net: sock_queue_err_skb() dont mess with sk_forward_alloc

Correct sk_forward_alloc handling for error_queue would need to use a
backlog of frames that softirq handler could not deliver because socket
is owned by user thread. Or extend backlog processing to be able to
process normal and error packets.

Another possibility is to not use mem charge for error queue, this is
what I implemented in this patch.

Note: this reverts commit 29030374
(net: fix sk_forward_alloc corruptions), since we dont need to lock
socket anymore.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 32 insertions, 10 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 4e7ac09c281a..9f07e749d7b1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2965,6 +2965,34 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
 }
 EXPORT_SYMBOL_GPL(skb_cow_data);
 
+static void sock_rmem_free(struct sk_buff *skb)
+{
+        struct sock *sk = skb->sk;
+
+        atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+}
+
+/*
+ * Note: We dont mem charge error packets (no sk_forward_alloc changes)
+ */
+int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
+{
+        if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
+            (unsigned)sk->sk_rcvbuf)
+                return -ENOMEM;
+
+        skb_orphan(skb);
+        skb->sk = sk;
+        skb->destructor = sock_rmem_free;
+        atomic_add(skb->truesize, &sk->sk_rmem_alloc);
+
+        skb_queue_tail(&sk->sk_error_queue, skb);
+        if (!sock_flag(sk, SOCK_DEAD))
+                sk->sk_data_ready(sk, skb->len);
+        return 0;
+}
+EXPORT_SYMBOL(sock_queue_err_skb);
+
 void skb_tstamp_tx(struct sk_buff *orig_skb,
                 struct skb_shared_hwtstamps *hwtstamps)
 {
@@ -2997,9 +3025,7 @@ void skb_tstamp_tx(struct sk_buff *orig_skb,
         serr->ee.ee_errno = ENOMSG;
         serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 
-        bh_lock_sock(sk);
         err = sock_queue_err_skb(sk, skb);
-        bh_unlock_sock(sk);
 
         if (err)
                 kfree_skb(skb);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 50678f9a2763..eec4ff456e33 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -633,11 +633,9 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
         if (!inet->recverr) {
                 if (!harderr || sk->sk_state != TCP_ESTABLISHED)
                         goto out;
-        } else {
-                bh_lock_sock(sk);
+        } else
                 ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1));
-                bh_unlock_sock(sk);
-        }
+
         sk->sk_err = err;
         sk->sk_error_report(sk);
 out:
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 3048f906c042..87be58673b55 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -466,11 +466,9 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
         if (sk->sk_state != TCP_ESTABLISHED && !np->recverr)
                 goto out;
 
-        if (np->recverr) {
-                bh_lock_sock(sk);
+        if (np->recverr)
                 ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1));
-                bh_unlock_sock(sk);
-        }
+
         sk->sk_err = err;
         sk->sk_error_report(sk);
 out: