From 335ff4990cf3bfa42d8846f9b3d8c09456f51801 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:03 -0700
Subject: bpf: Merge printk and seq_printf VARARG max macros

MAX_SNPRINTF_VARARGS and MAX_SEQ_PRINTF_VARARGS are used by bpf helpers
bpf_snprintf and bpf_seq_printf to limit their varargs. Both call into
bpf_bprintf_prepare for print formatting logic and have convenience
macros in libbpf (BPF_SNPRINTF, BPF_SEQ_PRINTF) which use the same
helper macros to convert varargs to a byte array.

Changing shared functionality to support more varargs for either bpf
helper would affect the other as well, so let's combine the _VARARGS
macros to make this more obvious.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-2-davemarchevsky@fb.com
---
 include/linux/bpf.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f4c16f19f83e..be8d57e6e78a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2216,6 +2216,8 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 struct btf_id_set;
 bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
 
+#define MAX_BPRINTF_VARARGS		12
+
 int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 			u32 **bin_buf, u32 num_args);
 void bpf_bprintf_cleanup(void);
-- 
cgit v1.2.3


From 10aceb629e198429c849d5e995c3bb1ba7a9aaa3 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:05 -0700
Subject: bpf: Add bpf_trace_vprintk helper

This helper is meant to be "bpf_trace_printk, but with proper vararg
support". Follow bpf_snprintf's example and take a u64 pseudo-vararg
array. Write to /sys/kernel/debug/tracing/trace_pipe using the same
mechanism as bpf_trace_printk. The functionality of this helper was
requested in the libbpf issue tracker [0].

[0] Closes: https://github.com/libbpf/libbpf/issues/315

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-4-davemarchevsky@fb.com
---
 include/linux/bpf.h            |  1 +
 include/uapi/linux/bpf.h       | 11 +++++++++
 kernel/bpf/core.c              |  5 ++++
 kernel/bpf/helpers.c           |  2 ++
 kernel/trace/bpf_trace.c       | 52 +++++++++++++++++++++++++++++++++++++++++-
 tools/include/uapi/linux/bpf.h | 11 +++++++++
 6 files changed, 81 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index be8d57e6e78a..b6c45a6cbbba 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1088,6 +1088,7 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f
 int bpf_prog_calc_tag(struct bpf_prog *fp);
 
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
+const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void);
 
 typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
 					unsigned long off, unsigned long len);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3e9785f1064a..98ca79a67937 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4898,6 +4898,16 @@ union bpf_attr {
  *		**-EINVAL** if *flags* is not zero.
  *
  *		**-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ *	Description
+ *		Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64
+ *		to format and can handle more format args as a result.
+ *
+ *		Arguments are to be used as in **bpf_seq_printf**\ () helper.
+ *	Return
+ *		The number of bytes written to the buffer, or a negative error
+ *		in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5077,6 +5087,7 @@ union bpf_attr {
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
 	FN(get_branch_snapshot),	\
+	FN(trace_vprintk),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9f4636d021b1..6fddc13fe67f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2357,6 +2357,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 	return NULL;
 }
 
+const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void)
+{
+	return NULL;
+}
+
 u64 __weak
 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)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 8f9f392c1322..2c604ff8c7fb 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1435,6 +1435,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_snprintf_proto;
 	case BPF_FUNC_task_pt_regs:
 		return &bpf_task_pt_regs_proto;
+	case BPF_FUNC_trace_vprintk:
+		return bpf_get_trace_vprintk_proto();
 	default:
 		return NULL;
 	}
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 4ec779fa0c1d..6b3153841a33 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -398,7 +398,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = {
 	.arg2_type	= ARG_CONST_SIZE,
 };
 
-const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
+static void __set_printk_clr_event(void)
 {
 	/*
 	 * This program might be calling bpf_trace_printk,
@@ -410,10 +410,58 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	 */
 	if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1))
 		pr_warn_ratelimited("could not enable bpf_trace_printk events");
+}
 
+const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
+{
+	__set_printk_clr_event();
 	return &bpf_trace_printk_proto;
 }
 
+BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data,
+	   u32, data_len)
+{
+	static char buf[BPF_TRACE_PRINTK_SIZE];
+	unsigned long flags;
+	int ret, num_args;
+	u32 *bin_args;
+
+	if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 ||
+	    (data_len && !data))
+		return -EINVAL;
+	num_args = data_len / 8;
+
+	ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args);
+	if (ret < 0)
+		return ret;
+
+	raw_spin_lock_irqsave(&trace_printk_lock, flags);
+	ret = bstr_printf(buf, sizeof(buf), fmt, bin_args);
+
+	trace_bpf_trace_printk(buf);
+	raw_spin_unlock_irqrestore(&trace_printk_lock, flags);
+
+	bpf_bprintf_cleanup();
+
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_trace_vprintk_proto = {
+	.func		= bpf_trace_vprintk,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_MEM_OR_NULL,
+	.arg4_type	= ARG_CONST_SIZE_OR_ZERO,
+};
+
+const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void)
+{
+	__set_printk_clr_event();
+	return &bpf_trace_vprintk_proto;
+}
+
 BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size,
 	   const void *, data, u32, data_len)
 {
@@ -1160,6 +1208,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_func_ip_proto_tracing;
 	case BPF_FUNC_get_branch_snapshot:
 		return &bpf_get_branch_snapshot_proto;
+	case BPF_FUNC_trace_vprintk:
+		return bpf_get_trace_vprintk_proto();
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3e9785f1064a..98ca79a67937 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4898,6 +4898,16 @@ union bpf_attr {
  *		**-EINVAL** if *flags* is not zero.
  *
  *		**-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ *	Description
+ *		Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64
+ *		to format and can handle more format args as a result.
+ *
+ *		Arguments are to be used as in **bpf_seq_printf**\ () helper.
+ *	Return
+ *		The number of bytes written to the buffer, or a negative error
+ *		in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5077,6 +5087,7 @@ union bpf_attr {
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
 	FN(get_branch_snapshot),	\
+	FN(trace_vprintk),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From a42effb0b24fcaf49513c2d7d77ef6daa9e32a6f Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:11 -0700
Subject: bpf: Clarify data_len param in bpf_snprintf and bpf_seq_printf
 comments

Since the data_len in these two functions is a byte len of the preceding
u64 *data array, it must always be a multiple of 8. If this isn't the
case both helpers error out, so let's make the requirement explicit so
users don't need to infer it.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-10-davemarchevsky@fb.com
---
 include/uapi/linux/bpf.h       | 5 +++--
 tools/include/uapi/linux/bpf.h | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 98ca79a67937..6fc59d61937a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4046,7 +4046,7 @@ union bpf_attr {
  * 		arguments. The *data* are a **u64** array and corresponding format string
  * 		values are stored in the array. For strings and pointers where pointees
  * 		are accessed, only the pointer values are stored in the *data* array.
- * 		The *data_len* is the size of *data* in bytes.
+ * 		The *data_len* is the size of *data* in bytes - must be a multiple of 8.
  *
  *		Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
  *		Reading kernel memory may fail due to either invalid address or
@@ -4751,7 +4751,8 @@ union bpf_attr {
  *		Each format specifier in **fmt** corresponds to one u64 element
  *		in the **data** array. For strings and pointers where pointees
  *		are accessed, only the pointer values are stored in the *data*
- *		array. The *data_len* is the size of *data* in bytes.
+ *		array. The *data_len* is the size of *data* in bytes - must be
+ *		a multiple of 8.
  *
  *		Formats **%s** and **%p{i,I}{4,6}** require to read kernel
  *		memory. Reading kernel memory may fail due to either invalid
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 98ca79a67937..6fc59d61937a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4046,7 +4046,7 @@ union bpf_attr {
  * 		arguments. The *data* are a **u64** array and corresponding format string
  * 		values are stored in the array. For strings and pointers where pointees
  * 		are accessed, only the pointer values are stored in the *data* array.
- * 		The *data_len* is the size of *data* in bytes.
+ * 		The *data_len* is the size of *data* in bytes - must be a multiple of 8.
  *
  *		Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
  *		Reading kernel memory may fail due to either invalid address or
@@ -4751,7 +4751,8 @@ union bpf_attr {
  *		Each format specifier in **fmt** corresponds to one u64 element
  *		in the **data** array. For strings and pointers where pointees
  *		are accessed, only the pointer values are stored in the *data*
- *		array. The *data_len* is the size of *data* in bytes.
+ *		array. The *data_len* is the size of *data* in bytes - must be
+ *		a multiple of 8.
  *
  *		Formats **%s** and **%p{i,I}{4,6}** require to read kernel
  *		memory. Reading kernel memory may fail due to either invalid
-- 
cgit v1.2.3


From 10a5e009b93a812956e232cee8804ed99f5b93bb Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:01 +0200
Subject: xsk: Get rid of unused entry in struct xdp_buff_xsk

Get rid of the unused entry "unaligned" in struct xdp_buff_xsk.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-2-magnus.karlsson@gmail.com
---
 include/net/xsk_buff_pool.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 7a9a23e7a604..bcb29a10307f 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -23,7 +23,6 @@ struct xdp_buff_xsk {
 	dma_addr_t dma;
 	dma_addr_t frame_dma;
 	struct xsk_buff_pool *pool;
-	bool unaligned;
 	u64 orig_addr;
 	struct list_head free_list_node;
 };
-- 
cgit v1.2.3


From 47e4075df300050a920b99299c4db3dad9adaba9 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:02 +0200
Subject: xsk: Batched buffer allocation for the pool

Add a new driver interface xsk_buff_alloc_batch() offering batched
buffer allocations to improve performance. The new interface takes
three arguments: the buffer pool to allocated from, a pointer to an
array of struct xdp_buff pointers which will contain pointers to the
allocated xdp_buffs, and an unsigned integer specifying the max number
of buffers to allocate. The return value is the actual number of
buffers that the allocator managed to allocate and it will be in the
range 0 <= N <= max, where max is the third parameter to the function.

u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
                         u32 max);

A second driver interface is also introduced that need to be used in
conjunction with xsk_buff_alloc_batch(). It is a helper that sets the
size of struct xdp_buff and is used by the NIC Rx irq routine when
receiving a packet. This helper sets the three struct members data,
data_meta, and data_end. The two first ones is in the xsk_buff_alloc()
case set in the allocation routine and data_end is set when a packet
is received in the receive irq function. This unfortunately leads to
worse performance since the xdp_buff is touched twice with a long time
period in between leading to an extra cache miss. Instead, we fill out
the xdp_buff with all 3 fields at one single point in time in the
driver, when the size of the packet is known. Hence this helper. Note
that the driver has to use this helper (or set all three fields
itself) when using xsk_buff_alloc_batch(). xsk_buff_alloc() works as
before and does not require this.

void xsk_buff_set_size(struct xdp_buff *xdp, u32 size);

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-3-magnus.karlsson@gmail.com
---
 include/net/xdp_sock_drv.h  | 22 ++++++++++++
 include/net/xsk_buff_pool.h |  1 +
 net/xdp/xsk_buff_pool.c     | 87 +++++++++++++++++++++++++++++++++++++++++++++
 net/xdp/xsk_queue.h         | 12 ++++---
 4 files changed, 118 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 4e295541e396..443d45951564 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -77,6 +77,12 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 	return xp_alloc(pool);
 }
 
+/* Returns as many entries as possible up to max. 0 <= N <= max. */
+static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
+{
+	return xp_alloc_batch(pool, xdp, max);
+}
+
 static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
 	return xp_can_alloc(pool, count);
@@ -89,6 +95,13 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 	xp_free(xskb);
 }
 
+static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
+{
+	xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
+	xdp->data_meta = xdp->data;
+	xdp->data_end = xdp->data + size;
+}
+
 static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
 					      u64 addr)
 {
@@ -212,6 +225,11 @@ static inline struct xdp_buff *xsk_buff_alloc(struct xsk_buff_pool *pool)
 	return NULL;
 }
 
+static inline u32 xsk_buff_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
+{
+	return 0;
+}
+
 static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
 	return false;
@@ -221,6 +239,10 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 {
 }
 
+static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
+{
+}
+
 static inline dma_addr_t xsk_buff_raw_get_dma(struct xsk_buff_pool *pool,
 					      u64 addr)
 {
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index bcb29a10307f..b7068f97639f 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -104,6 +104,7 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 	       unsigned long attrs, struct page **pages, u32 nr_pages);
 void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs);
 struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool);
+u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max);
 bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count);
 void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr);
 dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 8de01aaac4a0..884d95d70f5e 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -507,6 +507,93 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
 }
 EXPORT_SYMBOL(xp_alloc);
 
+static u32 xp_alloc_new_from_fq(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
+{
+	u32 i, cached_cons, nb_entries;
+
+	if (max > pool->free_heads_cnt)
+		max = pool->free_heads_cnt;
+	max = xskq_cons_nb_entries(pool->fq, max);
+
+	cached_cons = pool->fq->cached_cons;
+	nb_entries = max;
+	i = max;
+	while (i--) {
+		struct xdp_buff_xsk *xskb;
+		u64 addr;
+		bool ok;
+
+		__xskq_cons_read_addr_unchecked(pool->fq, cached_cons++, &addr);
+
+		ok = pool->unaligned ? xp_check_unaligned(pool, &addr) :
+			xp_check_aligned(pool, &addr);
+		if (unlikely(!ok)) {
+			pool->fq->invalid_descs++;
+			nb_entries--;
+			continue;
+		}
+
+		xskb = pool->free_heads[--pool->free_heads_cnt];
+		*xdp = &xskb->xdp;
+		xskb->orig_addr = addr;
+		xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom;
+		xskb->frame_dma = (pool->dma_pages[addr >> PAGE_SHIFT] &
+				   ~XSK_NEXT_PG_CONTIG_MASK) + (addr & ~PAGE_MASK);
+		xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM;
+		xdp++;
+	}
+
+	xskq_cons_release_n(pool->fq, max);
+	return nb_entries;
+}
+
+static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 nb_entries)
+{
+	struct xdp_buff_xsk *xskb;
+	u32 i;
+
+	nb_entries = min_t(u32, nb_entries, pool->free_list_cnt);
+
+	i = nb_entries;
+	while (i--) {
+		xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node);
+		list_del(&xskb->free_list_node);
+
+		*xdp = &xskb->xdp;
+		xdp++;
+	}
+	pool->free_list_cnt -= nb_entries;
+
+	return nb_entries;
+}
+
+u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
+{
+	u32 nb_entries1 = 0, nb_entries2;
+
+	if (unlikely(pool->dma_need_sync)) {
+		/* Slow path */
+		*xdp = xp_alloc(pool);
+		return !!*xdp;
+	}
+
+	if (unlikely(pool->free_list_cnt)) {
+		nb_entries1 = xp_alloc_reused(pool, xdp, max);
+		if (nb_entries1 == max)
+			return nb_entries1;
+
+		max -= nb_entries1;
+		xdp += nb_entries1;
+	}
+
+	nb_entries2 = xp_alloc_new_from_fq(pool, xdp, max);
+	if (!nb_entries2)
+		pool->fq->queue_empty_descs++;
+
+	return nb_entries1 + nb_entries2;
+}
+EXPORT_SYMBOL(xp_alloc_batch);
+
 bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
 	if (pool->free_list_cnt >= count)
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 9ae13cccfb28..e9aa2c236356 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -111,14 +111,18 @@ struct xsk_queue {
 
 /* Functions that read and validate content from consumer rings. */
 
-static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
+static inline void __xskq_cons_read_addr_unchecked(struct xsk_queue *q, u32 cached_cons, u64 *addr)
 {
 	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+	u32 idx = cached_cons & q->ring_mask;
 
-	if (q->cached_cons != q->cached_prod) {
-		u32 idx = q->cached_cons & q->ring_mask;
+	*addr = ring->desc[idx];
+}
 
-		*addr = ring->desc[idx];
+static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
+{
+	if (q->cached_cons != q->cached_prod) {
+		__xskq_cons_read_addr_unchecked(q, q->cached_cons, addr);
 		return true;
 	}
 
-- 
cgit v1.2.3


From 94033cd8e73b8632bab7c8b7bb54caa4f5616db7 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:06 +0200
Subject: xsk: Optimize for aligned case

Optimize for the aligned case by precomputing the parameter values of
the xdp_buff_xsk and xdp_buff structures in the heads array. We can do
this as the heads array size is equal to the number of chunks in the
umem for the aligned case. Then every entry in this array will reflect
a certain chunk/frame and can therefore be prepopulated with the
correct values and we can drop the use of the free_heads stack. Note
that it is not possible to allocate more buffers than what has been
allocated in the aligned case since each chunk can only contain a
single buffer.

We can unfortunately not do this in the unaligned case as one chunk
might contain multiple buffers. In this case, we keep the old scheme
of populating a heads entry every time it is used and using
the free_heads stack.

Also move xp_release() and xp_get_handle() to xsk_buff_pool.h. They
were for some reason in xsk.c even though they are buffer pool
operations.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-7-magnus.karlsson@gmail.com
---
 include/net/xsk_buff_pool.h | 46 ++++++++++++++++++++++++++++++++++++-
 net/xdp/xsk.c               | 15 ------------
 net/xdp/xsk_buff_pool.c     | 56 +++++++++++++++++++++++++++------------------
 3 files changed, 79 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index b7068f97639f..ddeefc4a1040 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -7,6 +7,7 @@
 #include <linux/if_xdp.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
+#include <linux/bpf.h>
 #include <net/xdp.h>
 
 struct xsk_buff_pool;
@@ -66,6 +67,7 @@ struct xsk_buff_pool {
 	u32 free_heads_cnt;
 	u32 headroom;
 	u32 chunk_size;
+	u32 chunk_shift;
 	u32 frame_len;
 	u8 cached_need_wakeup;
 	bool uses_need_wakeup;
@@ -80,6 +82,13 @@ struct xsk_buff_pool {
 	struct xdp_buff_xsk *free_heads[];
 };
 
+/* Masks for xdp_umem_page flags.
+ * The low 12-bits of the addr will be 0 since this is the page address, so we
+ * can use them for flags.
+ */
+#define XSK_NEXT_PG_CONTIG_SHIFT 0
+#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
+
 /* AF_XDP core. */
 struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 						struct xdp_umem *umem);
@@ -88,7 +97,6 @@ int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
 int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
 			 struct net_device *dev, u16 queue_id);
 void xp_destroy(struct xsk_buff_pool *pool);
-void xp_release(struct xdp_buff_xsk *xskb);
 void xp_get_pool(struct xsk_buff_pool *pool);
 bool xp_put_pool(struct xsk_buff_pool *pool);
 void xp_clear_dev(struct xsk_buff_pool *pool);
@@ -98,6 +106,21 @@ void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs);
 /* AF_XDP, and XDP core. */
 void xp_free(struct xdp_buff_xsk *xskb);
 
+static inline void xp_init_xskb_addr(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool,
+				     u64 addr)
+{
+	xskb->orig_addr = addr;
+	xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom;
+}
+
+static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_pool *pool,
+				    dma_addr_t *dma_pages, u64 addr)
+{
+	xskb->frame_dma = (dma_pages[addr >> PAGE_SHIFT] & ~XSK_NEXT_PG_CONTIG_MASK) +
+		(addr & ~PAGE_MASK);
+	xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM;
+}
+
 /* AF_XDP ZC drivers, via xdp_sock_buff.h */
 void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq);
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
@@ -180,4 +203,25 @@ static inline u64 xp_unaligned_add_offset_to_addr(u64 addr)
 		xp_unaligned_extract_offset(addr);
 }
 
+static inline u32 xp_aligned_extract_idx(struct xsk_buff_pool *pool, u64 addr)
+{
+	return xp_aligned_extract_addr(pool, addr) >> pool->chunk_shift;
+}
+
+static inline void xp_release(struct xdp_buff_xsk *xskb)
+{
+	if (xskb->pool->unaligned)
+		xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb;
+}
+
+static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb)
+{
+	u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start;
+
+	offset += xskb->pool->headroom;
+	if (!xskb->pool->unaligned)
+		return xskb->orig_addr + offset;
+	return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
+}
+
 #endif /* XSK_BUFF_POOL_H_ */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index d6b500dc4208..f16074eb53c7 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -134,21 +134,6 @@ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
 	return 0;
 }
 
-void xp_release(struct xdp_buff_xsk *xskb)
-{
-	xskb->pool->free_heads[xskb->pool->free_heads_cnt++] = xskb;
-}
-
-static u64 xp_get_handle(struct xdp_buff_xsk *xskb)
-{
-	u64 offset = xskb->xdp.data - xskb->xdp.data_hard_start;
-
-	offset += xskb->pool->headroom;
-	if (!xskb->pool->unaligned)
-		return xskb->orig_addr + offset;
-	return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
-}
-
 static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 884d95d70f5e..96b14e51ba7e 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -44,12 +44,13 @@ void xp_destroy(struct xsk_buff_pool *pool)
 struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 						struct xdp_umem *umem)
 {
+	bool unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
 	struct xsk_buff_pool *pool;
 	struct xdp_buff_xsk *xskb;
-	u32 i;
+	u32 i, entries;
 
-	pool = kvzalloc(struct_size(pool, free_heads, umem->chunks),
-			GFP_KERNEL);
+	entries = unaligned ? umem->chunks : 0;
+	pool = kvzalloc(struct_size(pool, free_heads, entries),	GFP_KERNEL);
 	if (!pool)
 		goto out;
 
@@ -63,7 +64,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 	pool->free_heads_cnt = umem->chunks;
 	pool->headroom = umem->headroom;
 	pool->chunk_size = umem->chunk_size;
-	pool->unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
+	pool->chunk_shift = ffs(umem->chunk_size) - 1;
+	pool->unaligned = unaligned;
 	pool->frame_len = umem->chunk_size - umem->headroom -
 		XDP_PACKET_HEADROOM;
 	pool->umem = umem;
@@ -81,7 +83,10 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		xskb = &pool->heads[i];
 		xskb->pool = pool;
 		xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
-		pool->free_heads[i] = xskb;
+		if (pool->unaligned)
+			pool->free_heads[i] = xskb;
+		else
+			xp_init_xskb_addr(xskb, pool, i * pool->chunk_size);
 	}
 
 	return pool;
@@ -406,6 +411,12 @@ int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 
 	if (pool->unaligned)
 		xp_check_dma_contiguity(dma_map);
+	else
+		for (i = 0; i < pool->heads_cnt; i++) {
+			struct xdp_buff_xsk *xskb = &pool->heads[i];
+
+			xp_init_xskb_dma(xskb, pool, dma_map->dma_pages, xskb->orig_addr);
+		}
 
 	err = xp_init_dma_info(pool, dma_map);
 	if (err) {
@@ -448,8 +459,6 @@ static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool)
 	if (pool->free_heads_cnt == 0)
 		return NULL;
 
-	xskb = pool->free_heads[--pool->free_heads_cnt];
-
 	for (;;) {
 		if (!xskq_cons_peek_addr_unchecked(pool->fq, &addr)) {
 			pool->fq->queue_empty_descs++;
@@ -466,17 +475,17 @@ static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool)
 		}
 		break;
 	}
-	xskq_cons_release(pool->fq);
 
-	xskb->orig_addr = addr;
-	xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom;
-	if (pool->dma_pages_cnt) {
-		xskb->frame_dma = (pool->dma_pages[addr >> PAGE_SHIFT] &
-				   ~XSK_NEXT_PG_CONTIG_MASK) +
-				  (addr & ~PAGE_MASK);
-		xskb->dma = xskb->frame_dma + pool->headroom +
-			    XDP_PACKET_HEADROOM;
+	if (pool->unaligned) {
+		xskb = pool->free_heads[--pool->free_heads_cnt];
+		xp_init_xskb_addr(xskb, pool, addr);
+		if (pool->dma_pages_cnt)
+			xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr);
+	} else {
+		xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)];
 	}
+
+	xskq_cons_release(pool->fq);
 	return xskb;
 }
 
@@ -533,13 +542,16 @@ static u32 xp_alloc_new_from_fq(struct xsk_buff_pool *pool, struct xdp_buff **xd
 			continue;
 		}
 
-		xskb = pool->free_heads[--pool->free_heads_cnt];
+		if (pool->unaligned) {
+			xskb = pool->free_heads[--pool->free_heads_cnt];
+			xp_init_xskb_addr(xskb, pool, addr);
+			if (pool->dma_pages_cnt)
+				xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr);
+		} else {
+			xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)];
+		}
+
 		*xdp = &xskb->xdp;
-		xskb->orig_addr = addr;
-		xskb->xdp.data_hard_start = pool->addrs + addr + pool->headroom;
-		xskb->frame_dma = (pool->dma_pages[addr >> PAGE_SHIFT] &
-				   ~XSK_NEXT_PG_CONTIG_MASK) + (addr & ~PAGE_MASK);
-		xskb->dma = xskb->frame_dma + pool->headroom + XDP_PACKET_HEADROOM;
 		xdp++;
 	}
 
-- 
cgit v1.2.3


From 3d717fad5081b8e3bda76d86907fad95398cbde8 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 28 Sep 2021 16:09:45 -0700
Subject: bpf: Replace "want address" users of BPF_CAST_CALL with BPF_CALL_IMM

In order to keep ahead of cases in the kernel where Control Flow
Integrity (CFI) may trip over function call casts, enabling
-Wcast-function-type is helpful. To that end, BPF_CAST_CALL causes
various warnings and is one of the last places in the kernel triggering
this warning.

Most places using BPF_CAST_CALL actually just want a void * to perform
math on. It's not actually performing a call, so just use a different
helper to get the void *, by way of the new BPF_CALL_IMM() helper, which
can clean up a common copy/paste idiom as well.

This change results in no object code difference.

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://github.com/KSPP/linux/issues/20
Link: https://lore.kernel.org/lkml/CAEf4Bzb46=-J5Fxc3mMZ8JQPtK1uoE0q6+g6WPz53Cvx=CBEhw@mail.gmail.com
Link: https://lore.kernel.org/bpf/20210928230946.4062144-2-keescook@chromium.org
---
 include/linux/filter.h |  6 +++++-
 kernel/bpf/hashtab.c   |  6 +++---
 kernel/bpf/verifier.c  | 26 +++++++++-----------------
 lib/test_bpf.c         |  2 +-
 4 files changed, 18 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4a93c12543ee..6c247663d4ce 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -365,13 +365,17 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 #define BPF_CAST_CALL(x)					\
 		((u64 (*)(u64, u64, u64, u64, u64))(x))
 
+/* Convert function address to BPF immediate */
+
+#define BPF_CALL_IMM(x)	((void *)(x) - (void *)__bpf_call_base)
+
 #define BPF_EMIT_CALL(FUNC)					\
 	((struct bpf_insn) {					\
 		.code  = BPF_JMP | BPF_CALL,			\
 		.dst_reg = 0,					\
 		.src_reg = 0,					\
 		.off   = 0,					\
-		.imm   = ((FUNC) - __bpf_call_base) })
+		.imm   = BPF_CALL_IMM(FUNC) })
 
 /* Raw code statement block */
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 32471ba02708..3d8f9d6997d5 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -668,7 +668,7 @@ static int htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 
 	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
 		     (void *(*)(struct bpf_map *map, void *key))NULL));
-	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
 				offsetof(struct htab_elem, key) +
@@ -709,7 +709,7 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map,
 
 	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
 		     (void *(*)(struct bpf_map *map, void *key))NULL));
-	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4);
 	*insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret,
 			      offsetof(struct htab_elem, lru_node) +
@@ -2397,7 +2397,7 @@ static int htab_of_map_gen_lookup(struct bpf_map *map,
 
 	BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem,
 		     (void *(*)(struct bpf_map *map, void *key))NULL));
-	*insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem));
+	*insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem);
 	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2);
 	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
 				offsetof(struct htab_elem, key) +
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7a8351604f67..1433752db740 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1744,7 +1744,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
 
 	desc = &tab->descs[tab->nr_descs++];
 	desc->func_id = func_id;
-	desc->imm = BPF_CAST_CALL(addr) - __bpf_call_base;
+	desc->imm = BPF_CALL_IMM(addr);
 	err = btf_distill_func_proto(&env->log, btf_vmlinux,
 				     func_proto, func_name,
 				     &desc->func_model);
@@ -12514,8 +12514,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 			if (!bpf_pseudo_call(insn))
 				continue;
 			subprog = insn->off;
-			insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) -
-				    __bpf_call_base;
+			insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func);
 		}
 
 		/* we use the aux data to keep a list of the start addresses
@@ -12995,32 +12994,25 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 patch_map_ops_generic:
 			switch (insn->imm) {
 			case BPF_FUNC_map_lookup_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_lookup_elem);
 				continue;
 			case BPF_FUNC_map_update_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_update_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_update_elem);
 				continue;
 			case BPF_FUNC_map_delete_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_delete_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_delete_elem);
 				continue;
 			case BPF_FUNC_map_push_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_push_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_push_elem);
 				continue;
 			case BPF_FUNC_map_pop_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_pop_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_pop_elem);
 				continue;
 			case BPF_FUNC_map_peek_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_peek_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_peek_elem);
 				continue;
 			case BPF_FUNC_redirect_map:
-				insn->imm = BPF_CAST_CALL(ops->map_redirect) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_redirect);
 				continue;
 			}
 
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 08f438e6fe9e..21ea1ab253a1 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -12439,7 +12439,7 @@ static __init int prepare_tail_call_tests(struct bpf_array **pprogs)
 					err = -EFAULT;
 					goto out_err;
 				}
-				*insn = BPF_EMIT_CALL(BPF_CAST_CALL(addr));
+				*insn = BPF_EMIT_CALL(addr);
 				if ((long)__bpf_call_base + insn->imm != addr)
 					*insn = BPF_JMP_A(0); /* Skip: NOP */
 				break;
-- 
cgit v1.2.3


From 102acbacfd9a96d101abd96d1a7a5bf92b7c3e8e Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 28 Sep 2021 16:09:46 -0700
Subject: bpf: Replace callers of BPF_CAST_CALL with proper function typedef

In order to keep ahead of cases in the kernel where Control Flow
Integrity (CFI) may trip over function call casts, enabling
-Wcast-function-type is helpful. To that end, BPF_CAST_CALL causes
various warnings and is one of the last places in the kernel
triggering this warning.

For actual function calls, replace BPF_CAST_CALL() with a typedef, which
captures the same details about the given function pointers.

This change results in no object code difference.

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://github.com/KSPP/linux/issues/20
Link: https://lore.kernel.org/lkml/CAEf4Bzb46=-J5Fxc3mMZ8JQPtK1uoE0q6+g6WPz53Cvx=CBEhw@mail.gmail.com
Link: https://lore.kernel.org/bpf/20210928230946.4062144-3-keescook@chromium.org
---
 include/linux/bpf.h    | 4 +++-
 include/linux/filter.h | 5 -----
 kernel/bpf/arraymap.c  | 7 +++----
 kernel/bpf/hashtab.c   | 7 +++----
 kernel/bpf/helpers.c   | 5 ++---
 5 files changed, 11 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b6c45a6cbbba..19735d59230a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -48,6 +48,7 @@ extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 extern struct kobject *btf_kobj;
 
+typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
 typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
 					struct bpf_iter_aux_info *aux);
 typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
@@ -142,7 +143,8 @@ struct bpf_map_ops {
 	int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env,
 					      struct bpf_func_state *caller,
 					      struct bpf_func_state *callee);
-	int (*map_for_each_callback)(struct bpf_map *map, void *callback_fn,
+	int (*map_for_each_callback)(struct bpf_map *map,
+				     bpf_callback_t callback_fn,
 				     void *callback_ctx, u64 flags);
 
 	/* BTF name and id of struct allocated by map_alloc */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 6c247663d4ce..47f80adbe744 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -360,11 +360,6 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 		.off   = 0,					\
 		.imm   = TGT })
 
-/* Function call */
-
-#define BPF_CAST_CALL(x)					\
-		((u64 (*)(u64, u64, u64, u64, u64))(x))
-
 /* Convert function address to BPF immediate */
 
 #define BPF_CALL_IMM(x)	((void *)(x) - (void *)__bpf_call_base)
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index cebd4fb06d19..5e1ccfae916b 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -645,7 +645,7 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_array_map_info),
 };
 
-static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn,
+static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_fn,
 				   void *callback_ctx, u64 flags)
 {
 	u32 i, key, num_elems = 0;
@@ -668,9 +668,8 @@ static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn,
 			val = array->value + array->elem_size * i;
 		num_elems++;
 		key = i;
-		ret = BPF_CAST_CALL(callback_fn)((u64)(long)map,
-					(u64)(long)&key, (u64)(long)val,
-					(u64)(long)callback_ctx, 0);
+		ret = callback_fn((u64)(long)map, (u64)(long)&key,
+				  (u64)(long)val, (u64)(long)callback_ctx, 0);
 		/* return value: 0 - continue, 1 - stop and return */
 		if (ret)
 			break;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3d8f9d6997d5..d29af9988f37 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2049,7 +2049,7 @@ static const struct bpf_iter_seq_info iter_seq_info = {
 	.seq_priv_size		= sizeof(struct bpf_iter_seq_hash_map_info),
 };
 
-static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn,
+static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_fn,
 				  void *callback_ctx, u64 flags)
 {
 	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
@@ -2089,9 +2089,8 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn,
 				val = elem->key + roundup_key_size;
 			}
 			num_elems++;
-			ret = BPF_CAST_CALL(callback_fn)((u64)(long)map,
-					(u64)(long)key, (u64)(long)val,
-					(u64)(long)callback_ctx, 0);
+			ret = callback_fn((u64)(long)map, (u64)(long)key,
+					  (u64)(long)val, (u64)(long)callback_ctx, 0);
 			/* return value: 0 - continue, 1 - stop and return */
 			if (ret) {
 				rcu_read_unlock();
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 2c604ff8c7fb..1ffd469c217f 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1056,7 +1056,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer)
 	struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer);
 	struct bpf_map *map = t->map;
 	void *value = t->value;
-	void *callback_fn;
+	bpf_callback_t callback_fn;
 	void *key;
 	u32 idx;
 
@@ -1081,8 +1081,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer)
 		key = value - round_up(map->key_size, 8);
 	}
 
-	BPF_CAST_CALL(callback_fn)((u64)(long)map, (u64)(long)key,
-				   (u64)(long)value, 0, 0);
+	callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0);
 	/* The verifier checked that return value is zero. */
 
 	this_cpu_write(hrtimer_running, NULL);
-- 
cgit v1.2.3


From 6bbc7103738f0e0871a9331351ee3cd4d462b431 Mon Sep 17 00:00:00 2001
From: Kev Jackson <foamdino@gmail.com>
Date: Thu, 30 Sep 2021 07:34:02 +0100
Subject: bpf, xdp, docs: Correct some English grammar and spelling

Header DOC on include/net/xdp.h contained a few English grammer and
spelling errors.

Signed-off-by: Kev Jackson <foamdino@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Link: https://lore.kernel.org/bpf/YVVaWmKqA8l9Tm4J@kev-VirtualBox
---
 include/net/xdp.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/xdp.h b/include/net/xdp.h
index ad5b02dcb6f4..447f9b1578f3 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -15,13 +15,13 @@
  * level RX-ring queues.  It is information that is specific to how
  * the driver have configured a given RX-ring queue.
  *
- * Each xdp_buff frame received in the driver carry a (pointer)
+ * Each xdp_buff frame received in the driver carries a (pointer)
  * reference to this xdp_rxq_info structure.  This provides the XDP
  * data-path read-access to RX-info for both kernel and bpf-side
  * (limited subset).
  *
  * For now, direct access is only safe while running in NAPI/softirq
- * context.  Contents is read-mostly and must not be updated during
+ * context.  Contents are read-mostly and must not be updated during
  * driver NAPI/softirq poll.
  *
  * The driver usage API is a register and unregister API.
@@ -30,8 +30,8 @@
  * can be attached as long as it doesn't change the underlying
  * RX-ring.  If the RX-ring does change significantly, the NIC driver
  * naturally need to stop the RX-ring before purging and reallocating
- * memory.  In that process the driver MUST call unregistor (which
- * also apply for driver shutdown and unload).  The register API is
+ * memory.  In that process the driver MUST call unregister (which
+ * also applies for driver shutdown and unload).  The register API is
  * also mandatory during RX-ring setup.
  */
 
-- 
cgit v1.2.3