From 07f4c90062f8fc7c8c26f8f95324cbe8fa3145a5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 24 May 2015 14:49:35 -0700 Subject: [PATCH] tcp/dccp: try to not exhaust ip_local_port_range in connect() A long standing problem on busy servers is the tiny available TCP port range (/proc/sys/net/ipv4/ip_local_port_range) and the default sequential allocation of source ports in connect() system call. If a host is having a lot of active TCP sessions, chances are very high that all ports are in use by at least one flow, and subsequent bind(0) attempts fail, or have to scan a big portion of space to find a slot. In this patch, I changed the starting point in __inet_hash_connect() so that we try to favor even [1] ports, leaving odd ports for bind() users. We still perform a sequential search, so there is no guarantee, but if connect() targets are very different, end result is we leave more ports available to bind(), and we spread them all over the range, lowering time for both connect() and bind() to find a slot. This strategy only works well if /proc/sys/net/ipv4/ip_local_port_range is even, ie if start/end values have different parity. Therefore, default /proc/sys/net/ipv4/ip_local_port_range was changed to 32768 - 60999 (instead of 32768 - 61000) There is no change on security aspects here, only some poor hashing schemes could be eventually impacted by this change. [1] : The odd/even property depends on ip_local_port_range values parity Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 8 +++++--- net/ipv4/af_inet.c | 2 +- net/ipv4/inet_hashtables.c | 10 ++++++++-- 3 files changed, 14 insertions(+), 6 deletions(-) diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index cb083e0d682c..5fae7704daab 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -751,8 +751,10 @@ IP Variables: ip_local_port_range - 2 INTEGERS Defines the local port range that is used by TCP and UDP to choose the local port. The first number is the first, the - second the last local port number. The default values are - 32768 and 61000 respectively. + second the last local port number. + If possible, it is better these numbers have different parity. + (one even and one odd values) + The default values are 32768 and 60999 respectively. ip_local_reserved_ports - list of comma separated ranges Specify the ports which are reserved for known third-party @@ -775,7 +777,7 @@ ip_local_reserved_ports - list of comma separated ranges ip_local_port_range, e.g.: $ cat /proc/sys/net/ipv4/ip_local_port_range - 32000 61000 + 32000 60999 $ cat /proc/sys/net/ipv4/ip_local_reserved_ports 8080,9148 diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 235d36afece3..6ad0f7a711c9 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1595,7 +1595,7 @@ static __net_init int inet_init_net(struct net *net) */ seqlock_init(&net->ipv4.ip_local_ports.lock); net->ipv4.ip_local_ports.range[0] = 32768; - net->ipv4.ip_local_ports.range[1] = 61000; + net->ipv4.ip_local_ports.range[1] = 60999; seqlock_init(&net->ipv4.ping_group_range.lock); /* diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 185efef0f125..1b336dc179f8 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -502,8 +502,14 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; + /* By starting with offset being an even number, + * we tend to leave about 50% of ports for other uses, + * like bind(0). + */ + offset &= ~1; + local_bh_disable(); - for (i = 1; i <= remaining; i++) { + for (i = 0; i < remaining; i++) { port = low + (i + offset) % remaining; if (inet_is_local_reserved_port(net, port)) continue; @@ -547,7 +553,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, return -EADDRNOTAVAIL; ok: - hint += i; + hint += (i + 2) & ~1; /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, port);