Merge tag 'v5.10.12' into linux-5.10.y-rt

This is the 5.10.12 stable release

9 files changed, 40 insertions, 46 deletions

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 8b07f3a4f2db..a3271ec3e162 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -443,7 +443,6 @@ static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb,
 int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
 	u8 *tail;
-	u8 *vaddr;
 	int nfrags;
 	int esph_offset;
 	struct page *page;
@@ -485,14 +484,10 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			page = pfrag->page;
 			get_page(page);
 
-			vaddr = kmap_atomic(page);
-
-			tail = vaddr + pfrag->offset;
+			tail = page_address(page) + pfrag->offset;
 
 			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
 
-			kunmap_atomic(vaddr);
-
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f60869acbef0..48d2b615edc2 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -851,6 +851,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		newicsk->icsk_retransmits = 0;
 		newicsk->icsk_backoff	  = 0;
 		newicsk->icsk_probes_out  = 0;
+		newicsk->icsk_probes_tstamp = 0;
 
 		/* Deinitialize accept_queue to trap illegal accesses. */
 		memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index cc23f1ce239c..8cd3224d913e 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -76,7 +76,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	flow.daddr = iph->saddr;
 	flow.saddr = rpfilter_get_saddr(iph->daddr);
 	flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
-	flow.flowi4_tos = RT_TOS(iph->tos);
+	flow.flowi4_tos = iph->tos & IPTOS_RT_MASK;
 	flow.flowi4_scope = RT_SCOPE_UNIVERSE;
 	flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par));
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b2bc3d7fe9e8..41d03683b13d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2685,6 +2685,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	icsk->icsk_backoff = 0;
 	icsk->icsk_probes_out = 0;
+	icsk->icsk_probes_tstamp = 0;
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	icsk->icsk_rto_min = TCP_RTO_MIN;
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ef4bdb038a4b..6bf066f924c1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3370,6 +3370,7 @@ static void tcp_ack_probe(struct sock *sk)
 		return;
 	if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) {
 		icsk->icsk_backoff = 0;
+		icsk->icsk_probes_tstamp = 0;
 		inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
 		/* Socket must be waked up by subsequent tcp_data_snd_check().
 		 * This function is not for random using!
@@ -4379,10 +4380,9 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb)
 	 * The receiver remembers and reflects via DSACKs. Leverage the
 	 * DSACK state and change the txhash to re-route speculatively.
 	 */
-	if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) {
-		sk_rethink_txhash(sk);
+	if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq &&
+	    sk_rethink_txhash(sk))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH);
-	}
 }
 
 static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 595dcc3afac5..ab8ed0fc4769 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1590,6 +1590,8 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 		tcp_move_syn(newtp, req);
 		ireq->ireq_opt = NULL;
 	} else {
+		newinet->inet_opt = NULL;
+
 		if (!req_unhash && found_dup_sk) {
 			/* This code path should only be executed in the
 			 * syncookie case only
@@ -1597,8 +1599,6 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 			bh_unlock_sock(newsk);
 			sock_put(newsk);
 			newsk = NULL;
-		} else {
-			newinet->inet_opt = NULL;
 		}
 	}
 	return newsk;
@@ -1755,6 +1755,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf);
+	u32 tail_gso_size, tail_gso_segs;
 	struct skb_shared_info *shinfo;
 	const struct tcphdr *th;
 	struct tcphdr *thtail;
@@ -1762,6 +1763,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	unsigned int hdrlen;
 	bool fragstolen;
 	u32 gso_segs;
+	u32 gso_size;
 	int delta;
 
 	/* In case all data was pulled from skb frags (in __pskb_pull_tail()),
@@ -1787,13 +1789,6 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	 */
 	th = (const struct tcphdr *)skb->data;
 	hdrlen = th->doff * 4;
-	shinfo = skb_shinfo(skb);
-
-	if (!shinfo->gso_size)
-		shinfo->gso_size = skb->len - hdrlen;
-
-	if (!shinfo->gso_segs)
-		shinfo->gso_segs = 1;
 
 	tail = sk->sk_backlog.tail;
 	if (!tail)
@@ -1816,6 +1811,15 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 		goto no_coalesce;
 
 	__skb_pull(skb, hdrlen);
+
+	shinfo = skb_shinfo(skb);
+	gso_size = shinfo->gso_size ?: skb->len;
+	gso_segs = shinfo->gso_segs ?: 1;
+
+	shinfo = skb_shinfo(tail);
+	tail_gso_size = shinfo->gso_size ?: (tail->len - hdrlen);
+	tail_gso_segs = shinfo->gso_segs ?: 1;
+
 	if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) {
 		TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq;
 
@@ -1842,11 +1846,8 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 		}
 
 		/* Not as strict as GRO. We only need to carry mss max value */
-		skb_shinfo(tail)->gso_size = max(shinfo->gso_size,
-						 skb_shinfo(tail)->gso_size);
-
-		gso_segs = skb_shinfo(tail)->gso_segs + shinfo->gso_segs;
-		skb_shinfo(tail)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+		shinfo->gso_size = max(gso_size, tail_gso_size);
+		shinfo->gso_segs = min_t(u32, gso_segs + tail_gso_segs, 0xFFFF);
 
 		sk->sk_backlog.len += delta;
 		__NET_INC_STATS(sock_net(sk),
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 99011768c264..e58e2589d7f9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4080,6 +4080,7 @@ void tcp_send_probe0(struct sock *sk)
 		/* Cancel probe timer, if it is not required. */
 		icsk->icsk_probes_out = 0;
 		icsk->icsk_backoff = 0;
+		icsk->icsk_probes_tstamp = 0;
 		return;
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6c62b9ea1320..faa92948441b 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -219,14 +219,8 @@ static int tcp_write_timeout(struct sock *sk)
 	int retry_until;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
-		if (icsk->icsk_retransmits) {
-			dst_negative_advice(sk);
-		} else {
-			sk_rethink_txhash(sk);
-			tp->timeout_rehash++;
-			__NET_INC_STATS(sock_net(sk),
-					LINUX_MIB_TCPTIMEOUTREHASH);
-		}
+		if (icsk->icsk_retransmits)
+			__dst_negative_advice(sk);
 		retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
 		expired = icsk->icsk_retransmits >= retry_until;
 	} else {
@@ -234,12 +228,7 @@ static int tcp_write_timeout(struct sock *sk)
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
-			dst_negative_advice(sk);
-		} else {
-			sk_rethink_txhash(sk);
-			tp->timeout_rehash++;
-			__NET_INC_STATS(sock_net(sk),
-					LINUX_MIB_TCPTIMEOUTREHASH);
+			__dst_negative_advice(sk);
 		}
 
 		retry_until = net->ipv4.sysctl_tcp_retries2;
@@ -270,6 +259,11 @@ static int tcp_write_timeout(struct sock *sk)
 		return 1;
 	}
 
+	if (sk_rethink_txhash(sk)) {
+		tp->timeout_rehash++;
+		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH);
+	}
+
 	return 0;
 }
 
@@ -349,6 +343,7 @@ static void tcp_probe_timer(struct sock *sk)
 
 	if (tp->packets_out || !skb) {
 		icsk->icsk_probes_out = 0;
+		icsk->icsk_probes_tstamp = 0;
 		return;
 	}
 
@@ -360,13 +355,12 @@ static void tcp_probe_timer(struct sock *sk)
 	 * corresponding system limit. We also implement similar policy when
 	 * we use RTO to probe window in tcp_retransmit_timer().
 	 */
-	if (icsk->icsk_user_timeout) {
-		u32 elapsed = tcp_model_timeout(sk, icsk->icsk_probes_out,
-						tcp_probe0_base(sk));
-
-		if (elapsed >= icsk->icsk_user_timeout)
-			goto abort;
-	}
+	if (!icsk->icsk_probes_tstamp)
+		icsk->icsk_probes_tstamp = tcp_jiffies32;
+	else if (icsk->icsk_user_timeout &&
+		 (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >=
+		 msecs_to_jiffies(icsk->icsk_user_timeout))
+		goto abort;
 
 	max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
 	if (sock_flag(sk, SOCK_DEAD)) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9eeebd4a0054..e37a2fa65c29 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2553,7 +2553,8 @@ int udp_v4_early_demux(struct sk_buff *skb)
 		 */
 		if (!inet_sk(sk)->inet_daddr && in_dev)
 			return ip_mc_validate_source(skb, iph->daddr,
-						     iph->saddr, iph->tos,
+						     iph->saddr,
+						     iph->tos & IPTOS_RT_MASK,
 						     skb->dev, in_dev, &itag);
 	}
 	return 0;