c
@@ -28,11 +28,13 @@
 static unsigned int master_timeout __read_mostly = 300;
 static char *ts_algo = "kmp";
 
+#define HELPER_NAME "amanda"
+
 MODULE_AUTHOR("Brian J. Murrell <netfilter@interlinx.bc.ca>");
 MODULE_DESCRIPTION("Amanda connection tracking module");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("ip_conntrack_amanda");
-MODULE_ALIAS_NFCT_HELPER("amanda");
+MODULE_ALIAS_NFCT_HELPER(HELPER_NAME);
 
 module_param(master_timeout, uint, 0600);
 MODULE_PARM_DESC(master_timeout, "timeout for the master connection");
@@ -179,13 +181,14 @@ static const struct nf_conntrack_expect_policy amanda_exp_policy = {
 
 static struct nf_conntrack_helper amanda_helper[2] __read_mostly = {
 	{
-		.name			= "amanda",
+		.name			= HELPER_NAME,
 		.me			= THIS_MODULE,
 		.help			= amanda_help,
 		.tuple.src.l3num	= AF_INET,
 		.tuple.src.u.udp.port	= cpu_to_be16(10080),
 		.tuple.dst.protonum	= IPPROTO_UDP,
 		.expect_policy		= &amanda_exp_policy,
+		.nat_mod_name		= NF_NAT_HELPER_NAME(HELPER_NAME),
 	},
 	{
 		.name			= "amanda",
@@ -195,6 +198,7 @@ static struct nf_conntrack_helper amanda_helper[2] __read_mostly = {
 		.tuple.src.u.udp.port	= cpu_to_be16(10080),
 		.tuple.dst.protonum	= IPPROTO_UDP,
 		.expect_policy		= &amanda_exp_policy,
+		.nat_mod_name		= NF_NAT_HELPER_NAME(HELPER_NAME),
 	},
 };
 
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index a11c304fb771..32aeac1c4760 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -29,11 +29,13 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <linux/netfilter/nf_conntrack_ftp.h>
 
+#define HELPER_NAME "ftp"
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>");
 MODULE_DESCRIPTION("ftp connection tracking helper");
 MODULE_ALIAS("ip_conntrack_ftp");
-MODULE_ALIAS_NFCT_HELPER("ftp");
+MODULE_ALIAS_NFCT_HELPER(HELPER_NAME);
 
 /* This is slow, but it's simple. --RR */
 static char *ftp_buffer;
@@ -588,12 +590,14 @@ static int __init nf_conntrack_ftp_init(void)
 	/* FIXME should be configurable whether IPv4 and IPv6 FTP connections
 		 are tracked or not - YK */
 	for (i = 0; i < ports_c; i++) {
-		nf_ct_helper_init(&ftp[2 * i], AF_INET, IPPROTO_TCP, "ftp",
-				  FTP_PORT, ports[i], ports[i], &ftp_exp_policy,
-				  0, help, nf_ct_ftp_from_nlattr, THIS_MODULE);
-		nf_ct_helper_init(&ftp[2 * i + 1], AF_INET6, IPPROTO_TCP, "ftp",
-				  FTP_PORT, ports[i], ports[i], &ftp_exp_policy,
-				  0, help, nf_ct_ftp_from_nlattr, THIS_MODULE);
+		nf_ct_helper_init(&ftp[2 * i], AF_INET, IPPROTO_TCP,
+				  HELPER_NAME, FTP_PORT, ports[i], ports[i],
+				  &ftp_exp_policy, 0, help,
+				  nf_ct_ftp_from_nlattr, THIS_MODULE);
+		nf_ct_helper_init(&ftp[2 * i + 1], AF_INET6, IPPROTO_TCP,
+				  HELPER_NAME, FTP_PORT, ports[i], ports[i],
+				  &ftp_exp_policy, 0, help,
+				  nf_ct_ftp_from_nlattr, THIS_MODULE);
 	}
 
 	ret = nf_conntrack_helpers_register(ftp, ports_c * 2);
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 274baf1dab87..918df7f71c8f 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -42,6 +42,9 @@ module_param_named(nf_conntrack_helper, nf_ct_auto_assign_helper, bool, 0644);
 MODULE_PARM_DESC(nf_conntrack_helper,
 		 "Enable automatic conntrack helper assignment (default 0)");
 
+static DEFINE_MUTEX(nf_ct_nat_helpers_mutex);
+static struct list_head nf_ct_nat_helpers __read_mostly;
+
 /* Stupid hash, but collision free for the default registrations of the
  * helpers currently in the kernel. */
 static unsigned int helper_hash(const struct nf_conntrack_tuple *tuple)
@@ -130,6 +133,70 @@ void nf_conntrack_helper_put(struct nf_conntrack_helper *helper)
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_put);
 
+static struct nf_conntrack_nat_helper *
+nf_conntrack_nat_helper_find(const char *mod_name)
+{
+	struct nf_conntrack_nat_helper *cur;
+	bool found = false;
+
+	list_for_each_entry_rcu(cur, &nf_ct_nat_helpers, list) {
+		if (!strcmp(cur->mod_name, mod_name)) {
+			found = true;
+			break;
+		}
+	}
+	return found ? cur : NULL;
+}
+
+int
+nf_nat_helper_try_module_get(const char *name, u16 l3num, u8 protonum)
+{
+	struct nf_conntrack_helper *h;
+	struct nf_conntrack_nat_helper *nat;
+	char mod_name[NF_CT_HELPER_NAME_LEN];
+	int ret = 0;
+
+	rcu_read_lock();
+	h = __nf_conntrack_helper_find(name, l3num, protonum);
+	if (!h) {
+		rcu_read_unlock();
+		return -ENOENT;
+	}
+
+	nat = nf_conntrack_nat_helper_find(h->nat_mod_name);
+	if (!nat) {
+		snprintf(mod_name, sizeof(mod_name), "%s", h->nat_mod_name);
+		rcu_read_unlock();
+		request_module(mod_name);
+
+		rcu_read_lock();
+		nat = nf_conntrack_nat_helper_find(mod_name);
+		if (!nat) {
+			rcu_read_unlock();
+			return -ENOENT;
+		}
+	}
+
+	if (!try_module_get(nat->module))
+		ret = -ENOENT;
+
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nf_nat_helper_try_module_get);
+
+void nf_nat_helper_put(struct nf_conntrack_helper *helper)
+{
+	struct nf_conntrack_nat_helper *nat;
+
+	nat = nf_conntrack_nat_helper_find(helper->nat_mod_name);
+	if (WARN_ON_ONCE(!nat))
+		return;
+
+	module_put(nat->module);
+}
+EXPORT_SYMBOL_GPL(nf_nat_helper_put);
+
 struct nf_conn_help *
 nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp)
 {
@@ -430,6 +497,8 @@ void nf_ct_helper_init(struct nf_conntrack_helper *helper,
 	helper->help = help;
 	helper->from_nlattr = from_nlattr;
 	helper->me = module;
+	snprintf(helper->nat_mod_name, sizeof(helper->nat_mod_name),
+		 NF_NAT_HELPER_PREFIX "%s", name);
 
 	if (spec_port == default_port)
 		snprintf(helper->name, sizeof(helper->name), "%s", name);
@@ -466,6 +535,22 @@ void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *helper,
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helpers_unregister);
 
+void nf_nat_helper_register(struct nf_conntrack_nat_helper *nat)
+{
+	mutex_lock(&nf_ct_nat_helpers_mutex);
+	list_add_rcu(&nat->list, &nf_ct_nat_helpers);
+	mutex_unlock(&nf_ct_nat_helpers_mutex);
+}
+EXPORT_SYMBOL_GPL(nf_nat_helper_register);
+
+void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat)
+{
+	mutex_lock(&nf_ct_nat_helpers_mutex);
+	list_del_rcu(&nat->list);
+	mutex_unlock(&nf_ct_nat_helpers_mutex);
+}
+EXPORT_SYMBOL_GPL(nf_nat_helper_unregister);
+
 static const struct nf_ct_ext_type helper_extend = {
 	.len	= sizeof(struct nf_conn_help),
 	.align	= __alignof__(struct nf_conn_help),
@@ -493,6 +578,7 @@ int nf_conntrack_helper_init(void)
 		goto out_extend;
 	}
 
+	INIT_LIST_HEAD(&nf_ct_nat_helpers);
 	return 0;
 out_extend:
 	kvfree(nf_ct_helper_hash);
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 4099f4d79bae..79e5014b3b0d 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -42,11 +42,13 @@ unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb,
 				struct nf_conntrack_expect *exp) __read_mostly;
 EXPORT_SYMBOL_GPL(nf_nat_irc_hook);
 
+#define HELPER_NAME "irc"
+
 MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
 MODULE_DESCRIPTION("IRC (DCC) connection tracking helper");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("ip_conntrack_irc");
-MODULE_ALIAS_NFCT_HELPER("irc");
+MODULE_ALIAS_NFCT_HELPER(HELPER_NAME);
 
 module_param_array(ports, ushort, &ports_c, 0400);
 MODULE_PARM_DESC(ports, "port numbers of IRC servers");
@@ -259,7 +261,7 @@ static int __init nf_conntrack_irc_init(void)
 		ports[ports_c++] = IRC_PORT;
 
 	for (i = 0; i < ports_c; i++) {
-		nf_ct_helper_init(&irc[i], AF_INET, IPPROTO_TCP, "irc",
+		nf_ct_helper_init(&irc[i], AF_INET, IPPROTO_TCP, HELPER_NAME,
 				  IRC_PORT, ports[i], i, &irc_exp_policy,
 				  0, help, NULL, THIS_MODULE);
 	}
diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c
index 5072ff96ab33..83306648dd0f 100644
--- a/net/netfilter/nf_conntrack_sane.c
+++ b/net/netfilter/nf_conntrack_sane.c
@@ -30,10 +30,12 @@
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <linux/netfilter/nf_conntrack_sane.h>
 
+#define HELPER_NAME "sane"
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Michal Schmidt <mschmidt@redhat.com>");
 MODULE_DESCRIPTION("SANE connection tracking helper");
-MODULE_ALIAS_NFCT_HELPER("sane");
+MODULE_ALIAS_NFCT_HELPER(HELPER_NAME);
 
 static char *sane_buffer;
 
@@ -195,12 +197,12 @@ static int __init nf_conntrack_sane_init(void)
 	/* FIXME should be configurable whether IPv4 and IPv6 connections
 		 are tracked or not - YK */
 	for (i = 0; i < ports_c; i++) {
-		nf_ct_helper_init(&sane[2 * i], AF_INET, IPPROTO_TCP, "sane",
-				  SANE_PORT, ports[i], ports[i],
+		nf_ct_helper_init(&sane[2 * i], AF_INET, IPPROTO_TCP,
+				  HELPER_NAME, SANE_PORT, ports[i], ports[i],
 				  &sane_exp_policy, 0, help, NULL,
 				  THIS_MODULE);
-		nf_ct_helper_init(&sane[2 * i + 1], AF_INET6, IPPROTO_TCP, "sane",
-				  SANE_PORT, ports[i], ports[i],
+		nf_ct_helper_init(&sane[2 * i + 1], AF_INET6, IPPROTO_TCP,
+				  HELPER_NAME, SANE_PORT, ports[i], ports[i],
 				  &sane_exp_policy, 0, help, NULL,
 				  THIS_MODULE);
 	}
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index d5454d1031a3..c30c883c370b 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -30,11 +30,13 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <linux/netfilter/nf_conntrack_sip.h>
 
+#define HELPER_NAME "sip"
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Christian Hentschel <chentschel@arnet.com.ar>");
 MODULE_DESCRIPTION("SIP connection tracking helper");
 MODULE_ALIAS("ip_conntrack_sip");
-MODULE_ALIAS_NFCT_HELPER("sip");
+MODULE_ALIAS_NFCT_HELPER(HELPER_NAME);
 
 #define MAX_PORTS	8
 static unsigned short ports[MAX_PORTS];
@@ -1669,21 +1671,21 @@ static int __init nf_conntrack_sip_init(void)
 		ports[ports_c++] = SIP_PORT;
 
 	for (i = 0; i < ports_c; i++) {
-		nf_ct_helper_init(&sip[4 * i], AF_INET, IPPROTO_UDP, "sip",
-				  SIP_PORT, ports[i], i, sip_exp_policy,
-				  SIP_EXPECT_MAX, sip_help_udp,
+		nf_ct_helper_init(&sip[4 * i], AF_INET, IPPROTO_UDP,
+				  HELPER_NAME, SIP_PORT, ports[i], i,
+				  sip_exp_policy, SIP_EXPECT_MAX, sip_help_udp,
 				  NULL, THIS_MODULE);
-		nf_ct_helper_init(&sip[4 * i + 1], AF_INET, IPPROTO_TCP, "sip",
-				  SIP_PORT, ports[i], i, sip_exp_policy,
-				  SIP_EXPECT_MAX, sip_help_tcp,
+		nf_ct_helper_init(&sip[4 * i + 1], AF_INET, IPPROTO_TCP,
+				  HELPER_NAME, SIP_PORT, ports[i], i,
+				  sip_exp_policy, SIP_EXPECT_MAX, sip_help_tcp,
 				  NULL, THIS_MODULE);
-		nf_ct_helper_init(&sip[4 * i + 2], AF_INET6, IPPROTO_UDP, "sip",
-				  SIP_PORT, ports[i], i, sip_exp_policy,
-				  SIP_EXPECT_MAX, sip_help_udp,
+		nf_ct_helper_init(&sip[4 * i + 2], AF_INET6, IPPROTO_UDP,
+				  HELPER_NAME, SIP_PORT, ports[i], i,
+				  sip_exp_policy, SIP_EXPECT_MAX, sip_help_udp,
 				  NULL, THIS_MODULE);
-		nf_ct_helper_init(&sip[4 * i + 3], AF_INET6, IPPROTO_TCP, "sip",
-				  SIP_PORT, ports[i], i, sip_exp_policy,
-				  SIP_EXPECT_MAX, sip_help_tcp,
+		nf_ct_helper_init(&sip[4 * i + 3], AF_INET6, IPPROTO_TCP,
+				  HELPER_NAME, SIP_PORT, ports[i], i,
+				  sip_exp_policy, SIP_EXPECT_MAX, sip_help_tcp,
 				  NULL, THIS_MODULE);
 	}
 
diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c
index 548b673b3625..6977cb91ae9a 100644
--- a/net/netfilter/nf_conntrack_tftp.c
+++ b/net/netfilter/nf_conntrack_tftp.c
@@ -20,11 +20,13 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <linux/netfilter/nf_conntrack_tftp.h>
 
+#define HELPER_NAME "tftp"
+
 MODULE_AUTHOR("Magnus Boden <mb@ozaba.mine.nu>");
 MODULE_DESCRIPTION("TFTP connection tracking helper");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("ip_conntrack_tftp");
-MODULE_ALIAS_NFCT_HELPER("tftp");
+MODULE_ALIAS_NFCT_HELPER(HELPER_NAME);
 
 #define MAX_PORTS 8
 static unsigned short ports[MAX_PORTS];
@@ -119,12 +121,14 @@ static int __init nf_conntrack_tftp_init(void)
 		ports[ports_c++] = TFTP_PORT;
 
 	for (i = 0; i < ports_c; i++) {
-		nf_ct_helper_init(&tftp[2 * i], AF_INET, IPPROTO_UDP, "tftp",
-				  TFTP_PORT, ports[i], i, &tftp_exp_policy,
-				  0, tftp_help, NULL, THIS_MODULE);
-		nf_ct_helper_init(&tftp[2 * i + 1], AF_INET6, IPPROTO_UDP, "tftp",
-				  TFTP_PORT, ports[i], i, &tftp_exp_policy,
-				  0, tftp_help, NULL, THIS_MODULE);
+		nf_ct_helper_init(&tftp[2 * i], AF_INET, IPPROTO_UDP,
+				  HELPER_NAME, TFTP_PORT, ports[i], i,
+				  &tftp_exp_policy, 0, tftp_help, NULL,
+				  THIS_MODULE);
+		nf_ct_helper_init(&tftp[2 * i + 1], AF_INET6, IPPROTO_UDP,
+				  HELPER_NAME, TFTP_PORT, ports[i], i,
+				  &tftp_exp_policy, 0, tftp_help, NULL,
+				  THIS_MODULE);
 	}
 
 	ret = nf_conntrack_helpers_register(tftp, ports_c * 2);
-- 
cgit v1.2.3


From 3087c3f7c23b9c54b956ee5519e97a42413ddf22 Mon Sep 17 00:00:00 2001
From: Brett Mastbergen <bmastbergen@untangle.com>
Date: Wed, 24 Apr 2019 10:48:44 -0400
Subject: netfilter: nft_ct: Add ct id support

The 'id' key returns the unique id of the conntrack entry as returned
by nf_ct_get_id().

Signed-off-by: Brett Mastbergen <bmastbergen@untangle.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 2 ++
 net/netfilter/nft_ct.c                   | 8 ++++++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 061bb3eb20c3..f0cf7b0f4f35 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -967,6 +967,7 @@ enum nft_socket_keys {
  * @NFT_CT_SRC_IP6: conntrack layer 3 protocol source (IPv6 address)
  * @NFT_CT_DST_IP6: conntrack layer 3 protocol destination (IPv6 address)
  * @NFT_CT_TIMEOUT: connection tracking timeout policy assigned to conntrack
+ * @NFT_CT_ID: conntrack id
  */
 enum nft_ct_keys {
 	NFT_CT_STATE,
@@ -993,6 +994,7 @@ enum nft_ct_keys {
 	NFT_CT_SRC_IP6,
 	NFT_CT_DST_IP6,
 	NFT_CT_TIMEOUT,
+	NFT_CT_ID,
 	__NFT_CT_MAX
 };
 #define NFT_CT_MAX		(__NFT_CT_MAX - 1)
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index b422b74bfe08..f043936763f3 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -178,6 +178,11 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 		return;
 	}
 #endif
+	case NFT_CT_ID:
+		if (!nf_ct_is_confirmed(ct))
+			goto err;
+		*dest = nf_ct_get_id(ct);
+		return;
 	default:
 		break;
 	}
@@ -479,6 +484,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx,
 		len = sizeof(u16);
 		break;
 #endif
+	case NFT_CT_ID:
+		len = sizeof(u32);
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From 33162e9a0590f16e1b21be764caae517e2bb310c Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 28 Apr 2019 21:45:43 +0300
Subject: net: dsa: Store vlan_filtering as a property of dsa_port

This allows drivers to query the VLAN setting imposed by the bridge
driver directly from DSA, instead of keeping their own state based on
the .port_vlan_filtering callback.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  1 +
 net/dsa/port.c    | 12 ++++++++----
 2 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index b550f7bb5314..79a87913126c 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -161,6 +161,7 @@ struct dsa_port {
 	const char		*mac;
 	struct device_node	*dn;
 	unsigned int		ageing_time;
+	bool			vlan_filtering;
 	u8			stp_state;
 	struct net_device	*bridge_dev;
 	struct devlink_port	devlink_port;
diff --git a/net/dsa/port.c b/net/dsa/port.c
index caeef4c99dc0..a86fe3be1261 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -158,15 +158,19 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
 			    struct switchdev_trans *trans)
 {
 	struct dsa_switch *ds = dp->ds;
+	int err;
 
 	/* bridge skips -EOPNOTSUPP, so skip the prepare phase */
 	if (switchdev_trans_ph_prepare(trans))
 		return 0;
 
-	if (ds->ops->port_vlan_filtering)
-		return ds->ops->port_vlan_filtering(ds, dp->index,
-						    vlan_filtering);
-
+	if (ds->ops->port_vlan_filtering) {
+		err = ds->ops->port_vlan_filtering(ds, dp->index,
+						   vlan_filtering);
+		if (err)
+			return err;
+		dp->vlan_filtering = vlan_filtering;
+	}
 	return 0;
 }
 
-- 
cgit v1.2.3


From 8f5d16f638b9a1adf544a7f8cfd11ac1c01c6e25 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 28 Apr 2019 21:45:44 +0300
Subject: net: dsa: Be aware of switches where VLAN filtering is a global
 setting

On some switches, the action of whether to parse VLAN frame headers and use
that information for ingress admission is configurable, but not per
port. Such is the case for the Broadcom BCM53xx and the NXP SJA1105
families, for example. In that case, DSA can prevent the bridge core
from trying to apply different VLAN filtering settings on net devices
that belong to the same switch.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Suggested-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  5 +++++
 net/dsa/port.c    | 52 +++++++++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 50 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 79a87913126c..aab3c2029edd 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -228,6 +228,11 @@ struct dsa_switch {
 	/* Number of switch port queues */
 	unsigned int		num_tx_queues;
 
+	/* Disallow bridge core from requesting different VLAN awareness
+	 * settings on ports if not hardware-supported
+	 */
+	bool			vlan_filtering_is_global;
+
 	unsigned long		*bitmap;
 	unsigned long		_bitmap;
 
diff --git a/net/dsa/port.c b/net/dsa/port.c
index a86fe3be1261..9a6ed138878c 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -154,6 +154,39 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br)
 	dsa_port_set_state_now(dp, BR_STATE_FORWARDING);
 }
 
+static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp,
+					      bool vlan_filtering)
+{
+	struct dsa_switch *ds = dp->ds;
+	int i;
+
+	if (!ds->vlan_filtering_is_global)
+		return true;
+
+	/* For cases where enabling/disabling VLAN awareness is global to the
+	 * switch, we need to handle the case where multiple bridges span
+	 * different ports of the same switch device and one of them has a
+	 * different setting than what is being requested.
+	 */
+	for (i = 0; i < ds->num_ports; i++) {
+		struct net_device *other_bridge;
+
+		other_bridge = dsa_to_port(ds, i)->bridge_dev;
+		if (!other_bridge)
+			continue;
+		/* If it's the same bridge, it also has same
+		 * vlan_filtering setting => no need to check
+		 */
+		if (other_bridge == dp->bridge_dev)
+			continue;
+		if (br_vlan_enabled(other_bridge) != vlan_filtering) {
+			dev_err(ds->dev, "VLAN filtering is a global setting\n");
+			return false;
+		}
+	}
+	return true;
+}
+
 int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
 			    struct switchdev_trans *trans)
 {
@@ -164,13 +197,18 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
 	if (switchdev_trans_ph_prepare(trans))
 		return 0;
 
-	if (ds->ops->port_vlan_filtering) {
-		err = ds->ops->port_vlan_filtering(ds, dp->index,
-						   vlan_filtering);
-		if (err)
-			return err;
-		dp->vlan_filtering = vlan_filtering;
-	}
+	if (!ds->ops->port_vlan_filtering)
+		return 0;
+
+	if (!dsa_port_can_apply_vlan_filtering(dp, vlan_filtering))
+		return -EINVAL;
+
+	err = ds->ops->port_vlan_filtering(ds, dp->index,
+					   vlan_filtering);
+	if (err)
+		return err;
+
+	dp->vlan_filtering = vlan_filtering;
 	return 0;
 }
 
-- 
cgit v1.2.3


From 145746765f06a3dbc7869c81d0165b3ab96f935a Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 28 Apr 2019 21:45:48 +0300
Subject: net: dsa: Keep the vlan_filtering setting in dsa_switch if it's
 global

The current behavior is not as obvious as one would assume (which is
that, if the driver set vlan_filtering_is_global = 1, then checking any
dp->vlan_filtering would yield the same result). Only the ports which
are actively enslaved into a bridge would have vlan_filtering set.

This makes it tricky for drivers to check what the global state is.
So fix this and make the struct dsa_switch hold this global setting.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 5 +++++
 net/dsa/port.c    | 5 ++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index aab3c2029edd..4e0f7e9c5aa1 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -233,6 +233,11 @@ struct dsa_switch {
 	 */
 	bool			vlan_filtering_is_global;
 
+	/* In case vlan_filtering_is_global is set, the VLAN awareness state
+	 * should be retrieved from here and not from the per-port settings.
+	 */
+	bool			vlan_filtering;
+
 	unsigned long		*bitmap;
 	unsigned long		_bitmap;
 
diff --git a/net/dsa/port.c b/net/dsa/port.c
index 9a6ed138878c..c27c16b69ab6 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -208,7 +208,10 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
 	if (err)
 		return err;
 
-	dp->vlan_filtering = vlan_filtering;
+	if (ds->vlan_filtering_is_global)
+		ds->vlan_filtering = vlan_filtering;
+	else
+		dp->vlan_filtering = vlan_filtering;
 	return 0;
 }
 
-- 
cgit v1.2.3


From cf2d45f5ba9a730df6ec190e0345cecde80b1d8b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 28 Apr 2019 21:45:49 +0300
Subject: net: dsa: Add helper function to retrieve VLAN awareness setting

Since different types of hardware may or may not support this setting
per-port, DSA keeps it either in dsa_switch or in dsa_port.

While drivers may know the characteristics of their hardware and
retrieve it from the correct place without the need of helpers, it is
cumbersone to find out an unambigous answer from generic DSA code.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 4e0f7e9c5aa1..1e6b4efc80b9 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -305,6 +305,16 @@ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port)
 	return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index);
 }
 
+static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp)
+{
+	const struct dsa_switch *ds = dp->ds;
+
+	if (ds->vlan_filtering_is_global)
+		return ds->vlan_filtering;
+	else
+		return dp->vlan_filtering;
+}
+
 typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid,
 			      bool is_static, void *data);
 struct dsa_switch_ops {
-- 
cgit v1.2.3


From 93e86b3bc842c159a60e6987444bf3952adcd4db Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Sun, 28 Apr 2019 02:56:23 +0200
Subject: net: dsa: Remove legacy probing support

Now that all drivers can be probed using more traditional methods,
remove the legacy probe code.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h  |  23 --
 net/dsa/Kconfig    |   9 -
 net/dsa/Makefile   |   1 -
 net/dsa/dsa.c      |   5 -
 net/dsa/dsa_priv.h |  12 -
 net/dsa/legacy.c   | 747 -----------------------------------------------------
 6 files changed, 797 deletions(-)
 delete mode 100644 net/dsa/legacy.c

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 1e6b4efc80b9..18db7b8e7a8e 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -318,15 +318,6 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp)
 typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid,
 			      bool is_static, void *data);
 struct dsa_switch_ops {
-#if IS_ENABLED(CONFIG_NET_DSA_LEGACY)
-	/*
-	 * Legacy probing.
-	 */
-	const char	*(*probe)(struct device *dsa_dev,
-				  struct device *host_dev, int sw_addr,
-				  void **priv);
-#endif
-
 	enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds,
 						  int port);
 
@@ -516,20 +507,6 @@ struct dsa_switch_driver {
 	const struct dsa_switch_ops *ops;
 };
 
-#if IS_ENABLED(CONFIG_NET_DSA_LEGACY)
-/* Legacy driver registration */
-void register_switch_driver(struct dsa_switch_driver *type);
-void unregister_switch_driver(struct dsa_switch_driver *type);
-struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev);
-
-#else
-static inline void register_switch_driver(struct dsa_switch_driver *type) { }
-static inline void unregister_switch_driver(struct dsa_switch_driver *type) { }
-static inline struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev)
-{
-	return NULL;
-}
-#endif
 struct net_device *dsa_dev_to_net_device(struct device *dev);
 
 /* Keep inline for faster access in hot path */
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 1f48642089ea..c0734028c7dc 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -17,15 +17,6 @@ menuconfig NET_DSA
 
 if NET_DSA
 
-config NET_DSA_LEGACY
-	bool "Support for older platform device and Device Tree registration"
-	default y
-	---help---
-	  Say Y if you want to enable support for the older platform device and
-	  deprecated Device Tree binding registration.
-
-	  This feature is scheduled for removal in 4.17.
-
 config NET_DSA_TAG_BRCM_COMMON
 	tristate
 	default n
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 717ac1618100..8a737b6ee94c 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -2,7 +2,6 @@
 # the core
 obj-$(CONFIG_NET_DSA) += dsa_core.o
 dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o
-dsa_core-$(CONFIG_NET_DSA_LEGACY) += legacy.o
 
 # tagging formats
 obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index ba04c78633be..9e1fc0b08290 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -346,10 +346,6 @@ static int __init dsa_init_module(void)
 	if (rc)
 		return rc;
 
-	rc = dsa_legacy_register();
-	if (rc)
-		return rc;
-
 	dev_add_pack(&dsa_pack_type);
 
 	dsa_tag_driver_register(&DSA_TAG_DRIVER_NAME(none_ops),
@@ -365,7 +361,6 @@ static void __exit dsa_cleanup_module(void)
 
 	dsa_slave_unregister_notifier();
 	dev_remove_pack(&dsa_pack_type);
-	dsa_legacy_unregister();
 	destroy_workqueue(dsa_owq);
 }
 module_exit(dsa_cleanup_module);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 37751b505572..b434f5ff55ab 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -90,18 +90,6 @@ void dsa_tag_driver_put(const struct dsa_device_ops *ops);
 bool dsa_schedule_work(struct work_struct *work);
 const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops);
 
-/* legacy.c */
-#if IS_ENABLED(CONFIG_NET_DSA_LEGACY)
-int dsa_legacy_register(void);
-void dsa_legacy_unregister(void);
-#else
-static inline int dsa_legacy_register(void)
-{
-	return 0;
-}
-
-static inline void dsa_legacy_unregister(void) { }
-#endif
 int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		       struct net_device *dev,
 		       const unsigned char *addr, u16 vid,
diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c
deleted file mode 100644
index 219f4fa7ff4b..000000000000
--- a/net/dsa/legacy.c
+++ /dev/null
@@ -1,747 +0,0 @@
-/*
- * net/dsa/legacy.c - Hardware switch handling
- * Copyright (c) 2008-2009 Marvell Semiconductor
- * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <linux/device.h>
-#include <linux/list.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_mdio.h>
-#include <linux/of_platform.h>
-#include <linux/of_net.h>
-#include <linux/netdevice.h>
-#include <linux/sysfs.h>
-#include <linux/phy_fixed.h>
-#include <linux/etherdevice.h>
-
-#include "dsa_priv.h"
-
-/* switch driver registration ***********************************************/
-static DEFINE_MUTEX(dsa_switch_drivers_mutex);
-static LIST_HEAD(dsa_switch_drivers);
-
-void register_switch_driver(struct dsa_switch_driver *drv)
-{
-	mutex_lock(&dsa_switch_drivers_mutex);
-	list_add_tail(&drv->list, &dsa_switch_drivers);
-	mutex_unlock(&dsa_switch_drivers_mutex);
-}
-EXPORT_SYMBOL_GPL(register_switch_driver);
-
-void unregister_switch_driver(struct dsa_switch_driver *drv)
-{
-	mutex_lock(&dsa_switch_drivers_mutex);
-	list_del_init(&drv->list);
-	mutex_unlock(&dsa_switch_drivers_mutex);
-}
-EXPORT_SYMBOL_GPL(unregister_switch_driver);
-
-static const struct dsa_switch_ops *
-dsa_switch_probe(struct device *parent, struct device *host_dev, int sw_addr,
-		 const char **_name, void **priv)
-{
-	const struct dsa_switch_ops *ret;
-	struct list_head *list;
-	const char *name;
-
-	ret = NULL;
-	name = NULL;
-
-	mutex_lock(&dsa_switch_drivers_mutex);
-	list_for_each(list, &dsa_switch_drivers) {
-		const struct dsa_switch_ops *ops;
-		struct dsa_switch_driver *drv;
-
-		drv = list_entry(list, struct dsa_switch_driver, list);
-		ops = drv->ops;
-
-		name = ops->probe(parent, host_dev, sw_addr, priv);
-		if (name != NULL) {
-			ret = ops;
-			break;
-		}
-	}
-	mutex_unlock(&dsa_switch_drivers_mutex);
-
-	*_name = name;
-
-	return ret;
-}
-
-/* basic switch operations **************************************************/
-static int dsa_cpu_dsa_setups(struct dsa_switch *ds)
-{
-	int ret, port;
-
-	for (port = 0; port < ds->num_ports; port++) {
-		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
-			continue;
-
-		ret = dsa_port_link_register_of(&ds->ports[port]);
-		if (ret)
-			return ret;
-	}
-	return 0;
-}
-
-static int dsa_switch_setup_one(struct dsa_switch *ds,
-				struct net_device *master)
-{
-	const struct dsa_switch_ops *ops = ds->ops;
-	struct dsa_switch_tree *dst = ds->dst;
-	struct dsa_chip_data *cd = ds->cd;
-	bool valid_name_found = false;
-	int index = ds->index;
-	struct dsa_port *dp;
-	int i, ret;
-
-	/*
-	 * Validate supplied switch configuration.
-	 */
-	for (i = 0; i < ds->num_ports; i++) {
-		char *name;
-
-		dp = &ds->ports[i];
-
-		name = cd->port_names[i];
-		if (name == NULL)
-			continue;
-		dp->name = name;
-
-		if (!strcmp(name, "cpu")) {
-			if (dst->cpu_dp) {
-				netdev_err(master,
-					   "multiple cpu ports?!\n");
-				return -EINVAL;
-			}
-			dst->cpu_dp = &ds->ports[i];
-			dst->cpu_dp->master = master;
-			dp->type = DSA_PORT_TYPE_CPU;
-		} else if (!strcmp(name, "dsa")) {
-			dp->type = DSA_PORT_TYPE_DSA;
-		} else {
-			dp->type = DSA_PORT_TYPE_USER;
-		}
-		valid_name_found = true;
-	}
-
-	if (!valid_name_found && i == ds->num_ports)
-		return -EINVAL;
-
-	/* Make the built-in MII bus mask match the number of ports,
-	 * switch drivers can override this later
-	 */
-	ds->phys_mii_mask |= dsa_user_ports(ds);
-
-	/*
-	 * If the CPU connects to this switch, set the switch tree
-	 * tagging protocol to the preferred tagging format of this
-	 * switch.
-	 */
-	if (dst->cpu_dp->ds == ds) {
-		const struct dsa_device_ops *tag_ops;
-		enum dsa_tag_protocol tag_protocol;
-
-		tag_protocol = ops->get_tag_protocol(ds, dst->cpu_dp->index);
-		tag_ops = dsa_tag_driver_get(tag_protocol);
-		if (IS_ERR(tag_ops))
-			return PTR_ERR(tag_ops);
-
-		dst->cpu_dp->tag_ops = tag_ops;
-
-		/* Few copies for faster access in master receive hot path */
-		dst->cpu_dp->rcv = dst->cpu_dp->tag_ops->rcv;
-		dst->cpu_dp->dst = dst;
-	}
-
-	dsa_tag_driver_put(dst->cpu_dp->tag_ops);
-
-	memcpy(ds->rtable, cd->rtable, sizeof(ds->rtable));
-
-	/*
-	 * Do basic register setup.
-	 */
-	ret = ops->setup(ds);
-	if (ret < 0)
-		return ret;
-
-	ret = dsa_switch_register_notifier(ds);
-	if (ret)
-		return ret;
-
-	if (!ds->slave_mii_bus && ops->phy_read) {
-		ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
-		if (!ds->slave_mii_bus)
-			return -ENOMEM;
-		dsa_slave_mii_bus_init(ds);
-
-		ret = mdiobus_register(ds->slave_mii_bus);
-		if (ret < 0)
-			return ret;
-	}
-
-	/*
-	 * Create network devices for physical switch ports.
-	 */
-	for (i = 0; i < ds->num_ports; i++) {
-		ds->ports[i].dn = cd->port_dn[i];
-		ds->ports[i].cpu_dp = dst->cpu_dp;
-
-		if (!dsa_is_user_port(ds, i))
-			continue;
-
-		ret = dsa_slave_create(&ds->ports[i]);
-		if (ret < 0)
-			netdev_err(master, "[%d]: can't create dsa slave device for port %d(%s): %d\n",
-				   index, i, cd->port_names[i], ret);
-	}
-
-	/* Perform configuration of the CPU and DSA ports */
-	ret = dsa_cpu_dsa_setups(ds);
-	if (ret < 0)
-		netdev_err(master, "[%d] : can't configure CPU and DSA ports\n",
-			   index);
-
-	return 0;
-}
-
-static struct dsa_switch *
-dsa_switch_setup(struct dsa_switch_tree *dst, struct net_device *master,
-		 int index, struct device *parent, struct device *host_dev)
-{
-	struct dsa_chip_data *cd = dst->pd->chip + index;
-	const struct dsa_switch_ops *ops;
-	struct dsa_switch *ds;
-	int ret;
-	const char *name;
-	void *priv;
-
-	/*
-	 * Probe for switch model.
-	 */
-	ops = dsa_switch_probe(parent, host_dev, cd->sw_addr, &name, &priv);
-	if (!ops) {
-		netdev_err(master, "[%d]: could not detect attached switch\n",
-			   index);
-		return ERR_PTR(-EINVAL);
-	}
-	netdev_info(master, "[%d]: detected a %s switch\n",
-		    index, name);
-
-
-	/*
-	 * Allocate and initialise switch state.
-	 */
-	ds = dsa_switch_alloc(parent, DSA_MAX_PORTS);
-	if (!ds)
-		return ERR_PTR(-ENOMEM);
-
-	ds->dst = dst;
-	ds->index = index;
-	ds->cd = cd;
-	ds->ops = ops;
-	ds->priv = priv;
-
-	ret = dsa_switch_setup_one(ds, master);
-	if (ret)
-		return ERR_PTR(ret);
-
-	return ds;
-}
-
-static void dsa_switch_destroy(struct dsa_switch *ds)
-{
-	int port;
-
-	/* Destroy network devices for physical switch ports. */
-	for (port = 0; port < ds->num_ports; port++) {
-		if (!dsa_is_user_port(ds, port))
-			continue;
-
-		if (!ds->ports[port].slave)
-			continue;
-
-		dsa_slave_destroy(ds->ports[port].slave);
-	}
-
-	/* Disable configuration of the CPU and DSA ports */
-	for (port = 0; port < ds->num_ports; port++) {
-		if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
-			continue;
-		dsa_port_link_unregister_of(&ds->ports[port]);
-	}
-
-	if (ds->slave_mii_bus && ds->ops->phy_read)
-		mdiobus_unregister(ds->slave_mii_bus);
-
-	dsa_switch_unregister_notifier(ds);
-}
-
-/* platform driver init and cleanup *****************************************/
-static int dev_is_class(struct device *dev, void *class)
-{
-	if (dev->class != NULL && !strcmp(dev->class->name, class))
-		return 1;
-
-	return 0;
-}
-
-static struct device *dev_find_class(struct device *parent, char *class)
-{
-	if (dev_is_class(parent, class)) {
-		get_device(parent);
-		return parent;
-	}
-
-	return device_find_child(parent, class, dev_is_class);
-}
-
-struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev)
-{
-	struct device *d;
-
-	d = dev_find_class(dev, "mdio_bus");
-	if (d != NULL) {
-		struct mii_bus *bus;
-
-		bus = to_mii_bus(d);
-		put_device(d);
-
-		return bus;
-	}
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(dsa_host_dev_to_mii_bus);
-
-#ifdef CONFIG_OF
-static int dsa_of_setup_routing_table(struct dsa_platform_data *pd,
-					struct dsa_chip_data *cd,
-					int chip_index, int port_index,
-					struct device_node *link)
-{
-	const __be32 *reg;
-	int link_sw_addr;
-	struct device_node *parent_sw;
-	int len;
-
-	parent_sw = of_get_parent(link);
-	if (!parent_sw)
-		return -EINVAL;
-
-	reg = of_get_property(parent_sw, "reg", &len);
-	if (!reg || (len != sizeof(*reg) * 2))
-		return -EINVAL;
-
-	/*
-	 * Get the destination switch number from the second field of its 'reg'
-	 * property, i.e. for "reg = <0x19 1>" sw_addr is '1'.
-	 */
-	link_sw_addr = be32_to_cpup(reg + 1);
-
-	if (link_sw_addr >= pd->nr_chips)
-		return -EINVAL;
-
-	cd->rtable[link_sw_addr] = port_index;
-
-	return 0;
-}
-
-static int dsa_of_probe_links(struct dsa_platform_data *pd,
-			      struct dsa_chip_data *cd,
-			      int chip_index, int port_index,
-			      struct device_node *port,
-			      const char *port_name)
-{
-	struct device_node *link;
-	int link_index;
-	int ret;
-
-	for (link_index = 0;; link_index++) {
-		link = of_parse_phandle(port, "link", link_index);
-		if (!link)
-			break;
-
-		if (!strcmp(port_name, "dsa") && pd->nr_chips > 1) {
-			ret = dsa_of_setup_routing_table(pd, cd, chip_index,
-							 port_index, link);
-			if (ret)
-				return ret;
-		}
-	}
-	return 0;
-}
-
-static void dsa_of_free_platform_data(struct dsa_platform_data *pd)
-{
-	int i;
-	int port_index;
-
-	for (i = 0; i < pd->nr_chips; i++) {
-		port_index = 0;
-		while (port_index < DSA_MAX_PORTS) {
-			kfree(pd->chip[i].port_names[port_index]);
-			port_index++;
-		}
-
-		/* Drop our reference to the MDIO bus device */
-		put_device(pd->chip[i].host_dev);
-	}
-	kfree(pd->chip);
-}
-
-static int dsa_of_probe(struct device *dev)
-{
-	struct device_node *np = dev->of_node;
-	struct device_node *child, *mdio, *ethernet, *port;
-	struct mii_bus *mdio_bus, *mdio_bus_switch;
-	struct net_device *ethernet_dev;
-	struct dsa_platform_data *pd;
-	struct dsa_chip_data *cd;
-	const char *port_name;
-	int chip_index, port_index;
-	const unsigned int *sw_addr, *port_reg;
-	u32 eeprom_len;
-	int ret;
-
-	mdio = of_parse_phandle(np, "dsa,mii-bus", 0);
-	if (!mdio)
-		return -EINVAL;
-
-	mdio_bus = of_mdio_find_bus(mdio);
-	if (!mdio_bus)
-		return -EPROBE_DEFER;
-
-	ethernet = of_parse_phandle(np, "dsa,ethernet", 0);
-	if (!ethernet) {
-		ret = -EINVAL;
-		goto out_put_mdio;
-	}
-
-	ethernet_dev = of_find_net_device_by_node(ethernet);
-	if (!ethernet_dev) {
-		ret = -EPROBE_DEFER;
-		goto out_put_mdio;
-	}
-
-	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
-	if (!pd) {
-		ret = -ENOMEM;
-		goto out_put_ethernet;
-	}
-
-	dev->platform_data = pd;
-	pd->of_netdev = ethernet_dev;
-	pd->nr_chips = of_get_available_child_count(np);
-	if (pd->nr_chips > DSA_MAX_SWITCHES)
-		pd->nr_chips = DSA_MAX_SWITCHES;
-
-	pd->chip = kcalloc(pd->nr_chips, sizeof(struct dsa_chip_data),
-			   GFP_KERNEL);
-	if (!pd->chip) {
-		ret = -ENOMEM;
-		goto out_free;
-	}
-
-	chip_index = -1;
-	for_each_available_child_of_node(np, child) {
-		int i;
-
-		chip_index++;
-		cd = &pd->chip[chip_index];
-
-		cd->of_node = child;
-
-		/* Initialize the routing table */
-		for (i = 0; i < DSA_MAX_SWITCHES; ++i)
-			cd->rtable[i] = DSA_RTABLE_NONE;
-
-		/* When assigning the host device, increment its refcount */
-		cd->host_dev = get_device(&mdio_bus->dev);
-
-		sw_addr = of_get_property(child, "reg", NULL);
-		if (!sw_addr)
-			continue;
-
-		cd->sw_addr = be32_to_cpup(sw_addr);
-		if (cd->sw_addr >= PHY_MAX_ADDR)
-			continue;
-
-		if (!of_property_read_u32(child, "eeprom-length", &eeprom_len))
-			cd->eeprom_len = eeprom_len;
-
-		mdio = of_parse_phandle(child, "mii-bus", 0);
-		if (mdio) {
-			mdio_bus_switch = of_mdio_find_bus(mdio);
-			if (!mdio_bus_switch) {
-				ret = -EPROBE_DEFER;
-				goto out_free_chip;
-			}
-
-			/* Drop the mdio_bus device ref, replacing the host
-			 * device with the mdio_bus_switch device, keeping
-			 * the refcount from of_mdio_find_bus() above.
-			 */
-			put_device(cd->host_dev);
-			cd->host_dev = &mdio_bus_switch->dev;
-		}
-
-		for_each_available_child_of_node(child, port) {
-			port_reg = of_get_property(port, "reg", NULL);
-			if (!port_reg)
-				continue;
-
-			port_index = be32_to_cpup(port_reg);
-			if (port_index >= DSA_MAX_PORTS)
-				break;
-
-			port_name = of_get_property(port, "label", NULL);
-			if (!port_name)
-				continue;
-
-			cd->port_dn[port_index] = port;
-
-			cd->port_names[port_index] = kstrdup(port_name,
-					GFP_KERNEL);
-			if (!cd->port_names[port_index]) {
-				ret = -ENOMEM;
-				goto out_free_chip;
-			}
-
-			ret = dsa_of_probe_links(pd, cd, chip_index,
-						 port_index, port, port_name);
-			if (ret)
-				goto out_free_chip;
-
-		}
-	}
-
-	/* The individual chips hold their own refcount on the mdio bus,
-	 * so drop ours */
-	put_device(&mdio_bus->dev);
-
-	return 0;
-
-out_free_chip:
-	dsa_of_free_platform_data(pd);
-out_free:
-	kfree(pd);
-	dev->platform_data = NULL;
-out_put_ethernet:
-	put_device(&ethernet_dev->dev);
-out_put_mdio:
-	put_device(&mdio_bus->dev);
-	return ret;
-}
-
-static void dsa_of_remove(struct device *dev)
-{
-	struct dsa_platform_data *pd = dev->platform_data;
-
-	if (!dev->of_node)
-		return;
-
-	dsa_of_free_platform_data(pd);
-	put_device(&pd->of_netdev->dev);
-	kfree(pd);
-}
-#else
-static inline int dsa_of_probe(struct device *dev)
-{
-	return 0;
-}
-
-static inline void dsa_of_remove(struct device *dev)
-{
-}
-#endif
-
-static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev,
-			 struct device *parent, struct dsa_platform_data *pd)
-{
-	int i;
-	unsigned configured = 0;
-
-	dst->pd = pd;
-
-	for (i = 0; i < pd->nr_chips; i++) {
-		struct dsa_switch *ds;
-
-		ds = dsa_switch_setup(dst, dev, i, parent, pd->chip[i].host_dev);
-		if (IS_ERR(ds)) {
-			netdev_err(dev, "[%d]: couldn't create dsa switch instance (error %ld)\n",
-				   i, PTR_ERR(ds));
-			continue;
-		}
-
-		dst->ds[i] = ds;
-
-		++configured;
-	}
-
-	/*
-	 * If no switch was found, exit cleanly
-	 */
-	if (!configured)
-		return -EPROBE_DEFER;
-
-	return dsa_master_setup(dst->cpu_dp->master, dst->cpu_dp);
-}
-
-static int dsa_probe(struct platform_device *pdev)
-{
-	struct dsa_platform_data *pd = pdev->dev.platform_data;
-	struct net_device *dev;
-	struct dsa_switch_tree *dst;
-	int ret;
-
-	if (pdev->dev.of_node) {
-		ret = dsa_of_probe(&pdev->dev);
-		if (ret)
-			return ret;
-
-		pd = pdev->dev.platform_data;
-	}
-
-	if (pd == NULL || (pd->netdev == NULL && pd->of_netdev == NULL))
-		return -EINVAL;
-
-	if (pd->of_netdev) {
-		dev = pd->of_netdev;
-		dev_hold(dev);
-	} else {
-		dev = dsa_dev_to_net_device(pd->netdev);
-	}
-	if (dev == NULL) {
-		ret = -EPROBE_DEFER;
-		goto out;
-	}
-
-	if (dev->dsa_ptr != NULL) {
-		dev_put(dev);
-		ret = -EEXIST;
-		goto out;
-	}
-
-	dst = devm_kzalloc(&pdev->dev, sizeof(*dst), GFP_KERNEL);
-	if (dst == NULL) {
-		dev_put(dev);
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	platform_set_drvdata(pdev, dst);
-
-	ret = dsa_setup_dst(dst, dev, &pdev->dev, pd);
-	if (ret) {
-		dev_put(dev);
-		goto out;
-	}
-
-	return 0;
-
-out:
-	dsa_of_remove(&pdev->dev);
-
-	return ret;
-}
-
-static void dsa_remove_dst(struct dsa_switch_tree *dst)
-{
-	int i;
-
-	dsa_master_teardown(dst->cpu_dp->master);
-
-	for (i = 0; i < dst->pd->nr_chips; i++) {
-		struct dsa_switch *ds = dst->ds[i];
-
-		if (ds)
-			dsa_switch_destroy(ds);
-	}
-
-	dev_put(dst->cpu_dp->master);
-}
-
-static int dsa_remove(struct platform_device *pdev)
-{
-	struct dsa_switch_tree *dst = platform_get_drvdata(pdev);
-
-	dsa_remove_dst(dst);
-	dsa_of_remove(&pdev->dev);
-
-	return 0;
-}
-
-static void dsa_shutdown(struct platform_device *pdev)
-{
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int dsa_suspend(struct device *d)
-{
-	struct dsa_switch_tree *dst = dev_get_drvdata(d);
-	int i, ret = 0;
-
-	for (i = 0; i < dst->pd->nr_chips; i++) {
-		struct dsa_switch *ds = dst->ds[i];
-
-		if (ds != NULL)
-			ret = dsa_switch_suspend(ds);
-	}
-
-	return ret;
-}
-
-static int dsa_resume(struct device *d)
-{
-	struct dsa_switch_tree *dst = dev_get_drvdata(d);
-	int i, ret = 0;
-
-	for (i = 0; i < dst->pd->nr_chips; i++) {
-		struct dsa_switch *ds = dst->ds[i];
-
-		if (ds != NULL)
-			ret = dsa_switch_resume(ds);
-	}
-
-	return ret;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(dsa_pm_ops, dsa_suspend, dsa_resume);
-
-static const struct of_device_id dsa_of_match_table[] = {
-	{ .compatible = "marvell,dsa", },
-	{}
-};
-MODULE_DEVICE_TABLE(of, dsa_of_match_table);
-
-static struct platform_driver dsa_driver = {
-	.probe		= dsa_probe,
-	.remove		= dsa_remove,
-	.shutdown	= dsa_shutdown,
-	.driver = {
-		.name	= "dsa",
-		.of_match_table = dsa_of_match_table,
-		.pm	= &dsa_pm_ops,
-	},
-};
-
-int dsa_legacy_register(void)
-{
-	return platform_driver_register(&dsa_driver);
-}
-
-void dsa_legacy_unregister(void)
-{
-	platform_driver_unregister(&dsa_driver);
-}
-- 
cgit v1.2.3


From b587bdaf5f820cf7dac2c1b351db97bf98e1f427 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Mon, 29 Apr 2019 12:41:45 +0300
Subject: devlink: Change devlink health locking mechanism

The devlink health reporters create/destroy and user commands currently
use the devlink->lock as a locking mechanism. Different reporters have
different rules in the driver and are being created/destroyed during
different stages of driver load/unload/running. So during execution of a
reporter recover the flow can go through another reporter's destroy and
create. Such flow leads to deadlock trying to lock a mutex already
held.

With the new locking mechanism the different reporters share mutex lock
only to protect access to shared reporters list.
Added refcount per reporter, to protect the reporters from destroy while
being used.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h |  1 +
 net/core/devlink.c    | 97 +++++++++++++++++++++++++++++++++++++++------------
 2 files changed, 75 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 4f5e41613503..1c4adfb4195a 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -32,6 +32,7 @@ struct devlink {
 	struct list_head region_list;
 	u32 snapshot_id;
 	struct list_head reporter_list;
+	struct mutex reporters_lock; /* protects reporter_list */
 	struct devlink_dpipe_headers *dpipe_headers;
 	const struct devlink_ops *ops;
 	struct device *dev;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 4e28d04c0165..d43bc52b8840 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -20,6 +20,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/spinlock.h>
+#include <linux/refcount.h>
 #include <rdma/ib_verbs.h>
 #include <net/netlink.h>
 #include <net/genetlink.h>
@@ -4432,6 +4433,7 @@ struct devlink_health_reporter {
 	u64 error_count;
 	u64 recovery_count;
 	u64 last_recovery_ts;
+	refcount_t refcount;
 };
 
 void *
@@ -4447,6 +4449,7 @@ devlink_health_reporter_find_by_name(struct devlink *devlink,
 {
 	struct devlink_health_reporter *reporter;
 
+	lockdep_assert_held(&devlink->reporters_lock);
 	list_for_each_entry(reporter, &devlink->reporter_list, list)
 		if (!strcmp(reporter->ops->name, reporter_name))
 			return reporter;
@@ -4470,7 +4473,7 @@ devlink_health_reporter_create(struct devlink *devlink,
 {
 	struct devlink_health_reporter *reporter;
 
-	mutex_lock(&devlink->lock);
+	mutex_lock(&devlink->reporters_lock);
 	if (devlink_health_reporter_find_by_name(devlink, ops->name)) {
 		reporter = ERR_PTR(-EEXIST);
 		goto unlock;
@@ -4494,9 +4497,10 @@ devlink_health_reporter_create(struct devlink *devlink,
 	reporter->graceful_period = graceful_period;
 	reporter->auto_recover = auto_recover;
 	mutex_init(&reporter->dump_lock);
+	refcount_set(&reporter->refcount, 1);
 	list_add_tail(&reporter->list, &devlink->reporter_list);
 unlock:
-	mutex_unlock(&devlink->lock);
+	mutex_unlock(&devlink->reporters_lock);
 	return reporter;
 }
 EXPORT_SYMBOL_GPL(devlink_health_reporter_create);
@@ -4509,10 +4513,12 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_create);
 void
 devlink_health_reporter_destroy(struct devlink_health_reporter *reporter)
 {
-	mutex_lock(&reporter->devlink->lock);
+	mutex_lock(&reporter->devlink->reporters_lock);
 	list_del(&reporter->list);
+	mutex_unlock(&reporter->devlink->reporters_lock);
+	while (refcount_read(&reporter->refcount) > 1)
+		msleep(100);
 	mutex_destroy(&reporter->dump_lock);
-	mutex_unlock(&reporter->devlink->lock);
 	if (reporter->dump_fmsg)
 		devlink_fmsg_free(reporter->dump_fmsg);
 	kfree(reporter);
@@ -4648,6 +4654,7 @@ static struct devlink_health_reporter *
 devlink_health_reporter_get_from_info(struct devlink *devlink,
 				      struct genl_info *info)
 {
+	struct devlink_health_reporter *reporter;
 	char *reporter_name;
 
 	if (!info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME])
@@ -4655,7 +4662,18 @@ devlink_health_reporter_get_from_info(struct devlink *devlink,
 
 	reporter_name =
 		nla_data(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]);
-	return devlink_health_reporter_find_by_name(devlink, reporter_name);
+	mutex_lock(&devlink->reporters_lock);
+	reporter = devlink_health_reporter_find_by_name(devlink, reporter_name);
+	if (reporter)
+		refcount_inc(&reporter->refcount);
+	mutex_unlock(&devlink->reporters_lock);
+	return reporter;
+}
+
+static void
+devlink_health_reporter_put(struct devlink_health_reporter *reporter)
+{
+	refcount_dec(&reporter->refcount);
 }
 
 static int
@@ -4730,8 +4748,10 @@ static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb,
 		return -EINVAL;
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
+	if (!msg) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	err = devlink_nl_health_reporter_fill(msg, devlink, reporter,
 					      DEVLINK_CMD_HEALTH_REPORTER_GET,
@@ -4739,10 +4759,13 @@ static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb,
 					      0);
 	if (err) {
 		nlmsg_free(msg);
-		return err;
+		goto out;
 	}
 
-	return genlmsg_reply(msg, info);
+	err = genlmsg_reply(msg, info);
+out:
+	devlink_health_reporter_put(reporter);
+	return err;
 }
 
 static int
@@ -4759,7 +4782,7 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg,
 	list_for_each_entry(devlink, &devlink_list, list) {
 		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
 			continue;
-		mutex_lock(&devlink->lock);
+		mutex_lock(&devlink->reporters_lock);
 		list_for_each_entry(reporter, &devlink->reporter_list,
 				    list) {
 			if (idx < start) {
@@ -4773,12 +4796,12 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg,
 							      cb->nlh->nlmsg_seq,
 							      NLM_F_MULTI);
 			if (err) {
-				mutex_unlock(&devlink->lock);
+				mutex_unlock(&devlink->reporters_lock);
 				goto out;
 			}
 			idx++;
 		}
-		mutex_unlock(&devlink->lock);
+		mutex_unlock(&devlink->reporters_lock);
 	}
 out:
 	mutex_unlock(&devlink_mutex);
@@ -4793,6 +4816,7 @@ devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_health_reporter *reporter;
+	int err;
 
 	reporter = devlink_health_reporter_get_from_info(devlink, info);
 	if (!reporter)
@@ -4800,8 +4824,10 @@ devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 
 	if (!reporter->ops->recover &&
 	    (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] ||
-	     info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]))
-		return -EOPNOTSUPP;
+	     info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
 
 	if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD])
 		reporter->graceful_period =
@@ -4811,7 +4837,11 @@ devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb,
 		reporter->auto_recover =
 			nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]);
 
+	devlink_health_reporter_put(reporter);
 	return 0;
+out:
+	devlink_health_reporter_put(reporter);
+	return err;
 }
 
 static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
@@ -4819,12 +4849,16 @@ static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb,
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_health_reporter *reporter;
+	int err;
 
 	reporter = devlink_health_reporter_get_from_info(devlink, info);
 	if (!reporter)
 		return -EINVAL;
 
-	return devlink_health_reporter_recover(reporter, NULL);
+	err = devlink_health_reporter_recover(reporter, NULL);
+
+	devlink_health_reporter_put(reporter);
+	return err;
 }
 
 static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb,
@@ -4839,12 +4873,16 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb,
 	if (!reporter)
 		return -EINVAL;
 
-	if (!reporter->ops->diagnose)
+	if (!reporter->ops->diagnose) {
+		devlink_health_reporter_put(reporter);
 		return -EOPNOTSUPP;
+	}
 
 	fmsg = devlink_fmsg_alloc();
-	if (!fmsg)
+	if (!fmsg) {
+		devlink_health_reporter_put(reporter);
 		return -ENOMEM;
+	}
 
 	err = devlink_fmsg_obj_nest_start(fmsg);
 	if (err)
@@ -4863,6 +4901,7 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb,
 
 out:
 	devlink_fmsg_free(fmsg);
+	devlink_health_reporter_put(reporter);
 	return err;
 }
 
@@ -4877,8 +4916,10 @@ static int devlink_nl_cmd_health_reporter_dump_get_doit(struct sk_buff *skb,
 	if (!reporter)
 		return -EINVAL;
 
-	if (!reporter->ops->dump)
+	if (!reporter->ops->dump) {
+		devlink_health_reporter_put(reporter);
 		return -EOPNOTSUPP;
+	}
 
 	mutex_lock(&reporter->dump_lock);
 	err = devlink_health_do_dump(reporter, NULL);
@@ -4890,6 +4931,7 @@ static int devlink_nl_cmd_health_reporter_dump_get_doit(struct sk_buff *skb,
 
 out:
 	mutex_unlock(&reporter->dump_lock);
+	devlink_health_reporter_put(reporter);
 	return err;
 }
 
@@ -4904,12 +4946,15 @@ devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb,
 	if (!reporter)
 		return -EINVAL;
 
-	if (!reporter->ops->dump)
+	if (!reporter->ops->dump) {
+		devlink_health_reporter_put(reporter);
 		return -EOPNOTSUPP;
+	}
 
 	mutex_lock(&reporter->dump_lock);
 	devlink_health_dump_clear(reporter);
 	mutex_unlock(&reporter->dump_lock);
+	devlink_health_reporter_put(reporter);
 	return 0;
 }
 
@@ -5191,7 +5236,8 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_health_reporter_get_doit,
 		.dumpit = devlink_nl_cmd_health_reporter_get_dumpit,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+				  DEVLINK_NL_FLAG_NO_LOCK,
 		/* can be retrieved by unprivileged users */
 	},
 	{
@@ -5199,21 +5245,24 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_health_reporter_set_doit,
 		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+				  DEVLINK_NL_FLAG_NO_LOCK,
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_health_reporter_recover_doit,
 		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+				  DEVLINK_NL_FLAG_NO_LOCK,
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_health_reporter_diagnose_doit,
 		.flags = GENL_ADMIN_PERM,
-		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
+				  DEVLINK_NL_FLAG_NO_LOCK,
 	},
 	{
 		.cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET,
@@ -5284,6 +5333,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	INIT_LIST_HEAD(&devlink->region_list);
 	INIT_LIST_HEAD(&devlink->reporter_list);
 	mutex_init(&devlink->lock);
+	mutex_init(&devlink->reporters_lock);
 	return devlink;
 }
 EXPORT_SYMBOL_GPL(devlink_alloc);
@@ -5326,6 +5376,7 @@ EXPORT_SYMBOL_GPL(devlink_unregister);
  */
 void devlink_free(struct devlink *devlink)
 {
+	mutex_destroy(&devlink->reporters_lock);
 	mutex_destroy(&devlink->lock);
 	WARN_ON(!list_empty(&devlink->reporter_list));
 	WARN_ON(!list_empty(&devlink->region_list));
-- 
cgit v1.2.3


From a3d43c0d56f1b94e74963a2fbadfb70126d92213 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 29 Apr 2019 15:48:31 -0700
Subject: taprio: Add support adding an admin schedule

The IEEE 802.1Q-2018 defines two "types" of schedules, the "Oper" (from
operational?) and "Admin" ones. Up until now, 'taprio' only had
support for the "Oper" one, added when the qdisc is created. This adds
support for the "Admin" one, which allows the .change() operation to
be supported.

Just for clarification, some quick (and dirty) definitions, the "Oper"
schedule is the currently (as in this instant) running one, and it's
read-only. The "Admin" one is the one that the system configurator has
installed, it can be changed, and it will be "promoted" to "Oper" when
it's 'base-time' is reached.

The idea behing this patch is that calling something like the below,
(after taprio is already configured with an initial schedule):

$ tc qdisc change taprio dev IFACE parent root 	     \
     	   base-time X 	     	   	       	     \
     	   sched-entry <CMD> <GATES> <INTERVAL>	     \
	   ...

Will cause a new admin schedule to be created and programmed to be
"promoted" to "Oper" at instant X. If an "Admin" schedule already
exists, it will be overwritten with the new parameters.

Up until now, there was some code that was added to ease the support
of changing a single entry of a schedule, but was ultimately unused.
Now, that we have support for "change" with more well thought
semantics, updating a single entry seems to be less useful.

So we remove what is in practice dead code, and return a "not
supported" error if the user tries to use it. If changing a single
entry would make the user's life easier we may ressurrect this idea,
but at this point, removing it simplifies the code.

For now, only the schedule specific bits are allowed to be added for a
new schedule, that means that 'clockid', 'num_tc', 'map' and 'queues'
cannot be modified.

Example:

$ tc qdisc change dev IFACE parent root handle 100 taprio \
      base-time $BASE_TIME \
      sched-entry S 00 500000 \
      sched-entry S 0f 500000 \
      clockid CLOCK_TAI

The only change in the netlink API introduced by this change is the
introduction of an "admin" type in the response to a dump request,
that type allows userspace to separate the "oper" schedule from the
"admin" schedule. If userspace doesn't support the "admin" type, it
will only display the "oper" schedule.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  11 +
 net/sched/sch_taprio.c         | 511 +++++++++++++++++++++++++----------------
 2 files changed, 329 insertions(+), 193 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 7ee74c3474bf..d59770d0eb84 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -1148,6 +1148,16 @@ enum {
 
 #define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1)
 
+/* The format for the admin sched (dump only):
+ * [TCA_TAPRIO_SCHED_ADMIN_SCHED]
+ *   [TCA_TAPRIO_ATTR_SCHED_BASE_TIME]
+ *   [TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]
+ *     [TCA_TAPRIO_ATTR_SCHED_ENTRY]
+ *       [TCA_TAPRIO_ATTR_SCHED_ENTRY_CMD]
+ *       [TCA_TAPRIO_ATTR_SCHED_ENTRY_GATES]
+ *       [TCA_TAPRIO_ATTR_SCHED_ENTRY_INTERVAL]
+ */
+
 enum {
 	TCA_TAPRIO_ATTR_UNSPEC,
 	TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */
@@ -1156,6 +1166,7 @@ enum {
 	TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */
 	TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */
 	TCA_TAPRIO_PAD,
+	TCA_TAPRIO_ATTR_ADMIN_SCHED, /* The admin sched, only used in dump */
 	__TCA_TAPRIO_ATTR_MAX,
 };
 
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index f827caa73862..ec8ccaee64e6 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -16,6 +16,7 @@
 #include <linux/math64.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
+#include <linux/rcupdate.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
@@ -41,25 +42,69 @@ struct sched_entry {
 	u8 command;
 };
 
+struct sched_gate_list {
+	struct rcu_head rcu;
+	struct list_head entries;
+	size_t num_entries;
+	s64 base_time;
+};
+
 struct taprio_sched {
 	struct Qdisc **qdiscs;
 	struct Qdisc *root;
-	s64 base_time;
 	int clockid;
 	atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+
 				    * speeds it's sub-nanoseconds per byte
 				    */
-	size_t num_entries;
 
 	/* Protects the update side of the RCU protected current_entry */
 	spinlock_t current_entry_lock;
 	struct sched_entry __rcu *current_entry;
-	struct list_head entries;
+	struct sched_gate_list __rcu *oper_sched;
+	struct sched_gate_list __rcu *admin_sched;
 	ktime_t (*get_time)(void);
 	struct hrtimer advance_timer;
 	struct list_head taprio_list;
 };
 
+static ktime_t sched_base_time(const struct sched_gate_list *sched)
+{
+	if (!sched)
+		return KTIME_MAX;
+
+	return ns_to_ktime(sched->base_time);
+}
+
+static void taprio_free_sched_cb(struct rcu_head *head)
+{
+	struct sched_gate_list *sched = container_of(head, struct sched_gate_list, rcu);
+	struct sched_entry *entry, *n;
+
+	if (!sched)
+		return;
+
+	list_for_each_entry_safe(entry, n, &sched->entries, list) {
+		list_del(&entry->list);
+		kfree(entry);
+	}
+
+	kfree(sched);
+}
+
+static void switch_schedules(struct taprio_sched *q,
+			     struct sched_gate_list **admin,
+			     struct sched_gate_list **oper)
+{
+	rcu_assign_pointer(q->oper_sched, *admin);
+	rcu_assign_pointer(q->admin_sched, NULL);
+
+	if (*oper)
+		call_rcu(&(*oper)->rcu, taprio_free_sched_cb);
+
+	*oper = *admin;
+	*admin = NULL;
+}
+
 static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			  struct sk_buff **to_free)
 {
@@ -211,10 +256,31 @@ done:
 	return skb;
 }
 
+static bool should_change_schedules(const struct sched_gate_list *admin,
+				    const struct sched_gate_list *oper,
+				    ktime_t close_time)
+{
+	ktime_t next_base_time;
+
+	if (!admin)
+		return false;
+
+	next_base_time = sched_base_time(admin);
+
+	/* This is the simple case, the close_time would fall after
+	 * the next schedule base_time.
+	 */
+	if (ktime_compare(next_base_time, close_time) <= 0)
+		return true;
+
+	return false;
+}
+
 static enum hrtimer_restart advance_sched(struct hrtimer *timer)
 {
 	struct taprio_sched *q = container_of(timer, struct taprio_sched,
 					      advance_timer);
+	struct sched_gate_list *oper, *admin;
 	struct sched_entry *entry, *next;
 	struct Qdisc *sch = q->root;
 	ktime_t close_time;
@@ -222,26 +288,43 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer)
 	spin_lock(&q->current_entry_lock);
 	entry = rcu_dereference_protected(q->current_entry,
 					  lockdep_is_held(&q->current_entry_lock));
+	oper = rcu_dereference_protected(q->oper_sched,
+					 lockdep_is_held(&q->current_entry_lock));
+	admin = rcu_dereference_protected(q->admin_sched,
+					  lockdep_is_held(&q->current_entry_lock));
 
-	/* This is the case that it's the first time that the schedule
-	 * runs, so it only happens once per schedule. The first entry
-	 * is pre-calculated during the schedule initialization.
+	if (!oper)
+		switch_schedules(q, &admin, &oper);
+
+	/* This can happen in two cases: 1. this is the very first run
+	 * of this function (i.e. we weren't running any schedule
+	 * previously); 2. The previous schedule just ended. The first
+	 * entry of all schedules are pre-calculated during the
+	 * schedule initialization.
 	 */
-	if (unlikely(!entry)) {
-		next = list_first_entry(&q->entries, struct sched_entry,
+	if (unlikely(!entry || entry->close_time == oper->base_time)) {
+		next = list_first_entry(&oper->entries, struct sched_entry,
 					list);
 		close_time = next->close_time;
 		goto first_run;
 	}
 
-	if (list_is_last(&entry->list, &q->entries))
-		next = list_first_entry(&q->entries, struct sched_entry,
+	if (list_is_last(&entry->list, &oper->entries))
+		next = list_first_entry(&oper->entries, struct sched_entry,
 					list);
 	else
 		next = list_next_entry(entry, list);
 
 	close_time = ktime_add_ns(entry->close_time, next->interval);
 
+	if (should_change_schedules(admin, oper, close_time)) {
+		/* Set things so the next time this runs, the new
+		 * schedule runs.
+		 */
+		close_time = sched_base_time(admin);
+		switch_schedules(q, &admin, &oper);
+	}
+
 	next->close_time = close_time;
 	taprio_set_budget(q, next);
 
@@ -324,71 +407,8 @@ static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry,
 	return fill_sched_entry(tb, entry, extack);
 }
 
-/* Returns the number of entries in case of success */
-static int parse_sched_single_entry(struct nlattr *n,
-				    struct taprio_sched *q,
-				    struct netlink_ext_ack *extack)
-{
-	struct nlattr *tb_entry[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { };
-	struct nlattr *tb_list[TCA_TAPRIO_SCHED_MAX + 1] = { };
-	struct sched_entry *entry;
-	bool found = false;
-	u32 index;
-	int err;
-
-	err = nla_parse_nested_deprecated(tb_list, TCA_TAPRIO_SCHED_MAX, n,
-					  entry_list_policy, NULL);
-	if (err < 0) {
-		NL_SET_ERR_MSG(extack, "Could not parse nested entry");
-		return -EINVAL;
-	}
-
-	if (!tb_list[TCA_TAPRIO_SCHED_ENTRY]) {
-		NL_SET_ERR_MSG(extack, "Single-entry must include an entry");
-		return -EINVAL;
-	}
-
-	err = nla_parse_nested_deprecated(tb_entry,
-					  TCA_TAPRIO_SCHED_ENTRY_MAX,
-					  tb_list[TCA_TAPRIO_SCHED_ENTRY],
-					  entry_policy, NULL);
-	if (err < 0) {
-		NL_SET_ERR_MSG(extack, "Could not parse nested entry");
-		return -EINVAL;
-	}
-
-	if (!tb_entry[TCA_TAPRIO_SCHED_ENTRY_INDEX]) {
-		NL_SET_ERR_MSG(extack, "Entry must specify an index\n");
-		return -EINVAL;
-	}
-
-	index = nla_get_u32(tb_entry[TCA_TAPRIO_SCHED_ENTRY_INDEX]);
-	if (index >= q->num_entries) {
-		NL_SET_ERR_MSG(extack, "Index for single entry exceeds number of entries in schedule");
-		return -EINVAL;
-	}
-
-	list_for_each_entry(entry, &q->entries, list) {
-		if (entry->index == index) {
-			found = true;
-			break;
-		}
-	}
-
-	if (!found) {
-		NL_SET_ERR_MSG(extack, "Could not find entry");
-		return -ENOENT;
-	}
-
-	err = fill_sched_entry(tb_entry, entry, extack);
-	if (err < 0)
-		return err;
-
-	return q->num_entries;
-}
-
 static int parse_sched_list(struct nlattr *list,
-			    struct taprio_sched *q,
+			    struct sched_gate_list *sched,
 			    struct netlink_ext_ack *extack)
 {
 	struct nlattr *n;
@@ -418,64 +438,36 @@ static int parse_sched_list(struct nlattr *list,
 			return err;
 		}
 
-		list_add_tail(&entry->list, &q->entries);
+		list_add_tail(&entry->list, &sched->entries);
 		i++;
 	}
 
-	q->num_entries = i;
+	sched->num_entries = i;
 
 	return i;
 }
 
-/* Returns the number of entries in case of success */
-static int parse_taprio_opt(struct nlattr **tb, struct taprio_sched *q,
-			    struct netlink_ext_ack *extack)
+static int parse_taprio_schedule(struct nlattr **tb,
+				 struct sched_gate_list *new,
+				 struct netlink_ext_ack *extack)
 {
 	int err = 0;
-	int clockid;
-
-	if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] &&
-	    tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY])
-		return -EINVAL;
 
-	if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] && q->num_entries == 0)
-		return -EINVAL;
-
-	if (q->clockid == -1 && !tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID])
-		return -EINVAL;
+	if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]) {
+		NL_SET_ERR_MSG(extack, "Adding a single entry is not supported");
+		return -ENOTSUPP;
+	}
 
 	if (tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME])
-		q->base_time = nla_get_s64(
-			tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]);
-
-	if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) {
-		clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]);
-
-		/* We only support static clockids and we don't allow
-		 * for it to be modified after the first init.
-		 */
-		if (clockid < 0 || (q->clockid != -1 && q->clockid != clockid))
-			return -EINVAL;
-
-		q->clockid = clockid;
-	}
+		new->base_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]);
 
 	if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST])
 		err = parse_sched_list(
-			tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], q, extack);
-	else if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY])
-		err = parse_sched_single_entry(
-			tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY], q, extack);
-
-	/* parse_sched_* return the number of entries in the schedule,
-	 * a schedule with zero entries is an error.
-	 */
-	if (err == 0) {
-		NL_SET_ERR_MSG(extack, "The schedule should contain at least one entry");
-		return -EINVAL;
-	}
+			tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack);
+	if (err < 0)
+		return err;
 
-	return err;
+	return 0;
 }
 
 static int taprio_parse_mqprio_opt(struct net_device *dev,
@@ -484,11 +476,17 @@ static int taprio_parse_mqprio_opt(struct net_device *dev,
 {
 	int i, j;
 
-	if (!qopt) {
+	if (!qopt && !dev->num_tc) {
 		NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary");
 		return -EINVAL;
 	}
 
+	/* If num_tc is already set, it means that the user already
+	 * configured the mqprio part
+	 */
+	if (dev->num_tc)
+		return 0;
+
 	/* Verify num_tc is not out of max range */
 	if (qopt->num_tc > TC_MAX_QUEUE) {
 		NL_SET_ERR_MSG(extack, "Number of traffic classes is outside valid range");
@@ -534,14 +532,16 @@ static int taprio_parse_mqprio_opt(struct net_device *dev,
 	return 0;
 }
 
-static int taprio_get_start_time(struct Qdisc *sch, ktime_t *start)
+static int taprio_get_start_time(struct Qdisc *sch,
+				 struct sched_gate_list *sched,
+				 ktime_t *start)
 {
 	struct taprio_sched *q = qdisc_priv(sch);
 	struct sched_entry *entry;
 	ktime_t now, base, cycle;
 	s64 n;
 
-	base = ns_to_ktime(q->base_time);
+	base = sched_base_time(sched);
 	now = q->get_time();
 
 	if (ktime_after(base, now)) {
@@ -552,7 +552,7 @@ static int taprio_get_start_time(struct Qdisc *sch, ktime_t *start)
 	/* Calculate the cycle_time, by summing all the intervals.
 	 */
 	cycle = 0;
-	list_for_each_entry(entry, &q->entries, list)
+	list_for_each_entry(entry, &sched->entries, list)
 		cycle = ktime_add_ns(cycle, entry->interval);
 
 	/* The qdisc is expected to have at least one sched_entry.  Moreover,
@@ -571,22 +571,34 @@ static int taprio_get_start_time(struct Qdisc *sch, ktime_t *start)
 	return 0;
 }
 
-static void taprio_start_sched(struct Qdisc *sch, ktime_t start)
+static void setup_first_close_time(struct taprio_sched *q,
+				   struct sched_gate_list *sched, ktime_t base)
 {
-	struct taprio_sched *q = qdisc_priv(sch);
 	struct sched_entry *first;
-	unsigned long flags;
-
-	spin_lock_irqsave(&q->current_entry_lock, flags);
 
-	first = list_first_entry(&q->entries, struct sched_entry,
-				 list);
+	first = list_first_entry(&sched->entries,
+				 struct sched_entry, list);
 
-	first->close_time = ktime_add_ns(start, first->interval);
+	first->close_time = ktime_add_ns(base, first->interval);
 	taprio_set_budget(q, first);
 	rcu_assign_pointer(q->current_entry, NULL);
+}
 
-	spin_unlock_irqrestore(&q->current_entry_lock, flags);
+static void taprio_start_sched(struct Qdisc *sch,
+			       ktime_t start, struct sched_gate_list *new)
+{
+	struct taprio_sched *q = qdisc_priv(sch);
+	ktime_t expires;
+
+	expires = hrtimer_get_expires(&q->advance_timer);
+	if (expires == 0)
+		expires = KTIME_MAX;
+
+	/* If the new schedule starts before the next expiration, we
+	 * reprogram it to the earliest one, so we change the admin
+	 * schedule to the operational one at the right time.
+	 */
+	start = min_t(ktime_t, start, expires);
 
 	hrtimer_start(&q->advance_timer, start, HRTIMER_MODE_ABS);
 }
@@ -641,10 +653,12 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 			 struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[TCA_TAPRIO_ATTR_MAX + 1] = { };
+	struct sched_gate_list *oper, *admin, *new_admin;
 	struct taprio_sched *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
 	struct tc_mqprio_qopt *mqprio = NULL;
-	int i, err, size;
+	int i, err, clockid;
+	unsigned long flags;
 	ktime_t start;
 
 	err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_ATTR_MAX, opt,
@@ -659,48 +673,64 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	if (err < 0)
 		return err;
 
-	/* A schedule with less than one entry is an error */
-	size = parse_taprio_opt(tb, q, extack);
-	if (size < 0)
-		return size;
+	new_admin = kzalloc(sizeof(*new_admin), GFP_KERNEL);
+	if (!new_admin) {
+		NL_SET_ERR_MSG(extack, "Not enough memory for a new schedule");
+		return -ENOMEM;
+	}
+	INIT_LIST_HEAD(&new_admin->entries);
 
-	hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS);
-	q->advance_timer.function = advance_sched;
+	rcu_read_lock();
+	oper = rcu_dereference(q->oper_sched);
+	admin = rcu_dereference(q->admin_sched);
+	rcu_read_unlock();
 
-	switch (q->clockid) {
-	case CLOCK_REALTIME:
-		q->get_time = ktime_get_real;
-		break;
-	case CLOCK_MONOTONIC:
-		q->get_time = ktime_get;
-		break;
-	case CLOCK_BOOTTIME:
-		q->get_time = ktime_get_boottime;
-		break;
-	case CLOCK_TAI:
-		q->get_time = ktime_get_clocktai;
-		break;
-	default:
-		return -ENOTSUPP;
+	if (mqprio && (oper || admin)) {
+		NL_SET_ERR_MSG(extack, "Changing the traffic mapping of a running schedule is not supported");
+		err = -ENOTSUPP;
+		goto free_sched;
 	}
 
-	for (i = 0; i < dev->num_tx_queues; i++) {
-		struct netdev_queue *dev_queue;
-		struct Qdisc *qdisc;
+	err = parse_taprio_schedule(tb, new_admin, extack);
+	if (err < 0)
+		goto free_sched;
 
-		dev_queue = netdev_get_tx_queue(dev, i);
-		qdisc = qdisc_create_dflt(dev_queue,
-					  &pfifo_qdisc_ops,
-					  TC_H_MAKE(TC_H_MAJ(sch->handle),
-						    TC_H_MIN(i + 1)),
-					  extack);
-		if (!qdisc)
-			return -ENOMEM;
+	if (new_admin->num_entries == 0) {
+		NL_SET_ERR_MSG(extack, "There should be at least one entry in the schedule");
+		err = -EINVAL;
+		goto free_sched;
+	}
 
-		if (i < dev->real_num_tx_queues)
-			qdisc_hash_add(qdisc, false);
+	if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) {
+		clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]);
 
-		q->qdiscs[i] = qdisc;
+		/* We only support static clockids and we don't allow
+		 * for it to be modified after the first init.
+		 */
+		if (clockid < 0 ||
+		    (q->clockid != -1 && q->clockid != clockid)) {
+			NL_SET_ERR_MSG(extack, "Changing the 'clockid' of a running schedule is not supported");
+			err = -ENOTSUPP;
+			goto free_sched;
+		}
+
+		q->clockid = clockid;
+	}
+
+	if (q->clockid == -1 && !tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) {
+		NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory");
+		err = -EINVAL;
+		goto free_sched;
+	}
+
+	taprio_set_picos_per_byte(dev, q);
+
+	/* Protects against enqueue()/dequeue() */
+	spin_lock_bh(qdisc_lock(sch));
+
+	if (!hrtimer_active(&q->advance_timer)) {
+		hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS);
+		q->advance_timer.function = advance_sched;
 	}
 
 	if (mqprio) {
@@ -716,24 +746,60 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 					       mqprio->prio_tc_map[i]);
 	}
 
-	taprio_set_picos_per_byte(dev, q);
+	switch (q->clockid) {
+	case CLOCK_REALTIME:
+		q->get_time = ktime_get_real;
+		break;
+	case CLOCK_MONOTONIC:
+		q->get_time = ktime_get;
+		break;
+	case CLOCK_BOOTTIME:
+		q->get_time = ktime_get_boottime;
+		break;
+	case CLOCK_TAI:
+		q->get_time = ktime_get_clocktai;
+		break;
+	default:
+		NL_SET_ERR_MSG(extack, "Invalid 'clockid'");
+		err = -EINVAL;
+		goto unlock;
+	}
 
-	err = taprio_get_start_time(sch, &start);
+	err = taprio_get_start_time(sch, new_admin, &start);
 	if (err < 0) {
 		NL_SET_ERR_MSG(extack, "Internal error: failed get start time");
-		return err;
+		goto unlock;
 	}
 
-	taprio_start_sched(sch, start);
+	setup_first_close_time(q, new_admin, start);
 
-	return 0;
+	/* Protects against advance_sched() */
+	spin_lock_irqsave(&q->current_entry_lock, flags);
+
+	taprio_start_sched(sch, start, new_admin);
+
+	rcu_assign_pointer(q->admin_sched, new_admin);
+	if (admin)
+		call_rcu(&admin->rcu, taprio_free_sched_cb);
+	new_admin = NULL;
+
+	spin_unlock_irqrestore(&q->current_entry_lock, flags);
+
+	err = 0;
+
+unlock:
+	spin_unlock_bh(qdisc_lock(sch));
+
+free_sched:
+	kfree(new_admin);
+
+	return err;
 }
 
 static void taprio_destroy(struct Qdisc *sch)
 {
 	struct taprio_sched *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
-	struct sched_entry *entry, *n;
 	unsigned int i;
 
 	spin_lock(&taprio_list_lock);
@@ -752,10 +818,11 @@ static void taprio_destroy(struct Qdisc *sch)
 
 	netdev_set_num_tc(dev, 0);
 
-	list_for_each_entry_safe(entry, n, &q->entries, list) {
-		list_del(&entry->list);
-		kfree(entry);
-	}
+	if (q->oper_sched)
+		call_rcu(&q->oper_sched->rcu, taprio_free_sched_cb);
+
+	if (q->admin_sched)
+		call_rcu(&q->admin_sched->rcu, taprio_free_sched_cb);
 }
 
 static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
@@ -763,12 +830,12 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct taprio_sched *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
+	int i;
 
-	INIT_LIST_HEAD(&q->entries);
 	spin_lock_init(&q->current_entry_lock);
 
-	/* We may overwrite the configuration later */
 	hrtimer_init(&q->advance_timer, CLOCK_TAI, HRTIMER_MODE_ABS);
+	q->advance_timer.function = advance_sched;
 
 	q->root = sch;
 
@@ -798,6 +865,25 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 	list_add(&q->taprio_list, &taprio_list);
 	spin_unlock(&taprio_list_lock);
 
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		struct netdev_queue *dev_queue;
+		struct Qdisc *qdisc;
+
+		dev_queue = netdev_get_tx_queue(dev, i);
+		qdisc = qdisc_create_dflt(dev_queue,
+					  &pfifo_qdisc_ops,
+					  TC_H_MAKE(TC_H_MAJ(sch->handle),
+						    TC_H_MIN(i + 1)),
+					  extack);
+		if (!qdisc)
+			return -ENOMEM;
+
+		if (i < dev->real_num_tx_queues)
+			qdisc_hash_add(qdisc, false);
+
+		q->qdiscs[i] = qdisc;
+	}
+
 	return taprio_change(sch, opt, extack);
 }
 
@@ -869,15 +955,47 @@ nla_put_failure:
 	return -1;
 }
 
+static int dump_schedule(struct sk_buff *msg,
+			 const struct sched_gate_list *root)
+{
+	struct nlattr *entry_list;
+	struct sched_entry *entry;
+
+	if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_BASE_TIME,
+			root->base_time, TCA_TAPRIO_PAD))
+		return -1;
+
+	entry_list = nla_nest_start_noflag(msg,
+					   TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST);
+	if (!entry_list)
+		goto error_nest;
+
+	list_for_each_entry(entry, &root->entries, list) {
+		if (dump_entry(msg, entry) < 0)
+			goto error_nest;
+	}
+
+	nla_nest_end(msg, entry_list);
+	return 0;
+
+error_nest:
+	nla_nest_cancel(msg, entry_list);
+	return -1;
+}
+
 static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct taprio_sched *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
+	struct sched_gate_list *oper, *admin;
 	struct tc_mqprio_qopt opt = { 0 };
-	struct nlattr *nest, *entry_list;
-	struct sched_entry *entry;
+	struct nlattr *nest, *sched_nest;
 	unsigned int i;
 
+	rcu_read_lock();
+	oper = rcu_dereference(q->oper_sched);
+	admin = rcu_dereference(q->admin_sched);
+
 	opt.num_tc = netdev_get_num_tc(dev);
 	memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map));
 
@@ -888,35 +1006,41 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 
 	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (!nest)
-		return -ENOSPC;
+		goto start_error;
 
 	if (nla_put(skb, TCA_TAPRIO_ATTR_PRIOMAP, sizeof(opt), &opt))
 		goto options_error;
 
-	if (nla_put_s64(skb, TCA_TAPRIO_ATTR_SCHED_BASE_TIME,
-			q->base_time, TCA_TAPRIO_PAD))
-		goto options_error;
-
 	if (nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid))
 		goto options_error;
 
-	entry_list = nla_nest_start_noflag(skb,
-					   TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST);
-	if (!entry_list)
+	if (oper && dump_schedule(skb, oper))
 		goto options_error;
 
-	list_for_each_entry(entry, &q->entries, list) {
-		if (dump_entry(skb, entry) < 0)
-			goto options_error;
-	}
+	if (!admin)
+		goto done;
+
+	sched_nest = nla_nest_start_noflag(skb, TCA_TAPRIO_ATTR_ADMIN_SCHED);
 
-	nla_nest_end(skb, entry_list);
+	if (dump_schedule(skb, admin))
+		goto admin_error;
+
+	nla_nest_end(skb, sched_nest);
+
+done:
+	rcu_read_unlock();
 
 	return nla_nest_end(skb, nest);
 
+admin_error:
+	nla_nest_cancel(skb, sched_nest);
+
 options_error:
 	nla_nest_cancel(skb, nest);
-	return -1;
+
+start_error:
+	rcu_read_unlock();
+	return -ENOSPC;
 }
 
 static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl)
@@ -1003,6 +1127,7 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = {
 	.id		= "taprio",
 	.priv_size	= sizeof(struct taprio_sched),
 	.init		= taprio_init,
+	.change		= taprio_change,
 	.destroy	= taprio_destroy,
 	.peek		= taprio_peek,
 	.dequeue	= taprio_dequeue,
-- 
cgit v1.2.3


From 6ca6a6654225f3cd001304d33429c817e0c0b85f Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 29 Apr 2019 15:48:32 -0700
Subject: taprio: Add support for setting the cycle-time manually

IEEE 802.1Q-2018 defines that a the cycle-time of a schedule may be
overridden, so the schedule is truncated to a determined "width".

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  1 +
 net/sched/sch_taprio.c         | 59 ++++++++++++++++++++++++++++++++++++------
 2 files changed, 52 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index d59770d0eb84..7a32276838e1 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -1167,6 +1167,7 @@ enum {
 	TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */
 	TCA_TAPRIO_PAD,
 	TCA_TAPRIO_ATTR_ADMIN_SCHED, /* The admin sched, only used in dump */
+	TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, /* s64 */
 	__TCA_TAPRIO_ATTR_MAX,
 };
 
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index ec8ccaee64e6..6b37ffda23ec 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -46,6 +46,8 @@ struct sched_gate_list {
 	struct rcu_head rcu;
 	struct list_head entries;
 	size_t num_entries;
+	ktime_t cycle_close_time;
+	s64 cycle_time;
 	s64 base_time;
 };
 
@@ -105,6 +107,22 @@ static void switch_schedules(struct taprio_sched *q,
 	*admin = NULL;
 }
 
+static ktime_t get_cycle_time(struct sched_gate_list *sched)
+{
+	struct sched_entry *entry;
+	ktime_t cycle = 0;
+
+	if (sched->cycle_time != 0)
+		return sched->cycle_time;
+
+	list_for_each_entry(entry, &sched->entries, list)
+		cycle = ktime_add_ns(cycle, entry->interval);
+
+	sched->cycle_time = cycle;
+
+	return cycle;
+}
+
 static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			  struct sk_buff **to_free)
 {
@@ -256,6 +274,18 @@ done:
 	return skb;
 }
 
+static bool should_restart_cycle(const struct sched_gate_list *oper,
+				 const struct sched_entry *entry)
+{
+	if (list_is_last(&entry->list, &oper->entries))
+		return true;
+
+	if (ktime_compare(entry->close_time, oper->cycle_close_time) == 0)
+		return true;
+
+	return false;
+}
+
 static bool should_change_schedules(const struct sched_gate_list *admin,
 				    const struct sched_gate_list *oper,
 				    ktime_t close_time)
@@ -309,13 +339,17 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer)
 		goto first_run;
 	}
 
-	if (list_is_last(&entry->list, &oper->entries))
+	if (should_restart_cycle(oper, entry)) {
 		next = list_first_entry(&oper->entries, struct sched_entry,
 					list);
-	else
+		oper->cycle_close_time = ktime_add_ns(oper->cycle_close_time,
+						      oper->cycle_time);
+	} else {
 		next = list_next_entry(entry, list);
+	}
 
 	close_time = ktime_add_ns(entry->close_time, next->interval);
+	close_time = min_t(ktime_t, close_time, oper->cycle_close_time);
 
 	if (should_change_schedules(admin, oper, close_time)) {
 		/* Set things so the next time this runs, the new
@@ -360,6 +394,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]      = { .type = NLA_S64 },
 	[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]   = { .type = NLA_NESTED },
 	[TCA_TAPRIO_ATTR_SCHED_CLOCKID]        = { .type = NLA_S32 },
+	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]     = { .type = NLA_S64 },
 };
 
 static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
@@ -461,6 +496,9 @@ static int parse_taprio_schedule(struct nlattr **tb,
 	if (tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME])
 		new->base_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]);
 
+	if (tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME])
+		new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]);
+
 	if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST])
 		err = parse_sched_list(
 			tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack);
@@ -537,7 +575,6 @@ static int taprio_get_start_time(struct Qdisc *sch,
 				 ktime_t *start)
 {
 	struct taprio_sched *q = qdisc_priv(sch);
-	struct sched_entry *entry;
 	ktime_t now, base, cycle;
 	s64 n;
 
@@ -549,11 +586,7 @@ static int taprio_get_start_time(struct Qdisc *sch,
 		return 0;
 	}
 
-	/* Calculate the cycle_time, by summing all the intervals.
-	 */
-	cycle = 0;
-	list_for_each_entry(entry, &sched->entries, list)
-		cycle = ktime_add_ns(cycle, entry->interval);
+	cycle = get_cycle_time(sched);
 
 	/* The qdisc is expected to have at least one sched_entry.  Moreover,
 	 * any entry must have 'interval' > 0. Thus if the cycle time is zero,
@@ -575,10 +608,16 @@ static void setup_first_close_time(struct taprio_sched *q,
 				   struct sched_gate_list *sched, ktime_t base)
 {
 	struct sched_entry *first;
+	ktime_t cycle;
 
 	first = list_first_entry(&sched->entries,
 				 struct sched_entry, list);
 
+	cycle = get_cycle_time(sched);
+
+	/* FIXME: find a better place to do this */
+	sched->cycle_close_time = ktime_add_ns(base, cycle);
+
 	first->close_time = ktime_add_ns(base, first->interval);
 	taprio_set_budget(q, first);
 	rcu_assign_pointer(q->current_entry, NULL);
@@ -965,6 +1004,10 @@ static int dump_schedule(struct sk_buff *msg,
 			root->base_time, TCA_TAPRIO_PAD))
 		return -1;
 
+	if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME,
+			root->cycle_time, TCA_TAPRIO_PAD))
+		return -1;
+
 	entry_list = nla_nest_start_noflag(msg,
 					   TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST);
 	if (!entry_list)
-- 
cgit v1.2.3


From c25031e993440debdd530278ce2171ce477df029 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 29 Apr 2019 15:48:33 -0700
Subject: taprio: Add support for cycle-time-extension

IEEE 802.1Q-2018 defines the concept of a cycle-time-extension, so the
last entry of a schedule before the start of a new schedule can be
extended, so "too-short" entries can be avoided.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  1 +
 net/sched/sch_taprio.c         | 35 +++++++++++++++++++++++++++++------
 2 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 7a32276838e1..8b2f993cbb77 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -1168,6 +1168,7 @@ enum {
 	TCA_TAPRIO_PAD,
 	TCA_TAPRIO_ATTR_ADMIN_SCHED, /* The admin sched, only used in dump */
 	TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, /* s64 */
+	TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, /* s64 */
 	__TCA_TAPRIO_ATTR_MAX,
 };
 
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 6b37ffda23ec..539677120b9f 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -48,6 +48,7 @@ struct sched_gate_list {
 	size_t num_entries;
 	ktime_t cycle_close_time;
 	s64 cycle_time;
+	s64 cycle_time_extension;
 	s64 base_time;
 };
 
@@ -290,7 +291,7 @@ static bool should_change_schedules(const struct sched_gate_list *admin,
 				    const struct sched_gate_list *oper,
 				    ktime_t close_time)
 {
-	ktime_t next_base_time;
+	ktime_t next_base_time, extension_time;
 
 	if (!admin)
 		return false;
@@ -303,6 +304,20 @@ static bool should_change_schedules(const struct sched_gate_list *admin,
 	if (ktime_compare(next_base_time, close_time) <= 0)
 		return true;
 
+	/* This is the cycle_time_extension case, if the close_time
+	 * plus the amount that can be extended would fall after the
+	 * next schedule base_time, we can extend the current schedule
+	 * for that amount.
+	 */
+	extension_time = ktime_add_ns(close_time, oper->cycle_time_extension);
+
+	/* FIXME: the IEEE 802.1Q-2018 Specification isn't clear about
+	 * how precisely the extension should be made. So after
+	 * conformance testing, this logic may change.
+	 */
+	if (ktime_compare(next_base_time, extension_time) <= 0)
+		return true;
+
 	return false;
 }
 
@@ -390,11 +405,12 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_PRIOMAP]	       = {
 		.len = sizeof(struct tc_mqprio_qopt)
 	},
-	[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]     = { .type = NLA_NESTED },
-	[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]      = { .type = NLA_S64 },
-	[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]   = { .type = NLA_NESTED },
-	[TCA_TAPRIO_ATTR_SCHED_CLOCKID]        = { .type = NLA_S32 },
-	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]     = { .type = NLA_S64 },
+	[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]           = { .type = NLA_NESTED },
+	[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]            = { .type = NLA_S64 },
+	[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]         = { .type = NLA_NESTED },
+	[TCA_TAPRIO_ATTR_SCHED_CLOCKID]              = { .type = NLA_S32 },
+	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]           = { .type = NLA_S64 },
+	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 },
 };
 
 static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
@@ -496,6 +512,9 @@ static int parse_taprio_schedule(struct nlattr **tb,
 	if (tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME])
 		new->base_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]);
 
+	if (tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION])
+		new->cycle_time_extension = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION]);
+
 	if (tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME])
 		new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]);
 
@@ -1008,6 +1027,10 @@ static int dump_schedule(struct sk_buff *msg,
 			root->cycle_time, TCA_TAPRIO_PAD))
 		return -1;
 
+	if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION,
+			root->cycle_time_extension, TCA_TAPRIO_PAD))
+		return -1;
+
 	entry_list = nla_nest_start_noflag(msg,
 					   TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST);
 	if (!entry_list)
-- 
cgit v1.2.3


From 8425c41d1ef762cc15d9501d7117f009a79f3fe9 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Tue, 30 Apr 2019 09:17:49 +0200
Subject: net: ll_temac: Extend support to non-device-tree platforms

Support initialization with platdata, so the driver can be used on
non-device-tree platforms.

For currently supported device-tree platforms, the driver should behave
as before.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/ll_temac.h        |   3 +
 drivers/net/ethernet/xilinx/ll_temac_main.c   | 187 +++++++++++++++++---------
 drivers/net/ethernet/xilinx/ll_temac_mdio.c   |  23 +++-
 include/linux/platform_data/xilinx-ll-temac.h |  19 +++
 4 files changed, 166 insertions(+), 66 deletions(-)
 create mode 100644 include/linux/platform_data/xilinx-ll-temac.h

(limited to 'include')

diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h
index 45575788ed54..e338b4fa3c60 100644
--- a/drivers/net/ethernet/xilinx/ll_temac.h
+++ b/drivers/net/ethernet/xilinx/ll_temac.h
@@ -334,6 +334,9 @@ struct temac_local {
 
 	/* Connection to PHY device */
 	struct device_node *phy_node;
+	/* For non-device-tree devices */
+	char phy_name[MII_BUS_ID_SIZE + 3];
+	phy_interface_t phy_interface;
 
 	/* MDIO bus data */
 	struct mii_bus *mii_bus;	/* MII bus reference */
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index c4e85a96df75..fddd1b3ac194 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -33,6 +33,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
+#include <linux/if_ether.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
@@ -51,6 +52,7 @@
 #include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
+#include <linux/platform_data/xilinx-ll-temac.h>
 
 #include "ll_temac.h"
 
@@ -187,7 +189,7 @@ static int temac_dcr_setup(struct temac_local *lp, struct platform_device *op,
 
 /*
  * temac_dcr_setup - This is a stub for when DCR is not supported,
- * such as with MicroBlaze
+ * such as with MicroBlaze and x86
  */
 static int temac_dcr_setup(struct temac_local *lp, struct platform_device *op,
 				struct device_node *np)
@@ -857,7 +859,14 @@ static int temac_open(struct net_device *ndev)
 			dev_err(lp->dev, "of_phy_connect() failed\n");
 			return -ENODEV;
 		}
-
+		phy_start(phydev);
+	} else if (strlen(lp->phy_name) > 0) {
+		phydev = phy_connect(lp->ndev, lp->phy_name, temac_adjust_link,
+				     lp->phy_interface);
+		if (!phydev) {
+			dev_err(lp->dev, "phy_connect() failed\n");
+			return -ENODEV;
+		}
 		phy_start(phydev);
 	}
 
@@ -977,11 +986,13 @@ static const struct ethtool_ops temac_ethtool_ops = {
 	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
 
-static int temac_of_probe(struct platform_device *op)
+static int temac_probe(struct platform_device *pdev)
 {
-	struct device_node *np;
+	struct ll_temac_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	struct device_node *temac_np = dev_of_node(&pdev->dev), *dma_np;
 	struct temac_local *lp;
 	struct net_device *ndev;
+	struct resource *res;
 	const void *addr;
 	__be32 *p;
 	int rc = 0;
@@ -991,8 +1002,8 @@ static int temac_of_probe(struct platform_device *op)
 	if (!ndev)
 		return -ENOMEM;
 
-	platform_set_drvdata(op, ndev);
-	SET_NETDEV_DEV(ndev, &op->dev);
+	platform_set_drvdata(pdev, ndev);
+	SET_NETDEV_DEV(ndev, &pdev->dev);
 	ndev->flags &= ~IFF_MULTICAST;  /* clear multicast */
 	ndev->features = NETIF_F_SG;
 	ndev->netdev_ops = &temac_netdev_ops;
@@ -1014,79 +1025,129 @@ static int temac_of_probe(struct platform_device *op)
 	/* setup temac private info structure */
 	lp = netdev_priv(ndev);
 	lp->ndev = ndev;
-	lp->dev = &op->dev;
+	lp->dev = &pdev->dev;
 	lp->options = XTE_OPTION_DEFAULTS;
 	spin_lock_init(&lp->rx_lock);
 	mutex_init(&lp->indirect_mutex);
 
 	/* map device registers */
-	lp->regs = devm_of_iomap(&op->dev, op->dev.of_node, 0, NULL);
-	if (!lp->regs) {
-		dev_err(&op->dev, "could not map temac regs.\n");
-		return -ENOMEM;
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	lp->regs = devm_ioremap_nocache(&pdev->dev, res->start,
+					resource_size(res));
+	if (IS_ERR(lp->regs)) {
+		dev_err(&pdev->dev, "could not map TEMAC registers\n");
+		return PTR_ERR(lp->regs);
 	}
 
 	/* Setup checksum offload, but default to off if not specified */
 	lp->temac_features = 0;
-	p = (__be32 *)of_get_property(op->dev.of_node, "xlnx,txcsum", NULL);
-	if (p && be32_to_cpu(*p)) {
-		lp->temac_features |= TEMAC_FEATURE_TX_CSUM;
+	if (temac_np) {
+		p = (__be32 *)of_get_property(temac_np, "xlnx,txcsum", NULL);
+		if (p && be32_to_cpu(*p))
+			lp->temac_features |= TEMAC_FEATURE_TX_CSUM;
+		p = (__be32 *)of_get_property(temac_np, "xlnx,rxcsum", NULL);
+		if (p && be32_to_cpu(*p))
+			lp->temac_features |= TEMAC_FEATURE_RX_CSUM;
+	} else if (pdata) {
+		if (pdata->txcsum)
+			lp->temac_features |= TEMAC_FEATURE_TX_CSUM;
+		if (pdata->rxcsum)
+			lp->temac_features |= TEMAC_FEATURE_RX_CSUM;
+	}
+	if (lp->temac_features & TEMAC_FEATURE_TX_CSUM)
 		/* Can checksum TCP/UDP over IPv4. */
 		ndev->features |= NETIF_F_IP_CSUM;
-	}
-	p = (__be32 *)of_get_property(op->dev.of_node, "xlnx,rxcsum", NULL);
-	if (p && be32_to_cpu(*p))
-		lp->temac_features |= TEMAC_FEATURE_RX_CSUM;
-
-	/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
-	np = of_parse_phandle(op->dev.of_node, "llink-connected", 0);
-	if (!np) {
-		dev_err(&op->dev, "could not find DMA node\n");
-		return -ENODEV;
-	}
 
-	/* Setup the DMA register accesses, could be DCR or memory mapped */
-	if (temac_dcr_setup(lp, op, np)) {
+	/* Setup LocalLink DMA */
+	if (temac_np) {
+		/* Find the DMA node, map the DMA registers, and
+		 * decode the DMA IRQs.
+		 */
+		dma_np = of_parse_phandle(temac_np, "llink-connected", 0);
+		if (!dma_np) {
+			dev_err(&pdev->dev, "could not find DMA node\n");
+			return -ENODEV;
+		}
 
-		/* no DCR in the device tree, try non-DCR */
-		lp->sdma_regs = devm_of_iomap(&op->dev, np, 0, NULL);
-		if (lp->sdma_regs) {
+		/* Setup the DMA register accesses, could be DCR or
+		 * memory mapped.
+		 */
+		if (temac_dcr_setup(lp, pdev, dma_np)) {
+			/* no DCR in the device tree, try non-DCR */
+			lp->sdma_regs = devm_of_iomap(&pdev->dev, dma_np, 0,
+						      NULL);
+			if (IS_ERR(lp->sdma_regs)) {
+				dev_err(&pdev->dev,
+					"unable to map DMA registers\n");
+				of_node_put(dma_np);
+				return PTR_ERR(lp->sdma_regs);
+			}
 			lp->dma_in = temac_dma_in32;
 			lp->dma_out = temac_dma_out32;
-			dev_dbg(&op->dev, "MEM base: %p\n", lp->sdma_regs);
-		} else {
-			dev_err(&op->dev, "unable to map DMA registers\n");
-			of_node_put(np);
-			return -ENOMEM;
+			dev_dbg(&pdev->dev, "MEM base: %p\n", lp->sdma_regs);
 		}
-	}
-
-	lp->rx_irq = irq_of_parse_and_map(np, 0);
-	lp->tx_irq = irq_of_parse_and_map(np, 1);
 
-	of_node_put(np); /* Finished with the DMA node; drop the reference */
+		/* Get DMA RX and TX interrupts */
+		lp->rx_irq = irq_of_parse_and_map(dma_np, 0);
+		lp->tx_irq = irq_of_parse_and_map(dma_np, 1);
+
+		/* Finished with the DMA node; drop the reference */
+		of_node_put(dma_np);
+	} else if (pdata) {
+		/* 2nd memory resource specifies DMA registers */
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		lp->sdma_regs = devm_ioremap_nocache(&pdev->dev, res->start,
+						     resource_size(res));
+		if (IS_ERR(lp->sdma_regs)) {
+			dev_err(&pdev->dev,
+				"could not map DMA registers\n");
+			return PTR_ERR(lp->sdma_regs);
+		}
+		lp->dma_in = temac_dma_in32;
+		lp->dma_out = temac_dma_out32;
 
-	if (!lp->rx_irq || !lp->tx_irq) {
-		dev_err(&op->dev, "could not determine irqs\n");
-		return -ENOMEM;
+		/* Get DMA RX and TX interrupts */
+		lp->rx_irq = platform_get_irq(pdev, 0);
+		lp->tx_irq = platform_get_irq(pdev, 1);
 	}
 
+	/* Error handle returned DMA RX and TX interrupts */
+	if (lp->rx_irq < 0) {
+		if (lp->rx_irq != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "could not get DMA RX irq\n");
+		return lp->rx_irq;
+	}
+	if (lp->tx_irq < 0) {
+		if (lp->tx_irq != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "could not get DMA TX irq\n");
+		return lp->tx_irq;
+	}
 
-	/* Retrieve the MAC address */
-	addr = of_get_mac_address(op->dev.of_node);
-	if (!addr) {
-		dev_err(&op->dev, "could not find MAC address\n");
-		return -ENODEV;
+	if (temac_np) {
+		/* Retrieve the MAC address */
+		addr = of_get_mac_address(temac_np);
+		if (!addr) {
+			dev_err(&pdev->dev, "could not find MAC address\n");
+			return -ENODEV;
+		}
+		temac_init_mac_address(ndev, addr);
+	} else if (pdata) {
+		temac_init_mac_address(ndev, pdata->mac_addr);
 	}
-	temac_init_mac_address(ndev, addr);
 
 	rc = temac_mdio_setup(lp, pdev);
 	if (rc)
-		dev_warn(&op->dev, "error registering MDIO bus\n");
-
-	lp->phy_node = of_parse_phandle(op->dev.of_node, "phy-handle", 0);
-	if (lp->phy_node)
-		dev_dbg(lp->dev, "using PHY node %pOF (%p)\n", np, np);
+		dev_warn(&pdev->dev, "error registering MDIO bus\n");
+
+	if (temac_np) {
+		lp->phy_node = of_parse_phandle(temac_np, "phy-handle", 0);
+		if (lp->phy_node)
+			dev_dbg(lp->dev, "using PHY node %pOF\n", temac_np);
+	} else if (pdata) {
+		snprintf(lp->phy_name, sizeof(lp->phy_name),
+			 PHY_ID_FMT, lp->mii_bus->id, pdata->phy_addr);
+		lp->phy_interface = pdata->phy_interface;
+	}
 
 	/* Add the device attributes */
 	rc = sysfs_create_group(&lp->dev->kobj, &temac_attr_group);
@@ -1106,19 +1167,21 @@ static int temac_of_probe(struct platform_device *op)
 err_register_ndev:
 	sysfs_remove_group(&lp->dev->kobj, &temac_attr_group);
 err_sysfs_create:
-	of_node_put(lp->phy_node);
+	if (lp->phy_node)
+		of_node_put(lp->phy_node);
 	temac_mdio_teardown(lp);
 	return rc;
 }
 
-static int temac_of_remove(struct platform_device *op)
+static int temac_remove(struct platform_device *pdev)
 {
-	struct net_device *ndev = platform_get_drvdata(op);
+	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct temac_local *lp = netdev_priv(ndev);
 
 	unregister_netdev(ndev);
 	sysfs_remove_group(&lp->dev->kobj, &temac_attr_group);
-	of_node_put(lp->phy_node);
+	if (lp->phy_node)
+		of_node_put(lp->phy_node);
 	temac_mdio_teardown(lp);
 	return 0;
 }
@@ -1132,16 +1195,16 @@ static const struct of_device_id temac_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, temac_of_match);
 
-static struct platform_driver temac_of_driver = {
-	.probe = temac_of_probe,
-	.remove = temac_of_remove,
+static struct platform_driver temac_driver = {
+	.probe = temac_probe,
+	.remove = temac_remove,
 	.driver = {
 		.name = "xilinx_temac",
 		.of_match_table = temac_of_match,
 	},
 };
 
-module_platform_driver(temac_of_driver);
+module_platform_driver(temac_driver);
 
 MODULE_DESCRIPTION("Xilinx LL_TEMAC Ethernet driver");
 MODULE_AUTHOR("Yoshio Kashiwagi");
diff --git a/drivers/net/ethernet/xilinx/ll_temac_mdio.c b/drivers/net/ethernet/xilinx/ll_temac_mdio.c
index a0b365e43ebf..c5307e5b8e0a 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_mdio.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_mdio.c
@@ -14,6 +14,7 @@
 #include <linux/of_address.h>
 #include <linux/slab.h>
 #include <linux/of_mdio.h>
+#include <linux/platform_data/xilinx-ll-temac.h>
 
 #include "ll_temac.h"
 
@@ -59,6 +60,7 @@ static int temac_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val)
 
 int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev)
 {
+	struct ll_temac_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct device_node *np = dev_of_node(&pdev->dev);
 	struct mii_bus *bus;
 	u32 bus_hz;
@@ -66,9 +68,16 @@ int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev)
 	int rc;
 	struct resource res;
 
+	/* Get MDIO bus frequency (if specified) */
+	bus_hz = 0;
+	if (np)
+		of_property_read_u32(np, "clock-frequency", &bus_hz);
+	else if (pdata)
+		bus_hz = pdata->mdio_clk_freq;
+
 	/* Calculate a reasonable divisor for the clock rate */
 	clk_div = 0x3f; /* worst-case default setting */
-	if (of_property_read_u32(np, "clock-frequency", &bus_hz) == 0) {
+	if (bus_hz != 0) {
 		clk_div = bus_hz / (2500 * 1000 * 2) - 1;
 		if (clk_div < 1)
 			clk_div = 1;
@@ -86,9 +95,15 @@ int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev)
 	if (!bus)
 		return -ENOMEM;
 
-	of_address_to_resource(np, 0, &res);
-	snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx",
-		 (unsigned long long)res.start);
+	if (np) {
+		of_address_to_resource(np, 0, &res);
+		snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx",
+			 (unsigned long long)res.start);
+	} else if (pdata && pdata->mdio_bus_id >= 0) {
+		snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx",
+			 pdata->mdio_bus_id);
+	}
+
 	bus->priv = lp;
 	bus->name = "Xilinx TEMAC MDIO";
 	bus->read = temac_mdio_read;
diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h
new file mode 100644
index 000000000000..82e2f80648b0
--- /dev/null
+++ b/include/linux/platform_data/xilinx-ll-temac.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_XILINX_LL_TEMAC_H
+#define __LINUX_XILINX_LL_TEMAC_H
+
+#include <linux/if_ether.h>
+#include <linux/phy.h>
+
+struct ll_temac_platform_data {
+	bool txcsum;		/* Enable/disable TX checksum */
+	bool rxcsum;		/* Enable/disable RX checksum */
+	u8 mac_addr[ETH_ALEN];	/* MAC address (6 bytes) */
+	/* Clock frequency for input to MDIO clock generator */
+	u32 mdio_clk_freq;
+	unsigned long long mdio_bus_id; /* Unique id for MDIO bus */
+	int phy_addr;		/* Address of the PHY to connect to */
+	phy_interface_t phy_interface; /* PHY interface mode */
+};
+
+#endif /* __LINUX_XILINX_LL_TEMAC_H */
-- 
cgit v1.2.3


From a3246dc41aa3c9d799478ccc8dac5d19c509a923 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Tue, 30 Apr 2019 09:17:51 +0200
Subject: net: ll_temac: Add support for non-native register endianness

Replace the powerpc specific MMIO register access functions with the
generic big-endian mmio access functions, and add support for
little-endian access depending on configuration.

Big-endian access is maintained as the default, but little-endian can
be configured in device-tree binding or in platform data.

The temac_ior()/temac_iow() functions are replaced with macro wrappers
to avoid modifying existing code more than necessary.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/ll_temac.h        | 12 ++--
 drivers/net/ethernet/xilinx/ll_temac_main.c   | 87 +++++++++++++++++++++------
 include/linux/platform_data/xilinx-ll-temac.h |  2 +
 3 files changed, 79 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h
index e338b4fa3c60..23d8dd5330f8 100644
--- a/drivers/net/ethernet/xilinx/ll_temac.h
+++ b/drivers/net/ethernet/xilinx/ll_temac.h
@@ -347,8 +347,10 @@ struct temac_local {
 #ifdef CONFIG_PPC_DCR
 	dcr_host_t sdma_dcrs;
 #endif
-	u32 (*dma_in)(struct temac_local *, int);
-	void (*dma_out)(struct temac_local *, int, u32);
+	u32 (*temac_ior)(struct temac_local *lp, int offset);
+	void (*temac_iow)(struct temac_local *lp, int offset, u32 value);
+	u32 (*dma_in)(struct temac_local *lp, int reg);
+	void (*dma_out)(struct temac_local *lp, int reg, u32 value);
 
 	int tx_irq;
 	int rx_irq;
@@ -372,9 +374,11 @@ struct temac_local {
 	int rx_bd_ci;
 };
 
+/* Wrappers for temac_ior()/temac_iow() function pointers above */
+#define temac_ior(lp, o) ((lp)->temac_ior(lp, o))
+#define temac_iow(lp, o, v) ((lp)->temac_iow(lp, o, v))
+
 /* xilinx_temac.c */
-u32 temac_ior(struct temac_local *lp, int offset);
-void temac_iow(struct temac_local *lp, int offset, u32 value);
 int temac_indirect_busywait(struct temac_local *lp);
 u32 temac_indirect_in32(struct temac_local *lp, int reg);
 void temac_indirect_out32(struct temac_local *lp, int reg, u32 value);
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index bcafb8925f75..58c67138ed2b 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -63,14 +63,24 @@
  * Low level register access functions
  */
 
-u32 temac_ior(struct temac_local *lp, int offset)
+u32 _temac_ior_be(struct temac_local *lp, int offset)
 {
-	return in_be32(lp->regs + offset);
+	return ioread32be(lp->regs + offset);
 }
 
-void temac_iow(struct temac_local *lp, int offset, u32 value)
+void _temac_iow_be(struct temac_local *lp, int offset, u32 value)
 {
-	out_be32(lp->regs + offset, value);
+	return iowrite32be(value, lp->regs + offset);
+}
+
+u32 _temac_ior_le(struct temac_local *lp, int offset)
+{
+	return ioread32(lp->regs + offset);
+}
+
+void _temac_iow_le(struct temac_local *lp, int offset, u32 value)
+{
+	return iowrite32(value, lp->regs + offset);
 }
 
 int temac_indirect_busywait(struct temac_local *lp)
@@ -121,23 +131,35 @@ void temac_indirect_out32(struct temac_local *lp, int reg, u32 value)
 }
 
 /**
- * temac_dma_in32 - Memory mapped DMA read, this function expects a
- * register input that is based on DCR word addresses which
- * are then converted to memory mapped byte addresses
+ * temac_dma_in32_* - Memory mapped DMA read, these function expects a
+ * register input that is based on DCR word addresses which are then
+ * converted to memory mapped byte addresses.  To be assigned to
+ * lp->dma_in32.
  */
-static u32 temac_dma_in32(struct temac_local *lp, int reg)
+static u32 temac_dma_in32_be(struct temac_local *lp, int reg)
 {
-	return in_be32(lp->sdma_regs + (reg << 2));
+	return ioread32be(lp->sdma_regs + (reg << 2));
+}
+
+static u32 temac_dma_in32_le(struct temac_local *lp, int reg)
+{
+	return ioread32(lp->sdma_regs + (reg << 2));
 }
 
 /**
- * temac_dma_out32 - Memory mapped DMA read, this function expects a
- * register input that is based on DCR word addresses which
- * are then converted to memory mapped byte addresses
+ * temac_dma_out32_* - Memory mapped DMA read, these function expects
+ * a register input that is based on DCR word addresses which are then
+ * converted to memory mapped byte addresses.  To be assigned to
+ * lp->dma_out32.
  */
-static void temac_dma_out32(struct temac_local *lp, int reg, u32 value)
+static void temac_dma_out32_be(struct temac_local *lp, int reg, u32 value)
+{
+	iowrite32be(value, lp->sdma_regs + (reg << 2));
+}
+
+static void temac_dma_out32_le(struct temac_local *lp, int reg, u32 value)
 {
-	out_be32(lp->sdma_regs + (reg << 2), value);
+	iowrite32(value, lp->sdma_regs + (reg << 2));
 }
 
 /* DMA register access functions can be DCR based or memory mapped.
@@ -1024,6 +1046,7 @@ static int temac_probe(struct platform_device *pdev)
 	struct resource *res;
 	const void *addr;
 	__be32 *p;
+	bool little_endian;
 	int rc = 0;
 
 	/* Init network device structure */
@@ -1068,6 +1091,24 @@ static int temac_probe(struct platform_device *pdev)
 		return PTR_ERR(lp->regs);
 	}
 
+	/* Select register access functions with the specified
+	 * endianness mode.  Default for OF devices is big-endian.
+	 */
+	little_endian = false;
+	if (temac_np) {
+		if (of_get_property(temac_np, "little-endian", NULL))
+			little_endian = true;
+	} else if (pdata) {
+		little_endian = pdata->reg_little_endian;
+	}
+	if (little_endian) {
+		lp->temac_ior = _temac_ior_le;
+		lp->temac_iow = _temac_iow_le;
+	} else {
+		lp->temac_ior = _temac_ior_be;
+		lp->temac_iow = _temac_iow_be;
+	}
+
 	/* Setup checksum offload, but default to off if not specified */
 	lp->temac_features = 0;
 	if (temac_np) {
@@ -1111,8 +1152,13 @@ static int temac_probe(struct platform_device *pdev)
 				of_node_put(dma_np);
 				return PTR_ERR(lp->sdma_regs);
 			}
-			lp->dma_in = temac_dma_in32;
-			lp->dma_out = temac_dma_out32;
+			if (of_get_property(dma_np, "little-endian", NULL)) {
+				lp->dma_in = temac_dma_in32_le;
+				lp->dma_out = temac_dma_out32_le;
+			} else {
+				lp->dma_in = temac_dma_in32_be;
+				lp->dma_out = temac_dma_out32_be;
+			}
 			dev_dbg(&pdev->dev, "MEM base: %p\n", lp->sdma_regs);
 		}
 
@@ -1132,8 +1178,13 @@ static int temac_probe(struct platform_device *pdev)
 				"could not map DMA registers\n");
 			return PTR_ERR(lp->sdma_regs);
 		}
-		lp->dma_in = temac_dma_in32;
-		lp->dma_out = temac_dma_out32;
+		if (pdata->dma_little_endian) {
+			lp->dma_in = temac_dma_in32_le;
+			lp->dma_out = temac_dma_out32_le;
+		} else {
+			lp->dma_in = temac_dma_in32_be;
+			lp->dma_out = temac_dma_out32_be;
+		}
 
 		/* Get DMA RX and TX interrupts */
 		lp->rx_irq = platform_get_irq(pdev, 0);
diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h
index 82e2f80648b0..af87927abab3 100644
--- a/include/linux/platform_data/xilinx-ll-temac.h
+++ b/include/linux/platform_data/xilinx-ll-temac.h
@@ -14,6 +14,8 @@ struct ll_temac_platform_data {
 	unsigned long long mdio_bus_id; /* Unique id for MDIO bus */
 	int phy_addr;		/* Address of the PHY to connect to */
 	phy_interface_t phy_interface; /* PHY interface mode */
+	bool reg_little_endian;	/* Little endian TEMAC register access  */
+	bool dma_little_endian;	/* Little endian DMA register access  */
 };
 
 #endif /* __LINUX_XILINX_LL_TEMAC_H */
-- 
cgit v1.2.3


From f14f5c11f051ca4a41e65017d94408e5e702ba9d Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Tue, 30 Apr 2019 09:17:54 +0200
Subject: net: ll_temac: Support indirect_mutex share within TEMAC IP

Indirect register access goes through a DCR bus bridge, which
allows only one outstanding transaction.  And to make matters
worse, each TEMAC IP block contains two Ethernet interfaces, and
although they seem to have separate registers for indirect access,
they actually share the registers.  Or to be more specific, MSW, LSW
and CTL registers are physically shared between Ethernet interfaces
in same TEMAC IP, with RDY register being (almost) specificic to
the Ethernet interface.  The 0x10000 bit in RDY reflects combined
bus ready state though.

So we need to take care to synchronize not only within a single
device, but also between devices in same TEMAC IP.

This commit allows to do that with legacy platform devices.

For OF devices, the xlnx,compound parent of the temac node should be
used to find siblings, and setup a shared indirect_mutex between them.
I will leave this work to somebody else, as I don't have hardware to
test that.  No regression is introduced by that, as before this commit
using two Ethernet interfaces in same TEMAC block is simply broken.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/ll_temac.h        |  5 +++-
 drivers/net/ethernet/xilinx/ll_temac_main.c   | 36 +++++++++++++++++++--------
 drivers/net/ethernet/xilinx/ll_temac_mdio.c   | 16 ++++++------
 include/linux/platform_data/xilinx-ll-temac.h |  6 +++++
 4 files changed, 43 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h
index 23d8dd5330f8..990f9ed151b2 100644
--- a/drivers/net/ethernet/xilinx/ll_temac.h
+++ b/drivers/net/ethernet/xilinx/ll_temac.h
@@ -358,7 +358,10 @@ struct temac_local {
 
 	struct sk_buff **rx_skb;
 	spinlock_t rx_lock;
-	struct mutex indirect_mutex;
+	/* For synchronization of indirect register access.  Must be
+	 * shared mutex between interfaces in same TEMAC block.
+	 */
+	struct mutex *indirect_mutex;
 	u32 options;			/* Current options word */
 	int last_link;
 	unsigned int temac_features;
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 179a9984bc64..d3899e7efd45 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -344,7 +344,7 @@ static void temac_do_set_mac_address(struct net_device *ndev)
 	struct temac_local *lp = netdev_priv(ndev);
 
 	/* set up unicast MAC address filter set its mac address */
-	mutex_lock(&lp->indirect_mutex);
+	mutex_lock(lp->indirect_mutex);
 	temac_indirect_out32(lp, XTE_UAW0_OFFSET,
 			     (ndev->dev_addr[0]) |
 			     (ndev->dev_addr[1] << 8) |
@@ -355,7 +355,7 @@ static void temac_do_set_mac_address(struct net_device *ndev)
 	temac_indirect_out32(lp, XTE_UAW1_OFFSET,
 			     (ndev->dev_addr[4] & 0x000000ff) |
 			     (ndev->dev_addr[5] << 8));
-	mutex_unlock(&lp->indirect_mutex);
+	mutex_unlock(lp->indirect_mutex);
 }
 
 static int temac_init_mac_address(struct net_device *ndev, const void *address)
@@ -384,7 +384,7 @@ static void temac_set_multicast_list(struct net_device *ndev)
 	u32 multi_addr_msw, multi_addr_lsw, val;
 	int i;
 
-	mutex_lock(&lp->indirect_mutex);
+	mutex_lock(lp->indirect_mutex);
 	if (ndev->flags & (IFF_ALLMULTI | IFF_PROMISC) ||
 	    netdev_mc_count(ndev) > MULTICAST_CAM_TABLE_NUM) {
 		/*
@@ -423,7 +423,7 @@ static void temac_set_multicast_list(struct net_device *ndev)
 		temac_indirect_out32(lp, XTE_MAW1_OFFSET, 0);
 		dev_info(&ndev->dev, "Promiscuous mode disabled.\n");
 	}
-	mutex_unlock(&lp->indirect_mutex);
+	mutex_unlock(lp->indirect_mutex);
 }
 
 static struct temac_option {
@@ -515,7 +515,7 @@ static u32 temac_setoptions(struct net_device *ndev, u32 options)
 	struct temac_option *tp = &temac_options[0];
 	int reg;
 
-	mutex_lock(&lp->indirect_mutex);
+	mutex_lock(lp->indirect_mutex);
 	while (tp->opt) {
 		reg = temac_indirect_in32(lp, tp->reg) & ~tp->m_or;
 		if (options & tp->opt)
@@ -524,7 +524,7 @@ static u32 temac_setoptions(struct net_device *ndev, u32 options)
 		tp++;
 	}
 	lp->options |= options;
-	mutex_unlock(&lp->indirect_mutex);
+	mutex_unlock(lp->indirect_mutex);
 
 	return 0;
 }
@@ -543,7 +543,7 @@ static void temac_device_reset(struct net_device *ndev)
 
 	dev_dbg(&ndev->dev, "%s()\n", __func__);
 
-	mutex_lock(&lp->indirect_mutex);
+	mutex_lock(lp->indirect_mutex);
 	/* Reset the receiver and wait for it to finish reset */
 	temac_indirect_out32(lp, XTE_RXC1_OFFSET, XTE_RXC1_RXRST_MASK);
 	timeout = 1000;
@@ -595,7 +595,7 @@ static void temac_device_reset(struct net_device *ndev)
 	temac_indirect_out32(lp, XTE_TXC_OFFSET, 0);
 	temac_indirect_out32(lp, XTE_FCC_OFFSET, XTE_FCC_RXFLO_MASK);
 
-	mutex_unlock(&lp->indirect_mutex);
+	mutex_unlock(lp->indirect_mutex);
 
 	/* Sync default options with HW
 	 * but leave receiver and transmitter disabled.  */
@@ -623,7 +623,7 @@ static void temac_adjust_link(struct net_device *ndev)
 	/* hash together the state values to decide if something has changed */
 	link_state = phy->speed | (phy->duplex << 1) | phy->link;
 
-	mutex_lock(&lp->indirect_mutex);
+	mutex_lock(lp->indirect_mutex);
 	if (lp->last_link != link_state) {
 		mii_speed = temac_indirect_in32(lp, XTE_EMCFG_OFFSET);
 		mii_speed &= ~XTE_EMCFG_LINKSPD_MASK;
@@ -639,7 +639,7 @@ static void temac_adjust_link(struct net_device *ndev)
 		lp->last_link = link_state;
 		phy_print_status(phy);
 	}
-	mutex_unlock(&lp->indirect_mutex);
+	mutex_unlock(lp->indirect_mutex);
 }
 
 #ifdef CONFIG_64BIT
@@ -1091,7 +1091,21 @@ static int temac_probe(struct platform_device *pdev)
 	lp->dev = &pdev->dev;
 	lp->options = XTE_OPTION_DEFAULTS;
 	spin_lock_init(&lp->rx_lock);
-	mutex_init(&lp->indirect_mutex);
+
+	/* Setup mutex for synchronization of indirect register access */
+	if (pdata) {
+		if (!pdata->indirect_mutex) {
+			dev_err(&pdev->dev,
+				"indirect_mutex missing in platform_data\n");
+			return -EINVAL;
+		}
+		lp->indirect_mutex = pdata->indirect_mutex;
+	} else {
+		lp->indirect_mutex = devm_kmalloc(&pdev->dev,
+						  sizeof(*lp->indirect_mutex),
+						  GFP_KERNEL);
+		mutex_init(lp->indirect_mutex);
+	}
 
 	/* map device registers */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/net/ethernet/xilinx/ll_temac_mdio.c b/drivers/net/ethernet/xilinx/ll_temac_mdio.c
index c5307e5b8e0a..c2a11703bc6d 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_mdio.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_mdio.c
@@ -29,10 +29,10 @@ static int temac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 	/* Write the PHY address to the MIIM Access Initiator register.
 	 * When the transfer completes, the PHY register value will appear
 	 * in the LSW0 register */
-	mutex_lock(&lp->indirect_mutex);
+	mutex_lock(lp->indirect_mutex);
 	temac_iow(lp, XTE_LSW0_OFFSET, (phy_id << 5) | reg);
 	rc = temac_indirect_in32(lp, XTE_MIIMAI_OFFSET);
-	mutex_unlock(&lp->indirect_mutex);
+	mutex_unlock(lp->indirect_mutex);
 
 	dev_dbg(lp->dev, "temac_mdio_read(phy_id=%i, reg=%x) == %x\n",
 		phy_id, reg, rc);
@@ -50,10 +50,10 @@ static int temac_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val)
 	/* First write the desired value into the write data register
 	 * and then write the address into the access initiator register
 	 */
-	mutex_lock(&lp->indirect_mutex);
+	mutex_lock(lp->indirect_mutex);
 	temac_indirect_out32(lp, XTE_MGTDR_OFFSET, val);
 	temac_indirect_out32(lp, XTE_MIIMAI_OFFSET, (phy_id << 5) | reg);
-	mutex_unlock(&lp->indirect_mutex);
+	mutex_unlock(lp->indirect_mutex);
 
 	return 0;
 }
@@ -87,9 +87,9 @@ int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev)
 
 	/* Enable the MDIO bus by asserting the enable bit and writing
 	 * in the clock config */
-	mutex_lock(&lp->indirect_mutex);
+	mutex_lock(lp->indirect_mutex);
 	temac_indirect_out32(lp, XTE_MC_OFFSET, 1 << 6 | clk_div);
-	mutex_unlock(&lp->indirect_mutex);
+	mutex_unlock(lp->indirect_mutex);
 
 	bus = devm_mdiobus_alloc(&pdev->dev);
 	if (!bus)
@@ -116,10 +116,10 @@ int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev)
 	if (rc)
 		return rc;
 
-	mutex_lock(&lp->indirect_mutex);
+	mutex_lock(lp->indirect_mutex);
 	dev_dbg(lp->dev, "MDIO bus registered;  MC:%x\n",
 		temac_indirect_in32(lp, XTE_MC_OFFSET));
-	mutex_unlock(&lp->indirect_mutex);
+	mutex_unlock(lp->indirect_mutex);
 	return 0;
 }
 
diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h
index af87927abab3..b0b8238a9b7d 100644
--- a/include/linux/platform_data/xilinx-ll-temac.h
+++ b/include/linux/platform_data/xilinx-ll-temac.h
@@ -16,6 +16,12 @@ struct ll_temac_platform_data {
 	phy_interface_t phy_interface; /* PHY interface mode */
 	bool reg_little_endian;	/* Little endian TEMAC register access  */
 	bool dma_little_endian;	/* Little endian DMA register access  */
+	/* Pre-initialized mutex to use for synchronizing indirect
+	 * register access.  When using both interfaces of a single
+	 * TEMAC IP block, the same mutex should be passed here, as
+	 * they share the same DCR bus bridge.
+	 */
+	struct mutex *indirect_mutex;
 };
 
 #endif /* __LINUX_XILINX_LL_TEMAC_H */
-- 
cgit v1.2.3


From 7e97a194aca03c6ff86f84e46e196f5c9ed5c32c Mon Sep 17 00:00:00 2001
From: Esben Haabendal <esben@geanix.com>
Date: Tue, 30 Apr 2019 09:17:58 +0200
Subject: net: ll_temac: Allow configuration of IRQ coalescing

This allows custom setup of IRQ coalescing for platforms using legacy
platform_device. The irq timeout and count parameters can be used for
tuning cpu load vs. latency.

I have maintained the 0x00000400 bit in TX_CHNL_CTRL.  It is specified as
unused in the documentation I have available.  It does not make any
difference in the hardware I have available, so it is left in to not risk
breaking other platforms where it might be used.

Signed-off-by: Esben Haabendal <esben@geanix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/ll_temac.h        |  4 +++
 drivers/net/ethernet/xilinx/ll_temac_main.c   | 40 +++++++++++++++++++--------
 include/linux/platform_data/xilinx-ll-temac.h |  5 ++++
 3 files changed, 37 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/xilinx/ll_temac.h b/drivers/net/ethernet/xilinx/ll_temac.h
index 990f9ed151b2..1aeda084b8f1 100644
--- a/drivers/net/ethernet/xilinx/ll_temac.h
+++ b/drivers/net/ethernet/xilinx/ll_temac.h
@@ -375,6 +375,10 @@ struct temac_local {
 	int tx_bd_next;
 	int tx_bd_tail;
 	int rx_bd_ci;
+
+	/* DMA channel control setup */
+	u32 tx_chnl_ctrl;
+	u32 rx_chnl_ctrl;
 };
 
 /* Wrappers for temac_ior()/temac_iow() function pointers above */
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index fec8e4c22944..bccef30bf64e 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -304,18 +304,15 @@ static int temac_dma_bd_init(struct net_device *ndev)
 		lp->rx_bd_v[i].app0 = cpu_to_be32(STS_CTRL_APP0_IRQONEND);
 	}
 
-	lp->dma_out(lp, TX_CHNL_CTRL, 0x10220400 |
-					  CHNL_CTRL_IRQ_EN |
-					  CHNL_CTRL_IRQ_DLY_EN |
-					  CHNL_CTRL_IRQ_COAL_EN);
-	/* 0x10220483 */
-	/* 0x00100483 */
-	lp->dma_out(lp, RX_CHNL_CTRL, 0xff070000 |
-					  CHNL_CTRL_IRQ_EN |
-					  CHNL_CTRL_IRQ_DLY_EN |
-					  CHNL_CTRL_IRQ_COAL_EN |
-					  CHNL_CTRL_IRQ_IOE);
-	/* 0xff010283 */
+	/* Configure DMA channel (irq setup) */
+	lp->dma_out(lp, TX_CHNL_CTRL, lp->tx_chnl_ctrl |
+		    0x00000400 | // Use 1 Bit Wide Counters. Currently Not Used!
+		    CHNL_CTRL_IRQ_EN | CHNL_CTRL_IRQ_ERR_EN |
+		    CHNL_CTRL_IRQ_DLY_EN | CHNL_CTRL_IRQ_COAL_EN);
+	lp->dma_out(lp, RX_CHNL_CTRL, lp->rx_chnl_ctrl |
+		    CHNL_CTRL_IRQ_IOE |
+		    CHNL_CTRL_IRQ_EN | CHNL_CTRL_IRQ_ERR_EN |
+		    CHNL_CTRL_IRQ_DLY_EN | CHNL_CTRL_IRQ_COAL_EN);
 
 	lp->dma_out(lp, RX_CURDESC_PTR,  lp->rx_bd_p);
 	lp->dma_out(lp, RX_TAILDESC_PTR,
@@ -1191,6 +1188,13 @@ static int temac_probe(struct platform_device *pdev)
 		lp->rx_irq = irq_of_parse_and_map(dma_np, 0);
 		lp->tx_irq = irq_of_parse_and_map(dma_np, 1);
 
+		/* Use defaults for IRQ delay/coalescing setup.  These
+		 * are configuration values, so does not belong in
+		 * device-tree.
+		 */
+		lp->tx_chnl_ctrl = 0x10220000;
+		lp->rx_chnl_ctrl = 0xff070000;
+
 		/* Finished with the DMA node; drop the reference */
 		of_node_put(dma_np);
 	} else if (pdata) {
@@ -1214,6 +1218,18 @@ static int temac_probe(struct platform_device *pdev)
 		/* Get DMA RX and TX interrupts */
 		lp->rx_irq = platform_get_irq(pdev, 0);
 		lp->tx_irq = platform_get_irq(pdev, 1);
+
+		/* IRQ delay/coalescing setup */
+		if (pdata->tx_irq_timeout || pdata->tx_irq_count)
+			lp->tx_chnl_ctrl = (pdata->tx_irq_timeout << 24) |
+				(pdata->tx_irq_count << 16);
+		else
+			lp->tx_chnl_ctrl = 0x10220000;
+		if (pdata->rx_irq_timeout || pdata->rx_irq_count)
+			lp->rx_chnl_ctrl = (pdata->rx_irq_timeout << 24) |
+				(pdata->rx_irq_count << 16);
+		else
+			lp->rx_chnl_ctrl = 0xff070000;
 	}
 
 	/* Error handle returned DMA RX and TX interrupts */
diff --git a/include/linux/platform_data/xilinx-ll-temac.h b/include/linux/platform_data/xilinx-ll-temac.h
index b0b8238a9b7d..368530f98176 100644
--- a/include/linux/platform_data/xilinx-ll-temac.h
+++ b/include/linux/platform_data/xilinx-ll-temac.h
@@ -22,6 +22,11 @@ struct ll_temac_platform_data {
 	 * they share the same DCR bus bridge.
 	 */
 	struct mutex *indirect_mutex;
+	/* DMA channel control setup */
+	u8 tx_irq_timeout;	/* TX Interrupt Delay Time-out */
+	u8 tx_irq_count;	/* TX Interrupt Coalescing Threshold Count */
+	u8 rx_irq_timeout;	/* RX Interrupt Delay Time-out */
+	u8 rx_irq_count;	/* RX Interrupt Coalescing Threshold Count */
 };
 
 #endif /* __LINUX_XILINX_LL_TEMAC_H */
-- 
cgit v1.2.3


From 91a40a48d52d13fbde3239d5839335cabd9a4eae Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 1 May 2019 03:21:05 +0000
Subject: net/mlx5: Fix broken hca cap offset

The cited commit broke the offsets of hca cap struct, fix it.
While at it, cleanup a white space introduced by the same commit.

Fixes: b169e64a2444 ("net/mlx5: Geneve, Add flow table capabilities for Geneve decap with TLV options")
Reported-by: Qian Cai <cai@lca.pw>
Cc: Yevgeny Kliteynik <kliteyn@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/mlx5_ifc.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6a7fc18a9fe3..6b2e6b710ac0 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1265,7 +1265,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         max_geneve_tlv_option_data_len[0x5];
 	u8         reserved_at_570[0x10];
 
-	u8         reserved_at_580[0x1c];
+	u8         reserved_at_580[0x3c];
 	u8         mini_cqe_resp_stride_index[0x1];
 	u8         cqe_128_always[0x1];
 	u8         cqe_compression_128[0x1];
@@ -9566,7 +9566,7 @@ struct mlx5_ifc_sw_icm_bits {
 	u8         sw_icm_start_addr[0x40];
 
 	u8         reserved_at_c0[0x140];
-}; 
+};
 
 struct mlx5_ifc_geneve_tlv_option_bits {
 	u8         modify_field_select[0x40];
-- 
cgit v1.2.3


From 0e1a2a3e6e7d37cea9f8586f6d7745b539147d9f Mon Sep 17 00:00:00 2001
From: Erez Alfasi <ereza@mellanox.com>
Date: Tue, 5 Mar 2019 15:42:23 +0200
Subject: ethtool: Add SFF-8436 and SFF-8636 max EEPROM length definitions

Added max EEPROM length defines for ethtool usage:
 #define ETH_MODULE_SFF_8636_MAX_LEN     640
 #define ETH_MODULE_SFF_8436_MAX_LEN     640

These definitions are used to determine the EEPROM
data length when reading high eeprom pages.

For example, SFF-8636 EEPROM data from page 03h
needs to be stored at data[512] - data[639].

Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/uapi/linux/ethtool.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 818ad368b586..3534ce157ae9 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1712,6 +1712,9 @@ static inline int ethtool_validate_duplex(__u8 duplex)
 #define ETH_MODULE_SFF_8436		0x4
 #define ETH_MODULE_SFF_8436_LEN		256
 
+#define ETH_MODULE_SFF_8636_MAX_LEN     640
+#define ETH_MODULE_SFF_8436_MAX_LEN     640
+
 /* Reset flags */
 /* The reset() operation must clear the flags for the components which
  * were actually reset.  On successful return, the flags indicate the
-- 
cgit v1.2.3


From a708fb7b1f8dcc7a8ed949839958cd5d812dd939 Mon Sep 17 00:00:00 2001
From: Erez Alfasi <ereza@mellanox.com>
Date: Thu, 21 Mar 2019 15:02:13 +0200
Subject: net/mlx5e: ethtool, Add support for EEPROM high pages query

Add the support to read additional EEPROM information from high pages.
Information for modules such as SFF-8436 and SFF-8636:
 1) Application select table
 2) User writable EEPROM
 3) Thresholds and alarms

Signed-off-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |  8 ++---
 drivers/net/ethernet/mellanox/mlx5/core/port.c     | 40 ++++++++++++++++++----
 include/linux/mlx5/port.h                          |  1 +
 3 files changed, 39 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 78dc8fe2a83c..7efaa58ae034 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1561,7 +1561,7 @@ static int mlx5e_get_module_info(struct net_device *netdev,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *dev = priv->mdev;
 	int size_read = 0;
-	u8 data[4];
+	u8 data[4] = {0};
 
 	size_read = mlx5_query_module_eeprom(dev, 0, 2, data);
 	if (size_read < 2)
@@ -1571,17 +1571,17 @@ static int mlx5e_get_module_info(struct net_device *netdev,
 	switch (data[0]) {
 	case MLX5_MODULE_ID_QSFP:
 		modinfo->type       = ETH_MODULE_SFF_8436;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
 		break;
 	case MLX5_MODULE_ID_QSFP_PLUS:
 	case MLX5_MODULE_ID_QSFP28:
 		/* data[1] = revision id */
 		if (data[0] == MLX5_MODULE_ID_QSFP28 || data[1] >= 0x3) {
 			modinfo->type       = ETH_MODULE_SFF_8636;
-			modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN;
 		} else {
 			modinfo->type       = ETH_MODULE_SFF_8436;
-			modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
 		}
 		break;
 	case MLX5_MODULE_ID_SFP:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 361468e0435d..cc262b30aed5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -293,15 +293,36 @@ static int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num)
 	return 0;
 }
 
+static int mlx5_eeprom_page(int offset)
+{
+	if (offset < MLX5_EEPROM_PAGE_LENGTH)
+		/* Addresses between 0-255 - page 00 */
+		return 0;
+
+	/* Addresses between 256 - 639 belongs to pages 01, 02 and 03
+	 * For example, offset = 400 belongs to page 02:
+	 * 1 + ((400 - 256)/128) = 2
+	 */
+	return 1 + ((offset - MLX5_EEPROM_PAGE_LENGTH) /
+		    MLX5_EEPROM_HIGH_PAGE_LENGTH);
+}
+
+static int mlx5_eeprom_high_page_offset(int page_num)
+{
+	if (!page_num) /* Page 0 always start from low page */
+		return 0;
+
+	/* High page */
+	return page_num * MLX5_EEPROM_HIGH_PAGE_LENGTH;
+}
+
 int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 			     u16 offset, u16 size, u8 *data)
 {
+	int module_num, page_num, status, err;
 	u32 out[MLX5_ST_SZ_DW(mcia_reg)];
 	u32 in[MLX5_ST_SZ_DW(mcia_reg)];
-	int module_num;
 	u16 i2c_addr;
-	int status;
-	int err;
 	void *ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0);
 
 	err = mlx5_query_module_num(dev, &module_num);
@@ -311,8 +332,15 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 	memset(in, 0, sizeof(in));
 	size = min_t(int, size, MLX5_EEPROM_MAX_BYTES);
 
-	if (offset < MLX5_EEPROM_PAGE_LENGTH &&
-	    offset + size > MLX5_EEPROM_PAGE_LENGTH)
+	/* Get the page number related to the given offset */
+	page_num = mlx5_eeprom_page(offset);
+
+	/* Set the right offset according to the page number,
+	 * For page_num > 0, relative offset is always >= 128 (high page).
+	 */
+	offset -= mlx5_eeprom_high_page_offset(page_num);
+
+	if (offset + size > MLX5_EEPROM_PAGE_LENGTH)
 		/* Cross pages read, read until offset 256 in low page */
 		size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
 
@@ -321,7 +349,7 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 	MLX5_SET(mcia_reg, in, l, 0);
 	MLX5_SET(mcia_reg, in, module, module_num);
 	MLX5_SET(mcia_reg, in, i2c_device_address, i2c_addr);
-	MLX5_SET(mcia_reg, in, page_number, 0);
+	MLX5_SET(mcia_reg, in, page_number, page_num);
 	MLX5_SET(mcia_reg, in, device_address, offset);
 	MLX5_SET(mcia_reg, in, size, size);
 
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 64e78394fc9c..de9a272c9f3d 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -60,6 +60,7 @@ enum mlx5_an_status {
 #define MLX5_I2C_ADDR_LOW		0x50
 #define MLX5_I2C_ADDR_HIGH		0x51
 #define MLX5_EEPROM_PAGE_LENGTH		256
+#define MLX5_EEPROM_HIGH_PAGE_LENGTH	128
 
 enum mlx5e_link_mode {
 	MLX5E_1000BASE_CX_SGMII	 = 0,
-- 
cgit v1.2.3


From c9bbfb378bc35fcd0b51e4a8950bd50447f39832 Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Fri, 12 Apr 2019 16:14:03 -0500
Subject: net/mlx5: Remove unused mlx5_query_nic_vport_vlans

mlx5_query_nic_vport_vlans() is not used anymore. Hence remove it.
This patch doesn't change any functionality.

Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vport.c | 61 -------------------------
 include/linux/mlx5/vport.h                      |  4 --
 2 files changed, 65 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index ef95feca9961..95cdc8cbcba4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -371,67 +371,6 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_list);
 
-int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev,
-			       u16 vport,
-			       u16 vlans[],
-			       int *size)
-{
-	u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)];
-	void *nic_vport_ctx;
-	int req_list_size;
-	int max_list_size;
-	int out_sz;
-	void *out;
-	int err;
-	int i;
-
-	req_list_size = *size;
-	max_list_size = 1 << MLX5_CAP_GEN(dev, log_max_vlan_list);
-	if (req_list_size > max_list_size) {
-		mlx5_core_warn(dev, "Requested list size (%d) > (%d) max list size\n",
-			       req_list_size, max_list_size);
-		req_list_size = max_list_size;
-	}
-
-	out_sz = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in) +
-			req_list_size * MLX5_ST_SZ_BYTES(vlan_layout);
-
-	memset(in, 0, sizeof(in));
-	out = kzalloc(out_sz, GFP_KERNEL);
-	if (!out)
-		return -ENOMEM;
-
-	MLX5_SET(query_nic_vport_context_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT);
-	MLX5_SET(query_nic_vport_context_in, in, allowed_list_type,
-		 MLX5_NVPRT_LIST_TYPE_VLAN);
-	MLX5_SET(query_nic_vport_context_in, in, vport_number, vport);
-
-	if (vport)
-		MLX5_SET(query_nic_vport_context_in, in, other_vport, 1);
-
-	err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz);
-	if (err)
-		goto out;
-
-	nic_vport_ctx = MLX5_ADDR_OF(query_nic_vport_context_out, out,
-				     nic_vport_context);
-	req_list_size = MLX5_GET(nic_vport_context, nic_vport_ctx,
-				 allowed_list_size);
-
-	*size = req_list_size;
-	for (i = 0; i < req_list_size; i++) {
-		void *vlan_addr = MLX5_ADDR_OF(nic_vport_context,
-					       nic_vport_ctx,
-					       current_uc_mac_address[i]);
-		vlans[i] = MLX5_GET(vlan_layout, vlan_addr, vlan);
-	}
-out:
-	kfree(out);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_vlans);
-
 int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev,
 				u16 vlans[],
 				int list_size)
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 0eef548b9946..3d1c6cdbbba7 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -118,10 +118,6 @@ int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev,
 				  int promisc_uc,
 				  int promisc_mc,
 				  int promisc_all);
-int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev,
-			       u16 vport,
-			       u16 vlans[],
-			       int *size);
 int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev,
 				u16 vlans[],
 				int list_size);
-- 
cgit v1.2.3


From 6f4e02193c9a9ea54dd3151cf97489fa787cd0e6 Mon Sep 17 00:00:00 2001
From: Bodong Wang <bodong@mellanox.com>
Date: Thu, 18 Apr 2019 18:24:15 -0500
Subject: net/mlx5: E-Switch, Use atomic rep state to serialize state change

When the state of rep was introduced, it was also designed to prevent
duplicate unloading of the same rep. Considering the following two
flows when an eswitch manager is at switchdev mode with n VF reps loaded.

+--------------------------------------+--------------------------------+
| cpu-0                                | cpu-1                          |
| --------                             | --------                       |
| mlx5_ib_remove                       | mlx5_eswitch_disable_sriov     |
|  mlx5_ib_unregister_vport_reps       |  esw_offloads_cleanup          |
|   mlx5_eswitch_unregister_vport_reps |   esw_offloads_unload_all_reps |
|    __unload_reps_all_vport           |    __unload_reps_all_vport     |
+--------------------------------------+--------------------------------+

These two flows will try to unload the same rep. Per original design,
once one flow unloads the rep, the state moves to REGISTERED. The 2nd
flow will no longer needs to do the unload and bails out. However, as
read and write of the state is not atomic, when 1st flow is doing the
unload, the state is still LOADED, 2nd flow is able to do the same
unload action. Kernel crash will happen.

To solve this, driver should do atomic test-and-set for the state. So
that only one flow can change the rep state from LOADED to REGISTERED,
and proceed to do the actual unloading.

Since the state is changing to atomic type, all other read/write should
be atomic action as well.

Fixes: f121e0ea9586 (net/mlx5: E-Switch, Add state to eswitch vport representors)
Signed-off-by: Bodong Wang <bodong@mellanox.com>
Reviewed-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Vu Pham <vuhuong@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 36 ++++++++++------------
 include/linux/mlx5/eswitch.h                       |  2 +-
 2 files changed, 18 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index e88feaa293f6..e09ae27485ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -333,7 +333,7 @@ static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
 	esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
 	for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) {
 		rep = &esw->offloads.vport_reps[vf_vport];
-		if (rep->rep_if[REP_ETH].state != REP_LOADED)
+		if (atomic_read(&rep->rep_if[REP_ETH].state) != REP_LOADED)
 			continue;
 
 		err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val);
@@ -1277,7 +1277,8 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 		ether_addr_copy(rep->hw_id, hw_id);
 
 		for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
-			rep->rep_if[rep_type].state = REP_UNREGISTERED;
+			atomic_set(&rep->rep_if[rep_type].state,
+				   REP_UNREGISTERED);
 	}
 
 	return 0;
@@ -1286,11 +1287,9 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
 				      struct mlx5_eswitch_rep *rep, u8 rep_type)
 {
-	if (rep->rep_if[rep_type].state != REP_LOADED)
-		return;
-
-	rep->rep_if[rep_type].unload(rep);
-	rep->rep_if[rep_type].state = REP_REGISTERED;
+	if (atomic_cmpxchg(&rep->rep_if[rep_type].state,
+			   REP_LOADED, REP_REGISTERED) == REP_LOADED)
+		rep->rep_if[rep_type].unload(rep);
 }
 
 static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
@@ -1351,16 +1350,15 @@ static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
 {
 	int err = 0;
 
-	if (rep->rep_if[rep_type].state != REP_REGISTERED)
-		return 0;
-
-	err = rep->rep_if[rep_type].load(esw->dev, rep);
-	if (err)
-		return err;
-
-	rep->rep_if[rep_type].state = REP_LOADED;
+	if (atomic_cmpxchg(&rep->rep_if[rep_type].state,
+			   REP_REGISTERED, REP_LOADED) == REP_REGISTERED) {
+		err = rep->rep_if[rep_type].load(esw->dev, rep);
+		if (err)
+			atomic_set(&rep->rep_if[rep_type].state,
+				   REP_REGISTERED);
+	}
 
-	return 0;
+	return err;
 }
 
 static int __load_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
@@ -2217,7 +2215,7 @@ void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
 		rep_if->get_proto_dev = __rep_if->get_proto_dev;
 		rep_if->priv = __rep_if->priv;
 
-		rep_if->state = REP_REGISTERED;
+		atomic_set(&rep_if->state, REP_REGISTERED);
 	}
 }
 EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
@@ -2232,7 +2230,7 @@ void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
 		__unload_reps_all_vport(esw, max_vf, rep_type);
 
 	mlx5_esw_for_all_reps(esw, i, rep)
-		rep->rep_if[rep_type].state = REP_UNREGISTERED;
+		atomic_set(&rep->rep_if[rep_type].state, REP_UNREGISTERED);
 }
 EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);
 
@@ -2252,7 +2250,7 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
 
 	rep = mlx5_eswitch_get_rep(esw, vport);
 
-	if (rep->rep_if[rep_type].state == REP_LOADED &&
+	if (atomic_read(&rep->rep_if[rep_type].state) == REP_LOADED &&
 	    rep->rep_if[rep_type].get_proto_dev)
 		return rep->rep_if[rep_type].get_proto_dev(rep);
 	return NULL;
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index 96d8435421de..0ca77dd1429c 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -35,7 +35,7 @@ struct mlx5_eswitch_rep_if {
 	void		       (*unload)(struct mlx5_eswitch_rep *rep);
 	void		       *(*get_proto_dev)(struct mlx5_eswitch_rep *rep);
 	void			*priv;
-	u8			state;
+	atomic_t		state;
 };
 
 struct mlx5_eswitch_rep {
-- 
cgit v1.2.3


From 8b952747844526cef50fa2e0ae903f586e3cb2e4 Mon Sep 17 00:00:00 2001
From: Nicolas Ferre <nicolas.ferre@microchip.com>
Date: Fri, 3 May 2019 12:36:58 +0200
Subject: net: macb: shrink macb_platform_data structure

This structure was used intensively for machine specific values
when DT was not used. Since the removal of AVR32 from the kernel,
this structure is only used for passing clocks from PCI macb wrapper, all
other fields being 0.
All other known platforms use DT.

Remove the leftovers but make sure that PCI macb still works as
expected by using default values:
- phydev->irq is set to PHY_POLL by mdiobus_alloc()
- mii_bus->phy_mask is cleared while allocating it
- bp->phy_interface is set to PHY_INTERFACE_MODE_MII if mode not found
in DT.

This simplifies driver probe path and particularly phy handling.

Signed-off-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 59 ++++++--------------------------
 include/linux/platform_data/macb.h       |  9 -----
 2 files changed, 11 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 59531adcbb42..bd6a62f4bd7d 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -285,34 +285,22 @@ static void macb_set_hwaddr(struct macb *bp)
 
 static void macb_get_hwaddr(struct macb *bp)
 {
-	struct macb_platform_data *pdata;
 	u32 bottom;
 	u16 top;
 	u8 addr[6];
 	int i;
 
-	pdata = dev_get_platdata(&bp->pdev->dev);
-
 	/* Check all 4 address register for valid address */
 	for (i = 0; i < 4; i++) {
 		bottom = macb_or_gem_readl(bp, SA1B + i * 8);
 		top = macb_or_gem_readl(bp, SA1T + i * 8);
 
-		if (pdata && pdata->rev_eth_addr) {
-			addr[5] = bottom & 0xff;
-			addr[4] = (bottom >> 8) & 0xff;
-			addr[3] = (bottom >> 16) & 0xff;
-			addr[2] = (bottom >> 24) & 0xff;
-			addr[1] = top & 0xff;
-			addr[0] = (top & 0xff00) >> 8;
-		} else {
-			addr[0] = bottom & 0xff;
-			addr[1] = (bottom >> 8) & 0xff;
-			addr[2] = (bottom >> 16) & 0xff;
-			addr[3] = (bottom >> 24) & 0xff;
-			addr[4] = top & 0xff;
-			addr[5] = (top >> 8) & 0xff;
-		}
+		addr[0] = bottom & 0xff;
+		addr[1] = (bottom >> 8) & 0xff;
+		addr[2] = (bottom >> 16) & 0xff;
+		addr[3] = (bottom >> 24) & 0xff;
+		addr[4] = top & 0xff;
+		addr[5] = (top >> 8) & 0xff;
 
 		if (is_valid_ether_addr(addr)) {
 			memcpy(bp->dev->dev_addr, addr, sizeof(addr));
@@ -510,12 +498,10 @@ static void macb_handle_link_change(struct net_device *dev)
 static int macb_mii_probe(struct net_device *dev)
 {
 	struct macb *bp = netdev_priv(dev);
-	struct macb_platform_data *pdata;
 	struct phy_device *phydev;
 	struct device_node *np;
-	int phy_irq, ret, i;
+	int ret, i;
 
-	pdata = dev_get_platdata(&bp->pdev->dev);
 	np = bp->pdev->dev.of_node;
 	ret = 0;
 
@@ -557,19 +543,6 @@ static int macb_mii_probe(struct net_device *dev)
 			return -ENXIO;
 		}
 
-		if (pdata) {
-			if (gpio_is_valid(pdata->phy_irq_pin)) {
-				ret = devm_gpio_request(&bp->pdev->dev,
-							pdata->phy_irq_pin, "phy int");
-				if (!ret) {
-					phy_irq = gpio_to_irq(pdata->phy_irq_pin);
-					phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq;
-				}
-			} else {
-				phydev->irq = PHY_POLL;
-			}
-		}
-
 		/* attach the mac to the phy */
 		ret = phy_connect_direct(dev, phydev, &macb_handle_link_change,
 					 bp->phy_interface);
@@ -598,7 +571,6 @@ static int macb_mii_probe(struct net_device *dev)
 
 static int macb_mii_init(struct macb *bp)
 {
-	struct macb_platform_data *pdata;
 	struct device_node *np;
 	int err = -ENXIO;
 
@@ -618,7 +590,6 @@ static int macb_mii_init(struct macb *bp)
 		 bp->pdev->name, bp->pdev->id);
 	bp->mii_bus->priv = bp;
 	bp->mii_bus->parent = &bp->pdev->dev;
-	pdata = dev_get_platdata(&bp->pdev->dev);
 
 	dev_set_drvdata(&bp->dev->dev, bp->mii_bus);
 
@@ -632,9 +603,6 @@ static int macb_mii_init(struct macb *bp)
 
 		err = mdiobus_register(bp->mii_bus);
 	} else {
-		if (pdata)
-			bp->mii_bus->phy_mask = pdata->phy_mask;
-
 		err = of_mdiobus_register(bp->mii_bus, np);
 	}
 
@@ -4050,7 +4018,6 @@ static int macb_probe(struct platform_device *pdev)
 	struct clk *pclk, *hclk = NULL, *tx_clk = NULL, *rx_clk = NULL;
 	struct clk *tsu_clk = NULL;
 	unsigned int queue_mask, num_queues;
-	struct macb_platform_data *pdata;
 	bool native_io;
 	struct phy_device *phydev;
 	struct net_device *dev;
@@ -4182,15 +4149,11 @@ static int macb_probe(struct platform_device *pdev)
 	}
 
 	err = of_get_phy_mode(np);
-	if (err < 0) {
-		pdata = dev_get_platdata(&pdev->dev);
-		if (pdata && pdata->is_rmii)
-			bp->phy_interface = PHY_INTERFACE_MODE_RMII;
-		else
-			bp->phy_interface = PHY_INTERFACE_MODE_MII;
-	} else {
+	if (err < 0)
+		/* not found in DT, MII by default */
+		bp->phy_interface = PHY_INTERFACE_MODE_MII;
+	else
 		bp->phy_interface = err;
-	}
 
 	/* IP specific init */
 	err = init(pdev);
diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h
index 7815d50c26ff..2bc51b822956 100644
--- a/include/linux/platform_data/macb.h
+++ b/include/linux/platform_data/macb.h
@@ -12,19 +12,10 @@
 
 /**
  * struct macb_platform_data - platform data for MACB Ethernet
- * @phy_mask:		phy mask passed when register the MDIO bus
- *			within the driver
- * @phy_irq_pin:	PHY IRQ
- * @is_rmii:		using RMII interface?
- * @rev_eth_addr:	reverse Ethernet address byte order
  * @pclk:		platform clock
  * @hclk:		AHB clock
  */
 struct macb_platform_data {
-	u32		phy_mask;
-	int		phy_irq_pin;
-	u8		is_rmii;
-	u8		rev_eth_addr;
 	struct clk	*pclk;
 	struct clk	*hclk;
 };
-- 
cgit v1.2.3


From 554aae35007e49f533d3d10e788295f7141725bc Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Thu, 2 May 2019 23:23:29 +0300
Subject: lib: Add support for generic packing operations

This provides an unified API for accessing register bit fields
regardless of memory layout. The basic unit of data for these API
functions is the u64. The process of transforming an u64 from native CPU
encoding into the peripheral's encoding is called 'pack', and
transforming it from peripheral to native CPU encoding is 'unpack'.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/packing.txt | 149 ++++++++++++++++++++++++++++++++
 MAINTAINERS               |   8 ++
 include/linux/packing.h   |  49 +++++++++++
 lib/Kconfig               |  17 ++++
 lib/Makefile              |   1 +
 lib/packing.c             | 213 ++++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 437 insertions(+)
 create mode 100644 Documentation/packing.txt
 create mode 100644 include/linux/packing.h
 create mode 100644 lib/packing.c

(limited to 'include')

diff --git a/Documentation/packing.txt b/Documentation/packing.txt
new file mode 100644
index 000000000000..f830c98645f1
--- /dev/null
+++ b/Documentation/packing.txt
@@ -0,0 +1,149 @@
+================================================
+Generic bitfield packing and unpacking functions
+================================================
+
+Problem statement
+-----------------
+
+When working with hardware, one has to choose between several approaches of
+interfacing with it.
+One can memory-map a pointer to a carefully crafted struct over the hardware
+device's memory region, and access its fields as struct members (potentially
+declared as bitfields). But writing code this way would make it less portable,
+due to potential endianness mismatches between the CPU and the hardware device.
+Additionally, one has to pay close attention when translating register
+definitions from the hardware documentation into bit field indices for the
+structs. Also, some hardware (typically networking equipment) tends to group
+its register fields in ways that violate any reasonable word boundaries
+(sometimes even 64 bit ones). This creates the inconvenience of having to
+define "high" and "low" portions of register fields within the struct.
+A more robust alternative to struct field definitions would be to extract the
+required fields by shifting the appropriate number of bits. But this would
+still not protect from endianness mismatches, except if all memory accesses
+were performed byte-by-byte. Also the code can easily get cluttered, and the
+high-level idea might get lost among the many bit shifts required.
+Many drivers take the bit-shifting approach and then attempt to reduce the
+clutter with tailored macros, but more often than not these macros take
+shortcuts that still prevent the code from being truly portable.
+
+The solution
+------------
+
+This API deals with 2 basic operations:
+  - Packing a CPU-usable number into a memory buffer (with hardware
+    constraints/quirks)
+  - Unpacking a memory buffer (which has hardware constraints/quirks)
+    into a CPU-usable number.
+
+The API offers an abstraction over said hardware constraints and quirks,
+over CPU endianness and therefore between possible mismatches between
+the two.
+
+The basic unit of these API functions is the u64. From the CPU's
+perspective, bit 63 always means bit offset 7 of byte 7, albeit only
+logically. The question is: where do we lay this bit out in memory?
+
+The following examples cover the memory layout of a packed u64 field.
+The byte offsets in the packed buffer are always implicitly 0, 1, ... 7.
+What the examples show is where the logical bytes and bits sit.
+
+1. Normally (no quirks), we would do it like this:
+
+63 62 61 60 59 58 57 56 55 54 53 52 51 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32
+7                       6                       5                        4
+31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10  9  8  7  6  5  4  3  2  1  0
+3                       2                       1                        0
+
+That is, the MSByte (7) of the CPU-usable u64 sits at memory offset 0, and the
+LSByte (0) of the u64 sits at memory offset 7.
+This corresponds to what most folks would regard to as "big endian", where
+bit i corresponds to the number 2^i. This is also referred to in the code
+comments as "logical" notation.
+
+
+2. If QUIRK_MSB_ON_THE_RIGHT is set, we do it like this:
+
+56 57 58 59 60 61 62 63 48 49 50 51 52 53 54 55 40 41 42 43 44 45 46 47 32 33 34 35 36 37 38 39
+7                       6                        5                       4
+24 25 26 27 28 29 30 31 16 17 18 19 20 21 22 23  8  9 10 11 12 13 14 15  0  1  2  3  4  5  6  7
+3                       2                        1                       0
+
+That is, QUIRK_MSB_ON_THE_RIGHT does not affect byte positioning, but
+inverts bit offsets inside a byte.
+
+
+3. If QUIRK_LITTLE_ENDIAN is set, we do it like this:
+
+39 38 37 36 35 34 33 32 47 46 45 44 43 42 41 40 55 54 53 52 51 50 49 48 63 62 61 60 59 58 57 56
+4                       5                       6                       7
+7  6  5  4  3  2  1  0  15 14 13 12 11 10  9  8 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24
+0                       1                       2                       3
+
+Therefore, QUIRK_LITTLE_ENDIAN means that inside the memory region, every
+byte from each 4-byte word is placed at its mirrored position compared to
+the boundary of that word.
+
+4. If QUIRK_MSB_ON_THE_RIGHT and QUIRK_LITTLE_ENDIAN are both set, we do it
+   like this:
+
+32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
+4                       5                       6                       7
+0  1  2  3  4  5  6  7  8   9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
+0                       1                       2                       3
+
+
+5. If just QUIRK_LSW32_IS_FIRST is set, we do it like this:
+
+31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 15 14 13 12 11 10  9  8  7  6  5  4  3  2  1  0
+3                       2                       1                        0
+63 62 61 60 59 58 57 56 55 54 53 52 51 50 49 48 47 46 45 44 43 42 41 40 39 38 37 36 35 34 33 32
+7                       6                       5                        4
+
+In this case the 8 byte memory region is interpreted as follows: first
+4 bytes correspond to the least significant 4-byte word, next 4 bytes to
+the more significant 4-byte word.
+
+
+6. If QUIRK_LSW32_IS_FIRST and QUIRK_MSB_ON_THE_RIGHT are set, we do it like
+   this:
+
+24 25 26 27 28 29 30 31 16 17 18 19 20 21 22 23  8  9 10 11 12 13 14 15  0  1  2  3  4  5  6  7
+3                       2                        1                       0
+56 57 58 59 60 61 62 63 48 49 50 51 52 53 54 55 40 41 42 43 44 45 46 47 32 33 34 35 36 37 38 39
+7                       6                        5                       4
+
+
+7. If QUIRK_LSW32_IS_FIRST and QUIRK_LITTLE_ENDIAN are set, it looks like
+   this:
+
+7  6  5  4  3  2  1  0  15 14 13 12 11 10  9  8 23 22 21 20 19 18 17 16 31 30 29 28 27 26 25 24
+0                       1                       2                       3
+39 38 37 36 35 34 33 32 47 46 45 44 43 42 41 40 55 54 53 52 51 50 49 48 63 62 61 60 59 58 57 56
+4                       5                       6                       7
+
+
+8. If QUIRK_LSW32_IS_FIRST, QUIRK_LITTLE_ENDIAN and QUIRK_MSB_ON_THE_RIGHT
+   are set, it looks like this:
+
+0  1  2  3  4  5  6  7  8   9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
+0                       1                       2                       3
+32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
+4                       5                       6                       7
+
+
+We always think of our offsets as if there were no quirk, and we translate
+them afterwards, before accessing the memory region.
+
+Intended use
+------------
+
+Drivers that opt to use this API first need to identify which of the above 3
+quirk combinations (for a total of 8) match what the hardware documentation
+describes. Then they should wrap the packing() function, creating a new
+xxx_packing() that calls it using the proper QUIRK_* one-hot bits set.
+
+The packing() function returns an int-encoded error code, which protects the
+programmer against incorrect API use.  The errors are not expected to occur
+durring runtime, therefore it is reasonable for xxx_packing() to return void
+and simply swallow those errors. Optionally it can dump stack or print the
+error description.
diff --git a/MAINTAINERS b/MAINTAINERS
index 0af66fa919a8..ff029f3d0f13 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11673,6 +11673,14 @@ L:	linux-i2c@vger.kernel.org
 S:	Orphan
 F:	drivers/i2c/busses/i2c-pasemi.c
 
+PACKING
+M:	Vladimir Oltean <olteanv@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	lib/packing.c
+F:	include/linux/packing.h
+F:	Documentation/packing.txt
+
 PADATA PARALLEL EXECUTION MECHANISM
 M:	Steffen Klassert <steffen.klassert@secunet.com>
 L:	linux-crypto@vger.kernel.org
diff --git a/include/linux/packing.h b/include/linux/packing.h
new file mode 100644
index 000000000000..54667735cc67
--- /dev/null
+++ b/include/linux/packing.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2016-2018, NXP Semiconductors
+ * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#ifndef _LINUX_PACKING_H
+#define _LINUX_PACKING_H
+
+#include <linux/types.h>
+#include <linux/bitops.h>
+
+#define QUIRK_MSB_ON_THE_RIGHT	BIT(0)
+#define QUIRK_LITTLE_ENDIAN	BIT(1)
+#define QUIRK_LSW32_IS_FIRST	BIT(2)
+
+enum packing_op {
+	PACK,
+	UNPACK,
+};
+
+/**
+ * packing - Convert numbers (currently u64) between a packed and an unpacked
+ *	     format. Unpacked means laid out in memory in the CPU's native
+ *	     understanding of integers, while packed means anything else that
+ *	     requires translation.
+ *
+ * @pbuf: Pointer to a buffer holding the packed value.
+ * @uval: Pointer to an u64 holding the unpacked value.
+ * @startbit: The index (in logical notation, compensated for quirks) where
+ *	      the packed value starts within pbuf. Must be larger than, or
+ *	      equal to, endbit.
+ * @endbit: The index (in logical notation, compensated for quirks) where
+ *	    the packed value ends within pbuf. Must be smaller than, or equal
+ *	    to, startbit.
+ * @op: If PACK, then uval will be treated as const pointer and copied (packed)
+ *	into pbuf, between startbit and endbit.
+ *	If UNPACK, then pbuf will be treated as const pointer and the logical
+ *	value between startbit and endbit will be copied (unpacked) to uval.
+ * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and
+ *	    QUIRK_MSB_ON_THE_RIGHT.
+ *
+ * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming
+ *	   correct usage, return code may be discarded.
+ *	   If op is PACK, pbuf is modified.
+ *	   If op is UNPACK, uval is modified.
+ */
+int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen,
+	    enum packing_op op, u8 quirks);
+
+#endif
diff --git a/lib/Kconfig b/lib/Kconfig
index a9e56539bd11..ac1fcf06d8ea 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -18,6 +18,23 @@ config RAID6_PQ_BENCHMARK
 	  Benchmark all available RAID6 PQ functions on init and choose the
 	  fastest one.
 
+config PACKING
+	bool "Generic bitfield packing and unpacking"
+	default n
+	help
+	  This option provides the packing() helper function, which permits
+	  converting bitfields between a CPU-usable representation and a
+	  memory representation that can have any combination of these quirks:
+	    - Is little endian (bytes are reversed within a 32-bit group)
+	    - The least-significant 32-bit word comes first (within a 64-bit
+	      group)
+	    - The most significant bit of a byte is at its right (bit 0 of a
+	      register description is numerically 2^7).
+	  Drivers may use these helpers to match the bit indices as described
+	  in the data sheets of the peripherals they are in control of.
+
+	  When in doubt, say N.
+
 config BITREVERSE
 	tristate
 
diff --git a/lib/Makefile b/lib/Makefile
index 3b08673e8881..7d4db18fabf1 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -108,6 +108,7 @@ obj-$(CONFIG_DEBUG_LIST) += list_debug.o
 obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
 
 obj-$(CONFIG_BITREVERSE) += bitrev.o
+obj-$(CONFIG_PACKING)	+= packing.o
 obj-$(CONFIG_RATIONAL)	+= rational.o
 obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
 obj-$(CONFIG_CRC16)	+= crc16.o
diff --git a/lib/packing.c b/lib/packing.c
new file mode 100644
index 000000000000..50d1e9f2f5a7
--- /dev/null
+++ b/lib/packing.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018, NXP Semiconductors
+ * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#include <linux/packing.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+
+static int get_le_offset(int offset)
+{
+	int closest_multiple_of_4;
+
+	closest_multiple_of_4 = (offset / 4) * 4;
+	offset -= closest_multiple_of_4;
+	return closest_multiple_of_4 + (3 - offset);
+}
+
+static int get_reverse_lsw32_offset(int offset, size_t len)
+{
+	int closest_multiple_of_4;
+	int word_index;
+
+	word_index = offset / 4;
+	closest_multiple_of_4 = word_index * 4;
+	offset -= closest_multiple_of_4;
+	word_index = (len / 4) - word_index - 1;
+	return word_index * 4 + offset;
+}
+
+static u64 bit_reverse(u64 val, unsigned int width)
+{
+	u64 new_val = 0;
+	unsigned int bit;
+	unsigned int i;
+
+	for (i = 0; i < width; i++) {
+		bit = (val & (1 << i)) != 0;
+		new_val |= (bit << (width - i - 1));
+	}
+	return new_val;
+}
+
+static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit,
+				       int *box_end_bit, u8 *box_mask)
+{
+	int box_bit_width = *box_start_bit - *box_end_bit + 1;
+	int new_box_start_bit, new_box_end_bit;
+
+	*to_write >>= *box_end_bit;
+	*to_write = bit_reverse(*to_write, box_bit_width);
+	*to_write <<= *box_end_bit;
+
+	new_box_end_bit   = box_bit_width - *box_start_bit - 1;
+	new_box_start_bit = box_bit_width - *box_end_bit - 1;
+	*box_mask = GENMASK_ULL(new_box_start_bit, new_box_end_bit);
+	*box_start_bit = new_box_start_bit;
+	*box_end_bit   = new_box_end_bit;
+}
+
+/**
+ * packing - Convert numbers (currently u64) between a packed and an unpacked
+ *	     format. Unpacked means laid out in memory in the CPU's native
+ *	     understanding of integers, while packed means anything else that
+ *	     requires translation.
+ *
+ * @pbuf: Pointer to a buffer holding the packed value.
+ * @uval: Pointer to an u64 holding the unpacked value.
+ * @startbit: The index (in logical notation, compensated for quirks) where
+ *	      the packed value starts within pbuf. Must be larger than, or
+ *	      equal to, endbit.
+ * @endbit: The index (in logical notation, compensated for quirks) where
+ *	    the packed value ends within pbuf. Must be smaller than, or equal
+ *	    to, startbit.
+ * @op: If PACK, then uval will be treated as const pointer and copied (packed)
+ *	into pbuf, between startbit and endbit.
+ *	If UNPACK, then pbuf will be treated as const pointer and the logical
+ *	value between startbit and endbit will be copied (unpacked) to uval.
+ * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and
+ *	    QUIRK_MSB_ON_THE_RIGHT.
+ *
+ * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming
+ *	   correct usage, return code may be discarded.
+ *	   If op is PACK, pbuf is modified.
+ *	   If op is UNPACK, uval is modified.
+ */
+int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen,
+	    enum packing_op op, u8 quirks)
+{
+	/* Number of bits for storing "uval"
+	 * also width of the field to access in the pbuf
+	 */
+	u64 value_width;
+	/* Logical byte indices corresponding to the
+	 * start and end of the field.
+	 */
+	int plogical_first_u8, plogical_last_u8, box;
+
+	/* startbit is expected to be larger than endbit */
+	if (startbit < endbit)
+		/* Invalid function call */
+		return -EINVAL;
+
+	value_width = startbit - endbit + 1;
+	if (value_width > 64)
+		return -ERANGE;
+
+	/* Check if "uval" fits in "value_width" bits.
+	 * If value_width is 64, the check will fail, but any
+	 * 64-bit uval will surely fit.
+	 */
+	if (op == PACK && value_width < 64 && (*uval >= (1ull << value_width)))
+		/* Cannot store "uval" inside "value_width" bits.
+		 * Truncating "uval" is most certainly not desirable,
+		 * so simply erroring out is appropriate.
+		 */
+		return -ERANGE;
+
+	/* Initialize parameter */
+	if (op == UNPACK)
+		*uval = 0;
+
+	/* Iterate through an idealistic view of the pbuf as an u64 with
+	 * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low
+	 * logical bit significance. "box" denotes the current logical u8.
+	 */
+	plogical_first_u8 = startbit / 8;
+	plogical_last_u8  = endbit / 8;
+
+	for (box = plogical_first_u8; box >= plogical_last_u8; box--) {
+		/* Bit indices into the currently accessed 8-bit box */
+		int box_start_bit, box_end_bit, box_addr;
+		u8  box_mask;
+		/* Corresponding bits from the unpacked u64 parameter */
+		int proj_start_bit, proj_end_bit;
+		u64 proj_mask;
+
+		/* This u8 may need to be accessed in its entirety
+		 * (from bit 7 to bit 0), or not, depending on the
+		 * input arguments startbit and endbit.
+		 */
+		if (box == plogical_first_u8)
+			box_start_bit = startbit % 8;
+		else
+			box_start_bit = 7;
+		if (box == plogical_last_u8)
+			box_end_bit = endbit % 8;
+		else
+			box_end_bit = 0;
+
+		/* We have determined the box bit start and end.
+		 * Now we calculate where this (masked) u8 box would fit
+		 * in the unpacked (CPU-readable) u64 - the u8 box's
+		 * projection onto the unpacked u64. Though the
+		 * box is u8, the projection is u64 because it may fall
+		 * anywhere within the unpacked u64.
+		 */
+		proj_start_bit = ((box * 8) + box_start_bit) - endbit;
+		proj_end_bit   = ((box * 8) + box_end_bit) - endbit;
+		proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit);
+		box_mask  = GENMASK_ULL(box_start_bit, box_end_bit);
+
+		/* Determine the offset of the u8 box inside the pbuf,
+		 * adjusted for quirks. The adjusted box_addr will be used for
+		 * effective addressing inside the pbuf (so it's not
+		 * logical any longer).
+		 */
+		box_addr = pbuflen - box - 1;
+		if (quirks & QUIRK_LITTLE_ENDIAN)
+			box_addr = get_le_offset(box_addr);
+		if (quirks & QUIRK_LSW32_IS_FIRST)
+			box_addr = get_reverse_lsw32_offset(box_addr,
+							    pbuflen);
+
+		if (op == UNPACK) {
+			u64 pval;
+
+			/* Read from pbuf, write to uval */
+			pval = ((u8 *)pbuf)[box_addr] & box_mask;
+			if (quirks & QUIRK_MSB_ON_THE_RIGHT)
+				adjust_for_msb_right_quirk(&pval,
+							   &box_start_bit,
+							   &box_end_bit,
+							   &box_mask);
+
+			pval >>= box_end_bit;
+			pval <<= proj_end_bit;
+			*uval &= ~proj_mask;
+			*uval |= pval;
+		} else {
+			u64 pval;
+
+			/* Write to pbuf, read from uval */
+			pval = (*uval) & proj_mask;
+			pval >>= proj_end_bit;
+			if (quirks & QUIRK_MSB_ON_THE_RIGHT)
+				adjust_for_msb_right_quirk(&pval,
+							   &box_start_bit,
+							   &box_end_bit,
+							   &box_mask);
+
+			pval <<= box_end_bit;
+			((u8 *)pbuf)[box_addr] &= ~box_mask;
+			((u8 *)pbuf)[box_addr] |= pval;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL(packing);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Generic bitfield packing and unpacking");
-- 
cgit v1.2.3


From 8aa9ebccae87621d997707e4f25e53fddd7e30e4 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Thu, 2 May 2019 23:23:30 +0300
Subject: net: dsa: Introduce driver for NXP SJA1105 5-port L2 switch

At this moment the following is supported:
* Link state management through phylib
* Autonomous L2 forwarding managed through iproute2 bridge commands.

IP termination must be done currently through the master netdevice,
since the switch is unmanaged at this point and using
DSA_TAG_PROTO_NONE.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Georg Waibel <georg.waibel@sensor-technik.de>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                                      |   6 +
 drivers/net/dsa/Kconfig                          |   2 +
 drivers/net/dsa/Makefile                         |   1 +
 drivers/net/dsa/sja1105/Kconfig                  |  16 +
 drivers/net/dsa/sja1105/Makefile                 |   8 +
 drivers/net/dsa/sja1105/sja1105.h                | 138 ++++
 drivers/net/dsa/sja1105/sja1105_clocking.c       | 598 ++++++++++++++
 drivers/net/dsa/sja1105/sja1105_dynamic_config.c | 489 ++++++++++++
 drivers/net/dsa/sja1105/sja1105_dynamic_config.h |  43 +
 drivers/net/dsa/sja1105/sja1105_main.c           | 928 ++++++++++++++++++++++
 drivers/net/dsa/sja1105/sja1105_spi.c            | 553 +++++++++++++
 drivers/net/dsa/sja1105/sja1105_static_config.c  | 949 +++++++++++++++++++++++
 drivers/net/dsa/sja1105/sja1105_static_config.h  | 250 ++++++
 include/linux/dsa/sja1105.h                      |  19 +
 14 files changed, 4000 insertions(+)
 create mode 100644 drivers/net/dsa/sja1105/Kconfig
 create mode 100644 drivers/net/dsa/sja1105/Makefile
 create mode 100644 drivers/net/dsa/sja1105/sja1105.h
 create mode 100644 drivers/net/dsa/sja1105/sja1105_clocking.c
 create mode 100644 drivers/net/dsa/sja1105/sja1105_dynamic_config.c
 create mode 100644 drivers/net/dsa/sja1105/sja1105_dynamic_config.h
 create mode 100644 drivers/net/dsa/sja1105/sja1105_main.c
 create mode 100644 drivers/net/dsa/sja1105/sja1105_spi.c
 create mode 100644 drivers/net/dsa/sja1105/sja1105_static_config.c
 create mode 100644 drivers/net/dsa/sja1105/sja1105_static_config.h
 create mode 100644 include/linux/dsa/sja1105.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index ff029f3d0f13..25db3db8fe38 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11120,6 +11120,12 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/sound/sgtl5000.txt
 F:	sound/soc/codecs/sgtl5000*
 
+NXP SJA1105 ETHERNET SWITCH DRIVER
+M:	Vladimir Oltean <olteanv@gmail.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/net/dsa/sja1105
+
 NXP TDA998X DRM DRIVER
 M:	Russell King <linux@armlinux.org.uk>
 S:	Maintained
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 82560b710681..c6c5ecdbcaef 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -51,6 +51,8 @@ source "drivers/net/dsa/microchip/Kconfig"
 
 source "drivers/net/dsa/mv88e6xxx/Kconfig"
 
+source "drivers/net/dsa/sja1105/Kconfig"
+
 config NET_DSA_QCA8K
 	tristate "Qualcomm Atheros QCA8K Ethernet switch family support"
 	depends on NET_DSA
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index 82e5d794c41f..fefb6aaa82ba 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -18,3 +18,4 @@ obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx.o
 obj-y				+= b53/
 obj-y				+= microchip/
 obj-y				+= mv88e6xxx/
+obj-y				+= sja1105/
diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig
new file mode 100644
index 000000000000..038685bb9d57
--- /dev/null
+++ b/drivers/net/dsa/sja1105/Kconfig
@@ -0,0 +1,16 @@
+config NET_DSA_SJA1105
+tristate "NXP SJA1105 Ethernet switch family support"
+	depends on NET_DSA && SPI
+	select PACKING
+	select CRC32
+	help
+	  This is the driver for the NXP SJA1105 automotive Ethernet switch
+	  family. These are 5-port devices and are managed over an SPI
+	  interface. Probing is handled based on OF bindings and so is the
+	  linkage to phylib. The driver supports the following revisions:
+	    - SJA1105E (Gen. 1, No TT-Ethernet)
+	    - SJA1105T (Gen. 1, TT-Ethernet)
+	    - SJA1105P (Gen. 2, No SGMII, No TT-Ethernet)
+	    - SJA1105Q (Gen. 2, No SGMII, TT-Ethernet)
+	    - SJA1105R (Gen. 2, SGMII, No TT-Ethernet)
+	    - SJA1105S (Gen. 2, SGMII, TT-Ethernet)
diff --git a/drivers/net/dsa/sja1105/Makefile b/drivers/net/dsa/sja1105/Makefile
new file mode 100644
index 000000000000..d3237b313a4e
--- /dev/null
+++ b/drivers/net/dsa/sja1105/Makefile
@@ -0,0 +1,8 @@
+obj-$(CONFIG_NET_DSA_SJA1105) += sja1105.o
+
+sja1105-objs := \
+    sja1105_spi.o \
+    sja1105_main.o \
+    sja1105_clocking.o \
+    sja1105_static_config.o \
+    sja1105_dynamic_config.o \
diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
new file mode 100644
index 000000000000..e01cb854cbcd
--- /dev/null
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -0,0 +1,138 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2018, Sensor-Technik Wiedemann GmbH
+ * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#ifndef _SJA1105_H
+#define _SJA1105_H
+
+#include <linux/dsa/sja1105.h>
+#include <net/dsa.h>
+#include "sja1105_static_config.h"
+
+#define SJA1105_NUM_PORTS		5
+#define SJA1105_NUM_TC			8
+#define SJA1105ET_FDB_BIN_SIZE		4
+
+/* Keeps the different addresses between E/T and P/Q/R/S */
+struct sja1105_regs {
+	u64 device_id;
+	u64 prod_id;
+	u64 status;
+	u64 rgu;
+	u64 config;
+	u64 rmii_pll1;
+	u64 pad_mii_tx[SJA1105_NUM_PORTS];
+	u64 cgu_idiv[SJA1105_NUM_PORTS];
+	u64 rgmii_pad_mii_tx[SJA1105_NUM_PORTS];
+	u64 mii_tx_clk[SJA1105_NUM_PORTS];
+	u64 mii_rx_clk[SJA1105_NUM_PORTS];
+	u64 mii_ext_tx_clk[SJA1105_NUM_PORTS];
+	u64 mii_ext_rx_clk[SJA1105_NUM_PORTS];
+	u64 rgmii_tx_clk[SJA1105_NUM_PORTS];
+	u64 rmii_ref_clk[SJA1105_NUM_PORTS];
+	u64 rmii_ext_tx_clk[SJA1105_NUM_PORTS];
+	u64 mac[SJA1105_NUM_PORTS];
+	u64 mac_hl1[SJA1105_NUM_PORTS];
+	u64 mac_hl2[SJA1105_NUM_PORTS];
+	u64 qlevel[SJA1105_NUM_PORTS];
+};
+
+struct sja1105_info {
+	u64 device_id;
+	/* Needed for distinction between P and R, and between Q and S
+	 * (since the parts with/without SGMII share the same
+	 * switch core and device_id)
+	 */
+	u64 part_no;
+	const struct sja1105_dynamic_table_ops *dyn_ops;
+	const struct sja1105_table_ops *static_ops;
+	const struct sja1105_regs *regs;
+	int (*reset_cmd)(const void *ctx, const void *data);
+	const char *name;
+};
+
+struct sja1105_private {
+	struct sja1105_static_config static_config;
+	const struct sja1105_info *info;
+	struct gpio_desc *reset_gpio;
+	struct spi_device *spidev;
+	struct dsa_switch *ds;
+};
+
+#include "sja1105_dynamic_config.h"
+
+struct sja1105_spi_message {
+	u64 access;
+	u64 read_count;
+	u64 address;
+};
+
+typedef enum {
+	SPI_READ = 0,
+	SPI_WRITE = 1,
+} sja1105_spi_rw_mode_t;
+
+/* From sja1105_spi.c */
+int sja1105_spi_send_packed_buf(const struct sja1105_private *priv,
+				sja1105_spi_rw_mode_t rw, u64 reg_addr,
+				void *packed_buf, size_t size_bytes);
+int sja1105_spi_send_int(const struct sja1105_private *priv,
+			 sja1105_spi_rw_mode_t rw, u64 reg_addr,
+			 u64 *value, u64 size_bytes);
+int sja1105_spi_send_long_packed_buf(const struct sja1105_private *priv,
+				     sja1105_spi_rw_mode_t rw, u64 base_addr,
+				     void *packed_buf, u64 buf_len);
+int sja1105_static_config_upload(struct sja1105_private *priv);
+
+extern struct sja1105_info sja1105e_info;
+extern struct sja1105_info sja1105t_info;
+extern struct sja1105_info sja1105p_info;
+extern struct sja1105_info sja1105q_info;
+extern struct sja1105_info sja1105r_info;
+extern struct sja1105_info sja1105s_info;
+
+/* From sja1105_clocking.c */
+
+typedef enum {
+	XMII_MAC = 0,
+	XMII_PHY = 1,
+} sja1105_mii_role_t;
+
+typedef enum {
+	XMII_MODE_MII		= 0,
+	XMII_MODE_RMII		= 1,
+	XMII_MODE_RGMII		= 2,
+} sja1105_phy_interface_t;
+
+typedef enum {
+	SJA1105_SPEED_10MBPS	= 3,
+	SJA1105_SPEED_100MBPS	= 2,
+	SJA1105_SPEED_1000MBPS	= 1,
+	SJA1105_SPEED_AUTO	= 0,
+} sja1105_speed_t;
+
+int sja1105_clocking_setup_port(struct sja1105_private *priv, int port);
+int sja1105_clocking_setup(struct sja1105_private *priv);
+
+/* From sja1105_dynamic_config.c */
+
+int sja1105_dynamic_config_read(struct sja1105_private *priv,
+				enum sja1105_blk_idx blk_idx,
+				int index, void *entry);
+int sja1105_dynamic_config_write(struct sja1105_private *priv,
+				 enum sja1105_blk_idx blk_idx,
+				 int index, void *entry, bool keep);
+
+/* Common implementations for the static and dynamic configs */
+size_t sja1105_l2_forwarding_entry_packing(void *buf, void *entry_ptr,
+					   enum packing_op op);
+size_t sja1105pqrs_l2_lookup_entry_packing(void *buf, void *entry_ptr,
+					   enum packing_op op);
+size_t sja1105et_l2_lookup_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op);
+size_t sja1105_vlan_lookup_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op);
+size_t sja1105pqrs_mac_config_entry_packing(void *buf, void *entry_ptr,
+					    enum packing_op op);
+
+#endif
diff --git a/drivers/net/dsa/sja1105/sja1105_clocking.c b/drivers/net/dsa/sja1105/sja1105_clocking.c
new file mode 100644
index 000000000000..598544297931
--- /dev/null
+++ b/drivers/net/dsa/sja1105/sja1105_clocking.c
@@ -0,0 +1,598 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/* Copyright (c) 2016-2018, NXP Semiconductors
+ * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#include <linux/packing.h>
+#include "sja1105.h"
+
+#define SJA1105_SIZE_CGU_CMD	4
+
+struct sja1105_cfg_pad_mii_tx {
+	u64 d32_os;
+	u64 d32_ipud;
+	u64 d10_os;
+	u64 d10_ipud;
+	u64 ctrl_os;
+	u64 ctrl_ipud;
+	u64 clk_os;
+	u64 clk_ih;
+	u64 clk_ipud;
+};
+
+/* UM10944 Table 82.
+ * IDIV_0_C to IDIV_4_C control registers
+ * (addr. 10000Bh to 10000Fh)
+ */
+struct sja1105_cgu_idiv {
+	u64 clksrc;
+	u64 autoblock;
+	u64 idiv;
+	u64 pd;
+};
+
+/* PLL_1_C control register
+ *
+ * SJA1105 E/T: UM10944 Table 81 (address 10000Ah)
+ * SJA1105 P/Q/R/S: UM11040 Table 116 (address 10000Ah)
+ */
+struct sja1105_cgu_pll_ctrl {
+	u64 pllclksrc;
+	u64 msel;
+	u64 autoblock;
+	u64 psel;
+	u64 direct;
+	u64 fbsel;
+	u64 bypass;
+	u64 pd;
+};
+
+enum {
+	CLKSRC_MII0_TX_CLK	= 0x00,
+	CLKSRC_MII0_RX_CLK	= 0x01,
+	CLKSRC_MII1_TX_CLK	= 0x02,
+	CLKSRC_MII1_RX_CLK	= 0x03,
+	CLKSRC_MII2_TX_CLK	= 0x04,
+	CLKSRC_MII2_RX_CLK	= 0x05,
+	CLKSRC_MII3_TX_CLK	= 0x06,
+	CLKSRC_MII3_RX_CLK	= 0x07,
+	CLKSRC_MII4_TX_CLK	= 0x08,
+	CLKSRC_MII4_RX_CLK	= 0x09,
+	CLKSRC_PLL0		= 0x0B,
+	CLKSRC_PLL1		= 0x0E,
+	CLKSRC_IDIV0		= 0x11,
+	CLKSRC_IDIV1		= 0x12,
+	CLKSRC_IDIV2		= 0x13,
+	CLKSRC_IDIV3		= 0x14,
+	CLKSRC_IDIV4		= 0x15,
+};
+
+/* UM10944 Table 83.
+ * MIIx clock control registers 1 to 30
+ * (addresses 100013h to 100035h)
+ */
+struct sja1105_cgu_mii_ctrl {
+	u64 clksrc;
+	u64 autoblock;
+	u64 pd;
+};
+
+static void sja1105_cgu_idiv_packing(void *buf, struct sja1105_cgu_idiv *idiv,
+				     enum packing_op op)
+{
+	const int size = 4;
+
+	sja1105_packing(buf, &idiv->clksrc,    28, 24, size, op);
+	sja1105_packing(buf, &idiv->autoblock, 11, 11, size, op);
+	sja1105_packing(buf, &idiv->idiv,       5,  2, size, op);
+	sja1105_packing(buf, &idiv->pd,         0,  0, size, op);
+}
+
+static int sja1105_cgu_idiv_config(struct sja1105_private *priv, int port,
+				   bool enabled, int factor)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct device *dev = priv->ds->dev;
+	struct sja1105_cgu_idiv idiv;
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+
+	if (enabled && factor != 1 && factor != 10) {
+		dev_err(dev, "idiv factor must be 1 or 10\n");
+		return -ERANGE;
+	}
+
+	/* Payload for packed_buf */
+	idiv.clksrc    = 0x0A;            /* 25MHz */
+	idiv.autoblock = 1;               /* Block clk automatically */
+	idiv.idiv      = factor - 1;      /* Divide by 1 or 10 */
+	idiv.pd        = enabled ? 0 : 1; /* Power down? */
+	sja1105_cgu_idiv_packing(packed_buf, &idiv, PACK);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE,
+					   regs->cgu_idiv[port], packed_buf,
+					   SJA1105_SIZE_CGU_CMD);
+}
+
+static void
+sja1105_cgu_mii_control_packing(void *buf, struct sja1105_cgu_mii_ctrl *cmd,
+				enum packing_op op)
+{
+	const int size = 4;
+
+	sja1105_packing(buf, &cmd->clksrc,    28, 24, size, op);
+	sja1105_packing(buf, &cmd->autoblock, 11, 11, size, op);
+	sja1105_packing(buf, &cmd->pd,         0,  0, size, op);
+}
+
+static int sja1105_cgu_mii_tx_clk_config(struct sja1105_private *priv,
+					 int port, sja1105_mii_role_t role)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct sja1105_cgu_mii_ctrl mii_tx_clk;
+	const int mac_clk_sources[] = {
+		CLKSRC_MII0_TX_CLK,
+		CLKSRC_MII1_TX_CLK,
+		CLKSRC_MII2_TX_CLK,
+		CLKSRC_MII3_TX_CLK,
+		CLKSRC_MII4_TX_CLK,
+	};
+	const int phy_clk_sources[] = {
+		CLKSRC_IDIV0,
+		CLKSRC_IDIV1,
+		CLKSRC_IDIV2,
+		CLKSRC_IDIV3,
+		CLKSRC_IDIV4,
+	};
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+	int clksrc;
+
+	if (role == XMII_MAC)
+		clksrc = mac_clk_sources[port];
+	else
+		clksrc = phy_clk_sources[port];
+
+	/* Payload for packed_buf */
+	mii_tx_clk.clksrc    = clksrc;
+	mii_tx_clk.autoblock = 1;  /* Autoblock clk while changing clksrc */
+	mii_tx_clk.pd        = 0;  /* Power Down off => enabled */
+	sja1105_cgu_mii_control_packing(packed_buf, &mii_tx_clk, PACK);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE,
+					   regs->mii_tx_clk[port], packed_buf,
+					   SJA1105_SIZE_CGU_CMD);
+}
+
+static int
+sja1105_cgu_mii_rx_clk_config(struct sja1105_private *priv, int port)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct sja1105_cgu_mii_ctrl mii_rx_clk;
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+	const int clk_sources[] = {
+		CLKSRC_MII0_RX_CLK,
+		CLKSRC_MII1_RX_CLK,
+		CLKSRC_MII2_RX_CLK,
+		CLKSRC_MII3_RX_CLK,
+		CLKSRC_MII4_RX_CLK,
+	};
+
+	/* Payload for packed_buf */
+	mii_rx_clk.clksrc    = clk_sources[port];
+	mii_rx_clk.autoblock = 1;  /* Autoblock clk while changing clksrc */
+	mii_rx_clk.pd        = 0;  /* Power Down off => enabled */
+	sja1105_cgu_mii_control_packing(packed_buf, &mii_rx_clk, PACK);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE,
+					   regs->mii_rx_clk[port], packed_buf,
+					   SJA1105_SIZE_CGU_CMD);
+}
+
+static int
+sja1105_cgu_mii_ext_tx_clk_config(struct sja1105_private *priv, int port)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct sja1105_cgu_mii_ctrl mii_ext_tx_clk;
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+	const int clk_sources[] = {
+		CLKSRC_IDIV0,
+		CLKSRC_IDIV1,
+		CLKSRC_IDIV2,
+		CLKSRC_IDIV3,
+		CLKSRC_IDIV4,
+	};
+
+	/* Payload for packed_buf */
+	mii_ext_tx_clk.clksrc    = clk_sources[port];
+	mii_ext_tx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */
+	mii_ext_tx_clk.pd        = 0; /* Power Down off => enabled */
+	sja1105_cgu_mii_control_packing(packed_buf, &mii_ext_tx_clk, PACK);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE,
+					   regs->mii_ext_tx_clk[port],
+					   packed_buf, SJA1105_SIZE_CGU_CMD);
+}
+
+static int
+sja1105_cgu_mii_ext_rx_clk_config(struct sja1105_private *priv, int port)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct sja1105_cgu_mii_ctrl mii_ext_rx_clk;
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+	const int clk_sources[] = {
+		CLKSRC_IDIV0,
+		CLKSRC_IDIV1,
+		CLKSRC_IDIV2,
+		CLKSRC_IDIV3,
+		CLKSRC_IDIV4,
+	};
+
+	/* Payload for packed_buf */
+	mii_ext_rx_clk.clksrc    = clk_sources[port];
+	mii_ext_rx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */
+	mii_ext_rx_clk.pd        = 0; /* Power Down off => enabled */
+	sja1105_cgu_mii_control_packing(packed_buf, &mii_ext_rx_clk, PACK);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE,
+					   regs->mii_ext_rx_clk[port],
+					   packed_buf, SJA1105_SIZE_CGU_CMD);
+}
+
+static int sja1105_mii_clocking_setup(struct sja1105_private *priv, int port,
+				      sja1105_mii_role_t role)
+{
+	struct device *dev = priv->ds->dev;
+	int rc;
+
+	dev_dbg(dev, "Configuring MII-%s clocking\n",
+		(role == XMII_MAC) ? "MAC" : "PHY");
+	/* If role is MAC, disable IDIV
+	 * If role is PHY, enable IDIV and configure for 1/1 divider
+	 */
+	rc = sja1105_cgu_idiv_config(priv, port, (role == XMII_PHY), 1);
+	if (rc < 0)
+		return rc;
+
+	/* Configure CLKSRC of MII_TX_CLK_n
+	 *   * If role is MAC, select TX_CLK_n
+	 *   * If role is PHY, select IDIV_n
+	 */
+	rc = sja1105_cgu_mii_tx_clk_config(priv, port, role);
+	if (rc < 0)
+		return rc;
+
+	/* Configure CLKSRC of MII_RX_CLK_n
+	 * Select RX_CLK_n
+	 */
+	rc = sja1105_cgu_mii_rx_clk_config(priv, port);
+	if (rc < 0)
+		return rc;
+
+	if (role == XMII_PHY) {
+		/* Per MII spec, the PHY (which is us) drives the TX_CLK pin */
+
+		/* Configure CLKSRC of EXT_TX_CLK_n
+		 * Select IDIV_n
+		 */
+		rc = sja1105_cgu_mii_ext_tx_clk_config(priv, port);
+		if (rc < 0)
+			return rc;
+
+		/* Configure CLKSRC of EXT_RX_CLK_n
+		 * Select IDIV_n
+		 */
+		rc = sja1105_cgu_mii_ext_rx_clk_config(priv, port);
+		if (rc < 0)
+			return rc;
+	}
+	return 0;
+}
+
+static void
+sja1105_cgu_pll_control_packing(void *buf, struct sja1105_cgu_pll_ctrl *cmd,
+				enum packing_op op)
+{
+	const int size = 4;
+
+	sja1105_packing(buf, &cmd->pllclksrc, 28, 24, size, op);
+	sja1105_packing(buf, &cmd->msel,      23, 16, size, op);
+	sja1105_packing(buf, &cmd->autoblock, 11, 11, size, op);
+	sja1105_packing(buf, &cmd->psel,       9,  8, size, op);
+	sja1105_packing(buf, &cmd->direct,     7,  7, size, op);
+	sja1105_packing(buf, &cmd->fbsel,      6,  6, size, op);
+	sja1105_packing(buf, &cmd->bypass,     1,  1, size, op);
+	sja1105_packing(buf, &cmd->pd,         0,  0, size, op);
+}
+
+static int sja1105_cgu_rgmii_tx_clk_config(struct sja1105_private *priv,
+					   int port, sja1105_speed_t speed)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct sja1105_cgu_mii_ctrl txc;
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+	int clksrc;
+
+	if (speed == SJA1105_SPEED_1000MBPS) {
+		clksrc = CLKSRC_PLL0;
+	} else {
+		int clk_sources[] = {CLKSRC_IDIV0, CLKSRC_IDIV1, CLKSRC_IDIV2,
+				     CLKSRC_IDIV3, CLKSRC_IDIV4};
+		clksrc = clk_sources[port];
+	}
+
+	/* RGMII: 125MHz for 1000, 25MHz for 100, 2.5MHz for 10 */
+	txc.clksrc = clksrc;
+	/* Autoblock clk while changing clksrc */
+	txc.autoblock = 1;
+	/* Power Down off => enabled */
+	txc.pd = 0;
+	sja1105_cgu_mii_control_packing(packed_buf, &txc, PACK);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE,
+					   regs->rgmii_tx_clk[port],
+					   packed_buf, SJA1105_SIZE_CGU_CMD);
+}
+
+/* AGU */
+static void
+sja1105_cfg_pad_mii_tx_packing(void *buf, struct sja1105_cfg_pad_mii_tx *cmd,
+			       enum packing_op op)
+{
+	const int size = 4;
+
+	sja1105_packing(buf, &cmd->d32_os,   28, 27, size, op);
+	sja1105_packing(buf, &cmd->d32_ipud, 25, 24, size, op);
+	sja1105_packing(buf, &cmd->d10_os,   20, 19, size, op);
+	sja1105_packing(buf, &cmd->d10_ipud, 17, 16, size, op);
+	sja1105_packing(buf, &cmd->ctrl_os,  12, 11, size, op);
+	sja1105_packing(buf, &cmd->ctrl_ipud, 9,  8, size, op);
+	sja1105_packing(buf, &cmd->clk_os,    4,  3, size, op);
+	sja1105_packing(buf, &cmd->clk_ih,    2,  2, size, op);
+	sja1105_packing(buf, &cmd->clk_ipud,  1,  0, size, op);
+}
+
+static int sja1105_rgmii_cfg_pad_tx_config(struct sja1105_private *priv,
+					   int port)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct sja1105_cfg_pad_mii_tx pad_mii_tx;
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+
+	/* Payload */
+	pad_mii_tx.d32_os    = 3; /* TXD[3:2] output stage: */
+				  /*          high noise/high speed */
+	pad_mii_tx.d10_os    = 3; /* TXD[1:0] output stage: */
+				  /*          high noise/high speed */
+	pad_mii_tx.d32_ipud  = 2; /* TXD[3:2] input stage: */
+				  /*          plain input (default) */
+	pad_mii_tx.d10_ipud  = 2; /* TXD[1:0] input stage: */
+				  /*          plain input (default) */
+	pad_mii_tx.ctrl_os   = 3; /* TX_CTL / TX_ER output stage */
+	pad_mii_tx.ctrl_ipud = 2; /* TX_CTL / TX_ER input stage (default) */
+	pad_mii_tx.clk_os    = 3; /* TX_CLK output stage */
+	pad_mii_tx.clk_ih    = 0; /* TX_CLK input hysteresis (default) */
+	pad_mii_tx.clk_ipud  = 2; /* TX_CLK input stage (default) */
+	sja1105_cfg_pad_mii_tx_packing(packed_buf, &pad_mii_tx, PACK);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE,
+					   regs->rgmii_pad_mii_tx[port],
+					   packed_buf, SJA1105_SIZE_CGU_CMD);
+}
+
+static int sja1105_rgmii_clocking_setup(struct sja1105_private *priv, int port)
+{
+	struct device *dev = priv->ds->dev;
+	struct sja1105_mac_config_entry *mac;
+	sja1105_speed_t speed;
+	int rc;
+
+	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
+	speed = mac[port].speed;
+
+	dev_dbg(dev, "Configuring port %d RGMII at speed %dMbps\n",
+		port, speed);
+
+	switch (speed) {
+	case SJA1105_SPEED_1000MBPS:
+		/* 1000Mbps, IDIV disabled (125 MHz) */
+		rc = sja1105_cgu_idiv_config(priv, port, false, 1);
+		break;
+	case SJA1105_SPEED_100MBPS:
+		/* 100Mbps, IDIV enabled, divide by 1 (25 MHz) */
+		rc = sja1105_cgu_idiv_config(priv, port, true, 1);
+		break;
+	case SJA1105_SPEED_10MBPS:
+		/* 10Mbps, IDIV enabled, divide by 10 (2.5 MHz) */
+		rc = sja1105_cgu_idiv_config(priv, port, true, 10);
+		break;
+	case SJA1105_SPEED_AUTO:
+		/* Skip CGU configuration if there is no speed available
+		 * (e.g. link is not established yet)
+		 */
+		dev_dbg(dev, "Speed not available, skipping CGU config\n");
+		return 0;
+	default:
+		rc = -EINVAL;
+	}
+
+	if (rc < 0) {
+		dev_err(dev, "Failed to configure idiv\n");
+		return rc;
+	}
+	rc = sja1105_cgu_rgmii_tx_clk_config(priv, port, speed);
+	if (rc < 0) {
+		dev_err(dev, "Failed to configure RGMII Tx clock\n");
+		return rc;
+	}
+	rc = sja1105_rgmii_cfg_pad_tx_config(priv, port);
+	if (rc < 0) {
+		dev_err(dev, "Failed to configure Tx pad registers\n");
+		return rc;
+	}
+	return 0;
+}
+
+static int sja1105_cgu_rmii_ref_clk_config(struct sja1105_private *priv,
+					   int port)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct sja1105_cgu_mii_ctrl ref_clk;
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+	const int clk_sources[] = {
+		CLKSRC_MII0_TX_CLK,
+		CLKSRC_MII1_TX_CLK,
+		CLKSRC_MII2_TX_CLK,
+		CLKSRC_MII3_TX_CLK,
+		CLKSRC_MII4_TX_CLK,
+	};
+
+	/* Payload for packed_buf */
+	ref_clk.clksrc    = clk_sources[port];
+	ref_clk.autoblock = 1;      /* Autoblock clk while changing clksrc */
+	ref_clk.pd        = 0;      /* Power Down off => enabled */
+	sja1105_cgu_mii_control_packing(packed_buf, &ref_clk, PACK);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE,
+					   regs->rmii_ref_clk[port],
+					   packed_buf, SJA1105_SIZE_CGU_CMD);
+}
+
+static int
+sja1105_cgu_rmii_ext_tx_clk_config(struct sja1105_private *priv, int port)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct sja1105_cgu_mii_ctrl ext_tx_clk;
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+
+	/* Payload for packed_buf */
+	ext_tx_clk.clksrc    = CLKSRC_PLL1;
+	ext_tx_clk.autoblock = 1;   /* Autoblock clk while changing clksrc */
+	ext_tx_clk.pd        = 0;   /* Power Down off => enabled */
+	sja1105_cgu_mii_control_packing(packed_buf, &ext_tx_clk, PACK);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE,
+					   regs->rmii_ext_tx_clk[port],
+					   packed_buf, SJA1105_SIZE_CGU_CMD);
+}
+
+static int sja1105_cgu_rmii_pll_config(struct sja1105_private *priv)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0};
+	struct sja1105_cgu_pll_ctrl pll = {0};
+	struct device *dev = priv->ds->dev;
+	int rc;
+
+	/* PLL1 must be enabled and output 50 Mhz.
+	 * This is done by writing first 0x0A010941 to
+	 * the PLL_1_C register and then deasserting
+	 * power down (PD) 0x0A010940.
+	 */
+
+	/* Step 1: PLL1 setup for 50Mhz */
+	pll.pllclksrc = 0xA;
+	pll.msel      = 0x1;
+	pll.autoblock = 0x1;
+	pll.psel      = 0x1;
+	pll.direct    = 0x0;
+	pll.fbsel     = 0x1;
+	pll.bypass    = 0x0;
+	pll.pd        = 0x1;
+
+	sja1105_cgu_pll_control_packing(packed_buf, &pll, PACK);
+	rc = sja1105_spi_send_packed_buf(priv, SPI_WRITE, regs->rmii_pll1,
+					 packed_buf, SJA1105_SIZE_CGU_CMD);
+	if (rc < 0) {
+		dev_err(dev, "failed to configure PLL1 for 50MHz\n");
+		return rc;
+	}
+
+	/* Step 2: Enable PLL1 */
+	pll.pd = 0x0;
+
+	sja1105_cgu_pll_control_packing(packed_buf, &pll, PACK);
+	rc = sja1105_spi_send_packed_buf(priv, SPI_WRITE, regs->rmii_pll1,
+					 packed_buf, SJA1105_SIZE_CGU_CMD);
+	if (rc < 0) {
+		dev_err(dev, "failed to enable PLL1\n");
+		return rc;
+	}
+	return rc;
+}
+
+static int sja1105_rmii_clocking_setup(struct sja1105_private *priv, int port,
+				       sja1105_mii_role_t role)
+{
+	struct device *dev = priv->ds->dev;
+	int rc;
+
+	dev_dbg(dev, "Configuring RMII-%s clocking\n",
+		(role == XMII_MAC) ? "MAC" : "PHY");
+	/* AH1601.pdf chapter 2.5.1. Sources */
+	if (role == XMII_MAC) {
+		/* Configure and enable PLL1 for 50Mhz output */
+		rc = sja1105_cgu_rmii_pll_config(priv);
+		if (rc < 0)
+			return rc;
+	}
+	/* Disable IDIV for this port */
+	rc = sja1105_cgu_idiv_config(priv, port, false, 1);
+	if (rc < 0)
+		return rc;
+	/* Source to sink mappings */
+	rc = sja1105_cgu_rmii_ref_clk_config(priv, port);
+	if (rc < 0)
+		return rc;
+	if (role == XMII_MAC) {
+		rc = sja1105_cgu_rmii_ext_tx_clk_config(priv, port);
+		if (rc < 0)
+			return rc;
+	}
+	return 0;
+}
+
+int sja1105_clocking_setup_port(struct sja1105_private *priv, int port)
+{
+	struct sja1105_xmii_params_entry *mii;
+	struct device *dev = priv->ds->dev;
+	sja1105_phy_interface_t phy_mode;
+	sja1105_mii_role_t role;
+	int rc;
+
+	mii = priv->static_config.tables[BLK_IDX_XMII_PARAMS].entries;
+
+	/* RGMII etc */
+	phy_mode = mii->xmii_mode[port];
+	/* MAC or PHY, for applicable types (not RGMII) */
+	role = mii->phy_mac[port];
+
+	switch (phy_mode) {
+	case XMII_MODE_MII:
+		rc = sja1105_mii_clocking_setup(priv, port, role);
+		break;
+	case XMII_MODE_RMII:
+		rc = sja1105_rmii_clocking_setup(priv, port, role);
+		break;
+	case XMII_MODE_RGMII:
+		rc = sja1105_rgmii_clocking_setup(priv, port);
+		break;
+	default:
+		dev_err(dev, "Invalid interface mode specified: %d\n",
+			phy_mode);
+		return -EINVAL;
+	}
+	if (rc)
+		dev_err(dev, "Clocking setup for port %d failed: %d\n",
+			port, rc);
+	return rc;
+}
+
+int sja1105_clocking_setup(struct sja1105_private *priv)
+{
+	int port, rc;
+
+	for (port = 0; port < SJA1105_NUM_PORTS; port++) {
+		rc = sja1105_clocking_setup_port(priv, port);
+		if (rc < 0)
+			return rc;
+	}
+	return 0;
+}
diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
new file mode 100644
index 000000000000..d8f145488063
--- /dev/null
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
@@ -0,0 +1,489 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#include "sja1105.h"
+
+#define SJA1105_SIZE_DYN_CMD					4
+
+#define SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY			\
+	SJA1105_SIZE_DYN_CMD
+
+#define SJA1105ET_SIZE_L2_LOOKUP_DYN_CMD			\
+	(SJA1105_SIZE_DYN_CMD + SJA1105ET_SIZE_L2_LOOKUP_ENTRY)
+
+#define SJA1105PQRS_SIZE_L2_LOOKUP_DYN_CMD			\
+	(SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY)
+
+#define SJA1105_SIZE_VLAN_LOOKUP_DYN_CMD			\
+	(SJA1105_SIZE_DYN_CMD + 4 + SJA1105_SIZE_VLAN_LOOKUP_ENTRY)
+
+#define SJA1105_SIZE_L2_FORWARDING_DYN_CMD			\
+	(SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_L2_FORWARDING_ENTRY)
+
+#define SJA1105ET_SIZE_MAC_CONFIG_DYN_CMD			\
+	(SJA1105_SIZE_DYN_CMD + SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY)
+
+#define SJA1105PQRS_SIZE_MAC_CONFIG_DYN_CMD			\
+	(SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY)
+
+#define SJA1105ET_SIZE_L2_LOOKUP_PARAMS_DYN_CMD			\
+	SJA1105_SIZE_DYN_CMD
+
+#define SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD			\
+	SJA1105_SIZE_DYN_CMD
+
+#define SJA1105_MAX_DYN_CMD_SIZE				\
+	SJA1105PQRS_SIZE_MAC_CONFIG_DYN_CMD
+
+static void
+sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				  enum packing_op op)
+{
+	u8 *p = buf + SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,    31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset,  30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,   29, 29, size, op);
+	sja1105_packing(p, &cmd->valident, 27, 27, size, op);
+	/* Hack - The hardware takes the 'index' field within
+	 * struct sja1105_l2_lookup_entry as the index on which this command
+	 * will operate. However it will ignore everything else, so 'index'
+	 * is logically part of command but physically part of entry.
+	 * Populate the 'index' entry field from within the command callback,
+	 * such that our API doesn't need to ask for a full-blown entry
+	 * structure when e.g. a delete is requested.
+	 */
+	sja1105_packing(buf, &cmd->index, 29, 20,
+			SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY, op);
+	/* TODO hostcmd */
+}
+
+static void
+sja1105et_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				enum packing_op op)
+{
+	u8 *p = buf + SJA1105ET_SIZE_L2_LOOKUP_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,    31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset,  30, 30, size, op);
+	sja1105_packing(p, &cmd->errors,   29, 29, size, op);
+	sja1105_packing(p, &cmd->valident, 27, 27, size, op);
+	/* Hack - see comments above. */
+	sja1105_packing(buf, &cmd->index, 29, 20,
+			SJA1105ET_SIZE_L2_LOOKUP_ENTRY, op);
+}
+
+static void
+sja1105et_mgmt_route_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				 enum packing_op op)
+{
+	u8 *p = buf + SJA1105ET_SIZE_L2_LOOKUP_ENTRY;
+	u64 mgmtroute = 1;
+
+	sja1105et_l2_lookup_cmd_packing(buf, cmd, op);
+	if (op == PACK)
+		sja1105_pack(p, &mgmtroute, 26, 26, SJA1105_SIZE_DYN_CMD);
+}
+
+static size_t sja1105et_mgmt_route_entry_packing(void *buf, void *entry_ptr,
+						 enum packing_op op)
+{
+	struct sja1105_mgmt_entry *entry = entry_ptr;
+	const size_t size = SJA1105ET_SIZE_L2_LOOKUP_ENTRY;
+
+	/* UM10944: To specify if a PTP egress timestamp shall be captured on
+	 * each port upon transmission of the frame, the LSB of VLANID in the
+	 * ENTRY field provided by the host must be set.
+	 * Bit 1 of VLANID then specifies the register where the timestamp for
+	 * this port is stored in.
+	 */
+	sja1105_packing(buf, &entry->tsreg,     85, 85, size, op);
+	sja1105_packing(buf, &entry->takets,    84, 84, size, op);
+	sja1105_packing(buf, &entry->macaddr,   83, 36, size, op);
+	sja1105_packing(buf, &entry->destports, 35, 31, size, op);
+	sja1105_packing(buf, &entry->enfport,   30, 30, size, op);
+	return size;
+}
+
+/* In E/T, entry is at addresses 0x27-0x28. There is a 4 byte gap at 0x29,
+ * and command is at 0x2a. Similarly in P/Q/R/S there is a 1 register gap
+ * between entry (0x2d, 0x2e) and command (0x30).
+ */
+static void
+sja1105_vlan_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				enum packing_op op)
+{
+	u8 *p = buf + SJA1105_SIZE_VLAN_LOOKUP_ENTRY + 4;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,    31, 31, size, op);
+	sja1105_packing(p, &cmd->rdwrset,  30, 30, size, op);
+	sja1105_packing(p, &cmd->valident, 27, 27, size, op);
+	/* Hack - see comments above, applied for 'vlanid' field of
+	 * struct sja1105_vlan_lookup_entry.
+	 */
+	sja1105_packing(buf, &cmd->index, 38, 27,
+			SJA1105_SIZE_VLAN_LOOKUP_ENTRY, op);
+}
+
+static void
+sja1105_l2_forwarding_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				  enum packing_op op)
+{
+	u8 *p = buf + SJA1105_SIZE_L2_FORWARDING_ENTRY;
+	const int size = SJA1105_SIZE_DYN_CMD;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->errors,  30, 30, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 29, 29, size, op);
+	sja1105_packing(p, &cmd->index,    4,  0, size, op);
+}
+
+static void
+sja1105et_mac_config_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				 enum packing_op op)
+{
+	const int size = SJA1105_SIZE_DYN_CMD;
+	/* Yup, user manual definitions are reversed */
+	u8 *reg1 = buf + 4;
+
+	sja1105_packing(reg1, &cmd->valid, 31, 31, size, op);
+	sja1105_packing(reg1, &cmd->index, 26, 24, size, op);
+}
+
+static size_t sja1105et_mac_config_entry_packing(void *buf, void *entry_ptr,
+						 enum packing_op op)
+{
+	const int size = SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY;
+	struct sja1105_mac_config_entry *entry = entry_ptr;
+	/* Yup, user manual definitions are reversed */
+	u8 *reg1 = buf + 4;
+	u8 *reg2 = buf;
+
+	sja1105_packing(reg1, &entry->speed,     30, 29, size, op);
+	sja1105_packing(reg1, &entry->drpdtag,   23, 23, size, op);
+	sja1105_packing(reg1, &entry->drpuntag,  22, 22, size, op);
+	sja1105_packing(reg1, &entry->retag,     21, 21, size, op);
+	sja1105_packing(reg1, &entry->dyn_learn, 20, 20, size, op);
+	sja1105_packing(reg1, &entry->egress,    19, 19, size, op);
+	sja1105_packing(reg1, &entry->ingress,   18, 18, size, op);
+	sja1105_packing(reg1, &entry->ing_mirr,  17, 17, size, op);
+	sja1105_packing(reg1, &entry->egr_mirr,  16, 16, size, op);
+	sja1105_packing(reg1, &entry->vlanprio,  14, 12, size, op);
+	sja1105_packing(reg1, &entry->vlanid,    11,  0, size, op);
+	sja1105_packing(reg2, &entry->tp_delin,  31, 16, size, op);
+	sja1105_packing(reg2, &entry->tp_delout, 15,  0, size, op);
+	/* MAC configuration table entries which can't be reconfigured:
+	 * top, base, enabled, ifg, maxage, drpnona664
+	 */
+	/* Bogus return value, not used anywhere */
+	return 0;
+}
+
+static void
+sja1105pqrs_mac_config_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				   enum packing_op op)
+{
+	const int size = SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY;
+	u8 *p = buf + SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY;
+
+	sja1105_packing(p, &cmd->valid,   31, 31, size, op);
+	sja1105_packing(p, &cmd->errors,  30, 30, size, op);
+	sja1105_packing(p, &cmd->rdwrset, 29, 29, size, op);
+	sja1105_packing(p, &cmd->index,    2,  0, size, op);
+}
+
+static void
+sja1105et_l2_lookup_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				       enum packing_op op)
+{
+	sja1105_packing(buf, &cmd->valid, 31, 31,
+			SJA1105ET_SIZE_L2_LOOKUP_PARAMS_DYN_CMD, op);
+}
+
+static size_t
+sja1105et_l2_lookup_params_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op)
+{
+	struct sja1105_l2_lookup_params_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->poly, 7, 0,
+			SJA1105ET_SIZE_L2_LOOKUP_PARAMS_DYN_CMD, op);
+	/* Bogus return value, not used anywhere */
+	return 0;
+}
+
+static void
+sja1105et_general_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+				     enum packing_op op)
+{
+	const int size = SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD;
+
+	sja1105_packing(buf, &cmd->valid,  31, 31, size, op);
+	sja1105_packing(buf, &cmd->errors, 30, 30, size, op);
+}
+
+static size_t
+sja1105et_general_params_entry_packing(void *buf, void *entry_ptr,
+				       enum packing_op op)
+{
+	struct sja1105_general_params_entry *entry = entry_ptr;
+	const int size = SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD;
+
+	sja1105_packing(buf, &entry->mirr_port, 2, 0, size, op);
+	/* Bogus return value, not used anywhere */
+	return 0;
+}
+
+#define OP_READ		BIT(0)
+#define OP_WRITE	BIT(1)
+#define OP_DEL		BIT(2)
+
+/* SJA1105E/T: First generation */
+struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = {
+	[BLK_IDX_L2_LOOKUP] = {
+		.entry_packing = sja1105et_l2_lookup_entry_packing,
+		.cmd_packing = sja1105et_l2_lookup_cmd_packing,
+		.access = (OP_READ | OP_WRITE | OP_DEL),
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
+		.packed_size = SJA1105ET_SIZE_L2_LOOKUP_DYN_CMD,
+		.addr = 0x20,
+	},
+	[BLK_IDX_MGMT_ROUTE] = {
+		.entry_packing = sja1105et_mgmt_route_entry_packing,
+		.cmd_packing = sja1105et_mgmt_route_cmd_packing,
+		.access = (OP_READ | OP_WRITE),
+		.max_entry_count = SJA1105_NUM_PORTS,
+		.packed_size = SJA1105ET_SIZE_L2_LOOKUP_DYN_CMD,
+		.addr = 0x20,
+	},
+	[BLK_IDX_L2_POLICING] = {0},
+	[BLK_IDX_VLAN_LOOKUP] = {
+		.entry_packing = sja1105_vlan_lookup_entry_packing,
+		.cmd_packing = sja1105_vlan_lookup_cmd_packing,
+		.access = (OP_WRITE | OP_DEL),
+		.max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT,
+		.packed_size = SJA1105_SIZE_VLAN_LOOKUP_DYN_CMD,
+		.addr = 0x27,
+	},
+	[BLK_IDX_L2_FORWARDING] = {
+		.entry_packing = sja1105_l2_forwarding_entry_packing,
+		.cmd_packing = sja1105_l2_forwarding_cmd_packing,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT,
+		.access = OP_WRITE,
+		.packed_size = SJA1105_SIZE_L2_FORWARDING_DYN_CMD,
+		.addr = 0x24,
+	},
+	[BLK_IDX_MAC_CONFIG] = {
+		.entry_packing = sja1105et_mac_config_entry_packing,
+		.cmd_packing = sja1105et_mac_config_cmd_packing,
+		.max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT,
+		.access = OP_WRITE,
+		.packed_size = SJA1105ET_SIZE_MAC_CONFIG_DYN_CMD,
+		.addr = 0x36,
+	},
+	[BLK_IDX_L2_LOOKUP_PARAMS] = {
+		.entry_packing = sja1105et_l2_lookup_params_entry_packing,
+		.cmd_packing = sja1105et_l2_lookup_params_cmd_packing,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+		.access = OP_WRITE,
+		.packed_size = SJA1105ET_SIZE_L2_LOOKUP_PARAMS_DYN_CMD,
+		.addr = 0x38,
+	},
+	[BLK_IDX_L2_FORWARDING_PARAMS] = {0},
+	[BLK_IDX_GENERAL_PARAMS] = {
+		.entry_packing = sja1105et_general_params_entry_packing,
+		.cmd_packing = sja1105et_general_params_cmd_packing,
+		.max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT,
+		.access = OP_WRITE,
+		.packed_size = SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD,
+		.addr = 0x34,
+	},
+	[BLK_IDX_XMII_PARAMS] = {0},
+};
+
+/* SJA1105P/Q/R/S: Second generation: TODO */
+struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = {
+	[BLK_IDX_L2_LOOKUP] = {
+		.entry_packing = sja1105pqrs_l2_lookup_entry_packing,
+		.cmd_packing = sja1105pqrs_l2_lookup_cmd_packing,
+		.access = (OP_READ | OP_WRITE | OP_DEL),
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
+		.packed_size = SJA1105ET_SIZE_L2_LOOKUP_DYN_CMD,
+		.addr = 0x24,
+	},
+	[BLK_IDX_L2_POLICING] = {0},
+	[BLK_IDX_VLAN_LOOKUP] = {
+		.entry_packing = sja1105_vlan_lookup_entry_packing,
+		.cmd_packing = sja1105_vlan_lookup_cmd_packing,
+		.access = (OP_READ | OP_WRITE | OP_DEL),
+		.max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT,
+		.packed_size = SJA1105_SIZE_VLAN_LOOKUP_DYN_CMD,
+		.addr = 0x2D,
+	},
+	[BLK_IDX_L2_FORWARDING] = {
+		.entry_packing = sja1105_l2_forwarding_entry_packing,
+		.cmd_packing = sja1105_l2_forwarding_cmd_packing,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT,
+		.access = OP_WRITE,
+		.packed_size = SJA1105_SIZE_L2_FORWARDING_DYN_CMD,
+		.addr = 0x2A,
+	},
+	[BLK_IDX_MAC_CONFIG] = {
+		.entry_packing = sja1105pqrs_mac_config_entry_packing,
+		.cmd_packing = sja1105pqrs_mac_config_cmd_packing,
+		.max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT,
+		.access = (OP_READ | OP_WRITE),
+		.packed_size = SJA1105PQRS_SIZE_MAC_CONFIG_DYN_CMD,
+		.addr = 0x4B,
+	},
+	[BLK_IDX_L2_LOOKUP_PARAMS] = {
+		.entry_packing = sja1105et_l2_lookup_params_entry_packing,
+		.cmd_packing = sja1105et_l2_lookup_params_cmd_packing,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+		.access = (OP_READ | OP_WRITE),
+		.packed_size = SJA1105ET_SIZE_L2_LOOKUP_PARAMS_DYN_CMD,
+		.addr = 0x38,
+	},
+	[BLK_IDX_L2_FORWARDING_PARAMS] = {0},
+	[BLK_IDX_GENERAL_PARAMS] = {
+		.entry_packing = sja1105et_general_params_entry_packing,
+		.cmd_packing = sja1105et_general_params_cmd_packing,
+		.max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT,
+		.access = OP_WRITE,
+		.packed_size = SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD,
+		.addr = 0x34,
+	},
+	[BLK_IDX_XMII_PARAMS] = {0},
+};
+
+int sja1105_dynamic_config_read(struct sja1105_private *priv,
+				enum sja1105_blk_idx blk_idx,
+				int index, void *entry)
+{
+	const struct sja1105_dynamic_table_ops *ops;
+	struct sja1105_dyn_cmd cmd = {0};
+	/* SPI payload buffer */
+	u8 packed_buf[SJA1105_MAX_DYN_CMD_SIZE] = {0};
+	int retries = 3;
+	int rc;
+
+	if (blk_idx >= BLK_IDX_MAX_DYN)
+		return -ERANGE;
+
+	ops = &priv->info->dyn_ops[blk_idx];
+
+	if (index >= ops->max_entry_count)
+		return -ERANGE;
+	if (!(ops->access & OP_READ))
+		return -EOPNOTSUPP;
+	if (ops->packed_size > SJA1105_MAX_DYN_CMD_SIZE)
+		return -ERANGE;
+	if (!ops->cmd_packing)
+		return -EOPNOTSUPP;
+	if (!ops->entry_packing)
+		return -EOPNOTSUPP;
+
+	cmd.valid = true; /* Trigger action on table entry */
+	cmd.rdwrset = SPI_READ; /* Action is read */
+	cmd.index = index;
+	ops->cmd_packing(packed_buf, &cmd, PACK);
+
+	/* Send SPI write operation: read config table entry */
+	rc = sja1105_spi_send_packed_buf(priv, SPI_WRITE, ops->addr,
+					 packed_buf, ops->packed_size);
+	if (rc < 0)
+		return rc;
+
+	/* Loop until we have confirmation that hardware has finished
+	 * processing the command and has cleared the VALID field
+	 */
+	do {
+		memset(packed_buf, 0, ops->packed_size);
+
+		/* Retrieve the read operation's result */
+		rc = sja1105_spi_send_packed_buf(priv, SPI_READ, ops->addr,
+						 packed_buf, ops->packed_size);
+		if (rc < 0)
+			return rc;
+
+		cmd = (struct sja1105_dyn_cmd) {0};
+		ops->cmd_packing(packed_buf, &cmd, UNPACK);
+		/* UM10944: [valident] will always be found cleared
+		 * during a read access with MGMTROUTE set.
+		 * So don't error out in that case.
+		 */
+		if (!cmd.valident && blk_idx != BLK_IDX_MGMT_ROUTE)
+			return -EINVAL;
+		cpu_relax();
+	} while (cmd.valid && --retries);
+
+	if (cmd.valid)
+		return -ETIMEDOUT;
+
+	/* Don't dereference possibly NULL pointer - maybe caller
+	 * only wanted to see whether the entry existed or not.
+	 */
+	if (entry)
+		ops->entry_packing(packed_buf, entry, UNPACK);
+	return 0;
+}
+
+int sja1105_dynamic_config_write(struct sja1105_private *priv,
+				 enum sja1105_blk_idx blk_idx,
+				 int index, void *entry, bool keep)
+{
+	const struct sja1105_dynamic_table_ops *ops;
+	struct sja1105_dyn_cmd cmd = {0};
+	/* SPI payload buffer */
+	u8 packed_buf[SJA1105_MAX_DYN_CMD_SIZE] = {0};
+	int rc;
+
+	if (blk_idx >= BLK_IDX_MAX_DYN)
+		return -ERANGE;
+
+	ops = &priv->info->dyn_ops[blk_idx];
+
+	if (index >= ops->max_entry_count)
+		return -ERANGE;
+	if (!(ops->access & OP_WRITE))
+		return -EOPNOTSUPP;
+	if (!keep && !(ops->access & OP_DEL))
+		return -EOPNOTSUPP;
+	if (ops->packed_size > SJA1105_MAX_DYN_CMD_SIZE)
+		return -ERANGE;
+
+	cmd.valident = keep; /* If false, deletes entry */
+	cmd.valid = true; /* Trigger action on table entry */
+	cmd.rdwrset = SPI_WRITE; /* Action is write */
+	cmd.index = index;
+
+	if (!ops->cmd_packing)
+		return -EOPNOTSUPP;
+	ops->cmd_packing(packed_buf, &cmd, PACK);
+
+	if (!ops->entry_packing)
+		return -EOPNOTSUPP;
+	/* Don't dereference potentially NULL pointer if just
+	 * deleting a table entry is what was requested. For cases
+	 * where 'index' field is physically part of entry structure,
+	 * and needed here, we deal with that in the cmd_packing callback.
+	 */
+	if (keep)
+		ops->entry_packing(packed_buf, entry, PACK);
+
+	/* Send SPI write operation: read config table entry */
+	rc = sja1105_spi_send_packed_buf(priv, SPI_WRITE, ops->addr,
+					 packed_buf, ops->packed_size);
+	if (rc < 0)
+		return rc;
+
+	cmd = (struct sja1105_dyn_cmd) {0};
+	ops->cmd_packing(packed_buf, &cmd, UNPACK);
+	if (cmd.errors)
+		return -EINVAL;
+
+	return 0;
+}
diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
new file mode 100644
index 000000000000..77be59546a55
--- /dev/null
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#ifndef _SJA1105_DYNAMIC_CONFIG_H
+#define _SJA1105_DYNAMIC_CONFIG_H
+
+#include "sja1105.h"
+#include <linux/packing.h>
+
+struct sja1105_dyn_cmd {
+	u64 valid;
+	u64 rdwrset;
+	u64 errors;
+	u64 valident;
+	u64 index;
+};
+
+struct sja1105_dynamic_table_ops {
+	/* This returns size_t just to keep same prototype as the
+	 * static config ops, of which we are reusing some functions.
+	 */
+	size_t (*entry_packing)(void *buf, void *entry_ptr, enum packing_op op);
+	void (*cmd_packing)(void *buf, struct sja1105_dyn_cmd *cmd,
+			    enum packing_op op);
+	size_t max_entry_count;
+	size_t packed_size;
+	u64 addr;
+	u8 access;
+};
+
+struct sja1105_mgmt_entry {
+	u64 tsreg;
+	u64 takets;
+	u64 macaddr;
+	u64 destports;
+	u64 enfport;
+	u64 index;
+};
+
+extern struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN];
+extern struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN];
+
+#endif
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
new file mode 100644
index 000000000000..7d2ad2db0d88
--- /dev/null
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -0,0 +1,928 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018, Sensor-Technik Wiedemann GmbH
+ * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/spi/spi.h>
+#include <linux/errno.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
+#include <linux/of_device.h>
+#include <linux/netdev_features.h>
+#include <linux/netdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/if_ether.h>
+#include "sja1105.h"
+
+static void sja1105_hw_reset(struct gpio_desc *gpio, unsigned int pulse_len,
+			     unsigned int startup_delay)
+{
+	gpiod_set_value_cansleep(gpio, 1);
+	/* Wait for minimum reset pulse length */
+	msleep(pulse_len);
+	gpiod_set_value_cansleep(gpio, 0);
+	/* Wait until chip is ready after reset */
+	msleep(startup_delay);
+}
+
+static void
+sja1105_port_allow_traffic(struct sja1105_l2_forwarding_entry *l2_fwd,
+			   int from, int to, bool allow)
+{
+	if (allow) {
+		l2_fwd[from].bc_domain  |= BIT(to);
+		l2_fwd[from].reach_port |= BIT(to);
+		l2_fwd[from].fl_domain  |= BIT(to);
+	} else {
+		l2_fwd[from].bc_domain  &= ~BIT(to);
+		l2_fwd[from].reach_port &= ~BIT(to);
+		l2_fwd[from].fl_domain  &= ~BIT(to);
+	}
+}
+
+/* Structure used to temporarily transport device tree
+ * settings into sja1105_setup
+ */
+struct sja1105_dt_port {
+	phy_interface_t phy_mode;
+	sja1105_mii_role_t role;
+};
+
+static int sja1105_init_mac_settings(struct sja1105_private *priv)
+{
+	struct sja1105_mac_config_entry default_mac = {
+		/* Enable all 8 priority queues on egress.
+		 * Every queue i holds top[i] - base[i] frames.
+		 * Sum of top[i] - base[i] is 511 (max hardware limit).
+		 */
+		.top  = {0x3F, 0x7F, 0xBF, 0xFF, 0x13F, 0x17F, 0x1BF, 0x1FF},
+		.base = {0x0, 0x40, 0x80, 0xC0, 0x100, 0x140, 0x180, 0x1C0},
+		.enabled = {true, true, true, true, true, true, true, true},
+		/* Keep standard IFG of 12 bytes on egress. */
+		.ifg = 0,
+		/* Always put the MAC speed in automatic mode, where it can be
+		 * retrieved from the PHY object through phylib and
+		 * sja1105_adjust_port_config.
+		 */
+		.speed = SJA1105_SPEED_AUTO,
+		/* No static correction for 1-step 1588 events */
+		.tp_delin = 0,
+		.tp_delout = 0,
+		/* Disable aging for critical TTEthernet traffic */
+		.maxage = 0xFF,
+		/* Internal VLAN (pvid) to apply to untagged ingress */
+		.vlanprio = 0,
+		.vlanid = 0,
+		.ing_mirr = false,
+		.egr_mirr = false,
+		/* Don't drop traffic with other EtherType than ETH_P_IP */
+		.drpnona664 = false,
+		/* Don't drop double-tagged traffic */
+		.drpdtag = false,
+		/* Don't drop untagged traffic */
+		.drpuntag = false,
+		/* Don't retag 802.1p (VID 0) traffic with the pvid */
+		.retag = false,
+		/* Enable learning and I/O on user ports by default. */
+		.dyn_learn = true,
+		.egress = false,
+		.ingress = false,
+	};
+	struct sja1105_mac_config_entry *mac;
+	struct sja1105_table *table;
+	int i;
+
+	table = &priv->static_config.tables[BLK_IDX_MAC_CONFIG];
+
+	/* Discard previous MAC Configuration Table */
+	if (table->entry_count) {
+		kfree(table->entries);
+		table->entry_count = 0;
+	}
+
+	table->entries = kcalloc(SJA1105_NUM_PORTS,
+				 table->ops->unpacked_entry_size, GFP_KERNEL);
+	if (!table->entries)
+		return -ENOMEM;
+
+	/* Override table based on phylib DT bindings */
+	table->entry_count = SJA1105_NUM_PORTS;
+
+	mac = table->entries;
+
+	for (i = 0; i < SJA1105_NUM_PORTS; i++)
+		mac[i] = default_mac;
+
+	return 0;
+}
+
+static int sja1105_init_mii_settings(struct sja1105_private *priv,
+				     struct sja1105_dt_port *ports)
+{
+	struct device *dev = &priv->spidev->dev;
+	struct sja1105_xmii_params_entry *mii;
+	struct sja1105_table *table;
+	int i;
+
+	table = &priv->static_config.tables[BLK_IDX_XMII_PARAMS];
+
+	/* Discard previous xMII Mode Parameters Table */
+	if (table->entry_count) {
+		kfree(table->entries);
+		table->entry_count = 0;
+	}
+
+	table->entries = kcalloc(SJA1105_MAX_XMII_PARAMS_COUNT,
+				 table->ops->unpacked_entry_size, GFP_KERNEL);
+	if (!table->entries)
+		return -ENOMEM;
+
+	/* Override table based on phylib DT bindings */
+	table->entry_count = SJA1105_MAX_XMII_PARAMS_COUNT;
+
+	mii = table->entries;
+
+	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+		switch (ports[i].phy_mode) {
+		case PHY_INTERFACE_MODE_MII:
+			mii->xmii_mode[i] = XMII_MODE_MII;
+			break;
+		case PHY_INTERFACE_MODE_RMII:
+			mii->xmii_mode[i] = XMII_MODE_RMII;
+			break;
+		case PHY_INTERFACE_MODE_RGMII:
+		case PHY_INTERFACE_MODE_RGMII_ID:
+		case PHY_INTERFACE_MODE_RGMII_RXID:
+		case PHY_INTERFACE_MODE_RGMII_TXID:
+			mii->xmii_mode[i] = XMII_MODE_RGMII;
+			break;
+		default:
+			dev_err(dev, "Unsupported PHY mode %s!\n",
+				phy_modes(ports[i].phy_mode));
+		}
+
+		mii->phy_mac[i] = ports[i].role;
+	}
+	return 0;
+}
+
+static int sja1105_init_static_fdb(struct sja1105_private *priv)
+{
+	struct sja1105_table *table;
+
+	table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP];
+
+	if (table->entry_count) {
+		kfree(table->entries);
+		table->entry_count = 0;
+	}
+	return 0;
+}
+
+static int sja1105_init_l2_lookup_params(struct sja1105_private *priv)
+{
+	struct sja1105_table *table;
+	struct sja1105_l2_lookup_params_entry default_l2_lookup_params = {
+		/* TODO Learned FDB entries are never forgotten */
+		.maxage = 0,
+		/* All entries within a FDB bin are available for learning */
+		.dyn_tbsz = SJA1105ET_FDB_BIN_SIZE,
+		/* 2^8 + 2^5 + 2^3 + 2^2 + 2^1 + 1 in Koopman notation */
+		.poly = 0x97,
+		/* This selects between Independent VLAN Learning (IVL) and
+		 * Shared VLAN Learning (SVL)
+		 */
+		.shared_learn = false,
+		/* Don't discard management traffic based on ENFPORT -
+		 * we don't perform SMAC port enforcement anyway, so
+		 * what we are setting here doesn't matter.
+		 */
+		.no_enf_hostprt = false,
+		/* Don't learn SMAC for mac_fltres1 and mac_fltres0.
+		 * Maybe correlate with no_linklocal_learn from bridge driver?
+		 */
+		.no_mgmt_learn = true,
+	};
+
+	table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS];
+
+	if (table->entry_count) {
+		kfree(table->entries);
+		table->entry_count = 0;
+	}
+
+	table->entries = kcalloc(SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+				 table->ops->unpacked_entry_size, GFP_KERNEL);
+	if (!table->entries)
+		return -ENOMEM;
+
+	table->entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT;
+
+	/* This table only has a single entry */
+	((struct sja1105_l2_lookup_params_entry *)table->entries)[0] =
+				default_l2_lookup_params;
+
+	return 0;
+}
+
+static int sja1105_init_static_vlan(struct sja1105_private *priv)
+{
+	struct sja1105_table *table;
+	struct sja1105_vlan_lookup_entry pvid = {
+		.ving_mirr = 0,
+		.vegr_mirr = 0,
+		.vmemb_port = 0,
+		.vlan_bc = 0,
+		.tag_port = 0,
+		.vlanid = 0,
+	};
+	int i;
+
+	table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP];
+
+	/* The static VLAN table will only contain the initial pvid of 0.
+	 */
+	if (table->entry_count) {
+		kfree(table->entries);
+		table->entry_count = 0;
+	}
+
+	table->entries = kcalloc(1, table->ops->unpacked_entry_size,
+				 GFP_KERNEL);
+	if (!table->entries)
+		return -ENOMEM;
+
+	table->entry_count = 1;
+
+	/* VLAN ID 0: all DT-defined ports are members; no restrictions on
+	 * forwarding; always transmit priority-tagged frames as untagged.
+	 */
+	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+		pvid.vmemb_port |= BIT(i);
+		pvid.vlan_bc |= BIT(i);
+		pvid.tag_port &= ~BIT(i);
+	}
+
+	((struct sja1105_vlan_lookup_entry *)table->entries)[0] = pvid;
+	return 0;
+}
+
+static int sja1105_init_l2_forwarding(struct sja1105_private *priv)
+{
+	struct sja1105_l2_forwarding_entry *l2fwd;
+	struct sja1105_table *table;
+	int i, j;
+
+	table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING];
+
+	if (table->entry_count) {
+		kfree(table->entries);
+		table->entry_count = 0;
+	}
+
+	table->entries = kcalloc(SJA1105_MAX_L2_FORWARDING_COUNT,
+				 table->ops->unpacked_entry_size, GFP_KERNEL);
+	if (!table->entries)
+		return -ENOMEM;
+
+	table->entry_count = SJA1105_MAX_L2_FORWARDING_COUNT;
+
+	l2fwd = table->entries;
+
+	/* First 5 entries define the forwarding rules */
+	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+		unsigned int upstream = dsa_upstream_port(priv->ds, i);
+
+		for (j = 0; j < SJA1105_NUM_TC; j++)
+			l2fwd[i].vlan_pmap[j] = j;
+
+		if (i == upstream)
+			continue;
+
+		sja1105_port_allow_traffic(l2fwd, i, upstream, true);
+		sja1105_port_allow_traffic(l2fwd, upstream, i, true);
+	}
+	/* Next 8 entries define VLAN PCP mapping from ingress to egress.
+	 * Create a one-to-one mapping.
+	 */
+	for (i = 0; i < SJA1105_NUM_TC; i++)
+		for (j = 0; j < SJA1105_NUM_PORTS; j++)
+			l2fwd[SJA1105_NUM_PORTS + i].vlan_pmap[j] = i;
+
+	return 0;
+}
+
+static int sja1105_init_l2_forwarding_params(struct sja1105_private *priv)
+{
+	struct sja1105_l2_forwarding_params_entry default_l2fwd_params = {
+		/* Disallow dynamic reconfiguration of vlan_pmap */
+		.max_dynp = 0,
+		/* Use a single memory partition for all ingress queues */
+		.part_spc = { SJA1105_MAX_FRAME_MEMORY, 0, 0, 0, 0, 0, 0, 0 },
+	};
+	struct sja1105_table *table;
+
+	table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING_PARAMS];
+
+	if (table->entry_count) {
+		kfree(table->entries);
+		table->entry_count = 0;
+	}
+
+	table->entries = kcalloc(SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
+				 table->ops->unpacked_entry_size, GFP_KERNEL);
+	if (!table->entries)
+		return -ENOMEM;
+
+	table->entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT;
+
+	/* This table only has a single entry */
+	((struct sja1105_l2_forwarding_params_entry *)table->entries)[0] =
+				default_l2fwd_params;
+
+	return 0;
+}
+
+static int sja1105_init_general_params(struct sja1105_private *priv)
+{
+	struct sja1105_general_params_entry default_general_params = {
+		/* Disallow dynamic changing of the mirror port */
+		.mirr_ptacu = 0,
+		.switchid = priv->ds->index,
+		/* Priority queue for link-local frames trapped to CPU */
+		.hostprio = 0,
+		.mac_fltres1 = SJA1105_LINKLOCAL_FILTER_A,
+		.mac_flt1    = SJA1105_LINKLOCAL_FILTER_A_MASK,
+		.incl_srcpt1 = true,
+		.send_meta1  = false,
+		.mac_fltres0 = SJA1105_LINKLOCAL_FILTER_B,
+		.mac_flt0    = SJA1105_LINKLOCAL_FILTER_B_MASK,
+		.incl_srcpt0 = true,
+		.send_meta0  = false,
+		/* The destination for traffic matching mac_fltres1 and
+		 * mac_fltres0 on all ports except host_port. Such traffic
+		 * receieved on host_port itself would be dropped, except
+		 * by installing a temporary 'management route'
+		 */
+		.host_port = dsa_upstream_port(priv->ds, 0),
+		/* Same as host port */
+		.mirr_port = dsa_upstream_port(priv->ds, 0),
+		/* Link-local traffic received on casc_port will be forwarded
+		 * to host_port without embedding the source port and device ID
+		 * info in the destination MAC address (presumably because it
+		 * is a cascaded port and a downstream SJA switch already did
+		 * that). Default to an invalid port (to disable the feature)
+		 * and overwrite this if we find any DSA (cascaded) ports.
+		 */
+		.casc_port = SJA1105_NUM_PORTS,
+		/* No TTEthernet */
+		.vllupformat = 0,
+		.vlmarker = 0,
+		.vlmask = 0,
+		/* Only update correctionField for 1-step PTP (L2 transport) */
+		.ignore2stf = 0,
+		.tpid = ETH_P_8021Q,
+		.tpid2 = ETH_P_8021Q,
+	};
+	struct sja1105_table *table;
+	int i;
+
+	for (i = 0; i < SJA1105_NUM_PORTS; i++)
+		if (dsa_is_dsa_port(priv->ds, i))
+			default_general_params.casc_port = i;
+
+	table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
+
+	if (table->entry_count) {
+		kfree(table->entries);
+		table->entry_count = 0;
+	}
+
+	table->entries = kcalloc(SJA1105_MAX_GENERAL_PARAMS_COUNT,
+				 table->ops->unpacked_entry_size, GFP_KERNEL);
+	if (!table->entries)
+		return -ENOMEM;
+
+	table->entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT;
+
+	/* This table only has a single entry */
+	((struct sja1105_general_params_entry *)table->entries)[0] =
+				default_general_params;
+
+	return 0;
+}
+
+#define SJA1105_RATE_MBPS(speed) (((speed) * 64000) / 1000)
+
+static inline void
+sja1105_setup_policer(struct sja1105_l2_policing_entry *policing,
+		      int index)
+{
+	policing[index].sharindx = index;
+	policing[index].smax = 65535; /* Burst size in bytes */
+	policing[index].rate = SJA1105_RATE_MBPS(1000);
+	policing[index].maxlen = ETH_FRAME_LEN + VLAN_HLEN + ETH_FCS_LEN;
+	policing[index].partition = 0;
+}
+
+static int sja1105_init_l2_policing(struct sja1105_private *priv)
+{
+	struct sja1105_l2_policing_entry *policing;
+	struct sja1105_table *table;
+	int i, j, k;
+
+	table = &priv->static_config.tables[BLK_IDX_L2_POLICING];
+
+	/* Discard previous L2 Policing Table */
+	if (table->entry_count) {
+		kfree(table->entries);
+		table->entry_count = 0;
+	}
+
+	table->entries = kcalloc(SJA1105_MAX_L2_POLICING_COUNT,
+				 table->ops->unpacked_entry_size, GFP_KERNEL);
+	if (!table->entries)
+		return -ENOMEM;
+
+	table->entry_count = SJA1105_MAX_L2_POLICING_COUNT;
+
+	policing = table->entries;
+
+	/* k sweeps through all unicast policers (0-39).
+	 * bcast sweeps through policers 40-44.
+	 */
+	for (i = 0, k = 0; i < SJA1105_NUM_PORTS; i++) {
+		int bcast = (SJA1105_NUM_PORTS * SJA1105_NUM_TC) + i;
+
+		for (j = 0; j < SJA1105_NUM_TC; j++, k++)
+			sja1105_setup_policer(policing, k);
+
+		/* Set up this port's policer for broadcast traffic */
+		sja1105_setup_policer(policing, bcast);
+	}
+	return 0;
+}
+
+static int sja1105_static_config_load(struct sja1105_private *priv,
+				      struct sja1105_dt_port *ports)
+{
+	int rc;
+
+	sja1105_static_config_free(&priv->static_config);
+	rc = sja1105_static_config_init(&priv->static_config,
+					priv->info->static_ops,
+					priv->info->device_id);
+	if (rc)
+		return rc;
+
+	/* Build static configuration */
+	rc = sja1105_init_mac_settings(priv);
+	if (rc < 0)
+		return rc;
+	rc = sja1105_init_mii_settings(priv, ports);
+	if (rc < 0)
+		return rc;
+	rc = sja1105_init_static_fdb(priv);
+	if (rc < 0)
+		return rc;
+	rc = sja1105_init_static_vlan(priv);
+	if (rc < 0)
+		return rc;
+	rc = sja1105_init_l2_lookup_params(priv);
+	if (rc < 0)
+		return rc;
+	rc = sja1105_init_l2_forwarding(priv);
+	if (rc < 0)
+		return rc;
+	rc = sja1105_init_l2_forwarding_params(priv);
+	if (rc < 0)
+		return rc;
+	rc = sja1105_init_l2_policing(priv);
+	if (rc < 0)
+		return rc;
+	rc = sja1105_init_general_params(priv);
+	if (rc < 0)
+		return rc;
+
+	/* Send initial configuration to hardware via SPI */
+	return sja1105_static_config_upload(priv);
+}
+
+static int sja1105_parse_ports_node(struct sja1105_private *priv,
+				    struct sja1105_dt_port *ports,
+				    struct device_node *ports_node)
+{
+	struct device *dev = &priv->spidev->dev;
+	struct device_node *child;
+
+	for_each_child_of_node(ports_node, child) {
+		struct device_node *phy_node;
+		int phy_mode;
+		u32 index;
+
+		/* Get switch port number from DT */
+		if (of_property_read_u32(child, "reg", &index) < 0) {
+			dev_err(dev, "Port number not defined in device tree "
+				"(property \"reg\")\n");
+			return -ENODEV;
+		}
+
+		/* Get PHY mode from DT */
+		phy_mode = of_get_phy_mode(child);
+		if (phy_mode < 0) {
+			dev_err(dev, "Failed to read phy-mode or "
+				"phy-interface-type property for port %d\n",
+				index);
+			return -ENODEV;
+		}
+		ports[index].phy_mode = phy_mode;
+
+		phy_node = of_parse_phandle(child, "phy-handle", 0);
+		if (!phy_node) {
+			if (!of_phy_is_fixed_link(child)) {
+				dev_err(dev, "phy-handle or fixed-link "
+					"properties missing!\n");
+				return -ENODEV;
+			}
+			/* phy-handle is missing, but fixed-link isn't.
+			 * So it's a fixed link. Default to PHY role.
+			 */
+			ports[index].role = XMII_PHY;
+		} else {
+			/* phy-handle present => put port in MAC role */
+			ports[index].role = XMII_MAC;
+			of_node_put(phy_node);
+		}
+
+		/* The MAC/PHY role can be overridden with explicit bindings */
+		if (of_property_read_bool(child, "sja1105,role-mac"))
+			ports[index].role = XMII_MAC;
+		else if (of_property_read_bool(child, "sja1105,role-phy"))
+			ports[index].role = XMII_PHY;
+	}
+
+	return 0;
+}
+
+static int sja1105_parse_dt(struct sja1105_private *priv,
+			    struct sja1105_dt_port *ports)
+{
+	struct device *dev = &priv->spidev->dev;
+	struct device_node *switch_node = dev->of_node;
+	struct device_node *ports_node;
+	int rc;
+
+	ports_node = of_get_child_by_name(switch_node, "ports");
+	if (!ports_node) {
+		dev_err(dev, "Incorrect bindings: absent \"ports\" node\n");
+		return -ENODEV;
+	}
+
+	rc = sja1105_parse_ports_node(priv, ports, ports_node);
+	of_node_put(ports_node);
+
+	return rc;
+}
+
+/* Convert back and forth MAC speed from Mbps to SJA1105 encoding */
+static int sja1105_speed[] = {
+	[SJA1105_SPEED_AUTO]     = 0,
+	[SJA1105_SPEED_10MBPS]   = 10,
+	[SJA1105_SPEED_100MBPS]  = 100,
+	[SJA1105_SPEED_1000MBPS] = 1000,
+};
+
+static sja1105_speed_t sja1105_get_speed_cfg(unsigned int speed_mbps)
+{
+	int i;
+
+	for (i = SJA1105_SPEED_AUTO; i <= SJA1105_SPEED_1000MBPS; i++)
+		if (sja1105_speed[i] == speed_mbps)
+			return i;
+	return -EINVAL;
+}
+
+/* Set link speed and enable/disable traffic I/O in the MAC configuration
+ * for a specific port.
+ *
+ * @speed_mbps: If 0, leave the speed unchanged, else adapt MAC to PHY speed.
+ * @enabled: Manage Rx and Tx settings for this port. Overrides the static
+ *	     configuration settings.
+ */
+static int sja1105_adjust_port_config(struct sja1105_private *priv, int port,
+				      int speed_mbps, bool enabled)
+{
+	struct sja1105_xmii_params_entry *mii;
+	struct sja1105_mac_config_entry *mac;
+	struct device *dev = priv->ds->dev;
+	sja1105_phy_interface_t phy_mode;
+	sja1105_speed_t speed;
+	int rc;
+
+	mii = priv->static_config.tables[BLK_IDX_XMII_PARAMS].entries;
+	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
+
+	speed = sja1105_get_speed_cfg(speed_mbps);
+	if (speed_mbps && speed < 0) {
+		dev_err(dev, "Invalid speed %iMbps\n", speed_mbps);
+		return -EINVAL;
+	}
+
+	/* If requested, overwrite SJA1105_SPEED_AUTO from the static MAC
+	 * configuration table, since this will be used for the clocking setup,
+	 * and we no longer need to store it in the static config (already told
+	 * hardware we want auto during upload phase).
+	 */
+	if (speed_mbps)
+		mac[port].speed = speed;
+	else
+		mac[port].speed = SJA1105_SPEED_AUTO;
+
+	/* On P/Q/R/S, one can read from the device via the MAC reconfiguration
+	 * tables. On E/T, MAC reconfig tables are not readable, only writable.
+	 * We have to *know* what the MAC looks like.  For the sake of keeping
+	 * the code common, we'll use the static configuration tables as a
+	 * reasonable approximation for both E/T and P/Q/R/S.
+	 */
+	mac[port].ingress = enabled;
+	mac[port].egress  = enabled;
+
+	/* Write to the dynamic reconfiguration tables */
+	rc = sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG,
+					  port, &mac[port], true);
+	if (rc < 0) {
+		dev_err(dev, "Failed to write MAC config: %d\n", rc);
+		return rc;
+	}
+
+	/* Reconfigure the PLLs for the RGMII interfaces (required 125 MHz at
+	 * gigabit, 25 MHz at 100 Mbps and 2.5 MHz at 10 Mbps). For MII and
+	 * RMII no change of the clock setup is required. Actually, changing
+	 * the clock setup does interrupt the clock signal for a certain time
+	 * which causes trouble for all PHYs relying on this signal.
+	 */
+	if (!enabled)
+		return 0;
+
+	phy_mode = mii->xmii_mode[port];
+	if (phy_mode != XMII_MODE_RGMII)
+		return 0;
+
+	return sja1105_clocking_setup_port(priv, port);
+}
+
+static void sja1105_adjust_link(struct dsa_switch *ds, int port,
+				struct phy_device *phydev)
+{
+	struct sja1105_private *priv = ds->priv;
+
+	if (!phydev->link)
+		sja1105_adjust_port_config(priv, port, 0, false);
+	else
+		sja1105_adjust_port_config(priv, port, phydev->speed, true);
+}
+
+static int sja1105_bridge_member(struct dsa_switch *ds, int port,
+				 struct net_device *br, bool member)
+{
+	struct sja1105_l2_forwarding_entry *l2_fwd;
+	struct sja1105_private *priv = ds->priv;
+	int i, rc;
+
+	l2_fwd = priv->static_config.tables[BLK_IDX_L2_FORWARDING].entries;
+
+	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+		/* Add this port to the forwarding matrix of the
+		 * other ports in the same bridge, and viceversa.
+		 */
+		if (!dsa_is_user_port(ds, i))
+			continue;
+		/* For the ports already under the bridge, only one thing needs
+		 * to be done, and that is to add this port to their
+		 * reachability domain. So we can perform the SPI write for
+		 * them immediately. However, for this port itself (the one
+		 * that is new to the bridge), we need to add all other ports
+		 * to its reachability domain. So we do that incrementally in
+		 * this loop, and perform the SPI write only at the end, once
+		 * the domain contains all other bridge ports.
+		 */
+		if (i == port)
+			continue;
+		if (dsa_to_port(ds, i)->bridge_dev != br)
+			continue;
+		sja1105_port_allow_traffic(l2_fwd, i, port, member);
+		sja1105_port_allow_traffic(l2_fwd, port, i, member);
+
+		rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_FORWARDING,
+						  i, &l2_fwd[i], true);
+		if (rc < 0)
+			return rc;
+	}
+
+	return sja1105_dynamic_config_write(priv, BLK_IDX_L2_FORWARDING,
+					    port, &l2_fwd[port], true);
+}
+
+static int sja1105_bridge_join(struct dsa_switch *ds, int port,
+			       struct net_device *br)
+{
+	return sja1105_bridge_member(ds, port, br, true);
+}
+
+static void sja1105_bridge_leave(struct dsa_switch *ds, int port,
+				 struct net_device *br)
+{
+	sja1105_bridge_member(ds, port, br, false);
+}
+
+static enum dsa_tag_protocol
+sja1105_get_tag_protocol(struct dsa_switch *ds, int port)
+{
+	return DSA_TAG_PROTO_NONE;
+}
+
+/* The programming model for the SJA1105 switch is "all-at-once" via static
+ * configuration tables. Some of these can be dynamically modified at runtime,
+ * but not the xMII mode parameters table.
+ * Furthermode, some PHYs may not have crystals for generating their clocks
+ * (e.g. RMII). Instead, their 50MHz clock is supplied via the SJA1105 port's
+ * ref_clk pin. So port clocking needs to be initialized early, before
+ * connecting to PHYs is attempted, otherwise they won't respond through MDIO.
+ * Setting correct PHY link speed does not matter now.
+ * But dsa_slave_phy_setup is called later than sja1105_setup, so the PHY
+ * bindings are not yet parsed by DSA core. We need to parse early so that we
+ * can populate the xMII mode parameters table.
+ */
+static int sja1105_setup(struct dsa_switch *ds)
+{
+	struct sja1105_dt_port ports[SJA1105_NUM_PORTS];
+	struct sja1105_private *priv = ds->priv;
+	int rc;
+
+	rc = sja1105_parse_dt(priv, ports);
+	if (rc < 0) {
+		dev_err(ds->dev, "Failed to parse DT: %d\n", rc);
+		return rc;
+	}
+	/* Create and send configuration down to device */
+	rc = sja1105_static_config_load(priv, ports);
+	if (rc < 0) {
+		dev_err(ds->dev, "Failed to load static config: %d\n", rc);
+		return rc;
+	}
+	/* Configure the CGU (PHY link modes and speeds) */
+	rc = sja1105_clocking_setup(priv);
+	if (rc < 0) {
+		dev_err(ds->dev, "Failed to configure MII clocking: %d\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+static const struct dsa_switch_ops sja1105_switch_ops = {
+	.get_tag_protocol	= sja1105_get_tag_protocol,
+	.setup			= sja1105_setup,
+	.adjust_link		= sja1105_adjust_link,
+	.port_bridge_join	= sja1105_bridge_join,
+	.port_bridge_leave	= sja1105_bridge_leave,
+};
+
+static int sja1105_check_device_id(struct sja1105_private *priv)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	u8 prod_id[SJA1105_SIZE_DEVICE_ID] = {0};
+	struct device *dev = &priv->spidev->dev;
+	u64 device_id;
+	u64 part_no;
+	int rc;
+
+	rc = sja1105_spi_send_int(priv, SPI_READ, regs->device_id,
+				  &device_id, SJA1105_SIZE_DEVICE_ID);
+	if (rc < 0)
+		return rc;
+
+	if (device_id != priv->info->device_id) {
+		dev_err(dev, "Expected device ID 0x%llx but read 0x%llx\n",
+			priv->info->device_id, device_id);
+		return -ENODEV;
+	}
+
+	rc = sja1105_spi_send_packed_buf(priv, SPI_READ, regs->prod_id,
+					 prod_id, SJA1105_SIZE_DEVICE_ID);
+	if (rc < 0)
+		return rc;
+
+	sja1105_unpack(prod_id, &part_no, 19, 4, SJA1105_SIZE_DEVICE_ID);
+
+	if (part_no != priv->info->part_no) {
+		dev_err(dev, "Expected part number 0x%llx but read 0x%llx\n",
+			priv->info->part_no, part_no);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int sja1105_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct sja1105_private *priv;
+	struct dsa_switch *ds;
+	int rc;
+
+	if (!dev->of_node) {
+		dev_err(dev, "No DTS bindings for SJA1105 driver\n");
+		return -EINVAL;
+	}
+
+	priv = devm_kzalloc(dev, sizeof(struct sja1105_private), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	/* Configure the optional reset pin and bring up switch */
+	priv->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(priv->reset_gpio))
+		dev_dbg(dev, "reset-gpios not defined, ignoring\n");
+	else
+		sja1105_hw_reset(priv->reset_gpio, 1, 1);
+
+	/* Populate our driver private structure (priv) based on
+	 * the device tree node that was probed (spi)
+	 */
+	priv->spidev = spi;
+	spi_set_drvdata(spi, priv);
+
+	/* Configure the SPI bus */
+	spi->bits_per_word = 8;
+	rc = spi_setup(spi);
+	if (rc < 0) {
+		dev_err(dev, "Could not init SPI\n");
+		return rc;
+	}
+
+	priv->info = of_device_get_match_data(dev);
+
+	/* Detect hardware device */
+	rc = sja1105_check_device_id(priv);
+	if (rc < 0) {
+		dev_err(dev, "Device ID check failed: %d\n", rc);
+		return rc;
+	}
+
+	dev_info(dev, "Probed switch chip: %s\n", priv->info->name);
+
+	ds = dsa_switch_alloc(dev, SJA1105_NUM_PORTS);
+	if (!ds)
+		return -ENOMEM;
+
+	ds->ops = &sja1105_switch_ops;
+	ds->priv = priv;
+	priv->ds = ds;
+
+	return dsa_register_switch(priv->ds);
+}
+
+static int sja1105_remove(struct spi_device *spi)
+{
+	struct sja1105_private *priv = spi_get_drvdata(spi);
+
+	dsa_unregister_switch(priv->ds);
+	sja1105_static_config_free(&priv->static_config);
+	return 0;
+}
+
+static const struct of_device_id sja1105_dt_ids[] = {
+	{ .compatible = "nxp,sja1105e", .data = &sja1105e_info },
+	{ .compatible = "nxp,sja1105t", .data = &sja1105t_info },
+	{ .compatible = "nxp,sja1105p", .data = &sja1105p_info },
+	{ .compatible = "nxp,sja1105q", .data = &sja1105q_info },
+	{ .compatible = "nxp,sja1105r", .data = &sja1105r_info },
+	{ .compatible = "nxp,sja1105s", .data = &sja1105s_info },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, sja1105_dt_ids);
+
+static struct spi_driver sja1105_driver = {
+	.driver = {
+		.name  = "sja1105",
+		.owner = THIS_MODULE,
+		.of_match_table = of_match_ptr(sja1105_dt_ids),
+	},
+	.probe  = sja1105_probe,
+	.remove = sja1105_remove,
+};
+
+module_spi_driver(sja1105_driver);
+
+MODULE_AUTHOR("Vladimir Oltean <olteanv@gmail.com>");
+MODULE_AUTHOR("Georg Waibel <georg.waibel@sensor-technik.de>");
+MODULE_DESCRIPTION("SJA1105 Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c
new file mode 100644
index 000000000000..07890bbf40f8
--- /dev/null
+++ b/drivers/net/dsa/sja1105/sja1105_spi.c
@@ -0,0 +1,553 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/* Copyright (c) 2016-2018, NXP Semiconductors
+ * Copyright (c) 2018, Sensor-Technik Wiedemann GmbH
+ * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#include <linux/spi/spi.h>
+#include <linux/packing.h>
+#include "sja1105.h"
+
+#define SJA1105_SIZE_RESET_CMD		4
+#define SJA1105_SIZE_SPI_MSG_HEADER	4
+#define SJA1105_SIZE_SPI_MSG_MAXLEN	(64 * 4)
+#define SJA1105_SIZE_SPI_TRANSFER_MAX	\
+	(SJA1105_SIZE_SPI_MSG_HEADER + SJA1105_SIZE_SPI_MSG_MAXLEN)
+
+static int sja1105_spi_transfer(const struct sja1105_private *priv,
+				const void *tx, void *rx, int size)
+{
+	struct spi_device *spi = priv->spidev;
+	struct spi_transfer transfer = {
+		.tx_buf = tx,
+		.rx_buf = rx,
+		.len = size,
+	};
+	struct spi_message msg;
+	int rc;
+
+	if (size > SJA1105_SIZE_SPI_TRANSFER_MAX) {
+		dev_err(&spi->dev, "SPI message (%d) longer than max of %d\n",
+			size, SJA1105_SIZE_SPI_TRANSFER_MAX);
+		return -EMSGSIZE;
+	}
+
+	spi_message_init(&msg);
+	spi_message_add_tail(&transfer, &msg);
+
+	rc = spi_sync(spi, &msg);
+	if (rc < 0) {
+		dev_err(&spi->dev, "SPI transfer failed: %d\n", rc);
+		return rc;
+	}
+
+	return rc;
+}
+
+static void
+sja1105_spi_message_pack(void *buf, const struct sja1105_spi_message *msg)
+{
+	const int size = SJA1105_SIZE_SPI_MSG_HEADER;
+
+	memset(buf, 0, size);
+
+	sja1105_pack(buf, &msg->access,     31, 31, size);
+	sja1105_pack(buf, &msg->read_count, 30, 25, size);
+	sja1105_pack(buf, &msg->address,    24,  4, size);
+}
+
+/* If @rw is:
+ * - SPI_WRITE: creates and sends an SPI write message at absolute
+ *		address reg_addr, taking size_bytes from *packed_buf
+ * - SPI_READ:  creates and sends an SPI read message from absolute
+ *		address reg_addr, writing size_bytes into *packed_buf
+ *
+ * This function should only be called if it is priorly known that
+ * @size_bytes is smaller than SIZE_SPI_MSG_MAXLEN. Larger packed buffers
+ * are chunked in smaller pieces by sja1105_spi_send_long_packed_buf below.
+ */
+int sja1105_spi_send_packed_buf(const struct sja1105_private *priv,
+				sja1105_spi_rw_mode_t rw, u64 reg_addr,
+				void *packed_buf, size_t size_bytes)
+{
+	u8 tx_buf[SJA1105_SIZE_SPI_TRANSFER_MAX] = {0};
+	u8 rx_buf[SJA1105_SIZE_SPI_TRANSFER_MAX] = {0};
+	const int msg_len = size_bytes + SJA1105_SIZE_SPI_MSG_HEADER;
+	struct sja1105_spi_message msg = {0};
+	int rc;
+
+	if (msg_len > SJA1105_SIZE_SPI_TRANSFER_MAX)
+		return -ERANGE;
+
+	msg.access = rw;
+	msg.address = reg_addr;
+	if (rw == SPI_READ)
+		msg.read_count = size_bytes / 4;
+
+	sja1105_spi_message_pack(tx_buf, &msg);
+
+	if (rw == SPI_WRITE)
+		memcpy(tx_buf + SJA1105_SIZE_SPI_MSG_HEADER,
+		       packed_buf, size_bytes);
+
+	rc = sja1105_spi_transfer(priv, tx_buf, rx_buf, msg_len);
+	if (rc < 0)
+		return rc;
+
+	if (rw == SPI_READ)
+		memcpy(packed_buf, rx_buf + SJA1105_SIZE_SPI_MSG_HEADER,
+		       size_bytes);
+
+	return 0;
+}
+
+/* If @rw is:
+ * - SPI_WRITE: creates and sends an SPI write message at absolute
+ *		address reg_addr, taking size_bytes from *packed_buf
+ * - SPI_READ:  creates and sends an SPI read message from absolute
+ *		address reg_addr, writing size_bytes into *packed_buf
+ *
+ * The u64 *value is unpacked, meaning that it's stored in the native
+ * CPU endianness and directly usable by software running on the core.
+ *
+ * This is a wrapper around sja1105_spi_send_packed_buf().
+ */
+int sja1105_spi_send_int(const struct sja1105_private *priv,
+			 sja1105_spi_rw_mode_t rw, u64 reg_addr,
+			 u64 *value, u64 size_bytes)
+{
+	u8 packed_buf[SJA1105_SIZE_SPI_MSG_MAXLEN];
+	int rc;
+
+	if (size_bytes > SJA1105_SIZE_SPI_MSG_MAXLEN)
+		return -ERANGE;
+
+	if (rw == SPI_WRITE)
+		sja1105_pack(packed_buf, value, 8 * size_bytes - 1, 0,
+			     size_bytes);
+
+	rc = sja1105_spi_send_packed_buf(priv, rw, reg_addr, packed_buf,
+					 size_bytes);
+
+	if (rw == SPI_READ)
+		sja1105_unpack(packed_buf, value, 8 * size_bytes - 1, 0,
+			       size_bytes);
+
+	return rc;
+}
+
+/* Should be used if a @packed_buf larger than SJA1105_SIZE_SPI_MSG_MAXLEN
+ * must be sent/received. Splitting the buffer into chunks and assembling
+ * those into SPI messages is done automatically by this function.
+ */
+int sja1105_spi_send_long_packed_buf(const struct sja1105_private *priv,
+				     sja1105_spi_rw_mode_t rw, u64 base_addr,
+				     void *packed_buf, u64 buf_len)
+{
+	struct chunk {
+		void *buf_ptr;
+		int len;
+		u64 spi_address;
+	} chunk;
+	int distance_to_end;
+	int rc;
+
+	/* Initialize chunk */
+	chunk.buf_ptr = packed_buf;
+	chunk.spi_address = base_addr;
+	chunk.len = min_t(int, buf_len, SJA1105_SIZE_SPI_MSG_MAXLEN);
+
+	while (chunk.len) {
+		rc = sja1105_spi_send_packed_buf(priv, rw, chunk.spi_address,
+						 chunk.buf_ptr, chunk.len);
+		if (rc < 0)
+			return rc;
+
+		chunk.buf_ptr += chunk.len;
+		chunk.spi_address += chunk.len / 4;
+		distance_to_end = (uintptr_t)(packed_buf + buf_len -
+					      chunk.buf_ptr);
+		chunk.len = min(distance_to_end, SJA1105_SIZE_SPI_MSG_MAXLEN);
+	}
+
+	return 0;
+}
+
+/* Back-ported structure from UM11040 Table 112.
+ * Reset control register (addr. 100440h)
+ * In the SJA1105 E/T, only warm_rst and cold_rst are
+ * supported (exposed in UM10944 as rst_ctrl), but the bit
+ * offsets of warm_rst and cold_rst are actually reversed.
+ */
+struct sja1105_reset_cmd {
+	u64 switch_rst;
+	u64 cfg_rst;
+	u64 car_rst;
+	u64 otp_rst;
+	u64 warm_rst;
+	u64 cold_rst;
+	u64 por_rst;
+};
+
+static void
+sja1105et_reset_cmd_pack(void *buf, const struct sja1105_reset_cmd *reset)
+{
+	const int size = SJA1105_SIZE_RESET_CMD;
+
+	memset(buf, 0, size);
+
+	sja1105_pack(buf, &reset->cold_rst, 3, 3, size);
+	sja1105_pack(buf, &reset->warm_rst, 2, 2, size);
+}
+
+static void
+sja1105pqrs_reset_cmd_pack(void *buf, const struct sja1105_reset_cmd *reset)
+{
+	const int size = SJA1105_SIZE_RESET_CMD;
+
+	memset(buf, 0, size);
+
+	sja1105_pack(buf, &reset->switch_rst, 8, 8, size);
+	sja1105_pack(buf, &reset->cfg_rst,    7, 7, size);
+	sja1105_pack(buf, &reset->car_rst,    5, 5, size);
+	sja1105_pack(buf, &reset->otp_rst,    4, 4, size);
+	sja1105_pack(buf, &reset->warm_rst,   3, 3, size);
+	sja1105_pack(buf, &reset->cold_rst,   2, 2, size);
+	sja1105_pack(buf, &reset->por_rst,    1, 1, size);
+}
+
+static int sja1105et_reset_cmd(const void *ctx, const void *data)
+{
+	const struct sja1105_private *priv = ctx;
+	const struct sja1105_reset_cmd *reset = data;
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct device *dev = priv->ds->dev;
+	u8 packed_buf[SJA1105_SIZE_RESET_CMD];
+
+	if (reset->switch_rst ||
+	    reset->cfg_rst ||
+	    reset->car_rst ||
+	    reset->otp_rst ||
+	    reset->por_rst) {
+		dev_err(dev, "Only warm and cold reset is supported "
+			"for SJA1105 E/T!\n");
+		return -EINVAL;
+	}
+
+	if (reset->warm_rst)
+		dev_dbg(dev, "Warm reset requested\n");
+	if (reset->cold_rst)
+		dev_dbg(dev, "Cold reset requested\n");
+
+	sja1105et_reset_cmd_pack(packed_buf, reset);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE, regs->rgu,
+					   packed_buf, SJA1105_SIZE_RESET_CMD);
+}
+
+static int sja1105pqrs_reset_cmd(const void *ctx, const void *data)
+{
+	const struct sja1105_private *priv = ctx;
+	const struct sja1105_reset_cmd *reset = data;
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct device *dev = priv->ds->dev;
+	u8 packed_buf[SJA1105_SIZE_RESET_CMD];
+
+	if (reset->switch_rst)
+		dev_dbg(dev, "Main reset for all functional modules requested\n");
+	if (reset->cfg_rst)
+		dev_dbg(dev, "Chip configuration reset requested\n");
+	if (reset->car_rst)
+		dev_dbg(dev, "Clock and reset control logic reset requested\n");
+	if (reset->otp_rst)
+		dev_dbg(dev, "OTP read cycle for reading product "
+			"config settings requested\n");
+	if (reset->warm_rst)
+		dev_dbg(dev, "Warm reset requested\n");
+	if (reset->cold_rst)
+		dev_dbg(dev, "Cold reset requested\n");
+	if (reset->por_rst)
+		dev_dbg(dev, "Power-on reset requested\n");
+
+	sja1105pqrs_reset_cmd_pack(packed_buf, reset);
+
+	return sja1105_spi_send_packed_buf(priv, SPI_WRITE, regs->rgu,
+					   packed_buf, SJA1105_SIZE_RESET_CMD);
+}
+
+static int sja1105_cold_reset(const struct sja1105_private *priv)
+{
+	struct sja1105_reset_cmd reset = {0};
+
+	reset.cold_rst = 1;
+	return priv->info->reset_cmd(priv, &reset);
+}
+
+struct sja1105_status {
+	u64 configs;
+	u64 crcchkl;
+	u64 ids;
+	u64 crcchkg;
+};
+
+/* This is not reading the entire General Status area, which is also
+ * divergent between E/T and P/Q/R/S, but only the relevant bits for
+ * ensuring that the static config upload procedure was successful.
+ */
+static void sja1105_status_unpack(void *buf, struct sja1105_status *status)
+{
+	/* So that addition translates to 4 bytes */
+	u32 *p = buf;
+
+	/* device_id is missing from the buffer, but we don't
+	 * want to diverge from the manual definition of the
+	 * register addresses, so we'll back off one step with
+	 * the register pointer, and never access p[0].
+	 */
+	p--;
+	sja1105_unpack(p + 0x1, &status->configs,   31, 31, 4);
+	sja1105_unpack(p + 0x1, &status->crcchkl,   30, 30, 4);
+	sja1105_unpack(p + 0x1, &status->ids,       29, 29, 4);
+	sja1105_unpack(p + 0x1, &status->crcchkg,   28, 28, 4);
+}
+
+static int sja1105_status_get(struct sja1105_private *priv,
+			      struct sja1105_status *status)
+{
+	const struct sja1105_regs *regs = priv->info->regs;
+	u8 packed_buf[4];
+	int rc;
+
+	rc = sja1105_spi_send_packed_buf(priv, SPI_READ,
+					 regs->status,
+					 packed_buf, 4);
+	if (rc < 0)
+		return rc;
+
+	sja1105_status_unpack(packed_buf, status);
+
+	return 0;
+}
+
+/* Not const because unpacking priv->static_config into buffers and preparing
+ * for upload requires the recalculation of table CRCs and updating the
+ * structures with these.
+ */
+static int
+static_config_buf_prepare_for_upload(struct sja1105_private *priv,
+				     void *config_buf, int buf_len)
+{
+	struct sja1105_static_config *config = &priv->static_config;
+	struct sja1105_table_header final_header;
+	sja1105_config_valid_t valid;
+	char *final_header_ptr;
+	int crc_len;
+
+	valid = sja1105_static_config_check_valid(config);
+	if (valid != SJA1105_CONFIG_OK) {
+		dev_err(&priv->spidev->dev,
+			sja1105_static_config_error_msg[valid]);
+		return -EINVAL;
+	}
+
+	/* Write Device ID and config tables to config_buf */
+	sja1105_static_config_pack(config_buf, config);
+	/* Recalculate CRC of the last header (right now 0xDEADBEEF).
+	 * Don't include the CRC field itself.
+	 */
+	crc_len = buf_len - 4;
+	/* Read the whole table header */
+	final_header_ptr = config_buf + buf_len - SJA1105_SIZE_TABLE_HEADER;
+	sja1105_table_header_packing(final_header_ptr, &final_header, UNPACK);
+	/* Modify */
+	final_header.crc = sja1105_crc32(config_buf, crc_len);
+	/* Rewrite */
+	sja1105_table_header_packing(final_header_ptr, &final_header, PACK);
+
+	return 0;
+}
+
+#define RETRIES 10
+
+int sja1105_static_config_upload(struct sja1105_private *priv)
+{
+	struct sja1105_static_config *config = &priv->static_config;
+	const struct sja1105_regs *regs = priv->info->regs;
+	struct device *dev = &priv->spidev->dev;
+	struct sja1105_status status;
+	int rc, retries = RETRIES;
+	u8 *config_buf;
+	int buf_len;
+
+	buf_len = sja1105_static_config_get_length(config);
+	config_buf = kcalloc(buf_len, sizeof(char), GFP_KERNEL);
+	if (!config_buf)
+		return -ENOMEM;
+
+	rc = static_config_buf_prepare_for_upload(priv, config_buf, buf_len);
+	if (rc < 0) {
+		dev_err(dev, "Invalid config, cannot upload\n");
+		return -EINVAL;
+	}
+	do {
+		/* Put the SJA1105 in programming mode */
+		rc = sja1105_cold_reset(priv);
+		if (rc < 0) {
+			dev_err(dev, "Failed to reset switch, retrying...\n");
+			continue;
+		}
+		/* Wait for the switch to come out of reset */
+		usleep_range(1000, 5000);
+		/* Upload the static config to the device */
+		rc = sja1105_spi_send_long_packed_buf(priv, SPI_WRITE,
+						      regs->config,
+						      config_buf, buf_len);
+		if (rc < 0) {
+			dev_err(dev, "Failed to upload config, retrying...\n");
+			continue;
+		}
+		/* Check that SJA1105 responded well to the config upload */
+		rc = sja1105_status_get(priv, &status);
+		if (rc < 0)
+			continue;
+
+		if (status.ids == 1) {
+			dev_err(dev, "Mismatch between hardware and static config "
+				"device id. Wrote 0x%llx, wants 0x%llx\n",
+				config->device_id, priv->info->device_id);
+			continue;
+		}
+		if (status.crcchkl == 1) {
+			dev_err(dev, "Switch reported invalid local CRC on "
+				"the uploaded config, retrying...\n");
+			continue;
+		}
+		if (status.crcchkg == 1) {
+			dev_err(dev, "Switch reported invalid global CRC on "
+				"the uploaded config, retrying...\n");
+			continue;
+		}
+		if (status.configs == 0) {
+			dev_err(dev, "Switch reported that configuration is "
+				"invalid, retrying...\n");
+			continue;
+		}
+	} while (--retries && (status.crcchkl == 1 || status.crcchkg == 1 ||
+		 status.configs == 0 || status.ids == 1));
+
+	if (!retries) {
+		rc = -EIO;
+		dev_err(dev, "Failed to upload config to device, giving up\n");
+		goto out;
+	} else if (retries != RETRIES - 1) {
+		dev_info(dev, "Succeeded after %d tried\n", RETRIES - retries);
+	}
+
+	dev_info(dev, "Reset switch and programmed static config\n");
+out:
+	kfree(config_buf);
+	return rc;
+}
+
+struct sja1105_regs sja1105et_regs = {
+	.device_id = 0x0,
+	.prod_id = 0x100BC3,
+	.status = 0x1,
+	.config = 0x020000,
+	.rgu = 0x100440,
+	.pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808},
+	.rmii_pll1 = 0x10000A,
+	.cgu_idiv = {0x10000B, 0x10000C, 0x10000D, 0x10000E, 0x10000F},
+	/* UM10944.pdf, Table 86, ACU Register overview */
+	.rgmii_pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808},
+	.mac = {0x200, 0x202, 0x204, 0x206, 0x208},
+	.mac_hl1 = {0x400, 0x410, 0x420, 0x430, 0x440},
+	.mac_hl2 = {0x600, 0x610, 0x620, 0x630, 0x640},
+	/* UM10944.pdf, Table 78, CGU Register overview */
+	.mii_tx_clk = {0x100013, 0x10001A, 0x100021, 0x100028, 0x10002F},
+	.mii_rx_clk = {0x100014, 0x10001B, 0x100022, 0x100029, 0x100030},
+	.mii_ext_tx_clk = {0x100018, 0x10001F, 0x100026, 0x10002D, 0x100034},
+	.mii_ext_rx_clk = {0x100019, 0x100020, 0x100027, 0x10002E, 0x100035},
+	.rgmii_tx_clk = {0x100016, 0x10001D, 0x100024, 0x10002B, 0x100032},
+	.rmii_ref_clk = {0x100015, 0x10001C, 0x100023, 0x10002A, 0x100031},
+	.rmii_ext_tx_clk = {0x100018, 0x10001F, 0x100026, 0x10002D, 0x100034},
+};
+
+struct sja1105_regs sja1105pqrs_regs = {
+	.device_id = 0x0,
+	.prod_id = 0x100BC3,
+	.status = 0x1,
+	.config = 0x020000,
+	.rgu = 0x100440,
+	.pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808},
+	.rmii_pll1 = 0x10000A,
+	.cgu_idiv = {0x10000B, 0x10000C, 0x10000D, 0x10000E, 0x10000F},
+	/* UM10944.pdf, Table 86, ACU Register overview */
+	.rgmii_pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808},
+	.mac = {0x200, 0x202, 0x204, 0x206, 0x208},
+	.mac_hl1 = {0x400, 0x410, 0x420, 0x430, 0x440},
+	.mac_hl2 = {0x600, 0x610, 0x620, 0x630, 0x640},
+	/* UM11040.pdf, Table 114 */
+	.mii_tx_clk = {0x100013, 0x100019, 0x10001F, 0x100025, 0x10002B},
+	.mii_rx_clk = {0x100014, 0x10001A, 0x100020, 0x100026, 0x10002C},
+	.mii_ext_tx_clk = {0x100017, 0x10001D, 0x100023, 0x100029, 0x10002F},
+	.mii_ext_rx_clk = {0x100018, 0x10001E, 0x100024, 0x10002A, 0x100030},
+	.rgmii_tx_clk = {0x100016, 0x10001C, 0x100022, 0x100028, 0x10002E},
+	.rmii_ref_clk = {0x100015, 0x10001B, 0x100021, 0x100027, 0x10002D},
+	.rmii_ext_tx_clk = {0x100017, 0x10001D, 0x100023, 0x100029, 0x10002F},
+	.qlevel = {0x604, 0x614, 0x624, 0x634, 0x644},
+};
+
+struct sja1105_info sja1105e_info = {
+	.device_id		= SJA1105E_DEVICE_ID,
+	.part_no		= SJA1105ET_PART_NO,
+	.static_ops		= sja1105e_table_ops,
+	.dyn_ops		= sja1105et_dyn_ops,
+	.reset_cmd		= sja1105et_reset_cmd,
+	.regs			= &sja1105et_regs,
+	.name			= "SJA1105E",
+};
+struct sja1105_info sja1105t_info = {
+	.device_id		= SJA1105T_DEVICE_ID,
+	.part_no		= SJA1105ET_PART_NO,
+	.static_ops		= sja1105t_table_ops,
+	.dyn_ops		= sja1105et_dyn_ops,
+	.reset_cmd		= sja1105et_reset_cmd,
+	.regs			= &sja1105et_regs,
+	.name			= "SJA1105T",
+};
+struct sja1105_info sja1105p_info = {
+	.device_id		= SJA1105PR_DEVICE_ID,
+	.part_no		= SJA1105P_PART_NO,
+	.static_ops		= sja1105p_table_ops,
+	.dyn_ops		= sja1105pqrs_dyn_ops,
+	.reset_cmd		= sja1105pqrs_reset_cmd,
+	.regs			= &sja1105pqrs_regs,
+	.name			= "SJA1105P",
+};
+struct sja1105_info sja1105q_info = {
+	.device_id		= SJA1105QS_DEVICE_ID,
+	.part_no		= SJA1105Q_PART_NO,
+	.static_ops		= sja1105q_table_ops,
+	.dyn_ops		= sja1105pqrs_dyn_ops,
+	.reset_cmd		= sja1105pqrs_reset_cmd,
+	.regs			= &sja1105pqrs_regs,
+	.name			= "SJA1105Q",
+};
+struct sja1105_info sja1105r_info = {
+	.device_id		= SJA1105PR_DEVICE_ID,
+	.part_no		= SJA1105R_PART_NO,
+	.static_ops		= sja1105r_table_ops,
+	.dyn_ops		= sja1105pqrs_dyn_ops,
+	.reset_cmd		= sja1105pqrs_reset_cmd,
+	.regs			= &sja1105pqrs_regs,
+	.name			= "SJA1105R",
+};
+struct sja1105_info sja1105s_info = {
+	.device_id		= SJA1105QS_DEVICE_ID,
+	.part_no		= SJA1105S_PART_NO,
+	.static_ops		= sja1105s_table_ops,
+	.dyn_ops		= sja1105pqrs_dyn_ops,
+	.regs			= &sja1105pqrs_regs,
+	.reset_cmd		= sja1105pqrs_reset_cmd,
+	.name			= "SJA1105S",
+};
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c
new file mode 100644
index 000000000000..84ee623c6336
--- /dev/null
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.c
@@ -0,0 +1,949 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/* Copyright (c) 2016-2018, NXP Semiconductors
+ * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#include "sja1105_static_config.h"
+#include <linux/crc32.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+
+/* Convenience wrappers over the generic packing functions. These take into
+ * account the SJA1105 memory layout quirks and provide some level of
+ * programmer protection against incorrect API use. The errors are not expected
+ * to occur durring runtime, therefore printing and swallowing them here is
+ * appropriate instead of clutterring up higher-level code.
+ */
+void sja1105_pack(void *buf, const u64 *val, int start, int end, size_t len)
+{
+	int rc = packing(buf, (u64 *)val, start, end, len,
+			 PACK, QUIRK_LSW32_IS_FIRST);
+
+	if (likely(!rc))
+		return;
+
+	if (rc == -EINVAL) {
+		pr_err("Start bit (%d) expected to be larger than end (%d)\n",
+		       start, end);
+	} else if (rc == -ERANGE) {
+		if ((start - end + 1) > 64)
+			pr_err("Field %d-%d too large for 64 bits!\n",
+			       start, end);
+		else
+			pr_err("Cannot store %llx inside bits %d-%d (would truncate)\n",
+			       *val, start, end);
+	}
+	dump_stack();
+}
+
+void sja1105_unpack(const void *buf, u64 *val, int start, int end, size_t len)
+{
+	int rc = packing((void *)buf, val, start, end, len,
+			 UNPACK, QUIRK_LSW32_IS_FIRST);
+
+	if (likely(!rc))
+		return;
+
+	if (rc == -EINVAL)
+		pr_err("Start bit (%d) expected to be larger than end (%d)\n",
+		       start, end);
+	else if (rc == -ERANGE)
+		pr_err("Field %d-%d too large for 64 bits!\n",
+		       start, end);
+	dump_stack();
+}
+
+void sja1105_packing(void *buf, u64 *val, int start, int end,
+		     size_t len, enum packing_op op)
+{
+	int rc = packing(buf, val, start, end, len, op, QUIRK_LSW32_IS_FIRST);
+
+	if (likely(!rc))
+		return;
+
+	if (rc == -EINVAL) {
+		pr_err("Start bit (%d) expected to be larger than end (%d)\n",
+		       start, end);
+	} else if (rc == -ERANGE) {
+		if ((start - end + 1) > 64)
+			pr_err("Field %d-%d too large for 64 bits!\n",
+			       start, end);
+		else
+			pr_err("Cannot store %llx inside bits %d-%d (would truncate)\n",
+			       *val, start, end);
+	}
+	dump_stack();
+}
+
+/* Little-endian Ethernet CRC32 of data packed as big-endian u32 words */
+u32 sja1105_crc32(const void *buf, size_t len)
+{
+	unsigned int i;
+	u64 word;
+	u32 crc;
+
+	/* seed */
+	crc = ~0;
+	for (i = 0; i < len; i += 4) {
+		sja1105_unpack((void *)buf + i, &word, 31, 0, 4);
+		crc = crc32_le(crc, (u8 *)&word, 4);
+	}
+	return ~crc;
+}
+
+static size_t sja1105et_general_params_entry_packing(void *buf, void *entry_ptr,
+						     enum packing_op op)
+{
+	const size_t size = SJA1105ET_SIZE_GENERAL_PARAMS_ENTRY;
+	struct sja1105_general_params_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->vllupformat, 319, 319, size, op);
+	sja1105_packing(buf, &entry->mirr_ptacu,  318, 318, size, op);
+	sja1105_packing(buf, &entry->switchid,    317, 315, size, op);
+	sja1105_packing(buf, &entry->hostprio,    314, 312, size, op);
+	sja1105_packing(buf, &entry->mac_fltres1, 311, 264, size, op);
+	sja1105_packing(buf, &entry->mac_fltres0, 263, 216, size, op);
+	sja1105_packing(buf, &entry->mac_flt1,    215, 168, size, op);
+	sja1105_packing(buf, &entry->mac_flt0,    167, 120, size, op);
+	sja1105_packing(buf, &entry->incl_srcpt1, 119, 119, size, op);
+	sja1105_packing(buf, &entry->incl_srcpt0, 118, 118, size, op);
+	sja1105_packing(buf, &entry->send_meta1,  117, 117, size, op);
+	sja1105_packing(buf, &entry->send_meta0,  116, 116, size, op);
+	sja1105_packing(buf, &entry->casc_port,   115, 113, size, op);
+	sja1105_packing(buf, &entry->host_port,   112, 110, size, op);
+	sja1105_packing(buf, &entry->mirr_port,   109, 107, size, op);
+	sja1105_packing(buf, &entry->vlmarker,    106,  75, size, op);
+	sja1105_packing(buf, &entry->vlmask,       74,  43, size, op);
+	sja1105_packing(buf, &entry->tpid,         42,  27, size, op);
+	sja1105_packing(buf, &entry->ignore2stf,   26,  26, size, op);
+	sja1105_packing(buf, &entry->tpid2,        25,  10, size, op);
+	return size;
+}
+
+static size_t
+sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op)
+{
+	const size_t size = SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY;
+	struct sja1105_general_params_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->vllupformat, 351, 351, size, op);
+	sja1105_packing(buf, &entry->mirr_ptacu,  350, 350, size, op);
+	sja1105_packing(buf, &entry->switchid,    349, 347, size, op);
+	sja1105_packing(buf, &entry->hostprio,    346, 344, size, op);
+	sja1105_packing(buf, &entry->mac_fltres1, 343, 296, size, op);
+	sja1105_packing(buf, &entry->mac_fltres0, 295, 248, size, op);
+	sja1105_packing(buf, &entry->mac_flt1,    247, 200, size, op);
+	sja1105_packing(buf, &entry->mac_flt0,    199, 152, size, op);
+	sja1105_packing(buf, &entry->incl_srcpt1, 151, 151, size, op);
+	sja1105_packing(buf, &entry->incl_srcpt0, 150, 150, size, op);
+	sja1105_packing(buf, &entry->send_meta1,  149, 149, size, op);
+	sja1105_packing(buf, &entry->send_meta0,  148, 148, size, op);
+	sja1105_packing(buf, &entry->casc_port,   147, 145, size, op);
+	sja1105_packing(buf, &entry->host_port,   144, 142, size, op);
+	sja1105_packing(buf, &entry->mirr_port,   141, 139, size, op);
+	sja1105_packing(buf, &entry->vlmarker,    138, 107, size, op);
+	sja1105_packing(buf, &entry->vlmask,      106,  75, size, op);
+	sja1105_packing(buf, &entry->tpid,         74,  59, size, op);
+	sja1105_packing(buf, &entry->ignore2stf,   58,  58, size, op);
+	sja1105_packing(buf, &entry->tpid2,        57,  42, size, op);
+	sja1105_packing(buf, &entry->queue_ts,     41,  41, size, op);
+	sja1105_packing(buf, &entry->egrmirrvid,   40,  29, size, op);
+	sja1105_packing(buf, &entry->egrmirrpcp,   28,  26, size, op);
+	sja1105_packing(buf, &entry->egrmirrdei,   25,  25, size, op);
+	sja1105_packing(buf, &entry->replay_port,  24,  22, size, op);
+	return size;
+}
+
+static size_t
+sja1105_l2_forwarding_params_entry_packing(void *buf, void *entry_ptr,
+					   enum packing_op op)
+{
+	const size_t size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY;
+	struct sja1105_l2_forwarding_params_entry *entry = entry_ptr;
+	int offset, i;
+
+	sja1105_packing(buf, &entry->max_dynp, 95, 93, size, op);
+	for (i = 0, offset = 13; i < 8; i++, offset += 10)
+		sja1105_packing(buf, &entry->part_spc[i],
+				offset + 9, offset + 0, size, op);
+	return size;
+}
+
+size_t sja1105_l2_forwarding_entry_packing(void *buf, void *entry_ptr,
+					   enum packing_op op)
+{
+	const size_t size = SJA1105_SIZE_L2_FORWARDING_ENTRY;
+	struct sja1105_l2_forwarding_entry *entry = entry_ptr;
+	int offset, i;
+
+	sja1105_packing(buf, &entry->bc_domain,  63, 59, size, op);
+	sja1105_packing(buf, &entry->reach_port, 58, 54, size, op);
+	sja1105_packing(buf, &entry->fl_domain,  53, 49, size, op);
+	for (i = 0, offset = 25; i < 8; i++, offset += 3)
+		sja1105_packing(buf, &entry->vlan_pmap[i],
+				offset + 2, offset + 0, size, op);
+	return size;
+}
+
+static size_t
+sja1105et_l2_lookup_params_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op)
+{
+	const size_t size = SJA1105ET_SIZE_L2_LOOKUP_PARAMS_ENTRY;
+	struct sja1105_l2_lookup_params_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->maxage,         31, 17, size, op);
+	sja1105_packing(buf, &entry->dyn_tbsz,       16, 14, size, op);
+	sja1105_packing(buf, &entry->poly,           13,  6, size, op);
+	sja1105_packing(buf, &entry->shared_learn,    5,  5, size, op);
+	sja1105_packing(buf, &entry->no_enf_hostprt,  4,  4, size, op);
+	sja1105_packing(buf, &entry->no_mgmt_learn,   3,  3, size, op);
+	return size;
+}
+
+static size_t
+sja1105pqrs_l2_lookup_params_entry_packing(void *buf, void *entry_ptr,
+					   enum packing_op op)
+{
+	const size_t size = SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY;
+	struct sja1105_l2_lookup_params_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->maxage,         57,  43, size, op);
+	sja1105_packing(buf, &entry->shared_learn,   27,  27, size, op);
+	sja1105_packing(buf, &entry->no_enf_hostprt, 26,  26, size, op);
+	sja1105_packing(buf, &entry->no_mgmt_learn,  25,  25, size, op);
+	return size;
+}
+
+size_t sja1105et_l2_lookup_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op)
+{
+	const size_t size = SJA1105ET_SIZE_L2_LOOKUP_ENTRY;
+	struct sja1105_l2_lookup_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->vlanid,    95, 84, size, op);
+	sja1105_packing(buf, &entry->macaddr,   83, 36, size, op);
+	sja1105_packing(buf, &entry->destports, 35, 31, size, op);
+	sja1105_packing(buf, &entry->enfport,   30, 30, size, op);
+	sja1105_packing(buf, &entry->index,     29, 20, size, op);
+	return size;
+}
+
+size_t sja1105pqrs_l2_lookup_entry_packing(void *buf, void *entry_ptr,
+					   enum packing_op op)
+{
+	const size_t size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY;
+	struct sja1105_l2_lookup_entry *entry = entry_ptr;
+
+	/* These are static L2 lookup entries, so the structure
+	 * should match UM11040 Table 16/17 definitions when
+	 * LOCKEDS is 1.
+	 */
+	sja1105_packing(buf, &entry->vlanid,        81,  70, size, op);
+	sja1105_packing(buf, &entry->macaddr,       69,  22, size, op);
+	sja1105_packing(buf, &entry->destports,     21,  17, size, op);
+	sja1105_packing(buf, &entry->enfport,       16,  16, size, op);
+	sja1105_packing(buf, &entry->index,         15,   6, size, op);
+	return size;
+}
+
+static size_t sja1105_l2_policing_entry_packing(void *buf, void *entry_ptr,
+						enum packing_op op)
+{
+	const size_t size = SJA1105_SIZE_L2_POLICING_ENTRY;
+	struct sja1105_l2_policing_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->sharindx,  63, 58, size, op);
+	sja1105_packing(buf, &entry->smax,      57, 42, size, op);
+	sja1105_packing(buf, &entry->rate,      41, 26, size, op);
+	sja1105_packing(buf, &entry->maxlen,    25, 15, size, op);
+	sja1105_packing(buf, &entry->partition, 14, 12, size, op);
+	return size;
+}
+
+static size_t sja1105et_mac_config_entry_packing(void *buf, void *entry_ptr,
+						 enum packing_op op)
+{
+	const size_t size = SJA1105ET_SIZE_MAC_CONFIG_ENTRY;
+	struct sja1105_mac_config_entry *entry = entry_ptr;
+	int offset, i;
+
+	for (i = 0, offset = 72; i < 8; i++, offset += 19) {
+		sja1105_packing(buf, &entry->enabled[i],
+				offset +  0, offset +  0, size, op);
+		sja1105_packing(buf, &entry->base[i],
+				offset +  9, offset +  1, size, op);
+		sja1105_packing(buf, &entry->top[i],
+				offset + 18, offset + 10, size, op);
+	}
+	sja1105_packing(buf, &entry->ifg,       71, 67, size, op);
+	sja1105_packing(buf, &entry->speed,     66, 65, size, op);
+	sja1105_packing(buf, &entry->tp_delin,  64, 49, size, op);
+	sja1105_packing(buf, &entry->tp_delout, 48, 33, size, op);
+	sja1105_packing(buf, &entry->maxage,    32, 25, size, op);
+	sja1105_packing(buf, &entry->vlanprio,  24, 22, size, op);
+	sja1105_packing(buf, &entry->vlanid,    21, 10, size, op);
+	sja1105_packing(buf, &entry->ing_mirr,   9,  9, size, op);
+	sja1105_packing(buf, &entry->egr_mirr,   8,  8, size, op);
+	sja1105_packing(buf, &entry->drpnona664, 7,  7, size, op);
+	sja1105_packing(buf, &entry->drpdtag,    6,  6, size, op);
+	sja1105_packing(buf, &entry->drpuntag,   5,  5, size, op);
+	sja1105_packing(buf, &entry->retag,      4,  4, size, op);
+	sja1105_packing(buf, &entry->dyn_learn,  3,  3, size, op);
+	sja1105_packing(buf, &entry->egress,     2,  2, size, op);
+	sja1105_packing(buf, &entry->ingress,    1,  1, size, op);
+	return size;
+}
+
+size_t sja1105pqrs_mac_config_entry_packing(void *buf, void *entry_ptr,
+					    enum packing_op op)
+{
+	const size_t size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY;
+	struct sja1105_mac_config_entry *entry = entry_ptr;
+	int offset, i;
+
+	for (i = 0, offset = 104; i < 8; i++, offset += 19) {
+		sja1105_packing(buf, &entry->enabled[i],
+				offset +  0, offset +  0, size, op);
+		sja1105_packing(buf, &entry->base[i],
+				offset +  9, offset +  1, size, op);
+		sja1105_packing(buf, &entry->top[i],
+				offset + 18, offset + 10, size, op);
+	}
+	sja1105_packing(buf, &entry->ifg,       103, 99, size, op);
+	sja1105_packing(buf, &entry->speed,      98, 97, size, op);
+	sja1105_packing(buf, &entry->tp_delin,   96, 81, size, op);
+	sja1105_packing(buf, &entry->tp_delout,  80, 65, size, op);
+	sja1105_packing(buf, &entry->maxage,     64, 57, size, op);
+	sja1105_packing(buf, &entry->vlanprio,   56, 54, size, op);
+	sja1105_packing(buf, &entry->vlanid,     53, 42, size, op);
+	sja1105_packing(buf, &entry->ing_mirr,   41, 41, size, op);
+	sja1105_packing(buf, &entry->egr_mirr,   40, 40, size, op);
+	sja1105_packing(buf, &entry->drpnona664, 39, 39, size, op);
+	sja1105_packing(buf, &entry->drpdtag,    38, 38, size, op);
+	sja1105_packing(buf, &entry->drpuntag,   35, 35, size, op);
+	sja1105_packing(buf, &entry->retag,      34, 34, size, op);
+	sja1105_packing(buf, &entry->dyn_learn,  33, 33, size, op);
+	sja1105_packing(buf, &entry->egress,     32, 32, size, op);
+	sja1105_packing(buf, &entry->ingress,    31, 31, size, op);
+	return size;
+}
+
+size_t sja1105_vlan_lookup_entry_packing(void *buf, void *entry_ptr,
+					 enum packing_op op)
+{
+	const size_t size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY;
+	struct sja1105_vlan_lookup_entry *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->ving_mirr,  63, 59, size, op);
+	sja1105_packing(buf, &entry->vegr_mirr,  58, 54, size, op);
+	sja1105_packing(buf, &entry->vmemb_port, 53, 49, size, op);
+	sja1105_packing(buf, &entry->vlan_bc,    48, 44, size, op);
+	sja1105_packing(buf, &entry->tag_port,   43, 39, size, op);
+	sja1105_packing(buf, &entry->vlanid,     38, 27, size, op);
+	return size;
+}
+
+static size_t sja1105_xmii_params_entry_packing(void *buf, void *entry_ptr,
+						enum packing_op op)
+{
+	const size_t size = SJA1105_SIZE_XMII_PARAMS_ENTRY;
+	struct sja1105_xmii_params_entry *entry = entry_ptr;
+	int offset, i;
+
+	for (i = 0, offset = 17; i < 5; i++, offset += 3) {
+		sja1105_packing(buf, &entry->xmii_mode[i],
+				offset + 1, offset + 0, size, op);
+		sja1105_packing(buf, &entry->phy_mac[i],
+				offset + 2, offset + 2, size, op);
+	}
+	return size;
+}
+
+size_t sja1105_table_header_packing(void *buf, void *entry_ptr,
+				    enum packing_op op)
+{
+	const size_t size = SJA1105_SIZE_TABLE_HEADER;
+	struct sja1105_table_header *entry = entry_ptr;
+
+	sja1105_packing(buf, &entry->block_id, 31, 24, size, op);
+	sja1105_packing(buf, &entry->len,      55, 32, size, op);
+	sja1105_packing(buf, &entry->crc,      95, 64, size, op);
+	return size;
+}
+
+/* WARNING: the *hdr pointer is really non-const, because it is
+ * modifying the CRC of the header for a 2-stage packing operation
+ */
+void
+sja1105_table_header_pack_with_crc(void *buf, struct sja1105_table_header *hdr)
+{
+	/* First pack the table as-is, then calculate the CRC, and
+	 * finally put the proper CRC into the packed buffer
+	 */
+	memset(buf, 0, SJA1105_SIZE_TABLE_HEADER);
+	sja1105_table_header_packing(buf, hdr, PACK);
+	hdr->crc = sja1105_crc32(buf, SJA1105_SIZE_TABLE_HEADER - 4);
+	sja1105_pack(buf + SJA1105_SIZE_TABLE_HEADER - 4, &hdr->crc, 31, 0, 4);
+}
+
+static void sja1105_table_write_crc(u8 *table_start, u8 *crc_ptr)
+{
+	u64 computed_crc;
+	int len_bytes;
+
+	len_bytes = (uintptr_t)(crc_ptr - table_start);
+	computed_crc = sja1105_crc32(table_start, len_bytes);
+	sja1105_pack(crc_ptr, &computed_crc, 31, 0, 4);
+}
+
+/* The block IDs that the switches support are unfortunately sparse, so keep a
+ * mapping table to "block indices" and translate back and forth so that we
+ * don't waste useless memory in struct sja1105_static_config.
+ * Also, since the block id comes from essentially untrusted input (unpacking
+ * the static config from userspace) it has to be sanitized (range-checked)
+ * before blindly indexing kernel memory with the blk_idx.
+ */
+static u64 blk_id_map[BLK_IDX_MAX] = {
+	[BLK_IDX_L2_LOOKUP] = BLKID_L2_LOOKUP,
+	[BLK_IDX_L2_POLICING] = BLKID_L2_POLICING,
+	[BLK_IDX_VLAN_LOOKUP] = BLKID_VLAN_LOOKUP,
+	[BLK_IDX_L2_FORWARDING] = BLKID_L2_FORWARDING,
+	[BLK_IDX_MAC_CONFIG] = BLKID_MAC_CONFIG,
+	[BLK_IDX_L2_LOOKUP_PARAMS] = BLKID_L2_LOOKUP_PARAMS,
+	[BLK_IDX_L2_FORWARDING_PARAMS] = BLKID_L2_FORWARDING_PARAMS,
+	[BLK_IDX_GENERAL_PARAMS] = BLKID_GENERAL_PARAMS,
+	[BLK_IDX_XMII_PARAMS] = BLKID_XMII_PARAMS,
+};
+
+const char *sja1105_static_config_error_msg[] = {
+	[SJA1105_CONFIG_OK] = "",
+	[SJA1105_MISSING_L2_POLICING_TABLE] =
+		"l2-policing-table needs to have at least one entry",
+	[SJA1105_MISSING_L2_FORWARDING_TABLE] =
+		"l2-forwarding-table is either missing or incomplete",
+	[SJA1105_MISSING_L2_FORWARDING_PARAMS_TABLE] =
+		"l2-forwarding-parameters-table is missing",
+	[SJA1105_MISSING_GENERAL_PARAMS_TABLE] =
+		"general-parameters-table is missing",
+	[SJA1105_MISSING_VLAN_TABLE] =
+		"vlan-lookup-table needs to have at least the default untagged VLAN",
+	[SJA1105_MISSING_XMII_TABLE] =
+		"xmii-table is missing",
+	[SJA1105_MISSING_MAC_TABLE] =
+		"mac-configuration-table needs to contain an entry for each port",
+	[SJA1105_OVERCOMMITTED_FRAME_MEMORY] =
+		"Not allowed to overcommit frame memory. L2 memory partitions "
+		"and VL memory partitions share the same space. The sum of all "
+		"16 memory partitions is not allowed to be larger than 929 "
+		"128-byte blocks (or 910 with retagging). Please adjust "
+		"l2-forwarding-parameters-table.part_spc and/or "
+		"vl-forwarding-parameters-table.partspc.",
+};
+
+sja1105_config_valid_t
+static_config_check_memory_size(const struct sja1105_table *tables)
+{
+	const struct sja1105_l2_forwarding_params_entry *l2_fwd_params;
+	int i, mem = 0;
+
+	l2_fwd_params = tables[BLK_IDX_L2_FORWARDING_PARAMS].entries;
+
+	for (i = 0; i < 8; i++)
+		mem += l2_fwd_params->part_spc[i];
+
+	if (mem > SJA1105_MAX_FRAME_MEMORY)
+		return SJA1105_OVERCOMMITTED_FRAME_MEMORY;
+
+	return SJA1105_CONFIG_OK;
+}
+
+sja1105_config_valid_t
+sja1105_static_config_check_valid(const struct sja1105_static_config *config)
+{
+	const struct sja1105_table *tables = config->tables;
+#define IS_FULL(blk_idx) \
+	(tables[blk_idx].entry_count == tables[blk_idx].ops->max_entry_count)
+
+	if (tables[BLK_IDX_L2_POLICING].entry_count == 0)
+		return SJA1105_MISSING_L2_POLICING_TABLE;
+
+	if (tables[BLK_IDX_VLAN_LOOKUP].entry_count == 0)
+		return SJA1105_MISSING_VLAN_TABLE;
+
+	if (!IS_FULL(BLK_IDX_L2_FORWARDING))
+		return SJA1105_MISSING_L2_FORWARDING_TABLE;
+
+	if (!IS_FULL(BLK_IDX_MAC_CONFIG))
+		return SJA1105_MISSING_MAC_TABLE;
+
+	if (!IS_FULL(BLK_IDX_L2_FORWARDING_PARAMS))
+		return SJA1105_MISSING_L2_FORWARDING_PARAMS_TABLE;
+
+	if (!IS_FULL(BLK_IDX_GENERAL_PARAMS))
+		return SJA1105_MISSING_GENERAL_PARAMS_TABLE;
+
+	if (!IS_FULL(BLK_IDX_XMII_PARAMS))
+		return SJA1105_MISSING_XMII_TABLE;
+
+	return static_config_check_memory_size(tables);
+#undef IS_FULL
+}
+
+void
+sja1105_static_config_pack(void *buf, struct sja1105_static_config *config)
+{
+	struct sja1105_table_header header = {0};
+	enum sja1105_blk_idx i;
+	char *p = buf;
+	int j;
+
+	sja1105_pack(p, &config->device_id, 31, 0, 4);
+	p += SJA1105_SIZE_DEVICE_ID;
+
+	for (i = 0; i < BLK_IDX_MAX; i++) {
+		const struct sja1105_table *table;
+		char *table_start;
+
+		table = &config->tables[i];
+		if (!table->entry_count)
+			continue;
+
+		header.block_id = blk_id_map[i];
+		header.len = table->entry_count *
+			     table->ops->packed_entry_size / 4;
+		sja1105_table_header_pack_with_crc(p, &header);
+		p += SJA1105_SIZE_TABLE_HEADER;
+		table_start = p;
+		for (j = 0; j < table->entry_count; j++) {
+			u8 *entry_ptr = table->entries;
+
+			entry_ptr += j * table->ops->unpacked_entry_size;
+			memset(p, 0, table->ops->packed_entry_size);
+			table->ops->packing(p, entry_ptr, PACK);
+			p += table->ops->packed_entry_size;
+		}
+		sja1105_table_write_crc(table_start, p);
+		p += 4;
+	}
+	/* Final header:
+	 * Block ID does not matter
+	 * Length of 0 marks that header is final
+	 * CRC will be replaced on-the-fly on "config upload"
+	 */
+	header.block_id = 0;
+	header.len = 0;
+	header.crc = 0xDEADBEEF;
+	memset(p, 0, SJA1105_SIZE_TABLE_HEADER);
+	sja1105_table_header_packing(p, &header, PACK);
+}
+
+size_t
+sja1105_static_config_get_length(const struct sja1105_static_config *config)
+{
+	unsigned int sum;
+	unsigned int header_count;
+	enum sja1105_blk_idx i;
+
+	/* Ending header */
+	header_count = 1;
+	sum = SJA1105_SIZE_DEVICE_ID;
+
+	/* Tables (headers and entries) */
+	for (i = 0; i < BLK_IDX_MAX; i++) {
+		const struct sja1105_table *table;
+
+		table = &config->tables[i];
+		if (table->entry_count)
+			header_count++;
+
+		sum += table->ops->packed_entry_size * table->entry_count;
+	}
+	/* Headers have an additional CRC at the end */
+	sum += header_count * (SJA1105_SIZE_TABLE_HEADER + 4);
+	/* Last header does not have an extra CRC because there is no data */
+	sum -= 4;
+
+	return sum;
+}
+
+/* Compatibility matrices */
+
+/* SJA1105E: First generation, no TTEthernet */
+struct sja1105_table_ops sja1105e_table_ops[BLK_IDX_MAX] = {
+	[BLK_IDX_L2_LOOKUP] = {
+		.packing = sja1105et_l2_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry),
+		.packed_entry_size = SJA1105ET_SIZE_L2_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_POLICING] = {
+		.packing = sja1105_l2_policing_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_POLICING_COUNT,
+	},
+	[BLK_IDX_VLAN_LOOKUP] = {
+		.packing = sja1105_vlan_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry),
+		.packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING] = {
+		.packing = sja1105_l2_forwarding_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT,
+	},
+	[BLK_IDX_MAC_CONFIG] = {
+		.packing = sja1105et_mac_config_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_mac_config_entry),
+		.packed_entry_size = SJA1105ET_SIZE_MAC_CONFIG_ENTRY,
+		.max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT,
+	},
+	[BLK_IDX_L2_LOOKUP_PARAMS] = {
+		.packing = sja1105et_l2_lookup_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry),
+		.packed_entry_size = SJA1105ET_SIZE_L2_LOOKUP_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING_PARAMS] = {
+		.packing = sja1105_l2_forwarding_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
+	},
+	[BLK_IDX_GENERAL_PARAMS] = {
+		.packing = sja1105et_general_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
+		.packed_entry_size = SJA1105ET_SIZE_GENERAL_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT,
+	},
+	[BLK_IDX_XMII_PARAMS] = {
+		.packing = sja1105_xmii_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry),
+		.packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT,
+	},
+};
+
+/* SJA1105T: First generation, TTEthernet */
+struct sja1105_table_ops sja1105t_table_ops[BLK_IDX_MAX] = {
+	[BLK_IDX_L2_LOOKUP] = {
+		.packing = sja1105et_l2_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry),
+		.packed_entry_size = SJA1105ET_SIZE_L2_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_POLICING] = {
+		.packing = sja1105_l2_policing_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_POLICING_COUNT,
+	},
+	[BLK_IDX_VLAN_LOOKUP] = {
+		.packing = sja1105_vlan_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry),
+		.packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING] = {
+		.packing = sja1105_l2_forwarding_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT,
+	},
+	[BLK_IDX_MAC_CONFIG] = {
+		.packing = sja1105et_mac_config_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_mac_config_entry),
+		.packed_entry_size = SJA1105ET_SIZE_MAC_CONFIG_ENTRY,
+		.max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT,
+	},
+	[BLK_IDX_L2_LOOKUP_PARAMS] = {
+		.packing = sja1105et_l2_lookup_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry),
+		.packed_entry_size = SJA1105ET_SIZE_L2_LOOKUP_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING_PARAMS] = {
+		.packing = sja1105_l2_forwarding_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
+	},
+	[BLK_IDX_GENERAL_PARAMS] = {
+		.packing = sja1105et_general_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
+		.packed_entry_size = SJA1105ET_SIZE_GENERAL_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT,
+	},
+	[BLK_IDX_XMII_PARAMS] = {
+		.packing = sja1105_xmii_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry),
+		.packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT,
+	},
+};
+
+/* SJA1105P: Second generation, no TTEthernet, no SGMII */
+struct sja1105_table_ops sja1105p_table_ops[BLK_IDX_MAX] = {
+	[BLK_IDX_L2_LOOKUP] = {
+		.packing = sja1105pqrs_l2_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_POLICING] = {
+		.packing = sja1105_l2_policing_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_POLICING_COUNT,
+	},
+	[BLK_IDX_VLAN_LOOKUP] = {
+		.packing = sja1105_vlan_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry),
+		.packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING] = {
+		.packing = sja1105_l2_forwarding_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT,
+	},
+	[BLK_IDX_MAC_CONFIG] = {
+		.packing = sja1105pqrs_mac_config_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_mac_config_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY,
+		.max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT,
+	},
+	[BLK_IDX_L2_LOOKUP_PARAMS] = {
+		.packing = sja1105pqrs_l2_lookup_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING_PARAMS] = {
+		.packing = sja1105_l2_forwarding_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
+	},
+	[BLK_IDX_GENERAL_PARAMS] = {
+		.packing = sja1105pqrs_general_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT,
+	},
+	[BLK_IDX_XMII_PARAMS] = {
+		.packing = sja1105_xmii_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry),
+		.packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT,
+	},
+};
+
+/* SJA1105Q: Second generation, TTEthernet, no SGMII */
+struct sja1105_table_ops sja1105q_table_ops[BLK_IDX_MAX] = {
+	[BLK_IDX_L2_LOOKUP] = {
+		.packing = sja1105pqrs_l2_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_POLICING] = {
+		.packing = sja1105_l2_policing_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_POLICING_COUNT,
+	},
+	[BLK_IDX_VLAN_LOOKUP] = {
+		.packing = sja1105_vlan_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry),
+		.packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING] = {
+		.packing = sja1105_l2_forwarding_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT,
+	},
+	[BLK_IDX_MAC_CONFIG] = {
+		.packing = sja1105pqrs_mac_config_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_mac_config_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY,
+		.max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT,
+	},
+	[BLK_IDX_L2_LOOKUP_PARAMS] = {
+		.packing = sja1105pqrs_l2_lookup_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING_PARAMS] = {
+		.packing = sja1105_l2_forwarding_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
+	},
+	[BLK_IDX_GENERAL_PARAMS] = {
+		.packing = sja1105pqrs_general_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT,
+	},
+	[BLK_IDX_XMII_PARAMS] = {
+		.packing = sja1105_xmii_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry),
+		.packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT,
+	},
+};
+
+/* SJA1105R: Second generation, no TTEthernet, SGMII */
+struct sja1105_table_ops sja1105r_table_ops[BLK_IDX_MAX] = {
+	[BLK_IDX_L2_LOOKUP] = {
+		.packing = sja1105pqrs_l2_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_POLICING] = {
+		.packing = sja1105_l2_policing_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_POLICING_COUNT,
+	},
+	[BLK_IDX_VLAN_LOOKUP] = {
+		.packing = sja1105_vlan_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry),
+		.packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING] = {
+		.packing = sja1105_l2_forwarding_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT,
+	},
+	[BLK_IDX_MAC_CONFIG] = {
+		.packing = sja1105pqrs_mac_config_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_mac_config_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY,
+		.max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT,
+	},
+	[BLK_IDX_L2_LOOKUP_PARAMS] = {
+		.packing = sja1105pqrs_l2_lookup_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING_PARAMS] = {
+		.packing = sja1105_l2_forwarding_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
+	},
+	[BLK_IDX_GENERAL_PARAMS] = {
+		.packing = sja1105pqrs_general_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT,
+	},
+	[BLK_IDX_XMII_PARAMS] = {
+		.packing = sja1105_xmii_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry),
+		.packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT,
+	},
+};
+
+/* SJA1105S: Second generation, TTEthernet, SGMII */
+struct sja1105_table_ops sja1105s_table_ops[BLK_IDX_MAX] = {
+	[BLK_IDX_L2_LOOKUP] = {
+		.packing = sja1105pqrs_l2_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_POLICING] = {
+		.packing = sja1105_l2_policing_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_POLICING_COUNT,
+	},
+	[BLK_IDX_VLAN_LOOKUP] = {
+		.packing = sja1105_vlan_lookup_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry),
+		.packed_entry_size = SJA1105_SIZE_VLAN_LOOKUP_ENTRY,
+		.max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING] = {
+		.packing = sja1105_l2_forwarding_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_COUNT,
+	},
+	[BLK_IDX_MAC_CONFIG] = {
+		.packing = sja1105pqrs_mac_config_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_mac_config_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY,
+		.max_entry_count = SJA1105_MAX_MAC_CONFIG_COUNT,
+	},
+	[BLK_IDX_L2_LOOKUP_PARAMS] = {
+		.packing = sja1105pqrs_l2_lookup_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT,
+	},
+	[BLK_IDX_L2_FORWARDING_PARAMS] = {
+		.packing = sja1105_l2_forwarding_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry),
+		.packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT,
+	},
+	[BLK_IDX_GENERAL_PARAMS] = {
+		.packing = sja1105pqrs_general_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_general_params_entry),
+		.packed_entry_size = SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT,
+	},
+	[BLK_IDX_XMII_PARAMS] = {
+		.packing = sja1105_xmii_params_entry_packing,
+		.unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry),
+		.packed_entry_size = SJA1105_SIZE_XMII_PARAMS_ENTRY,
+		.max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT,
+	},
+};
+
+int sja1105_static_config_init(struct sja1105_static_config *config,
+			       const struct sja1105_table_ops *static_ops,
+			       u64 device_id)
+{
+	enum sja1105_blk_idx i;
+
+	*config = (struct sja1105_static_config) {0};
+
+	/* Transfer static_ops array from priv into per-table ops
+	 * for handier access
+	 */
+	for (i = 0; i < BLK_IDX_MAX; i++)
+		config->tables[i].ops = &static_ops[i];
+
+	config->device_id = device_id;
+	return 0;
+}
+
+void sja1105_static_config_free(struct sja1105_static_config *config)
+{
+	enum sja1105_blk_idx i;
+
+	for (i = 0; i < BLK_IDX_MAX; i++) {
+		if (config->tables[i].entry_count) {
+			kfree(config->tables[i].entries);
+			config->tables[i].entry_count = 0;
+		}
+	}
+}
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h
new file mode 100644
index 000000000000..7b0a02fe3147
--- /dev/null
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.h
@@ -0,0 +1,250 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2016-2018, NXP Semiconductors
+ * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#ifndef _SJA1105_STATIC_CONFIG_H
+#define _SJA1105_STATIC_CONFIG_H
+
+#include <linux/packing.h>
+#include <linux/types.h>
+#include <asm/types.h>
+
+#define SJA1105_SIZE_DEVICE_ID				4
+#define SJA1105_SIZE_TABLE_HEADER			12
+#define SJA1105_SIZE_L2_POLICING_ENTRY			8
+#define SJA1105_SIZE_VLAN_LOOKUP_ENTRY			8
+#define SJA1105_SIZE_L2_FORWARDING_ENTRY		8
+#define SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY		12
+#define SJA1105_SIZE_XMII_PARAMS_ENTRY			4
+#define SJA1105ET_SIZE_L2_LOOKUP_ENTRY			12
+#define SJA1105ET_SIZE_MAC_CONFIG_ENTRY			28
+#define SJA1105ET_SIZE_L2_LOOKUP_PARAMS_ENTRY		4
+#define SJA1105ET_SIZE_GENERAL_PARAMS_ENTRY		40
+#define SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY		20
+#define SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY		32
+#define SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY		16
+#define SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY		44
+
+/* UM10944.pdf Page 11, Table 2. Configuration Blocks */
+enum {
+	BLKID_L2_LOOKUP					= 0x05,
+	BLKID_L2_POLICING				= 0x06,
+	BLKID_VLAN_LOOKUP				= 0x07,
+	BLKID_L2_FORWARDING				= 0x08,
+	BLKID_MAC_CONFIG				= 0x09,
+	BLKID_L2_LOOKUP_PARAMS				= 0x0D,
+	BLKID_L2_FORWARDING_PARAMS			= 0x0E,
+	BLKID_GENERAL_PARAMS				= 0x11,
+	BLKID_XMII_PARAMS				= 0x4E,
+};
+
+enum sja1105_blk_idx {
+	BLK_IDX_L2_LOOKUP = 0,
+	BLK_IDX_L2_POLICING,
+	BLK_IDX_VLAN_LOOKUP,
+	BLK_IDX_L2_FORWARDING,
+	BLK_IDX_MAC_CONFIG,
+	BLK_IDX_L2_LOOKUP_PARAMS,
+	BLK_IDX_L2_FORWARDING_PARAMS,
+	BLK_IDX_GENERAL_PARAMS,
+	BLK_IDX_XMII_PARAMS,
+	BLK_IDX_MAX,
+	/* Fake block indices that are only valid for dynamic access */
+	BLK_IDX_MGMT_ROUTE,
+	BLK_IDX_MAX_DYN,
+	BLK_IDX_INVAL = -1,
+};
+
+#define SJA1105_MAX_L2_LOOKUP_COUNT			1024
+#define SJA1105_MAX_L2_POLICING_COUNT			45
+#define SJA1105_MAX_VLAN_LOOKUP_COUNT			4096
+#define SJA1105_MAX_L2_FORWARDING_COUNT			13
+#define SJA1105_MAX_MAC_CONFIG_COUNT			5
+#define SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT		1
+#define SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT		1
+#define SJA1105_MAX_GENERAL_PARAMS_COUNT		1
+#define SJA1105_MAX_XMII_PARAMS_COUNT			1
+
+#define SJA1105_MAX_FRAME_MEMORY			929
+
+#define SJA1105E_DEVICE_ID				0x9C00000Cull
+#define SJA1105T_DEVICE_ID				0x9E00030Eull
+#define SJA1105PR_DEVICE_ID				0xAF00030Eull
+#define SJA1105QS_DEVICE_ID				0xAE00030Eull
+
+#define SJA1105ET_PART_NO				0x9A83
+#define SJA1105P_PART_NO				0x9A84
+#define SJA1105Q_PART_NO				0x9A85
+#define SJA1105R_PART_NO				0x9A86
+#define SJA1105S_PART_NO				0x9A87
+
+struct sja1105_general_params_entry {
+	u64 vllupformat;
+	u64 mirr_ptacu;
+	u64 switchid;
+	u64 hostprio;
+	u64 mac_fltres1;
+	u64 mac_fltres0;
+	u64 mac_flt1;
+	u64 mac_flt0;
+	u64 incl_srcpt1;
+	u64 incl_srcpt0;
+	u64 send_meta1;
+	u64 send_meta0;
+	u64 casc_port;
+	u64 host_port;
+	u64 mirr_port;
+	u64 vlmarker;
+	u64 vlmask;
+	u64 tpid;
+	u64 ignore2stf;
+	u64 tpid2;
+	/* P/Q/R/S only */
+	u64 queue_ts;
+	u64 egrmirrvid;
+	u64 egrmirrpcp;
+	u64 egrmirrdei;
+	u64 replay_port;
+};
+
+struct sja1105_vlan_lookup_entry {
+	u64 ving_mirr;
+	u64 vegr_mirr;
+	u64 vmemb_port;
+	u64 vlan_bc;
+	u64 tag_port;
+	u64 vlanid;
+};
+
+struct sja1105_l2_lookup_entry {
+	u64 vlanid;
+	u64 macaddr;
+	u64 destports;
+	u64 enfport;
+	u64 index;
+};
+
+struct sja1105_l2_lookup_params_entry {
+	u64 maxage;          /* Shared */
+	u64 dyn_tbsz;        /* E/T only */
+	u64 poly;            /* E/T only */
+	u64 shared_learn;    /* Shared */
+	u64 no_enf_hostprt;  /* Shared */
+	u64 no_mgmt_learn;   /* Shared */
+};
+
+struct sja1105_l2_forwarding_entry {
+	u64 bc_domain;
+	u64 reach_port;
+	u64 fl_domain;
+	u64 vlan_pmap[8];
+};
+
+struct sja1105_l2_forwarding_params_entry {
+	u64 max_dynp;
+	u64 part_spc[8];
+};
+
+struct sja1105_l2_policing_entry {
+	u64 sharindx;
+	u64 smax;
+	u64 rate;
+	u64 maxlen;
+	u64 partition;
+};
+
+struct sja1105_mac_config_entry {
+	u64 top[8];
+	u64 base[8];
+	u64 enabled[8];
+	u64 ifg;
+	u64 speed;
+	u64 tp_delin;
+	u64 tp_delout;
+	u64 maxage;
+	u64 vlanprio;
+	u64 vlanid;
+	u64 ing_mirr;
+	u64 egr_mirr;
+	u64 drpnona664;
+	u64 drpdtag;
+	u64 drpuntag;
+	u64 retag;
+	u64 dyn_learn;
+	u64 egress;
+	u64 ingress;
+};
+
+struct sja1105_xmii_params_entry {
+	u64 phy_mac[5];
+	u64 xmii_mode[5];
+};
+
+struct sja1105_table_header {
+	u64 block_id;
+	u64 len;
+	u64 crc;
+};
+
+struct sja1105_table_ops {
+	size_t (*packing)(void *buf, void *entry_ptr, enum packing_op op);
+	size_t unpacked_entry_size;
+	size_t packed_entry_size;
+	size_t max_entry_count;
+};
+
+struct sja1105_table {
+	const struct sja1105_table_ops *ops;
+	size_t entry_count;
+	void *entries;
+};
+
+struct sja1105_static_config {
+	u64 device_id;
+	struct sja1105_table tables[BLK_IDX_MAX];
+};
+
+extern struct sja1105_table_ops sja1105e_table_ops[BLK_IDX_MAX];
+extern struct sja1105_table_ops sja1105t_table_ops[BLK_IDX_MAX];
+extern struct sja1105_table_ops sja1105p_table_ops[BLK_IDX_MAX];
+extern struct sja1105_table_ops sja1105q_table_ops[BLK_IDX_MAX];
+extern struct sja1105_table_ops sja1105r_table_ops[BLK_IDX_MAX];
+extern struct sja1105_table_ops sja1105s_table_ops[BLK_IDX_MAX];
+
+size_t sja1105_table_header_packing(void *buf, void *hdr, enum packing_op op);
+void
+sja1105_table_header_pack_with_crc(void *buf, struct sja1105_table_header *hdr);
+size_t
+sja1105_static_config_get_length(const struct sja1105_static_config *config);
+
+typedef enum {
+	SJA1105_CONFIG_OK = 0,
+	SJA1105_MISSING_L2_POLICING_TABLE,
+	SJA1105_MISSING_L2_FORWARDING_TABLE,
+	SJA1105_MISSING_L2_FORWARDING_PARAMS_TABLE,
+	SJA1105_MISSING_GENERAL_PARAMS_TABLE,
+	SJA1105_MISSING_VLAN_TABLE,
+	SJA1105_MISSING_XMII_TABLE,
+	SJA1105_MISSING_MAC_TABLE,
+	SJA1105_OVERCOMMITTED_FRAME_MEMORY,
+} sja1105_config_valid_t;
+
+extern const char *sja1105_static_config_error_msg[];
+
+sja1105_config_valid_t
+sja1105_static_config_check_valid(const struct sja1105_static_config *config);
+void
+sja1105_static_config_pack(void *buf, struct sja1105_static_config *config);
+int sja1105_static_config_init(struct sja1105_static_config *config,
+			       const struct sja1105_table_ops *static_ops,
+			       u64 device_id);
+void sja1105_static_config_free(struct sja1105_static_config *config);
+
+u32 sja1105_crc32(const void *buf, size_t len);
+
+void sja1105_pack(void *buf, const u64 *val, int start, int end, size_t len);
+void sja1105_unpack(const void *buf, u64 *val, int start, int end, size_t len);
+void sja1105_packing(void *buf, u64 *val, int start, int end,
+		     size_t len, enum packing_op op);
+
+#endif
diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h
new file mode 100644
index 000000000000..30559d1d0e1b
--- /dev/null
+++ b/include/linux/dsa/sja1105.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+
+/* Included by drivers/net/dsa/sja1105/sja1105.h */
+
+#ifndef _NET_DSA_SJA1105_H
+#define _NET_DSA_SJA1105_H
+
+/* The switch can only be convinced to stay in unmanaged mode and not trap any
+ * link-local traffic by actually telling it to filter frames sent at the
+ * 00:00:00:00:00:00 destination MAC.
+ */
+#define SJA1105_LINKLOCAL_FILTER_A		0x000000000000ull
+#define SJA1105_LINKLOCAL_FILTER_A_MASK		0xFFFFFFFFFFFFull
+#define SJA1105_LINKLOCAL_FILTER_B		0x000000000000ull
+#define SJA1105_LINKLOCAL_FILTER_B_MASK		0xFFFFFFFFFFFFull
+
+#endif /* _NET_DSA_SJA1105_H */
-- 
cgit v1.2.3


From bf5bc3ce8a8f32a0d45b6820ede8f9fc3e9c23df Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Thu, 2 May 2019 23:23:33 +0300
Subject: ether: Add dedicated Ethertype for pseudo-802.1Q DSA tagging

There are two possible utilizations so far:

- Switch devices that don't support a native insertion/extraction header
  on the CPU port may still enjoy the benefits of port isolation with a
  custom VLAN tag.

  For this, they need to have a customizable TPID in hardware and a new
  Ethertype to distinguish between real 802.1Q traffic and the private
  tags used for port separation.

- Switches that don't support the deactivation of VLAN awareness, but
  still want to have a mode in which they accept all traffic, including
  frames that are tagged with a VLAN not configured on their ports, may
  use this as a fake to trick the hardware into thinking that the TPID
  for VLAN is something other than 0x8100.

What follows after the ETH_P_DSA_8021Q EtherType is a regular VLAN
header (TCI), however there is no other EtherType that can be used for
this purpose and doesn't already have a well-defined meaning.
ETH_P_8021AD, ETH_P_QINQ1, ETH_P_QINQ2 and ETH_P_QINQ3 expect that
another follow-up VLAN tag is present, which is not the case here.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Suggested-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_ether.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
index 3a45b4ad71a3..3158ba672b72 100644
--- a/include/uapi/linux/if_ether.h
+++ b/include/uapi/linux/if_ether.h
@@ -109,6 +109,7 @@
 #define ETH_P_QINQ2	0x9200		/* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
 #define ETH_P_QINQ3	0x9300		/* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */
 #define ETH_P_EDSA	0xDADA		/* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */
+#define ETH_P_DSA_8021Q	0xDADB		/* Fake VLAN Header for DSA [ NOT AN OFFICIALLY REGISTERED ID ] */
 #define ETH_P_IFE	0xED3E		/* ForCES inter-FE LFB type */
 #define ETH_P_AF_IUCV   0xFBFB		/* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */
 
-- 
cgit v1.2.3


From 6666cebc5e306f49a25bd20aa8c1cb8ef8950df5 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Thu, 2 May 2019 23:23:34 +0300
Subject: net: dsa: sja1105: Add support for VLAN operations

VLAN filtering cannot be properly disabled in SJA1105. So in order to
emulate the "no VLAN awareness" behavior (not dropping traffic that is
tagged with a VID that isn't configured on the port), we need to hack
another switch feature: programmable TPID (which is 0x8100 for 802.1Q).
We are reprogramming the TPID to a bogus value which leaves the switch
thinking that all traffic is untagged, and therefore accepts it.

Under a vlan_filtering bridge, the proper TPID of ETH_P_8021Q is
installed again, and the switch starts identifying 802.1Q-tagged
traffic.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c          | 248 +++++++++++++++++++++++-
 drivers/net/dsa/sja1105/sja1105_static_config.c |  38 ++++
 drivers/net/dsa/sja1105/sja1105_static_config.h |   3 +
 include/linux/dsa/sja1105.h                     |   4 +
 4 files changed, 291 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index d27b9c178cba..f7b1525b388a 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -251,6 +251,13 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv)
 	table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP];
 
 	/* The static VLAN table will only contain the initial pvid of 0.
+	 * All other VLANs are to be configured through dynamic entries,
+	 * and kept in the static configuration table as backing memory.
+	 * The pvid of 0 is sufficient to pass traffic while the ports are
+	 * standalone and when vlan_filtering is disabled. When filtering
+	 * gets enabled, the switchdev core sets up the VLAN ID 1 and sets
+	 * it as the new pvid. Actually 'pvid 1' still comes up in 'bridge
+	 * vlan' even when vlan_filtering is off, but it has no effect.
 	 */
 	if (table->entry_count) {
 		kfree(table->entries);
@@ -391,8 +398,11 @@ static int sja1105_init_general_params(struct sja1105_private *priv)
 		.vlmask = 0,
 		/* Only update correctionField for 1-step PTP (L2 transport) */
 		.ignore2stf = 0,
-		.tpid = ETH_P_8021Q,
-		.tpid2 = ETH_P_8021Q,
+		/* Forcefully disable VLAN filtering by telling
+		 * the switch that VLAN has a different EtherType.
+		 */
+		.tpid = ETH_P_SJA1105,
+		.tpid2 = ETH_P_SJA1105,
 	};
 	struct sja1105_table *table;
 	int i;
@@ -954,12 +964,233 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port,
 	sja1105_bridge_member(ds, port, br, false);
 }
 
+/* For situations where we need to change a setting at runtime that is only
+ * available through the static configuration, resetting the switch in order
+ * to upload the new static config is unavoidable. Back up the settings we
+ * modify at runtime (currently only MAC) and restore them after uploading,
+ * such that this operation is relatively seamless.
+ */
+static int sja1105_static_config_reload(struct sja1105_private *priv)
+{
+	struct sja1105_mac_config_entry *mac;
+	int speed_mbps[SJA1105_NUM_PORTS];
+	int rc, i;
+
+	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
+
+	/* Back up settings changed by sja1105_adjust_port_config and
+	 * and restore their defaults.
+	 */
+	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+		speed_mbps[i] = sja1105_speed[mac[i].speed];
+		mac[i].speed = SJA1105_SPEED_AUTO;
+	}
+
+	/* Reset switch and send updated static configuration */
+	rc = sja1105_static_config_upload(priv);
+	if (rc < 0)
+		goto out;
+
+	/* Configure the CGU (PLLs) for MII and RMII PHYs.
+	 * For these interfaces there is no dynamic configuration
+	 * needed, since PLLs have same settings at all speeds.
+	 */
+	rc = sja1105_clocking_setup(priv);
+	if (rc < 0)
+		goto out;
+
+	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+		bool enabled = (speed_mbps[i] != 0);
+
+		rc = sja1105_adjust_port_config(priv, i, speed_mbps[i],
+						enabled);
+		if (rc < 0)
+			goto out;
+	}
+out:
+	return rc;
+}
+
+/* The TPID setting belongs to the General Parameters table,
+ * which can only be partially reconfigured at runtime (and not the TPID).
+ * So a switch reset is required.
+ */
+static int sja1105_change_tpid(struct sja1105_private *priv,
+			       u16 tpid, u16 tpid2)
+{
+	struct sja1105_general_params_entry *general_params;
+	struct sja1105_table *table;
+
+	table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
+	general_params = table->entries;
+	general_params->tpid = tpid;
+	general_params->tpid2 = tpid2;
+	return sja1105_static_config_reload(priv);
+}
+
+static int sja1105_pvid_apply(struct sja1105_private *priv, int port, u16 pvid)
+{
+	struct sja1105_mac_config_entry *mac;
+
+	mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
+
+	mac[port].vlanid = pvid;
+
+	return sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG, port,
+					   &mac[port], true);
+}
+
+static int sja1105_is_vlan_configured(struct sja1105_private *priv, u16 vid)
+{
+	struct sja1105_vlan_lookup_entry *vlan;
+	int count, i;
+
+	vlan = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entries;
+	count = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entry_count;
+
+	for (i = 0; i < count; i++)
+		if (vlan[i].vlanid == vid)
+			return i;
+
+	/* Return an invalid entry index if not found */
+	return -1;
+}
+
+static int sja1105_vlan_apply(struct sja1105_private *priv, int port, u16 vid,
+			      bool enabled, bool untagged)
+{
+	struct sja1105_vlan_lookup_entry *vlan;
+	struct sja1105_table *table;
+	bool keep = true;
+	int match, rc;
+
+	table = &priv->static_config.tables[BLK_IDX_VLAN_LOOKUP];
+
+	match = sja1105_is_vlan_configured(priv, vid);
+	if (match < 0) {
+		/* Can't delete a missing entry. */
+		if (!enabled)
+			return 0;
+		rc = sja1105_table_resize(table, table->entry_count + 1);
+		if (rc)
+			return rc;
+		match = table->entry_count - 1;
+	}
+	/* Assign pointer after the resize (it's new memory) */
+	vlan = table->entries;
+	vlan[match].vlanid = vid;
+	if (enabled) {
+		vlan[match].vlan_bc |= BIT(port);
+		vlan[match].vmemb_port |= BIT(port);
+	} else {
+		vlan[match].vlan_bc &= ~BIT(port);
+		vlan[match].vmemb_port &= ~BIT(port);
+	}
+	/* Also unset tag_port if removing this VLAN was requested,
+	 * just so we don't have a confusing bitmap (no practical purpose).
+	 */
+	if (untagged || !enabled)
+		vlan[match].tag_port &= ~BIT(port);
+	else
+		vlan[match].tag_port |= BIT(port);
+	/* If there's no port left as member of this VLAN,
+	 * it's time for it to go.
+	 */
+	if (!vlan[match].vmemb_port)
+		keep = false;
+
+	dev_dbg(priv->ds->dev,
+		"%s: port %d, vid %llu, broadcast domain 0x%llx, "
+		"port members 0x%llx, tagged ports 0x%llx, keep %d\n",
+		__func__, port, vlan[match].vlanid, vlan[match].vlan_bc,
+		vlan[match].vmemb_port, vlan[match].tag_port, keep);
+
+	rc = sja1105_dynamic_config_write(priv, BLK_IDX_VLAN_LOOKUP, vid,
+					  &vlan[match], keep);
+	if (rc < 0)
+		return rc;
+
+	if (!keep)
+		return sja1105_table_delete_entry(table, match);
+
+	return 0;
+}
+
 static enum dsa_tag_protocol
 sja1105_get_tag_protocol(struct dsa_switch *ds, int port)
 {
 	return DSA_TAG_PROTO_NONE;
 }
 
+/* This callback needs to be present */
+static int sja1105_vlan_prepare(struct dsa_switch *ds, int port,
+				const struct switchdev_obj_port_vlan *vlan)
+{
+	return 0;
+}
+
+static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
+{
+	struct sja1105_private *priv = ds->priv;
+	int rc;
+
+	if (enabled)
+		/* Enable VLAN filtering. */
+		rc = sja1105_change_tpid(priv, ETH_P_8021Q, ETH_P_8021AD);
+	else
+		/* Disable VLAN filtering. */
+		rc = sja1105_change_tpid(priv, ETH_P_SJA1105, ETH_P_SJA1105);
+	if (rc)
+		dev_err(ds->dev, "Failed to change VLAN Ethertype\n");
+
+	return rc;
+}
+
+static void sja1105_vlan_add(struct dsa_switch *ds, int port,
+			     const struct switchdev_obj_port_vlan *vlan)
+{
+	struct sja1105_private *priv = ds->priv;
+	u16 vid;
+	int rc;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		rc = sja1105_vlan_apply(priv, port, vid, true, vlan->flags &
+					BRIDGE_VLAN_INFO_UNTAGGED);
+		if (rc < 0) {
+			dev_err(ds->dev, "Failed to add VLAN %d to port %d: %d\n",
+				vid, port, rc);
+			return;
+		}
+		if (vlan->flags & BRIDGE_VLAN_INFO_PVID) {
+			rc = sja1105_pvid_apply(ds->priv, port, vid);
+			if (rc < 0) {
+				dev_err(ds->dev, "Failed to set pvid %d on port %d: %d\n",
+					vid, port, rc);
+				return;
+			}
+		}
+	}
+}
+
+static int sja1105_vlan_del(struct dsa_switch *ds, int port,
+			    const struct switchdev_obj_port_vlan *vlan)
+{
+	struct sja1105_private *priv = ds->priv;
+	u16 vid;
+	int rc;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		rc = sja1105_vlan_apply(priv, port, vid, false, vlan->flags &
+					BRIDGE_VLAN_INFO_UNTAGGED);
+		if (rc < 0) {
+			dev_err(ds->dev, "Failed to remove VLAN %d from port %d: %d\n",
+				vid, port, rc);
+			return rc;
+		}
+	}
+	return 0;
+}
+
 /* The programming model for the SJA1105 switch is "all-at-once" via static
  * configuration tables. Some of these can be dynamically modified at runtime,
  * but not the xMII mode parameters table.
@@ -1005,6 +1236,15 @@ static int sja1105_setup(struct dsa_switch *ds)
 		dev_err(ds->dev, "Failed to configure MII clocking: %d\n", rc);
 		return rc;
 	}
+	/* On SJA1105, VLAN filtering per se is always enabled in hardware.
+	 * The only thing we can do to disable it is lie about what the 802.1Q
+	 * EtherType is.
+	 * So it will still try to apply VLAN filtering, but all ingress
+	 * traffic (except frames received with EtherType of ETH_P_SJA1105)
+	 * will be internally tagged with a distorted VLAN header where the
+	 * TPID is ETH_P_SJA1105, and the VLAN ID is the port pvid.
+	 */
+	ds->vlan_filtering_is_global = true;
 
 	return 0;
 }
@@ -1018,6 +1258,10 @@ static const struct dsa_switch_ops sja1105_switch_ops = {
 	.port_fdb_del		= sja1105_fdb_del,
 	.port_bridge_join	= sja1105_bridge_join,
 	.port_bridge_leave	= sja1105_bridge_leave,
+	.port_vlan_prepare	= sja1105_vlan_prepare,
+	.port_vlan_filtering	= sja1105_vlan_filtering,
+	.port_vlan_add		= sja1105_vlan_add,
+	.port_vlan_del		= sja1105_vlan_del,
 	.port_mdb_prepare	= sja1105_mdb_prepare,
 	.port_mdb_add		= sja1105_mdb_add,
 	.port_mdb_del		= sja1105_mdb_del,
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c
index 84ee623c6336..b3c992b0abb0 100644
--- a/drivers/net/dsa/sja1105/sja1105_static_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.c
@@ -947,3 +947,41 @@ void sja1105_static_config_free(struct sja1105_static_config *config)
 		}
 	}
 }
+
+int sja1105_table_delete_entry(struct sja1105_table *table, int i)
+{
+	size_t entry_size = table->ops->unpacked_entry_size;
+	u8 *entries = table->entries;
+
+	if (i > table->entry_count)
+		return -ERANGE;
+
+	memmove(entries + i * entry_size, entries + (i + 1) * entry_size,
+		(table->entry_count - i) * entry_size);
+
+	table->entry_count--;
+
+	return 0;
+}
+
+/* No pointers to table->entries should be kept when this is called. */
+int sja1105_table_resize(struct sja1105_table *table, size_t new_count)
+{
+	size_t entry_size = table->ops->unpacked_entry_size;
+	void *new_entries, *old_entries = table->entries;
+
+	if (new_count > table->ops->max_entry_count)
+		return -ERANGE;
+
+	new_entries = kcalloc(new_count, entry_size, GFP_KERNEL);
+	if (!new_entries)
+		return -ENOMEM;
+
+	memcpy(new_entries, old_entries, min(new_count, table->entry_count) *
+		entry_size);
+
+	table->entries = new_entries;
+	table->entry_count = new_count;
+	kfree(old_entries);
+	return 0;
+}
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h
index 7b0a02fe3147..069ca8fd059c 100644
--- a/drivers/net/dsa/sja1105/sja1105_static_config.h
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.h
@@ -240,6 +240,9 @@ int sja1105_static_config_init(struct sja1105_static_config *config,
 			       u64 device_id);
 void sja1105_static_config_free(struct sja1105_static_config *config);
 
+int sja1105_table_delete_entry(struct sja1105_table *table, int i);
+int sja1105_table_resize(struct sja1105_table *table, size_t new_count);
+
 u32 sja1105_crc32(const void *buf, size_t len);
 
 void sja1105_pack(void *buf, const u64 *val, int start, int end, size_t len);
diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h
index 30559d1d0e1b..abf3977e34fd 100644
--- a/include/linux/dsa/sja1105.h
+++ b/include/linux/dsa/sja1105.h
@@ -7,6 +7,10 @@
 #ifndef _NET_DSA_SJA1105_H
 #define _NET_DSA_SJA1105_H
 
+#include <linux/etherdevice.h>
+
+#define ETH_P_SJA1105				ETH_P_DSA_8021Q
+
 /* The switch can only be convinced to stay in unmanaged mode and not trap any
  * link-local traffic by actually telling it to filter frames sent at the
  * 00:00:00:00:00:00 destination MAC.
-- 
cgit v1.2.3


From a27415decd84dac124c6185f1184b6c779d0a5ab Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 1 May 2019 00:10:50 +0200
Subject: net: dsa: mv88e6xxx: Pass interrupt number in platform data

Allow an interrupt number to be passed in the platform data. The
driver will then use it if not zero, otherwise it will poll for
interrupts.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c        | 13 +++++++++----
 include/linux/platform_data/mv88e6xxx.h |  1 +
 2 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 46020fe1b5e7..bad30be699bf 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -4894,12 +4894,17 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	if (err)
 		goto out;
 
-	chip->irq = of_irq_get(np, 0);
-	if (chip->irq == -EPROBE_DEFER) {
-		err = chip->irq;
-		goto out;
+	if (np) {
+		chip->irq = of_irq_get(np, 0);
+		if (chip->irq == -EPROBE_DEFER) {
+			err = chip->irq;
+			goto out;
+		}
 	}
 
+	if (pdata)
+		chip->irq = pdata->irq;
+
 	/* Has to be performed before the MDIO bus is created, because
 	 * the PHYs will link their interrupts to these interrupt
 	 * controllers
diff --git a/include/linux/platform_data/mv88e6xxx.h b/include/linux/platform_data/mv88e6xxx.h
index 963730b44aea..21452a9365e1 100644
--- a/include/linux/platform_data/mv88e6xxx.h
+++ b/include/linux/platform_data/mv88e6xxx.h
@@ -13,6 +13,7 @@ struct dsa_mv88e6xxx_pdata {
 	unsigned int enabled_ports;
 	struct net_device *netdev;
 	u32 eeprom_len;
+	int irq;
 };
 
 #endif
-- 
cgit v1.2.3


From 141b6b2ad75d92770240de3af98d55c41ce7cd18 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Wed, 1 May 2019 19:56:59 -0700
Subject: net: add a generic tracepoint for TX queue timeout

Although devlink health report does a nice job on reporting TX
timeout and other NIC errors, unfortunately it requires drivers
to support it but currently only mlx5 has implemented it.
Before other drivers could catch up, it is useful to have a
generic tracepoint to monitor this kind of TX timeout. We have
been suffering TX timeout with different drivers, we plan to
start to monitor it with rasdaemon which just needs a new tracepoint.

Sample output:

  ksoftirqd/1-16    [001] ..s2   144.043173: net_dev_xmit_timeout: dev=ens3 driver=e1000 queue=0

Cc: Eran Ben Elisha <eranbe@mellanox.com>
Cc: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/net.h | 23 +++++++++++++++++++++++
 net/sched/sch_generic.c    |  2 ++
 2 files changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 1efd7d9b25fe..2399073c3afc 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -95,6 +95,29 @@ TRACE_EVENT(net_dev_xmit,
 		__get_str(name), __entry->skbaddr, __entry->len, __entry->rc)
 );
 
+TRACE_EVENT(net_dev_xmit_timeout,
+
+	TP_PROTO(struct net_device *dev,
+		 int queue_index),
+
+	TP_ARGS(dev, queue_index),
+
+	TP_STRUCT__entry(
+		__string(	name,		dev->name	)
+		__string(	driver,		netdev_drivername(dev))
+		__field(	int,		queue_index	)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, dev->name);
+		__assign_str(driver, netdev_drivername(dev));
+		__entry->queue_index = queue_index;
+	),
+
+	TP_printk("dev=%s driver=%s queue=%d",
+		__get_str(name), __get_str(driver), __entry->queue_index)
+);
+
 DECLARE_EVENT_CLASS(net_dev_template,
 
 	TP_PROTO(struct sk_buff *skb),
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 848aab3693bd..cce1e9ee85af 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -32,6 +32,7 @@
 #include <net/pkt_sched.h>
 #include <net/dst.h>
 #include <trace/events/qdisc.h>
+#include <trace/events/net.h>
 #include <net/xfrm.h>
 
 /* Qdisc to use by default */
@@ -441,6 +442,7 @@ static void dev_watchdog(struct timer_list *t)
 			}
 
 			if (some_queue_timedout) {
+				trace_net_dev_xmit_timeout(dev, i);
 				WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
 				       dev->name, netdev_drivername(dev), i);
 				dev->netdev_ops->ndo_tx_timeout(dev);
-- 
cgit v1.2.3


From 22c0ef6b1475aef4765efc4aa764b8580018123c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 1 May 2019 21:34:43 +0200
Subject: net: phy: improve pause handling

When probing the phy device we set sym and asym pause in the "supported"
bitmap (unless the PHY tells us otherwise). However we don't know yet
whether the MAC supports pause. Simply copying phy->supported to
phy->advertising will trigger advertising pause, and that's not
what we want. Therefore add phy_advertise_supported() that copies all
modes but doesn't touch the pause bits.

In phy_support_(a)sym_pause we shouldn't set any bits in the supported
bitmap because we may set a bit the PHY intentionally disabled.
Effective pause support should be the AND-combined PHY and MAC pause
capabilities. If the MAC supports everything, then it's only relevant
what the PHY supports. If MAC supports sym pause only, then we have to
clear the asym bit in phydev->supported.
Copy the pause flags only and don't touch the modes, because a driver
may have intentionally removed a mode from phydev->advertising.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/fixed_phy.c  |  2 +-
 drivers/net/phy/phy-core.c   |  2 +-
 drivers/net/phy/phy_device.c | 36 +++++++++++++++++++++++++++++-------
 include/linux/phy.h          |  1 +
 4 files changed, 32 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 1acd8bfdb3bc..3ffe46df249e 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -301,7 +301,7 @@ static struct phy_device *__fixed_phy_register(unsigned int irq,
 				 phy->supported);
 	}
 
-	linkmode_copy(phy->advertising, phy->supported);
+	phy_advertise_supported(phy);
 
 	ret = phy_device_register(phy);
 	if (ret) {
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 12ce671020a5..3daf0214a242 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -228,7 +228,7 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed)
 	if (err)
 		return err;
 
-	linkmode_copy(phydev->advertising, phydev->supported);
+	phy_advertise_supported(phydev);
 
 	return 0;
 }
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 2a2aaa5f3e74..068ab750c9ce 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1985,10 +1985,35 @@ EXPORT_SYMBOL(genphy_loopback);
 void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode)
 {
 	linkmode_clear_bit(link_mode, phydev->supported);
-	linkmode_copy(phydev->advertising, phydev->supported);
+	phy_advertise_supported(phydev);
 }
 EXPORT_SYMBOL(phy_remove_link_mode);
 
+static void phy_copy_pause_bits(unsigned long *dst, unsigned long *src)
+{
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, dst,
+		linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, src));
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, dst,
+		linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, src));
+}
+
+/**
+ * phy_advertise_supported - Advertise all supported modes
+ * @phydev: target phy_device struct
+ *
+ * Description: Called to advertise all supported modes, doesn't touch
+ * pause mode advertising.
+ */
+void phy_advertise_supported(struct phy_device *phydev)
+{
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(new);
+
+	linkmode_copy(new, phydev->supported);
+	phy_copy_pause_bits(new, phydev->advertising);
+	linkmode_copy(phydev->advertising, new);
+}
+EXPORT_SYMBOL(phy_advertise_supported);
+
 /**
  * phy_support_sym_pause - Enable support of symmetrical pause
  * @phydev: target phy_device struct
@@ -1999,8 +2024,7 @@ EXPORT_SYMBOL(phy_remove_link_mode);
 void phy_support_sym_pause(struct phy_device *phydev)
 {
 	linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->supported);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported);
-	linkmode_copy(phydev->advertising, phydev->supported);
+	phy_copy_pause_bits(phydev->advertising, phydev->supported);
 }
 EXPORT_SYMBOL(phy_support_sym_pause);
 
@@ -2012,9 +2036,7 @@ EXPORT_SYMBOL(phy_support_sym_pause);
  */
 void phy_support_asym_pause(struct phy_device *phydev)
 {
-	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->supported);
-	linkmode_copy(phydev->advertising, phydev->supported);
+	phy_copy_pause_bits(phydev->advertising, phydev->supported);
 }
 EXPORT_SYMBOL(phy_support_asym_pause);
 
@@ -2177,7 +2199,7 @@ static int phy_probe(struct device *dev)
 		phydev->is_gigabit_capable = 1;
 
 	of_set_phy_supported(phydev);
-	linkmode_copy(phydev->advertising, phydev->supported);
+	phy_advertise_supported(phydev);
 
 	/* Get the EEE modes we want to prohibit. We will ask
 	 * the PHY stop advertising these mode later on
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 0f9552b17ee7..4a03f8a46d33 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1154,6 +1154,7 @@ void phy_request_interrupt(struct phy_device *phydev);
 void phy_print_status(struct phy_device *phydev);
 int phy_set_max_speed(struct phy_device *phydev, u32 max_speed);
 void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode);
+void phy_advertise_supported(struct phy_device *phydev);
 void phy_support_sym_pause(struct phy_device *phydev);
 void phy_support_asym_pause(struct phy_device *phydev);
 void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx,
-- 
cgit v1.2.3


From f24098f80748ea95d53603a7bb7954a41bb3ca1b Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 1 May 2019 22:14:21 +0200
Subject: net: phy: improve resuming from hibernation

I got an interesting report [0] that after resuming from hibernation
the link has 100Mbps instead of 1Gbps. Reason is that another OS has
been used whilst Linux was hibernated. And this OS speeds down the link
due to WoL. Therefore, when resuming, we shouldn't expect that what
the PHY advertises is what it did when hibernating.
Easiest way to do this is removing state PHY_RESUMING. Instead always
go via PHY_UP that configures PHY advertisement.

[0] https://bugzilla.kernel.org/show_bug.cgi?id=202851

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 7 +------
 include/linux/phy.h   | 9 +--------
 2 files changed, 2 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 984de987241c..1a146c5c5036 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -43,7 +43,6 @@ static const char *phy_state_to_str(enum phy_state st)
 	PHY_STATE_STR(NOLINK)
 	PHY_STATE_STR(FORCING)
 	PHY_STATE_STR(HALTED)
-	PHY_STATE_STR(RESUMING)
 	}
 
 	return NULL;
@@ -859,10 +858,7 @@ void phy_start(struct phy_device *phydev)
 			goto out;
 	}
 
-	if (phydev->state == PHY_READY)
-		phydev->state = PHY_UP;
-	else
-		phydev->state = PHY_RESUMING;
+	phydev->state = PHY_UP;
 
 	phy_start_machine(phydev);
 out:
@@ -897,7 +893,6 @@ void phy_state_machine(struct work_struct *work)
 		break;
 	case PHY_NOLINK:
 	case PHY_RUNNING:
-	case PHY_RESUMING:
 		err = phy_check_link_status(phydev);
 		break;
 	case PHY_FORCING:
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 4a03f8a46d33..073fb151b5a9 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -308,13 +308,7 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
  *
  * HALTED: PHY is up, but no polling or interrupts are done. Or
  * PHY is in an error state.
- *
- * - phy_start moves to RESUMING
- *
- * RESUMING: PHY was halted, but now wants to run again.
- * - If we are forcing, or aneg is done, timer moves to RUNNING
- * - If aneg is not done, timer moves to AN
- * - phy_stop moves to HALTED
+ * - phy_start moves to UP
  */
 enum phy_state {
 	PHY_DOWN = 0,
@@ -324,7 +318,6 @@ enum phy_state {
 	PHY_RUNNING,
 	PHY_NOLINK,
 	PHY_FORCING,
-	PHY_RESUMING
 };
 
 /**
-- 
cgit v1.2.3


From b424e432e770d6dd572765459d5b6a96a19c5286 Mon Sep 17 00:00:00 2001
From: Michal Kubecek <mkubecek@suse.cz>
Date: Thu, 2 May 2019 16:15:10 +0200
Subject: netlink: add validation of NLA_F_NESTED flag

Add new validation flag NL_VALIDATE_NESTED which adds three consistency
checks of NLA_F_NESTED_FLAG:

  - the flag is set on attributes with NLA_NESTED{,_ARRAY} policy
  - the flag is not set on attributes with other policies except NLA_UNSPEC
  - the flag is set on attribute passed to nla_parse_nested()

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>

v2: change error messages to mention NLA_F_NESTED explicitly
Reviewed-by: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h | 11 ++++++++++-
 lib/nlattr.c          | 15 +++++++++++++++
 2 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 679f649748d4..395b4406f4b0 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -401,6 +401,8 @@ struct nl_info {
  *	are enforced going forward.
  * @NL_VALIDATE_STRICT_ATTRS: strict attribute policy parsing (e.g.
  *	U8, U16, U32 must have exact size, etc.)
+ * @NL_VALIDATE_NESTED: Check that NLA_F_NESTED is set for NLA_NESTED(_ARRAY)
+ *	and unset for other policies.
  */
 enum netlink_validation {
 	NL_VALIDATE_LIBERAL = 0,
@@ -408,6 +410,7 @@ enum netlink_validation {
 	NL_VALIDATE_MAXTYPE = BIT(1),
 	NL_VALIDATE_UNSPEC = BIT(2),
 	NL_VALIDATE_STRICT_ATTRS = BIT(3),
+	NL_VALIDATE_NESTED = BIT(4),
 };
 
 #define NL_VALIDATE_DEPRECATED_STRICT (NL_VALIDATE_TRAILING |\
@@ -415,7 +418,8 @@ enum netlink_validation {
 #define NL_VALIDATE_STRICT (NL_VALIDATE_TRAILING |\
 			    NL_VALIDATE_MAXTYPE |\
 			    NL_VALIDATE_UNSPEC |\
-			    NL_VALIDATE_STRICT_ATTRS)
+			    NL_VALIDATE_STRICT_ATTRS |\
+			    NL_VALIDATE_NESTED)
 
 int netlink_rcv_skb(struct sk_buff *skb,
 		    int (*cb)(struct sk_buff *, struct nlmsghdr *,
@@ -1132,6 +1136,11 @@ static inline int nla_parse_nested(struct nlattr *tb[], int maxtype,
 				   const struct nla_policy *policy,
 				   struct netlink_ext_ack *extack)
 {
+	if (!(nla->nla_type & NLA_F_NESTED)) {
+		NL_SET_ERR_MSG_ATTR(extack, nla, "NLA_F_NESTED is missing");
+		return -EINVAL;
+	}
+
 	return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy,
 			   NL_VALIDATE_STRICT, extack);
 }
diff --git a/lib/nlattr.c b/lib/nlattr.c
index adc919b32bf9..cace9b307781 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -184,6 +184,21 @@ static int validate_nla(const struct nlattr *nla, int maxtype,
 		}
 	}
 
+	if (validate & NL_VALIDATE_NESTED) {
+		if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) &&
+		    !(nla->nla_type & NLA_F_NESTED)) {
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "NLA_F_NESTED is missing");
+			return -EINVAL;
+		}
+		if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY &&
+		    pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) {
+			NL_SET_ERR_MSG_ATTR(extack, nla,
+					    "NLA_F_NESTED not expected");
+			return -EINVAL;
+		}
+	}
+
 	switch (pt->type) {
 	case NLA_EXACT_LEN:
 		if (attrlen != pt->len)
-- 
cgit v1.2.3


From 0f457a36626fa94026e483836fbf29e451434567 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 30 Apr 2019 07:45:48 -0700
Subject: ipv4: Move cached routes to fib_nh_common

While the cached routes, nh_pcpu_rth_output and nh_rth_input, are IPv4
specific, a later patch wants to make them accessible for IPv6 nexthops
with IPv4 routes using a fib6_nh. Move the cached routes from fib_nh to
fib_nh_common and update references.

Initialization of the cached entries is moved to fib_nh_common_init,
and free is moved to fib_nh_common_release.

Change in location only, from fib_nh up to fib_nh_common; no functional
change intended.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  6 ++++--
 net/ipv4/fib_semantics.c | 36 +++++++++++++++++++-----------------
 net/ipv4/route.c         | 18 +++++++++---------
 3 files changed, 32 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 772a9e61bd84..659c5081c40b 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -96,6 +96,10 @@ struct fib_nh_common {
 
 	int			nhc_weight;
 	atomic_t		nhc_upper_bound;
+
+	/* v4 specific, but allows fib6_nh with v4 routes */
+	struct rtable __rcu * __percpu *nhc_pcpu_rth_output;
+	struct rtable __rcu     *nhc_rth_input;
 };
 
 struct fib_nh {
@@ -107,8 +111,6 @@ struct fib_nh {
 #endif
 	__be32			nh_saddr;
 	int			nh_saddr_genid;
-	struct rtable __rcu * __percpu *nh_pcpu_rth_output;
-	struct rtable __rcu	*nh_rth_input;
 	struct fnhe_hash_bucket	__rcu *nh_exceptions;
 #define fib_nh_family		nh_common.nhc_family
 #define fib_nh_dev		nh_common.nhc_dev
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 71c2165a2ce3..4402ec6dc426 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -212,6 +212,8 @@ void fib_nh_common_release(struct fib_nh_common *nhc)
 		dev_put(nhc->nhc_dev);
 
 	lwtstate_put(nhc->nhc_lwtstate);
+	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
+	rt_fibinfo_free(&nhc->nhc_rth_input);
 }
 EXPORT_SYMBOL_GPL(fib_nh_common_release);
 
@@ -223,8 +225,6 @@ void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
 #endif
 	fib_nh_common_release(&fib_nh->nh_common);
 	free_nh_exceptions(fib_nh);
-	rt_fibinfo_free_cpus(fib_nh->nh_pcpu_rth_output);
-	rt_fibinfo_free(&fib_nh->nh_rth_input);
 }
 
 /* Release a nexthop info record */
@@ -491,23 +491,35 @@ int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *encap,
 		       u16 encap_type, void *cfg, gfp_t gfp_flags,
 		       struct netlink_ext_ack *extack)
 {
+	int err;
+
+	nhc->nhc_pcpu_rth_output = alloc_percpu_gfp(struct rtable __rcu *,
+						    gfp_flags);
+	if (!nhc->nhc_pcpu_rth_output)
+		return -ENOMEM;
+
 	if (encap) {
 		struct lwtunnel_state *lwtstate;
-		int err;
 
 		if (encap_type == LWTUNNEL_ENCAP_NONE) {
 			NL_SET_ERR_MSG(extack, "LWT encap type not specified");
-			return -EINVAL;
+			err = -EINVAL;
+			goto lwt_failure;
 		}
 		err = lwtunnel_build_state(encap_type, encap, nhc->nhc_family,
 					   cfg, &lwtstate, extack);
 		if (err)
-			return err;
+			goto lwt_failure;
 
 		nhc->nhc_lwtstate = lwtstate_get(lwtstate);
 	}
 
 	return 0;
+
+lwt_failure:
+	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
+	nhc->nhc_pcpu_rth_output = NULL;
+	return err;
 }
 EXPORT_SYMBOL_GPL(fib_nh_common_init);
 
@@ -515,18 +527,14 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 		struct fib_config *cfg, int nh_weight,
 		struct netlink_ext_ack *extack)
 {
-	int err = -ENOMEM;
+	int err;
 
 	nh->fib_nh_family = AF_INET;
 
-	nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
-	if (!nh->nh_pcpu_rth_output)
-		goto err_out;
-
 	err = fib_nh_common_init(&nh->nh_common, cfg->fc_encap,
 				 cfg->fc_encap_type, cfg, GFP_KERNEL, extack);
 	if (err)
-		goto init_failure;
+		return err;
 
 	nh->fib_nh_oif = cfg->fc_oif;
 	nh->fib_nh_gw_family = cfg->fc_gw_family;
@@ -546,12 +554,6 @@ int fib_nh_init(struct net *net, struct fib_nh *nh,
 	nh->fib_nh_weight = nh_weight;
 #endif
 	return 0;
-
-init_failure:
-	rt_fibinfo_free_cpus(nh->nh_pcpu_rth_output);
-	nh->nh_pcpu_rth_output = NULL;
-err_out:
-	return err;
 }
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 795aed6e4720..662ac9bd956e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -646,6 +646,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh
 static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 				  u32 pmtu, bool lock, unsigned long expires)
 {
+	struct fib_nh_common *nhc = &nh->nh_common;
 	struct fnhe_hash_bucket *hash;
 	struct fib_nh_exception *fnhe;
 	struct rtable *rt;
@@ -715,13 +716,13 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 		 * stale, so anyone caching it rechecks if this exception
 		 * applies to them.
 		 */
-		rt = rcu_dereference(nh->nh_rth_input);
+		rt = rcu_dereference(nhc->nhc_rth_input);
 		if (rt)
 			rt->dst.obsolete = DST_OBSOLETE_KILL;
 
 		for_each_possible_cpu(i) {
 			struct rtable __rcu **prt;
-			prt = per_cpu_ptr(nh->nh_pcpu_rth_output, i);
+			prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i);
 			rt = rcu_dereference(*prt);
 			if (rt)
 				rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1471,13 +1472,14 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 
 static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 {
+	struct fib_nh_common *nhc = &nh->nh_common;
 	struct rtable *orig, *prev, **p;
 	bool ret = true;
 
 	if (rt_is_input_route(rt)) {
-		p = (struct rtable **)&nh->nh_rth_input;
+		p = (struct rtable **)&nhc->nhc_rth_input;
 	} else {
-		p = (struct rtable **)raw_cpu_ptr(nh->nh_pcpu_rth_output);
+		p = (struct rtable **)raw_cpu_ptr(nhc->nhc_pcpu_rth_output);
 	}
 	orig = *p;
 
@@ -1810,7 +1812,7 @@ static int __mkroute_input(struct sk_buff *skb,
 		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
 		else
-			rth = rcu_dereference(nh->nh_rth_input);
+			rth = rcu_dereference(nhc->nhc_rth_input);
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2105,10 +2107,8 @@ local_input:
 	if (res->fi) {
 		if (!itag) {
 			struct fib_nh_common *nhc = FIB_RES_NHC(*res);
-			struct fib_nh *nh;
 
-			nh = container_of(nhc, struct fib_nh, nh_common);
-			rth = rcu_dereference(nh->nh_rth_input);
+			rth = rcu_dereference(nhc->nhc_rth_input);
 			if (rt_cache_valid(rth)) {
 				skb_dst_set_noref(skb, &rth->dst);
 				err = 0;
@@ -2337,7 +2337,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 				do_cache = false;
 				goto add;
 			}
-			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
+			prth = raw_cpu_ptr(nhc->nhc_pcpu_rth_output);
 		}
 		rth = rcu_dereference(*prth);
 		if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst))
-- 
cgit v1.2.3


From a5995e7107eb3d9c44744d3cf47d49fabfef01f5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 30 Apr 2019 07:45:50 -0700
Subject: ipv4: Move exception bucket to nh_common

Similar to the cached routes, make IPv4 exceptions accessible when
using an IPv6 nexthop struct with IPv4 routes. Simplify the exception
functions by passing in fib_nh_common since that is all it needs,
and then cleanup the call sites that have extraneous fib_nh conversions.

As with the cached routes this is a change in location only, from fib_nh
up to fib_nh_common; no functional change intended.

Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h     |  2 +-
 net/ipv4/fib_semantics.c | 12 ++++++------
 net/ipv4/route.c         | 41 +++++++++++++++++------------------------
 3 files changed, 24 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 659c5081c40b..d0e28f4ab099 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -100,6 +100,7 @@ struct fib_nh_common {
 	/* v4 specific, but allows fib6_nh with v4 routes */
 	struct rtable __rcu * __percpu *nhc_pcpu_rth_output;
 	struct rtable __rcu     *nhc_rth_input;
+	struct fnhe_hash_bucket	__rcu *nhc_exceptions;
 };
 
 struct fib_nh {
@@ -111,7 +112,6 @@ struct fib_nh {
 #endif
 	__be32			nh_saddr;
 	int			nh_saddr_genid;
-	struct fnhe_hash_bucket	__rcu *nh_exceptions;
 #define fib_nh_family		nh_common.nhc_family
 #define fib_nh_dev		nh_common.nhc_dev
 #define fib_nh_oif		nh_common.nhc_oif
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 4402ec6dc426..d3da6a10f86f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -159,12 +159,12 @@ static void rt_fibinfo_free(struct rtable __rcu **rtp)
 	dst_release_immediate(&rt->dst);
 }
 
-static void free_nh_exceptions(struct fib_nh *nh)
+static void free_nh_exceptions(struct fib_nh_common *nhc)
 {
 	struct fnhe_hash_bucket *hash;
 	int i;
 
-	hash = rcu_dereference_protected(nh->nh_exceptions, 1);
+	hash = rcu_dereference_protected(nhc->nhc_exceptions, 1);
 	if (!hash)
 		return;
 	for (i = 0; i < FNHE_HASH_SIZE; i++) {
@@ -214,6 +214,7 @@ void fib_nh_common_release(struct fib_nh_common *nhc)
 	lwtstate_put(nhc->nhc_lwtstate);
 	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
 	rt_fibinfo_free(&nhc->nhc_rth_input);
+	free_nh_exceptions(nhc);
 }
 EXPORT_SYMBOL_GPL(fib_nh_common_release);
 
@@ -224,7 +225,6 @@ void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
 		net->ipv4.fib_num_tclassid_users--;
 #endif
 	fib_nh_common_release(&fib_nh->nh_common);
-	free_nh_exceptions(fib_nh);
 }
 
 /* Release a nexthop info record */
@@ -1713,12 +1713,12 @@ static int call_fib_nh_notifiers(struct fib_nh *nh,
  * - if the new MTU is greater than the PMTU, don't make any change
  * - otherwise, unlock and set PMTU
  */
-static void nh_update_mtu(struct fib_nh *nh, u32 new, u32 orig)
+static void nh_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig)
 {
 	struct fnhe_hash_bucket *bucket;
 	int i;
 
-	bucket = rcu_dereference_protected(nh->nh_exceptions, 1);
+	bucket = rcu_dereference_protected(nhc->nhc_exceptions, 1);
 	if (!bucket)
 		return;
 
@@ -1749,7 +1749,7 @@ void fib_sync_mtu(struct net_device *dev, u32 orig_mtu)
 
 	hlist_for_each_entry(nh, head, nh_hash) {
 		if (nh->fib_nh_dev == dev)
-			nh_update_mtu(nh, dev->mtu, orig_mtu);
+			nh_update_mtu(&nh->nh_common, dev->mtu, orig_mtu);
 	}
 }
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 9b50d0440940..11ddc276776e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -643,10 +643,10 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh
 	}
 }
 
-static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
-				  u32 pmtu, bool lock, unsigned long expires)
+static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
+				  __be32 gw, u32 pmtu, bool lock,
+				  unsigned long expires)
 {
-	struct fib_nh_common *nhc = &nh->nh_common;
 	struct fnhe_hash_bucket *hash;
 	struct fib_nh_exception *fnhe;
 	struct rtable *rt;
@@ -654,17 +654,17 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 	unsigned int i;
 	int depth;
 
-	genid = fnhe_genid(dev_net(nh->fib_nh_dev));
+	genid = fnhe_genid(dev_net(nhc->nhc_dev));
 	hval = fnhe_hashfun(daddr);
 
 	spin_lock_bh(&fnhe_lock);
 
-	hash = rcu_dereference(nh->nh_exceptions);
+	hash = rcu_dereference(nhc->nhc_exceptions);
 	if (!hash) {
 		hash = kcalloc(FNHE_HASH_SIZE, sizeof(*hash), GFP_ATOMIC);
 		if (!hash)
 			goto out_unlock;
-		rcu_assign_pointer(nh->nh_exceptions, hash);
+		rcu_assign_pointer(nhc->nhc_exceptions, hash);
 	}
 
 	hash += hval;
@@ -789,10 +789,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 		} else {
 			if (fib_lookup(net, fl4, &res, 0) == 0) {
 				struct fib_nh_common *nhc = FIB_RES_NHC(res);
-				struct fib_nh *nh;
 
-				nh = container_of(nhc, struct fib_nh, nh_common);
-				update_or_create_fnhe(nh, fl4->daddr, new_gw,
+				update_or_create_fnhe(nhc, fl4->daddr, new_gw,
 						0, false,
 						jiffies + ip_rt_gc_timeout);
 			}
@@ -1040,10 +1038,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 	rcu_read_lock();
 	if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
 		struct fib_nh_common *nhc = FIB_RES_NHC(res);
-		struct fib_nh *nh;
 
-		nh = container_of(nhc, struct fib_nh, nh_common);
-		update_or_create_fnhe(nh, fl4->daddr, 0, mtu, lock,
+		update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock,
 				      jiffies + ip_rt_mtu_expires);
 	}
 	rcu_read_unlock();
@@ -1329,7 +1325,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
-static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+static void ip_del_fnhe(struct fib_nh_common *nhc, __be32 daddr)
 {
 	struct fnhe_hash_bucket *hash;
 	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
@@ -1337,7 +1333,7 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
 
 	spin_lock_bh(&fnhe_lock);
 
-	hash = rcu_dereference_protected(nh->nh_exceptions,
+	hash = rcu_dereference_protected(nhc->nhc_exceptions,
 					 lockdep_is_held(&fnhe_lock));
 	hash += hval;
 
@@ -1363,9 +1359,10 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
 	spin_unlock_bh(&fnhe_lock);
 }
 
-static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
+static struct fib_nh_exception *find_exception(struct fib_nh_common *nhc,
+					       __be32 daddr)
 {
-	struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
+	struct fnhe_hash_bucket *hash = rcu_dereference(nhc->nhc_exceptions);
 	struct fib_nh_exception *fnhe;
 	u32 hval;
 
@@ -1379,7 +1376,7 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 		if (fnhe->fnhe_daddr == daddr) {
 			if (fnhe->fnhe_expires &&
 			    time_after(jiffies, fnhe->fnhe_expires)) {
-				ip_del_fnhe(nh, daddr);
+				ip_del_fnhe(nhc, daddr);
 				break;
 			}
 			return fnhe;
@@ -1406,10 +1403,9 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 		mtu = fi->fib_mtu;
 
 	if (likely(!mtu)) {
-		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 		struct fib_nh_exception *fnhe;
 
-		fnhe = find_exception(nh, daddr);
+		fnhe = find_exception(nhc, daddr);
 		if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires))
 			mtu = fnhe->fnhe_pmtu;
 	}
@@ -1760,7 +1756,6 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct net_device *dev = nhc->nhc_dev;
 	struct fib_nh_exception *fnhe;
 	struct rtable *rth;
-	struct fib_nh *nh;
 	int err;
 	struct in_device *out_dev;
 	bool do_cache;
@@ -1808,8 +1803,7 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
-	nh = container_of(nhc, struct fib_nh, nh_common);
-	fnhe = find_exception(nh, daddr);
+	fnhe = find_exception(nhc, daddr);
 	if (do_cache) {
 		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
@@ -2321,10 +2315,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	do_cache &= fi != NULL;
 	if (fi) {
 		struct fib_nh_common *nhc = FIB_RES_NHC(*res);
-		struct fib_nh *nh = container_of(nhc, struct fib_nh, nh_common);
 		struct rtable __rcu **prth;
 
-		fnhe = find_exception(nh, fl4->daddr);
+		fnhe = find_exception(nhc, fl4->daddr);
 		if (!do_cache)
 			goto add;
 		if (fnhe) {
-- 
cgit v1.2.3


From f80c5dad7b6467b884c445ffea45985793b4b2d0 Mon Sep 17 00:00:00 2001
From: João Paulo Rechi Vita <jprvita@gmail.com>
Date: Thu, 2 May 2019 10:01:52 +0800
Subject: Bluetooth: Ignore CC events not matching the last HCI command
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This commit makes the kernel not send the next queued HCI command until
a command complete arrives for the last HCI command sent to the
controller. This change avoids a problem with some buggy controllers
(seen on two SKUs of QCA9377) that send an extra command complete event
for the previous command after the kernel had already sent a new HCI
command to the controller.

The problem was reproduced when starting an active scanning procedure,
where an extra command complete event arrives for the LE_SET_RANDOM_ADDR
command. When this happends the kernel ends up not processing the
command complete for the following commmand, LE_SET_SCAN_PARAM, and
ultimately behaving as if a passive scanning procedure was being
performed, when in fact controller is performing an active scanning
procedure. This makes it impossible to discover BLE devices as no device
found events are sent to userspace.

This problem is reproducible on 100% of the attempts on the affected
controllers. The extra command complete event can be seen at timestamp
27.420131 on the btmon logs bellow.

Bluetooth monitor ver 5.50
= Note: Linux version 5.0.0+ (x86_64)                                  0.352340
= Note: Bluetooth subsystem version 2.22                               0.352343
= New Index: 80:C5:F2:8F:87:84 (Primary,USB,hci0)               [hci0] 0.352344
= Open Index: 80:C5:F2:8F:87:84                                 [hci0] 0.352345
= Index Info: 80:C5:F2:8F:87:84 (Qualcomm)                      [hci0] 0.352346
@ MGMT Open: bluetoothd (privileged) version 1.14             {0x0001} 0.352347
@ MGMT Open: btmon (privileged) version 1.14                  {0x0002} 0.352366
@ MGMT Open: btmgmt (privileged) version 1.14                {0x0003} 27.302164
@ MGMT Command: Start Discovery (0x0023) plen 1       {0x0003} [hci0] 27.302310
        Address type: 0x06
          LE Public
          LE Random
< HCI Command: LE Set Random Address (0x08|0x0005) plen 6   #1 [hci0] 27.302496
        Address: 15:60:F2:91:B2:24 (Non-Resolvable)
> HCI Event: Command Complete (0x0e) plen 4                 #2 [hci0] 27.419117
      LE Set Random Address (0x08|0x0005) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Set Scan Parameters (0x08|0x000b) plen 7  #3 [hci0] 27.419244
        Type: Active (0x01)
        Interval: 11.250 msec (0x0012)
        Window: 11.250 msec (0x0012)
        Own address type: Random (0x01)
        Filter policy: Accept all advertisement (0x00)
> HCI Event: Command Complete (0x0e) plen 4                 #4 [hci0] 27.420131
      LE Set Random Address (0x08|0x0005) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Set Scan Enable (0x08|0x000c) plen 2      #5 [hci0] 27.420259
        Scanning: Enabled (0x01)
        Filter duplicates: Enabled (0x01)
> HCI Event: Command Complete (0x0e) plen 4                 #6 [hci0] 27.420969
      LE Set Scan Parameters (0x08|0x000b) ncmd 1
        Status: Success (0x00)
> HCI Event: Command Complete (0x0e) plen 4                 #7 [hci0] 27.421983
      LE Set Scan Enable (0x08|0x000c) ncmd 1
        Status: Success (0x00)
@ MGMT Event: Command Complete (0x0001) plen 4        {0x0003} [hci0] 27.422059
      Start Discovery (0x0023) plen 1
        Status: Success (0x00)
        Address type: 0x06
          LE Public
          LE Random
@ MGMT Event: Discovering (0x0013) plen 2             {0x0003} [hci0] 27.422067
        Address type: 0x06
          LE Public
          LE Random
        Discovery: Enabled (0x01)
@ MGMT Event: Discovering (0x0013) plen 2             {0x0002} [hci0] 27.422067
        Address type: 0x06
          LE Public
          LE Random
        Discovery: Enabled (0x01)
@ MGMT Event: Discovering (0x0013) plen 2             {0x0001} [hci0] 27.422067
        Address type: 0x06
          LE Public
          LE Random
        Discovery: Enabled (0x01)

Signed-off-by: João Paulo Rechi Vita <jprvita@endlessm.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h |  1 +
 net/bluetooth/hci_core.c    |  5 +++++
 net/bluetooth/hci_event.c   | 12 ++++++++++++
 net/bluetooth/hci_request.c |  5 +++++
 net/bluetooth/hci_request.h |  1 +
 5 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index fbba43e9bef5..9a5330eed794 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -282,6 +282,7 @@ enum {
 	HCI_FORCE_BREDR_SMP,
 	HCI_FORCE_STATIC_ADDR,
 	HCI_LL_RPA_RESOLUTION,
+	HCI_CMD_PENDING,
 
 	__HCI_NUM_FLAGS,
 };
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 3d9175f130b3..b81bf53c5ac4 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -4381,6 +4381,9 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status,
 		return;
 	}
 
+	/* If we reach this point this event matches the last command sent */
+	hci_dev_clear_flag(hdev, HCI_CMD_PENDING);
+
 	/* If the command succeeded and there's still more commands in
 	 * this request the request is not yet complete.
 	 */
@@ -4491,6 +4494,8 @@ static void hci_cmd_work(struct work_struct *work)
 
 		hdev->sent_cmd = skb_clone(skb, GFP_KERNEL);
 		if (hdev->sent_cmd) {
+			if (hci_req_status_pend(hdev))
+				hci_dev_set_flag(hdev, HCI_CMD_PENDING);
 			atomic_dec(&hdev->cmd_cnt);
 			hci_send_frame(hdev, skb);
 			if (test_bit(HCI_RESET, &hdev->flags))
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 66b631ab0d35..9e4fcf406d9c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3404,6 +3404,12 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 	hci_req_cmd_complete(hdev, *opcode, *status, req_complete,
 			     req_complete_skb);
 
+	if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) {
+		bt_dev_err(hdev,
+			   "unexpected event for opcode 0x%4.4x", *opcode);
+		return;
+	}
+
 	if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q))
 		queue_work(hdev->workqueue, &hdev->cmd_work);
 }
@@ -3511,6 +3517,12 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_req_cmd_complete(hdev, *opcode, ev->status, req_complete,
 				     req_complete_skb);
 
+	if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) {
+		bt_dev_err(hdev,
+			   "unexpected event for opcode 0x%4.4x", *opcode);
+		return;
+	}
+
 	if (atomic_read(&hdev->cmd_cnt) && !skb_queue_empty(&hdev->cmd_q))
 		queue_work(hdev->workqueue, &hdev->cmd_work);
 }
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index ca73d36cc149..e9a95ed65491 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -46,6 +46,11 @@ void hci_req_purge(struct hci_request *req)
 	skb_queue_purge(&req->cmd_q);
 }
 
+bool hci_req_status_pend(struct hci_dev *hdev)
+{
+	return hdev->req_status == HCI_REQ_PEND;
+}
+
 static int req_run(struct hci_request *req, hci_req_complete_t complete,
 		   hci_req_complete_skb_t complete_skb)
 {
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index 692cc8b13368..55b2050cc9ff 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -37,6 +37,7 @@ struct hci_request {
 
 void hci_req_init(struct hci_request *req, struct hci_dev *hdev);
 void hci_req_purge(struct hci_request *req);
+bool hci_req_status_pend(struct hci_dev *hdev);
 int hci_req_run(struct hci_request *req, hci_req_complete_t complete);
 int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete);
 void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,
-- 
cgit v1.2.3


From 47d3d7fdb10a21c223036b58bd70ffdc24a472c4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 May 2019 08:24:44 -0700
Subject: ip6: fix skb leak in ip6frag_expire_frag_queue()

Since ip6frag_expire_frag_queue() now pulls the head skb
from frag queue, we should no longer use skb_get(), since
this leads to an skb leak.

Stefan Bader initially reported a problem in 4.4.stable [1] caused
by the skb_get(), so this patch should also fix this issue.

296583.091021] kernel BUG at /build/linux-6VmqmP/linux-4.4.0/net/core/skbuff.c:1207!
[296583.091734] Call Trace:
[296583.091749]  [<ffffffff81740e50>] __pskb_pull_tail+0x50/0x350
[296583.091764]  [<ffffffff8183939a>] _decode_session6+0x26a/0x400
[296583.091779]  [<ffffffff817ec719>] __xfrm_decode_session+0x39/0x50
[296583.091795]  [<ffffffff818239d0>] icmpv6_route_lookup+0xf0/0x1c0
[296583.091809]  [<ffffffff81824421>] icmp6_send+0x5e1/0x940
[296583.091823]  [<ffffffff81753238>] ? __netif_receive_skb+0x18/0x60
[296583.091838]  [<ffffffff817532b2>] ? netif_receive_skb_internal+0x32/0xa0
[296583.091858]  [<ffffffffc0199f74>] ? ixgbe_clean_rx_irq+0x594/0xac0 [ixgbe]
[296583.091876]  [<ffffffffc04eb260>] ? nf_ct_net_exit+0x50/0x50 [nf_defrag_ipv6]
[296583.091893]  [<ffffffff8183d431>] icmpv6_send+0x21/0x30
[296583.091906]  [<ffffffff8182b500>] ip6_expire_frag_queue+0xe0/0x120
[296583.091921]  [<ffffffffc04eb27f>] nf_ct_frag6_expire+0x1f/0x30 [nf_defrag_ipv6]
[296583.091938]  [<ffffffff810f3b57>] call_timer_fn+0x37/0x140
[296583.091951]  [<ffffffffc04eb260>] ? nf_ct_net_exit+0x50/0x50 [nf_defrag_ipv6]
[296583.091968]  [<ffffffff810f5464>] run_timer_softirq+0x234/0x330
[296583.091982]  [<ffffffff8108a339>] __do_softirq+0x109/0x2b0

Fixes: d4289fcc9b16 ("net: IP6 defrag: use rbtrees for IPv6 defrag")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Stefan Bader <stefan.bader@canonical.com>
Cc: Peter Oskolkov <posk@google.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6_frag.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
index 28aa9b30aece..1f77fb4dc79d 100644
--- a/include/net/ipv6_frag.h
+++ b/include/net/ipv6_frag.h
@@ -94,7 +94,6 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
 		goto out;
 
 	head->dev = dev;
-	skb_get(head);
 	spin_unlock(&fq->q.lock);
 
 	icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
-- 
cgit v1.2.3


From 9b3040a6aafd7898ece7fc7efcbca71e42aa8069 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Sun, 5 May 2019 11:16:20 -0700
Subject: ipv4: Define __ipv4_neigh_lookup_noref when CONFIG_INET is disabled

Define __ipv4_neigh_lookup_noref to return NULL when CONFIG_INET is disabled.

Fixes: 4b2a2bfeb3f0 ("neighbor: Call __ipv4_neigh_lookup_noref in neigh_xmit")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/arp.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/net/arp.h b/include/net/arp.h
index 977aabfcdc03..c8f580a0e6b1 100644
--- a/include/net/arp.h
+++ b/include/net/arp.h
@@ -18,6 +18,7 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32
 	return val * hash_rnd[0];
 }
 
+#ifdef CONFIG_INET
 static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key)
 {
 	if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
@@ -25,6 +26,13 @@ static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev
 
 	return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev);
 }
+#else
+static inline
+struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key)
+{
+	return NULL;
+}
+#endif
 
 static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key)
 {
-- 
cgit v1.2.3


From 522e4077e8dcdfc5b8e96469d3bc2324bc5d6466 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Sun, 28 Apr 2019 15:12:19 +0800
Subject: netfilter: slightly optimize nf_inet_addr_mask

using 64bit computation to slightly optimize nf_inet_addr_mask

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index a7252f3baeb0..996bc247ef6e 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -41,10 +41,19 @@ static inline void nf_inet_addr_mask(const union nf_inet_addr *a1,
 				     union nf_inet_addr *result,
 				     const union nf_inet_addr *mask)
 {
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+	const unsigned long *ua = (const unsigned long *)a1;
+	unsigned long *ur = (unsigned long *)result;
+	const unsigned long *um = (const unsigned long *)mask;
+
+	ur[0] = ua[0] & um[0];
+	ur[1] = ua[1] & um[1];
+#else
 	result->all[0] = a1->all[0] & mask->all[0];
 	result->all[1] = a1->all[1] & mask->all[1];
 	result->all[2] = a1->all[2] & mask->all[2];
 	result->all[3] = a1->all[3] & mask->all[3];
+#endif
 }
 
 int netfilter_init(void);
-- 
cgit v1.2.3


From a7a7be6087b07563490725f61f4dbf4826f099e2 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Sat, 4 May 2019 04:46:16 -0700
Subject: net/sched: add sample action to the hardware intermediate
 representation

Add sample action to the hardware intermediate representation model which
would subsequently allow it to be used by drivers for offload.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_offload.h | 7 +++++++
 net/sched/cls_api.c        | 8 ++++++++
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index d035183c8d03..9a6c89b2c2bb 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -118,6 +118,7 @@ enum flow_action_id {
 	FLOW_ACTION_MARK,
 	FLOW_ACTION_WAKE,
 	FLOW_ACTION_QUEUE,
+	FLOW_ACTION_SAMPLE,
 };
 
 /* This is mirroring enum pedit_header_type definition for easy mapping between
@@ -157,6 +158,12 @@ struct flow_action_entry {
 			u32		index;
 			u8		vf;
 		} queue;
+		struct {				/* FLOW_ACTION_SAMPLE */
+			struct psample_group	*psample_group;
+			u32			rate;
+			u32			trunc_size;
+			bool			truncate;
+		} sample;
 	};
 };
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 263c2ec082c9..f8ee2d78654a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -37,6 +37,7 @@
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_csum.h>
 #include <net/tc_act/tc_gact.h>
+#include <net/tc_act/tc_sample.h>
 #include <net/tc_act/tc_skbedit.h>
 
 extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
@@ -3257,6 +3258,13 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 		} else if (is_tcf_skbedit_mark(act)) {
 			entry->id = FLOW_ACTION_MARK;
 			entry->mark = tcf_skbedit_mark(act);
+		} else if (is_tcf_sample(act)) {
+			entry->id = FLOW_ACTION_SAMPLE;
+			entry->sample.psample_group =
+				tcf_sample_psample_group(act);
+			entry->sample.trunc_size = tcf_sample_trunc_size(act);
+			entry->sample.truncate = tcf_sample_truncate(act);
+			entry->sample.rate = tcf_sample_rate(act);
 		} else {
 			goto err_out;
 		}
-- 
cgit v1.2.3


From f00cbf1968145afbae385a867a66c69845e30711 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Sat, 4 May 2019 04:46:17 -0700
Subject: net/sched: use the hardware intermediate representation for matchall

Extends matchall offload to make use of the hardware intermediate
representation. More specifically, this patch moves the native TC
actions in cls_matchall offload to the newer flow_action
representation. This ultimately allows us to avoid a direct
dependency on native TC actions for matchall.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h    |  1 +
 net/sched/cls_matchall.c | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index d5e7a1af346f..c852ed502cc6 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -789,6 +789,7 @@ enum tc_matchall_command {
 struct tc_cls_matchall_offload {
 	struct tc_cls_common_offload common;
 	enum tc_matchall_command command;
+	struct flow_rule *rule;
 	struct tcf_exts *exts;
 	unsigned long cookie;
 };
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 46982b4ea70a..8d135ecab098 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -89,12 +89,30 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 	bool skip_sw = tc_skip_sw(head->flags);
 	int err;
 
+	cls_mall.rule =	flow_rule_alloc(tcf_exts_num_actions(&head->exts));
+	if (!cls_mall.rule)
+		return -ENOMEM;
+
 	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
 	cls_mall.command = TC_CLSMATCHALL_REPLACE;
 	cls_mall.exts = &head->exts;
 	cls_mall.cookie = cookie;
 
+	err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts);
+	if (err) {
+		kfree(cls_mall.rule);
+		mall_destroy_hw_filter(tp, head, cookie, NULL);
+		if (skip_sw)
+			NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action");
+		else
+			err = 0;
+
+		return err;
+	}
+
 	err = tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, skip_sw);
+	kfree(cls_mall.rule);
+
 	if (err < 0) {
 		mall_destroy_hw_filter(tp, head, cookie, NULL);
 		return err;
@@ -272,13 +290,28 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 	if (tc_skip_hw(head->flags))
 		return 0;
 
+	cls_mall.rule =	flow_rule_alloc(tcf_exts_num_actions(&head->exts));
+	if (!cls_mall.rule)
+		return -ENOMEM;
+
 	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
 	cls_mall.command = add ?
 		TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY;
 	cls_mall.exts = &head->exts;
 	cls_mall.cookie = (unsigned long)head;
 
+	err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts);
+	if (err) {
+		kfree(cls_mall.rule);
+		if (add && tc_skip_sw(head->flags)) {
+			NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action");
+			return err;
+		}
+	}
+
 	err = cb(TC_SETUP_CLSMATCHALL, &cls_mall, cb_priv);
+	kfree(cls_mall.rule);
+
 	if (err) {
 		if (add && tc_skip_sw(head->flags))
 			return err;
-- 
cgit v1.2.3


From ab79af32b0a5606324ce04c0f04a0d2f90b94464 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Sat, 4 May 2019 04:46:18 -0700
Subject: mlxsw: use intermediate representation for matchall offload

Updates the Mellanox spectrum driver to use the newer intermediate
representation for flow actions in matchall offloads.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 38 +++++++++++++-------------
 include/net/flow_offload.h                     | 11 ++++++++
 2 files changed, 30 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index a6c6d5ee9ead..f594c6a913ec 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1269,21 +1269,19 @@ mlxsw_sp_port_mall_tc_entry_find(struct mlxsw_sp_port *port,
 static int
 mlxsw_sp_port_add_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port,
 				      struct mlxsw_sp_port_mall_mirror_tc_entry *mirror,
-				      const struct tc_action *a,
+				      const struct flow_action_entry *act,
 				      bool ingress)
 {
 	enum mlxsw_sp_span_type span_type;
-	struct net_device *to_dev;
 
-	to_dev = tcf_mirred_dev(a);
-	if (!to_dev) {
+	if (!act->dev) {
 		netdev_err(mlxsw_sp_port->dev, "Could not find requested device\n");
 		return -EINVAL;
 	}
 
 	mirror->ingress = ingress;
 	span_type = ingress ? MLXSW_SP_SPAN_INGRESS : MLXSW_SP_SPAN_EGRESS;
-	return mlxsw_sp_span_mirror_add(mlxsw_sp_port, to_dev, span_type,
+	return mlxsw_sp_span_mirror_add(mlxsw_sp_port, act->dev, span_type,
 					true, &mirror->span_id);
 }
 
@@ -1302,7 +1300,7 @@ mlxsw_sp_port_del_cls_matchall_mirror(struct mlxsw_sp_port *mlxsw_sp_port,
 static int
 mlxsw_sp_port_add_cls_matchall_sample(struct mlxsw_sp_port *mlxsw_sp_port,
 				      struct tc_cls_matchall_offload *cls,
-				      const struct tc_action *a,
+				      const struct flow_action_entry *act,
 				      bool ingress)
 {
 	int err;
@@ -1313,18 +1311,18 @@ mlxsw_sp_port_add_cls_matchall_sample(struct mlxsw_sp_port *mlxsw_sp_port,
 		netdev_err(mlxsw_sp_port->dev, "sample already active\n");
 		return -EEXIST;
 	}
-	if (tcf_sample_rate(a) > MLXSW_REG_MPSC_RATE_MAX) {
+	if (act->sample.rate > MLXSW_REG_MPSC_RATE_MAX) {
 		netdev_err(mlxsw_sp_port->dev, "sample rate not supported\n");
 		return -EOPNOTSUPP;
 	}
 
 	rcu_assign_pointer(mlxsw_sp_port->sample->psample_group,
-			   tcf_sample_psample_group(a));
-	mlxsw_sp_port->sample->truncate = tcf_sample_truncate(a);
-	mlxsw_sp_port->sample->trunc_size = tcf_sample_trunc_size(a);
-	mlxsw_sp_port->sample->rate = tcf_sample_rate(a);
+			   act->sample.psample_group);
+	mlxsw_sp_port->sample->truncate = act->sample.truncate;
+	mlxsw_sp_port->sample->trunc_size = act->sample.trunc_size;
+	mlxsw_sp_port->sample->rate = act->sample.rate;
 
-	err = mlxsw_sp_port_sample_set(mlxsw_sp_port, true, tcf_sample_rate(a));
+	err = mlxsw_sp_port_sample_set(mlxsw_sp_port, true, act->sample.rate);
 	if (err)
 		goto err_port_sample_set;
 	return 0;
@@ -1350,10 +1348,10 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 {
 	struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry;
 	__be16 protocol = f->common.protocol;
-	const struct tc_action *a;
+	struct flow_action_entry *act;
 	int err;
 
-	if (!tcf_exts_has_one_action(f->exts)) {
+	if (!flow_offload_has_one_action(&f->rule->action)) {
 		netdev_err(mlxsw_sp_port->dev, "only singular actions are supported\n");
 		return -EOPNOTSUPP;
 	}
@@ -1363,19 +1361,21 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 		return -ENOMEM;
 	mall_tc_entry->cookie = f->cookie;
 
-	a = tcf_exts_first_action(f->exts);
+	act = &f->rule->action.entries[0];
 
-	if (is_tcf_mirred_egress_mirror(a) && protocol == htons(ETH_P_ALL)) {
+	if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) {
 		struct mlxsw_sp_port_mall_mirror_tc_entry *mirror;
 
 		mall_tc_entry->type = MLXSW_SP_PORT_MALL_MIRROR;
 		mirror = &mall_tc_entry->mirror;
 		err = mlxsw_sp_port_add_cls_matchall_mirror(mlxsw_sp_port,
-							    mirror, a, ingress);
-	} else if (is_tcf_sample(a) && protocol == htons(ETH_P_ALL)) {
+							    mirror, act,
+							    ingress);
+	} else if (act->id == FLOW_ACTION_SAMPLE &&
+		   protocol == htons(ETH_P_ALL)) {
 		mall_tc_entry->type = MLXSW_SP_PORT_MALL_SAMPLE;
 		err = mlxsw_sp_port_add_cls_matchall_sample(mlxsw_sp_port, f,
-							    a, ingress);
+							    act, ingress);
 	} else {
 		err = -EOPNOTSUPP;
 	}
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 9a6c89b2c2bb..3bf67dd64be5 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -177,6 +177,17 @@ static inline bool flow_action_has_entries(const struct flow_action *action)
 	return action->num_entries;
 }
 
+/**
+ * flow_action_has_one_action() - check if exactly one action is present
+ * @action: tc filter flow offload action
+ *
+ * Returns true if exactly one action is present.
+ */
+static inline bool flow_offload_has_one_action(const struct flow_action *action)
+{
+	return action->num_entries == 1;
+}
+
 #define flow_action_for_each(__i, __act, __actions)			\
         for (__i = 0, __act = &(__actions)->entries[0]; __i < (__actions)->num_entries; __act = &(__actions)->entries[++__i])
 
-- 
cgit v1.2.3


From dfcb19f0fae3d07f9c56f6efe2c9bbebef6826c9 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Sat, 4 May 2019 04:46:20 -0700
Subject: net/sched: remove unused functions for matchall offload

Cleanup unused functions and variables after porting to the newer
intermediate representation.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h    | 25 -------------------------
 net/sched/cls_matchall.c |  2 --
 2 files changed, 27 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index c852ed502cc6..2d0470661277 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -371,30 +371,6 @@ static inline bool tcf_exts_has_actions(struct tcf_exts *exts)
 #endif
 }
 
-/**
- * tcf_exts_has_one_action - check if exactly one action is present
- * @exts: tc filter extensions handle
- *
- * Returns true if exactly one action is present.
- */
-static inline bool tcf_exts_has_one_action(struct tcf_exts *exts)
-{
-#ifdef CONFIG_NET_CLS_ACT
-	return exts->nr_actions == 1;
-#else
-	return false;
-#endif
-}
-
-static inline struct tc_action *tcf_exts_first_action(struct tcf_exts *exts)
-{
-#ifdef CONFIG_NET_CLS_ACT
-	return exts->actions[0];
-#else
-	return NULL;
-#endif
-}
-
 /**
  * tcf_exts_exec - execute tc filter extensions
  * @skb: socket buffer
@@ -790,7 +766,6 @@ struct tc_cls_matchall_offload {
 	struct tc_cls_common_offload common;
 	enum tc_matchall_command command;
 	struct flow_rule *rule;
-	struct tcf_exts *exts;
 	unsigned long cookie;
 };
 
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 8d135ecab098..87bff17ac782 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -95,7 +95,6 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 
 	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
 	cls_mall.command = TC_CLSMATCHALL_REPLACE;
-	cls_mall.exts = &head->exts;
 	cls_mall.cookie = cookie;
 
 	err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts);
@@ -297,7 +296,6 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
 	cls_mall.command = add ?
 		TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY;
-	cls_mall.exts = &head->exts;
 	cls_mall.cookie = (unsigned long)head;
 
 	err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts);
-- 
cgit v1.2.3


From fa762da94d9860f584c909621d1f8ccbe24c5d5e Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Sat, 4 May 2019 04:46:21 -0700
Subject: net/sched: move police action structures to header

Move tcf_police_params, tcf_police and tc_police_compat structures to a
header. Making them usable to other code for example drivers that would
offload police actions to hardware.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tc_act/tc_police.h | 70 ++++++++++++++++++++++++++++++++++++++++++
 net/sched/act_police.c         | 37 +---------------------
 2 files changed, 71 insertions(+), 36 deletions(-)
 create mode 100644 include/net/tc_act/tc_police.h

(limited to 'include')

diff --git a/include/net/tc_act/tc_police.h b/include/net/tc_act/tc_police.h
new file mode 100644
index 000000000000..8b9ef3664262
--- /dev/null
+++ b/include/net/tc_act/tc_police.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_TC_POLICE_H
+#define __NET_TC_POLICE_H
+
+#include <net/act_api.h>
+
+struct tcf_police_params {
+	int			tcfp_result;
+	u32			tcfp_ewma_rate;
+	s64			tcfp_burst;
+	u32			tcfp_mtu;
+	s64			tcfp_mtu_ptoks;
+	struct psched_ratecfg	rate;
+	bool			rate_present;
+	struct psched_ratecfg	peak;
+	bool			peak_present;
+	struct rcu_head rcu;
+};
+
+struct tcf_police {
+	struct tc_action	common;
+	struct tcf_police_params __rcu *params;
+
+	spinlock_t		tcfp_lock ____cacheline_aligned_in_smp;
+	s64			tcfp_toks;
+	s64			tcfp_ptoks;
+	s64			tcfp_t_c;
+};
+
+#define to_police(pc) ((struct tcf_police *)pc)
+
+/* old policer structure from before tc actions */
+struct tc_police_compat {
+	u32			index;
+	int			action;
+	u32			limit;
+	u32			burst;
+	u32			mtu;
+	struct tc_ratespec	rate;
+	struct tc_ratespec	peakrate;
+};
+
+static inline bool is_tcf_police(const struct tc_action *act)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	if (act->ops && act->ops->id == TCA_ID_POLICE)
+		return true;
+#endif
+	return false;
+}
+
+static inline u64 tcf_police_rate_bytes_ps(const struct tc_action *act)
+{
+	struct tcf_police *police = to_police(act);
+	struct tcf_police_params *params;
+
+	params = rcu_dereference_bh(police->params);
+	return params->rate.rate_bytes_ps;
+}
+
+static inline s64 tcf_police_tcfp_burst(const struct tc_action *act)
+{
+	struct tcf_police *police = to_police(act);
+	struct tcf_police_params *params;
+
+	params = rcu_dereference_bh(police->params);
+	return params->tcfp_burst;
+}
+
+#endif /* __NET_TC_POLICE_H */
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index b48e40c69ad0..e33bcab75d1f 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -22,42 +22,7 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 #include <net/pkt_cls.h>
-
-struct tcf_police_params {
-	int			tcfp_result;
-	u32			tcfp_ewma_rate;
-	s64			tcfp_burst;
-	u32			tcfp_mtu;
-	s64			tcfp_mtu_ptoks;
-	struct psched_ratecfg	rate;
-	bool			rate_present;
-	struct psched_ratecfg	peak;
-	bool			peak_present;
-	struct rcu_head rcu;
-};
-
-struct tcf_police {
-	struct tc_action	common;
-	struct tcf_police_params __rcu *params;
-
-	spinlock_t		tcfp_lock ____cacheline_aligned_in_smp;
-	s64			tcfp_toks;
-	s64			tcfp_ptoks;
-	s64			tcfp_t_c;
-};
-
-#define to_police(pc) ((struct tcf_police *)pc)
-
-/* old policer structure from before tc actions */
-struct tc_police_compat {
-	u32			index;
-	int			action;
-	u32			limit;
-	u32			burst;
-	u32			mtu;
-	struct tc_ratespec	rate;
-	struct tc_ratespec	peakrate;
-};
+#include <net/tc_act/tc_police.h>
 
 /* Each policer is serialized by its individual spinlock */
 
-- 
cgit v1.2.3


From 8c8cfc6ed274e6fb86f00b53f3e7811afce29043 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Sat, 4 May 2019 04:46:22 -0700
Subject: net/sched: add police action to the hardware intermediate
 representation

Add police action to the hardware intermediate representation which
would subsequently allow it to be used by drivers for offload.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_offload.h | 5 +++++
 net/sched/cls_api.c        | 6 ++++++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 3bf67dd64be5..6200900434e1 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -119,6 +119,7 @@ enum flow_action_id {
 	FLOW_ACTION_WAKE,
 	FLOW_ACTION_QUEUE,
 	FLOW_ACTION_SAMPLE,
+	FLOW_ACTION_POLICE,
 };
 
 /* This is mirroring enum pedit_header_type definition for easy mapping between
@@ -164,6 +165,10 @@ struct flow_action_entry {
 			u32			trunc_size;
 			bool			truncate;
 		} sample;
+		struct {				/* FLOW_ACTION_POLICE */
+			s64			burst;
+			u64			rate_bytes_ps;
+		} police;
 	};
 };
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index f8ee2d78654a..d4699156974a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -37,6 +37,7 @@
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_csum.h>
 #include <net/tc_act/tc_gact.h>
+#include <net/tc_act/tc_police.h>
 #include <net/tc_act/tc_sample.h>
 #include <net/tc_act/tc_skbedit.h>
 
@@ -3265,6 +3266,11 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 			entry->sample.trunc_size = tcf_sample_trunc_size(act);
 			entry->sample.truncate = tcf_sample_truncate(act);
 			entry->sample.rate = tcf_sample_rate(act);
+		} else if (is_tcf_police(act)) {
+			entry->id = FLOW_ACTION_POLICE;
+			entry->police.burst = tcf_police_tcfp_burst(act);
+			entry->police.rate_bytes_ps =
+				tcf_police_rate_bytes_ps(act);
 		} else {
 			goto err_out;
 		}
-- 
cgit v1.2.3


From b7fe4ab8a6013c3c721bed91f73e76eec8fb5d89 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Sat, 4 May 2019 04:46:23 -0700
Subject: net/sched: extend matchall offload for hardware statistics

Introduce a new command for matchall classifiers that allows hardware
to update statistics.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h    |  2 ++
 net/sched/cls_matchall.c | 20 ++++++++++++++++++++
 2 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 2d0470661277..161fcf8516ac 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -760,12 +760,14 @@ tc_cls_flower_offload_flow_rule(struct tc_cls_flower_offload *tc_flow_cmd)
 enum tc_matchall_command {
 	TC_CLSMATCHALL_REPLACE,
 	TC_CLSMATCHALL_DESTROY,
+	TC_CLSMATCHALL_STATS,
 };
 
 struct tc_cls_matchall_offload {
 	struct tc_cls_common_offload common;
 	enum tc_matchall_command command;
 	struct flow_rule *rule;
+	struct flow_stats stats;
 	unsigned long cookie;
 };
 
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 87bff17ac782..da916f39b719 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -321,6 +321,23 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 	return 0;
 }
 
+static void mall_stats_hw_filter(struct tcf_proto *tp,
+				 struct cls_mall_head *head,
+				 unsigned long cookie)
+{
+	struct tc_cls_matchall_offload cls_mall = {};
+	struct tcf_block *block = tp->chain->block;
+
+	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, NULL);
+	cls_mall.command = TC_CLSMATCHALL_STATS;
+	cls_mall.cookie = cookie;
+
+	tc_setup_cb_call(block, TC_SETUP_CLSMATCHALL, &cls_mall, false);
+
+	tcf_exts_stats_update(&head->exts, cls_mall.stats.bytes,
+			      cls_mall.stats.pkts, cls_mall.stats.lastused);
+}
+
 static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,
 		     struct sk_buff *skb, struct tcmsg *t, bool rtnl_held)
 {
@@ -332,6 +349,9 @@ static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	if (!head)
 		return skb->len;
 
+	if (!tc_skip_hw(head->flags))
+		mall_stats_hw_filter(tp, head, (unsigned long)head);
+
 	t->tcm_handle = head->handle;
 
 	nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
-- 
cgit v1.2.3


From 88c44a5200849c8182eaf36535b4ceae6b90b19d Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Sat, 4 May 2019 04:46:25 -0700
Subject: net/sched: add block pointer to tc_cls_common_offload structure

Some actions like the police action are stateful and could share state
between devices. This is incompatible with offloading to multiple devices
and drivers might want to test for shared blocks when offloading.
Store a pointer to the tcf_block structure in the tc_cls_common_offload
structure to allow drivers to determine when offloads apply to a shared
block.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h    |  8 ++++++++
 net/sched/cls_bpf.c      |  7 ++++---
 net/sched/cls_flower.c   | 11 +++++++----
 net/sched/cls_matchall.c | 12 ++++++++----
 net/sched/cls_u32.c      | 17 +++++++++++------
 5 files changed, 38 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 161fcf8516ac..eed98f8fcb5e 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -100,6 +100,11 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		 struct tcf_result *res, bool compat_mode);
 
 #else
+static inline bool tcf_block_shared(struct tcf_block *block)
+{
+	return false;
+}
+
 static inline
 int tcf_block_get(struct tcf_block **p_block,
 		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
@@ -624,6 +629,7 @@ struct tc_cls_common_offload {
 	u32 chain_index;
 	__be16 protocol;
 	u32 prio;
+	struct tcf_block *block;
 	struct netlink_ext_ack *extack;
 };
 
@@ -725,11 +731,13 @@ static inline bool tc_in_hw(u32 flags)
 static inline void
 tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common,
 			   const struct tcf_proto *tp, u32 flags,
+			   struct tcf_block *block,
 			   struct netlink_ext_ack *extack)
 {
 	cls_common->chain_index = tp->chain->index;
 	cls_common->protocol = tp->protocol;
 	cls_common->prio = tp->prio;
+	cls_common->block = block;
 	if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE)
 		cls_common->extack = extack;
 }
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 9bcf499cce0c..ce7ff286ccb8 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -157,7 +157,7 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 	skip_sw = prog && tc_skip_sw(prog->gen_flags);
 	obj = prog ?: oldprog;
 
-	tc_cls_common_offload_init(&cls_bpf.common, tp, obj->gen_flags,
+	tc_cls_common_offload_init(&cls_bpf.common, tp, obj->gen_flags, block,
 				   extack);
 	cls_bpf.command = TC_CLSBPF_OFFLOAD;
 	cls_bpf.exts = &obj->exts;
@@ -227,7 +227,8 @@ static void cls_bpf_offload_update_stats(struct tcf_proto *tp,
 	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_bpf_offload cls_bpf = {};
 
-	tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags, NULL);
+	tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags, block,
+				   NULL);
 	cls_bpf.command = TC_CLSBPF_STATS;
 	cls_bpf.exts = &prog->exts;
 	cls_bpf.prog = prog->filter;
@@ -669,7 +670,7 @@ static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 			continue;
 
 		tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags,
-					   extack);
+					   block, extack);
 		cls_bpf.command = TC_CLSBPF_OFFLOAD;
 		cls_bpf.exts = &prog->exts;
 		cls_bpf.prog = add ? prog->filter : NULL;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index f6685fc53119..3cb372b0e933 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -389,7 +389,8 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f,
 	if (!rtnl_held)
 		rtnl_lock();
 
-	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack);
+	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, block,
+				   extack);
 	cls_flower.command = TC_CLSFLOWER_DESTROY;
 	cls_flower.cookie = (unsigned long) f;
 
@@ -422,7 +423,8 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 		goto errout;
 	}
 
-	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack);
+	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, block,
+				   extack);
 	cls_flower.command = TC_CLSFLOWER_REPLACE;
 	cls_flower.cookie = (unsigned long) f;
 	cls_flower.rule->match.dissector = &f->mask->dissector;
@@ -478,7 +480,8 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f,
 	if (!rtnl_held)
 		rtnl_lock();
 
-	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL);
+	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, block,
+				   NULL);
 	cls_flower.command = TC_CLSFLOWER_STATS;
 	cls_flower.cookie = (unsigned long) f;
 	cls_flower.classid = f->res.classid;
@@ -1757,7 +1760,7 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 		}
 
 		tc_cls_common_offload_init(&cls_flower.common, tp, f->flags,
-					   extack);
+					   block, extack);
 		cls_flower.command = add ?
 			TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY;
 		cls_flower.cookie = (unsigned long)f;
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index da916f39b719..820938fa09ed 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -71,7 +71,8 @@ static void mall_destroy_hw_filter(struct tcf_proto *tp,
 	struct tc_cls_matchall_offload cls_mall = {};
 	struct tcf_block *block = tp->chain->block;
 
-	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
+	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, block,
+				   extack);
 	cls_mall.command = TC_CLSMATCHALL_DESTROY;
 	cls_mall.cookie = cookie;
 
@@ -93,7 +94,8 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 	if (!cls_mall.rule)
 		return -ENOMEM;
 
-	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
+	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, block,
+				   extack);
 	cls_mall.command = TC_CLSMATCHALL_REPLACE;
 	cls_mall.cookie = cookie;
 
@@ -293,7 +295,8 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 	if (!cls_mall.rule)
 		return -ENOMEM;
 
-	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
+	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, block,
+				   extack);
 	cls_mall.command = add ?
 		TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY;
 	cls_mall.cookie = (unsigned long)head;
@@ -328,7 +331,8 @@ static void mall_stats_hw_filter(struct tcf_proto *tp,
 	struct tc_cls_matchall_offload cls_mall = {};
 	struct tcf_block *block = tp->chain->block;
 
-	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, NULL);
+	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, block,
+				   NULL);
 	cls_mall.command = TC_CLSMATCHALL_STATS;
 	cls_mall.cookie = cookie;
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 4b8710a266cc..2feed0ffa269 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -485,7 +485,8 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
 	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, h->flags, extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, h->flags, block,
+				   extack);
 	cls_u32.command = TC_CLSU32_DELETE_HNODE;
 	cls_u32.hnode.divisor = h->divisor;
 	cls_u32.hnode.handle = h->handle;
@@ -503,7 +504,7 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
 	bool offloaded = false;
 	int err;
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, flags, extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, flags, block, extack);
 	cls_u32.command = TC_CLSU32_NEW_HNODE;
 	cls_u32.hnode.divisor = h->divisor;
 	cls_u32.hnode.handle = h->handle;
@@ -529,7 +530,8 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, block,
+				   extack);
 	cls_u32.command = TC_CLSU32_DELETE_KNODE;
 	cls_u32.knode.handle = n->handle;
 
@@ -546,7 +548,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	bool skip_sw = tc_skip_sw(flags);
 	int err;
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, flags, extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, flags, block, extack);
 	cls_u32.command = TC_CLSU32_REPLACE_KNODE;
 	cls_u32.knode.handle = n->handle;
 	cls_u32.knode.fshift = n->fshift;
@@ -1170,10 +1172,12 @@ static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 			       bool add, tc_setup_cb_t *cb, void *cb_priv,
 			       struct netlink_ext_ack *extack)
 {
+	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 	int err;
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, ht->flags, extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, ht->flags, block,
+				   extack);
 	cls_u32.command = add ? TC_CLSU32_NEW_HNODE : TC_CLSU32_DELETE_HNODE;
 	cls_u32.hnode.divisor = ht->divisor;
 	cls_u32.hnode.handle = ht->handle;
@@ -1195,7 +1199,8 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	struct tc_cls_u32_offload cls_u32 = {};
 	int err;
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, block,
+				   extack);
 	cls_u32.command = add ?
 		TC_CLSU32_REPLACE_KNODE : TC_CLSU32_DELETE_KNODE;
 	cls_u32.knode.handle = n->handle;
-- 
cgit v1.2.3


From f9bbe4477c30ece44296437ee26142b42ef8070b Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 5 May 2019 13:19:22 +0300
Subject: net: dsa: Optional VLAN-based port separation for switches without
 tagging

This patch provides generic DSA code for using VLAN (802.1Q) tags for
the same purpose as a dedicated switch tag for injection/extraction.
It is based on the discussions and interest that has been so far
expressed in https://www.spinics.net/lists/netdev/msg556125.html.

Unlike all other DSA-supported tagging protocols, CONFIG_NET_DSA_TAG_8021Q
does not offer a complete solution for drivers (nor can it). Instead, it
provides generic code that driver can opt into calling:
- dsa_8021q_xmit: Inserts a VLAN header with the specified contents.
  Can be called from another tagging protocol's xmit function.
  Currently the LAN9303 driver is inserting headers that are simply
  802.1Q with custom fields, so this is an opportunity for code reuse.
- dsa_8021q_rcv: Retrieves the TPID and TCI from a VLAN-tagged skb.
  Removing the VLAN header is left as a decision for the caller to make.
- dsa_port_setup_8021q_tagging: For each user port, installs an Rx VID
  and a Tx VID, for proper untagged traffic identification on ingress
  and steering on egress. Also sets up the VLAN trunk on the upstream
  (CPU or DSA) port. Drivers are intentionally left to call this
  function explicitly, depending on the context and hardware support.
  The expected switch behavior and VLAN semantics should not be violated
  under any conditions. That is, after calling
  dsa_port_setup_8021q_tagging, the hardware should still pass all
  ingress traffic, be it tagged or untagged.

For uniformity with the other tagging protocols, a module for the
dsa_8021q_netdev_ops structure is registered, but the typical usage is
to set up another tagging protocol which selects CONFIG_NET_DSA_TAG_8021Q,
and calls the API from tag_8021q.h. Null function definitions are also
provided so that a "depends on" is not forced in the Kconfig.

This tagging protocol only works when switch ports are standalone, or
when they are added to a VLAN-unaware bridge. It will probably remain
this way for the reasons below.

When added to a bridge that has vlan_filtering 1, the bridge core will
install its own VLANs and reset the pvids through switchdev. For the
bridge core, switchdev is a write-only pipe. All VLAN-related state is
kept in the bridge core and nothing is read from DSA/switchdev or from
the driver. So the bridge core will break this port separation because
it will install the vlan_default_pvid into all switchdev ports.

Even if we could teach the bridge driver about switchdev preference of a
certain vlan_default_pvid (task difficult in itself since the current
setting is per-bridge but we would need it per-port), there would still
exist many other challenges.

Firstly, in the DSA rcv callback, a driver would have to perform an
iterative reverse lookup to find the correct switch port. That is
because the port is a bridge slave, so its Rx VID (port PVID) is subject
to user configuration. How would we ensure that the user doesn't reset
the pvid to a different value (which would make an O(1) translation
impossible), or to a non-unique value within this DSA switch tree (which
would make any translation impossible)?

Finally, not all switch ports are equal in DSA, and that makes it
difficult for the bridge to be completely aware of this anyway.
The CPU port needs to transmit tagged packets (VLAN trunk) in order for
the DSA rcv code to be able to decode source information.
But the bridge code has absolutely no idea which switch port is the CPU
port, if nothing else then just because there is no netdevice registered
by DSA for the CPU port.
Also DSA does not currently allow the user to specify that they want the
CPU port to do VLAN trunking anyway. VLANs are added to the CPU port
using the same flags as they were added on the user port.

So the VLANs installed by dsa_port_setup_8021q_tagging per driver
request should remain private from the bridge's and user's perspective,
and should not alter the VLAN semantics observed by the user.

In the current implementation a VLAN range ending at 4095 (VLAN_N_VID)
is reserved for this purpose. Each port receives a unique Rx VLAN and a
unique Tx VLAN. Separate VLANs are needed for Rx and Tx because they
serve different purposes: on Rx the switch must process traffic as
untagged and process it with a port-based VLAN, but with care not to
hinder bridging. On the other hand, the Tx VLAN is where the
reachability restrictions are imposed, since by tagging frames in the
xmit callback we are telling the switch onto which port to steer the
frame.

Some general guidance on how this support might be employed for
real-life hardware (some comments made by Florian Fainelli):

- If the hardware supports VLAN tag stacking, it should somehow back
  up its private VLAN settings when the bridge tries to override them.
  Then the driver could re-apply them as outer tags. Dedicating an outer
  tag per bridge device would allow identical inner tag VID numbers to
  co-exist, yet preserve broadcast domain isolation.

- If the switch cannot handle VLAN tag stacking, it should disable this
  port separation when added as slave to a vlan_filtering bridge, in
  that case having reduced functionality.

- Drivers for old switches that don't support the entire VLAN_N_VID
  range will need to rework the current range selection mechanism.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/dsa/8021q.h |  76 ++++++++++++++++
 include/net/dsa.h         |   2 +
 net/dsa/Kconfig           |  11 +++
 net/dsa/Makefile          |   1 +
 net/dsa/tag_8021q.c       | 222 ++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 312 insertions(+)
 create mode 100644 include/linux/dsa/8021q.h
 create mode 100644 net/dsa/tag_8021q.c

(limited to 'include')

diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
new file mode 100644
index 000000000000..3911e0586478
--- /dev/null
+++ b/include/linux/dsa/8021q.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+
+#ifndef _NET_DSA_8021Q_H
+#define _NET_DSA_8021Q_H
+
+#include <linux/types.h>
+
+struct dsa_switch;
+struct sk_buff;
+struct net_device;
+struct packet_type;
+
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q)
+
+int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index,
+				 bool enabled);
+
+struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
+			       u16 tpid, u16 tci);
+
+struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev,
+			      struct packet_type *pt, u16 *tpid, u16 *tci);
+
+u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port);
+
+u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port);
+
+int dsa_8021q_rx_switch_id(u16 vid);
+
+int dsa_8021q_rx_source_port(u16 vid);
+
+#else
+
+int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index,
+				 bool enabled)
+{
+	return 0;
+}
+
+struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
+			       u16 tpid, u16 tci)
+{
+	return NULL;
+}
+
+struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev,
+			      struct packet_type *pt, u16 *tpid, u16 *tci)
+{
+	return NULL;
+}
+
+u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port)
+{
+	return 0;
+}
+
+u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port)
+{
+	return 0;
+}
+
+int dsa_8021q_rx_switch_id(u16 vid)
+{
+	return 0;
+}
+
+int dsa_8021q_rx_source_port(u16 vid)
+{
+	return 0;
+}
+
+#endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */
+
+#endif /* _NET_DSA_8021Q_H */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 18db7b8e7a8e..69f3714f42ba 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -42,6 +42,7 @@ struct phylink_link_state;
 #define DSA_TAG_PROTO_MTK_VALUE			9
 #define DSA_TAG_PROTO_QCA_VALUE			10
 #define DSA_TAG_PROTO_TRAILER_VALUE		11
+#define DSA_TAG_PROTO_8021Q_VALUE		12
 
 enum dsa_tag_protocol {
 	DSA_TAG_PROTO_NONE		= DSA_TAG_PROTO_NONE_VALUE,
@@ -56,6 +57,7 @@ enum dsa_tag_protocol {
 	DSA_TAG_PROTO_MTK		= DSA_TAG_PROTO_MTK_VALUE,
 	DSA_TAG_PROTO_QCA		= DSA_TAG_PROTO_QCA_VALUE,
 	DSA_TAG_PROTO_TRAILER		= DSA_TAG_PROTO_TRAILER_VALUE,
+	DSA_TAG_PROTO_8021Q		= DSA_TAG_PROTO_8021Q_VALUE,
 };
 
 struct packet_type;
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index c0734028c7dc..fc15a7e1a6df 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -17,6 +17,17 @@ menuconfig NET_DSA
 
 if NET_DSA
 
+# tagging formats
+config NET_DSA_TAG_8021Q
+	tristate "Tag driver for switches using custom 802.1Q VLAN headers"
+	select VLAN_8021Q
+	help
+	  Unlike the other tagging protocols, the 802.1Q config option simply
+	  provides helpers for other tagging implementations that might rely on
+	  VLAN in one way or another. It is not a complete solution.
+
+	  Drivers which use these helpers should select this as dependency.
+
 config NET_DSA_TAG_BRCM_COMMON
 	tristate
 	default n
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 8a737b6ee94c..e97c794ec57b 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_NET_DSA) += dsa_core.o
 dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o
 
 # tagging formats
+obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o
 obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o
 obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
 obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
new file mode 100644
index 000000000000..8ae48c7e1e76
--- /dev/null
+++ b/net/dsa/tag_8021q.c
@@ -0,0 +1,222 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+ *
+ * This module is not a complete tagger implementation. It only provides
+ * primitives for taggers that rely on 802.1Q VLAN tags to use. The
+ * dsa_8021q_netdev_ops is registered for API compliance and not used
+ * directly by callers.
+ */
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+
+#include "dsa_priv.h"
+
+/* Allocating two VLAN tags per port - one for the RX VID and
+ * the other for the TX VID - see below
+ */
+#define DSA_8021Q_VID_RANGE	(DSA_MAX_SWITCHES * DSA_MAX_PORTS)
+#define DSA_8021Q_VID_BASE	(VLAN_N_VID - 2 * DSA_8021Q_VID_RANGE - 1)
+#define DSA_8021Q_RX_VID_BASE	(DSA_8021Q_VID_BASE)
+#define DSA_8021Q_TX_VID_BASE	(DSA_8021Q_VID_BASE + DSA_8021Q_VID_RANGE)
+
+/* Returns the VID to be inserted into the frame from xmit for switch steering
+ * instructions on egress. Encodes switch ID and port ID.
+ */
+u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port)
+{
+	return DSA_8021Q_TX_VID_BASE + (DSA_MAX_PORTS * ds->index) + port;
+}
+EXPORT_SYMBOL_GPL(dsa_8021q_tx_vid);
+
+/* Returns the VID that will be installed as pvid for this switch port, sent as
+ * tagged egress towards the CPU port and decoded by the rcv function.
+ */
+u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port)
+{
+	return DSA_8021Q_RX_VID_BASE + (DSA_MAX_PORTS * ds->index) + port;
+}
+EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid);
+
+/* Returns the decoded switch ID from the RX VID. */
+int dsa_8021q_rx_switch_id(u16 vid)
+{
+	return ((vid - DSA_8021Q_RX_VID_BASE) / DSA_MAX_PORTS);
+}
+EXPORT_SYMBOL_GPL(dsa_8021q_rx_switch_id);
+
+/* Returns the decoded port ID from the RX VID. */
+int dsa_8021q_rx_source_port(u16 vid)
+{
+	return ((vid - DSA_8021Q_RX_VID_BASE) % DSA_MAX_PORTS);
+}
+EXPORT_SYMBOL_GPL(dsa_8021q_rx_source_port);
+
+/* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single
+ * front-panel switch port (here swp0).
+ *
+ * Port identification through VLAN (802.1Q) tags has different requirements
+ * for it to work effectively:
+ *  - On RX (ingress from network): each front-panel port must have a pvid
+ *    that uniquely identifies it, and the egress of this pvid must be tagged
+ *    towards the CPU port, so that software can recover the source port based
+ *    on the VID in the frame. But this would only work for standalone ports;
+ *    if bridged, this VLAN setup would break autonomous forwarding and would
+ *    force all switched traffic to pass through the CPU. So we must also make
+ *    the other front-panel ports members of this VID we're adding, albeit
+ *    we're not making it their PVID (they'll still have their own).
+ *    By the way - just because we're installing the same VID in multiple
+ *    switch ports doesn't mean that they'll start to talk to one another, even
+ *    while not bridged: the final forwarding decision is still an AND between
+ *    the L2 forwarding information (which is limiting forwarding in this case)
+ *    and the VLAN-based restrictions (of which there are none in this case,
+ *    since all ports are members).
+ *  - On TX (ingress from CPU and towards network) we are faced with a problem.
+ *    If we were to tag traffic (from within DSA) with the port's pvid, all
+ *    would be well, assuming the switch ports were standalone. Frames would
+ *    have no choice but to be directed towards the correct front-panel port.
+ *    But because we also want the RX VLAN to not break bridging, then
+ *    inevitably that means that we have to give them a choice (of what
+ *    front-panel port to go out on), and therefore we cannot steer traffic
+ *    based on the RX VID. So what we do is simply install one more VID on the
+ *    front-panel and CPU ports, and profit off of the fact that steering will
+ *    work just by virtue of the fact that there is only one other port that's
+ *    a member of the VID we're tagging the traffic with - the desired one.
+ *
+ * So at the end, each front-panel port will have one RX VID (also the PVID),
+ * the RX VID of all other front-panel ports, and one TX VID. Whereas the CPU
+ * port will have the RX and TX VIDs of all front-panel ports, and on top of
+ * that, is also tagged-input and tagged-output (VLAN trunk).
+ *
+ *               CPU port                               CPU port
+ * +-------------+-----+-------------+    +-------------+-----+-------------+
+ * |  RX VID     |     |             |    |  TX VID     |     |             |
+ * |  of swp0    |     |             |    |  of swp0    |     |             |
+ * |             +-----+             |    |             +-----+             |
+ * |                ^ T              |    |                | Tagged         |
+ * |                |                |    |                | ingress        |
+ * |    +-------+---+---+-------+    |    |    +-----------+                |
+ * |    |       |       |       |    |    |    | Untagged                   |
+ * |    |     U v     U v     U v    |    |    v egress                     |
+ * | +-----+ +-----+ +-----+ +-----+ |    | +-----+ +-----+ +-----+ +-----+ |
+ * | |     | |     | |     | |     | |    | |     | |     | |     | |     | |
+ * | |PVID | |     | |     | |     | |    | |     | |     | |     | |     | |
+ * +-+-----+-+-----+-+-----+-+-----+-+    +-+-----+-+-----+-+-----+-+-----+-+
+ *   swp0    swp1    swp2    swp3           swp0    swp1    swp2    swp3
+ */
+int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled)
+{
+	int upstream = dsa_upstream_port(ds, port);
+	struct dsa_port *dp = &ds->ports[port];
+	struct dsa_port *upstream_dp = &ds->ports[upstream];
+	u16 rx_vid = dsa_8021q_rx_vid(ds, port);
+	u16 tx_vid = dsa_8021q_tx_vid(ds, port);
+	int i, err;
+
+	/* The CPU port is implicitly configured by
+	 * configuring the front-panel ports
+	 */
+	if (!dsa_is_user_port(ds, port))
+		return 0;
+
+	/* Add this user port's RX VID to the membership list of all others
+	 * (including itself). This is so that bridging will not be hindered.
+	 * L2 forwarding rules still take precedence when there are no VLAN
+	 * restrictions, so there are no concerns about leaking traffic.
+	 */
+	for (i = 0; i < ds->num_ports; i++) {
+		struct dsa_port *other_dp = &ds->ports[i];
+		u16 flags;
+
+		if (i == upstream)
+			/* CPU port needs to see this port's RX VID
+			 * as tagged egress.
+			 */
+			flags = 0;
+		else if (i == port)
+			/* The RX VID is pvid on this port */
+			flags = BRIDGE_VLAN_INFO_UNTAGGED |
+				BRIDGE_VLAN_INFO_PVID;
+		else
+			/* The RX VID is a regular VLAN on all others */
+			flags = BRIDGE_VLAN_INFO_UNTAGGED;
+
+		if (enabled)
+			err = dsa_port_vid_add(other_dp, rx_vid, flags);
+		else
+			err = dsa_port_vid_del(other_dp, rx_vid);
+		if (err) {
+			dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n",
+				rx_vid, port, err);
+			return err;
+		}
+	}
+	/* Finally apply the TX VID on this port and on the CPU port */
+	if (enabled)
+		err = dsa_port_vid_add(dp, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED);
+	else
+		err = dsa_port_vid_del(dp, tx_vid);
+	if (err) {
+		dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n",
+			tx_vid, port, err);
+		return err;
+	}
+	if (enabled)
+		err = dsa_port_vid_add(upstream_dp, tx_vid, 0);
+	else
+		err = dsa_port_vid_del(upstream_dp, tx_vid);
+	if (err) {
+		dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n",
+			tx_vid, upstream, err);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dsa_port_setup_8021q_tagging);
+
+struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev,
+			       u16 tpid, u16 tci)
+{
+	/* skb->data points at skb_mac_header, which
+	 * is fine for vlan_insert_tag.
+	 */
+	return vlan_insert_tag(skb, htons(tpid), tci);
+}
+EXPORT_SYMBOL_GPL(dsa_8021q_xmit);
+
+struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev,
+			      struct packet_type *pt, u16 *tpid, u16 *tci)
+{
+	struct vlan_ethhdr *tag;
+
+	if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
+		return NULL;
+
+	tag = vlan_eth_hdr(skb);
+	*tpid = ntohs(tag->h_vlan_proto);
+	*tci = ntohs(tag->h_vlan_TCI);
+
+	/* skb->data points in the middle of the VLAN tag,
+	 * after tpid and before tci. This is because so far,
+	 * ETH_HLEN (DMAC, SMAC, EtherType) bytes were pulled.
+	 * There are 2 bytes of VLAN tag left in skb->data, and upper
+	 * layers expect the 'real' EtherType to be consumed as well.
+	 * Coincidentally, a VLAN header is also of the same size as
+	 * the number of bytes that need to be pulled.
+	 */
+	skb_pull_rcsum(skb, VLAN_HLEN);
+
+	return skb;
+}
+EXPORT_SYMBOL_GPL(dsa_8021q_rcv);
+
+static const struct dsa_device_ops dsa_8021q_netdev_ops = {
+	.name		= "8021q",
+	.proto		= DSA_TAG_PROTO_8021Q,
+	.overhead	= VLAN_HLEN,
+};
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_8021Q);
+
+module_dsa_tag_driver(dsa_8021q_netdev_ops);
-- 
cgit v1.2.3


From cc1939e4b3aaf534fb2f3706820012036825731c Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 5 May 2019 13:19:23 +0300
Subject: net: dsa: Allow drivers to filter packets they can decode source port
 from

Frames get processed by DSA and redirected to switch port net devices
based on the ETH_P_XDSA multiplexed packet_type handler found by the
network stack when calling eth_type_trans().

The running assumption is that once the DSA .rcv function is called, DSA
is always able to decode the switch tag in order to change the skb->dev
from its master.

However there are tagging protocols (such as the new DSA_TAG_PROTO_SJA1105,
user of DSA_TAG_PROTO_8021Q) where this assumption is not completely
true, since switch tagging piggybacks on the absence of a vlan_filtering
bridge. Moreover, management traffic (BPDU, PTP) for this switch doesn't
rely on switch tagging, but on a different mechanism. So it would make
sense to at least be able to terminate that.

Having DSA receive traffic it can't decode would put it in an impossible
situation: the eth_type_trans() function would invoke the DSA .rcv(),
which could not change skb->dev, then eth_type_trans() would be invoked
again, which again would call the DSA .rcv, and the packet would never
be able to exit the DSA filter and would spiral in a loop until the
whole system dies.

This happens because eth_type_trans() doesn't actually look at the skb
(so as to identify a potential tag) when it deems it as being
ETH_P_XDSA. It just checks whether skb->dev has a DSA private pointer
installed (therefore it's a DSA master) and that there exists a .rcv
callback (everybody except DSA_TAG_PROTO_NONE has that). This is
understandable as there are many switch tags out there, and exhaustively
checking for all of them is far from ideal.

The solution lies in introducing a filtering function for each tagging
protocol. In the absence of a filtering function, all traffic is passed
to the .rcv DSA callback. The tagging protocol should see the filtering
function as a pre-validation that it can decode the incoming skb. The
traffic that doesn't match the filter will bypass the DSA .rcv callback
and be left on the master netdevice, which wasn't previously possible.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h  | 15 +++++++++++++++
 net/dsa/dsa2.c     |  1 +
 net/ethernet/eth.c |  6 +++++-
 3 files changed, 21 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 69f3714f42ba..c90ceeec7d1f 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -69,6 +69,11 @@ struct dsa_device_ops {
 			       struct packet_type *pt);
 	int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto,
 			    int *offset);
+	/* Used to determine which traffic should match the DSA filter in
+	 * eth_type_trans, and which, if any, should bypass it and be processed
+	 * as regular on the master net device.
+	 */
+	bool (*filter)(const struct sk_buff *skb, struct net_device *dev);
 	unsigned int overhead;
 	const char *name;
 	enum dsa_tag_protocol proto;
@@ -148,6 +153,7 @@ struct dsa_port {
 	struct dsa_switch_tree *dst;
 	struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev,
 			       struct packet_type *pt);
+	bool (*filter)(const struct sk_buff *skb, struct net_device *dev);
 
 	enum {
 		DSA_PORT_TYPE_UNUSED = 0,
@@ -520,6 +526,15 @@ static inline bool netdev_uses_dsa(struct net_device *dev)
 	return false;
 }
 
+static inline bool dsa_can_decode(const struct sk_buff *skb,
+				  struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	return !dev->dsa_ptr->filter || dev->dsa_ptr->filter(skb, dev);
+#endif
+	return false;
+}
+
 struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n);
 void dsa_unregister_switch(struct dsa_switch *ds);
 int dsa_register_switch(struct dsa_switch *ds);
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index f1ad80851616..3b5f434cad3f 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -586,6 +586,7 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master)
 	}
 
 	dp->type = DSA_PORT_TYPE_CPU;
+	dp->filter = tag_ops->filter;
 	dp->rcv = tag_ops->rcv;
 	dp->tag_ops = tag_ops;
 	dp->master = master;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 0f9863dc4d44..fddcee38c1da 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -185,8 +185,12 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
 	 * at all, so we check here whether one of those tagging
 	 * variants has been configured on the receiving interface,
 	 * and if so, set skb->protocol without looking at the packet.
+	 * The DSA tagging protocol may be able to decode some but not all
+	 * traffic (for example only for management). In that case give it the
+	 * option to filter the packets from which it can decode source port
+	 * information.
 	 */
-	if (unlikely(netdev_uses_dsa(dev)))
+	if (unlikely(netdev_uses_dsa(dev)) && dsa_can_decode(skb, dev))
 		return htons(ETH_P_XDSA);
 
 	if (likely(eth_proto_is_802_3(eth->h_proto)))
-- 
cgit v1.2.3


From b68b0dd0fb2d91056d5241a19960cf47d4a80f05 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 5 May 2019 13:19:24 +0300
Subject: net: dsa: Keep private info in the skb->cb

Map a DSA structure over the 48-byte control block that will hold
skb info on transmit and receive. This is only for use within the DSA
processing layer (e.g. communicating between DSA core and tagger) and
not for passing info around with other layers such as the master net
device.

Also add a DSA_SKB_CB_PRIV() macro which retrieves a pointer to the
space up to 48 bytes that the DSA structure does not use. This space can
be used for drivers to add their own private info.

One use is for the PTP timestamping code path. When cloning a skb,
annotate the original with a pointer to the clone, which the driver can
then find easily and place the timestamp to. This avoids the need of a
separate queue to hold clones and a way to match an original to a cloned
skb.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index c90ceeec7d1f..d628587e0bde 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -83,6 +83,37 @@ struct dsa_device_ops {
 #define MODULE_ALIAS_DSA_TAG_DRIVER(__proto)				\
 	MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __stringify(__proto##_VALUE))
 
+struct dsa_skb_cb {
+	struct sk_buff *clone;
+};
+
+struct __dsa_skb_cb {
+	struct dsa_skb_cb cb;
+	u8 priv[48 - sizeof(struct dsa_skb_cb)];
+};
+
+#define __DSA_SKB_CB(skb) ((struct __dsa_skb_cb *)((skb)->cb))
+
+#define DSA_SKB_CB(skb) ((struct dsa_skb_cb *)((skb)->cb))
+
+#define DSA_SKB_CB_COPY(nskb, skb)		\
+	{ *__DSA_SKB_CB(nskb) = *__DSA_SKB_CB(skb); }
+
+#define DSA_SKB_CB_ZERO(skb)			\
+	{ *__DSA_SKB_CB(skb) = (struct __dsa_skb_cb) {0}; }
+
+#define DSA_SKB_CB_PRIV(skb)			\
+	((void *)(skb)->cb + offsetof(struct __dsa_skb_cb, priv))
+
+#define DSA_SKB_CB_CLONE(_clone, _skb)		\
+	{					\
+		struct sk_buff *clone = _clone;	\
+		struct sk_buff *skb = _skb;	\
+						\
+		DSA_SKB_CB_COPY(clone, skb);	\
+		DSA_SKB_CB(skb)->clone = clone; \
+	}
+
 struct dsa_switch_tree {
 	struct list_head	list;
 
-- 
cgit v1.2.3


From 97a69a0dea9a048c6769249f1552de5f56731524 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 5 May 2019 13:19:25 +0300
Subject: net: dsa: Add support for deferred xmit

Some hardware needs to take work to get convinced to receive frames on
the CPU port (such as the sja1105 which takes temporary L2 forwarding
rules over SPI that last for a single frame). Such work needs a
sleepable context, and because the regular .ndo_start_xmit is atomic,
this cannot be done in the tagger. So introduce a generic DSA mechanism
that sets up a transmit skb queue and a workqueue for deferred
transmission.

The new driver callback (.port_deferred_xmit) is in dsa_switch and not
in the tagger because the operations that require sleeping typically
also involve interacting with the hardware, and not simply skb
manipulations. Therefore having it there simplifies the structure a bit
and makes it unnecessary to export functions from the driver to the
tagger.

The driver is responsible of calling dsa_enqueue_skb which transfers it
to the master netdevice. This is so that it has a chance of performing
some more work afterwards, such as cleanup or TX timestamping.

To tell DSA that skb xmit deferral is required, I have thought about
changing the return type of the tagger .xmit from struct sk_buff * into
a enum dsa_tx_t that could potentially encode a DSA_XMIT_DEFER value.

But the trailer tagger is reallocating every skb on xmit and therefore
making a valid use of the pointer return value. So instead of reworking
the API in complicated ways, right now a boolean property in the newly
introduced DSA_SKB_CB is set.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h  | 12 ++++++++++
 net/dsa/dsa_priv.h |  2 ++
 net/dsa/slave.c    | 64 ++++++++++++++++++++++++++++++++++++++++++++----------
 3 files changed, 66 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index d628587e0bde..0260b73938e2 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -85,6 +85,7 @@ struct dsa_device_ops {
 
 struct dsa_skb_cb {
 	struct sk_buff *clone;
+	bool deferred_xmit;
 };
 
 struct __dsa_skb_cb {
@@ -205,6 +206,10 @@ struct dsa_port {
 	struct net_device	*bridge_dev;
 	struct devlink_port	devlink_port;
 	struct phylink		*pl;
+
+	struct work_struct	xmit_work;
+	struct sk_buff_head	xmit_queue;
+
 	/*
 	 * Original copy of the master netdev ethtool_ops
 	 */
@@ -539,6 +544,12 @@ struct dsa_switch_ops {
 				 struct sk_buff *clone, unsigned int type);
 	bool	(*port_rxtstamp)(struct dsa_switch *ds, int port,
 				 struct sk_buff *skb, unsigned int type);
+
+	/*
+	 * Deferred frame Tx
+	 */
+	netdev_tx_t (*port_deferred_xmit)(struct dsa_switch *ds, int port,
+					  struct sk_buff *skb);
 };
 
 struct dsa_switch_driver {
@@ -634,6 +645,7 @@ static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev,
 #define BRCM_TAG_GET_QUEUE(v)		((v) & 0xff)
 
 
+netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev);
 int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data);
 int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data);
 int dsa_port_get_phy_sset_count(struct dsa_port *dp);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index b434f5ff55ab..8f1222324646 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -174,6 +174,8 @@ int dsa_slave_resume(struct net_device *slave_dev);
 int dsa_slave_register_notifier(void);
 void dsa_slave_unregister_notifier(void);
 
+void *dsa_defer_xmit(struct sk_buff *skb, struct net_device *dev);
+
 static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 6ce2fdb64db0..316bce9e0fbf 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -120,6 +120,9 @@ static int dsa_slave_close(struct net_device *dev)
 	struct net_device *master = dsa_slave_to_master(dev);
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 
+	cancel_work_sync(&dp->xmit_work);
+	skb_queue_purge(&dp->xmit_queue);
+
 	phylink_stop(dp->pl);
 
 	dsa_port_disable(dp);
@@ -430,6 +433,24 @@ static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p,
 	kfree_skb(clone);
 }
 
+netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev)
+{
+	/* SKB for netpoll still need to be mangled with the protocol-specific
+	 * tag to be successfully transmitted
+	 */
+	if (unlikely(netpoll_tx_running(dev)))
+		return dsa_slave_netpoll_send_skb(dev, skb);
+
+	/* Queue the SKB for transmission on the parent interface, but
+	 * do not modify its EtherType
+	 */
+	skb->dev = dsa_slave_to_master(dev);
+	dev_queue_xmit(skb);
+
+	return NETDEV_TX_OK;
+}
+EXPORT_SYMBOL_GPL(dsa_enqueue_skb);
+
 static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -452,23 +473,37 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	nskb = p->xmit(skb, dev);
 	if (!nskb) {
-		kfree_skb(skb);
+		if (!DSA_SKB_CB(skb)->deferred_xmit)
+			kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
 
-	/* SKB for netpoll still need to be mangled with the protocol-specific
-	 * tag to be successfully transmitted
-	 */
-	if (unlikely(netpoll_tx_running(dev)))
-		return dsa_slave_netpoll_send_skb(dev, nskb);
+	return dsa_enqueue_skb(nskb, dev);
+}
 
-	/* Queue the SKB for transmission on the parent interface, but
-	 * do not modify its EtherType
-	 */
-	nskb->dev = dsa_slave_to_master(dev);
-	dev_queue_xmit(nskb);
+void *dsa_defer_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
 
-	return NETDEV_TX_OK;
+	DSA_SKB_CB(skb)->deferred_xmit = true;
+
+	skb_queue_tail(&dp->xmit_queue, skb);
+	schedule_work(&dp->xmit_work);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(dsa_defer_xmit);
+
+static void dsa_port_xmit_work(struct work_struct *work)
+{
+	struct dsa_port *dp = container_of(work, struct dsa_port, xmit_work);
+	struct dsa_switch *ds = dp->ds;
+	struct sk_buff *skb;
+
+	if (unlikely(!ds->ops->port_deferred_xmit))
+		return;
+
+	while ((skb = skb_dequeue(&dp->xmit_queue)) != NULL)
+		ds->ops->port_deferred_xmit(ds, dp->index, skb);
 }
 
 /* ethtool operations *******************************************************/
@@ -1318,6 +1353,9 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 	if (!netif_running(slave_dev))
 		return 0;
 
+	cancel_work_sync(&dp->xmit_work);
+	skb_queue_purge(&dp->xmit_queue);
+
 	netif_device_detach(slave_dev);
 
 	rtnl_lock();
@@ -1405,6 +1443,8 @@ int dsa_slave_create(struct dsa_port *port)
 	}
 	p->dp = port;
 	INIT_LIST_HEAD(&p->mall_tc_list);
+	INIT_WORK(&port->xmit_work, dsa_port_xmit_work);
+	skb_queue_head_init(&port->xmit_queue);
 	p->xmit = cpu_dp->tag_ops->xmit;
 	port->slave = slave_dev;
 
-- 
cgit v1.2.3


From c362beb072e14b929eb657dc174d83ccdd9b0eed Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 5 May 2019 13:19:26 +0300
Subject: net: dsa: Add a private structure pointer to dsa_port

This is supposed to share information between the driver and the tagger,
or used by the tagger to keep some state. Its use is optional.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/net/dsa.h b/include/net/dsa.h
index 0260b73938e2..e20be1ceb306 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -210,6 +210,12 @@ struct dsa_port {
 	struct work_struct	xmit_work;
 	struct sk_buff_head	xmit_queue;
 
+	/*
+	 * Give the switch driver somewhere to hang its per-port private data
+	 * structures (accessible from the tagger).
+	 */
+	void *priv;
+
 	/*
 	 * Original copy of the master netdev ethtool_ops
 	 */
-- 
cgit v1.2.3


From 227d07a07ef126272ea2eed97fd136cd7a803d81 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 5 May 2019 13:19:27 +0300
Subject: net: dsa: sja1105: Add support for traffic through standalone ports

In order to support this, we are creating a make-shift switch tag out of
a VLAN trunk configured on the CPU port. Termination of normal traffic
on switch ports only works when not under a vlan_filtering bridge.
Termination of management (PTP, BPDU) traffic works under all
circumstances because it uses a different tagging mechanism
(incl_srcpt). We are making use of the generic CONFIG_NET_DSA_TAG_8021Q
code and leveraging it from our own CONFIG_NET_DSA_TAG_SJA1105.

There are two types of traffic: regular and link-local.

The link-local traffic received on the CPU port is trapped from the
switch's regular forwarding decisions because it matched one of the two
DMAC filters for management traffic.

On transmission, the switch requires special massaging for these
link-local frames. Due to a weird implementation of the switching IP, by
default it drops link-local frames that originate on the CPU port.
It needs to be told where to forward them to, through an SPI command
("management route") that is valid for only a single frame.
So when we're sending link-local traffic, we are using the
dsa_defer_xmit mechanism.

Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/Kconfig        |   1 +
 drivers/net/dsa/sja1105/sja1105.h      |   6 ++
 drivers/net/dsa/sja1105/sja1105_main.c | 138 +++++++++++++++++++++++++++++++--
 include/linux/dsa/sja1105.h            |  35 ++++++---
 include/net/dsa.h                      |   2 +
 net/dsa/Kconfig                        |   9 +++
 net/dsa/Makefile                       |   1 +
 net/dsa/tag_sja1105.c                  | 131 +++++++++++++++++++++++++++++++
 8 files changed, 308 insertions(+), 15 deletions(-)
 create mode 100644 net/dsa/tag_sja1105.c

(limited to 'include')

diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig
index 038685bb9d57..757751a89819 100644
--- a/drivers/net/dsa/sja1105/Kconfig
+++ b/drivers/net/dsa/sja1105/Kconfig
@@ -1,6 +1,7 @@
 config NET_DSA_SJA1105
 tristate "NXP SJA1105 Ethernet switch family support"
 	depends on NET_DSA && SPI
+	select NET_DSA_TAG_SJA1105
 	select PACKING
 	select CRC32
 	help
diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index b0a155b57e17..b043bfc408f2 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -7,6 +7,7 @@
 
 #include <linux/dsa/sja1105.h>
 #include <net/dsa.h>
+#include <linux/mutex.h>
 #include "sja1105_static_config.h"
 
 #define SJA1105_NUM_PORTS		5
@@ -65,6 +66,11 @@ struct sja1105_private {
 	struct gpio_desc *reset_gpio;
 	struct spi_device *spidev;
 	struct dsa_switch *ds;
+	struct sja1105_port ports[SJA1105_NUM_PORTS];
+	/* Serializes transmission of management frames so that
+	 * the switch doesn't confuse them with one another.
+	 */
+	struct mutex mgmt_lock;
 };
 
 #include "sja1105_dynamic_config.h"
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 74f8ff9e17e0..785bb42cb993 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -20,6 +20,7 @@
 #include <linux/netdevice.h>
 #include <linux/if_bridge.h>
 #include <linux/if_ether.h>
+#include <linux/dsa/8021q.h>
 #include "sja1105.h"
 
 static void sja1105_hw_reset(struct gpio_desc *gpio, unsigned int pulse_len,
@@ -406,11 +407,14 @@ static int sja1105_init_general_params(struct sja1105_private *priv)
 		.tpid2 = ETH_P_SJA1105,
 	};
 	struct sja1105_table *table;
-	int i;
+	int i, k = 0;
 
-	for (i = 0; i < SJA1105_NUM_PORTS; i++)
+	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
 		if (dsa_is_dsa_port(priv->ds, i))
 			default_general_params.casc_port = i;
+		else if (dsa_is_user_port(priv->ds, i))
+			priv->ports[i].mgmt_slot = k++;
+	}
 
 	table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
 
@@ -1146,10 +1150,27 @@ static int sja1105_vlan_apply(struct sja1105_private *priv, int port, u16 vid,
 	return 0;
 }
 
+static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled)
+{
+	int rc, i;
+
+	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+		rc = dsa_port_setup_8021q_tagging(ds, i, enabled);
+		if (rc < 0) {
+			dev_err(ds->dev, "Failed to setup VLAN tagging for port %d: %d\n",
+				i, rc);
+			return rc;
+		}
+	}
+	dev_info(ds->dev, "%s switch tagging\n",
+		 enabled ? "Enabled" : "Disabled");
+	return 0;
+}
+
 static enum dsa_tag_protocol
 sja1105_get_tag_protocol(struct dsa_switch *ds, int port)
 {
-	return DSA_TAG_PROTO_NONE;
+	return DSA_TAG_PROTO_SJA1105;
 }
 
 /* This callback needs to be present */
@@ -1173,7 +1194,11 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
 	if (rc)
 		dev_err(ds->dev, "Failed to change VLAN Ethertype\n");
 
-	return rc;
+	/* Switch port identification based on 802.1Q is only passable
+	 * if we are not under a vlan_filtering bridge. So make sure
+	 * the two configurations are mutually exclusive.
+	 */
+	return sja1105_setup_8021q_tagging(ds, !enabled);
 }
 
 static void sja1105_vlan_add(struct dsa_switch *ds, int port,
@@ -1276,7 +1301,98 @@ static int sja1105_setup(struct dsa_switch *ds)
 	 */
 	ds->vlan_filtering_is_global = true;
 
-	return 0;
+	/* The DSA/switchdev model brings up switch ports in standalone mode by
+	 * default, and that means vlan_filtering is 0 since they're not under
+	 * a bridge, so it's safe to set up switch tagging at this time.
+	 */
+	return sja1105_setup_8021q_tagging(ds, true);
+}
+
+static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot,
+			     struct sk_buff *skb)
+{
+	struct sja1105_mgmt_entry mgmt_route = {0};
+	struct sja1105_private *priv = ds->priv;
+	struct ethhdr *hdr;
+	int timeout = 10;
+	int rc;
+
+	hdr = eth_hdr(skb);
+
+	mgmt_route.macaddr = ether_addr_to_u64(hdr->h_dest);
+	mgmt_route.destports = BIT(port);
+	mgmt_route.enfport = 1;
+
+	rc = sja1105_dynamic_config_write(priv, BLK_IDX_MGMT_ROUTE,
+					  slot, &mgmt_route, true);
+	if (rc < 0) {
+		kfree_skb(skb);
+		return rc;
+	}
+
+	/* Transfer skb to the host port. */
+	dsa_enqueue_skb(skb, ds->ports[port].slave);
+
+	/* Wait until the switch has processed the frame */
+	do {
+		rc = sja1105_dynamic_config_read(priv, BLK_IDX_MGMT_ROUTE,
+						 slot, &mgmt_route);
+		if (rc < 0) {
+			dev_err_ratelimited(priv->ds->dev,
+					    "failed to poll for mgmt route\n");
+			continue;
+		}
+
+		/* UM10944: The ENFPORT flag of the respective entry is
+		 * cleared when a match is found. The host can use this
+		 * flag as an acknowledgment.
+		 */
+		cpu_relax();
+	} while (mgmt_route.enfport && --timeout);
+
+	if (!timeout) {
+		/* Clean up the management route so that a follow-up
+		 * frame may not match on it by mistake.
+		 */
+		sja1105_dynamic_config_write(priv, BLK_IDX_MGMT_ROUTE,
+					     slot, &mgmt_route, false);
+		dev_err_ratelimited(priv->ds->dev, "xmit timed out\n");
+	}
+
+	return NETDEV_TX_OK;
+}
+
+/* Deferred work is unfortunately necessary because setting up the management
+ * route cannot be done from atomit context (SPI transfer takes a sleepable
+ * lock on the bus)
+ */
+static netdev_tx_t sja1105_port_deferred_xmit(struct dsa_switch *ds, int port,
+					      struct sk_buff *skb)
+{
+	struct sja1105_private *priv = ds->priv;
+	struct sja1105_port *sp = &priv->ports[port];
+	int slot = sp->mgmt_slot;
+
+	/* The tragic fact about the switch having 4x2 slots for installing
+	 * management routes is that all of them except one are actually
+	 * useless.
+	 * If 2 slots are simultaneously configured for two BPDUs sent to the
+	 * same (multicast) DMAC but on different egress ports, the switch
+	 * would confuse them and redirect first frame it receives on the CPU
+	 * port towards the port configured on the numerically first slot
+	 * (therefore wrong port), then second received frame on second slot
+	 * (also wrong port).
+	 * So for all practical purposes, there needs to be a lock that
+	 * prevents that from happening. The slot used here is utterly useless
+	 * (could have simply been 0 just as fine), but we are doing it
+	 * nonetheless, in case a smarter idea ever comes up in the future.
+	 */
+	mutex_lock(&priv->mgmt_lock);
+
+	sja1105_mgmt_xmit(ds, port, slot, skb);
+
+	mutex_unlock(&priv->mgmt_lock);
+	return NETDEV_TX_OK;
 }
 
 /* The MAXAGE setting belongs to the L2 Forwarding Parameters table,
@@ -1324,6 +1440,7 @@ static const struct dsa_switch_ops sja1105_switch_ops = {
 	.port_mdb_prepare	= sja1105_mdb_prepare,
 	.port_mdb_add		= sja1105_mdb_add,
 	.port_mdb_del		= sja1105_mdb_del,
+	.port_deferred_xmit	= sja1105_port_deferred_xmit,
 };
 
 static int sja1105_check_device_id(struct sja1105_private *priv)
@@ -1367,7 +1484,7 @@ static int sja1105_probe(struct spi_device *spi)
 	struct device *dev = &spi->dev;
 	struct sja1105_private *priv;
 	struct dsa_switch *ds;
-	int rc;
+	int rc, i;
 
 	if (!dev->of_node) {
 		dev_err(dev, "No DTS bindings for SJA1105 driver\n");
@@ -1418,6 +1535,15 @@ static int sja1105_probe(struct spi_device *spi)
 	ds->priv = priv;
 	priv->ds = ds;
 
+	/* Connections between dsa_port and sja1105_port */
+	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
+		struct sja1105_port *sp = &priv->ports[i];
+
+		ds->ports[i].priv = sp;
+		sp->dp = &ds->ports[i];
+	}
+	mutex_init(&priv->mgmt_lock);
+
 	return dsa_register_switch(priv->ds);
 }
 
diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h
index abf3977e34fd..603a02e5a8cb 100644
--- a/include/linux/dsa/sja1105.h
+++ b/include/linux/dsa/sja1105.h
@@ -2,22 +2,39 @@
  * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
  */
 
-/* Included by drivers/net/dsa/sja1105/sja1105.h */
+/* Included by drivers/net/dsa/sja1105/sja1105.h and net/dsa/tag_sja1105.c */
 
 #ifndef _NET_DSA_SJA1105_H
 #define _NET_DSA_SJA1105_H
 
+#include <linux/skbuff.h>
 #include <linux/etherdevice.h>
+#include <net/dsa.h>
 
 #define ETH_P_SJA1105				ETH_P_DSA_8021Q
 
-/* The switch can only be convinced to stay in unmanaged mode and not trap any
- * link-local traffic by actually telling it to filter frames sent at the
- * 00:00:00:00:00:00 destination MAC.
- */
-#define SJA1105_LINKLOCAL_FILTER_A		0x000000000000ull
-#define SJA1105_LINKLOCAL_FILTER_A_MASK		0xFFFFFFFFFFFFull
-#define SJA1105_LINKLOCAL_FILTER_B		0x000000000000ull
-#define SJA1105_LINKLOCAL_FILTER_B_MASK		0xFFFFFFFFFFFFull
+/* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */
+#define SJA1105_LINKLOCAL_FILTER_A		0x0180C2000000ull
+#define SJA1105_LINKLOCAL_FILTER_A_MASK		0xFFFFFF000000ull
+/* IEEE 1588 Annex F: Transport of PTP over Ethernet (01:1B:19:xx:xx:xx) */
+#define SJA1105_LINKLOCAL_FILTER_B		0x011B19000000ull
+#define SJA1105_LINKLOCAL_FILTER_B_MASK		0xFFFFFF000000ull
+
+enum sja1105_frame_type {
+	SJA1105_FRAME_TYPE_NORMAL = 0,
+	SJA1105_FRAME_TYPE_LINK_LOCAL,
+};
+
+struct sja1105_skb_cb {
+	enum sja1105_frame_type type;
+};
+
+#define SJA1105_SKB_CB(skb) \
+	((struct sja1105_skb_cb *)DSA_SKB_CB_PRIV(skb))
+
+struct sja1105_port {
+	struct dsa_port *dp;
+	int mgmt_slot;
+};
 
 #endif /* _NET_DSA_SJA1105_H */
diff --git a/include/net/dsa.h b/include/net/dsa.h
index e20be1ceb306..6aaaadd6a413 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -43,6 +43,7 @@ struct phylink_link_state;
 #define DSA_TAG_PROTO_QCA_VALUE			10
 #define DSA_TAG_PROTO_TRAILER_VALUE		11
 #define DSA_TAG_PROTO_8021Q_VALUE		12
+#define DSA_TAG_PROTO_SJA1105_VALUE		13
 
 enum dsa_tag_protocol {
 	DSA_TAG_PROTO_NONE		= DSA_TAG_PROTO_NONE_VALUE,
@@ -58,6 +59,7 @@ enum dsa_tag_protocol {
 	DSA_TAG_PROTO_QCA		= DSA_TAG_PROTO_QCA_VALUE,
 	DSA_TAG_PROTO_TRAILER		= DSA_TAG_PROTO_TRAILER_VALUE,
 	DSA_TAG_PROTO_8021Q		= DSA_TAG_PROTO_8021Q_VALUE,
+	DSA_TAG_PROTO_SJA1105		= DSA_TAG_PROTO_SJA1105_VALUE,
 };
 
 struct packet_type;
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index fc15a7e1a6df..cf855352a440 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -102,6 +102,15 @@ config NET_DSA_TAG_LAN9303
 	  Say Y or M if you want to enable support for tagging frames for the
 	  SMSC/Microchip LAN9303 family of switches.
 
+config NET_DSA_TAG_SJA1105
+	tristate "Tag driver for NXP SJA1105 switches"
+	select NET_DSA_TAG_8021Q
+	help
+	  Say Y or M if you want to enable support for tagging frames with the
+	  NXP SJA1105 switch family. Both the native tagging protocol (which
+	  is only for link-local traffic) as well as non-native tagging (based
+	  on a custom 802.1Q VLAN header) are available.
+
 config NET_DSA_TAG_TRAILER
 	tristate "Tag driver for switches using a trailer tag"
 	help
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index e97c794ec57b..c342f54715ba 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -13,4 +13,5 @@ obj-$(CONFIG_NET_DSA_TAG_KSZ_COMMON) += tag_ksz.o
 obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o
 obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o
 obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o
+obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o
 obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
new file mode 100644
index 000000000000..969402c7dbf1
--- /dev/null
+++ b/net/dsa/tag_sja1105.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+ */
+#include <linux/if_vlan.h>
+#include <linux/dsa/sja1105.h>
+#include <linux/dsa/8021q.h>
+#include <linux/packing.h>
+#include "dsa_priv.h"
+
+/* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */
+static inline bool sja1105_is_link_local(const struct sk_buff *skb)
+{
+	const struct ethhdr *hdr = eth_hdr(skb);
+	u64 dmac = ether_addr_to_u64(hdr->h_dest);
+
+	if ((dmac & SJA1105_LINKLOCAL_FILTER_A_MASK) ==
+		    SJA1105_LINKLOCAL_FILTER_A)
+		return true;
+	if ((dmac & SJA1105_LINKLOCAL_FILTER_B_MASK) ==
+		    SJA1105_LINKLOCAL_FILTER_B)
+		return true;
+	return false;
+}
+
+/* This is the first time the tagger sees the frame on RX.
+ * Figure out if we can decode it, and if we can, annotate skb->cb with how we
+ * plan to do that, so we don't need to check again in the rcv function.
+ */
+static bool sja1105_filter(const struct sk_buff *skb, struct net_device *dev)
+{
+	if (sja1105_is_link_local(skb)) {
+		SJA1105_SKB_CB(skb)->type = SJA1105_FRAME_TYPE_LINK_LOCAL;
+		return true;
+	}
+	if (!dsa_port_is_vlan_filtering(dev->dsa_ptr)) {
+		SJA1105_SKB_CB(skb)->type = SJA1105_FRAME_TYPE_NORMAL;
+		return true;
+	}
+	return false;
+}
+
+static struct sk_buff *sja1105_xmit(struct sk_buff *skb,
+				    struct net_device *netdev)
+{
+	struct dsa_port *dp = dsa_slave_to_port(netdev);
+	struct dsa_switch *ds = dp->ds;
+	u16 tx_vid = dsa_8021q_tx_vid(ds, dp->index);
+	u8 pcp = skb->priority;
+
+	/* Transmitting management traffic does not rely upon switch tagging,
+	 * but instead SPI-installed management routes. Part 2 of this
+	 * is the .port_deferred_xmit driver callback.
+	 */
+	if (unlikely(sja1105_is_link_local(skb)))
+		return dsa_defer_xmit(skb, netdev);
+
+	/* If we are under a vlan_filtering bridge, IP termination on
+	 * switch ports based on 802.1Q tags is simply too brittle to
+	 * be passable. So just defer to the dsa_slave_notag_xmit
+	 * implementation.
+	 */
+	if (dsa_port_is_vlan_filtering(dp))
+		return skb;
+
+	return dsa_8021q_xmit(skb, netdev, ETH_P_SJA1105,
+			     ((pcp << VLAN_PRIO_SHIFT) | tx_vid));
+}
+
+static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
+				   struct net_device *netdev,
+				   struct packet_type *pt)
+{
+	struct ethhdr *hdr = eth_hdr(skb);
+	u64 source_port, switch_id;
+	struct sk_buff *nskb;
+	u16 tpid, vid, tci;
+	bool is_tagged;
+
+	nskb = dsa_8021q_rcv(skb, netdev, pt, &tpid, &tci);
+	is_tagged = (nskb && tpid == ETH_P_SJA1105);
+
+	skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+	vid = tci & VLAN_VID_MASK;
+
+	skb->offload_fwd_mark = 1;
+
+	if (SJA1105_SKB_CB(skb)->type == SJA1105_FRAME_TYPE_LINK_LOCAL) {
+		/* Management traffic path. Switch embeds the switch ID and
+		 * port ID into bytes of the destination MAC, courtesy of
+		 * the incl_srcpt options.
+		 */
+		source_port = hdr->h_dest[3];
+		switch_id = hdr->h_dest[4];
+		/* Clear the DMAC bytes that were mangled by the switch */
+		hdr->h_dest[3] = 0;
+		hdr->h_dest[4] = 0;
+	} else {
+		/* Normal traffic path. */
+		source_port = dsa_8021q_rx_source_port(vid);
+		switch_id = dsa_8021q_rx_switch_id(vid);
+	}
+
+	skb->dev = dsa_master_find_slave(netdev, switch_id, source_port);
+	if (!skb->dev) {
+		netdev_warn(netdev, "Couldn't decode source port\n");
+		return NULL;
+	}
+
+	/* Delete/overwrite fake VLAN header, DSA expects to not find
+	 * it there, see dsa_switch_rcv: skb_push(skb, ETH_HLEN).
+	 */
+	if (is_tagged)
+		memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - VLAN_HLEN,
+			ETH_HLEN - VLAN_HLEN);
+
+	return skb;
+}
+
+static struct dsa_device_ops sja1105_netdev_ops = {
+	.name = "sja1105",
+	.proto = DSA_TAG_PROTO_SJA1105,
+	.xmit = sja1105_xmit,
+	.rcv = sja1105_rcv,
+	.filter = sja1105_filter,
+	.overhead = VLAN_HLEN,
+};
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105);
+
+module_dsa_tag_driver(sja1105_netdev_ops);
-- 
cgit v1.2.3


From d6787147e15dffa7b7f3116a5bc3cbe0670bd74f Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Mon, 6 May 2019 17:24:21 -0700
Subject: net/sched: remove block pointer from common offload structure

Based on feedback from Jiri avoid carrying a pointer to the tcf_block
structure in the tc_cls_common_offload structure. Instead store
a flag in driver private data which indicates if offloads apply
to a shared block at block binding time.

Suggested-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.h     |  2 ++
 drivers/net/ethernet/netronome/nfp/flower/offload.c  |  4 ++++
 drivers/net/ethernet/netronome/nfp/flower/qos_conf.c |  4 ++--
 include/net/pkt_cls.h                                |  3 ---
 net/sched/cls_bpf.c                                  |  8 +++-----
 net/sched/cls_flower.c                               | 11 ++++-------
 net/sched/cls_matchall.c                             | 12 ++++--------
 net/sched/cls_u32.c                                  | 17 ++++++-----------
 8 files changed, 25 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 6a6be7285105..40957a8dbfe6 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -215,6 +215,7 @@ struct nfp_fl_qos {
  * @lag_port_flags:	Extended port flags to record lag state of repr
  * @mac_offloaded:	Flag indicating a MAC address is offloaded for repr
  * @offloaded_mac_addr:	MAC address that has been offloaded for repr
+ * @block_shared:	Flag indicating if offload applies to shared blocks
  * @mac_list:		List entry of reprs that share the same offloaded MAC
  * @qos_table:		Stored info on filters implementing qos
  */
@@ -223,6 +224,7 @@ struct nfp_flower_repr_priv {
 	unsigned long lag_port_flags;
 	bool mac_offloaded;
 	u8 offloaded_mac_addr[ETH_ALEN];
+	bool block_shared;
 	struct list_head mac_list;
 	struct nfp_fl_qos qos_table;
 };
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 9c6bcc6e9d68..1fbfeb43c538 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1197,10 +1197,14 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev,
 				     struct tc_block_offload *f)
 {
 	struct nfp_repr *repr = netdev_priv(netdev);
+	struct nfp_flower_repr_priv *repr_priv;
 
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
+	repr_priv = repr->app_priv;
+	repr_priv->block_shared = tcf_block_shared(f->block);
+
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c b/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
index 1b2ee18d7ff9..86e968cd5ffd 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
@@ -76,8 +76,9 @@ nfp_flower_install_rate_limiter(struct nfp_app *app, struct net_device *netdev,
 		return -EOPNOTSUPP;
 	}
 	repr = netdev_priv(netdev);
+	repr_priv = repr->app_priv;
 
-	if (tcf_block_shared(flow->common.block)) {
+	if (repr_priv->block_shared) {
 		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload not supported on shared blocks");
 		return -EOPNOTSUPP;
 	}
@@ -123,7 +124,6 @@ nfp_flower_install_rate_limiter(struct nfp_app *app, struct net_device *netdev,
 	config->cir = cpu_to_be32(rate);
 	nfp_ctrl_tx(repr->app->ctrl, skb);
 
-	repr_priv = repr->app_priv;
 	repr_priv->qos_table.netdev_port_id = netdev_port_id;
 	fl_priv->qos_rate_limiters++;
 	if (fl_priv->qos_rate_limiters == 1)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index eed98f8fcb5e..514e3c80ecc1 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -629,7 +629,6 @@ struct tc_cls_common_offload {
 	u32 chain_index;
 	__be16 protocol;
 	u32 prio;
-	struct tcf_block *block;
 	struct netlink_ext_ack *extack;
 };
 
@@ -731,13 +730,11 @@ static inline bool tc_in_hw(u32 flags)
 static inline void
 tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common,
 			   const struct tcf_proto *tp, u32 flags,
-			   struct tcf_block *block,
 			   struct netlink_ext_ack *extack)
 {
 	cls_common->chain_index = tp->chain->index;
 	cls_common->protocol = tp->protocol;
 	cls_common->prio = tp->prio;
-	cls_common->block = block;
 	if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE)
 		cls_common->extack = extack;
 }
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index ce7ff286ccb8..27365ed3fe0b 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -157,8 +157,7 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 	skip_sw = prog && tc_skip_sw(prog->gen_flags);
 	obj = prog ?: oldprog;
 
-	tc_cls_common_offload_init(&cls_bpf.common, tp, obj->gen_flags, block,
-				   extack);
+	tc_cls_common_offload_init(&cls_bpf.common, tp, obj->gen_flags, extack);
 	cls_bpf.command = TC_CLSBPF_OFFLOAD;
 	cls_bpf.exts = &obj->exts;
 	cls_bpf.prog = prog ? prog->filter : NULL;
@@ -227,8 +226,7 @@ static void cls_bpf_offload_update_stats(struct tcf_proto *tp,
 	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_bpf_offload cls_bpf = {};
 
-	tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags, block,
-				   NULL);
+	tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags, NULL);
 	cls_bpf.command = TC_CLSBPF_STATS;
 	cls_bpf.exts = &prog->exts;
 	cls_bpf.prog = prog->filter;
@@ -670,7 +668,7 @@ static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 			continue;
 
 		tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags,
-					   block, extack);
+					   extack);
 		cls_bpf.command = TC_CLSBPF_OFFLOAD;
 		cls_bpf.exts = &prog->exts;
 		cls_bpf.prog = add ? prog->filter : NULL;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 3cb372b0e933..f6685fc53119 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -389,8 +389,7 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f,
 	if (!rtnl_held)
 		rtnl_lock();
 
-	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, block,
-				   extack);
+	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack);
 	cls_flower.command = TC_CLSFLOWER_DESTROY;
 	cls_flower.cookie = (unsigned long) f;
 
@@ -423,8 +422,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 		goto errout;
 	}
 
-	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, block,
-				   extack);
+	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack);
 	cls_flower.command = TC_CLSFLOWER_REPLACE;
 	cls_flower.cookie = (unsigned long) f;
 	cls_flower.rule->match.dissector = &f->mask->dissector;
@@ -480,8 +478,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f,
 	if (!rtnl_held)
 		rtnl_lock();
 
-	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, block,
-				   NULL);
+	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL);
 	cls_flower.command = TC_CLSFLOWER_STATS;
 	cls_flower.cookie = (unsigned long) f;
 	cls_flower.classid = f->res.classid;
@@ -1760,7 +1757,7 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 		}
 
 		tc_cls_common_offload_init(&cls_flower.common, tp, f->flags,
-					   block, extack);
+					   extack);
 		cls_flower.command = add ?
 			TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY;
 		cls_flower.cookie = (unsigned long)f;
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 820938fa09ed..da916f39b719 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -71,8 +71,7 @@ static void mall_destroy_hw_filter(struct tcf_proto *tp,
 	struct tc_cls_matchall_offload cls_mall = {};
 	struct tcf_block *block = tp->chain->block;
 
-	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, block,
-				   extack);
+	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
 	cls_mall.command = TC_CLSMATCHALL_DESTROY;
 	cls_mall.cookie = cookie;
 
@@ -94,8 +93,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 	if (!cls_mall.rule)
 		return -ENOMEM;
 
-	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, block,
-				   extack);
+	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
 	cls_mall.command = TC_CLSMATCHALL_REPLACE;
 	cls_mall.cookie = cookie;
 
@@ -295,8 +293,7 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 	if (!cls_mall.rule)
 		return -ENOMEM;
 
-	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, block,
-				   extack);
+	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
 	cls_mall.command = add ?
 		TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY;
 	cls_mall.cookie = (unsigned long)head;
@@ -331,8 +328,7 @@ static void mall_stats_hw_filter(struct tcf_proto *tp,
 	struct tc_cls_matchall_offload cls_mall = {};
 	struct tcf_block *block = tp->chain->block;
 
-	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, block,
-				   NULL);
+	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, NULL);
 	cls_mall.command = TC_CLSMATCHALL_STATS;
 	cls_mall.cookie = cookie;
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 2feed0ffa269..4b8710a266cc 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -485,8 +485,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
 	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, h->flags, block,
-				   extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, h->flags, extack);
 	cls_u32.command = TC_CLSU32_DELETE_HNODE;
 	cls_u32.hnode.divisor = h->divisor;
 	cls_u32.hnode.handle = h->handle;
@@ -504,7 +503,7 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
 	bool offloaded = false;
 	int err;
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, flags, block, extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, flags, extack);
 	cls_u32.command = TC_CLSU32_NEW_HNODE;
 	cls_u32.hnode.divisor = h->divisor;
 	cls_u32.hnode.handle = h->handle;
@@ -530,8 +529,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, block,
-				   extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack);
 	cls_u32.command = TC_CLSU32_DELETE_KNODE;
 	cls_u32.knode.handle = n->handle;
 
@@ -548,7 +546,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	bool skip_sw = tc_skip_sw(flags);
 	int err;
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, flags, block, extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, flags, extack);
 	cls_u32.command = TC_CLSU32_REPLACE_KNODE;
 	cls_u32.knode.handle = n->handle;
 	cls_u32.knode.fshift = n->fshift;
@@ -1172,12 +1170,10 @@ static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 			       bool add, tc_setup_cb_t *cb, void *cb_priv,
 			       struct netlink_ext_ack *extack)
 {
-	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 	int err;
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, ht->flags, block,
-				   extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, ht->flags, extack);
 	cls_u32.command = add ? TC_CLSU32_NEW_HNODE : TC_CLSU32_DELETE_HNODE;
 	cls_u32.hnode.divisor = ht->divisor;
 	cls_u32.hnode.handle = ht->handle;
@@ -1199,8 +1195,7 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	struct tc_cls_u32_offload cls_u32 = {};
 	int err;
 
-	tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, block,
-				   extack);
+	tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack);
 	cls_u32.command = add ?
 		TC_CLSU32_REPLACE_KNODE : TC_CLSU32_DELETE_KNODE;
 	cls_u32.knode.handle = n->handle;
-- 
cgit v1.2.3