sock: allocate skbs from optmem

Add sock_omalloc and sock_ofree to be able to allocate control skbs,
for instance for looping errors onto sk_error_queue.

The transmit budget (sk_wmem_alloc) is involved in transmit skb
shaping, most notably in TCP Small Queues. Using this budget for
control packets would impact transmission.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/sock.h b/include/net/sock.h
index 393c38e..0f778d3 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1531,6 +1531,8 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
                             gfp_t priority);
 void __sock_wfree(struct sk_buff *skb);
 void sock_wfree(struct sk_buff *skb);
+struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
+                            gfp_t priority);
 void skb_orphan_partial(struct sk_buff *skb);
 void sock_rfree(struct sk_buff *skb);
 void sock_efree(struct sk_buff *skb);

diff --git a/net/core/sock.c b/net/core/sock.c
index 742f68c..1261880 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1923,6 +1923,33 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
 }
 EXPORT_SYMBOL(sock_wmalloc);
 
+static void sock_ofree(struct sk_buff *skb)
+{
+       struct sock *sk = skb->sk;
+
+       atomic_sub(skb->truesize, &sk->sk_omem_alloc);
+}
+
+struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
+                            gfp_t priority)
+{
+       struct sk_buff *skb;
+
+       /* small safe race: SKB_TRUESIZE may differ from final skb->truesize */
+       if (atomic_read(&sk->sk_omem_alloc) + SKB_TRUESIZE(size) >
+           sysctl_optmem_max)
+               return NULL;
+
+       skb = alloc_skb(size, priority);
+       if (!skb)
+               return NULL;
+
+       atomic_add(skb->truesize, &sk->sk_omem_alloc);
+       skb->sk = sk;
+       skb->destructor = sock_ofree;
+       return skb;
+}
+
 /*
  * Allocate a memory block from the socket's option memory buffer.
  */