Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

Conflicts:

net/dsa/port.c
  9945c1fb03a3 ("net: dsa: fix older DSA drivers using phylink")
  a88dd7538461 ("net: dsa: remove legacy_pre_march2020 detection")
https://lore.kernel.org/all/20230731102254.2c9868ca@canb.auug.org.au/

net/xdp/xsk.c
  3c5b4d69c358 ("net: annotate data-races around sk->sk_mark")
  b7f72a30e9ac ("xsk: introduce wrappers and helpers for supporting multi-buffer in Tx path")
https://lore.kernel.org/all/20230731102631.39988412@canb.auug.org.au/

drivers/net/ethernet/broadcom/bnxt/bnxt.c
  37b61cda9c16 ("bnxt: don't handle XDP in netpoll")
  2b56b3d99241 ("eth: bnxt: handle invalid Tx completions more gracefully")
https://lore.kernel.org/all/20230801101708.1dc7faac@canb.auug.org.au/

Adjacent changes:

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
  62da08331f1a ("net/mlx5e: Set proper IPsec source port in L4 selector")
  fbd517549c32 ("net/mlx5e: Add function to get IPsec offload namespace")

drivers/net/ethernet/sfc/selftest.c
  55c1528f9b97 ("sfc: fix field-spanning memcpy in selftest")
  ae9d445cd41f ("sfc: Miscellaneous comment removals")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 76 insertions, 42 deletions

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index b812eb36f0e3..f7426926a104 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -150,7 +150,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	}
 #endif
 
-	if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark))
+	if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, READ_ONCE(sk->sk_mark)))
 		goto errout;
 
 	if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) ||
@@ -799,7 +799,7 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
 	entry.ifindex = sk->sk_bound_dev_if;
 	entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0;
 	if (sk_fullsock(sk))
-		entry.mark = sk->sk_mark;
+		entry.mark = READ_ONCE(sk->sk_mark);
 	else if (sk->sk_state == TCP_NEW_SYN_RECV)
 		entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark;
 	else if (sk->sk_state == TCP_TIME_WAIT)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6e70839257f7..6ba1a0fafbaa 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -184,9 +184,9 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 		ip_options_build(skb, &opt->opt, daddr, rt);
 	}
 
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 	if (!skb->mark)
-		skb->mark = sk->sk_mark;
+		skb->mark = READ_ONCE(sk->sk_mark);
 
 	/* Send it out. */
 	return ip_local_out(net, skb->sk, skb);
@@ -528,8 +528,8 @@ packet_routed:
 			     skb_shinfo(skb)->gso_segs ?: 1);
 
 	/* TODO : should we use skb->sk here instead of sk ? */
-	skb->priority = sk->sk_priority;
-	skb->mark = sk->sk_mark;
+	skb->priority = READ_ONCE(sk->sk_priority);
+	skb->mark = READ_ONCE(sk->sk_mark);
 
 	res = ip_local_out(net, sk, skb);
 	rcu_read_unlock();
@@ -1158,10 +1158,15 @@ alloc_new_skb:
 			}
 
 			copy = datalen - transhdrlen - fraggap - pagedlen;
+			/* [!] NOTE: copy will be negative if pagedlen>0
+			 * because then the equation reduces to -fraggap.
+			 */
 			if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
 				err = -EFAULT;
 				kfree_skb(skb);
 				goto error;
+			} else if (flags & MSG_SPLICE_PAGES) {
+				copy = 0;
 			}
 
 			offset += copy;
@@ -1209,6 +1214,10 @@ alloc_new_skb:
 		} else if (flags & MSG_SPLICE_PAGES) {
 			struct msghdr *msg = from;
 
+			err = -EIO;
+			if (WARN_ON_ONCE(copy > msg->msg_iter.count))
+				goto error;
+
 			err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
 						   sk->sk_allocation);
 			if (err < 0)
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 8e97d8d4cc9d..d41bce8927b2 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -592,7 +592,7 @@ void __ip_sock_set_tos(struct sock *sk, int val)
 	}
 	if (inet_sk(sk)->tos != val) {
 		inet_sk(sk)->tos = val;
-		sk->sk_priority = rt_tos2priority(val);
+		WRITE_ONCE(sk->sk_priority, rt_tos2priority(val));
 		sk_dst_reset(sk);
 	}
 }
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 7782ff5e6539..cb381f5aa464 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -348,7 +348,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		goto error;
 	skb_reserve(skb, hlen);
 
-	skb->priority = sk->sk_priority;
+	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
 	skb->tstamp = sockc->transmit_time;
 	skb_dst_set(skb, &rt->dst);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 98d7e6ba7493..92fede388d52 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -518,7 +518,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
 		const struct inet_sock *inet = inet_sk(sk);
 
 		oif = sk->sk_bound_dev_if;
-		mark = sk->sk_mark;
+		mark = READ_ONCE(sk->sk_mark);
 		tos = ip_sock_rt_tos(sk);
 		scope = ip_sock_rt_scope(sk);
 		prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol;
@@ -552,7 +552,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
 	inet_opt = rcu_dereference(inet->inet_opt);
 	if (inet_opt && inet_opt->opt.srr)
 		daddr = inet_opt->opt.faddr;
-	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+	flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark),
 			   ip_sock_rt_tos(sk) & IPTOS_RT_MASK,
 			   ip_sock_rt_scope(sk),
 			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 09cffbc82d32..5b18a048f613 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -932,9 +932,9 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	ctl_sk = this_cpu_read(ipv4_tcp_sk);
 	sock_net_set(ctl_sk, net);
 	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
-			   inet_twsk(sk)->tw_mark : sk->sk_mark;
+			   inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark);
 	ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
-			   inet_twsk(sk)->tw_priority : sk->sk_priority;
+			   inet_twsk(sk)->tw_priority : READ_ONCE(sk->sk_priority);
 	transmit_time = tcp_transmit_time(sk);
 	ip_send_unicast_reply(ctl_sk,
 			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 82f4575f9cd9..99ac5efe244d 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -40,7 +40,7 @@ struct tcp_fastopen_metrics {
 
 struct tcp_metrics_block {
 	struct tcp_metrics_block __rcu	*tcpm_next;
-	possible_net_t			tcpm_net;
+	struct net			*tcpm_net;
 	struct inetpeer_addr		tcpm_saddr;
 	struct inetpeer_addr		tcpm_daddr;
 	unsigned long			tcpm_stamp;
@@ -51,34 +51,38 @@ struct tcp_metrics_block {
 	struct rcu_head			rcu_head;
 };
 
-static inline struct net *tm_net(struct tcp_metrics_block *tm)
+static inline struct net *tm_net(const struct tcp_metrics_block *tm)
 {
-	return read_pnet(&tm->tcpm_net);
+	/* Paired with the WRITE_ONCE() in tcpm_new() */
+	return READ_ONCE(tm->tcpm_net);
 }
 
 static bool tcp_metric_locked(struct tcp_metrics_block *tm,
 			      enum tcp_metric_index idx)
 {
-	return tm->tcpm_lock & (1 << idx);
+	/* Paired with WRITE_ONCE() in tcpm_suck_dst() */
+	return READ_ONCE(tm->tcpm_lock) & (1 << idx);
 }
 
-static u32 tcp_metric_get(struct tcp_metrics_block *tm,
+static u32 tcp_metric_get(const struct tcp_metrics_block *tm,
 			  enum tcp_metric_index idx)
 {
-	return tm->tcpm_vals[idx];
+	/* Paired with WRITE_ONCE() in tcp_metric_set() */
+	return READ_ONCE(tm->tcpm_vals[idx]);
 }
 
 static void tcp_metric_set(struct tcp_metrics_block *tm,
 			   enum tcp_metric_index idx,
 			   u32 val)
 {
-	tm->tcpm_vals[idx] = val;
+	/* Paired with READ_ONCE() in tcp_metric_get() */
+	WRITE_ONCE(tm->tcpm_vals[idx], val);
 }
 
 static bool addr_same(const struct inetpeer_addr *a,
 		      const struct inetpeer_addr *b)
 {
-	return inetpeer_addr_cmp(a, b) == 0;
+	return (a->family == b->family) && !inetpeer_addr_cmp(a, b);
 }
 
 struct tcpm_hash_bucket {
@@ -89,6 +93,7 @@ static struct tcpm_hash_bucket	*tcp_metrics_hash __read_mostly;
 static unsigned int		tcp_metrics_hash_log __read_mostly;
 
 static DEFINE_SPINLOCK(tcp_metrics_lock);
+static DEFINE_SEQLOCK(fastopen_seqlock);
 
 static void tcpm_suck_dst(struct tcp_metrics_block *tm,
 			  const struct dst_entry *dst,
@@ -97,7 +102,7 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
 	u32 msval;
 	u32 val;
 
-	tm->tcpm_stamp = jiffies;
+	WRITE_ONCE(tm->tcpm_stamp, jiffies);
 
 	val = 0;
 	if (dst_metric_locked(dst, RTAX_RTT))
@@ -110,30 +115,42 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm,
 		val |= 1 << TCP_METRIC_CWND;
 	if (dst_metric_locked(dst, RTAX_REORDERING))
 		val |= 1 << TCP_METRIC_REORDERING;
-	tm->tcpm_lock = val;
+	/* Paired with READ_ONCE() in tcp_metric_locked() */
+	WRITE_ONCE(tm->tcpm_lock, val);
 
 	msval = dst_metric_raw(dst, RTAX_RTT);
-	tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC;
+	tcp_metric_set(tm, TCP_METRIC_RTT, msval * USEC_PER_MSEC);
 
 	msval = dst_metric_raw(dst, RTAX_RTTVAR);
-	tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC;
-	tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
-	tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
-	tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
+	tcp_metric_set(tm, TCP_METRIC_RTTVAR, msval * USEC_PER_MSEC);
+	tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
+		       dst_metric_raw(dst, RTAX_SSTHRESH));
+	tcp_metric_set(tm, TCP_METRIC_CWND,
+		       dst_metric_raw(dst, RTAX_CWND));
+	tcp_metric_set(tm, TCP_METRIC_REORDERING,
+		       dst_metric_raw(dst, RTAX_REORDERING));
 	if (fastopen_clear) {
+		write_seqlock(&fastopen_seqlock);
 		tm->tcpm_fastopen.mss = 0;
 		tm->tcpm_fastopen.syn_loss = 0;
 		tm->tcpm_fastopen.try_exp = 0;
 		tm->tcpm_fastopen.cookie.exp = false;
 		tm->tcpm_fastopen.cookie.len = 0;
+		write_sequnlock(&fastopen_seqlock);
 	}
 }
 
 #define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
 
-static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
+static void tcpm_check_stamp(struct tcp_metrics_block *tm,
+			     const struct dst_entry *dst)
 {
-	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
+	unsigned long limit;
+
+	if (!tm)
+		return;
+	limit = READ_ONCE(tm->tcpm_stamp) + TCP_METRICS_TIMEOUT;
+	if (unlikely(time_after(jiffies, limit)))
 		tcpm_suck_dst(tm, dst, false);
 }
 
@@ -174,20 +191,23 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
 		oldest = deref_locked(tcp_metrics_hash[hash].chain);
 		for (tm = deref_locked(oldest->tcpm_next); tm;
 		     tm = deref_locked(tm->tcpm_next)) {
-			if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp))
+			if (time_before(READ_ONCE(tm->tcpm_stamp),
+					READ_ONCE(oldest->tcpm_stamp)))
 				oldest = tm;
 		}
 		tm = oldest;
 	} else {
-		tm = kmalloc(sizeof(*tm), GFP_ATOMIC);
+		tm = kzalloc(sizeof(*tm), GFP_ATOMIC);
 		if (!tm)
 			goto out_unlock;
 	}
-	write_pnet(&tm->tcpm_net, net);
+	/* Paired with the READ_ONCE() in tm_net() */
+	WRITE_ONCE(tm->tcpm_net, net);
+
 	tm->tcpm_saddr = *saddr;
 	tm->tcpm_daddr = *daddr;
 
-	tcpm_suck_dst(tm, dst, true);
+	tcpm_suck_dst(tm, dst, reclaim);
 
 	if (likely(!reclaim)) {
 		tm->tcpm_next = tcp_metrics_hash[hash].chain;
@@ -434,7 +454,7 @@ void tcp_update_metrics(struct sock *sk)
 					       tp->reordering);
 		}
 	}
-	tm->tcpm_stamp = jiffies;
+	WRITE_ONCE(tm->tcpm_stamp, jiffies);
 out_unlock:
 	rcu_read_unlock();
 }
@@ -539,8 +559,6 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst)
 	return ret;
 }
 
-static DEFINE_SEQLOCK(fastopen_seqlock);
-
 void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
 			    struct tcp_fastopen_cookie *cookie)
 {
@@ -647,7 +665,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 	}
 
 	if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE,
-			  jiffies - tm->tcpm_stamp,
+			  jiffies - READ_ONCE(tm->tcpm_stamp),
 			  TCP_METRICS_ATTR_PAD) < 0)
 		goto nla_put_failure;
 
@@ -658,7 +676,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 		if (!nest)
 			goto nla_put_failure;
 		for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) {
-			u32 val = tm->tcpm_vals[i];
+			u32 val = tcp_metric_get(tm, i);
 
 			if (!val)
 				continue;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8c3ebd95f5b9..1ee9e56dc79a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -114,6 +114,7 @@
 #include <net/sock_reuseport.h>
 #include <net/addrconf.h>
 #include <net/udp_tunnel.h>
+#include <net/gro.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6_stubs.h>
 #endif
@@ -555,10 +556,13 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct net *net = dev_net(skb->dev);
+	int iif, sdif;
+
+	inet_get_iif_sdif(skb, &iif, &sdif);
 
 	return __udp4_lib_lookup(net, iph->saddr, sport,
-				 iph->daddr, dport, inet_iif(skb),
-				 inet_sdif(skb), net->ipv4.udp_table, NULL);
+				 iph->daddr, dport, iif,
+				 sdif, net->ipv4.udp_table, NULL);
 }
 
 /* Must be called under rcu_read_lock().
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index f402946da344..0f46b3c2e4ac 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -609,10 +609,13 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
 {
 	const struct iphdr *iph = skb_gro_network_header(skb);
 	struct net *net = dev_net(skb->dev);
+	int iif, sdif;
+
+	inet_get_iif_sdif(skb, &iif, &sdif);
 
 	return __udp4_lib_lookup(net, iph->saddr, sport,
-				 iph->daddr, dport, inet_iif(skb),
-				 inet_sdif(skb), net->ipv4.udp_table, NULL);
+				 iph->daddr, dport, iif,
+				 sdif, net->ipv4.udp_table, NULL);
 }
 
 INDIRECT_CALLABLE_SCOPE