1 files changed, 25 insertions, 15 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e457c7ab2e2..2aa69c8ae60 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -536,13 +536,14 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int answ;
+	bool slow;
 
 	switch (cmd) {
 	case SIOCINQ:
 		if (sk->sk_state == TCP_LISTEN)
 			return -EINVAL;
 
-		lock_sock(sk);
+		slow = lock_sock_fast(sk);
 		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
 			answ = 0;
 		else if (sock_flag(sk, SOCK_URGINLINE) ||
@@ -557,7 +558,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 				answ--;
 		} else
 			answ = tp->urg_seq - tp->copied_seq;
-		release_sock(sk);
+		unlock_sock_fast(sk, slow);
 		break;
 	case SIOCATMARK:
 		answ = tp->urg_data && tp->urg_seq == tp->copied_seq;
@@ -1427,12 +1428,12 @@ static void tcp_service_net_dma(struct sock *sk, bool wait)
 }
 #endif
 
-static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
+static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 {
 	struct sk_buff *skb;
 	u32 offset;
 
-	skb_queue_walk(&sk->sk_receive_queue, skb) {
+	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
 		offset = seq - TCP_SKB_CB(skb)->seq;
 		if (tcp_hdr(skb)->syn)
 			offset--;
@@ -1440,6 +1441,11 @@ static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 			*off = offset;
 			return skb;
 		}
+		/* This looks weird, but this can happen if TCP collapsing
+		 * splitted a fat GRO packet, while we released socket lock
+		 * in skb_splice_bits()
+		 */
+		sk_eat_skb(sk, skb, false);
 	}
 	return NULL;
 }
@@ -1481,7 +1487,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 					break;
 			}
 			used = recv_actor(desc, skb, offset, len);
-			if (used < 0) {
+			if (used <= 0) {
 				if (!copied)
 					copied = used;
 				break;
@@ -1490,15 +1496,19 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 				copied += used;
 				offset += used;
 			}
-			/*
-			 * If recv_actor drops the lock (e.g. TCP splice
+			/* If recv_actor drops the lock (e.g. TCP splice
 			 * receive) the skb pointer might be invalid when
 			 * getting here: tcp_collapse might have deleted it
 			 * while aggregating skbs from the socket queue.
 			 */
-			skb = tcp_recv_skb(sk, seq-1, &offset);
-			if (!skb || (offset+1 != skb->len))
+			skb = tcp_recv_skb(sk, seq - 1, &offset);
+			if (!skb)
 				break;
+			/* TCP coalescing might have appended data to the skb.
+			 * Try to splice more frags
+			 */
+			if (offset + 1 != skb->len)
+				continue;
 		}
 		if (tcp_hdr(skb)->fin) {
 			sk_eat_skb(sk, skb, false);
@@ -1515,8 +1525,10 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 	tcp_rcv_space_adjust(sk);
 
 	/* Clean up data we have read: This will do ACK frames. */
-	if (copied > 0)
+	if (copied > 0) {
+		tcp_recv_skb(sk, seq, &offset);
 		tcp_cleanup_rbuf(sk, copied);
+	}
 	return copied;
 }
 EXPORT_SYMBOL(tcp_read_sock);
@@ -2300,7 +2312,7 @@ void tcp_sock_destruct(struct sock *sk)
 
 static inline bool tcp_can_repair_sock(const struct sock *sk)
 {
-	return capable(CAP_NET_ADMIN) &&
+	return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) &&
 		((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED));
 }
 
@@ -3586,8 +3598,7 @@ void __init tcp_init(void)
 		alloc_large_system_hash("TCP established",
 					sizeof(struct inet_ehash_bucket),
 					thash_entries,
-					(totalram_pages >= 128 * 1024) ?
-					13 : 15,
+					17, /* one slot per 128 KB of memory */
 					0,
 					NULL,
 					&tcp_hashinfo.ehash_mask,
@@ -3603,8 +3614,7 @@ void __init tcp_init(void)
 		alloc_large_system_hash("TCP bind",
 					sizeof(struct inet_bind_hashbucket),
 					tcp_hashinfo.ehash_mask + 1,
-					(totalram_pages >= 128 * 1024) ?
-					13 : 15,
+					17, /* one slot per 128 KB of memory */
 					0,
 					&tcp_hashinfo.bhash_size,
 					NULL,