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>

4 files changed, 50 insertions, 34 deletions

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index d4172534dfa8..cca7594be92e 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -496,8 +496,11 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
 		return ERR_PTR(-EPERM);
 
 	nla_for_each_nested(nla, nla_stgs, rem) {
-		if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD)
+		if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) {
+			if (nla_len(nla) != sizeof(u32))
+				return ERR_PTR(-EINVAL);
 			nr_maps++;
+		}
 	}
 
 	diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1777a5e1830b..6d2180b8edb3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -5139,13 +5139,17 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
 	if (br_spec) {
 		nla_for_each_nested(attr, br_spec, rem) {
-			if (nla_type(attr) == IFLA_BRIDGE_FLAGS) {
+			if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) {
 				if (nla_len(attr) < sizeof(flags))
 					return -EINVAL;
 
 				have_flags = true;
 				flags = nla_get_u16(attr);
-				break;
+			}
+
+			if (nla_type(attr) == IFLA_BRIDGE_MODE) {
+				if (nla_len(attr) < sizeof(u16))
+					return -EINVAL;
 			}
 		}
 	}
diff --git a/net/core/sock.c b/net/core/sock.c
index 4ad267ba0099..49915801d53a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -429,6 +429,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
 {
 	struct __kernel_sock_timeval tv;
 	int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval);
+	long val;
 
 	if (err)
 		return err;
@@ -439,7 +440,7 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
 	if (tv.tv_sec < 0) {
 		static int warned __read_mostly;
 
-		*timeo_p = 0;
+		WRITE_ONCE(*timeo_p, 0);
 		if (warned < 10 && net_ratelimit()) {
 			warned++;
 			pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
@@ -447,11 +448,12 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
 		}
 		return 0;
 	}
-	*timeo_p = MAX_SCHEDULE_TIMEOUT;
-	if (tv.tv_sec == 0 && tv.tv_usec == 0)
-		return 0;
-	if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1))
-		*timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ);
+	val = MAX_SCHEDULE_TIMEOUT;
+	if ((tv.tv_sec || tv.tv_usec) &&
+	    (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)))
+		val = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec,
+						    USEC_PER_SEC / HZ);
+	WRITE_ONCE(*timeo_p, val);
 	return 0;
 }
 
@@ -804,7 +806,7 @@ EXPORT_SYMBOL(sock_no_linger);
 void sock_set_priority(struct sock *sk, u32 priority)
 {
 	lock_sock(sk);
-	sk->sk_priority = priority;
+	WRITE_ONCE(sk->sk_priority, priority);
 	release_sock(sk);
 }
 EXPORT_SYMBOL(sock_set_priority);
@@ -813,9 +815,9 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs)
 {
 	lock_sock(sk);
 	if (secs && secs < MAX_SCHEDULE_TIMEOUT / HZ - 1)
-		sk->sk_sndtimeo = secs * HZ;
+		WRITE_ONCE(sk->sk_sndtimeo, secs * HZ);
 	else
-		sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+		WRITE_ONCE(sk->sk_sndtimeo, MAX_SCHEDULE_TIMEOUT);
 	release_sock(sk);
 }
 EXPORT_SYMBOL(sock_set_sndtimeo);
@@ -988,7 +990,7 @@ EXPORT_SYMBOL(sock_set_rcvbuf);
 static void __sock_set_mark(struct sock *sk, u32 val)
 {
 	if (val != sk->sk_mark) {
-		sk->sk_mark = val;
+		WRITE_ONCE(sk->sk_mark, val);
 		sk_dst_reset(sk);
 	}
 }
@@ -1007,7 +1009,7 @@ static void sock_release_reserved_memory(struct sock *sk, int bytes)
 	bytes = round_down(bytes, PAGE_SIZE);
 
 	WARN_ON(bytes > sk->sk_reserved_mem);
-	sk->sk_reserved_mem -= bytes;
+	WRITE_ONCE(sk->sk_reserved_mem, sk->sk_reserved_mem - bytes);
 	sk_mem_reclaim(sk);
 }
 
@@ -1044,7 +1046,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 	}
 	sk->sk_forward_alloc += pages << PAGE_SHIFT;
 
-	sk->sk_reserved_mem += pages << PAGE_SHIFT;
+	WRITE_ONCE(sk->sk_reserved_mem,
+		   sk->sk_reserved_mem + (pages << PAGE_SHIFT));
 
 	return 0;
 }
@@ -1213,7 +1216,7 @@ set_sndbuf:
 		if ((val >= 0 && val <= 6) ||
 		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
 		    sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
-			sk->sk_priority = val;
+			WRITE_ONCE(sk->sk_priority, val);
 		else
 			ret = -EPERM;
 		break;
@@ -1429,7 +1432,8 @@ set_sndbuf:
 			cmpxchg(&sk->sk_pacing_status,
 				SK_PACING_NONE,
 				SK_PACING_NEEDED);
-		sk->sk_max_pacing_rate = ulval;
+		/* Pairs with READ_ONCE() from sk_getsockopt() */
+		WRITE_ONCE(sk->sk_max_pacing_rate, ulval);
 		sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval);
 		break;
 		}
@@ -1524,7 +1528,9 @@ set_sndbuf:
 		}
 		if ((u8)val == SOCK_TXREHASH_DEFAULT)
 			val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
-		/* Paired with READ_ONCE() in tcp_rtx_synack() */
+		/* Paired with READ_ONCE() in tcp_rtx_synack()
+		 * and sk_getsockopt().
+		 */
 		WRITE_ONCE(sk->sk_txrehash, (u8)val);
 		break;
 
@@ -1624,11 +1630,11 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_SNDBUF:
-		v.val = sk->sk_sndbuf;
+		v.val = READ_ONCE(sk->sk_sndbuf);
 		break;
 
 	case SO_RCVBUF:
-		v.val = sk->sk_rcvbuf;
+		v.val = READ_ONCE(sk->sk_rcvbuf);
 		break;
 
 	case SO_REUSEADDR:
@@ -1670,7 +1676,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_PRIORITY:
-		v.val = sk->sk_priority;
+		v.val = READ_ONCE(sk->sk_priority);
 		break;
 
 	case SO_LINGER:
@@ -1708,16 +1714,18 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 
 	case SO_RCVTIMEO_OLD:
 	case SO_RCVTIMEO_NEW:
-		lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname);
+		lv = sock_get_timeout(READ_ONCE(sk->sk_rcvtimeo), &v,
+				      SO_RCVTIMEO_OLD == optname);
 		break;
 
 	case SO_SNDTIMEO_OLD:
 	case SO_SNDTIMEO_NEW:
-		lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname);
+		lv = sock_get_timeout(READ_ONCE(sk->sk_sndtimeo), &v,
+				      SO_SNDTIMEO_OLD == optname);
 		break;
 
 	case SO_RCVLOWAT:
-		v.val = sk->sk_rcvlowat;
+		v.val = READ_ONCE(sk->sk_rcvlowat);
 		break;
 
 	case SO_SNDLOWAT:
@@ -1834,7 +1842,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 							 optval, optlen, len);
 
 	case SO_MARK:
-		v.val = sk->sk_mark;
+		v.val = READ_ONCE(sk->sk_mark);
 		break;
 
 	case SO_RCVMARK:
@@ -1853,7 +1861,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		if (!sock->ops->set_peek_off)
 			return -EOPNOTSUPP;
 
-		v.val = sk->sk_peek_off;
+		v.val = READ_ONCE(sk->sk_peek_off);
 		break;
 	case SO_NOFCS:
 		v.val = sock_flag(sk, SOCK_NOFCS);
@@ -1883,7 +1891,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	case SO_BUSY_POLL:
-		v.val = sk->sk_ll_usec;
+		v.val = READ_ONCE(sk->sk_ll_usec);
 		break;
 	case SO_PREFER_BUSY_POLL:
 		v.val = READ_ONCE(sk->sk_prefer_busy_poll);
@@ -1891,12 +1899,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 #endif
 
 	case SO_MAX_PACING_RATE:
+		/* The READ_ONCE() pair with the WRITE_ONCE() in sk_setsockopt() */
 		if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) {
 			lv = sizeof(v.ulval);
-			v.ulval = sk->sk_max_pacing_rate;
+			v.ulval = READ_ONCE(sk->sk_max_pacing_rate);
 		} else {
 			/* 32bit version */
-			v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U);
+			v.val = min_t(unsigned long, ~0U,
+				      READ_ONCE(sk->sk_max_pacing_rate));
 		}
 		break;
 
@@ -1964,11 +1974,12 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case SO_RESERVE_MEM:
-		v.val = sk->sk_reserved_mem;
+		v.val = READ_ONCE(sk->sk_reserved_mem);
 		break;
 
 	case SO_TXREHASH:
-		v.val = sk->sk_txrehash;
+		/* Paired with WRITE_ONCE() in sk_setsockopt() */
+		v.val = READ_ONCE(sk->sk_txrehash);
 		break;
 
 	default:
@@ -3159,7 +3170,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim);
 
 int sk_set_peek_off(struct sock *sk, int val)
 {
-	sk->sk_peek_off = val;
+	WRITE_ONCE(sk->sk_peek_off, val);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sk_set_peek_off);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 19538d628714..08ab108206bf 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -115,7 +115,6 @@ static void sock_map_sk_acquire(struct sock *sk)
 	__acquires(&sk->sk_lock.slock)
 {
 	lock_sock(sk);
-	preempt_disable();
 	rcu_read_lock();
 }
 
@@ -123,7 +122,6 @@ static void sock_map_sk_release(struct sock *sk)
 	__releases(&sk->sk_lock.slock)
 {
 	rcu_read_unlock();
-	preempt_enable();
 	release_sock(sk);
 }