From 9b04f350057863d1fad1ba071e09362a1da3503e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Aug 2012 20:48:29 +0000 Subject: ipv4: properly update pmtu Sylvain Munault reported following info : - TCP connection get "stuck" with data in send queue when doing "large" transfers ( like typing 'ps ax' on a ssh connection ) - Only happens on path where the PMTU is lower than the MTU of the interface - Is not present right after boot, it only appears 10-20min after boot or so. (and that's inside the _same_ TCP connection, it works fine at first and then in the same ssh session, it'll get stuck) - Definitely seems related to fragments somehow since I see a router sending ICMP message saying fragmentation is needed. - Exact same setup works fine with kernel 3.5.1 Problem happens when the 10 minutes (ip_rt_mtu_expires) expiration period is over. ip_rt_update_pmtu() calls dst_set_expires() to rearm a new expiration, but dst_set_expires() does nothing because dst.expires is already set. It seems we want to set the expires field to a new value, regardless of prior one. With help from Julian Anastasov. Reported-by: Sylvain Munaut Signed-off-by: Eric Dumazet CC: Julian Anastasov Tested-by: Sylvain Munaut Signed-off-by: David S. Miller --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/route.c') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index fd9ecb52c66..8c8c748ebb2 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -956,7 +956,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, dst->obsolete = DST_OBSOLETE_KILL; } else { rt->rt_pmtu = mtu; - dst_set_expires(&rt->dst, ip_rt_mtu_expires); + rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires); } } -- cgit v1.2.3 From 78df76a065ae3b5dbcb9a29912adc02f697de498 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 Aug 2012 05:40:47 +0000 Subject: ipv4: take rt_uncached_lock only if needed Multicast traffic allocates dst with DST_NOCACHE, but dst is not inserted into rt_uncached_list. This slowdown multicast workloads on SMP because rt_uncached_lock is contended. Change the test before taking the lock to actually check the dst was inserted into rt_uncached_list. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/route.c') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8c8c748ebb2..24fd4c59664 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1263,7 +1263,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst) { struct rtable *rt = (struct rtable *) dst; - if (dst->flags & DST_NOCACHE) { + if (!list_empty(&rt->rt_uncached)) { spin_lock_bh(&rt_uncached_lock); list_del(&rt->rt_uncached); spin_unlock_bh(&rt_uncached_lock); -- cgit v1.2.3 From c5ae7d41927dbd208c885d4794e30617ad6cdf12 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Aug 2012 12:33:07 +0000 Subject: ipv4: must use rcu protection while calling fib_lookup Following lockdep splat was reported by Pavel Roskin : [ 1570.586223] =============================== [ 1570.586225] [ INFO: suspicious RCU usage. ] [ 1570.586228] 3.6.0-rc3-wl-main #98 Not tainted [ 1570.586229] ------------------------------- [ 1570.586231] /home/proski/src/linux/net/ipv4/route.c:645 suspicious rcu_dereference_check() usage! [ 1570.586233] [ 1570.586233] other info that might help us debug this: [ 1570.586233] [ 1570.586236] [ 1570.586236] rcu_scheduler_active = 1, debug_locks = 0 [ 1570.586238] 2 locks held by Chrome_IOThread/4467: [ 1570.586240] #0: (slock-AF_INET){+.-...}, at: [] release_sock+0x2c/0xa0 [ 1570.586253] #1: (fnhe_lock){+.-...}, at: [] update_or_create_fnhe+0x2c/0x270 [ 1570.586260] [ 1570.586260] stack backtrace: [ 1570.586263] Pid: 4467, comm: Chrome_IOThread Not tainted 3.6.0-rc3-wl-main #98 [ 1570.586265] Call Trace: [ 1570.586271] [] lockdep_rcu_suspicious+0xfd/0x130 [ 1570.586275] [] update_or_create_fnhe+0x15c/0x270 [ 1570.586278] [] __ip_rt_update_pmtu+0x73/0xb0 [ 1570.586282] [] ip_rt_update_pmtu+0x29/0x90 [ 1570.586285] [] inet_csk_update_pmtu+0x2c/0x80 [ 1570.586290] [] tcp_v4_mtu_reduced+0x2e/0xc0 [ 1570.586293] [] tcp_release_cb+0xa4/0xb0 [ 1570.586296] [] release_sock+0x55/0xa0 [ 1570.586300] [] tcp_sendmsg+0x4af/0xf50 [ 1570.586305] [] inet_sendmsg+0x120/0x230 [ 1570.586308] [] ? inet_sk_rebuild_header+0x40/0x40 [ 1570.586312] [] ? sock_update_classid+0xbd/0x3b0 [ 1570.586315] [] ? sock_update_classid+0x130/0x3b0 [ 1570.586320] [] do_sock_write+0xc5/0xe0 [ 1570.586323] [] sock_aio_write+0x53/0x80 [ 1570.586328] [] do_sync_write+0xa3/0xe0 [ 1570.586332] [] vfs_write+0x165/0x180 [ 1570.586335] [] sys_write+0x45/0x90 [ 1570.586340] [] system_call_fastpath+0x16/0x1b Signed-off-by: Eric Dumazet Reported-by: Pavel Roskin Signed-off-by: David S. Miller --- net/ipv4/route.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4/route.c') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 24fd4c59664..82cf2a722b2 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -934,12 +934,14 @@ static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (mtu < ip_rt_min_pmtu) mtu = ip_rt_min_pmtu; + rcu_read_lock(); if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) { struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, 0, mtu, jiffies + ip_rt_mtu_expires); } + rcu_read_unlock(); return mtu; } -- cgit v1.2.3