From d651983dde41a854e25664d98cbfc999d55785a8 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Fri, 12 May 2017 09:35:46 -0300 Subject: net: fix some identation issues at kernel-doc markups Sphinx is very pedantic with regards to identation and escape sequences: ./include/net/sock.h:1967: ERROR: Unexpected indentation. ./include/net/sock.h:1969: ERROR: Unexpected indentation. ./include/net/sock.h:1970: WARNING: Block quote ends without a blank line; unexpected unindent. ./include/net/sock.h:1971: WARNING: Block quote ends without a blank line; unexpected unindent. ./include/net/sock.h:2268: WARNING: Inline emphasis start-string without end-string. ./net/core/sock.c:2686: ERROR: Unexpected indentation. ./net/core/sock.c:2687: WARNING: Block quote ends without a blank line; unexpected unindent. ./net/core/datagram.c:182: WARNING: Inline emphasis start-string without end-string. ./include/linux/netdevice.h:1444: ERROR: Unexpected indentation. ./drivers/net/phy/phy.c:381: ERROR: Unexpected indentation. ./drivers/net/phy/phy.c:382: WARNING: Block quote ends without a blank line; unexpected unindent. - Fix spacing where needed; - Properly escape constants; - Use a literal block for a race description. No functional changes. Signed-off-by: Mauro Carvalho Chehab --- include/net/sock.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 66349e49d468..9ca99b5c1328 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1953,11 +1953,10 @@ static inline bool sk_has_allocations(const struct sock *sk) * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. * - * Consider following tcp code paths: + * Consider following tcp code paths:: * - * CPU1 CPU2 - * - * sys_select receive packet + * CPU1 CPU2 + * sys_select receive packet * ... ... * __add_wait_queue update tp->rcv_nxt * ... ... @@ -2264,7 +2263,7 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags); * @tsflags: timestamping flags to use * @tx_flags: completed with instructions for time stamping * - * Note : callers should take care of initial *tx_flags value (usually 0) + * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ static inline void sock_tx_timestamp(const struct sock *sk, __u16 tsflags, __u8 *tx_flags) -- cgit v1.2.3 From 65101aeca52241a05e66f23c96eb896c9412718d Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 16 May 2017 11:20:13 +0200 Subject: net/sock: factor out dequeue/peek with offset code And update __sk_queue_drop_skb() to work on the specified queue. This will help the udp protocol to use an additional private rx queue in a later patch. Signed-off-by: Paolo Abeni Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 ++++ include/net/sock.h | 4 +-- net/core/datagram.c | 90 ++++++++++++++++++++++++++++---------------------- 3 files changed, 60 insertions(+), 41 deletions(-) (limited to 'include/net') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a098d95b3d84..bfc7892f6c33 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3056,6 +3056,13 @@ static inline void skb_frag_list_init(struct sk_buff *skb) int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, const struct sk_buff *skb); +struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, + struct sk_buff_head *queue, + unsigned int flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb), + int *peeked, 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), diff --git a/include/net/sock.h b/include/net/sock.h index f33e3d134e0b..42264035dec0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2035,8 +2035,8 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer, void sk_stop_timer(struct sock *sk, struct timer_list *timer); -int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, - unsigned int flags, +int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, + struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); diff --git a/net/core/datagram.c b/net/core/datagram.c index db1866f2ffcf..a4592b43b40d 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -161,6 +161,43 @@ done: return skb; } +struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, + struct sk_buff_head *queue, + unsigned int flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb), + int *peeked, int *off, int *err, + struct sk_buff **last) +{ + struct sk_buff *skb; + + *last = queue->prev; + skb_queue_walk(queue, skb) { + if (flags & MSG_PEEK) { + if (*off >= skb->len && (skb->len || *off || + skb->peeked)) { + *off -= skb->len; + continue; + } + if (!skb->len) { + skb = skb_set_peeked(skb); + if (unlikely(IS_ERR(skb))) { + *err = PTR_ERR(skb); + return skb; + } + } + *peeked = 1; + atomic_inc(&skb->users); + } else { + __skb_unlink(skb, queue); + if (destructor) + destructor(sk, skb); + } + return skb; + } + return NULL; +} + /** * __skb_try_recv_datagram - Receive a datagram skbuff * @sk: socket @@ -216,46 +253,20 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, *peeked = 0; do { + int _off = *off; + /* Again only user level code calls this function, so nothing * interrupt level will suddenly eat the receive_queue. * * Look at current nfs client by the way... * However, this function was correct in any case. 8) */ - int _off = *off; - - *last = (struct sk_buff *)queue; spin_lock_irqsave(&queue->lock, cpu_flags); - skb_queue_walk(queue, skb) { - *last = skb; - if (flags & MSG_PEEK) { - if (_off >= skb->len && (skb->len || _off || - skb->peeked)) { - _off -= skb->len; - continue; - } - if (!skb->len) { - skb = skb_set_peeked(skb); - if (IS_ERR(skb)) { - error = PTR_ERR(skb); - spin_unlock_irqrestore(&queue->lock, - cpu_flags); - goto no_packet; - } - } - *peeked = 1; - atomic_inc(&skb->users); - } else { - __skb_unlink(skb, queue); - if (destructor) - destructor(sk, skb); - } - spin_unlock_irqrestore(&queue->lock, cpu_flags); - *off = _off; - return skb; - } - + skb = __skb_try_recv_from_queue(sk, queue, flags, destructor, + peeked, &_off, err, last); spin_unlock_irqrestore(&queue->lock, cpu_flags); + if (skb) + return skb; if (!sk_can_busy_loop(sk)) break; @@ -335,8 +346,8 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len) } EXPORT_SYMBOL(__skb_free_datagram_locked); -int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, - unsigned int flags, +int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, + struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb)) { @@ -344,15 +355,15 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, if (flags & MSG_PEEK) { err = -ENOENT; - spin_lock_bh(&sk->sk_receive_queue.lock); - if (skb == skb_peek(&sk->sk_receive_queue)) { - __skb_unlink(skb, &sk->sk_receive_queue); + spin_lock_bh(&sk_queue->lock); + if (skb == skb_peek(sk_queue)) { + __skb_unlink(skb, sk_queue); atomic_dec(&skb->users); if (destructor) destructor(sk, skb); err = 0; } - spin_unlock_bh(&sk->sk_receive_queue.lock); + spin_unlock_bh(&sk_queue->lock); } atomic_inc(&sk->sk_drops); @@ -383,7 +394,8 @@ EXPORT_SYMBOL(__sk_queue_drop_skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) { - int err = __sk_queue_drop_skb(sk, skb, flags, NULL); + int err = __sk_queue_drop_skb(sk, &sk->sk_receive_queue, skb, flags, + NULL); kfree_skb(skb); sk_mem_reclaim_partial(sk); -- cgit v1.2.3 From 2276f58ac5890e58d2b6a48b95493faff7347e3a Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 16 May 2017 11:20:14 +0200 Subject: udp: use a separate rx queue for packet reception under udp flood the sk_receive_queue spinlock is heavily contended. This patch try to reduce the contention on such lock adding a second receive queue to the udp sockets; recvmsg() looks first in such queue and, only if empty, tries to fetch the data from sk_receive_queue. The latter is spliced into the newly added queue every time the receive path has to acquire the sk_receive_queue lock. The accounting of forward allocated memory is still protected with the sk_receive_queue lock, so udp_rmem_release() needs to acquire both locks when the forward deficit is flushed. On specific scenarios we can end up acquiring and releasing the sk_receive_queue lock multiple times; that will be covered by the next patch Suggested-by: Eric Dumazet Signed-off-by: Paolo Abeni Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/udp.h | 3 ++ include/net/udp.h | 9 +--- include/net/udplite.h | 2 +- net/ipv4/udp.c | 138 ++++++++++++++++++++++++++++++++++++++++++++------ net/ipv6/udp.c | 3 +- 5 files changed, 131 insertions(+), 24 deletions(-) (limited to 'include/net') diff --git a/include/linux/udp.h b/include/linux/udp.h index 6cb4061a720d..eaea63bc79bb 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -80,6 +80,9 @@ struct udp_sock { struct sk_buff *skb, int nhoff); + /* udp_recvmsg try to use this before splicing sk_receive_queue */ + struct sk_buff_head reader_queue ____cacheline_aligned_in_smp; + /* This field is dirtied by udp_recvmsg() */ int forward_deficit; }; diff --git a/include/net/udp.h b/include/net/udp.h index 3391dbd73959..1468dbd0f09a 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -249,13 +249,8 @@ void udp_destruct_sock(struct sock *sk); 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); -static inline struct sk_buff * -__skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *peeked, - int *off, int *err) -{ - return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - udp_skb_destructor, peeked, off, err); -} +struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, + int noblock, int *peeked, int *off, int *err); static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, int noblock, int *err) { diff --git a/include/net/udplite.h b/include/net/udplite.h index ea340524f99b..b7a18f63d86d 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -26,8 +26,8 @@ static __inline__ int udplite_getfrag(void *from, char *to, int offset, /* Designate sk as UDP-Lite socket */ static inline int udplite_sk_init(struct sock *sk) { + udp_init_sock(sk); udp_sk(sk)->pcflag = UDPLITE_BIT; - sk->sk_destruct = udp_destruct_sock; return 0; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ea6e4cff9faf..492c76be9230 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1167,19 +1167,24 @@ out: static void udp_rmem_release(struct sock *sk, int size, int partial) { struct udp_sock *up = udp_sk(sk); + struct sk_buff_head *sk_queue; int amt; if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; if (size < (sk->sk_rcvbuf >> 2) && - !skb_queue_empty(&sk->sk_receive_queue)) + !skb_queue_empty(&up->reader_queue)) return; } else { size += up->forward_deficit; } up->forward_deficit = 0; + /* acquire the sk_receive_queue for fwd allocated memory scheduling */ + sk_queue = &sk->sk_receive_queue; + spin_lock(&sk_queue->lock); + sk->sk_forward_alloc += size; amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1); sk->sk_forward_alloc -= amt; @@ -1188,9 +1193,14 @@ static void udp_rmem_release(struct sock *sk, int size, int partial) __sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT); atomic_sub(size, &sk->sk_rmem_alloc); + + /* this can save us from acquiring the rx queue lock on next receive */ + skb_queue_splice_tail_init(sk_queue, &up->reader_queue); + + spin_unlock(&sk_queue->lock); } -/* Note: called with sk_receive_queue.lock held. +/* Note: called with reader_queue.lock held. * Instead of using skb->truesize here, find a copy of it in skb->dev_scratch * This avoids a cache line miss while receive_queue lock is held. * Look at __udp_enqueue_schedule_skb() to find where this copy is done. @@ -1306,10 +1316,12 @@ EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb); void udp_destruct_sock(struct sock *sk) { /* reclaim completely the forward allocated memory */ + struct udp_sock *up = udp_sk(sk); unsigned int total = 0; struct sk_buff *skb; - while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { + skb_queue_splice_tail_init(&sk->sk_receive_queue, &up->reader_queue); + while ((skb = __skb_dequeue(&up->reader_queue)) != NULL) { total += skb->truesize; kfree_skb(skb); } @@ -1321,6 +1333,7 @@ EXPORT_SYMBOL_GPL(udp_destruct_sock); int udp_init_sock(struct sock *sk) { + skb_queue_head_init(&udp_sk(sk)->reader_queue); sk->sk_destruct = udp_destruct_sock; return 0; } @@ -1338,6 +1351,26 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) } EXPORT_SYMBOL_GPL(skb_consume_udp); +static struct sk_buff *__first_packet_length(struct sock *sk, + struct sk_buff_head *rcvq, + int *total) +{ + struct sk_buff *skb; + + while ((skb = skb_peek(rcvq)) != NULL && + udp_lib_checksum_complete(skb)) { + __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, + IS_UDPLITE(sk)); + __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + atomic_inc(&sk->sk_drops); + __skb_unlink(skb, rcvq); + *total += skb->truesize; + kfree_skb(skb); + } + return skb; +} + /** * first_packet_length - return length of first packet in receive queue * @sk: socket @@ -1347,22 +1380,20 @@ EXPORT_SYMBOL_GPL(skb_consume_udp); */ static int first_packet_length(struct sock *sk) { - struct sk_buff_head *rcvq = &sk->sk_receive_queue; + struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; + struct sk_buff_head *sk_queue = &sk->sk_receive_queue; struct sk_buff *skb; int total = 0; int res; spin_lock_bh(&rcvq->lock); - while ((skb = skb_peek(rcvq)) != NULL && - udp_lib_checksum_complete(skb)) { - __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, - IS_UDPLITE(sk)); - __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, - IS_UDPLITE(sk)); - atomic_inc(&sk->sk_drops); - __skb_unlink(skb, rcvq); - total += skb->truesize; - kfree_skb(skb); + skb = __first_packet_length(sk, rcvq, &total); + if (!skb && !skb_queue_empty(sk_queue)) { + spin_lock(&sk_queue->lock); + skb_queue_splice_tail_init(sk_queue, rcvq); + spin_unlock(&sk_queue->lock); + + skb = __first_packet_length(sk, rcvq, &total); } res = skb ? skb->len : -1; if (total) @@ -1400,6 +1431,79 @@ 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) +{ + struct sk_buff_head *sk_queue = &sk->sk_receive_queue; + struct sk_buff_head *queue; + struct sk_buff *last; + long timeo; + int error; + + queue = &udp_sk(sk)->reader_queue; + flags |= noblock ? MSG_DONTWAIT : 0; + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + do { + struct sk_buff *skb; + + error = sock_error(sk); + if (error) + break; + + error = -EAGAIN; + *peeked = 0; + do { + int _off = *off; + + spin_lock_bh(&queue->lock); + skb = __skb_try_recv_from_queue(sk, queue, flags, + udp_skb_destructor, + peeked, &_off, err, + &last); + if (skb) { + spin_unlock_bh(&queue->lock); + *off = _off; + return skb; + } + + if (skb_queue_empty(sk_queue)) { + spin_unlock_bh(&queue->lock); + goto busy_check; + } + + /* refill the reader queue and walk it again */ + _off = *off; + spin_lock(&sk_queue->lock); + skb_queue_splice_tail_init(sk_queue, queue); + spin_unlock(&sk_queue->lock); + + skb = __skb_try_recv_from_queue(sk, queue, flags, + udp_skb_destructor, + peeked, &_off, err, + &last); + spin_unlock_bh(&queue->lock); + if (skb) { + *off = _off; + return skb; + } + +busy_check: + if (!sk_can_busy_loop(sk)) + break; + + sk_busy_loop(sk, flags & MSG_DONTWAIT); + } while (!skb_queue_empty(sk_queue)); + + /* sk_queue is empty, reader_queue may contain peeked packets */ + } while (timeo && + !__skb_wait_for_more_packets(sk, &error, &timeo, + (struct sk_buff *)sk_queue)); + + *err = error; + return NULL; +} +EXPORT_SYMBOL_GPL(__skb_recv_udp); + /* * This should be easy, if there is something there we * return it, otherwise we block. @@ -1490,7 +1594,8 @@ try_again: return err; csum_copy_err: - if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) { + if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, + udp_skb_destructor)) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } @@ -2325,6 +2430,9 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) unsigned int mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; + if (!skb_queue_empty(&udp_sk(sk)->reader_queue)) + mask |= POLLIN | POLLRDNORM; + sock_rps_record_flow(sk); /* Check for false positives due to checksum errors */ diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 04862abfe4ec..f78fdf8c9f0f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -455,7 +455,8 @@ try_again: return err; csum_copy_err: - if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) { + if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, + udp_skb_destructor)) { if (is_udp4) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); -- cgit v1.2.3 From 218af599fa635b107cfe10acf3249c4dfe5e4123 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2017 04:24:36 -0700 Subject: tcp: internal implementation for pacing BBR congestion control depends on pacing, and pacing is currently handled by sch_fq packet scheduler for performance reasons, and also because implemening pacing with FQ was convenient to truly avoid bursts. However there are many cases where this packet scheduler constraint is not practical. - Many linux hosts are not focusing on handling thousands of TCP flows in the most efficient way. - Some routers use fq_codel or other AQM, but still would like to use BBR for the few TCP flows they initiate/terminate. This patch implements an automatic fallback to internal pacing. Pacing is requested either by BBR or use of SO_MAX_PACING_RATE option. If sch_fq happens to be in the egress path, pacing is delegated to the qdisc, otherwise pacing is done by TCP itself. One advantage of pacing from TCP stack is to get more precise rtt estimations, and less work done from TX completion, since TCP Small queue limits are not generally hit. Setups with single TX queue but many cpus might even benefit from this. Note that unlike sch_fq, we do not take into account header sizes. Taking care of these headers would add additional complexity for no practical differences in behavior. Some performance numbers using 800 TCP_STREAM flows rate limited to ~48 Mbit per second on 40Gbit NIC. If MQ+pfifo_fast is used on the NIC : $ sar -n DEV 1 5 | grep eth 14:48:44 eth0 725743.00 2932134.00 46776.76 4335184.68 0.00 0.00 1.00 14:48:45 eth0 725349.00 2932112.00 46751.86 4335158.90 0.00 0.00 0.00 14:48:46 eth0 725101.00 2931153.00 46735.07 4333748.63 0.00 0.00 0.00 14:48:47 eth0 725099.00 2931161.00 46735.11 4333760.44 0.00 0.00 1.00 14:48:48 eth0 725160.00 2931731.00 46738.88 4334606.07 0.00 0.00 0.00 Average: eth0 725290.40 2931658.20 46747.54 4334491.74 0.00 0.00 0.40 $ vmstat 1 5 procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu----- r b swpd free buff cache si so bi bo in cs us sy id wa st 4 0 0 259825920 45644 2708324 0 0 21 2 247 98 0 0 100 0 0 4 0 0 259823744 45644 2708356 0 0 0 0 2400825 159843 0 19 81 0 0 0 0 0 259824208 45644 2708072 0 0 0 0 2407351 159929 0 19 81 0 0 1 0 0 259824592 45644 2708128 0 0 0 0 2405183 160386 0 19 80 0 0 1 0 0 259824272 45644 2707868 0 0 0 32 2396361 158037 0 19 81 0 0 Now use MQ+FQ : lpaa23:~# echo fq >/proc/sys/net/core/default_qdisc lpaa23:~# tc qdisc replace dev eth0 root mq $ sar -n DEV 1 5 | grep eth 14:49:57 eth0 678614.00 2727930.00 43739.13 4033279.14 0.00 0.00 0.00 14:49:58 eth0 677620.00 2723971.00 43674.69 4027429.62 0.00 0.00 1.00 14:49:59 eth0 676396.00 2719050.00 43596.83 4020125.02 0.00 0.00 0.00 14:50:00 eth0 675197.00 2714173.00 43518.62 4012938.90 0.00 0.00 1.00 14:50:01 eth0 676388.00 2719063.00 43595.47 4020171.64 0.00 0.00 0.00 Average: eth0 676843.00 2720837.40 43624.95 4022788.86 0.00 0.00 0.40 $ vmstat 1 5 procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu----- r b swpd free buff cache si so bi bo in cs us sy id wa st 2 0 0 259832240 46008 2710912 0 0 21 2 223 192 0 1 99 0 0 1 0 0 259832896 46008 2710744 0 0 0 0 1702206 198078 0 17 82 0 0 0 0 0 259830272 46008 2710596 0 0 0 0 1696340 197756 1 17 83 0 0 4 0 0 259829168 46024 2710584 0 0 16 0 1688472 197158 1 17 82 0 0 3 0 0 259830224 46024 2710408 0 0 0 0 1692450 197212 0 18 82 0 0 As expected, number of interrupts per second is very different. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Cc: Neal Cardwell Cc: Yuchung Cheng Cc: Van Jacobson Cc: Jerry Chu Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ include/net/sock.h | 9 +++++- include/net/tcp.h | 3 ++ net/core/sock.c | 4 +++ net/ipv4/tcp_bbr.c | 9 +++--- net/ipv4/tcp_output.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_timer.c | 3 ++ net/sched/sch_fq.c | 8 ++++++ 8 files changed, 113 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index b6d5adcee8fc..22854f028434 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -293,6 +293,8 @@ struct tcp_sock { u32 sacked_out; /* SACK'd packets */ u32 fackets_out; /* FACK'd packets */ + struct hrtimer pacing_timer; + /* from STCP, retrans queue hinting */ struct sk_buff* lost_skb_hint; struct sk_buff *retransmit_skb_hint; diff --git a/include/net/sock.h b/include/net/sock.h index 42264035dec0..3467d9e89e7d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -253,6 +253,7 @@ struct sock_common { * @sk_ll_usec: usecs to busypoll when there is no data * @sk_allocation: allocation mode * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) + * @sk_pacing_status: Pacing status (requested, handled by sch_fq) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes * @sk_padding: unused element for alignment @@ -396,7 +397,7 @@ struct sock { __s32 sk_peek_off; int sk_write_pending; __u32 sk_dst_pending_confirm; - /* Note: 32bit hole on 64bit arches */ + u32 sk_pacing_status; /* see enum sk_pacing */ long sk_sndtimeo; struct timer_list sk_timer; __u32 sk_priority; @@ -475,6 +476,12 @@ struct sock { struct rcu_head sk_rcu; }; +enum sk_pacing { + SK_PACING_NONE = 0, + SK_PACING_NEEDED = 1, + SK_PACING_FQ = 2, +}; + #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) #define rcu_dereference_sk_user_data(sk) rcu_dereference(__sk_user_data((sk))) diff --git a/include/net/tcp.h b/include/net/tcp.h index 38a7427ae902..b4dc93dae98c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -574,6 +574,7 @@ void tcp_fin(struct sock *sk); void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) { + hrtimer_cancel(&tcp_sk(sk)->pacing_timer); inet_csk_clear_xmit_timers(sk); } @@ -1945,4 +1946,6 @@ static inline void tcp_listendrop(const struct sock *sk) __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS); } +enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); + #endif /* _TCP_H */ diff --git a/net/core/sock.c b/net/core/sock.c index e43e71d7856b..93d011e35b83 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1041,6 +1041,10 @@ set_rcvbuf: #endif case SO_MAX_PACING_RATE: + if (val != ~0U) + cmpxchg(&sk->sk_pacing_status, + SK_PACING_NONE, + SK_PACING_NEEDED); sk->sk_max_pacing_rate = val; sk->sk_pacing_rate = min(sk->sk_pacing_rate, sk->sk_max_pacing_rate); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index b89bce4c721e..92b045c72163 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -52,10 +52,9 @@ * There is a public e-mail list for discussing BBR development and testing: * https://groups.google.com/forum/#!forum/bbr-dev * - * NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled, - * since pacing is integral to the BBR design and implementation. - * BBR without pacing would not function properly, and may incur unnecessary - * high packet loss rates. + * NOTE: BBR might be used with the fq qdisc ("man tc-fq") with pacing enabled, + * otherwise TCP stack falls back to an internal pacing using one high + * resolution timer per TCP socket and may use more resources. */ #include #include @@ -830,6 +829,8 @@ static void bbr_init(struct sock *sk) bbr->cycle_idx = 0; bbr_reset_lt_bw_sampling(sk); bbr_reset_startup_mode(sk); + + cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); } static u32 bbr_sndbuf_expand(struct sock *sk) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4858e190f6ac..a32172d69a03 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -904,6 +904,72 @@ out: sk_free(sk); } +/* Note: Called under hard irq. + * We can not call TCP stack right away. + */ +enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) +{ + struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer); + struct sock *sk = (struct sock *)tp; + unsigned long nval, oval; + + for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { + struct tsq_tasklet *tsq; + bool empty; + + if (oval & TSQF_QUEUED) + break; + + nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED; + nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); + if (nval != oval) + continue; + + if (!atomic_inc_not_zero(&sk->sk_wmem_alloc)) + break; + /* queue this socket to tasklet queue */ + tsq = this_cpu_ptr(&tsq_tasklet); + empty = list_empty(&tsq->head); + list_add(&tp->tsq_node, &tsq->head); + if (empty) + tasklet_schedule(&tsq->tasklet); + break; + } + return HRTIMER_NORESTART; +} + +/* BBR congestion control needs pacing. + * Same remark for SO_MAX_PACING_RATE. + * sch_fq packet scheduler is efficiently handling pacing, + * but is not always installed/used. + * Return true if TCP stack should pace packets itself. + */ +static bool tcp_needs_internal_pacing(const struct sock *sk) +{ + return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; +} + +static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) +{ + u64 len_ns; + u32 rate; + + if (!tcp_needs_internal_pacing(sk)) + return; + rate = sk->sk_pacing_rate; + if (!rate || rate == ~0U) + return; + + /* Should account for header sizes as sch_fq does, + * but lets make things simple. + */ + len_ns = (u64)skb->len * NSEC_PER_SEC; + do_div(len_ns, rate); + hrtimer_start(&tcp_sk(sk)->pacing_timer, + ktime_add_ns(ktime_get(), len_ns), + HRTIMER_MODE_ABS_PINNED); +} + /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. @@ -1034,6 +1100,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); tp->data_segs_out += tcp_skb_pcount(skb); + tcp_internal_pacing(sk, skb); } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) @@ -2086,6 +2153,12 @@ static int tcp_mtu_probe(struct sock *sk) return -1; } +static bool tcp_pacing_check(const struct sock *sk) +{ + return tcp_needs_internal_pacing(sk) && + hrtimer_active(&tcp_sk(sk)->pacing_timer); +} + /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) @@ -2210,6 +2283,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, while ((skb = tcp_send_head(sk))) { unsigned int limit; + if (tcp_pacing_check(sk)) + break; + tso_segs = tcp_init_tso_segs(skb, mss_now); BUG_ON(!tso_segs); @@ -2878,6 +2954,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (skb == tcp_send_head(sk)) break; + + if (tcp_pacing_check(sk)) + break; + /* we could do better than to assign each time */ if (!hole) tp->retransmit_skb_hint = skb; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 14672543cf0b..86934bcf685a 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -710,4 +710,7 @@ void tcp_init_xmit_timers(struct sock *sk) { inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); + hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED); + tcp_sk(sk)->pacing_timer.function = tcp_pace_kick; } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index b488721a0059..147fde73a0f5 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -390,9 +390,17 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->stat_tcp_retrans++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { + struct sock *sk = skb->sk; + fq_flow_add_tail(&q->new_flows, f); if (time_after(jiffies, f->age + q->flow_refill_delay)) f->credit = max_t(u32, f->credit, q->quantum); + if (sk && q->rate_enable) { + if (unlikely(smp_load_acquire(&sk->sk_pacing_status) != + SK_PACING_FQ)) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + } q->inactive_flows--; } -- cgit v1.2.3 From 484a54c2e597dbc4ace79c1687022282905afba0 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Thu, 6 Apr 2017 11:38:26 +0200 Subject: mac80211: Dynamically set CoDel parameters per station MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CoDel can be too aggressive if a station sends at a very low rate, leading reduced throughput. This gets worse the more stations are present, as each station gets more bursty the longer the round-robin scheduling between stations takes. This adds dynamic adjustment of CoDel parameters per station. It uses the rate selection information to estimate throughput and sets more lenient CoDel parameters if the estimated throughput is below a threshold (modified by the number of active stations). A new callback is added that drivers can use to notify mac80211 about changes in expected throughput, so the same adjustment can be made for cards that implement rate control in firmware. Drivers that don't use this will just get the default parameters. Signed-off-by: Toke Høiland-Jørgensen [remove currently unnecessary EXPORT_SYMBOL, fix kernel-doc, remove inline annotation] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 16 ++++++++++++++++ net/mac80211/debugfs_sta.c | 6 ++++++ net/mac80211/rate.c | 3 ++- net/mac80211/sta_info.c | 30 ++++++++++++++++++++++++++++++ net/mac80211/sta_info.h | 11 +++++++++++ net/mac80211/tx.c | 9 ++++++++- 6 files changed, 73 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 76ed24a201eb..e01daff1e255 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -4204,6 +4204,22 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, struct ieee80211_tx_rate *dest, int max_rates); +/** + * ieee80211_sta_set_expected_throughput - set the expected tpt for a station + * + * Call this function to notify mac80211 about a change in expected throughput + * to a station. A driver for a device that does rate control in firmware can + * call this function when the expected throughput estimate towards a station + * changes. The information is used to tune the CoDel AQM applied to traffic + * going towards that station (which can otherwise be too aggressive and cause + * slow stations to starve). + * + * @pubsta: the station to set throughput for. + * @thr: the current expected throughput in kbps. + */ +void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta, + u32 thr); + /** * ieee80211_tx_status - transmit status callback * diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 42601820db20..b15412c21ac9 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -152,6 +152,12 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, spin_lock_bh(&local->fq.lock); rcu_read_lock(); + p += scnprintf(p, + bufsz+buf-p, + "target %uus interval %uus ecn %s\n", + codel_time_to_us(sta->cparams.target), + codel_time_to_us(sta->cparams.interval), + sta->cparams.ecn ? "yes" : "no"); p += scnprintf(p, bufsz+buf-p, "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets\n"); diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index ea1f4315c521..76f303fda3ed 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -943,6 +943,8 @@ int rate_control_set_rates(struct ieee80211_hw *hw, drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta); + ieee80211_sta_set_expected_throughput(pubsta, sta_get_expected_throughput(sta)); + return 0; } EXPORT_SYMBOL(rate_control_set_rates); @@ -991,4 +993,3 @@ void rate_control_deinitialize(struct ieee80211_local *local) local->rate_ctrl = NULL; rate_control_free(local, ref); } - diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 7cdf7a835bb0..f59434ac385d 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -20,6 +20,7 @@ #include #include +#include #include #include "ieee80211_i.h" #include "driver-ops.h" @@ -425,6 +426,11 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->sta.max_rc_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_BA; + sta->cparams.ce_threshold = CODEL_DISABLED_THRESHOLD; + sta->cparams.target = MS2TIME(20); + sta->cparams.interval = MS2TIME(100); + sta->cparams.ecn = true; + sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); return sta; @@ -2310,3 +2316,27 @@ unsigned long ieee80211_sta_last_active(struct sta_info *sta) return stats->last_rx; return sta->status_stats.last_ack; } + +static void sta_update_codel_params(struct sta_info *sta, u32 thr) +{ + if (!sta->sdata->local->ops->wake_tx_queue) + return; + + if (thr && thr < STA_SLOW_THRESHOLD * sta->local->num_sta) { + sta->cparams.target = MS2TIME(50); + sta->cparams.interval = MS2TIME(300); + sta->cparams.ecn = false; + } else { + sta->cparams.target = MS2TIME(20); + sta->cparams.interval = MS2TIME(100); + sta->cparams.ecn = true; + } +} + +void ieee80211_sta_set_expected_throughput(struct ieee80211_sta *pubsta, + u32 thr) +{ + struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + + sta_update_codel_params(sta, thr); +} diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 5609cacb20d5..b58c3b19ab78 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -393,6 +393,14 @@ struct ieee80211_sta_rx_stats { u64 msdu[IEEE80211_NUM_TIDS + 1]; }; +/** + * The bandwidth threshold below which the per-station CoDel parameters will be + * scaled to be more lenient (to prevent starvation of slow stations). This + * value will be scaled by the number of active stations when it is being + * applied. + */ +#define STA_SLOW_THRESHOLD 6000 /* 6 Mbps */ + /** * struct sta_info - STA information * @@ -446,6 +454,7 @@ struct ieee80211_sta_rx_stats { * @known_smps_mode: the smps_mode the client thinks we are in. Relevant for * AP only. * @cipher_scheme: optional cipher scheme for this station + * @cparams: CoDel parameters for this station. * @reserved_tid: reserved TID (if any, otherwise IEEE80211_TID_UNRESERVED) * @fast_tx: TX fastpath information * @fast_rx: RX fastpath information @@ -549,6 +558,8 @@ struct sta_info { enum ieee80211_smps_mode known_smps_mode; const struct ieee80211_cipher_scheme *cipher_scheme; + struct codel_params cparams; + u8 reserved_tid; struct cfg80211_chan_def tdls_chandef; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 04b22f8982fe..b8dc41191835 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1340,9 +1340,16 @@ static struct sk_buff *fq_tin_dequeue_func(struct fq *fq, local = container_of(fq, struct ieee80211_local, fq); txqi = container_of(tin, struct txq_info, tin); - cparams = &local->cparams; cstats = &txqi->cstats; + if (txqi->txq.sta) { + struct sta_info *sta = container_of(txqi->txq.sta, + struct sta_info, sta); + cparams = &sta->cparams; + } else { + cparams = &local->cparams; + } + if (flow == &txqi->def_flow) cvars = &txqi->def_cvars; else -- cgit v1.2.3 From 8b0d3ea555876533b6aa61479335be2c9bdb47e7 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Tue, 16 May 2017 14:10:33 -0400 Subject: net: dsa: store CPU port pointer in the tree A dsa_switch_tree instance holds a dsa_switch pointer and a port index to identify the switch port to which the CPU is attached. Now that the DSA layer has a dsa_port structure to hold this data, use it to point the switch CPU port. This patch simply substitutes s/dst->cpu_switch/dst->cpu_dp->ds/ and s/dst->cpu_port/dst->cpu_dp->index/. Signed-off-by: Vivien Didelot Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 4 ++-- drivers/net/dsa/bcm_sf2.c | 4 ++-- drivers/net/dsa/mv88e6060.c | 2 +- drivers/net/dsa/qca8k.c | 2 +- include/net/dsa.h | 13 ++++++------- net/dsa/dsa2.c | 14 ++++++-------- net/dsa/legacy.c | 10 ++++------ net/dsa/slave.c | 10 +++++----- net/dsa/tag_brcm.c | 2 +- net/dsa/tag_qca.c | 2 +- net/dsa/tag_trailer.c | 2 +- 11 files changed, 30 insertions(+), 35 deletions(-) (limited to 'include/net') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index fa0eece21eef..658a12c888a8 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1344,7 +1344,7 @@ EXPORT_SYMBOL(b53_fdb_dump); int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br) { struct b53_device *dev = ds->priv; - s8 cpu_port = ds->dst->cpu_port; + s8 cpu_port = ds->dst->cpu_dp->index; u16 pvlan, reg; unsigned int i; @@ -1390,7 +1390,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) { struct b53_device *dev = ds->priv; struct b53_vlan *vl = &dev->vlans[0]; - s8 cpu_port = ds->dst->cpu_port; + s8 cpu_port = ds->dst->cpu_dp->index; unsigned int i; u16 pvlan, reg, pvid; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 2be963252ca5..215d41c1e71f 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -228,7 +228,7 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port, struct phy_device *phy) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - s8 cpu_port = ds->dst[ds->index].cpu_port; + s8 cpu_port = ds->dst->cpu_dp->index; unsigned int i; u32 reg; @@ -832,7 +832,7 @@ static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port, { struct net_device *p = ds->dst[ds->index].master_netdev; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - s8 cpu_port = ds->dst[ds->index].cpu_port; + s8 cpu_port = ds->dst->cpu_dp->index; struct ethtool_wolinfo pwol; p->ethtool_ops->get_wol(p, &pwol); diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index 5934b7a4c448..dce7fa57eb55 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -176,7 +176,7 @@ static int mv88e6060_setup_port(struct dsa_switch *ds, int p) ((p & 0xf) << PORT_VLAN_MAP_DBNUM_SHIFT) | (dsa_is_cpu_port(ds, p) ? ds->enabled_port_mask : - BIT(ds->dst->cpu_port))); + BIT(ds->dst->cpu_dp->index))); /* Port Association Vector: when learning source addresses * of packets, add the address to the address database using diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index a4fd4ccf7b67..942b9ac7f92a 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -507,7 +507,7 @@ qca8k_setup(struct dsa_switch *ds) pr_warn("regmap initialization failed"); /* Initialize CPU port pad mode (xMII type, delays...) */ - phy_mode = of_get_phy_mode(ds->ports[ds->dst->cpu_port].dn); + phy_mode = of_get_phy_mode(ds->dst->cpu_dp->dn); if (phy_mode < 0) { pr_err("Can't find phy-mode for master device\n"); return phy_mode; diff --git a/include/net/dsa.h b/include/net/dsa.h index 8e24677b1c62..118a8bd2fd9a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -137,10 +137,9 @@ struct dsa_switch_tree { const struct ethtool_ops *master_orig_ethtool_ops; /* - * The switch and port to which the CPU is attached. + * The switch port to which the CPU is attached. */ - struct dsa_switch *cpu_switch; - s8 cpu_port; + struct dsa_port *cpu_dp; /* * Data for the individual switch chips. @@ -251,7 +250,7 @@ struct dsa_switch { static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { - return !!(ds == ds->dst->cpu_switch && p == ds->dst->cpu_port); + return ds->dst->cpu_dp == &ds->ports[p]; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) @@ -279,10 +278,10 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) * Else return the (DSA) port number that connects to the * switch that is one hop closer to the cpu. */ - if (dst->cpu_switch == ds) - return dst->cpu_port; + if (dst->cpu_dp->ds == ds) + return dst->cpu_dp->index; else - return ds->rtable[dst->cpu_switch->index]; + return ds->rtable[dst->cpu_dp->ds->index]; } struct switchdev_trans; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 033b3bfb63dc..2ac62349ba12 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -443,8 +443,8 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst) return err; } - if (dst->cpu_switch) { - err = dsa_cpu_port_ethtool_setup(dst->cpu_switch); + if (dst->cpu_dp) { + err = dsa_cpu_port_ethtool_setup(dst->cpu_dp->ds); if (err) return err; } @@ -484,8 +484,8 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) dsa_ds_unapply(dst, ds); } - if (dst->cpu_switch) - dsa_cpu_port_ethtool_restore(dst->cpu_switch); + if (dst->cpu_dp) + dsa_cpu_port_ethtool_restore(dst->cpu_dp->ds); pr_info("DSA: tree %d unapplied\n", dst->tree); dst->applied = false; @@ -518,10 +518,8 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, if (!dst->master_netdev) dst->master_netdev = ethernet_dev; - if (!dst->cpu_switch) { - dst->cpu_switch = ds; - dst->cpu_port = index; - } + if (!dst->cpu_dp) + dst->cpu_dp = port; tag_protocol = ds->ops->get_tag_protocol(ds); dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol); diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index ad345c8b0b06..bb28b011ba5a 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -115,13 +115,12 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) continue; if (!strcmp(name, "cpu")) { - if (dst->cpu_switch) { + if (dst->cpu_dp) { netdev_err(dst->master_netdev, "multiple cpu ports?!\n"); return -EINVAL; } - dst->cpu_switch = ds; - dst->cpu_port = i; + dst->cpu_dp = &ds->ports[i]; ds->cpu_port_mask |= 1 << i; } else if (!strcmp(name, "dsa")) { ds->dsa_port_mask |= 1 << i; @@ -144,7 +143,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) * tagging protocol to the preferred tagging format of this * switch. */ - if (dst->cpu_switch == ds) { + if (dst->cpu_dp->ds == ds) { enum dsa_tag_protocol tag_protocol; tag_protocol = ops->get_tag_protocol(ds); @@ -624,7 +623,6 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, dst->pd = pd; dst->master_netdev = dev; - dst->cpu_port = -1; for (i = 0; i < pd->nr_chips; i++) { struct dsa_switch *ds; @@ -735,7 +733,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) dsa_switch_destroy(ds); } - dsa_cpu_port_ethtool_restore(dst->cpu_switch); + dsa_cpu_port_ethtool_restore(dst->cpu_dp->ds); dev_put(dst->master_netdev); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7693182df81e..77324c483d14 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -821,8 +821,8 @@ static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev, uint64_t *data) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds = dst->cpu_switch; - s8 cpu_port = dst->cpu_port; + struct dsa_switch *ds = dst->cpu_dp->ds; + s8 cpu_port = dst->cpu_dp->index; int count = 0; if (dst->master_ethtool_ops.get_sset_count) { @@ -838,7 +838,7 @@ static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev, static int dsa_cpu_port_get_sset_count(struct net_device *dev, int sset) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds = dst->cpu_switch; + struct dsa_switch *ds = dst->cpu_dp->ds; int count = 0; if (dst->master_ethtool_ops.get_sset_count) @@ -854,8 +854,8 @@ static void dsa_cpu_port_get_strings(struct net_device *dev, uint32_t stringset, uint8_t *data) { struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_switch *ds = dst->cpu_switch; - s8 cpu_port = dst->cpu_port; + struct dsa_switch *ds = dst->cpu_dp->ds; + s8 cpu_port = dst->cpu_dp->index; int len = ETH_GSTRING_LEN; int mcount = 0, count; unsigned int i; diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 2a9b52c5af86..658ddee63dc9 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -101,7 +101,7 @@ static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, int source_port; u8 *brcm_tag; - ds = dst->cpu_switch; + ds = dst->cpu_dp->ds; if (unlikely(!pskb_may_pull(skb, BRCM_TAG_LEN))) goto out_drop; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 3ba3f59f7a34..be3b67750ac8 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -99,7 +99,7 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, /* This protocol doesn't support cascading multiple switches so it's * safe to assume the switch is first in the tree */ - ds = dst->cpu_switch; + ds = dst->cpu_dp->ds; if (!ds) goto out_drop; diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index aafc2fc74c30..aa05e276ea22 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -67,7 +67,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, u8 *trailer; int source_port; - ds = dst->cpu_switch; + ds = dst->cpu_dp->ds; if (skb_linearize(skb)) goto out_drop; -- cgit v1.2.3 From eb7b721129f1dc67041662da229a28dfc5c3c1dd Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 16 May 2017 22:40:07 +0200 Subject: net: dsa: Sort DSA tagging protocol drivers With more tag protocols being added, regain some order by sorting the entries in various places. Signed-off-by: Andrew Lunn Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 8 ++++---- net/dsa/Kconfig | 8 ++++---- net/dsa/Makefile | 6 +++--- net/dsa/dsa.c | 18 +++++++++--------- net/dsa/dsa_priv.h | 18 +++++++++--------- 5 files changed, 29 insertions(+), 29 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 118a8bd2fd9a..ed767beca9c6 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -27,13 +27,13 @@ struct fixed_phy_status; enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = 0, + DSA_TAG_PROTO_BRCM, DSA_TAG_PROTO_DSA, - DSA_TAG_PROTO_TRAILER, DSA_TAG_PROTO_EDSA, - DSA_TAG_PROTO_BRCM, - DSA_TAG_PROTO_QCA, - DSA_TAG_PROTO_MTK, DSA_TAG_PROTO_LAN9303, + DSA_TAG_PROTO_MTK, + DSA_TAG_PROTO_QCA, + DSA_TAG_PROTO_TRAILER, DSA_TAG_LAST, /* MUST BE LAST */ }; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 81a0868edb1d..297389b2ab35 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -25,16 +25,16 @@ config NET_DSA_TAG_DSA config NET_DSA_TAG_EDSA bool -config NET_DSA_TAG_TRAILER +config NET_DSA_TAG_LAN9303 bool -config NET_DSA_TAG_QCA +config NET_DSA_TAG_MTK bool -config NET_DSA_TAG_MTK +config NET_DSA_TAG_TRAILER bool -config NET_DSA_TAG_LAN9303 +config NET_DSA_TAG_QCA bool endif diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 0b747d75e65a..f8c0251d1f43 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -6,7 +6,7 @@ dsa_core-y += dsa.o slave.o dsa2.o switch.o legacy.o dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o -dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o -dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o -dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o dsa_core-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o +dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o +dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o +dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 26130ae438da..c0a1307c87dd 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -40,26 +40,26 @@ static const struct dsa_device_ops 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_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_TRAILER - [DSA_TAG_PROTO_TRAILER] = &trailer_netdev_ops, +#ifdef CONFIG_NET_DSA_TAG_LAN9303 + [DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops, #endif -#ifdef CONFIG_NET_DSA_TAG_BRCM - [DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops, +#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_MTK - [DSA_TAG_PROTO_MTK] = &mtk_netdev_ops, -#endif -#ifdef CONFIG_NET_DSA_TAG_LAN9303 - [DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops, +#ifdef CONFIG_NET_DSA_TAG_TRAILER + [DSA_TAG_PROTO_TRAILER] = &trailer_netdev_ops, #endif [DSA_TAG_PROTO_NONE] = &none_ops, }; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index f4a88e485213..e9003b79cbbc 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -75,25 +75,25 @@ void dsa_slave_unregister_notifier(void); 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; + /* 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_trailer.c */ -extern const struct dsa_device_ops trailer_netdev_ops; +/* tag_lan9303.c */ +extern const struct dsa_device_ops lan9303_netdev_ops; -/* tag_brcm.c */ -extern const struct dsa_device_ops brcm_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_mtk.c */ -extern const struct dsa_device_ops mtk_netdev_ops; - -/* tag_lan9303.c */ -extern const struct dsa_device_ops lan9303_netdev_ops; +/* tag_trailer.c */ +extern const struct dsa_device_ops trailer_netdev_ops; #endif -- cgit v1.2.3 From 87d83093bfc2f4938ff21524ebb50ecf53c15a64 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:07:54 +0200 Subject: net: sched: move tc_classify function to cls_api.c Move tc_classify function to cls_api.c where it belongs, rename it to fit the namespace. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 9 +++++++++ include/net/pkt_sched.h | 3 --- net/core/dev.c | 5 +++-- net/sched/cls_api.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ net/sched/sch_api.c | 48 ------------------------------------------------ net/sched/sch_atm.c | 2 +- net/sched/sch_cbq.c | 2 +- net/sched/sch_drr.c | 2 +- net/sched/sch_dsmark.c | 2 +- net/sched/sch_fq_codel.c | 2 +- net/sched/sch_hfsc.c | 2 +- net/sched/sch_htb.c | 2 +- net/sched/sch_multiq.c | 2 +- net/sched/sch_prio.c | 2 +- net/sched/sch_qfq.c | 2 +- net/sched/sch_sfb.c | 2 +- net/sched/sch_sfq.c | 2 +- 17 files changed, 72 insertions(+), 65 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 269fd78bb0ae..cb745067feb3 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -19,10 +19,19 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #ifdef CONFIG_NET_CLS void tcf_destroy_chain(struct tcf_proto __rcu **fl); +int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode); + #else static inline void tcf_destroy_chain(struct tcf_proto __rcu **fl) { } + +static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ + return TC_ACT_UNSPEC; +} #endif static inline unsigned long diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index bec46f63f10c..2579c209ea51 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -113,9 +113,6 @@ static inline void qdisc_run(struct Qdisc *q) __qdisc_run(q); } -int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode); - static inline __be16 tc_skb_protocol(const struct sk_buff *skb) { /* We need to take extra care in case the skb came via diff --git a/net/core/dev.c b/net/core/dev.c index fca407b4a6ea..acd594c56f0a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -105,6 +105,7 @@ #include #include #include +#include #include #include #include @@ -3178,7 +3179,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ qdisc_bstats_cpu_update(cl->q, skb); - switch (tc_classify(skb, cl, &cl_res, false)) { + switch (tcf_classify(skb, cl, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); @@ -3948,7 +3949,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, skb->tc_at_ingress = 1; qdisc_bstats_cpu_update(cl->q, skb); - switch (tc_classify(skb, cl, &cl_res, false)) { + switch (tcf_classify(skb, cl, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 22f88b35a546..af58bbef6610 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -196,6 +196,54 @@ void tcf_destroy_chain(struct tcf_proto __rcu **fl) } EXPORT_SYMBOL(tcf_destroy_chain); +/* Main classifier routine: scans classifier chain attached + * to this qdisc, (optionally) tests for protocol and asks + * specific classifiers. + */ +int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ + __be16 protocol = tc_skb_protocol(skb); +#ifdef CONFIG_NET_CLS_ACT + const int max_reclassify_loop = 4; + const struct tcf_proto *old_tp = tp; + int limit = 0; + +reclassify: +#endif + for (; tp; tp = rcu_dereference_bh(tp->next)) { + int err; + + if (tp->protocol != protocol && + tp->protocol != htons(ETH_P_ALL)) + continue; + + err = tp->classify(skb, tp, res); +#ifdef CONFIG_NET_CLS_ACT + if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) + goto reset; +#endif + if (err >= 0) + return err; + } + + return TC_ACT_UNSPEC; /* signal: continue lookup */ +#ifdef CONFIG_NET_CLS_ACT +reset: + if (unlikely(limit++ >= max_reclassify_loop)) { + net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n", + tp->q->ops->id, tp->prio & 0xffff, + ntohs(tp->protocol)); + return TC_ACT_SHOT; + } + + tp = old_tp; + protocol = tc_skb_protocol(skb); + goto reclassify; +#endif +} +EXPORT_SYMBOL(tcf_classify); + /* Add/change/delete/get a filter node */ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index e88342fde1bc..a3bcd972d940 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1878,54 +1878,6 @@ done: return skb->len; } -/* Main classifier routine: scans classifier chain attached - * to this qdisc, (optionally) tests for protocol and asks - * specific classifiers. - */ -int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode) -{ - __be16 protocol = tc_skb_protocol(skb); -#ifdef CONFIG_NET_CLS_ACT - const int max_reclassify_loop = 4; - const struct tcf_proto *old_tp = tp; - int limit = 0; - -reclassify: -#endif - for (; tp; tp = rcu_dereference_bh(tp->next)) { - int err; - - if (tp->protocol != protocol && - tp->protocol != htons(ETH_P_ALL)) - continue; - - err = tp->classify(skb, tp, res); -#ifdef CONFIG_NET_CLS_ACT - if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) - goto reset; -#endif - if (err >= 0) - return err; - } - - return TC_ACT_UNSPEC; /* signal: continue lookup */ -#ifdef CONFIG_NET_CLS_ACT -reset: - if (unlikely(limit++ >= max_reclassify_loop)) { - net_notice_ratelimited("%s: reclassify loop, rule prio %u, protocol %02x\n", - tp->q->ops->id, tp->prio & 0xffff, - ntohs(tp->protocol)); - return TC_ACT_SHOT; - } - - tp = old_tp; - protocol = tc_skb_protocol(skb); - goto reclassify; -#endif -} -EXPORT_SYMBOL(tc_classify); - #ifdef CONFIG_PROC_FS static int psched_show(struct seq_file *seq, void *v) { diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 40cbceed4de8..89d32fad9f89 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -377,7 +377,7 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, list_for_each_entry(flow, &p->flows, list) { fl = rcu_dereference_bh(flow->filter_list); if (fl) { - result = tc_classify(skb, fl, &res, true); + result = tcf_classify(skb, fl, &res, true); if (result < 0) continue; flow = (struct atm_flow_data *)res.class; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 7415859fd4c3..c543ea3e3043 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -233,7 +233,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 2+n. Apply classifier. */ - result = tc_classify(skb, fl, &res, true); + result = tcf_classify(skb, fl, &res, true); if (!fl || result < 0) goto fallback; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 58a8c32eab23..446d79bb25d9 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -333,7 +333,7 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 1c0f877f673a..7bc638d2e67f 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -234,7 +234,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, else { struct tcf_result res; struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tc_classify(skb, fl, &res, false); + int result = tcf_classify(skb, fl, &res, false); pr_debug("result %d class 0x%04x\n", result, res.classid); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 9201abce928c..42ba81ad327c 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -96,7 +96,7 @@ static unsigned int fq_codel_classify(struct sk_buff *skb, struct Qdisc *sch, return fq_codel_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, filter, &res, false); + result = tcf_classify(skb, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 5cb82f6c1b06..b0dcab199205 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1142,7 +1142,7 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; head = &q->root; tcf = rcu_dereference_bh(q->root.filter_list); - while (tcf && (result = tc_classify(skb, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 570ef3b0c09b..640f5f336195 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -231,7 +231,7 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, } *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - while (tcf && (result = tc_classify(skb, tcf, &res, false)) >= 0) { + while (tcf && (result = tcf_classify(skb, tcf, &res, false)) >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_QUEUED: diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 43a3a10b3c81..25bb9ffc2df1 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -46,7 +46,7 @@ multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) int err; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - err = tc_classify(skb, fl, &res, false); + err = tcf_classify(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 92c2e6d448d7..7997363f7e0d 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -42,7 +42,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; if (TC_H_MAJ(skb->priority) != sch->handle) { fl = rcu_dereference_bh(q->filter_list); - err = tc_classify(skb, fl, &res, false); + err = tcf_classify(skb, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 041eba3006cc..73c7ac37b570 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -720,7 +720,7 @@ static struct qfq_class *qfq_classify(struct sk_buff *skb, struct Qdisc *sch, *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; fl = rcu_dereference_bh(q->filter_list); - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 0f777273ba29..b287880829e2 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -259,7 +259,7 @@ static bool sfb_classify(struct sk_buff *skb, struct tcf_proto *fl, struct tcf_result res; int result; - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 332d94be6e1c..53a641f2ccb5 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -180,7 +180,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return sfq_hash(q, skb) + 1; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - result = tc_classify(skb, fl, &res, false); + result = tcf_classify(skb, fl, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { -- cgit v1.2.3 From 6529eaba33f0465fc6d228e1d05b1745f7d0e8c9 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:07:55 +0200 Subject: net: sched: introduce tcf block infractructure Currently, the filter chains are direcly put into the private structures of qdiscs. In order to be able to have multiple chains per qdisc and to allow filter chains sharing among qdiscs, there is a need for common object that would hold the chains. This introduces such object and calls it "tcf_block". Helpers to get and put the blocks are provided to be called from individual qdisc code. Also, the original filter_list pointers are left in qdisc privs to allow the entry into tcf_block processing without any added overhead of possible multiple pointer dereference on fast path. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 13 ++++++++-- include/net/sch_generic.h | 7 +++++- net/sched/cls_api.c | 48 +++++++++++++++++++++++++++++-------- net/sched/sch_api.c | 2 +- net/sched/sch_atm.c | 27 ++++++++++++++------- net/sched/sch_cbq.c | 19 ++++++++++----- net/sched/sch_drr.c | 13 ++++++---- net/sched/sch_dsmark.c | 17 ++++++++----- net/sched/sch_fq_codel.c | 15 ++++++++---- net/sched/sch_hfsc.c | 19 ++++++++++----- net/sched/sch_htb.c | 26 +++++++++++++------- net/sched/sch_ingress.c | 61 ++++++++++++++++++++++++++++++++++------------- net/sched/sch_multiq.c | 14 +++++++---- net/sched/sch_prio.c | 17 +++++++++---- net/sched/sch_qfq.c | 14 +++++++---- net/sched/sch_sfb.c | 15 ++++++++---- net/sched/sch_sfq.c | 15 ++++++++---- 17 files changed, 243 insertions(+), 99 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index cb745067feb3..e56e7157c280 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -18,12 +18,21 @@ int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #ifdef CONFIG_NET_CLS -void tcf_destroy_chain(struct tcf_proto __rcu **fl); +int tcf_block_get(struct tcf_block **p_block, + struct tcf_proto __rcu **p_filter_chain); +void tcf_block_put(struct tcf_block *block); int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); #else -static inline void tcf_destroy_chain(struct tcf_proto __rcu **fl) +static inline +int tcf_block_get(struct tcf_block **p_block, + struct tcf_proto __rcu **p_filter_chain) +{ + return 0; +} + +static inline void tcf_block_put(struct tcf_block *block) { } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 22e52093bfda..98cf2f23602d 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -153,7 +153,7 @@ struct Qdisc_class_ops { void (*walk)(struct Qdisc *, struct qdisc_walker * arg); /* Filter manipulation */ - struct tcf_proto __rcu ** (*tcf_chain)(struct Qdisc *, unsigned long); + struct tcf_block * (*tcf_block)(struct Qdisc *, unsigned long); bool (*tcf_cl_offload)(u32 classid); unsigned long (*bind_tcf)(struct Qdisc *, unsigned long, u32 classid); @@ -236,6 +236,7 @@ struct tcf_proto { struct Qdisc *q; void *data; const struct tcf_proto_ops *ops; + struct tcf_block *block; struct rcu_head rcu; }; @@ -247,6 +248,10 @@ struct qdisc_skb_cb { unsigned char data[QDISC_CB_PRIV_LEN]; }; +struct tcf_block { + struct tcf_proto __rcu **p_filter_chain; +}; + static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index af58bbef6610..d30116f77156 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -129,7 +129,8 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) } static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, - u32 prio, u32 parent, struct Qdisc *q) + u32 prio, u32 parent, struct Qdisc *q, + struct tcf_block *block) { struct tcf_proto *tp; int err; @@ -165,6 +166,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, tp->prio = prio; tp->classid = parent; tp->q = q; + tp->block = block; err = tp->ops->init(tp); if (err) { @@ -185,7 +187,7 @@ static void tcf_proto_destroy(struct tcf_proto *tp) kfree_rcu(tp, rcu); } -void tcf_destroy_chain(struct tcf_proto __rcu **fl) +static void tcf_destroy_chain(struct tcf_proto __rcu **fl) { struct tcf_proto *tp; @@ -194,7 +196,28 @@ void tcf_destroy_chain(struct tcf_proto __rcu **fl) tcf_proto_destroy(tp); } } -EXPORT_SYMBOL(tcf_destroy_chain); + +int tcf_block_get(struct tcf_block **p_block, + struct tcf_proto __rcu **p_filter_chain) +{ + struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); + + if (!block) + return -ENOMEM; + block->p_filter_chain = p_filter_chain; + *p_block = block; + return 0; +} +EXPORT_SYMBOL(tcf_block_get); + +void tcf_block_put(struct tcf_block *block) +{ + if (!block) + return; + tcf_destroy_chain(block->p_filter_chain); + kfree(block); +} +EXPORT_SYMBOL(tcf_block_put); /* Main classifier routine: scans classifier chain attached * to this qdisc, (optionally) tests for protocol and asks @@ -260,6 +283,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct Qdisc *q; struct tcf_proto __rcu **back; struct tcf_proto __rcu **chain; + struct tcf_block *block; struct tcf_proto *next; struct tcf_proto *tp; const struct Qdisc_class_ops *cops; @@ -328,7 +352,7 @@ replay: if (!cops) return -EINVAL; - if (cops->tcf_chain == NULL) + if (!cops->tcf_block) return -EOPNOTSUPP; /* Do we search for filter, attached to class? */ @@ -339,11 +363,13 @@ replay: } /* And the last stroke */ - chain = cops->tcf_chain(q, cl); - if (chain == NULL) { + block = cops->tcf_block(q, cl); + if (!block) { err = -EINVAL; goto errout; } + chain = block->p_filter_chain; + if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); tcf_destroy_chain(chain); @@ -387,7 +413,7 @@ replay: nprio = TC_H_MAJ(tcf_auto_prio(rtnl_dereference(*back))); tp = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, nprio, parent, q); + protocol, nprio, parent, q, block); if (IS_ERR(tp)) { err = PTR_ERR(tp); goto errout; @@ -556,6 +582,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) int s_t; struct net_device *dev; struct Qdisc *q; + struct tcf_block *block; struct tcf_proto *tp, __rcu **chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); unsigned long cl = 0; @@ -577,16 +604,17 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) cops = q->ops->cl_ops; if (!cops) goto errout; - if (cops->tcf_chain == NULL) + if (!cops->tcf_block) goto errout; if (TC_H_MIN(tcm->tcm_parent)) { cl = cops->get(q, tcm->tcm_parent); if (cl == 0) goto errout; } - chain = cops->tcf_chain(q, cl); - if (chain == NULL) + block = cops->tcf_block(q, cl); + if (!block) goto errout; + chain = block->p_filter_chain; s_t = cb->args[0]; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index a3bcd972d940..5d95401bbc02 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -163,7 +163,7 @@ int register_qdisc(struct Qdisc_ops *qops) if (!(cops->get && cops->put && cops->walk && cops->leaf)) goto out_einval; - if (cops->tcf_chain && !(cops->bind_tcf && cops->unbind_tcf)) + if (cops->tcf_block && !(cops->bind_tcf && cops->unbind_tcf)) goto out_einval; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 89d32fad9f89..f435546c3864 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -43,6 +43,7 @@ struct atm_flow_data { struct Qdisc *q; /* FIFO, TBF, etc. */ struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ void (*old_pop)(struct atm_vcc *vcc, struct sk_buff *skb); /* chaining */ @@ -143,7 +144,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl) list_del_init(&flow->list); pr_debug("atm_tc_put: qdisc %p\n", flow->q); qdisc_destroy(flow->q); - tcf_destroy_chain(&flow->filter_list); + tcf_block_put(flow->block); if (flow->sock) { pr_debug("atm_tc_put: f_count %ld\n", file_count(flow->sock->file)); @@ -274,7 +275,13 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, error = -ENOBUFS; goto err_out; } - RCU_INIT_POINTER(flow->filter_list, NULL); + + error = tcf_block_get(&flow->block, &flow->filter_list); + if (error) { + kfree(flow); + goto err_out; + } + flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); if (!flow->q) flow->q = &noop_qdisc; @@ -346,14 +353,13 @@ static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_proto __rcu **atm_tc_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl) { struct atm_qdisc_data *p = qdisc_priv(sch); struct atm_flow_data *flow = (struct atm_flow_data *)cl; pr_debug("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - return flow ? &flow->filter_list : &p->link.filter_list; + return flow ? flow->block : p->link.block; } /* --------------------------- Qdisc operations ---------------------------- */ @@ -524,6 +530,7 @@ static struct sk_buff *atm_tc_peek(struct Qdisc *sch) static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) { struct atm_qdisc_data *p = qdisc_priv(sch); + int err; pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); INIT_LIST_HEAD(&p->flows); @@ -534,7 +541,11 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) if (!p->link.q) p->link.q = &noop_qdisc; pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - RCU_INIT_POINTER(p->link.filter_list, NULL); + + err = tcf_block_get(&p->link.block, &p->link.filter_list); + if (err) + return err; + p->link.vcc = NULL; p->link.sock = NULL; p->link.classid = sch->handle; @@ -561,7 +572,7 @@ static void atm_tc_destroy(struct Qdisc *sch) pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); list_for_each_entry(flow, &p->flows, list) - tcf_destroy_chain(&flow->filter_list); + tcf_block_put(flow->block); list_for_each_entry_safe(flow, tmp, &p->flows, list) { if (flow->ref > 1) @@ -646,7 +657,7 @@ static const struct Qdisc_class_ops atm_class_ops = { .change = atm_tc_change, .delete = atm_tc_delete, .walk = atm_tc_walk, - .tcf_chain = atm_tc_find_tcf, + .tcf_block = atm_tc_tcf_block, .bind_tcf = atm_tc_bind_filter, .unbind_tcf = atm_tc_put, .dump = atm_tc_dump_class, diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index c543ea3e3043..8dd6d0aca678 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -127,6 +127,7 @@ struct cbq_class { struct tc_cbq_xstats xstats; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; int refcnt; int filters; @@ -1405,7 +1406,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) WARN_ON(cl->filters); - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); qdisc_destroy(cl->q); qdisc_put_rtab(cl->R_tab); gen_kill_estimator(&cl->rate_est); @@ -1430,7 +1431,7 @@ static void cbq_destroy(struct Qdisc *sch) */ for (h = 0; h < q->clhash.hashsize; h++) { hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); } for (h = 0; h < q->clhash.hashsize; h++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], @@ -1585,12 +1586,19 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (cl == NULL) goto failure; + err = tcf_block_get(&cl->block, &cl->filter_list); + if (err) { + kfree(cl); + return err; + } + if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { + tcf_block_put(cl->block); kfree(cl); goto failure; } @@ -1688,8 +1696,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) return 0; } -static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch, - unsigned long arg) +static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl = (struct cbq_class *)arg; @@ -1697,7 +1704,7 @@ static struct tcf_proto __rcu **cbq_find_tcf(struct Qdisc *sch, if (cl == NULL) cl = &q->link; - return &cl->filter_list; + return cl->block; } static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, @@ -1756,7 +1763,7 @@ static const struct Qdisc_class_ops cbq_class_ops = { .change = cbq_change_class, .delete = cbq_delete, .walk = cbq_walk, - .tcf_chain = cbq_find_tcf, + .tcf_block = cbq_tcf_block, .bind_tcf = cbq_bind_filter, .unbind_tcf = cbq_unbind_filter, .dump = cbq_dump_class, diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 446d79bb25d9..5db2a2843c66 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -36,6 +36,7 @@ struct drr_class { struct drr_sched { struct list_head active; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct Qdisc_class_hash clhash; }; @@ -190,15 +191,14 @@ static void drr_put_class(struct Qdisc *sch, unsigned long arg) drr_destroy_class(sch, cl); } -static struct tcf_proto __rcu **drr_tcf_chain(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *drr_tcf_block(struct Qdisc *sch, unsigned long cl) { struct drr_sched *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent, @@ -431,6 +431,9 @@ static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt) struct drr_sched *q = qdisc_priv(sch); int err; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; @@ -462,7 +465,7 @@ static void drr_destroy_qdisc(struct Qdisc *sch) struct hlist_node *next; unsigned int i; - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -477,7 +480,7 @@ static const struct Qdisc_class_ops drr_class_ops = { .delete = drr_delete_class, .get = drr_get_class, .put = drr_put_class, - .tcf_chain = drr_tcf_chain, + .tcf_block = drr_tcf_block, .bind_tcf = drr_bind_tcf, .unbind_tcf = drr_unbind_tcf, .graft = drr_graft_class, diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 7bc638d2e67f..ba45102cff94 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -44,6 +44,7 @@ struct mask_value { struct dsmark_qdisc_data { struct Qdisc *q; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct mask_value *mv; u16 indices; u8 set_tc_index; @@ -183,11 +184,11 @@ ignore: } } -static inline struct tcf_proto __rcu **dsmark_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl) { struct dsmark_qdisc_data *p = qdisc_priv(sch); - return &p->filter_list; + + return p->block; } /* --------------------------- Qdisc operations ---------------------------- */ @@ -332,7 +333,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) { struct dsmark_qdisc_data *p = qdisc_priv(sch); struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; + int err; u32 default_index = NO_DEFAULT_INDEX; u16 indices; int i; @@ -342,6 +343,10 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) goto errout; + err = tcf_block_get(&p->block, &p->filter_list); + if (err) + return err; + err = nla_parse_nested(tb, TCA_DSMARK_MAX, opt, dsmark_policy, NULL); if (err < 0) goto errout; @@ -400,7 +405,7 @@ static void dsmark_destroy(struct Qdisc *sch) pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - tcf_destroy_chain(&p->filter_list); + tcf_block_put(p->block); qdisc_destroy(p->q); if (p->mv != p->embedded) kfree(p->mv); @@ -468,7 +473,7 @@ static const struct Qdisc_class_ops dsmark_class_ops = { .change = dsmark_change, .delete = dsmark_delete, .walk = dsmark_walk, - .tcf_chain = dsmark_find_tcf, + .tcf_block = dsmark_tcf_block, .bind_tcf = dsmark_bind_filter, .unbind_tcf = dsmark_put, .dump = dsmark_dump_class, diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 42ba81ad327c..f201e73947fb 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -55,6 +55,7 @@ struct fq_codel_flow { struct fq_codel_sched_data { struct tcf_proto __rcu *filter_list; /* optional external classifier */ + struct tcf_block *block; struct fq_codel_flow *flows; /* Flows table [flows_cnt] */ u32 *backlogs; /* backlog table [flows_cnt] */ u32 flows_cnt; /* number of flows */ @@ -450,7 +451,7 @@ static void fq_codel_destroy(struct Qdisc *sch) { struct fq_codel_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); kvfree(q->backlogs); kvfree(q->flows); } @@ -459,6 +460,7 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) { struct fq_codel_sched_data *q = qdisc_priv(sch); int i; + int err; sch->limit = 10*1024; q->flows_cnt = 1024; @@ -478,6 +480,10 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) return err; } + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + if (!q->flows) { q->flows = kvzalloc(q->flows_cnt * sizeof(struct fq_codel_flow), GFP_KERNEL); @@ -589,14 +595,13 @@ static void fq_codel_put(struct Qdisc *q, unsigned long cl) { } -static struct tcf_proto __rcu **fq_codel_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *fq_codel_tcf_block(struct Qdisc *sch, unsigned long cl) { struct fq_codel_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static int fq_codel_dump_class(struct Qdisc *sch, unsigned long cl, @@ -679,7 +684,7 @@ static const struct Qdisc_class_ops fq_codel_class_ops = { .leaf = fq_codel_leaf, .get = fq_codel_get, .put = fq_codel_put, - .tcf_chain = fq_codel_find_tcf, + .tcf_block = fq_codel_tcf_block, .bind_tcf = fq_codel_bind, .unbind_tcf = fq_codel_put, .dump = fq_codel_dump_class, diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b0dcab199205..a324f84b1ccd 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -116,6 +116,7 @@ struct hfsc_class { struct gnet_stats_queue qstats; struct net_rate_estimator __rcu *rate_est; struct tcf_proto __rcu *filter_list; /* filter list */ + struct tcf_block *block; unsigned int filter_cnt; /* filter count */ unsigned int level; /* class level in hierarchy */ @@ -1040,12 +1041,19 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; + err = tcf_block_get(&cl->block, &cl->filter_list); + if (err) { + kfree(cl); + return err; + } + if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { + tcf_block_put(cl->block); kfree(cl); return err; } @@ -1091,7 +1099,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) { struct hfsc_sched *q = qdisc_priv(sch); - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); qdisc_destroy(cl->qdisc); gen_kill_estimator(&cl->rate_est); if (cl != &q->root) @@ -1261,8 +1269,7 @@ hfsc_unbind_tcf(struct Qdisc *sch, unsigned long arg) cl->filter_cnt--; } -static struct tcf_proto __rcu ** -hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg) +static struct tcf_block *hfsc_tcf_block(struct Qdisc *sch, unsigned long arg) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl = (struct hfsc_class *)arg; @@ -1270,7 +1277,7 @@ hfsc_tcf_chain(struct Qdisc *sch, unsigned long arg) if (cl == NULL) cl = &q->root; - return &cl->filter_list; + return cl->block; } static int @@ -1515,7 +1522,7 @@ hfsc_destroy_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1662,7 +1669,7 @@ static const struct Qdisc_class_ops hfsc_class_ops = { .put = hfsc_put_class, .bind_tcf = hfsc_bind_tcf, .unbind_tcf = hfsc_unbind_tcf, - .tcf_chain = hfsc_tcf_chain, + .tcf_block = hfsc_tcf_block, .dump = hfsc_dump_class, .dump_stats = hfsc_dump_class_stats, .walk = hfsc_walk diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 640f5f336195..195bbca9eb0b 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -105,6 +105,7 @@ struct htb_class { int quantum; /* but stored for parent-to-leaf return */ struct tcf_proto __rcu *filter_list; /* class attached filters */ + struct tcf_block *block; int filter_cnt; int refcnt; /* usage count of this class */ @@ -156,6 +157,7 @@ struct htb_sched { /* filters for qdisc itself */ struct tcf_proto __rcu *filter_list; + struct tcf_block *block; #define HTB_WARN_TOOMANYEVENTS 0x1 unsigned int warned; /* only one warning */ @@ -1017,6 +1019,10 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) if (!opt) return -EINVAL; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + err = nla_parse_nested(tb, TCA_HTB_MAX, opt, htb_policy, NULL); if (err < 0) return err; @@ -1230,7 +1236,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) qdisc_destroy(cl->un.leaf.q); } gen_kill_estimator(&cl->rate_est); - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); kfree(cl); } @@ -1248,11 +1254,11 @@ static void htb_destroy(struct Qdisc *sch) * because filter need its target class alive to be able to call * unbind_filter on it (without Oops). */ - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) - tcf_destroy_chain(&cl->filter_list); + tcf_block_put(cl->block); } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1396,6 +1402,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!cl) goto failure; + err = tcf_block_get(&cl->block, &cl->filter_list); + if (err) { + kfree(cl); + goto failure; + } if (htb_rate_est || tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, @@ -1403,6 +1414,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_root_sleeping_running(sch), tca[TCA_RATE] ? : &est.nla); if (err) { + tcf_block_put(cl->block); kfree(cl); goto failure; } @@ -1521,14 +1533,12 @@ failure: return err; } -static struct tcf_proto __rcu **htb_find_tcf(struct Qdisc *sch, - unsigned long arg) +static struct tcf_block *htb_tcf_block(struct Qdisc *sch, unsigned long arg) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; - struct tcf_proto __rcu **fl = cl ? &cl->filter_list : &q->filter_list; - return fl; + return cl ? cl->block : q->block; } static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent, @@ -1591,7 +1601,7 @@ static const struct Qdisc_class_ops htb_class_ops = { .change = htb_change_class, .delete = htb_delete, .walk = htb_walk, - .tcf_chain = htb_find_tcf, + .tcf_block = htb_tcf_block, .bind_tcf = htb_bind_filter, .unbind_tcf = htb_unbind_filter, .dump = htb_dump_class, diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 3bab5f66c392..d8a9bebcab90 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -18,6 +18,10 @@ #include #include +struct ingress_sched_data { + struct tcf_block *block; +}; + static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg) { return NULL; @@ -47,16 +51,23 @@ static void ingress_walk(struct Qdisc *sch, struct qdisc_walker *walker) { } -static struct tcf_proto __rcu **ingress_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *ingress_tcf_block(struct Qdisc *sch, unsigned long cl) { - struct net_device *dev = qdisc_dev(sch); + struct ingress_sched_data *q = qdisc_priv(sch); - return &dev->ingress_cl_list; + return q->block; } static int ingress_init(struct Qdisc *sch, struct nlattr *opt) { + struct ingress_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err; + + err = tcf_block_get(&q->block, &dev->ingress_cl_list); + if (err) + return err; + net_inc_ingress_queue(); sch->flags |= TCQ_F_CPUSTATS; @@ -65,9 +76,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt) static void ingress_destroy(struct Qdisc *sch) { - struct net_device *dev = qdisc_dev(sch); + struct ingress_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&dev->ingress_cl_list); + tcf_block_put(q->block); net_dec_ingress_queue(); } @@ -91,7 +102,7 @@ static const struct Qdisc_class_ops ingress_class_ops = { .get = ingress_get, .put = ingress_put, .walk = ingress_walk, - .tcf_chain = ingress_find_tcf, + .tcf_block = ingress_tcf_block, .tcf_cl_offload = ingress_cl_offload, .bind_tcf = ingress_bind_filter, .unbind_tcf = ingress_put, @@ -100,12 +111,18 @@ static const struct Qdisc_class_ops ingress_class_ops = { static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", + .priv_size = sizeof(struct ingress_sched_data), .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, .owner = THIS_MODULE, }; +struct clsact_sched_data { + struct tcf_block *ingress_block; + struct tcf_block *egress_block; +}; + static unsigned long clsact_get(struct Qdisc *sch, u32 classid) { switch (TC_H_MIN(classid)) { @@ -128,16 +145,15 @@ static unsigned long clsact_bind_filter(struct Qdisc *sch, return clsact_get(sch, classid); } -static struct tcf_proto __rcu **clsact_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *clsact_tcf_block(struct Qdisc *sch, unsigned long cl) { - struct net_device *dev = qdisc_dev(sch); + struct clsact_sched_data *q = qdisc_priv(sch); switch (cl) { case TC_H_MIN(TC_H_MIN_INGRESS): - return &dev->ingress_cl_list; + return q->ingress_block; case TC_H_MIN(TC_H_MIN_EGRESS): - return &dev->egress_cl_list; + return q->egress_block; default: return NULL; } @@ -145,6 +161,18 @@ static struct tcf_proto __rcu **clsact_find_tcf(struct Qdisc *sch, static int clsact_init(struct Qdisc *sch, struct nlattr *opt) { + struct clsact_sched_data *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err; + + err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list); + if (err) + return err; + + err = tcf_block_get(&q->egress_block, &dev->egress_cl_list); + if (err) + return err; + net_inc_ingress_queue(); net_inc_egress_queue(); @@ -155,10 +183,10 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt) static void clsact_destroy(struct Qdisc *sch) { - struct net_device *dev = qdisc_dev(sch); + struct clsact_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&dev->ingress_cl_list); - tcf_destroy_chain(&dev->egress_cl_list); + tcf_block_put(q->egress_block); + tcf_block_put(q->ingress_block); net_dec_ingress_queue(); net_dec_egress_queue(); @@ -169,7 +197,7 @@ static const struct Qdisc_class_ops clsact_class_ops = { .get = clsact_get, .put = ingress_put, .walk = ingress_walk, - .tcf_chain = clsact_find_tcf, + .tcf_block = clsact_tcf_block, .tcf_cl_offload = clsact_cl_offload, .bind_tcf = clsact_bind_filter, .unbind_tcf = ingress_put, @@ -178,6 +206,7 @@ static const struct Qdisc_class_ops clsact_class_ops = { static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", + .priv_size = sizeof(struct clsact_sched_data), .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 25bb9ffc2df1..604767482ad0 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -32,6 +32,7 @@ struct multiq_sched_data { u16 max_bands; u16 curband; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct Qdisc **queues; }; @@ -170,7 +171,7 @@ multiq_destroy(struct Qdisc *sch) int band; struct multiq_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (band = 0; band < q->bands; band++) qdisc_destroy(q->queues[band]); @@ -243,6 +244,10 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) if (opt == NULL) return -EINVAL; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + q->max_bands = qdisc_dev(sch)->num_tx_queues; q->queues = kcalloc(q->max_bands, sizeof(struct Qdisc *), GFP_KERNEL); @@ -367,14 +372,13 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto __rcu **multiq_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl) { struct multiq_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static const struct Qdisc_class_ops multiq_class_ops = { @@ -383,7 +387,7 @@ static const struct Qdisc_class_ops multiq_class_ops = { .get = multiq_get, .put = multiq_put, .walk = multiq_walk, - .tcf_chain = multiq_find_tcf, + .tcf_block = multiq_tcf_block, .bind_tcf = multiq_bind, .unbind_tcf = multiq_put, .dump = multiq_dump_class, diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 7997363f7e0d..a2404688dd01 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -25,6 +25,7 @@ struct prio_sched_data { int bands; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; u8 prio2band[TC_PRIO_MAX+1]; struct Qdisc *queues[TCQ_PRIO_BANDS]; }; @@ -145,7 +146,7 @@ prio_destroy(struct Qdisc *sch) int prio; struct prio_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (prio = 0; prio < q->bands; prio++) qdisc_destroy(q->queues[prio]); } @@ -204,9 +205,16 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) static int prio_init(struct Qdisc *sch, struct nlattr *opt) { + struct prio_sched_data *q = qdisc_priv(sch); + int err; + if (!opt) return -EINVAL; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + return prio_tune(sch, opt); } @@ -317,14 +325,13 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto __rcu **prio_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *prio_tcf_block(struct Qdisc *sch, unsigned long cl) { struct prio_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static const struct Qdisc_class_ops prio_class_ops = { @@ -333,7 +340,7 @@ static const struct Qdisc_class_ops prio_class_ops = { .get = prio_get, .put = prio_put, .walk = prio_walk, - .tcf_chain = prio_find_tcf, + .tcf_block = prio_tcf_block, .bind_tcf = prio_bind, .unbind_tcf = prio_put, .dump = prio_dump_class, diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 73c7ac37b570..076ad032befb 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -182,6 +182,7 @@ struct qfq_group { struct qfq_sched { struct tcf_proto __rcu *filter_list; + struct tcf_block *block; struct Qdisc_class_hash clhash; u64 oldV, V; /* Precise virtual times. */ @@ -582,15 +583,14 @@ static void qfq_put_class(struct Qdisc *sch, unsigned long arg) qfq_destroy_class(sch, cl); } -static struct tcf_proto __rcu **qfq_tcf_chain(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *qfq_tcf_block(struct Qdisc *sch, unsigned long cl) { struct qfq_sched *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static unsigned long qfq_bind_tcf(struct Qdisc *sch, unsigned long parent, @@ -1438,6 +1438,10 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) int i, j, err; u32 max_cl_shift, maxbudg_shift, max_classes; + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; + err = qdisc_class_hash_init(&q->clhash); if (err < 0) return err; @@ -1492,7 +1496,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) struct hlist_node *next; unsigned int i; - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], @@ -1508,7 +1512,7 @@ static const struct Qdisc_class_ops qfq_class_ops = { .delete = qfq_delete_class, .get = qfq_get_class, .put = qfq_put_class, - .tcf_chain = qfq_tcf_chain, + .tcf_block = qfq_tcf_block, .bind_tcf = qfq_bind_tcf, .unbind_tcf = qfq_unbind_tcf, .graft = qfq_graft_class, diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index b287880829e2..9756b1ccd345 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -56,6 +56,7 @@ struct sfb_bins { struct sfb_sched_data { struct Qdisc *qdisc; struct tcf_proto __rcu *filter_list; + struct tcf_block *block; unsigned long rehash_interval; unsigned long warmup_time; /* double buffering warmup time in jiffies */ u32 max; @@ -465,7 +466,7 @@ static void sfb_destroy(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); qdisc_destroy(q->qdisc); } @@ -549,6 +550,11 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) static int sfb_init(struct Qdisc *sch, struct nlattr *opt) { struct sfb_sched_data *q = qdisc_priv(sch); + int err; + + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; q->qdisc = &noop_qdisc; return sfb_change(sch, opt); @@ -657,14 +663,13 @@ static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static struct tcf_proto __rcu **sfb_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *sfb_tcf_block(struct Qdisc *sch, unsigned long cl) { struct sfb_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static unsigned long sfb_bind(struct Qdisc *sch, unsigned long parent, @@ -682,7 +687,7 @@ static const struct Qdisc_class_ops sfb_class_ops = { .change = sfb_change_class, .delete = sfb_delete, .walk = sfb_walk, - .tcf_chain = sfb_find_tcf, + .tcf_block = sfb_tcf_block, .bind_tcf = sfb_bind, .unbind_tcf = sfb_put, .dump = sfb_dump_class, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 53a641f2ccb5..66dfd15b7946 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -126,6 +126,7 @@ struct sfq_sched_data { u8 flags; unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ struct tcf_proto __rcu *filter_list; + struct tcf_block *block; sfq_index *ht; /* Hash table ('divisor' slots) */ struct sfq_slot *slots; /* Flows table ('maxflows' entries) */ @@ -697,7 +698,7 @@ static void sfq_destroy(struct Qdisc *sch) { struct sfq_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(&q->filter_list); + tcf_block_put(q->block); q->perturb_period = 0; del_timer_sync(&q->perturb_timer); sfq_free(q->ht); @@ -709,6 +710,11 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) { struct sfq_sched_data *q = qdisc_priv(sch); int i; + int err; + + err = tcf_block_get(&q->block, &q->filter_list); + if (err) + return err; setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, (unsigned long)sch); @@ -815,14 +821,13 @@ static void sfq_put(struct Qdisc *q, unsigned long cl) { } -static struct tcf_proto __rcu **sfq_find_tcf(struct Qdisc *sch, - unsigned long cl) +static struct tcf_block *sfq_tcf_block(struct Qdisc *sch, unsigned long cl) { struct sfq_sched_data *q = qdisc_priv(sch); if (cl) return NULL; - return &q->filter_list; + return q->block; } static int sfq_dump_class(struct Qdisc *sch, unsigned long cl, @@ -878,7 +883,7 @@ static const struct Qdisc_class_ops sfq_class_ops = { .leaf = sfq_leaf, .get = sfq_get, .put = sfq_put, - .tcf_chain = sfq_find_tcf, + .tcf_block = sfq_tcf_block, .bind_tcf = sfq_bind, .unbind_tcf = sfq_put, .dump = sfq_dump_class, -- cgit v1.2.3 From 2190d1d0944f84c55cdfdb89c7920f8f9311bdde Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:07:59 +0200 Subject: net: sched: introduce helpers to work with filter chains Introduce struct tcf_chain object and set of helpers around it. Wraps up insertion, deletion and search in the filter chain. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/sch_generic.h | 7 ++- net/sched/cls_api.c | 148 +++++++++++++++++++++++++++++++++------------- 2 files changed, 113 insertions(+), 42 deletions(-) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 98cf2f23602d..52bceede534b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -248,10 +248,15 @@ struct qdisc_skb_cb { unsigned char data[QDISC_CB_PRIV_LEN]; }; -struct tcf_block { +struct tcf_chain { + struct tcf_proto __rcu *filter_chain; struct tcf_proto __rcu **p_filter_chain; }; +struct tcf_block { + struct tcf_chain *chain; +}; + static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 690457c988b2..fee3d7faeb79 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -106,13 +106,12 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, - struct tcf_proto __rcu **chain, int event) + struct tcf_chain *chain, int event) { - struct tcf_proto __rcu **it_chain; struct tcf_proto *tp; - for (it_chain = chain; (tp = rtnl_dereference(*it_chain)) != NULL; - it_chain = &tp->next) + for (tp = rtnl_dereference(chain->filter_chain); + tp; tp = rtnl_dereference(tp->next)) tfilter_notify(net, oskb, n, tp, 0, event, false); } @@ -187,26 +186,49 @@ static void tcf_proto_destroy(struct tcf_proto *tp) kfree_rcu(tp, rcu); } -static void tcf_chain_destroy(struct tcf_proto __rcu **fl) +static struct tcf_chain *tcf_chain_create(void) +{ + return kzalloc(sizeof(struct tcf_chain), GFP_KERNEL); +} + +static void tcf_chain_destroy(struct tcf_chain *chain) { struct tcf_proto *tp; - while ((tp = rtnl_dereference(*fl)) != NULL) { - RCU_INIT_POINTER(*fl, tp->next); + while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) { + RCU_INIT_POINTER(chain->filter_chain, tp->next); tcf_proto_destroy(tp); } + kfree(chain); +} + +static void +tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain, + struct tcf_proto __rcu **p_filter_chain) +{ + chain->p_filter_chain = p_filter_chain; } int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain) { struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); + int err; if (!block) return -ENOMEM; - block->p_filter_chain = p_filter_chain; + block->chain = tcf_chain_create(); + if (!block->chain) { + err = -ENOMEM; + goto err_chain_create; + } + tcf_chain_filter_chain_ptr_set(block->chain, p_filter_chain); *p_block = block; return 0; + +err_chain_create: + kfree(block); + return err; } EXPORT_SYMBOL(tcf_block_get); @@ -214,7 +236,7 @@ void tcf_block_put(struct tcf_block *block) { if (!block) return; - tcf_chain_destroy(block->p_filter_chain); + tcf_chain_destroy(block->chain); kfree(block); } EXPORT_SYMBOL(tcf_block_put); @@ -267,6 +289,65 @@ reset: } EXPORT_SYMBOL(tcf_classify); +struct tcf_chain_info { + struct tcf_proto __rcu **pprev; + struct tcf_proto __rcu *next; +}; + +static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain_info *chain_info) +{ + return rtnl_dereference(*chain_info->pprev); +} + +static void tcf_chain_tp_insert(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + struct tcf_proto *tp) +{ + if (chain->p_filter_chain && + *chain_info->pprev == chain->filter_chain) + *chain->p_filter_chain = tp; + RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info)); + rcu_assign_pointer(*chain_info->pprev, tp); +} + +static void tcf_chain_tp_remove(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + struct tcf_proto *tp) +{ + struct tcf_proto *next = rtnl_dereference(chain_info->next); + + if (chain->p_filter_chain && tp == chain->filter_chain) + *chain->p_filter_chain = next; + RCU_INIT_POINTER(*chain_info->pprev, next); +} + +static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + u32 protocol, u32 prio, + bool prio_allocate) +{ + struct tcf_proto **pprev; + struct tcf_proto *tp; + + /* Check the chain for existence of proto-tcf with this priority */ + for (pprev = &chain->filter_chain; + (tp = rtnl_dereference(*pprev)); pprev = &tp->next) { + if (tp->prio >= prio) { + if (tp->prio == prio) { + if (prio_allocate || + (tp->protocol != protocol && protocol)) + return ERR_PTR(-EINVAL); + } else { + tp = NULL; + } + break; + } + } + chain_info->pprev = pprev; + chain_info->next = tp ? tp->next : NULL; + return tp; +} + /* Add/change/delete/get a filter node */ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -281,10 +362,9 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, u32 parent; struct net_device *dev; struct Qdisc *q; - struct tcf_proto __rcu **back; - struct tcf_proto __rcu **chain; + struct tcf_chain_info chain_info; + struct tcf_chain *chain; struct tcf_block *block; - struct tcf_proto *next; struct tcf_proto *tp; const struct Qdisc_class_ops *cops; unsigned long cl; @@ -369,7 +449,7 @@ replay: err = -EINVAL; goto errout; } - chain = block->p_filter_chain; + chain = block->chain; if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); @@ -378,22 +458,11 @@ replay: goto errout; } - /* Check the chain for existence of proto-tcf with this priority */ - for (back = chain; - (tp = rtnl_dereference(*back)) != NULL; - back = &tp->next) { - if (tp->prio >= prio) { - if (tp->prio == prio) { - if (prio_allocate || - (tp->protocol != protocol && protocol)) { - err = -EINVAL; - goto errout; - } - } else { - tp = NULL; - } - break; - } + tp = tcf_chain_tp_find(chain, &chain_info, protocol, + prio, prio_allocate); + if (IS_ERR(tp)) { + err = PTR_ERR(tp); + goto errout; } if (tp == NULL) { @@ -411,7 +480,7 @@ replay: } if (prio_allocate) - prio = tcf_auto_prio(rtnl_dereference(*back)); + prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info)); tp = tcf_proto_create(nla_data(tca[TCA_KIND]), protocol, prio, parent, q, block); @@ -429,8 +498,7 @@ replay: if (fh == 0) { if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) { - next = rtnl_dereference(tp->next); - RCU_INIT_POINTER(*back, next); + tcf_chain_tp_remove(chain, &chain_info, tp); tfilter_notify(net, skb, n, tp, fh, RTM_DELTFILTER, false); tcf_proto_destroy(tp); @@ -459,11 +527,10 @@ replay: err = tp->ops->delete(tp, fh, &last); if (err) goto errout; - next = rtnl_dereference(tp->next); tfilter_notify(net, skb, n, tp, t->tcm_handle, RTM_DELTFILTER, false); if (last) { - RCU_INIT_POINTER(*back, next); + tcf_chain_tp_remove(chain, &chain_info, tp); tcf_proto_destroy(tp); } goto errout; @@ -480,10 +547,8 @@ replay: err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE); if (err == 0) { - if (tp_created) { - RCU_INIT_POINTER(tp->next, rtnl_dereference(*back)); - rcu_assign_pointer(*back, tp); - } + if (tp_created) + tcf_chain_tp_insert(chain, &chain_info, tp); tfilter_notify(net, skb, n, tp, fh, RTM_NEWTFILTER, false); } else { if (tp_created) @@ -584,7 +649,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct Qdisc *q; struct tcf_block *block; - struct tcf_proto *tp, __rcu **chain; + struct tcf_proto *tp; + struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); unsigned long cl = 0; const struct Qdisc_class_ops *cops; @@ -615,11 +681,11 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) block = cops->tcf_block(q, cl); if (!block) goto errout; - chain = block->p_filter_chain; + chain = block->chain; s_t = cb->args[0]; - for (tp = rtnl_dereference(*chain), t = 0; + for (tp = rtnl_dereference(chain->filter_chain), t = 0; tp; tp = rtnl_dereference(tp->next), t++) { if (t < s_t) continue; -- cgit v1.2.3 From 5bc1701881e395cec51811d07ec6961f3d1b2612 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:08:01 +0200 Subject: net: sched: introduce multichain support for filters Instead of having only one filter per block, introduce a list of chains for every block. Create chain 0 by default. UAPI is extended so the user can specify which chain he wants to change. If the new attribute is not specified, chain 0 is used. That allows to maintain backward compatibility. If chain does not exist and user wants to manipulate with it, new chain is created with specified index. Also, when last filter is removed from the chain, the chain is destroyed. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 2 + include/net/sch_generic.h | 9 +++- include/uapi/linux/rtnetlink.h | 1 + net/sched/cls_api.c | 104 ++++++++++++++++++++++++++++++++++------- 4 files changed, 98 insertions(+), 18 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index e56e7157c280..2c213a69c196 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -18,6 +18,8 @@ int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #ifdef CONFIG_NET_CLS +struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index); +void tcf_chain_put(struct tcf_chain *chain); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain); void tcf_block_put(struct tcf_block *block); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 52bceede534b..569b5654c30c 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -236,7 +237,7 @@ struct tcf_proto { struct Qdisc *q; void *data; const struct tcf_proto_ops *ops; - struct tcf_block *block; + struct tcf_chain *chain; struct rcu_head rcu; }; @@ -251,10 +252,14 @@ struct qdisc_skb_cb { struct tcf_chain { struct tcf_proto __rcu *filter_chain; struct tcf_proto __rcu **p_filter_chain; + struct list_head list; + struct tcf_block *block; + u32 index; /* chain index */ + unsigned int refcnt; }; struct tcf_block { - struct tcf_chain *chain; + struct list_head chain_list; }; static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index cce061382e40..6487b21b2c1e 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -549,6 +549,7 @@ enum { TCA_STAB, TCA_PAD, TCA_DUMP_INVISIBLE, + TCA_CHAIN, __TCA_MAX }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 63aa2ea5f00c..adacaf299c4a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -129,7 +129,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, u32 prio, u32 parent, struct Qdisc *q, - struct tcf_block *block) + struct tcf_chain *chain) { struct tcf_proto *tp; int err; @@ -165,7 +165,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, tp->prio = prio; tp->classid = parent; tp->q = q; - tp->block = block; + tp->chain = chain; err = tp->ops->init(tp); if (err) { @@ -186,15 +186,26 @@ static void tcf_proto_destroy(struct tcf_proto *tp) kfree_rcu(tp, rcu); } -static struct tcf_chain *tcf_chain_create(void) +static struct tcf_chain *tcf_chain_create(struct tcf_block *block, + u32 chain_index) { - return kzalloc(sizeof(struct tcf_chain), GFP_KERNEL); + struct tcf_chain *chain; + + chain = kzalloc(sizeof(*chain), GFP_KERNEL); + if (!chain) + return NULL; + list_add_tail(&chain->list, &block->chain_list); + chain->block = block; + chain->index = chain_index; + chain->refcnt = 1; + return chain; } static void tcf_chain_destroy(struct tcf_chain *chain) { struct tcf_proto *tp; + list_del(&chain->list); while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) { RCU_INIT_POINTER(chain->filter_chain, tp->next); tcf_proto_destroy(tp); @@ -202,6 +213,30 @@ static void tcf_chain_destroy(struct tcf_chain *chain) kfree(chain); } +struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index) +{ + struct tcf_chain *chain; + + list_for_each_entry(chain, &block->chain_list, list) { + if (chain->index == chain_index) { + chain->refcnt++; + return chain; + } + } + return tcf_chain_create(block, chain_index); +} +EXPORT_SYMBOL(tcf_chain_get); + +void tcf_chain_put(struct tcf_chain *chain) +{ + /* Destroy unused chain, with exception of chain 0, which is the + * default one and has to be always present. + */ + if (--chain->refcnt == 0 && !chain->filter_chain && chain->index != 0) + tcf_chain_destroy(chain); +} +EXPORT_SYMBOL(tcf_chain_put); + static void tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain, struct tcf_proto __rcu **p_filter_chain) @@ -213,16 +248,19 @@ int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain) { struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL); + struct tcf_chain *chain; int err; if (!block) return -ENOMEM; - block->chain = tcf_chain_create(); - if (!block->chain) { + INIT_LIST_HEAD(&block->chain_list); + /* Create chain 0 by default, it has to be always present. */ + chain = tcf_chain_create(block, 0); + if (!chain) { err = -ENOMEM; goto err_chain_create; } - tcf_chain_filter_chain_ptr_set(block->chain, p_filter_chain); + tcf_chain_filter_chain_ptr_set(chain, p_filter_chain); *p_block = block; return 0; @@ -234,9 +272,13 @@ EXPORT_SYMBOL(tcf_block_get); void tcf_block_put(struct tcf_block *block) { + struct tcf_chain *chain, *tmp; + if (!block) return; - tcf_chain_destroy(block->chain); + + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) + tcf_chain_destroy(chain); kfree(block); } EXPORT_SYMBOL(tcf_block_put); @@ -360,10 +402,11 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, u32 prio; bool prio_allocate; u32 parent; + u32 chain_index; struct net_device *dev; struct Qdisc *q; struct tcf_chain_info chain_info; - struct tcf_chain *chain; + struct tcf_chain *chain = NULL; struct tcf_block *block; struct tcf_proto *tp; const struct Qdisc_class_ops *cops; @@ -449,7 +492,17 @@ replay: err = -EINVAL; goto errout; } - chain = block->chain; + + chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; + if (chain_index > TC_ACT_EXT_VAL_MASK) { + err = -EINVAL; + goto errout; + } + chain = tcf_chain_get(block, chain_index); + if (!chain) { + err = -ENOMEM; + goto errout; + } if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) { tfilter_notify_chain(net, skb, n, chain, RTM_DELTFILTER); @@ -483,7 +536,7 @@ replay: prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info)); tp = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, parent, q, block); + protocol, prio, parent, q, chain); if (IS_ERR(tp)) { err = PTR_ERR(tp); goto errout; @@ -556,6 +609,8 @@ replay: } errout: + if (chain) + tcf_chain_put(chain); if (cl) cops->put(q, cl); if (err == -EAGAIN) @@ -584,6 +639,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol); if (nla_put_string(skb, TCA_KIND, tp->ops->kind)) goto nla_put_failure; + if (nla_put_u32(skb, TCA_CHAIN, tp->chain->index)) + goto nla_put_failure; tcm->tcm_handle = fh; if (RTM_DELTFILTER != event) { tcm->tcm_handle = 0; @@ -640,7 +697,7 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, RTM_NEWTFILTER); } -static void tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, +static bool tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, struct netlink_callback *cb, long index_start, long *p_index) { @@ -667,7 +724,7 @@ static void tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) - break; + return false; cb->args[1] = 1; } @@ -682,14 +739,16 @@ static void tcf_chain_dump(struct tcf_chain *chain, struct sk_buff *skb, tp->ops->walk(tp, &arg.w); cb->args[1] = arg.w.count + 1; if (arg.w.stop) - break; + return false; } + return true; } /* called with RTNL */ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; struct Qdisc *q; struct tcf_block *block; @@ -699,9 +758,15 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) const struct Qdisc_class_ops *cops; long index_start; long index; + int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) return skb->len; + + err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL); + if (err) + return err; + dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return skb->len; @@ -725,11 +790,18 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) block = cops->tcf_block(q, cl); if (!block) goto errout; - chain = block->chain; index_start = cb->args[0]; index = 0; - tcf_chain_dump(chain, skb, cb, index_start, &index); + + list_for_each_entry(chain, &block->chain_list, list) { + if (tca[TCA_CHAIN] && + nla_get_u32(tca[TCA_CHAIN]) != chain->index) + continue; + if (!tcf_chain_dump(chain, skb, cb, index_start, &index)) + break; + } + cb->args[0] = index; errout: -- cgit v1.2.3 From 9fb9f251d229f6cabd9dbe4214eb7f1e6a4e8a9d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:08:02 +0200 Subject: net: sched: push tp down to action init Tp pointer will be needed by the next patch in order to get the chain. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 12 ++++++------ net/sched/act_api.c | 15 ++++++++------- net/sched/cls_api.c | 9 +++++---- 3 files changed, 19 insertions(+), 17 deletions(-) (limited to 'include/net') diff --git a/include/net/act_api.h b/include/net/act_api.h index cfa2ae33da9a..b22c6f3d6710 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -180,12 +180,12 @@ int tcf_unregister_action(struct tc_action_ops *a, int tcf_action_destroy(struct list_head *actions, int bind); int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res); -int tcf_action_init(struct net *net, struct nlattr *nla, - struct nlattr *est, char *n, int ovr, - int bind, struct list_head *); -struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, - struct nlattr *est, char *n, int ovr, - int bind); +int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, + struct nlattr *est, char *name, int ovr, int bind, + struct list_head *actions); +struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, + struct nlattr *nla, struct nlattr *est, + char *name, int ovr, int bind); int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index a90e8f355c00..e389eb45b484 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -570,9 +570,9 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } -struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, - struct nlattr *est, char *name, int ovr, - int bind) +struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, + struct nlattr *nla, struct nlattr *est, + char *name, int ovr, int bind) { struct tc_action *a; struct tc_action_ops *a_o; @@ -680,8 +680,9 @@ static void cleanup_a(struct list_head *actions, int ovr) a->tcfa_refcnt--; } -int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind, struct list_head *actions) +int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, + struct nlattr *est, char *name, int ovr, int bind, + struct list_head *actions) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; @@ -693,7 +694,7 @@ int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est, return err; for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_init_1(net, tb[i], est, name, ovr, bind); + act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; @@ -1020,7 +1021,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, int ret = 0; LIST_HEAD(actions); - ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions); + ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions); if (ret) return ret; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index adacaf299c4a..9e0c4bb82528 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -832,8 +832,9 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct tc_action *act; if (exts->police && tb[exts->police]) { - act = tcf_action_init_1(net, tb[exts->police], rate_tlv, - "police", ovr, TCA_ACT_BIND); + act = tcf_action_init_1(net, tp, tb[exts->police], + rate_tlv, "police", ovr, + TCA_ACT_BIND); if (IS_ERR(act)) return PTR_ERR(act); @@ -844,8 +845,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, LIST_HEAD(actions); int err, i = 0; - err = tcf_action_init(net, tb[exts->action], rate_tlv, - NULL, ovr, TCA_ACT_BIND, + err = tcf_action_init(net, tp, tb[exts->action], + rate_tlv, NULL, ovr, TCA_ACT_BIND, &actions); if (err) return err; -- cgit v1.2.3 From db50514f9a9c7ef1f17e9921b1cc0902746872f3 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 17 May 2017 11:08:03 +0200 Subject: net: sched: add termination action to allow goto chain Introduce new type of termination action called "goto_chain". This allows user to specify a chain to be processed. This action type is then processed as a return value in tcf_classify loop in similar way as "reclassify" is, only it does not reset to the first filter in chain but rather reset to the first filter of the desired chain. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/net/act_api.h | 1 + include/net/sch_generic.h | 9 +++++++-- include/uapi/linux/pkt_cls.h | 1 + net/sched/act_api.c | 40 ++++++++++++++++++++++++++++++++++++++++ net/sched/cls_api.c | 6 +++++- 5 files changed, 54 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/act_api.h b/include/net/act_api.h index b22c6f3d6710..26ffd8333f50 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -42,6 +42,7 @@ struct tc_action { struct gnet_stats_basic_cpu __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; struct tc_cookie *act_cookie; + struct tcf_chain *goto_chain; }; #define tcf_head common.tcfa_head #define tcf_index common.tcfa_index diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 569b5654c30c..368850194c94 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -193,8 +193,13 @@ struct Qdisc_ops { struct tcf_result { - unsigned long class; - u32 classid; + union { + struct { + unsigned long class; + u32 classid; + }; + const struct tcf_proto *goto_tp; + }; }; struct tcf_proto_ops { diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index d613be3b3239..1b9aa9e6b4fd 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -51,6 +51,7 @@ enum { (((combined) & (~TC_ACT_EXT_VAL_MASK)) == opcode) #define TC_ACT_JUMP __TC_ACT_EXT(1) +#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2) /* Action type identifiers*/ enum { diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e389eb45b484..0ecf2a858767 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -28,6 +28,31 @@ #include #include +static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) +{ + u32 chain_index = a->tcfa_action & TC_ACT_EXT_VAL_MASK; + + if (!tp) + return -EINVAL; + a->goto_chain = tcf_chain_get(tp->chain->block, chain_index); + if (!a->goto_chain) + return -ENOMEM; + return 0; +} + +static void tcf_action_goto_chain_fini(struct tc_action *a) +{ + tcf_chain_put(a->goto_chain); +} + +static void tcf_action_goto_chain_exec(const struct tc_action *a, + struct tcf_result *res) +{ + const struct tcf_chain *chain = a->goto_chain; + + res->goto_tp = rcu_dereference_bh(chain->filter_chain); +} + static void free_tcf(struct rcu_head *head) { struct tc_action *p = container_of(head, struct tc_action, tcfa_rcu); @@ -39,6 +64,8 @@ static void free_tcf(struct rcu_head *head) kfree(p->act_cookie->data); kfree(p->act_cookie); } + if (p->goto_chain) + tcf_action_goto_chain_fini(p); kfree(p); } @@ -465,6 +492,8 @@ repeat: else /* faulty graph, stop pipeline */ return TC_ACT_OK; } + } else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) { + tcf_action_goto_chain_exec(a, res); } if (ret != TC_ACT_PIPE) @@ -657,6 +686,17 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (err != ACT_P_CREATED) module_put(a_o->owner); + if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) { + err = tcf_action_goto_chain_init(a, tp); + if (err) { + LIST_HEAD(actions); + + list_add_tail(&a->list, &actions); + tcf_action_destroy(&actions, bind); + return ERR_PTR(err); + } + } + return a; err_mod: diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 9e0c4bb82528..4020b8d932a1 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -307,8 +307,12 @@ reclassify: err = tp->classify(skb, tp, res); #ifdef CONFIG_NET_CLS_ACT - if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) + if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) { goto reset; + } else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) { + old_tp = res->goto_tp; + goto reset; + } #endif if (err >= 0) return err; -- cgit v1.2.3 From ec66eda82d4b0c552bf40005d8f53b63b2b07de4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2017 14:00:01 -0700 Subject: tcp: introduce tcp_jiffies32 We abuse tcp_time_stamp for two different cases : 1) base to generate TCP Timestamp options (RFC 7323) 2) A 32bit version of jiffies since some TCP fields are 32bit wide to save memory. Since we want in the future to have 1ms TCP TS clock, regardless of HZ value, we want to cleanup things. tcp_jiffies32 is the truncated jiffies value, which will be used only in places where we want a 'host' timestamp. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/tcp.h | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index b4dc93dae98c..4b45be570821 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -700,11 +700,14 @@ u32 __tcp_select_window(struct sock *sk); void tcp_send_window_probe(struct sock *sk); -/* TCP timestamps are only 32-bits, this causes a slight - * complication on 64-bit systems since we store a snapshot - * of jiffies in the buffer control blocks below. We decided - * to use only the low 32-bits of jiffies and hide the ugly - * casts with the following macro. +/* TCP uses 32bit jiffies to save some space. + * Note that this is different from tcp_time_stamp, which + * historically has been the same until linux-4.13. + */ +#define tcp_jiffies32 ((u32)jiffies) + +/* Generator for TCP TS option (RFC 7323) + * Currently tied to 'jiffies' but will soon be driven by 1 ms clock. */ #define tcp_time_stamp ((__u32)(jiffies)) -- cgit v1.2.3 From d635fbe27ebee0f4b845abe5e9620c9400785a5c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2017 14:00:03 -0700 Subject: tcp: use tcp_jiffies32 to feed tp->lsndtime Use tcp_jiffies32 instead of tcp_time_stamp to feed tp->lsndtime. tcp_time_stamp will soon be a litle bit more expensive than simply reading 'jiffies'. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/tcp.h | 2 +- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_cubic.c | 2 +- net/ipv4/tcp_input.c | 4 ++-- net/ipv4/tcp_output.c | 4 ++-- net/ipv4/tcp_timer.c | 4 ++-- 6 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 4b45be570821..feba4c0406e5 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1245,7 +1245,7 @@ static inline void tcp_slow_start_after_idle_check(struct sock *sk) if (!sysctl_tcp_slow_start_after_idle || tp->packets_out || ca_ops->cong_control) return; - delta = tcp_time_stamp - tp->lsndtime; + delta = tcp_jiffies32 - tp->lsndtime; if (delta > inet_csk(sk)->icsk_rto) tcp_cwnd_restart(sk, delta); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1e4c76d2b827..d0bb61ee28bb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2841,7 +2841,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_retrans = tp->retrans_out; info->tcpi_fackets = tp->fackets_out; - now = tcp_time_stamp; + now = tcp_jiffies32; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime); info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 0683ba447d77..2052ca740916 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -155,7 +155,7 @@ static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { struct bictcp *ca = inet_csk_ca(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_jiffies32; s32 delta; delta = now - tcp_sk(sk)->lsndtime; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 06e2dbc2b4a2..c0b3f909df39 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5571,7 +5571,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) /* Prevent spurious tcp_cwnd_restart() on first data * packet. */ - tp->lsndtime = tcp_time_stamp; + tp->lsndtime = tcp_jiffies32; tcp_init_buffer_space(sk); @@ -6008,7 +6008,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_update_pacing_rate(sk); /* Prevent spurious tcp_cwnd_restart() on first data packet */ - tp->lsndtime = tcp_time_stamp; + tp->lsndtime = tcp_jiffies32; tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4c8a6eaba6b3..be9f8f483e21 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -160,7 +160,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - const u32 now = tcp_time_stamp; + const u32 now = tcp_jiffies32; if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); @@ -1918,7 +1918,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, /* Avoid bursty behavior by allowing defer * only if the last write was recent. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) > 0) + if ((s32)(tcp_jiffies32 - tp->lsndtime) > 0) goto send_now; in_flight = tcp_packets_in_flight(tp); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index ec7c5473c788..5f6f219a431e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -63,7 +63,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) + if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ @@ -73,7 +73,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN || + if ((s32)(tcp_jiffies32 - tp->lsndtime) <= TCP_TIMEWAIT_LEN || /* 2. Window is closed. */ (!tp->snd_wnd && !tp->packets_out)) do_reset = true; -- cgit v1.2.3 From 70eabf0e1b8fe11519f793416655266605f700b9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2017 14:00:07 -0700 Subject: tcp: use tcp_jiffies32 for rcv_tstamp and lrcvtime Use tcp_jiffies32 instead of tcp_time_stamp, since tcp_time_stamp will soon be only used for TCP TS option. Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/tcp.h | 4 ++-- net/ipv4/tcp_input.c | 6 +++--- net/ipv4/tcp_minisocks.c | 2 +- net/ipv4/tcp_output.c | 2 +- net/ipv4/tcp_timer.c | 2 +- 5 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index feba4c0406e5..5b2932b8363f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1307,8 +1307,8 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) { const struct inet_connection_sock *icsk = &tp->inet_conn; - return min_t(u32, tcp_time_stamp - icsk->icsk_ack.lrcvtime, - tcp_time_stamp - tp->rcv_tstamp); + return min_t(u32, tcp_jiffies32 - icsk->icsk_ack.lrcvtime, + tcp_jiffies32 - tp->rcv_tstamp); } static inline int tcp_fin_time(const struct sock *sk) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6a15c9b80b09..eeb4967df25a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -672,7 +672,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) tcp_rcv_rtt_measure(tp); - now = tcp_time_stamp; + now = tcp_jiffies32; if (!icsk->icsk_ack.ato) { /* The _first_ data packet received, initialize @@ -3636,7 +3636,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) */ sk->sk_err_soft = 0; icsk->icsk_probes_out = 0; - tp->rcv_tstamp = tcp_time_stamp; + tp->rcv_tstamp = tcp_jiffies32; if (!prior_packets) goto no_queue; @@ -5554,7 +5554,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) struct inet_connection_sock *icsk = inet_csk(sk); tcp_set_state(sk, TCP_ESTABLISHED); - icsk->icsk_ack.lrcvtime = tcp_time_stamp; + icsk->icsk_ack.lrcvtime = tcp_jiffies32; if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 717be4de5324..59c32e0086c0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -447,7 +447,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&newtp->rtt_min, tcp_time_stamp, ~0U); newicsk->icsk_rto = TCP_TIMEOUT_INIT; - newicsk->icsk_ack.lrcvtime = tcp_time_stamp; + newicsk->icsk_ack.lrcvtime = tcp_jiffies32; newtp->packets_out = 0; newtp->retrans_out = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4bd50f0b236b..cbda5de16449 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3324,7 +3324,7 @@ static void tcp_connect_init(struct sock *sk) if (likely(!tp->repair)) tp->rcv_nxt = 0; else - tp->rcv_tstamp = tcp_time_stamp; + tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; tp->copied_seq = tp->rcv_nxt; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 5f6f219a431e..9e0616cb8c17 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -451,7 +451,7 @@ void tcp_retransmit_timer(struct sock *sk) tp->snd_una, tp->snd_nxt); } #endif - if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) { + if (tcp_jiffies32 - tp->rcv_tstamp > TCP_RTO_MAX) { tcp_write_err(sk); goto out; } -- cgit v1.2.3 From 9a568de4818dea9a05af141046bd3e589245ab83 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 May 2017 14:00:14 -0700 Subject: tcp: switch TCP TS option (RFC 7323) to 1ms clock TCP Timestamps option is defined in RFC 7323 Traditionally on linux, it has been tied to the internal 'jiffies' variable, because it had been a cheap and good enough generator. For TCP flows on the Internet, 1 ms resolution would be much better than 4ms or 10ms (HZ=250 or HZ=100 respectively) For TCP flows in the DC, Google has used usec resolution for more than two years with great success [1] Receive size autotuning (DRS) is indeed more precise and converges faster to optimal window size. This patch converts tp->tcp_mstamp to a plain u64 value storing a 1 usec TCP clock. This choice will allow us to upstream the 1 usec TS option as discussed in IETF 97. [1] https://www.ietf.org/proceedings/97/slides/slides-97-tcpm-tcp-options-for-low-latency-00.pdf Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/linux/skbuff.h | 62 +------------------------- include/linux/tcp.h | 22 ++++----- include/net/tcp.h | 59 ++++++++++++++++++++---- net/ipv4/syncookies.c | 8 ++-- net/ipv4/tcp.c | 4 +- net/ipv4/tcp_bbr.c | 22 ++++----- net/ipv4/tcp_input.c | 96 ++++++++++++++++++++-------------------- net/ipv4/tcp_ipv4.c | 17 +++---- net/ipv4/tcp_lp.c | 12 ++--- net/ipv4/tcp_minisocks.c | 4 +- net/ipv4/tcp_output.c | 16 +++---- net/ipv4/tcp_rate.c | 16 +++---- net/ipv4/tcp_recovery.c | 23 +++++----- net/ipv4/tcp_timer.c | 8 ++-- net/ipv6/syncookies.c | 2 +- net/ipv6/tcp_ipv6.c | 4 +- net/netfilter/nf_synproxy_core.c | 2 +- 17 files changed, 178 insertions(+), 199 deletions(-) (limited to 'include/net') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bfc7892f6c33..7c0cb2ce8b01 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -506,66 +506,6 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif -/** - * struct skb_mstamp - multi resolution time stamps - * @stamp_us: timestamp in us resolution - * @stamp_jiffies: timestamp in jiffies - */ -struct skb_mstamp { - union { - u64 v64; - struct { - u32 stamp_us; - u32 stamp_jiffies; - }; - }; -}; - -/** - * skb_mstamp_get - get current timestamp - * @cl: place to store timestamps - */ -static inline void skb_mstamp_get(struct skb_mstamp *cl) -{ - u64 val = local_clock(); - - do_div(val, NSEC_PER_USEC); - cl->stamp_us = (u32)val; - cl->stamp_jiffies = (u32)jiffies; -} - -/** - * skb_mstamp_delta - compute the difference in usec between two skb_mstamp - * @t1: pointer to newest sample - * @t0: pointer to oldest sample - */ -static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, - const struct skb_mstamp *t0) -{ - s32 delta_us = t1->stamp_us - t0->stamp_us; - u32 delta_jiffies = t1->stamp_jiffies - t0->stamp_jiffies; - - /* If delta_us is negative, this might be because interval is too big, - * or local_clock() drift is too big : fallback using jiffies. - */ - if (delta_us <= 0 || - delta_jiffies >= (INT_MAX / (USEC_PER_SEC / HZ))) - - delta_us = jiffies_to_usecs(delta_jiffies); - - return delta_us; -} - -static inline bool skb_mstamp_after(const struct skb_mstamp *t1, - const struct skb_mstamp *t0) -{ - s32 diff = t1->stamp_jiffies - t0->stamp_jiffies; - - if (!diff) - diff = t1->stamp_us - t0->stamp_us; - return diff > 0; -} - /** * struct sk_buff - socket buffer * @next: Next buffer in list @@ -646,7 +586,7 @@ struct sk_buff { union { ktime_t tstamp; - struct skb_mstamp skb_mstamp; + u64 skb_mstamp; }; }; struct rb_node rbnode; /* used in netem & tcp stack */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 22854f028434..542ca1ae02c4 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -123,7 +123,7 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; - struct skb_mstamp snt_synack; /* first SYNACK sent time */ + u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; u32 txhash; u32 rcv_isn; @@ -211,7 +211,7 @@ struct tcp_sock { /* Information of the most recently (s)acked skb */ struct tcp_rack { - struct skb_mstamp mstamp; /* (Re)sent time of the skb */ + u64 mstamp; /* (Re)sent time of the skb */ u32 rtt_us; /* Associated RTT */ u32 end_seq; /* Ending TCP sequence of the skb */ u8 advanced; /* mstamp advanced since last lost marking */ @@ -240,7 +240,7 @@ struct tcp_sock { u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ /* RTT measurement */ - struct skb_mstamp tcp_mstamp; /* most recent packet received/sent */ + u64 tcp_mstamp; /* most recent packet received/sent */ u32 srtt_us; /* smoothed round trip time << 3 in usecs */ u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ @@ -280,8 +280,8 @@ struct tcp_sock { u32 delivered; /* Total data packets delivered incl. rexmits */ u32 lost; /* Total data packets lost incl. rexmits */ u32 app_limited; /* limited until "delivered" reaches this val */ - struct skb_mstamp first_tx_mstamp; /* start of window send phase */ - struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */ + u64 first_tx_mstamp; /* start of window send phase */ + u64 delivered_mstamp; /* time we reached "delivered" */ u32 rate_delivered; /* saved rate sample: packets delivered */ u32 rate_interval_us; /* saved rate sample: time elapsed */ @@ -335,16 +335,16 @@ struct tcp_sock { /* Receiver side RTT estimation */ struct { - u32 rtt_us; - u32 seq; - struct skb_mstamp time; + u32 rtt_us; + u32 seq; + u64 time; } rcv_rtt_est; /* Receiver queue space */ struct { - int space; - u32 seq; - struct skb_mstamp time; + int space; + u32 seq; + u64 time; } rcvq_space; /* TCP-specific MTU probe information. */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 5b2932b8363f..82462db97183 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -519,7 +519,7 @@ static inline u32 tcp_cookie_time(void) u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); -__u32 cookie_init_timestamp(struct request_sock *req); +u64 cookie_init_timestamp(struct request_sock *req); bool cookie_timestamp_decode(struct tcp_options_received *opt); bool cookie_ecn_ok(const struct tcp_options_received *opt, const struct net *net, const struct dst_entry *dst); @@ -706,14 +706,55 @@ void tcp_send_window_probe(struct sock *sk); */ #define tcp_jiffies32 ((u32)jiffies) -/* Generator for TCP TS option (RFC 7323) - * Currently tied to 'jiffies' but will soon be driven by 1 ms clock. +/* + * Deliver a 32bit value for TCP timestamp option (RFC 7323) + * It is no longer tied to jiffies, but to 1 ms clock. + * Note: double check if you want to use tcp_jiffies32 instead of this. + */ +#define TCP_TS_HZ 1000 + +static inline u64 tcp_clock_ns(void) +{ + return local_clock(); +} + +static inline u64 tcp_clock_us(void) +{ + return div_u64(tcp_clock_ns(), NSEC_PER_USEC); +} + +/* This should only be used in contexts where tp->tcp_mstamp is up to date */ +static inline u32 tcp_time_stamp(const struct tcp_sock *tp) +{ + return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ); +} + +/* Could use tcp_clock_us() / 1000, but this version uses a single divide */ +static inline u32 tcp_time_stamp_raw(void) +{ + return div_u64(tcp_clock_ns(), NSEC_PER_SEC / TCP_TS_HZ); +} + + +/* Refresh 1us clock of a TCP socket, + * ensuring monotically increasing values. */ -#define tcp_time_stamp ((__u32)(jiffies)) +static inline void tcp_mstamp_refresh(struct tcp_sock *tp) +{ + u64 val = tcp_clock_us(); + + if (val > tp->tcp_mstamp) + tp->tcp_mstamp = val; +} + +static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) +{ + return max_t(s64, t1 - t0, 0); +} static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) { - return skb->skb_mstamp.stamp_jiffies; + return div_u64(skb->skb_mstamp, USEC_PER_SEC / TCP_TS_HZ); } @@ -778,9 +819,9 @@ struct tcp_skb_cb { /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ - struct skb_mstamp first_tx_mstamp; + u64 first_tx_mstamp; /* when we reached the "delivered" count */ - struct skb_mstamp delivered_mstamp; + u64 delivered_mstamp; } tx; /* only used for outgoing skbs */ union { struct inet_skb_parm h4; @@ -896,7 +937,7 @@ struct ack_sample { * A sample is invalid if "delivered" or "interval_us" is negative. */ struct rate_sample { - struct skb_mstamp prior_mstamp; /* starting timestamp for interval */ + u64 prior_mstamp; /* starting timestamp for interval */ u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ long interval_us; /* time for tp->delivered to incr "delivered" */ @@ -1862,7 +1903,7 @@ void tcp_init(void); /* tcp_recovery.c */ extern void tcp_rack_mark_lost(struct sock *sk); extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, - const struct skb_mstamp *xmit_time); + u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); /* diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 0257d965f111..6426250a58ea 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -66,10 +66,10 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, * Since subsequent timestamps use the normal tcp_time_stamp value, we * must make sure that the resulting initial timestamp is <= tcp_time_stamp. */ -__u32 cookie_init_timestamp(struct request_sock *req) +u64 cookie_init_timestamp(struct request_sock *req) { struct inet_request_sock *ireq; - u32 ts, ts_now = tcp_time_stamp; + u32 ts, ts_now = tcp_time_stamp_raw(); u32 options = 0; ireq = inet_rsk(req); @@ -88,7 +88,7 @@ __u32 cookie_init_timestamp(struct request_sock *req) ts <<= TSBITS; ts |= options; } - return ts; + return (u64)ts * (USEC_PER_SEC / TCP_TS_HZ); } @@ -343,7 +343,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack.v64 = 0; + treq->snt_synack = 0; treq->tfo_listener = false; ireq->ir_iif = inet_request_bound_dev_if(sk, skb); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 850054800526..b5d18484746d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2706,7 +2706,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (!tp->repair) err = -EPERM; else - tp->tsoffset = val - tcp_time_stamp; + tp->tsoffset = val - tcp_time_stamp_raw(); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); @@ -3072,7 +3072,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TIMESTAMP: - val = tcp_time_stamp + tp->tsoffset; + val = tcp_time_stamp_raw() + tp->tsoffset; break; case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 40dc4fc5f6ac..dbcc9352a48f 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -91,7 +91,7 @@ struct bbr { struct minmax bw; /* Max recent delivery rate in pkts/uS << 24 */ u32 rtt_cnt; /* count of packet-timed rounds elapsed */ u32 next_rtt_delivered; /* scb->tx.delivered at end of round */ - struct skb_mstamp cycle_mstamp; /* time of this cycle phase start */ + u64 cycle_mstamp; /* time of this cycle phase start */ u32 mode:3, /* current bbr_mode in state machine */ prev_ca_state:3, /* CA state on previous ACK */ packet_conservation:1, /* use packet conservation? */ @@ -411,7 +411,7 @@ static bool bbr_is_next_cycle_phase(struct sock *sk, struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); bool is_full_length = - skb_mstamp_us_delta(&tp->delivered_mstamp, &bbr->cycle_mstamp) > + tcp_stamp_us_delta(tp->delivered_mstamp, bbr->cycle_mstamp) > bbr->min_rtt_us; u32 inflight, bw; @@ -497,7 +497,7 @@ static void bbr_reset_lt_bw_sampling_interval(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - bbr->lt_last_stamp = tp->delivered_mstamp.stamp_jiffies; + bbr->lt_last_stamp = div_u64(tp->delivered_mstamp, USEC_PER_MSEC); bbr->lt_last_delivered = tp->delivered; bbr->lt_last_lost = tp->lost; bbr->lt_rtt_cnt = 0; @@ -551,7 +551,7 @@ static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) struct bbr *bbr = inet_csk_ca(sk); u32 lost, delivered; u64 bw; - s32 t; + u32 t; if (bbr->lt_use_bw) { /* already using long-term rate, lt_bw? */ if (bbr->mode == BBR_PROBE_BW && bbr->round_start && @@ -603,15 +603,15 @@ static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs) return; /* Find average delivery rate in this sampling interval. */ - t = (s32)(tp->delivered_mstamp.stamp_jiffies - bbr->lt_last_stamp); - if (t < 1) - return; /* interval is less than one jiffy, so wait */ - t = jiffies_to_usecs(t); - /* Interval long enough for jiffies_to_usecs() to return a bogus 0? */ - if (t < 1) { + t = div_u64(tp->delivered_mstamp, USEC_PER_MSEC) - bbr->lt_last_stamp; + if ((s32)t < 1) + return; /* interval is less than one ms, so wait */ + /* Check if can multiply without overflow */ + if (t >= ~0U / USEC_PER_MSEC) { bbr_reset_lt_bw_sampling(sk); /* interval too long; reset */ return; } + t *= USEC_PER_MSEC; bw = (u64)delivered * BW_UNIT; do_div(bw, t); bbr_lt_bw_interval_done(sk, bw); @@ -825,7 +825,7 @@ static void bbr_init(struct sock *sk) bbr->idle_restart = 0; bbr->full_bw = 0; bbr->full_bw_cnt = 0; - bbr->cycle_mstamp.v64 = 0; + bbr->cycle_mstamp = 0; bbr->cycle_idx = 0; bbr_reset_lt_bw_sampling(sk); bbr_reset_startup_mode(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 10e6775464f6..9a5a9e8eda89 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -441,7 +441,7 @@ void tcp_init_buffer_space(struct sock *sk) tcp_sndbuf_expand(sk); tp->rcvq_space.space = tp->rcv_wnd; - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); tp->rcvq_space.time = tp->tcp_mstamp; tp->rcvq_space.seq = tp->copied_seq; @@ -555,11 +555,11 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp) { u32 delta_us; - if (tp->rcv_rtt_est.time.v64 == 0) + if (tp->rcv_rtt_est.time == 0) goto new_measure; if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq)) return; - delta_us = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcv_rtt_est.time); + delta_us = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcv_rtt_est.time); tcp_rcv_rtt_update(tp, delta_us, 1); new_measure: @@ -571,13 +571,15 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + if (tp->rx_opt.rcv_tsecr && (TCP_SKB_CB(skb)->end_seq - - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) - tcp_rcv_rtt_update(tp, - jiffies_to_usecs(tcp_time_stamp - - tp->rx_opt.rcv_tsecr), - 0); + TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) { + u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; + u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + + tcp_rcv_rtt_update(tp, delta_us, 0); + } } /* @@ -590,7 +592,7 @@ void tcp_rcv_space_adjust(struct sock *sk) int time; int copied; - time = skb_mstamp_us_delta(&tp->tcp_mstamp, &tp->rcvq_space.time); + time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0) return; @@ -1134,8 +1136,8 @@ struct tcp_sacktag_state { * that was SACKed. RTO needs the earliest RTT to stay conservative, * but congestion control should still get an accurate delay signal. */ - struct skb_mstamp first_sackt; - struct skb_mstamp last_sackt; + u64 first_sackt; + u64 last_sackt; struct rate_sample *rate; int flag; }; @@ -1200,7 +1202,7 @@ static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, int dup_sack, int pcount, - const struct skb_mstamp *xmit_time) + u64 xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1242,9 +1244,9 @@ static u8 tcp_sacktag_one(struct sock *sk, state->reord); if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; - if (state->first_sackt.v64 == 0) - state->first_sackt = *xmit_time; - state->last_sackt = *xmit_time; + if (state->first_sackt == 0) + state->first_sackt = xmit_time; + state->last_sackt = xmit_time; } if (sacked & TCPCB_LOST) { @@ -1304,7 +1306,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, - &skb->skb_mstamp); + skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); if (skb == tp->lost_skb_hint) @@ -1356,8 +1358,8 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, tcp_advance_highest_sack(sk, skb); tcp_skb_collapse_tstamp(prev, skb); - if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp.v64)) - TCP_SKB_CB(prev)->tx.delivered_mstamp.v64 = 0; + if (unlikely(TCP_SKB_CB(prev)->tx.delivered_mstamp)) + TCP_SKB_CB(prev)->tx.delivered_mstamp = 0; tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); @@ -1587,7 +1589,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), - &skb->skb_mstamp); + skb->skb_mstamp); tcp_rate_skb_delivered(sk, skb, state->rate); if (!before(TCP_SKB_CB(skb)->seq, @@ -2936,9 +2938,12 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * See draft-ietf-tcplw-high-performance-00, section 3.3. */ if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && - flag & FLAG_ACKED) - seq_rtt_us = ca_rtt_us = jiffies_to_usecs(tcp_time_stamp - - tp->rx_opt.rcv_tsecr); + flag & FLAG_ACKED) { + u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; + u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + + seq_rtt_us = ca_rtt_us = delta_us; + } if (seq_rtt_us < 0) return false; @@ -2960,12 +2965,8 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) { long rtt_us = -1L; - if (req && !req->num_retrans && tcp_rsk(req)->snt_synack.v64) { - struct skb_mstamp now; - - skb_mstamp_get(&now); - rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack); - } + if (req && !req->num_retrans && tcp_rsk(req)->snt_synack) + rtt_us = tcp_stamp_us_delta(tcp_clock_us(), tcp_rsk(req)->snt_synack); tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us); } @@ -3003,7 +3004,7 @@ void tcp_rearm_rto(struct sock *sk) struct sk_buff *skb = tcp_write_queue_head(sk); const u32 rto_time_stamp = tcp_skb_timestamp(skb) + rto; - s32 delta = (s32)(rto_time_stamp - tcp_time_stamp); + s32 delta = (s32)(rto_time_stamp - tcp_jiffies32); /* delta may not be positive if the socket is locked * when the retrans timer fires and is rescheduled. */ @@ -3060,9 +3061,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, struct tcp_sacktag_state *sack) { const struct inet_connection_sock *icsk = inet_csk(sk); - struct skb_mstamp first_ackt, last_ackt; + u64 first_ackt, last_ackt; struct tcp_sock *tp = tcp_sk(sk); - struct skb_mstamp *now = &tp->tcp_mstamp; u32 prior_sacked = tp->sacked_out; u32 reord = tp->packets_out; bool fully_acked = true; @@ -3075,7 +3075,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, bool rtt_update; int flag = 0; - first_ackt.v64 = 0; + first_ackt = 0; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); @@ -3106,8 +3106,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, flag |= FLAG_RETRANS_DATA_ACKED; } else if (!(sacked & TCPCB_SACKED_ACKED)) { last_ackt = skb->skb_mstamp; - WARN_ON_ONCE(last_ackt.v64 == 0); - if (!first_ackt.v64) + WARN_ON_ONCE(last_ackt == 0); + if (!first_ackt) first_ackt = last_ackt; last_in_flight = TCP_SKB_CB(skb)->tx.in_flight; @@ -3122,7 +3122,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->delivered += acked_pcount; if (!tcp_skb_spurious_retrans(tp, skb)) tcp_rack_advance(tp, sacked, scb->end_seq, - &skb->skb_mstamp); + skb->skb_mstamp); } if (sacked & TCPCB_LOST) tp->lost_out -= acked_pcount; @@ -3165,13 +3165,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - if (likely(first_ackt.v64) && !(flag & FLAG_RETRANS_DATA_ACKED)) { - seq_rtt_us = skb_mstamp_us_delta(now, &first_ackt); - ca_rtt_us = skb_mstamp_us_delta(now, &last_ackt); + if (likely(first_ackt) && !(flag & FLAG_RETRANS_DATA_ACKED)) { + seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt); + ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, last_ackt); } - if (sack->first_sackt.v64) { - sack_rtt_us = skb_mstamp_us_delta(now, &sack->first_sackt); - ca_rtt_us = skb_mstamp_us_delta(now, &sack->last_sackt); + if (sack->first_sackt) { + sack_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->first_sackt); + ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, sack->last_sackt); } sack->rate->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet, or -1 */ rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us, @@ -3201,7 +3201,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); } else if (skb && rtt_update && sack_rtt_us >= 0 && - sack_rtt_us > skb_mstamp_us_delta(now, &skb->skb_mstamp)) { + sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp, skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3553,7 +3553,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int acked = 0; /* Number of packets newly acked */ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */ - sack_state.first_sackt.v64 = 0; + sack_state.first_sackt = 0; sack_state.rate = &rs; /* We very likely will need to access write queue head. */ @@ -5356,7 +5356,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); if (unlikely(!sk->sk_rx_dst)) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* @@ -5672,7 +5672,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp, - tcp_time_stamp)) { + tcp_time_stamp(tp))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); goto reset_and_undo; @@ -5917,7 +5917,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_SYN_SENT: tp->rx_opt.saw_tstamp = 0; - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); queued = tcp_rcv_synsent_state_process(sk, skb, th); if (queued >= 0) return queued; @@ -5929,7 +5929,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) return 0; } - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); tp->rx_opt.saw_tstamp = 0; req = tp->fastopen_rsk; if (req) { @@ -6202,7 +6202,7 @@ static void tcp_openreq_init(struct request_sock *req, req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - skb_mstamp_get(&tcp_rsk(req)->snt_synack); + tcp_rsk(req)->snt_synack = tcp_clock_us(); tcp_rsk(req)->last_oow_ack_time = 0; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d8fe25db79f2..191b2f78b19d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -376,8 +376,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) struct sock *sk; struct sk_buff *skb; struct request_sock *fastopen; - __u32 seq, snd_una; - __u32 remaining; + u32 seq, snd_una; + s32 remaining; + u32 delta_us; int err; struct net *net = dev_net(icmp_skb->dev); @@ -483,12 +484,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) skb = tcp_write_queue_head(sk); BUG_ON(!skb); - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); + delta_us = (u32)(tp->tcp_mstamp - skb->skb_mstamp); remaining = icsk->icsk_rto - - min(icsk->icsk_rto, - tcp_time_stamp - tcp_skb_timestamp(skb)); + usecs_to_jiffies(delta_us); - if (remaining) { + if (remaining > 0) { inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, TCP_RTO_MAX); } else { @@ -812,7 +813,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp + tcptw->tw_ts_offset, + tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), @@ -840,7 +841,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp + tcp_rsk(req)->ts_off, + tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, 0, tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index ef3122abb373..ae10ed64fe13 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -37,7 +37,7 @@ #include /* resolution of owd */ -#define LP_RESOL 1000 +#define LP_RESOL TCP_TS_HZ /** * enum tcp_lp_state @@ -147,9 +147,9 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk) tp->rx_opt.rcv_tsecr == lp->local_ref_time) goto out; - m = HZ * (tp->rx_opt.rcv_tsval - - lp->remote_ref_time) / (tp->rx_opt.rcv_tsecr - - lp->local_ref_time); + m = TCP_TS_HZ * + (tp->rx_opt.rcv_tsval - lp->remote_ref_time) / + (tp->rx_opt.rcv_tsecr - lp->local_ref_time); if (m < 0) m = -m; @@ -194,7 +194,7 @@ static u32 tcp_lp_owd_calculator(struct sock *sk) if (lp->flag & LP_VALID_RHZ) { owd = tp->rx_opt.rcv_tsval * (LP_RESOL / lp->remote_hz) - - tp->rx_opt.rcv_tsecr * (LP_RESOL / HZ); + tp->rx_opt.rcv_tsecr * (LP_RESOL / TCP_TS_HZ); if (owd < 0) owd = -owd; } @@ -264,7 +264,7 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample) { struct tcp_sock *tp = tcp_sk(sk); struct lp *lp = inet_csk_ca(sk); - u32 now = tcp_time_stamp; + u32 now = tcp_time_stamp(tp); u32 delta; if (sample->rtt_us > 0) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6504f1082bdf..d0642df73044 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -455,7 +455,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fackets_out = 0; newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; newtp->tlp_high_seq = 0; - newtp->lsndtime = treq->snt_synack.stamp_jiffies; + newtp->lsndtime = tcp_jiffies32; newsk->sk_txhash = treq->txhash; newtp->last_oow_ack_time = 0; newtp->total_retrans = req->num_retrans; @@ -526,7 +526,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fastopen_req = NULL; newtp->fastopen_rsk = NULL; newtp->syn_data_acked = 0; - newtp->rack.mstamp.v64 = 0; + newtp->rack.mstamp = 0; newtp->rack.advanced = 0; __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 65472e931a0b..478f75baee31 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1962,7 +1962,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, head = tcp_write_queue_head(sk); - age = skb_mstamp_us_delta(&tp->tcp_mstamp, &head->skb_mstamp); + age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp); /* If next ACK is likely to come too late (half srtt), do not defer */ if (age < (tp->srtt_us >> 4)) goto send_now; @@ -2279,7 +2279,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, } max_segs = tcp_tso_segs(sk, mss_now); - skb_mstamp_get(&tp->tcp_mstamp); + tcp_mstamp_refresh(tp); while ((skb = tcp_send_head(sk))) { unsigned int limit; @@ -3095,7 +3095,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); - skb_mstamp_get(&tcp_sk(sk)->tcp_mstamp); + tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); @@ -3191,10 +3191,10 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, memset(&opts, 0, sizeof(opts)); #ifdef CONFIG_SYN_COOKIES if (unlikely(req->cookie_ts)) - skb->skb_mstamp.stamp_jiffies = cookie_init_timestamp(req); + skb->skb_mstamp = cookie_init_timestamp(req); else #endif - skb_mstamp_get(&skb->skb_mstamp); + skb->skb_mstamp = tcp_clock_us(); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); @@ -3453,8 +3453,8 @@ int tcp_connect(struct sock *sk) return -ENOBUFS; tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); - skb_mstamp_get(&tp->tcp_mstamp); - tp->retrans_stamp = tp->tcp_mstamp.stamp_jiffies; + tcp_mstamp_refresh(tp); + tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); @@ -3615,7 +3615,7 @@ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; - skb_mstamp_get(&tcp_sk(sk)->tcp_mstamp); + tcp_mstamp_refresh(tcp_sk(sk)); tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE); } } diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index c6a9fa894646..ad99569d4c1e 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -78,7 +78,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); - if (!scb->tx.delivered_mstamp.v64) + if (!scb->tx.delivered_mstamp) return; if (!rs->prior_delivered || @@ -89,9 +89,9 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, rs->is_retrans = scb->sacked & TCPCB_RETRANS; /* Find the duration of the "send phase" of this window: */ - rs->interval_us = skb_mstamp_us_delta( - &skb->skb_mstamp, - &scb->tx.first_tx_mstamp); + rs->interval_us = tcp_stamp_us_delta( + skb->skb_mstamp, + scb->tx.first_tx_mstamp); /* Record send time of most recently ACKed packet: */ tp->first_tx_mstamp = skb->skb_mstamp; @@ -101,7 +101,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, * we don't need to reset since it'll be freed soon. */ if (scb->sacked & TCPCB_SACKED_ACKED) - scb->tx.delivered_mstamp.v64 = 0; + scb->tx.delivered_mstamp = 0; } /* Update the connection delivery information and generate a rate sample. */ @@ -125,7 +125,7 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, rs->acked_sacked = delivered; /* freshly ACKed or SACKed */ rs->losses = lost; /* freshly marked lost */ /* Return an invalid sample if no timing information is available. */ - if (!rs->prior_mstamp.v64) { + if (!rs->prior_mstamp) { rs->delivered = -1; rs->interval_us = -1; return; @@ -138,8 +138,8 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, * longer phase. */ snd_us = rs->interval_us; /* send phase */ - ack_us = skb_mstamp_us_delta(&tp->tcp_mstamp, - &rs->prior_mstamp); /* ack phase */ + ack_us = tcp_stamp_us_delta(tp->tcp_mstamp, + rs->prior_mstamp); /* ack phase */ rs->interval_us = max(snd_us, ack_us); /* Normally we expect interval_us >= min-rtt. diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index cd72b3d3879e..fe9a493d0208 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -17,12 +17,9 @@ static void tcp_rack_mark_skb_lost(struct sock *sk, struct sk_buff *skb) } } -static bool tcp_rack_sent_after(const struct skb_mstamp *t1, - const struct skb_mstamp *t2, - u32 seq1, u32 seq2) +static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { - return skb_mstamp_after(t1, t2) || - (t1->v64 == t2->v64 && after(seq1, seq2)); + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); } /* RACK loss detection (IETF draft draft-ietf-tcpm-rack-01): @@ -72,14 +69,14 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) scb->sacked & TCPCB_SACKED_ACKED) continue; - if (tcp_rack_sent_after(&tp->rack.mstamp, &skb->skb_mstamp, + if (tcp_rack_sent_after(tp->rack.mstamp, skb->skb_mstamp, tp->rack.end_seq, scb->end_seq)) { /* Step 3 in draft-cheng-tcpm-rack-00.txt: * A packet is lost if its elapsed time is beyond * the recent RTT plus the reordering window. */ - u32 elapsed = skb_mstamp_us_delta(&tp->tcp_mstamp, - &skb->skb_mstamp); + u32 elapsed = tcp_stamp_us_delta(tp->tcp_mstamp, + skb->skb_mstamp); s32 remaining = tp->rack.rtt_us + reo_wnd - elapsed; if (remaining < 0) { @@ -127,16 +124,16 @@ void tcp_rack_mark_lost(struct sock *sk) * draft-cheng-tcpm-rack-00.txt */ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, - const struct skb_mstamp *xmit_time) + u64 xmit_time) { u32 rtt_us; - if (tp->rack.mstamp.v64 && - !tcp_rack_sent_after(xmit_time, &tp->rack.mstamp, + if (tp->rack.mstamp && + !tcp_rack_sent_after(xmit_time, tp->rack.mstamp, end_seq, tp->rack.end_seq)) return; - rtt_us = skb_mstamp_us_delta(&tp->tcp_mstamp, xmit_time); + rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, xmit_time); if (sacked & TCPCB_RETRANS) { /* If the sacked packet was retransmitted, it's ambiguous * whether the retransmission or the original (or the prior @@ -152,7 +149,7 @@ void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, return; } tp->rack.rtt_us = rtt_us; - tp->rack.mstamp = *xmit_time; + tp->rack.mstamp = xmit_time; tp->rack.end_seq = end_seq; tp->rack.advanced = 1; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 6629f47aa7f0..27a667bce806 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -153,8 +153,8 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int timeout, bool syn_set) { - unsigned int linear_backoff_thresh, start_ts; unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN; + unsigned int linear_backoff_thresh, start_ts; if (!inet_csk(sk)->icsk_retransmits) return false; @@ -172,7 +172,7 @@ static bool retransmits_timed_out(struct sock *sk, timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; } - return (tcp_time_stamp - start_ts) >= timeout; + return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= jiffies_to_msecs(timeout); } /* A write timeout has occurred. Process the after effects. */ @@ -341,7 +341,7 @@ static void tcp_probe_timer(struct sock *sk) if (!start_ts) tcp_send_head(sk)->skb_mstamp = tp->tcp_mstamp; else if (icsk->icsk_user_timeout && - (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout) + (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout) goto abort; max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; @@ -561,7 +561,7 @@ void tcp_write_timer_handler(struct sock *sk) goto out; } - skb_mstamp_get(&tcp_sk(sk)->tcp_mstamp); + tcp_mstamp_refresh(tcp_sk(sk)); event = icsk->icsk_pending; switch (event) { diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 5abc3692b901..971823359f5b 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -211,7 +211,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack.v64 = 0; + treq->snt_synack = 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; treq->ts_off = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4f4310a36a04..233edfabe1db 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -949,7 +949,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp + tcptw->tw_ts_offset, + tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); @@ -971,7 +971,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp + tcp_rsk(req)->ts_off, + tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0, 0); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index a504e87c6ddf..49bd8bb16b18 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -152,7 +152,7 @@ void synproxy_init_timestamp_cookie(const struct xt_synproxy_info *info, struct synproxy_options *opts) { opts->tsecr = opts->tsval; - opts->tsval = tcp_time_stamp & ~0x3f; + opts->tsval = tcp_time_stamp_raw() & ~0x3f; if (opts->options & XT_SYNPROXY_OPT_WSCALE) { opts->tsval |= opts->wscale; -- cgit v1.2.3 From 9756d33b852a17ee67539545c2acf8dc3bda4574 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 1 May 2017 23:54:17 -0700 Subject: Bluetooth: Enable LE Channel Selection Algorithm event If the Channel Selection Algorithm #2 feature is supported, then enable the new LE Channel Selection Algorithm event. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 1 + net/bluetooth/hci_core.c | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'include/net') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 99aa5e5e3100..dd43cfdd443a 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -399,6 +399,7 @@ enum { #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 #define HCI_LE_EXT_SCAN_POLICY 0x80 +#define HCI_LE_CHAN_SEL_ALG2 0x40 /* Connection modes */ #define HCI_CM_ACTIVE 0x0000 diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 4a0cac774107..e58b9034afff 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -635,6 +635,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) * Report */ + /* If the controller supports Channel Selection Algorithm #2 + * feature, enable the corresponding event. + */ + if (hdev->le_features[1] & HCI_LE_CHAN_SEL_ALG2) + events[2] |= 0x08; /* LE Channel Selection + * Algorithm + */ + /* If the controller supports the LE Set Scan Enable command, * enable the corresponding advertising report event. */ -- cgit v1.2.3 From de2ba3039cfb61334b2523677cc032422873ff93 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Mon, 1 May 2017 23:54:19 -0700 Subject: Bluetooth: Set LE Default PHY preferences If the LE Set Default PHY command is supported, the indicate to the controller that the host has no preferences for transmitter PHY or receiver PHY selection. Issuing this command gives the controller a clear indication that other PHY can be selected if available. Signed-off-by: Marcel Holtmann Signed-off-by: Johan Hedberg --- include/net/bluetooth/hci.h | 7 +++++++ net/bluetooth/hci_core.c | 12 ++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/net') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index dd43cfdd443a..fe98f0a5bef0 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1499,6 +1499,13 @@ struct hci_rp_le_read_max_data_len { __le16 rx_time; } __packed; +#define HCI_OP_LE_SET_DEFAULT_PHY 0x2031 +struct hci_cp_le_set_default_phy { + __u8 all_phys; + __u8 tx_phys; + __u8 rx_phys; +} __packed; + /* ---- HCI Events ---- */ #define HCI_EV_INQUIRY_COMPLETE 0x01 diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 88a616a2b959..43fecd59dfef 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -794,6 +794,18 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt) hci_req_add(req, HCI_OP_LE_WRITE_DEF_DATA_LEN, sizeof(cp), &cp); } + /* Set Default PHY parameters if command is supported */ + if (hdev->commands[35] & 0x20) { + struct hci_cp_le_set_default_phy cp; + + /* No transmitter PHY or receiver PHY preferences */ + cp.all_phys = 0x03; + cp.tx_phys = 0; + cp.rx_phys = 0; + + hci_req_add(req, HCI_OP_LE_SET_DEFAULT_PHY, sizeof(cp), &cp); + } + return 0; } -- cgit v1.2.3 From 667271455f883d23e6418ef3376eb1214da9d066 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Wed, 17 May 2017 19:31:39 +0300 Subject: net: make struct dst_entry::dev first member struct dst_entry::dev is used most often. Move it so it can be accessed without imm8 offset on x86_64. add/remove: 0/0 grow/shrink: 9/239 up/down: 52/-413 (-361) function old new delta dst_rcu_free 126 138 +12 fnhe_flush_routes 211 219 +8 rt_set_nexthop 747 754 +7 rt_cache_route 85 91 +6 rt6_release 209 215 +6 dst_release 107 111 +4 dst_destroy_rcu 29 33 +4 dn_dst_check_expire 329 333 +4 dn_insert_route 484 485 +1 xfrm_resolve_and_create_bundle 2991 2990 -1 ... ip_route_me_harder 1163 1157 -6 __ip_append_data.isra 2730 2724 -6 ip6_forward 3052 3045 -7 callforward_do_filter 659 651 -8 dst_gc_task 571 549 -22 Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/dst.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 049af33da3b6..755a0eedffde 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -31,9 +31,9 @@ struct sk_buff; struct dst_entry { + struct net_device *dev; struct rcu_head rcu_head; struct dst_entry *child; - struct net_device *dev; struct dst_ops *ops; unsigned long _metrics; unsigned long expires; -- cgit v1.2.3 From f0c24ccf491b09de53cee32114c924551218f2bc Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Wed, 17 May 2017 15:46:04 -0400 Subject: net: dsa: include switchdev.h only once DSA drivers and core use switchdev. Include switchdev.h only once, in the dsa.h public header, so that inclusion in DSA drivers or forward declarations of switchdev structures in not necessary anymore. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 1 - drivers/net/dsa/bcm_sf2.c | 1 - drivers/net/dsa/dsa_loop.c | 1 - drivers/net/dsa/mt7530.c | 1 - drivers/net/dsa/mv88e6xxx/chip.c | 1 - drivers/net/dsa/qca8k.c | 1 - include/net/dsa.h | 7 +------ net/dsa/slave.c | 1 - 8 files changed, 1 insertion(+), 13 deletions(-) (limited to 'include/net') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 658a12c888a8..fbc3eb17c7a3 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -29,7 +29,6 @@ #include #include #include -#include #include "b53_regs.h" #include "b53_priv.h" diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 215d41c1e71f..687a8bae5d73 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include "bcm_sf2.h" diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index a19e1781e9bb..6afab16d13dd 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include "dsa_loop.h" diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index b070c167e70f..1bcbe15870ed 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -28,7 +28,6 @@ #include #include #include -#include #include "mt7530.h" diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d034d8cd7d22..386d878569ed 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -32,7 +32,6 @@ #include #include #include -#include #include "mv88e6xxx.h" #include "global1.h" diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 942b9ac7f92a..149f109dbffb 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/include/net/dsa.h b/include/net/dsa.h index ed767beca9c6..bf6a2abb9b99 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -20,6 +20,7 @@ #include #include #include +#include struct tc_action; struct phy_device; @@ -284,12 +285,6 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) return ds->rtable[dst->cpu_dp->ds->index]; } -struct switchdev_trans; -struct switchdev_obj; -struct switchdev_obj_port_fdb; -struct switchdev_obj_port_mdb; -struct switchdev_obj_port_vlan; - #define DSA_NOTIFIER_BRIDGE_JOIN 1 #define DSA_NOTIFIER_BRIDGE_LEAVE 2 diff --git a/net/dsa/slave.c b/net/dsa/slave.c index fb13c5d7d587..91236d602301 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From 438ff53739ee523de3755a98ae3a290e69752620 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Wed, 17 May 2017 15:46:05 -0400 Subject: net: dsa: use switchdev_obj_dump_cb_t everywhere Now that the DSA public header includes switchdev.h, use the provided switchdev_obj_dump_cb_t typedef for the object dump callback. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 6 +++--- drivers/net/dsa/b53/b53_priv.h | 4 ++-- drivers/net/dsa/dsa_loop.c | 2 +- drivers/net/dsa/mt7530.c | 2 +- drivers/net/dsa/mv88e6xxx/chip.c | 10 +++++----- drivers/net/dsa/qca8k.c | 2 +- include/net/dsa.h | 6 +++--- 7 files changed, 16 insertions(+), 16 deletions(-) (limited to 'include/net') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index fbc3eb17c7a3..fa099ed41652 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1055,7 +1055,7 @@ EXPORT_SYMBOL(b53_vlan_del); int b53_vlan_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct b53_device *dev = ds->priv; u16 vid, vid_start = 0, pvid; @@ -1284,7 +1284,7 @@ static void b53_arl_search_rd(struct b53_device *dev, u8 idx, static int b53_fdb_copy(struct net_device *dev, int port, const struct b53_arl_entry *ent, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { if (!ent->is_valid) return 0; @@ -1301,7 +1301,7 @@ static int b53_fdb_copy(struct net_device *dev, int port, int b53_fdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct b53_device *priv = ds->priv; struct net_device *dev = ds->ports[port].netdev; diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index a9dc90a01438..155a9c48c317 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -395,7 +395,7 @@ int b53_vlan_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int b53_vlan_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(struct switchdev_obj *obj)); + switchdev_obj_dump_cb_t *cb); int b53_fdb_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb, struct switchdev_trans *trans); @@ -406,7 +406,7 @@ int b53_fdb_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_fdb *fdb); int b53_fdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)); + switchdev_obj_dump_cb_t *cb); int b53_mirror_add(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress); void b53_mirror_del(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index 6afab16d13dd..5edf07beb9d2 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -187,7 +187,7 @@ static int dsa_loop_port_vlan_del(struct dsa_switch *ds, int port, static int dsa_loop_port_vlan_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct dsa_loop_priv *ps = ds->priv; struct mii_bus *bus = ps->bus; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 1bcbe15870ed..4d2f45153ede 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -853,7 +853,7 @@ mt7530_port_fdb_del(struct dsa_switch *ds, int port, static int mt7530_port_fdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mt7530_priv *priv = ds->priv; struct mt7530_fdb _fdb = { 0 }; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 386d878569ed..41de250dbcc3 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1268,7 +1268,7 @@ static int mv88e6xxx_vtu_loadpurge(struct mv88e6xxx_chip *chip, static int mv88e6xxx_port_vlan_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mv88e6xxx_chip *chip = ds->priv; struct mv88e6xxx_vtu_entry next = { @@ -1699,7 +1699,7 @@ static int mv88e6xxx_port_fdb_del(struct dsa_switch *ds, int port, static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip, u16 fid, u16 vid, int port, struct switchdev_obj *obj, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mv88e6xxx_atu_entry addr; int err; @@ -1754,7 +1754,7 @@ static int mv88e6xxx_port_db_dump_fid(struct mv88e6xxx_chip *chip, static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port, struct switchdev_obj *obj, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mv88e6xxx_vtu_entry vlan = { .vid = chip->info->max_vid, @@ -1791,7 +1791,7 @@ static int mv88e6xxx_port_db_dump(struct mv88e6xxx_chip *chip, int port, static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mv88e6xxx_chip *chip = ds->priv; int err; @@ -4037,7 +4037,7 @@ static int mv88e6xxx_port_mdb_del(struct dsa_switch *ds, int port, static int mv88e6xxx_port_mdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_mdb *mdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct mv88e6xxx_chip *chip = ds->priv; int err; diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 149f109dbffb..0f6a011d8ed1 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -872,7 +872,7 @@ qca8k_port_fdb_del(struct dsa_switch *ds, int port, static int qca8k_port_fdb_dump(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)) + switchdev_obj_dump_cb_t *cb) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; struct qca8k_fdb _fdb = { 0 }; diff --git a/include/net/dsa.h b/include/net/dsa.h index bf6a2abb9b99..791fed62fb16 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -404,7 +404,7 @@ struct dsa_switch_ops { const struct switchdev_obj_port_vlan *vlan); int (*port_vlan_dump)(struct dsa_switch *ds, int port, struct switchdev_obj_port_vlan *vlan, - int (*cb)(struct switchdev_obj *obj)); + switchdev_obj_dump_cb_t *cb); /* * Forwarding database @@ -419,7 +419,7 @@ struct dsa_switch_ops { const struct switchdev_obj_port_fdb *fdb); int (*port_fdb_dump)(struct dsa_switch *ds, int port, struct switchdev_obj_port_fdb *fdb, - int (*cb)(struct switchdev_obj *obj)); + switchdev_obj_dump_cb_t *cb); /* * Multicast database @@ -434,7 +434,7 @@ struct dsa_switch_ops { const struct switchdev_obj_port_mdb *mdb); int (*port_mdb_dump)(struct dsa_switch *ds, int port, struct switchdev_obj_port_mdb *mdb, - int (*cb)(struct switchdev_obj *obj)); + switchdev_obj_dump_cb_t *cb); /* * RXNFC -- cgit v1.2.3 From d37d49c2f18fb53c6315b2b0fd7f1fb3d8be57ac Mon Sep 17 00:00:00 2001 From: Benjamin Berg Date: Tue, 16 May 2017 11:23:11 +0200 Subject: wireless: Only join DFS channels in mesh mode if userspace flags support When joining a mesh network it is not guaranteed that userspace has a daemon listening for radar events. This is however required for channels requiring DFS. To flag that userspace will handle radar events, it needs to set NL80211_ATTR_HANDLE_DFS. This matches the current mechanism used for IBSS mode. Signed-off-by: Benjamin Berg Signed-off-by: Simon Wunderlich Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ net/wireless/mesh.c | 8 ++++++++ net/wireless/nl80211.c | 3 +++ 3 files changed, 15 insertions(+) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index b083e6cbae8c..fa25fbb67cb6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1441,6 +1441,9 @@ struct mesh_config { * @mcast_rate: multicat rate for Mesh Node [6Mbps is the default for 802.11a] * @basic_rates: basic rates to use when creating the mesh * @beacon_rate: bitrate to be used for beacons + * @userspace_handles_dfs: whether user space controls DFS operation, i.e. + * changes the channel when a radar is detected. This is required + * to operate on DFS channels. * * These parameters are fixed when the mesh is created. */ @@ -1462,6 +1465,7 @@ struct mesh_setup { int mcast_rate[NUM_NL80211_BANDS]; u32 basic_rates; struct cfg80211_bitrate_mask beacon_rate; + bool userspace_handles_dfs; }; /** diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index ec0b1c20ac99..421a6b80ec62 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -174,6 +174,14 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, scan_width); } + err = cfg80211_chandef_dfs_required(&rdev->wiphy, + &setup->chandef, + NL80211_IFTYPE_MESH_POINT); + if (err < 0) + return err; + if (err > 0 && !setup->userspace_handles_dfs) + return -EINVAL; + if (!cfg80211_reg_can_beacon(&rdev->wiphy, &setup->chandef, NL80211_IFTYPE_MESH_POINT)) return -EINVAL; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c3bc9da30cff..d47e55e3f445 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9962,6 +9962,9 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info) return err; } + setup.userspace_handles_dfs = + nla_get_flag(info->attrs[NL80211_ATTR_HANDLE_DFS]); + return cfg80211_join_mesh(rdev, dev, &setup, &cfg); } -- cgit v1.2.3 From 6d8422a175ccf2846d9460ed2b6228fe0b12c243 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 21 May 2017 10:12:02 -0600 Subject: net: ipv4: Plumb extack through route add functions Plumb extack argument down to route add functions. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 3 ++- net/ipv4/fib_frontend.c | 16 +++++++++------- net/ipv4/fib_lookup.h | 3 ++- net/ipv4/fib_semantics.c | 22 +++++++++++++--------- net/ipv4/fib_trie.c | 4 ++-- 5 files changed, 28 insertions(+), 20 deletions(-) (limited to 'include/net') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 6692c5758b33..42e8b8f55f7c 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -263,7 +263,8 @@ struct fib_table { int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); -int fib_table_insert(struct net *, struct fib_table *, struct fib_config *); +int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, + struct netlink_ext_ack *extack); int fib_table_delete(struct net *, struct fib_table *, struct fib_config *); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 83e3ed258467..511edff76c01 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -594,7 +594,8 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) } else { tb = fib_new_table(net, cfg.fc_table); if (tb) - err = fib_table_insert(net, tb, &cfg); + err = fib_table_insert(net, tb, + &cfg, NULL); else err = -ENOBUFS; } @@ -626,14 +627,15 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_config *cfg) + struct nlmsghdr *nlh, struct fib_config *cfg, + struct netlink_ext_ack *extack) { struct nlattr *attr; int err, remaining; struct rtmsg *rtm; err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy, - NULL); + extack); if (err < 0) goto errout; @@ -718,7 +720,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_table *tb; int err; - err = rtm_to_fib_config(net, skb, nlh, &cfg); + err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; @@ -741,7 +743,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_table *tb; int err; - err = rtm_to_fib_config(net, skb, nlh, &cfg); + err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; @@ -751,7 +753,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - err = fib_table_insert(net, tb, &cfg); + err = fib_table_insert(net, tb, &cfg, extack); errout: return err; } @@ -845,7 +847,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) - fib_table_insert(net, tb, &cfg); + fib_table_insert(net, tb, &cfg, NULL); else fib_table_delete(net, tb, &cfg); } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 9c02920725db..2704e08545da 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -28,7 +28,8 @@ static inline void fib_alias_accessed(struct fib_alias *fa) /* Exported by fib_semantics.c */ void fib_release_info(struct fib_info *); -struct fib_info *fib_create_info(struct fib_config *cfg); +struct fib_info *fib_create_info(struct fib_config *cfg, + struct netlink_ext_ack *extack); int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index da449ddb8cc1..8587d1b55b53 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -454,7 +454,8 @@ static int fib_detect_death(struct fib_info *fi, int order, #ifdef CONFIG_IP_ROUTE_MULTIPATH -static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) +static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining, + struct netlink_ext_ack *extack) { int nhs = 0; @@ -468,7 +469,8 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) } static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, - int remaining, struct fib_config *cfg) + int remaining, struct fib_config *cfg, + struct netlink_ext_ack *extack) { int ret; @@ -714,7 +716,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) * |-> {local prefix} (terminal node) */ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, - struct fib_nh *nh) + struct fib_nh *nh, struct netlink_ext_ack *extack) { int err = 0; struct net *net; @@ -797,7 +799,6 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) return -EINVAL; - rcu_read_lock(); err = -ENODEV; in_dev = inetdev_by_index(net, nh->nh_oif); @@ -980,7 +981,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) return 0; } -struct fib_info *fib_create_info(struct fib_config *cfg) +struct fib_info *fib_create_info(struct fib_config *cfg, + struct netlink_ext_ack *extack) { int err; struct fib_info *fi = NULL; @@ -1000,7 +1002,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) #ifdef CONFIG_IP_ROUTE_MULTIPATH if (cfg->fc_mp) { - nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); + nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len, extack); if (nhs == 0) goto err_inval; } @@ -1062,7 +1064,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (cfg->fc_mp) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg); + 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) @@ -1129,7 +1131,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg) struct fib_nh *nh = fi->fib_nh; /* Local address is added. */ - if (nhs != 1 || nh->nh_gw) + if (nhs != 1) + goto err_inval; + if (nh->nh_gw) goto err_inval; nh->nh_scope = RT_SCOPE_NOWHERE; nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif); @@ -1140,7 +1144,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) int linkdown = 0; change_nexthops(fi) { - err = fib_check_nh(cfg, fi, nexthop_nh); + err = fib_check_nh(cfg, fi, nexthop_nh, extack); if (err != 0) goto failure; if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 51182ff2b441..6d0f6c79d9aa 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1101,7 +1101,7 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, - struct fib_config *cfg) + struct fib_config *cfg, struct netlink_ext_ack *extack) { enum fib_event_type event = FIB_EVENT_ENTRY_ADD; struct trie *t = (struct trie *)tb->tb_data; @@ -1125,7 +1125,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, if ((plen < KEYLENGTH) && (key << plen)) return -EINVAL; - fi = fib_create_info(cfg); + fi = fib_create_info(cfg, extack); if (IS_ERR(fi)) { err = PTR_ERR(fi); goto err; -- cgit v1.2.3 From 333c430167c21b96de81a674fa6cbe84b09475dc Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 21 May 2017 10:12:04 -0600 Subject: net: ipv6: Plumb extack through route add functions Plumb extack argument down to route add functions. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 3 ++- include/net/ip6_route.h | 2 +- net/ipv6/addrconf.c | 4 ++-- net/ipv6/ip6_fib.c | 14 +++++++----- net/ipv6/route.c | 57 +++++++++++++++++++++++++++---------------------- 5 files changed, 46 insertions(+), 34 deletions(-) (limited to 'include/net') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index c979c878df1c..aa50e2e6fa2a 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -277,7 +277,8 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), void *arg); int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc); + struct nl_info *info, struct mx6_config *mxc, + struct netlink_ext_ack *extack); int fib6_del(struct rt6_info *rt, struct nl_info *info); void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f5e625f53367..f3da9dd2a8db 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -90,7 +90,7 @@ void ip6_route_cleanup(void); int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg); -int ip6_route_add(struct fib6_config *cfg); +int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack); int ip6_ins_rt(struct rt6_info *); int ip6_del_rt(struct rt6_info *); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6a4fb1e629fb..25443fd946a8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2280,7 +2280,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, cfg.fc_flags |= RTF_NONEXTHOP; #endif - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); } @@ -2335,7 +2335,7 @@ static void addrconf_add_mroute(struct net_device *dev) ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index d4bf2c68a545..c1197e167d3e 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -473,7 +473,8 @@ out: static struct fib6_node *fib6_add_1(struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, - int replace_required, int sernum) + int replace_required, int sernum, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; @@ -964,7 +965,8 @@ void fib6_force_start_gc(struct net *net) */ int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc) + struct nl_info *info, struct mx6_config *mxc, + struct netlink_ext_ack *extack) { struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; @@ -987,7 +989,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), allow_create, - replace_required, sernum); + replace_required, sernum, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; @@ -1028,7 +1030,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, sn = fib6_add_1(sfn, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum); + allow_create, replace_required, sernum, + extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated @@ -1047,7 +1050,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), - allow_create, replace_required, sernum); + allow_create, replace_required, sernum, + extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dc61b0b5e64e..ca754ec4054a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -938,14 +938,15 @@ EXPORT_SYMBOL(rt6_lookup); */ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, - struct mx6_config *mxc) + struct mx6_config *mxc, + struct netlink_ext_ack *extack) { int err; struct fib6_table *table; table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, info, mxc); + err = fib6_add(&table->tb6_root, rt, info, mxc, extack); write_unlock_bh(&table->tb6_lock); return err; @@ -956,7 +957,7 @@ int ip6_ins_rt(struct rt6_info *rt) struct nl_info info = { .nl_net = dev_net(rt->dst.dev), }; struct mx6_config mxc = { .mx = NULL, }; - return __ip6_ins_rt(rt, &info, &mxc); + return __ip6_ins_rt(rt, &info, &mxc, NULL); } static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, @@ -1844,7 +1845,8 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net, return rt; } -static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg) +static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct rt6_info *rt = NULL; @@ -2111,13 +2113,14 @@ out: return ERR_PTR(err); } -int ip6_route_add(struct fib6_config *cfg) +int ip6_route_add(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct mx6_config mxc = { .mx = NULL, }; struct rt6_info *rt; int err; - rt = ip6_route_info_create(cfg); + rt = ip6_route_info_create(cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; @@ -2128,7 +2131,7 @@ int ip6_route_add(struct fib6_config *cfg) if (err) goto out; - err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc); + err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc, extack); kfree(mxc.mx); @@ -2222,7 +2225,8 @@ out_put: return err; } -static int ip6_route_del(struct fib6_config *cfg) +static int ip6_route_del(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct fib6_table *table; struct fib6_node *fn; @@ -2483,7 +2487,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; - ip6_route_add(&cfg); + ip6_route_add(&cfg, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } @@ -2529,7 +2533,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, cfg.fc_gateway = *gwaddr; - if (!ip6_route_add(&cfg)) { + if (!ip6_route_add(&cfg, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); @@ -2622,10 +2626,10 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) rtnl_lock(); switch (cmd) { case SIOCADDRT: - err = ip6_route_add(&cfg); + err = ip6_route_add(&cfg, NULL); break; case SIOCDELRT: - err = ip6_route_del(&cfg); + err = ip6_route_del(&cfg, NULL); break; default: err = -EINVAL; @@ -2903,7 +2907,8 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, - struct fib6_config *cfg) + struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; @@ -3097,7 +3102,8 @@ static void ip6_route_mpath_notify(struct rt6_info *rt, inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); } -static int ip6_route_multipath_add(struct fib6_config *cfg) +static int ip6_route_multipath_add(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct rt6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; @@ -3145,7 +3151,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) r_cfg.fc_encap_type = nla_get_u16(nla); } - rt = ip6_route_info_create(&r_cfg); + rt = ip6_route_info_create(&r_cfg, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; @@ -3170,7 +3176,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg) err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { rt_last = nh->rt6_info; - err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc); + err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc, extack); /* save reference to first route for notification */ if (!rt_notif && !err) rt_notif = nh->rt6_info; @@ -3212,7 +3218,7 @@ add_errout: list_for_each_entry(nh, &rt6_nh_list, next) { if (err_nh == nh) break; - ip6_route_del(&nh->r_cfg); + ip6_route_del(&nh->r_cfg, extack); } cleanup: @@ -3227,7 +3233,8 @@ cleanup: return err; } -static int ip6_route_multipath_del(struct fib6_config *cfg) +static int ip6_route_multipath_del(struct fib6_config *cfg, + struct netlink_ext_ack *extack) { struct fib6_config r_cfg; struct rtnexthop *rtnh; @@ -3254,7 +3261,7 @@ static int ip6_route_multipath_del(struct fib6_config *cfg) r_cfg.fc_flags |= RTF_GATEWAY; } } - err = ip6_route_del(&r_cfg); + err = ip6_route_del(&r_cfg, extack); if (err) last_err = err; @@ -3270,15 +3277,15 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config cfg; int err; - err = rtm_to_fib6_config(skb, nlh, &cfg); + err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_mp) - return ip6_route_multipath_del(&cfg); + return ip6_route_multipath_del(&cfg, extack); else { cfg.fc_delete_all_nh = 1; - return ip6_route_del(&cfg); + return ip6_route_del(&cfg, extack); } } @@ -3288,14 +3295,14 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config cfg; int err; - err = rtm_to_fib6_config(skb, nlh, &cfg); + err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_mp) - return ip6_route_multipath_add(&cfg); + return ip6_route_multipath_add(&cfg, extack); else - return ip6_route_add(&cfg); + return ip6_route_add(&cfg, extack); } static size_t rt6_nlmsg_size(struct rt6_info *rt) -- cgit v1.2.3 From 52c96f9d7003c74c7fbec7438c0ed78df0cc1c79 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 19 May 2017 17:00:51 -0400 Subject: net: dsa: move notifier info to private header The DSA notifier events and info structure definitions are not meant for DSA drivers and users, but only used internally by the DSA core files. Move them from the public net/dsa.h file to the private dsa_priv.h file. Also use this opportunity to turn the events into an anonymous enum, because we don't care about the values, and this will prevent future conflicts when adding (and sorting) new events. Signed-off-by: Vivien Didelot Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 10 ---------- net/dsa/dsa_priv.h | 12 ++++++++++++ 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 791fed62fb16..c0e567c0c824 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -285,16 +285,6 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) return ds->rtable[dst->cpu_dp->ds->index]; } -#define DSA_NOTIFIER_BRIDGE_JOIN 1 -#define DSA_NOTIFIER_BRIDGE_LEAVE 2 - -/* DSA_NOTIFIER_BRIDGE_* */ -struct dsa_notifier_bridge_info { - struct net_device *br; - int sw_index; - int port; -}; - struct dsa_switch_ops { /* * Legacy probing. diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 16021a891095..c19241eb094b 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -16,6 +16,18 @@ #include #include +enum { + DSA_NOTIFIER_BRIDGE_JOIN, + DSA_NOTIFIER_BRIDGE_LEAVE, +}; + +/* DSA_NOTIFIER_BRIDGE_* */ +struct dsa_notifier_bridge_info { + struct net_device *br; + int sw_index; + int port; +}; + struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, -- cgit v1.2.3 From 4c0ebd6fed66388584abb27d7b0f188cc1ec01fe Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 23 May 2017 00:20:26 +0300 Subject: net: make struct inet_frags::qsize unsigned This field is sizeof of corresponding kmem_cache so it can't be negative. Prepare for 32-bit kmem_cache_create(). Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 5894730ec82a..975779d0e7b0 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -92,7 +92,7 @@ struct inet_frags { */ u32 rnd; seqlock_t rnd_seqlock; - int qsize; + unsigned int qsize; unsigned int (*hashfn)(const struct inet_frag_queue *); bool (*match)(const struct inet_frag_queue *q, -- cgit v1.2.3 From 417ccf6b5bc3f1a390505d5ef65ec17f10e8b29a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 23 May 2017 00:21:39 +0300 Subject: net: make struct request_sock_ops::obj_size unsigned This field is sizeof of corresponding kmem_cache so it can't be negative. Space will be saved after 32-bit kmem_cache_create() patch. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/request_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index a12a5d25b27e..53ced67c4ae9 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -29,7 +29,7 @@ struct proto; struct request_sock_ops { int family; - int obj_size; + unsigned int obj_size; struct kmem_cache *slab; char *slab_name; int (*rtx_syn_ack)(const struct sock *sk, -- cgit v1.2.3 From ac4bb5de27010e41f027c635dedca1393e7ebf55 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 23 May 2017 18:40:44 +0200 Subject: net: flow_dissector: add support for dissection of tcp flags Add support for dissection of tcp flags. Uses similar function call to tcp dissection function as arp, mpls and others. Signed-off-by: Jiri Pirko Acked-by: Or Gerlitz Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 9 +++++++++ net/core/flow_dissector.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'include/net') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 8d21d448daa9..efe34eec61dc 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -157,6 +157,14 @@ struct flow_dissector_key_eth_addrs { unsigned char src[ETH_ALEN]; }; +/** + * struct flow_dissector_key_tcp: + * @flags: flags + */ +struct flow_dissector_key_tcp { + __be16 flags; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -177,6 +185,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_ENC_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ + FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ FLOW_DISSECTOR_KEY_MAX, }; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 28d94bce4df8..5a45943081f5 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -342,6 +343,30 @@ __skb_flow_dissect_gre(const struct sk_buff *skb, return FLOW_DISSECT_RET_OUT_PROTO_AGAIN; } +static void +__skb_flow_dissect_tcp(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, int thoff, int hlen) +{ + struct flow_dissector_key_tcp *key_tcp; + struct tcphdr *th, _th; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TCP)) + return; + + th = __skb_header_pointer(skb, thoff, sizeof(_th), data, hlen, &_th); + if (!th) + return; + + if (unlikely(__tcp_hdrlen(th) < sizeof(_th))) + return; + + key_tcp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_TCP, + target_container); + key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -683,6 +708,10 @@ ip_proto_again: case IPPROTO_MPLS: proto = htons(ETH_P_MPLS_UC); goto mpls; + case IPPROTO_TCP: + __skb_flow_dissect_tcp(skb, flow_dissector, target_container, + data, nhoff, hlen); + break; default: break; } -- cgit v1.2.3 From 367a8ce896f14018cc2c6cf2681aa440fff274f4 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 23 May 2017 09:42:37 -0700 Subject: net_sched: only create filter chains for new filters/actions tcf_chain_get() always creates a new filter chain if not found in existing ones. This is totally unnecessary when we get or delete filters, new chain should be only created for new filters (or new actions). Fixes: 5bc1701881e3 ("net: sched: introduce multichain support for filters") Cc: Jamal Hadi Salim Cc: Jiri Pirko Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/pkt_cls.h | 3 ++- net/sched/act_api.c | 2 +- net/sched/cls_api.c | 13 +++++++++---- 3 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 2c213a69c196..f7762295b7b8 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -18,7 +18,8 @@ int register_tcf_proto_ops(struct tcf_proto_ops *ops); int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #ifdef CONFIG_NET_CLS -struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index); +struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, + bool create); void tcf_chain_put(struct tcf_chain *chain); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 0ecf2a858767..aed6cf2e9fd8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -34,7 +34,7 @@ static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp) if (!tp) return -EINVAL; - a->goto_chain = tcf_chain_get(tp->chain->block, chain_index); + a->goto_chain = tcf_chain_get(tp->chain->block, chain_index, true); if (!a->goto_chain) return -ENOMEM; return 0; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 89fbb35bc666..39da0c5801c9 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -220,7 +220,8 @@ static void tcf_chain_destroy(struct tcf_chain *chain) kfree(chain); } -struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index) +struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, + bool create) { struct tcf_chain *chain; @@ -230,7 +231,10 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index) return chain; } } - return tcf_chain_create(block, chain_index); + if (create) + return tcf_chain_create(block, chain_index); + else + return NULL; } EXPORT_SYMBOL(tcf_chain_get); @@ -511,9 +515,10 @@ replay: err = -EINVAL; goto errout; } - chain = tcf_chain_get(block, chain_index); + chain = tcf_chain_get(block, chain_index, + n->nlmsg_type == RTM_NEWTFILTER); if (!chain) { - err = -ENOMEM; + err = n->nlmsg_type == RTM_NEWTFILTER ? -ENOMEM : -EINVAL; goto errout; } -- cgit v1.2.3 From 3abd1ade6765e8edcccad6a9e1039cc709e65dde Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 25 May 2017 10:42:33 -0700 Subject: net: ipv4: refactor __ip_route_output_key_hash A later patch wants access to the fib result on an output route lookup with the rcu lock held. Refactor __ip_route_output_key_hash, pushing the logic between rcu_read_lock ... rcu_read_unlock into a new helper with the fib_result as an input arg. To keep the name length under control remove the leading underscores from the name and add _rcu to the name of the new helper indicating it is called with the rcu read lock held. Signed-off-by: David Ahern Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/route.h | 9 ++++++--- net/ipv4/icmp.c | 2 +- net/ipv4/route.c | 53 +++++++++++++++++++++++++++++++---------------------- 3 files changed, 38 insertions(+), 26 deletions(-) (limited to 'include/net') diff --git a/include/net/route.h b/include/net/route.h index 2cc0e14c6359..89e4028cd063 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -113,13 +113,16 @@ struct in_device; int ip_rt_init(void); void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); -struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *flp, - const struct sk_buff *skb); +struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp, + const struct sk_buff *skb); +struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp, + struct fib_result *res, + const struct sk_buff *skb); static inline struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp) { - return __ip_route_output_key_hash(net, flp, NULL); + return ip_route_output_key_hash(net, flp, NULL); } struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 43318b5f5647..5610971bf859 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -489,7 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); - rt = __ip_route_output_key_hash(net, fl4, skb_in); + rt = ip_route_output_key_hash(net, fl4, skb_in); if (IS_ERR(rt)) return rt; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 655d9eebe43e..c9b55cb0e316 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2246,29 +2246,40 @@ add: * Major route resolver routine. */ -struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, - const struct sk_buff *skb) +struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, + const struct sk_buff *skb) { - struct net_device *dev_out = NULL; __u8 tos = RT_FL_TOS(fl4); - unsigned int flags = 0; struct fib_result res; struct rtable *rth; - int orig_oif; - int err = -ENETUNREACH; res.tclassid = 0; res.fi = NULL; res.table = NULL; - orig_oif = fl4->flowi4_oif; - fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos = tos & IPTOS_RT_MASK; fl4->flowi4_scope = ((tos & RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); rcu_read_lock(); + rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); + rcu_read_unlock(); + + return rth; +} +EXPORT_SYMBOL_GPL(ip_route_output_key_hash); + +struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, + struct fib_result *res, + const struct sk_buff *skb) +{ + struct net_device *dev_out = NULL; + int orig_oif = fl4->flowi4_oif; + unsigned int flags = 0; + struct rtable *rth; + int err = -ENETUNREACH; + if (fl4->saddr) { rth = ERR_PTR(-EINVAL); if (ipv4_is_multicast(fl4->saddr) || @@ -2354,15 +2365,15 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; fl4->flowi4_oif = LOOPBACK_IFINDEX; - res.type = RTN_LOCAL; + res->type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; } - err = fib_lookup(net, fl4, &res, 0); + err = fib_lookup(net, fl4, res, 0); if (err) { - res.fi = NULL; - res.table = NULL; + res->fi = NULL; + res->table = NULL; if (fl4->flowi4_oif && (ipv4_is_multicast(fl4->daddr) || !netif_index_is_l3_master(net, fl4->flowi4_oif))) { @@ -2387,43 +2398,41 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, if (fl4->saddr == 0) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); - res.type = RTN_UNICAST; + res->type = RTN_UNICAST; goto make_route; } rth = ERR_PTR(err); goto out; } - if (res.type == RTN_LOCAL) { + if (res->type == RTN_LOCAL) { if (!fl4->saddr) { - if (res.fi->fib_prefsrc) - fl4->saddr = res.fi->fib_prefsrc; + if (res->fi->fib_prefsrc) + fl4->saddr = res->fi->fib_prefsrc; else fl4->saddr = fl4->daddr; } /* L3 master device is the loopback for that domain */ - dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? : + dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? : net->loopback_dev; fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; } - fib_select_path(net, &res, fl4, skb); + fib_select_path(net, res, fl4, skb); - dev_out = FIB_RES_DEV(res); + dev_out = FIB_RES_DEV(*res); fl4->flowi4_oif = dev_out->ifindex; make_route: - rth = __mkroute_output(&res, fl4, orig_oif, dev_out, flags); + rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); out: - rcu_read_unlock(); return rth; } -EXPORT_SYMBOL_GPL(__ip_route_output_key_hash); static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) { -- cgit v1.2.3 From 5510cdf7be042a1943222e19912f13a396c0b914 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 25 May 2017 10:42:34 -0700 Subject: net: ipv4: refactor ip_route_input_noref A later patch wants access to the fib result on an input route lookup with the rcu lock held. Refactor ip_route_input_noref pushing the logic between rcu_read_lock ... rcu_read_unlock into a new helper that takes the fib_result as an input arg. Signed-off-by: David Ahern Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/route.h | 3 +++ net/ipv4/route.c | 66 ++++++++++++++++++++++++++++++----------------------- 2 files changed, 40 insertions(+), 29 deletions(-) (limited to 'include/net') diff --git a/include/net/route.h b/include/net/route.h index 89e4028cd063..08e689f23365 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -178,6 +178,9 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin); +int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src, + u8 tos, struct net_device *devin, + struct fib_result *res); static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c9b55cb0e316..1dc8fd1e60a9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1852,9 +1852,9 @@ static int ip_mkroute_input(struct sk_buff *skb, */ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev) + u8 tos, struct net_device *dev, + struct fib_result *res) { - struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); struct ip_tunnel_info *tun_info; struct flowi4 fl4; @@ -1884,8 +1884,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; - res.fi = NULL; - res.table = NULL; + res->fi = NULL; + res->table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; @@ -1921,17 +1921,17 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); - err = fib_lookup(net, &fl4, &res, 0); + err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) err = -EHOSTUNREACH; goto no_route; } - if (res.type == RTN_BROADCAST) + if (res->type == RTN_BROADCAST) goto brd_input; - if (res.type == RTN_LOCAL) { + if (res->type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &itag); if (err < 0) @@ -1943,10 +1943,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, err = -EHOSTUNREACH; goto no_route; } - if (res.type != RTN_UNICAST) + if (res->type != RTN_UNICAST) goto martian_destination; - err = ip_mkroute_input(skb, &res, in_dev, daddr, saddr, tos); + err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos); out: return err; brd_input: @@ -1960,14 +1960,14 @@ brd_input: goto martian_source; } flags |= RTCF_BROADCAST; - res.type = RTN_BROADCAST; + res->type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: do_cache = false; - if (res.fi) { + if (res->fi) { if (!itag) { - rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input); + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); err = 0; @@ -1978,7 +1978,7 @@ local_input: } rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev, - flags | RTCF_LOCAL, res.type, + flags | RTCF_LOCAL, res->type, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache); if (!rth) goto e_nobufs; @@ -1988,18 +1988,18 @@ local_input: rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; - if (res.table) - rth->rt_table_id = res.table->tb_id; + if (res->table) + rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); - if (res.type == RTN_UNREACHABLE) { + if (res->type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } if (do_cache) { - struct fib_nh *nh = &FIB_RES_NH(res); + struct fib_nh *nh = &FIB_RES_NH(*res); rth->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); if (lwtunnel_input_redirect(rth->dst.lwtstate)) { @@ -2019,9 +2019,9 @@ local_input: no_route: RT_CACHE_STAT_INC(in_no_route); - res.type = RTN_UNREACHABLE; - res.fi = NULL; - res.table = NULL; + res->type = RTN_UNREACHABLE; + res->fi = NULL; + res->table = NULL; goto local_input; /* @@ -2051,11 +2051,22 @@ martian_source: int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev) { - int res; + struct fib_result res; + int err; tos &= IPTOS_RT_MASK; rcu_read_lock(); + err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res); + rcu_read_unlock(); + return err; +} +EXPORT_SYMBOL(ip_route_input_noref); + +/* called with rcu_read_lock held */ +int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, struct fib_result *res) +{ /* Multicast recognition logic is moved from route cache to here. The problem was that too many Ethernet cards have broken/missing hardware multicast filters :-( As result the host on multicasting @@ -2070,6 +2081,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_multicast(daddr)) { struct in_device *in_dev = __in_dev_get_rcu(dev); int our = 0; + int err = -EINVAL; if (in_dev) our = ip_check_mc_rcu(in_dev, daddr, saddr, @@ -2085,7 +2097,6 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, ip_hdr(skb)->protocol); } - res = -EINVAL; if (our #ifdef CONFIG_IP_MROUTE || @@ -2093,17 +2104,14 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, IN_DEV_MFORWARD(in_dev)) #endif ) { - res = ip_route_input_mc(skb, daddr, saddr, + err = ip_route_input_mc(skb, daddr, saddr, tos, dev, our); } - rcu_read_unlock(); - return res; + return err; } - res = ip_route_input_slow(skb, daddr, saddr, tos, dev); - rcu_read_unlock(); - return res; + + return ip_route_input_slow(skb, daddr, saddr, tos, dev, res); } -EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, -- cgit v1.2.3 From 6ffd903415320d68a528865296e4740da350785e Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 25 May 2017 10:42:37 -0700 Subject: net: ipv4: Save trie prefix to fib lookup result Prefix is needed for returning matching route spec on get route request. Signed-off-by: David Ahern Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/ip_fib.h | 1 + net/ipv4/fib_trie.c | 1 + 2 files changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 42e8b8f55f7c..25f5c516afd1 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -136,6 +136,7 @@ struct fib_rule; struct fib_table; struct fib_result { + __be32 prefix; unsigned char prefixlen; unsigned char nh_sel; unsigned char type; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 6d0f6c79d9aa..6e9df7d9bcc2 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1452,6 +1452,7 @@ found: if (!(fib_flags & FIB_LOOKUP_NOREF)) atomic_inc(&fi->fib_clntref); + res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; res->nh_sel = nhsel; res->type = fa->fa_type; -- cgit v1.2.3 From 7a7e96e09d463c7c3d51a51c539ae4352085ed18 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Sat, 27 May 2017 10:14:35 -0400 Subject: bonding: Prevent duplicate userspace notification Whenever a user changes bonding options, a NETDEV_CHANGEINFODATA notificatin is generated which results in a rtnelink message to be sent. While runnig 'ip monitor', we can actually see 2 messages, one a result of the event, and the other a result of state change that is generated bo netdev_state_change(). However, this is not always the case. If bonding changes were done via sysfs or ifenslave (old ioctl interface), then only 1 message is seen. This patch removes duplicate messages in the case of using netlink to configure bonding. It introduceds a separte function that triggers a netdev event and uses that function in the syfs and ioctl cases. This was discovered while auditing all the different envents and continues the effort of cleaning up duplicated netlink messages. CC: David Ahern CC: Jiri Pirko Signed-off-by: Vladislav Yasevich Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 3 ++- drivers/net/bonding/bond_options.c | 27 +++++++++++++++++++++++++-- include/net/bond_options.h | 2 ++ 3 files changed, 29 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2359478b977f..d4484d1a8164 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3488,7 +3488,8 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd case BOND_CHANGE_ACTIVE_OLD: case SIOCBONDCHANGEACTIVE: bond_opt_initstr(&newval, slave_dev->name); - res = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval); + res = __bond_opt_set_notify(bond, BOND_OPT_ACTIVE_SLAVE, + &newval); break; default: res = -EOPNOTSUPP; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 1bcbb8913e17..8ca683396fcc 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -673,7 +673,30 @@ int __bond_opt_set(struct bonding *bond, out: if (ret) bond_opt_error_interpret(bond, opt, ret, val); - else if (bond->dev->reg_state == NETREG_REGISTERED) + + return ret; +} +/** + * __bond_opt_set_notify - set a bonding option + * @bond: target bond device + * @option: option to set + * @val: value to set it to + * + * This function is used to change the bond's option value and trigger + * a notification to user sapce. It can be used for both enabling/changing + * an option and for disabling it. RTNL lock must be obtained before calling + * this function. + */ +int __bond_opt_set_notify(struct bonding *bond, + unsigned int option, struct bond_opt_value *val) +{ + int ret = -ENOENT; + + ASSERT_RTNL(); + + ret = __bond_opt_set(bond, option, val); + + if (!ret && (bond->dev->reg_state == NETREG_REGISTERED)) call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev); return ret; @@ -696,7 +719,7 @@ int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf) if (!rtnl_trylock()) return restart_syscall(); bond_opt_initstr(&optval, buf); - ret = __bond_opt_set(bond, option, &optval); + ret = __bond_opt_set_notify(bond, option, &optval); rtnl_unlock(); return ret; diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 1797235cd590..d79d28f5318c 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -104,6 +104,8 @@ struct bond_option { int __bond_opt_set(struct bonding *bond, unsigned int option, struct bond_opt_value *val); +int __bond_opt_set_notify(struct bonding *bond, unsigned int option, + struct bond_opt_value *val); int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, -- cgit v1.2.3 From 9fd6452d67fb2acda12e5914e2ad371f067f3465 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 21 May 2017 12:52:55 +0200 Subject: netfilter: conntrack: rename nf_ct_iterate_cleanup There are several places where we needlesly call nf_ct_iterate_cleanup, we should instead iterate the full table at module unload time. This is a leftover from back when the conntrack table got duplicated per net namespace. So rename nf_ct_iterate_cleanup to nf_ct_iterate_cleanup_net. A later patch will then add a non-net variant. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 6 +++--- net/ipv4/netfilter/nf_nat_masquerade_ipv4.c | 4 ++-- net/ipv6/netfilter/nf_nat_masquerade_ipv6.c | 10 +++++----- net/netfilter/nf_conntrack_core.c | 10 +++++----- net/netfilter/nf_conntrack_netlink.c | 4 ++-- net/netfilter/nf_conntrack_proto.c | 4 ++-- net/netfilter/nf_nat_core.c | 6 +++--- 7 files changed, 22 insertions(+), 22 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 8ece3612d0cd..f21180ea4558 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -225,9 +225,9 @@ extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct, u32 seq); /* Iterate over all conntracks: if iter returns true, it's deleted. */ -void nf_ct_iterate_cleanup(struct net *net, - int (*iter)(struct nf_conn *i, void *data), - void *data, u32 portid, int report); +void nf_ct_iterate_cleanup_net(struct net *net, + int (*iter)(struct nf_conn *i, void *data), + void *data, u32 portid, int report); struct nf_conntrack_zone; diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index dc1dea15c1b4..f39037fca923 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -98,8 +98,8 @@ static int masq_device_event(struct notifier_block *this, */ NF_CT_ASSERT(dev->ifindex != 0); - nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_ct_iterate_cleanup_net(net, device_cmp, + (void *)(long)dev->ifindex, 0, 0); } return NOTIFY_DONE; diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 2297c9f073ba..d7b679037bae 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -75,8 +75,8 @@ static int masq_device_event(struct notifier_block *this, struct net *net = dev_net(dev); if (event == NETDEV_DOWN) - nf_ct_iterate_cleanup(net, device_cmp, - (void *)(long)dev->ifindex, 0, 0); + nf_ct_iterate_cleanup_net(net, device_cmp, + (void *)(long)dev->ifindex, 0, 0); return NOTIFY_DONE; } @@ -99,7 +99,7 @@ static void iterate_cleanup_work(struct work_struct *work) w = container_of(work, struct masq_dev_work, work); index = w->ifindex; - nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0); + nf_ct_iterate_cleanup_net(w->net, device_cmp, (void *)index, 0, 0); put_net(w->net); kfree(w); @@ -110,12 +110,12 @@ static void iterate_cleanup_work(struct work_struct *work) /* ipv6 inet notifier is an atomic notifier, i.e. we cannot * schedule. * - * Unfortunately, nf_ct_iterate_cleanup can run for a long + * Unfortunately, nf_ct_iterate_cleanup_net can run for a long * time if there are lots of conntracks and the system * handles high softirq load, so it frequently calls cond_resched * while iterating the conntrack table. * - * So we defer nf_ct_iterate_cleanup walk to the system workqueue. + * So we defer nf_ct_iterate_cleanup_net walk to the system workqueue. * * As we can have 'a lot' of inet_events (depending on amount * of ipv6 addresses being deleted), we also need to add an upper diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e847dbaa0c6b..2730f9df33b7 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1634,9 +1634,9 @@ found: return ct; } -void nf_ct_iterate_cleanup(struct net *net, - int (*iter)(struct nf_conn *i, void *data), - void *data, u32 portid, int report) +void nf_ct_iterate_cleanup_net(struct net *net, + int (*iter)(struct nf_conn *i, void *data), + void *data, u32 portid, int report) { struct nf_conn *ct; unsigned int bucket = 0; @@ -1654,7 +1654,7 @@ void nf_ct_iterate_cleanup(struct net *net, cond_resched(); } } -EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup); +EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup_net); static int kill_all(struct nf_conn *i, void *data) { @@ -1723,7 +1723,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { - nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0); + nf_ct_iterate_cleanup_net(net, kill_all, NULL, 0, 0); if (atomic_read(&net->ct.count) != 0) busy = 1; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index f08604dd1a59..e1eca47105bd 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1117,8 +1117,8 @@ static int ctnetlink_flush_conntrack(struct net *net, return PTR_ERR(filter); } - nf_ct_iterate_cleanup(net, ctnetlink_filter_match, filter, - portid, report); + nf_ct_iterate_cleanup_net(net, ctnetlink_filter_match, filter, + portid, report); kfree(filter); return 0; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 2de6c1fe3261..b7d01f27d463 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -282,7 +282,7 @@ void nf_ct_l3proto_pernet_unregister(struct net *net, proto->net_ns_put(net); /* Remove all contrack entries for this protocol */ - nf_ct_iterate_cleanup(net, kill_l3proto, proto, 0, 0); + nf_ct_iterate_cleanup_net(net, kill_l3proto, proto, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_unregister); @@ -450,7 +450,7 @@ void nf_ct_l4proto_pernet_unregister_one(struct net *net, nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); /* Remove all contrack entries for this protocol */ - nf_ct_iterate_cleanup(net, kill_l4proto, l4proto, 0, 0); + nf_ct_iterate_cleanup_net(net, kill_l4proto, l4proto, 0, 0); } EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index ef0be325a0c6..daf5b22c07f8 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -586,7 +586,7 @@ static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) rtnl_lock(); for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0); + nf_ct_iterate_cleanup_net(net, nf_nat_proto_remove, &clean, 0, 0); rtnl_unlock(); } @@ -600,7 +600,7 @@ static void nf_nat_l3proto_clean(u8 l3proto) rtnl_lock(); for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0); + nf_ct_iterate_cleanup_net(net, nf_nat_proto_remove, &clean, 0, 0); rtnl_unlock(); } @@ -826,7 +826,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) { struct nf_nat_proto_clean clean = {}; - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean, 0, 0); + nf_ct_iterate_cleanup_net(net, nf_nat_proto_clean, &clean, 0, 0); } static struct pernet_operations nf_nat_net_ops = { -- cgit v1.2.3 From 2843fb69980b84dfa939733c91dceae533aa89e9 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 21 May 2017 12:52:57 +0200 Subject: netfilter: conntrack: add nf_ct_iterate_destroy sledgehammer to be used on module unload (to remove affected conntracks from all namespaces). It will also flag all unconfirmed conntracks as dying, i.e. they will not be committed to main table. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 4 ++ net/netfilter/nf_conntrack_core.c | 87 ++++++++++++++++++++++++++++++------ 2 files changed, 78 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index f21180ea4558..48407569585d 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -229,6 +229,10 @@ void nf_ct_iterate_cleanup_net(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data, u32 portid, int report); +/* also set unconfirmed conntracks as dying. Only use in module exit path. */ +void nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), + void *data); + struct nf_conntrack_zone; void nf_conntrack_free(struct nf_conn *ct); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 08733685d732..7ecee79c78b8 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1586,7 +1586,7 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) /* Bring out ya dead! */ static struct nf_conn * -get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), +get_next_corpse(int (*iter)(struct nf_conn *i, void *data), void *data, unsigned int *bucket) { struct nf_conntrack_tuple_hash *h; @@ -1603,8 +1603,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = nf_ct_tuplehash_to_ctrack(h); - if (net_eq(nf_ct_net(ct), net) && - iter(ct, data)) + if (iter(ct, data)) goto found; } } @@ -1621,6 +1620,39 @@ found: return ct; } +static void nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data), + void *data, u32 portid, int report) +{ + struct nf_conn *ct; + unsigned int bucket = 0; + + might_sleep(); + + while ((ct = get_next_corpse(iter, data, &bucket)) != NULL) { + /* Time to push up daises... */ + + nf_ct_delete(ct, portid, report); + nf_ct_put(ct); + cond_resched(); + } +} + +struct iter_data { + int (*iter)(struct nf_conn *i, void *data); + void *data; + struct net *net; +}; + +static int iter_net_only(struct nf_conn *i, void *data) +{ + struct iter_data *d = data; + + if (!net_eq(d->net, nf_ct_net(i))) + return 0; + + return d->iter(i, d->data); +} + static void __nf_ct_unconfirmed_destroy(struct net *net) { @@ -1653,8 +1685,7 @@ void nf_ct_iterate_cleanup_net(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data, u32 portid, int report) { - struct nf_conn *ct; - unsigned int bucket = 0; + struct iter_data d; might_sleep(); @@ -1663,21 +1694,51 @@ void nf_ct_iterate_cleanup_net(struct net *net, __nf_ct_unconfirmed_destroy(net); + d.iter = iter; + d.data = data; + d.net = net; + synchronize_net(); - while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { - /* Time to push up daises... */ + nf_ct_iterate_cleanup(iter_net_only, &d, portid, report); +} +EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup_net); - nf_ct_delete(ct, portid, report); - nf_ct_put(ct); - cond_resched(); +/** + * nf_ct_iterate_destroy - destroy unconfirmed conntracks and iterate table + * @iter: callback to invoke for each conntrack + * @data: data to pass to @iter + * + * Like nf_ct_iterate_cleanup, but first marks conntracks on the + * unconfirmed list as dying (so they will not be inserted into + * main table). + */ +void +nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data) +{ + struct net *net; + + rtnl_lock(); + for_each_net(net) { + if (atomic_read(&net->ct.count) == 0) + continue; + __nf_ct_unconfirmed_destroy(net); } + rtnl_unlock(); + + /* a conntrack could have been unlinked from unconfirmed list + * before we grabbed pcpu lock in __nf_ct_unconfirmed_destroy(). + * This makes sure its inserted into conntrack table. + */ + synchronize_net(); + + nf_ct_iterate_cleanup(iter, data, 0, 0); } -EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup_net); +EXPORT_SYMBOL_GPL(nf_ct_iterate_destroy); static int kill_all(struct nf_conn *i, void *data) { - return 1; + return net_eq(nf_ct_net(i), data); } void nf_ct_free_hashtable(void *hash, unsigned int size) @@ -1742,7 +1803,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { - nf_ct_iterate_cleanup_net(net, kill_all, NULL, 0, 0); + nf_ct_iterate_cleanup(kill_all, net, 0, 0); if (atomic_read(&net->ct.count) != 0) busy = 1; } -- cgit v1.2.3 From 2b664957c27fe708035b217c908edd1048be355e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 22 May 2017 17:47:51 +0100 Subject: netfilter: nf_tables: select set backend flavour depending on description This patch adds the infrastructure to support several implementations of the same set type. This selection will be based on the set description and the features available for this set. This allow us to select set backend implementation that will result in better performance numbers. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 26 +++++++++++++---- net/netfilter/nf_tables_api.c | 59 ++++++++++++++++++++++++--------------- net/netfilter/nft_set_bitmap.c | 10 +++++-- net/netfilter/nft_set_hash.c | 10 +++++-- net/netfilter/nft_set_rbtree.c | 10 +++++-- 5 files changed, 80 insertions(+), 35 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 8a8bab8d7b15..f27012098846 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -281,6 +281,23 @@ struct nft_set_estimate { enum nft_set_class space; }; +/** + * struct nft_set_type - nf_tables set type + * + * @select_ops: function to select nft_set_ops + * @ops: default ops, used when no select_ops functions is present + * @list: used internally + * @owner: module reference + */ +struct nft_set_type { + const struct nft_set_ops *(*select_ops)(const struct nft_ctx *, + const struct nft_set_desc *desc, + u32 flags); + const struct nft_set_ops *ops; + struct list_head list; + struct module *owner; +}; + struct nft_set_ext; struct nft_expr; @@ -297,8 +314,6 @@ struct nft_expr; * @privsize: function to return size of set private data * @init: initialize private data of new set instance * @destroy: destroy private data of set instance - * @list: nf_tables_set_ops list node - * @owner: module reference * @elemsize: element private size * @features: features supported by the implementation */ @@ -345,14 +360,13 @@ struct nft_set_ops { const struct nlattr * const nla[]); void (*destroy)(const struct nft_set *set); - struct list_head list; - struct module *owner; unsigned int elemsize; u32 features; + const struct nft_set_type *type; }; -int nft_register_set(struct nft_set_ops *ops); -void nft_unregister_set(struct nft_set_ops *ops); +int nft_register_set(struct nft_set_type *type); +void nft_unregister_set(struct nft_set_type *type); /** * struct nft_set - nf_tables set instance diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index da314be0c048..c0b2b19607e1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2377,64 +2377,77 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, * Sets */ -static LIST_HEAD(nf_tables_set_ops); +static LIST_HEAD(nf_tables_set_types); -int nft_register_set(struct nft_set_ops *ops) +int nft_register_set(struct nft_set_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_add_tail_rcu(&ops->list, &nf_tables_set_ops); + list_add_tail_rcu(&type->list, &nf_tables_set_types); nfnl_unlock(NFNL_SUBSYS_NFTABLES); return 0; } EXPORT_SYMBOL_GPL(nft_register_set); -void nft_unregister_set(struct nft_set_ops *ops) +void nft_unregister_set(struct nft_set_type *type) { nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_del_rcu(&ops->list); + list_del_rcu(&type->list); nfnl_unlock(NFNL_SUBSYS_NFTABLES); } EXPORT_SYMBOL_GPL(nft_unregister_set); +#define NFT_SET_FEATURES (NFT_SET_INTERVAL | NFT_SET_MAP | \ + NFT_SET_TIMEOUT | NFT_SET_OBJECT) + +static bool nft_set_ops_candidate(const struct nft_set_ops *ops, u32 flags) +{ + return (flags & ops->features) == (flags & NFT_SET_FEATURES); +} + /* * Select a set implementation based on the data characteristics and the * given policy. The total memory use might not be known if no size is * given, in that case the amount of memory per element is used. */ static const struct nft_set_ops * -nft_select_set_ops(const struct nlattr * const nla[], +nft_select_set_ops(const struct nft_ctx *ctx, + const struct nlattr * const nla[], const struct nft_set_desc *desc, enum nft_set_policies policy) { const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; - u32 features; + const struct nft_set_type *type; + u32 flags = 0; #ifdef CONFIG_MODULES - if (list_empty(&nf_tables_set_ops)) { + if (list_empty(&nf_tables_set_types)) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); request_module("nft-set"); nfnl_lock(NFNL_SUBSYS_NFTABLES); - if (!list_empty(&nf_tables_set_ops)) + if (!list_empty(&nf_tables_set_types)) return ERR_PTR(-EAGAIN); } #endif - features = 0; - if (nla[NFTA_SET_FLAGS] != NULL) { - features = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); - features &= NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_TIMEOUT | - NFT_SET_OBJECT; - } + if (nla[NFTA_SET_FLAGS] != NULL) + flags = ntohl(nla_get_be32(nla[NFTA_SET_FLAGS])); bops = NULL; best.size = ~0; best.lookup = ~0; best.space = ~0; - list_for_each_entry(ops, &nf_tables_set_ops, list) { - if ((ops->features & features) != features) + list_for_each_entry(type, &nf_tables_set_types, list) { + if (!type->select_ops) + ops = type->ops; + else + ops = type->select_ops(ctx, desc, flags); + if (!ops) + continue; + + if (!nft_set_ops_candidate(ops, flags)) continue; - if (!ops->estimate(desc, features, &est)) + if (!ops->estimate(desc, flags, &est)) continue; switch (policy) { @@ -2465,10 +2478,10 @@ nft_select_set_ops(const struct nlattr * const nla[], break; } - if (!try_module_get(ops->owner)) + if (!try_module_get(type->owner)) continue; if (bops != NULL) - module_put(bops->owner); + module_put(bops->type->owner); bops = ops; best = est; @@ -3029,7 +3042,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (!(nlh->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; - ops = nft_select_set_ops(nla, &desc, policy); + ops = nft_select_set_ops(&ctx, nla, &desc, policy); if (IS_ERR(ops)) return PTR_ERR(ops); @@ -3089,14 +3102,14 @@ err3: err2: kfree(set); err1: - module_put(ops->owner); + module_put(ops->type->owner); return err; } static void nft_set_destroy(struct nft_set *set) { set->ops->destroy(set); - module_put(set->ops->owner); + module_put(set->ops->type->owner); kfree(set); } diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index b988162b5b15..87d17691278f 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -278,7 +278,9 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, return true; } +static struct nft_set_type nft_bitmap_type; static struct nft_set_ops nft_bitmap_ops __read_mostly = { + .type = &nft_bitmap_type, .privsize = nft_bitmap_privsize, .elemsize = offsetof(struct nft_bitmap_elem, ext), .estimate = nft_bitmap_estimate, @@ -291,17 +293,21 @@ static struct nft_set_ops nft_bitmap_ops __read_mostly = { .activate = nft_bitmap_activate, .lookup = nft_bitmap_lookup, .walk = nft_bitmap_walk, +}; + +static struct nft_set_type nft_bitmap_type __read_mostly = { + .ops = &nft_bitmap_ops, .owner = THIS_MODULE, }; static int __init nft_bitmap_module_init(void) { - return nft_register_set(&nft_bitmap_ops); + return nft_register_set(&nft_bitmap_type); } static void __exit nft_bitmap_module_exit(void) { - nft_unregister_set(&nft_bitmap_ops); + nft_unregister_set(&nft_bitmap_type); } module_init(nft_bitmap_module_init); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 7c21e3da0d88..4ba0717408d9 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -379,7 +379,9 @@ static bool nft_rhash_estimate(const struct nft_set_desc *desc, u32 features, return true; } +static struct nft_set_type nft_hash_type; static struct nft_set_ops nft_rhash_ops __read_mostly = { + .type = &nft_hash_type, .privsize = nft_rhash_privsize, .elemsize = offsetof(struct nft_rhash_elem, ext), .estimate = nft_rhash_estimate, @@ -394,17 +396,21 @@ static struct nft_set_ops nft_rhash_ops __read_mostly = { .update = nft_rhash_update, .walk = nft_rhash_walk, .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, +}; + +static struct nft_set_type nft_hash_type __read_mostly = { + .ops = &nft_rhash_ops, .owner = THIS_MODULE, }; static int __init nft_hash_module_init(void) { - return nft_register_set(&nft_rhash_ops); + return nft_register_set(&nft_hash_type); } static void __exit nft_hash_module_exit(void) { - nft_unregister_set(&nft_rhash_ops); + nft_unregister_set(&nft_hash_type); } module_init(nft_hash_module_init); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index fbfb3cbb3916..29d41d378339 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -295,7 +295,9 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } +static struct nft_set_type nft_rbtree_type; static struct nft_set_ops nft_rbtree_ops __read_mostly = { + .type = &nft_rbtree_type, .privsize = nft_rbtree_privsize, .elemsize = offsetof(struct nft_rbtree_elem, ext), .estimate = nft_rbtree_estimate, @@ -309,17 +311,21 @@ static struct nft_set_ops nft_rbtree_ops __read_mostly = { .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT, +}; + +static struct nft_set_type nft_rbtree_type __read_mostly = { + .ops = &nft_rbtree_ops, .owner = THIS_MODULE, }; static int __init nft_rbtree_module_init(void) { - return nft_register_set(&nft_rbtree_ops); + return nft_register_set(&nft_rbtree_type); } static void __exit nft_rbtree_module_exit(void) { - nft_unregister_set(&nft_rbtree_ops); + nft_unregister_set(&nft_rbtree_type); } module_init(nft_rbtree_module_init); -- cgit v1.2.3 From 347b408d59e7eadcd09f97eba96fa4c270eb3b23 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 22 May 2017 17:47:54 +0100 Subject: netfilter: nf_tables: pass set description to ->privsize The new non-resizable hashtable variant needs this to calculate the size of the bucket array. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 ++- net/netfilter/nf_tables_api.c | 2 +- net/netfilter/nft_set_bitmap.c | 3 ++- net/netfilter/nft_set_hash.c | 3 ++- net/netfilter/nft_set_rbtree.c | 3 ++- 5 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f27012098846..bd5be0d691d5 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -351,7 +351,8 @@ struct nft_set_ops { struct nft_set *set, struct nft_set_iter *iter); - unsigned int (*privsize)(const struct nlattr * const nla[]); + unsigned int (*privsize)(const struct nlattr * const nla[], + const struct nft_set_desc *desc); bool (*estimate)(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c0b2b19607e1..2969016d8cad 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3052,7 +3052,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, size = 0; if (ops->privsize != NULL) - size = ops->privsize(nla); + size = ops->privsize(nla, &desc); err = -ENOMEM; set = kzalloc(sizeof(*set) + size + udlen, GFP_KERNEL); diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 87d17691278f..734989c40579 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -236,7 +236,8 @@ static inline u32 nft_bitmap_total_size(u32 klen) return sizeof(struct nft_bitmap) + nft_bitmap_size(klen); } -static unsigned int nft_bitmap_privsize(const struct nlattr * const nla[]) +static unsigned int nft_bitmap_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { u32 klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN])); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 4ba0717408d9..455a11ce8cd0 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -321,7 +321,8 @@ schedule: nft_set_gc_interval(set)); } -static unsigned int nft_rhash_privsize(const struct nlattr * const nla[]) +static unsigned int nft_rhash_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { return sizeof(struct nft_rhash); } diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 29d41d378339..491e805d3ca2 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -251,7 +251,8 @@ cont: read_unlock_bh(&priv->lock); } -static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[]) +static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[], + const struct nft_set_desc *desc) { return sizeof(struct nft_rbtree); } -- cgit v1.2.3 From 78055998954b7a3e6c31eb24d1d26f0b63a7ec0d Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 27 May 2017 16:19:26 -0600 Subject: net: ipv4: Add extack message for invalid prefix or length Add extack error message for invalid prefix length and invalid prefix. Example of the latter is a route spec containing 172.16.100.1/24, where the /24 mask means the lower 8-bits should be 0. Amazing how easy that one is to overlook when an EINVAL is returned. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 3 ++- net/ipv4/fib_frontend.c | 7 ++++--- net/ipv4/fib_trie.c | 17 +++++++++++------ 3 files changed, 17 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index dcbfd5dfd25e..3dbfd5e6a347 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -266,7 +266,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); -int fib_table_delete(struct net *, struct fib_table *, struct fib_config *); +int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, + struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb); int fib_table_flush(struct net *net, struct fib_table *table); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 14d2f7bd7c76..715b7967d8ea 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -588,7 +588,8 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) - err = fib_table_delete(net, tb, &cfg); + err = fib_table_delete(net, tb, &cfg, + NULL); else err = -ESRCH; } else { @@ -732,7 +733,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; } - err = fib_table_delete(net, tb, &cfg); + err = fib_table_delete(net, tb, &cfg, extack); errout: return err; } @@ -851,7 +852,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad if (cmd == RTM_NEWROUTE) fib_table_insert(net, tb, &cfg, NULL); else - fib_table_delete(net, tb, &cfg); + fib_table_delete(net, tb, &cfg, NULL); } void fib_add_ifaddr(struct in_ifaddr *ifa) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 9bd46e1e1037..a624d380c81d 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1099,13 +1099,18 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, return 0; } -static bool fib_valid_key_len(u32 key, u8 plen) +static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) { - if (plen > KEYLENGTH) + if (plen > KEYLENGTH) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); return false; + } - if ((plen < KEYLENGTH) && (key << plen)) + if ((plen < KEYLENGTH) && (key << plen)) { + NL_SET_ERR_MSG(extack, + "Invalid prefix for given prefix length"); return false; + } return true; } @@ -1128,7 +1133,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen)) + if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); @@ -1516,7 +1521,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, - struct fib_config *cfg) + struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *fa_to_delete; @@ -1528,7 +1533,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen)) + if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; l = fib_find_node(t, &tp, key); -- cgit v1.2.3 From c255bd681d1a93fff2a2c249d91449cce830ac64 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 27 May 2017 16:19:27 -0600 Subject: net: lwtunnel: Add extack to encap attr validation Pass extack down to lwtunnel_valid_encap_type and lwtunnel_valid_encap_type_attr. Add messages for unknown or unsupported encap types. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/lwtunnel.h | 13 +++++++++---- net/core/lwtunnel.c | 18 +++++++++++++----- net/ipv4/fib_frontend.c | 6 ++++-- net/ipv6/route.c | 4 ++-- 4 files changed, 28 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index ebfe237aad7e..ca6f002774ef 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -107,8 +107,10 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num); -int lwtunnel_valid_encap_type(u16 encap_type); -int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len); +int lwtunnel_valid_encap_type(u16 encap_type, + struct netlink_ext_ack *extack); +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, + struct netlink_ext_ack *extack); int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, @@ -172,11 +174,14 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, return -EOPNOTSUPP; } -static inline int lwtunnel_valid_encap_type(u16 encap_type) +static inline int lwtunnel_valid_encap_type(u16 encap_type, + struct netlink_ext_ack *extack) { + NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel"); return -EOPNOTSUPP; } -static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len) +static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, + struct netlink_ext_ack *extack) { /* return 0 since we are not walking attr looking for * RTA_ENCAP_TYPE attribute on nexthops. diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index cfae3d5fe11f..ab840386a74d 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -126,14 +126,16 @@ int lwtunnel_build_state(u16 encap_type, } EXPORT_SYMBOL(lwtunnel_build_state); -int lwtunnel_valid_encap_type(u16 encap_type) +int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || - encap_type > LWTUNNEL_ENCAP_MAX) + encap_type > LWTUNNEL_ENCAP_MAX) { + NL_SET_ERR_MSG(extack, "Unknown lwt encapsulation type"); return ret; + } rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); @@ -153,11 +155,16 @@ int lwtunnel_valid_encap_type(u16 encap_type) } } #endif - return ops ? 0 : -EOPNOTSUPP; + ret = ops ? 0 : -EOPNOTSUPP; + if (ret < 0) + NL_SET_ERR_MSG(extack, "lwt encapsulation type not supported"); + + return ret; } EXPORT_SYMBOL(lwtunnel_valid_encap_type); -int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining, + struct netlink_ext_ack *extack) { struct rtnexthop *rtnh = (struct rtnexthop *)attr; struct nlattr *nla_entype; @@ -174,7 +181,8 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) if (nla_entype) { encap_type = nla_get_u16(nla_entype); - if (lwtunnel_valid_encap_type(encap_type) != 0) + if (lwtunnel_valid_encap_type(encap_type, + extack) != 0) return -EOPNOTSUPP; } } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 715b7967d8ea..4e678fa892dd 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -685,7 +685,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_MULTIPATH: err = lwtunnel_valid_encap_type_attr(nla_data(attr), - nla_len(attr)); + nla_len(attr), + extack); if (err < 0) goto errout; cfg->fc_mp = nla_data(attr); @@ -702,7 +703,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); - err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type, + extack); if (err < 0) goto errout; break; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2fe84bdc4e60..524a76b5206e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3016,7 +3016,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); err = lwtunnel_valid_encap_type_attr(cfg->fc_mp, - cfg->fc_mp_len); + cfg->fc_mp_len, extack); if (err < 0) goto errout; } @@ -3035,7 +3035,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); - err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; } -- cgit v1.2.3 From 9ae287274817c032a4428fde84d1ab26d6b96761 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 27 May 2017 16:19:28 -0600 Subject: net: add extack arg to lwtunnel build state Pass extack arg down to lwtunnel_build_state and the build_state callbacks. Add messages for failures in lwtunnel_build_state, and add the extarg to nla_parse where possible in the build_state callbacks. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netlink.h | 10 ++++++++++ include/net/lwtunnel.h | 9 ++++++--- net/core/lwt_bpf.c | 5 +++-- net/core/lwtunnel.c | 20 +++++++++++++++++--- net/ipv4/fib_lookup.h | 3 ++- net/ipv4/fib_semantics.c | 20 +++++++++++--------- net/ipv4/fib_trie.c | 2 +- net/ipv4/ip_tunnel_core.c | 11 +++++++---- net/ipv6/ila/ila_lwt.c | 5 +++-- net/ipv6/route.c | 2 +- net/ipv6/seg6_iptunnel.c | 5 +++-- net/mpls/mpls_iptunnel.c | 5 +++-- 12 files changed, 67 insertions(+), 30 deletions(-) (limited to 'include/net') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index a68aad484c69..8664fd26eb5d 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -102,6 +102,16 @@ struct netlink_ext_ack { (extack)->bad_attr = (attr); \ } while (0) +#define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do { \ + static const char __msg[] = (msg); \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (__extack) { \ + __extack->_msg = __msg; \ + __extack->bad_attr = (attr); \ + } \ +} while (0) + extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index ca6f002774ef..7c26863b8cf4 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -35,7 +35,8 @@ struct lwtunnel_state { struct lwtunnel_encap_ops { int (*build_state)(struct nlattr *encap, unsigned int family, const void *cfg, - struct lwtunnel_state **ts); + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack); void (*destroy_state)(struct lwtunnel_state *lws); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*input)(struct sk_buff *skb); @@ -114,7 +115,8 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, - struct lwtunnel_state **lws); + struct lwtunnel_state **lws, + struct netlink_ext_ack *extack); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate); @@ -192,7 +194,8 @@ static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, static inline int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, - struct lwtunnel_state **lws) + struct lwtunnel_state **lws, + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index b3bc0a31af9f..1307731ddfe4 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -240,7 +240,8 @@ static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = { static int bpf_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct nlattr *tb[LWT_BPF_MAX + 1]; struct lwtunnel_state *newts; @@ -250,7 +251,7 @@ 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, NULL); + ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, extack); if (ret < 0) return ret; diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index ab840386a74d..d9cb3532f1dd 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -103,25 +103,39 @@ EXPORT_SYMBOL(lwtunnel_encap_del_ops); int lwtunnel_build_state(u16 encap_type, struct nlattr *encap, unsigned int family, - const void *cfg, struct lwtunnel_state **lws) + const void *cfg, struct lwtunnel_state **lws, + struct netlink_ext_ack *extack) { const struct lwtunnel_encap_ops *ops; + bool found = false; int ret = -EINVAL; if (encap_type == LWTUNNEL_ENCAP_NONE || - encap_type > LWTUNNEL_ENCAP_MAX) + encap_type > LWTUNNEL_ENCAP_MAX) { + NL_SET_ERR_MSG_ATTR(extack, encap, + "Unknown LWT encapsulation type"); return ret; + } ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); if (likely(ops && ops->build_state && try_module_get(ops->owner))) { - ret = ops->build_state(encap, family, cfg, lws); + found = true; + ret = ops->build_state(encap, family, cfg, lws, extack); if (ret) module_put(ops->owner); } rcu_read_unlock(); + /* don't rely on -EOPNOTSUPP to detect match as build_state + * handlers could return it + */ + if (!found) { + NL_SET_ERR_MSG_ATTR(extack, encap, + "LWT encapsulation type not supported"); + } + return ret; } EXPORT_SYMBOL(lwtunnel_build_state); diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 2704e08545da..769ab87ebc4b 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -30,7 +30,8 @@ static inline void fib_alias_accessed(struct fib_alias *fa) void fib_release_info(struct fib_info *); struct fib_info *fib_create_info(struct fib_config *cfg, struct netlink_ext_ack *extack); -int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); +int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, + struct netlink_ext_ack *extack); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index de9484658232..2157dc08c407 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -532,7 +532,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, ret = lwtunnel_build_state(nla_get_u16( nla_entype), nla, AF_INET, cfg, - &lwtstate); + &lwtstate, extack); if (ret) goto errout; nexthop_nh->nh_lwtstate = @@ -614,7 +614,8 @@ static inline void fib_add_weight(struct fib_info *fi, static int fib_encap_match(u16 encap_type, struct nlattr *encap, const struct fib_nh *nh, - const struct fib_config *cfg) + const struct fib_config *cfg, + struct netlink_ext_ack *extack) { struct lwtunnel_state *lwtstate; int ret, result = 0; @@ -622,8 +623,8 @@ static int fib_encap_match(u16 encap_type, if (encap_type == LWTUNNEL_ENCAP_NONE) return 0; - ret = lwtunnel_build_state(encap_type, encap, - AF_INET, cfg, &lwtstate); + ret = lwtunnel_build_state(encap_type, encap, AF_INET, + cfg, &lwtstate, extack); if (!ret) { result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate); lwtstate_free(lwtstate); @@ -632,7 +633,8 @@ static int fib_encap_match(u16 encap_type, return result; } -int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) +int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, + struct netlink_ext_ack *extack) { #ifdef CONFIG_IP_ROUTE_MULTIPATH struct rtnexthop *rtnh; @@ -644,9 +646,9 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) if (cfg->fc_oif || cfg->fc_gw) { if (cfg->fc_encap) { - if (fib_encap_match(cfg->fc_encap_type, - cfg->fc_encap, fi->fib_nh, cfg)) - return 1; + if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap, + fi->fib_nh, cfg, extack)) + return 1; } if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) @@ -1148,7 +1150,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, } err = lwtunnel_build_state(cfg->fc_encap_type, cfg->fc_encap, AF_INET, cfg, - &lwtstate); + &lwtstate, extack); if (err) goto failure; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index a624d380c81d..d56659e97a6e 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1562,7 +1562,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && - fib_nh_match(cfg, fi) == 0) { + fib_nh_match(cfg, fi, extack) == 0) { fa_to_delete = fa; break; } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index baf196eaf1d8..90e11479c725 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -228,14 +228,16 @@ static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { static int ip_tun_build_state(struct nlattr *attr, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ip_tunnel_info *tun_info; struct lwtunnel_state *new_state; struct nlattr *tb[LWTUNNEL_IP_MAX + 1]; int err; - err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, NULL); + err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, + extack); if (err < 0) return err; @@ -325,7 +327,8 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { static int ip6_tun_build_state(struct nlattr *attr, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ip_tunnel_info *tun_info; struct lwtunnel_state *new_state; @@ -333,7 +336,7 @@ static int ip6_tun_build_state(struct nlattr *attr, int err; err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy, - NULL); + extack); if (err < 0) return err; diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index f4a413aba423..0c02a09bc351 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -117,7 +117,8 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { static int ila_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct ila_lwt *ilwt; struct ila_params *p; @@ -146,7 +147,7 @@ static int ila_build_state(struct nlattr *nla, return -EINVAL; } - ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, NULL); + ret = nla_parse_nested(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 524a76b5206e..9d9b5bbea153 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1939,7 +1939,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, err = lwtunnel_build_state(cfg->fc_encap_type, cfg->fc_encap, AF_INET6, cfg, - &lwtstate); + &lwtstate, extack); if (err) goto out; rt->dst.lwtstate = lwtstate_get(lwtstate); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 6a495490d43e..264d772d3c7d 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -326,7 +326,8 @@ drop: static int seg6_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1]; struct seg6_iptunnel_encap *tuninfo; @@ -336,7 +337,7 @@ static int seg6_build_state(struct nlattr *nla, int err; err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla, - seg6_iptunnel_policy, NULL); + seg6_iptunnel_policy, extack); if (err < 0) return err; diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 369c7a23c86c..15e1aa708e50 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -159,7 +159,8 @@ drop: static int mpls_build_state(struct nlattr *nla, unsigned int family, const void *cfg, - struct lwtunnel_state **ts) + struct lwtunnel_state **ts, + struct netlink_ext_ack *extack) { struct mpls_iptunnel_encap *tun_encap_info; struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1]; @@ -168,7 +169,7 @@ static int mpls_build_state(struct nlattr *nla, int ret; ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla, - mpls_iptunnel_policy, NULL); + mpls_iptunnel_policy, extack); if (ret < 0) return ret; -- cgit v1.2.3 From 23c9ee4934e7a79b49151d0f05c24117d69c73fe Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 26 May 2017 18:12:51 -0400 Subject: net: dsa: remove dev arg of dsa_register_switch The current dsa_register_switch function takes a useless struct device pointer argument, which always equals ds->dev. Drivers either call it with ds->dev, or with the same device pointer passed to dsa_switch_alloc, which ends up being assigned to ds->dev. This patch removes the second argument of the dsa_register_switch and _dsa_register_switch functions. Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_common.c | 2 +- drivers/net/dsa/dsa_loop.c | 2 +- drivers/net/dsa/lan9303-core.c | 2 +- drivers/net/dsa/mt7530.c | 2 +- drivers/net/dsa/mv88e6xxx/chip.c | 2 +- drivers/net/dsa/qca8k.c | 2 +- include/net/dsa.h | 2 +- net/dsa/dsa2.c | 10 +++++----- 8 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 6a5648a9cb09..e68d368e20ac 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1989,7 +1989,7 @@ int b53_switch_register(struct b53_device *dev) pr_info("found switch: %s, rev %i\n", dev->name, dev->core_rev); - return dsa_register_switch(dev->ds, dev->ds->dev); + return dsa_register_switch(dev->ds); } EXPORT_SYMBOL(b53_switch_register); diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index 5edf07beb9d2..79e62593ff4e 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -271,7 +271,7 @@ static int dsa_loop_drv_probe(struct mdio_device *mdiodev) dev_set_drvdata(&mdiodev->dev, ds); - return dsa_register_switch(ds, ds->dev); + return dsa_register_switch(ds); } static void dsa_loop_drv_remove(struct mdio_device *mdiodev) diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index c8b2423c8ef7..cd76e61f1fca 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -802,7 +802,7 @@ static int lan9303_register_switch(struct lan9303 *chip) chip->ds->ops = &lan9303_switch_ops; chip->ds->phys_mii_mask = chip->phy_addr_sel_strap ? 0xe : 0x7; - return dsa_register_switch(chip->ds, chip->dev); + return dsa_register_switch(chip->ds); } static void lan9303_probe_reset_gpio(struct lan9303 *chip, diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 4d2f45153ede..25e00d5e0eec 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1080,7 +1080,7 @@ mt7530_probe(struct mdio_device *mdiodev) mutex_init(&priv->reg_mutex); dev_set_drvdata(&mdiodev->dev, priv); - return dsa_register_switch(priv->ds, &mdiodev->dev); + return dsa_register_switch(priv->ds); } static void diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 070e82ac6132..7cf470c3e662 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3884,7 +3884,7 @@ static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip) dev_set_drvdata(dev, ds); - return dsa_register_switch(ds, dev); + return dsa_register_switch(ds); } static void mv88e6xxx_unregister_switch(struct mv88e6xxx_chip *chip) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 0f6a011d8ed1..b3bee7eab45f 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -958,7 +958,7 @@ qca8k_sw_probe(struct mdio_device *mdiodev) mutex_init(&priv->reg_mutex); dev_set_drvdata(&mdiodev->dev, priv); - return dsa_register_switch(priv->ds, &mdiodev->dev); + return dsa_register_switch(priv->ds); } static void diff --git a/include/net/dsa.h b/include/net/dsa.h index c0e567c0c824..d9bd6939229a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -480,7 +480,7 @@ static inline bool netdev_uses_dsa(struct net_device *dev) 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, struct device *dev); +int dsa_register_switch(struct dsa_switch *ds); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 4301f52e4f5a..c0a4576db4a2 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -686,10 +686,10 @@ static struct device_node *dsa_get_ports(struct dsa_switch *ds, return ports; } -static int _dsa_register_switch(struct dsa_switch *ds, struct device *dev) +static int _dsa_register_switch(struct dsa_switch *ds) { - struct dsa_chip_data *pdata = dev->platform_data; - struct device_node *np = dev->of_node; + struct dsa_chip_data *pdata = ds->dev->platform_data; + struct device_node *np = ds->dev->of_node; struct dsa_switch_tree *dst; struct device_node *ports; u32 tree, index; @@ -803,12 +803,12 @@ struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n) } EXPORT_SYMBOL_GPL(dsa_switch_alloc); -int dsa_register_switch(struct dsa_switch *ds, struct device *dev) +int dsa_register_switch(struct dsa_switch *ds) { int err; mutex_lock(&dsa2_mutex); - err = _dsa_register_switch(ds, dev); + err = _dsa_register_switch(ds); mutex_unlock(&dsa2_mutex); return err; -- cgit v1.2.3 From d897a638e98c476c56118d0dcc1bc55450504866 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 31 May 2017 08:06:43 -0700 Subject: sched: add helper for updating statistics on all actions Forgetting to disable preemption around tcf_action_stats_update() seems to be a common mistake. Add a helper function for updating stats on all actions of a filter. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 10 +--------- drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 10 +--------- drivers/net/ethernet/netronome/nfp/nfp_net_offload.c | 11 ++--------- include/net/pkt_cls.h | 19 +++++++++++++++++++ 4 files changed, 23 insertions(+), 27 deletions(-) (limited to 'include/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index d2f90ba2dbc4..7914a32a3036 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1863,9 +1863,7 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, { struct mlx5e_tc_table *tc = &priv->fs.tc; struct mlx5e_tc_flow *flow; - struct tc_action *a; struct mlx5_fc *counter; - LIST_HEAD(actions); u64 bytes; u64 packets; u64 lastuse; @@ -1884,13 +1882,7 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); - preempt_disable(); - - tcf_exts_to_list(f->exts, &actions); - list_for_each_entry(a, &actions, list) - tcf_action_stats_update(a, bytes, packets, lastuse); - - preempt_enable(); + tcf_exts_stats_update(f->exts, bytes, packets, lastuse); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index ed75c6a85bc3..13af8e358847 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -397,8 +397,6 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_acl_ruleset *ruleset; struct mlxsw_sp_acl_rule *rule; - struct tc_action *a; - LIST_HEAD(actions); u64 packets; u64 lastuse; u64 bytes; @@ -419,13 +417,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, if (err) goto err_rule_get_stats; - preempt_disable(); - - tcf_exts_to_list(f->exts, &actions); - list_for_each_entry(a, &actions, list) - tcf_action_stats_update(a, bytes, packets, lastuse); - - preempt_enable(); + tcf_exts_stats_update(f->exts, bytes, packets, lastuse); mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset); return 0; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c index cc823df12c8a..2fa7b67d0c6f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_offload.c @@ -84,8 +84,6 @@ static void nfp_net_bpf_stats_reset(struct nfp_net *nn) static int nfp_net_bpf_stats_update(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) { - struct tc_action *a; - LIST_HEAD(actions); u64 bytes, pkts; pkts = nn->rx_filter.pkts - nn->rx_filter_prev.pkts; @@ -94,13 +92,8 @@ nfp_net_bpf_stats_update(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) nn->rx_filter_prev = nn->rx_filter; - preempt_disable(); - - tcf_exts_to_list(cls_bpf->exts, &actions); - list_for_each_entry(a, &actions, list) - tcf_action_stats_update(a, bytes, pkts, nn->rx_filter_change); - - preempt_enable(); + tcf_exts_stats_update(cls_bpf->exts, + bytes, pkts, nn->rx_filter_change); return 0; } diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index f7762295b7b8..537d0a0ad4c4 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -157,6 +157,25 @@ static inline void tcf_exts_to_list(const struct tcf_exts *exts, #endif } +static inline void +tcf_exts_stats_update(const struct tcf_exts *exts, + u64 bytes, u64 packets, u64 lastuse) +{ +#ifdef CONFIG_NET_CLS_ACT + int i; + + preempt_disable(); + + for (i = 0; i < exts->nr_actions; i++) { + struct tc_action *a = exts->actions[i]; + + tcf_action_stats_update(a, bytes, packets, lastuse); + } + + preempt_enable(); +#endif +} + /** * tcf_exts_exec - execute tc filter extensions * @skb: socket buffer -- cgit v1.2.3 From 8b8010fb7876e816300ddd60fa089e9ceb209f3e Mon Sep 17 00:00:00 2001 From: Woojung Huh Date: Wed, 31 May 2017 20:19:06 +0000 Subject: dsa: add support for Microchip KSZ tail tagging Adding support for the Microchip KSZ switch family tail tagging. Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: Woojung Huh Signed-off-by: David S. Miller --- include/net/dsa.h | 1 + net/dsa/Kconfig | 3 ++ net/dsa/Makefile | 1 + net/dsa/dsa.c | 3 ++ net/dsa/dsa_priv.h | 3 ++ net/dsa/tag_ksz.c | 101 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 112 insertions(+) create mode 100644 net/dsa/tag_ksz.c (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index d9bd6939229a..7de1234ba136 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -31,6 +31,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_BRCM, DSA_TAG_PROTO_DSA, DSA_TAG_PROTO_EDSA, + DSA_TAG_PROTO_KSZ, DSA_TAG_PROTO_LAN9303, DSA_TAG_PROTO_MTK, DSA_TAG_PROTO_QCA, diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 297389b2ab35..cc5f8f971689 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -25,6 +25,9 @@ config NET_DSA_TAG_DSA config NET_DSA_TAG_EDSA bool +config NET_DSA_TAG_KSZ + bool + config NET_DSA_TAG_LAN9303 bool diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 90e5aa6f7d0f..fcce25da937c 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -6,6 +6,7 @@ dsa_core-y += dsa.o dsa2.o legacy.o port.o slave.o switch.o dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o +dsa_core-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o dsa_core-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o dsa_core-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 3288a80d4d6c..402459e73f33 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -49,6 +49,9 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { #ifdef CONFIG_NET_DSA_TAG_EDSA [DSA_TAG_PROTO_EDSA] = &edsa_netdev_ops, #endif +#ifdef CONFIG_NET_DSA_TAG_KSZ + [DSA_TAG_PROTO_KSZ] = &ksz_netdev_ops, +#endif #ifdef CONFIG_NET_DSA_TAG_LAN9303 [DSA_TAG_PROTO_LAN9303] = &lan9303_netdev_ops, #endif diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index c1d4180651af..7459d5735d8b 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -167,6 +167,9 @@ extern const struct dsa_device_ops dsa_netdev_ops; /* tag_edsa.c */ extern const struct dsa_device_ops edsa_netdev_ops; +/* tag_ksz.c */ +extern const struct dsa_device_ops ksz_netdev_ops; + /* tag_lan9303.c */ extern const struct dsa_device_ops lan9303_netdev_ops; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c new file mode 100644 index 000000000000..0b08a40b493a --- /dev/null +++ b/net/dsa/tag_ksz.c @@ -0,0 +1,101 @@ +/* + * net/dsa/tag_ksz.c - Microchip KSZ Switch tag format handling + * Copyright (c) 2017 Microchip Technology + * + * 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 +#include +#include +#include +#include "dsa_priv.h" + +/* For Ingress (Host -> KSZ), 2 bytes are added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * tag0 : Prioritization (not used now) + * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x10=port5) + * + * For Egress (KSZ -> Host), 1 byte is added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * tag0 : zero-based value represents port + * (eg, 0x00=port1, 0x02=port3, 0x06=port7) + */ + +#define KSZ_INGRESS_TAG_LEN 2 +#define KSZ_EGRESS_TAG_LEN 1 + +static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct sk_buff *nskb; + int padlen; + u8 *tag; + + padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len; + + if (skb_tailroom(skb) >= padlen + KSZ_INGRESS_TAG_LEN) { + nskb = skb; + } else { + nskb = alloc_skb(NET_IP_ALIGN + skb->len + + padlen + KSZ_INGRESS_TAG_LEN, GFP_ATOMIC); + if (!nskb) { + kfree_skb(skb); + return NULL; + } + skb_reserve(nskb, NET_IP_ALIGN); + + skb_reset_mac_header(nskb); + skb_set_network_header(nskb, + skb_network_header(skb) - skb->head); + skb_set_transport_header(nskb, + skb_transport_header(skb) - skb->head); + skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len)); + kfree_skb(skb); + } + + /* skb is freed when it fails */ + if (skb_put_padto(nskb, nskb->len + padlen)) + return NULL; + + tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); + tag[0] = 0; + tag[1] = 1 << p->dp->index; /* destination port */ + + return nskb; +} + +struct sk_buff *ksz_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_switch *ds; + u8 *tag; + int source_port; + + ds = dst->cpu_dp->ds; + + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + + source_port = tag[0] & 7; + if (source_port >= ds->num_ports || !ds->ports[source_port].netdev) + return NULL; + + pskb_trim_rcsum(skb, skb->len - KSZ_EGRESS_TAG_LEN); + + skb->dev = ds->ports[source_port].netdev; + + return skb; +} + +const struct dsa_device_ops ksz_netdev_ops = { + .xmit = ksz_xmit, + .rcv = ksz_rcv, +}; -- cgit v1.2.3 From 73a7ece8f70c955464080e434b5324bcdfdcb1b1 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 1 Jun 2017 16:07:11 -0400 Subject: net: dsa: comment hot path requirements The DSA layer uses inline helpers and copy of the tagging functions for faster access in hot path. Add comments to detail that. Reviewed-by: Florian Fainelli Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 3 +++ net/dsa/dsa_priv.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 7de1234ba136..18ca0a935c96 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -127,6 +127,8 @@ struct dsa_switch_tree { * protocol to use. */ struct net_device *master_netdev; + + /* Copy of tag_ops->rcv for faster access in hot path */ struct sk_buff * (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, @@ -465,6 +467,7 @@ struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev); struct net_device *dsa_dev_to_net_device(struct device *dev); +/* Keep inline for faster access in hot path */ static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) { return dst->rcv != NULL; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 7459d5735d8b..db2a7b9edfb8 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -73,6 +73,7 @@ struct dsa_device_ops { }; struct dsa_slave_priv { + /* Copy of dp->ds->dst->tag_ops->xmit for faster access in hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); -- cgit v1.2.3 From 717ffbfb28ac2b53d3140b2a7dfd345e1569b3a5 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 1 Jun 2017 16:07:13 -0400 Subject: net: dsa: remove dsa_uses_tagged_protocol Since dev->dsa_ptr is a pointer to a dsa_switch_tree, there is no need to have another inline helper just to check rcv. Remove dsa_uses_tagged_protocol and check dsa_ptr && dsa_ptr->rcv together at the same time. Reviewed-by: Florian Fainelli Signed-off-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 18ca0a935c96..448d8bc77707 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -468,16 +468,10 @@ struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev); struct net_device *dsa_dev_to_net_device(struct device *dev); /* Keep inline for faster access in hot path */ -static inline bool dsa_uses_tagged_protocol(struct dsa_switch_tree *dst) -{ - return dst->rcv != NULL; -} - static inline bool netdev_uses_dsa(struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) - if (dev->dsa_ptr != NULL) - return dsa_uses_tagged_protocol(dev->dsa_ptr); + return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } -- cgit v1.2.3 From cee360ab4dd66fc1de33a5fa1cb418fa21c27ce3 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 31 May 2017 16:36:31 +0800 Subject: sctp: define the member stream as an object instead of pointer in asoc As Marcelo's suggestion, stream is a fixed size member of asoc and would not grow with more streams. To avoid an allocation for it, this patch is to define it as an object instead of pointer and update the places using it, also create sctp_stream_update() called in sctp_assoc_update() to migrate the stream info from one stream to another. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 3 +- net/sctp/associola.c | 13 ++++----- net/sctp/chunk.c | 4 +-- net/sctp/outqueue.c | 10 +++---- net/sctp/proc.c | 4 +-- net/sctp/sm_make_chunk.c | 2 +- net/sctp/sm_statefuns.c | 8 +++--- net/sctp/socket.c | 14 +++++----- net/sctp/stream.c | 68 ++++++++++++++++++++++------------------------ net/sctp/ulpqueue.c | 8 +++--- 10 files changed, 65 insertions(+), 69 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index a8b38e123f97..c8dbf410c4f5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -381,6 +381,7 @@ int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp); int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp); void sctp_stream_free(struct sctp_stream *stream); void sctp_stream_clear(struct sctp_stream *stream); +void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new); /* What is the current SSN number for this stream? */ #define sctp_ssn_peek(stream, type, sid) \ @@ -1750,7 +1751,7 @@ struct sctp_association { __u32 default_rcv_context; /* Stream arrays */ - struct sctp_stream *stream; + struct sctp_stream stream; /* All outbound chunks go through this structure. */ struct sctp_outq outqueue; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 95238284c422..6625b15ab81a 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -291,7 +291,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a return asoc; stream_free: - sctp_stream_free(asoc->stream); + sctp_stream_free(&asoc->stream); fail_init: sock_put(asoc->base.sk); sctp_endpoint_put(asoc->ep); @@ -365,7 +365,7 @@ void sctp_association_free(struct sctp_association *asoc) sctp_tsnmap_free(&asoc->peer.tsn_map); /* Free stream information. */ - sctp_stream_free(asoc->stream); + sctp_stream_free(&asoc->stream); if (asoc->strreset_chunk) sctp_chunk_free(asoc->strreset_chunk); @@ -1151,7 +1151,7 @@ void sctp_assoc_update(struct sctp_association *asoc, /* Reinitialize SSN for both local streams * and peer's streams. */ - sctp_stream_clear(asoc->stream); + sctp_stream_clear(&asoc->stream); /* Flush the ULP reassembly and ordered queue. * Any data there will now be stale and will @@ -1177,11 +1177,8 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point; - if (sctp_state(asoc, COOKIE_WAIT)) { - sctp_stream_free(asoc->stream); - asoc->stream = new->stream; - new->stream = NULL; - } + if (sctp_state(asoc, COOKIE_WAIT)) + sctp_stream_update(&asoc->stream, &new->stream); if (!asoc->assoc_id) { /* get a new association id since we don't have one diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 697721a7a3f1..81466f6442e8 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -307,7 +307,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = - &chunk->asoc->stream->out[chunk->sinfo.sinfo_stream]; + &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; @@ -320,7 +320,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk) } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { struct sctp_stream_out *streamout = - &chunk->asoc->stream->out[chunk->sinfo.sinfo_stream]; + &chunk->asoc->stream.out[chunk->sinfo.sinfo_stream]; chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; streamout->abandoned_sent[SCTP_PR_INDEX(RTX)]++; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index fe4c3d462f6e..20299df163b9 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -363,7 +363,7 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc, sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); - streamout = &asoc->stream->out[chk->sinfo.sinfo_stream]; + streamout = &asoc->stream.out[chk->sinfo.sinfo_stream]; asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; @@ -400,9 +400,9 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, q->out_qlen -= chk->skb->len; asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; - if (chk->sinfo.sinfo_stream < asoc->stream->outcnt) { + if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { struct sctp_stream_out *streamout = - &asoc->stream->out[chk->sinfo.sinfo_stream]; + &asoc->stream.out[chk->sinfo.sinfo_stream]; streamout->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; } @@ -1036,7 +1036,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) /* RFC 2960 6.5 Every DATA chunk MUST carry a valid * stream identifier. */ - if (chunk->sinfo.sinfo_stream >= asoc->stream->outcnt) { + if (chunk->sinfo.sinfo_stream >= asoc->stream.outcnt) { /* Mark as failed send. */ sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM); @@ -1054,7 +1054,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) continue; } - if (asoc->stream->out[sid].state == SCTP_STREAM_CLOSED) { + if (asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) { sctp_outq_head_data(q, chunk); goto sctp_flush_out; } diff --git a/net/sctp/proc.c b/net/sctp/proc.c index a0b29d43627f..5a27d0f03df5 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -361,8 +361,8 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) sctp_seq_dump_remote_addrs(seq, assoc); seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d " "%8d %8d %8d %8d", - assoc->hbinterval, assoc->stream->incnt, - assoc->stream->outcnt, assoc->max_retrans, + assoc->hbinterval, assoc->stream.incnt, + assoc->stream.outcnt, assoc->max_retrans, assoc->init_retries, assoc->shutdown_retries, assoc->rtx_data_chunks, atomic_read(&sk->sk_wmem_alloc), diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 92e332e17391..244181413bca 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1544,7 +1544,7 @@ void sctp_chunk_assign_ssn(struct sctp_chunk *chunk) /* All fragments will be on the same stream */ sid = ntohs(chunk->subh.data_hdr->stream); - stream = chunk->asoc->stream; + stream = &chunk->asoc->stream; /* Now assign the sequence number to the entire message. * All fragments must have the same stream sequence number. diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index f863b5573e42..df73190da761 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -3958,7 +3958,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn(struct net *net, /* Silently discard the chunk if stream-id is not valid */ sctp_walk_fwdtsn(skip, chunk) { - if (ntohs(skip->stream) >= asoc->stream->incnt) + if (ntohs(skip->stream) >= asoc->stream.incnt) goto discard_noforce; } @@ -4029,7 +4029,7 @@ sctp_disposition_t sctp_sf_eat_fwd_tsn_fast( /* Silently discard the chunk if stream-id is not valid */ sctp_walk_fwdtsn(skip, chunk) { - if (ntohs(skip->stream) >= asoc->stream->incnt) + if (ntohs(skip->stream) >= asoc->stream.incnt) goto gen_shutdown; } @@ -6365,7 +6365,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * and discard the DATA chunk. */ sid = ntohs(data_hdr->stream); - if (sid >= asoc->stream->incnt) { + if (sid >= asoc->stream.incnt) { /* Mark tsn as received even though we drop it */ sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn)); @@ -6387,7 +6387,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * and is invalid. */ ssn = ntohs(data_hdr->ssn); - if (ordered && SSN_lt(ssn, sctp_ssn_peek(asoc->stream, in, sid))) + if (ordered && SSN_lt(ssn, sctp_ssn_peek(&asoc->stream, in, sid))) return SCTP_IERROR_PROTO_VIOLATION; /* Send the data up to the user. Note: Schedule the diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f16c8d97b7f3..0822046e4f3f 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1920,7 +1920,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) } /* Check for invalid stream. */ - if (sinfo->sinfo_stream >= asoc->stream->outcnt) { + if (sinfo->sinfo_stream >= asoc->stream.outcnt) { err = -EINVAL; goto out_free; } @@ -4497,8 +4497,8 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, info->sctpi_rwnd = asoc->a_rwnd; info->sctpi_unackdata = asoc->unack_data; info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); - info->sctpi_instrms = asoc->stream->incnt; - info->sctpi_outstrms = asoc->stream->outcnt; + info->sctpi_instrms = asoc->stream.incnt; + info->sctpi_outstrms = asoc->stream.outcnt; list_for_each(pos, &asoc->base.inqueue.in_chunk_list) info->sctpi_inqueue++; list_for_each(pos, &asoc->outqueue.out_chunk_list) @@ -4727,8 +4727,8 @@ static int sctp_getsockopt_sctp_status(struct sock *sk, int len, status.sstat_unackdata = asoc->unack_data; status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map); - status.sstat_instrms = asoc->stream->incnt; - status.sstat_outstrms = asoc->stream->outcnt; + status.sstat_instrms = asoc->stream.incnt; + status.sstat_outstrms = asoc->stream.outcnt; status.sstat_fragmentation_point = asoc->frag_point; status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc); memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr, @@ -6600,10 +6600,10 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); - if (!asoc || params.sprstat_sid >= asoc->stream->outcnt) + if (!asoc || params.sprstat_sid >= asoc->stream.outcnt) goto out; - streamout = &asoc->stream->out[params.sprstat_sid]; + streamout = &asoc->stream.out[params.sprstat_sid]; if (policy == SCTP_PR_SCTP_NONE) { params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index dda53a293986..af6b49850344 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -37,30 +37,23 @@ int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp) { - struct sctp_stream *stream; + struct sctp_stream *stream = &asoc->stream; int i; - stream = kzalloc(sizeof(*stream), gfp); - if (!stream) - return -ENOMEM; - stream->outcnt = asoc->c.sinit_num_ostreams; stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); - if (!stream->out) { - kfree(stream); + if (!stream->out) return -ENOMEM; - } + for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; - asoc->stream = stream; - return 0; } int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp) { - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; int i; /* Initial stream->out size may be very big, so free it and alloc @@ -70,7 +63,7 @@ int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp) stream->outcnt = asoc->c.sinit_num_ostreams; stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); if (!stream->out) - goto nomem; + return -ENOMEM; for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; @@ -79,26 +72,17 @@ int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp) stream->in = kcalloc(stream->incnt, sizeof(*stream->in), gfp); if (!stream->in) { kfree(stream->out); - goto nomem; + stream->out = NULL; + return -ENOMEM; } return 0; - -nomem: - asoc->stream = NULL; - kfree(stream); - - return -ENOMEM; } void sctp_stream_free(struct sctp_stream *stream) { - if (unlikely(!stream)) - return; - kfree(stream->out); kfree(stream->in); - kfree(stream); } void sctp_stream_clear(struct sctp_stream *stream) @@ -112,6 +96,19 @@ void sctp_stream_clear(struct sctp_stream *stream) stream->in[i].ssn = 0; } +void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) +{ + sctp_stream_free(stream); + + stream->out = new->out; + stream->in = new->in; + stream->outcnt = new->outcnt; + stream->incnt = new->incnt; + + new->out = NULL; + new->in = NULL; +} + static int sctp_send_reconf(struct sctp_association *asoc, struct sctp_chunk *chunk) { @@ -128,7 +125,7 @@ static int sctp_send_reconf(struct sctp_association *asoc, int sctp_send_reset_streams(struct sctp_association *asoc, struct sctp_reset_streams *params) { - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u16 i, str_nums, *str_list; struct sctp_chunk *chunk; int retval = -EINVAL; @@ -214,6 +211,7 @@ out: int sctp_send_reset_assoc(struct sctp_association *asoc) { + struct sctp_stream *stream = &asoc->stream; struct sctp_chunk *chunk = NULL; int retval; __u16 i; @@ -230,8 +228,8 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) return -ENOMEM; /* Block further xmit of data until this request is completed */ - for (i = 0; i < asoc->stream->outcnt; i++) - asoc->stream->out[i].state = SCTP_STREAM_CLOSED; + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_CLOSED; asoc->strreset_chunk = chunk; sctp_chunk_hold(asoc->strreset_chunk); @@ -241,8 +239,8 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) sctp_chunk_put(asoc->strreset_chunk); asoc->strreset_chunk = NULL; - for (i = 0; i < asoc->stream->outcnt; i++) - asoc->stream->out[i].state = SCTP_STREAM_OPEN; + for (i = 0; i < stream->outcnt; i++) + stream->out[i].state = SCTP_STREAM_OPEN; return retval; } @@ -255,7 +253,7 @@ int sctp_send_reset_assoc(struct sctp_association *asoc) int sctp_send_add_streams(struct sctp_association *asoc, struct sctp_add_streams *params) { - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; struct sctp_chunk *chunk = NULL; int retval = -ENOMEM; __u32 outcnt, incnt; @@ -357,7 +355,7 @@ struct sctp_chunk *sctp_process_strreset_outreq( struct sctp_ulpevent **evp) { struct sctp_strreset_outreq *outreq = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u16 i, nums, flags = 0, *str_p = NULL; __u32 result = SCTP_STRRESET_DENIED; __u32 request_seq; @@ -449,7 +447,7 @@ struct sctp_chunk *sctp_process_strreset_inreq( struct sctp_ulpevent **evp) { struct sctp_strreset_inreq *inreq = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; struct sctp_chunk *chunk = NULL; __u16 i, nums, *str_p; @@ -523,7 +521,7 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( { __u32 init_tsn = 0, next_tsn = 0, max_tsn_seen; struct sctp_strreset_tsnreq *tsnreq = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; __u32 request_seq; __u16 i; @@ -612,7 +610,7 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( struct sctp_ulpevent **evp) { struct sctp_strreset_addstrm *addstrm = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; struct sctp_stream_in *streamin; __u32 request_seq, incnt; @@ -687,7 +685,7 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( struct sctp_ulpevent **evp) { struct sctp_strreset_addstrm *addstrm = param.v; - struct sctp_stream *stream = asoc->stream; + struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; struct sctp_stream_out *streamout; struct sctp_chunk *chunk = NULL; @@ -758,8 +756,8 @@ struct sctp_chunk *sctp_process_strreset_resp( union sctp_params param, struct sctp_ulpevent **evp) { + struct sctp_stream *stream = &asoc->stream; struct sctp_strreset_resp *resp = param.v; - struct sctp_stream *stream = asoc->stream; struct sctp_transport *t; __u16 i, nums, flags = 0; sctp_paramhdr_t *req; diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index aa3624d50278..25f7e4140566 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -764,7 +764,7 @@ static void sctp_ulpq_retrieve_ordered(struct sctp_ulpq *ulpq, __u16 sid, csid, cssn; sid = event->stream; - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; event_list = (struct sk_buff_head *) sctp_event2skb(event)->prev; @@ -858,7 +858,7 @@ static struct sctp_ulpevent *sctp_ulpq_order(struct sctp_ulpq *ulpq, /* Note: The stream ID must be verified before this routine. */ sid = event->stream; ssn = event->ssn; - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; /* Is this the expected SSN for this stream ID? */ if (ssn != sctp_ssn_peek(stream, in, sid)) { @@ -893,7 +893,7 @@ static void sctp_ulpq_reap_ordered(struct sctp_ulpq *ulpq, __u16 sid) struct sk_buff_head *lobby = &ulpq->lobby; __u16 csid, cssn; - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; /* We are holding the chunks by stream, by SSN. */ skb_queue_head_init(&temp); @@ -958,7 +958,7 @@ void sctp_ulpq_skip(struct sctp_ulpq *ulpq, __u16 sid, __u16 ssn) struct sctp_stream *stream; /* Note: The stream ID must be verified before this routine. */ - stream = ulpq->asoc->stream; + stream = &ulpq->asoc->stream; /* Is this an old SSN? If so ignore. */ if (SSN_lt(ssn, sctp_ssn_peek(stream, in, sid))) -- cgit v1.2.3 From ff356414dc006170153c79434eb81d130c03beec Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 31 May 2017 16:36:32 +0800 Subject: sctp: merge sctp_stream_new and sctp_stream_init Since last patch, sctp doesn't need to alloc memory for asoc->stream any more. sctp_stream_new and sctp_stream_init both are used to alloc memory for stream.in or stream.out, and their names are also confusing. This patch is to merge them into sctp_stream_init, and only pass stream and streamcnt parameters into it, instead of the whole asoc. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 4 ++-- net/sctp/associola.c | 3 ++- net/sctp/sm_make_chunk.c | 3 ++- net/sctp/stream.c | 33 +++++++++++---------------------- 4 files changed, 17 insertions(+), 26 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index c8dbf410c4f5..5051317162df 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -377,8 +377,8 @@ typedef struct sctp_sender_hb_info { __u64 hb_nonce; } sctp_sender_hb_info_t; -int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp); -int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp); +int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, + gfp_t gfp); void sctp_stream_free(struct sctp_stream *stream); void sctp_stream_clear(struct sctp_stream *stream); void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 6625b15ab81a..288c5e0cda5d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -246,7 +246,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a if (!sctp_ulpq_init(&asoc->ulpq, asoc)) goto fail_init; - if (sctp_stream_new(asoc, gfp)) + if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, + 0, gfp)) goto fail_init; /* Assume that peer would support both address types unless we are diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 244181413bca..bd439edf2d8a 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2454,7 +2454,8 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, * stream sequence number shall be set to 0. */ - if (sctp_stream_init(asoc, gfp)) + if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, + asoc->c.sinit_max_instreams, gfp)) goto clean_up; if (!asoc->temp && sctp_assoc_set_id(asoc, gfp)) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index af6b49850344..82e6d40052a8 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -35,47 +35,36 @@ #include #include -int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp) +int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, + gfp_t gfp) { - struct sctp_stream *stream = &asoc->stream; - int i; - - stream->outcnt = asoc->c.sinit_num_ostreams; - stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); - if (!stream->out) - return -ENOMEM; - - for (i = 0; i < stream->outcnt; i++) - stream->out[i].state = SCTP_STREAM_OPEN; - - return 0; -} - -int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp) -{ - struct sctp_stream *stream = &asoc->stream; int i; /* Initial stream->out size may be very big, so free it and alloc * a new one with new outcnt to save memory. */ kfree(stream->out); - stream->outcnt = asoc->c.sinit_num_ostreams; - stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp); + + stream->out = kcalloc(outcnt, sizeof(*stream->out), gfp); if (!stream->out) return -ENOMEM; + stream->outcnt = outcnt; for (i = 0; i < stream->outcnt; i++) stream->out[i].state = SCTP_STREAM_OPEN; - stream->incnt = asoc->c.sinit_max_instreams; - stream->in = kcalloc(stream->incnt, sizeof(*stream->in), gfp); + if (!incnt) + return 0; + + stream->in = kcalloc(incnt, sizeof(*stream->in), gfp); if (!stream->in) { kfree(stream->out); stream->out = NULL; return -ENOMEM; } + stream->incnt = incnt; + return 0; } -- cgit v1.2.3 From 518d8a2e9bad83c6040eccebc3d1f7388fc034e7 Mon Sep 17 00:00:00 2001 From: Or Gerlitz Date: Thu, 1 Jun 2017 21:37:37 +0300 Subject: net/flow_dissector: add support for dissection of misc ip header fields Add support for dissection of ip tos and ttl and ipv6 traffic-class and hoplimit. Both are dissected into the same struct. Uses similar call to ip dissection function as with tcp, arp and others. Signed-off-by: Or Gerlitz Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/flow_dissector.h | 11 +++++++++++ net/core/flow_dissector.c | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include/net') diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index efe34eec61dc..e2663e900b0a 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -165,6 +165,16 @@ struct flow_dissector_key_tcp { __be16 flags; }; +/** + * struct flow_dissector_key_ip: + * @tos: tos + * @ttl: ttl + */ +struct flow_dissector_key_ip { + __u8 tos; + __u8 ttl; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -186,6 +196,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ + FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_MAX, }; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 5a45943081f5..fc5fc4594c90 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -367,6 +367,40 @@ __skb_flow_dissect_tcp(const struct sk_buff *skb, key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); } +static void +__skb_flow_dissect_ipv4(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, const struct iphdr *iph) +{ + struct flow_dissector_key_ip *key_ip; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) + return; + + key_ip = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IP, + target_container); + key_ip->tos = iph->tos; + key_ip->ttl = iph->ttl; +} + +static void +__skb_flow_dissect_ipv6(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, const struct ipv6hdr *iph) +{ + struct flow_dissector_key_ip *key_ip; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) + return; + + key_ip = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IP, + target_container); + key_ip->tos = ipv6_get_dsfield(iph); + key_ip->ttl = iph->hop_limit; +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -469,6 +503,9 @@ ip: } } + __skb_flow_dissect_ipv4(skb, flow_dissector, + target_container, data, iph); + if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) goto out_good; @@ -514,6 +551,9 @@ ipv6: goto out_good; } + __skb_flow_dissect_ipv6(skb, flow_dissector, + target_container, data, iph); + if (flags & FLOW_DISSECTOR_F_STOP_AT_L3) goto out_good; -- cgit v1.2.3 From 14be36c2c96cd18cfa036f230b57ea78d82a303f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 2 Jun 2017 12:31:23 -0700 Subject: net: dsa: Initialize all CPU and enabled ports masks in dsa_ds_parse() There was no reason for duplicating the code that initializes ds->enabled_port_mask in both dsa_parse_ports_dn() and dsa_parse_ports(), instead move this to dsa_ds_parse() which is early enough before ops->setup() has run. While at it, we can now make dsa_is_cpu_port() check ds->cpu_port_mask which is a step towards being multi-CPU port capable. Signed-off-by: Florian Fainelli Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- include/net/dsa.h | 2 +- net/dsa/dsa2.c | 33 +++++++++++++++------------------ 2 files changed, 16 insertions(+), 19 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 448d8bc77707..2effb0af9d7c 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -254,7 +254,7 @@ struct dsa_switch { static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { - return ds->dst->cpu_dp == &ds->ports[p]; + return !!(ds->cpu_port_mask & (1 << p)); } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 067daec644c1..cd13bb54a30c 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -250,8 +250,6 @@ static int dsa_cpu_port_apply(struct dsa_port *port) return err; } - ds->cpu_port_mask |= BIT(port->index); - memset(&port->devlink_port, 0, sizeof(port->devlink_port)); err = devlink_port_register(ds->devlink, &port->devlink_port, port->index); @@ -522,6 +520,12 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, dst->rcv = dst->tag_ops->rcv; + /* Initialize cpu_port_mask now for drv->setup() + * to have access to a correct value, just like what + * net/dsa/dsa.c::dsa_switch_setup_one does. + */ + ds->cpu_port_mask |= BIT(index); + return 0; } @@ -533,14 +537,22 @@ static int dsa_ds_parse(struct dsa_switch_tree *dst, struct dsa_switch *ds) for (index = 0; index < ds->num_ports; index++) { port = &ds->ports[index]; - if (!dsa_port_is_valid(port)) + if (!dsa_port_is_valid(port) || + dsa_port_is_dsa(port)) continue; if (dsa_port_is_cpu(port)) { err = dsa_cpu_parse(port, index, dst, ds); if (err) return err; + } else { + /* Initialize enabled_port_mask now for drv->setup() + * to have access to a correct value, just like what + * net/dsa/dsa.c::dsa_switch_setup_one does. + */ + ds->enabled_port_mask |= BIT(index); } + } pr_info("DSA: switch %d %d parsed\n", dst->tree, ds->index); @@ -589,13 +601,6 @@ static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds) return -EINVAL; ds->ports[reg].dn = port; - - /* Initialize enabled_port_mask now for ops->setup() - * to have access to a correct value, just like what - * net/dsa/dsa.c::dsa_switch_setup_one does. - */ - if (!dsa_port_is_cpu(&ds->ports[reg])) - ds->enabled_port_mask |= 1 << reg; } return 0; @@ -611,14 +616,6 @@ static int dsa_parse_ports(struct dsa_chip_data *cd, struct dsa_switch *ds) continue; ds->ports[i].name = cd->port_names[i]; - - /* Initialize enabled_port_mask now for drv->setup() - * to have access to a correct value, just like what - * net/dsa/dsa.c::dsa_switch_setup_one does. - */ - if (!dsa_port_is_cpu(&ds->ports[i])) - ds->enabled_port_mask |= 1 << i; - valid_name_found = true; } -- cgit v1.2.3 From 5071034e4af709d6783b7d105dc296a5cc84739b Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Fri, 2 Jun 2017 09:01:49 -0700 Subject: neigh: Really delete an arp/neigh entry on "ip neigh delete" or "arp -d" The command # arp -s 62.2.0.1 a:b:c:d:e:f dev eth2 adds an entry like the following (listed by "arp -an") ? (62.2.0.1) at 0a:0b:0c:0d:0e:0f [ether] PERM on eth2 but the symmetric deletion command # arp -i eth2 -d 62.2.0.1 does not remove the PERM entry from the table, and instead leaves behind ? (62.2.0.1) at on eth2 The reason is that there is a refcnt of 1 for the arp_tbl itself (neigh_alloc starts off the entry with a refcnt of 1), thus the neigh_release() call from arp_invalidate() will (at best) just decrement the ref to 1, but will never actually free it from the table. To fix this, we need to do something like neigh_forced_gc: if the refcnt is 1 (i.e., on the table's ref), remove the entry from the table and free it. This patch refactors and shares common code between neigh_forced_gc and the newly added neigh_remove_one. A similar issue exists for IPv6 Neighbor Cache entries, and is fixed in a similar manner by this patch. Signed-off-by: Sowmini Varadhan Reviewed-by: Julian Anastasov Signed-off-by: David S. Miller --- include/net/neighbour.h | 1 + net/core/neighbour.c | 60 ++++++++++++++++++++++++++++++++++++++++--------- net/ipv4/arp.c | 4 ++++ 3 files changed, 54 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e4dd3a214034..639b67564a7d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -317,6 +317,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb); int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); +bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index d274f81fcc2c..dadb5eef91c3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -118,6 +118,50 @@ unsigned long neigh_rand_reach_time(unsigned long base) EXPORT_SYMBOL(neigh_rand_reach_time); +static bool neigh_del(struct neighbour *n, __u8 state, + struct neighbour __rcu **np, struct neigh_table *tbl) +{ + bool retval = false; + + write_lock(&n->lock); + if (atomic_read(&n->refcnt) == 1 && !(n->nud_state & state)) { + struct neighbour *neigh; + + neigh = rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock)); + rcu_assign_pointer(*np, neigh); + n->dead = 1; + retval = true; + } + write_unlock(&n->lock); + if (retval) + neigh_cleanup_and_release(n); + return retval; +} + +bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl) +{ + struct neigh_hash_table *nht; + void *pkey = ndel->primary_key; + u32 hash_val; + struct neighbour *n; + struct neighbour __rcu **np; + + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + hash_val = tbl->hash(pkey, ndel->dev, nht->hash_rnd); + hash_val = hash_val >> (32 - nht->hash_shift); + + np = &nht->hash_buckets[hash_val]; + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock)))) { + if (n == ndel) + return neigh_del(n, 0, np, tbl); + np = &n->next; + } + return false; +} + static int neigh_forced_gc(struct neigh_table *tbl) { int shrunk = 0; @@ -140,19 +184,10 @@ static int neigh_forced_gc(struct neigh_table *tbl) * - nobody refers to it. * - it is not permanent */ - write_lock(&n->lock); - if (atomic_read(&n->refcnt) == 1 && - !(n->nud_state & NUD_PERMANENT)) { - rcu_assign_pointer(*np, - rcu_dereference_protected(n->next, - lockdep_is_held(&tbl->lock))); - n->dead = 1; - shrunk = 1; - write_unlock(&n->lock); - neigh_cleanup_and_release(n); + if (neigh_del(n, NUD_PERMANENT, np, tbl)) { + shrunk = 1; continue; } - write_unlock(&n->lock); np = &n->next; } } @@ -1649,7 +1684,10 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, NETLINK_CB(skb).portid); + write_lock_bh(&tbl->lock); neigh_release(neigh); + neigh_remove_one(neigh, tbl); + write_unlock_bh(&tbl->lock); out: return err; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index e9f3386a528b..a651c53260ec 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1113,13 +1113,17 @@ static int arp_invalidate(struct net_device *dev, __be32 ip) { struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); int err = -ENXIO; + struct neigh_table *tbl = &arp_tbl; if (neigh) { if (neigh->nud_state & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN, 0); + write_lock_bh(&tbl->lock); neigh_release(neigh); + neigh_remove_one(neigh, tbl); + write_unlock_bh(&tbl->lock); } return err; -- cgit v1.2.3 From 4e2ec43654f240a3731612764850140f669d1b4b Mon Sep 17 00:00:00 2001 From: "Rosen, Rami" Date: Sun, 4 Jun 2017 15:20:01 +0300 Subject: genetlink: remove ops_list from genetlink header. commit d91824c08fbc ("genetlink: register family ops as array") removed the ops_list member from both genl_family and genl_ops; while the documentation of genl_family was updated accordingly by this patch, ops_list remained in the documentation of the genl_ops object. This patch fixes it by removing ops_list from genl_ops documentation. Signed-off-by: Rami Rosen Signed-off-by: David S. Miller --- include/net/genetlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 68b88192b00c..c59a098221db 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -128,7 +128,6 @@ static inline int genl_err_attr(struct genl_info *info, int err, * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps - * @ops_list: operations list */ struct genl_ops { const struct nla_policy *policy; -- cgit v1.2.3 From 5a4d1fee2f844813cb2092b7a06b0e20ed9e2fa4 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 6 Jun 2017 14:12:03 +0200 Subject: net: sched: introduce helper to identify gact trap action Introduce a helper called is_tcf_gact_trap which could be used to tell if the action is gact trap or not. Signed-off-by: Jiri Pirko Reviewed-by: Yotam Gigi Signed-off-by: David S. Miller --- include/net/tc_act/tc_gact.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index b6f173910226..d576374c4d6f 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -15,7 +15,7 @@ struct tcf_gact { }; #define to_gact(a) ((struct tcf_gact *)a) -static inline bool is_tcf_gact_shot(const struct tc_action *a) +static inline bool __is_tcf_gact_act(const struct tc_action *a, int act) { #ifdef CONFIG_NET_CLS_ACT struct tcf_gact *gact; @@ -24,10 +24,21 @@ static inline bool is_tcf_gact_shot(const struct tc_action *a) return false; gact = to_gact(a); - if (gact->tcf_action == TC_ACT_SHOT) + if (gact->tcf_action == act) return true; #endif return false; } + +static inline bool is_tcf_gact_shot(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_SHOT); +} + +static inline bool is_tcf_gact_trap(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_TRAP); +} + #endif /* __NET_TC_GACT_H */ -- cgit v1.2.3 From 4ab47d47af20addd6ecee1ece0205b1fbf483942 Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Tue, 6 Jun 2017 12:12:13 +0200 Subject: xfrm: extend MIGRATE with UDP encapsulation port Add UDP encapsulation port to XFRM_MSG_MIGRATE using an optional netlink attribute XFRMA_ENCAP. The devices that support IKE MOBIKE extension (RFC-4555 Section 3.8) could go to sleep for a few minutes and wake up. When it wake up the NAT mapping could have expired, the device send a MOBIKE UPDATE_SA message to migrate the IPsec SA. The change could be a change UDP encapsulation port, IP address, or both. Reported-by: Paul Wouters Signed-off-by: Antony Antony Reviewed-by: Richard Guy Briggs Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 6 ++++-- net/key/af_key.c | 2 +- net/xfrm/xfrm_policy.c | 11 ++++------- net/xfrm/xfrm_state.c | 18 +++++++++++++----- net/xfrm/xfrm_user.c | 14 ++++++++++++-- 5 files changed, 34 insertions(+), 17 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6793a30c66b1..1cc71726e581 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1688,10 +1688,12 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_kmaddress *k); struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, - struct xfrm_migrate *m); + struct xfrm_migrate *m, + struct xfrm_encap_tmpl *encap); int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, - struct xfrm_kmaddress *k, struct net *net); + struct xfrm_kmaddress *k, struct net *net, + struct xfrm_encap_tmpl *encap); #endif int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); diff --git a/net/key/af_key.c b/net/key/af_key.c index c1950bb14735..3b130cbdc463 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2602,7 +2602,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, } return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i, - kma ? &k : NULL, net); + kma ? &k : NULL, net, NULL); out: return err; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index b00a1d5a7f52..d47f055ca90e 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3315,11 +3315,6 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) return -EINVAL; for (i = 0; i < num_migrate; i++) { - if (xfrm_addr_equal(&m[i].old_daddr, &m[i].new_daddr, - m[i].old_family) && - xfrm_addr_equal(&m[i].old_saddr, &m[i].new_saddr, - m[i].old_family)) - return -EINVAL; if (xfrm_addr_any(&m[i].new_daddr, m[i].new_family) || xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) return -EINVAL; @@ -3343,7 +3338,8 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, - struct xfrm_kmaddress *k, struct net *net) + struct xfrm_kmaddress *k, struct net *net, + struct xfrm_encap_tmpl *encap) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; @@ -3366,7 +3362,8 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, if ((x = xfrm_migrate_state_find(mp, net))) { x_cur[nx_cur] = x; nx_cur++; - if ((xc = xfrm_state_migrate(x, mp))) { + xc = xfrm_state_migrate(x, mp, encap); + if (xc) { x_new[nx_new] = xc; nx_new++; } else { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 5780cdad2260..b76e6730b165 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1309,7 +1309,8 @@ out: EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE -static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig) +static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, + struct xfrm_encap_tmpl *encap) { struct net *net = xs_net(orig); struct xfrm_state *x = xfrm_state_alloc(net); @@ -1351,8 +1352,14 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig) } x->props.calgo = orig->props.calgo; - if (orig->encap) { - x->encap = kmemdup(orig->encap, sizeof(*x->encap), GFP_KERNEL); + if (encap || orig->encap) { + if (encap) + x->encap = kmemdup(encap, sizeof(*x->encap), + GFP_KERNEL); + else + x->encap = kmemdup(orig->encap, sizeof(*x->encap), + GFP_KERNEL); + if (!x->encap) goto error; } @@ -1440,11 +1447,12 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n EXPORT_SYMBOL(xfrm_migrate_state_find); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, - struct xfrm_migrate *m) + struct xfrm_migrate *m, + struct xfrm_encap_tmpl *encap) { struct xfrm_state *xc; - xc = xfrm_state_clone(x); + xc = xfrm_state_clone(x, encap); if (!xc) return NULL; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 38614df33ec8..fb98892f7d89 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2243,6 +2243,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, int err; int n = 0; struct net *net = sock_net(skb->sk); + struct xfrm_encap_tmpl *encap = NULL; if (attrs[XFRMA_MIGRATE] == NULL) return -EINVAL; @@ -2260,9 +2261,18 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, if (!n) return 0; - xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net); + if (attrs[XFRMA_ENCAP]) { + encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), + sizeof(*encap), GFP_KERNEL); + if (!encap) + return 0; + } - return 0; + err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap); + + kfree(encap); + + return err; } #else static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, -- cgit v1.2.3 From 8bafd73093f2f431f5a363f8057abc0ccc118853 Mon Sep 17 00:00:00 2001 From: Antony Antony Date: Tue, 6 Jun 2017 12:12:14 +0200 Subject: xfrm: add UDP encapsulation port in migrate message Add XFRMA_ENCAP, UDP encapsulation port, to km_migrate announcement to userland. Only add if XFRMA_ENCAP was in user migrate request. Signed-off-by: Antony Antony Reviewed-by: Richard Guy Briggs Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 6 ++++-- net/key/af_key.c | 6 ++++-- net/xfrm/xfrm_policy.c | 2 +- net/xfrm/xfrm_state.c | 6 ++++-- net/xfrm/xfrm_user.c | 23 +++++++++++++++++------ 5 files changed, 30 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 1cc71726e581..34420d9708a0 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -631,7 +631,8 @@ struct xfrm_mgr { u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, - const struct xfrm_kmaddress *k); + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap); bool (*is_alive)(const struct km_event *c); }; @@ -1685,7 +1686,8 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, - const struct xfrm_kmaddress *k); + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap); struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, diff --git a/net/key/af_key.c b/net/key/af_key.c index 3b130cbdc463..d539bb7df01d 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3508,7 +3508,8 @@ static int set_ipsecrequest(struct sk_buff *skb, #ifdef CONFIG_NET_KEY_MIGRATE static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, - const struct xfrm_kmaddress *k) + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap) { int i; int sasize_sel; @@ -3618,7 +3619,8 @@ err: #else static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, - const struct xfrm_kmaddress *k) + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap) { return -ENOPROTOOPT; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d47f055ca90e..e6141891d23c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3384,7 +3384,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } /* Stage 5 - announce */ - km_migrate(sel, dir, type, m, num_migrate, k); + km_migrate(sel, dir, type, m, num_migrate, k, encap); xfrm_pol_put(pol); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index b76e6730b165..f2421c668449 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1964,7 +1964,8 @@ EXPORT_SYMBOL(km_policy_expired); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, - const struct xfrm_kmaddress *k) + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap) { int err = -EINVAL; int ret; @@ -1973,7 +1974,8 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->migrate) { - ret = km->migrate(sel, dir, type, m, num_migrate, k); + ret = km->migrate(sel, dir, type, m, num_migrate, k, + encap); if (!ret) err = ret; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index fb98892f7d89..6197c7231bc7 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2314,17 +2314,20 @@ static int copy_to_user_kmaddress(const struct xfrm_kmaddress *k, struct sk_buff return nla_put(skb, XFRMA_KMADDRESS, sizeof(uk), &uk); } -static inline size_t xfrm_migrate_msgsize(int num_migrate, int with_kma) +static inline size_t xfrm_migrate_msgsize(int num_migrate, int with_kma, + int with_encp) { return NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_id)) + (with_kma ? nla_total_size(sizeof(struct xfrm_kmaddress)) : 0) + + (with_encp ? nla_total_size(sizeof(struct xfrm_encap_tmpl)) : 0) + nla_total_size(sizeof(struct xfrm_user_migrate) * num_migrate) + userpolicy_type_attrsize(); } static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m, int num_migrate, const struct xfrm_kmaddress *k, - const struct xfrm_selector *sel, u8 dir, u8 type) + const struct xfrm_selector *sel, + const struct xfrm_encap_tmpl *encap, u8 dir, u8 type) { const struct xfrm_migrate *mp; struct xfrm_userpolicy_id *pol_id; @@ -2346,6 +2349,11 @@ static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m, if (err) goto out_cancel; } + if (encap) { + err = nla_put(skb, XFRMA_ENCAP, sizeof(*encap), encap); + if (err) + goto out_cancel; + } err = copy_to_user_policy_type(type, skb); if (err) goto out_cancel; @@ -2365,17 +2373,19 @@ out_cancel: static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, - const struct xfrm_kmaddress *k) + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap) { struct net *net = &init_net; struct sk_buff *skb; - skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k), GFP_ATOMIC); + skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k, !!encap), + GFP_ATOMIC); if (skb == NULL) return -ENOMEM; /* build migrate */ - if (build_migrate(skb, m, num_migrate, k, sel, dir, type) < 0) + if (build_migrate(skb, m, num_migrate, k, sel, encap, dir, type) < 0) BUG(); return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE); @@ -2383,7 +2393,8 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, #else static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, - const struct xfrm_kmaddress *k) + const struct xfrm_kmaddress *k, + const struct xfrm_encap_tmpl *encap) { return -ENOPROTOOPT; } -- cgit v1.2.3 From e754eba685aac2a9b5538176fa2d254ad25f464d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 7 Jun 2017 12:40:03 +0100 Subject: rxrpc: Provide a cmsg to specify the amount of Tx data for a call Provide a control message that can be specified on the first sendmsg() of a client call or the first sendmsg() of a service response to indicate the total length of the data to be transmitted for that call. Currently, because the length of the payload of an encrypted DATA packet is encrypted in front of the data, the packet cannot be encrypted until we know how much data it will hold. By specifying the length at the beginning of the transmit phase, each DATA packet length can be set before we start loading data from userspace (where several sendmsg() calls may contribute to a particular packet). An error will be returned if too little or too much data is presented in the Tx phase. Signed-off-by: David Howells --- Documentation/networking/rxrpc.txt | 34 ++++++++++++++++++++++++ fs/afs/rxrpc.c | 18 ++++++++++++- include/linux/rxrpc.h | 1 + include/net/af_rxrpc.h | 2 ++ net/rxrpc/af_rxrpc.c | 5 +++- net/rxrpc/ar-internal.h | 3 ++- net/rxrpc/call_object.c | 3 +++ net/rxrpc/sendmsg.c | 54 ++++++++++++++++++++++++++++++++++++-- 8 files changed, 115 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index bce8e10a2a8e..8c70ba5dee4d 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -327,6 +327,7 @@ calls, to invoke certain actions and to report certain conditions. These are: RXRPC_ACCEPT s-- n/a Accept new call RXRPC_EXCLUSIVE_CALL s-- n/a Make an exclusive client call RXRPC_UPGRADE_SERVICE s-- n/a Client call can be upgraded + RXRPC_TX_LENGTH s-- data len Total length of Tx data (SRT = usable in Sendmsg / delivered by Recvmsg / Terminal message) @@ -406,6 +407,19 @@ calls, to invoke certain actions and to report certain conditions. These are: future communication to that server and RXRPC_UPGRADE_SERVICE should no longer be set. + (*) RXRPC_TX_LENGTH + + This is used to inform the kernel of the total amount of data that is + going to be transmitted by a call (whether in a client request or a + service response). If given, it allows the kernel to encrypt from the + userspace buffer directly to the packet buffers, rather than copying into + the buffer and then encrypting in place. This may only be given with the + first sendmsg() providing data for a call. EMSGSIZE will be generated if + the amount of data actually given is different. + + This takes a parameter of __s64 type that indicates how much will be + transmitted. This may not be less than zero. + The symbol RXRPC__SUPPORTED is defined as one more than the highest control message type supported. At run time this can be queried by means of the RXRPC_SUPPORTED_CMSG socket option (see below). @@ -577,6 +591,9 @@ A client would issue an operation by: MSG_MORE should be set in msghdr::msg_flags on all but the last part of the request. Multiple requests may be made simultaneously. + An RXRPC_TX_LENGTH control message can also be specified on the first + sendmsg() call. + If a call is intended to go to a destination other than the default specified through connect(), then msghdr::msg_name should be set on the first request message of that call. @@ -764,6 +781,7 @@ The kernel interface functions are as follows: struct sockaddr_rxrpc *srx, struct key *key, unsigned long user_call_ID, + s64 tx_total_len, gfp_t gfp); This allocates the infrastructure to make a new RxRPC call and assigns @@ -780,6 +798,11 @@ The kernel interface functions are as follows: control data buffer. It is entirely feasible to use this to point to a kernel data structure. + tx_total_len is the amount of data the caller is intending to transmit + with this call (or -1 if unknown at this point). Setting the data size + allows the kernel to encrypt directly to the packet buffers, thereby + saving a copy. The value may not be less than -1. + If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. @@ -931,6 +954,17 @@ The kernel interface functions are as follows: This is used to find the remote peer address of a call. + (*) Set the total transmit data size on a call. + + void rxrpc_kernel_set_tx_length(struct socket *sock, + struct rxrpc_call *call, + s64 tx_total_len); + + This sets the amount of data that the caller is intending to transmit on a + call. It's intended to be used for setting the reply size as the request + size should be set when the call is begun. tx_total_len may not be less + than zero. + ======================= CONFIGURABLE PARAMETERS diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index d5990eb160bd..02781e78ffb6 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -341,6 +341,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, struct msghdr msg; struct kvec iov[1]; size_t offset; + s64 tx_total_len; u32 abort_code; int ret; @@ -364,9 +365,20 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, srx.transport.sin.sin_port = call->port; memcpy(&srx.transport.sin.sin_addr, addr, 4); + /* Work out the length we're going to transmit. This is awkward for + * calls such as FS.StoreData where there's an extra injection of data + * after the initial fixed part. + */ + tx_total_len = call->request_size; + if (call->send_pages) { + tx_total_len += call->last_to - call->first_offset; + tx_total_len += (call->last - call->first) * PAGE_SIZE; + } + /* create a call */ rxcall = rxrpc_kernel_begin_call(afs_socket, &srx, call->key, - (unsigned long) call, gfp, + (unsigned long)call, + tx_total_len, gfp, (async ? afs_wake_up_async_call : afs_wake_up_call_waiter)); @@ -738,6 +750,8 @@ void afs_send_empty_reply(struct afs_call *call) _enter(""); + rxrpc_kernel_set_tx_length(afs_socket, call->rxcall, 0); + msg.msg_name = NULL; msg.msg_namelen = 0; iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); @@ -772,6 +786,8 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) _enter(""); + rxrpc_kernel_set_tx_length(afs_socket, call->rxcall, len); + iov[0].iov_base = (void *) buf; iov[0].iov_len = len; msg.msg_name = NULL; diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h index bdd3175b9a48..7343f71783dc 100644 --- a/include/linux/rxrpc.h +++ b/include/linux/rxrpc.h @@ -57,6 +57,7 @@ enum rxrpc_cmsg_type { RXRPC_ACCEPT = 9, /* s-: [Service] accept request */ RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */ RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */ + RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */ RXRPC__SUPPORTED }; diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index b5f5187f488c..c172709787af 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -33,6 +33,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *, struct sockaddr_rxrpc *, struct key *, unsigned long, + s64, gfp_t, rxrpc_notify_rx_t); int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *, @@ -46,5 +47,6 @@ void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *); int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t); +void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64); #endif /* _NET_RXRPC_H */ diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 44a52b82bb5d..58ae0db52ea1 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -262,6 +262,7 @@ static int rxrpc_listen(struct socket *sock, int backlog) * @srx: The address of the peer to contact * @key: The security context to use (defaults to socket setting) * @user_call_ID: The ID to use + * @tx_total_len: Total length of data to transmit during the call (or -1) * @gfp: The allocation constraints * @notify_rx: Where to send notifications instead of socket queue * @@ -276,6 +277,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, struct sockaddr_rxrpc *srx, struct key *key, unsigned long user_call_ID, + s64 tx_total_len, gfp_t gfp, rxrpc_notify_rx_t notify_rx) { @@ -303,7 +305,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, cp.security_level = 0; cp.exclusive = false; cp.service_id = srx->srx_service; - call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, gfp); + call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, tx_total_len, + gfp); /* The socket has been unlocked. */ if (!IS_ERR(call)) call->notify_rx = notify_rx; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index e9b536cb0acf..adbf37946450 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -528,6 +528,7 @@ struct rxrpc_call { struct rb_node sock_node; /* Node in rx->calls */ struct sk_buff *tx_pending; /* Tx socket buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ + s64 tx_total_len; /* Total length left to be transmitted (or -1) */ __be32 crypto_buf[2]; /* Temporary packet crypto buffer */ unsigned long user_call_ID; /* user-defined call ID */ unsigned long flags; @@ -683,7 +684,7 @@ struct rxrpc_call *rxrpc_alloc_call(gfp_t); struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, - unsigned long, gfp_t); + unsigned long, s64, gfp_t); void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 692110808baa..423030fd93be 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -127,6 +127,7 @@ struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) rwlock_init(&call->state_lock); atomic_set(&call->usage, 1); call->debug_id = atomic_inc_return(&rxrpc_debug_id); + call->tx_total_len = -1; memset(&call->sock_node, 0xed, sizeof(call->sock_node)); @@ -201,6 +202,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, struct rxrpc_conn_parameters *cp, struct sockaddr_rxrpc *srx, unsigned long user_call_ID, + s64 tx_total_len, gfp_t gfp) __releases(&rx->sk.sk_lock.slock) { @@ -219,6 +221,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, return call; } + call->tx_total_len = tx_total_len; trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage), here, (const void *)user_call_ID); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index d939a5b1abc3..2e636a525a65 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -29,6 +29,7 @@ enum rxrpc_command { }; struct rxrpc_send_params { + s64 tx_total_len; /* Total Tx data length (if send data) */ unsigned long user_call_ID; /* User's call ID */ u32 abort_code; /* Abort code to Tx (if abort) */ enum rxrpc_command command : 8; /* The command to implement */ @@ -207,6 +208,13 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, more = msg->msg_flags & MSG_MORE; + if (call->tx_total_len != -1) { + if (len > call->tx_total_len) + return -EMSGSIZE; + if (!more && len != call->tx_total_len) + return -EMSGSIZE; + } + skb = call->tx_pending; call->tx_pending = NULL; rxrpc_see_skb(skb, rxrpc_skb_tx_seen); @@ -299,6 +307,8 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, sp->remain -= copy; skb->mark += copy; copied += copy; + if (call->tx_total_len != -1) + call->tx_total_len -= copy; } /* check for the far side aborting the call or a network error @@ -436,6 +446,14 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p) return -EINVAL; break; + case RXRPC_TX_LENGTH: + if (p->tx_total_len != -1 || len != sizeof(__s64)) + return -EINVAL; + p->tx_total_len = *(__s64 *)CMSG_DATA(cmsg); + if (p->tx_total_len < 0) + return -EINVAL; + break; + default: return -EINVAL; } @@ -443,6 +461,8 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p) if (!got_user_ID) return -EINVAL; + if (p->tx_total_len != -1 && p->command != RXRPC_CMD_SEND_DATA) + return -EINVAL; _leave(" = 0"); return 0; } @@ -481,7 +501,8 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, cp.exclusive = rx->exclusive | p->exclusive; cp.upgrade = p->upgrade; cp.service_id = srx->srx_service; - call = rxrpc_new_client_call(rx, &cp, srx, p->user_call_ID, GFP_KERNEL); + call = rxrpc_new_client_call(rx, &cp, srx, p->user_call_ID, + p->tx_total_len, GFP_KERNEL); /* The socket is now unlocked */ _leave(" = %p\n", call); @@ -501,6 +522,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) int ret; struct rxrpc_send_params p = { + .tx_total_len = -1, .user_call_ID = 0, .abort_code = 0, .command = RXRPC_CMD_SEND_DATA, @@ -555,6 +577,15 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) ret = -ERESTARTSYS; goto error_put; } + + if (p.tx_total_len != -1) { + ret = -EINVAL; + if (call->tx_total_len != -1 || + call->tx_pending || + call->tx_top != 0) + goto error_put; + call->tx_total_len = p.tx_total_len; + } } state = READ_ONCE(call->state); @@ -672,5 +703,24 @@ bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, mutex_unlock(&call->user_mutex); return aborted; } - EXPORT_SYMBOL(rxrpc_kernel_abort_call); + +/** + * rxrpc_kernel_set_tx_length - Set the total Tx length on a call + * @sock: The socket the call is on + * @call: The call to be informed + * @tx_total_len: The amount of data to be transmitted for this call + * + * Allow a kernel service to set the total transmit length on a call. This + * allows buffer-to-packet encrypt-and-copy to be performed. + * + * This function is primarily for use for setting the reply length since the + * request length can be set when beginning the call. + */ +void rxrpc_kernel_set_tx_length(struct socket *sock, struct rxrpc_call *call, + s64 tx_total_len) +{ + WARN_ON(call->tx_total_len != -1); + call->tx_total_len = tx_total_len; +} +EXPORT_SYMBOL(rxrpc_kernel_set_tx_length); -- cgit v1.2.3 From 699cb58c8a52ff39bf659bff7971893ebe111bf2 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 30 May 2017 16:34:46 +0200 Subject: mac80211: manage RX BA session offload without SKB queue Instead of using the SKB queue with the fake pkt_type for the offloaded RX BA session management, also handle this with the normal aggregation state machine worker. This also makes the use of this more reliable since it gets rid of the allocation of the fake skb. Combined with the previous patch, this finally allows us to get rid of the pkt_type hack entirely, so do that as well. Signed-off-by: Johannes Berg --- include/net/mac80211.h | 21 +++++++++++++++++---- net/mac80211/agg-rx.c | 47 ++++++++++++---------------------------------- net/mac80211/ht.c | 12 ++++++++++++ net/mac80211/ieee80211_i.h | 11 ----------- net/mac80211/iface.c | 25 ++---------------------- net/mac80211/rx.c | 4 ---- net/mac80211/sta_info.h | 3 +++ 7 files changed, 46 insertions(+), 77 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e01daff1e255..b2b5419467cc 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5452,6 +5452,9 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, */ void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn); +void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, const u8 *addr, + unsigned int bit); + /** * ieee80211_start_rx_ba_session_offl - start a Rx BA session * @@ -5466,8 +5469,13 @@ void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn); * @addr: station mac address * @tid: the rx tid */ -void ieee80211_start_rx_ba_session_offl(struct ieee80211_vif *vif, - const u8 *addr, u16 tid); +static inline void ieee80211_start_rx_ba_session_offl(struct ieee80211_vif *vif, + const u8 *addr, u16 tid) +{ + if (WARN_ON(tid >= IEEE80211_NUM_TIDS)) + return; + ieee80211_manage_rx_ba_offl(vif, addr, tid); +} /** * ieee80211_stop_rx_ba_session_offl - stop a Rx BA session @@ -5483,8 +5491,13 @@ void ieee80211_start_rx_ba_session_offl(struct ieee80211_vif *vif, * @addr: station mac address * @tid: the rx tid */ -void ieee80211_stop_rx_ba_session_offl(struct ieee80211_vif *vif, - const u8 *addr, u16 tid); +static inline void ieee80211_stop_rx_ba_session_offl(struct ieee80211_vif *vif, + const u8 *addr, u16 tid) +{ + if (WARN_ON(tid >= IEEE80211_NUM_TIDS)) + return; + ieee80211_manage_rx_ba_offl(vif, addr, tid + IEEE80211_NUM_TIDS); +} /* Rate control API */ diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 1b7a4daf283c..3a0282188ad6 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -449,44 +449,21 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, buf_size, true, false); } -void ieee80211_start_rx_ba_session_offl(struct ieee80211_vif *vif, - const u8 *addr, u16 tid) +void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, + const u8 *addr, unsigned int bit) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; - struct ieee80211_rx_agg *rx_agg; - struct sk_buff *skb = dev_alloc_skb(0); - - if (unlikely(!skb)) - return; - - rx_agg = (struct ieee80211_rx_agg *) &skb->cb; - memcpy(&rx_agg->addr, addr, ETH_ALEN); - rx_agg->tid = tid; - - skb->pkt_type = IEEE80211_SDATA_QUEUE_RX_AGG_START; - skb_queue_tail(&sdata->skb_queue, skb); - ieee80211_queue_work(&local->hw, &sdata->work); -} -EXPORT_SYMBOL(ieee80211_start_rx_ba_session_offl); - -void ieee80211_stop_rx_ba_session_offl(struct ieee80211_vif *vif, - const u8 *addr, u16 tid) -{ - struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); - struct ieee80211_local *local = sdata->local; - struct ieee80211_rx_agg *rx_agg; - struct sk_buff *skb = dev_alloc_skb(0); - - if (unlikely(!skb)) - return; + struct sta_info *sta; - rx_agg = (struct ieee80211_rx_agg *) &skb->cb; - memcpy(&rx_agg->addr, addr, ETH_ALEN); - rx_agg->tid = tid; + rcu_read_lock(); + sta = sta_info_get_bss(sdata, addr); + if (!sta) + goto unlock; - skb->pkt_type = IEEE80211_SDATA_QUEUE_RX_AGG_STOP; - skb_queue_tail(&sdata->skb_queue, skb); - ieee80211_queue_work(&local->hw, &sdata->work); + set_bit(bit, sta->ampdu_mlme.tid_rx_manage_offl); + ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work); + unlock: + rcu_read_unlock(); } -EXPORT_SYMBOL(ieee80211_stop_rx_ba_session_offl); +EXPORT_SYMBOL(ieee80211_manage_rx_ba_offl); diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 6ca5442b1e03..9e71226c2d25 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -331,6 +331,18 @@ void ieee80211_ba_session_work(struct work_struct *work) sta, tid, WLAN_BACK_RECIPIENT, WLAN_REASON_UNSPECIFIED, true); + if (test_and_clear_bit(tid, + sta->ampdu_mlme.tid_rx_manage_offl)) + __ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid, + IEEE80211_MAX_AMPDU_BUF, + false, true); + + if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS, + sta->ampdu_mlme.tid_rx_manage_offl)) + ___ieee80211_stop_rx_ba_session( + sta, tid, WLAN_BACK_RECIPIENT, + 0, false); + spin_lock_bh(&sta->lock); tid_tx = sta->ampdu_mlme.tid_start_tx[tid]; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index f24f1d7b8937..392fbab73c04 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1031,17 +1031,6 @@ ieee80211_vif_get_shift(struct ieee80211_vif *vif) return shift; } -struct ieee80211_rx_agg { - u8 addr[ETH_ALEN]; - u16 tid; -}; - -enum sdata_queue_type { - IEEE80211_SDATA_QUEUE_TYPE_FRAME = 0, - IEEE80211_SDATA_QUEUE_RX_AGG_START = 3, - IEEE80211_SDATA_QUEUE_RX_AGG_STOP = 4, -}; - enum { IEEE80211_RX_MSG = 1, IEEE80211_TX_STATUS_MSG = 2, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 8fae1a72e6a7..6ac0a0198d19 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1237,7 +1237,6 @@ static void ieee80211_iface_work(struct work_struct *work) struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct sta_info *sta; - struct ieee80211_rx_agg *rx_agg; if (!ieee80211_sdata_running(sdata)) return; @@ -1252,28 +1251,8 @@ static void ieee80211_iface_work(struct work_struct *work) while ((skb = skb_dequeue(&sdata->skb_queue))) { struct ieee80211_mgmt *mgmt = (void *)skb->data; - if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_START) { - rx_agg = (void *)&skb->cb; - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, rx_agg->addr); - if (sta) - __ieee80211_start_rx_ba_session(sta, - 0, 0, 0, 1, rx_agg->tid, - IEEE80211_MAX_AMPDU_BUF, - false, true); - mutex_unlock(&local->sta_mtx); - } else if (skb->pkt_type == IEEE80211_SDATA_QUEUE_RX_AGG_STOP) { - rx_agg = (void *)&skb->cb; - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, rx_agg->addr); - if (sta) - __ieee80211_stop_rx_ba_session(sta, - rx_agg->tid, - WLAN_BACK_RECIPIENT, 0, - false); - mutex_unlock(&local->sta_mtx); - } else if (ieee80211_is_action(mgmt->frame_control) && - mgmt->u.action.category == WLAN_CATEGORY_BACK) { + if (ieee80211_is_action(mgmt->frame_control) && + mgmt->u.action.category == WLAN_CATEGORY_BACK) { int len = skb->len; mutex_lock(&local->sta_mtx); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1f75280ba26c..8c7d932fd09b 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -237,7 +237,6 @@ static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, if (!skb) return; - skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; skb_queue_tail(&sdata->skb_queue, skb); ieee80211_queue_work(&sdata->local->hw, &sdata->work); } @@ -1217,7 +1216,6 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, /* if this mpdu is fragmented - terminate rx aggregation session */ sc = le16_to_cpu(hdr->seq_ctrl); if (sc & IEEE80211_SCTL_FRAG) { - skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; skb_queue_tail(&rx->sdata->skb_queue, skb); ieee80211_queue_work(&local->hw, &rx->sdata->work); return; @@ -3100,7 +3098,6 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) return RX_QUEUED; queue: - rx->skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; skb_queue_tail(&sdata->skb_queue, rx->skb); ieee80211_queue_work(&local->hw, &sdata->work); if (rx->sta) @@ -3246,7 +3243,6 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) } /* queue up frame and kick off work to process it */ - rx->skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME; skb_queue_tail(&sdata->skb_queue, rx->skb); ieee80211_queue_work(&rx->local->hw, &sdata->work); if (rx->sta) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index cde89c6d0386..3acbdfa9f649 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -233,6 +233,8 @@ struct tid_ampdu_rx { * RX timer expired until the work for it runs * @tid_rx_stop_requested: bitmap indicating which BA sessions per TID the * driver requested to close until the work for it runs + * @tid_rx_manage_offl: bitmap indicating which BA sessions were requested + * to be treated as started/stopped due to offloading * @agg_session_valid: bitmap indicating which TID has a rx BA session open on * @unexpected_agg: bitmap indicating which TID already sent a delBA due to * unexpected aggregation related frames outside a session @@ -250,6 +252,7 @@ struct sta_ampdu_mlme { u8 tid_rx_token[IEEE80211_NUM_TIDS]; unsigned long tid_rx_timer_expired[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; unsigned long tid_rx_stop_requested[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; + unsigned long tid_rx_manage_offl[BITS_TO_LONGS(2 * IEEE80211_NUM_TIDS)]; unsigned long agg_session_valid[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; unsigned long unexpected_agg[BITS_TO_LONGS(IEEE80211_NUM_TIDS)]; /* tx */ -- cgit v1.2.3 From eed29f17f09ad7f400bc245f209acad6a8214fac Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Jun 2017 10:34:36 -0700 Subject: tcp: add a struct net parameter to tcp_parse_options() We want to move some TCP sysctls to net namespaces in the future. tcp_window_scaling, tcp_sack and tcp_timestamps being fetched from tcp_parse_options(), we need to pass an extra parameter. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/infiniband/hw/cxgb4/cm.c | 2 +- include/net/tcp.h | 2 +- net/ipv4/syncookies.c | 2 +- net/ipv4/tcp_input.c | 18 +++++++++++------- net/ipv4/tcp_minisocks.c | 4 ++-- net/ipv6/syncookies.c | 2 +- 6 files changed, 17 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index b0ae4f0c8aa7..2f1136bf7b1f 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3756,7 +3756,7 @@ static void build_cpl_pass_accept_req(struct sk_buff *skb, int stid , u8 tos) */ memset(&tmp_opt, 0, sizeof(tmp_opt)); tcp_clear_options(&tmp_opt); - tcp_parse_options(skb, &tmp_opt, 0, NULL); + tcp_parse_options(&init_net, skb, &tmp_opt, 0, NULL); req = (struct cpl_pass_accept_req *)__skb_push(skb, sizeof(*req)); memset(req, 0, sizeof(*req)); diff --git a/include/net/tcp.h b/include/net/tcp.h index 28b577a35786..0b0cfeefa05b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -427,7 +427,7 @@ void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); -void tcp_parse_options(const struct sk_buff *skb, +void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); const u8 *tcp_parse_md5sig_option(const struct tcphdr *th); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 6426250a58ea..6a32cb381877 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -312,7 +312,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0, NULL); + tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { tsoff = secure_tcp_ts_off(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4ea8ec5c7bb4..99ee707f0ef4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3724,7 +3724,8 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie, * But, this can also be called on packets in the established flow when * the fast version below fails. */ -void tcp_parse_options(const struct sk_buff *skb, +void tcp_parse_options(const struct net *net, + const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc) { @@ -3858,7 +3859,8 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr /* Fast parse options. This hopes to only see timestamps. * If it is wrong it falls back on tcp_parse_options(). */ -static bool tcp_fast_parse_options(const struct sk_buff *skb, +static bool tcp_fast_parse_options(const struct net *net, + const struct sk_buff *skb, const struct tcphdr *th, struct tcp_sock *tp) { /* In the spirit of fast parsing, compare doff directly to constant @@ -3873,7 +3875,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, return true; } - tcp_parse_options(skb, &tp->rx_opt, 1, NULL); + tcp_parse_options(net, skb, &tp->rx_opt, 1, NULL); if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; @@ -5234,7 +5236,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, bool rst_seq_match = false; /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && + if (tcp_fast_parse_options(sock_net(sk), skb, th, tp) && + tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); @@ -5605,7 +5608,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, /* Get original SYNACK MSS value if user MSS sets mss_clamp */ tcp_clear_options(&opt); opt.user_mss = opt.mss_clamp = 0; - tcp_parse_options(synack, &opt, 0, NULL); + tcp_parse_options(sock_net(sk), synack, &opt, 0, NULL); mss = opt.mss_clamp; } @@ -5659,7 +5662,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, int saved_clamp = tp->rx_opt.mss_clamp; bool fastopen_fail; - tcp_parse_options(skb, &tp->rx_opt, 0, &foc); + tcp_parse_options(sock_net(sk), skb, &tp->rx_opt, 0, &foc); if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; @@ -6332,7 +6335,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = af_ops->mss_clamp; tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc); + tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, + want_cookie ? NULL : &foc); if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d0642df73044..d30ee31e94eb 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -98,7 +98,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { - tcp_parse_options(skb, &tmp_opt, 0, NULL); + tcp_parse_options(twsk_net(tw), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { if (tmp_opt.rcv_tsecr) @@ -559,7 +559,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { - tcp_parse_options(skb, &tmp_opt, 0, NULL); + tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 971823359f5b..4c0a047ec230 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -162,7 +162,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) /* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0, NULL); + tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { tsoff = secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32, -- cgit v1.2.3 From f930103421f6579719b8252285c94c1195f6e032 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Jun 2017 10:34:37 -0700 Subject: tcp: Namespaceify sysctl_tcp_sack Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 4 ++-- net/ipv4/syncookies.c | 7 ++++--- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_input.c | 3 +-- net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_output.c | 2 +- net/ipv6/syncookies.c | 2 +- 8 files changed, 18 insertions(+), 16 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index cd686c4fb32d..bb02482ec821 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -122,6 +122,7 @@ struct netns_ipv4 { int sysctl_tcp_fin_timeout; unsigned int sysctl_tcp_notsent_lowat; int sysctl_tcp_tw_reuse; + int sysctl_tcp_sack; struct inet_timewait_death_row tcp_death_row; int sysctl_max_syn_backlog; diff --git a/include/net/tcp.h b/include/net/tcp.h index 0b0cfeefa05b..f9d2ce0ba676 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -239,7 +239,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* sysctl variables for tcp */ extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; -extern int sysctl_tcp_sack; extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; extern int sysctl_tcp_stdurg; @@ -520,7 +519,8 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); u64 cookie_init_timestamp(struct request_sock *req); -bool cookie_timestamp_decode(struct tcp_options_received *opt); +bool cookie_timestamp_decode(const struct net *net, + struct tcp_options_received *opt); bool cookie_ecn_ok(const struct tcp_options_received *opt, const struct net *net, const struct dst_entry *dst); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 6a32cb381877..b386e8592ffd 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -232,7 +232,8 @@ EXPORT_SYMBOL(tcp_get_cookie_sock); * return false if we decode a tcp option that is disabled * on the host. */ -bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt) +bool cookie_timestamp_decode(const struct net *net, + struct tcp_options_received *tcp_opt) { /* echoed timestamp, lowest bits contain options */ u32 options = tcp_opt->rcv_tsecr; @@ -247,7 +248,7 @@ bool cookie_timestamp_decode(struct tcp_options_received *tcp_opt) tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0; - if (tcp_opt->sack_ok && !sysctl_tcp_sack) + if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack) return false; if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK) @@ -319,7 +320,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) tcp_opt.rcv_tsecr -= tsoff; } - if (!cookie_timestamp_decode(&tcp_opt)) + if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt)) goto out; ret = NULL; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 86957e9cd6c6..74718f8a0aa8 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -378,13 +378,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_sack", - .data = &sysctl_tcp_sack, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_retrans_collapse", .data = &sysctl_tcp_retrans_collapse, @@ -1116,6 +1109,13 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &one, }, #endif + { + .procname = "tcp_sack", + .data = &init_net.ipv4.sysctl_tcp_sack, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 99ee707f0ef4..2eacfcaf1257 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -78,7 +78,6 @@ int sysctl_tcp_timestamps __read_mostly = 1; int sysctl_tcp_window_scaling __read_mostly = 1; -int sysctl_tcp_sack __read_mostly = 1; int sysctl_tcp_fack __read_mostly; int sysctl_tcp_max_reordering __read_mostly = 300; int sysctl_tcp_dsack __read_mostly = 1; @@ -3790,7 +3789,7 @@ void tcp_parse_options(const struct net *net, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && sysctl_tcp_sack) { + !estab && net->ipv4.sysctl_tcp_sack) { opt_rx->sack_ok = TCP_SACK_SEEN; tcp_sack_reset(opt_rx); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 191b2f78b19d..3c475a2a8432 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2465,6 +2465,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256); + net->ipv4.sysctl_tcp_sack = 1; return 0; fail: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e3aab1c1cf78..45c8e459db49 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -580,7 +580,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } - if (likely(sysctl_tcp_sack)) { + if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 4c0a047ec230..aa6443c6da19 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) tcp_opt.rcv_tsecr -= tsoff; } - if (!cookie_timestamp_decode(&tcp_opt)) + if (!cookie_timestamp_decode(sock_net(sk), &tcp_opt)) goto out; ret = NULL; -- cgit v1.2.3 From 9bb37ef00e932eb4b989e855245468feb3980700 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Jun 2017 10:34:38 -0700 Subject: tcp: Namespaceify sysctl_tcp_window_scaling Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 1 - net/ipv4/syncookies.c | 2 +- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_input.c | 3 +-- net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_output.c | 4 ++-- 7 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index bb02482ec821..1a2ae74a1085 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -123,6 +123,7 @@ struct netns_ipv4 { unsigned int sysctl_tcp_notsent_lowat; int sysctl_tcp_tw_reuse; int sysctl_tcp_sack; + int sysctl_tcp_window_scaling; struct inet_timewait_death_row tcp_death_row; int sysctl_max_syn_backlog; diff --git a/include/net/tcp.h b/include/net/tcp.h index f9d2ce0ba676..f41ed5bac493 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -238,7 +238,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* sysctl variables for tcp */ extern int sysctl_tcp_timestamps; -extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; extern int sysctl_tcp_stdurg; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b386e8592ffd..3d74a45773f1 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -257,7 +257,7 @@ bool cookie_timestamp_decode(const struct net *net, tcp_opt->wscale_ok = 1; tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK; - return sysctl_tcp_window_scaling != 0; + return net->ipv4.sysctl_tcp_window_scaling != 0; } EXPORT_SYMBOL(cookie_timestamp_decode); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 74718f8a0aa8..c30ac2ba0e14 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -371,13 +371,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "tcp_window_scaling", - .data = &sysctl_tcp_window_scaling, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_retrans_collapse", .data = &sysctl_tcp_retrans_collapse, @@ -1116,6 +1109,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_window_scaling", + .data = &init_net.ipv4.sysctl_tcp_window_scaling, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2eacfcaf1257..675ee903370f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -77,7 +77,6 @@ #include int sysctl_tcp_timestamps __read_mostly = 1; -int sysctl_tcp_window_scaling __read_mostly = 1; int sysctl_tcp_fack __read_mostly; int sysctl_tcp_max_reordering __read_mostly = 300; int sysctl_tcp_dsack __read_mostly = 1; @@ -3765,7 +3764,7 @@ void tcp_parse_options(const struct net *net, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && sysctl_tcp_window_scaling) { + !estab && net->ipv4.sysctl_tcp_window_scaling) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > TCP_MAX_WSCALE) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3c475a2a8432..e07ef5b14aaf 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2466,6 +2466,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256); net->ipv4.sysctl_tcp_sack = 1; + net->ipv4.sysctl_tcp_window_scaling = 1; return 0; fail: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 45c8e459db49..3f4095010785 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -575,7 +575,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } - if (likely(sysctl_tcp_window_scaling)) { + if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; @@ -3303,7 +3303,7 @@ static void tcp_connect_init(struct sock *sk) tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, - sysctl_tcp_window_scaling, + sock_net(sk)->ipv4.sysctl_tcp_window_scaling, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); -- cgit v1.2.3 From 5d2ed0521ac98f1ae0243fe52b8ebf95e2abf791 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Jun 2017 10:34:39 -0700 Subject: tcp: Namespaceify sysctl_tcp_timestamps Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + include/net/secure_seq.h | 5 +++-- include/net/tcp.h | 3 +-- net/core/secure_seq.c | 9 +++++---- net/ipv4/syncookies.c | 6 ++++-- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp_input.c | 5 ++--- net/ipv4/tcp_ipv4.c | 9 +++++---- net/ipv4/tcp_output.c | 7 ++++--- net/ipv6/syncookies.c | 3 ++- net/ipv6/tcp_ipv6.c | 7 ++++--- 11 files changed, 38 insertions(+), 31 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 1a2ae74a1085..9a14a0850b0e 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -124,6 +124,7 @@ struct netns_ipv4 { int sysctl_tcp_tw_reuse; int sysctl_tcp_sack; int sysctl_tcp_window_scaling; + int sysctl_tcp_timestamps; struct inet_timewait_death_row tcp_death_row; int sysctl_max_syn_backlog; diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index b94006f6fbdd..031bf16d1521 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -8,10 +8,11 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); u32 secure_tcp_seq(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); -u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr); +u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr); u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport); -u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr); +u32 secure_tcpv6_ts_off(const struct net *net, + const __be32 *saddr, const __be32 *daddr); u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, diff --git a/include/net/tcp.h b/include/net/tcp.h index f41ed5bac493..aec092560d9b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -237,7 +237,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); /* sysctl variables for tcp */ -extern int sysctl_tcp_timestamps; extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; extern int sysctl_tcp_stdurg; @@ -1869,7 +1868,7 @@ struct tcp_request_sock_ops { struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, const struct request_sock *req); u32 (*init_seq)(const struct sk_buff *skb); - u32 (*init_ts_off)(const struct sk_buff *skb); + u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index ae35cce3a40d..7232274de334 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -51,7 +51,8 @@ static u32 seq_scale(u32 seq) #endif #if IS_ENABLED(CONFIG_IPV6) -u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr) +u32 secure_tcpv6_ts_off(const struct net *net, + const __be32 *saddr, const __be32 *daddr) { const struct { struct in6_addr saddr; @@ -61,7 +62,7 @@ u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr) .daddr = *(struct in6_addr *)daddr, }; - if (sysctl_tcp_timestamps != 1) + if (net->ipv4.sysctl_tcp_timestamps != 1) return 0; ts_secret_init(); @@ -113,9 +114,9 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr) +u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) { - if (sysctl_tcp_timestamps != 1) + if (net->ipv4.sysctl_tcp_timestamps != 1) return 0; ts_secret_init(); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 3d74a45773f1..7835bb4a1fab 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -243,7 +243,7 @@ bool cookie_timestamp_decode(const struct net *net, return true; } - if (!sysctl_tcp_timestamps) + if (!net->ipv4.sysctl_tcp_timestamps) return false; tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0; @@ -316,7 +316,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcp_ts_off(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); + tsoff = secure_tcp_ts_off(sock_net(sk), + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr); tcp_opt.rcv_tsecr -= tsoff; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index c30ac2ba0e14..7065234a89a5 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -364,13 +364,6 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, } static struct ctl_table ipv4_table[] = { - { - .procname = "tcp_timestamps", - .data = &sysctl_tcp_timestamps, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "tcp_retrans_collapse", .data = &sysctl_tcp_retrans_collapse, @@ -1116,6 +1109,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_timestamps", + .data = &init_net.ipv4.sysctl_tcp_timestamps, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 675ee903370f..2ab7e2fa9bb9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -76,7 +76,6 @@ #include #include -int sysctl_tcp_timestamps __read_mostly = 1; int sysctl_tcp_fack __read_mostly; int sysctl_tcp_max_reordering __read_mostly = 300; int sysctl_tcp_dsack __read_mostly = 1; @@ -3780,7 +3779,7 @@ void tcp_parse_options(const struct net *net, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && sysctl_tcp_timestamps))) { + (!estab && net->ipv4.sysctl_tcp_timestamps))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); @@ -6352,7 +6351,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_free; if (tmp_opt.tstamp_ok) - tcp_rsk(req)->ts_off = af_ops->init_ts_off(skb); + tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); if (!want_cookie && !isn) { /* Kill the following clause, if you dislike this way. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e07ef5b14aaf..13c7ae7d4504 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -102,10 +102,9 @@ static u32 tcp_v4_init_seq(const struct sk_buff *skb) tcp_hdr(skb)->source); } -static u32 tcp_v4_init_ts_off(const struct sk_buff *skb) +static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcp_ts_off(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr); + return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -242,7 +241,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, usin->sin_port); - tp->tsoffset = secure_tcp_ts_off(inet->inet_saddr, + tp->tsoffset = secure_tcp_ts_off(sock_net(sk), + inet->inet_saddr, inet->inet_daddr); } @@ -2467,6 +2467,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256); net->ipv4.sysctl_tcp_sack = 1; net->ipv4.sysctl_tcp_window_scaling = 1; + net->ipv4.sysctl_tcp_timestamps = 1; return 0; fail: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3f4095010785..9a9c395b6235 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -569,7 +569,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sysctl_tcp_timestamps && !*md5)) { + if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; @@ -3271,8 +3271,9 @@ static void tcp_connect_init(struct sock *sk) /* We'll fix this up when we get a response from the other end. * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ - tp->tcp_header_len = sizeof(struct tcphdr) + - (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0); + tp->tcp_header_len = sizeof(struct tcphdr); + if (sock_net(sk)->ipv4.sysctl_tcp_timestamps) + tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk)) diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index aa6443c6da19..2f7e99af67db 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -165,7 +165,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) tcp_parse_options(sock_net(sk), skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32, + tsoff = secure_tcpv6_ts_off(sock_net(sk), + ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); tcp_opt.rcv_tsecr -= tsoff; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 233edfabe1db..5a525426fe93 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -109,9 +109,9 @@ static u32 tcp_v6_init_seq(const struct sk_buff *skb) tcp_hdr(skb)->source); } -static u32 tcp_v6_init_ts_off(const struct sk_buff *skb) +static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32, + return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); } @@ -292,7 +292,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); - tp->tsoffset = secure_tcpv6_ts_off(np->saddr.s6_addr32, + tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk), + np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); } -- cgit v1.2.3 From 0604475119de5f80dc051a5db055c6a2a75bd542 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 7 Jun 2017 13:29:12 -0700 Subject: tcp: add TCPMemoryPressuresChrono counter DRAM supply shortage and poor memory pressure tracking in TCP stack makes any change in SO_SNDBUF/SO_RCVBUF (or equivalent autotuning limits) and tcp_mem[] quite hazardous. TCPMemoryPressures SNMP counter is an indication of tcp_mem sysctl limits being hit, but only tracking number of transitions. If TCP stack behavior under stress was perfect : 1) It would maintain memory usage close to the limit. 2) Memory pressure state would be entered for short times. We certainly prefer 100 events lasting 10ms compared to one event lasting 200 seconds. This patch adds a new SNMP counter tracking cumulative duration of memory pressure events, given in ms units. $ cat /proc/sys/net/ipv4/tcp_mem 3088 4117 6176 $ grep TCP /proc/net/sockstat TCP: inuse 180 orphan 0 tw 2 alloc 234 mem 4140 $ nstat -n ; sleep 10 ; nstat |grep Pressure TcpExtTCPMemoryPressures 1700 TcpExtTCPMemoryPressuresChrono 5209 v2: Used EXPORT_SYMBOL_GPL() instead of EXPORT_SYMBOL() as David instructed. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 22 ++-------------------- include/net/tcp.h | 3 ++- include/uapi/linux/snmp.h | 1 + net/core/sock.c | 20 ++++++++++++++++++++ net/decnet/af_decnet.c | 2 +- net/ipv4/proc.c | 1 + net/ipv4/tcp.c | 31 +++++++++++++++++++++++++------ net/ipv4/tcp_ipv4.c | 1 + net/ipv6/tcp_ipv6.c | 1 + net/sctp/socket.c | 2 +- 10 files changed, 55 insertions(+), 29 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 3467d9e89e7d..858891c36f94 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1080,6 +1080,7 @@ struct proto { bool (*stream_memory_free)(const struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); + void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* @@ -1088,7 +1089,7 @@ struct proto { * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ - int *memory_pressure; + unsigned long *memory_pressure; long *sysctl_mem; int *sysctl_wmem; int *sysctl_rmem; @@ -1193,25 +1194,6 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) return !!*sk->sk_prot->memory_pressure; } -static inline void sk_leave_memory_pressure(struct sock *sk) -{ - int *memory_pressure = sk->sk_prot->memory_pressure; - - if (!memory_pressure) - return; - - if (*memory_pressure) - *memory_pressure = 0; -} - -static inline void sk_enter_memory_pressure(struct sock *sk) -{ - if (!sk->sk_prot->enter_memory_pressure) - return; - - sk->sk_prot->enter_memory_pressure(sk); -} - static inline long sk_memory_allocated(const struct sock *sk) { diff --git a/include/net/tcp.h b/include/net/tcp.h index aec092560d9b..3ab677d11d02 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -276,7 +276,7 @@ extern int sysctl_tcp_pacing_ca_ratio; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; -extern int tcp_memory_pressure; +extern unsigned long tcp_memory_pressure; /* optimized version of sk_under_memory_pressure() for TCP sockets */ static inline bool tcp_under_memory_pressure(const struct sock *sk) @@ -1320,6 +1320,7 @@ extern void tcp_openreq_init_rwin(struct request_sock *req, const struct dst_entry *dst); void tcp_enter_memory_pressure(struct sock *sk); +void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 95cffcb21dfd..d85693295798 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -228,6 +228,7 @@ enum LINUX_MIB_TCPABORTONLINGER, /* TCPAbortOnLinger */ LINUX_MIB_TCPABORTFAILED, /* TCPAbortFailed */ LINUX_MIB_TCPMEMORYPRESSURES, /* TCPMemoryPressures */ + LINUX_MIB_TCPMEMORYPRESSURESCHRONO, /* TCPMemoryPressuresChrono */ LINUX_MIB_TCPSACKDISCARD, /* TCPSACKDiscard */ LINUX_MIB_TCPDSACKIGNOREDOLD, /* TCPSACKIgnoredOld */ LINUX_MIB_TCPDSACKIGNOREDNOUNDO, /* TCPSACKIgnoredNoUndo */ diff --git a/net/core/sock.c b/net/core/sock.c index bef844127e01..ad8a4bc84126 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2076,6 +2076,26 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg, } EXPORT_SYMBOL(sock_cmsg_send); +static void sk_enter_memory_pressure(struct sock *sk) +{ + if (!sk->sk_prot->enter_memory_pressure) + return; + + sk->sk_prot->enter_memory_pressure(sk); +} + +static void sk_leave_memory_pressure(struct sock *sk) +{ + if (sk->sk_prot->leave_memory_pressure) { + sk->sk_prot->leave_memory_pressure(sk); + } else { + unsigned long *memory_pressure = sk->sk_prot->memory_pressure; + + if (memory_pressure && *memory_pressure) + *memory_pressure = 0; + } +} + /* On 32bit arches, an skb frag is limited to 2^15 */ #define SKB_FRAG_PAGE_ORDER get_order(32768) diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 405483a07efc..73a0399dc7a2 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -447,7 +447,7 @@ static void dn_destruct(struct sock *sk) dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); } -static int dn_memory_pressure; +static unsigned long dn_memory_pressure; static void dn_enter_memory_pressure(struct sock *sk) { diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index fa44e752a9a3..43eb6567b3a0 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -250,6 +250,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPAbortOnLinger", LINUX_MIB_TCPABORTONLINGER), SNMP_MIB_ITEM("TCPAbortFailed", LINUX_MIB_TCPABORTFAILED), SNMP_MIB_ITEM("TCPMemoryPressures", LINUX_MIB_TCPMEMORYPRESSURES), + SNMP_MIB_ITEM("TCPMemoryPressuresChrono", LINUX_MIB_TCPMEMORYPRESSURESCHRONO), SNMP_MIB_ITEM("TCPSACKDiscard", LINUX_MIB_TCPSACKDISCARD), SNMP_MIB_ITEM("TCPDSACKIgnoredOld", LINUX_MIB_TCPDSACKIGNOREDOLD), SNMP_MIB_ITEM("TCPDSACKIgnoredNoUndo", LINUX_MIB_TCPDSACKIGNOREDNOUNDO), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 87981fcdfcf2..cc8fd8b747a4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -320,17 +320,36 @@ struct tcp_splice_state { * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ -int tcp_memory_pressure __read_mostly; -EXPORT_SYMBOL(tcp_memory_pressure); +unsigned long tcp_memory_pressure __read_mostly; +EXPORT_SYMBOL_GPL(tcp_memory_pressure); void tcp_enter_memory_pressure(struct sock *sk) { - if (!tcp_memory_pressure) { + unsigned long val; + + if (tcp_memory_pressure) + return; + val = jiffies; + + if (!val) + val--; + if (!cmpxchg(&tcp_memory_pressure, 0, val)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES); - tcp_memory_pressure = 1; - } } -EXPORT_SYMBOL(tcp_enter_memory_pressure); +EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure); + +void tcp_leave_memory_pressure(struct sock *sk) +{ + unsigned long val; + + if (!tcp_memory_pressure) + return; + val = xchg(&tcp_memory_pressure, 0); + if (val) + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO, + jiffies_to_msecs(jiffies - val)); +} +EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure); /* Convert seconds to retransmits based on initial and max timeout */ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 13c7ae7d4504..1dc8c449e16a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2387,6 +2387,7 @@ struct proto tcp_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5a525426fe93..0840543fc245 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1910,6 +1910,7 @@ struct proto tcpv6_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0822046e4f3f..5f58dd03e3ac 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -103,7 +103,7 @@ static int sctp_autobind(struct sock *sk); static void sctp_sock_migrate(struct sock *, struct sock *, struct sctp_association *, sctp_socket_type_t); -static int sctp_memory_pressure; +static unsigned long sctp_memory_pressure; static atomic_long_t sctp_memory_allocated; struct percpu_counter sctp_sockets_allocated; -- cgit v1.2.3 From dc0ecabd6231f6cec2493783a4111f7a85175c8a Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Thu, 8 Jun 2017 08:44:10 +0200 Subject: net: switchdev: Add support for querying supported bridge flags by hardware This is done as a preparation stage before setting the bridge port flags from the bridge code. Currently the device can be queried for the bridge flags state, but the querier cannot distinguish if the flag is disabled or if it is not supported at all. Thus, add new attr and a bit-mask which include information regarding the support on a per-flag basis. Drivers that support bridge offload but not support bridge flags should return zeroed bitmask. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Reviewed-by: Ivan Vecera Signed-off-by: Jiri Pirko Reviewed-by: Ivan Vecera Signed-off-by: David S. Miller --- include/net/switchdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 929d6af321cd..63a754d4ff9b 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -46,6 +46,7 @@ enum switchdev_attr_id { SWITCHDEV_ATTR_ID_PORT_PARENT_ID, SWITCHDEV_ATTR_ID_PORT_STP_STATE, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, + SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT, SWITCHDEV_ATTR_ID_PORT_MROUTER, SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, @@ -62,6 +63,7 @@ struct switchdev_attr { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ + unsigned long brport_flags_support; /* PORT_BRIDGE_FLAGS_SUPPORT */ bool mrouter; /* PORT_MROUTER */ clock_t ageing_time; /* BRIDGE_AGEING_TIME */ bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ -- cgit v1.2.3 From 6b26b51b1d13c62a09f55d745b06a8e964900715 Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Thu, 8 Jun 2017 08:44:14 +0200 Subject: net: bridge: Add support for notifying devices about FDB add/del Currently the bridge doesn't notify the underlying devices about new FDBs learned. The FDB sync is placed on the switchdev notifier chain because devices may potentially learn FDB that are not directly related to their ports, for example: 1. Mixed SW/HW bridge - FDBs that point to the ASICs external devices should be offloaded as CPU traps in order to perform forwarding in slow path. 2. EVPN - Externally learned FDBs for the vtep device. Notification is sent only about static FDB add/del. This is done due to fact that currently this is the only scenario supported by switch drivers. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Reviewed-by: Nikolay Aleksandrov Reviewed-by: Ivan Vecera Signed-off-by: David S. Miller --- .../ethernet/mellanox/mlxsw/spectrum_switchdev.c | 2 +- drivers/net/ethernet/rocker/rocker_ofdpa.c | 4 +-- include/net/switchdev.h | 6 ++-- net/bridge/br.c | 4 +-- net/bridge/br_fdb.c | 2 ++ net/bridge/br_private.h | 7 +++++ net/bridge/br_switchdev.c | 33 ++++++++++++++++++++++ 7 files changed, 51 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index edcc273d7597..0111a77c36e8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1867,7 +1867,7 @@ static void mlxsw_sp_fdb_call_notifiers(bool learning_sync, bool adding, if (learning_sync) { info.addr = mac; info.vid = vid; - notifier_type = adding ? SWITCHDEV_FDB_ADD : SWITCHDEV_FDB_DEL; + notifier_type = adding ? SWITCHDEV_FDB_ADD_TO_BRIDGE : SWITCHDEV_FDB_DEL_TO_BRIDGE; call_switchdev_notifiers(notifier_type, dev, &info.info); } } diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 2ae852454780..f659dad818e2 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -1939,10 +1939,10 @@ static void ofdpa_port_fdb_learn_work(struct work_struct *work) rtnl_lock(); if (learned && removing) - call_switchdev_notifiers(SWITCHDEV_FDB_DEL, + call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, lw->ofdpa_port->dev, &info.info); else if (learned && !removing) - call_switchdev_notifiers(SWITCHDEV_FDB_ADD, + call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, lw->ofdpa_port->dev, &info.info); rtnl_unlock(); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 63a754d4ff9b..8165ed93c58b 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -155,8 +155,10 @@ struct switchdev_ops { }; enum switchdev_notifier_type { - SWITCHDEV_FDB_ADD = 1, - SWITCHDEV_FDB_DEL, + SWITCHDEV_FDB_ADD_TO_BRIDGE = 1, + SWITCHDEV_FDB_DEL_TO_BRIDGE, + SWITCHDEV_FDB_ADD_TO_DEVICE, + SWITCHDEV_FDB_DEL_TO_DEVICE, }; struct switchdev_notifier_info { diff --git a/net/bridge/br.c b/net/bridge/br.c index e962fff8c0d9..96d209caf6db 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -138,14 +138,14 @@ static int br_switchdev_event(struct notifier_block *unused, br = p->br; switch (event) { - case SWITCHDEV_FDB_ADD: + case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, fdb_info->vid); if (err) err = notifier_from_errno(err); break; - case SWITCHDEV_FDB_DEL: + case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_del(br, p, fdb_info->addr, fdb_info->vid); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 5c780cdee93a..26a1dae2d434 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -690,6 +690,8 @@ static void fdb_notify(struct net_bridge *br, struct sk_buff *skb; int err = -ENOBUFS; + br_switchdev_fdb_notify(fdb, type); + skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index a122684b6a41..98410ea032cb 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1085,6 +1085,8 @@ bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, int br_switchdev_set_port_flag(struct net_bridge_port *p, unsigned long flags, unsigned long mask); +void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, + int type); #else static inline int nbp_switchdev_mark_set(struct net_bridge_port *p) { @@ -1108,6 +1110,11 @@ static inline int br_switchdev_set_port_flag(struct net_bridge_port *p, { return 0; } + +static inline void +br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) +{ +} #endif /* CONFIG_NET_SWITCHDEV */ #endif diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index b975959ac15a..181a44d0f1da 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -98,3 +98,36 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, return 0; } + +static void +br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac, + u16 vid, struct net_device *dev) +{ + struct switchdev_notifier_fdb_info info; + unsigned long notifier_type; + + info.addr = mac; + info.vid = vid; + notifier_type = adding ? SWITCHDEV_FDB_ADD_TO_DEVICE : SWITCHDEV_FDB_DEL_TO_DEVICE; + call_switchdev_notifiers(notifier_type, dev, &info.info); +} + +void +br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) +{ + if (!fdb->added_by_user) + return; + + switch (type) { + case RTM_DELNEIGH: + br_switchdev_fdb_call_notifiers(false, fdb->addr.addr, + fdb->vlan_id, + fdb->dst->dev); + break; + case RTM_NEWNEIGH: + br_switchdev_fdb_call_notifiers(true, fdb->addr.addr, + fdb->vlan_id, + fdb->dst->dev); + break; + } +} -- cgit v1.2.3 From 9fe8bcec0dbc19604acc3a2cd469febf96f0d59a Mon Sep 17 00:00:00 2001 From: Arkadi Sharshevsky Date: Thu, 8 Jun 2017 08:44:15 +0200 Subject: net: bridge: Receive notification about successful FDB offload When a new static FDB is added to the bridge a notification is sent to the driver for offload. In case of successful offload the driver should notify the bridge back, which in turn should mark the FDB as offloaded. Currently, externally learned is equivalent for being offloaded which is not correct due to the fact that FDBs which are added from user-space are also marked as externally learned. In order to specify if an FDB was successfully offloaded a new flag is introduced. Signed-off-by: Arkadi Sharshevsky Reviewed-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/switchdev.h | 1 + include/uapi/linux/neighbour.h | 1 + net/bridge/br.c | 11 ++++++++++- net/bridge/br_fdb.c | 22 +++++++++++++++++++++- net/bridge/br_private.h | 5 ++++- 5 files changed, 37 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 8165ed93c58b..c784a6ac6ef1 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -159,6 +159,7 @@ enum switchdev_notifier_type { SWITCHDEV_FDB_DEL_TO_BRIDGE, SWITCHDEV_FDB_ADD_TO_DEVICE, SWITCHDEV_FDB_DEL_TO_DEVICE, + SWITCHDEV_FDB_OFFLOADED, }; struct switchdev_notifier_info { diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index f3d16dbe09d6..3199d28980b3 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -41,6 +41,7 @@ enum { #define NTF_MASTER 0x04 #define NTF_PROXY 0x08 /* == ATF_PUBL */ #define NTF_EXT_LEARNED 0x10 +#define NTF_OFFLOADED 0x20 #define NTF_ROUTER 0x80 /* diff --git a/net/bridge/br.c b/net/bridge/br.c index 96d209caf6db..1407d1ba7577 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -142,8 +142,12 @@ static int br_switchdev_event(struct notifier_block *unused, fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, fdb_info->vid); - if (err) + if (err) { err = notifier_from_errno(err); + break; + } + br_fdb_offloaded_set(br, p, fdb_info->addr, + fdb_info->vid); break; case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = ptr; @@ -152,6 +156,11 @@ static int br_switchdev_event(struct notifier_block *unused, if (err) err = notifier_from_errno(err); break; + case SWITCHDEV_FDB_OFFLOADED: + fdb_info = ptr; + br_fdb_offloaded_set(br, p, fdb_info->addr, + fdb_info->vid); + break; } out: diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 26a1dae2d434..fef7872a320b 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -511,6 +511,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, fdb->is_static = is_static; fdb->added_by_user = 0; fdb->added_by_external_learn = 0; + fdb->offloaded = 0; fdb->updated = fdb->used = jiffies; hlist_add_head_rcu(&fdb->hlist, head); } @@ -647,11 +648,16 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_family = AF_BRIDGE; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = fdb->added_by_external_learn ? NTF_EXT_LEARNED : 0; + ndm->ndm_flags = 0; ndm->ndm_type = 0; ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex; ndm->ndm_state = fdb_to_nud(br, fdb); + if (fdb->offloaded) + ndm->ndm_flags |= NTF_OFFLOADED; + if (fdb->added_by_external_learn) + ndm->ndm_flags |= NTF_EXT_LEARNED; + if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr)) goto nla_put_failure; if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex)) @@ -1123,3 +1129,17 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, return err; } + +void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p, + const unsigned char *addr, u16 vid) +{ + struct net_bridge_fdb_entry *fdb; + + spin_lock_bh(&br->hash_lock); + + fdb = br_fdb_find(br, addr, vid); + if (fdb) + fdb->offloaded = 1; + + spin_unlock_bh(&br->hash_lock); +} diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 98410ea032cb..c18682f804a0 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -169,7 +169,8 @@ struct net_bridge_fdb_entry { unsigned char is_local:1, is_static:1, added_by_user:1, - added_by_external_learn:1; + added_by_external_learn:1, + offloaded:1; /* write-heavy members should not affect lookups */ unsigned long updated ____cacheline_aligned_in_smp; @@ -536,6 +537,8 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid); int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid); +void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p, + const unsigned char *addr, u16 vid); /* br_forward.c */ enum br_pkt_type { -- cgit v1.2.3 From 3ad7d2468f79fc13215eb941f766a692d34b1381 Mon Sep 17 00:00:00 2001 From: Krister Johansen Date: Thu, 8 Jun 2017 13:12:14 -0700 Subject: Ipvlan should return an error when an address is already in use. The ipvlan code already knows how to detect when a duplicate address is about to be assigned to an ipvlan device. However, that failure is not propogated outward and leads to a silent failure. Introduce a validation step at ip address creation time and allow device drivers to register to validate the incoming ip addresses. The ipvlan code is the first consumer. If it detects an address in use, we can return an error to the user before beginning to commit the new ifa in the networking code. This can be especially useful if it is necessary to provision many ipvlans in containers. The provisioning software (or operator) can use this to detect situations where an ip address is unexpectedly in use. Signed-off-by: Krister Johansen Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_main.c | 69 ++++++++++++++++++++++++++++++++++++++++ include/linux/inetdevice.h | 7 ++++ include/net/addrconf.h | 10 +++++- net/ipv4/devinet.c | 33 +++++++++++++++++++ net/ipv6/addrconf.c | 17 +++++++++- net/ipv6/addrconf_core.c | 19 +++++++++++ 6 files changed, 153 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 618ed88fad0f..e4141d62b5c3 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -824,6 +824,33 @@ static int ipvlan_addr6_event(struct notifier_block *unused, return NOTIFY_OK; } +static int ipvlan_addr6_validator_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct in6_validator_info *i6vi = (struct in6_validator_info *)ptr; + struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev; + struct ipvl_dev *ipvlan = netdev_priv(dev); + + /* FIXME IPv6 autoconf calls us from bh without RTNL */ + if (in_softirq()) + return NOTIFY_DONE; + + if (!netif_is_ipvlan(dev)) + return NOTIFY_DONE; + + if (!ipvlan || !ipvlan->port) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_UP: + if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) + return notifier_from_errno(-EADDRINUSE); + break; + } + + return NOTIFY_OK; +} + static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) { @@ -871,10 +898,37 @@ static int ipvlan_addr4_event(struct notifier_block *unused, return NOTIFY_OK; } +static int ipvlan_addr4_validator_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct in_validator_info *ivi = (struct in_validator_info *)ptr; + struct net_device *dev = (struct net_device *)ivi->ivi_dev->dev; + struct ipvl_dev *ipvlan = netdev_priv(dev); + + if (!netif_is_ipvlan(dev)) + return NOTIFY_DONE; + + if (!ipvlan || !ipvlan->port) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_UP: + if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) + return notifier_from_errno(-EADDRINUSE); + break; + } + + return NOTIFY_OK; +} + static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = { .notifier_call = ipvlan_addr4_event, }; +static struct notifier_block ipvlan_addr4_vtor_notifier_block __read_mostly = { + .notifier_call = ipvlan_addr4_validator_event, +}; + static struct notifier_block ipvlan_notifier_block __read_mostly = { .notifier_call = ipvlan_device_event, }; @@ -883,6 +937,10 @@ static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_event, }; +static struct notifier_block ipvlan_addr6_vtor_notifier_block __read_mostly = { + .notifier_call = ipvlan_addr6_validator_event, +}; + static void ipvlan_ns_exit(struct net *net) { struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); @@ -907,7 +965,10 @@ static int __init ipvlan_init_module(void) ipvlan_init_secret(); register_netdevice_notifier(&ipvlan_notifier_block); register_inet6addr_notifier(&ipvlan_addr6_notifier_block); + register_inet6addr_validator_notifier( + &ipvlan_addr6_vtor_notifier_block); register_inetaddr_notifier(&ipvlan_addr4_notifier_block); + register_inetaddr_validator_notifier(&ipvlan_addr4_vtor_notifier_block); err = register_pernet_subsys(&ipvlan_net_ops); if (err < 0) @@ -922,7 +983,11 @@ static int __init ipvlan_init_module(void) return 0; error: unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); + unregister_inetaddr_validator_notifier( + &ipvlan_addr4_vtor_notifier_block); unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); + unregister_inet6addr_validator_notifier( + &ipvlan_addr6_vtor_notifier_block); unregister_netdevice_notifier(&ipvlan_notifier_block); return err; } @@ -933,7 +998,11 @@ static void __exit ipvlan_cleanup_module(void) unregister_pernet_subsys(&ipvlan_net_ops); unregister_netdevice_notifier(&ipvlan_notifier_block); unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); + unregister_inetaddr_validator_notifier( + &ipvlan_addr4_vtor_notifier_block); unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); + unregister_inet6addr_validator_notifier( + &ipvlan_addr6_vtor_notifier_block); } module_init(ipvlan_init_module); diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index a2e9d6ea1349..e7c04c4e4bcd 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -150,8 +150,15 @@ struct in_ifaddr { unsigned long ifa_tstamp; /* updated timestamp */ }; +struct in_validator_info { + __be32 ivi_addr; + struct in_device *ivi_dev; +}; + int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); +int register_inetaddr_validator_notifier(struct notifier_block *nb); +int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index b43a4eec3cec..d0889cb50172 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -48,11 +48,15 @@ struct prefix_info { struct in6_addr prefix; }; - #include #include #include +struct in6_validator_info { + struct in6_addr i6vi_addr; + struct inet6_dev *i6vi_dev; +}; + #define IN6_ADDR_HSIZE_SHIFT 4 #define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT) @@ -278,6 +282,10 @@ int register_inet6addr_notifier(struct notifier_block *nb); int unregister_inet6addr_notifier(struct notifier_block *nb); int inet6addr_notifier_call_chain(unsigned long val, void *v); +int register_inet6addr_validator_notifier(struct notifier_block *nb); +int unregister_inet6addr_validator_notifier(struct notifier_block *nb); +int inet6addr_validator_notifier_call_chain(unsigned long val, void *v); + void inet6_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv6_devconf *devconf); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index df14815a3b8c..a7dd088d5fc9 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -176,6 +176,7 @@ EXPORT_SYMBOL(__ip_dev_find); static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); +static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, int destroy); #ifdef CONFIG_SYSCTL @@ -441,6 +442,8 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1, **ifap, **last_primary; + struct in_validator_info ivi; + int ret; ASSERT_RTNL(); @@ -471,6 +474,23 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, } } + /* Allow any devices that wish to register ifaddr validtors to weigh + * in now, before changes are committed. The rntl lock is serializing + * access here, so the state should not change between a validator call + * and a final notify on commit. This isn't invoked on promotion under + * the assumption that validators are checking the address itself, and + * not the flags. + */ + ivi.ivi_addr = ifa->ifa_address; + ivi.ivi_dev = ifa->ifa_dev; + ret = blocking_notifier_call_chain(&inetaddr_validator_chain, + NETDEV_UP, &ivi); + ret = notifier_to_errno(ret); + if (ret) { + inet_free_ifa(ifa); + return ret; + } + if (!(ifa->ifa_flags & IFA_F_SECONDARY)) { prandom_seed((__force u32) ifa->ifa_local); ifap = last_primary; @@ -1356,6 +1376,19 @@ int unregister_inetaddr_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_inetaddr_notifier); +int register_inetaddr_validator_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&inetaddr_validator_chain, nb); +} +EXPORT_SYMBOL(register_inetaddr_validator_notifier); + +int unregister_inetaddr_validator_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&inetaddr_validator_chain, + nb); +} +EXPORT_SYMBOL(unregister_inetaddr_validator_notifier); + /* Rename ifa_labels for a device name change. Make some effort to preserve * existing alias numbering and to create unique labels if possible. */ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 25443fd946a8..0aa36b093013 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -963,6 +963,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; struct rt6_info *rt; + struct in6_validator_info i6vi; unsigned int hash; int err = 0; int addr_type = ipv6_addr_type(addr); @@ -974,6 +975,9 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, return ERR_PTR(-EADDRNOTAVAIL); rcu_read_lock_bh(); + + in6_dev_hold(idev); + if (idev->dead) { err = -ENODEV; /*XXX*/ goto out2; @@ -984,6 +988,17 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, goto out2; } + i6vi.i6vi_addr = *addr; + i6vi.i6vi_dev = idev; + rcu_read_unlock_bh(); + + err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); + + rcu_read_lock_bh(); + err = notifier_to_errno(err); + if (err) + goto out2; + spin_lock(&addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ @@ -1034,7 +1049,6 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->rt = rt; ifa->idev = idev; - in6_dev_hold(idev); /* For caller */ in6_ifa_hold(ifa); @@ -1062,6 +1076,7 @@ out2: inet6addr_notifier_call_chain(NETDEV_UP, ifa); else { kfree(ifa); + in6_dev_put(idev); ifa = ERR_PTR(err); } diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index bfa941fc1165..9e3488d50b15 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -88,6 +88,7 @@ int __ipv6_addr_type(const struct in6_addr *addr) EXPORT_SYMBOL(__ipv6_addr_type); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); +static ATOMIC_NOTIFIER_HEAD(inet6addr_validator_chain); int register_inet6addr_notifier(struct notifier_block *nb) { @@ -107,6 +108,24 @@ int inet6addr_notifier_call_chain(unsigned long val, void *v) } EXPORT_SYMBOL(inet6addr_notifier_call_chain); +int register_inet6addr_validator_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&inet6addr_validator_chain, nb); +} +EXPORT_SYMBOL(register_inet6addr_validator_notifier); + +int unregister_inet6addr_validator_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&inet6addr_validator_chain, nb); +} +EXPORT_SYMBOL(unregister_inet6addr_validator_notifier); + +int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&inet6addr_validator_chain, val, v); +} +EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); + static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1, struct dst_entry **u2, struct flowi6 *u3) -- cgit v1.2.3 From 91b5ab628929d97357108594610e7c07be93e2fd Mon Sep 17 00:00:00 2001 From: Eliad Peller Date: Fri, 9 Jun 2017 13:08:42 +0100 Subject: cfg80211: support 4-way handshake offloading for WPA/WPA2-PSK Let drivers advertise support for station-mode 4-way handshake offloading with a new NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK flag. Extend use of NL80211_ATTR_PMK attribute indicating it might be passed as part of NL80211_CMD_CONNECT command, and contain the PSK (which is the PMK, hence the name.) The driver/device is assumed to handle the 4-way handshake by itself in this case (including key derivations, etc.), instead of relying on the supplicant. This patch is somewhat based on this one (by Vladimir Kondratiev): https://patchwork.kernel.org/patch/1309561/. Signed-off-by: Vladimir Kondratiev Signed-off-by: Eliad Peller Signed-off-by: Luca Coelho [arend.vanspriel@broadcom.com rebase dealing with existing ATTR_PMK] Signed-off-by: Arend van Spriel [reword NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK docs to indicate that this offload might be required] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + include/net/cfg80211.h | 2 ++ include/uapi/linux/nl80211.h | 22 ++++++++++++++++++++-- net/wireless/nl80211.c | 9 +++++++++ 4 files changed, 32 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 69033353d0d1..e97ca3a9a67b 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2401,6 +2401,7 @@ enum ieee80211_sa_query_action { #define WLAN_MAX_KEY_LEN 32 #define WLAN_PMKID_LEN 16 +#define WLAN_PMK_LEN 32 #define WLAN_OUI_WFA 0x506f9a #define WLAN_OUI_TYPE_WFA_P2P 9 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index fa25fbb67cb6..1b288bac5d1a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -649,6 +649,7 @@ struct survey_info { * @wep_keys: static WEP keys, if not NULL points to an array of * CFG80211_MAX_WEP_KEYS WEP keys * @wep_tx_key: key index (0..3) of the default TX static WEP key + * @psk: PSK (for devices supporting 4-way-handshake offload) */ struct cfg80211_crypto_settings { u32 wpa_versions; @@ -662,6 +663,7 @@ struct cfg80211_crypto_settings { bool control_port_no_encrypt; struct key_params *wep_keys; int wep_tx_key; + const u8 *psk; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index b8c44b98f12d..f1f7da25bca4 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -172,6 +172,18 @@ * Multiple such rules can be created. */ +/** + * DOC: WPA/WPA2 EAPOL handshake offload + * + * By setting @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK flag drivers + * can indicate they support offloading EAPOL handshakes for WPA/WPA2 + * preshared key authentication. In %NL80211_CMD_CONNECT the preshared + * key should be specified using %NL80211_ATTR_PMK. Drivers supporting + * this offload may reject the %NL80211_CMD_CONNECT when no preshared + * key material is provided, for example when that driver does not + * support setting the temporal keys through %CMD_NEW_KEY. + */ + /** * DOC: FILS shared key authentication offload * @@ -2080,8 +2092,10 @@ enum nl80211_commands { * identifying the scope of PMKSAs. This is used with * @NL80211_CMD_SET_PMKSA and @NL80211_CMD_DEL_PMKSA. * - * @NL80211_ATTR_PMK: PMK for the PMKSA identified by %NL80211_ATTR_PMKID. - * This is used with @NL80211_CMD_SET_PMKSA. + * @NL80211_ATTR_PMK: attribute for passing PMK key material. Used with + * %NL80211_CMD_SET_PMKSA for the PMKSA identified by %NL80211_ATTR_PMKID. + * For %NL80211_CMD_CONNECT it is used to provide PSK for offloading 4-way + * handshake for WPA/WPA2-PSK networks. * * @NL80211_ATTR_SCHED_SCAN_MULTI: flag attribute which user-space shall use to * indicate that it supports multiple active scheduled scan requests. @@ -4852,6 +4866,9 @@ enum nl80211_feature_flags { * RSSI threshold values to monitor rather than exactly one threshold. * @NL80211_EXT_FEATURE_FILS_SK_OFFLOAD: Driver SME supports FILS shared key * authentication with %NL80211_CMD_CONNECT. + * @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK: Device wants to do 4-way + * handshake with PSK in station mode (PSK is passed as part of the connect + * and associate commands), doing it in the host might not be supported. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4872,6 +4889,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SCHED_SCAN_RELATIVE_RSSI, NL80211_EXT_FEATURE_CQM_RSSI_LIST, NL80211_EXT_FEATURE_FILS_SK_OFFLOAD, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9eb59196a378..2c6863aee4e4 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -8168,6 +8168,15 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev, memcpy(settings->akm_suites, data, len); } + if (info->attrs[NL80211_ATTR_PMK]) { + if (nla_len(info->attrs[NL80211_ATTR_PMK]) != WLAN_PMK_LEN) + return -EINVAL; + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK)) + return -EINVAL; + settings->psk = nla_data(info->attrs[NL80211_ATTR_PMK]); + } + return 0; } -- cgit v1.2.3 From 3a00df5707b6af715e78c26569800e0c2eb615fe Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Fri, 9 Jun 2017 13:08:43 +0100 Subject: cfg80211: support 4-way handshake offloading for 802.1X Add API for setting the PMK to the driver. For FT support, allow setting also the PMK-R0 Name. This can be used by drivers that support 4-Way handshake offload while IEEE802.1X authentication is managed by upper layers. Signed-off-by: Avraham Stern Signed-off-by: Johannes Berg [arend.vanspriel@broadcom.com: add WANT_1X_4WAY_HS attribute] Signed-off-by: Arend van Spriel [reword NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X docs a bit to say that the device may require it] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 ++ include/net/cfg80211.h | 32 +++++++++++++ include/uapi/linux/nl80211.h | 39 +++++++++++++++- net/wireless/core.c | 5 +++ net/wireless/nl80211.c | 105 +++++++++++++++++++++++++++++++++++++++++++ net/wireless/rdev-ops.h | 25 +++++++++++ net/wireless/trace.h | 60 +++++++++++++++++++++++++ 7 files changed, 268 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index e97ca3a9a67b..34e1bcd2d7ff 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2400,8 +2400,11 @@ enum ieee80211_sa_query_action { #define WLAN_MAX_KEY_LEN 32 +#define WLAN_PMK_NAME_LEN 16 #define WLAN_PMKID_LEN 16 +#define WLAN_PMK_LEN_EAP_LEAP 16 #define WLAN_PMK_LEN 32 +#define WLAN_PMK_LEN_SUITE_B_192 48 #define WLAN_OUI_WFA 0x506f9a #define WLAN_OUI_TYPE_WFA_P2P 9 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1b288bac5d1a..2174e51c6595 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2112,6 +2112,8 @@ struct cfg80211_bss_selection { * @fils_erp_rrk: ERP re-authentication Root Key (rRK) used to derive additional * keys in FILS or %NULL if not specified. * @fils_erp_rrk_len: Length of @fils_erp_rrk in octets. + * @want_1x: indicates user-space supports and wants to use 802.1X driver + * offload of 4-way handshake. */ struct cfg80211_connect_params { struct ieee80211_channel *channel; @@ -2144,6 +2146,7 @@ struct cfg80211_connect_params { u16 fils_erp_next_seq_num; const u8 *fils_erp_rrk; size_t fils_erp_rrk_len; + bool want_1x; }; /** @@ -2565,6 +2568,23 @@ struct cfg80211_nan_func { u64 cookie; }; +/** + * struct cfg80211_pmk_conf - PMK configuration + * + * @aa: authenticator address + * @pmk_len: PMK length in bytes. + * @pmk: the PMK material + * @pmk_r0_name: PMK-R0 Name. NULL if not applicable (i.e., the PMK + * is not PMK-R0). When pmk_r0_name is not NULL, the pmk field + * holds PMK-R0. + */ +struct cfg80211_pmk_conf { + const u8 *aa; + u8 pmk_len; + const u8 *pmk; + const u8 *pmk_r0_name; +}; + /** * struct cfg80211_ops - backend description for wireless configuration * @@ -2881,6 +2901,13 @@ struct cfg80211_nan_func { * All other parameters must be ignored. * * @set_multicast_to_unicast: configure multicast to unicast conversion for BSS + * + * @set_pmk: configure the PMK to be used for offloaded 802.1X 4-Way handshake. + * If not deleted through @del_pmk the PMK remains valid until disconnect + * upon which the driver should clear it. + * (invoked with the wireless_dev mutex held) + * @del_pmk: delete the previously configured PMK for the given authenticator. + * (invoked with the wireless_dev mutex held) */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -3169,6 +3196,11 @@ struct cfg80211_ops { int (*set_multicast_to_unicast)(struct wiphy *wiphy, struct net_device *dev, const bool enabled); + + int (*set_pmk)(struct wiphy *wiphy, struct net_device *dev, + const struct cfg80211_pmk_conf *conf); + int (*del_pmk)(struct wiphy *wiphy, struct net_device *dev, + const u8 *aa); }; /* diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f1f7da25bca4..073e26850195 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -182,6 +182,17 @@ * this offload may reject the %NL80211_CMD_CONNECT when no preshared * key material is provided, for example when that driver does not * support setting the temporal keys through %CMD_NEW_KEY. + * + * Similarly @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X flag can be + * set by drivers indicating offload support of the PTK/GTK EAPOL + * handshakes during 802.1X authentication. In order to use the offload + * the %NL80211_CMD_CONNECT should have %NL80211_ATTR_WANT_1X_4WAY_HS + * attribute flag. Drivers supporting this offload may reject the + * %NL80211_CMD_CONNECT when the attribute flag is not present. + * + * For 802.1X the PMK or PMK-R0 are set by providing %NL80211_ATTR_PMK + * using %NL80211_CMD_SET_PMK. For offloaded FT support also + * %NL80211_ATTR_PMKR0_NAME must be provided. */ /** @@ -959,6 +970,14 @@ * does not result in a change for the current association. Currently, * only the %NL80211_ATTR_IE data is used and updated with this command. * + * @NL80211_CMD_SET_PMK: For offloaded 4-Way handshake, set the PMK or PMK-R0 + * for the given authenticator address (specified with &NL80211_ATTR_MAC). + * When &NL80211_ATTR_PMKR0_NAME is set, &NL80211_ATTR_PMK specifies the + * PMK-R0, otherwise it specifies the PMK. + * @NL80211_CMD_DEL_PMK: For offloaded 4-Way handshake, delete the previously + * configured PMK for the authenticator address identified by + * &NL80211_ATTR_MAC. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1158,6 +1177,9 @@ enum nl80211_commands { NL80211_CMD_UPDATE_CONNECT_PARAMS, + NL80211_CMD_SET_PMK, + NL80211_CMD_DEL_PMK, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2095,13 +2117,20 @@ enum nl80211_commands { * @NL80211_ATTR_PMK: attribute for passing PMK key material. Used with * %NL80211_CMD_SET_PMKSA for the PMKSA identified by %NL80211_ATTR_PMKID. * For %NL80211_CMD_CONNECT it is used to provide PSK for offloading 4-way - * handshake for WPA/WPA2-PSK networks. + * handshake for WPA/WPA2-PSK networks. For 802.1X authentication it is + * used with %NL80211_CMD_SET_PMK. For offloaded FT support this attribute + * specifies the PMK-R0 if NL80211_ATTR_PMKR0_NAME is included as well. * * @NL80211_ATTR_SCHED_SCAN_MULTI: flag attribute which user-space shall use to * indicate that it supports multiple active scheduled scan requests. * @NL80211_ATTR_SCHED_SCAN_MAX_REQS: indicates maximum number of scheduled * scan request that may be active for the device (u32). * + * @NL80211_ATTR_WANT_1X_4WAY_HS: flag attribute which user-space can include + * in %NL80211_CMD_CONNECT to indicate that for 802.1X authentication it + * wants to use the supported offload of the 4-way handshake. + * @NL80211_ATTR_PMKR0_NAME: PMK-R0 Name for offloaded FT. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2524,6 +2553,9 @@ enum nl80211_attrs { NL80211_ATTR_SCHED_SCAN_MULTI, NL80211_ATTR_SCHED_SCAN_MAX_REQS, + NL80211_ATTR_WANT_1X_4WAY_HS, + NL80211_ATTR_PMKR0_NAME, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -4869,6 +4901,10 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK: Device wants to do 4-way * handshake with PSK in station mode (PSK is passed as part of the connect * and associate commands), doing it in the host might not be supported. + * @NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X: Device wants to do doing 4-way + * handshake with 802.1X in station mode (will pass EAP frames to the host + * and accept the set_pmk/del_pmk commands), doing it in the host might not + * be supported. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4890,6 +4926,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_CQM_RSSI_LIST, NL80211_EXT_FEATURE_FILS_SK_OFFLOAD, NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_PSK, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/core.c b/net/wireless/core.c index 83ea164f16b3..7b33e8c366bc 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -711,6 +711,11 @@ int wiphy_register(struct wiphy *wiphy) (wiphy->bss_select_support & ~(BIT(__NL80211_BSS_SELECT_ATTR_AFTER_LAST) - 2)))) return -EINVAL; + if (WARN_ON(wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X) && + (!rdev->ops->set_pmk || !rdev->ops->del_pmk))) + return -EINVAL; + if (wiphy->addresses) memcpy(wiphy->perm_addr, wiphy->addresses[0].addr, ETH_ALEN); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2c6863aee4e4..8148b01bcdd2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -8881,6 +8881,12 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) connect.privacy = info->attrs[NL80211_ATTR_PRIVACY]; + if (info->attrs[NL80211_ATTR_WANT_1X_4WAY_HS] && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X)) + return -EINVAL; + connect.want_1x = info->attrs[NL80211_ATTR_WANT_1X_4WAY_HS]; + err = nl80211_crypto_settings(rdev, info, &connect.crypto, NL80211_MAX_NR_CIPHER_SUITES); if (err) @@ -12265,6 +12271,90 @@ static int nl80211_set_multicast_to_unicast(struct sk_buff *skb, return rdev_set_multicast_to_unicast(rdev, dev, enabled); } +static int nl80211_set_pmk(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 cfg80211_pmk_conf pmk_conf = {}; + int ret; + + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; + + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X)) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_MAC] || !info->attrs[NL80211_ATTR_PMK]) + return -EINVAL; + + wdev_lock(wdev); + if (!wdev->current_bss) { + ret = -ENOTCONN; + goto out; + } + + pmk_conf.aa = nla_data(info->attrs[NL80211_ATTR_MAC]); + if (memcmp(pmk_conf.aa, wdev->current_bss->pub.bssid, ETH_ALEN)) { + ret = -EINVAL; + goto out; + } + + pmk_conf.pmk = nla_data(info->attrs[NL80211_ATTR_PMK]); + pmk_conf.pmk_len = nla_len(info->attrs[NL80211_ATTR_PMK]); + if (pmk_conf.pmk_len != WLAN_PMK_LEN && + pmk_conf.pmk_len != WLAN_PMK_LEN_SUITE_B_192) { + ret = -EINVAL; + goto out; + } + + if (info->attrs[NL80211_ATTR_PMKR0_NAME]) { + int r0_name_len = nla_len(info->attrs[NL80211_ATTR_PMKR0_NAME]); + + if (r0_name_len != WLAN_PMK_NAME_LEN) { + ret = -EINVAL; + goto out; + } + + pmk_conf.pmk_r0_name = + nla_data(info->attrs[NL80211_ATTR_PMKR0_NAME]); + } + + ret = rdev_set_pmk(rdev, dev, &pmk_conf); +out: + wdev_unlock(wdev); + return ret; +} + +static int nl80211_del_pmk(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; + const u8 *aa; + int ret; + + if (wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) + return -EOPNOTSUPP; + + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_4WAY_HANDSHAKE_STA_1X)) + return -EOPNOTSUPP; + + if (!info->attrs[NL80211_ATTR_MAC]) + return -EINVAL; + + wdev_lock(wdev); + aa = nla_data(info->attrs[NL80211_ATTR_MAC]); + ret = rdev_del_pmk(rdev, dev, aa); + wdev_unlock(wdev); + + return ret; +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -13140,6 +13230,21 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV | NL80211_FLAG_NEED_RTNL, }, + { + .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, + }, + }; static struct genl_family nl80211_fam __ro_after_init = { diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 0598c1e5d0ad..ce23d7d49960 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1164,4 +1164,29 @@ rdev_set_coalesce(struct cfg80211_registered_device *rdev, trace_rdev_return_int(&rdev->wiphy, ret); return ret; } + +static inline int rdev_set_pmk(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_pmk_conf *pmk_conf) +{ + int ret = -EOPNOTSUPP; + + trace_rdev_set_pmk(&rdev->wiphy, dev, pmk_conf); + if (rdev->ops->set_pmk) + ret = rdev->ops->set_pmk(&rdev->wiphy, dev, pmk_conf); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_del_pmk(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *aa) +{ + int ret = -EOPNOTSUPP; + + trace_rdev_del_pmk(&rdev->wiphy, dev, aa); + if (rdev->ops->del_pmk) + ret = rdev->ops->del_pmk(&rdev->wiphy, dev, aa); + 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 ca8b2059f92c..0f8db41eaddb 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2258,6 +2258,66 @@ TRACE_EVENT(rdev_tdls_cancel_channel_switch, WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(addr)) ); +TRACE_EVENT(rdev_set_pmk, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_pmk_conf *pmk_conf), + + TP_ARGS(wiphy, netdev, pmk_conf), + + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(aa) + __field(u8, pmk_len) + __field(u8, pmk_r0_name_len) + __dynamic_array(u8, pmk, pmk_conf->pmk_len) + __dynamic_array(u8, pmk_r0_name, WLAN_PMK_NAME_LEN) + ), + + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(aa, pmk_conf->aa); + __entry->pmk_len = pmk_conf->pmk_len; + __entry->pmk_r0_name_len = + pmk_conf->pmk_r0_name ? WLAN_PMK_NAME_LEN : 0; + memcpy(__get_dynamic_array(pmk), pmk_conf->pmk, + pmk_conf->pmk_len); + memcpy(__get_dynamic_array(pmk_r0_name), pmk_conf->pmk_r0_name, + pmk_conf->pmk_r0_name ? WLAN_PMK_NAME_LEN : 0); + ), + + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT + "pmk_len=%u, pmk: %s pmk_r0_name: %s", WIPHY_PR_ARG, + NETDEV_PR_ARG, MAC_PR_ARG(aa), __entry->pmk_len, + __print_array(__get_dynamic_array(pmk), + __get_dynamic_array_len(pmk), 1), + __entry->pmk_r0_name_len ? + __print_array(__get_dynamic_array(pmk_r0_name), + __get_dynamic_array_len(pmk_r0_name), 1) : "") +); + +TRACE_EVENT(rdev_del_pmk, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *aa), + + TP_ARGS(wiphy, netdev, aa), + + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(aa) + ), + + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(aa, aa); + ), + + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(aa)) +); + /************************************************************* * cfg80211 exported functions traces * *************************************************************/ -- cgit v1.2.3 From f45cbe6e691fcdeda480ecc9c66533a8277f0ca4 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Fri, 9 Jun 2017 13:08:45 +0100 Subject: nl80211: add authorized flag to ROAM event Drivers that initiate roaming while being connected to a network that uses 802.1X authentication need to inform user space if 802.1X authentication is further required after roaming. For example, when using the Fast transition protocol, roaming within the mobility domain does not require new 802.1X authentication, but roaming to another mobility domain does. In addition, some drivers may not support 802.1X authentication (so it has to be done in user space), while other drivers do. Add a flag to the roaming notification to indicate if user space is required to do 802.1X authentication after the roaming or not. This flag will only be used for networks that use 802.1X authentication. For networks that do not use 802.1X authentication it is assumed that no further action is required from user space after the roaming notification. Signed-off-by: Avraham Stern Signed-off-by: Luca Coelho [arend.vanspriel@broadcom.com reuse NL80211_ATTR_PORT_AUTHORIZED] Signed-off-by: Arend van Spriel [rebase to apply w/o the flag in CONNECT] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 4 ++++ include/uapi/linux/nl80211.h | 11 +++++++++++ net/wireless/nl80211.c | 4 +++- net/wireless/sme.c | 1 + 4 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 2174e51c6595..f12fa5245a45 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5441,6 +5441,9 @@ cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) * @resp_ie_len: assoc response IEs length + * @authorized: true if the 802.1X authentication was done by the driver or is + * not needed (e.g., when Fast Transition protocol was used), false + * otherwise. Ignored for networks that don't use 802.1X authentication. */ struct cfg80211_roam_info { struct ieee80211_channel *channel; @@ -5450,6 +5453,7 @@ struct cfg80211_roam_info { size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; + bool authorized; }; /** diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 073e26850195..72f15c3fc5a6 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -571,6 +571,12 @@ * well to remain backwards compatible. * @NL80211_CMD_ROAM: request that the card roam (currently not implemented), * sent as an event when the card/driver roamed by itself. + * When used as an event, and the driver roamed in a network that requires + * 802.1X authentication, %NL80211_ATTR_PORT_AUTHORIZED should be set + * if the 802.1X authentication was done by the driver or if roaming was + * done using Fast Transition protocol (in which case 802.1X authentication + * is not needed). If %NL80211_ATTR_PORT_AUTHORIZED is not set, user space + * is responsible for the 802.1X authentication. * @NL80211_CMD_DISCONNECT: drop a given connection; also used to notify * userspace that a connection was dropped by the AP or due to other * reasons, for this the %NL80211_ATTR_DISCONNECTED_BY_AP and @@ -2130,6 +2136,10 @@ enum nl80211_commands { * in %NL80211_CMD_CONNECT to indicate that for 802.1X authentication it * wants to use the supported offload of the 4-way handshake. * @NL80211_ATTR_PMKR0_NAME: PMK-R0 Name for offloaded FT. + * @NL80211_ATTR_PORT_AUTHORIZED: flag attribute used in %NL80211_CMD_ROAMED + * notification indicating that that 802.1X authentication was done by + * the driver or is not needed (because roaming used the Fast Transition + * protocol). * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2555,6 +2565,7 @@ enum nl80211_attrs { NL80211_ATTR_WANT_1X_4WAY_HS, NL80211_ATTR_PMKR0_NAME, + NL80211_ATTR_PORT_AUTHORIZED, /* add attributes here, update the policy in nl80211.c */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8148b01bcdd2..5487cd775b6f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13800,7 +13800,9 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, info->req_ie)) || (info->resp_ie && nla_put(msg, NL80211_ATTR_RESP_IE, info->resp_ie_len, - info->resp_ie))) + info->resp_ie)) || + (info->authorized && + nla_put_flag(msg, NL80211_ATTR_PORT_AUTHORIZED))) goto nla_put_failure; genlmsg_end(msg, hdr); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 532a0007ce82..0a49b88070d0 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -960,6 +960,7 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, ev->rm.resp_ie_len = info->resp_ie_len; memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); ev->rm.bss = info->bss; + ev->rm.authorized = info->authorized; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); -- cgit v1.2.3 From 6d3c8c0dd88a5ffc7e3695997641e4b6d4c11065 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 13 Jun 2017 13:27:19 -0700 Subject: net: dsa: Remove master_netdev and use dst->cpu_dp->netdev In preparation for supporting multiple CPU ports, remove dst->master_netdev and ds->master_netdev and replace them with only one instance of the common object we have for a port: struct dsa_port::netdev. ds->master_netdev is currently write only and would be helpful in the case where we have two switches, both with CPU ports, and also connected within each other, which the multi-CPU port patch series would address. While at it, introduce a helper function used in net/dsa/slave.c to immediately get a reference on the master network device called dsa_master_netdev(). Reviewed-by: Vivien Didelot Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/bcm_sf2.c | 4 ++-- drivers/net/dsa/mt7530.c | 4 ++-- include/net/dsa.h | 5 ----- net/dsa/dsa.c | 9 ++------- net/dsa/dsa2.c | 18 +++++++----------- net/dsa/dsa_priv.h | 5 +++++ net/dsa/legacy.c | 22 +++++++++++++--------- net/dsa/slave.c | 21 +++++++++------------ 8 files changed, 40 insertions(+), 48 deletions(-) (limited to 'include/net') diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 687a8bae5d73..76e98e8ed315 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -806,7 +806,7 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds) static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { - struct net_device *p = ds->dst[ds->index].master_netdev; + struct net_device *p = ds->dst[ds->index].cpu_dp->netdev; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); struct ethtool_wolinfo pwol; @@ -829,7 +829,7 @@ static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { - struct net_device *p = ds->dst[ds->index].master_netdev; + struct net_device *p = ds->dst[ds->index].cpu_dp->netdev; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); s8 cpu_port = ds->dst->cpu_dp->index; struct ethtool_wolinfo pwol; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 25e00d5e0eec..1e46418a3b74 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -912,11 +912,11 @@ mt7530_setup(struct dsa_switch *ds) struct device_node *dn; struct mt7530_dummy_poll p; - /* The parent node of master_netdev which holds the common system + /* The parent node of cpu_dp->netdev which holds the common system * controller also is the container for two GMACs nodes representing * as two netdev instances. */ - dn = ds->master_netdev->dev.of_node->parent; + dn = ds->dst->cpu_dp->netdev->dev.of_node->parent; priv->ethernet = syscon_node_to_regmap(dn); if (IS_ERR(priv->ethernet)) return PTR_ERR(priv->ethernet); diff --git a/include/net/dsa.h b/include/net/dsa.h index 2effb0af9d7c..b2fb53f5e28e 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -226,11 +226,6 @@ struct dsa_switch { */ s8 rtable[DSA_MAX_SWITCHES]; - /* - * The lower device this switch uses to talk to the host - */ - struct net_device *master_netdev; - /* * Slave mii_bus and devices for the individual ports. */ diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 517215391514..6aacc2314a8f 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -118,10 +118,7 @@ int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp) struct net_device *master; struct ethtool_ops *cpu_ops; - master = ds->dst->master_netdev; - if (ds->master_netdev) - master = ds->master_netdev; - + master = ds->dst->cpu_dp->netdev; cpu_ops = devm_kzalloc(ds->dev, sizeof(*cpu_ops), GFP_KERNEL); if (!cpu_ops) return -ENOMEM; @@ -142,9 +139,7 @@ void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp) struct dsa_switch *ds = cpu_dp->ds; struct net_device *master; - master = ds->dst->master_netdev; - if (ds->master_netdev) - master = ds->master_netdev; + master = ds->dst->cpu_dp->netdev; master->ethtool_ops = ds->dst->master_orig_ethtool_ops; } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index f88e1dddb74a..ab48c4f989da 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -337,7 +337,7 @@ static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) return err; if (ds->ops->set_addr) { - err = ds->ops->set_addr(ds, dst->master_netdev->dev_addr); + err = ds->ops->set_addr(ds, dst->cpu_dp->netdev->dev_addr); if (err < 0) return err; } @@ -444,7 +444,7 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst) * sent to the tag format's receive function. */ wmb(); - dst->master_netdev->dsa_ptr = dst; + dst->cpu_dp->netdev->dsa_ptr = dst; dst->applied = true; return 0; @@ -458,7 +458,7 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) if (!dst->applied) return; - dst->master_netdev->dsa_ptr = NULL; + dst->cpu_dp->netdev->dsa_ptr = NULL; /* If we used a tagging format that doesn't have an ethertype * field, make sure that all packets from this point get sent @@ -504,14 +504,10 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, if (!ethernet_dev) return -EPROBE_DEFER; - if (!ds->master_netdev) - ds->master_netdev = ethernet_dev; - - if (!dst->master_netdev) - dst->master_netdev = ethernet_dev; - - if (!dst->cpu_dp) + if (!dst->cpu_dp) { dst->cpu_dp = port; + dst->cpu_dp->netdev = ethernet_dev; + } tag_protocol = ds->ops->get_tag_protocol(ds); dst->tag_ops = dsa_resolve_tag_protocol(tag_protocol); @@ -578,7 +574,7 @@ static int dsa_dst_parse(struct dsa_switch_tree *dst) return err; } - if (!dst->master_netdev) { + if (!dst->cpu_dp->netdev) { pr_warn("Tree has no master device\n"); return -EINVAL; } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 66ee248796c8..5c510f4ba0ce 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -183,4 +183,9 @@ extern const struct dsa_device_ops qca_netdev_ops; /* tag_trailer.c */ extern const struct dsa_device_ops trailer_netdev_ops; +static inline struct net_device *dsa_master_netdev(struct dsa_slave_priv *p) +{ + return p->dp->ds->dst->cpu_dp->netdev; +} + #endif diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 3a56de8f51a8..5d4f6ffa3424 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -101,9 +101,12 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) struct dsa_switch_tree *dst = ds->dst; struct dsa_chip_data *cd = ds->cd; bool valid_name_found = false; + struct net_device *master; int index = ds->index; int i, ret; + master = dst->cpu_dp->netdev; + /* * Validate supplied switch configuration. */ @@ -116,7 +119,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) if (!strcmp(name, "cpu")) { if (dst->cpu_dp) { - netdev_err(dst->master_netdev, + netdev_err(master, "multiple cpu ports?!\n"); return -EINVAL; } @@ -168,7 +171,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) return ret; if (ops->set_addr) { - ret = ops->set_addr(ds, dst->master_netdev->dev_addr); + ret = ops->set_addr(ds, master->dev_addr); if (ret < 0) return ret; } @@ -195,14 +198,14 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) ret = dsa_slave_create(ds, parent, i, cd->port_names[i]); if (ret < 0) - netdev_err(dst->master_netdev, "[%d]: can't create dsa slave device for port %d(%s): %d\n", + 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, parent); if (ret < 0) - netdev_err(dst->master_netdev, "[%d] : can't configure CPU and DSA ports\n", + netdev_err(master, "[%d] : can't configure CPU and DSA ports\n", index); ret = dsa_cpu_port_ethtool_setup(ds->dst->cpu_dp); @@ -217,6 +220,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, struct device *parent, struct device *host_dev) { struct dsa_chip_data *cd = dst->pd->chip + index; + struct net_device *master = dst->cpu_dp->netdev; const struct dsa_switch_ops *ops; struct dsa_switch *ds; int ret; @@ -228,11 +232,11 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, */ ops = dsa_switch_probe(parent, host_dev, cd->sw_addr, &name, &priv); if (!ops) { - netdev_err(dst->master_netdev, "[%d]: could not detect attached switch\n", + netdev_err(master, "[%d]: could not detect attached switch\n", index); return ERR_PTR(-EINVAL); } - netdev_info(dst->master_netdev, "[%d]: detected a %s switch\n", + netdev_info(master, "[%d]: detected a %s switch\n", index, name); @@ -575,7 +579,7 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, unsigned configured = 0; dst->pd = pd; - dst->master_netdev = dev; + dst->cpu_dp->netdev = dev; for (i = 0; i < pd->nr_chips; i++) { struct dsa_switch *ds; @@ -671,7 +675,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) { int i; - dst->master_netdev->dsa_ptr = NULL; + dst->cpu_dp->netdev->dsa_ptr = NULL; /* If we used a tagging format that doesn't have an ethertype * field, make sure that all packets from this point get sent @@ -688,7 +692,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) dsa_cpu_port_ethtool_restore(dst->cpu_dp); - dev_put(dst->master_netdev); + dev_put(dst->cpu_dp->netdev); } static int dsa_remove(struct platform_device *pdev) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 5e45ae5c3f71..658bc67c5320 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -66,7 +66,7 @@ static int dsa_slave_get_iflink(const struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - return p->dp->ds->dst->master_netdev->ifindex; + return dsa_master_netdev(p)->ifindex; } static int dsa_slave_open(struct net_device *dev) @@ -74,7 +74,7 @@ static int dsa_slave_open(struct net_device *dev) struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_port *dp = p->dp; struct dsa_switch *ds = dp->ds; - struct net_device *master = ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING; int err; @@ -127,7 +127,7 @@ out: static int dsa_slave_close(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = p->dp->ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); struct dsa_switch *ds = p->dp->ds; if (p->phy) @@ -154,7 +154,7 @@ static int dsa_slave_close(struct net_device *dev) static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = p->dp->ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); if (change & IFF_ALLMULTI) dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); @@ -165,7 +165,7 @@ static void dsa_slave_change_rx_flags(struct net_device *dev, int change) static void dsa_slave_set_rx_mode(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = p->dp->ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); dev_mc_sync(master, dev); dev_uc_sync(master, dev); @@ -174,7 +174,7 @@ static void dsa_slave_set_rx_mode(struct net_device *dev) static int dsa_slave_set_mac_address(struct net_device *dev, void *a) { struct dsa_slave_priv *p = netdev_priv(dev); - struct net_device *master = p->dp->ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); struct sockaddr *addr = a; int err; @@ -375,7 +375,7 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ - nskb->dev = p->dp->ds->dst->master_netdev; + nskb->dev = dsa_master_netdev(p); dev_queue_xmit(nskb); return NETDEV_TX_OK; @@ -684,8 +684,7 @@ static int dsa_slave_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - struct net_device *master = ds->dst->master_netdev; + struct net_device *master = dsa_master_netdev(p); struct netpoll *netpoll; int err = 0; @@ -1143,9 +1142,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, struct dsa_slave_priv *p; int ret; - master = ds->dst->master_netdev; - if (ds->master_netdev) - master = ds->master_netdev; + master = ds->dst->cpu_dp->netdev; slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), name, NET_NAME_UNKNOWN, ether_setup); -- cgit v1.2.3 From 67dbb9d433447e358de7d293f15318bb5db9529b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 13 Jun 2017 13:27:20 -0700 Subject: net: dsa: Relocate master ethtool operations Relocate master_ethtool_ops and master_orig_ethtool_ops into struct dsa_port in order to be both consistent, and make things self contained within the dsa_port structure. This is a preliminary change to supporting multiple CPU port interfaces. Reviewed-by: Vivien Didelot Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 17 +++++------------ net/dsa/dsa.c | 16 ++++++---------- net/dsa/slave.c | 16 ++++++++-------- 3 files changed, 19 insertions(+), 30 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index b2fb53f5e28e..7e93869819f9 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -122,24 +122,12 @@ struct dsa_switch_tree { */ struct dsa_platform_data *pd; - /* - * Reference to network device to use, and which tagging - * protocol to use. - */ - struct net_device *master_netdev; - /* Copy of tag_ops->rcv for faster access in hot path */ struct sk_buff * (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); - /* - * Original copy of the master netdev ethtool_ops - */ - struct ethtool_ops master_ethtool_ops; - const struct ethtool_ops *master_orig_ethtool_ops; - /* * The switch port to which the CPU is attached. */ @@ -189,6 +177,11 @@ struct dsa_port { u8 stp_state; struct net_device *bridge_dev; struct devlink_port devlink_port; + /* + * Original copy of the master netdev ethtool_ops + */ + struct ethtool_ops ethtool_ops; + const struct ethtool_ops *orig_ethtool_ops; }; struct dsa_switch { diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 6aacc2314a8f..416ac4ef9ba9 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -118,15 +118,16 @@ int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp) struct net_device *master; struct ethtool_ops *cpu_ops; - master = ds->dst->cpu_dp->netdev; + master = cpu_dp->netdev; + cpu_ops = devm_kzalloc(ds->dev, sizeof(*cpu_ops), GFP_KERNEL); if (!cpu_ops) return -ENOMEM; - memcpy(&ds->dst->master_ethtool_ops, master->ethtool_ops, + memcpy(&cpu_dp->ethtool_ops, master->ethtool_ops, sizeof(struct ethtool_ops)); - ds->dst->master_orig_ethtool_ops = master->ethtool_ops; - memcpy(cpu_ops, &ds->dst->master_ethtool_ops, + cpu_dp->orig_ethtool_ops = master->ethtool_ops; + memcpy(cpu_ops, &cpu_dp->ethtool_ops, sizeof(struct ethtool_ops)); dsa_cpu_port_ethtool_init(cpu_ops); master->ethtool_ops = cpu_ops; @@ -136,12 +137,7 @@ int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp) void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp) { - struct dsa_switch *ds = cpu_dp->ds; - struct net_device *master; - - master = ds->dst->cpu_dp->netdev; - - master->ethtool_ops = ds->dst->master_orig_ethtool_ops; + cpu_dp->netdev->ethtool_ops = cpu_dp->orig_ethtool_ops; } void dsa_cpu_dsa_destroy(struct dsa_port *port) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 658bc67c5320..9bf4c27f3393 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -524,10 +524,10 @@ static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev, s8 cpu_port = dst->cpu_dp->index; int count = 0; - if (dst->master_ethtool_ops.get_sset_count) { - count = dst->master_ethtool_ops.get_sset_count(dev, + if (dst->cpu_dp->ethtool_ops.get_sset_count) { + count = dst->cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS); - dst->master_ethtool_ops.get_ethtool_stats(dev, stats, data); + dst->cpu_dp->ethtool_ops.get_ethtool_stats(dev, stats, data); } if (ds->ops->get_ethtool_stats) @@ -540,8 +540,8 @@ static int dsa_cpu_port_get_sset_count(struct net_device *dev, int sset) struct dsa_switch *ds = dst->cpu_dp->ds; int count = 0; - if (dst->master_ethtool_ops.get_sset_count) - count += dst->master_ethtool_ops.get_sset_count(dev, sset); + if (dst->cpu_dp->ethtool_ops.get_sset_count) + count += dst->cpu_dp->ethtool_ops.get_sset_count(dev, sset); if (sset == ETH_SS_STATS && ds->ops->get_sset_count) count += ds->ops->get_sset_count(ds); @@ -565,10 +565,10 @@ static void dsa_cpu_port_get_strings(struct net_device *dev, /* We do not want to be NULL-terminated, since this is a prefix */ pfx[sizeof(pfx) - 1] = '_'; - if (dst->master_ethtool_ops.get_sset_count) { - mcount = dst->master_ethtool_ops.get_sset_count(dev, + if (dst->cpu_dp->ethtool_ops.get_sset_count) { + mcount = dst->cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS); - dst->master_ethtool_ops.get_strings(dev, stringset, data); + dst->cpu_dp->ethtool_ops.get_strings(dev, stringset, data); } if (stringset == ETH_SS_STATS && ds->ops->get_strings) { -- cgit v1.2.3 From a29342e739115211615acc33616e547b2d3e0663 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 13 Jun 2017 13:27:21 -0700 Subject: net: dsa: Associate slave network device with CPU port In preparation for supporting multiple CPU ports with DSA, have the dsa_port structure know which CPU it is associated with. This will be important in order to make sure the correct CPU is used for transmission of the frames. If not for functional reasons, for performance (e.g: load balancing) and forwarding decisions. Reviewed-by: Vivien Didelot Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/net/dsa.h | 1 + net/dsa/dsa2.c | 11 +++++++++++ net/dsa/dsa_priv.h | 2 +- net/dsa/legacy.c | 1 + net/dsa/slave.c | 4 +++- 5 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/dsa.h b/include/net/dsa.h index 7e93869819f9..58969b9a090c 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -171,6 +171,7 @@ struct dsa_port { struct dsa_switch *ds; unsigned int index; const char *name; + struct dsa_port *cpu_dp; struct net_device *netdev; struct device_node *dn; unsigned int ageing_time; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index ab48c4f989da..52af8401af07 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -490,6 +490,8 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, enum dsa_tag_protocol tag_protocol; struct net_device *ethernet_dev; struct device_node *ethernet; + struct dsa_port *p; + unsigned int i; if (port->dn) { ethernet = of_parse_phandle(port->dn, "ethernet", 0); @@ -507,6 +509,15 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index, if (!dst->cpu_dp) { dst->cpu_dp = port; dst->cpu_dp->netdev = ethernet_dev; + + for (i = 0; i < ds->num_ports; i++) { + p = &ds->ports[i]; + if (!dsa_port_is_valid(p) || + i == index) + continue; + + p->cpu_dp = port; + } } tag_protocol = ds->ops->get_tag_protocol(ds); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 5c510f4ba0ce..7c2326f3b538 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -185,7 +185,7 @@ extern const struct dsa_device_ops trailer_netdev_ops; static inline struct net_device *dsa_master_netdev(struct dsa_slave_priv *p) { - return p->dp->ds->dst->cpu_dp->netdev; + return p->dp->cpu_dp->netdev; } #endif diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 5d4f6ffa3424..e60906125375 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -129,6 +129,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) ds->dsa_port_mask |= 1 << i; } else { ds->enabled_port_mask |= 1 << i; + ds->ports[i].cpu_dp = dst->cpu_dp; } valid_name_found = true; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 9bf4c27f3393..a80b46777a04 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1140,9 +1140,11 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, struct net_device *master; struct net_device *slave_dev; struct dsa_slave_priv *p; + struct dsa_port *cpu_dp; int ret; - master = ds->dst->cpu_dp->netdev; + cpu_dp = ds->dst->cpu_dp; + master = cpu_dp->netdev; slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), name, NET_NAME_UNKNOWN, ether_setup); -- cgit v1.2.3 From 734942cc4ea6478eed125af258da1bdbb4afe578 Mon Sep 17 00:00:00 2001 From: Dave Watson Date: Wed, 14 Jun 2017 11:37:14 -0700 Subject: tcp: ULP infrastructure Add the infrustructure for attaching Upper Layer Protocols (ULPs) over TCP sockets. Based on a similar infrastructure in tcp_cong. The idea is that any ULP can add its own logic by changing the TCP proto_ops structure to its own methods. Example usage: setsockopt(sock, SOL_TCP, TCP_ULP, "tls", sizeof("tls")); modules will call: tcp_register_ulp(&tcp_tls_ulp_ops); to register/unregister their ulp, with an init function and name. A list of registered ulps will be returned by tcp_get_available_ulp, which is hooked up to /proc. Example: $ cat /proc/sys/net/ipv4/tcp_available_ulp tls There is currently no functionality to remove or chain ULPs, but it should be possible to add these in the future if needed. Signed-off-by: Boris Pismenny Signed-off-by: Dave Watson Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 4 ++ include/net/tcp.h | 25 +++++++ include/uapi/linux/tcp.h | 1 + net/ipv4/Makefile | 2 +- net/ipv4/sysctl_net_ipv4.c | 25 +++++++ net/ipv4/tcp.c | 28 ++++++++ net/ipv4/tcp_ipv4.c | 2 + net/ipv4/tcp_ulp.c | 134 +++++++++++++++++++++++++++++++++++++ 8 files changed, 220 insertions(+), 1 deletion(-) create mode 100644 net/ipv4/tcp_ulp.c (limited to 'include/net') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c7a577976bec..13e4c89a8231 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -75,6 +75,8 @@ struct inet_connection_sock_af_ops { * @icsk_pmtu_cookie Last pmtu seen by socket * @icsk_ca_ops Pluggable congestion control hook * @icsk_af_ops Operations which are AF_INET{4,6} specific + * @icsk_ulp_ops Pluggable ULP control hook + * @icsk_ulp_data ULP private data * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event @@ -97,6 +99,8 @@ struct inet_connection_sock { __u32 icsk_pmtu_cookie; const struct tcp_congestion_ops *icsk_ca_ops; const struct inet_connection_sock_af_ops *icsk_af_ops; + const struct tcp_ulp_ops *icsk_ulp_ops; + void *icsk_ulp_data; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:6, icsk_ca_setsockopt:1, diff --git a/include/net/tcp.h b/include/net/tcp.h index 3ab677d11d02..b439f46f149c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1991,4 +1991,29 @@ static inline void tcp_listendrop(const struct sock *sk) enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer); +/* + * Interface for adding Upper Level Protocols over TCP + */ + +#define TCP_ULP_NAME_MAX 16 +#define TCP_ULP_MAX 128 +#define TCP_ULP_BUF_MAX (TCP_ULP_NAME_MAX*TCP_ULP_MAX) + +struct tcp_ulp_ops { + struct list_head list; + + /* initialize ulp */ + int (*init)(struct sock *sk); + /* cleanup ulp */ + void (*release)(struct sock *sk); + + char name[TCP_ULP_NAME_MAX]; + struct module *owner; +}; +int tcp_register_ulp(struct tcp_ulp_ops *type); +void tcp_unregister_ulp(struct tcp_ulp_ops *type); +int tcp_set_ulp(struct sock *sk, const char *name); +void tcp_get_available_ulp(char *buf, size_t len); +void tcp_cleanup_ulp(struct sock *sk); + #endif /* _TCP_H */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 38a2b07afdff..8204dcebc6f3 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -117,6 +117,7 @@ enum { #define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */ #define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */ #define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */ +#define TCP_ULP 31 /* Attach a ULP to a TCP connection */ struct tcp_repair_opt { __u32 opt_code; diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index f83de23a30e7..afcb435adfbe 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -8,7 +8,7 @@ obj-y := route.o inetpeer.o protocol.o \ inet_timewait_sock.o inet_connection_sock.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ - tcp_rate.o tcp_recovery.o \ + tcp_rate.o tcp_recovery.o tcp_ulp.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 7065234a89a5..9bf809726066 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -360,6 +360,25 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) tcp_fastopen_active_timeout_reset(); + + return ret; +} + +static int proc_tcp_available_ulp(struct ctl_table *ctl, + int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct ctl_table tbl = { .maxlen = TCP_ULP_BUF_MAX, }; + int ret; + + tbl.data = kmalloc(tbl.maxlen, GFP_USER); + if (!tbl.data) + return -ENOMEM; + tcp_get_available_ulp(tbl.data, TCP_ULP_BUF_MAX); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + kfree(tbl.data); + return ret; } @@ -685,6 +704,12 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, + { + .procname = "tcp_available_ulp", + .maxlen = TCP_ULP_BUF_MAX, + .mode = 0444, + .proc_handler = proc_tcp_available_ulp, + }, { .procname = "icmp_msgs_per_sec", .data = &sysctl_icmp_msgs_per_sec, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index cc8fd8b747a4..b06ee3086a0e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2482,6 +2482,24 @@ static int do_tcp_setsockopt(struct sock *sk, int level, release_sock(sk); return err; } + case TCP_ULP: { + char name[TCP_ULP_NAME_MAX]; + + if (optlen < 1) + return -EINVAL; + + val = strncpy_from_user(name, optval, + min_t(long, TCP_ULP_NAME_MAX - 1, + optlen)); + if (val < 0) + return -EFAULT; + name[val] = 0; + + lock_sock(sk); + err = tcp_set_ulp(sk, name); + release_sock(sk); + return err; + } default: /* fallthru */ break; @@ -3038,6 +3056,16 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EFAULT; return 0; + case TCP_ULP: + if (get_user(len, optlen)) + return -EFAULT; + len = min_t(unsigned int, len, TCP_ULP_NAME_MAX); + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, icsk->icsk_ulp_ops->name, len)) + return -EFAULT; + return 0; + case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1dc8c449e16a..eec2ff907279 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1860,6 +1860,8 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_cleanup_congestion_control(sk); + tcp_cleanup_ulp(sk); + /* Cleanup up the write buffer. */ tcp_write_queue_purge(sk); diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c new file mode 100644 index 000000000000..e855ea70819b --- /dev/null +++ b/net/ipv4/tcp_ulp.c @@ -0,0 +1,134 @@ +/* + * Pluggable TCP upper layer protocol support. + * + * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2017, Dave Watson . All rights reserved. + * + */ + +#include +#include +#include +#include +#include +#include + +static DEFINE_SPINLOCK(tcp_ulp_list_lock); +static LIST_HEAD(tcp_ulp_list); + +/* Simple linear search, don't expect many entries! */ +static struct tcp_ulp_ops *tcp_ulp_find(const char *name) +{ + struct tcp_ulp_ops *e; + + list_for_each_entry_rcu(e, &tcp_ulp_list, list) { + if (strcmp(e->name, name) == 0) + return e; + } + + return NULL; +} + +static const struct tcp_ulp_ops *__tcp_ulp_find_autoload(const char *name) +{ + const struct tcp_ulp_ops *ulp = NULL; + + rcu_read_lock(); + ulp = tcp_ulp_find(name); + +#ifdef CONFIG_MODULES + if (!ulp && capable(CAP_NET_ADMIN)) { + rcu_read_unlock(); + request_module("%s", name); + rcu_read_lock(); + ulp = tcp_ulp_find(name); + } +#endif + if (!ulp || !try_module_get(ulp->owner)) + ulp = NULL; + + rcu_read_unlock(); + return ulp; +} + +/* Attach new upper layer protocol to the list + * of available protocols. + */ +int tcp_register_ulp(struct tcp_ulp_ops *ulp) +{ + int ret = 0; + + spin_lock(&tcp_ulp_list_lock); + if (tcp_ulp_find(ulp->name)) { + pr_notice("%s already registered or non-unique name\n", + ulp->name); + ret = -EEXIST; + } else { + list_add_tail_rcu(&ulp->list, &tcp_ulp_list); + } + spin_unlock(&tcp_ulp_list_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(tcp_register_ulp); + +void tcp_unregister_ulp(struct tcp_ulp_ops *ulp) +{ + spin_lock(&tcp_ulp_list_lock); + list_del_rcu(&ulp->list); + spin_unlock(&tcp_ulp_list_lock); + + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(tcp_unregister_ulp); + +/* Build string with list of available upper layer protocl values */ +void tcp_get_available_ulp(char *buf, size_t maxlen) +{ + struct tcp_ulp_ops *ulp_ops; + size_t offs = 0; + + rcu_read_lock(); + list_for_each_entry_rcu(ulp_ops, &tcp_ulp_list, list) { + offs += snprintf(buf + offs, maxlen - offs, + "%s%s", + offs == 0 ? "" : " ", ulp_ops->name); + } + rcu_read_unlock(); +} + +void tcp_cleanup_ulp(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (!icsk->icsk_ulp_ops) + return; + + if (icsk->icsk_ulp_ops->release) + icsk->icsk_ulp_ops->release(sk); + module_put(icsk->icsk_ulp_ops->owner); +} + +/* Change upper layer protocol for socket */ +int tcp_set_ulp(struct sock *sk, const char *name) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_ulp_ops *ulp_ops; + int err = 0; + + if (icsk->icsk_ulp_ops) + return -EEXIST; + + ulp_ops = __tcp_ulp_find_autoload(name); + if (!ulp_ops) + err = -ENOENT; + else + err = ulp_ops->init(sk); + + if (err) + goto out; + + icsk->icsk_ulp_ops = ulp_ops; + out: + return err; +} -- cgit v1.2.3 From e3b5616a347603a521fe3ac46f3194a60900e3a7 Mon Sep 17 00:00:00 2001 From: Dave Watson Date: Wed, 14 Jun 2017 11:37:26 -0700 Subject: tcp: export do_tcp_sendpages and tcp_rate_check_app_limited functions Export do_tcp_sendpages and tcp_rate_check_app_limited, since tls will need to sendpages while the socket is already locked. tcp_sendpage is exported, but requires the socket lock to not be held already. Signed-off-by: Aviad Yehezkel Signed-off-by: Ilya Lesokhin Signed-off-by: Boris Pismenny Signed-off-by: Dave Watson Signed-off-by: David S. Miller --- include/net/tcp.h | 2 ++ net/ipv4/tcp.c | 5 +++-- net/ipv4/tcp_rate.c | 1 + 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index b439f46f149c..e17ec286e8df 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -350,6 +350,8 @@ int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); +ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, + size_t size, int flags); void tcp_release_cb(struct sock *sk); void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b06ee3086a0e..11e4ee281aa0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -901,8 +901,8 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } -static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, - size_t size, int flags) +ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, + size_t size, int flags) { struct tcp_sock *tp = tcp_sk(sk); int mss_now, size_goal; @@ -1032,6 +1032,7 @@ out_err: } return sk_stream_error(sk, flags, err); } +EXPORT_SYMBOL_GPL(do_tcp_sendpages); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index ad99569d4c1e..3330a370d306 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -185,3 +185,4 @@ void tcp_rate_check_app_limited(struct sock *sk) tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ? : 1; } +EXPORT_SYMBOL_GPL(tcp_rate_check_app_limited); -- cgit v1.2.3 From 3c4d7559159bfe1e3b94df3a657b2cda3a34e218 Mon Sep 17 00:00:00 2001 From: Dave Watson Date: Wed, 14 Jun 2017 11:37:39 -0700 Subject: tls: kernel TLS support Software implementation of transport layer security, implemented using ULP infrastructure. tcp proto_ops are replaced with tls equivalents of sendmsg and sendpage. Only symmetric crypto is done in the kernel, keys are passed by setsockopt after the handshake is complete. All control messages are supported via CMSG data - the actual symmetric encryption is the same, just the message type needs to be passed separately. For user API, please see Documentation patch. Pieces that can be shared between hw and sw implementation are in tls_main.c Signed-off-by: Boris Pismenny Signed-off-by: Ilya Lesokhin Signed-off-by: Aviad Yehezkel Signed-off-by: Dave Watson Signed-off-by: David S. Miller --- MAINTAINERS | 10 + include/linux/socket.h | 1 + include/net/tls.h | 237 +++++++++++++++ include/uapi/linux/tls.h | 79 +++++ net/Kconfig | 1 + net/Makefile | 1 + net/tls/Kconfig | 12 + net/tls/Makefile | 7 + net/tls/tls_main.c | 487 ++++++++++++++++++++++++++++++ net/tls/tls_sw.c | 772 +++++++++++++++++++++++++++++++++++++++++++++++ 10 files changed, 1607 insertions(+) create mode 100644 include/net/tls.h create mode 100644 include/uapi/linux/tls.h create mode 100644 net/tls/Kconfig create mode 100644 net/tls/Makefile create mode 100644 net/tls/tls_main.c create mode 100644 net/tls/tls_sw.c (limited to 'include/net') diff --git a/MAINTAINERS b/MAINTAINERS index 10f158ee95a3..71a74555afdf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8978,6 +8978,16 @@ F: net/ipv6/ F: include/net/ip* F: arch/x86/net/* +NETWORKING [TLS] +M: Ilya Lesokhin +M: Aviad Yehezkel +M: Dave Watson +L: netdev@vger.kernel.org +S: Maintained +F: net/tls/* +F: include/uapi/linux/tls.h +F: include/net/tls.h + NETWORKING [IPSEC] M: Steffen Klassert M: Herbert Xu diff --git a/include/linux/socket.h b/include/linux/socket.h index 082027457825..8b13db5163cc 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -334,6 +334,7 @@ struct ucred { #define SOL_ALG 279 #define SOL_NFC 280 #define SOL_KCM 281 +#define SOL_TLS 282 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/net/tls.h b/include/net/tls.h new file mode 100644 index 000000000000..b89d397dd62f --- /dev/null +++ b/include/net/tls.h @@ -0,0 +1,237 @@ +/* + * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2017, Dave Watson . All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * 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 _TLS_OFFLOAD_H +#define _TLS_OFFLOAD_H + +#include + +#include + + +/* Maximum data size carried in a TLS record */ +#define TLS_MAX_PAYLOAD_SIZE ((size_t)1 << 14) + +#define TLS_HEADER_SIZE 5 +#define TLS_NONCE_OFFSET TLS_HEADER_SIZE + +#define TLS_CRYPTO_INFO_READY(info) ((info)->cipher_type) + +#define TLS_RECORD_TYPE_DATA 0x17 + +#define TLS_AAD_SPACE_SIZE 13 + +struct tls_sw_context { + struct crypto_aead *aead_send; + + /* Sending context */ + char aad_space[TLS_AAD_SPACE_SIZE]; + + unsigned int sg_plaintext_size; + int sg_plaintext_num_elem; + struct scatterlist sg_plaintext_data[MAX_SKB_FRAGS]; + + unsigned int sg_encrypted_size; + int sg_encrypted_num_elem; + struct scatterlist sg_encrypted_data[MAX_SKB_FRAGS]; + + /* AAD | sg_plaintext_data | sg_tag */ + struct scatterlist sg_aead_in[2]; + /* AAD | sg_encrypted_data (data contain overhead for hdr&iv&tag) */ + struct scatterlist sg_aead_out[2]; +}; + +enum { + TLS_PENDING_CLOSED_RECORD +}; + +struct tls_context { + union { + struct tls_crypto_info crypto_send; + struct tls12_crypto_info_aes_gcm_128 crypto_send_aes_gcm_128; + }; + + void *priv_ctx; + + u16 prepend_size; + u16 tag_size; + u16 overhead_size; + u16 iv_size; + char *iv; + u16 rec_seq_size; + char *rec_seq; + + struct scatterlist *partially_sent_record; + u16 partially_sent_offset; + unsigned long flags; + + u16 pending_open_record_frags; + int (*push_pending_record)(struct sock *sk, int flags); + void (*free_resources)(struct sock *sk); + + void (*sk_write_space)(struct sock *sk); + void (*sk_proto_close)(struct sock *sk, long timeout); + + int (*setsockopt)(struct sock *sk, int level, + int optname, char __user *optval, + unsigned int optlen); + int (*getsockopt)(struct sock *sk, int level, + int optname, char __user *optval, + int __user *optlen); +}; + +int wait_on_pending_writer(struct sock *sk, long *timeo); +int tls_sk_query(struct sock *sk, int optname, char __user *optval, + int __user *optlen); +int tls_sk_attach(struct sock *sk, int optname, char __user *optval, + unsigned int optlen); + + +int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx); +int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +int tls_sw_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags); +void tls_sw_close(struct sock *sk, long timeout); + +void tls_sk_destruct(struct sock *sk, struct tls_context *ctx); +void tls_icsk_clean_acked(struct sock *sk); + +int tls_push_sg(struct sock *sk, struct tls_context *ctx, + struct scatterlist *sg, u16 first_offset, + int flags); +int tls_push_pending_closed_record(struct sock *sk, struct tls_context *ctx, + int flags, long *timeo); + +static inline bool tls_is_pending_closed_record(struct tls_context *ctx) +{ + return test_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); +} + +static inline int tls_complete_pending_work(struct sock *sk, + struct tls_context *ctx, + int flags, long *timeo) +{ + int rc = 0; + + if (unlikely(sk->sk_write_pending)) + rc = wait_on_pending_writer(sk, timeo); + + if (!rc && tls_is_pending_closed_record(ctx)) + rc = tls_push_pending_closed_record(sk, ctx, flags, timeo); + + return rc; +} + +static inline bool tls_is_partially_sent_record(struct tls_context *ctx) +{ + return !!ctx->partially_sent_record; +} + +static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) +{ + return tls_ctx->pending_open_record_frags; +} + +static inline void tls_err_abort(struct sock *sk) +{ + sk->sk_err = -EBADMSG; + sk->sk_error_report(sk); +} + +static inline bool tls_bigint_increment(unsigned char *seq, int len) +{ + int i; + + for (i = len - 1; i >= 0; i--) { + ++seq[i]; + if (seq[i] != 0) + break; + } + + return (i == -1); +} + +static inline void tls_advance_record_sn(struct sock *sk, + struct tls_context *ctx) +{ + if (tls_bigint_increment(ctx->rec_seq, ctx->rec_seq_size)) + tls_err_abort(sk); + tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + ctx->iv_size); +} + +static inline void tls_fill_prepend(struct tls_context *ctx, + char *buf, + size_t plaintext_len, + unsigned char record_type) +{ + size_t pkt_len, iv_size = ctx->iv_size; + + pkt_len = plaintext_len + iv_size + ctx->tag_size; + + /* we cover nonce explicit here as well, so buf should be of + * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE + */ + buf[0] = record_type; + buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.version); + buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.version); + /* we can use IV for nonce explicit according to spec */ + buf[3] = pkt_len >> 8; + buf[4] = pkt_len & 0xFF; + memcpy(buf + TLS_NONCE_OFFSET, + ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size); +} + +static inline struct tls_context *tls_get_ctx(const struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ulp_data; +} + +static inline struct tls_sw_context *tls_sw_ctx( + const struct tls_context *tls_ctx) +{ + return (struct tls_sw_context *)tls_ctx->priv_ctx; +} + +static inline struct tls_offload_context *tls_offload_ctx( + const struct tls_context *tls_ctx) +{ + return (struct tls_offload_context *)tls_ctx->priv_ctx; +} + +int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, + unsigned char *record_type); + +#endif /* _TLS_OFFLOAD_H */ diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h new file mode 100644 index 000000000000..cc1d21db35d8 --- /dev/null +++ b/include/uapi/linux/tls.h @@ -0,0 +1,79 @@ +/* + * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * 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_TLS_H +#define _UAPI_LINUX_TLS_H + +#include +#include +#include +#include +#include + +/* TLS socket options */ +#define TLS_TX 1 /* Set transmit parameters */ + +/* Supported versions */ +#define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) +#define TLS_VERSION_MAJOR(ver) (((ver) >> 8) & 0xFF) + +#define TLS_VERSION_NUMBER(id) ((((id##_VERSION_MAJOR) & 0xFF) << 8) | \ + ((id##_VERSION_MINOR) & 0xFF)) + +#define TLS_1_2_VERSION_MAJOR 0x3 +#define TLS_1_2_VERSION_MINOR 0x3 +#define TLS_1_2_VERSION TLS_VERSION_NUMBER(TLS_1_2) + +/* Supported ciphers */ +#define TLS_CIPHER_AES_GCM_128 51 +#define TLS_CIPHER_AES_GCM_128_IV_SIZE 8 +#define TLS_CIPHER_AES_GCM_128_KEY_SIZE 16 +#define TLS_CIPHER_AES_GCM_128_SALT_SIZE 4 +#define TLS_CIPHER_AES_GCM_128_TAG_SIZE 16 +#define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE 8 + +#define TLS_SET_RECORD_TYPE 1 + +struct tls_crypto_info { + __u16 version; + __u16 cipher_type; +}; + +struct tls12_crypto_info_aes_gcm_128 { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_AES_GCM_128_IV_SIZE]; + unsigned char key[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_AES_GCM_128_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE]; +}; + +#endif /* _UAPI_LINUX_TLS_H */ diff --git a/net/Kconfig b/net/Kconfig index 102f781a0131..7d57ef34b79c 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -55,6 +55,7 @@ menu "Networking options" source "net/packet/Kconfig" source "net/unix/Kconfig" +source "net/tls/Kconfig" source "net/xfrm/Kconfig" source "net/iucv/Kconfig" source "net/smc/Kconfig" diff --git a/net/Makefile b/net/Makefile index 9086ffbb5085..bed80fa398b7 100644 --- a/net/Makefile +++ b/net/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_LLC) += llc/ obj-$(CONFIG_NET) += ethernet/ 802/ sched/ netlink/ bpf/ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ +obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ obj-$(CONFIG_UNIX) += unix/ obj-$(CONFIG_NET) += ipv6/ diff --git a/net/tls/Kconfig b/net/tls/Kconfig new file mode 100644 index 000000000000..61e532964c82 --- /dev/null +++ b/net/tls/Kconfig @@ -0,0 +1,12 @@ +# +# TLS configuration +# +config TLS + tristate "Transport Layer Security support" + depends on NET + default m + ---help--- + Enable kernel support for TLS protocol. This allows symmetric + encryption handling of the TLS protocol to be done in-kernel. + + If unsure, say M. diff --git a/net/tls/Makefile b/net/tls/Makefile new file mode 100644 index 000000000000..a930fd1c4f7b --- /dev/null +++ b/net/tls/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the TLS subsystem. +# + +obj-$(CONFIG_TLS) += tls.o + +tls-y := tls_main.o tls_sw.o diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c new file mode 100644 index 000000000000..2ebc328bda96 --- /dev/null +++ b/net/tls/tls_main.c @@ -0,0 +1,487 @@ +/* + * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2017, Dave Watson . All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * 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. + */ + +#include + +#include +#include +#include +#include +#include + +#include + +MODULE_AUTHOR("Mellanox Technologies"); +MODULE_DESCRIPTION("Transport Layer Security Support"); +MODULE_LICENSE("Dual BSD/GPL"); + +static struct proto tls_base_prot; +static struct proto tls_sw_prot; + +int wait_on_pending_writer(struct sock *sk, long *timeo) +{ + int rc = 0; + DEFINE_WAIT_FUNC(wait, woken_wake_function); + + add_wait_queue(sk_sleep(sk), &wait); + while (1) { + if (!*timeo) { + rc = -EAGAIN; + break; + } + + if (signal_pending(current)) { + rc = sock_intr_errno(*timeo); + break; + } + + if (sk_wait_event(sk, timeo, !sk->sk_write_pending, &wait)) + break; + } + remove_wait_queue(sk_sleep(sk), &wait); + return rc; +} + +int tls_push_sg(struct sock *sk, + struct tls_context *ctx, + struct scatterlist *sg, + u16 first_offset, + int flags) +{ + int sendpage_flags = flags | MSG_SENDPAGE_NOTLAST; + int ret = 0; + struct page *p; + size_t size; + int offset = first_offset; + + size = sg->length - offset; + offset += sg->offset; + + while (1) { + if (sg_is_last(sg)) + sendpage_flags = flags; + + /* is sending application-limited? */ + tcp_rate_check_app_limited(sk); + p = sg_page(sg); +retry: + ret = do_tcp_sendpages(sk, p, offset, size, sendpage_flags); + + if (ret != size) { + if (ret > 0) { + offset += ret; + size -= ret; + goto retry; + } + + offset -= sg->offset; + ctx->partially_sent_offset = offset; + ctx->partially_sent_record = (void *)sg; + return ret; + } + + put_page(p); + sk_mem_uncharge(sk, sg->length); + sg = sg_next(sg); + if (!sg) + break; + + offset = sg->offset; + size = sg->length; + } + + clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); + + return 0; +} + +static int tls_handle_open_record(struct sock *sk, int flags) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (tls_is_pending_open_record(ctx)) + return ctx->push_pending_record(sk, flags); + + return 0; +} + +int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, + unsigned char *record_type) +{ + struct cmsghdr *cmsg; + int rc = -EINVAL; + + for_each_cmsghdr(cmsg, msg) { + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + if (cmsg->cmsg_level != SOL_TLS) + continue; + + switch (cmsg->cmsg_type) { + case TLS_SET_RECORD_TYPE: + if (cmsg->cmsg_len < CMSG_LEN(sizeof(*record_type))) + return -EINVAL; + + if (msg->msg_flags & MSG_MORE) + return -EINVAL; + + rc = tls_handle_open_record(sk, msg->msg_flags); + if (rc) + return rc; + + *record_type = *(unsigned char *)CMSG_DATA(cmsg); + rc = 0; + break; + default: + return -EINVAL; + } + } + + return rc; +} + +int tls_push_pending_closed_record(struct sock *sk, struct tls_context *ctx, + int flags, long *timeo) +{ + struct scatterlist *sg; + u16 offset; + + if (!tls_is_partially_sent_record(ctx)) + return ctx->push_pending_record(sk, flags); + + sg = ctx->partially_sent_record; + offset = ctx->partially_sent_offset; + + ctx->partially_sent_record = NULL; + return tls_push_sg(sk, ctx, sg, offset, flags); +} + +static void tls_write_space(struct sock *sk) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) { + gfp_t sk_allocation = sk->sk_allocation; + int rc; + long timeo = 0; + + sk->sk_allocation = GFP_ATOMIC; + rc = tls_push_pending_closed_record(sk, ctx, + MSG_DONTWAIT | + MSG_NOSIGNAL, + &timeo); + sk->sk_allocation = sk_allocation; + + if (rc < 0) + return; + } + + ctx->sk_write_space(sk); +} + +static void tls_sk_proto_close(struct sock *sk, long timeout) +{ + struct tls_context *ctx = tls_get_ctx(sk); + long timeo = sock_sndtimeo(sk, 0); + void (*sk_proto_close)(struct sock *sk, long timeout); + + lock_sock(sk); + + if (!tls_complete_pending_work(sk, ctx, 0, &timeo)) + tls_handle_open_record(sk, 0); + + if (ctx->partially_sent_record) { + struct scatterlist *sg = ctx->partially_sent_record; + + while (1) { + put_page(sg_page(sg)); + sk_mem_uncharge(sk, sg->length); + + if (sg_is_last(sg)) + break; + sg++; + } + } + ctx->free_resources(sk); + kfree(ctx->rec_seq); + kfree(ctx->iv); + + sk_proto_close = ctx->sk_proto_close; + kfree(ctx); + + release_sock(sk); + sk_proto_close(sk, timeout); +} + +static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, + int __user *optlen) +{ + int rc = 0; + struct tls_context *ctx = tls_get_ctx(sk); + struct tls_crypto_info *crypto_info; + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + if (!optval || (len < sizeof(*crypto_info))) { + rc = -EINVAL; + goto out; + } + + if (!ctx) { + rc = -EBUSY; + goto out; + } + + /* get user crypto info */ + crypto_info = &ctx->crypto_send; + + if (!TLS_CRYPTO_INFO_READY(crypto_info)) { + rc = -EBUSY; + goto out; + } + + if (len == sizeof(crypto_info)) { + rc = copy_to_user(optval, crypto_info, sizeof(*crypto_info)); + goto out; + } + + switch (crypto_info->cipher_type) { + case TLS_CIPHER_AES_GCM_128: { + struct tls12_crypto_info_aes_gcm_128 * + crypto_info_aes_gcm_128 = + container_of(crypto_info, + struct tls12_crypto_info_aes_gcm_128, + info); + + if (len != sizeof(*crypto_info_aes_gcm_128)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(crypto_info_aes_gcm_128->iv, ctx->iv, + TLS_CIPHER_AES_GCM_128_IV_SIZE); + release_sock(sk); + rc = copy_to_user(optval, + crypto_info_aes_gcm_128, + sizeof(*crypto_info_aes_gcm_128)); + break; + } + default: + rc = -EINVAL; + } + +out: + return rc; +} + +static int do_tls_getsockopt(struct sock *sk, int optname, + char __user *optval, int __user *optlen) +{ + int rc = 0; + + switch (optname) { + case TLS_TX: + rc = do_tls_getsockopt_tx(sk, optval, optlen); + break; + default: + rc = -ENOPROTOOPT; + break; + } + return rc; +} + +static int tls_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (level != SOL_TLS) + return ctx->getsockopt(sk, level, optname, optval, optlen); + + return do_tls_getsockopt(sk, optname, optval, optlen); +} + +static int do_tls_setsockopt_tx(struct sock *sk, char __user *optval, + unsigned int optlen) +{ + struct tls_crypto_info *crypto_info, tmp_crypto_info; + struct tls_context *ctx = tls_get_ctx(sk); + struct proto *prot = NULL; + int rc = 0; + + if (!optval || (optlen < sizeof(*crypto_info))) { + rc = -EINVAL; + goto out; + } + + rc = copy_from_user(&tmp_crypto_info, optval, sizeof(*crypto_info)); + if (rc) { + rc = -EFAULT; + goto out; + } + + /* check version */ + if (tmp_crypto_info.version != TLS_1_2_VERSION) { + rc = -ENOTSUPP; + goto out; + } + + /* get user crypto info */ + crypto_info = &ctx->crypto_send; + + /* Currently we don't support set crypto info more than one time */ + if (TLS_CRYPTO_INFO_READY(crypto_info)) + goto out; + + switch (tmp_crypto_info.cipher_type) { + case TLS_CIPHER_AES_GCM_128: { + if (optlen != sizeof(struct tls12_crypto_info_aes_gcm_128)) { + rc = -EINVAL; + goto out; + } + rc = copy_from_user( + crypto_info, + optval, + sizeof(struct tls12_crypto_info_aes_gcm_128)); + + if (rc) { + rc = -EFAULT; + goto err_crypto_info; + } + break; + } + default: + rc = -EINVAL; + goto out; + } + + ctx->sk_write_space = sk->sk_write_space; + sk->sk_write_space = tls_write_space; + + ctx->sk_proto_close = sk->sk_prot->close; + + /* currently SW is default, we will have ethtool in future */ + rc = tls_set_sw_offload(sk, ctx); + prot = &tls_sw_prot; + if (rc) + goto err_crypto_info; + + sk->sk_prot = prot; + goto out; + +err_crypto_info: + memset(crypto_info, 0, sizeof(*crypto_info)); +out: + return rc; +} + +static int do_tls_setsockopt(struct sock *sk, int optname, + char __user *optval, unsigned int optlen) +{ + int rc = 0; + + switch (optname) { + case TLS_TX: + lock_sock(sk); + rc = do_tls_setsockopt_tx(sk, optval, optlen); + release_sock(sk); + break; + default: + rc = -ENOPROTOOPT; + break; + } + return rc; +} + +static int tls_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (level != SOL_TLS) + return ctx->setsockopt(sk, level, optname, optval, optlen); + + return do_tls_setsockopt(sk, optname, optval, optlen); +} + +static int tls_init(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tls_context *ctx; + int rc = 0; + + /* allocate tls context */ + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) { + rc = -ENOMEM; + goto out; + } + icsk->icsk_ulp_data = ctx; + ctx->setsockopt = sk->sk_prot->setsockopt; + ctx->getsockopt = sk->sk_prot->getsockopt; + sk->sk_prot = &tls_base_prot; +out: + return rc; +} + +static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { + .name = "tls", + .owner = THIS_MODULE, + .init = tls_init, +}; + +static int __init tls_register(void) +{ + tls_base_prot = tcp_prot; + tls_base_prot.setsockopt = tls_setsockopt; + tls_base_prot.getsockopt = tls_getsockopt; + + tls_sw_prot = tls_base_prot; + tls_sw_prot.sendmsg = tls_sw_sendmsg; + tls_sw_prot.sendpage = tls_sw_sendpage; + tls_sw_prot.close = tls_sk_proto_close; + + tcp_register_ulp(&tcp_tls_ulp_ops); + + return 0; +} + +static void __exit tls_unregister(void) +{ + tcp_unregister_ulp(&tcp_tls_ulp_ops); +} + +module_init(tls_register); +module_exit(tls_unregister); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c new file mode 100644 index 000000000000..fa596fa71ba7 --- /dev/null +++ b/net/tls/tls_sw.c @@ -0,0 +1,772 @@ +/* + * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2017, Dave Watson . All rights reserved. + * Copyright (c) 2016-2017, Lance Chao . All rights reserved. + * Copyright (c) 2016, Fridolin Pokorny . All rights reserved. + * Copyright (c) 2016, Nikos Mavrogiannopoulos . All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * 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. + */ + +#include +#include + +#include + +static inline void tls_make_aad(int recv, + char *buf, + size_t size, + char *record_sequence, + int record_sequence_size, + unsigned char record_type) +{ + memcpy(buf, record_sequence, record_sequence_size); + + buf[8] = record_type; + buf[9] = TLS_1_2_VERSION_MAJOR; + buf[10] = TLS_1_2_VERSION_MINOR; + buf[11] = size >> 8; + buf[12] = size & 0xFF; +} + +static void trim_sg(struct sock *sk, struct scatterlist *sg, + int *sg_num_elem, unsigned int *sg_size, int target_size) +{ + int i = *sg_num_elem - 1; + int trim = *sg_size - target_size; + + if (trim <= 0) { + WARN_ON(trim < 0); + return; + } + + *sg_size = target_size; + while (trim >= sg[i].length) { + trim -= sg[i].length; + sk_mem_uncharge(sk, sg[i].length); + put_page(sg_page(&sg[i])); + i--; + + if (i < 0) + goto out; + } + + sg[i].length -= trim; + sk_mem_uncharge(sk, trim); + +out: + *sg_num_elem = i + 1; +} + +static void trim_both_sgl(struct sock *sk, int target_size) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + + trim_sg(sk, ctx->sg_plaintext_data, + &ctx->sg_plaintext_num_elem, + &ctx->sg_plaintext_size, + target_size); + + if (target_size > 0) + target_size += tls_ctx->overhead_size; + + trim_sg(sk, ctx->sg_encrypted_data, + &ctx->sg_encrypted_num_elem, + &ctx->sg_encrypted_size, + target_size); +} + +static int alloc_sg(struct sock *sk, int len, struct scatterlist *sg, + int *sg_num_elem, unsigned int *sg_size, + int first_coalesce) +{ + struct page_frag *pfrag; + unsigned int size = *sg_size; + int num_elem = *sg_num_elem, use = 0, rc = 0; + struct scatterlist *sge; + unsigned int orig_offset; + + len -= size; + pfrag = sk_page_frag(sk); + + while (len > 0) { + if (!sk_page_frag_refill(sk, pfrag)) { + rc = -ENOMEM; + goto out; + } + + use = min_t(int, len, pfrag->size - pfrag->offset); + + if (!sk_wmem_schedule(sk, use)) { + rc = -ENOMEM; + goto out; + } + + sk_mem_charge(sk, use); + size += use; + orig_offset = pfrag->offset; + pfrag->offset += use; + + sge = sg + num_elem - 1; + if (num_elem > first_coalesce && sg_page(sg) == pfrag->page && + sg->offset + sg->length == orig_offset) { + sg->length += use; + } else { + sge++; + sg_unmark_end(sge); + sg_set_page(sge, pfrag->page, use, orig_offset); + get_page(pfrag->page); + ++num_elem; + if (num_elem == MAX_SKB_FRAGS) { + rc = -ENOSPC; + break; + } + } + + len -= use; + } + goto out; + +out: + *sg_size = size; + *sg_num_elem = num_elem; + return rc; +} + +static int alloc_encrypted_sg(struct sock *sk, int len) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + int rc = 0; + + rc = alloc_sg(sk, len, ctx->sg_encrypted_data, + &ctx->sg_encrypted_num_elem, &ctx->sg_encrypted_size, 0); + + return rc; +} + +static int alloc_plaintext_sg(struct sock *sk, int len) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + int rc = 0; + + rc = alloc_sg(sk, len, ctx->sg_plaintext_data, + &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size, + tls_ctx->pending_open_record_frags); + + return rc; +} + +static void free_sg(struct sock *sk, struct scatterlist *sg, + int *sg_num_elem, unsigned int *sg_size) +{ + int i, n = *sg_num_elem; + + for (i = 0; i < n; ++i) { + sk_mem_uncharge(sk, sg[i].length); + put_page(sg_page(&sg[i])); + } + *sg_num_elem = 0; + *sg_size = 0; +} + +static void tls_free_both_sg(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + + free_sg(sk, ctx->sg_encrypted_data, &ctx->sg_encrypted_num_elem, + &ctx->sg_encrypted_size); + + free_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem, + &ctx->sg_plaintext_size); +} + +static int tls_do_encryption(struct tls_context *tls_ctx, + struct tls_sw_context *ctx, size_t data_len, + gfp_t flags) +{ + unsigned int req_size = sizeof(struct aead_request) + + crypto_aead_reqsize(ctx->aead_send); + struct aead_request *aead_req; + int rc; + + aead_req = kmalloc(req_size, flags); + if (!aead_req) + return -ENOMEM; + + ctx->sg_encrypted_data[0].offset += tls_ctx->prepend_size; + ctx->sg_encrypted_data[0].length -= tls_ctx->prepend_size; + + aead_request_set_tfm(aead_req, ctx->aead_send); + aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); + aead_request_set_crypt(aead_req, ctx->sg_aead_in, ctx->sg_aead_out, + data_len, tls_ctx->iv); + rc = crypto_aead_encrypt(aead_req); + + ctx->sg_encrypted_data[0].offset -= tls_ctx->prepend_size; + ctx->sg_encrypted_data[0].length += tls_ctx->prepend_size; + + kfree(aead_req); + return rc; +} + +static int tls_push_record(struct sock *sk, int flags, + unsigned char record_type) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + int rc; + + sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1); + sg_mark_end(ctx->sg_encrypted_data + ctx->sg_encrypted_num_elem - 1); + + tls_make_aad(0, ctx->aad_space, ctx->sg_plaintext_size, + tls_ctx->rec_seq, tls_ctx->rec_seq_size, + record_type); + + tls_fill_prepend(tls_ctx, + page_address(sg_page(&ctx->sg_encrypted_data[0])) + + ctx->sg_encrypted_data[0].offset, + ctx->sg_plaintext_size, record_type); + + tls_ctx->pending_open_record_frags = 0; + set_bit(TLS_PENDING_CLOSED_RECORD, &tls_ctx->flags); + + rc = tls_do_encryption(tls_ctx, ctx, ctx->sg_plaintext_size, + sk->sk_allocation); + if (rc < 0) { + /* If we are called from write_space and + * we fail, we need to set this SOCK_NOSPACE + * to trigger another write_space in the future. + */ + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + return rc; + } + + free_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem, + &ctx->sg_plaintext_size); + + ctx->sg_encrypted_num_elem = 0; + ctx->sg_encrypted_size = 0; + + /* Only pass through MSG_DONTWAIT and MSG_NOSIGNAL flags */ + rc = tls_push_sg(sk, tls_ctx, ctx->sg_encrypted_data, 0, flags); + if (rc < 0 && rc != -EAGAIN) + tls_err_abort(sk); + + tls_advance_record_sn(sk, tls_ctx); + return rc; +} + +static int tls_sw_push_pending_record(struct sock *sk, int flags) +{ + return tls_push_record(sk, flags, TLS_RECORD_TYPE_DATA); +} + +static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from, + int length) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct page *pages[MAX_SKB_FRAGS]; + + size_t offset; + ssize_t copied, use; + int i = 0; + unsigned int size = ctx->sg_plaintext_size; + int num_elem = ctx->sg_plaintext_num_elem; + int rc = 0; + int maxpages; + + while (length > 0) { + i = 0; + maxpages = ARRAY_SIZE(ctx->sg_plaintext_data) - num_elem; + if (maxpages == 0) { + rc = -EFAULT; + goto out; + } + copied = iov_iter_get_pages(from, pages, + length, + maxpages, &offset); + if (copied <= 0) { + rc = -EFAULT; + goto out; + } + + iov_iter_advance(from, copied); + + length -= copied; + size += copied; + while (copied) { + use = min_t(int, copied, PAGE_SIZE - offset); + + sg_set_page(&ctx->sg_plaintext_data[num_elem], + pages[i], use, offset); + sg_unmark_end(&ctx->sg_plaintext_data[num_elem]); + sk_mem_charge(sk, use); + + offset = 0; + copied -= use; + + ++i; + ++num_elem; + } + } + +out: + ctx->sg_plaintext_size = size; + ctx->sg_plaintext_num_elem = num_elem; + return rc; +} + +static int memcopy_from_iter(struct sock *sk, struct iov_iter *from, + int bytes) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct scatterlist *sg = ctx->sg_plaintext_data; + int copy, i, rc = 0; + + for (i = tls_ctx->pending_open_record_frags; + i < ctx->sg_plaintext_num_elem; ++i) { + copy = sg[i].length; + if (copy_from_iter( + page_address(sg_page(&sg[i])) + sg[i].offset, + copy, from) != copy) { + rc = -EFAULT; + goto out; + } + bytes -= copy; + + ++tls_ctx->pending_open_record_frags; + + if (!bytes) + break; + } + +out: + return rc; +} + +int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + int ret = 0; + int required_size; + long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + bool eor = !(msg->msg_flags & MSG_MORE); + size_t try_to_copy, copied = 0; + unsigned char record_type = TLS_RECORD_TYPE_DATA; + int record_room; + bool full_record; + int orig_size; + + if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) + return -ENOTSUPP; + + lock_sock(sk); + + if (tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo)) + goto send_end; + + if (unlikely(msg->msg_controllen)) { + ret = tls_proccess_cmsg(sk, msg, &record_type); + if (ret) + goto send_end; + } + + while (msg_data_left(msg)) { + if (sk->sk_err) { + ret = sk->sk_err; + goto send_end; + } + + orig_size = ctx->sg_plaintext_size; + full_record = false; + try_to_copy = msg_data_left(msg); + record_room = TLS_MAX_PAYLOAD_SIZE - ctx->sg_plaintext_size; + if (try_to_copy >= record_room) { + try_to_copy = record_room; + full_record = true; + } + + required_size = ctx->sg_plaintext_size + try_to_copy + + tls_ctx->overhead_size; + + if (!sk_stream_memory_free(sk)) + goto wait_for_sndbuf; +alloc_encrypted: + ret = alloc_encrypted_sg(sk, required_size); + if (ret) { + if (ret != -ENOSPC) + goto wait_for_memory; + + /* Adjust try_to_copy according to the amount that was + * actually allocated. The difference is due + * to max sg elements limit + */ + try_to_copy -= required_size - ctx->sg_encrypted_size; + full_record = true; + } + + if (full_record || eor) { + ret = zerocopy_from_iter(sk, &msg->msg_iter, + try_to_copy); + if (ret) + goto fallback_to_reg_send; + + copied += try_to_copy; + ret = tls_push_record(sk, msg->msg_flags, record_type); + if (!ret) + continue; + if (ret == -EAGAIN) + goto send_end; + + copied -= try_to_copy; +fallback_to_reg_send: + iov_iter_revert(&msg->msg_iter, + ctx->sg_plaintext_size - orig_size); + trim_sg(sk, ctx->sg_plaintext_data, + &ctx->sg_plaintext_num_elem, + &ctx->sg_plaintext_size, + orig_size); + } + + required_size = ctx->sg_plaintext_size + try_to_copy; +alloc_plaintext: + ret = alloc_plaintext_sg(sk, required_size); + if (ret) { + if (ret != -ENOSPC) + goto wait_for_memory; + + /* Adjust try_to_copy according to the amount that was + * actually allocated. The difference is due + * to max sg elements limit + */ + try_to_copy -= required_size - ctx->sg_plaintext_size; + full_record = true; + + trim_sg(sk, ctx->sg_encrypted_data, + &ctx->sg_encrypted_num_elem, + &ctx->sg_encrypted_size, + ctx->sg_plaintext_size + + tls_ctx->overhead_size); + } + + ret = memcopy_from_iter(sk, &msg->msg_iter, try_to_copy); + if (ret) + goto trim_sgl; + + copied += try_to_copy; + if (full_record || eor) { +push_record: + ret = tls_push_record(sk, msg->msg_flags, record_type); + if (ret) { + if (ret == -ENOMEM) + goto wait_for_memory; + + goto send_end; + } + } + + continue; + +wait_for_sndbuf: + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +wait_for_memory: + ret = sk_stream_wait_memory(sk, &timeo); + if (ret) { +trim_sgl: + trim_both_sgl(sk, orig_size); + goto send_end; + } + + if (tls_is_pending_closed_record(tls_ctx)) + goto push_record; + + if (ctx->sg_encrypted_size < required_size) + goto alloc_encrypted; + + goto alloc_plaintext; + } + +send_end: + ret = sk_stream_error(sk, msg->msg_flags, ret); + + release_sock(sk); + return copied ? copied : ret; +} + +int tls_sw_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + int ret = 0; + long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + bool eor; + size_t orig_size = size; + unsigned char record_type = TLS_RECORD_TYPE_DATA; + struct scatterlist *sg; + bool full_record; + int record_room; + + if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | + MSG_SENDPAGE_NOTLAST)) + return -ENOTSUPP; + + /* No MSG_EOR from splice, only look at MSG_MORE */ + eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST)); + + lock_sock(sk); + + sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); + + if (tls_complete_pending_work(sk, tls_ctx, flags, &timeo)) + goto sendpage_end; + + /* Call the sk_stream functions to manage the sndbuf mem. */ + while (size > 0) { + size_t copy, required_size; + + if (sk->sk_err) { + ret = sk->sk_err; + goto sendpage_end; + } + + full_record = false; + record_room = TLS_MAX_PAYLOAD_SIZE - ctx->sg_plaintext_size; + copy = size; + if (copy >= record_room) { + copy = record_room; + full_record = true; + } + required_size = ctx->sg_plaintext_size + copy + + tls_ctx->overhead_size; + + if (!sk_stream_memory_free(sk)) + goto wait_for_sndbuf; +alloc_payload: + ret = alloc_encrypted_sg(sk, required_size); + if (ret) { + if (ret != -ENOSPC) + goto wait_for_memory; + + /* Adjust copy according to the amount that was + * actually allocated. The difference is due + * to max sg elements limit + */ + copy -= required_size - ctx->sg_plaintext_size; + full_record = true; + } + + get_page(page); + sg = ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem; + sg_set_page(sg, page, copy, offset); + ctx->sg_plaintext_num_elem++; + + sk_mem_charge(sk, copy); + offset += copy; + size -= copy; + ctx->sg_plaintext_size += copy; + tls_ctx->pending_open_record_frags = ctx->sg_plaintext_num_elem; + + if (full_record || eor || + ctx->sg_plaintext_num_elem == + ARRAY_SIZE(ctx->sg_plaintext_data)) { +push_record: + ret = tls_push_record(sk, flags, record_type); + if (ret) { + if (ret == -ENOMEM) + goto wait_for_memory; + + goto sendpage_end; + } + } + continue; +wait_for_sndbuf: + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); +wait_for_memory: + ret = sk_stream_wait_memory(sk, &timeo); + if (ret) { + trim_both_sgl(sk, ctx->sg_plaintext_size); + goto sendpage_end; + } + + if (tls_is_pending_closed_record(tls_ctx)) + goto push_record; + + goto alloc_payload; + } + +sendpage_end: + if (orig_size > size) + ret = orig_size - size; + else + ret = sk_stream_error(sk, flags, ret); + + release_sock(sk); + return ret; +} + +void tls_sw_free_resources(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + + if (ctx->aead_send) + crypto_free_aead(ctx->aead_send); + + tls_free_both_sg(sk); + + kfree(ctx); +} + +int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx) +{ + char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; + struct tls_crypto_info *crypto_info; + struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; + struct tls_sw_context *sw_ctx; + u16 nonce_size, tag_size, iv_size, rec_seq_size; + char *iv, *rec_seq; + int rc = 0; + + if (!ctx) { + rc = -EINVAL; + goto out; + } + + if (ctx->priv_ctx) { + rc = -EEXIST; + goto out; + } + + sw_ctx = kzalloc(sizeof(*sw_ctx), GFP_KERNEL); + if (!sw_ctx) { + rc = -ENOMEM; + goto out; + } + + ctx->priv_ctx = (struct tls_offload_context *)sw_ctx; + ctx->free_resources = tls_sw_free_resources; + + crypto_info = &ctx->crypto_send; + switch (crypto_info->cipher_type) { + case TLS_CIPHER_AES_GCM_128: { + nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; + tag_size = TLS_CIPHER_AES_GCM_128_TAG_SIZE; + iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; + iv = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->iv; + rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE; + rec_seq = + ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq; + gcm_128_info = + (struct tls12_crypto_info_aes_gcm_128 *)crypto_info; + break; + } + default: + rc = -EINVAL; + goto out; + } + + ctx->prepend_size = TLS_HEADER_SIZE + nonce_size; + ctx->tag_size = tag_size; + ctx->overhead_size = ctx->prepend_size + ctx->tag_size; + ctx->iv_size = iv_size; + ctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + GFP_KERNEL); + if (!ctx->iv) { + rc = -ENOMEM; + goto out; + } + memcpy(ctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + memcpy(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); + ctx->rec_seq_size = rec_seq_size; + ctx->rec_seq = kmalloc(rec_seq_size, GFP_KERNEL); + if (!ctx->rec_seq) { + rc = -ENOMEM; + goto free_iv; + } + memcpy(ctx->rec_seq, rec_seq, rec_seq_size); + + sg_init_table(sw_ctx->sg_encrypted_data, + ARRAY_SIZE(sw_ctx->sg_encrypted_data)); + sg_init_table(sw_ctx->sg_plaintext_data, + ARRAY_SIZE(sw_ctx->sg_plaintext_data)); + + sg_init_table(sw_ctx->sg_aead_in, 2); + sg_set_buf(&sw_ctx->sg_aead_in[0], sw_ctx->aad_space, + sizeof(sw_ctx->aad_space)); + sg_unmark_end(&sw_ctx->sg_aead_in[1]); + sg_chain(sw_ctx->sg_aead_in, 2, sw_ctx->sg_plaintext_data); + sg_init_table(sw_ctx->sg_aead_out, 2); + sg_set_buf(&sw_ctx->sg_aead_out[0], sw_ctx->aad_space, + sizeof(sw_ctx->aad_space)); + sg_unmark_end(&sw_ctx->sg_aead_out[1]); + sg_chain(sw_ctx->sg_aead_out, 2, sw_ctx->sg_encrypted_data); + + if (!sw_ctx->aead_send) { + sw_ctx->aead_send = crypto_alloc_aead("gcm(aes)", 0, 0); + if (IS_ERR(sw_ctx->aead_send)) { + rc = PTR_ERR(sw_ctx->aead_send); + sw_ctx->aead_send = NULL; + goto free_rec_seq; + } + } + + ctx->push_pending_record = tls_sw_push_pending_record; + + memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); + + rc = crypto_aead_setkey(sw_ctx->aead_send, keyval, + TLS_CIPHER_AES_GCM_128_KEY_SIZE); + if (rc) + goto free_aead; + + rc = crypto_aead_setauthsize(sw_ctx->aead_send, ctx->tag_size); + if (!rc) + goto out; + +free_aead: + crypto_free_aead(sw_ctx->aead_send); + sw_ctx->aead_send = NULL; +free_rec_seq: + kfree(ctx->rec_seq); + ctx->rec_seq = NULL; +free_iv: + kfree(ctx->iv); + ctx->iv = NULL; +out: + return rc; +} -- cgit v1.2.3 From 5f56f409b5142bb4e88e1f64dedeb4a76c678177 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Sat, 17 Jun 2017 10:42:27 -0700 Subject: net: introduce DST_NOGC in dst_release() to destroy dst based on refcnt The current mechanism of freeing dst is a bit complicated. dst has its ref count and when user grabs the reference to the dst, the ref count is properly taken in most cases except in IPv4/IPv6/decnet/xfrm routing code due to some historic reasons. If the reference to dst is always taken properly, we should be able to simplify the logic in dst_release() to destroy dst when dst->__refcnt drops from 1 to 0. And this should be the only condition to determine if we can call dst_destroy(). And as dst is always ref counted, there is no need for a dst garbage list to hold the dst entries that already get removed by the routing code but are still held by other users. And the task to periodically check the list to free dst if ref count become 0 is also not needed anymore. This patch introduces a temporary flag DST_NOGC(no garbage collector). If it is set in the dst, dst_release() will call dst_destroy() when dst->__refcnt drops to 0. dst_hold_safe() will also check for this flag and do atomic_inc_not_zero() similar as DST_NOCACHE to avoid double free issue. This temporary flag is mainly used so that we can make the transition component by component without breaking other parts. This flag will be removed after all components are properly transitioned. This patch also introduces a new function dst_release_immediate() which destroys dst without waiting on the rcu when refcnt drops to 0. It will be used in later patches. Follow-up patches will correct all the places to properly take ref count on dst and mark DST_NOGC. dst_release() or dst_release_immediate() will be used to release the dst instead of dst_free() and its related functions. And final clean-up patch will remove the DST_NOGC flag. Signed-off-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/dst.h | 5 ++++- net/core/dst.c | 20 ++++++++++++++++++-- 2 files changed, 22 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 1969008783d8..2735d5a1e774 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -58,6 +58,7 @@ struct dst_entry { #define DST_XFRM_TUNNEL 0x0080 #define DST_XFRM_QUEUE 0x0100 #define DST_METADATA 0x0200 +#define DST_NOGC 0x0400 short error; @@ -278,6 +279,8 @@ static inline struct dst_entry *dst_clone(struct dst_entry *dst) void dst_release(struct dst_entry *dst); +void dst_release_immediate(struct dst_entry *dst); + static inline void refdst_drop(unsigned long refdst) { if (!(refdst & SKB_DST_NOREF)) @@ -334,7 +337,7 @@ static inline void skb_dst_force(struct sk_buff *skb) */ static inline bool dst_hold_safe(struct dst_entry *dst) { - if (dst->flags & DST_NOCACHE) + if (dst->flags & (DST_NOCACHE | DST_NOGC)) return atomic_inc_not_zero(&dst->__refcnt); dst_hold(dst); return true; diff --git a/net/core/dst.c b/net/core/dst.c index 13ba4a090c41..551834c3363f 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -300,18 +300,34 @@ void dst_release(struct dst_entry *dst) { if (dst) { int newrefcnt; - unsigned short nocache = dst->flags & DST_NOCACHE; + unsigned short destroy_after_rcu = dst->flags & + (DST_NOCACHE | DST_NOGC); newrefcnt = atomic_dec_return(&dst->__refcnt); if (unlikely(newrefcnt < 0)) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); - if (!newrefcnt && unlikely(nocache)) + if (!newrefcnt && unlikely(destroy_after_rcu)) call_rcu(&dst->rcu_head, dst_destroy_rcu); } } EXPORT_SYMBOL(dst_release); +void dst_release_immediate(struct dst_entry *dst) +{ + if (dst) { + int newrefcnt; + + newrefcnt = atomic_dec_return(&dst->__refcnt); + if (unlikely(newrefcnt < 0)) + net_warn_ratelimited("%s: dst:%p refcnt:%d\n", + __func__, dst, newrefcnt); + if (!newrefcnt) + dst_destroy(dst); + } +} +EXPORT_SYMBOL(dst_release_immediate); + u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) { struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC); -- cgit v1.2.3 From 4a6ce2b6f2ecabbddcfe47e7cf61dd0f00b10e36 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Sat, 17 Jun 2017 10:42:28 -0700 Subject: net: introduce a new function dst_dev_put() This function should be called when removing routes from fib tree after the dst gc is no longer in use. We first mark DST_OBSOLETE_DEAD on this dst to make sure next dst_ops->check() fails and returns NULL. Secondly, as we no longer keep the gc_list, we need to properly release dst->dev right at the moment when the dst is removed from the fib/fib6 tree. It does the following: 1. change dst->input and output pointers to dst_discard/dst_dscard_out to discard all packets 2. replace dst->dev with loopback interface Signed-off-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/dst.h | 1 + net/core/dst.c | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 2735d5a1e774..11d779803c0d 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -428,6 +428,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, unsigned short flags); void __dst_free(struct dst_entry *dst); struct dst_entry *dst_destroy(struct dst_entry *dst); +void dst_dev_put(struct dst_entry *dst); static inline void dst_free(struct dst_entry *dst) { diff --git a/net/core/dst.c b/net/core/dst.c index 551834c3363f..56998f69b84e 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -296,6 +296,30 @@ static void dst_destroy_rcu(struct rcu_head *head) __dst_free(dst); } +/* Operations to mark dst as DEAD and clean up the net device referenced + * by dst: + * 1. put the dst under loopback interface and discard all tx/rx packets + * on this route. + * 2. release the net_device + * This function should be called when removing routes from the fib tree + * in preparation for a NETDEV_DOWN/NETDEV_UNREGISTER event and also to + * make the next dst_ops->check() fail. + */ +void dst_dev_put(struct dst_entry *dst) +{ + struct net_device *dev = dst->dev; + + dst->obsolete = DST_OBSOLETE_DEAD; + if (dst->ops->ifdown) + dst->ops->ifdown(dst, dev, true); + dst->input = dst_discard; + dst->output = dst_discard_out; + dst->dev = dev_net(dst->dev)->loopback_dev; + dev_hold(dst->dev); + dev_put(dev); +} +EXPORT_SYMBOL(dst_dev_put); + void dst_release(struct dst_entry *dst) { if (dst) { -- cgit v1.2.3 From 9df16efadd2a8a82731dc76ff656c771e261827f Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Sat, 17 Jun 2017 10:42:31 -0700 Subject: ipv4: call dst_hold_safe() properly This patch checks all the calls to dst_hold()/skb_dst_force()/dst_clone()/dst_use() to see if dst_hold_safe() is needed to avoid double free issue if dst gc is removed and dst_release() directly destroys dst when dst->__refcnt drops to 0. In tx path, TCP hold sk->sk_rx_dst ref count and also hold sock_lock(). UDP and other similar protocols always hold refcount for skb->_skb_refdst. So both paths seem to be safe. In rx path, as it is lockless and skb_dst_set_noref() is likely to be used, dst_hold_safe() should always be used when trying to hold dst. In the routing code, if dst is held during an rcu protected session, it is necessary to call dst_hold_safe() as the current dst might be in its rcu grace period. Signed-off-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/route.h | 4 +++- net/ipv4/route.c | 4 +--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/route.h b/include/net/route.h index 08e689f23365..cb0a76d9dde1 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -190,7 +190,9 @@ static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, rcu_read_lock(); err = ip_route_input_noref(skb, dst, src, tos, devin); if (!err) - skb_dst_force(skb); + skb_dst_force_safe(skb); + if (!skb_dst(skb)) + err = -EINVAL; rcu_read_unlock(); return err; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d986d80258d2..903a12c601ac 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2234,10 +2234,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth = rcu_dereference(*prth); rt_cache: - if (rt_cache_valid(rth)) { - dst_hold(&rth->dst); + if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; - } } add: -- cgit v1.2.3 From db916649b5dd0fa2bddeb9427dab513b41e1e984 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Sat, 17 Jun 2017 10:42:37 -0700 Subject: ipv6: get rid of icmp6 dst garbage collector icmp6 dst route is currently ref counted during creation and will be freed by user during its call of dst_release(). So no need of a garbage collector for it. Remove all icmp6 dst garbage collector related code. Signed-off-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/ip6_route.h | 1 - net/ipv6/ip6_fib.c | 3 +-- net/ipv6/route.c | 46 ---------------------------------------------- 3 files changed, 1 insertion(+), 49 deletions(-) (limited to 'include/net') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f3da9dd2a8db..0fbf73dd531a 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -116,7 +116,6 @@ struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, int flags); struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6); -int icmp6_dst_gc(void); void fib6_force_start_gc(struct net *net); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index e3b35e146eef..c67ec79bf0da 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1822,8 +1822,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) } gc_args.timeout = expires ? (int)expires : net->ipv6.sysctl.ip6_rt_gc_interval; - - gc_args.more = icmp6_dst_gc(); + gc_args.more = 0; fib6_clean_all(net, fib6_age, &gc_args); now = jiffies; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5f859ee67172..c88044b8fa7c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1657,9 +1657,6 @@ out: return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } -static struct dst_entry *icmp6_dst_gc_list; -static DEFINE_SPINLOCK(icmp6_dst_lock); - struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6) { @@ -1697,48 +1694,6 @@ out: return dst; } -int icmp6_dst_gc(void) -{ - struct dst_entry *dst, **pprev; - int more = 0; - - spin_lock_bh(&icmp6_dst_lock); - pprev = &icmp6_dst_gc_list; - - while ((dst = *pprev) != NULL) { - if (!atomic_read(&dst->__refcnt)) { - *pprev = dst->next; - dst_free(dst); - } else { - pprev = &dst->next; - ++more; - } - } - - spin_unlock_bh(&icmp6_dst_lock); - - return more; -} - -static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg), - void *arg) -{ - struct dst_entry *dst, **pprev; - - spin_lock_bh(&icmp6_dst_lock); - pprev = &icmp6_dst_gc_list; - while ((dst = *pprev) != NULL) { - struct rt6_info *rt = (struct rt6_info *) dst; - if (func(rt, arg)) { - *pprev = dst->next; - dst_free(dst); - } else { - pprev = &dst->next; - } - } - spin_unlock_bh(&icmp6_dst_lock); -} - static int ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); @@ -2856,7 +2811,6 @@ void rt6_ifdown(struct net *net, struct net_device *dev) }; fib6_clean_all(net, fib6_ifdown, &adn); - icmp6_clean_all(fib6_ifdown, &adn); if (dev) rt6_uncached_list_flush_dev(net, dev); } -- cgit v1.2.3 From 52df157f17e564ec22afc3e4a89b21828220f576 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Sat, 17 Jun 2017 10:42:38 -0700 Subject: xfrm: take refcnt of dst when creating struct xfrm_dst bundle During the creation of xfrm_dst bundle, always take ref count when allocating the dst. This way, xfrm_bundle_create() will form a linked list of dst with dst->child pointing to a ref counted dst child. And the returned dst pointer is also ref counted. This makes the link from the flow cache to this dst now ref counted properly. As the dst is always ref counted properly, we can safely mark DST_NOGC flag so dst_release() will release dst based on refcnt only. And dst gc is no longer needed and all dst_free() and its related function calls should be replaced with dst_release() or dst_release_immediate(). The special handling logic for dst->child in dst_destroy() can be replaced with a simple dst_release_immediate() call on the child to release the whole list linked by dst->child pointer. Previously used DST_NOHASH flag is not needed anymore as well. The reason that DST_NOHASH is used in the existing code is mainly to prevent the dst inserted in the fib tree to be wrongly destroyed during the deletion of the xfrm_dst bundle. So in the existing code, DST_NOHASH flag is marked in all the dst children except the one which is in the fib tree. However, with this patch series to remove dst gc logic and release dst only based on ref count, it is safe to release all the children from a xfrm_dst bundle as long as the dst children are all ref counted properly which is already the case in the existing code. So, this patch removes the use of DST_NOHASH flag. Signed-off-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/dst.h | 1 - net/core/dst.c | 19 ++----------------- net/xfrm/xfrm_policy.c | 48 ++++++++++++++++++++++++++++++------------------ 3 files changed, 32 insertions(+), 36 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 11d779803c0d..88ebb87ad312 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -51,7 +51,6 @@ struct dst_entry { #define DST_HOST 0x0001 #define DST_NOXFRM 0x0002 #define DST_NOPOLICY 0x0004 -#define DST_NOHASH 0x0008 #define DST_NOCACHE 0x0010 #define DST_NOCOUNT 0x0020 #define DST_FAKE_RTABLE 0x0040 diff --git a/net/core/dst.c b/net/core/dst.c index 56998f69b84e..64056ecca5b8 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -250,7 +250,6 @@ struct dst_entry *dst_destroy(struct dst_entry * dst) smp_rmb(); -again: child = dst->child; if (!(dst->flags & DST_NOCOUNT)) @@ -269,20 +268,8 @@ again: kmem_cache_free(dst->ops->kmem_cachep, dst); dst = child; - if (dst) { - int nohash = dst->flags & DST_NOHASH; - - if (atomic_dec_and_test(&dst->__refcnt)) { - /* We were real parent of this dst, so kill child. */ - if (nohash) - goto again; - } else { - /* Child is still referenced, return it for freeing. */ - if (nohash) - return dst; - /* Child is still in his hash table */ - } - } + if (dst) + dst_release_immediate(dst); return NULL; } EXPORT_SYMBOL(dst_destroy); @@ -292,8 +279,6 @@ static void dst_destroy_rcu(struct rcu_head *head) struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); dst = dst_destroy(dst); - if (dst) - __dst_free(dst); } /* Operations to mark dst as DEAD and clean up the net device referenced diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ed4e52d95172..85e1e13639cc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1590,7 +1590,9 @@ static void xfrm_bundle_flo_delete(struct flow_cache_object *flo) struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo); struct dst_entry *dst = &xdst->u.dst; - dst_free(dst); + /* Mark DST_OBSOLETE_DEAD to fail the next xfrm_dst_check() */ + dst->obsolete = DST_OBSOLETE_DEAD; + dst_release_immediate(dst); } static const struct flow_cache_ops xfrm_bundle_fc_ops = { @@ -1620,7 +1622,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) default: BUG(); } - xdst = dst_alloc(dst_ops, NULL, 0, DST_OBSOLETE_NONE, 0); + xdst = dst_alloc(dst_ops, NULL, 1, DST_OBSOLETE_NONE, DST_NOGC); if (likely(xdst)) { struct dst_entry *dst = &xdst->u.dst; @@ -1723,10 +1725,11 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (!dst_prev) dst0 = dst1; - else { - dst_prev->child = dst_clone(dst1); - dst1->flags |= DST_NOHASH; - } + else + /* Ref count is taken during xfrm_alloc_dst() + * No need to do dst_clone() on dst1 + */ + dst_prev->child = dst1; xdst->route = dst; dst_copy_metrics(dst1, dst); @@ -1792,7 +1795,7 @@ put_states: xfrm_state_put(xfrm[i]); free_dst: if (dst0) - dst_free(dst0); + dst_release_immediate(dst0); dst0 = ERR_PTR(err); goto out; } @@ -2073,7 +2076,11 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, pol_dead |= pols[i]->walk.dead; } if (pol_dead) { - dst_free(&xdst->u.dst); + /* Mark DST_OBSOLETE_DEAD to fail the next + * xfrm_dst_check() + */ + xdst->u.dst.obsolete = DST_OBSOLETE_DEAD; + dst_release_immediate(&xdst->u.dst); xdst = NULL; num_pols = 0; num_xfrms = 0; @@ -2120,11 +2127,12 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, if (xdst) { /* The policies were stolen for newly generated bundle */ xdst->num_pols = 0; - dst_free(&xdst->u.dst); + /* Mark DST_OBSOLETE_DEAD to fail the next xfrm_dst_check() */ + xdst->u.dst.obsolete = DST_OBSOLETE_DEAD; + dst_release_immediate(&xdst->u.dst); } - /* Flow cache does not have reference, it dst_free()'s, - * but we do need to return one reference for original caller */ + /* We do need to return one reference for original caller */ dst_hold(&new_xdst->u.dst); return &new_xdst->flo; @@ -2147,9 +2155,11 @@ make_dummy_bundle: inc_error: XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); error: - if (xdst != NULL) - dst_free(&xdst->u.dst); - else + if (xdst != NULL) { + /* Mark DST_OBSOLETE_DEAD to fail the next xfrm_dst_check() */ + xdst->u.dst.obsolete = DST_OBSOLETE_DEAD; + dst_release_immediate(&xdst->u.dst); + } else xfrm_pols_put(pols, num_pols); return ERR_PTR(err); } @@ -2636,10 +2646,12 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) * notice. That's what we are validating here via the * stale_bundle() check. * - * When a policy's bundle is pruned, we dst_free() the XFRM - * dst which causes it's ->obsolete field to be set to - * DST_OBSOLETE_DEAD. If an XFRM dst has been pruned like - * this, we want to force a new route lookup. + * When an xdst is removed from flow cache, DST_OBSOLETE_DEAD will + * be marked on it. + * When a dst is removed from the fib tree, DST_OBSOLETE_DEAD will + * be marked on it. + * Both will force stable_bundle() to fail on any xdst bundle with + * this dst linked in it. */ if (dst->obsolete < 0 && !stale_bundle(dst)) return dst; -- cgit v1.2.3 From 5b7c9a8ff828287af5aebe93e707271bf1a82cc3 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Sat, 17 Jun 2017 10:42:40 -0700 Subject: net: remove dst gc related code This patch removes all dst gc related code and all the dst free functions Signed-off-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/dst.h | 21 ------ net/core/dev.c | 1 - net/core/dst.c | 213 ------------------------------------------------------ 3 files changed, 235 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 88ebb87ad312..0c56d1fc4d7f 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -425,28 +425,9 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref, void dst_init(struct dst_entry *dst, struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, unsigned short flags); -void __dst_free(struct dst_entry *dst); struct dst_entry *dst_destroy(struct dst_entry *dst); void dst_dev_put(struct dst_entry *dst); -static inline void dst_free(struct dst_entry *dst) -{ - if (dst->obsolete > 0) - return; - if (!atomic_read(&dst->__refcnt)) { - dst = dst_destroy(dst); - if (!dst) - return; - } - __dst_free(dst); -} - -static inline void dst_rcu_free(struct rcu_head *head) -{ - struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); - dst_free(dst); -} - static inline void dst_confirm(struct dst_entry *dst) { } @@ -508,8 +489,6 @@ static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie) return dst; } -void dst_subsys_init(void); - /* Flags for xfrm_lookup flags argument. */ enum { XFRM_LOOKUP_ICMP = 1 << 0, diff --git a/net/core/dev.c b/net/core/dev.c index b8d6dd9e8b5c..5d1830b8d2cf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8681,7 +8681,6 @@ static int __init net_dev_init(void) rc = cpuhp_setup_state_nocalls(CPUHP_NET_DEV_DEAD, "net/dev:dead", NULL, dev_cpu_dead); WARN_ON(rc < 0); - dst_subsys_init(); rc = 0; out: return rc; diff --git a/net/core/dst.c b/net/core/dst.c index 64056ecca5b8..30bea01d2262 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -42,108 +42,6 @@ * 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. */ -static struct { - spinlock_t lock; - struct dst_entry *list; - unsigned long timer_inc; - unsigned long timer_expires; -} dst_garbage = { - .lock = __SPIN_LOCK_UNLOCKED(dst_garbage.lock), - .timer_inc = DST_GC_MAX, -}; -static void dst_gc_task(struct work_struct *work); -static void ___dst_free(struct dst_entry *dst); - -static DECLARE_DELAYED_WORK(dst_gc_work, dst_gc_task); - -static DEFINE_MUTEX(dst_gc_mutex); -/* - * long lived entries are maintained in this list, guarded by dst_gc_mutex - */ -static struct dst_entry *dst_busy_list; - -static void dst_gc_task(struct work_struct *work) -{ - int delayed = 0; - int work_performed = 0; - unsigned long expires = ~0L; - struct dst_entry *dst, *next, head; - struct dst_entry *last = &head; - - mutex_lock(&dst_gc_mutex); - next = dst_busy_list; - -loop: - while ((dst = next) != NULL) { - next = dst->next; - prefetch(&next->next); - cond_resched(); - if (likely(atomic_read(&dst->__refcnt))) { - last->next = dst; - last = dst; - delayed++; - continue; - } - work_performed++; - - dst = dst_destroy(dst); - if (dst) { - /* NOHASH and still referenced. Unless it is already - * on gc list, invalidate it and add to gc list. - * - * Note: this is temporary. Actually, NOHASH dst's - * must be obsoleted when parent is obsoleted. - * But we do not have state "obsoleted, but - * referenced by parent", so it is right. - */ - if (dst->obsolete > 0) - continue; - - ___dst_free(dst); - dst->next = next; - next = dst; - } - } - - spin_lock_bh(&dst_garbage.lock); - next = dst_garbage.list; - if (next) { - dst_garbage.list = NULL; - spin_unlock_bh(&dst_garbage.lock); - goto loop; - } - last->next = NULL; - dst_busy_list = head.next; - if (!dst_busy_list) - dst_garbage.timer_inc = DST_GC_MAX; - else { - /* - * if we freed less than 1/10 of delayed entries, - * we can sleep longer. - */ - if (work_performed <= delayed/10) { - dst_garbage.timer_expires += dst_garbage.timer_inc; - if (dst_garbage.timer_expires > DST_GC_MAX) - dst_garbage.timer_expires = DST_GC_MAX; - dst_garbage.timer_inc += DST_GC_INC; - } else { - dst_garbage.timer_inc = DST_GC_INC; - dst_garbage.timer_expires = DST_GC_MIN; - } - expires = dst_garbage.timer_expires; - /* - * if the next desired timer is more than 4 seconds in the - * future then round the timer to whole seconds - */ - if (expires > 4*HZ) - expires = round_jiffies_relative(expires); - schedule_delayed_work(&dst_gc_work, expires); - } - - spin_unlock_bh(&dst_garbage.lock); - mutex_unlock(&dst_gc_mutex); -} - int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); @@ -216,34 +114,6 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, } EXPORT_SYMBOL(dst_alloc); -static void ___dst_free(struct dst_entry *dst) -{ - /* The first case (dev==NULL) is required, when - protocol module is unloaded. - */ - if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { - dst->input = dst_discard; - dst->output = dst_discard_out; - } - dst->obsolete = DST_OBSOLETE_DEAD; -} - -void __dst_free(struct dst_entry *dst) -{ - spin_lock_bh(&dst_garbage.lock); - ___dst_free(dst); - dst->next = dst_garbage.list; - dst_garbage.list = dst; - if (dst_garbage.timer_inc > DST_GC_INC) { - dst_garbage.timer_inc = DST_GC_INC; - dst_garbage.timer_expires = DST_GC_MIN; - mod_delayed_work(system_wq, &dst_gc_work, - dst_garbage.timer_expires); - } - spin_unlock_bh(&dst_garbage.lock); -} -EXPORT_SYMBOL(__dst_free); - struct dst_entry *dst_destroy(struct dst_entry * dst) { struct dst_entry *child; @@ -448,86 +318,3 @@ struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags) return md_dst; } EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); - -/* Dirty hack. We did it in 2.2 (in __dst_free), - * we have _very_ good reasons not to repeat - * this mistake in 2.3, but we have no choice - * now. _It_ _is_ _explicit_ _deliberate_ - * _race_ _condition_. - * - * Commented and originally written by Alexey. - */ -static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int unregister) -{ - if (dst->ops->ifdown) - dst->ops->ifdown(dst, dev, unregister); - - if (dev != dst->dev) - return; - - if (!unregister) { - dst->input = dst_discard; - dst->output = dst_discard_out; - } else { - dst->dev = dev_net(dst->dev)->loopback_dev; - dev_hold(dst->dev); - dev_put(dev); - } -} - -static int dst_dev_event(struct notifier_block *this, unsigned long event, - void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct dst_entry *dst, *last = NULL; - - switch (event) { - case NETDEV_UNREGISTER_FINAL: - case NETDEV_DOWN: - mutex_lock(&dst_gc_mutex); - for (dst = dst_busy_list; dst; dst = dst->next) { - last = dst; - dst_ifdown(dst, dev, event != NETDEV_DOWN); - } - - spin_lock_bh(&dst_garbage.lock); - dst = dst_garbage.list; - dst_garbage.list = NULL; - /* The code in dst_ifdown places a hold on the loopback device. - * If the gc entry processing is set to expire after a lengthy - * interval, this hold can cause netdev_wait_allrefs() to hang - * out and wait for a long time -- until the the loopback - * interface is released. If we're really unlucky, it'll emit - * pr_emerg messages to console too. Reset the interval here, - * so dst cleanups occur in a more timely fashion. - */ - if (dst_garbage.timer_inc > DST_GC_INC) { - dst_garbage.timer_inc = DST_GC_INC; - dst_garbage.timer_expires = DST_GC_MIN; - mod_delayed_work(system_wq, &dst_gc_work, - dst_garbage.timer_expires); - } - spin_unlock_bh(&dst_garbage.lock); - - if (last) - last->next = dst; - else - dst_busy_list = dst; - for (; dst; dst = dst->next) - dst_ifdown(dst, dev, event != NETDEV_DOWN); - mutex_unlock(&dst_gc_mutex); - break; - } - return NOTIFY_DONE; -} - -static struct notifier_block dst_dev_notifier = { - .notifier_call = dst_dev_event, - .priority = -10, /* must be called after other network notifiers */ -}; - -void __init dst_subsys_init(void) -{ - register_netdevice_notifier(&dst_dev_notifier); -} -- cgit v1.2.3 From b2a9c0ed75a32e788d034a58a18f2fc46396e412 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Sat, 17 Jun 2017 10:42:41 -0700 Subject: net: remove DST_NOGC flag Now that all the components have been changed to release dst based on refcnt only and not depend on dst gc anymore, we can remove the temporary flag DST_NOGC. Note that we also need to remove the DST_NOCACHE check in dst_release() and dst_hold_safe() because now all the dst are released based on refcnt and behaves as DST_NOCACHE. Signed-off-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/dst.h | 6 +----- net/core/dst.c | 4 +--- net/decnet/dn_route.c | 6 ++---- net/ipv4/route.c | 5 ++--- net/ipv6/route.c | 5 ++--- net/xfrm/xfrm_policy.c | 2 +- 6 files changed, 9 insertions(+), 19 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 0c56d1fc4d7f..1be82f672c37 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -57,7 +57,6 @@ struct dst_entry { #define DST_XFRM_TUNNEL 0x0080 #define DST_XFRM_QUEUE 0x0100 #define DST_METADATA 0x0200 -#define DST_NOGC 0x0400 short error; @@ -336,10 +335,7 @@ static inline void skb_dst_force(struct sk_buff *skb) */ static inline bool dst_hold_safe(struct dst_entry *dst) { - if (dst->flags & (DST_NOCACHE | DST_NOGC)) - return atomic_inc_not_zero(&dst->__refcnt); - dst_hold(dst); - return true; + return atomic_inc_not_zero(&dst->__refcnt); } /** diff --git a/net/core/dst.c b/net/core/dst.c index 30bea01d2262..70543dabb797 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -179,14 +179,12 @@ void dst_release(struct dst_entry *dst) { if (dst) { int newrefcnt; - unsigned short destroy_after_rcu = dst->flags & - (DST_NOCACHE | DST_NOGC); newrefcnt = atomic_dec_return(&dst->__refcnt); if (unlikely(newrefcnt < 0)) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); - if (!newrefcnt && unlikely(destroy_after_rcu)) + if (!newrefcnt) call_rcu(&dst->rcu_head, dst_destroy_rcu); } } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index f467c4e3205b..5d17d843ac86 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1179,8 +1179,7 @@ make_route: if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, - DST_HOST | DST_NOGC); + rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, DST_HOST); if (rt == NULL) goto e_nobufs; @@ -1445,8 +1444,7 @@ static int dn_route_input_slow(struct sk_buff *skb) } make_route: - rt = dst_alloc(&dn_dst_ops, out_dev, 1, DST_OBSOLETE_NONE, - DST_HOST | DST_NOGC); + rt = dst_alloc(&dn_dst_ops, out_dev, 1, DST_OBSOLETE_NONE, DST_HOST); if (rt == NULL) goto e_nobufs; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 80b30c2bf47d..9a0f496f8bf4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1496,8 +1496,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | (nopolicy ? DST_NOPOLICY : 0) | - (noxfrm ? DST_NOXFRM : 0) | - DST_NOGC); + (noxfrm ? DST_NOXFRM : 0)); if (rt) { rt->rt_genid = rt_genid_ipv4(dev_net(dev)); @@ -2503,7 +2502,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or struct rtable *ort = (struct rtable *) dst_orig; struct rtable *rt; - rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, DST_NOGC); + rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0); if (rt) { struct dst_entry *new = &rt->dst; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c88044b8fa7c..6b6528fa3292 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -354,8 +354,7 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, int flags) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, - 1, DST_OBSOLETE_FORCE_CHK, - flags | DST_NOGC); + 1, DST_OBSOLETE_FORCE_CHK, flags); if (rt) rt6_info_init(rt); @@ -1255,7 +1254,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori struct dst_entry *new = NULL; rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, 1, - DST_OBSOLETE_NONE, DST_NOGC); + DST_OBSOLETE_NONE, 0); if (rt) { rt6_info_init(rt); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 85e1e13639cc..3f7e77f11112 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1622,7 +1622,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) default: BUG(); } - xdst = dst_alloc(dst_ops, NULL, 1, DST_OBSOLETE_NONE, DST_NOGC); + xdst = dst_alloc(dst_ops, NULL, 1, DST_OBSOLETE_NONE, 0); if (likely(xdst)) { struct dst_entry *dst = &xdst->u.dst; -- cgit v1.2.3 From a4c2fd7f78915a0d7c5275e7612e7793157a01f2 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Sat, 17 Jun 2017 10:42:42 -0700 Subject: net: remove DST_NOCACHE flag DST_NOCACHE flag check has been removed from dst_release() and dst_hold_safe() in a previous patch because all the dst are now ref counted properly and can be released based on refcnt only. Looking at the rest of the DST_NOCACHE use, all of them can now be removed or replaced with other checks. So this patch gets rid of all the DST_NOCACHE usage and remove this flag completely. Signed-off-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- drivers/net/vrf.c | 2 +- include/net/dst.h | 1 - include/net/ip6_fib.h | 2 +- net/core/dst.c | 2 +- net/ipv4/route.c | 23 +++++++++++------------ net/ipv6/ip6_fib.c | 4 +--- net/ipv6/route.c | 7 ++----- net/xfrm/xfrm_policy.c | 1 - 8 files changed, 17 insertions(+), 25 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index d038927acfca..997ef25189fd 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -563,7 +563,7 @@ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) static int vrf_rt6_create(struct net_device *dev) { - int flags = DST_HOST | DST_NOPOLICY | DST_NOXFRM | DST_NOCACHE; + int flags = DST_HOST | DST_NOPOLICY | DST_NOXFRM; struct net_vrf *vrf = netdev_priv(dev); struct net *net = dev_net(dev); struct fib6_table *rt6i_table; diff --git a/include/net/dst.h b/include/net/dst.h index 1be82f672c37..642483ed4edf 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -51,7 +51,6 @@ struct dst_entry { #define DST_HOST 0x0001 #define DST_NOXFRM 0x0002 #define DST_NOPOLICY 0x0004 -#define DST_NOCACHE 0x0010 #define DST_NOCOUNT 0x0020 #define DST_FAKE_RTABLE 0x0040 #define DST_XFRM_TUNNEL 0x0080 diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index aa50e2e6fa2a..1a88008cc6f5 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -170,7 +170,7 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) static inline u32 rt6_get_cookie(const struct rt6_info *rt) { if (rt->rt6i_flags & RTF_PCPU || - (unlikely(rt->dst.flags & DST_NOCACHE) && rt->dst.from)) + (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->dst.from)) rt = (struct rt6_info *)(rt->dst.from); return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; diff --git a/net/core/dst.c b/net/core/dst.c index 70543dabb797..f851adb9ec9b 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -270,7 +270,7 @@ static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen) dst = &md_dst->dst; dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE, - DST_METADATA | DST_NOCACHE | DST_NOCOUNT); + DST_METADATA | DST_NOCOUNT); dst->input = dst_md_discard; dst->output = dst_md_discard_out; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 9a0f496f8bf4..c816cd53f7fc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1299,7 +1299,7 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) } static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, - __be32 daddr) + __be32 daddr, const bool do_cache) { bool ret = false; @@ -1328,7 +1328,7 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, if (!rt->rt_gateway) rt->rt_gateway = daddr; - if (!(rt->dst.flags & DST_NOCACHE)) { + if (do_cache) { dst_hold(&rt->dst); rcu_assign_pointer(*porig, rt); if (orig) { @@ -1441,7 +1441,8 @@ static bool rt_cache_valid(const struct rtable *rt) static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, struct fib_nh_exception *fnhe, - struct fib_info *fi, u16 type, u32 itag) + struct fib_info *fi, u16 type, u32 itag, + const bool do_cache) { bool cached = false; @@ -1462,8 +1463,8 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, #endif rt->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); if (unlikely(fnhe)) - cached = rt_bind_exception(rt, fnhe, daddr); - else if (!(rt->dst.flags & DST_NOCACHE)) + cached = rt_bind_exception(rt, fnhe, daddr, do_cache); + else if (do_cache) cached = rt_cache_route(nh, rt); if (unlikely(!cached)) { /* Routes we intend to cache in nexthop exception or @@ -1471,7 +1472,6 @@ 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. */ - rt->dst.flags |= DST_NOCACHE; if (!rt->rt_gateway) rt->rt_gateway = daddr; rt_add_uncached_list(rt); @@ -1494,7 +1494,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, struct rtable *rt; rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, - (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | + (will_cache ? 0 : DST_HOST) | (nopolicy ? DST_NOPOLICY : 0) | (noxfrm ? DST_NOXFRM : 0)); @@ -1738,7 +1738,8 @@ rt_cache: rth->dst.input = ip_forward; - rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag); + rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, + do_cache); set_lwt_redirect(rth); skb_dst_set(skb, &rth->dst); out: @@ -2026,10 +2027,8 @@ local_input: rth->dst.input = lwtunnel_input; } - if (unlikely(!rt_cache_route(nh, rth))) { - rth->dst.flags |= DST_NOCACHE; + if (unlikely(!rt_cache_route(nh, rth))) rt_add_uncached_list(rth); - } } skb_dst_set(skb, &rth->dst); err = 0; @@ -2260,7 +2259,7 @@ add: #endif } - rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0); + rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); set_lwt_redirect(rth); return rth; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index c67ec79bf0da..4f3e4657f2d6 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -975,8 +975,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, int replace_required = 0; int sernum = fib6_new_sernum(info->nl_net); - if (WARN_ON_ONCE((rt->dst.flags & DST_NOCACHE) && - !atomic_read(&rt->dst.__refcnt))) + if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt))) return -EINVAL; if (info->nlh) { @@ -1073,7 +1072,6 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, fib6_start_gc(info->nl_net, rt); if (!(rt->rt6i_flags & RTF_CACHE)) fib6_prune_clones(info->nl_net, pn); - rt->dst.flags &= ~DST_NOCACHE; } out: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6b6528fa3292..2e4490076061 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -128,7 +128,6 @@ static void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); - rt->dst.flags |= DST_NOCACHE; rt->rt6i_uncached_list = ul; spin_lock_bh(&ul->lock); @@ -1326,7 +1325,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt6_dst_from_metrics_check(rt); if (rt->rt6i_flags & RTF_PCPU || - (unlikely(dst->flags & DST_NOCACHE) && rt->dst.from)) + (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->dst.from)) return rt6_dst_from_check(rt, cookie); else return rt6_check(rt, cookie); @@ -2130,8 +2129,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) struct fib6_table *table; struct net *net = dev_net(rt->dst.dev); - if (rt == net->ipv6.ip6_null_entry || - rt->dst.flags & DST_NOCACHE) { + if (rt == net->ipv6.ip6_null_entry) { err = -ENOENT; goto out; } @@ -2722,7 +2720,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_dst.plen = 128; tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; rt->rt6i_table = fib6_get_table(net, tb_id); - rt->dst.flags |= DST_NOCACHE; return rt; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 3f7e77f11112..af8e38f47b5b 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2231,7 +2231,6 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, } dst_hold(&xdst->u.dst); - xdst->u.dst.flags |= DST_NOCACHE; route = xdst->route; } } -- cgit v1.2.3 From 1eb04e7c9e63e0480cc52b84187283de4fe5f982 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Sat, 17 Jun 2017 10:42:43 -0700 Subject: net: reorder all the dst flags As some dst flags are removed, reorder the dst flags to fill in the blanks. Note: these flags are not exposed into user space. So it is safe to reorder. Signed-off-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/dst.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 642483ed4edf..d912b44d2dcb 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -51,11 +51,11 @@ struct dst_entry { #define DST_HOST 0x0001 #define DST_NOXFRM 0x0002 #define DST_NOPOLICY 0x0004 -#define DST_NOCOUNT 0x0020 -#define DST_FAKE_RTABLE 0x0040 -#define DST_XFRM_TUNNEL 0x0080 -#define DST_XFRM_QUEUE 0x0100 -#define DST_METADATA 0x0200 +#define DST_NOCOUNT 0x0008 +#define DST_FAKE_RTABLE 0x0010 +#define DST_XFRM_TUNNEL 0x0020 +#define DST_XFRM_QUEUE 0x0040 +#define DST_METADATA 0x0080 short error; -- cgit v1.2.3 From 44ebe79149ff415e810529bf192faa5c38d4a0de Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Sat, 17 Jun 2017 10:42:44 -0700 Subject: net: add debug atomic_inc_not_zero() in dst_hold() This patch is meant to add a debug warning on the situation where dst is being held during its destroy phase. This could potentially cause double free issue on the dst. Signed-off-by: Wei Wang Acked-by: Martin KaFai Lau Signed-off-by: David S. Miller --- include/net/dst.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index d912b44d2dcb..f73611ec4017 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -251,7 +251,7 @@ static inline void dst_hold(struct dst_entry *dst) * __pad_to_align_refcnt declaration in struct dst_entry */ BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63); - atomic_inc(&dst->__refcnt); + WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0); } static inline void dst_use(struct dst_entry *dst, unsigned long time) -- cgit v1.2.3 From 7866cc57b51c1e118e5d78d1a8f721f378eec5c4 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 30 May 2017 11:38:12 +0200 Subject: netns: add and use net_ns_barrier Quoting Joe Stringer: If a user loads nf_conntrack_ftp, sends FTP traffic through a network namespace, destroys that namespace then unloads the FTP helper module, then the kernel will crash. Events that lead to the crash: 1. conntrack is created with ftp helper in netns x 2. This netns is destroyed 3. netns destruction is scheduled 4. netns destruction wq starts, removes netns from global list 5. ftp helper is unloaded, which resets all helpers of the conntracks via for_each_net() but because netns is already gone from list the for_each_net() loop doesn't include it, therefore all of these conntracks are unaffected. 6. helper module unload finishes 7. netns wq invokes destructor for rmmod'ed helper CC: "Eric W. Biederman" Reported-by: Joe Stringer Signed-off-by: Florian Westphal Acked-by: David S. Miller Acked-by: "Eric W. Biederman" Signed-off-by: Pablo Neira Ayuso --- include/net/net_namespace.h | 3 +++ net/core/net_namespace.c | 17 +++++++++++++++++ net/netfilter/nf_conntrack_core.c | 9 +++++++++ 3 files changed, 29 insertions(+) (limited to 'include/net') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index fe80bb48ab1f..a24a57593202 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -158,6 +158,7 @@ extern struct net init_net; struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net); +void net_ns_barrier(void); #else /* CONFIG_NET_NS */ #include #include @@ -168,6 +169,8 @@ static inline struct net *copy_net_ns(unsigned long flags, return ERR_PTR(-EINVAL); return old_net; } + +static inline void net_ns_barrier(void) {} #endif /* CONFIG_NET_NS */ diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 1934efd4a9d4..1f15abb1d733 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -482,6 +482,23 @@ static void cleanup_net(struct work_struct *work) net_drop_ns(net); } } + +/** + * net_ns_barrier - wait until concurrent net_cleanup_work is done + * + * cleanup_net runs from work queue and will first remove namespaces + * from the global list, then run net exit functions. + * + * Call this in module exit path to make sure that all netns + * ->exit ops have been invoked before the function is removed. + */ +void net_ns_barrier(void) +{ + mutex_lock(&net_mutex); + mutex_unlock(&net_mutex); +} +EXPORT_SYMBOL(net_ns_barrier); + static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c3bd9b086dcc..9979f46c81dc 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1720,6 +1720,8 @@ EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup_net); * Like nf_ct_iterate_cleanup, but first marks conntracks on the * unconfirmed list as dying (so they will not be inserted into * main table). + * + * Can only be called in module exit path. */ void nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data) @@ -1734,6 +1736,13 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data) } rtnl_unlock(); + /* Need to wait for netns cleanup worker to finish, if its + * running -- it might have deleted a net namespace from + * the global list, so our __nf_ct_unconfirmed_destroy() might + * not have affected all namespaces. + */ + net_ns_barrier(); + /* a conntrack could have been unlinked from unconfirmed list * before we grabbed pcpu lock in __nf_ct_unconfirmed_destroy(). * This makes sure its inserted into conntrack table. -- cgit v1.2.3 From b7b5fda4686874c9b9b8c27ba9d57a8534f48a70 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 14 Jun 2017 11:54:07 +0200 Subject: netfilter: conntrack: use NFPROTO_MAX to size array We don't support anything larger than NFPROTO_MAX, so we can shrink this a bit: text data dec hex filename old: 8259 1096 9355 248b net/netfilter/nf_conntrack_proto.o new: 8259 624 8883 22b3 net/netfilter/nf_conntrack_proto.o Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l3proto.h | 4 ++-- net/netfilter/nf_conntrack_proto.c | 18 +++++++++--------- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index e01559b4d781..6d14b36e3a49 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -71,7 +71,7 @@ struct nf_conntrack_l3proto { struct module *me; }; -extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX]; +extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO]; #ifdef CONFIG_SYSCTL /* Protocol pernet registration. */ @@ -100,7 +100,7 @@ extern struct nf_conntrack_l3proto nf_conntrack_l3proto_generic; static inline struct nf_conntrack_l3proto * __nf_ct_l3proto_find(u_int16_t l3proto) { - if (unlikely(l3proto >= AF_MAX)) + if (unlikely(l3proto >= NFPROTO_NUMPROTO)) return &nf_conntrack_l3proto_generic; return rcu_dereference(nf_ct_l3protos[l3proto]); } diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 6a36623e897c..1dcad229c3cc 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -28,8 +28,8 @@ #include #include -static struct nf_conntrack_l4proto __rcu **nf_ct_protos[PF_MAX] __read_mostly; -struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX] __read_mostly; +static struct nf_conntrack_l4proto __rcu **nf_ct_protos[NFPROTO_NUMPROTO] __read_mostly; +struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO] __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_l3protos); static DEFINE_MUTEX(nf_ct_proto_mutex); @@ -68,7 +68,7 @@ nf_ct_unregister_sysctl(struct ctl_table_header **header, struct nf_conntrack_l4proto * __nf_ct_l4proto_find(u_int16_t l3proto, u_int8_t l4proto) { - if (unlikely(l3proto >= AF_MAX || nf_ct_protos[l3proto] == NULL)) + if (unlikely(l3proto >= NFPROTO_NUMPROTO || nf_ct_protos[l3proto] == NULL)) return &nf_conntrack_l4proto_generic; return rcu_dereference(nf_ct_protos[l3proto][l4proto]); @@ -212,7 +212,7 @@ int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto) int ret = 0; struct nf_conntrack_l3proto *old; - if (proto->l3proto >= AF_MAX) + if (proto->l3proto >= NFPROTO_NUMPROTO) return -EBUSY; if (proto->tuple_to_nlattr && !proto->nlattr_tuple_size) @@ -254,7 +254,7 @@ EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_register); void nf_ct_l3proto_unregister(struct nf_conntrack_l3proto *proto) { - BUG_ON(proto->l3proto >= AF_MAX); + BUG_ON(proto->l3proto >= NFPROTO_NUMPROTO); mutex_lock(&nf_ct_proto_mutex); BUG_ON(rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], @@ -341,7 +341,7 @@ int nf_ct_l4proto_register_one(struct nf_conntrack_l4proto *l4proto) { int ret = 0; - if (l4proto->l3proto >= PF_MAX) + if (l4proto->l3proto >= ARRAY_SIZE(nf_ct_protos)) return -EBUSY; if ((l4proto->to_nlattr && !l4proto->nlattr_size) || @@ -423,7 +423,7 @@ EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register_one); static void __nf_ct_l4proto_unregister_one(struct nf_conntrack_l4proto *l4proto) { - BUG_ON(l4proto->l3proto >= PF_MAX); + BUG_ON(l4proto->l3proto >= ARRAY_SIZE(nf_ct_protos)); BUG_ON(rcu_dereference_protected( nf_ct_protos[l4proto->l3proto][l4proto->l4proto], @@ -556,7 +556,7 @@ void nf_conntrack_proto_pernet_fini(struct net *net) int nf_conntrack_proto_init(void) { unsigned int i; - for (i = 0; i < AF_MAX; i++) + for (i = 0; i < NFPROTO_NUMPROTO; i++) rcu_assign_pointer(nf_ct_l3protos[i], &nf_conntrack_l3proto_generic); return 0; @@ -566,6 +566,6 @@ void nf_conntrack_proto_fini(void) { unsigned int i; /* free l3proto protocol tables */ - for (i = 0; i < PF_MAX; i++) + for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++) kfree(nf_ct_protos[i]); } -- cgit v1.2.3 From 6797318e623da68dfbacd0cb5c246f5ecd2baf6e Mon Sep 17 00:00:00 2001 From: Ivan Delalande Date: Thu, 15 Jun 2017 18:07:06 -0700 Subject: tcp: md5: add an address prefix for key lookup This allows the keys used for TCP MD5 signature to be used for whole range of addresses, specified with a prefix length, instead of only one address as it currently is. Signed-off-by: Bob Gilligan Signed-off-by: Eric Mowat Signed-off-by: Ivan Delalande Signed-off-by: David S. Miller --- include/net/tcp.h | 6 +++-- net/ipv4/tcp_ipv4.c | 68 ++++++++++++++++++++++++++++++++++++++++++++++------- net/ipv6/tcp_ipv6.c | 12 ++++++---- 3 files changed, 70 insertions(+), 16 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index e17ec286e8df..8f4076d31669 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1441,6 +1441,7 @@ struct tcp_md5sig_key { u8 keylen; u8 family; /* AF_INET or AF_INET6 */ union tcp_md5_addr addr; + u8 prefixlen; u8 key[TCP_MD5SIG_MAXKEYLEN]; struct rcu_head rcu; }; @@ -1484,9 +1485,10 @@ struct tcp_md5sig_pool { int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, const u8 *newkey, u8 newkeylen, gfp_t gfp); + int family, u8 prefixlen, const u8 *newkey, u8 newkeylen, + gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, - int family); + int family, u8 prefixlen); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index eec2ff907279..a3c67866b780 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -80,6 +80,7 @@ #include #include #include +#include #include #include @@ -908,6 +909,9 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, struct tcp_md5sig_key *key; unsigned int size = sizeof(struct in_addr); const struct tcp_md5sig_info *md5sig; + __be32 mask; + struct tcp_md5sig_key *best_match = NULL; + bool match; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, @@ -921,12 +925,55 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; - if (!memcmp(&key->addr, addr, size)) + + if (family == AF_INET) { + mask = inet_make_mask(key->prefixlen); + match = (key->addr.a4.s_addr & mask) == + (addr->a4.s_addr & mask); +#if IS_ENABLED(CONFIG_IPV6) + } else if (family == AF_INET6) { + match = ipv6_prefix_equal(&key->addr.a6, &addr->a6, + key->prefixlen); +#endif + } else { + match = false; + } + + if (match && (!best_match || + key->prefixlen > best_match->prefixlen)) + best_match = key; + } + return best_match; +} +EXPORT_SYMBOL(tcp_md5_do_lookup); + +struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, + const union tcp_md5_addr *addr, + int family, u8 prefixlen) +{ + const struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_key *key; + unsigned int size = sizeof(struct in_addr); + const struct tcp_md5sig_info *md5sig; + + /* caller either holds rcu_read_lock() or socket lock */ + md5sig = rcu_dereference_check(tp->md5sig_info, + lockdep_sock_is_held(sk)); + if (!md5sig) + return NULL; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) + size = sizeof(struct in6_addr); +#endif + hlist_for_each_entry_rcu(key, &md5sig->head, node) { + if (key->family != family) + continue; + if (!memcmp(&key->addr, addr, size) && + key->prefixlen == prefixlen) return key; } return NULL; } -EXPORT_SYMBOL(tcp_md5_do_lookup); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) @@ -940,14 +987,15 @@ EXPORT_SYMBOL(tcp_v4_md5_lookup); /* This can be called on a newly created socket, from other files */ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, const u8 *newkey, u8 newkeylen, gfp_t gfp) + int family, u8 prefixlen, const u8 *newkey, u8 newkeylen, + gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; - key = tcp_md5_do_lookup(sk, addr, family); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (key) { /* Pre-existing entry - just update that one. */ memcpy(key->key, newkey, newkeylen); @@ -978,6 +1026,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; key->family = family; + key->prefixlen = prefixlen; memcpy(&key->addr, addr, (family == AF_INET6) ? sizeof(struct in6_addr) : sizeof(struct in_addr)); @@ -986,11 +1035,12 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, } EXPORT_SYMBOL(tcp_md5_do_add); -int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) +int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, + u8 prefixlen) { struct tcp_md5sig_key *key; - key = tcp_md5_do_lookup(sk, addr, family); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (!key) return -ENOENT; hlist_del_rcu(&key->node); @@ -1033,13 +1083,13 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, if (!cmd.tcpm_keylen) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET); + AF_INET, 32); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, + AF_INET, 32, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } @@ -1342,7 +1392,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr, - AF_INET, key->key, key->keylen, GFP_ATOMIC); + AF_INET, 32, key->key, key->keylen, GFP_ATOMIC); sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6264917fe4c7..261689310408 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -533,9 +533,9 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, if (!cmd.tcpm_keylen) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET); + AF_INET, 32); return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6); + AF_INET6, 128); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) @@ -543,10 +543,12 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + AF_INET, 32, cmd.tcpm_key, + cmd.tcpm_keylen, GFP_KERNEL); return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + AF_INET6, 128, cmd.tcpm_key, cmd.tcpm_keylen, + GFP_KERNEL); } static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -1186,7 +1188,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, - AF_INET6, key->key, key->keylen, + AF_INET6, 128, key->key, key->keylen, sk_gfp_mask(sk, GFP_ATOMIC)); } #endif -- cgit v1.2.3 From 8917a777be3ba566377be05117f71b93a5fd909d Mon Sep 17 00:00:00 2001 From: Ivan Delalande Date: Thu, 15 Jun 2017 18:07:07 -0700 Subject: tcp: md5: add TCP_MD5SIG_EXT socket option to set a key address prefix Replace first padding in the tcp_md5sig structure with a new flag field and address prefix length so it can be specified when configuring a new key for TCP MD5 signature. The tcpm_flags field will only be used if the socket option is TCP_MD5SIG_EXT to avoid breaking existing programs, and tcpm_prefixlen only when the TCP_MD5SIG_FLAG_PREFIX flag is set. Signed-off-by: Bob Gilligan Signed-off-by: Eric Mowat Signed-off-by: Ivan Delalande Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + include/uapi/linux/tcp.h | 11 ++++++++--- net/ipv4/tcp.c | 3 ++- net/ipv4/tcp_ipv4.c | 16 ++++++++++++---- net/ipv6/tcp_ipv6.c | 25 ++++++++++++++++++------- 5 files changed, 41 insertions(+), 15 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 8f4076d31669..d0751b79d99c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1848,6 +1848,7 @@ struct tcp_sock_af_ops { const struct sock *sk, const struct sk_buff *skb); int (*md5_parse)(struct sock *sk, + int optname, char __user *optval, int optlen); #endif diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 8204dcebc6f3..a5507c977497 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -117,7 +117,8 @@ enum { #define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */ #define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */ #define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */ -#define TCP_ULP 31 /* Attach a ULP to a TCP connection */ +#define TCP_ULP 31 /* Attach a ULP to a TCP connection */ +#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */ struct tcp_repair_opt { __u32 opt_code; @@ -235,11 +236,15 @@ enum { /* for TCP_MD5SIG socket option */ #define TCP_MD5SIG_MAXKEYLEN 80 +/* tcp_md5sig extension flags for TCP_MD5SIG_EXT */ +#define TCP_MD5SIG_FLAG_PREFIX 1 /* address prefix length */ + struct tcp_md5sig { struct __kernel_sockaddr_storage tcpm_addr; /* address associated */ - __u16 __tcpm_pad1; /* zero */ + __u8 tcpm_flags; /* extension flags */ + __u8 tcpm_prefixlen; /* address prefix */ __u16 tcpm_keylen; /* key length */ - __u32 __tcpm_pad2; /* zero */ + __u32 __tcpm_pad; /* zero */ __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */ }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 11e4ee281aa0..058f509ca98e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2714,8 +2714,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: + case TCP_MD5SIG_EXT: /* Read the IP->Key mappings from userspace */ - err = tp->af_specific->md5_parse(sk, optval, optlen); + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_USER_TIMEOUT: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a3c67866b780..bf407f3e20dd 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1066,11 +1066,12 @@ static void tcp_clear_md5_list(struct sock *sk) } } -static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, - int optlen) +static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, + char __user *optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; + u8 prefixlen = 32; if (optlen < sizeof(cmd)) return -EINVAL; @@ -1081,15 +1082,22 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, if (sin->sin_family != AF_INET) return -EINVAL; + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { + prefixlen = cmd.tcpm_prefixlen; + if (prefixlen > 32) + return -EINVAL; + } + if (!cmd.tcpm_keylen) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET, 32); + AF_INET, prefixlen); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET, 32, cmd.tcpm_key, cmd.tcpm_keylen, + AF_INET, prefixlen, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 261689310408..68dc7472b44d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -515,11 +515,12 @@ static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); } -static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, - int optlen) +static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, + char __user *optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; + u8 prefixlen; if (optlen < sizeof(cmd)) return -EINVAL; @@ -530,12 +531,22 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, if (sin6->sin6_family != AF_INET6) return -EINVAL; + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { + prefixlen = cmd.tcpm_prefixlen; + if (prefixlen > 128 || (ipv6_addr_v4mapped(&sin6->sin6_addr) && + prefixlen > 32)) + return -EINVAL; + } else { + prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128; + } + if (!cmd.tcpm_keylen) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET, 32); + AF_INET, prefixlen); return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6, 128); + AF_INET6, prefixlen); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) @@ -543,12 +554,12 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, char __user *optval, if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET, 32, cmd.tcpm_key, + AF_INET, prefixlen, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6, 128, cmd.tcpm_key, cmd.tcpm_keylen, - GFP_KERNEL); + AF_INET6, prefixlen, cmd.tcpm_key, + cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp, -- cgit v1.2.3 From dc5321d79697db1b610c25fa4fad1aec7533ea3e Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Mon, 19 Jun 2017 10:03:56 +0200 Subject: vxlan: get rid of redundant vxlan_dev.flags There is no good reason to keep the flags twice in vxlan_dev and vxlan_config. Signed-off-by: Matthias Schiffer Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 76 +++++++++++++++++++++---------------------- include/net/vxlan.h | 1 - net/openvswitch/vport-vxlan.c | 4 +-- 3 files changed, 39 insertions(+), 42 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 9139f15a2ec1..b4fce3b29647 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -305,7 +305,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, if (rdst->remote_vni != vxlan->default_dst.remote_vni && nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) goto nla_put_failure; - if ((vxlan->flags & VXLAN_F_COLLECT_METADATA) && fdb->vni && + if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->vni && nla_put_u32(skb, NDA_SRC_VNI, be32_to_cpu(fdb->vni))) goto nla_put_failure; @@ -419,7 +419,7 @@ static u32 eth_vni_hash(const unsigned char *addr, __be32 vni) static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { - if (vxlan->flags & VXLAN_F_COLLECT_METADATA) + if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) return &vxlan->fdb_head[eth_vni_hash(mac, vni)]; else return &vxlan->fdb_head[eth_hash(mac)]; @@ -434,7 +434,7 @@ static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan, hlist_for_each_entry_rcu(f, head, hlist) { if (ether_addr_equal(mac, f->eth_addr)) { - if (vxlan->flags & VXLAN_F_COLLECT_METADATA) { + if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (vni == f->vni) return f; } else { @@ -1284,7 +1284,7 @@ static bool vxlan_set_mac(struct vxlan_dev *vxlan, #endif } - if ((vxlan->flags & VXLAN_F_LEARN) && + if ((vxlan->cfg.flags & VXLAN_F_LEARN) && vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source, vni)) return false; @@ -1507,7 +1507,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) if (netif_rx_ni(reply) == NET_RX_DROP) dev->stats.rx_dropped++; - } else if (vxlan->flags & VXLAN_F_L3MISS) { + } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, .sin.sin_family = AF_INET, @@ -1665,7 +1665,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) if (netif_rx_ni(reply) == NET_RX_DROP) dev->stats.rx_dropped++; - } else if (vxlan->flags & VXLAN_F_L3MISS) { + } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin6.sin6_addr = msg->target, .sin6.sin6_family = AF_INET6, @@ -1698,7 +1698,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) return false; pip = ip_hdr(skb); n = neigh_lookup(&arp_tbl, &pip->daddr, dev); - if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { + if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = pip->daddr, .sin.sin_family = AF_INET, @@ -1719,7 +1719,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) return false; pip6 = ipv6_hdr(skb); n = neigh_lookup(ipv6_stub->nd_tbl, &pip6->daddr, dev); - if (!n && (vxlan->flags & VXLAN_F_L3MISS)) { + if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin6.sin6_addr = pip6->daddr, .sin6.sin6_family = AF_INET6, @@ -1993,7 +1993,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, #endif } - if (dst_vxlan->flags & VXLAN_F_LEARN) + if (dst_vxlan->cfg.flags & VXLAN_F_LEARN) vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, vni); u64_stats_update_begin(&tx_stats->syncp); @@ -2031,7 +2031,7 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, dst_release(dst); dst_vxlan = vxlan_find_vni(vxlan->net, vni, daddr->sa.sa_family, dst_port, - vxlan->flags); + vxlan->cfg.flags); if (!dst_vxlan) { dev->stats.tx_errors++; kfree_skb(skb); @@ -2062,7 +2062,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, __be32 vni, label; __u8 tos, ttl; int err; - u32 flags = vxlan->flags; + u32 flags = vxlan->cfg.flags; bool udp_sum = false; bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev)); @@ -2244,7 +2244,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb); - if (vxlan->flags & VXLAN_F_COLLECT_METADATA) { + if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (info && info->mode & IP_TUNNEL_INFO_BRIDGE && info->mode & IP_TUNNEL_INFO_TX) { vni = tunnel_id_to_key32(info->key.tun_id); @@ -2257,7 +2257,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) } } - if (vxlan->flags & VXLAN_F_PROXY) { + if (vxlan->cfg.flags & VXLAN_F_PROXY) { eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_ARP) return arp_reduce(dev, skb, vni); @@ -2277,7 +2277,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) f = vxlan_find_mac(vxlan, eth->h_dest, vni); did_rsc = false; - if (f && (f->flags & NTF_ROUTER) && (vxlan->flags & VXLAN_F_RSC) && + if (f && (f->flags & NTF_ROUTER) && (vxlan->cfg.flags & VXLAN_F_RSC) && (ntohs(eth->h_proto) == ETH_P_IP || ntohs(eth->h_proto) == ETH_P_IPV6)) { did_rsc = route_shortcircuit(dev, skb); @@ -2288,7 +2288,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) if (f == NULL) { f = vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f == NULL) { - if ((vxlan->flags & VXLAN_F_L2MISS) && + if ((vxlan->cfg.flags & VXLAN_F_L2MISS) && !is_multicast_ether_addr(eth->h_dest)) vxlan_fdb_miss(vxlan, eth->h_dest); @@ -2832,7 +2832,7 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) if (!vxlan->cfg.no_share) { spin_lock(&vn->sock_lock); vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, - vxlan->cfg.dst_port, vxlan->flags); + vxlan->cfg.dst_port, vxlan->cfg.flags); if (vs && !atomic_add_unless(&vs->refcnt, 1, 0)) { spin_unlock(&vn->sock_lock); return -EBUSY; @@ -2841,7 +2841,7 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) } if (!vs) vs = vxlan_socket_create(vxlan->net, ipv6, - vxlan->cfg.dst_port, vxlan->flags); + vxlan->cfg.dst_port, vxlan->cfg.flags); if (IS_ERR(vs)) return PTR_ERR(vs); #if IS_ENABLED(CONFIG_IPV6) @@ -2856,8 +2856,8 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) static int vxlan_sock_add(struct vxlan_dev *vxlan) { - bool metadata = vxlan->flags & VXLAN_F_COLLECT_METADATA; - bool ipv6 = vxlan->flags & VXLAN_F_IPV6 || metadata; + bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; + bool ipv6 = vxlan->cfg.flags & VXLAN_F_IPV6 || metadata; bool ipv4 = !ipv6 || metadata; int ret = 0; @@ -2952,7 +2952,7 @@ static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf, (tmp->default_dst.remote_ip.sa.sa_family == AF_INET6 || tmp->cfg.saddr.sa.sa_family == AF_INET6) == use_ipv6 && tmp->cfg.dst_port == conf->dst_port && - (tmp->flags & VXLAN_F_RCV_FLAGS) == + (tmp->cfg.flags & VXLAN_F_RCV_FLAGS) == (conf->flags & VXLAN_F_RCV_FLAGS)) return -EEXIST; } @@ -3006,7 +3006,6 @@ static void vxlan_config_apply(struct net_device *dev, dev->needed_headroom = needed_headroom; memcpy(&vxlan->cfg, conf, sizeof(*conf)); - vxlan->flags |= conf->flags; } static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, @@ -3120,12 +3119,10 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], IPV6_FLOWLABEL_MASK; if (data[IFLA_VXLAN_LEARNING]) { - if (nla_get_u8(data[IFLA_VXLAN_LEARNING])) { + if (nla_get_u8(data[IFLA_VXLAN_LEARNING])) conf->flags |= VXLAN_F_LEARN; - } else { + else conf->flags &= ~VXLAN_F_LEARN; - vxlan->flags &= ~VXLAN_F_LEARN; - } } else if (!changelink) { /* default to learn on a new device */ conf->flags |= VXLAN_F_LEARN; @@ -3408,43 +3405,44 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, - !!(vxlan->flags & VXLAN_F_LEARN)) || + !!(vxlan->cfg.flags & VXLAN_F_LEARN)) || nla_put_u8(skb, IFLA_VXLAN_PROXY, - !!(vxlan->flags & VXLAN_F_PROXY)) || - nla_put_u8(skb, IFLA_VXLAN_RSC, !!(vxlan->flags & VXLAN_F_RSC)) || + !!(vxlan->cfg.flags & VXLAN_F_PROXY)) || + nla_put_u8(skb, IFLA_VXLAN_RSC, + !!(vxlan->cfg.flags & VXLAN_F_RSC)) || nla_put_u8(skb, IFLA_VXLAN_L2MISS, - !!(vxlan->flags & VXLAN_F_L2MISS)) || + !!(vxlan->cfg.flags & VXLAN_F_L2MISS)) || nla_put_u8(skb, IFLA_VXLAN_L3MISS, - !!(vxlan->flags & VXLAN_F_L3MISS)) || + !!(vxlan->cfg.flags & VXLAN_F_L3MISS)) || nla_put_u8(skb, IFLA_VXLAN_COLLECT_METADATA, - !!(vxlan->flags & VXLAN_F_COLLECT_METADATA)) || + !!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) || nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->cfg.age_interval) || nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) || nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) || nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM, - !(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM_TX)) || + !(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, - !!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) || + !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, - !!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) || + !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_TX, - !!(vxlan->flags & VXLAN_F_REMCSUM_TX)) || + !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_RX, - !!(vxlan->flags & VXLAN_F_REMCSUM_RX))) + !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_RX))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports)) goto nla_put_failure; - if (vxlan->flags & VXLAN_F_GBP && + if (vxlan->cfg.flags & VXLAN_F_GBP && nla_put_flag(skb, IFLA_VXLAN_GBP)) goto nla_put_failure; - if (vxlan->flags & VXLAN_F_GPE && + if (vxlan->cfg.flags & VXLAN_F_GPE && nla_put_flag(skb, IFLA_VXLAN_GPE)) goto nla_put_failure; - if (vxlan->flags & VXLAN_F_REMCSUM_NOPARTIAL && + if (vxlan->cfg.flags & VXLAN_F_REMCSUM_NOPARTIAL && nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL)) goto nla_put_failure; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 49a59202f85e..479bb75789ea 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -232,7 +232,6 @@ struct vxlan_dev { struct net_device *dev; struct net *net; /* netns for packet i/o */ struct vxlan_rdst default_dst; /* default destination */ - u32 flags; /* VXLAN_F_* in vxlan.h */ struct timer_list age_timer; spinlock_t hash_lock; diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 869acb3b3d3f..7e6301b2ec4d 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -40,14 +40,14 @@ static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port))) return -EMSGSIZE; - if (vxlan->flags & VXLAN_F_GBP) { + if (vxlan->cfg.flags & VXLAN_F_GBP) { struct nlattr *exts; exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION); if (!exts) return -EMSGSIZE; - if (vxlan->flags & VXLAN_F_GBP && + if (vxlan->cfg.flags & VXLAN_F_GBP && nla_put_flag(skb, OVS_VXLAN_EXT_GBP)) return -EMSGSIZE; -- cgit v1.2.3 From 0f22a3c68d5fd1696dbc15c45d7ea375c865b7a1 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Mon, 19 Jun 2017 10:03:58 +0200 Subject: vxlan: check valid combinations of address scopes * Multicast addresses are never valid as local address * Link-local IPv6 unicast addresses may only be used as remote when the local address is link-local as well * Don't allow link-local IPv6 local/remote addresses without interface We also store in the flags field if link-local addresses are used for the follow-up patches that actually make VXLAN over link-local IPv6 work. Signed-off-by: Matthias Schiffer Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 29 +++++++++++++++++++++++++++++ include/net/vxlan.h | 2 ++ 2 files changed, 31 insertions(+) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 00680cc597ac..d6d57317cbd5 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2907,11 +2907,35 @@ static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf, if (conf->saddr.sa.sa_family != conf->remote_ip.sa.sa_family) return -EINVAL; + if (vxlan_addr_multicast(&conf->saddr)) + return -EINVAL; + if (conf->saddr.sa.sa_family == AF_INET6) { if (!IS_ENABLED(CONFIG_IPV6)) return -EPFNOSUPPORT; use_ipv6 = true; conf->flags |= VXLAN_F_IPV6; + + if (!(conf->flags & VXLAN_F_COLLECT_METADATA)) { + int local_type = + ipv6_addr_type(&conf->saddr.sin6.sin6_addr); + int remote_type = + ipv6_addr_type(&conf->remote_ip.sin6.sin6_addr); + + if (local_type & IPV6_ADDR_LINKLOCAL) { + if (!(remote_type & IPV6_ADDR_LINKLOCAL) && + (remote_type != IPV6_ADDR_ANY)) + return -EINVAL; + + conf->flags |= VXLAN_F_IPV6_LINKLOCAL; + } else { + if (remote_type == + (IPV6_ADDR_UNICAST | IPV6_ADDR_LINKLOCAL)) + return -EINVAL; + + conf->flags &= ~VXLAN_F_IPV6_LINKLOCAL; + } + } } if (conf->label && !use_ipv6) @@ -2937,6 +2961,11 @@ static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf, if (vxlan_addr_multicast(&conf->remote_ip)) return -EINVAL; +#if IS_ENABLED(CONFIG_IPV6) + if (conf->flags & VXLAN_F_IPV6_LINKLOCAL) + return -EINVAL; +#endif + *lower = NULL; } diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 479bb75789ea..b816a0a6686e 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -258,6 +258,7 @@ struct vxlan_dev { #define VXLAN_F_REMCSUM_NOPARTIAL 0x1000 #define VXLAN_F_COLLECT_METADATA 0x2000 #define VXLAN_F_GPE 0x4000 +#define VXLAN_F_IPV6_LINKLOCAL 0x8000 /* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable @@ -272,6 +273,7 @@ struct vxlan_dev { /* Flags that can be set together with VXLAN_F_GPE. */ #define VXLAN_F_ALLOWED_GPE (VXLAN_F_GPE | \ VXLAN_F_IPV6 | \ + VXLAN_F_IPV6_LINKLOCAL | \ VXLAN_F_UDP_ZERO_CSUM_TX | \ VXLAN_F_UDP_ZERO_CSUM6_TX | \ VXLAN_F_UDP_ZERO_CSUM6_RX | \ -- cgit v1.2.3 From 5ee8aa689780f2c19702fe3768a3103b9c07d72e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 20 Jun 2017 16:05:11 +0800 Subject: sctp: handle errors when updating asoc It's a bad thing not to handle errors when updating asoc. The memory allocation failure in any of the functions called in sctp_assoc_update() would cause sctp to work unexpectedly. This patch is to fix it by aborting the asoc and reporting the error when any of these functions fails. Signed-off-by: Xin Long Acked-by: Neil Horman Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 4 ++-- net/sctp/associola.c | 25 ++++++++++++++----------- net/sctp/sm_sideeffect.c | 24 +++++++++++++++++++++++- 3 files changed, 39 insertions(+), 14 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 5051317162df..e26763bfabd6 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1953,8 +1953,8 @@ struct sctp_transport *sctp_assoc_is_match(struct sctp_association *, const union sctp_addr *, const union sctp_addr *); void sctp_assoc_migrate(struct sctp_association *, struct sock *); -void sctp_assoc_update(struct sctp_association *old, - struct sctp_association *new); +int sctp_assoc_update(struct sctp_association *old, + struct sctp_association *new); __u32 sctp_association_get_next_tsn(struct sctp_association *); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 72b07dd9b959..757be416f778 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1112,8 +1112,8 @@ void sctp_assoc_migrate(struct sctp_association *assoc, struct sock *newsk) } /* Update an association (possibly from unexpected COOKIE-ECHO processing). */ -void sctp_assoc_update(struct sctp_association *asoc, - struct sctp_association *new) +int sctp_assoc_update(struct sctp_association *asoc, + struct sctp_association *new) { struct sctp_transport *trans; struct list_head *pos, *temp; @@ -1124,8 +1124,10 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->peer.sack_needed = new->peer.sack_needed; asoc->peer.auth_capable = new->peer.auth_capable; asoc->peer.i = new->peer.i; - sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, - asoc->peer.i.initial_tsn, GFP_ATOMIC); + + if (!sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, + asoc->peer.i.initial_tsn, GFP_ATOMIC)) + return -ENOMEM; /* Remove any peer addresses not present in the new association. */ list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { @@ -1169,11 +1171,11 @@ void sctp_assoc_update(struct sctp_association *asoc, } else { /* Add any peer addresses from the new association. */ list_for_each_entry(trans, &new->peer.transport_addr_list, - transports) { - if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr)) - sctp_assoc_add_peer(asoc, &trans->ipaddr, - GFP_ATOMIC, trans->state); - } + transports) + if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr) && + !sctp_assoc_add_peer(asoc, &trans->ipaddr, + GFP_ATOMIC, trans->state)) + return -ENOMEM; asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point; @@ -1182,7 +1184,8 @@ void sctp_assoc_update(struct sctp_association *asoc, sctp_stream_update(&asoc->stream, &new->stream); /* get a new assoc id if we don't have one yet. */ - sctp_assoc_set_id(asoc, GFP_ATOMIC); + if (sctp_assoc_set_id(asoc, GFP_ATOMIC)) + return -ENOMEM; } /* SCTP-AUTH: Save the peer parameters from the new associations @@ -1200,7 +1203,7 @@ void sctp_assoc_update(struct sctp_association *asoc, asoc->peer.peer_hmacs = new->peer.peer_hmacs; new->peer.peer_hmacs = NULL; - sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); + return sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); } /* Update the retran path for sending a retransmitted packet. diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 76235663fe06..dfe1fcb520ba 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -818,6 +818,28 @@ static void sctp_cmd_setup_t2(sctp_cmd_seq_t *cmds, asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = t->rto; } +static void sctp_cmd_assoc_update(sctp_cmd_seq_t *cmds, + struct sctp_association *asoc, + struct sctp_association *new) +{ + struct net *net = sock_net(asoc->base.sk); + struct sctp_chunk *abort; + + if (!sctp_assoc_update(asoc, new)) + return; + + abort = sctp_make_abort(asoc, NULL, sizeof(sctp_errhdr_t)); + if (abort) { + sctp_init_cause(abort, SCTP_ERROR_RSRC_LOW, 0); + sctp_add_cmd_sf(cmds, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + } + sctp_add_cmd_sf(cmds, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); + sctp_add_cmd_sf(cmds, SCTP_CMD_ASSOC_FAILED, + SCTP_PERR(SCTP_ERROR_RSRC_LOW)); + SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); + SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); +} + /* Helper function to change the state of an association. */ static void sctp_cmd_new_state(sctp_cmd_seq_t *cmds, struct sctp_association *asoc, @@ -1294,7 +1316,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, break; case SCTP_CMD_UPDATE_ASSOC: - sctp_assoc_update(asoc, cmd->obj.asoc); + sctp_cmd_assoc_update(commands, asoc, cmd->obj.asoc); break; case SCTP_CMD_PURGE_OUTQUEUE: -- cgit v1.2.3 From 104b4e5139fe384431ac11c3b8a6cf4a529edf4a Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Tue, 20 Jun 2017 21:01:20 +0300 Subject: percpu_counter: Rename __percpu_counter_add to percpu_counter_add_batch Currently, percpu_counter_add is a wrapper around __percpu_counter_add which is preempt safe due to explicit calls to preempt_disable. Given how __ prefix is used in percpu related interfaces, the naming unfortunately creates the false sense that __percpu_counter_add is less safe than percpu_counter_add. In terms of context-safety, they're equivalent. The only difference is that the __ version takes a batch parameter. Make this a bit more explicit by just renaming __percpu_counter_add to percpu_counter_add_batch. This patch doesn't cause any functional changes. tj: Minor updates to patch description for clarity. Cosmetic indentation updates. Signed-off-by: Nikolay Borisov Signed-off-by: Tejun Heo Cc: Chris Mason Cc: Josef Bacik Cc: David Sterba Cc: Darrick J. Wong Cc: Jan Kara Cc: Jens Axboe Cc: linux-mm@kvack.org Cc: "David S. Miller" --- fs/btrfs/disk-io.c | 12 ++++++------ fs/btrfs/extent_io.c | 6 +++--- fs/btrfs/inode.c | 8 ++++---- fs/xfs/xfs_mount.c | 4 ++-- include/linux/backing-dev.h | 2 +- include/linux/blk-cgroup.h | 6 +++--- include/linux/mman.h | 2 +- include/linux/percpu_counter.h | 7 ++++--- include/net/inet_frag.h | 4 ++-- lib/flex_proportions.c | 6 +++--- lib/percpu_counter.c | 4 ++-- 11 files changed, 31 insertions(+), 30 deletions(-) (limited to 'include/net') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 061c1d1f774f..eb5c95569300 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1255,9 +1255,9 @@ void clean_tree_block(struct btrfs_fs_info *fs_info, btrfs_assert_tree_locked(buf); if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) { - __percpu_counter_add(&fs_info->dirty_metadata_bytes, - -buf->len, - fs_info->dirty_metadata_batch); + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, + -buf->len, + fs_info->dirty_metadata_batch); /* ugh, clear_extent_buffer_dirty needs to lock the page */ btrfs_set_lock_blocking(buf); clear_extent_buffer_dirty(buf); @@ -4046,9 +4046,9 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) buf->start, transid, fs_info->generation); was_dirty = set_extent_buffer_dirty(buf); if (!was_dirty) - __percpu_counter_add(&fs_info->dirty_metadata_bytes, - buf->len, - fs_info->dirty_metadata_batch); + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, + buf->len, + fs_info->dirty_metadata_batch); #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) { btrfs_print_leaf(fs_info, buf); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 27fdb250b446..a3455d216a1d 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3584,9 +3584,9 @@ lock_extent_buffer_for_io(struct extent_buffer *eb, set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); spin_unlock(&eb->refs_lock); btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); - __percpu_counter_add(&fs_info->dirty_metadata_bytes, - -eb->len, - fs_info->dirty_metadata_batch); + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, + -eb->len, + fs_info->dirty_metadata_batch); ret = 1; } else { spin_unlock(&eb->refs_lock); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5e71f1ea3391..aabdcb9f234f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1682,8 +1682,8 @@ static void btrfs_set_bit_hook(struct inode *inode, if (btrfs_is_testing(fs_info)) return; - __percpu_counter_add(&fs_info->delalloc_bytes, len, - fs_info->delalloc_batch); + percpu_counter_add_batch(&fs_info->delalloc_bytes, len, + fs_info->delalloc_batch); spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->delalloc_bytes += len; if (*bits & EXTENT_DEFRAG) @@ -1749,8 +1749,8 @@ static void btrfs_clear_bit_hook(struct btrfs_inode *inode, &inode->vfs_inode, state->start, len); - __percpu_counter_add(&fs_info->delalloc_bytes, -len, - fs_info->delalloc_batch); + percpu_counter_add_batch(&fs_info->delalloc_bytes, -len, + fs_info->delalloc_batch); spin_lock(&inode->lock); inode->delalloc_bytes -= len; if (do_list && inode->delalloc_bytes == 0 && diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 2eaf81859166..7147d4a8d207 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1209,7 +1209,7 @@ xfs_mod_icount( struct xfs_mount *mp, int64_t delta) { - __percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH); + percpu_counter_add_batch(&mp->m_icount, delta, XFS_ICOUNT_BATCH); if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) { ASSERT(0); percpu_counter_add(&mp->m_icount, -delta); @@ -1288,7 +1288,7 @@ xfs_mod_fdblocks( else batch = XFS_FDBLOCKS_BATCH; - __percpu_counter_add(&mp->m_fdblocks, delta, batch); + percpu_counter_add_batch(&mp->m_fdblocks, delta, batch); if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_alloc_set_aside, XFS_FDBLOCKS_BATCH) >= 0) { /* we had space! */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 557d84063934..ace73f96eb1e 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -66,7 +66,7 @@ static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) static inline void __add_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { - __percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH); + percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } static inline void __inc_wb_stat(struct bdi_writeback *wb, diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 01b62e7bac74..7104bea8dab1 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -518,7 +518,7 @@ static inline void blkg_stat_exit(struct blkg_stat *stat) */ static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val) { - __percpu_counter_add(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH); + percpu_counter_add_batch(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH); } /** @@ -597,14 +597,14 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; - __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); if (op_is_sync(op)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; - __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); + percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); } /** diff --git a/include/linux/mman.h b/include/linux/mman.h index 634c4c51fe3a..c8367041fafd 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -22,7 +22,7 @@ unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { - __percpu_counter_add(&vm_committed_as, pages, vm_committed_as_batch); + percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 84a109449610..ec065387f443 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -39,7 +39,8 @@ int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); -void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); +void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, + s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); @@ -50,7 +51,7 @@ static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { - __percpu_counter_add(fbc, amount, percpu_counter_batch); + percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) @@ -136,7 +137,7 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount) } static inline void -__percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch) +percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { percpu_counter_add(fbc, amount); } diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 5894730ec82a..5932e6de8fc0 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -154,12 +154,12 @@ static inline int frag_mem_limit(struct netns_frags *nf) static inline void sub_frag_mem_limit(struct netns_frags *nf, int i) { - __percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch); + percpu_counter_add_batch(&nf->mem, -i, frag_percpu_counter_batch); } static inline void add_frag_mem_limit(struct netns_frags *nf, int i) { - __percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch); + percpu_counter_add_batch(&nf->mem, i, frag_percpu_counter_batch); } static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf) diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c index a71cf1bdd4c9..2cc1f94e03a1 100644 --- a/lib/flex_proportions.c +++ b/lib/flex_proportions.c @@ -207,7 +207,7 @@ static void fprop_reflect_period_percpu(struct fprop_global *p, if (val < (nr_cpu_ids * PROP_BATCH)) val = percpu_counter_sum(&pl->events); - __percpu_counter_add(&pl->events, + percpu_counter_add_batch(&pl->events, -val + (val >> (period-pl->period)), PROP_BATCH); } else percpu_counter_set(&pl->events, 0); @@ -219,7 +219,7 @@ static void fprop_reflect_period_percpu(struct fprop_global *p, void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl) { fprop_reflect_period_percpu(p, pl); - __percpu_counter_add(&pl->events, 1, PROP_BATCH); + percpu_counter_add_batch(&pl->events, 1, PROP_BATCH); percpu_counter_add(&p->events, 1); } @@ -267,6 +267,6 @@ void __fprop_inc_percpu_max(struct fprop_global *p, return; } else fprop_reflect_period_percpu(p, pl); - __percpu_counter_add(&pl->events, 1, PROP_BATCH); + percpu_counter_add_batch(&pl->events, 1, PROP_BATCH); percpu_counter_add(&p->events, 1); } diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 9c21000df0b5..8ee7e5ec21be 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -72,7 +72,7 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) } EXPORT_SYMBOL(percpu_counter_set); -void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch) +void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; @@ -89,7 +89,7 @@ void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch) } preempt_enable(); } -EXPORT_SYMBOL(__percpu_counter_add); +EXPORT_SYMBOL(percpu_counter_add_batch); /* * Add up all the per-cpu counts, return the result. This is a more accurate -- cgit v1.2.3 From 34cfb542b5b1762c73479a4a61e0a3b77253f876 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 21 Jun 2017 11:45:31 +0200 Subject: sock: avoid dirtying incoming_cpu if not needed for connected socket, the incoming_cpu field in the sock struct is not going to change frequently, but we are setting it unconditionally for each packet. Since sk_incoming_cpu and sk_flags share the same cacheline, and the latter is access by udp_recvmsg(), this cause a cache miss for each packet for UDP connected socket. With this patch, we set the incoming cpu field only when the ingress cpu really changes. This gives a small but measurable performance improvement for connected UDP socket. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/sock.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 858891c36f94..00d09140e354 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -907,7 +907,10 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) static inline void sk_incoming_cpu_update(struct sock *sk) { - sk->sk_incoming_cpu = raw_smp_processor_id(); + int cpu = raw_smp_processor_id(); + + if (unlikely(sk->sk_incoming_cpu != cpu)) + sk->sk_incoming_cpu = cpu; } static inline void sock_rps_record_flow_hash(__u32 hash) -- cgit v1.2.3 From 3fcece12bc1b6dcdf0986f2cd9e8f63b1f9b6aa0 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 23 Jun 2017 22:11:58 +0200 Subject: net: store port/representator id in metadata_dst Switches and modern SR-IOV enabled NICs may multiplex traffic from Port representators and control messages over single set of hardware queues. Control messages and muxed traffic may need ordered delivery. Those requirements make it hard to comfortably use TC infrastructure today unless we have a way of attaching metadata to skbs at the upper device. Because single set of queues is used for many netdevs stopping TC/sched queues of all of them reliably is impossible and lower device has to retreat to returning NETDEV_TX_BUSY and usually has to take extra locks on the fastpath. This patch attempts to enable port/representative devs to attach metadata to skbs which carry port id. This way representatives can be queueless and all queuing can be performed at the lower netdev in the usual way. Traffic arriving on the port/representative interfaces will be have metadata attached and will subsequently be queued to the lower device for transmission. The lower device should recognize the metadata and translate it to HW specific format which is most likely either a special header inserted before the network headers or descriptor/metadata fields. Metadata is associated with the lower device by storing the netdev pointer along with port id so that if TC decides to redirect or mirror the new netdev will not try to interpret it. This is mostly for SR-IOV devices since switches don't have lower netdevs today. Signed-off-by: Jakub Kicinski Signed-off-by: Sridhar Samudrala Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- include/net/dst_metadata.h | 41 ++++++++++++++++++++++++++++++++--------- net/core/dst.c | 15 ++++++++++----- net/core/filter.c | 1 + net/ipv4/ip_tunnel_core.c | 6 ++++-- net/openvswitch/flow_netlink.c | 4 +++- 5 files changed, 50 insertions(+), 17 deletions(-) (limited to 'include/net') diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 701fc814d0af..a803129a4849 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -5,10 +5,22 @@ #include #include +enum metadata_type { + METADATA_IP_TUNNEL, + METADATA_HW_PORT_MUX, +}; + +struct hw_port_info { + struct net_device *lower_dev; + u32 port_id; +}; + struct metadata_dst { struct dst_entry dst; + enum metadata_type type; union { struct ip_tunnel_info tun_info; + struct hw_port_info port_info; } u; }; @@ -27,7 +39,7 @@ static inline struct ip_tunnel_info *skb_tunnel_info(struct sk_buff *skb) struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dst_entry *dst; - if (md_dst) + if (md_dst && md_dst->type == METADATA_IP_TUNNEL) return &md_dst->u.tun_info; dst = skb_dst(skb); @@ -55,22 +67,33 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, a = (const struct metadata_dst *) skb_dst(skb_a); b = (const struct metadata_dst *) skb_dst(skb_b); - if (!a != !b || a->u.tun_info.options_len != b->u.tun_info.options_len) + if (!a != !b || a->type != b->type) return 1; - return memcmp(&a->u.tun_info, &b->u.tun_info, - sizeof(a->u.tun_info) + a->u.tun_info.options_len); + switch (a->type) { + case METADATA_HW_PORT_MUX: + return memcmp(&a->u.port_info, &b->u.port_info, + sizeof(a->u.port_info)); + case METADATA_IP_TUNNEL: + return memcmp(&a->u.tun_info, &b->u.tun_info, + sizeof(a->u.tun_info) + + a->u.tun_info.options_len); + default: + return 1; + } } void metadata_dst_free(struct metadata_dst *); -struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags); -struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags); +struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, + gfp_t flags); +struct metadata_dst __percpu * +metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags); static inline struct metadata_dst *tun_rx_dst(int md_size) { struct metadata_dst *tun_dst; - tun_dst = metadata_dst_alloc(md_size, GFP_ATOMIC); + tun_dst = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!tun_dst) return NULL; @@ -85,11 +108,11 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) int md_size; struct metadata_dst *new_md; - if (!md_dst) + if (!md_dst || md_dst->type != METADATA_IP_TUNNEL) return ERR_PTR(-EINVAL); md_size = md_dst->u.tun_info.options_len; - new_md = metadata_dst_alloc(md_size, GFP_ATOMIC); + new_md = metadata_dst_alloc(md_size, METADATA_IP_TUNNEL, GFP_ATOMIC); if (!new_md) return ERR_PTR(-ENOMEM); diff --git a/net/core/dst.c b/net/core/dst.c index f851adb9ec9b..00aa972ad1a1 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -264,7 +264,9 @@ static int dst_md_discard(struct sk_buff *skb) return 0; } -static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen) +static void __metadata_dst_init(struct metadata_dst *md_dst, + enum metadata_type type, u8 optslen) + { struct dst_entry *dst; @@ -276,9 +278,11 @@ static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen) dst->output = dst_md_discard_out; memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); + md_dst->type = type; } -struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags) +struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, + gfp_t flags) { struct metadata_dst *md_dst; @@ -286,7 +290,7 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags) if (!md_dst) return NULL; - __metadata_dst_init(md_dst, optslen); + __metadata_dst_init(md_dst, type, optslen); return md_dst; } @@ -300,7 +304,8 @@ void metadata_dst_free(struct metadata_dst *md_dst) kfree(md_dst); } -struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags) +struct metadata_dst __percpu * +metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) { int cpu; struct metadata_dst __percpu *md_dst; @@ -311,7 +316,7 @@ struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags) return NULL; for_each_possible_cpu(cpu) - __metadata_dst_init(per_cpu_ptr(md_dst, cpu), optslen); + __metadata_dst_init(per_cpu_ptr(md_dst, cpu), type, optslen); return md_dst; } diff --git a/net/core/filter.c b/net/core/filter.c index 4b788007415f..b39c869d22e3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2565,6 +2565,7 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) * that is holding verifier mutex. */ md_dst = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, + METADATA_IP_TUNNEL, GFP_KERNEL); if (!md_dst) return NULL; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 90e11479c725..2f39479be92f 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -134,10 +134,12 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, struct metadata_dst *res; struct ip_tunnel_info *dst, *src; - if (!md || md->u.tun_info.mode & IP_TUNNEL_INFO_TX) + if (!md || md->type != METADATA_IP_TUNNEL || + md->u.tun_info.mode & IP_TUNNEL_INFO_TX) + return NULL; - res = metadata_dst_alloc(0, flags); + res = metadata_dst_alloc(0, METADATA_IP_TUNNEL, flags); if (!res) return NULL; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7e1d8a2afa63..f07d10ac35d8 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2202,7 +2202,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, if (start < 0) return start; - tun_dst = metadata_dst_alloc(key.tun_opts_len, GFP_KERNEL); + tun_dst = metadata_dst_alloc(key.tun_opts_len, METADATA_IP_TUNNEL, + GFP_KERNEL); + if (!tun_dst) return -ENOMEM; -- cgit v1.2.3 From 7a3f4a185169b195c33f1c54f33a44eba2d6aa96 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 25 Jun 2017 23:55:59 +0200 Subject: net: add netlink_ext_ack argument to rtnl_link_ops.newlink Add support for extended error reporting. Signed-off-by: Matthias Schiffer Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 3 ++- drivers/net/bonding/bond_netlink.c | 3 ++- drivers/net/caif/caif_hsi.c | 3 ++- drivers/net/can/dev.c | 3 ++- drivers/net/can/vxcan.c | 3 ++- drivers/net/geneve.c | 3 ++- drivers/net/gtp.c | 3 ++- drivers/net/ipvlan/ipvlan.h | 3 ++- drivers/net/ipvlan/ipvlan_main.c | 3 ++- drivers/net/ipvlan/ipvtap.c | 9 ++++----- drivers/net/macsec.c | 3 ++- drivers/net/macvlan.c | 3 ++- drivers/net/macvtap.c | 7 +++---- drivers/net/ppp/ppp_generic.c | 3 ++- drivers/net/team/team.c | 3 ++- drivers/net/veth.c | 3 ++- drivers/net/vrf.c | 3 ++- drivers/net/vxlan.c | 3 ++- include/net/rtnetlink.h | 3 ++- net/8021q/vlan_netlink.c | 3 ++- net/bridge/br_netlink.c | 3 ++- net/caif/chnl_net.c | 3 ++- net/core/rtnetlink.c | 3 ++- net/hsr/hsr_netlink.c | 3 ++- net/ieee802154/6lowpan/core.c | 3 ++- net/ipv4/ip_gre.c | 5 +++-- net/ipv4/ip_vti.c | 3 ++- net/ipv4/ipip.c | 3 ++- net/ipv6/ip6_gre.c | 3 ++- net/ipv6/ip6_tunnel.c | 3 ++- net/ipv6/ip6_vti.c | 3 ++- net/ipv6/sit.c | 3 ++- 32 files changed, 68 insertions(+), 40 deletions(-) (limited to 'include/net') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c index 28884781311b..8b75f80da56c 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c @@ -93,7 +93,8 @@ out_err: } static int ipoib_new_child_link(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_device *pdev; struct ipoib_dev_priv *ppriv; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 47a8103610bc..f817fb8005ef 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -438,7 +438,8 @@ static int bond_changelink(struct net_device *bond_dev, } static int bond_newlink(struct net *src_net, struct net_device *bond_dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { int err; diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c index 11ba6e3eea22..ed4723a9031f 100644 --- a/drivers/net/caif/caif_hsi.c +++ b/drivers/net/caif/caif_hsi.c @@ -1399,7 +1399,8 @@ static int caif_hsi_fill_info(struct sk_buff *skb, const struct net_device *dev) } static int caif_hsi_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct cfhsi *cfhsi = NULL; struct cfhsi_ops *(*get_ops)(void); diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index a3011c001080..7f99e8a5dd09 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -1146,7 +1146,8 @@ nla_put_failure: } static int can_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index cfe889e8f172..8404e8852a0f 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -163,7 +163,8 @@ static void vxcan_setup(struct net_device *dev) static struct rtnl_link_ops vxcan_link_ops; static int vxcan_newlink(struct net *net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct vxcan_priv *priv; struct net_device *peer; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index d586ad93aaff..0a72d914e1f9 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1181,7 +1181,8 @@ static void init_tnl_info(struct ip_tunnel_info *info, __u16 dst_port) } static int geneve_newlink(struct net *net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { bool use_udp6_rx_checksums = false; struct ip_tunnel_info info; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 8e333a8a2295..9cfe8a24c1fc 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -636,7 +636,8 @@ static void gtp_hashtable_free(struct gtp_dev *gtp); static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]); static int gtp_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct gtp_dev *gtp; struct gtp_net *gn; diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 7919369c0a72..ba8173a0b62e 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -140,7 +140,8 @@ unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast); int ipvlan_link_new(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]); + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack); void ipvlan_link_delete(struct net_device *dev, struct list_head *head); void ipvlan_link_setup(struct net_device *dev); int ipvlan_link_register(struct rtnl_link_ops *ops); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index dc888dd344eb..7bda5f630ac9 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -508,7 +508,8 @@ err: } int ipvlan_link_new(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port; diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index 2b713b63b62c..22f133ea8d7b 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -73,10 +73,9 @@ static void ipvtap_update_features(struct tap_dev *tap, netdev_update_features(vlan->dev); } -static int ipvtap_newlink(struct net *src_net, - struct net_device *dev, - struct nlattr *tb[], - struct nlattr *data[]) +static int ipvtap_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ipvtap_dev *vlantap = netdev_priv(dev); int err; @@ -98,7 +97,7 @@ static int ipvtap_newlink(struct net *src_net, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - err = ipvlan_link_new(src_net, dev, tb, data); + err = ipvlan_link_new(src_net, dev, tb, data, extack); if (err) { netdev_rx_handler_unregister(dev); return err; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index e370d7c894cb..60f3e3089ec3 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3203,7 +3203,8 @@ static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len) } static int macsec_newlink(struct net *net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 8ca274c6df3d..526d23db3b71 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1390,7 +1390,8 @@ destroy_macvlan_port: EXPORT_SYMBOL_GPL(macvlan_common_newlink); static int macvlan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { return macvlan_common_newlink(src_net, dev, tb, data); } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index da85057680d6..91e7b19bbf86 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -77,10 +77,9 @@ static void macvtap_update_features(struct tap_dev *tap, netdev_update_features(vlan->dev); } -static int macvtap_newlink(struct net *src_net, - struct net_device *dev, - struct nlattr *tb[], - struct nlattr *data[]) +static int macvtap_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct macvtap_dev *vlantap = netdev_priv(dev); int err; diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index d42091f11eb8..8479c130fe2e 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1075,7 +1075,8 @@ static int ppp_nl_validate(struct nlattr *tb[], struct nlattr *data[]) } static int ppp_nl_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ppp_config conf = { .unit = -1, diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 629a412dc690..bbe97bb7c9cc 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2101,7 +2101,8 @@ static void team_setup(struct net_device *dev) } static int team_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS] == NULL) eth_hw_addr_random(dev); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 0156fe8cac17..3db907cb7d07 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -347,7 +347,8 @@ static int veth_validate(struct nlattr *tb[], struct nlattr *data[]) static struct rtnl_link_ops veth_link_ops; static int veth_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { int err; struct net_device *peer; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 997ef25189fd..762f4d033e1b 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1389,7 +1389,8 @@ static void vrf_dellink(struct net_device *dev, struct list_head *head) } static int vrf_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_vrf *vrf = netdev_priv(dev); bool *add_fib_rules; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 653b2bb32be1..50a208747179 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3333,7 +3333,8 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], } static int vxlan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct vxlan_config conf; int err; diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 78fa5fe32947..33332a104ac5 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -68,7 +68,8 @@ struct rtnl_link_ops { int (*newlink)(struct net *src_net, struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]); + struct nlattr *data[], + struct netlink_ext_ack *extack); int (*changelink)(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 9c94aad153b3..11b74e2b1036 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -115,7 +115,8 @@ static int vlan_changelink(struct net_device *dev, } static int vlan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 63dca347b73b..39c1fa104c8d 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1213,7 +1213,8 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], } static int br_dev_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); int err; diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index fe3c53efb949..3ad833cd042f 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -461,7 +461,8 @@ static void caif_netlink_parms(struct nlattr *data[], } static int ipcaif_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { int ret; struct chnl_net *caifdev; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9a1bd510c812..8b3faa00905f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2705,7 +2705,8 @@ replay: dev->ifindex = ifm->ifi_index; if (ops->newlink) { - err = ops->newlink(link_net ? : net, dev, tb, data); + err = ops->newlink(link_net ? : net, dev, tb, data, + extack); /* Drivers should call free_netdev() in ->destructor * and unregister it on failure after registration * so that device could be finally freed in rtnl_unlock. diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 81dac16933fc..b9cce0fd5696 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -33,7 +33,8 @@ static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = { * hsr_dev_setup routine has been executed. Nice! */ static int hsr_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_device *link[2]; unsigned char multicast_spec, hsr_version; diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 0a866f332290..1a4c585f3950 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -121,7 +121,8 @@ static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) } static int lowpan_newlink(struct net *src_net, struct net_device *ldev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_device *wdev; int ret; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 41394a4b9af9..989f29f2f0d5 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -957,7 +957,8 @@ static void ipgre_tap_setup(struct net_device *dev) } static int ipgre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; @@ -1155,7 +1156,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, t = netdev_priv(dev); t->collect_md = true; - err = ipgre_newlink(net, dev, tb, NULL); + err = ipgre_newlink(net, dev, tb, NULL, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 4ec9affb2252..d748c5017d3b 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -503,7 +503,8 @@ static void vti_netlink_parms(struct nlattr *data[], } static int vti_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel_parm parms; __u32 fwmark = 0; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 1e441c6f2160..51132060397d 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -469,7 +469,8 @@ static bool ipip_netlink_encap_parms(struct nlattr *data[], } static int ipip_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index e0e726c338a7..f7c949d41fda 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1342,7 +1342,8 @@ static bool ip6gre_netlink_encap_parms(struct nlattr *data[], } static int ip6gre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *nt; struct net *net = dev_net(dev); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 8c6c3c8e7eef..ca12b2e33ae3 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1974,7 +1974,8 @@ static bool ip6_tnl_netlink_encap_parms(struct nlattr *data[], } static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 837ea1eefe7f..736a4f3f731d 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -940,7 +940,8 @@ static void vti6_netlink_parms(struct nlattr *data[], } static int vti6_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip6_tnl *nt; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 2378503577b0..f7445fdb5e64 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1537,7 +1537,8 @@ static bool ipip6_netlink_6rd_parms(struct nlattr *data[], #endif static int ipip6_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip_tunnel *nt; -- cgit v1.2.3 From ad744b223c521b1e01752a826774545c3e3acd8e Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 25 Jun 2017 23:56:00 +0200 Subject: net: add netlink_ext_ack argument to rtnl_link_ops.changelink Add support for extended error reporting. Signed-off-by: Matthias Schiffer Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 7 ++++--- drivers/net/bonding/bond_netlink.c | 7 ++++--- drivers/net/caif/caif_hsi.c | 3 ++- drivers/net/can/dev.c | 5 +++-- drivers/net/ipvlan/ipvlan_main.c | 3 ++- drivers/net/macsec.c | 3 ++- drivers/net/macvlan.c | 3 ++- drivers/net/vxlan.c | 3 ++- include/net/rtnetlink.h | 3 ++- net/8021q/vlan_netlink.c | 7 ++++--- net/bridge/br_netlink.c | 5 +++-- net/caif/chnl_net.c | 3 ++- net/core/rtnetlink.c | 2 +- net/ipv4/ip_gre.c | 3 ++- net/ipv4/ip_vti.c | 3 ++- net/ipv4/ipip.c | 3 ++- net/ipv6/ip6_gre.c | 3 ++- net/ipv6/ip6_tunnel.c | 3 ++- net/ipv6/ip6_vti.c | 3 ++- net/ipv6/sit.c | 3 ++- 20 files changed, 47 insertions(+), 28 deletions(-) (limited to 'include/net') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c index 8b75f80da56c..3e44087935ae 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c @@ -64,8 +64,9 @@ nla_put_failure: return -EMSGSIZE; } -static int ipoib_changelink(struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) +static int ipoib_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) { u16 mode, umcast; int ret = 0; @@ -134,7 +135,7 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev, child_pkey, IPOIB_RTNL_CHILD); if (!err && data) - err = ipoib_changelink(dev, tb, data); + err = ipoib_changelink(dev, tb, data, extack); return err; } diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index f817fb8005ef..cb803c026f1f 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -156,8 +156,9 @@ static int bond_slave_changelink(struct net_device *bond_dev, return 0; } -static int bond_changelink(struct net_device *bond_dev, - struct nlattr *tb[], struct nlattr *data[]) +static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); struct bond_opt_value newval; @@ -443,7 +444,7 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev, { int err; - err = bond_changelink(bond_dev, tb, data); + err = bond_changelink(bond_dev, tb, data, extack); if (err < 0) return err; diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c index ed4723a9031f..438966bf51c2 100644 --- a/drivers/net/caif/caif_hsi.c +++ b/drivers/net/caif/caif_hsi.c @@ -1352,7 +1352,8 @@ static void cfhsi_netlink_parms(struct nlattr *data[], struct cfhsi *cfhsi) } static int caif_hsi_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { cfhsi_netlink_parms(data, netdev_priv(dev)); netdev_state_change(dev); diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 7f99e8a5dd09..6d8191f2ad32 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -880,8 +880,9 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int can_changelink(struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) +static int can_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct can_priv *priv = netdev_priv(dev); int err; diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 7bda5f630ac9..e7d54072d7b3 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -455,7 +455,8 @@ static const struct ethtool_ops ipvlan_ethtool_ops = { }; static int ipvlan_nl_changelink(struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 60f3e3089ec3..38ba3d73ac15 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3056,7 +3056,8 @@ static void macsec_changelink_common(struct net_device *dev, } static int macsec_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { if (!data) return 0; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 526d23db3b71..3064416578a9 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1409,7 +1409,8 @@ void macvlan_dellink(struct net_device *dev, struct list_head *head) EXPORT_SYMBOL_GPL(macvlan_dellink); static int macvlan_changelink(struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); enum macvlan_mode mode; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 50a208747179..60c40349e73e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3347,7 +3347,8 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, } static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 33332a104ac5..f7d0320f75b0 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -72,7 +72,8 @@ struct rtnl_link_ops { struct netlink_ext_ack *extack); int (*changelink)(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]); + struct nlattr *data[], + struct netlink_ext_ack *extack); void (*dellink)(struct net_device *dev, struct list_head *head); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 11b74e2b1036..f08b5e192e45 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -87,8 +87,9 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int vlan_changelink(struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[]) +static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ifla_vlan_flags *flags; struct ifla_vlan_qos_mapping *m; @@ -154,7 +155,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, else if (dev->mtu > max_mtu) return -EINVAL; - err = vlan_changelink(dev, tb, data); + err = vlan_changelink(dev, tb, data, extack); if (err < 0) return err; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 39c1fa104c8d..37e4ec2953b2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -960,7 +960,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int err; @@ -1229,7 +1230,7 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev, if (err) return err; - err = br_changelink(dev, tb, data); + err = br_changelink(dev, tb, data, extack); if (err) unregister_netdevice(dev); return err; diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 3ad833cd042f..922ac1d605b3 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -485,7 +485,8 @@ static int ipcaif_newlink(struct net *src_net, struct net_device *dev, } static int ipcaif_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct chnl_net *caifdev; ASSERT_RTNL(); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8b3faa00905f..bac81d1bb24d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2620,7 +2620,7 @@ replay: !ops->changelink) return -EOPNOTSUPP; - err = ops->changelink(dev, tb, data); + err = ops->changelink(dev, tb, data, extack); if (err < 0) return err; status |= DO_SETLINK_NOTIFY; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 989f29f2f0d5..a63985c4bec7 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -980,7 +980,8 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index d748c5017d3b..24acff67a4f2 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -514,7 +514,8 @@ static int vti_newlink(struct net *src_net, struct net_device *dev, } static int vti_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); __u32 fwmark = t->fwmark; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 51132060397d..eb7fe7b0046f 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -489,7 +489,8 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev, } static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f7c949d41fda..7232b28425f3 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1404,7 +1404,8 @@ out: } static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *t, *nt = netdev_priv(dev); struct net *net = nt->net; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index ca12b2e33ae3..d9f60a173107 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -2006,7 +2006,8 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm p; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 736a4f3f731d..2afdddb48e69 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -967,7 +967,8 @@ static void vti6_dellink(struct net_device *dev, struct list_head *head) } static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *t; struct __ip6_tnl_parm p; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index f7445fdb5e64..b8000429f78d 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1574,7 +1574,8 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, } static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; -- cgit v1.2.3 From a8b8a889e369de82f295f55455adb4a7c31c458c Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 25 Jun 2017 23:56:01 +0200 Subject: net: add netlink_ext_ack argument to rtnl_link_ops.validate Add support for extended error reporting. Signed-off-by: Matthias Schiffer Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/bonding/bond_netlink.c | 3 ++- drivers/net/can/dev.c | 3 ++- drivers/net/dummy.c | 3 ++- drivers/net/geneve.c | 3 ++- drivers/net/gtp.c | 3 ++- drivers/net/ifb.c | 3 ++- drivers/net/ipvlan/ipvlan_main.c | 3 ++- drivers/net/macsec.c | 3 ++- drivers/net/macvlan.c | 3 ++- drivers/net/nlmon.c | 3 ++- drivers/net/ppp/ppp_generic.c | 3 ++- drivers/net/team/team.c | 3 ++- drivers/net/tun.c | 3 ++- drivers/net/veth.c | 5 +++-- drivers/net/vrf.c | 3 ++- drivers/net/vxlan.c | 3 ++- include/net/rtnetlink.h | 3 ++- net/8021q/vlan_netlink.c | 3 ++- net/bridge/br_netlink.c | 4 +++- net/core/rtnetlink.c | 2 +- net/ieee802154/6lowpan/core.c | 3 ++- net/ipv4/ip_gre.c | 8 +++++--- net/ipv4/ip_vti.c | 3 ++- net/ipv4/ipip.c | 3 ++- net/ipv6/ip6_gre.c | 8 +++++--- net/ipv6/ip6_tunnel.c | 3 ++- net/ipv6/ip6_vti.c | 3 ++- net/ipv6/sit.c | 3 ++- 28 files changed, 63 insertions(+), 33 deletions(-) (limited to 'include/net') diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index cb803c026f1f..0a9d78de6138 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -118,7 +118,8 @@ static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { [IFLA_BOND_SLAVE_QUEUE_ID] = { .type = NLA_U16 }, }; -static int bond_validate(struct nlattr *tb[], struct nlattr *data[]) +static int bond_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 6d8191f2ad32..365a8cc62405 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -848,7 +848,8 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = { = { .len = sizeof(struct can_bittiming_const) }, }; -static int can_validate(struct nlattr *tb[], struct nlattr *data[]) +static int can_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { bool is_can_fd = false; diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index 9905b52fe293..d0c165d2086e 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -356,7 +356,8 @@ static void dummy_setup(struct net_device *dev) dev->max_mtu = ETH_MAX_MTU; } -static int dummy_validate(struct nlattr *tb[], struct nlattr *data[]) +static int dummy_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 0a72d914e1f9..eb77201cb718 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1058,7 +1058,8 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, }; -static int geneve_validate(struct nlattr *tb[], struct nlattr *data[]) +static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 9cfe8a24c1fc..1542e837fdfa 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -698,7 +698,8 @@ static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = { [IFLA_GTP_ROLE] = { .type = NLA_U32 }, }; -static int gtp_validate(struct nlattr *tb[], struct nlattr *data[]) +static int gtp_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (!data) return -EINVAL; diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 144ea5ae8ab4..8870bd2a2e8a 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -273,7 +273,8 @@ static int ifb_open(struct net_device *dev) return 0; } -static int ifb_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ifb_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index e7d54072d7b3..f37e3c1fd4e7 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -477,7 +477,8 @@ static size_t ipvlan_nl_getsize(const struct net_device *dev) ); } -static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (data && data[IFLA_IPVLAN_MODE]) { u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 38ba3d73ac15..5e1ab1160856 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3287,7 +3287,8 @@ unregister: return err; } -static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) +static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { u64 csid = MACSEC_DEFAULT_CIPHER_ID; u8 icv_len = DEFAULT_ICV_LEN; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 3064416578a9..9ffff0362a11 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1162,7 +1162,8 @@ static void macvlan_port_destroy(struct net_device *dev) kfree(port); } -static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[]) +static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c index c4b3362da4a2..4b22955de191 100644 --- a/drivers/net/nlmon.c +++ b/drivers/net/nlmon.c @@ -127,7 +127,8 @@ static void nlmon_setup(struct net_device *dev) dev->min_mtu = sizeof(struct nlmsghdr); } -static int nlmon_validate(struct nlattr *tb[], struct nlattr *data[]) +static int nlmon_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) return -EINVAL; diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 8479c130fe2e..13028833bee3 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1061,7 +1061,8 @@ static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = { [IFLA_PPP_DEV_FD] = { .type = NLA_S32 }, }; -static int ppp_nl_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ppp_nl_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (!data) return -EINVAL; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index bbe97bb7c9cc..464570409796 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2110,7 +2110,8 @@ static int team_newlink(struct net *src_net, struct net_device *dev, return register_netdevice(dev); } -static int team_validate(struct nlattr *tb[], struct nlattr *data[]) +static int team_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index ae49f4b99b67..3d4c24572ecd 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1580,7 +1580,8 @@ static void tun_setup(struct net_device *dev) /* Trivial set of netlink ops to allow deleting tun or tap * device with netlink. */ -static int tun_validate(struct nlattr *tb[], struct nlattr *data[]) +static int tun_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { return -EINVAL; } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 3db907cb7d07..b33553b1e19c 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -329,7 +329,8 @@ static void veth_setup(struct net_device *dev) * netlink interface */ -static int veth_validate(struct nlattr *tb[], struct nlattr *data[]) +static int veth_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) @@ -374,7 +375,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; - err = veth_validate(peer_tb, NULL); + err = veth_validate(peer_tb, NULL, extack); if (err < 0) return err; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 762f4d033e1b..f4d0054981c6 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1372,7 +1372,8 @@ static void vrf_setup(struct net_device *dev) dev->priv_flags |= IFF_NO_QUEUE; } -static int vrf_validate(struct nlattr *tb[], struct nlattr *data[]) +static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 60c40349e73e..0dafd8e6c665 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2711,7 +2711,8 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG }, }; -static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[]) +static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index f7d0320f75b0..11fe0ad60e43 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -63,7 +63,8 @@ struct rtnl_link_ops { int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], - struct nlattr *data[]); + struct nlattr *data[], + struct netlink_ext_ack *extack); int (*newlink)(struct net *src_net, struct net_device *dev, diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index f08b5e192e45..5e831de3103e 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -39,7 +39,8 @@ static inline int vlan_validate_qos_map(struct nlattr *attr) NULL); } -static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) +static int vlan_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ifla_vlan_flags *flags; u16 id; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 37e4ec2953b2..9af177ca4d31 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -858,7 +858,9 @@ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) return err; } -static int br_validate(struct nlattr *tb[], struct nlattr *data[]) + +static int br_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bac81d1bb24d..7136588e65e9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2582,7 +2582,7 @@ replay: data = attr; } if (ops->validate) { - err = ops->validate(tb, data); + err = ops->validate(tb, data, extack); if (err < 0) return err; } diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 1a4c585f3950..de2661cd0328 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -111,7 +111,8 @@ static void lowpan_setup(struct net_device *ldev) ldev->features |= NETIF_F_NETNS_LOCAL; } -static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) +static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a63985c4bec7..7a7829e839c2 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -779,7 +779,8 @@ static struct pernet_operations ipgre_net_ops = { .size = sizeof(struct ip_tunnel_net), }; -static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { __be16 flags; @@ -802,7 +803,8 @@ static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { __be32 daddr; @@ -823,7 +825,7 @@ static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) } out: - return ipgre_tunnel_validate(tb, data); + return ipgre_tunnel_validate(tb, data, extack); } static int ipgre_netlink_parms(struct net_device *dev, diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 24acff67a4f2..0192c255e508 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -465,7 +465,8 @@ static struct pernet_operations vti_net_ops = { .size = sizeof(struct ip_tunnel_net), }; -static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { return 0; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index eb7fe7b0046f..fb1ad22b5e29 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -375,7 +375,8 @@ static int ipip_tunnel_init(struct net_device *dev) return ip_tunnel_init(dev); } -static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { u8 proto; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 7232b28425f3..67ff2aaf5dcb 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1170,7 +1170,8 @@ static struct pernet_operations ip6gre_net_ops = { .size = sizeof(struct ip6gre_net), }; -static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { __be16 flags; @@ -1188,7 +1189,8 @@ static int ip6gre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct in6_addr daddr; @@ -1209,7 +1211,7 @@ static int ip6gre_tap_validate(struct nlattr *tb[], struct nlattr *data[]) } out: - return ip6gre_tunnel_validate(tb, data); + return ip6gre_tunnel_validate(tb, data, extack); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index d9f60a173107..3a0ba2ae4b0f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1885,7 +1885,8 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) return 0; } -static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { u8 proto; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 2afdddb48e69..486c2305f53c 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -907,7 +907,8 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) return 0; } -static int vti6_validate(struct nlattr *tb[], struct nlattr *data[]) +static int vti6_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { return 0; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index b8000429f78d..e9958b1398cb 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1406,7 +1406,8 @@ static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); } -static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[]) +static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { u8 proto; -- cgit v1.2.3 From 17dd0ec470f97518893a5ed7160a842a35482fb4 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 25 Jun 2017 23:56:02 +0200 Subject: net: add netlink_ext_ack argument to rtnl_link_ops.slave_changelink Add support for extended error reporting. Signed-off-by: Matthias Schiffer Acked-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/bonding/bond_netlink.c | 3 ++- include/net/rtnetlink.h | 3 ++- net/bridge/br_netlink.c | 3 ++- net/core/rtnetlink.c | 3 ++- 4 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 0a9d78de6138..a1b33aa6054a 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -132,7 +132,8 @@ static int bond_validate(struct nlattr *tb[], struct nlattr *data[], static int bond_slave_changelink(struct net_device *bond_dev, struct net_device *slave_dev, - struct nlattr *tb[], struct nlattr *data[]) + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); struct bond_opt_value newval; diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 11fe0ad60e43..baf99e173dca 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -95,7 +95,8 @@ struct rtnl_link_ops { int (*slave_changelink)(struct net_device *dev, struct net_device *slave_dev, struct nlattr *tb[], - struct nlattr *data[]); + struct nlattr *data[], + struct netlink_ext_ack *extack); size_t (*get_slave_size)(const struct net_device *dev, const struct net_device *slave_dev); int (*fill_slave_info)(struct sk_buff *skb, diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 9af177ca4d31..3bc890716c89 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -897,7 +897,8 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[], static int br_port_slave_changelink(struct net_device *brdev, struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[]) + struct nlattr *data[], + struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int ret; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 7136588e65e9..658a48959fc4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2631,7 +2631,8 @@ replay: return -EOPNOTSUPP; err = m_ops->slave_changelink(master_dev, dev, - tb, slave_data); + tb, slave_data, + extack); if (err < 0) return err; status |= DO_SETLINK_NOTIFY; -- cgit v1.2.3 From d116ffc770d80f241f0d750d355205d83a9eca5a Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Sun, 25 Jun 2017 23:56:03 +0200 Subject: net: add netlink_ext_ack argument to rtnl_link_ops.slave_validate Add support for extended error reporting. Signed-off-by: Matthias Schiffer Acked-by: David Ahern Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 3 ++- net/core/rtnetlink.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index baf99e173dca..abe6b733d473 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -91,7 +91,8 @@ struct rtnl_link_ops { int slave_maxtype; const struct nla_policy *slave_policy; int (*slave_validate)(struct nlattr *tb[], - struct nlattr *data[]); + struct nlattr *data[], + struct netlink_ext_ack *extack); int (*slave_changelink)(struct net_device *dev, struct net_device *slave_dev, struct nlattr *tb[], diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 658a48959fc4..ed51de525a88 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2601,7 +2601,8 @@ replay: slave_data = slave_attr; } if (m_ops->slave_validate) { - err = m_ops->slave_validate(tb, slave_data); + err = m_ops->slave_validate(tb, slave_data, + extack); if (err < 0) return err; } -- cgit v1.2.3 From b26bbdae460ba90fb8cda37123a66be15a43a2a9 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 26 Jun 2017 19:01:50 +0200 Subject: udp: move scratch area helpers into the include file So that they can be later used by the IPv6 code, too. Also lift the comments a bit. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/udp.h | 61 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/udp.c | 60 ------------------------------------------------------ 2 files changed, 61 insertions(+), 60 deletions(-) (limited to 'include/net') diff --git a/include/net/udp.h b/include/net/udp.h index 1468dbd0f09a..972ce4baab6b 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -302,6 +302,67 @@ struct sock *__udp6_lib_lookup(struct net *net, struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport); +/* UDP uses skb->dev_scratch to cache as much information as possible and avoid + * possibly multiple cache miss on dequeue() + */ +#if BITS_PER_LONG == 64 + +/* truesize, len and the bit needed to compute skb_csum_unnecessary will be on + * cold cache lines at recvmsg time. + * skb->len can be stored on 16 bits since the udp header has been already + * validated and pulled. + */ +struct udp_dev_scratch { + u32 truesize; + u16 len; + bool is_linear; + bool csum_unnecessary; +}; + +static inline unsigned int udp_skb_len(struct sk_buff *skb) +{ + return ((struct udp_dev_scratch *)&skb->dev_scratch)->len; +} + +static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) +{ + return ((struct udp_dev_scratch *)&skb->dev_scratch)->csum_unnecessary; +} + +static inline bool udp_skb_is_linear(struct sk_buff *skb) +{ + return ((struct udp_dev_scratch *)&skb->dev_scratch)->is_linear; +} + +#else +static inline unsigned int udp_skb_len(struct sk_buff *skb) +{ + return skb->len; +} + +static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb) +{ + return skb_csum_unnecessary(skb); +} + +static inline bool udp_skb_is_linear(struct sk_buff *skb) +{ + return !skb_is_nonlinear(skb); +} +#endif + +static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, + struct iov_iter *to) +{ + int n, copy = len - off; + + n = copy_to_iter(skb->data + off, copy, to); + if (n == copy) + return 0; + + return -EFAULT; +} + /* * SNMP statistics for UDP and UDP-Lite */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 47c7aa0501af..86fad2a14ac4 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1163,24 +1163,7 @@ out: return ret; } -/* Copy as much information as possible into skb->dev_scratch to avoid - * possibly multiple cache miss on dequeue(); - */ #if BITS_PER_LONG == 64 - -/* we can store multiple info here: truesize, len and the bit needed to - * compute skb_csum_unnecessary will be on cold cache lines at recvmsg - * time. - * skb->len can be stored on 16 bits since the udp header has been already - * validated and pulled. - */ -struct udp_dev_scratch { - u32 truesize; - u16 len; - bool is_linear; - bool csum_unnecessary; -}; - static void udp_set_dev_scratch(struct sk_buff *skb) { struct udp_dev_scratch *scratch; @@ -1197,22 +1180,6 @@ static int udp_skb_truesize(struct sk_buff *skb) { return ((struct udp_dev_scratch *)&skb->dev_scratch)->truesize; } - -static unsigned int udp_skb_len(struct sk_buff *skb) -{ - return ((struct udp_dev_scratch *)&skb->dev_scratch)->len; -} - -static bool udp_skb_csum_unnecessary(struct sk_buff *skb) -{ - return ((struct udp_dev_scratch *)&skb->dev_scratch)->csum_unnecessary; -} - -static bool udp_skb_is_linear(struct sk_buff *skb) -{ - return ((struct udp_dev_scratch *)&skb->dev_scratch)->is_linear; -} - #else static void udp_set_dev_scratch(struct sk_buff *skb) { @@ -1223,21 +1190,6 @@ static int udp_skb_truesize(struct sk_buff *skb) { return skb->dev_scratch; } - -static unsigned int udp_skb_len(struct sk_buff *skb) -{ - return skb->len; -} - -static bool udp_skb_csum_unnecessary(struct sk_buff *skb) -{ - return skb_csum_unnecessary(skb); -} - -static bool udp_skb_is_linear(struct sk_buff *skb) -{ - return !skb_is_nonlinear(skb); -} #endif /* fully reclaim rmem/fwd memory allocated for skb */ @@ -1598,18 +1550,6 @@ busy_check: } EXPORT_SYMBOL_GPL(__skb_recv_udp); -static int copy_linear_skb(struct sk_buff *skb, int len, int off, - struct iov_iter *to) -{ - int n, copy = len - off; - - n = copy_to_iter(skb->data + off, copy, to); - if (n == copy) - return 0; - - return -EFAULT; -} - /* * This should be easy, if there is something there we * return it, otherwise we block. -- cgit v1.2.3 From 3859a271a003aba01e45b85c9d8b355eb7bf25f9 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 28 Oct 2016 01:22:25 -0700 Subject: randstruct: Mark various structs for randomization This marks many critical kernel structures for randomization. These are structures that have been targeted in the past in security exploits, or contain functions pointers, pointers to function pointer tables, lists, workqueues, ref-counters, credentials, permissions, or are otherwise sensitive. This initial list was extracted from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Left out of this list is task_struct, which requires special handling and will be covered in a subsequent patch. Signed-off-by: Kees Cook --- arch/x86/include/asm/processor.h | 2 +- fs/mount.h | 4 ++-- fs/namei.c | 2 +- fs/proc/internal.h | 6 +++--- include/linux/binfmts.h | 4 ++-- include/linux/cdev.h | 2 +- include/linux/cred.h | 4 ++-- include/linux/dcache.h | 2 +- include/linux/fs.h | 17 +++++++++-------- include/linux/fs_struct.h | 2 +- include/linux/ipc.h | 2 +- include/linux/ipc_namespace.h | 2 +- include/linux/key-type.h | 4 ++-- include/linux/kmod.h | 2 +- include/linux/kobject.h | 2 +- include/linux/lsm_hooks.h | 4 ++-- include/linux/mm_types.h | 4 ++-- include/linux/module.h | 4 ++-- include/linux/mount.h | 2 +- include/linux/msg.h | 2 +- include/linux/path.h | 2 +- include/linux/pid_namespace.h | 2 +- include/linux/proc_ns.h | 2 +- include/linux/sched.h | 2 +- include/linux/sched/signal.h | 2 +- include/linux/sem.h | 2 +- include/linux/shm.h | 2 +- include/linux/sysctl.h | 2 +- include/linux/tty.h | 2 +- include/linux/tty_driver.h | 4 ++-- include/linux/user_namespace.h | 2 +- include/linux/utsname.h | 2 +- include/net/af_unix.h | 2 +- include/net/neighbour.h | 2 +- include/net/net_namespace.h | 2 +- include/net/sock.h | 2 +- kernel/futex.c | 4 ++-- security/keys/internal.h | 2 +- 38 files changed, 57 insertions(+), 56 deletions(-) (limited to 'include/net') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 3cada998a402..e2335edb9fc5 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -129,7 +129,7 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; -}; +} __randomize_layout; struct cpuid_regs { u32 eax, ebx, ecx, edx; diff --git a/fs/mount.h b/fs/mount.h index bf1fda6eed8f..e406b286fba1 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -16,7 +16,7 @@ struct mnt_namespace { u64 event; unsigned int mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; -}; +} __randomize_layout; struct mnt_pcp { int mnt_count; @@ -68,7 +68,7 @@ struct mount { struct hlist_head mnt_pins; struct fs_pin mnt_umount; struct dentry *mnt_ex_mountpoint; -}; +} __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ diff --git a/fs/namei.c b/fs/namei.c index 6571a5f5112e..1764620ac383 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -524,7 +524,7 @@ struct nameidata { struct inode *link_inode; unsigned root_seq; int dfd; -}; +} __randomize_layout; static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) { diff --git a/fs/proc/internal.h b/fs/proc/internal.h index c5ae09b6c726..07b16318223f 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -51,7 +51,7 @@ struct proc_dir_entry { spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ u8 namelen; char name[]; -}; +} __randomize_layout; union proc_op { int (*proc_get_link)(struct dentry *, struct path *); @@ -70,7 +70,7 @@ struct proc_inode { struct list_head sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; -}; +} __randomize_layout; /* * General functions @@ -279,7 +279,7 @@ struct proc_maps_private { #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif -}; +} __randomize_layout; struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode); diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 05488da3aee9..3ae9013eeaaa 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -46,7 +46,7 @@ struct linux_binprm { unsigned interp_flags; unsigned interp_data; unsigned long loader, exec; -}; +} __randomize_layout; #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 #define BINPRM_FLAGS_ENFORCE_NONDUMP (1 << BINPRM_FLAGS_ENFORCE_NONDUMP_BIT) @@ -81,7 +81,7 @@ struct linux_binfmt { int (*load_shlib)(struct file *); int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ -}; +} __randomize_layout; extern void __register_binfmt(struct linux_binfmt *fmt, int insert); diff --git a/include/linux/cdev.h b/include/linux/cdev.h index 408bc09ce497..cb28eb21e3ca 100644 --- a/include/linux/cdev.h +++ b/include/linux/cdev.h @@ -17,7 +17,7 @@ struct cdev { struct list_head list; dev_t dev; unsigned int count; -}; +} __randomize_layout; void cdev_init(struct cdev *, const struct file_operations *); diff --git a/include/linux/cred.h b/include/linux/cred.h index b03e7d049a64..82c8a9e1aabb 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -31,7 +31,7 @@ struct group_info { atomic_t usage; int ngroups; kgid_t gid[0]; -}; +} __randomize_layout; /** * get_group_info - Get a reference to a group info structure @@ -145,7 +145,7 @@ struct cred { struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ struct rcu_head rcu; /* RCU deletion hook */ -}; +} __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index d2e38dc6172c..7eb262e13d3c 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -113,7 +113,7 @@ struct dentry { struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; -}; +} __randomize_layout; /* * dentry->d_lock spinlock nesting subclasses: diff --git a/include/linux/fs.h b/include/linux/fs.h index 803e5a9b2654..8f28143486c4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -275,7 +275,7 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; -}; +} __randomize_layout; static inline bool is_sync_kiocb(struct kiocb *kiocb) { @@ -392,7 +392,7 @@ struct address_space { gfp_t gfp_mask; /* implicit gfp mask for allocations */ struct list_head private_list; /* ditto */ void *private_data; /* ditto */ -} __attribute__((aligned(sizeof(long)))); +} __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit @@ -435,7 +435,7 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; -}; +} __randomize_layout; /* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache @@ -653,7 +653,7 @@ struct inode { #endif void *i_private; /* fs or device private pointer */ -}; +} __randomize_layout; static inline unsigned int i_blocksize(const struct inode *node) { @@ -868,7 +868,8 @@ struct file { struct list_head f_tfile_llink; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; -} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ +} __randomize_layout + __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; @@ -1005,7 +1006,7 @@ struct file_lock { int state; /* state of grant or error if -ve */ } afs; } fl_u; -}; +} __randomize_layout; struct file_lock_context { spinlock_t flc_lock; @@ -1404,7 +1405,7 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ -}; +} __randomize_layout; /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can @@ -1690,7 +1691,7 @@ struct file_operations { u64); ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *, u64); -}; +} __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 0efc3e62843a..7a026240cbb1 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -12,7 +12,7 @@ struct fs_struct { int umask; int in_exec; struct path root, pwd; -}; +} __randomize_layout; extern struct kmem_cache *fs_cachep; diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 71fd92d81b26..ea0eb0b5f98c 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -20,6 +20,6 @@ struct kern_ipc_perm { umode_t mode; unsigned long seq; void *security; -} ____cacheline_aligned_in_smp; +} ____cacheline_aligned_in_smp __randomize_layout; #endif /* _LINUX_IPC_H */ diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 848e5796400e..65327ee0936b 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -61,7 +61,7 @@ struct ipc_namespace { struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct ipc_namespace init_ipc_ns; extern spinlock_t mq_lock; diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 8496cf64575c..9520fc3c3b9a 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -45,7 +45,7 @@ struct key_preparsed_payload { size_t datalen; /* Raw datalen */ size_t quotalen; /* Quota length for proposed payload */ time_t expiry; /* Expiry time of key */ -}; +} __randomize_layout; typedef int (*request_key_actor_t)(struct key_construction *key, const char *op, void *aux); @@ -158,7 +158,7 @@ struct key_type { /* internal fields */ struct list_head link; /* link in types list */ struct lock_class_key lock_class; /* key->sem lock class */ -}; +} __randomize_layout; extern struct key_type key_type_keyring; diff --git a/include/linux/kmod.h b/include/linux/kmod.h index c4e441e00db5..655082c88fd9 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -64,7 +64,7 @@ struct subprocess_info { int (*init)(struct subprocess_info *info, struct cred *new); void (*cleanup)(struct subprocess_info *info); void *data; -}; +} __randomize_layout; extern int call_usermodehelper(const char *path, char **argv, char **envp, int wait); diff --git a/include/linux/kobject.h b/include/linux/kobject.h index ca85cb80e99a..084513350317 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -172,7 +172,7 @@ struct kset { spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; -}; +} __randomize_layout; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 080f34e66017..565163fc9ad4 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1876,7 +1876,7 @@ struct security_hook_heads { struct list_head audit_rule_match; struct list_head audit_rule_free; #endif /* CONFIG_AUDIT */ -}; +} __randomize_layout; /* * Security module hook list structure. @@ -1887,7 +1887,7 @@ struct security_hook_list { struct list_head *head; union security_list_options hook; char *lsm; -}; +} __randomize_layout; /* * Initializing a security_hook_list structure takes diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 45cdb27791a3..ff151814a02d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -342,7 +342,7 @@ struct vm_area_struct { struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; -}; +} __randomize_layout; struct core_thread { struct task_struct *task; @@ -500,7 +500,7 @@ struct mm_struct { atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; -}; +} __randomize_layout; extern struct mm_struct init_mm; diff --git a/include/linux/module.h b/include/linux/module.h index 21f56393602f..d93111d7def6 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -45,7 +45,7 @@ struct module_kobject { struct kobject *drivers_dir; struct module_param_attrs *mp; struct completion *kobj_completion; -}; +} __randomize_layout; struct module_attribute { struct attribute attr; @@ -475,7 +475,7 @@ struct module { ctor_fn_t *ctors; unsigned int num_ctors; #endif -} ____cacheline_aligned; +} ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif diff --git a/include/linux/mount.h b/include/linux/mount.h index 8e0352af06b7..1ce85e6fd95f 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -67,7 +67,7 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; -}; +} __randomize_layout; struct file; /* forward dec */ struct path; diff --git a/include/linux/msg.h b/include/linux/msg.h index f3f302f9c197..a001305f5a79 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -29,7 +29,7 @@ struct msg_queue { struct list_head q_messages; struct list_head q_receivers; struct list_head q_senders; -}; +} __randomize_layout; /* Helper routines for sys_msgsnd and sys_msgrcv */ extern long do_msgsnd(int msqid, long mtype, void __user *mtext, diff --git a/include/linux/path.h b/include/linux/path.h index d1372186f431..cde895cc4af4 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -7,7 +7,7 @@ struct vfsmount; struct path { struct vfsmount *mnt; struct dentry *dentry; -}; +} __randomize_layout; extern void path_get(const struct path *); extern void path_put(const struct path *); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index c2a989dee876..b09136f88cf4 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -52,7 +52,7 @@ struct pid_namespace { int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; -}; +} __randomize_layout; extern struct pid_namespace init_pid_ns; diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 58ab28d81fc2..06844b54dfc1 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -21,7 +21,7 @@ struct proc_ns_operations { int (*install)(struct nsproxy *nsproxy, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); struct ns_common *(*get_parent)(struct ns_common *ns); -}; +} __randomize_layout; extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; diff --git a/include/linux/sched.h b/include/linux/sched.h index 2b69fc650201..f833254fce00 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -408,7 +408,7 @@ struct sched_rt_entity { /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif -}; +} __randomize_layout; struct sched_dl_entity { struct rb_node rb_node; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index c06d63b3a583..2a0dd40b15db 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -222,7 +222,7 @@ struct signal_struct { struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) */ -}; +} __randomize_layout; /* * Bits in flags field of signal_struct. diff --git a/include/linux/sem.h b/include/linux/sem.h index 9edec926e9d9..23bcbdfad4a6 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -21,7 +21,7 @@ struct sem_array { int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ unsigned int use_global_lock;/* >0: global lock required */ -}; +} __randomize_layout; #ifdef CONFIG_SYSVIPC diff --git a/include/linux/shm.h b/include/linux/shm.h index 04e881829625..0fb7061ec54c 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -22,7 +22,7 @@ struct shmid_kernel /* private to the kernel */ /* The task created the shm object. NULL if the task is dead. */ struct task_struct *shm_creator; struct list_head shm_clist; /* list by creator */ -}; +} __randomize_layout; /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 80d07816def0..9ddeef2c03e2 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -117,7 +117,7 @@ struct ctl_table struct ctl_table_poll *poll; void *extra1; void *extra2; -}; +} __randomize_layout; struct ctl_node { struct rb_node node; diff --git a/include/linux/tty.h b/include/linux/tty.h index d07cd2105a6c..73f8d0977bb0 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -333,7 +333,7 @@ struct tty_struct { /* If the tty has a pending do_SAK, queue it here - akpm */ struct work_struct SAK_work; struct tty_port *port; -}; +} __randomize_layout; /* Each of a tty's open files has private_data pointing to tty_file_private */ struct tty_file_private { diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index b742b5e47cc2..00b2213f6a35 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -291,7 +291,7 @@ struct tty_operations { void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif const struct file_operations *proc_fops; -}; +} __randomize_layout; struct tty_driver { int magic; /* magic number for this structure */ @@ -325,7 +325,7 @@ struct tty_driver { const struct tty_operations *ops; struct list_head tty_drivers; -}; +} __randomize_layout; extern struct list_head tty_drivers; diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 32354b4b4b2b..b3575ce29148 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -66,7 +66,7 @@ struct user_namespace { #endif struct ucounts *ucounts; int ucount_max[UCOUNT_COUNTS]; -}; +} __randomize_layout; struct ucounts { struct hlist_node node; diff --git a/include/linux/utsname.h b/include/linux/utsname.h index 60f0bb83b313..da826ed059cf 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -26,7 +26,7 @@ struct uts_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; -}; +} __randomize_layout; extern struct uts_namespace init_uts_ns; #ifdef CONFIG_UTS_NS diff --git a/include/net/af_unix.h b/include/net/af_unix.h index fd60eccb59a6..64e2a1e24a2c 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -36,7 +36,7 @@ struct unix_skb_parms { u32 secid; /* Security ID */ #endif u32 consumed; -}; +} __randomize_layout; #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e4dd3a214034..a62959d2b3f7 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -155,7 +155,7 @@ struct neighbour { struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; -}; +} __randomize_layout; struct neigh_ops { int family; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index fe80bb48ab1f..a224196d16ac 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -147,7 +147,7 @@ struct net { #endif struct sock *diag_nlsk; atomic_t fnhe_genid; -}; +} __randomize_layout; #include diff --git a/include/net/sock.h b/include/net/sock.h index f33e3d134e0b..d349297db9e9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1113,7 +1113,7 @@ struct proto { atomic_t socks; #endif int (*diag_destroy)(struct sock *sk, int err); -}; +} __randomize_layout; int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); diff --git a/kernel/futex.c b/kernel/futex.c index 357348a6cf6b..5616511abf39 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -212,7 +212,7 @@ struct futex_pi_state { atomic_t refcount; union futex_key key; -}; +} __randomize_layout; /** * struct futex_q - The hashed futex queue entry, one per waiting task @@ -246,7 +246,7 @@ struct futex_q { struct rt_mutex_waiter *rt_waiter; union futex_key *requeue_pi_key; u32 bitset; -}; +} __randomize_layout; static const struct futex_q futex_q_init = { /* list gets initialized in queue_me()*/ diff --git a/security/keys/internal.h b/security/keys/internal.h index c0f8682eba69..6494954e9980 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -197,7 +197,7 @@ struct request_key_auth { void *callout_info; size_t callout_len; pid_t pid; -}; +} __randomize_layout; extern struct key_type key_type_request_key_auth; extern struct key *request_key_auth_new(struct key *target, -- cgit v1.2.3 From 1cc9a98b59ba92fece1277f76aa43e05f34936a6 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:07:54 +0300 Subject: net: convert inet_peer.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. This conversion requires overall +1 on the whole refcounting scheme. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/inetpeer.h | 4 ++-- net/ipv4/inetpeer.c | 18 +++++++++--------- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 235c7811a86a..f2a215fc78e4 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -46,7 +46,7 @@ struct inet_peer { struct rcu_head gc_rcu; }; /* - * Once inet_peer is queued for deletion (refcnt == -1), following field + * Once inet_peer is queued for deletion (refcnt == 0), following field * is not available: rid * We can share memory with rcu_head to help keep inet_peer small. */ @@ -60,7 +60,7 @@ struct inet_peer { /* following fields might be frequently dirtied */ __u32 dtime; /* the time of last use of not referenced entries */ - atomic_t refcnt; + refcount_t refcnt; }; struct inet_peer_base { diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 86fa45809540..c5a117cc6619 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -115,7 +115,7 @@ static void inetpeer_gc_worker(struct work_struct *work) n = list_entry(p->gc_list.next, struct inet_peer, gc_list); - if (!atomic_read(&p->refcnt)) { + if (refcount_read(&p->refcnt) == 1) { list_del(&p->gc_list); kmem_cache_free(peer_cachep, p); } @@ -202,10 +202,11 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, int cmp = inetpeer_addr_cmp(daddr, &u->daddr); if (cmp == 0) { /* Before taking a reference, check if this entry was - * deleted (refcnt=-1) + * deleted (refcnt=0) */ - if (!atomic_add_unless(&u->refcnt, 1, -1)) + if (!refcount_inc_not_zero(&u->refcnt)) { u = NULL; + } return u; } if (cmp == -1) @@ -382,11 +383,10 @@ static int inet_peer_gc(struct inet_peer_base *base, while (stackptr > stack) { stackptr--; p = rcu_deref_locked(**stackptr, base); - if (atomic_read(&p->refcnt) == 0) { + if (refcount_read(&p->refcnt) == 1) { smp_rmb(); delta = (__u32)jiffies - p->dtime; - if (delta >= ttl && - atomic_cmpxchg(&p->refcnt, 0, -1) == 0) { + if (delta >= ttl && refcount_dec_if_one(&p->refcnt)) { p->gc_next = gchead; gchead = p; } @@ -432,7 +432,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, relookup: p = lookup(daddr, stack, base); if (p != peer_avl_empty) { - atomic_inc(&p->refcnt); + refcount_inc(&p->refcnt); write_sequnlock_bh(&base->lock); return p; } @@ -444,7 +444,7 @@ relookup: p = create ? kmem_cache_alloc(peer_cachep, GFP_ATOMIC) : NULL; if (p) { p->daddr = *daddr; - atomic_set(&p->refcnt, 1); + refcount_set(&p->refcnt, 2); atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; @@ -468,7 +468,7 @@ void inet_putpeer(struct inet_peer *p) { p->dtime = (__u32)jiffies; smp_mb__before_atomic(); - atomic_dec(&p->refcnt); + refcount_dec(&p->refcnt); } EXPORT_SYMBOL_GPL(inet_putpeer); -- cgit v1.2.3 From 9f23743017d11c103b38d2fa1f64674baeca41cd Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:07:55 +0300 Subject: net: convert neighbour.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/arp.h | 2 +- include/net/ndisc.h | 2 +- include/net/neighbour.h | 9 +++++---- net/atm/clip.c | 6 +++--- net/core/neighbour.c | 14 +++++++------- net/decnet/dn_neigh.c | 2 +- 6 files changed, 18 insertions(+), 17 deletions(-) (limited to 'include/net') diff --git a/include/net/arp.h b/include/net/arp.h index 65619a2de6f4..17d90e4e8dc5 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -28,7 +28,7 @@ static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 rcu_read_lock_bh(); n = __ipv4_neigh_lookup_noref(dev, key); - if (n && !atomic_inc_not_zero(&n->refcnt)) + if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock_bh(); diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 1036c902d2c9..31b1bb11ba3f 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -384,7 +384,7 @@ static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, cons rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref(dev, pkey); - if (n && !atomic_inc_not_zero(&n->refcnt)) + if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock_bh(); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 639b67564a7d..e5ee739d2b8c 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -17,6 +17,7 @@ */ #include +#include #include #include #include @@ -137,7 +138,7 @@ struct neighbour { unsigned long confirmed; unsigned long updated; rwlock_t lock; - atomic_t refcnt; + refcount_t refcnt; struct sk_buff_head arp_queue; unsigned int arp_queue_len_bytes; struct timer_list timer; @@ -410,18 +411,18 @@ static inline struct neigh_parms *neigh_parms_clone(struct neigh_parms *parms) static inline void neigh_release(struct neighbour *neigh) { - if (atomic_dec_and_test(&neigh->refcnt)) + if (refcount_dec_and_test(&neigh->refcnt)) neigh_destroy(neigh); } static inline struct neighbour * neigh_clone(struct neighbour *neigh) { if (neigh) - atomic_inc(&neigh->refcnt); + refcount_inc(&neigh->refcnt); return neigh; } -#define neigh_hold(n) atomic_inc(&(n)->refcnt) +#define neigh_hold(n) refcount_inc(&(n)->refcnt) static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { diff --git a/net/atm/clip.c b/net/atm/clip.c index a7e4018370b4..47c36f449df0 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -137,11 +137,11 @@ static int neigh_check_cb(struct neighbour *n) if (entry->vccs || time_before(jiffies, entry->expires)) return 0; - if (atomic_read(&n->refcnt) > 1) { + if (refcount_read(&n->refcnt) > 1) { struct sk_buff *skb; pr_debug("destruction postponed with ref %d\n", - atomic_read(&n->refcnt)); + refcount_read(&n->refcnt)); while ((skb = skb_dequeue(&n->arp_queue)) != NULL) dev_kfree_skb(skb); @@ -767,7 +767,7 @@ static void atmarp_info(struct seq_file *seq, struct neighbour *n, seq_printf(seq, "(resolving)\n"); else seq_printf(seq, "(expired, ref %d)\n", - atomic_read(&entry->neigh->refcnt)); + refcount_read(&entry->neigh->refcnt)); } else if (!svc) { seq_printf(seq, "%d.%d.%d\n", clip_vcc->vcc->dev->number, diff --git a/net/core/neighbour.c b/net/core/neighbour.c index dadb5eef91c3..0c78c8e0409d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -124,7 +124,7 @@ static bool neigh_del(struct neighbour *n, __u8 state, bool retval = false; write_lock(&n->lock); - if (atomic_read(&n->refcnt) == 1 && !(n->nud_state & state)) { + if (refcount_read(&n->refcnt) == 1 && !(n->nud_state & state)) { struct neighbour *neigh; neigh = rcu_dereference_protected(n->next, @@ -254,7 +254,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) neigh_del_timer(n); n->dead = 1; - if (atomic_read(&n->refcnt) != 1) { + if (refcount_read(&n->refcnt) != 1) { /* The most unpleasant situation. We must destroy neighbour entry, but someone still uses it. @@ -335,7 +335,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device NEIGH_CACHE_STAT_INC(tbl, allocs); n->tbl = tbl; - atomic_set(&n->refcnt, 1); + refcount_set(&n->refcnt, 1); n->dead = 1; out: return n; @@ -444,7 +444,7 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, rcu_read_lock_bh(); n = __neigh_lookup_noref(tbl, pkey, dev); if (n) { - if (!atomic_inc_not_zero(&n->refcnt)) + if (!refcount_inc_not_zero(&n->refcnt)) n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); } @@ -473,7 +473,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, n = rcu_dereference_bh(n->next)) { if (!memcmp(n->primary_key, pkey, key_len) && net_eq(dev_net(n->dev), net)) { - if (!atomic_inc_not_zero(&n->refcnt)) + if (!refcount_inc_not_zero(&n->refcnt)) n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); break; @@ -821,7 +821,7 @@ static void neigh_periodic_work(struct work_struct *work) if (time_before(n->used, n->confirmed)) n->used = n->confirmed; - if (atomic_read(&n->refcnt) == 1 && + if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; @@ -2234,7 +2234,7 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, ci.ndm_used = jiffies_to_clock_t(now - neigh->used); ci.ndm_confirmed = jiffies_to_clock_t(now - neigh->confirmed); ci.ndm_updated = jiffies_to_clock_t(now - neigh->updated); - ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; + ci.ndm_refcnt = refcount_read(&neigh->refcnt) - 1; read_unlock_bh(&neigh->lock); if (nla_put_u32(skb, NDA_PROBES, atomic_read(&neigh->probes)) || diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index eeb5fc561f80..21dedf6fd0f7 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -559,7 +559,7 @@ static inline void dn_neigh_format_entry(struct seq_file *seq, (dn->flags&DN_NDFLAG_R2) ? "2" : "-", (dn->flags&DN_NDFLAG_P3) ? "3" : "-", dn->n.nud_state, - atomic_read(&dn->n.refcnt), + refcount_read(&dn->n.refcnt), dn->blksize, (dn->n.dev) ? dn->n.dev->name : "?"); read_unlock(&n->lock); -- cgit v1.2.3 From 6343944bc1050dcec7c959f484ee0fb6928db3be Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:07:56 +0300 Subject: net: convert neigh_params.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/neighbour.h | 6 +++--- net/core/neighbour.c | 8 ++++---- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e5ee739d2b8c..afc39e3a3f7c 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -77,7 +77,7 @@ struct neigh_parms { void *sysctl_table; int dead; - atomic_t refcnt; + refcount_t refcnt; struct rcu_head rcu_head; int reachable_time; @@ -396,12 +396,12 @@ void neigh_sysctl_unregister(struct neigh_parms *p); static inline void __neigh_parms_put(struct neigh_parms *parms) { - atomic_dec(&parms->refcnt); + refcount_dec(&parms->refcnt); } static inline struct neigh_parms *neigh_parms_clone(struct neigh_parms *parms) { - atomic_inc(&parms->refcnt); + refcount_inc(&parms->refcnt); return parms; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 0c78c8e0409d..e31fc11a8000 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -709,7 +709,7 @@ static void neigh_parms_destroy(struct neigh_parms *parms); static inline void neigh_parms_put(struct neigh_parms *parms) { - if (atomic_dec_and_test(&parms->refcnt)) + if (refcount_dec_and_test(&parms->refcnt)) neigh_parms_destroy(parms); } @@ -1479,7 +1479,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL); if (p) { p->tbl = tbl; - atomic_set(&p->refcnt, 1); + refcount_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); dev_hold(dev); @@ -1542,7 +1542,7 @@ void neigh_table_init(int index, struct neigh_table *tbl) INIT_LIST_HEAD(&tbl->parms_list); list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); - atomic_set(&tbl->parms.refcnt, 1); + refcount_set(&tbl->parms.refcnt, 1); tbl->parms.reachable_time = neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); @@ -1796,7 +1796,7 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) if ((parms->dev && nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || - nla_put_u32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)) || + nla_put_u32(skb, NDTPA_REFCNT, refcount_read(&parms->refcnt)) || nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, NEIGH_VAR(parms, QUEUE_LEN_BYTES)) || /* approximative value for deprecated QUEUE_LEN (in packets) */ -- cgit v1.2.3 From 53869cebce4bc53f71a080e7830600d4ae1ab712 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:07:57 +0300 Subject: net: convert nf_bridge_info.use from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- include/net/netfilter/br_netfilter.h | 2 +- net/bridge/br_netfilter_hooks.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a17e235639ae..005793e01bd2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -252,7 +252,7 @@ struct nf_conntrack { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { - atomic_t use; + refcount_t use; enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, @@ -3589,13 +3589,13 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct) #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline void nf_bridge_put(struct nf_bridge_info *nf_bridge) { - if (nf_bridge && atomic_dec_and_test(&nf_bridge->use)) + if (nf_bridge && refcount_dec_and_test(&nf_bridge->use)) kfree(nf_bridge); } static inline void nf_bridge_get(struct nf_bridge_info *nf_bridge) { if (nf_bridge) - atomic_inc(&nf_bridge->use); + refcount_inc(&nf_bridge->use); } #endif /* CONFIG_BRIDGE_NETFILTER */ static inline void nf_reset(struct sk_buff *skb) diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 0b0c35c37125..925524ede6c8 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -8,7 +8,7 @@ static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) skb->nf_bridge = kzalloc(sizeof(struct nf_bridge_info), GFP_ATOMIC); if (likely(skb->nf_bridge)) - atomic_set(&(skb->nf_bridge->use), 1); + refcount_set(&(skb->nf_bridge->use), 1); return skb->nf_bridge; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 067cf0313449..2261e5194c82 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -149,12 +149,12 @@ static inline struct nf_bridge_info *nf_bridge_unshare(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = skb->nf_bridge; - if (atomic_read(&nf_bridge->use) > 1) { + if (refcount_read(&nf_bridge->use) > 1) { struct nf_bridge_info *tmp = nf_bridge_alloc(skb); if (tmp) { memcpy(tmp, nf_bridge, sizeof(struct nf_bridge_info)); - atomic_set(&tmp->use, 1); + refcount_set(&tmp->use, 1); } nf_bridge_put(nf_bridge); nf_bridge = tmp; -- cgit v1.2.3 From 14afee4b6092fde451ee17604e5f5c89da33e71e Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:08:00 +0300 Subject: net: convert sock.sk_wmem_alloc from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- drivers/atm/fore200e.c | 12 +----------- drivers/atm/he.c | 2 +- drivers/atm/idt77252.c | 4 ++-- include/linux/atmdev.h | 2 +- include/net/sock.h | 8 ++++---- net/atm/br2684.c | 2 +- net/atm/clip.c | 2 +- net/atm/common.c | 10 +++++----- net/atm/lec.c | 4 ++-- net/atm/mpc.c | 4 ++-- net/atm/pppoatm.c | 2 +- net/atm/raw.c | 2 +- net/atm/signaling.c | 2 +- net/caif/caif_socket.c | 2 +- net/core/datagram.c | 2 +- net/core/skbuff.c | 2 +- net/core/sock.c | 26 +++++++++++++------------- net/ipv4/af_inet.c | 2 +- net/ipv4/esp4.c | 2 +- net/ipv4/ip_output.c | 6 +++--- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_offload.c | 2 +- net/ipv4/tcp_output.c | 15 +++++++-------- net/ipv6/esp6.c | 2 +- net/ipv6/ip6_output.c | 4 ++-- net/kcm/kcmproc.c | 2 +- net/key/af_key.c | 2 +- net/netlink/af_netlink.c | 2 +- net/packet/af_packet.c | 4 ++-- net/phonet/socket.c | 2 +- net/rds/tcp_send.c | 2 +- net/rxrpc/af_rxrpc.c | 4 ++-- net/sched/sch_atm.c | 2 +- net/sctp/output.c | 2 +- net/sctp/proc.c | 2 +- net/sctp/socket.c | 4 ++-- net/unix/af_unix.c | 6 +++--- 37 files changed, 74 insertions(+), 85 deletions(-) (limited to 'include/net') diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index 7584ae1ded85..f0433adcd8fc 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -924,12 +924,7 @@ fore200e_tx_irq(struct fore200e* fore200e) else { dev_kfree_skb_any(entry->skb); } -#if 1 - /* race fixed by the above incarnation mechanism, but... */ - if (atomic_read(&sk_atm(vcc)->sk_wmem_alloc) < 0) { - atomic_set(&sk_atm(vcc)->sk_wmem_alloc, 0); - } -#endif + /* check error condition */ if (*entry->status & STATUS_ERROR) atomic_inc(&vcc->stats->tx_err); @@ -1130,13 +1125,9 @@ fore200e_push_rpd(struct fore200e* fore200e, struct atm_vcc* vcc, struct rpd* rp return -ENOMEM; } - ASSERT(atomic_read(&sk_atm(vcc)->sk_wmem_alloc) >= 0); - vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx); - ASSERT(atomic_read(&sk_atm(vcc)->sk_wmem_alloc) >= 0); - return 0; } @@ -1572,7 +1563,6 @@ fore200e_send(struct atm_vcc *vcc, struct sk_buff *skb) unsigned long flags; ASSERT(vcc); - ASSERT(atomic_read(&sk_atm(vcc)->sk_wmem_alloc) >= 0); ASSERT(fore200e); ASSERT(fore200e_vcc); diff --git a/drivers/atm/he.c b/drivers/atm/he.c index 461da2bce8ef..37ee21c5a5ca 100644 --- a/drivers/atm/he.c +++ b/drivers/atm/he.c @@ -2395,7 +2395,7 @@ he_close(struct atm_vcc *vcc) * TBRQ, the host issues the close command to the adapter. */ - while (((tx_inuse = atomic_read(&sk_atm(vcc)->sk_wmem_alloc)) > 1) && + while (((tx_inuse = refcount_read(&sk_atm(vcc)->sk_wmem_alloc)) > 1) && (retry < MAX_RETRY)) { msleep(sleep); if (sleep < 250) diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 4e64de380bda..60bacba03d17 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -724,7 +724,7 @@ push_on_scq(struct idt77252_dev *card, struct vc_map *vc, struct sk_buff *skb) struct sock *sk = sk_atm(vcc); vc->estimator->cells += (skb->len + 47) / 48; - if (atomic_read(&sk->sk_wmem_alloc) > + if (refcount_read(&sk->sk_wmem_alloc) > (sk->sk_sndbuf >> 1)) { u32 cps = vc->estimator->maxcps; @@ -2009,7 +2009,7 @@ idt77252_send_oam(struct atm_vcc *vcc, void *cell, int flags) atomic_inc(&vcc->stats->tx_err); return -ENOMEM; } - atomic_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); skb_put_data(skb, cell, 52); diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index c1da539f5e28..4d97a89da066 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -254,7 +254,7 @@ static inline void atm_return(struct atm_vcc *vcc,int truesize) static inline int atm_may_send(struct atm_vcc *vcc,unsigned int size) { - return (size + atomic_read(&sk_atm(vcc)->sk_wmem_alloc)) < + return (size + refcount_read(&sk_atm(vcc)->sk_wmem_alloc)) < sk_atm(vcc)->sk_sndbuf; } diff --git a/include/net/sock.h b/include/net/sock.h index 00d09140e354..5284e50fc81a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -390,7 +390,7 @@ struct sock { /* ===== cache line for TX ===== */ int sk_wmem_queued; - atomic_t sk_wmem_alloc; + refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; struct sk_buff *sk_send_head; struct sk_buff_head sk_write_queue; @@ -1911,7 +1911,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro */ static inline int sk_wmem_alloc_get(const struct sock *sk) { - return atomic_read(&sk->sk_wmem_alloc) - 1; + return refcount_read(&sk->sk_wmem_alloc) - 1; } /** @@ -2055,7 +2055,7 @@ static inline unsigned long sock_wspace(struct sock *sk) int amt = 0; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { - amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc); + amt = sk->sk_sndbuf - refcount_read(&sk->sk_wmem_alloc); if (amt < 0) amt = 0; } @@ -2136,7 +2136,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); */ static inline bool sock_writeable(const struct sock *sk) { - return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1); + return refcount_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1); } static inline gfp_t gfp_any(void) diff --git a/net/atm/br2684.c b/net/atm/br2684.c index fca84e111c89..4e111196f902 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -252,7 +252,7 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, ATM_SKB(skb)->vcc = atmvcc = brvcc->atmvcc; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, atmvcc, atmvcc->dev); - atomic_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(atmvcc)->sk_wmem_alloc); ATM_SKB(skb)->atm_options = atmvcc->atm_options; dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; diff --git a/net/atm/clip.c b/net/atm/clip.c index 47c36f449df0..f271a7bcf5b2 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -381,7 +381,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, memcpy(here, llc_oui, sizeof(llc_oui)); ((__be16 *) here)[3] = skb->protocol; } - atomic_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); ATM_SKB(skb)->atm_options = vcc->atm_options; entry->vccs->last_use = jiffies; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, vcc, vcc->dev); diff --git a/net/atm/common.c b/net/atm/common.c index f06422f4108d..8a4f99114cd2 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -80,9 +80,9 @@ static void vcc_sock_destruct(struct sock *sk) printk(KERN_DEBUG "%s: rmem leakage (%d bytes) detected.\n", __func__, atomic_read(&sk->sk_rmem_alloc)); - if (atomic_read(&sk->sk_wmem_alloc)) + if (refcount_read(&sk->sk_wmem_alloc)) printk(KERN_DEBUG "%s: wmem leakage (%d bytes) detected.\n", - __func__, atomic_read(&sk->sk_wmem_alloc)); + __func__, refcount_read(&sk->sk_wmem_alloc)); } static void vcc_def_wakeup(struct sock *sk) @@ -101,7 +101,7 @@ static inline int vcc_writable(struct sock *sk) struct atm_vcc *vcc = atm_sk(sk); return (vcc->qos.txtp.max_sdu + - atomic_read(&sk->sk_wmem_alloc)) <= sk->sk_sndbuf; + refcount_read(&sk->sk_wmem_alloc)) <= sk->sk_sndbuf; } static void vcc_write_space(struct sock *sk) @@ -156,7 +156,7 @@ int vcc_create(struct net *net, struct socket *sock, int protocol, int family, i memset(&vcc->local, 0, sizeof(struct sockaddr_atmsvc)); memset(&vcc->remote, 0, sizeof(struct sockaddr_atmsvc)); vcc->qos.txtp.max_sdu = 1 << 16; /* for meta VCs */ - atomic_set(&sk->sk_wmem_alloc, 1); + refcount_set(&sk->sk_wmem_alloc, 1); atomic_set(&sk->sk_rmem_alloc, 0); vcc->push = NULL; vcc->pop = NULL; @@ -630,7 +630,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) goto out; } pr_debug("%d += %d\n", sk_wmem_alloc_get(sk), skb->truesize); - atomic_add(skb->truesize, &sk->sk_wmem_alloc); + refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb->dev = NULL; /* for paths shared with net_device interfaces */ ATM_SKB(skb)->atm_options = vcc->atm_options; diff --git a/net/atm/lec.c b/net/atm/lec.c index 09cfe87f0a44..75545717fa46 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -181,7 +181,7 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb) ATM_SKB(skb)->vcc = vcc; ATM_SKB(skb)->atm_options = vcc->atm_options; - atomic_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); if (vcc->send(vcc, skb) < 0) { dev->stats.tx_dropped++; return; @@ -345,7 +345,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb) int i; char *tmp; /* FIXME */ - atomic_sub(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc)); mesg = (struct atmlec_msg *)skb->data; tmp = skb->data; tmp += sizeof(struct atmlec_msg); diff --git a/net/atm/mpc.c b/net/atm/mpc.c index a190800572bd..680a4b9095a1 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -555,7 +555,7 @@ static int send_via_shortcut(struct sk_buff *skb, struct mpoa_client *mpc) sizeof(struct llc_snap_hdr)); } - atomic_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(entry->shortcut)->sk_wmem_alloc); ATM_SKB(skb)->atm_options = entry->shortcut->atm_options; entry->shortcut->send(entry->shortcut, skb); entry->packets_fwded++; @@ -911,7 +911,7 @@ static int msg_from_mpoad(struct atm_vcc *vcc, struct sk_buff *skb) struct mpoa_client *mpc = find_mpc_by_vcc(vcc); struct k_message *mesg = (struct k_message *)skb->data; - atomic_sub(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc)); if (mpc == NULL) { pr_info("no mpc found\n"); diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index c4e09846d1de..21d9d341a619 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -350,7 +350,7 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb) return 1; } - atomic_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc); + refcount_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc); ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options; pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n", skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev); diff --git a/net/atm/raw.c b/net/atm/raw.c index 2e17e97a7a8b..821c0797553d 100644 --- a/net/atm/raw.c +++ b/net/atm/raw.c @@ -35,7 +35,7 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb) pr_debug("(%d) %d -= %d\n", vcc->vci, sk_wmem_alloc_get(sk), skb->truesize); - atomic_sub(skb->truesize, &sk->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); dev_kfree_skb_any(skb); sk->sk_write_space(sk); } diff --git a/net/atm/signaling.c b/net/atm/signaling.c index f640a99e14b8..983c3a21a133 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -67,7 +67,7 @@ static int sigd_send(struct atm_vcc *vcc, struct sk_buff *skb) struct sock *sk; msg = (struct atmsvc_msg *) skb->data; - atomic_sub(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize, &sk_atm(vcc)->sk_wmem_alloc)); vcc = *(struct atm_vcc **) &msg->vcc; pr_debug("%d (0x%lx)\n", (int)msg->type, (unsigned long)vcc); sk = sk_atm(vcc); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 7506b853a84d..632d5a416d97 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -1013,7 +1013,7 @@ static const struct proto_ops caif_stream_ops = { static void caif_sock_destructor(struct sock *sk) { struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); - caif_assert(!atomic_read(&sk->sk_wmem_alloc)); + caif_assert(!refcount_read(&sk->sk_wmem_alloc)); caif_assert(sk_unhashed(sk)); caif_assert(!sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { diff --git a/net/core/datagram.c b/net/core/datagram.c index 95d43543ac91..454ec8923333 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -614,7 +614,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) skb->data_len += copied; skb->len += copied; skb->truesize += truesize; - atomic_add(truesize, &skb->sk->sk_wmem_alloc); + refcount_add(truesize, &skb->sk->sk_wmem_alloc); while (copied) { int size = min_t(int, copied, PAGE_SIZE - start); skb_fill_page_desc(skb, frag++, pages[n], start, size); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 659dfc0494c5..c267713cd383 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3024,7 +3024,7 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, get_page(pfrag->page); skb->truesize += copy; - atomic_add(copy, &sk->sk_wmem_alloc); + refcount_add(copy, &sk->sk_wmem_alloc); skb->len += copy; skb->data_len += copy; offset += copy; diff --git a/net/core/sock.c b/net/core/sock.c index 6f4b090241c1..0866d59489cb 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1528,7 +1528,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, if (likely(sk->sk_net_refcnt)) get_net(net); sock_net_set(sk, net); - atomic_set(&sk->sk_wmem_alloc, 1); + refcount_set(&sk->sk_wmem_alloc, 1); mem_cgroup_sk_alloc(sk); cgroup_sk_alloc(&sk->sk_cgrp_data); @@ -1552,7 +1552,7 @@ static void __sk_destruct(struct rcu_head *head) sk->sk_destruct(sk); filter = rcu_dereference_check(sk->sk_filter, - atomic_read(&sk->sk_wmem_alloc) == 0); + refcount_read(&sk->sk_wmem_alloc) == 0); if (filter) { sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); @@ -1602,7 +1602,7 @@ void sk_free(struct sock *sk) * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ - if (atomic_dec_and_test(&sk->sk_wmem_alloc)) + if (refcount_dec_and_test(&sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sk_free); @@ -1659,7 +1659,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) /* * sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ - atomic_set(&newsk->sk_wmem_alloc, 1); + refcount_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); sk_init_common(newsk); @@ -1787,7 +1787,7 @@ void sock_wfree(struct sk_buff *skb) * Keep a reference on sk_wmem_alloc, this will be released * after sk_write_space() call */ - atomic_sub(len - 1, &sk->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc)); sk->sk_write_space(sk); len = 1; } @@ -1795,7 +1795,7 @@ void sock_wfree(struct sk_buff *skb) * if sk_wmem_alloc reaches 0, we must finish what sk_free() * could not do because of in-flight packets */ - if (atomic_sub_and_test(len, &sk->sk_wmem_alloc)) + if (refcount_sub_and_test(len, &sk->sk_wmem_alloc)) __sk_free(sk); } EXPORT_SYMBOL(sock_wfree); @@ -1807,7 +1807,7 @@ void __sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; - if (atomic_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)) + if (refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)) __sk_free(sk); } @@ -1829,7 +1829,7 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) * is enough to guarantee sk_free() wont free this sock until * all in-flight packets are completed */ - atomic_add(skb->truesize, &sk->sk_wmem_alloc); + refcount_add(skb->truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(skb_set_owner_w); @@ -1852,7 +1852,7 @@ void skb_orphan_partial(struct sk_buff *skb) struct sock *sk = skb->sk; if (atomic_inc_not_zero(&sk->sk_refcnt)) { - atomic_sub(skb->truesize, &sk->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); skb->destructor = sock_efree; } } else { @@ -1912,7 +1912,7 @@ EXPORT_SYMBOL(sock_i_ino); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { - if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { + if (force || refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { struct sk_buff *skb = alloc_skb(size, priority); if (skb) { skb_set_owner_w(skb, sk); @@ -1987,7 +1987,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) + if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) break; if (sk->sk_shutdown & SEND_SHUTDOWN) break; @@ -2310,7 +2310,7 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) if (sk->sk_type == SOCK_STREAM) { if (sk->sk_wmem_queued < prot->sysctl_wmem[0]) return 1; - } else if (atomic_read(&sk->sk_wmem_alloc) < + } else if (refcount_read(&sk->sk_wmem_alloc) < prot->sysctl_wmem[0]) return 1; } @@ -2577,7 +2577,7 @@ static void sock_def_write_space(struct sock *sk) /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { + if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 58925b6597de..76c2077c3f5b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -150,7 +150,7 @@ void inet_sock_destruct(struct sock *sk) } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(sk->sk_wmem_queued); WARN_ON(sk->sk_forward_alloc); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 1f18b4650253..0cbee0a666ff 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -307,7 +307,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * skb->data_len += tailen; skb->truesize += tailen; if (sk) - atomic_add(tailen, &sk->sk_wmem_alloc); + refcount_add(tailen, &sk->sk_wmem_alloc); goto out; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 532b36e9ce2a..2e61e2af251a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1037,7 +1037,7 @@ alloc_new_skb: (flags & MSG_DONTWAIT), &err); } else { skb = NULL; - if (atomic_read(&sk->sk_wmem_alloc) <= + if (refcount_read(&sk->sk_wmem_alloc) <= 2 * sk->sk_sndbuf) skb = sock_wmalloc(sk, alloclen + hh_len + 15, 1, @@ -1145,7 +1145,7 @@ alloc_new_skb: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - atomic_add(copy, &sk->sk_wmem_alloc); + refcount_add(copy, &sk->sk_wmem_alloc); } offset += copy; length -= copy; @@ -1369,7 +1369,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, skb->len += len; skb->data_len += len; skb->truesize += len; - atomic_add(len, &sk->sk_wmem_alloc); + refcount_add(len, &sk->sk_wmem_alloc); offset += len; size -= len; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4793fb78d93b..fae45e402742 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -664,7 +664,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, return skb->len < size_goal && sysctl_tcp_autocorking && skb != tcp_write_queue_head(sk) && - atomic_read(&sk->sk_wmem_alloc) > skb->truesize; + refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } static void tcp_push(struct sock *sk, int flags, int mss_now, @@ -692,7 +692,7 @@ static void tcp_push(struct sock *sk, int flags, int mss_now, /* It is possible TX completion already happened * before we set TSQ_THROTTLED. */ - if (atomic_read(&sk->sk_wmem_alloc) > skb->truesize) + if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize) return; } diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index bc68da38ea86..11f69bbf9307 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -152,7 +152,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, swap(gso_skb->sk, skb->sk); swap(gso_skb->destructor, skb->destructor); sum_truesize += skb->truesize; - atomic_add(sum_truesize - gso_skb->truesize, + refcount_add(sum_truesize - gso_skb->truesize, &skb->sk->sk_wmem_alloc); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9a9c395b6235..1d79137f3795 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -861,12 +861,11 @@ void tcp_wfree(struct sk_buff *skb) struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; - int wmem; /* Keep one reference on sk_wmem_alloc. * Will be released by sk_free() from here or tcp_tasklet_func() */ - wmem = atomic_sub_return(skb->truesize - 1, &sk->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc)); /* If this softirq is serviced by ksoftirqd, we are likely under stress. * Wait until our queues (qdisc + devices) are drained. @@ -875,7 +874,7 @@ void tcp_wfree(struct sk_buff *skb) * - chance for incoming ACK (processed by another cpu maybe) * to migrate this flow (skb->ooo_okay will be eventually set) */ - if (wmem >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) + if (refcount_read(&sk->sk_wmem_alloc) >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) goto out; for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { @@ -925,7 +924,7 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) if (nval != oval) continue; - if (!atomic_inc_not_zero(&sk->sk_wmem_alloc)) + if (!refcount_inc_not_zero(&sk->sk_wmem_alloc)) break; /* queue this socket to tasklet queue */ tsq = this_cpu_ptr(&tsq_tasklet); @@ -1045,7 +1044,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb->sk = sk; skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; skb_set_hash_from_sk(skb, sk); - atomic_add(skb->truesize, &sk->sk_wmem_alloc); + refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); @@ -2176,7 +2175,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes); limit <<= factor; - if (atomic_read(&sk->sk_wmem_alloc) > limit) { + if (refcount_read(&sk->sk_wmem_alloc) > limit) { /* Always send the 1st or 2nd skb in write queue. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. @@ -2192,7 +2191,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, * test again the condition. */ smp_mb__after_atomic(); - if (atomic_read(&sk->sk_wmem_alloc) > limit) + if (refcount_read(&sk->sk_wmem_alloc) > limit) return true; } return false; @@ -2812,7 +2811,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) /* Do not sent more than we queued. 1/4 is reserved for possible * copying overhead: fragmentation, tunneling, mangling etc. */ - if (atomic_read(&sk->sk_wmem_alloc) > + if (refcount_read(&sk->sk_wmem_alloc) > min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) return -EAGAIN; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 71faffdd55d9..9ed35473dcb5 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -275,7 +275,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info skb->data_len += tailen; skb->truesize += tailen; if (sk) - atomic_add(tailen, &sk->sk_wmem_alloc); + refcount_add(tailen, &sk->sk_wmem_alloc); goto out; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5f2657d98e82..1422d6c08377 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1472,7 +1472,7 @@ alloc_new_skb: (flags & MSG_DONTWAIT), &err); } else { skb = NULL; - if (atomic_read(&sk->sk_wmem_alloc) <= + if (refcount_read(&sk->sk_wmem_alloc) <= 2 * sk->sk_sndbuf) skb = sock_wmalloc(sk, alloclen + hh_len, 1, @@ -1581,7 +1581,7 @@ alloc_new_skb: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - atomic_add(copy, &sk->sk_wmem_alloc); + refcount_add(copy, &sk->sk_wmem_alloc); } offset += copy; length -= copy; diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c index bf75c9231cca..c343ac60bf50 100644 --- a/net/kcm/kcmproc.c +++ b/net/kcm/kcmproc.c @@ -162,7 +162,7 @@ static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq, psock->sk->sk_receive_queue.qlen, atomic_read(&psock->sk->sk_rmem_alloc), psock->sk->sk_write_queue.qlen, - atomic_read(&psock->sk->sk_wmem_alloc)); + refcount_read(&psock->sk->sk_wmem_alloc)); if (psock->done) seq_puts(seq, "Done "); diff --git a/net/key/af_key.c b/net/key/af_key.c index 287964a570e9..e466579c18fa 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -109,7 +109,7 @@ static void pfkey_sock_destruct(struct sock *sk) } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); atomic_dec(&net_pfkey->socks_nr); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 05030ad1a36c..8ced52e91181 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -372,7 +372,7 @@ static void netlink_sock_destruct(struct sock *sk) } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(nlk_sk(sk)->groups); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f9349a495caf..90fd38d5c458 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1317,7 +1317,7 @@ static void packet_sock_destruct(struct sock *sk) skb_queue_purge(&sk->sk_error_queue); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive packet socket: %p\n", sk); @@ -2523,7 +2523,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->data_len = to_write; skb->len += to_write; skb->truesize += to_write; - atomic_add(to_write, &po->sk.sk_wmem_alloc); + refcount_add(to_write, &po->sk.sk_wmem_alloc); while (likely(to_write)) { nr_frags = skb_shinfo(skb)->nr_frags; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 64634e3ec2fc..29c7f754c70d 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -360,7 +360,7 @@ static unsigned int pn_socket_poll(struct file *file, struct socket *sock, return POLLHUP; if (sk->sk_state == TCP_ESTABLISHED && - atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf && + refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf && atomic_read(&pn->tx_credits)) mask |= POLLOUT | POLLWRNORM | POLLWRBAND; diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index 52d11d7725c8..0d8616aa5bad 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -202,7 +202,7 @@ void rds_tcp_write_space(struct sock *sk) tc->t_last_seen_una = rds_tcp_snd_una(tc); rds_send_path_drop_acked(cp, rds_tcp_snd_una(tc), rds_tcp_is_acked); - if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) + if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) queue_delayed_work(rds_wq, &cp->cp_send_w, 0); out: diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 58ae0db52ea1..f1299f54627a 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -53,7 +53,7 @@ static void rxrpc_sock_destructor(struct sock *); */ static inline int rxrpc_writable(struct sock *sk) { - return atomic_read(&sk->sk_wmem_alloc) < (size_t) sk->sk_sndbuf; + return refcount_read(&sk->sk_wmem_alloc) < (size_t) sk->sk_sndbuf; } /* @@ -730,7 +730,7 @@ static void rxrpc_sock_destructor(struct sock *sk) rxrpc_purge_queue(&sk->sk_receive_queue); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(!sk_unhashed(sk)); WARN_ON(sk->sk_socket); diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index de162592eee0..572fe2584e48 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -498,7 +498,7 @@ static void sch_atm_dequeue(unsigned long data) ATM_SKB(skb)->vcc = flow->vcc; memcpy(skb_push(skb, flow->hdr_len), flow->hdr, flow->hdr_len); - atomic_add(skb->truesize, + refcount_add(skb->truesize, &sk_atm(flow->vcc)->sk_wmem_alloc); /* atm.atm_options are already set by atm_tc_enqueue */ flow->vcc->send(flow->vcc, skb); diff --git a/net/sctp/output.c b/net/sctp/output.c index 89cee1482d35..9bf9d84a96b7 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -402,7 +402,7 @@ static void sctp_packet_set_owner_w(struct sk_buff *skb, struct sock *sk) * therefore only reserve a single byte to keep socket around until * the packet has been transmitted. */ - atomic_inc(&sk->sk_wmem_alloc); + refcount_inc(&sk->sk_wmem_alloc); } static int sctp_packet_pack(struct sctp_packet *packet, diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 8e34db56bc1d..26b4be6b4172 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -363,7 +363,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) assoc->stream.outcnt, assoc->max_retrans, assoc->init_retries, assoc->shutdown_retries, assoc->rtx_data_chunks, - atomic_read(&sk->sk_wmem_alloc), + refcount_read(&sk->sk_wmem_alloc), sk->sk_wmem_queued, sk->sk_sndbuf, sk->sk_rcvbuf); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index b497ee8ae279..15401d09efc4 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -164,7 +164,7 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk) sizeof(struct sk_buff) + sizeof(struct sctp_chunk); - atomic_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); + refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); sk->sk_wmem_queued += chunk->skb->truesize; sk_mem_charge(sk, chunk->skb->truesize); } @@ -7684,7 +7684,7 @@ static void sctp_wfree(struct sk_buff *skb) sizeof(struct sk_buff) + sizeof(struct sctp_chunk); - atomic_sub(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); + WARN_ON(refcount_sub_and_test(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc)); /* * This undoes what is done via sctp_set_owner_w and sk_mem_charge diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 1a0c961f4ffe..7c2e21ebbedc 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -442,7 +442,7 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) static int unix_writable(const struct sock *sk) { return sk->sk_state != TCP_LISTEN && - (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; + (refcount_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf; } static void unix_write_space(struct sock *sk) @@ -487,7 +487,7 @@ static void unix_sock_destructor(struct sock *sk) skb_queue_purge(&sk->sk_receive_queue); - WARN_ON(atomic_read(&sk->sk_wmem_alloc)); + WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(!sk_unhashed(sk)); WARN_ON(sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { @@ -2033,7 +2033,7 @@ alloc_skb: skb->len += size; skb->data_len += size; skb->truesize += size; - atomic_add(size, &sk->sk_wmem_alloc); + refcount_add(size, &sk->sk_wmem_alloc); if (newskb) { err = unix_scm_to_skb(&scm, skb, false); -- cgit v1.2.3 From 41c6d650f6537e55a1b53438c646fbc3f49176bf Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:08:01 +0300 Subject: net: convert sock.sk_refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. This patch uses refcount_inc_not_zero() instead of atomic_inc_not_zero_hint() due to absense of a _hint() version of refcount API. If the hint() version must be used, we might need to revisit API. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- crypto/algif_aead.c | 2 +- include/net/inet_hashtables.h | 4 ++-- include/net/request_sock.h | 9 +++++---- include/net/sock.h | 17 +++++++++-------- net/atm/proc.c | 2 +- net/bluetooth/af_bluetooth.c | 2 +- net/bluetooth/rfcomm/sock.c | 2 +- net/core/skbuff.c | 6 +++--- net/core/sock.c | 6 +++--- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/inet_hashtables.c | 4 ++-- net/ipv4/inet_timewait_sock.c | 8 ++++---- net/ipv4/ping.c | 4 ++-- net/ipv4/raw.c | 2 +- net/ipv4/syncookies.c | 2 +- net/ipv4/tcp_fastopen.c | 2 +- net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv4/udp.c | 6 +++--- net/ipv4/udp_diag.c | 4 ++-- net/ipv6/datagram.c | 2 +- net/ipv6/inet6_hashtables.c | 4 ++-- net/ipv6/tcp_ipv6.c | 4 ++-- net/ipv6/udp.c | 4 ++-- net/key/af_key.c | 2 +- net/l2tp/l2tp_debugfs.c | 3 +-- net/llc/llc_conn.c | 8 ++++---- net/llc/llc_sap.c | 2 +- net/netfilter/xt_TPROXY.c | 4 ++-- net/netlink/af_netlink.c | 6 +++--- net/packet/af_packet.c | 2 +- net/phonet/socket.c | 2 +- net/rxrpc/af_rxrpc.c | 2 +- net/sched/em_meta.c | 2 +- net/tipc/socket.c | 2 +- net/unix/af_unix.c | 2 +- 35 files changed, 70 insertions(+), 69 deletions(-) (limited to 'include/net') diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 8af664f7d27c..be117495eb43 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -877,7 +877,7 @@ static void aead_sock_destruct(struct sock *sk) unsigned int ivlen = crypto_aead_ivsize( crypto_aead_reqtfm(&ctx->aead_req)); - WARN_ON(atomic_read(&sk->sk_refcnt) != 0); + WARN_ON(refcount_read(&sk->sk_refcnt) != 0); aead_put_sgl(sk); sock_kzfree_s(sk, ctx->iv, ivlen); sock_kfree_s(sk, ctx, ctx->len); diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 1178931288cb..b9e6e0e1f55c 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -32,7 +32,7 @@ #include #include -#include +#include #include /* This is for all connections with a full identity, no wildcards. @@ -334,7 +334,7 @@ static inline struct sock *inet_lookup(struct net *net, sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, dport, dif, &refcounted); - if (sk && !refcounted && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 53ced67c4ae9..23e22054aa60 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -19,6 +19,7 @@ #include #include #include +#include #include @@ -89,7 +90,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, return NULL; req->rsk_listener = NULL; if (attach_listener) { - if (unlikely(!atomic_inc_not_zero(&sk_listener->sk_refcnt))) { + if (unlikely(!refcount_inc_not_zero(&sk_listener->sk_refcnt))) { kmem_cache_free(ops->slab, req); return NULL; } @@ -100,7 +101,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, sk_node_init(&req_to_sk(req)->sk_node); sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; - atomic_set(&req->rsk_refcnt, 0); + refcount_set(&req->rsk_refcnt, 0); return req; } @@ -108,7 +109,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, static inline void reqsk_free(struct request_sock *req) { /* temporary debugging */ - WARN_ON_ONCE(atomic_read(&req->rsk_refcnt) != 0); + WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0); req->rsk_ops->destructor(req); if (req->rsk_listener) @@ -119,7 +120,7 @@ static inline void reqsk_free(struct request_sock *req) static inline void reqsk_put(struct request_sock *req) { - if (atomic_dec_and_test(&req->rsk_refcnt)) + if (refcount_dec_and_test(&req->rsk_refcnt)) reqsk_free(req); } diff --git a/include/net/sock.h b/include/net/sock.h index 5284e50fc81a..60200f4f4028 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -66,6 +66,7 @@ #include #include +#include #include #include #include @@ -219,7 +220,7 @@ struct sock_common { u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */ }; - atomic_t skc_refcnt; + refcount_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; union { @@ -611,7 +612,7 @@ static inline bool __sk_del_node_init(struct sock *sk) static __always_inline void sock_hold(struct sock *sk) { - atomic_inc(&sk->sk_refcnt); + refcount_inc(&sk->sk_refcnt); } /* Ungrab socket in the context, which assumes that socket refcnt @@ -619,7 +620,7 @@ static __always_inline void sock_hold(struct sock *sk) */ static __always_inline void __sock_put(struct sock *sk) { - atomic_dec(&sk->sk_refcnt); + refcount_dec(&sk->sk_refcnt); } static inline bool sk_del_node_init(struct sock *sk) @@ -628,7 +629,7 @@ static inline bool sk_del_node_init(struct sock *sk) if (rc) { /* paranoid for a while -acme */ - WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } return rc; @@ -650,7 +651,7 @@ static inline bool sk_nulls_del_node_init_rcu(struct sock *sk) if (rc) { /* paranoid for a while -acme */ - WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } return rc; @@ -1144,9 +1145,9 @@ static inline void sk_refcnt_debug_dec(struct sock *sk) static inline void sk_refcnt_debug_release(const struct sock *sk) { - if (atomic_read(&sk->sk_refcnt) != 1) + if (refcount_read(&sk->sk_refcnt) != 1) printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n", - sk->sk_prot->name, sk, atomic_read(&sk->sk_refcnt)); + sk->sk_prot->name, sk, refcount_read(&sk->sk_refcnt)); } #else /* SOCK_REFCNT_DEBUG */ #define sk_refcnt_debug_inc(sk) do { } while (0) @@ -1636,7 +1637,7 @@ void sock_init_data(struct socket *sock, struct sock *sk); /* Ungrab socket and destroy it, if it was the last reference. */ static inline void sock_put(struct sock *sk) { - if (atomic_dec_and_test(&sk->sk_refcnt)) + if (refcount_dec_and_test(&sk->sk_refcnt)) sk_free(sk); } /* Generic version of sock_put(), dealing with all sockets diff --git a/net/atm/proc.c b/net/atm/proc.c index bbb6461a4b7f..27c9c01c537d 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -211,7 +211,7 @@ static void vcc_info(struct seq_file *seq, struct atm_vcc *vcc) vcc->flags, sk->sk_err, sk_wmem_alloc_get(sk), sk->sk_sndbuf, sk_rmem_alloc_get(sk), sk->sk_rcvbuf, - atomic_read(&sk->sk_refcnt)); + refcount_read(&sk->sk_refcnt)); } static void svc_info(struct seq_file *seq, struct atm_vcc *vcc) diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 8a8f77a247e6..91e3ba280706 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -657,7 +657,7 @@ static int bt_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%pK %-6d %-6u %-6u %-6u %-6lu %-6lu", sk, - atomic_read(&sk->sk_refcnt), + refcount_read(&sk->sk_refcnt), sk_rmem_alloc_get(sk), sk_wmem_alloc_get(sk), from_kuid(seq_user_ns(seq), sock_i_uid(sk)), diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index ac3c650cb234..2172ae509cf1 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -197,7 +197,7 @@ static void rfcomm_sock_kill(struct sock *sk) if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) return; - BT_DBG("sk %p state %d refcnt %d", sk, sk->sk_state, atomic_read(&sk->sk_refcnt)); + BT_DBG("sk %p state %d refcnt %d", sk, sk->sk_state, refcount_read(&sk->sk_refcnt)); /* Kill poor orphan */ bt_sock_unlink(&rfcomm_sk_list, sk); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c267713cd383..8b11341ed69a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3844,7 +3844,7 @@ struct sk_buff *skb_clone_sk(struct sk_buff *skb) struct sock *sk = skb->sk; struct sk_buff *clone; - if (!sk || !atomic_inc_not_zero(&sk->sk_refcnt)) + if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; clone = skb_clone(skb, GFP_ATOMIC); @@ -3915,7 +3915,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ - if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { *skb_hwtstamps(skb) = *hwtstamps; __skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false); sock_put(sk); @@ -3997,7 +3997,7 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) /* Take a reference to prevent skb_orphan() from freeing the socket, * but only if the socket refcount is not zero. */ - if (likely(atomic_inc_not_zero(&sk->sk_refcnt))) { + if (likely(refcount_inc_not_zero(&sk->sk_refcnt))) { err = sock_queue_err_skb(sk, skb); sock_put(sk); } diff --git a/net/core/sock.c b/net/core/sock.c index 0866d59489cb..ba0ef6a7dbaf 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1708,7 +1708,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) * (Documentation/RCU/rculist_nulls.txt for details) */ smp_wmb(); - atomic_set(&newsk->sk_refcnt, 2); + refcount_set(&newsk->sk_refcnt, 2); /* * Increment the counter in the same struct proto as the master @@ -1851,7 +1851,7 @@ void skb_orphan_partial(struct sk_buff *skb) ) { struct sock *sk = skb->sk; - if (atomic_inc_not_zero(&sk->sk_refcnt)) { + if (refcount_inc_not_zero(&sk->sk_refcnt)) { WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); skb->destructor = sock_efree; } @@ -2687,7 +2687,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) * (Documentation/RCU/rculist_nulls.txt for details) */ smp_wmb(); - atomic_set(&sk->sk_refcnt, 1); + refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } EXPORT_SYMBOL(sock_init_data); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index a3fa1a5b6d98..4089c013cb03 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -756,7 +756,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, * are committed to memory and refcnt initialized. */ smp_wmb(); - atomic_set(&req->rsk_refcnt, 2 + 1); + refcount_set(&req->rsk_refcnt, 2 + 1); } void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e9a59d2d91d4..a4be2c1cb688 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -246,7 +246,7 @@ EXPORT_SYMBOL_GPL(__inet_lookup_listener); /* All sockets share common refcount, but have different destructors */ void sock_gen_put(struct sock *sk) { - if (!atomic_dec_and_test(&sk->sk_refcnt)) + if (!refcount_dec_and_test(&sk->sk_refcnt)) return; if (sk->sk_state == TCP_TIME_WAIT) @@ -287,7 +287,7 @@ begin: continue; if (likely(INET_MATCH(sk, net, acookie, saddr, daddr, ports, dif))) { - if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!INET_MATCH(sk, net, acookie, saddr, daddr, ports, dif))) { diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index f8aff2c71cde..5b039159e67a 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -76,7 +76,7 @@ void inet_twsk_free(struct inet_timewait_sock *tw) void inet_twsk_put(struct inet_timewait_sock *tw) { - if (atomic_dec_and_test(&tw->tw_refcnt)) + if (refcount_dec_and_test(&tw->tw_refcnt)) inet_twsk_free(tw); } EXPORT_SYMBOL_GPL(inet_twsk_put); @@ -131,7 +131,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, * We can use atomic_set() because prior spin_lock()/spin_unlock() * committed into memory all tw fields. */ - atomic_set(&tw->tw_refcnt, 4); + refcount_set(&tw->tw_refcnt, 4); inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ @@ -195,7 +195,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, * to a non null value before everything is setup for this * timewait socket. */ - atomic_set(&tw->tw_refcnt, 0); + refcount_set(&tw->tw_refcnt, 0); __module_get(tw->tw_prot->owner); } @@ -278,7 +278,7 @@ restart: atomic_read(&twsk_net(tw)->count)) continue; - if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt))) + if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) continue; if (unlikely((tw->tw_family != family) || diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index ccfbce13a633..b8f0db54b197 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -290,7 +290,7 @@ void ping_close(struct sock *sk, long timeout) { pr_debug("ping_close(sk=%p,sk->num=%u)\n", inet_sk(sk), inet_sk(sk)->inet_num); - pr_debug("isk->refcnt = %d\n", sk->sk_refcnt.counter); + pr_debug("isk->refcnt = %d\n", refcount_read(&sk->sk_refcnt)); sk_common_release(sk); } @@ -1127,7 +1127,7 @@ static void ping_v4_format_sock(struct sock *sp, struct seq_file *f, 0, 0L, 0, from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bdffad875691..b0bb5d0a30bd 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -1063,7 +1063,7 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) 0, 0L, 0, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } static int raw_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 7835bb4a1fab..0905cf04c2a4 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -213,7 +213,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst, NULL, &own_req); if (child) { - atomic_set(&req->rsk_refcnt, 1); + refcount_set(&req->rsk_refcnt, 1); tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); inet_csk_reqsk_queue_add(sk, req, child); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 4af82b914dd4..8b1539efaf38 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -214,7 +214,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT, TCP_RTO_MAX); - atomic_set(&req->rsk_refcnt, 2); + refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ inet_csk(child)->icsk_af_ops->rebuild_header(child); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d774bcd9a54b..6ec6900eb300 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2323,7 +2323,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)), icsk->icsk_probes_out, sock_i_ino(sk), - atomic_read(&sk->sk_refcnt), sk, + refcount_read(&sk->sk_refcnt), sk, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, @@ -2349,7 +2349,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, - atomic_read(&tw->tw_refcnt), tw); + refcount_read(&tw->tw_refcnt), tw); } #define TMPSZ 150 diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 86fad2a14ac4..25294d43e147 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -577,7 +577,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table, NULL); - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } @@ -2242,7 +2242,7 @@ void udp_v4_early_demux(struct sk_buff *skb) uh->source, iph->saddr, dif); } - if (!sk || !atomic_inc_not_zero_hint(&sk->sk_refcnt, 2)) + if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return; skb->sk = sk; @@ -2691,7 +2691,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, 0, 0L, 0, from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 9a89c10a55f0..4515836d2a3a 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -55,7 +55,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, req->id.idiag_dport, req->id.idiag_if, tbl, NULL); #endif - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); err = -ENOENT; @@ -206,7 +206,7 @@ static int __udp_diag_destroy(struct sk_buff *in_skb, return -EINVAL; } - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 5c786f5ab961..a1f918713006 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -1041,6 +1041,6 @@ void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index d0900918a19e..b13b8f93079d 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -75,7 +75,7 @@ begin: continue; if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif)) continue; - if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif))) { @@ -172,7 +172,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, ntohs(dport), dif, &refcounted); - if (sk && !refcounted && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f1a4881d9835..2521690d62d6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1809,7 +1809,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), icsk->icsk_probes_out, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, + refcount_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, @@ -1842,7 +1842,7 @@ static void get_timewait6_sock(struct seq_file *seq, dest->s6_addr32[2], dest->s6_addr32[3], destp, tw->tw_substate, 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, - atomic_read(&tw->tw_refcnt), tw); + refcount_read(&tw->tw_refcnt), tw); } static int tcp6_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 319aa8ed9cf8..4a3e65626e8b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -325,7 +325,7 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table, NULL); - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } @@ -916,7 +916,7 @@ static void udp_v6_early_demux(struct sk_buff *skb) else return; - if (!sk || !atomic_inc_not_zero_hint(&sk->sk_refcnt, 2)) + if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return; skb->sk = sk; diff --git a/net/key/af_key.c b/net/key/af_key.c index e466579c18fa..edcf1d0f82c8 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3739,7 +3739,7 @@ static int pfkey_seq_show(struct seq_file *f, void *v) else seq_printf(f, "%pK %-6d %-6u %-6u %-6u %-6lu\n", s, - atomic_read(&s->sk_refcnt), + refcount_read(&s->sk_refcnt), sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), from_kuid_munged(seq_user_ns(f), sock_i_uid(s)), diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index d100aed3d06f..98a005d0d04a 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -144,9 +144,8 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) tunnel->encap == L2TP_ENCAPTYPE_IP ? "IP" : ""); seq_printf(m, " %d sessions, refcnt %d/%d\n", session_count, - tunnel->sock ? atomic_read(&tunnel->sock->sk_refcnt) : 0, + tunnel->sock ? refcount_read(&tunnel->sock->sk_refcnt) : 0, atomic_read(&tunnel->ref_count)); - seq_printf(m, " %08x rx %ld/%ld/%ld rx %ld/%ld/%ld\n", tunnel->debug, atomic_long_read(&tunnel->stats.tx_packets), diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 9b02c13d258b..5e91b47f0d2a 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -507,7 +507,7 @@ again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_estab_match(sap, daddr, laddr, rc)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ - if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_estab_match(sap, daddr, laddr, rc))) { @@ -566,7 +566,7 @@ again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_listener_match(sap, laddr, rc)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ - if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_listener_match(sap, laddr, rc))) { @@ -973,9 +973,9 @@ void llc_sk_free(struct sock *sk) skb_queue_purge(&sk->sk_write_queue); skb_queue_purge(&llc->pdu_unack_q); #ifdef LLC_REFCNT_DEBUG - if (atomic_read(&sk->sk_refcnt) != 1) { + if (refcount_read(&sk->sk_refcnt) != 1) { printk(KERN_DEBUG "Destruction of LLC sock %p delayed in %s, cnt=%d\n", - sk, __func__, atomic_read(&sk->sk_refcnt)); + sk, __func__, refcount_read(&sk->sk_refcnt)); printk(KERN_DEBUG "%d LLC sockets are still alive\n", atomic_read(&llc_sock_nr)); } else { diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 63b6ab056370..d90928f50226 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -329,7 +329,7 @@ again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { if (llc_dgram_match(sap, laddr, rc)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ - if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt))) + if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || !llc_dgram_match(sap, laddr, rc))) { diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index df7f1df00330..d767e35fff6b 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -127,7 +127,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, daddr, dport, in->ifindex); - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in @@ -197,7 +197,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, daddr, ntohs(dport), in->ifindex); - if (sk && !atomic_inc_not_zero(&sk->sk_refcnt)) + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; /* NOTE: we return listeners even if bound to * 0.0.0.0, those are filtered out in diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 8ced52e91181..5acee49db90b 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -575,7 +575,7 @@ static void netlink_remove(struct sock *sk) table = &nl_table[sk->sk_protocol]; if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, netlink_rhashtable_params)) { - WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } @@ -691,7 +691,7 @@ static void deferred_put_nlk_sk(struct rcu_head *head) struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); struct sock *sk = &nlk->sk; - if (!atomic_dec_and_test(&sk->sk_refcnt)) + if (!refcount_dec_and_test(&sk->sk_refcnt)) return; if (nlk->cb_running && nlk->cb.done) { @@ -2568,7 +2568,7 @@ static int netlink_seq_show(struct seq_file *seq, void *v) sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), nlk->cb_running, - atomic_read(&s->sk_refcnt), + refcount_read(&s->sk_refcnt), atomic_read(&s->sk_drops), sock_i_ino(s) ); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 90fd38d5c458..643302b37b48 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4495,7 +4495,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, - atomic_read(&s->sk_refcnt), + refcount_read(&s->sk_refcnt), s->sk_type, ntohs(po->num), po->ifindex, diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 29c7f754c70d..1b050dd17393 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -614,7 +614,7 @@ static int pn_sock_seq_show(struct seq_file *seq, void *v) sk_wmem_alloc_get(sk), sk_rmem_alloc_get(sk), from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)), sock_i_ino(sk), - atomic_read(&sk->sk_refcnt), sk, + refcount_read(&sk->sk_refcnt), sk, atomic_read(&sk->sk_drops)); } seq_pad(seq, '\n'); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index f1299f54627a..a2ad4482376f 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -747,7 +747,7 @@ static int rxrpc_release_sock(struct sock *sk) { struct rxrpc_sock *rx = rxrpc_sk(sk); - _enter("%p{%d,%d}", sk, sk->sk_state, atomic_read(&sk->sk_refcnt)); + _enter("%p{%d,%d}", sk, sk->sk_state, refcount_read(&sk->sk_refcnt)); /* declare the socket closed for business */ sock_orphan(sk); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index eb0e9bab54c1..d6e97115500b 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -340,7 +340,7 @@ META_COLLECTOR(int_sk_refcnt) *err = -1; return; } - dst->value = atomic_read(&skb->sk->sk_refcnt); + dst->value = refcount_read(&skb->sk->sk_refcnt); } META_COLLECTOR(int_sk_rcvbuf) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1b92b72e812f..101e3597338f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2313,7 +2313,7 @@ static void tipc_sk_remove(struct tipc_sock *tsk) struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id); if (!rhashtable_remove_fast(&tn->sk_rht, &tsk->node, tsk_rht_params)) { - WARN_ON(atomic_read(&sk->sk_refcnt) == 1); + WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 7c2e21ebbedc..c88525403d2e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2847,7 +2847,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%pK: %08X %08X %08X %04X %02X %5lu", s, - atomic_read(&s->sk_refcnt), + refcount_read(&s->sk_refcnt), 0, s->sk_state == TCP_LISTEN ? __SO_ACCEPTCON : 0, s->sk_type, -- cgit v1.2.3 From 8c9814b97002f61846ebf3048e8df5aae52f7828 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:08:05 +0300 Subject: net: convert unix_address.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/af_unix.h | 3 ++- net/unix/af_unix.c | 8 ++++---- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index fd60eccb59a6..3a385e4767f0 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -4,6 +4,7 @@ #include #include #include +#include #include void unix_inflight(struct user_struct *user, struct file *fp); @@ -21,7 +22,7 @@ extern spinlock_t unix_table_lock; extern struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; struct unix_address { - atomic_t refcnt; + refcount_t refcnt; int len; unsigned int hash; struct sockaddr_un name[0]; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c88525403d2e..b9ee766054f6 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -212,7 +212,7 @@ EXPORT_SYMBOL_GPL(unix_peer_get); static inline void unix_release_addr(struct unix_address *addr) { - if (atomic_dec_and_test(&addr->refcnt)) + if (refcount_dec_and_test(&addr->refcnt)) kfree(addr); } @@ -864,7 +864,7 @@ static int unix_autobind(struct socket *sock) goto out; addr->name->sun_family = AF_UNIX; - atomic_set(&addr->refcnt, 1); + refcount_set(&addr->refcnt, 1); retry: addr->len = sprintf(addr->name->sun_path+1, "%05x", ordernum) + 1 + sizeof(short); @@ -1040,7 +1040,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) memcpy(addr->name, sunaddr, addr_len); addr->len = addr_len; addr->hash = hash ^ sk->sk_type; - atomic_set(&addr->refcnt, 1); + refcount_set(&addr->refcnt, 1); if (sun_path[0]) { addr->hash = UNIX_HASH_SIZE; @@ -1335,7 +1335,7 @@ restart: /* copy address information from listening to new sock*/ if (otheru->addr) { - atomic_inc(&otheru->addr->refcnt); + refcount_inc(&otheru->addr->refcnt); newu->addr = otheru->addr; } if (otheru->path.dentry) { -- cgit v1.2.3 From 717d1e993ad8d24a711775d8f2afbcdc76a520a1 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:08:06 +0300 Subject: net: convert fib_rule.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/fib_rules.h | 7 ++++--- net/core/fib_rules.c | 4 ++-- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 76c7300626d6..c487bfa2f479 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -29,7 +30,7 @@ struct fib_rule { struct fib_rule __rcu *ctarget; struct net *fr_net; - atomic_t refcnt; + refcount_t refcnt; u32 pref; int suppress_ifgroup; int suppress_prefixlen; @@ -103,12 +104,12 @@ struct fib_rules_ops { static inline void fib_rule_get(struct fib_rule *rule) { - atomic_inc(&rule->refcnt); + refcount_inc(&rule->refcnt); } static inline void fib_rule_put(struct fib_rule *rule) { - if (atomic_dec_and_test(&rule->refcnt)) + if (refcount_dec_and_test(&rule->refcnt)) kfree_rcu(rule, rcu); } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3bba291c6c32..c4ecd9f75a47 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -46,7 +46,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, if (r == NULL) return -ENOMEM; - atomic_set(&r->refcnt, 1); + refcount_set(&r->refcnt, 1); r->action = FR_ACT_TO_TBL; r->pref = pref; r->table = table; @@ -283,7 +283,7 @@ jumped: if (err != -EAGAIN) { if ((arg->flags & FIB_LOOKUP_NOREF) || - likely(atomic_inc_not_zero(&rule->refcnt))) { + likely(refcount_inc_not_zero(&rule->refcnt))) { arg->rule = rule; goto out; } -- cgit v1.2.3 From edcb691871b27c3cc463b7291afe75f1c3423406 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:08:07 +0300 Subject: net: convert inet_frag_queue.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/inet_frag.h | 4 ++-- net/ipv4/inet_fragment.c | 14 +++++++------- net/ipv4/ip_fragment.c | 2 +- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 975779d0e7b0..440c1e9d0623 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -50,7 +50,7 @@ struct inet_frag_queue { spinlock_t lock; struct timer_list timer; struct hlist_node list; - atomic_t refcnt; + refcount_t refcnt; struct sk_buff *fragments; struct sk_buff *fragments_tail; ktime_t stamp; @@ -129,7 +129,7 @@ void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q, static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f) { - if (atomic_dec_and_test(&q->refcnt)) + if (refcount_dec_and_test(&q->refcnt)) inet_frag_destroy(q, f); } diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index b5e9317eaf9e..96e95e83cc61 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -276,11 +276,11 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) { if (del_timer(&fq->timer)) - atomic_dec(&fq->refcnt); + refcount_dec(&fq->refcnt); if (!(fq->flags & INET_FRAG_COMPLETE)) { fq_unlink(fq, f); - atomic_dec(&fq->refcnt); + refcount_dec(&fq->refcnt); } } EXPORT_SYMBOL(inet_frag_kill); @@ -329,7 +329,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, */ hlist_for_each_entry(qp, &hb->chain, list) { if (qp->net == nf && f->match(qp, arg)) { - atomic_inc(&qp->refcnt); + refcount_inc(&qp->refcnt); spin_unlock(&hb->chain_lock); qp_in->flags |= INET_FRAG_COMPLETE; inet_frag_put(qp_in, f); @@ -339,9 +339,9 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, #endif qp = qp_in; if (!mod_timer(&qp->timer, jiffies + nf->timeout)) - atomic_inc(&qp->refcnt); + refcount_inc(&qp->refcnt); - atomic_inc(&qp->refcnt); + refcount_inc(&qp->refcnt); hlist_add_head(&qp->list, &hb->chain); spin_unlock(&hb->chain_lock); @@ -370,7 +370,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); - atomic_set(&q->refcnt, 1); + refcount_set(&q->refcnt, 1); return q; } @@ -405,7 +405,7 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, spin_lock(&hb->chain_lock); hlist_for_each_entry(q, &hb->chain, list) { if (q->net == nf && f->match(q, key)) { - atomic_inc(&q->refcnt); + refcount_inc(&q->refcnt); spin_unlock(&hb->chain_lock); return q; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b3cdeec85f1f..9a8cfac503dc 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -312,7 +312,7 @@ static int ip_frag_reinit(struct ipq *qp) unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) { - atomic_inc(&qp->q.refcnt); + refcount_inc(&qp->q.refcnt); return -ETIMEDOUT; } -- cgit v1.2.3 From c122e14df2d64311d1f0c0bbf4d8f42a7a8baf41 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:08:08 +0300 Subject: net: convert net.passive from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/net_namespace.h | 3 ++- net/core/net-sysfs.c | 2 +- net/core/net_namespace.c | 4 ++-- 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index a24a57593202..31a2b51bef2c 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -5,6 +5,7 @@ #define __NET_NET_NAMESPACE_H #include +#include #include #include #include @@ -46,7 +47,7 @@ struct netns_ipvs; #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) struct net { - atomic_t passive; /* To decided when the network + refcount_t passive; /* To decided when the network * namespace should be freed. */ atomic_t count; /* To decided when the network diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index fe7e145c543c..b4f9922b6f23 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1448,7 +1448,7 @@ static void *net_grab_current_ns(void) struct net *ns = current->nsproxy->net_ns; #ifdef CONFIG_NET_NS if (ns) - atomic_inc(&ns->passive); + refcount_inc(&ns->passive); #endif return ns; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6a2f41288249..8726d051f31d 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -284,7 +284,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) LIST_HEAD(net_exit_list); atomic_set(&net->count, 1); - atomic_set(&net->passive, 1); + refcount_set(&net->passive, 1); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); @@ -380,7 +380,7 @@ static void net_free(struct net *net) void net_drop_ns(void *p) { struct net *ns = p; - if (ns && atomic_dec_and_test(&ns->passive)) + if (ns && refcount_dec_and_test(&ns->passive)) net_free(ns); } -- cgit v1.2.3 From b4217b82893c23f9f45f77914b5aa3b662b75332 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Fri, 30 Jun 2017 13:08:09 +0300 Subject: net: convert netlbl_lsm_cache.refcount from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/netlabel.h | 8 ++++---- net/ipv4/cipso_ipv4.c | 4 ++-- net/ipv6/calipso.c | 4 ++-- 3 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/netlabel.h b/include/net/netlabel.h index efe98068880f..72d6435fc16c 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -37,7 +37,7 @@ #include #include #include -#include +#include struct cipso_v4_doi; struct calipso_doi; @@ -136,7 +136,7 @@ struct netlbl_audit { * */ struct netlbl_lsm_cache { - atomic_t refcount; + refcount_t refcount; void (*free) (const void *data); void *data; }; @@ -295,7 +295,7 @@ static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc(gfp_t flags) cache = kzalloc(sizeof(*cache), flags); if (cache) - atomic_set(&cache->refcount, 1); + refcount_set(&cache->refcount, 1); return cache; } @@ -309,7 +309,7 @@ static inline struct netlbl_lsm_cache *netlbl_secattr_cache_alloc(gfp_t flags) */ static inline void netlbl_secattr_cache_free(struct netlbl_lsm_cache *cache) { - if (!atomic_dec_and_test(&cache->refcount)) + if (!refcount_dec_and_test(&cache->refcount)) return; if (cache->free) diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index ae206163c273..c2044775ae7d 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -265,7 +265,7 @@ static int cipso_v4_cache_check(const unsigned char *key, entry->key_len == key_len && memcmp(entry->key, key, key_len) == 0) { entry->activity += 1; - atomic_inc(&entry->lsm_data->refcount); + refcount_inc(&entry->lsm_data->refcount); secattr->cache = entry->lsm_data; secattr->flags |= NETLBL_SECATTR_CACHE; secattr->type = NETLBL_NLTYPE_CIPSOV4; @@ -332,7 +332,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr, } entry->key_len = cipso_ptr_len; entry->hash = cipso_v4_map_cache_hash(cipso_ptr, cipso_ptr_len); - atomic_inc(&secattr->cache->refcount); + refcount_inc(&secattr->cache->refcount); entry->lsm_data = secattr->cache; bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1); diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 8d772fea1dde..44067521e7cd 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -227,7 +227,7 @@ static int calipso_cache_check(const unsigned char *key, entry->key_len == key_len && memcmp(entry->key, key, key_len) == 0) { entry->activity += 1; - atomic_inc(&entry->lsm_data->refcount); + refcount_inc(&entry->lsm_data->refcount); secattr->cache = entry->lsm_data; secattr->flags |= NETLBL_SECATTR_CACHE; secattr->type = NETLBL_NLTYPE_CALIPSO; @@ -296,7 +296,7 @@ static int calipso_cache_add(const unsigned char *calipso_ptr, } entry->key_len = calipso_ptr_len; entry->hash = calipso_map_cache_hash(calipso_ptr, calipso_ptr_len); - atomic_inc(&secattr->cache->refcount); + refcount_inc(&secattr->cache->refcount); entry->lsm_data = secattr->cache; bkt = entry->hash & (CALIPSO_CACHE_BUCKETS - 1); -- cgit v1.2.3 From d643a75ac2bcc559994405d29c50ed086aeae434 Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 29 Jun 2017 22:08:11 +0200 Subject: net: switchdev: add SET_SWITCHDEV_OPS helper Add a helper to allow switchdev ops to be set if NET_SWITCHDEV is configured and do nothing otherwise. This allows for slightly cleaner code which uses switchdev but does not select NET_SWITCHDEV. Signed-off-by: Simon Horman Acked-by: Ivan Vecera Signed-off-by: David S. Miller --- include/net/switchdev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index c784a6ac6ef1..8ae9e3b6392e 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -217,6 +217,8 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b); + +#define SWITCHDEV_SET_OPS(netdev, ops) ((netdev)->switchdev_ops = (ops)) #else static inline void switchdev_deferred_process(void) @@ -322,6 +324,8 @@ static inline bool switchdev_port_same_parent_id(struct net_device *a, return false; } +#define SWITCHDEV_SET_OPS(netdev, ops) do {} while (0) + #endif #endif /* _LINUX_SWITCHDEV_H_ */ -- cgit v1.2.3 From 922dbc5be2186659d2c453a53f2ae569e55b6101 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 30 Jun 2017 11:52:13 +0800 Subject: sctp: remove the typedef sctp_chunkhdr_t This patch is to remove the typedef sctp_chunkhdr_t, and replace with struct sctp_chunkhdr in the places where it's using this typedef. It is also to fix some indents and use sizeof(variable) instead of sizeof(type)., especially in sctp_new. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 34 ++++++++--------- include/net/sctp/sctp.h | 2 +- net/netfilter/ipvs/ip_vs_core.c | 4 +- net/netfilter/ipvs/ip_vs_proto_sctp.c | 6 +-- net/netfilter/nf_conntrack_proto_sctp.c | 29 +++++++------- net/netfilter/xt_sctp.c | 4 +- net/sctp/input.c | 20 +++++----- net/sctp/inqueue.c | 15 ++++---- net/sctp/sm_make_chunk.c | 17 +++++---- net/sctp/sm_sideeffect.c | 5 ++- net/sctp/sm_statefuns.c | 67 +++++++++++++++++---------------- net/sctp/ulpevent.c | 2 +- 12 files changed, 102 insertions(+), 103 deletions(-) (limited to 'include/net') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 85540ec4b561..9ad5b9e8df78 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -70,11 +70,11 @@ static inline struct sctphdr *sctp_hdr(const struct sk_buff *skb) } /* Section 3.2. Chunk Field Descriptions. */ -typedef struct sctp_chunkhdr { +struct sctp_chunkhdr { __u8 type; __u8 flags; __be16 length; -} sctp_chunkhdr_t; +}; /* Section 3.2. Chunk Type Values. @@ -236,8 +236,8 @@ typedef struct sctp_datahdr { } sctp_datahdr_t; typedef struct sctp_data_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_datahdr_t data_hdr; + struct sctp_chunkhdr chunk_hdr; + sctp_datahdr_t data_hdr; } sctp_data_chunk_t; /* DATA Chuck Specific Flags */ @@ -267,7 +267,7 @@ typedef struct sctp_inithdr { } sctp_inithdr_t; typedef struct sctp_init_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_inithdr_t init_hdr; } sctp_init_chunk_t; @@ -386,7 +386,7 @@ typedef struct sctp_sackhdr { } sctp_sackhdr_t; typedef struct sctp_sack_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_sackhdr_t sack_hdr; } sctp_sack_chunk_t; @@ -403,7 +403,7 @@ typedef struct sctp_heartbeathdr { } sctp_heartbeathdr_t; typedef struct sctp_heartbeat_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_heartbeathdr_t hb_hdr; } sctp_heartbeat_chunk_t; @@ -413,7 +413,7 @@ typedef struct sctp_heartbeat_chunk { * chunk descriptor. */ typedef struct sctp_abort_chunk { - sctp_chunkhdr_t uh; + struct sctp_chunkhdr uh; } sctp_abort_chunk_t; @@ -425,8 +425,8 @@ typedef struct sctp_shutdownhdr { } sctp_shutdownhdr_t; struct sctp_shutdown_chunk_t { - sctp_chunkhdr_t chunk_hdr; - sctp_shutdownhdr_t shutdown_hdr; + struct sctp_chunkhdr chunk_hdr; + sctp_shutdownhdr_t shutdown_hdr; }; /* RFC 2960. Section 3.3.10 Operation Error (ERROR) (9) */ @@ -438,8 +438,8 @@ typedef struct sctp_errhdr { } sctp_errhdr_t; typedef struct sctp_operr_chunk { - sctp_chunkhdr_t chunk_hdr; - sctp_errhdr_t err_hdr; + struct sctp_chunkhdr chunk_hdr; + sctp_errhdr_t err_hdr; } sctp_operr_chunk_t; /* RFC 2960 3.3.10 - Operation Error @@ -528,7 +528,7 @@ typedef struct sctp_ecnehdr { } sctp_ecnehdr_t; typedef struct sctp_ecne_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_ecnehdr_t ence_hdr; } sctp_ecne_chunk_t; @@ -540,7 +540,7 @@ typedef struct sctp_cwrhdr { } sctp_cwrhdr_t; typedef struct sctp_cwr_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_cwrhdr_t cwr_hdr; } sctp_cwr_chunk_t; @@ -649,7 +649,7 @@ typedef struct sctp_addiphdr { } sctp_addiphdr_t; typedef struct sctp_addip_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_addiphdr_t addip_hdr; } sctp_addip_chunk_t; @@ -709,7 +709,7 @@ typedef struct sctp_authhdr { } sctp_authhdr_t; typedef struct sctp_auth_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; sctp_authhdr_t auth_hdr; } sctp_auth_chunk_t; @@ -719,7 +719,7 @@ struct sctp_infox { }; struct sctp_reconf_chunk { - sctp_chunkhdr_t chunk_hdr; + struct sctp_chunkhdr chunk_hdr; __u8 params[0]; }; diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 069582ee5d7f..d756bd095683 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -478,7 +478,7 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length)) #define _sctp_walk_errors(err, chunk_hdr, end)\ for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \ - sizeof(sctp_chunkhdr_t));\ + sizeof(struct sctp_chunkhdr));\ (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\ ntohs(err->length) >= sizeof(sctp_errhdr_t); \ err = (sctp_errhdr_t *)((void *)err + SCTP_PAD4(ntohs(err->length)))) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 6f39af9fd6df..e31956b58aba 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1037,7 +1037,7 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, */ static inline int is_sctp_abort(const struct sk_buff *skb, int nh_len) { - sctp_chunkhdr_t *sch, schunk; + struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, nh_len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) @@ -1070,7 +1070,7 @@ static inline bool is_new_conn(const struct sk_buff *skb, return th->syn; } case IPPROTO_SCTP: { - sctp_chunkhdr_t *sch, schunk; + struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, iph->len + sizeof(struct sctphdr), sizeof(schunk), &schunk); diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 6b38cadab822..3ffad4adaddf 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -15,7 +15,7 @@ sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_iphdr *iph) { struct ip_vs_service *svc; - sctp_chunkhdr_t _schunkh, *sch; + struct sctp_chunkhdr _schunkh, *sch; struct sctphdr *sh, _sctph; __be16 _ports[2], *ports = NULL; @@ -377,7 +377,7 @@ static inline void set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, const struct sk_buff *skb) { - sctp_chunkhdr_t _sctpch, *sch; + struct sctp_chunkhdr _sctpch, *sch; unsigned char chunk_type; int event, next_state; int ihl, cofs; @@ -409,7 +409,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, (sch->type == SCTP_CID_COOKIE_ACK)) { int clen = ntohs(sch->length); - if (clen >= sizeof(sctp_chunkhdr_t)) { + if (clen >= sizeof(_sctpch)) { sch = skb_header_pointer(skb, cofs + ALIGN(clen, 4), sizeof(_sctpch), &_sctpch); if (sch && sch->type == SCTP_CID_ABORT) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index db87af41c342..b841a8aeee7c 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -202,7 +202,7 @@ static int do_basic_checks(struct nf_conn *ct, unsigned long *map) { u_int32_t offset, count; - sctp_chunkhdr_t _sch, *sch; + struct sctp_chunkhdr _sch, *sch; int flag; flag = 0; @@ -397,7 +397,7 @@ static int sctp_packet(struct nf_conn *ct, sch->type == SCTP_CID_INIT_ACK) { sctp_inithdr_t _inithdr, *ih; - ih = skb_header_pointer(skb, offset + sizeof(sctp_chunkhdr_t), + ih = skb_header_pointer(skb, offset + sizeof(_sch), sizeof(_inithdr), &_inithdr); if (ih == NULL) goto out_unlock; @@ -471,23 +471,20 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, /* Copy the vtag into the state info */ if (sch->type == SCTP_CID_INIT) { - if (sh->vtag == 0) { - sctp_inithdr_t _inithdr, *ih; + sctp_inithdr_t _inithdr, *ih; + /* Sec 8.5.1 (A) */ + if (sh->vtag) + return false; - ih = skb_header_pointer(skb, offset + sizeof(sctp_chunkhdr_t), - sizeof(_inithdr), &_inithdr); - if (ih == NULL) - return false; + ih = skb_header_pointer(skb, offset + sizeof(_sch), + sizeof(_inithdr), &_inithdr); + if (!ih) + return false; - pr_debug("Setting vtag %x for new conn\n", - ih->init_tag); + pr_debug("Setting vtag %x for new conn\n", + ih->init_tag); - ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = - ih->init_tag; - } else { - /* Sec 8.5.1 (A) */ - return false; - } + ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag; } else if (sch->type == SCTP_CID_HEARTBEAT) { pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index 0f20ea4f511e..2d2fa1d53ea6 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -42,8 +42,8 @@ match_packet(const struct sk_buff *skb, bool *hotdrop) { u_int32_t chunkmapcopy[256 / sizeof (u_int32_t)]; - const sctp_chunkhdr_t *sch; - sctp_chunkhdr_t _sch; + const struct sctp_chunkhdr *sch; + struct sctp_chunkhdr _sch; int chunk_match_type = info->chunk_match_type; const struct xt_sctp_flag_info *flag_info = info->flag_info; int flag_count = info->flag_count; diff --git a/net/sctp/input.c b/net/sctp/input.c index ba9ad32fc447..a9994c4afc18 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -663,19 +663,19 @@ out_unlock: */ static int sctp_rcv_ootb(struct sk_buff *skb) { - sctp_chunkhdr_t *ch, _ch; + struct sctp_chunkhdr *ch, _ch; int ch_end, offset = 0; /* Scan through all the chunks in the packet. */ do { /* Make sure we have at least the header there */ - if (offset + sizeof(sctp_chunkhdr_t) > skb->len) + if (offset + sizeof(_ch) > skb->len) break; ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch); /* Break out if chunk length is less then minimal. */ - if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) + if (ntohs(ch->length) < sizeof(_ch)) break; ch_end = offset + SCTP_PAD4(ntohs(ch->length)); @@ -1106,7 +1106,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, */ static struct sctp_association *__sctp_rcv_asconf_lookup( struct net *net, - sctp_chunkhdr_t *ch, + struct sctp_chunkhdr *ch, const union sctp_addr *laddr, __be16 peer_port, struct sctp_transport **transportp) @@ -1144,7 +1144,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, struct sctp_transport **transportp) { struct sctp_association *asoc = NULL; - sctp_chunkhdr_t *ch; + struct sctp_chunkhdr *ch; int have_auth = 0; unsigned int chunk_num = 1; __u8 *ch_end; @@ -1152,10 +1152,10 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, /* Walk through the chunks looking for AUTH or ASCONF chunks * to help us find the association. */ - ch = (sctp_chunkhdr_t *) skb->data; + ch = (struct sctp_chunkhdr *)skb->data; do { /* Break out if chunk length is less then minimal. */ - if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) + if (ntohs(ch->length) < sizeof(*ch)) break; ch_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); @@ -1192,7 +1192,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, if (asoc) break; - ch = (sctp_chunkhdr_t *) ch_end; + ch = (struct sctp_chunkhdr *)ch_end; chunk_num++; } while (ch_end < skb_tail_pointer(skb)); @@ -1210,7 +1210,7 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, const union sctp_addr *laddr, struct sctp_transport **transportp) { - sctp_chunkhdr_t *ch; + struct sctp_chunkhdr *ch; /* We do not allow GSO frames here as we need to linearize and * then cannot guarantee frame boundaries. This shouldn't be an @@ -1220,7 +1220,7 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) return NULL; - ch = (sctp_chunkhdr_t *) skb->data; + ch = (struct sctp_chunkhdr *)skb->data; /* The code below will attempt to walk the chunk and extract * parameter information. Before we do that, we need to verify diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index f731de3e8428..48392552ee7c 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -99,7 +99,7 @@ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) struct sctp_chunkhdr *sctp_inq_peek(struct sctp_inq *queue) { struct sctp_chunk *chunk; - sctp_chunkhdr_t *ch = NULL; + struct sctp_chunkhdr *ch = NULL; chunk = queue->in_progress; /* If there is no more chunks in this packet, say so */ @@ -108,7 +108,7 @@ struct sctp_chunkhdr *sctp_inq_peek(struct sctp_inq *queue) chunk->pdiscard) return NULL; - ch = (sctp_chunkhdr_t *)chunk->chunk_end; + ch = (struct sctp_chunkhdr *)chunk->chunk_end; return ch; } @@ -122,7 +122,7 @@ struct sctp_chunkhdr *sctp_inq_peek(struct sctp_inq *queue) struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) { struct sctp_chunk *chunk; - sctp_chunkhdr_t *ch = NULL; + struct sctp_chunkhdr *ch = NULL; /* The assumption is that we are safe to process the chunks * at this time. @@ -151,7 +151,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) chunk = queue->in_progress = NULL; } else { /* Nothing to do. Next chunk in the packet, please. */ - ch = (sctp_chunkhdr_t *) chunk->chunk_end; + ch = (struct sctp_chunkhdr *)chunk->chunk_end; /* Force chunk->skb->data to chunk->chunk_end. */ skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data); /* We are guaranteed to pull a SCTP header. */ @@ -195,7 +195,7 @@ next_chunk: new_skb: /* This is the first chunk in the packet. */ - ch = (sctp_chunkhdr_t *) chunk->skb->data; + ch = (struct sctp_chunkhdr *)chunk->skb->data; chunk->singleton = 1; chunk->data_accepted = 0; chunk->pdiscard = 0; @@ -214,11 +214,10 @@ new_skb: chunk->chunk_hdr = ch; chunk->chunk_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); - skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t)); + skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - if (chunk->chunk_end + sizeof(sctp_chunkhdr_t) < - skb_tail_pointer(chunk->skb)) { + if (chunk->chunk_end + sizeof(*ch) < skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 4b1967997c16..7d4c5a870f0e 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1379,20 +1379,20 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, gfp_t gfp) { struct sctp_chunk *retval; - sctp_chunkhdr_t *chunk_hdr; + struct sctp_chunkhdr *chunk_hdr; struct sk_buff *skb; struct sock *sk; /* No need to allocate LL here, as this is only a chunk. */ - skb = alloc_skb(SCTP_PAD4(sizeof(sctp_chunkhdr_t) + paylen), gfp); + skb = alloc_skb(SCTP_PAD4(sizeof(*chunk_hdr) + paylen), gfp); if (!skb) goto nodata; /* Make room for the chunk header. */ - chunk_hdr = skb_put(skb, sizeof(sctp_chunkhdr_t)); + chunk_hdr = (struct sctp_chunkhdr *)skb_put(skb, sizeof(*chunk_hdr)); chunk_hdr->type = type; chunk_hdr->flags = flags; - chunk_hdr->length = htons(sizeof(sctp_chunkhdr_t)); + chunk_hdr->length = htons(sizeof(*chunk_hdr)); sk = asoc ? asoc->base.sk : NULL; retval = sctp_chunkify(skb, asoc, sk, gfp); @@ -1402,7 +1402,7 @@ static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, } retval->chunk_hdr = chunk_hdr; - retval->chunk_end = ((__u8 *)chunk_hdr) + sizeof(struct sctp_chunkhdr); + retval->chunk_end = ((__u8 *)chunk_hdr) + sizeof(*chunk_hdr); /* Determine if the chunk needs to be authenticated */ if (sctp_auth_send_cid(type, asoc)) @@ -1710,7 +1710,7 @@ struct sctp_association *sctp_unpack_cookie( /* Header size is static data prior to the actual cookie, including * any padding. */ - headersize = sizeof(sctp_chunkhdr_t) + + headersize = sizeof(struct sctp_chunkhdr) + (sizeof(struct sctp_signed_cookie) - sizeof(struct sctp_cookie)); bodysize = ntohs(chunk->chunk_hdr->length) - headersize; @@ -3218,7 +3218,8 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, int chunk_len; __u32 serial; - chunk_len = ntohs(asconf->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); + chunk_len = ntohs(asconf->chunk_hdr->length) - + sizeof(struct sctp_chunkhdr); hdr = (sctp_addiphdr_t *)asconf->skb->data; serial = ntohl(hdr->serial); @@ -3364,7 +3365,7 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, err_code = SCTP_ERROR_REQ_REFUSED; asconf_ack_len = ntohs(asconf_ack->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t); + sizeof(struct sctp_chunkhdr); /* Skip the addiphdr from the asconf_ack chunk and store a pointer to * the first asconf_ack parameter. diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index dfe1fcb520ba..b255339f22a3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -955,9 +955,10 @@ static void sctp_cmd_process_operr(sctp_cmd_seq_t *cmds, switch (err_hdr->cause) { case SCTP_ERROR_UNKNOWN_CHUNK: { - sctp_chunkhdr_t *unk_chunk_hdr; + struct sctp_chunkhdr *unk_chunk_hdr; - unk_chunk_hdr = (sctp_chunkhdr_t *)err_hdr->variable; + unk_chunk_hdr = (struct sctp_chunkhdr *) + err_hdr->variable; switch (unk_chunk_hdr->type) { /* ADDIP 4.1 A9) If the peer responds to an ASCONF with * an ERROR chunk reporting that it did not recognized diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 8feff96a5bef..2b7c07f19b08 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -235,7 +235,7 @@ sctp_disposition_t sctp_sf_do_4_C(struct net *net, return sctp_sf_violation_chunk(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN_COMPLETE chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -368,9 +368,9 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, if (err_chunk) { packet = sctp_abort_pkt_new(net, ep, asoc, arg, (__u8 *)(err_chunk->chunk_hdr) + - sizeof(sctp_chunkhdr_t), + sizeof(struct sctp_chunkhdr), ntohs(err_chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); sctp_chunk_free(err_chunk); @@ -417,7 +417,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, len = 0; if (err_chunk) len = ntohs(err_chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t); + sizeof(struct sctp_chunkhdr); repl = sctp_make_init_ack(new_asoc, chunk, GFP_ATOMIC, len); if (!repl) @@ -437,7 +437,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, */ unk_param = (sctp_unrecognized_param_t *) ((__u8 *)(err_chunk->chunk_hdr) + - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); /* Replace the cause code with the "Unrecognized parameter" * parameter type. */ @@ -540,9 +540,9 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, if (err_chunk) { packet = sctp_abort_pkt_new(net, ep, asoc, arg, (__u8 *)(err_chunk->chunk_hdr) + - sizeof(sctp_chunkhdr_t), + sizeof(struct sctp_chunkhdr), ntohs(err_chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); sctp_chunk_free(err_chunk); @@ -673,7 +673,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, * chunk header. More detailed verification is done * in sctp_unpack_cookie(). */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* If the endpoint is not listening or if the number of associations @@ -691,7 +691,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, chunk->subh.cookie_hdr = (struct sctp_signed_cookie *)chunk->skb->data; if (!pskb_pull(chunk->skb, ntohs(chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t))) + sizeof(struct sctp_chunkhdr))) goto nomem; /* 5.1 D) Upon reception of the COOKIE ECHO chunk, Endpoint @@ -770,9 +770,10 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, auth.skb = chunk->auth_chunk; auth.asoc = chunk->asoc; auth.sctp_hdr = chunk->sctp_hdr; - auth.chunk_hdr = skb_push(chunk->auth_chunk, - sizeof(sctp_chunkhdr_t)); - skb_pull(chunk->auth_chunk, sizeof(sctp_chunkhdr_t)); + auth.chunk_hdr = (struct sctp_chunkhdr *) + skb_push(chunk->auth_chunk, + sizeof(struct sctp_chunkhdr)); + skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); auth.transport = chunk->transport; ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); @@ -886,7 +887,7 @@ sctp_disposition_t sctp_sf_do_5_1E_ca(struct net *net, /* Verify that the chunk length for the COOKIE-ACK is OK. * If we don't do this, any bundled chunks may be junked. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -1099,7 +1100,7 @@ sctp_disposition_t sctp_sf_beat_8_3(struct net *net, */ chunk->subh.hb_hdr = (sctp_heartbeathdr_t *) chunk->skb->data; param_hdr = (sctp_paramhdr_t *) chunk->subh.hb_hdr; - paylen = ntohs(chunk->chunk_hdr->length) - sizeof(sctp_chunkhdr_t); + paylen = ntohs(chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr); if (ntohs(param_hdr->length) > paylen) return sctp_sf_violation_paramlen(net, ep, asoc, type, arg, @@ -1164,7 +1165,7 @@ sctp_disposition_t sctp_sf_backbeat_8_3(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the HEARTBEAT-ACK chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t) + + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr) + sizeof(sctp_sender_hb_info_t))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -1469,9 +1470,9 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( if (err_chunk) { packet = sctp_abort_pkt_new(net, ep, asoc, arg, (__u8 *)(err_chunk->chunk_hdr) + - sizeof(sctp_chunkhdr_t), + sizeof(struct sctp_chunkhdr), ntohs(err_chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); if (packet) { sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, @@ -1535,7 +1536,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( len = 0; if (err_chunk) { len = ntohs(err_chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t); + sizeof(struct sctp_chunkhdr); } repl = sctp_make_init_ack(new_asoc, chunk, GFP_ATOMIC, len); @@ -1556,7 +1557,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( */ unk_param = (sctp_unrecognized_param_t *) ((__u8 *)(err_chunk->chunk_hdr) + - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); /* Replace the cause code with the "Unrecognized parameter" * parameter type. */ @@ -2044,7 +2045,7 @@ sctp_disposition_t sctp_sf_do_5_2_4_dupcook(struct net *net, * enough for the chunk header. Cookie length verification is * done later. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -2053,7 +2054,7 @@ sctp_disposition_t sctp_sf_do_5_2_4_dupcook(struct net *net, */ chunk->subh.cookie_hdr = (struct sctp_signed_cookie *)chunk->skb->data; if (!pskb_pull(chunk->skb, ntohs(chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t))) + sizeof(struct sctp_chunkhdr))) goto nomem; /* In RFC 2960 5.2.4 3, if both Verification Tags in the State Cookie @@ -2806,7 +2807,7 @@ sctp_disposition_t sctp_sf_do_9_2_reshutack(struct net *net, struct sctp_chunk *reply; /* Make sure that the chunk has a valid length */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -3358,7 +3359,7 @@ sctp_disposition_t sctp_sf_do_9_2_final(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* Make sure that the SHUTDOWN_ACK chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* 10.2 H) SHUTDOWN COMPLETE notification @@ -3435,7 +3436,7 @@ sctp_disposition_t sctp_sf_ootb(struct net *net, { struct sctp_chunk *chunk = arg; struct sk_buff *skb = chunk->skb; - sctp_chunkhdr_t *ch; + struct sctp_chunkhdr *ch; sctp_errhdr_t *err; __u8 *ch_end; int ootb_shut_ack = 0; @@ -3443,10 +3444,10 @@ sctp_disposition_t sctp_sf_ootb(struct net *net, SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); - ch = (sctp_chunkhdr_t *) chunk->chunk_hdr; + ch = (struct sctp_chunkhdr *)chunk->chunk_hdr; do { /* Report violation if the chunk is less then minimal */ - if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) + if (ntohs(ch->length) < sizeof(*ch)) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -3487,7 +3488,7 @@ sctp_disposition_t sctp_sf_ootb(struct net *net, } } - ch = (sctp_chunkhdr_t *) ch_end; + ch = (struct sctp_chunkhdr *)ch_end; } while (ch_end < skb_tail_pointer(skb)); if (ootb_shut_ack) @@ -3560,7 +3561,7 @@ static sctp_disposition_t sctp_sf_shut_8_4_5(struct net *net, /* If the chunk length is invalid, we don't want to process * the reset of the packet. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* We need to discard the rest of the packet to prevent @@ -3591,7 +3592,7 @@ sctp_disposition_t sctp_sf_do_8_5_1_E_sa(struct net *net, struct sctp_chunk *chunk = arg; /* Make sure that the SHUTDOWN_ACK chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -4256,7 +4257,7 @@ sctp_disposition_t sctp_sf_unk_chunk(struct net *net, { struct sctp_chunk *unk_chunk = arg; struct sctp_chunk *err_chunk; - sctp_chunkhdr_t *hdr; + struct sctp_chunkhdr *hdr; pr_debug("%s: processing unknown chunk id:%d\n", __func__, type.chunk); @@ -4267,7 +4268,7 @@ sctp_disposition_t sctp_sf_unk_chunk(struct net *net, * Since we don't know the chunk type, we use a general * chunkhdr structure to make a comparison. */ - if (!sctp_chunk_length_valid(unk_chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(unk_chunk, sizeof(*hdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -4340,7 +4341,7 @@ sctp_disposition_t sctp_sf_discard_chunk(struct net *net, * Since we don't know the chunk type, we use a general * chunkhdr structure to make a comparison. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -4405,7 +4406,7 @@ sctp_disposition_t sctp_sf_violation(struct net *net, struct sctp_chunk *chunk = arg; /* Make sure that the chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_chunkhdr_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 17854fb0e512..5f86c5062a98 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -158,7 +158,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_assoc_change( /* Trim the buffer to the right length. */ skb_trim(skb, sizeof(struct sctp_assoc_change) + ntohs(chunk->chunk_hdr->length) - - sizeof(sctp_chunkhdr_t)); + sizeof(struct sctp_chunkhdr)); } else { event = sctp_ulpevent_new(sizeof(struct sctp_assoc_change), MSG_NOTIFICATION, gfp); -- cgit v1.2.3 From 6d85e68f4cde48f8c2fac6d9c00ca6988cf6e327 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 30 Jun 2017 11:52:14 +0800 Subject: sctp: remove the typedef sctp_cid_t This patch is to remove the typedef sctp_cid_t, and replace with struct sctp_cid in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- include/net/sctp/auth.h | 6 ++++-- include/net/sctp/constants.h | 4 ++-- include/net/sctp/structs.h | 2 +- net/sctp/auth.c | 6 +++--- net/sctp/sm_make_chunk.c | 4 ++-- net/sctp/sm_statetable.c | 4 ++-- 7 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include/net') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 9ad5b9e8df78..6d7b8846c607 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -82,7 +82,7 @@ struct sctp_chunkhdr { * Value field. It takes a value from 0 to 254. The value of 255 is * reserved for future use as an extension field. */ -typedef enum { +enum sctp_cid { SCTP_CID_DATA = 0, SCTP_CID_INIT = 1, SCTP_CID_INIT_ACK = 2, @@ -109,7 +109,7 @@ typedef enum { SCTP_CID_ASCONF = 0xC1, SCTP_CID_ASCONF_ACK = 0x80, SCTP_CID_RECONF = 0x82, -} sctp_cid_t; /* enum */ +}; /* enum */ /* Section 3.2 diff --git a/include/net/sctp/auth.h b/include/net/sctp/auth.h index 9b9fb122b31f..171244bd856f 100644 --- a/include/net/sctp/auth.h +++ b/include/net/sctp/auth.h @@ -97,8 +97,10 @@ void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc, struct sctp_hmac_algo_param *hmacs); int sctp_auth_asoc_verify_hmac_id(const struct sctp_association *asoc, __be16 hmac_id); -int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc); -int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc); +int sctp_auth_send_cid(enum sctp_cid chunk, + const struct sctp_association *asoc); +int sctp_auth_recv_cid(enum sctp_cid chunk, + const struct sctp_association *asoc); void sctp_auth_calculate_hmac(const struct sctp_association *asoc, struct sk_buff *skb, struct sctp_auth_chunk *auth, gfp_t gfp); diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index b07a745ab69f..02e867bc4b43 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -130,7 +130,7 @@ typedef enum { */ typedef union { - sctp_cid_t chunk; + enum sctp_cid chunk; sctp_event_timeout_t timeout; sctp_event_other_t other; sctp_event_primitive_t primitive; @@ -141,7 +141,7 @@ static inline sctp_subtype_t \ SCTP_ST_## _name (_type _arg) \ { sctp_subtype_t _retval; _retval._elt = _arg; return _retval; } -SCTP_SUBTYPE_CONSTRUCTOR(CHUNK, sctp_cid_t, chunk) +SCTP_SUBTYPE_CONSTRUCTOR(CHUNK, enum sctp_cid, chunk) SCTP_SUBTYPE_CONSTRUCTOR(TIMEOUT, sctp_event_timeout_t, timeout) SCTP_SUBTYPE_CONSTRUCTOR(OTHER, sctp_event_other_t, other) SCTP_SUBTYPE_CONSTRUCTOR(PRIMITIVE, sctp_event_primitive_t, primitive) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index e26763bfabd6..9e9605ecb5c9 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1297,7 +1297,7 @@ int sctp_has_association(struct net *net, const union sctp_addr *laddr, int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - sctp_cid_t, sctp_init_chunk_t *peer_init, + enum sctp_cid cid, sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk, struct sctp_chunk **err_chunk); int sctp_process_init(struct sctp_association *, struct sctp_chunk *chunk, const union sctp_addr *peer, diff --git a/net/sctp/auth.c b/net/sctp/auth.c index f99d4855d3de..7171dd3d6e40 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -632,7 +632,7 @@ void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc, /* Check to see if the given chunk is supposed to be authenticated */ -static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param) +static int __sctp_auth_cid(enum sctp_cid chunk, struct sctp_chunks_param *param) { unsigned short len; int found = 0; @@ -668,7 +668,7 @@ static int __sctp_auth_cid(sctp_cid_t chunk, struct sctp_chunks_param *param) } /* Check if peer requested that this chunk is authenticated */ -int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc) +int sctp_auth_send_cid(enum sctp_cid chunk, const struct sctp_association *asoc) { if (!asoc) return 0; @@ -680,7 +680,7 @@ int sctp_auth_send_cid(sctp_cid_t chunk, const struct sctp_association *asoc) } /* Check if we requested that peer authenticate this chunk. */ -int sctp_auth_recv_cid(sctp_cid_t chunk, const struct sctp_association *asoc) +int sctp_auth_recv_cid(enum sctp_cid chunk, const struct sctp_association *asoc) { if (!asoc) return 0; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 7d4c5a870f0e..78c3f214d608 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2123,7 +2123,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, union sctp_params param, - sctp_cid_t cid, + enum sctp_cid cid, struct sctp_chunk *chunk, struct sctp_chunk **err_chunk) { @@ -2240,7 +2240,7 @@ fallthrough: /* Verify the INIT packet before we process it. */ int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, - const struct sctp_association *asoc, sctp_cid_t cid, + const struct sctp_association *asoc, enum sctp_cid cid, sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk, struct sctp_chunk **errp) { diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 419b18ebb056..3e958c1c4b95 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -53,7 +53,7 @@ static const sctp_sm_table_entry_t timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES]; static const sctp_sm_table_entry_t *sctp_chunk_event_lookup(struct net *net, - sctp_cid_t cid, + enum sctp_cid cid, sctp_state_t state); @@ -968,7 +968,7 @@ static const sctp_sm_table_entry_t timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][S }; static const sctp_sm_table_entry_t *sctp_chunk_event_lookup(struct net *net, - sctp_cid_t cid, + enum sctp_cid cid, sctp_state_t state) { if (state > SCTP_STATE_MAX) -- cgit v1.2.3 From 3c9187049214127d3401926b033d05eb75d69c39 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 30 Jun 2017 11:52:16 +0800 Subject: sctp: remove the typedef sctp_paramhdr_t This patch is to remove the typedef sctp_paramhdr_t, and replace with struct sctp_paramhdr in the places where it's using this typedef. It is also to fix some indents and use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 44 +++++++++++++++++++++---------------------- include/net/sctp/sctp.h | 2 +- include/net/sctp/structs.h | 5 +++-- net/sctp/associola.c | 6 +++--- net/sctp/auth.c | 22 +++++++++++++--------- net/sctp/endpointola.c | 7 ++++--- net/sctp/sm_make_chunk.c | 47 +++++++++++++++++++++++----------------------- net/sctp/sm_statefuns.c | 6 +++--- net/sctp/socket.c | 7 ++++--- net/sctp/stream.c | 4 ++-- 10 files changed, 79 insertions(+), 71 deletions(-) (limited to 'include/net') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index ffdccb4da7e5..142bb6aa88eb 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -162,10 +162,10 @@ enum { SCTP_CHUNK_FLAG_T = 0x01 }; * Section 3.2.1 Optional/Variable-length Parmaeter Format. */ -typedef struct sctp_paramhdr { +struct sctp_paramhdr { __be16 type; __be16 length; -} sctp_paramhdr_t; +}; typedef enum { @@ -274,37 +274,37 @@ typedef struct sctp_init_chunk { /* Section 3.3.2.1. IPv4 Address Parameter (5) */ typedef struct sctp_ipv4addr_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; struct in_addr addr; } sctp_ipv4addr_param_t; /* Section 3.3.2.1. IPv6 Address Parameter (6) */ typedef struct sctp_ipv6addr_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; struct in6_addr addr; } sctp_ipv6addr_param_t; /* Section 3.3.2.1 Cookie Preservative (9) */ typedef struct sctp_cookie_preserve_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __be32 lifespan_increment; } sctp_cookie_preserve_param_t; /* Section 3.3.2.1 Host Name Address (11) */ typedef struct sctp_hostname_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; uint8_t hostname[0]; } sctp_hostname_param_t; /* Section 3.3.2.1 Supported Address Types (12) */ typedef struct sctp_supported_addrs_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __be16 types[0]; } sctp_supported_addrs_param_t; /* Appendix A. ECN Capable (32768) */ typedef struct sctp_ecn_capable_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; } sctp_ecn_capable_param_t; /* ADDIP Section 3.2.6 Adaptation Layer Indication */ @@ -321,19 +321,19 @@ typedef struct sctp_supported_ext_param { /* AUTH Section 3.1 Random */ typedef struct sctp_random_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u8 random_val[0]; } sctp_random_param_t; /* AUTH Section 3.2 Chunk List */ typedef struct sctp_chunks_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u8 chunks[0]; } sctp_chunks_param_t; /* AUTH Section 3.3 HMAC Algorithm */ typedef struct sctp_hmac_algo_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __be16 hmac_ids[0]; } sctp_hmac_algo_param_t; @@ -345,14 +345,14 @@ typedef sctp_init_chunk_t sctp_initack_chunk_t; /* Section 3.3.3.1 State Cookie (7) */ typedef struct sctp_cookie_param { - sctp_paramhdr_t p; + struct sctp_paramhdr p; __u8 body[0]; } sctp_cookie_param_t; /* Section 3.3.3.1 Unrecognized Parameters (8) */ typedef struct sctp_unrecognized_param { - sctp_paramhdr_t param_hdr; - sctp_paramhdr_t unrecognized; + struct sctp_paramhdr param_hdr; + struct sctp_paramhdr unrecognized; } sctp_unrecognized_param_t; @@ -399,7 +399,7 @@ typedef struct sctp_sack_chunk { */ typedef struct sctp_heartbeathdr { - sctp_paramhdr_t info; + struct sctp_paramhdr info; } sctp_heartbeathdr_t; typedef struct sctp_heartbeat_chunk { @@ -639,7 +639,7 @@ struct sctp_fwdtsn_chunk { * report status of ASCONF processing. */ typedef struct sctp_addip_param { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __be32 crr_id; } sctp_addip_param_t; @@ -724,7 +724,7 @@ struct sctp_reconf_chunk { }; struct sctp_strreset_outreq { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 request_seq; __u32 response_seq; __u32 send_reset_at_tsn; @@ -732,18 +732,18 @@ struct sctp_strreset_outreq { }; struct sctp_strreset_inreq { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 request_seq; __u16 list_of_streams[0]; }; struct sctp_strreset_tsnreq { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 request_seq; }; struct sctp_strreset_addstrm { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 request_seq; __u16 number_of_streams; __u16 reserved; @@ -760,13 +760,13 @@ enum { }; struct sctp_strreset_resp { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 response_seq; __u32 result; }; struct sctp_strreset_resptsn { - sctp_paramhdr_t param_hdr; + struct sctp_paramhdr param_hdr; __u32 response_seq; __u32 result; __u32 senders_next_tsn; diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index d756bd095683..a9519a06a23b 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -470,7 +470,7 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member) #define _sctp_walk_params(pos, chunk, end, member)\ for (pos.v = chunk->member;\ pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\ - ntohs(pos.p->length) >= sizeof(sctp_paramhdr_t);\ + ntohs(pos.p->length) >= sizeof(struct sctp_paramhdr);\ pos.v += SCTP_PAD4(ntohs(pos.p->length))) #define sctp_walk_errors(err, chunk_hdr)\ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 9e9605ecb5c9..2393d2ee95c1 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -310,9 +310,10 @@ struct sctp_cookie { __u32 adaptation_ind; - __u8 auth_random[sizeof(sctp_paramhdr_t) + SCTP_AUTH_RANDOM_LENGTH]; + __u8 auth_random[sizeof(struct sctp_paramhdr) + + SCTP_AUTH_RANDOM_LENGTH]; __u8 auth_hmacs[SCTP_AUTH_NUM_HMACS * sizeof(__u16) + 2]; - __u8 auth_chunks[sizeof(sctp_paramhdr_t) + SCTP_AUTH_MAX_CHUNKS]; + __u8 auth_chunks[sizeof(struct sctp_paramhdr) + SCTP_AUTH_MAX_CHUNKS]; /* This is a shim for my peer's INIT packet, followed by * a copy of the raw address list of the association. diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 757be416f778..fa4f530ab7e1 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -71,7 +71,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a { struct net *net = sock_net(sk); struct sctp_sock *sp; - sctp_paramhdr_t *p; + struct sctp_paramhdr *p; int i; /* Retrieve the SCTP per socket area. */ @@ -284,9 +284,9 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a ntohs(ep->auth_chunk_list->param_hdr.length)); /* Get the AUTH random number for this association */ - p = (sctp_paramhdr_t *)asoc->c.auth_random; + p = (struct sctp_paramhdr *)asoc->c.auth_random; p->type = SCTP_PARAM_RANDOM; - p->length = htons(sizeof(sctp_paramhdr_t) + SCTP_AUTH_RANDOM_LENGTH); + p->length = htons(sizeof(*p) + SCTP_AUTH_RANDOM_LENGTH); get_random_bytes(p+1, SCTP_AUTH_RANDOM_LENGTH); return asoc; diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 7171dd3d6e40..8ffa5985cd6e 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -538,7 +538,8 @@ struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc) if (!hmacs) return NULL; - n_elt = (ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t)) >> 1; + n_elt = (ntohs(hmacs->param_hdr.length) - + sizeof(struct sctp_paramhdr)) >> 1; for (i = 0; i < n_elt; i++) { id = ntohs(hmacs->hmac_ids[i]); @@ -589,7 +590,8 @@ int sctp_auth_asoc_verify_hmac_id(const struct sctp_association *asoc, return 0; hmacs = (struct sctp_hmac_algo_param *)asoc->c.auth_hmacs; - n_elt = (ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t)) >> 1; + n_elt = (ntohs(hmacs->param_hdr.length) - + sizeof(struct sctp_paramhdr)) >> 1; return __sctp_auth_find_hmacid(hmacs->hmac_ids, n_elt, hmac_id); } @@ -612,8 +614,8 @@ void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc, if (asoc->default_hmac_id) return; - n_params = (ntohs(hmacs->param_hdr.length) - - sizeof(sctp_paramhdr_t)) >> 1; + n_params = (ntohs(hmacs->param_hdr.length) - + sizeof(struct sctp_paramhdr)) >> 1; ep = asoc->ep; for (i = 0; i < n_params; i++) { id = ntohs(hmacs->hmac_ids[i]); @@ -641,7 +643,7 @@ static int __sctp_auth_cid(enum sctp_cid chunk, struct sctp_chunks_param *param) if (!param || param->param_hdr.length == 0) return 0; - len = ntohs(param->param_hdr.length) - sizeof(sctp_paramhdr_t); + len = ntohs(param->param_hdr.length) - sizeof(struct sctp_paramhdr); /* SCTP-AUTH, Section 3.2 * The chunk types for INIT, INIT-ACK, SHUTDOWN-COMPLETE and AUTH @@ -775,7 +777,7 @@ int sctp_auth_ep_add_chunkid(struct sctp_endpoint *ep, __u8 chunk_id) /* Check if we can add this chunk to the array */ param_len = ntohs(p->param_hdr.length); - nchunks = param_len - sizeof(sctp_paramhdr_t); + nchunks = param_len - sizeof(struct sctp_paramhdr); if (nchunks == SCTP_NUM_CHUNK_TYPES) return -EINVAL; @@ -812,9 +814,11 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep, return -EINVAL; for (i = 0; i < hmacs->shmac_num_idents; i++) - ep->auth_hmacs_list->hmac_ids[i] = htons(hmacs->shmac_idents[i]); - ep->auth_hmacs_list->param_hdr.length = htons(sizeof(sctp_paramhdr_t) + - hmacs->shmac_num_idents * sizeof(__u16)); + ep->auth_hmacs_list->hmac_ids[i] = + htons(hmacs->shmac_idents[i]); + ep->auth_hmacs_list->param_hdr.length = + htons(sizeof(struct sctp_paramhdr) + + hmacs->shmac_num_idents * sizeof(__u16)); return 0; } diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 7772ca40ddaf..efbc31877804 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -90,12 +90,13 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, */ auth_hmacs->param_hdr.type = SCTP_PARAM_HMAC_ALGO; auth_hmacs->param_hdr.length = - htons(sizeof(sctp_paramhdr_t) + 2); + htons(sizeof(struct sctp_paramhdr) + 2); auth_hmacs->hmac_ids[0] = htons(SCTP_AUTH_HMAC_ID_SHA1); /* Initialize the CHUNKS parameter */ auth_chunks->param_hdr.type = SCTP_PARAM_CHUNKS; - auth_chunks->param_hdr.length = htons(sizeof(sctp_paramhdr_t)); + auth_chunks->param_hdr.length = + htons(sizeof(struct sctp_paramhdr)); /* If the Add-IP functionality is enabled, we must * authenticate, ASCONF and ASCONF-ACK chunks @@ -104,7 +105,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, auth_chunks->chunks[0] = SCTP_CID_ASCONF; auth_chunks->chunks[1] = SCTP_CID_ASCONF_ACK; auth_chunks->param_hdr.length = - htons(sizeof(sctp_paramhdr_t) + 2); + htons(sizeof(struct sctp_paramhdr) + 2); } } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 78c3f214d608..9f9d40c9a32a 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -229,7 +229,7 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, sctp_supported_ext_param_t ext_param; int num_ext = 0; __u8 extensions[3]; - sctp_paramhdr_t *auth_chunks = NULL, + struct sctp_paramhdr *auth_chunks = NULL, *auth_hmacs = NULL; /* RFC 2960 3.3.2 Initiation (INIT) (1) @@ -286,14 +286,14 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, chunksize += sizeof(asoc->c.auth_random); /* Add HMACS parameter length if any were defined */ - auth_hmacs = (sctp_paramhdr_t *)asoc->c.auth_hmacs; + auth_hmacs = (struct sctp_paramhdr *)asoc->c.auth_hmacs; if (auth_hmacs->length) chunksize += SCTP_PAD4(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; /* Add CHUNKS parameter length */ - auth_chunks = (sctp_paramhdr_t *)asoc->c.auth_chunks; + auth_chunks = (struct sctp_paramhdr *)asoc->c.auth_chunks; if (auth_chunks->length) chunksize += SCTP_PAD4(ntohs(auth_chunks->length)); else @@ -397,7 +397,7 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, sctp_supported_ext_param_t ext_param; int num_ext = 0; __u8 extensions[3]; - sctp_paramhdr_t *auth_chunks = NULL, + struct sctp_paramhdr *auth_chunks = NULL, *auth_hmacs = NULL, *auth_random = NULL; @@ -448,16 +448,16 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, chunksize += sizeof(aiparam); if (asoc->peer.auth_capable) { - auth_random = (sctp_paramhdr_t *)asoc->c.auth_random; + auth_random = (struct sctp_paramhdr *)asoc->c.auth_random; chunksize += ntohs(auth_random->length); - auth_hmacs = (sctp_paramhdr_t *)asoc->c.auth_hmacs; + auth_hmacs = (struct sctp_paramhdr *)asoc->c.auth_hmacs; if (auth_hmacs->length) chunksize += SCTP_PAD4(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; - auth_chunks = (sctp_paramhdr_t *)asoc->c.auth_chunks; + auth_chunks = (struct sctp_paramhdr *)asoc->c.auth_chunks; if (auth_chunks->length) chunksize += SCTP_PAD4(ntohs(auth_chunks->length)); else @@ -1085,18 +1085,18 @@ struct sctp_chunk *sctp_make_abort_violation( struct sctp_chunk *retval; struct sctp_paramhdr phdr; - retval = sctp_make_abort(asoc, chunk, sizeof(sctp_errhdr_t) + paylen - + sizeof(sctp_paramhdr_t)); + retval = sctp_make_abort(asoc, chunk, sizeof(sctp_errhdr_t) + paylen + + sizeof(phdr)); if (!retval) goto end; - sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, paylen - + sizeof(sctp_paramhdr_t)); + sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, paylen + + sizeof(phdr)); phdr.type = htons(chunk->chunk_hdr->type); phdr.length = chunk->chunk_hdr->length; sctp_addto_chunk(retval, paylen, payload); - sctp_addto_param(retval, sizeof(sctp_paramhdr_t), &phdr); + sctp_addto_param(retval, sizeof(phdr), &phdr); end: return retval; @@ -1110,16 +1110,16 @@ struct sctp_chunk *sctp_make_violation_paramlen( struct sctp_chunk *retval; static const char error[] = "The following parameter had invalid length:"; size_t payload_len = sizeof(error) + sizeof(sctp_errhdr_t) + - sizeof(sctp_paramhdr_t); + sizeof(*param); retval = sctp_make_abort(asoc, chunk, payload_len); if (!retval) goto nodata; sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, - sizeof(error) + sizeof(sctp_paramhdr_t)); + sizeof(error) + sizeof(*param)); sctp_addto_chunk(retval, sizeof(error), error); - sctp_addto_param(retval, sizeof(sctp_paramhdr_t), param); + sctp_addto_param(retval, sizeof(*param), param); nodata: return retval; @@ -1614,7 +1614,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, /* Header size is static data prior to the actual cookie, including * any padding. */ - headersize = sizeof(sctp_paramhdr_t) + + headersize = sizeof(struct sctp_paramhdr) + (sizeof(struct sctp_signed_cookie) - sizeof(struct sctp_cookie)); bodysize = sizeof(struct sctp_cookie) @@ -1975,7 +1975,7 @@ static int sctp_process_hn_param(const struct sctp_association *asoc, static int sctp_verify_ext_param(struct net *net, union sctp_params param) { - __u16 num_ext = ntohs(param.p->length) - sizeof(sctp_paramhdr_t); + __u16 num_ext = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); int have_auth = 0; int have_asconf = 0; int i; @@ -2010,7 +2010,7 @@ static void sctp_process_ext_param(struct sctp_association *asoc, union sctp_params param) { struct net *net = sock_net(asoc->base.sk); - __u16 num_ext = ntohs(param.p->length) - sizeof(sctp_paramhdr_t); + __u16 num_ext = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); int i; for (i = 0; i < num_ext; i++) { @@ -2180,7 +2180,7 @@ static sctp_ierror_t sctp_verify_param(struct net *net, * cause 'Protocol Violation'. */ if (SCTP_AUTH_RANDOM_LENGTH != - ntohs(param.p->length) - sizeof(sctp_paramhdr_t)) { + ntohs(param.p->length) - sizeof(struct sctp_paramhdr)) { sctp_process_inv_paramlength(asoc, param.p, chunk, err_chunk); retval = SCTP_IERROR_ABORT; @@ -2208,7 +2208,8 @@ static sctp_ierror_t sctp_verify_param(struct net *net, goto fallthrough; hmacs = (struct sctp_hmac_algo_param *)param.p; - n_elt = (ntohs(param.p->length) - sizeof(sctp_paramhdr_t)) >> 1; + n_elt = (ntohs(param.p->length) - + sizeof(struct sctp_paramhdr)) >> 1; /* SCTP-AUTH: Section 6.1 * The HMAC algorithm based on SHA-1 MUST be supported and @@ -2565,7 +2566,7 @@ do_addr_param: asoc->peer.ipv4_address = 1; /* Cycle through address types; avoid divide by 0. */ - sat = ntohs(param.p->length) - sizeof(sctp_paramhdr_t); + sat = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); if (sat) sat /= sizeof(__u16); @@ -2592,7 +2593,7 @@ do_addr_param: case SCTP_PARAM_STATE_COOKIE: asoc->peer.cookie_len = - ntohs(param.p->length) - sizeof(sctp_paramhdr_t); + ntohs(param.p->length) - sizeof(struct sctp_paramhdr); asoc->peer.cookie = param.cookie->body; break; @@ -3176,7 +3177,7 @@ bool sctp_verify_asconf(const struct sctp_association *asoc, return false; length = ntohs(param.addip->param_hdr.length); if (length < sizeof(sctp_addip_param_t) + - sizeof(sctp_paramhdr_t)) + sizeof(**errp)) return false; break; case SCTP_PARAM_SUCCESS_REPORT: diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 2b7c07f19b08..0a01c6858b0d 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1081,7 +1081,7 @@ sctp_disposition_t sctp_sf_beat_8_3(struct net *net, void *arg, sctp_cmd_seq_t *commands) { - sctp_paramhdr_t *param_hdr; + struct sctp_paramhdr *param_hdr; struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; size_t paylen = 0; @@ -1098,8 +1098,8 @@ sctp_disposition_t sctp_sf_beat_8_3(struct net *net, * respond with a HEARTBEAT ACK that contains the Heartbeat * Information field copied from the received HEARTBEAT chunk. */ - chunk->subh.hb_hdr = (sctp_heartbeathdr_t *) chunk->skb->data; - param_hdr = (sctp_paramhdr_t *) chunk->subh.hb_hdr; + chunk->subh.hb_hdr = (sctp_heartbeathdr_t *)chunk->skb->data; + param_hdr = (struct sctp_paramhdr *)chunk->subh.hb_hdr; paylen = ntohs(chunk->chunk_hdr->length) - sizeof(struct sctp_chunkhdr); if (ntohs(param_hdr->length) > paylen) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 15401d09efc4..0af103f85c79 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6033,7 +6033,8 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, return -EACCES; hmacs = ep->auth_hmacs_list; - data_len = ntohs(hmacs->param_hdr.length) - sizeof(sctp_paramhdr_t); + data_len = ntohs(hmacs->param_hdr.length) - + sizeof(struct sctp_paramhdr); if (len < sizeof(struct sctp_hmacalgo) + data_len) return -EINVAL; @@ -6117,7 +6118,7 @@ static int sctp_getsockopt_peer_auth_chunks(struct sock *sk, int len, goto num; /* See if the user provided enough room for all the data */ - num_chunks = ntohs(ch->param_hdr.length) - sizeof(sctp_paramhdr_t); + num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr); if (len < num_chunks) return -EINVAL; @@ -6165,7 +6166,7 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, if (!ch) goto num; - num_chunks = ntohs(ch->param_hdr.length) - sizeof(sctp_paramhdr_t); + num_chunks = ntohs(ch->param_hdr.length) - sizeof(struct sctp_paramhdr); if (len < sizeof(struct sctp_authchunks) + num_chunks) return -EINVAL; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 82e6d40052a8..63ea15503714 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -304,7 +304,7 @@ out: return retval; } -static sctp_paramhdr_t *sctp_chunk_lookup_strreset_param( +static struct sctp_paramhdr *sctp_chunk_lookup_strreset_param( struct sctp_association *asoc, __u32 resp_seq, __be16 type) { @@ -749,7 +749,7 @@ struct sctp_chunk *sctp_process_strreset_resp( struct sctp_strreset_resp *resp = param.v; struct sctp_transport *t; __u16 i, nums, flags = 0; - sctp_paramhdr_t *req; + struct sctp_paramhdr *req; __u32 result; req = sctp_chunk_lookup_strreset_param(asoc, resp->response_seq, 0); -- cgit v1.2.3 From 34b4e29b383559e3848eea30af66e94aa72af88c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 30 Jun 2017 11:52:17 +0800 Subject: sctp: remove the typedef sctp_param_t This patch is to remove the typedef sctp_param_t, and replace with struct sctp_paramhdr in the places where it's using this typedef. It is also to remove the useless declaration sctp_addip_addr_config and fix the lack of params for some other functions' declaration. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- include/net/sctp/sm.h | 14 ++++++-------- net/sctp/sm_make_chunk.c | 2 +- 3 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 142bb6aa88eb..5eecc0f14650 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -167,7 +167,7 @@ struct sctp_paramhdr { __be16 length; }; -typedef enum { +enum sctp_param { /* RFC 2960 Section 3.3.5 */ SCTP_PARAM_HEARTBEAT_INFO = cpu_to_be16(1), @@ -207,7 +207,7 @@ typedef enum { SCTP_PARAM_RESET_RESPONSE = cpu_to_be16(0x0010), SCTP_PARAM_RESET_ADD_OUT_STREAMS = cpu_to_be16(0x0011), SCTP_PARAM_RESET_ADD_IN_STREAMS = cpu_to_be16(0x0012), -} sctp_param_t; /* enum */ +}; /* enum */ /* RFC 2960 Section 3.2.1 diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 47113f2c4b0a..245eb22230a2 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -325,19 +325,17 @@ void sctp_generate_heartbeat_event(unsigned long peer); void sctp_generate_reconf_event(unsigned long peer); void sctp_generate_proto_unreach_event(unsigned long peer); -void sctp_ootb_pkt_free(struct sctp_packet *); +void sctp_ootb_pkt_free(struct sctp_packet *packet); -struct sctp_association *sctp_unpack_cookie(const struct sctp_endpoint *, - const struct sctp_association *, - struct sctp_chunk *, +struct sctp_association *sctp_unpack_cookie(const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + struct sctp_chunk *chunk, gfp_t gfp, int *err, struct sctp_chunk **err_chk_p); -int sctp_addip_addr_config(struct sctp_association *, sctp_param_t, - struct sockaddr_storage*, int); /* 3rd level prototypes */ -__u32 sctp_generate_tag(const struct sctp_endpoint *); -__u32 sctp_generate_tsn(const struct sctp_endpoint *); +__u32 sctp_generate_tag(const struct sctp_endpoint *ep); +__u32 sctp_generate_tsn(const struct sctp_endpoint *ep); /* Extern declarations for major data structures. */ extern sctp_timer_event_t *sctp_timer_events[SCTP_NUM_TIMEOUT_TYPES]; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 9f9d40c9a32a..3ed2108d1989 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1882,7 +1882,7 @@ struct __sctp_missing { * Report a missing mandatory parameter. */ static int sctp_process_missing_param(const struct sctp_association *asoc, - sctp_param_t paramtype, + enum sctp_param paramtype, struct sctp_chunk *chunk, struct sctp_chunk **errp) { -- cgit v1.2.3 From 9f8d31471548d9b74609335f9a3c75c7b664c8b4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 30 Jun 2017 11:52:20 +0800 Subject: sctp: remove the typedef sctp_data_chunk_t This patch is to remove the typedef sctp_data_chunk_t, and replace with struct sctp_data_chunk in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- include/net/sctp/constants.h | 2 +- include/net/sctp/sm.h | 2 +- net/sctp/output.c | 4 ++-- net/sctp/sm_statefuns.c | 6 +++--- net/sctp/ulpqueue.c | 2 +- 6 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 55d84c143122..91c888f21b24 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -235,10 +235,10 @@ struct sctp_datahdr { __u8 payload[0]; }; -typedef struct sctp_data_chunk { +struct sctp_data_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_datahdr data_hdr; -} sctp_data_chunk_t; +}; /* DATA Chuck Specific Flags */ enum { diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 02e867bc4b43..9b18044c551e 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -152,7 +152,7 @@ SCTP_SUBTYPE_CONSTRUCTOR(PRIMITIVE, sctp_event_primitive_t, primitive) /* Calculate the actual data size in a data chunk */ #define SCTP_DATA_SNDSIZE(c) ((int)((unsigned long)(c->chunk_end)\ - (unsigned long)(c->chunk_hdr)\ - - sizeof(sctp_data_chunk_t))) + - sizeof(struct sctp_data_chunk))) /* Internal error codes */ typedef enum { diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 245eb22230a2..860f378333b5 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -347,7 +347,7 @@ static inline __u16 sctp_data_size(struct sctp_chunk *chunk) __u16 size; size = ntohs(chunk->chunk_hdr->length); - size -= sizeof(sctp_data_chunk_t); + size -= sizeof(struct sctp_data_chunk); return size; } diff --git a/net/sctp/output.c b/net/sctp/output.c index 9bf9d84a96b7..9d8504985744 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -723,8 +723,8 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, /* Check whether this chunk and all the rest of pending data will fit * or delay in hopes of bundling a full sized packet. */ - if (chunk->skb->len + q->out_qlen > - transport->pathmtu - packet->overhead - sizeof(sctp_data_chunk_t) - 4) + if (chunk->skb->len + q->out_qlen > transport->pathmtu - + packet->overhead - sizeof(struct sctp_data_chunk) - 4) /* Enough data queued to fill a packet */ return SCTP_XMIT_OK; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 1ba9a9b04466..212fe7614d08 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -2990,7 +2990,7 @@ sctp_disposition_t sctp_sf_eat_data_6_2(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_data_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_data_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -3109,7 +3109,7 @@ sctp_disposition_t sctp_sf_eat_data_fast_4_4(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_data_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_data_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); @@ -6262,7 +6262,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * Actually, allow a little bit of overflow (up to a MTU). */ datalen = ntohs(chunk->chunk_hdr->length); - datalen -= sizeof(sctp_data_chunk_t); + datalen -= sizeof(struct sctp_data_chunk); deliver = SCTP_CMD_CHUNK_ULP; diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 25f7e4140566..0225d62a869f 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -1090,7 +1090,7 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, if (chunk) { needed = ntohs(chunk->chunk_hdr->length); - needed -= sizeof(sctp_data_chunk_t); + needed -= sizeof(struct sctp_data_chunk); } else needed = SCTP_DEFAULT_MAXWINDOW; -- cgit v1.2.3 From 01a992bea523d9568cf56a02003c15c9dc40eb20 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 30 Jun 2017 11:52:22 +0800 Subject: sctp: remove the typedef sctp_init_chunk_t This patch is to remove the typedef sctp_init_chunk_t, and replace with struct sctp_init_chunk in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- include/net/sctp/command.h | 4 ++-- include/net/sctp/structs.h | 4 ++-- net/sctp/input.c | 4 ++-- net/sctp/sm_make_chunk.c | 6 +++--- net/sctp/sm_sideeffect.c | 2 +- net/sctp/sm_statefuns.c | 28 ++++++++++++++-------------- 7 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/net') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 56241953e57e..99e866487e2f 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -266,10 +266,10 @@ struct sctp_inithdr { __u8 params[0]; }; -typedef struct sctp_init_chunk { +struct sctp_init_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_inithdr init_hdr; -} sctp_init_chunk_t; +}; /* Section 3.3.2.1. IPv4 Address Parameter (5) */ @@ -341,7 +341,7 @@ typedef struct sctp_hmac_algo_param { * The INIT ACK chunk is used to acknowledge the initiation of an SCTP * association. */ -typedef sctp_init_chunk_t sctp_initack_chunk_t; +typedef struct sctp_init_chunk sctp_initack_chunk_t; /* Section 3.3.3.1 State Cookie (7) */ typedef struct sctp_cookie_param { diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index d4a20d00461c..d4679e7a5ed5 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -132,7 +132,7 @@ typedef union { struct sctp_association *asoc; struct sctp_transport *transport; struct sctp_bind_addr *bp; - sctp_init_chunk_t *init; + struct sctp_init_chunk *init; struct sctp_ulpevent *ulpevent; struct sctp_packet *packet; sctp_sackhdr_t *sackh; @@ -173,7 +173,7 @@ SCTP_ARG_CONSTRUCTOR(CHUNK, struct sctp_chunk *, chunk) SCTP_ARG_CONSTRUCTOR(ASOC, struct sctp_association *, asoc) SCTP_ARG_CONSTRUCTOR(TRANSPORT, struct sctp_transport *, transport) SCTP_ARG_CONSTRUCTOR(BA, struct sctp_bind_addr *, bp) -SCTP_ARG_CONSTRUCTOR(PEER_INIT, sctp_init_chunk_t *, init) +SCTP_ARG_CONSTRUCTOR(PEER_INIT, struct sctp_init_chunk *, init) SCTP_ARG_CONSTRUCTOR(ULPEVENT, struct sctp_ulpevent *, ulpevent) SCTP_ARG_CONSTRUCTOR(PACKET, struct sctp_packet *, packet) SCTP_ARG_CONSTRUCTOR(SACKH, sctp_sackhdr_t *, sackh) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 2393d2ee95c1..07c11fefa8c4 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1298,11 +1298,11 @@ int sctp_has_association(struct net *net, const union sctp_addr *laddr, int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, - enum sctp_cid cid, sctp_init_chunk_t *peer_init, + enum sctp_cid cid, struct sctp_init_chunk *peer_init, struct sctp_chunk *chunk, struct sctp_chunk **err_chunk); int sctp_process_init(struct sctp_association *, struct sctp_chunk *chunk, const union sctp_addr *peer, - sctp_init_chunk_t *init, gfp_t gfp); + struct sctp_init_chunk *init, gfp_t gfp); __u32 sctp_generate_tag(const struct sctp_endpoint *); __u32 sctp_generate_tsn(const struct sctp_endpoint *); diff --git a/net/sctp/input.c b/net/sctp/input.c index a9994c4afc18..41eb2ec10460 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -1051,7 +1051,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, union sctp_addr *paddr = &addr; struct sctphdr *sh = sctp_hdr(skb); union sctp_params params; - sctp_init_chunk_t *init; + struct sctp_init_chunk *init; struct sctp_af *af; /* @@ -1070,7 +1070,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, /* Find the start of the TLVs and the end of the chunk. This is * the region we search for address parameters. */ - init = (sctp_init_chunk_t *)skb->data; + init = (struct sctp_init_chunk *)skb->data; /* Walk the parameters looking for embedded addresses. */ sctp_walk_params(params, init, init_hdr.params) { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 8b9ca107fd0c..3af4dd024ec0 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2242,8 +2242,8 @@ fallthrough: /* Verify the INIT packet before we process it. */ int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, enum sctp_cid cid, - sctp_init_chunk_t *peer_init, struct sctp_chunk *chunk, - struct sctp_chunk **errp) + struct sctp_init_chunk *peer_init, + struct sctp_chunk *chunk, struct sctp_chunk **errp) { union sctp_params param; bool has_cookie = false; @@ -2307,7 +2307,7 @@ int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, */ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, const union sctp_addr *peer_addr, - sctp_init_chunk_t *peer_init, gfp_t gfp) + struct sctp_init_chunk *peer_init, gfp_t gfp) { struct net *net = sock_net(asoc->base.sk); union sctp_params param; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index b255339f22a3..d6e5e9e0fd6d 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -647,7 +647,7 @@ static void sctp_cmd_assoc_failed(sctp_cmd_seq_t *commands, static int sctp_cmd_process_init(sctp_cmd_seq_t *commands, struct sctp_association *asoc, struct sctp_chunk *chunk, - sctp_init_chunk_t *peer_init, + struct sctp_init_chunk *peer_init, gfp_t gfp) { int error; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 71b6e3f66b65..b2a74c3823ee 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -345,7 +345,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, * error, but since we don't have an association, we'll * just discard the packet. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_init_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* If the INIT is coming toward a closing socket, we'll send back @@ -360,7 +360,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, - (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, + (struct sctp_init_chunk *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. * Send an ABORT, with causes if there is any. @@ -405,7 +405,7 @@ sctp_disposition_t sctp_sf_do_5_1B_init(struct net *net, /* The call, sctp_process_init(), can fail on memory allocation. */ if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), - (sctp_init_chunk_t *)chunk->chunk_hdr, + (struct sctp_init_chunk *)chunk->chunk_hdr, GFP_ATOMIC)) goto nomem_init; @@ -503,7 +503,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, sctp_cmd_seq_t *commands) { struct sctp_chunk *chunk = arg; - sctp_init_chunk_t *initchunk; + struct sctp_init_chunk *initchunk; struct sctp_chunk *err_chunk; struct sctp_packet *packet; @@ -527,7 +527,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, - (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, + (struct sctp_init_chunk *)chunk->chunk_hdr, chunk, &err_chunk)) { sctp_error_t error = SCTP_ERROR_NO_RESOURCE; @@ -578,7 +578,7 @@ sctp_disposition_t sctp_sf_do_5_1C_ack(struct net *net, */ chunk->param_hdr.v = skb_pull(chunk->skb, sizeof(struct sctp_inithdr)); - initchunk = (sctp_init_chunk_t *) chunk->chunk_hdr; + initchunk = (struct sctp_init_chunk *)chunk->chunk_hdr; sctp_add_cmd_sf(commands, SCTP_CMD_PEER_INIT, SCTP_PEER_INIT(initchunk)); @@ -653,7 +653,7 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, { struct sctp_chunk *chunk = arg; struct sctp_association *new_asoc; - sctp_init_chunk_t *peer_init; + struct sctp_init_chunk *peer_init; struct sctp_chunk *repl; struct sctp_ulpevent *ev, *ai_ev = NULL; int error = 0; @@ -1450,7 +1450,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( * In this case, we generate a protocol violation since we have * an association established. */ - if (!sctp_chunk_length_valid(chunk, sizeof(sctp_init_chunk_t))) + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); /* Grab the INIT header. */ @@ -1462,7 +1462,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( /* Verify the INIT chunk before processing it. */ err_chunk = NULL; if (!sctp_verify_init(net, ep, asoc, chunk->chunk_hdr->type, - (sctp_init_chunk_t *)chunk->chunk_hdr, chunk, + (struct sctp_init_chunk *)chunk->chunk_hdr, chunk, &err_chunk)) { /* This chunk contains fatal error. It is to be discarded. * Send an ABORT, with causes if there is any. @@ -1509,7 +1509,7 @@ static sctp_disposition_t sctp_sf_do_unexpected_init( * place (local tie-tag and per tie-tag) within the state cookie. */ if (!sctp_process_init(new_asoc, chunk, sctp_source(chunk), - (sctp_init_chunk_t *)chunk->chunk_hdr, + (struct sctp_init_chunk *)chunk->chunk_hdr, GFP_ATOMIC)) goto nomem; @@ -1730,7 +1730,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net, sctp_cmd_seq_t *commands, struct sctp_association *new_asoc) { - sctp_init_chunk_t *peer_init; + struct sctp_init_chunk *peer_init; struct sctp_ulpevent *ev; struct sctp_chunk *repl; struct sctp_chunk *err; @@ -1845,7 +1845,7 @@ static sctp_disposition_t sctp_sf_do_dupcook_b(struct net *net, sctp_cmd_seq_t *commands, struct sctp_association *new_asoc) { - sctp_init_chunk_t *peer_init; + struct sctp_init_chunk *peer_init; struct sctp_chunk *repl; /* new_asoc is a brand-new association, so these are not yet @@ -6124,9 +6124,9 @@ static struct sctp_packet *sctp_ootb_pkt_new(struct net *net, switch (chunk->chunk_hdr->type) { case SCTP_CID_INIT: { - sctp_init_chunk_t *init; + struct sctp_init_chunk *init; - init = (sctp_init_chunk_t *)chunk->chunk_hdr; + init = (struct sctp_init_chunk *)chunk->chunk_hdr; vtag = ntohl(init->init_hdr.init_tag); break; } -- cgit v1.2.3 From 40304b2a1567fecc321f640ee4239556dd0f3ee0 Mon Sep 17 00:00:00 2001 From: Lawrence Brakmo Date: Fri, 30 Jun 2017 20:02:40 -0700 Subject: bpf: BPF support for sock_ops Created a new BPF program type, BPF_PROG_TYPE_SOCK_OPS, and a corresponding struct that allows BPF programs of this type to access some of the socket's fields (such as IP addresses, ports, etc.). It uses the existing bpf cgroups infrastructure so the programs can be attached per cgroup with full inheritance support. The program will be called at appropriate times to set relevant connections parameters such as buffer sizes, SYN and SYN-ACK RTOs, etc., based on connection information such as IP addresses, port numbers, etc. Alghough there are already 3 mechanisms to set parameters (sysctls, route metrics and setsockopts), this new mechanism provides some distinct advantages. Unlike sysctls, it can set parameters per connection. In contrast to route metrics, it can also use port numbers and information provided by a user level program. In addition, it could set parameters probabilistically for evaluation purposes (i.e. do something different on 10% of the flows and compare results with the other 90% of the flows). Also, in cases where IPv6 addresses contain geographic information, the rules to make changes based on the distance (or RTT) between the hosts are much easier than route metric rules and can be global. Finally, unlike setsockopt, it oes not require application changes and it can be updated easily at any time. Although the bpf cgroup framework already contains a sock related program type (BPF_PROG_TYPE_CGROUP_SOCK), I created the new type (BPF_PROG_TYPE_SOCK_OPS) beccause the existing type expects to be called only once during the connections's lifetime. In contrast, the new program type will be called multiple times from different places in the network stack code. For example, before sending SYN and SYN-ACKs to set an appropriate timeout, when the connection is established to set congestion control, etc. As a result it has "op" field to specify the type of operation requested. The purpose of this new program type is to simplify setting connection parameters, such as buffer sizes, TCP's SYN RTO, etc. For example, it is easy to use facebook's internal IPv6 addresses to determine if both hosts of a connection are in the same datacenter. Therefore, it is easy to write a BPF program to choose a small SYN RTO value when both hosts are in the same datacenter. This patch only contains the framework to support the new BPF program type, following patches add the functionality to set various connection parameters. This patch defines a new BPF program type: BPF_PROG_TYPE_SOCKET_OPS and a new bpf syscall command to load a new program of this type: BPF_PROG_LOAD_SOCKET_OPS. Two new corresponding structs (one for the kernel one for the user/BPF program): /* kernel version */ struct bpf_sock_ops_kern { struct sock *sk; __u32 op; union { __u32 reply; __u32 replylong[4]; }; }; /* user version * Some fields are in network byte order reflecting the sock struct * Use the bpf_ntohl helper macro in samples/bpf/bpf_endian.h to * convert them to host byte order. */ struct bpf_sock_ops { __u32 op; union { __u32 reply; __u32 replylong[4]; }; __u32 family; __u32 remote_ip4; /* In network byte order */ __u32 local_ip4; /* In network byte order */ __u32 remote_ip6[4]; /* In network byte order */ __u32 local_ip6[4]; /* In network byte order */ __u32 remote_port; /* In network byte order */ __u32 local_port; /* In host byte horder */ }; Currently there are two types of ops. The first type expects the BPF program to return a value which is then used by the caller (or a negative value to indicate the operation is not supported). The second type expects state changes to be done by the BPF program, for example through a setsockopt BPF helper function, and they ignore the return value. The reply fields of the bpf_sockt_ops struct are there in case a bpf program needs to return a value larger than an integer. Signed-off-by: Lawrence Brakmo Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 18 +++++ include/linux/bpf_types.h | 1 + include/linux/filter.h | 9 +++ include/net/tcp.h | 36 ++++++++++ include/uapi/linux/bpf.h | 30 ++++++++ kernel/bpf/cgroup.c | 37 ++++++++++ kernel/bpf/syscall.c | 5 ++ net/core/filter.c | 168 +++++++++++++++++++++++++++++++++++++++++++++ samples/bpf/bpf_load.c | 13 +++- 9 files changed, 314 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index c970a25d2a49..360c082e885c 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -7,6 +7,7 @@ struct sock; struct cgroup; struct sk_buff; +struct bpf_sock_ops_kern; #ifdef CONFIG_CGROUP_BPF @@ -42,6 +43,10 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, int __cgroup_bpf_run_filter_sk(struct sock *sk, enum bpf_attach_type type); +int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, + struct bpf_sock_ops_kern *sock_ops, + enum bpf_attach_type type); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -75,6 +80,18 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, __ret; \ }) +#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled && (sock_ops)->sk) { \ + typeof(sk) __sk = sk_to_full_sk((sock_ops)->sk); \ + if (sk_fullsock(__sk)) \ + __ret = __cgroup_bpf_run_filter_sock_ops(__sk, \ + sock_ops, \ + BPF_CGROUP_SOCK_OPS); \ + } \ + __ret; \ +}) #else struct cgroup_bpf {}; @@ -85,6 +102,7 @@ static inline void cgroup_bpf_inherit(struct cgroup *cgrp, #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #endif /* CONFIG_CGROUP_BPF */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 03bf223f18be..3d137c33d664 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -10,6 +10,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops) #endif #ifdef CONFIG_BPF_EVENTS BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) diff --git a/include/linux/filter.h b/include/linux/filter.h index 1fa26dc562ce..738f8b14f025 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -898,4 +898,13 @@ static inline int bpf_tell_extensions(void) return SKF_AD_MAX; } +struct bpf_sock_ops_kern { + struct sock *sk; + u32 op; + union { + u32 reply; + u32 replylong[4]; + }; +}; + #endif /* __LINUX_FILTER_H__ */ diff --git a/include/net/tcp.h b/include/net/tcp.h index d0751b79d99c..e58500825006 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -46,6 +46,10 @@ #include #include +#include +#include +#include + extern struct inet_hashinfo tcp_hashinfo; extern struct percpu_counter tcp_orphan_count; @@ -2021,4 +2025,36 @@ int tcp_set_ulp(struct sock *sk, const char *name); void tcp_get_available_ulp(char *buf, size_t len); void tcp_cleanup_ulp(struct sock *sk); +/* Call BPF_SOCK_OPS program that returns an int. If the return value + * is < 0, then the BPF op failed (for example if the loaded BPF + * program does not support the chosen operation or there is no BPF + * program loaded). + */ +#ifdef CONFIG_BPF +static inline int tcp_call_bpf(struct sock *sk, int op) +{ + struct bpf_sock_ops_kern sock_ops; + int ret; + + if (sk_fullsock(sk)) + sock_owned_by_me(sk); + + memset(&sock_ops, 0, sizeof(sock_ops)); + sock_ops.sk = sk; + sock_ops.op = op; + + ret = BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops); + if (ret == 0) + ret = sock_ops.reply; + else + ret = -1; + return ret; +} +#else +static inline int tcp_call_bpf(struct sock *sk, int op) +{ + return -EPERM; +} +#endif + #endif /* _TCP_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f94b48b168dc..01cd485ccd4f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -120,12 +120,14 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_IN, BPF_PROG_TYPE_LWT_OUT, BPF_PROG_TYPE_LWT_XMIT, + BPF_PROG_TYPE_SOCK_OPS, }; enum bpf_attach_type { BPF_CGROUP_INET_INGRESS, BPF_CGROUP_INET_EGRESS, BPF_CGROUP_INET_SOCK_CREATE, + BPF_CGROUP_SOCK_OPS, __MAX_BPF_ATTACH_TYPE }; @@ -720,4 +722,32 @@ struct bpf_map_info { __u32 map_flags; } __attribute__((aligned(8))); +/* User bpf_sock_ops struct to access socket values and specify request ops + * and their replies. + * Some of this fields are in network (bigendian) byte order and may need + * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h). + * New fields can only be added at the end of this structure + */ +struct bpf_sock_ops { + __u32 op; + union { + __u32 reply; + __u32 replylong[4]; + }; + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ +}; + +/* List of known BPF sock_ops operators. + * New entries can only be added at the end + */ +enum { + BPF_SOCK_OPS_VOID, +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ea6033cba947..546113430049 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -236,3 +236,40 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); + +/** + * __cgroup_bpf_run_filter_sock_ops() - Run a program on a sock + * @sk: socket to get cgroup from + * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains + * sk with connection information (IP addresses, etc.) May not contain + * cgroup info if it is a req sock. + * @type: The type of program to be exectuted + * + * socket passed is expected to be of type INET or INET6. + * + * The program type passed in via @type must be suitable for sock_ops + * filtering. No further check is performed to assert that. + * + * This function will return %-EPERM if any if an attached program was found + * and if it returned != 1 during execution. In all other cases, 0 is returned. + */ +int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, + struct bpf_sock_ops_kern *sock_ops, + enum bpf_attach_type type) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_prog *prog; + int ret = 0; + + + rcu_read_lock(); + + prog = rcu_dereference(cgrp->bpf.effective[type]); + if (prog) + ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM; + + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4409ccca8831..d4d47de75bba 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1079,6 +1079,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_INET_SOCK_CREATE: ptype = BPF_PROG_TYPE_CGROUP_SOCK; break; + case BPF_CGROUP_SOCK_OPS: + ptype = BPF_PROG_TYPE_SOCK_OPS; + break; default: return -EINVAL; } @@ -1119,6 +1122,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_SOCK_OPS: cgrp = cgroup_get_from_fd(attr->target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); @@ -1133,6 +1137,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) return ret; } + #endif /* CONFIG_CGROUP_BPF */ #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration diff --git a/net/core/filter.c b/net/core/filter.c index b39c869d22e3..1f6a26c4f8b9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3110,6 +3110,36 @@ void bpf_warn_invalid_xdp_action(u32 act) } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); +static bool __is_valid_sock_ops_access(int off, int size) +{ + if (off < 0 || off >= sizeof(struct bpf_sock_ops)) + return false; + /* The verifier guarantees that size > 0. */ + if (off % size != 0) + return false; + if (size != sizeof(__u32)) + return false; + + return true; +} + +static bool sock_ops_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (type == BPF_WRITE) { + switch (off) { + case offsetof(struct bpf_sock_ops, op) ... + offsetof(struct bpf_sock_ops, replylong[3]): + break; + default: + return false; + } + } + + return __is_valid_sock_ops_access(off, size); +} + static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, @@ -3379,6 +3409,138 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } +static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog) +{ + struct bpf_insn *insn = insn_buf; + int off; + + switch (si->off) { + case offsetof(struct bpf_sock_ops, op) ... + offsetof(struct bpf_sock_ops, replylong[3]): + BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, op) != + FIELD_SIZEOF(struct bpf_sock_ops_kern, op)); + BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, reply) != + FIELD_SIZEOF(struct bpf_sock_ops_kern, reply)); + BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, replylong) != + FIELD_SIZEOF(struct bpf_sock_ops_kern, replylong)); + off = si->off; + off -= offsetof(struct bpf_sock_ops, op); + off += offsetof(struct bpf_sock_ops_kern, op); + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, + off); + else + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + off); + break; + + case offsetof(struct bpf_sock_ops, family): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_family)); + break; + + case offsetof(struct bpf_sock_ops, remote_ip4): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_daddr)); + break; + + case offsetof(struct bpf_sock_ops, local_ip4): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_rcv_saddr) != 4); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_rcv_saddr)); + break; + + case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... + offsetof(struct bpf_sock_ops, remote_ip6[3]): +#if IS_ENABLED(CONFIG_IPV6) + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_v6_daddr.s6_addr32[0]) != 4); + + off = si->off; + off -= offsetof(struct bpf_sock_ops, remote_ip6[0]); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_v6_daddr.s6_addr32[0]) + + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + + case offsetof(struct bpf_sock_ops, local_ip6[0]) ... + offsetof(struct bpf_sock_ops, local_ip6[3]): +#if IS_ENABLED(CONFIG_IPV6) + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + skc_v6_rcv_saddr.s6_addr32[0]) != 4); + + off = si->off; + off -= offsetof(struct bpf_sock_ops, local_ip6[0]); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, + skc_v6_rcv_saddr.s6_addr32[0]) + + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + + case offsetof(struct bpf_sock_ops, remote_port): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_dport)); +#ifndef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); +#endif + break; + + case offsetof(struct bpf_sock_ops, local_port): + BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, + offsetof(struct sock_common, skc_num)); + break; + } + return insn - insn_buf; +} + const struct bpf_verifier_ops sk_filter_prog_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, @@ -3428,6 +3590,12 @@ const struct bpf_verifier_ops cg_sock_prog_ops = { .convert_ctx_access = sock_filter_convert_ctx_access, }; +const struct bpf_verifier_ops sock_ops_prog_ops = { + .get_func_proto = bpf_base_func_proto, + .is_valid_access = sock_ops_is_valid_access, + .convert_ctx_access = sock_ops_convert_ctx_access, +}; + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index a91c57dd8571..a4be7cfa6519 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -64,6 +64,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) bool is_perf_event = strncmp(event, "perf_event", 10) == 0; bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0; bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0; + bool is_sockops = strncmp(event, "sockops", 7) == 0; size_t insns_cnt = size / sizeof(struct bpf_insn); enum bpf_prog_type prog_type; char buf[256]; @@ -89,6 +90,8 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) prog_type = BPF_PROG_TYPE_CGROUP_SKB; } else if (is_cgroup_sk) { prog_type = BPF_PROG_TYPE_CGROUP_SOCK; + } else if (is_sockops) { + prog_type = BPF_PROG_TYPE_SOCK_OPS; } else { printf("Unknown event '%s'\n", event); return -1; @@ -106,8 +109,11 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk) return 0; - if (is_socket) { - event += 6; + if (is_socket || is_sockops) { + if (is_socket) + event += 6; + else + event += 7; if (*event != '/') return 0; event++; @@ -560,7 +566,8 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) memcmp(shname, "xdp", 3) == 0 || memcmp(shname, "perf_event", 10) == 0 || memcmp(shname, "socket", 6) == 0 || - memcmp(shname, "cgroup/", 7) == 0) + memcmp(shname, "cgroup/", 7) == 0 || + memcmp(shname, "sockops", 7) == 0) load_and_attach(shname, data->d_buf, data->d_size); } -- cgit v1.2.3 From 8550f328f45db6d37981eb2041bc465810245c03 Mon Sep 17 00:00:00 2001 From: Lawrence Brakmo Date: Fri, 30 Jun 2017 20:02:42 -0700 Subject: bpf: Support for per connection SYN/SYN-ACK RTOs This patch adds support for setting a per connection SYN and SYN_ACK RTOs from within a BPF_SOCK_OPS program. For example, to set small RTOs when it is known both hosts are within a datacenter. Signed-off-by: Lawrence Brakmo Signed-off-by: David S. Miller --- include/net/tcp.h | 11 +++++++++++ include/uapi/linux/bpf.h | 3 +++ net/ipv4/tcp_input.c | 3 ++- net/ipv4/tcp_output.c | 2 +- 4 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index e58500825006..564af2dee236 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2057,4 +2057,15 @@ static inline int tcp_call_bpf(struct sock *sk, int op) } #endif +static inline u32 tcp_timeout_init(struct sock *sk) +{ + int timeout; + + timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT); + + if (timeout <= 0) + timeout = TCP_TIMEOUT_INIT; + return timeout; +} + #endif /* _TCP_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 01cd485ccd4f..00702b294447 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -748,6 +748,9 @@ struct bpf_sock_ops { */ enum { BPF_SOCK_OPS_VOID, + BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or + * -1 if default value should be used + */ }; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2ab7e2fa9bb9..bcc96654cd7e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6406,7 +6406,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, } else { tcp_rsk(req)->tfo_listener = false; if (!want_cookie) - inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + inet_csk_reqsk_queue_hash_add(sk, req, + tcp_timeout_init((struct sock *)req)); af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : TCP_SYNACK_COOKIE); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1d79137f3795..47fe0759a877 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3326,7 +3326,7 @@ static void tcp_connect_init(struct sock *sk) tp->rcv_wup = tp->rcv_nxt; tp->copied_seq = tp->rcv_nxt; - inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; + inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; tcp_clear_retrans(tp); } -- cgit v1.2.3 From 13d3b1ebe28762c79e981931a41914fae5d04386 Mon Sep 17 00:00:00 2001 From: Lawrence Brakmo Date: Fri, 30 Jun 2017 20:02:44 -0700 Subject: bpf: Support for setting initial receive window This patch adds suppport for setting the initial advertized window from within a BPF_SOCK_OPS program. This can be used to support larger initial cwnd values in environments where it is known to be safe. Signed-off-by: Lawrence Brakmo Signed-off-by: David S. Miller --- include/net/tcp.h | 10 ++++++++++ include/uapi/linux/bpf.h | 4 ++++ net/ipv4/tcp_minisocks.c | 9 ++++++++- net/ipv4/tcp_output.c | 7 ++++++- 4 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 564af2dee236..d6bb3948203d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2068,4 +2068,14 @@ static inline u32 tcp_timeout_init(struct sock *sk) return timeout; } +static inline u32 tcp_rwnd_init_bpf(struct sock *sk) +{ + int rwnd; + + rwnd = tcp_call_bpf(sk, BPF_SOCK_OPS_RWND_INIT); + + if (rwnd < 0) + rwnd = 0; + return rwnd; +} #endif /* _TCP_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 00702b294447..94d7ded1a6cf 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -751,6 +751,10 @@ enum { BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or * -1 if default value should be used */ + BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized + * window (in packets) or -1 if default + * value should be used + */ }; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d30ee31e94eb..0ff83c1637d8 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -351,6 +351,7 @@ void tcp_openreq_init_rwin(struct request_sock *req, int full_space = tcp_full_space(sk_listener); u32 window_clamp; __u8 rcv_wscale; + u32 rcv_wnd; int mss; mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); @@ -363,6 +364,12 @@ void tcp_openreq_init_rwin(struct request_sock *req, (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) req->rsk_window_clamp = full_space; + rcv_wnd = tcp_rwnd_init_bpf((struct sock *)req); + if (rcv_wnd == 0) + rcv_wnd = dst_metric(dst, RTAX_INITRWND); + else if (full_space < rcv_wnd * mss) + full_space = rcv_wnd * mss; + /* tcp_full_space because it is guaranteed to be the first packet */ tcp_select_initial_window(full_space, mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), @@ -370,7 +377,7 @@ void tcp_openreq_init_rwin(struct request_sock *req, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, - dst_metric(dst, RTAX_INITRWND)); + rcv_wnd); ireq->rcv_wscale = rcv_wscale; } EXPORT_SYMBOL(tcp_openreq_init_rwin); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 47fe0759a877..ef809426b538 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3266,6 +3266,7 @@ static void tcp_connect_init(struct sock *sk) const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; + u32 rcv_wnd; /* We'll fix this up when we get a response from the other end. * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. @@ -3299,13 +3300,17 @@ static void tcp_connect_init(struct sock *sk) (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) tp->window_clamp = tcp_full_space(sk); + rcv_wnd = tcp_rwnd_init_bpf(sk); + if (rcv_wnd == 0) + rcv_wnd = dst_metric(dst, RTAX_INITRWND); + tcp_select_initial_window(tcp_full_space(sk), tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, sock_net(sk)->ipv4.sysctl_tcp_window_scaling, &rcv_wscale, - dst_metric(dst, RTAX_INITRWND)); + rcv_wnd); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; -- cgit v1.2.3 From 91b5b21c7c16899abb37f4a9e4388b4e9aae0b9d Mon Sep 17 00:00:00 2001 From: Lawrence Brakmo Date: Fri, 30 Jun 2017 20:02:49 -0700 Subject: bpf: Add support for changing congestion control Added support for changing congestion control for SOCK_OPS bpf programs through the setsockopt bpf helper function. It also adds a new SOCK_OPS op, BPF_SOCK_OPS_NEEDS_ECN, that is needed for congestion controls, like dctcp, that need to enable ECN in the SYN packets. Signed-off-by: Lawrence Brakmo Signed-off-by: David S. Miller --- include/net/tcp.h | 9 ++++++++- include/uapi/linux/bpf.h | 3 +++ net/core/filter.c | 18 +++++++++++++++++- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_cong.c | 32 ++++++++++++++++++++++---------- net/ipv4/tcp_input.c | 3 ++- net/ipv4/tcp_output.c | 8 +++++--- 7 files changed, 58 insertions(+), 17 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index d6bb3948203d..70483296157f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1004,7 +1004,9 @@ void tcp_get_default_congestion_control(char *name); void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); -int tcp_set_congestion_control(struct sock *sk, const char *name); +int tcp_set_congestion_control(struct sock *sk, const char *name, bool load); +void tcp_reinit_congestion_control(struct sock *sk, + const struct tcp_congestion_ops *ca); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); @@ -2078,4 +2080,9 @@ static inline u32 tcp_rwnd_init_bpf(struct sock *sk) rwnd = 0; return rwnd; } + +static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) +{ + return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN) == 1); +} #endif /* _TCP_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2405fe304c98..cc4725982bd8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -778,6 +778,9 @@ enum { * passive connection is * established */ + BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control + * needs ECN + */ }; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/net/core/filter.c b/net/core/filter.c index ca033e15d35e..12df52711fe8 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2719,8 +2719,24 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, } } else if (level == SOL_TCP && sk->sk_prot->setsockopt == tcp_setsockopt) { - /* Place holder */ +#ifdef CONFIG_INET + if (optname == TCP_CONGESTION) { + char name[TCP_CA_NAME_MAX]; + + strncpy(name, optval, min_t(long, optlen, + TCP_CA_NAME_MAX-1)); + name[TCP_CA_NAME_MAX-1] = 0; + ret = tcp_set_congestion_control(sk, name, false); + if (!ret && bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN) + /* replacing an existing ca */ + tcp_reinit_congestion_control(sk, + inet_csk(sk)->icsk_ca_ops); + } else { + ret = -EINVAL; + } +#else ret = -EINVAL; +#endif } else { ret = -EINVAL; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fae45e402742..71ce33decd97 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2481,7 +2481,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, name[val] = 0; lock_sock(sk); - err = tcp_set_congestion_control(sk, name); + err = tcp_set_congestion_control(sk, name, true); release_sock(sk); return err; } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 324c9bcc5456..fde983f6376b 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -189,8 +189,8 @@ void tcp_init_congestion_control(struct sock *sk) INET_ECN_dontxmit(sk); } -static void tcp_reinit_congestion_control(struct sock *sk, - const struct tcp_congestion_ops *ca) +void tcp_reinit_congestion_control(struct sock *sk, + const struct tcp_congestion_ops *ca) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -333,8 +333,12 @@ out: return ret; } -/* Change congestion control for socket */ -int tcp_set_congestion_control(struct sock *sk, const char *name) +/* Change congestion control for socket. If load is false, then it is the + * responsibility of the caller to call tcp_init_congestion_control or + * tcp_reinit_congestion_control (if the current congestion control was + * already initialized. + */ +int tcp_set_congestion_control(struct sock *sk, const char *name, bool load) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; @@ -344,21 +348,29 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) return -EPERM; rcu_read_lock(); - ca = __tcp_ca_find_autoload(name); + if (!load) + ca = tcp_ca_find(name); + else + ca = __tcp_ca_find_autoload(name); /* No change asking for existing value */ if (ca == icsk->icsk_ca_ops) { icsk->icsk_ca_setsockopt = 1; goto out; } - if (!ca) + if (!ca) { err = -ENOENT; - else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || - ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) + } else if (!load) { + icsk->icsk_ca_ops = ca; + if (!try_module_get(ca->owner)) + err = -EBUSY; + } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || + ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) { err = -EPERM; - else if (!try_module_get(ca->owner)) + } else if (!try_module_get(ca->owner)) { err = -EBUSY; - else + } else { tcp_reinit_congestion_control(sk, ca); + } out: rcu_read_unlock(); return err; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 664210e5e4a7..2920e0cb09f8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6191,7 +6191,8 @@ static void tcp_ecn_create_request(struct request_sock *req, ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst; if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || - (ecn_ok_dst & DST_FEATURE_ECN_CA)) + (ecn_ok_dst & DST_FEATURE_ECN_CA) || + tcp_bpf_ca_needs_ecn((struct sock *)req)) inet_rsk(req)->ecn_ok = 1; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 33b3e401e812..4d36f0b093e6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -316,7 +316,8 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; if (!(tp->ecn_flags & TCP_ECN_OK)) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; - else if (tcp_ca_needs_ecn(sk)) + else if (tcp_ca_needs_ecn(sk) || + tcp_bpf_ca_needs_ecn(sk)) INET_ECN_xmit(sk); } @@ -324,8 +325,9 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 || - tcp_ca_needs_ecn(sk); + tcp_ca_needs_ecn(sk) || bpf_needs_ecn; if (!use_ecn) { const struct dst_entry *dst = __sk_dst_get(sk); @@ -339,7 +341,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) if (use_ecn) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; - if (tcp_ca_needs_ecn(sk)) + if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) INET_ECN_xmit(sk); } } -- cgit v1.2.3 From 69e766612c4bcb79e19cebed9eed61d4222c1d47 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Sun, 2 Jul 2017 19:00:57 +0200 Subject: vxlan: fix hlist corruption It's not a good idea to add the same hlist_node to two different hash lists. This leads to various hard to debug memory corruptions. Fixes: b1be00a6c39f ("vxlan: support both IPv4 and IPv6 sockets in a single vxlan device") Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 32 +++++++++++++++++++++----------- include/net/vxlan.h | 10 +++++++++- 2 files changed, 30 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 47d6e65851aa..b04e103350fb 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -229,25 +229,25 @@ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family, static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, int ifindex, __be32 vni) { - struct vxlan_dev *vxlan; + struct vxlan_dev_node *node; /* For flow based devices, map all packets to VNI 0 */ if (vs->flags & VXLAN_F_COLLECT_METADATA) vni = 0; - hlist_for_each_entry_rcu(vxlan, vni_head(vs, vni), hlist) { - if (vxlan->default_dst.remote_vni != vni) + hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) { + if (node->vxlan->default_dst.remote_vni != vni) continue; if (IS_ENABLED(CONFIG_IPV6)) { - const struct vxlan_config *cfg = &vxlan->cfg; + const struct vxlan_config *cfg = &node->vxlan->cfg; if ((cfg->flags & VXLAN_F_IPV6_LINKLOCAL) && cfg->remote_ifindex != ifindex) continue; } - return vxlan; + return node->vxlan; } return NULL; @@ -2387,17 +2387,22 @@ static void vxlan_vs_del_dev(struct vxlan_dev *vxlan) struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); spin_lock(&vn->sock_lock); - hlist_del_init_rcu(&vxlan->hlist); + hlist_del_init_rcu(&vxlan->hlist4.hlist); +#if IS_ENABLED(CONFIG_IPV6) + hlist_del_init_rcu(&vxlan->hlist6.hlist); +#endif spin_unlock(&vn->sock_lock); } -static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan) +static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan, + struct vxlan_dev_node *node) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); __be32 vni = vxlan->default_dst.remote_vni; + node->vxlan = vxlan; spin_lock(&vn->sock_lock); - hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni)); + hlist_add_head_rcu(&node->hlist, vni_head(vs, vni)); spin_unlock(&vn->sock_lock); } @@ -2849,6 +2854,7 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); struct vxlan_sock *vs = NULL; + struct vxlan_dev_node *node; if (!vxlan->cfg.no_share) { spin_lock(&vn->sock_lock); @@ -2866,12 +2872,16 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) if (IS_ERR(vs)) return PTR_ERR(vs); #if IS_ENABLED(CONFIG_IPV6) - if (ipv6) + if (ipv6) { rcu_assign_pointer(vxlan->vn6_sock, vs); - else + node = &vxlan->hlist6; + } else #endif + { rcu_assign_pointer(vxlan->vn4_sock, vs); - vxlan_vs_add_dev(vs, vxlan); + node = &vxlan->hlist4; + } + vxlan_vs_add_dev(vs, vxlan, node); return 0; } diff --git a/include/net/vxlan.h b/include/net/vxlan.h index b816a0a6686e..326e8498b10e 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -221,9 +221,17 @@ struct vxlan_config { bool no_share; }; +struct vxlan_dev_node { + struct hlist_node hlist; + struct vxlan_dev *vxlan; +}; + /* Pseudo network device */ struct vxlan_dev { - struct hlist_node hlist; /* vni hash table */ + struct vxlan_dev_node hlist4; /* vni hash table for IPv4 socket */ +#if IS_ENABLED(CONFIG_IPV6) + struct vxlan_dev_node hlist6; /* vni hash table for IPv6 socket */ +#endif struct list_head next; /* vxlan's per namespace list */ struct vxlan_sock __rcu *vn4_sock; /* listening socket for IPv4 */ #if IS_ENABLED(CONFIG_IPV6) -- cgit v1.2.3 From 784c372a8184bdb8ae722c94250c2d57dc327a8e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 3 Jul 2017 02:57:54 -0700 Subject: net: make sk_ehashfn() static sk_ehashfn() is only used from a single file. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 1 - net/ipv4/inet_hashtables.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index b9e6e0e1f55c..5026b1f08bb8 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -359,7 +359,6 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, refcounted); } -u32 sk_ehashfn(const struct sock *sk); u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index a4be2c1cb688..2e3389d614d1 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -43,7 +43,7 @@ static u32 inet_ehashfn(const struct net *net, const __be32 laddr, /* This function handles inet_sock, but also timewait and request sockets * for IPv4/IPv6. */ -u32 sk_ehashfn(const struct sock *sk) +static u32 sk_ehashfn(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6 && -- cgit v1.2.3 From 0aeea21ada517b99a6e95298ffc105381bcd3a52 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 09:34:54 +0300 Subject: net, ipv6: convert ipv6_txoptions.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/ipv6.h | 7 ++++--- net/ipv6/exthdrs.c | 4 ++-- net/ipv6/ipv6_sockglue.c | 2 +- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 3e505bbff8ca..6eac5cf8f1e6 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -203,7 +204,7 @@ extern rwlock_t ip6_ra_lock; */ struct ipv6_txoptions { - atomic_t refcnt; + refcount_t refcnt; /* Length of this structure */ int tot_len; @@ -265,7 +266,7 @@ static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) { - if (!atomic_inc_not_zero(&opt->refcnt)) + if (!refcount_inc_not_zero(&opt->refcnt)) opt = NULL; else opt = rcu_pointer_handoff(opt); @@ -276,7 +277,7 @@ static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) static inline void txopt_put(struct ipv6_txoptions *opt) { - if (opt && atomic_dec_and_test(&opt->refcnt)) + if (opt && refcount_dec_and_test(&opt->refcnt)) kfree_rcu(opt, rcu); } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 0460af226011..4996d734f1d2 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -971,7 +971,7 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) *((char **)&opt2->dst1opt) += dif; if (opt2->srcrt) *((char **)&opt2->srcrt) += dif; - atomic_set(&opt2->refcnt, 1); + refcount_set(&opt2->refcnt, 1); } return opt2; } @@ -1056,7 +1056,7 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, return ERR_PTR(-ENOBUFS); memset(opt2, 0, tot_len); - atomic_set(&opt2->refcnt, 1); + refcount_set(&opt2->refcnt, 1); opt2->tot_len = tot_len; p = (char *)(opt2 + 1); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index a531ba032b85..85404e7c3114 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -505,7 +505,7 @@ sticky_done: break; memset(opt, 0, sizeof(*opt)); - atomic_set(&opt->refcnt, 1); + refcount_set(&opt->refcnt, 1); opt->tot_len = sizeof(*opt) + optlen; retv = -EFAULT; if (copy_from_user(opt+1, optval, optlen)) -- cgit v1.2.3 From 1be9246077f6bb1583f9347c599480621d63c66a Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 09:34:55 +0300 Subject: net, ipv6: convert inet6_dev.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/addrconf.h | 8 ++++---- include/net/if_inet6.h | 3 ++- net/ipv6/addrconf.c | 2 +- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index d0889cb50172..620bd9a83ba9 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -316,7 +316,7 @@ static inline struct inet6_dev *in6_dev_get(const struct net_device *dev) rcu_read_lock(); idev = rcu_dereference(dev->ip6_ptr); if (idev) - atomic_inc(&idev->refcnt); + refcount_inc(&idev->refcnt); rcu_read_unlock(); return idev; } @@ -332,18 +332,18 @@ void in6_dev_finish_destroy(struct inet6_dev *idev); static inline void in6_dev_put(struct inet6_dev *idev) { - if (atomic_dec_and_test(&idev->refcnt)) + if (refcount_dec_and_test(&idev->refcnt)) in6_dev_finish_destroy(idev); } static inline void __in6_dev_put(struct inet6_dev *idev) { - atomic_dec(&idev->refcnt); + refcount_dec(&idev->refcnt); } static inline void in6_dev_hold(struct inet6_dev *idev) { - atomic_inc(&idev->refcnt); + refcount_inc(&idev->refcnt); } void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp); diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index f656f9051aca..e7a17b231afc 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -17,6 +17,7 @@ #include #include +#include /* inet6_dev.if_flags */ @@ -187,7 +188,7 @@ struct inet6_dev { struct ifacaddr6 *ac_list; rwlock_t lock; - atomic_t refcnt; + refcount_t refcnt; __u32 if_flags; int dead; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 114fb64cf176..2365f1224c6b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -426,7 +426,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) } /* One reference from device. */ - in6_dev_hold(ndev); + refcount_set(&ndev->refcnt, 1); if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) ndev->cnf.accept_dad = -1; -- cgit v1.2.3 From 271201c09c86cd75e0fd6206bde689176e85aa21 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 09:34:56 +0300 Subject: net, ipv6: convert inet6_ifaddr.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/addrconf.h | 6 +++--- include/net/if_inet6.h | 2 +- net/ipv6/addrconf.c | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 620bd9a83ba9..6df79e96a780 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -350,18 +350,18 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp); static inline void in6_ifa_put(struct inet6_ifaddr *ifp) { - if (atomic_dec_and_test(&ifp->refcnt)) + if (refcount_dec_and_test(&ifp->refcnt)) inet6_ifa_finish_destroy(ifp); } static inline void __in6_ifa_put(struct inet6_ifaddr *ifp) { - atomic_dec(&ifp->refcnt); + refcount_dec(&ifp->refcnt); } static inline void in6_ifa_hold(struct inet6_ifaddr *ifp) { - atomic_inc(&ifp->refcnt); + refcount_inc(&ifp->refcnt); } diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index e7a17b231afc..2b41cb86d62f 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -46,7 +46,7 @@ struct inet6_ifaddr { /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 valid_lft; __u32 prefered_lft; - atomic_t refcnt; + refcount_t refcnt; spinlock_t lock; int state; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2365f1224c6b..3c46e9513a31 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1050,7 +1050,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->idev = idev; /* For caller */ - in6_ifa_hold(ifa); + refcount_set(&ifa->refcnt, 1); /* Add to big hash table */ hash = inet6_addr_hash(addr); -- cgit v1.2.3 From d3981bc615f652b9ead0762dd180125ac2b21a3a Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 09:34:57 +0300 Subject: net, ipv6: convert ifmcaddr6.mca_refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/if_inet6.h | 2 +- net/ipv6/mcast.c | 18 +++++++++--------- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 2b41cb86d62f..4bb52ce634e8 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -127,7 +127,7 @@ struct ifmcaddr6 { struct timer_list mca_timer; unsigned int mca_flags; int mca_users; - atomic_t mca_refcnt; + refcount_t mca_refcnt; spinlock_t mca_lock; unsigned long mca_cstamp; unsigned long mca_tstamp; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index e2221135858b..12b7c27ce5ce 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -701,7 +701,7 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc) spin_lock_bh(&mc->mca_lock); if (del_timer(&mc->mca_timer)) - atomic_dec(&mc->mca_refcnt); + refcount_dec(&mc->mca_refcnt); spin_unlock_bh(&mc->mca_lock); } @@ -819,12 +819,12 @@ static void mld_clear_delrec(struct inet6_dev *idev) static void mca_get(struct ifmcaddr6 *mc) { - atomic_inc(&mc->mca_refcnt); + refcount_inc(&mc->mca_refcnt); } static void ma_put(struct ifmcaddr6 *mc) { - if (atomic_dec_and_test(&mc->mca_refcnt)) { + if (refcount_dec_and_test(&mc->mca_refcnt)) { in6_dev_put(mc->idev); kfree(mc); } @@ -846,7 +846,7 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, mc->mca_users = 1; /* mca_stamp should be updated upon changes */ mc->mca_cstamp = mc->mca_tstamp = jiffies; - atomic_set(&mc->mca_refcnt, 1); + refcount_set(&mc->mca_refcnt, 1); spin_lock_init(&mc->mca_lock); /* initial mode is (EX, empty) */ @@ -1065,7 +1065,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) return; if (del_timer(&ma->mca_timer)) { - atomic_dec(&ma->mca_refcnt); + refcount_dec(&ma->mca_refcnt); delay = ma->mca_timer.expires - jiffies; } @@ -1074,7 +1074,7 @@ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) ma->mca_timer.expires = jiffies + delay; if (!mod_timer(&ma->mca_timer, jiffies + delay)) - atomic_inc(&ma->mca_refcnt); + refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING; } @@ -1469,7 +1469,7 @@ int igmp6_event_report(struct sk_buff *skb) if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { spin_lock(&ma->mca_lock); if (del_timer(&ma->mca_timer)) - atomic_dec(&ma->mca_refcnt); + refcount_dec(&ma->mca_refcnt); ma->mca_flags &= ~(MAF_LAST_REPORTER|MAF_TIMER_RUNNING); spin_unlock(&ma->mca_lock); break; @@ -2391,12 +2391,12 @@ static void igmp6_join_group(struct ifmcaddr6 *ma) spin_lock_bh(&ma->mca_lock); if (del_timer(&ma->mca_timer)) { - atomic_dec(&ma->mca_refcnt); + refcount_dec(&ma->mca_refcnt); delay = ma->mca_timer.expires - jiffies; } if (!mod_timer(&ma->mca_timer, jiffies + delay)) - atomic_inc(&ma->mca_refcnt); + refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING | MAF_LAST_REPORTER; spin_unlock_bh(&ma->mca_lock); } -- cgit v1.2.3 From affa78bc6a204fac1b5ced4f34376f53c70ec0ac Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 09:34:58 +0300 Subject: net, ipv6: convert ifacaddr6.aca_refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/if_inet6.h | 2 +- net/ipv6/anycast.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 4bb52ce634e8..d4088d1a688d 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -147,7 +147,7 @@ struct ifacaddr6 { struct rt6_info *aca_rt; struct ifacaddr6 *aca_next; int aca_users; - atomic_t aca_refcnt; + refcount_t aca_refcnt; unsigned long aca_cstamp; unsigned long aca_tstamp; }; diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 514ac259f543..0bbab8a4b5d8 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -203,12 +203,12 @@ void ipv6_sock_ac_close(struct sock *sk) static void aca_get(struct ifacaddr6 *aca) { - atomic_inc(&aca->aca_refcnt); + refcount_inc(&aca->aca_refcnt); } static void aca_put(struct ifacaddr6 *ac) { - if (atomic_dec_and_test(&ac->aca_refcnt)) { + if (refcount_dec_and_test(&ac->aca_refcnt)) { in6_dev_put(ac->aca_idev); dst_release(&ac->aca_rt->dst); kfree(ac); @@ -232,7 +232,7 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; - atomic_set(&aca->aca_refcnt, 1); + refcount_set(&aca->aca_refcnt, 1); return aca; } -- cgit v1.2.3 From f6a6fede28e3cc3f9e4669a12839b47011330d95 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 09:35:01 +0300 Subject: net, ipv4: convert cipso_v4_doi.refcount from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/cipso_ipv4.h | 3 ++- net/ipv4/cipso_ipv4.c | 12 ++++++------ 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index a34b141f125f..880adb2f2afd 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -41,6 +41,7 @@ #include #include #include +#include #include /* known doi values */ @@ -85,7 +86,7 @@ struct cipso_v4_doi { } map; u8 tags[CIPSO_V4_TAG_MAXCNT]; - atomic_t refcount; + refcount_t refcount; struct list_head list; struct rcu_head rcu; }; diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index c2044775ae7d..c4c6e1969ed0 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -375,7 +375,7 @@ static struct cipso_v4_doi *cipso_v4_doi_search(u32 doi) struct cipso_v4_doi *iter; list_for_each_entry_rcu(iter, &cipso_v4_doi_list, list) - if (iter->doi == doi && atomic_read(&iter->refcount)) + if (iter->doi == doi && refcount_read(&iter->refcount)) return iter; return NULL; } @@ -429,7 +429,7 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def, } } - atomic_set(&doi_def->refcount, 1); + refcount_set(&doi_def->refcount, 1); spin_lock(&cipso_v4_doi_list_lock); if (cipso_v4_doi_search(doi_def->doi)) { @@ -533,7 +533,7 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!atomic_dec_and_test(&doi_def->refcount)) { + if (!refcount_dec_and_test(&doi_def->refcount)) { spin_unlock(&cipso_v4_doi_list_lock); ret_val = -EBUSY; goto doi_remove_return; @@ -576,7 +576,7 @@ struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi) doi_def = cipso_v4_doi_search(doi); if (!doi_def) goto doi_getdef_return; - if (!atomic_inc_not_zero(&doi_def->refcount)) + if (!refcount_inc_not_zero(&doi_def->refcount)) doi_def = NULL; doi_getdef_return: @@ -597,7 +597,7 @@ void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def) if (!doi_def) return; - if (!atomic_dec_and_test(&doi_def->refcount)) + if (!refcount_dec_and_test(&doi_def->refcount)) return; spin_lock(&cipso_v4_doi_list_lock); list_del_rcu(&doi_def->list); @@ -630,7 +630,7 @@ int cipso_v4_doi_walk(u32 *skip_cnt, rcu_read_lock(); list_for_each_entry_rcu(iter_doi, &cipso_v4_doi_list, list) - if (atomic_read(&iter_doi->refcount) > 0) { + if (refcount_read(&iter_doi->refcount) > 0) { if (doi_cnt++ < *skip_cnt) continue; ret_val = callback(iter_doi, cb_arg); -- cgit v1.2.3 From 0029c0deb590bc18732327d53b8fdab12eec6d7c Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 09:35:02 +0300 Subject: net, ipv4: convert fib_info.fib_clntref from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/ip_fib.h | 7 ++++--- net/ipv4/fib_semantics.c | 2 +- net/ipv4/fib_trie.c | 2 +- 3 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 3dbfd5e6a347..41d580c6185f 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -23,6 +23,7 @@ #include #include #include +#include struct fib_config { u8 fc_dst_len; @@ -105,7 +106,7 @@ struct fib_info { struct hlist_node fib_lhash; struct net *fib_net; int fib_treeref; - atomic_t fib_clntref; + refcount_t fib_clntref; unsigned int fib_flags; unsigned char fib_dead; unsigned char fib_protocol; @@ -430,12 +431,12 @@ void free_fib_info(struct fib_info *fi); static inline void fib_info_hold(struct fib_info *fi) { - atomic_inc(&fi->fib_clntref); + refcount_inc(&fi->fib_clntref); } static inline void fib_info_put(struct fib_info *fi) { - if (atomic_dec_and_test(&fi->fib_clntref)) + if (refcount_dec_and_test(&fi->fib_clntref)) free_fib_info(fi); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index ff47ea1408fe..222100103808 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1253,7 +1253,7 @@ link_it: } fi->fib_treeref++; - atomic_inc(&fi->fib_clntref); + refcount_set(&fi->fib_clntref, 1); spin_lock_bh(&fib_info_lock); hlist_add_head(&fi->fib_hash, &fib_info_hash[fib_info_hashfn(fi)]); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index d56659e97a6e..64668c69dda6 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1463,7 +1463,7 @@ found: } if (!(fib_flags & FIB_LOOKUP_NOREF)) - atomic_inc(&fi->fib_clntref); + refcount_inc(&fi->fib_clntref); res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; -- cgit v1.2.3 From 58951dde05fdac96a9d30805d8fa5d124dd4f92c Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:52:56 +0300 Subject: net, llc: convert llc_sap.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/llc.h | 6 +++--- net/llc/llc_core.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/llc.h b/include/net/llc.h index e8e61d4fb458..dc35f25eb679 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -55,7 +55,7 @@ struct llc_sap { unsigned char state; unsigned char p_bit; unsigned char f_bit; - atomic_t refcnt; + refcount_t refcnt; int (*rcv_func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, @@ -113,14 +113,14 @@ struct llc_sap *llc_sap_open(unsigned char lsap, struct net_device *orig_dev)); static inline void llc_sap_hold(struct llc_sap *sap) { - atomic_inc(&sap->refcnt); + refcount_inc(&sap->refcnt); } void llc_sap_close(struct llc_sap *sap); static inline void llc_sap_put(struct llc_sap *sap) { - if (atomic_dec_and_test(&sap->refcnt)) + if (refcount_dec_and_test(&sap->refcnt)) llc_sap_close(sap); } diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 842851cef698..89041260784c 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -41,7 +41,7 @@ static struct llc_sap *llc_sap_alloc(void) spin_lock_init(&sap->sk_lock); for (i = 0; i < LLC_SK_LADDR_HASH_ENTRIES; i++) INIT_HLIST_NULLS_HEAD(&sap->sk_laddr_hash[i], i); - atomic_set(&sap->refcnt, 1); + refcount_set(&sap->refcnt, 1); } return sap; } -- cgit v1.2.3 From 66af846fe54b780f8f5bd9a62aee081bd2ace582 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:52:59 +0300 Subject: net, vxlan: convert vxlan_sock.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 10 +++++----- include/net/vxlan.h | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index b04e103350fb..96aa7e6cf214 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1034,11 +1034,11 @@ static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev) /* The vxlan_sock is only used by dev, leaving group has * no effect on other vxlan devices. */ - if (family == AF_INET && sock4 && atomic_read(&sock4->refcnt) == 1) + if (family == AF_INET && sock4 && refcount_read(&sock4->refcnt) == 1) return false; #if IS_ENABLED(CONFIG_IPV6) sock6 = rtnl_dereference(dev->vn6_sock); - if (family == AF_INET6 && sock6 && atomic_read(&sock6->refcnt) == 1) + if (family == AF_INET6 && sock6 && refcount_read(&sock6->refcnt) == 1) return false; #endif @@ -1075,7 +1075,7 @@ static bool __vxlan_sock_release_prep(struct vxlan_sock *vs) if (!vs) return false; - if (!atomic_dec_and_test(&vs->refcnt)) + if (!refcount_dec_and_test(&vs->refcnt)) return false; vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id); @@ -2825,7 +2825,7 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, } vs->sock = sock; - atomic_set(&vs->refcnt, 1); + refcount_set(&vs->refcnt, 1); vs->flags = (flags & VXLAN_F_RCV_FLAGS); spin_lock(&vn->sock_lock); @@ -2860,7 +2860,7 @@ static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) spin_lock(&vn->sock_lock); vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, vxlan->cfg.dst_port, vxlan->cfg.flags); - if (vs && !atomic_add_unless(&vs->refcnt, 1, 0)) { + if (vs && !refcount_inc_not_zero(&vs->refcnt)) { spin_unlock(&vn->sock_lock); return -EBUSY; } diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 326e8498b10e..3f430e38ab82 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -183,7 +183,7 @@ struct vxlan_sock { struct hlist_node hlist; struct socket *sock; struct hlist_head vni_list[VNI_HASH_SIZE]; - atomic_t refcnt; + refcount_t refcnt; u32 flags; }; -- cgit v1.2.3 From e0542dd5185e68247b08c3418bdba14644b4c414 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:00 +0300 Subject: net, decnet: convert dn_fib_info.fib_clntref from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/dn_fib.h | 5 +++-- net/decnet/dn_fib.c | 6 +++--- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h index f2ca135ddcc9..81210a8b8d7c 100644 --- a/include/net/dn_fib.h +++ b/include/net/dn_fib.h @@ -2,6 +2,7 @@ #define _NET_DN_FIB_H #include +#include extern const struct nla_policy rtm_dn_policy[]; @@ -28,7 +29,7 @@ struct dn_fib_info { struct dn_fib_info *fib_next; struct dn_fib_info *fib_prev; int fib_treeref; - atomic_t fib_clntref; + refcount_t fib_clntref; int fib_dead; unsigned int fib_flags; int fib_protocol; @@ -130,7 +131,7 @@ void dn_fib_free_info(struct dn_fib_info *fi); static inline void dn_fib_info_put(struct dn_fib_info *fi) { - if (atomic_dec_and_test(&fi->fib_clntref)) + if (refcount_dec_and_test(&fi->fib_clntref)) dn_fib_free_info(fi); } diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index f9058ebeb635..f9f6fb3f3c5b 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -389,7 +389,7 @@ link_it: } fi->fib_treeref++; - atomic_inc(&fi->fib_clntref); + refcount_set(&fi->fib_clntref, 1); spin_lock(&dn_fib_info_lock); fi->fib_next = dn_fib_info_list; fi->fib_prev = NULL; @@ -425,7 +425,7 @@ int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn switch (type) { case RTN_NAT: DN_FIB_RES_RESET(*res); - atomic_inc(&fi->fib_clntref); + refcount_inc(&fi->fib_clntref); return 0; case RTN_UNICAST: case RTN_LOCAL: @@ -438,7 +438,7 @@ int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn } if (nhsel < fi->fib_nhs) { res->nh_sel = nhsel; - atomic_inc(&fi->fib_clntref); + refcount_inc(&fi->fib_clntref); return 0; } endfor_nexthops(fi); -- cgit v1.2.3 From edcd9270be1ba9c80cd0789ffbae7a7d204b7b05 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:06 +0300 Subject: net, calipso: convert calipso_doi.refcount from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/calipso.h | 4 ++-- net/ipv6/calipso.c | 12 ++++++------ 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/calipso.h b/include/net/calipso.h index b1b30cd36601..5f95b11a04bf 100644 --- a/include/net/calipso.h +++ b/include/net/calipso.h @@ -38,7 +38,7 @@ #include #include #include -#include +#include #include /* known doi values */ @@ -57,7 +57,7 @@ struct calipso_doi { u32 doi; u32 type; - atomic_t refcount; + refcount_t refcount; struct list_head list; struct rcu_head rcu; }; diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 44067521e7cd..1323b9679cf7 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -338,7 +338,7 @@ static struct calipso_doi *calipso_doi_search(u32 doi) struct calipso_doi *iter; list_for_each_entry_rcu(iter, &calipso_doi_list, list) - if (iter->doi == doi && atomic_read(&iter->refcount)) + if (iter->doi == doi && refcount_read(&iter->refcount)) return iter; return NULL; } @@ -370,7 +370,7 @@ static int calipso_doi_add(struct calipso_doi *doi_def, if (doi_def->doi == CALIPSO_DOI_UNKNOWN) goto doi_add_return; - atomic_set(&doi_def->refcount, 1); + refcount_set(&doi_def->refcount, 1); spin_lock(&calipso_doi_list_lock); if (calipso_doi_search(doi_def->doi)) { @@ -458,7 +458,7 @@ static int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!atomic_dec_and_test(&doi_def->refcount)) { + if (!refcount_dec_and_test(&doi_def->refcount)) { spin_unlock(&calipso_doi_list_lock); ret_val = -EBUSY; goto doi_remove_return; @@ -499,7 +499,7 @@ static struct calipso_doi *calipso_doi_getdef(u32 doi) doi_def = calipso_doi_search(doi); if (!doi_def) goto doi_getdef_return; - if (!atomic_inc_not_zero(&doi_def->refcount)) + if (!refcount_inc_not_zero(&doi_def->refcount)) doi_def = NULL; doi_getdef_return: @@ -520,7 +520,7 @@ static void calipso_doi_putdef(struct calipso_doi *doi_def) if (!doi_def) return; - if (!atomic_dec_and_test(&doi_def->refcount)) + if (!refcount_dec_and_test(&doi_def->refcount)) return; spin_lock(&calipso_doi_list_lock); list_del_rcu(&doi_def->list); @@ -553,7 +553,7 @@ static int calipso_doi_walk(u32 *skip_cnt, rcu_read_lock(); list_for_each_entry_rcu(iter_doi, &calipso_doi_list, list) - if (atomic_read(&iter_doi->refcount) > 0) { + if (refcount_read(&iter_doi->refcount) > 0) { if (doi_cnt++ < *skip_cnt) continue; ret_val = callback(iter_doi, cb_arg); -- cgit v1.2.3 From 7b9364050246bd4c24b36b71c8990b2922dcc027 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:07 +0300 Subject: net, sched: convert Qdisc.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/sch_generic.h | 3 ++- net/sched/sch_api.c | 8 ++++---- net/sched/sch_generic.c | 8 ++++---- 3 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include/net') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 368850194c94..1c123e2b2415 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -95,7 +96,7 @@ struct Qdisc { struct sk_buff *skb_bad_txq; struct rcu_head rcu_head; int padded; - atomic_t refcnt; + refcount_t refcnt; spinlock_t busylock ____cacheline_aligned_in_smp; }; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 43b94c7b69bd..bd24a550e0f9 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -839,7 +839,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, old = dev_graft_qdisc(dev_queue, new); if (new && i > 0) - atomic_inc(&new->refcnt); + refcount_inc(&new->refcnt); if (!ingress) qdisc_destroy(old); @@ -850,7 +850,7 @@ skip: notify_and_destroy(net, skb, n, classid, dev->qdisc, new); if (new && !new->ops->attach) - atomic_inc(&new->refcnt); + refcount_inc(&new->refcnt); dev->qdisc = new ? : &noop_qdisc; if (new && new->ops->attach) @@ -1259,7 +1259,7 @@ replay: if (q == p || (p && check_loop(q, p, 0))) return -ELOOP; - atomic_inc(&q->refcnt); + refcount_inc(&q->refcnt); goto graft; } else { if (!q) @@ -1374,7 +1374,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, tcm->tcm_ifindex = qdisc_dev(q)->ifindex; tcm->tcm_parent = clid; tcm->tcm_handle = q->handle; - tcm->tcm_info = atomic_read(&q->refcnt); + tcm->tcm_info = refcount_read(&q->refcnt); if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; if (q->ops->dump && q->ops->dump(q, skb) < 0) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 52a2c55f6d9e..57ba406f1437 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -633,7 +633,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; dev_hold(dev); - atomic_set(&sch->refcnt, 1); + refcount_set(&sch->refcnt, 1); return sch; errout: @@ -701,7 +701,7 @@ void qdisc_destroy(struct Qdisc *qdisc) const struct Qdisc_ops *ops = qdisc->ops; if (qdisc->flags & TCQ_F_BUILTIN || - !atomic_dec_and_test(&qdisc->refcnt)) + !refcount_dec_and_test(&qdisc->refcnt)) return; #ifdef CONFIG_NET_SCHED @@ -739,7 +739,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, spin_lock_bh(root_lock); /* Prune old scheduler */ - if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1) + if (oqdisc && refcount_read(&oqdisc->refcnt) <= 1) qdisc_reset(oqdisc); /* ... and graft new one */ @@ -785,7 +785,7 @@ static void attach_default_qdiscs(struct net_device *dev) dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); dev->qdisc = txq->qdisc_sleeping; - atomic_inc(&dev->qdisc->refcnt); + refcount_inc(&dev->qdisc->refcnt); } else { qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT); if (qdisc) { -- cgit v1.2.3 From 0408c58be5a475c99b271f08d85859f7b59ec767 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:08 +0300 Subject: net, lapb: convert lapb_cb.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/lapb.h | 3 ++- net/lapb/lapb_iface.c | 6 +++--- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/lapb.h b/include/net/lapb.h index 9510f8725f03..85e773742f4e 100644 --- a/include/net/lapb.h +++ b/include/net/lapb.h @@ -1,6 +1,7 @@ #ifndef _LAPB_H #define _LAPB_H #include +#include #define LAPB_HEADER_LEN 20 /* LAPB over Ethernet + a bit more */ @@ -101,7 +102,7 @@ struct lapb_cb { struct lapb_frame frmr_data; unsigned char frmr_type; - atomic_t refcnt; + refcount_t refcnt; }; /* lapb_iface.c */ diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index b50b64ac8815..e15314e3b464 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -54,12 +54,12 @@ static void lapb_free_cb(struct lapb_cb *lapb) static __inline__ void lapb_hold(struct lapb_cb *lapb) { - atomic_inc(&lapb->refcnt); + refcount_inc(&lapb->refcnt); } static __inline__ void lapb_put(struct lapb_cb *lapb) { - if (atomic_dec_and_test(&lapb->refcnt)) + if (refcount_dec_and_test(&lapb->refcnt)) lapb_free_cb(lapb); } @@ -136,7 +136,7 @@ static struct lapb_cb *lapb_create_cb(void) lapb->mode = LAPB_DEFAULT_MODE; lapb->window = LAPB_DEFAULT_WINDOW; lapb->state = LAPB_STATE_0; - atomic_set(&lapb->refcnt, 1); + refcount_set(&lapb->refcnt, 1); out: return lapb; } -- cgit v1.2.3 From d25189ca8665e3ed493c7bc0607e62c2fcb314ad Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:09 +0300 Subject: net, ipx: convert ipx_interface.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/ipx.h | 7 ++++--- net/ipx/af_ipx.c | 6 +++--- net/ipx/ipx_proc.c | 2 +- 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/ipx.h b/include/net/ipx.h index e5cff6811b30..2de12814ab81 100644 --- a/include/net/ipx.h +++ b/include/net/ipx.h @@ -14,6 +14,7 @@ #include #include #include +#include struct ipx_address { __be32 net; @@ -54,7 +55,7 @@ struct ipx_interface { /* IPX address */ __be32 if_netnum; unsigned char if_node[IPX_NODE_LEN]; - atomic_t refcnt; + refcount_t refcnt; /* physical device info */ struct net_device *if_dev; @@ -139,7 +140,7 @@ const char *ipx_device_name(struct ipx_interface *intrfc); static __inline__ void ipxitf_hold(struct ipx_interface *intrfc) { - atomic_inc(&intrfc->refcnt); + refcount_inc(&intrfc->refcnt); } void ipxitf_down(struct ipx_interface *intrfc); @@ -157,7 +158,7 @@ int ipxrtr_ioctl(unsigned int cmd, void __user *arg); static __inline__ void ipxitf_put(struct ipx_interface *intrfc) { - if (atomic_dec_and_test(&intrfc->refcnt)) + if (refcount_dec_and_test(&intrfc->refcnt)) ipxitf_down(intrfc); } diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index fa31ef29e3fa..ac598ec90589 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -308,7 +308,7 @@ void ipxitf_down(struct ipx_interface *intrfc) static void __ipxitf_put(struct ipx_interface *intrfc) { - if (atomic_dec_and_test(&intrfc->refcnt)) + if (refcount_dec_and_test(&intrfc->refcnt)) __ipxitf_down(intrfc); } @@ -876,7 +876,7 @@ static struct ipx_interface *ipxitf_alloc(struct net_device *dev, __be32 netnum, intrfc->if_ipx_offset = ipx_offset; intrfc->if_sknum = IPX_MIN_EPHEMERAL_SOCKET; INIT_HLIST_HEAD(&intrfc->if_sklist); - atomic_set(&intrfc->refcnt, 1); + refcount_set(&intrfc->refcnt, 1); spin_lock_init(&intrfc->if_sklist_lock); } @@ -1105,7 +1105,7 @@ static struct ipx_interface *ipxitf_auto_create(struct net_device *dev, memcpy((char *)&(intrfc->if_node[IPX_NODE_LEN-dev->addr_len]), dev->dev_addr, dev->addr_len); spin_lock_init(&intrfc->if_sklist_lock); - atomic_set(&intrfc->refcnt, 1); + refcount_set(&intrfc->refcnt, 1); ipxitf_insert(intrfc); dev_hold(dev); } diff --git a/net/ipx/ipx_proc.c b/net/ipx/ipx_proc.c index c1d247ebe916..7d75e4c5c75d 100644 --- a/net/ipx/ipx_proc.c +++ b/net/ipx/ipx_proc.c @@ -53,7 +53,7 @@ static int ipx_seq_interface_show(struct seq_file *seq, void *v) seq_printf(seq, "%-11s", ipx_device_name(i)); seq_printf(seq, "%-9s", ipx_frame_name(i->if_dlink_type)); #ifdef IPX_REFCNT_DEBUG - seq_printf(seq, "%6d", atomic_read(&i->refcnt)); + seq_printf(seq, "%6d", refcount_read(&i->refcnt)); #endif seq_puts(seq, "\n"); out: -- cgit v1.2.3 From 16f73c964956e0f78669f1681191093dd030c9ee Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:10 +0300 Subject: net, ipx: convert ipx_route.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/ipx.h | 6 +++--- net/ipx/ipx_route.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/ipx.h b/include/net/ipx.h index 2de12814ab81..af32b97b5ddd 100644 --- a/include/net/ipx.h +++ b/include/net/ipx.h @@ -81,7 +81,7 @@ struct ipx_route { unsigned char ir_routed; unsigned char ir_router_node[IPX_NODE_LEN]; struct list_head node; /* node in ipx_routes list */ - atomic_t refcnt; + refcount_t refcnt; }; struct ipx_cb { @@ -164,12 +164,12 @@ static __inline__ void ipxitf_put(struct ipx_interface *intrfc) static __inline__ void ipxrtr_hold(struct ipx_route *rt) { - atomic_inc(&rt->refcnt); + refcount_inc(&rt->refcnt); } static __inline__ void ipxrtr_put(struct ipx_route *rt) { - if (atomic_dec_and_test(&rt->refcnt)) + if (refcount_dec_and_test(&rt->refcnt)) kfree(rt); } #endif /* _NET_INET_IPX_H_ */ diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c index 3e2a32a9f3bd..b5d91447f3dc 100644 --- a/net/ipx/ipx_route.c +++ b/net/ipx/ipx_route.c @@ -59,7 +59,7 @@ int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc, if (!rt) goto out; - atomic_set(&rt->refcnt, 1); + refcount_set(&rt->refcnt, 1); ipxrtr_hold(rt); write_lock_bh(&ipx_routes_lock); list_add(&rt->node, &ipx_routes); -- cgit v1.2.3 From af4207494d9c8e089df80e9c1ceac44f2b3e7b53 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:11 +0300 Subject: net, netrom: convert nr_neigh.refcount from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/netrom.h | 7 ++++--- net/netrom/nr_route.c | 4 ++-- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/netrom.h b/include/net/netrom.h index 110350aca3df..cecb4fde0243 100644 --- a/include/net/netrom.h +++ b/include/net/netrom.h @@ -11,6 +11,7 @@ #include #include #include +#include #define NR_NETWORK_LEN 15 #define NR_TRANSPORT_LEN 5 @@ -93,7 +94,7 @@ struct nr_neigh { unsigned short count; unsigned int number; unsigned char failed; - atomic_t refcount; + refcount_t refcount; }; struct nr_route { @@ -128,11 +129,11 @@ static __inline__ void nr_node_put(struct nr_node *nr_node) } #define nr_neigh_hold(__nr_neigh) \ - atomic_inc(&((__nr_neigh)->refcount)) + refcount_inc(&((__nr_neigh)->refcount)) static __inline__ void nr_neigh_put(struct nr_neigh *nr_neigh) { - if (atomic_dec_and_test(&nr_neigh->refcount)) { + if (refcount_dec_and_test(&nr_neigh->refcount)) { if (nr_neigh->ax25) ax25_cb_put(nr_neigh->ax25); kfree(nr_neigh->digipeat); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index d72a4f1558f2..6b72970a0d6a 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -149,7 +149,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_neigh->count = 0; nr_neigh->number = nr_neigh_no++; nr_neigh->failed = 0; - atomic_set(&nr_neigh->refcount, 1); + refcount_set(&nr_neigh->refcount, 1); if (ax25_digi != NULL && ax25_digi->ndigi > 0) { nr_neigh->digipeat = kmemdup(ax25_digi, @@ -431,7 +431,7 @@ static int __must_check nr_add_neigh(ax25_address *callsign, nr_neigh->count = 0; nr_neigh->number = nr_neigh_no++; nr_neigh->failed = 0; - atomic_set(&nr_neigh->refcount, 1); + refcount_set(&nr_neigh->refcount, 1); if (ax25_digi != NULL && ax25_digi->ndigi > 0) { nr_neigh->digipeat = kmemdup(ax25_digi, sizeof(*ax25_digi), -- cgit v1.2.3 From 156be7edc85b4aeb0f31029f4d60c3de0c997f27 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:12 +0300 Subject: net, netrom: convert nr_node.refcount from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/netrom.h | 6 +++--- net/netrom/nr_route.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/netrom.h b/include/net/netrom.h index cecb4fde0243..443a4ffca7aa 100644 --- a/include/net/netrom.h +++ b/include/net/netrom.h @@ -110,7 +110,7 @@ struct nr_node { unsigned char which; unsigned char count; struct nr_route routes[3]; - atomic_t refcount; + refcount_t refcount; spinlock_t node_lock; }; @@ -119,11 +119,11 @@ struct nr_node { *********************************************************************/ #define nr_node_hold(__nr_node) \ - atomic_inc(&((__nr_node)->refcount)) + refcount_inc(&((__nr_node)->refcount)) static __inline__ void nr_node_put(struct nr_node *nr_node) { - if (atomic_dec_and_test(&nr_node->refcount)) { + if (refcount_dec_and_test(&nr_node->refcount)) { kfree(nr_node); } } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 6b72970a0d6a..0c59354e280e 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -184,7 +184,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_node->which = 0; nr_node->count = 1; - atomic_set(&nr_node->refcount, 1); + refcount_set(&nr_node->refcount, 1); spin_lock_init(&nr_node->node_lock); nr_node->routes[0].quality = quality; -- cgit v1.2.3 From 5f9ccf6f38a1cfbaf6920b843c09d4e847a89e98 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:19 +0300 Subject: net, x25: convert x25_route.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/x25.h | 7 ++++--- net/x25/x25_route.c | 2 +- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/x25.h b/include/net/x25.h index 6d30a01d281d..1ac14006bf78 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -11,6 +11,7 @@ #define _X25_H #include #include +#include #include #define X25_ADDR_LEN 16 @@ -129,7 +130,7 @@ struct x25_route { struct x25_address address; unsigned int sigdigits; struct net_device *dev; - atomic_t refcnt; + refcount_t refcnt; }; struct x25_neigh { @@ -265,12 +266,12 @@ void x25_route_free(void); static __inline__ void x25_route_hold(struct x25_route *rt) { - atomic_inc(&rt->refcnt); + refcount_inc(&rt->refcnt); } static __inline__ void x25_route_put(struct x25_route *rt) { - if (atomic_dec_and_test(&rt->refcnt)) + if (refcount_dec_and_test(&rt->refcnt)) kfree(rt); } diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c index 277c8d2448d6..b85b889596e5 100644 --- a/net/x25/x25_route.c +++ b/net/x25/x25_route.c @@ -55,7 +55,7 @@ static int x25_add_route(struct x25_address *address, unsigned int sigdigits, rt->sigdigits = sigdigits; rt->dev = dev; - atomic_set(&rt->refcnt, 1); + refcount_set(&rt->refcnt, 1); list_add(&rt->node, &x25_route_list); rc = 0; -- cgit v1.2.3 From 5534a51ab79f8925ee33d9830646f5e6df27eb54 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:20 +0300 Subject: net, x25: convert x25_neigh.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/x25.h | 6 +++--- net/x25/x25_link.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/x25.h b/include/net/x25.h index 1ac14006bf78..2609b57bd459 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -142,7 +142,7 @@ struct x25_neigh { unsigned long t20; struct timer_list t20timer; unsigned long global_facil_mask; - atomic_t refcnt; + refcount_t refcnt; }; struct x25_sock { @@ -243,12 +243,12 @@ void x25_link_free(void); /* x25_neigh.c */ static __inline__ void x25_neigh_hold(struct x25_neigh *nb) { - atomic_inc(&nb->refcnt); + refcount_inc(&nb->refcnt); } static __inline__ void x25_neigh_put(struct x25_neigh *nb) { - if (atomic_dec_and_test(&nb->refcnt)) + if (refcount_dec_and_test(&nb->refcnt)) kfree(nb); } diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index bcaa180d6a3f..e0cd04d28352 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -266,7 +266,7 @@ void x25_link_device_up(struct net_device *dev) X25_MASK_PACKET_SIZE | X25_MASK_WINDOW_SIZE; nb->t20 = sysctl_x25_restart_request_timeout; - atomic_set(&nb->refcnt, 1); + refcount_set(&nb->refcnt, 1); write_lock_bh(&x25_neigh_list_lock); list_add(&nb->node, &x25_neigh_list); -- cgit v1.2.3 From 88755e9c7c0027fb432ac808326103bc9438d5ea Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:21 +0300 Subject: net, xfrm: convert xfrm_state.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/xfrm.h | 9 +++++---- net/xfrm/xfrm_state.c | 4 ++-- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 01fa357e9a32..f5272a275e8f 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -137,7 +138,7 @@ struct xfrm_state { struct hlist_node bysrc; struct hlist_node byspi; - atomic_t refcnt; + refcount_t refcnt; spinlock_t lock; struct xfrm_id id; @@ -837,18 +838,18 @@ void __xfrm_state_destroy(struct xfrm_state *); static inline void __xfrm_state_put(struct xfrm_state *x) { - atomic_dec(&x->refcnt); + refcount_dec(&x->refcnt); } static inline void xfrm_state_put(struct xfrm_state *x) { - if (atomic_dec_and_test(&x->refcnt)) + if (refcount_dec_and_test(&x->refcnt)) __xfrm_state_destroy(x); } static inline void xfrm_state_hold(struct xfrm_state *x) { - atomic_inc(&x->refcnt); + refcount_inc(&x->refcnt); } static inline bool addr_match(const void *token1, const void *token2, diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 4a28f669c915..6c0956d10db6 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -48,7 +48,7 @@ static HLIST_HEAD(xfrm_state_gc_list); static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x) { - return atomic_inc_not_zero(&x->refcnt); + return refcount_inc_not_zero(&x->refcnt); } static inline unsigned int xfrm_dst_hash(struct net *net, @@ -558,7 +558,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) if (x) { write_pnet(&x->xs_net, net); - atomic_set(&x->refcnt, 1); + refcount_set(&x->refcnt, 1); atomic_set(&x->tunnel_users, 0); INIT_LIST_HEAD(&x->km.all); INIT_HLIST_NODE(&x->bydst); -- cgit v1.2.3 From 850a6212c6fa151076dca045821c75025723bc46 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:22 +0300 Subject: net, xfrm: convert xfrm_policy.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/xfrm.h | 6 +++--- net/key/af_key.c | 2 +- net/xfrm/xfrm_policy.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index f5272a275e8f..e1bd1de2d66a 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -560,7 +560,7 @@ struct xfrm_policy { /* This lock only affects elements except for entry. */ rwlock_t lock; - atomic_t refcnt; + refcount_t refcnt; struct timer_list timer; struct flow_cache_object flo; @@ -816,14 +816,14 @@ static inline void xfrm_audit_state_icvfail(struct xfrm_state *x, static inline void xfrm_pol_hold(struct xfrm_policy *policy) { if (likely(policy != NULL)) - atomic_inc(&policy->refcnt); + refcount_inc(&policy->refcnt); } void xfrm_policy_destroy(struct xfrm_policy *policy); static inline void xfrm_pol_put(struct xfrm_policy *policy) { - if (atomic_dec_and_test(&policy->refcnt)) + if (refcount_dec_and_test(&policy->refcnt)) xfrm_policy_destroy(policy); } diff --git a/net/key/af_key.c b/net/key/af_key.c index edcf1d0f82c8..ca9d3ae665e7 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2177,7 +2177,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, const struct xfrm_policy * } hdr->sadb_msg_len = size / sizeof(uint64_t); - hdr->sadb_msg_reserved = atomic_read(&xp->refcnt); + hdr->sadb_msg_reserved = refcount_read(&xp->refcnt); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 4706df612170..ff61d8557929 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -62,7 +62,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy) { - return atomic_inc_not_zero(&policy->refcnt); + return refcount_inc_not_zero(&policy->refcnt); } static inline bool @@ -292,7 +292,7 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) INIT_HLIST_NODE(&policy->bydst); INIT_HLIST_NODE(&policy->byidx); rwlock_init(&policy->lock); - atomic_set(&policy->refcnt, 1); + refcount_set(&policy->refcnt, 1); skb_queue_head_init(&policy->polq.hold_queue); setup_timer(&policy->timer, xfrm_policy_timer, (unsigned long)policy); -- cgit v1.2.3 From 55eabed60a68e918abc44f6beb64f38cc008b29d Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:23 +0300 Subject: net, xfrm: convert sec_path.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/xfrm.h | 6 +++--- net/xfrm/xfrm_input.c | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index e1bd1de2d66a..c0916ab18d32 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1030,7 +1030,7 @@ struct xfrm_offload { }; struct sec_path { - atomic_t refcnt; + refcount_t refcnt; int len; int olen; @@ -1051,7 +1051,7 @@ static inline struct sec_path * secpath_get(struct sec_path *sp) { if (sp) - atomic_inc(&sp->refcnt); + refcount_inc(&sp->refcnt); return sp; } @@ -1060,7 +1060,7 @@ void __secpath_destroy(struct sec_path *sp); static inline void secpath_put(struct sec_path *sp) { - if (sp && atomic_dec_and_test(&sp->refcnt)) + if (sp && refcount_dec_and_test(&sp->refcnt)) __secpath_destroy(sp); } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 9de4b1dbc0ae..923205e279f7 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -116,7 +116,7 @@ struct sec_path *secpath_dup(struct sec_path *src) for (i = 0; i < sp->len; i++) xfrm_state_hold(sp->xvec[i]); } - atomic_set(&sp->refcnt, 1); + refcount_set(&sp->refcnt, 1); return sp; } EXPORT_SYMBOL(secpath_dup); @@ -126,7 +126,7 @@ int secpath_set(struct sk_buff *skb) struct sec_path *sp; /* Allocate new secpath or COW existing one. */ - if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) { + if (!skb->sp || refcount_read(&skb->sp->refcnt) != 1) { sp = secpath_dup(skb->sp); if (!sp) return -ENOMEM; -- cgit v1.2.3 From 6871584a5e493a9fa3ad330a73966908b082deac Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:24 +0300 Subject: net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/sctp/auth.h | 5 +++-- net/sctp/auth.c | 4 ++-- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/auth.h b/include/net/sctp/auth.h index 171244bd856f..e5c57d0a082d 100644 --- a/include/net/sctp/auth.h +++ b/include/net/sctp/auth.h @@ -31,6 +31,7 @@ #define __sctp_auth_h__ #include +#include struct sctp_endpoint; struct sctp_association; @@ -53,7 +54,7 @@ struct sctp_hmac { * over SCTP-AUTH */ struct sctp_auth_bytes { - atomic_t refcnt; + refcount_t refcnt; __u32 len; __u8 data[]; }; @@ -76,7 +77,7 @@ static inline void sctp_auth_key_hold(struct sctp_auth_bytes *key) if (!key) return; - atomic_inc(&key->refcnt); + refcount_inc(&key->refcnt); } void sctp_auth_key_put(struct sctp_auth_bytes *key); diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 8ffa5985cd6e..e001b01b0e68 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -63,7 +63,7 @@ void sctp_auth_key_put(struct sctp_auth_bytes *key) if (!key) return; - if (atomic_dec_and_test(&key->refcnt)) { + if (refcount_dec_and_test(&key->refcnt)) { kzfree(key); SCTP_DBG_OBJCNT_DEC(keys); } @@ -84,7 +84,7 @@ static struct sctp_auth_bytes *sctp_auth_create_key(__u32 key_len, gfp_t gfp) return NULL; key->len = key_len; - atomic_set(&key->refcnt, 1); + refcount_set(&key->refcnt, 1); SCTP_DBG_OBJCNT_INC(keys); return key; -- cgit v1.2.3 From c0acdfb409c82047853df1e5f3dbdbe4005c78ae Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:25 +0300 Subject: net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 +- net/sctp/chunk.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 07c11fefa8c4..4d7c855d8443 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -496,7 +496,7 @@ struct sctp_datamsg { /* Chunks waiting to be submitted to lower layer. */ struct list_head chunks; /* Reference counting. */ - atomic_t refcnt; + refcount_t refcnt; /* When is this message no longer interesting to the peer? */ unsigned long expires_at; /* Did the messenge fail to send? */ diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 81466f6442e8..1323d41e68b8 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -49,7 +49,7 @@ /* Initialize datamsg from memory. */ static void sctp_datamsg_init(struct sctp_datamsg *msg) { - atomic_set(&msg->refcnt, 1); + refcount_set(&msg->refcnt, 1); msg->send_failed = 0; msg->send_error = 0; msg->can_delay = 1; @@ -136,13 +136,13 @@ static void sctp_datamsg_destroy(struct sctp_datamsg *msg) /* Hold a reference. */ static void sctp_datamsg_hold(struct sctp_datamsg *msg) { - atomic_inc(&msg->refcnt); + refcount_inc(&msg->refcnt); } /* Release a reference. */ void sctp_datamsg_put(struct sctp_datamsg *msg) { - if (atomic_dec_and_test(&msg->refcnt)) + if (refcount_dec_and_test(&msg->refcnt)) sctp_datamsg_destroy(msg); } -- cgit v1.2.3 From e7f027961759f334bcc939980ec35480faa7ef17 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:26 +0300 Subject: net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 +- net/sctp/sm_make_chunk.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 4d7c855d8443..0dfc5c14b696 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -524,7 +524,7 @@ int sctp_chunk_abandoned(struct sctp_chunk *); struct sctp_chunk { struct list_head list; - atomic_t refcnt; + refcount_t refcnt; /* How many times this chunk have been sent, for prsctp RTX policy */ int sent_count; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 3af4dd024ec0..4e16b02ed832 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1345,7 +1345,7 @@ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb, INIT_LIST_HEAD(&retval->transmitted_list); INIT_LIST_HEAD(&retval->frag_list); SCTP_DBG_OBJCNT_INC(chunk); - atomic_set(&retval->refcnt, 1); + refcount_set(&retval->refcnt, 1); nodata: return retval; @@ -1458,13 +1458,13 @@ void sctp_chunk_free(struct sctp_chunk *chunk) /* Grab a reference to the chunk. */ void sctp_chunk_hold(struct sctp_chunk *ch) { - atomic_inc(&ch->refcnt); + refcount_inc(&ch->refcnt); } /* Release a reference to the chunk. */ void sctp_chunk_put(struct sctp_chunk *ch) { - if (atomic_dec_and_test(&ch->refcnt)) + if (refcount_dec_and_test(&ch->refcnt)) sctp_chunk_destroy(ch); } -- cgit v1.2.3 From a4b2b58efd44db68358e1a6b71cf205c795d7ada Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:27 +0300 Subject: net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 +- net/sctp/transport.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 0dfc5c14b696..6a0d37258506 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -735,7 +735,7 @@ struct sctp_transport { struct rhlist_head node; /* Reference counting. */ - atomic_t refcnt; + refcount_t refcnt; /* RTO-Pending : A flag used to track if one of the DATA * chunks sent to this address is currently being * used to compute a RTT. If this flag is 0, diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 7cdd6bcddbc5..80a97c8501a7 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -99,7 +99,7 @@ static struct sctp_transport *sctp_transport_init(struct net *net, /* Initialize the 64-bit random nonce sent with heartbeat. */ get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce)); - atomic_set(&peer->refcnt, 1); + refcount_set(&peer->refcnt, 1); return peer; } @@ -172,7 +172,7 @@ static void sctp_transport_destroy_rcu(struct rcu_head *head) */ static void sctp_transport_destroy(struct sctp_transport *transport) { - if (unlikely(atomic_read(&transport->refcnt))) { + if (unlikely(refcount_read(&transport->refcnt))) { WARN(1, "Attempt to destroy undead transport %p!\n", transport); return; } @@ -311,7 +311,7 @@ void sctp_transport_route(struct sctp_transport *transport, /* Hold a reference to a transport. */ int sctp_transport_hold(struct sctp_transport *transport) { - return atomic_add_unless(&transport->refcnt, 1, 0); + return refcount_inc_not_zero(&transport->refcnt); } /* Release a reference to a transport and clean up @@ -319,7 +319,7 @@ int sctp_transport_hold(struct sctp_transport *transport) */ void sctp_transport_put(struct sctp_transport *transport) { - if (atomic_dec_and_test(&transport->refcnt)) + if (refcount_dec_and_test(&transport->refcnt)) sctp_transport_destroy(transport); } -- cgit v1.2.3 From c638457a7c6b8931cd4586d6a13a33887185342d Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:28 +0300 Subject: net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 +- net/sctp/associola.c | 6 +++--- net/sctp/endpointola.c | 6 +++--- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 6a0d37258506..5ab29af8ca8a 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1174,7 +1174,7 @@ struct sctp_ep_common { * refcnt - Reference count access to this object. * dead - Do not attempt to use this object. */ - atomic_t refcnt; + refcount_t refcnt; bool dead; /* What socket does this endpoint belong to? */ diff --git a/net/sctp/associola.c b/net/sctp/associola.c index fa4f530ab7e1..40ec83679d6e 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -88,7 +88,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->base.type = SCTP_EP_TYPE_ASSOCIATION; /* Initialize the object handling fields. */ - atomic_set(&asoc->base.refcnt, 1); + refcount_set(&asoc->base.refcnt, 1); /* Initialize the bind addr area. */ sctp_bind_addr_init(&asoc->base.bind_addr, ep->base.bind_addr.port); @@ -873,7 +873,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, /* Hold a reference to an association. */ void sctp_association_hold(struct sctp_association *asoc) { - atomic_inc(&asoc->base.refcnt); + refcount_inc(&asoc->base.refcnt); } /* Release a reference to an association and cleanup @@ -881,7 +881,7 @@ void sctp_association_hold(struct sctp_association *asoc) */ void sctp_association_put(struct sctp_association *asoc) { - if (atomic_dec_and_test(&asoc->base.refcnt)) + if (refcount_dec_and_test(&asoc->base.refcnt)) sctp_association_destroy(asoc); } diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index efbc31877804..0e86f988f836 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -114,7 +114,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, ep->base.type = SCTP_EP_TYPE_SOCKET; /* Initialize the basic object fields. */ - atomic_set(&ep->base.refcnt, 1); + refcount_set(&ep->base.refcnt, 1); ep->base.dead = false; /* Create an input queue. */ @@ -285,7 +285,7 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) /* Hold a reference to an endpoint. */ void sctp_endpoint_hold(struct sctp_endpoint *ep) { - atomic_inc(&ep->base.refcnt); + refcount_inc(&ep->base.refcnt); } /* Release a reference to an endpoint and clean up if there are @@ -293,7 +293,7 @@ void sctp_endpoint_hold(struct sctp_endpoint *ep) */ void sctp_endpoint_put(struct sctp_endpoint *ep) { - if (atomic_dec_and_test(&ep->base.refcnt)) + if (refcount_dec_and_test(&ep->base.refcnt)) sctp_endpoint_destroy(ep); } -- cgit v1.2.3 From 07f2282fc6a169980b08cedf3beaf8334b7b9dde Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:29 +0300 Subject: net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/ax25.h | 8 ++++---- net/ax25/ax25_uid.c | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/ax25.h b/include/net/ax25.h index e602f8177ebf..edd82f0a4d27 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include @@ -158,7 +158,7 @@ enum { typedef struct ax25_uid_assoc { struct hlist_node uid_node; - atomic_t refcount; + refcount_t refcount; kuid_t uid; ax25_address call; } ax25_uid_assoc; @@ -167,11 +167,11 @@ typedef struct ax25_uid_assoc { hlist_for_each_entry(__ax25, list, uid_node) #define ax25_uid_hold(ax25) \ - atomic_inc(&((ax25)->refcount)) + refcount_inc(&((ax25)->refcount)) static inline void ax25_uid_put(ax25_uid_assoc *assoc) { - if (atomic_dec_and_test(&assoc->refcount)) { + if (refcount_dec_and_test(&assoc->refcount)) { kfree(assoc); } } diff --git a/net/ax25/ax25_uid.c b/net/ax25/ax25_uid.c index 0403b0def7e6..83b035f56202 100644 --- a/net/ax25/ax25_uid.c +++ b/net/ax25/ax25_uid.c @@ -107,7 +107,7 @@ int ax25_uid_ioctl(int cmd, struct sockaddr_ax25 *sax) if ((ax25_uid = kmalloc(sizeof(*ax25_uid), GFP_KERNEL)) == NULL) return -ENOMEM; - atomic_set(&ax25_uid->refcount, 1); + refcount_set(&ax25_uid->refcount, 1); ax25_uid->uid = sax25_kuid; ax25_uid->call = sax->sax25_call; -- cgit v1.2.3 From 39f25d42c04959f0ddb5b14b01b27ea221736509 Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:30 +0300 Subject: net, ax25: convert ax25_route.refcount from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/ax25.h | 6 +++--- net/ax25/ax25_route.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/ax25.h b/include/net/ax25.h index edd82f0a4d27..e3467ba81f6e 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -185,7 +185,7 @@ typedef struct { typedef struct ax25_route { struct ax25_route *next; - atomic_t refcount; + refcount_t refcount; ax25_address callsign; struct net_device *dev; ax25_digi *digipeat; @@ -194,14 +194,14 @@ typedef struct ax25_route { static inline void ax25_hold_route(ax25_route *ax25_rt) { - atomic_inc(&ax25_rt->refcount); + refcount_inc(&ax25_rt->refcount); } void __ax25_put_route(ax25_route *ax25_rt); static inline void ax25_put_route(ax25_route *ax25_rt) { - if (atomic_dec_and_test(&ax25_rt->refcount)) + if (refcount_dec_and_test(&ax25_rt->refcount)) __ax25_put_route(ax25_rt); } diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index e1fda27cb27c..0446b892618a 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -114,7 +114,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) return -ENOMEM; } - atomic_set(&ax25_rt->refcount, 1); + refcount_set(&ax25_rt->refcount, 1); ax25_rt->callsign = route->dest_addr; ax25_rt->dev = ax25_dev->dev; ax25_rt->digipeat = NULL; -- cgit v1.2.3 From b6d52ede224836f74dff50666b6a3076a5b8c92d Mon Sep 17 00:00:00 2001 From: "Reshetova, Elena" Date: Tue, 4 Jul 2017 15:53:31 +0300 Subject: net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Signed-off-by: David S. Miller --- include/net/ax25.h | 6 +++--- net/ax25/af_ax25.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/ax25.h b/include/net/ax25.h index e3467ba81f6e..c4a0cf6f0810 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -244,7 +244,7 @@ typedef struct ax25_cb { unsigned char window; struct timer_list timer, dtimer; struct sock *sk; /* Backlink to socket */ - atomic_t refcount; + refcount_t refcount; } ax25_cb; struct ax25_sock { @@ -266,11 +266,11 @@ static inline struct ax25_cb *sk_to_ax25(const struct sock *sk) hlist_for_each_entry(__ax25, list, ax25_node) #define ax25_cb_hold(__ax25) \ - atomic_inc(&((__ax25)->refcount)) + refcount_inc(&((__ax25)->refcount)) static __inline__ void ax25_cb_put(ax25_cb *ax25) { - if (atomic_dec_and_test(&ax25->refcount)) { + if (refcount_dec_and_test(&ax25->refcount)) { kfree(ax25->digipeat); kfree(ax25); } diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 0c92ba0cbe0b..f3f9d18891de 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -510,7 +510,7 @@ ax25_cb *ax25_create_cb(void) if ((ax25 = kzalloc(sizeof(*ax25), GFP_ATOMIC)) == NULL) return NULL; - atomic_set(&ax25->refcount, 1); + refcount_set(&ax25->refcount, 1); skb_queue_head_init(&ax25->write_queue); skb_queue_head_init(&ax25->frag_queue); -- cgit v1.2.3 From f06b7549b79e29a672336d4e134524373fb7a232 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 5 Jul 2017 14:41:46 -0600 Subject: net: ipv6: Compare lwstate in detecting duplicate nexthops MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Lennert reported a failure to add different mpls encaps in a multipath route: $ ip -6 route add 1234::/16 \ nexthop encap mpls 10 via fe80::1 dev ens3 \ nexthop encap mpls 20 via fe80::1 dev ens3 RTNETLINK answers: File exists The problem is that the duplicate nexthop detection does not compare lwtunnel configuration. Add it. Fixes: 19e42e451506 ("ipv6: support for fib route lwtunnel encap attributes") Signed-off-by: David Ahern Reported-by: João Taveira Araújo Reported-by: Lennert Buytenhek Acked-by: Roopa Prabhu Tested-by: Lennert Buytenhek Signed-off-by: David S. Miller --- include/net/ip6_route.h | 8 ++++++++ net/ipv6/ip6_fib.c | 5 +---- net/ipv6/route.c | 8 +------- 3 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 0fbf73dd531a..199056933dcb 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -22,6 +22,7 @@ struct route_info { #include #include #include +#include #include #include #include @@ -232,4 +233,11 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, return daddr; } +static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b) +{ + return a->dst.dev == b->dst.dev && + a->rt6i_idev == b->rt6i_idev && + ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) && + !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate); +} #endif diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5477ba729c36..ebb299cf72b7 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -786,10 +786,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, goto next_iter; } - if (iter->dst.dev == rt->dst.dev && - iter->rt6i_idev == rt->rt6i_idev && - ipv6_addr_equal(&iter->rt6i_gateway, - &rt->rt6i_gateway)) { + if (rt6_duplicate_nexthop(iter, rt)) { if (rt->rt6i_nsiblings) rt->rt6i_nsiblings = 0; if (!(iter->rt6i_flags & RTF_EXPIRES)) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0488a24c2a44..4d30c96a819d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3036,17 +3036,11 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list, struct rt6_info *rt, struct fib6_config *r_cfg) { struct rt6_nh *nh; - struct rt6_info *rtnh; int err = -EEXIST; list_for_each_entry(nh, rt6_nh_list, next) { /* check if rt6_info already exists */ - rtnh = nh->rt6_info; - - if (rtnh->dst.dev == rt->dst.dev && - rtnh->rt6i_idev == rt->rt6i_idev && - ipv6_addr_equal(&rtnh->rt6i_gateway, - &rt->rt6i_gateway)) + if (rt6_duplicate_nexthop(nh->rt6_info, rt)) return err; } -- cgit v1.2.3 From 0ffdaf5b41cf4435ece14d1d3e977ce69012a20d Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Thu, 6 Jul 2017 08:15:07 -0700 Subject: net/sock: add WARN_ON(parent->sk) in sock_graft() sock_graft() unilaterally sets up parent->sk based on the assumption that the existing parent->sk is null. If this condition is not true, then the existing parent->sk would be leaked, so add a WARN_ON() to alert callers who may fall in this category. Signed-off-by: Sowmini Varadhan Signed-off-by: David S. Miller --- include/net/sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 48e4d5c38f85..8c85791fc196 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1697,6 +1697,7 @@ static inline void sock_orphan(struct sock *sk) static inline void sock_graft(struct sock *sk, struct socket *parent) { + WARN_ON(parent->sk); write_lock_bh(&sk->sk_callback_lock); sk->sk_wq = parent->wq; parent->sk = sk; -- cgit v1.2.3 From c4fac9100456995c10b65c13be84554258ed7fc8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 5 Jul 2017 16:25:37 +0100 Subject: 9p: Implement show_options Implement the show_options superblock op for 9p as part of a bid to get rid of s_options and generic_show_options() to make it easier to implement a context-based mount where the mount options can be passed individually over a file descriptor. Signed-off-by: David Howells cc: Eric Van Hensbergen cc: Ron Minnich cc: Latchesar Ionkov cc: v9fs-developer@lists.sourceforge.net Signed-off-by: Al Viro --- fs/9p/v9fs.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++ fs/9p/v9fs.h | 3 +++ fs/9p/vfs_super.c | 6 ++--- include/net/9p/client.h | 13 ++++++++++ include/net/9p/transport.h | 1 + net/9p/client.c | 25 +++++++++++++++++++ net/9p/trans_fd.c | 31 ++++++++++++++++++++--- net/9p/trans_rdma.c | 31 ++++++++++++++++++++--- 8 files changed, 161 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index c202930086ed..8fb89ddc6cc7 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -82,6 +83,13 @@ static const match_table_t tokens = { {Opt_err, NULL} }; +static const char *const v9fs_cache_modes[nr__p9_cache_modes] = { + [CACHE_NONE] = "none", + [CACHE_MMAP] = "mmap", + [CACHE_LOOSE] = "loose", + [CACHE_FSCACHE] = "fscache", +}; + /* Interpret mount options for cache mode */ static int get_cache_mode(char *s) { @@ -104,6 +112,58 @@ static int get_cache_mode(char *s) return version; } +/* + * Display the mount options in /proc/mounts. + */ +int v9fs_show_options(struct seq_file *m, struct dentry *root) +{ + struct v9fs_session_info *v9ses = root->d_sb->s_fs_info; + + if (v9ses->debug) + seq_printf(m, ",debug=%x", v9ses->debug); + if (!uid_eq(v9ses->dfltuid, V9FS_DEFUID)) + seq_printf(m, ",dfltuid=%u", + from_kuid_munged(&init_user_ns, v9ses->dfltuid)); + if (!gid_eq(v9ses->dfltgid, V9FS_DEFGID)) + seq_printf(m, ",dfltgid=%u", + from_kgid_munged(&init_user_ns, v9ses->dfltgid)); + if (v9ses->afid != ~0) + seq_printf(m, ",afid=%u", v9ses->afid); + if (strcmp(v9ses->uname, V9FS_DEFUSER) != 0) + seq_printf(m, ",uname=%s", v9ses->uname); + if (strcmp(v9ses->aname, V9FS_DEFANAME) != 0) + seq_printf(m, ",aname=%s", v9ses->aname); + if (v9ses->nodev) + seq_puts(m, ",nodevmap"); + if (v9ses->cache) + seq_printf(m, ",%s", v9fs_cache_modes[v9ses->cache]); +#ifdef CONFIG_9P_FSCACHE + if (v9ses->cachetag && v9ses->cache == CACHE_FSCACHE) + seq_printf(m, ",cachetag=%s", v9ses->cachetag); +#endif + + switch (v9ses->flags & V9FS_ACCESS_MASK) { + case V9FS_ACCESS_USER: + seq_puts(m, ",access=user"); + break; + case V9FS_ACCESS_ANY: + seq_puts(m, ",access=any"); + break; + case V9FS_ACCESS_CLIENT: + seq_puts(m, ",access=client"); + break; + case V9FS_ACCESS_SINGLE: + seq_printf(m, ",access=%u", + from_kuid_munged(&init_user_ns, v9ses->uid)); + break; + } + + if (v9ses->flags & V9FS_POSIX_ACL) + seq_puts(m, ",posixacl"); + + return p9_show_client_options(m, v9ses->clnt); +} + /** * v9fs_parse_options - parse mount options into session structure * @v9ses: existing v9fs session information @@ -230,6 +290,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) break; case Opt_cachetag: #ifdef CONFIG_9P_FSCACHE + kfree(v9ses->cachetag); v9ses->cachetag = match_strdup(&args[0]); #endif break; diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 76eaf49abd3a..982e017acadb 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -67,6 +67,7 @@ enum p9_cache_modes { CACHE_MMAP, CACHE_LOOSE, CACHE_FSCACHE, + nr__p9_cache_modes }; /** @@ -137,6 +138,8 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode) return container_of(inode, struct v9fs_inode, vfs_inode); } +extern int v9fs_show_options(struct seq_file *m, struct dentry *root); + struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *, char *); extern void v9fs_session_close(struct v9fs_session_info *v9ses); diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index a0965fb587a5..8b75463cb211 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include #include @@ -104,7 +103,6 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, sb->s_flags |= MS_POSIXACL; #endif - save_mount_options(sb, data); return 0; } @@ -349,7 +347,7 @@ static const struct super_operations v9fs_super_ops = { .destroy_inode = v9fs_destroy_inode, .statfs = simple_statfs, .evict_inode = v9fs_evict_inode, - .show_options = generic_show_options, + .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, .write_inode = v9fs_write_inode, }; @@ -360,7 +358,7 @@ static const struct super_operations v9fs_super_ops_dotl = { .statfs = v9fs_statfs, .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, - .show_options = generic_show_options, + .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, .write_inode = v9fs_write_inode_dotl, }; diff --git a/include/net/9p/client.h b/include/net/9p/client.h index b582339ccef5..7af9d769b97d 100644 --- a/include/net/9p/client.h +++ b/include/net/9p/client.h @@ -157,6 +157,18 @@ struct p9_client { enum p9_trans_status status; void *trans; + union { + struct { + int rfd; + int wfd; + } fd; + struct { + u16 port; + bool privport; + + } tcp; + } trans_opts; + struct p9_idpool *fidpool; struct list_head fidlist; @@ -213,6 +225,7 @@ struct p9_dirent { struct iov_iter; +int p9_show_client_options(struct seq_file *m, struct p9_client *clnt); int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb); int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid, const char *name); diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h index 5122b5e40f78..1625fb842ac4 100644 --- a/include/net/9p/transport.h +++ b/include/net/9p/transport.h @@ -62,6 +62,7 @@ struct p9_trans_module { int (*cancelled)(struct p9_client *, struct p9_req_t *req); int (*zc_request)(struct p9_client *, struct p9_req_t *, struct iov_iter *, struct iov_iter *, int , int, int); + int (*show_options)(struct seq_file *, struct p9_client *); }; void v9fs_register_trans(struct p9_trans_module *m); diff --git a/net/9p/client.c b/net/9p/client.c index 1218fb3b52da..4674235b0d9b 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include "protocol.h" @@ -77,6 +78,30 @@ inline int p9_is_proto_dotu(struct p9_client *clnt) } EXPORT_SYMBOL(p9_is_proto_dotu); +int p9_show_client_options(struct seq_file *m, struct p9_client *clnt) +{ + if (clnt->msize != 8192) + seq_printf(m, ",msize=%u", clnt->msize); + seq_printf(m, "trans=%s", clnt->trans_mod->name); + + switch (clnt->proto_version) { + case p9_proto_legacy: + seq_puts(m, ",noextend"); + break; + case p9_proto_2000u: + seq_puts(m, ",version=9p2000.u"); + break; + case p9_proto_2000L: + /* Default */ + break; + } + + if (clnt->trans_mod->show_options) + return clnt->trans_mod->show_options(m, clnt); + return 0; +} +EXPORT_SYMBOL(p9_show_client_options); + /* * Some error codes are taken directly from the server replies, * make sure they are valid. diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 7bc2208b6cc4..f2e0eaf58018 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include @@ -51,6 +52,9 @@ #define MAX_SOCK_BUF (64*1024) #define MAXPOLLWADDR 2 +static struct p9_trans_module p9_tcp_trans; +static struct p9_trans_module p9_fd_trans; + /** * struct p9_fd_opts - per-transport options * @rfd: file descriptor for reading (trans=fd) @@ -63,7 +67,7 @@ struct p9_fd_opts { int rfd; int wfd; u16 port; - int privport; + bool privport; }; /* @@ -720,6 +724,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) return 0; } +static int p9_fd_show_options(struct seq_file *m, struct p9_client *clnt) +{ + if (clnt->trans_mod == &p9_tcp_trans) { + if (clnt->trans_opts.tcp.port != P9_PORT) + seq_printf(m, "port=%u", clnt->trans_opts.tcp.port); + } else if (clnt->trans_mod == &p9_fd_trans) { + if (clnt->trans_opts.fd.rfd != ~0) + seq_printf(m, "rfd=%u", clnt->trans_opts.fd.rfd); + if (clnt->trans_opts.fd.wfd != ~0) + seq_printf(m, "wfd=%u", clnt->trans_opts.fd.wfd); + } + return 0; +} + /** * parse_opts - parse mount options into p9_fd_opts structure * @params: options string passed from mount @@ -738,7 +756,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) opts->port = P9_PORT; opts->rfd = ~0; opts->wfd = ~0; - opts->privport = 0; + opts->privport = false; if (!params) return 0; @@ -776,7 +794,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts) opts->wfd = option; break; case Opt_privport: - opts->privport = 1; + opts->privport = true; break; default: continue; @@ -942,6 +960,8 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) csocket = NULL; + client->trans_opts.tcp.port = opts.port; + client->trans_opts.tcp.privport = opts.privport; sin_server.sin_family = AF_INET; sin_server.sin_addr.s_addr = in_aton(addr); sin_server.sin_port = htons(opts.port); @@ -1020,6 +1040,8 @@ p9_fd_create(struct p9_client *client, const char *addr, char *args) struct p9_fd_opts opts; parse_opts(args, &opts); + client->trans_opts.fd.rfd = opts.rfd; + client->trans_opts.fd.wfd = opts.wfd; if (opts.rfd == ~0 || opts.wfd == ~0) { pr_err("Insufficient options for proto=fd\n"); @@ -1044,6 +1066,7 @@ static struct p9_trans_module p9_tcp_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; @@ -1056,6 +1079,7 @@ static struct p9_trans_module p9_unix_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; @@ -1068,6 +1092,7 @@ static struct p9_trans_module p9_fd_trans = { .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, + .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 553ed4ecb6a0..6d8e3031978f 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -70,6 +71,8 @@ * @dm_mr: DMA Memory Region pointer * @lkey: The local access only memory region key * @timeout: Number of uSecs to wait for connection management events + * @privport: Whether a privileged port may be used + * @port: The port to use * @sq_depth: The depth of the Send Queue * @sq_sem: Semaphore for the SQ * @rq_depth: The depth of the Receive Queue. @@ -95,6 +98,8 @@ struct p9_trans_rdma { struct ib_qp *qp; struct ib_cq *cq; long timeout; + bool privport; + u16 port; int sq_depth; struct semaphore sq_sem; int rq_depth; @@ -133,10 +138,10 @@ struct p9_rdma_context { */ struct p9_rdma_opts { short port; + bool privport; int sq_depth; int rq_depth; long timeout; - int privport; }; /* @@ -159,6 +164,23 @@ static match_table_t tokens = { {Opt_err, NULL}, }; +static int p9_rdma_show_options(struct seq_file *m, struct p9_client *clnt) +{ + struct p9_trans_rdma *rdma = clnt->trans; + + if (rdma->port != P9_PORT) + seq_printf(m, ",port=%u", rdma->port); + if (rdma->sq_depth != P9_RDMA_SQ_DEPTH) + seq_printf(m, ",sq=%u", rdma->sq_depth); + if (rdma->rq_depth != P9_RDMA_RQ_DEPTH) + seq_printf(m, ",rq=%u", rdma->rq_depth); + if (rdma->timeout != P9_RDMA_TIMEOUT) + seq_printf(m, ",timeout=%lu", rdma->timeout); + if (rdma->privport) + seq_puts(m, ",privport"); + return 0; +} + /** * parse_opts - parse mount options into rdma options structure * @params: options string passed from mount @@ -177,7 +199,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) opts->sq_depth = P9_RDMA_SQ_DEPTH; opts->rq_depth = P9_RDMA_RQ_DEPTH; opts->timeout = P9_RDMA_TIMEOUT; - opts->privport = 0; + opts->privport = false; if (!params) return 0; @@ -218,7 +240,7 @@ static int parse_opts(char *params, struct p9_rdma_opts *opts) opts->timeout = option; break; case Opt_privport: - opts->privport = 1; + opts->privport = true; break; default: continue; @@ -560,6 +582,8 @@ static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts) if (!rdma) return NULL; + rdma->port = opts->port; + rdma->privport = opts->privport; rdma->sq_depth = opts->sq_depth; rdma->rq_depth = opts->rq_depth; rdma->timeout = opts->timeout; @@ -733,6 +757,7 @@ static struct p9_trans_module p9_rdma_trans = { .request = rdma_request, .cancel = rdma_cancel, .cancelled = rdma_cancelled, + .show_options = p9_rdma_show_options, }; /** -- cgit v1.2.3 From 771edcafa753aad304babd3bab8e413574d5db3b Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 12 Jul 2017 09:29:06 -0700 Subject: socket: add documentation for missing elements Fill in missing kernel-doc for missing elements in struct sock. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/sock.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 8c85791fc196..f69c8c2782df 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -246,6 +246,7 @@ struct sock_common { * @sk_policy: flow policy * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed + * @sk_tsq_flags: TCP Small Queues flags * @sk_write_queue: Packet sending queue * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size @@ -257,6 +258,7 @@ struct sock_common { * @sk_pacing_status: Pacing status (requested, handled by sch_fq) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes + * @__sk_flags_offset: empty field used to determine location of bitfield * @sk_padding: unused element for alignment * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets @@ -277,6 +279,7 @@ struct sock_common { * @sk_drops: raw/udp drops counter * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() + * @sk_uid: user id of owner * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family -- cgit v1.2.3 From 2683701201ddb9a2a4d0fda5d950ab50ca8e77e4 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Thu, 13 Jul 2017 16:46:43 +0200 Subject: netlink: correctly document nla_put_u64_64bit() Signed-off-by: Rolf Eike Beer Signed-off-by: David S. Miller --- include/net/netlink.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/netlink.h b/include/net/netlink.h index 01709172b3d3..ef8e6c3a80a6 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -98,8 +98,8 @@ * nla_put_u8(skb, type, value) add u8 attribute to skb * nla_put_u16(skb, type, value) add u16 attribute to skb * nla_put_u32(skb, type, value) add u32 attribute to skb - * nla_put_u64_64bits(skb, type, - * value, padattr) add u64 attribute to skb + * nla_put_u64_64bit(skb, type, + * value, padattr) add u64 attribute to skb * nla_put_s8(skb, type, value) add s8 attribute to skb * nla_put_s16(skb, type, value) add s16 attribute to skb * nla_put_s32(skb, type, value) add s32 attribute to skb -- cgit v1.2.3 From b1f5bfc27a19f214006b9b4db7b9126df2dfdf5a Mon Sep 17 00:00:00 2001 From: Alexander Potapenko Date: Fri, 14 Jul 2017 18:32:45 +0200 Subject: sctp: don't dereference ptr before leaving _sctp_walk_{params, errors}() If the length field of the iterator (|pos.p| or |err|) is past the end of the chunk, we shouldn't access it. This bug has been detected by KMSAN. For the following pair of system calls: socket(PF_INET6, SOCK_STREAM, 0x84 /* IPPROTO_??? */) = 3 sendto(3, "A", 1, MSG_OOB, {sa_family=AF_INET6, sin6_port=htons(0), inet_pton(AF_INET6, "::1", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, 28) = 1 the tool has reported a use of uninitialized memory: ================================================================== BUG: KMSAN: use of uninitialized memory in sctp_rcv+0x17b8/0x43b0 CPU: 1 PID: 2940 Comm: probe Not tainted 4.11.0-rc5+ #2926 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 dump_stack+0x172/0x1c0 lib/dump_stack.c:52 kmsan_report+0x12a/0x180 mm/kmsan/kmsan.c:927 __msan_warning_32+0x61/0xb0 mm/kmsan/kmsan_instr.c:469 __sctp_rcv_init_lookup net/sctp/input.c:1074 __sctp_rcv_lookup_harder net/sctp/input.c:1233 __sctp_rcv_lookup net/sctp/input.c:1255 sctp_rcv+0x17b8/0x43b0 net/sctp/input.c:170 sctp6_rcv+0x32/0x70 net/sctp/ipv6.c:984 ip6_input_finish+0x82f/0x1ee0 net/ipv6/ip6_input.c:279 NF_HOOK ./include/linux/netfilter.h:257 ip6_input+0x239/0x290 net/ipv6/ip6_input.c:322 dst_input ./include/net/dst.h:492 ip6_rcv_finish net/ipv6/ip6_input.c:69 NF_HOOK ./include/linux/netfilter.h:257 ipv6_rcv+0x1dbd/0x22e0 net/ipv6/ip6_input.c:203 __netif_receive_skb_core+0x2f6f/0x3a20 net/core/dev.c:4208 __netif_receive_skb net/core/dev.c:4246 process_backlog+0x667/0xba0 net/core/dev.c:4866 napi_poll net/core/dev.c:5268 net_rx_action+0xc95/0x1590 net/core/dev.c:5333 __do_softirq+0x485/0x942 kernel/softirq.c:284 do_softirq_own_stack+0x1c/0x30 arch/x86/entry/entry_64.S:902 do_softirq kernel/softirq.c:328 __local_bh_enable_ip+0x25b/0x290 kernel/softirq.c:181 local_bh_enable+0x37/0x40 ./include/linux/bottom_half.h:31 rcu_read_unlock_bh ./include/linux/rcupdate.h:931 ip6_finish_output2+0x19b2/0x1cf0 net/ipv6/ip6_output.c:124 ip6_finish_output+0x764/0x970 net/ipv6/ip6_output.c:149 NF_HOOK_COND ./include/linux/netfilter.h:246 ip6_output+0x456/0x520 net/ipv6/ip6_output.c:163 dst_output ./include/net/dst.h:486 NF_HOOK ./include/linux/netfilter.h:257 ip6_xmit+0x1841/0x1c00 net/ipv6/ip6_output.c:261 sctp_v6_xmit+0x3b7/0x470 net/sctp/ipv6.c:225 sctp_packet_transmit+0x38cb/0x3a20 net/sctp/output.c:632 sctp_outq_flush+0xeb3/0x46e0 net/sctp/outqueue.c:885 sctp_outq_uncork+0xb2/0xd0 net/sctp/outqueue.c:750 sctp_side_effects net/sctp/sm_sideeffect.c:1773 sctp_do_sm+0x6962/0x6ec0 net/sctp/sm_sideeffect.c:1147 sctp_primitive_ASSOCIATE+0x12c/0x160 net/sctp/primitive.c:88 sctp_sendmsg+0x43e5/0x4f90 net/sctp/socket.c:1954 inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762 sock_sendmsg_nosec net/socket.c:633 sock_sendmsg net/socket.c:643 SYSC_sendto+0x608/0x710 net/socket.c:1696 SyS_sendto+0x8a/0xb0 net/socket.c:1664 do_syscall_64+0xe6/0x130 arch/x86/entry/common.c:285 entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:246 RIP: 0033:0x401133 RSP: 002b:00007fff6d99cd38 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00000000004002b0 RCX: 0000000000401133 RDX: 0000000000000001 RSI: 0000000000494088 RDI: 0000000000000003 RBP: 00007fff6d99cd90 R08: 00007fff6d99cd50 R09: 000000000000001c R10: 0000000000000001 R11: 0000000000000246 R12: 0000000000000000 R13: 00000000004063d0 R14: 0000000000406460 R15: 0000000000000000 origin: save_stack_trace+0x37/0x40 arch/x86/kernel/stacktrace.c:59 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:302 kmsan_internal_poison_shadow+0xb1/0x1a0 mm/kmsan/kmsan.c:198 kmsan_poison_shadow+0x6d/0xc0 mm/kmsan/kmsan.c:211 slab_alloc_node mm/slub.c:2743 __kmalloc_node_track_caller+0x200/0x360 mm/slub.c:4351 __kmalloc_reserve net/core/skbuff.c:138 __alloc_skb+0x26b/0x840 net/core/skbuff.c:231 alloc_skb ./include/linux/skbuff.h:933 sctp_packet_transmit+0x31e/0x3a20 net/sctp/output.c:570 sctp_outq_flush+0xeb3/0x46e0 net/sctp/outqueue.c:885 sctp_outq_uncork+0xb2/0xd0 net/sctp/outqueue.c:750 sctp_side_effects net/sctp/sm_sideeffect.c:1773 sctp_do_sm+0x6962/0x6ec0 net/sctp/sm_sideeffect.c:1147 sctp_primitive_ASSOCIATE+0x12c/0x160 net/sctp/primitive.c:88 sctp_sendmsg+0x43e5/0x4f90 net/sctp/socket.c:1954 inet_sendmsg+0x498/0x670 net/ipv4/af_inet.c:762 sock_sendmsg_nosec net/socket.c:633 sock_sendmsg net/socket.c:643 SYSC_sendto+0x608/0x710 net/socket.c:1696 SyS_sendto+0x8a/0xb0 net/socket.c:1664 do_syscall_64+0xe6/0x130 arch/x86/entry/common.c:285 return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:246 ================================================================== Signed-off-by: Alexander Potapenko Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a9519a06a23b..980807d7506f 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -469,6 +469,8 @@ _sctp_walk_params((pos), (chunk), ntohs((chunk)->chunk_hdr.length), member) #define _sctp_walk_params(pos, chunk, end, member)\ for (pos.v = chunk->member;\ + (pos.v + offsetof(struct sctp_paramhdr, length) + sizeof(pos.p->length) <\ + (void *)chunk + end) &&\ pos.v <= (void *)chunk + end - ntohs(pos.p->length) &&\ ntohs(pos.p->length) >= sizeof(struct sctp_paramhdr);\ pos.v += SCTP_PAD4(ntohs(pos.p->length))) @@ -479,6 +481,8 @@ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length)) #define _sctp_walk_errors(err, chunk_hdr, end)\ for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \ sizeof(struct sctp_chunkhdr));\ + ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <\ + (void *)chunk_hdr + end) &&\ (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\ ntohs(err->length) >= sizeof(sctp_errhdr_t); \ err = (sctp_errhdr_t *)((void *)err + SCTP_PAD4(ntohs(err->length)))) -- cgit v1.2.3