From 703fb94ec58e0e8769380c2877a8a34aeb5b6c97 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Tue, 13 Nov 2012 08:52:24 +0100 Subject: xfrm: Fix the gc threshold value for ipv4 The xfrm gc threshold value depends on ip_rt_max_size. This value was set to INT_MAX with the routing cache removal patch, so we start doing garbage collecting when we have INT_MAX/2 IPsec routes cached. Fix this by going back to the static threshold of 1024 routes. Signed-off-by: Steffen Klassert --- net/ipv4/route.c | 2 +- net/ipv4/xfrm4_policy.c | 13 +------------ 2 files changed, 2 insertions(+), 13 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a8c651216fa6..200d287e49f5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2597,7 +2597,7 @@ int __init ip_rt_init(void) pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM xfrm_init(); - xfrm4_init(ip_rt_max_size); + xfrm4_init(); #endif rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 05c5ab8d983c..3be0ac2c1920 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -279,19 +279,8 @@ static void __exit xfrm4_policy_fini(void) xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo); } -void __init xfrm4_init(int rt_max_size) +void __init xfrm4_init(void) { - /* - * Select a default value for the gc_thresh based on the main route - * table hash size. It seems to me the worst case scenario is when - * we have ipsec operating in transport mode, in which we create a - * dst_entry per socket. The xfrm gc algorithm starts trying to remove - * entries at gc_thresh, and prevents new allocations as 2*gc_thresh - * so lets set an initial xfrm gc_thresh value at the rt_max_size/2. - * That will let us store an ipsec connection per route table entry, - * and start cleaning when were 1/2 full - */ - xfrm4_dst_ops.gc_thresh = rt_max_size/2; dst_entries_init(&xfrm4_dst_ops); xfrm4_state_init(); -- cgit v1.2.2 From 636174219b52b5a8bc51bc23bbcba97cd30a65e3 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Thu, 22 Nov 2012 23:04:14 +0200 Subject: ipv4: do not cache looped multicasts Starting from 3.6 we cache output routes for multicasts only when using route to 224/4. For local receivers we can set RTCF_LOCAL flag depending on the membership but in such case we use maddr and saddr which are not caching keys as before. Additionally, we can not use same place to cache routes that differ in RTCF_LOCAL flag value. Fix it by caching only RTCF_MULTICAST entries without RTCF_LOCAL (send-only, no loopback). As a side effect, we avoid unneeded lookup for fnhe when not caching because multicasts are not redirected and they do not learn PMTU. Thanks to Maxime Bizon for showing the caching problems in __mkroute_output for 3.6 kernels: different RTCF_LOCAL flag in cache can lead to wrong ip_mc_output or ip_output call and the visible problem is that traffic can not reach local receivers via loopback. Reported-by: Maxime Bizon Tested-by: Maxime Bizon Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- net/ipv4/route.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 200d287e49f5..df251424d816 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1785,6 +1785,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; + do_cache = true; if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; fi = NULL; @@ -1793,6 +1794,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr, fl4->flowi4_proto)) flags &= ~RTCF_LOCAL; + else + do_cache = false; /* If multicast route do not exist use * default one, but do not gateway in this case. * Yes, it is hack. @@ -1802,8 +1805,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res, } fnhe = NULL; - do_cache = fi != NULL; - if (fi) { + do_cache &= fi != NULL; + if (do_cache) { struct rtable __rcu **prth; struct fib_nh *nh = &FIB_RES_NH(*res); -- cgit v1.2.2