lk/linux-kernel-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

net: sk_add_backlog() take rmem_alloc into account

Browse Source 
Current socket backlog limit is not enough to really stop DDOS attacks,
because user thread spend many time to process a full backlog each
round, and user might crazy spin on socket lock.

We should add backlog size and receive_queue size (aka rmem_alloc) to
pace writers, and let user run without being slow down too much.

Introduce a sk_rcvqueues_full() helper, to avoid taking socket lock in
stress situations.

Under huge stress from a multiqueue/RPS enabled NIC, a single flow udp
receiver can now process ~200.000 pps (instead of ~100 pps before the
patch) on a 8 core machine.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Eric Dumazet
2010-04-27 15:13:20 -07:00
committed by David S. Miller
parent 6e7676c1a7
commit c377411f24
5 changed files with 27 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
include/net/sock.h
View File

@ -256,7 +256,6 @@ struct sock {
struct sk_buff *head;
struct sk_buff *tail;
int len;
int limit;
} sk_backlog;
wait_queue_head_t *sk_sleep;
struct dst_entry *sk_dst_cache;
@ -608,10 +607,20 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
skb->next = NULL;
}
/*
* Take into account size of receive queue and backlog queue
*/
static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb)
{
unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc);
return qsize + skb->truesize > sk->sk_rcvbuf;
}
/* The per-socket spinlock must be held here. */
static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
if (sk->sk_backlog.len >= max(sk->sk_backlog.limit, sk->sk_rcvbuf << 1))
if (sk_rcvqueues_full(sk, skb))
return -ENOBUFS;
__sk_add_backlog(sk, skb);