Patchwork [net-next,v3] tcp: bind() use stronger condition for bind_conflict

login
register
mail settings
Submitter Alexandru Copot
Date April 13, 2012, 8:21 a.m.
Message ID <1334305305-19952-1-git-send-email-alex.mihai.c@gmail.com>
Download mbox | patch
Permalink /patch/152264/
State Accepted
Delegated to: David Miller
Headers show

Comments

Alexandru Copot - April 13, 2012, 8:21 a.m.
From: Alex Copot <alex.mihai.c@gmail.com>

We must try harder to get unique (addr, port) pairs when
doing port autoselection for sockets with SO_REUSEADDR
option set.

We achieve this by adding a relaxation parameter to
inet_csk_bind_conflict. When 'relax' parameter is off
we return a conflict whenever the current searched
pair (addr, port) is not unique.

This tries to address the problems reported in patch:
	8d238b25b1ec22a73b1c2206f111df2faaff8285
	Revert "tcp: bind() fix when many ports are bound"

Tests where ran for creating and binding(0) many sockets
on 100 IPs. The results are, on average:

	* 60000 sockets, 600 ports / IP:
		* 0.210 s, 620 (IP, port) duplicates without patch
		* 0.219 s, no duplicates with patch
	* 100000 sockets, 1000 ports / IP:
		* 0.371 s, 1720 duplicates without patch
		* 0.373 s, no duplicates with patch
	* 200000 sockets, 2000 ports / IP:
		* 0.766 s, 6900 duplicates without patch
		* 0.768 s, no duplicates with patch
	* 500000 sockets, 5000 ports / IP:
		* 2.227 s, 41500 duplicates without patch
		* 2.284 s, no duplicates with patch

Signed-off-by: Alex Copot <alex.mihai.c@gmail.com>
Signed-off-by: Daniel Baluta <dbaluta@ixiacom.com>

---
Changes from V2:
 - Fixed coding style issues
Changes from V1:
 - Fixed coding style
 - Replaced int flag with bool
 - Added test results
---
 include/net/inet6_connection_sock.h |    2 +-
 include/net/inet_connection_sock.h  |    4 ++--
 net/ipv4/inet_connection_sock.c     |   18 ++++++++++++++----
 net/ipv6/inet6_connection_sock.c    |    2 +-
 4 files changed, 18 insertions(+), 8 deletions(-)
Eric Dumazet - April 13, 2012, 8:53 a.m.
On Fri, 2012-04-13 at 11:21 +0300, Alexandru Copot wrote:
> From: Alex Copot <alex.mihai.c@gmail.com>
> 
> We must try harder to get unique (addr, port) pairs when
> doing port autoselection for sockets with SO_REUSEADDR
> option set.

...

>  			}
> +			if (!relax && reuse && sk2->sk_reuse &&
> +			   sk2->sk_state != TCP_LISTEN) {
> +				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
> +


Oh well, missing space here :(

I said :

if (condition_one ||
    condition_two) {

not

if (condition_one ||
   condition_two) {



Signed-off-by: Eric Dumazet <edumazet@google.com>

Thanks


--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
David Miller - April 14, 2012, 7:29 p.m.
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Fri, 13 Apr 2012 10:53:11 +0200

> On Fri, 2012-04-13 at 11:21 +0300, Alexandru Copot wrote:
>> From: Alex Copot <alex.mihai.c@gmail.com>
>> 
>> We must try harder to get unique (addr, port) pairs when
>> doing port autoselection for sockets with SO_REUSEADDR
>> option set.
> 
> ...
> 
>>  			}
>> +			if (!relax && reuse && sk2->sk_reuse &&
>> +			   sk2->sk_state != TCP_LISTEN) {
>> +				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
>> +
> 
> 
> Oh well, missing space here :(
> 
> I said :
> 
> if (condition_one ||
>     condition_two) {
> 
> not
> 
> if (condition_one ||
>    condition_two) {

I'll fix this up.

> Signed-off-by: Eric Dumazet <edumazet@google.com>

Applied, thanks.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h
index 3207e58..1866a67 100644
--- a/include/net/inet6_connection_sock.h
+++ b/include/net/inet6_connection_sock.h
@@ -23,7 +23,7 @@  struct sock;
 struct sockaddr;
 
 extern int inet6_csk_bind_conflict(const struct sock *sk,
-				   const struct inet_bind_bucket *tb);
+				   const struct inet_bind_bucket *tb, bool relax);
 
 extern struct dst_entry* inet6_csk_route_req(struct sock *sk,
 					     const struct request_sock *req);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index dbf9aab..46c9e2c 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -60,7 +60,7 @@  struct inet_connection_sock_af_ops {
 #endif
 	void	    (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
 	int	    (*bind_conflict)(const struct sock *sk,
-				     const struct inet_bind_bucket *tb);
+				     const struct inet_bind_bucket *tb, bool relax);
 };
 
 /** inet_connection_sock - INET connection oriented sock
@@ -245,7 +245,7 @@  extern struct request_sock *inet_csk_search_req(const struct sock *sk,
 						const __be32 raddr,
 						const __be32 laddr);
 extern int inet_csk_bind_conflict(const struct sock *sk,
-				  const struct inet_bind_bucket *tb);
+				  const struct inet_bind_bucket *tb, bool relax);
 extern int inet_csk_get_port(struct sock *sk, unsigned short snum);
 
 extern struct dst_entry* inet_csk_route_req(struct sock *sk,
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 19d66ce..9a3e88d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -53,7 +53,7 @@  void inet_get_local_port_range(int *low, int *high)
 EXPORT_SYMBOL(inet_get_local_port_range);
 
 int inet_csk_bind_conflict(const struct sock *sk,
-			   const struct inet_bind_bucket *tb)
+			   const struct inet_bind_bucket *tb, bool relax)
 {
 	struct sock *sk2;
 	struct hlist_node *node;
@@ -79,6 +79,14 @@  int inet_csk_bind_conflict(const struct sock *sk,
 				    sk2_rcv_saddr == sk_rcv_saddr(sk))
 					break;
 			}
+			if (!relax && reuse && sk2->sk_reuse &&
+			   sk2->sk_state != TCP_LISTEN) {
+				const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
+
+				if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) ||
+				    sk2_rcv_saddr == sk_rcv_saddr(sk))
+					break;
+			}
 		}
 	}
 	return node != NULL;
@@ -122,12 +130,13 @@  again:
 					    (tb->num_owners < smallest_size || smallest_size == -1)) {
 						smallest_size = tb->num_owners;
 						smallest_rover = rover;
-						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) {
+						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1 &&
+						    !inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) {
 							snum = smallest_rover;
 							goto tb_found;
 						}
 					}
-					if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
+					if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) {
 						snum = rover;
 						goto tb_found;
 					}
@@ -178,12 +187,13 @@  tb_found:
 			goto success;
 		} else {
 			ret = 1;
-			if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
+			if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) {
 				if (sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
 				    smallest_size != -1 && --attempts >= 0) {
 					spin_unlock(&head->lock);
 					goto again;
 				}
+
 				goto fail_unlock;
 			}
 		}
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 02dd203..e6cee52 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -28,7 +28,7 @@ 
 #include <net/inet6_connection_sock.h>
 
 int inet6_csk_bind_conflict(const struct sock *sk,
-			    const struct inet_bind_bucket *tb)
+			    const struct inet_bind_bucket *tb, bool relax)
 {
 	const struct sock *sk2;
 	const struct hlist_node *node;