Merging upstream version 6.8.11.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

10 files changed, 39 insertions, 9 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index a5a820ee20..ce5c26cf1e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1571,6 +1571,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 	/* The above will be needed by the transport layer if there is one
 	 * immediately following this IP hdr.
 	 */
+	NAPI_GRO_CB(skb)->inner_network_offset = off;
 
 	/* Note : No need to call skb_gro_postpull_rcsum() here,
 	 * as we already checked checksum over ipv4 header was 0
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 67d8466223..a38e63669c 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1473,7 +1473,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 		 * by icmp_hdr(skb)->type.
 		 */
 		if (sk->sk_type == SOCK_RAW &&
-		    !inet_test_bit(HDRINCL, sk))
+		    !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH))
 			icmp_type = fl4->fl4_icmp_type;
 		else
 			icmp_type = icmp_hdr(skb)->type;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 288f1846b3..a1d8218fa1 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -605,6 +605,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			    (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
 			   daddr, saddr, 0, 0, sk->sk_uid);
 
+	fl4.fl4_icmp_type = 0;
+	fl4.fl4_icmp_code = 0;
+
 	if (!hdrincl) {
 		rfv.msg = msg;
 		rfv.hlen = 0;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5887eac87b..94b129301d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2709,7 +2709,7 @@ void tcp_shutdown(struct sock *sk, int how)
 	/* If we've already sent a FIN, or it's a closed state, skip this. */
 	if ((1 << sk->sk_state) &
 	    (TCPF_ESTABLISHED | TCPF_SYN_SENT |
-	     TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) {
+	     TCPF_CLOSE_WAIT)) {
 		/* Clear out any half completed packets.  FIN if needed. */
 		if (tcp_close_state(sk))
 			tcp_send_fin(sk);
@@ -2818,7 +2818,7 @@ void __tcp_close(struct sock *sk, long timeout)
 		 * machine. State transitions:
 		 *
 		 * TCP_ESTABLISHED -> TCP_FIN_WAIT1
-		 * TCP_SYN_RECV	-> TCP_FIN_WAIT1 (forget it, it's impossible)
+		 * TCP_SYN_RECV	-> TCP_FIN_WAIT1 (it is difficult)
 		 * TCP_CLOSE_WAIT -> TCP_LAST_ACK
 		 *
 		 * are legal only when FIN has been sent (i.e. in window),
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index df7b13f0e5..ff10be8c76 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6752,6 +6752,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 		tcp_initialize_rcv_mss(sk);
 		tcp_fast_path_on(tp);
+		if (sk->sk_shutdown & SEND_SHUTDOWN)
+			tcp_shutdown(sk, SEND_SHUTDOWN);
 		break;
 
 	case TCP_FIN_WAIT1: {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0c50c5a32b..68a065c0e5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -154,6 +154,12 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	if (tcptw->tw_ts_recent_stamp &&
 	    (!twp || (reuse && time_after32(ktime_get_seconds(),
 					    tcptw->tw_ts_recent_stamp)))) {
+		/* inet_twsk_hashdance() sets sk_refcnt after putting twsk
+		 * and releasing the bucket lock.
+		 */
+		if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt)))
+			return 0;
+
 		/* In case of repair and re-using TIME-WAIT sockets we still
 		 * want to be sure that it is safe as above but honor the
 		 * sequence numbers and time stamps set as part of the repair
@@ -174,7 +180,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 			tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
 			tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
 		}
-		sock_hold(sktw);
+
 		return 1;
 	}
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e3167ad965..02caeb7bcf 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3563,7 +3563,9 @@ void tcp_send_fin(struct sock *sk)
 			return;
 		}
 	} else {
-		skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation);
+		skb = alloc_skb_fclone(MAX_TCP_HEADER,
+				       sk_gfp_mask(sk, GFP_ATOMIC |
+						       __GFP_NOWARN));
 		if (unlikely(!skb))
 			return;
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 40282a3418..9120694359 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -534,7 +534,8 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
 				 __be16 sport, __be16 dport)
 {
-	const struct iphdr *iph = ip_hdr(skb);
+	const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+	const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
 	struct net *net = dev_net(skb->dev);
 	int iif, sdif;
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index c3d67423ae..e5971890d6 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -471,6 +471,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 	struct sk_buff *p;
 	unsigned int ulen;
 	int ret = 0;
+	int flush;
 
 	/* requires non zero csum, for symmetry with GSO */
 	if (!uh->check) {
@@ -504,13 +505,22 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 			return p;
 		}
 
+		flush = NAPI_GRO_CB(p)->flush;
+
+		if (NAPI_GRO_CB(p)->flush_id != 1 ||
+		    NAPI_GRO_CB(p)->count != 1 ||
+		    !NAPI_GRO_CB(p)->is_atomic)
+			flush |= NAPI_GRO_CB(p)->flush_id;
+		else
+			NAPI_GRO_CB(p)->is_atomic = false;
+
 		/* Terminate the flow on len mismatch or if it grow "too much".
 		 * Under small packet flood GRO count could elsewhere grow a lot
 		 * leading to excessive truesize values.
 		 * On len mismatch merge the first packet shorter than gso_size,
 		 * otherwise complete the GRO packet.
 		 */
-		if (ulen > ntohs(uh2->len)) {
+		if (ulen > ntohs(uh2->len) || flush) {
 			pp = p;
 		} else {
 			if (NAPI_GRO_CB(skb)->is_flist) {
@@ -718,7 +728,8 @@ EXPORT_SYMBOL(udp_gro_complete);
 
 INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 {
-	const struct iphdr *iph = ip_hdr(skb);
+	const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+	const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
 	/* do fraglist only if there is no outer UDP encap (or we already processed it) */
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index c54676998e..801404f7d6 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -63,7 +63,11 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
 	ip_send_check(iph);
 
 	if (xo && (xo->flags & XFRM_GRO)) {
-		skb_mac_header_rebuild(skb);
+		/* The full l2 header needs to be preserved so that re-injecting the packet at l2
+		 * works correctly in the presence of vlan tags.
+		 */
+		skb_mac_header_rebuild_full(skb, xo->orig_mac_len);
+		skb_reset_network_header(skb);
 		skb_reset_transport_header(skb);
 		return 0;
 	}