Merge tag 'net-5.16-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from wireless, and wireguard.

  Mostly scattered driver changes this week, with one big clump in
  mv88e6xxx. Nothing of note, really.

  Current release - regressions:

   - smc: keep smc_close_final()'s error code during active close

  Current release - new code bugs:

   - iwlwifi: various static checker fixes (int overflow, leaks, missing
     error codes)

   - rtw89: fix size of firmware header before transfer, avoid crash

   - mt76: fix timestamp check in tx_status; fix pktid leak;

   - mscc: ocelot: fix missing unlock on error in ocelot_hwstamp_set()

  Previous releases - regressions:

   - smc: fix list corruption in smc_lgr_cleanup_early

   - ipv4: convert fib_num_tclassid_users to atomic_t

  Previous releases - always broken:

   - tls: fix authentication failure in CCM mode

   - vrf: reset IPCB/IP6CB when processing outbound pkts, prevent
     incorrect processing

   - dsa: mv88e6xxx: fixes for various device errata

   - rds: correct socket tunable error in rds_tcp_tune()

   - ipv6: fix memory leak in fib6_rule_suppress

   - wireguard: reset peer src endpoint when netns exits

   - wireguard: improve resilience to DoS around incoming handshakes

   - tcp: fix page frag corruption on page fault which involves TCP

   - mpls: fix missing attributes in delete notifications

   - mt7915: fix NULL pointer dereference with ad-hoc mode

  Misc:

   - rt2x00: be more lenient about EPROTO errors during start

   - mlx4_en: update reported link modes for 1/10G"

* tag 'net-5.16-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (85 commits)
  net: dsa: b53: Add SPI ID table
  gro: Fix inconsistent indenting
  selftests: net: Correct case name
  net/rds: correct socket tunable error in rds_tcp_tune()
  mctp: Don't let RTM_DELROUTE delete local routes
  net/smc: Keep smc_close_final rc during active close
  ibmvnic: drop bad optimization in reuse_tx_pools()
  ibmvnic: drop bad optimization in reuse_rx_pools()
  net/smc: fix wrong list_del in smc_lgr_cleanup_early
  Fix Comment of ETH_P_802_3_MIN
  ethernet: aquantia: Try MAC address from device tree
  ipv4: convert fib_num_tclassid_users to atomic_t
  net: avoid uninit-value from tcp_conn_request
  net: annotate data-races on txq->xmit_lock_owner
  octeontx2-af: Fix a memleak bug in rvu_mbox_init()
  net/mlx4_en: Fix an use-after-free bug in mlx4_en_try_alloc_resources()
  vrf: Reset IPCB/IP6CB when processing outbound pkts in vrf dev xmit
  net: qlogic: qlcnic: Fix a NULL pointer dereference in qlcnic_83xx_add_rings()
  net: dsa: mv88e6xxx: Link in pcs_get_state() if AN is bypassed
  net: dsa: mv88e6xxx: Fix inband AN for 2500base-x on 88E6393X family
  ...

10 files changed, 62 insertions, 29 deletions

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 3636df90899a..fbaab440a484 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -9698,7 +9698,10 @@ struct mlx5_ifc_mcam_access_reg_bits {
 	u8         regs_84_to_68[0x11];
 	u8         tracer_registers[0x4];
 
-	u8         regs_63_to_32[0x20];
+	u8         regs_63_to_46[0x12];
+	u8         mrtc[0x1];
+	u8         regs_44_to_32[0xd];
+
 	u8         regs_31_to_0[0x20];
 };
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3ec42495a43a..be5cb3360b94 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4404,7 +4404,8 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits)
 static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu)
 {
 	spin_lock(&txq->_xmit_lock);
-	txq->xmit_lock_owner = cpu;
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, cpu);
 }
 
 static inline bool __netif_tx_acquire(struct netdev_queue *txq)
@@ -4421,26 +4422,32 @@ static inline void __netif_tx_release(struct netdev_queue *txq)
 static inline void __netif_tx_lock_bh(struct netdev_queue *txq)
 {
 	spin_lock_bh(&txq->_xmit_lock);
-	txq->xmit_lock_owner = smp_processor_id();
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
 }
 
 static inline bool __netif_tx_trylock(struct netdev_queue *txq)
 {
 	bool ok = spin_trylock(&txq->_xmit_lock);
-	if (likely(ok))
-		txq->xmit_lock_owner = smp_processor_id();
+
+	if (likely(ok)) {
+		/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+		WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id());
+	}
 	return ok;
 }
 
 static inline void __netif_tx_unlock(struct netdev_queue *txq)
 {
-	txq->xmit_lock_owner = -1;
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock(&txq->_xmit_lock);
 }
 
 static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
 {
-	txq->xmit_lock_owner = -1;
+	/* Pairs with READ_ONCE() in __dev_queue_xmit() */
+	WRITE_ONCE(txq->xmit_lock_owner, -1);
 	spin_unlock_bh(&txq->_xmit_lock);
 }
 
diff --git a/include/linux/siphash.h b/include/linux/siphash.h
index bf21591a9e5e..0cda61855d90 100644
--- a/include/linux/siphash.h
+++ b/include/linux/siphash.h
@@ -27,9 +27,7 @@ static inline bool siphash_key_is_zero(const siphash_key_t *key)
 }
 
 u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key);
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key);
-#endif
 
 u64 siphash_1u64(const u64 a, const siphash_key_t *key);
 u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key);
@@ -82,10 +80,9 @@ static inline u64 ___siphash_aligned(const __le64 *data, size_t len,
 static inline u64 siphash(const void *data, size_t len,
 			  const siphash_key_t *key)
 {
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-	if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    !IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT))
 		return __siphash_unaligned(data, len, key);
-#endif
 	return ___siphash_aligned(data, len, key);
 }
 
@@ -96,10 +93,8 @@ typedef struct {
 
 u32 __hsiphash_aligned(const void *data, size_t len,
 		       const hsiphash_key_t *key);
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 u32 __hsiphash_unaligned(const void *data, size_t len,
 			 const hsiphash_key_t *key);
-#endif
 
 u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key);
 u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key);
@@ -135,10 +130,9 @@ static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len,
 static inline u32 hsiphash(const void *data, size_t len,
 			   const hsiphash_key_t *key)
 {
-#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-	if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    !IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT))
 		return __hsiphash_unaligned(data, len, key);
-#endif
 	return ___hsiphash_aligned(data, len, key);
 }
 
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 4202c609bb0b..7994455ec714 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -133,7 +133,7 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 	if (unlikely(READ_ONCE(sk->sk_napi_id) != skb->napi_id))
 		WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
 #endif
-	sk_rx_queue_set(sk, skb);
+	sk_rx_queue_update(sk, skb);
 }
 
 static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id)
diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h
index 67634675e919..df6622a5fe98 100644
--- a/include/net/dst_cache.h
+++ b/include/net/dst_cache.h
@@ -80,6 +80,17 @@ static inline void dst_cache_reset(struct dst_cache *dst_cache)
 }
 
 /**
+ *	dst_cache_reset_now - invalidate the cache contents immediately
+ *	@dst_cache: the cache
+ *
+ *	The caller must be sure there are no concurrent users, as this frees
+ *	all dst_cache users immediately, rather than waiting for the next
+ *	per-cpu usage like dst_cache_reset does. Most callers should use the
+ *	higher speed lazily-freed dst_cache_reset function instead.
+ */
+void dst_cache_reset_now(struct dst_cache *dst_cache);
+
+/**
  *	dst_cache_init - initialize the cache, allocating the required storage
  *	@dst_cache: the cache
  *	@gfp: allocation flags
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 4b10676c69d1..bd07484ab9dd 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -69,7 +69,7 @@ struct fib_rules_ops {
 	int			(*action)(struct fib_rule *,
 					  struct flowi *, int,
 					  struct fib_lookup_arg *);
-	bool			(*suppress)(struct fib_rule *,
+	bool			(*suppress)(struct fib_rule *, int,
 					    struct fib_lookup_arg *);
 	int			(*match)(struct fib_rule *,
 					 struct flowi *, int);
@@ -218,7 +218,9 @@ INDIRECT_CALLABLE_DECLARE(int fib4_rule_action(struct fib_rule *rule,
 			    struct fib_lookup_arg *arg));
 
 INDIRECT_CALLABLE_DECLARE(bool fib6_rule_suppress(struct fib_rule *rule,
+						int flags,
 						struct fib_lookup_arg *arg));
 INDIRECT_CALLABLE_DECLARE(bool fib4_rule_suppress(struct fib_rule *rule,
+						int flags,
 						struct fib_lookup_arg *arg));
 #endif
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index ab5348e57db1..3417ba2d27ad 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -438,7 +438,7 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 #ifdef CONFIG_IP_ROUTE_CLASSID
 static inline int fib_num_tclassid_users(struct net *net)
 {
-	return net->ipv4.fib_num_tclassid_users;
+	return atomic_read(&net->ipv4.fib_num_tclassid_users);
 }
 #else
 static inline int fib_num_tclassid_users(struct net *net)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 2f65701a43c9..6c5b2efc4f17 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -65,7 +65,7 @@ struct netns_ipv4 {
 	bool			fib_has_custom_local_routes;
 	bool			fib_offload_disabled;
 #ifdef CONFIG_IP_ROUTE_CLASSID
-	int			fib_num_tclassid_users;
+	atomic_t		fib_num_tclassid_users;
 #endif
 	struct hlist_head	*fib_table_hash;
 	struct sock		*fibnl;
diff --git a/include/net/sock.h b/include/net/sock.h
index b32906e1ab55..bea21ff70e74 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1913,18 +1913,31 @@ static inline int sk_tx_queue_get(const struct sock *sk)
 	return -1;
 }
 
-static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb)
+static inline void __sk_rx_queue_set(struct sock *sk,
+				     const struct sk_buff *skb,
+				     bool force_set)
 {
 #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING
 	if (skb_rx_queue_recorded(skb)) {
 		u16 rx_queue = skb_get_rx_queue(skb);
 
-		if (unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue))
+		if (force_set ||
+		    unlikely(READ_ONCE(sk->sk_rx_queue_mapping) != rx_queue))
 			WRITE_ONCE(sk->sk_rx_queue_mapping, rx_queue);
 	}
 #endif
 }
 
+static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb)
+{
+	__sk_rx_queue_set(sk, skb, true);
+}
+
+static inline void sk_rx_queue_update(struct sock *sk, const struct sk_buff *skb)
+{
+	__sk_rx_queue_set(sk, skb, false);
+}
+
 static inline void sk_rx_queue_clear(struct sock *sk)
 {
 #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING
@@ -2430,19 +2443,22 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk)
  * @sk: socket
  *
  * Use the per task page_frag instead of the per socket one for
- * optimization when we know that we're in the normal context and owns
+ * optimization when we know that we're in process context and own
  * everything that's associated with %current.
  *
- * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
- * inside other socket operations and end up recursing into sk_page_frag()
- * while it's already in use.
+ * Both direct reclaim and page faults can nest inside other
+ * socket operations and end up recursing into sk_page_frag()
+ * while it's already in use: explicitly avoid task page_frag
+ * usage if the caller is potentially doing any of them.
+ * This assumes that page fault handlers use the GFP_NOFS flags.
  *
  * Return: a per task page_frag if context allows that,
  * otherwise a per socket one.
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
-	if (gfpflags_normal_context(sk->sk_allocation))
+	if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) ==
+	    (__GFP_DIRECT_RECLAIM | __GFP_FS))
 		return &current->task_frag;
 
 	return &sk->sk_frag;
diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h
index 5da4ee234e0b..c0c2f3ed5729 100644
--- a/include/uapi/linux/if_ether.h
+++ b/include/uapi/linux/if_ether.h
@@ -117,7 +117,7 @@
 #define ETH_P_IFE	0xED3E		/* ForCES inter-FE LFB type */
 #define ETH_P_AF_IUCV   0xFBFB		/* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */
 
-#define ETH_P_802_3_MIN	0x0600		/* If the value in the ethernet type is less than this value
+#define ETH_P_802_3_MIN	0x0600		/* If the value in the ethernet type is more than this value
 					 * then the frame is Ethernet II. Else it is 802.3 */
 
 /*