From 64327fc811268d4a24de03dac242ea29de6be75f Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Thu, 31 Aug 2017 18:11:41 +0200 Subject: ipv4: Don't override return code from ip_route_input_noref() After ip_route_input() calls ip_route_input_noref(), another check on skb_dst() is done, but if this fails, we shouldn't override the return code from ip_route_input_noref(), as it could have been more specific (i.e. -EHOSTUNREACH). This also saves one call to skb_dst_force_safe() and one to skb_dst() in case the ip_route_input_noref() check fails. Reported-by: Sabrina Dubroca Fixes: 9df16efadd2a ("ipv4: call dst_hold_safe() properly") Signed-off-by: Stefano Brivio Acked-by: Wei Wang Acked-by: Sabrina Dubroca Signed-off-by: David S. Miller --- include/net/route.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index cb0a76d9dde1..1b09a9368c68 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -189,10 +189,11 @@ 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) + if (!err) { skb_dst_force_safe(skb); - if (!skb_dst(skb)) - err = -EINVAL; + if (!skb_dst(skb)) + err = -EINVAL; + } rcu_read_unlock(); return err; -- cgit v1.2.3 From fb452a1aa3fd4034d7999e309c5466ff2d7005aa Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 1 Sep 2017 11:26:08 +0200 Subject: Revert "net: use lib/percpu_counter API for fragmentation mem accounting" This reverts commit 6d7b857d541ecd1d9bd997c97242d4ef94b19de2. There is a bug in fragmentation codes use of the percpu_counter API, that can cause issues on systems with many CPUs. The frag_mem_limit() just reads the global counter (fbc->count), without considering other CPUs can have upto batch size (130K) that haven't been subtracted yet. Due to the 3MBytes lower thresh limit, this become dangerous at >=24 CPUs (3*1024*1024/130000=24). The correct API usage would be to use __percpu_counter_compare() which does the right thing, and takes into account the number of (online) CPUs and batch size, to account for this and call __percpu_counter_sum() when needed. We choose to revert the use of the lib/percpu_counter API for frag memory accounting for several reasons: 1) On systems with CPUs > 24, the heavier fully locked __percpu_counter_sum() is always invoked, which will be more expensive than the atomic_t that is reverted to. Given systems with more than 24 CPUs are becoming common this doesn't seem like a good option. To mitigate this, the batch size could be decreased and thresh be increased. 2) The add_frag_mem_limit+sub_frag_mem_limit pairs happen on the RX CPU, before SKBs are pushed into sockets on remote CPUs. Given NICs can only hash on L2 part of the IP-header, the NIC-RXq's will likely be limited. Thus, a fair chance that atomic add+dec happen on the same CPU. Revert note that commit 1d6119baf061 ("net: fix percpu memory leaks") removed init_frag_mem_limit() and instead use inet_frags_init_net(). After this revert, inet_frags_uninit_net() becomes empty. Fixes: 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting") Fixes: 1d6119baf061 ("net: fix percpu memory leaks") Signed-off-by: Jesper Dangaard Brouer Acked-by: Florian Westphal Signed-off-by: David S. Miller --- include/net/inet_frag.h | 30 +++++++++--------------------- 1 file changed, 9 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 6fdcd2427776..fa635aa6d0b9 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -1,14 +1,9 @@ #ifndef __NET_FRAG_H__ #define __NET_FRAG_H__ -#include - struct netns_frags { - /* The percpu_counter "mem" need to be cacheline aligned. - * mem.count must not share cacheline with other writers - */ - struct percpu_counter mem ____cacheline_aligned_in_smp; - + /* Keep atomic mem on separate cachelines in structs that include it */ + atomic_t mem ____cacheline_aligned_in_smp; /* sysctls */ int timeout; int high_thresh; @@ -110,11 +105,11 @@ void inet_frags_fini(struct inet_frags *); static inline int inet_frags_init_net(struct netns_frags *nf) { - return percpu_counter_init(&nf->mem, 0, GFP_KERNEL); + atomic_set(&nf->mem, 0); + return 0; } static inline void inet_frags_uninit_net(struct netns_frags *nf) { - percpu_counter_destroy(&nf->mem); } void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f); @@ -140,31 +135,24 @@ static inline bool inet_frag_evicting(struct inet_frag_queue *q) /* Memory Tracking Functions. */ -/* The default percpu_counter batch size is not big enough to scale to - * fragmentation mem acct sizes. - * The mem size of a 64K fragment is approx: - * (44 fragments * 2944 truesize) + frag_queue struct(200) = 129736 bytes - */ -static unsigned int frag_percpu_counter_batch = 130000; - static inline int frag_mem_limit(struct netns_frags *nf) { - return percpu_counter_read(&nf->mem); + return atomic_read(&nf->mem); } static inline void sub_frag_mem_limit(struct netns_frags *nf, int i) { - percpu_counter_add_batch(&nf->mem, -i, frag_percpu_counter_batch); + atomic_sub(i, &nf->mem); } static inline void add_frag_mem_limit(struct netns_frags *nf, int i) { - percpu_counter_add_batch(&nf->mem, i, frag_percpu_counter_batch); + atomic_add(i, &nf->mem); } -static inline unsigned int sum_frag_mem_limit(struct netns_frags *nf) +static inline int sum_frag_mem_limit(struct netns_frags *nf) { - return percpu_counter_sum_positive(&nf->mem); + return atomic_read(&nf->mem); } /* RFC 3168 support : -- cgit v1.2.3 From 5a63643e583b6a9789d7a225ae076fb4e603991c Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 1 Sep 2017 11:26:13 +0200 Subject: Revert "net: fix percpu memory leaks" This reverts commit 1d6119baf0610f813eb9d9580eb4fd16de5b4ceb. After reverting commit 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting") then here is no need for this fix-up patch. As percpu_counter is no longer used, it cannot memory leak it any-longer. Fixes: 6d7b857d541e ("net: use lib/percpu_counter API for fragmentation mem accounting") Fixes: 1d6119baf061 ("net: fix percpu memory leaks") Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/net/inet_frag.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index fa635aa6d0b9..fc59e0775e00 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -103,15 +103,10 @@ struct inet_frags { int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); -static inline int inet_frags_init_net(struct netns_frags *nf) +static inline void inet_frags_init_net(struct netns_frags *nf) { atomic_set(&nf->mem, 0); - return 0; } -static inline void inet_frags_uninit_net(struct netns_frags *nf) -{ -} - void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f); void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f); -- cgit v1.2.3