From c9be4a5c49cf51cc70a993f004c5bb30067a65ce Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Mon, 7 Jan 2013 21:17:00 +0000 Subject: net: prevent setting ttl=0 via IP_TTL A regression is introduced by the following commit: commit 4d52cfbef6266092d535237ba5a4b981458ab171 Author: Eric Dumazet Date: Tue Jun 2 00:42:16 2009 -0700 net: ipv4/ip_sockglue.c cleanups Pure cleanups but it is not a pure cleanup... - if (val != -1 && (val < 1 || val>255)) + if (val != -1 && (val < 0 || val > 255)) Since there is no reason provided to allow ttl=0, change it back. Reported-by: nitin padalia Cc: nitin padalia Cc: Eric Dumazet Cc: David S. Miller Signed-off-by: Cong Wang Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/ip_sockglue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 3c9d20880283..d9c4f113d709 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -590,7 +590,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, case IP_TTL: if (optlen < 1) goto e_inval; - if (val != -1 && (val < 0 || val > 255)) + if (val != -1 && (val < 1 || val > 255)) goto e_inval; inet->uc_ttl = val; break; -- cgit v1.2.3 From ff905b1e4aad8ccbbb0d42f7137f19482742ff07 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 10 Jan 2013 07:06:10 +0000 Subject: tcp: splice: fix an infinite loop in tcp_read_sock() commit 02275a2ee7c0 (tcp: don't abort splice() after small transfers) added a regression. [ 83.843570] INFO: rcu_sched self-detected stall on CPU [ 83.844575] INFO: rcu_sched detected stalls on CPUs/tasks: { 6} (detected by 0, t=21002 jiffies, g=4457, c=4456, q=13132) [ 83.844582] Task dump for CPU 6: [ 83.844584] netperf R running task 0 8966 8952 0x0000000c [ 83.844587] 0000000000000000 0000000000000006 0000000000006c6c 0000000000000000 [ 83.844589] 000000000000006c 0000000000000096 ffffffff819ce2bc ffffffffffffff10 [ 83.844592] ffffffff81088679 0000000000000010 0000000000000246 ffff880c4b9ddcd8 [ 83.844594] Call Trace: [ 83.844596] [] ? vprintk_emit+0x1c9/0x4c0 [ 83.844601] [] ? schedule+0x29/0x70 [ 83.844606] [] ? tcp_splice_data_recv+0x42/0x50 [ 83.844610] [] ? tcp_read_sock+0xda/0x260 [ 83.844613] [] ? tcp_prequeue_process+0xb0/0xb0 [ 83.844615] [] ? tcp_splice_read+0xc0/0x250 [ 83.844618] [] ? sock_splice_read+0x22/0x30 [ 83.844622] [] ? do_splice_to+0x7b/0xa0 [ 83.844627] [] ? sys_splice+0x59c/0x5d0 [ 83.844630] [] ? putname+0x2b/0x40 [ 83.844633] [] ? do_sys_open+0x174/0x1e0 [ 83.844636] [] ? system_call_fastpath+0x16/0x1b if recv_actor() returns 0, we should stop immediately, because looping wont give a chance to drain the pipe. Signed-off-by: Eric Dumazet Cc: Willy Tarreau Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1ca253635f7a..5f173dccd1e9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1482,7 +1482,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, break; } used = recv_actor(desc, skb, offset, len); - if (used < 0) { + if (used <= 0) { if (!copied) copied = used; break; -- cgit v1.2.3 From f26845b43c75d3f32f98d194c1327b5b1e6b3fb0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Jan 2013 20:59:09 +0000 Subject: tcp: fix splice() and tcp collapsing interaction Under unusual circumstances, TCP collapse can split a big GRO TCP packet while its being used in a splice(socket->pipe) operation. skb_splice_bits() releases the socket lock before calling splice_to_pipe(). [ 1081.353685] WARNING: at net/ipv4/tcp.c:1330 tcp_cleanup_rbuf+0x4d/0xfc() [ 1081.371956] Hardware name: System x3690 X5 -[7148Z68]- [ 1081.391820] cleanup rbuf bug: copied AD3BCF1 seq AD370AF rcvnxt AD3CF13 To fix this problem, we must eat skbs in tcp_recv_skb(). Remove the inline keyword from tcp_recv_skb() definition since it has three call sites. Reported-by: Christian Becker Cc: Willy Tarreau Signed-off-by: Eric Dumazet Tested-by: Willy Tarreau Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5f173dccd1e9..2aa69c8ae60c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1428,12 +1428,12 @@ static void tcp_service_net_dma(struct sock *sk, bool wait) } #endif -static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) +static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; u32 offset; - skb_queue_walk(&sk->sk_receive_queue, skb) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { offset = seq - TCP_SKB_CB(skb)->seq; if (tcp_hdr(skb)->syn) offset--; @@ -1441,6 +1441,11 @@ static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) *off = offset; return skb; } + /* This looks weird, but this can happen if TCP collapsing + * splitted a fat GRO packet, while we released socket lock + * in skb_splice_bits() + */ + sk_eat_skb(sk, skb, false); } return NULL; } @@ -1520,8 +1525,10 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ - if (copied > 0) + if (copied > 0) { + tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); + } return copied; } EXPORT_SYMBOL(tcp_read_sock); -- cgit v1.2.3 From 7b514a886ba50e3b99295b00805f0d5ad750ca66 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 10 Jan 2013 16:18:47 +0000 Subject: tcp: accept RST without ACK flag commit c3ae62af8e755 (tcp: should drop incoming frames without ACK flag set) added a regression on the handling of RST messages. RST should be allowed to come even without ACK bit set. We validate the RST by checking the exact sequence, as requested by RFC 793 and 5961 3.2, in tcp_validate_incoming() Reported-by: Eric Wong Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Tested-by: Eric Wong Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a28e4db8a952..18f97ca76b00 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5543,7 +5543,7 @@ slow_path: if (len < (th->doff << 2) || tcp_checksum_complete_user(sk, skb)) goto csum_error; - if (!th->ack) + if (!th->ack && !th->rst) goto discard; /* @@ -5988,7 +5988,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, goto discard; } - if (!th->ack) + if (!th->ack && !th->rst) goto discard; if (!tcp_validate_incoming(sk, skb, th, 0)) -- cgit v1.2.3