Merge branch 'tcp-mem-pressure-fixes'

Eric Dumazet says:

====================
tcp: final (?) round of mem pressure fixes

While working on prior patch series (e10b02e "Merge branch
'net-reduce-tcp_memory_allocated-inflation'"), I found that we
could still have frozen TCP flows under memory pressure.

I thought we had solved this in 2015, but the fix was not complete.

v2: deal with zerocopy tx paths.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

net/ipv4/tcp.c

@@ -951,6 +951,40 @@ static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb)
 	return 0;
 }
 
+static int tcp_wmem_schedule(struct sock *sk, int copy)
+{
+	int left;
+
+	if (likely(sk_wmem_schedule(sk, copy)))
+		return copy;
+
+	/* We could be in trouble if we have nothing queued.
+	 * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0]
+	 * to guarantee some progress.
+	 */
+	left = sock_net(sk)->ipv4.sysctl_tcp_wmem[0] - sk->sk_wmem_queued;
+	if (left > 0)
+		sk_forced_mem_schedule(sk, min(left, copy));
+	return min(copy, sk->sk_forward_alloc);
+}
+
+static int tcp_wmem_schedule(struct sock *sk, int copy)
+{
+	int left;
+
+	if (likely(sk_wmem_schedule(sk, copy)))
+		return copy;
+
+	/* We could be in trouble if we have nothing queued.
+	 * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0]
+	 * to guarantee some progress.
+	 */
+	left = sock_net(sk)->ipv4.sysctl_tcp_wmem[0] - sk->sk_wmem_queued;
+	if (left > 0)
+		sk_forced_mem_schedule(sk, min(left, copy));
+	return min(copy, sk->sk_forward_alloc);
+}
+
 static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
 				      struct page *page, int offset, size_t *size)
 {
@@ -986,7 +1020,11 @@ static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
 		tcp_mark_push(tp, skb);
 		goto new_segment;
 	}
-	if (tcp_downgrade_zcopy_pure(sk, skb) || !sk_wmem_schedule(sk, copy))
+	if (tcp_downgrade_zcopy_pure(sk, skb))
+		return NULL;
+
+	copy = tcp_wmem_schedule(sk, copy);
+	if (!copy)
 		return NULL;
 
 	if (can_coalesce) {
@@ -1334,8 +1372,11 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 
 			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 
-			if (tcp_downgrade_zcopy_pure(sk, skb) ||
-			    !sk_wmem_schedule(sk, copy))
+			if (tcp_downgrade_zcopy_pure(sk, skb))
+				goto wait_for_space;
+
+			copy = tcp_wmem_schedule(sk, copy);
+			if (!copy)
 				goto wait_for_space;
 
 			err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
@@ -1362,7 +1403,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 				skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY;
 
 			if (!skb_zcopy_pure(skb)) {
-				if (!sk_wmem_schedule(sk, copy))
+				copy = tcp_wmem_schedule(sk, copy);
+				if (!copy)
 					goto wait_for_space;
 			}
 

net/ipv4/tcp_output.c

@@ -3362,11 +3362,12 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
  */
 void sk_forced_mem_schedule(struct sock *sk, int size)
 {
-	int amt;
+	int delta, amt;
 
-	if (size <= sk->sk_forward_alloc)
+	delta = size - sk->sk_forward_alloc;
+	if (delta <= 0)
 		return;
-	amt = sk_mem_pages(size);
+	amt = sk_mem_pages(delta);
 	sk->sk_forward_alloc += amt << PAGE_SHIFT;
 	sk_memory_allocated_add(sk, amt);