Merge tag 'net-6.5-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Still trending up in size but the good news is that the "current"
  regressions are resolved, AFAIK.

  We're getting weirdly many fixes for Wake-on-LAN and suspend/resume
  handling on embedded this week (most not merged yet), not sure why.
  But those are all for older bugs.

  Current release - regressions:

   - tls: set MSG_SPLICE_PAGES consistently when handing encrypted data
     over to TCP

  Current release - new code bugs:

   - eth: mlx5: correct IDs on VFs internal to the device (IPU)

  Previous releases - regressions:

   - phy: at803x: fix WoL support / reporting on AR8032

   - bonding: fix incorrect deletion of ETH_P_8021AD protocol VID from
     slaves, leading to BUG_ON()

   - tun: prevent tun_build_skb() from exceeding the packet size limit

   - wifi: rtw89: fix 8852AE disconnection caused by RX full flags

   - eth/PCI: enetc: fix probing after 6fffbc7ae137 ("PCI: Honor
     firmware's device disabled status"), keep PCI devices around even
     if they are disabled / not going to be probed to be able to apply
     quirks on them

   - eth: prestera: fix handling IPv4 routes with nexthop IDs

  Previous releases - always broken:

   - netfilter: re-work garbage collection to avoid races between
     user-facing API and timeouts

   - tunnels: fix generating ipv4 PMTU error on non-linear skbs

   - nexthop: fix infinite nexthop bucket dump when using maximum
     nexthop ID

   - wifi: nl80211: fix integer overflow in nl80211_parse_mbssid_elems()

  Misc:

   - unix: use consistent error code in SO_PEERPIDFD

   - ipv6: adjust ndisc_is_useropt() to include PREFIX_INFO, in prep for
     upcoming IETF RFC"

* tag 'net-6.5-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (94 commits)
  net: hns3: fix strscpy causing content truncation issue
  net: tls: set MSG_SPLICE_PAGES consistently
  ibmvnic: Ensure login failure recovery is safe from other resets
  ibmvnic: Do partial reset on login failure
  ibmvnic: Handle DMA unmapping of login buffs in release functions
  ibmvnic: Unmap DMA login rsp buffer on send login fail
  ibmvnic: Enforce stronger sanity checks on login response
  net: mana: Fix MANA VF unload when hardware is unresponsive
  netfilter: nf_tables: remove busy mark and gc batch API
  netfilter: nft_set_hash: mark set element as dead when deleting from packet path
  netfilter: nf_tables: adapt set backend to use GC transaction API
  netfilter: nf_tables: GC transaction API to avoid race with control plane
  selftests/bpf: Add sockmap test for redirecting partial skb data
  selftests/bpf: fix a CI failure caused by vsock sockmap test
  bpf, sockmap: Fix bug that strp_done cannot be called
  bpf, sockmap: Fix map type error in sock_map_del_link
  xsk: fix refcount underflow in error path
  ipv6: adjust ndisc_is_useropt() to also return true for PIO
  selftests: forwarding: bridge_mdb: Make test more robust
  selftests: forwarding: bridge_mdb_max: Fix failing test with old libnet
  ...

4 files changed, 53 insertions, 76 deletions

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 054d7911bfc9..c1637515a8a4 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -62,6 +62,7 @@ struct sk_psock_progs {
 
 enum sk_psock_state_bits {
 	SK_PSOCK_TX_ENABLED,
+	SK_PSOCK_RX_STRP_ENABLED,
 };
 
 struct sk_psock_link {
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 7c7d03aa9d06..d6fa7c8767ad 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -562,6 +562,9 @@ ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband,
 	if (WARN_ON(iftype >= NL80211_IFTYPE_MAX))
 		return NULL;
 
+	if (iftype == NL80211_IFTYPE_AP_VLAN)
+		iftype = NL80211_IFTYPE_AP;
+
 	for (i = 0; i < sband->n_iftype_data; i++)  {
 		const struct ieee80211_sband_iftype_data *data =
 			&sband->iftype_data[i];
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 640441a2f926..35870858ddf2 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -512,6 +512,7 @@ struct nft_set_elem_expr {
  *
  *	@list: table set list node
  *	@bindings: list of set bindings
+ *	@refs: internal refcounting for async set destruction
  *	@table: table this set belongs to
  *	@net: netnamespace this set belongs to
  * 	@name: name of the set
@@ -541,6 +542,7 @@ struct nft_set_elem_expr {
 struct nft_set {
 	struct list_head		list;
 	struct list_head		bindings;
+	refcount_t			refs;
 	struct nft_table		*table;
 	possible_net_t			net;
 	char				*name;
@@ -562,7 +564,8 @@ struct nft_set {
 	struct list_head		pending_update;
 	/* runtime data below here */
 	const struct nft_set_ops	*ops ____cacheline_aligned;
-	u16				flags:14,
+	u16				flags:13,
+					dead:1,
 					genmask:2;
 	u8				klen;
 	u8				dlen;
@@ -596,7 +599,6 @@ struct nft_set *nft_set_lookup_global(const struct net *net,
 
 struct nft_set_ext *nft_set_catchall_lookup(const struct net *net,
 					    const struct nft_set *set);
-void *nft_set_catchall_gc(const struct nft_set *set);
 
 static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
 {
@@ -813,62 +815,6 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem,
 void nf_tables_set_elem_destroy(const struct nft_ctx *ctx,
 				const struct nft_set *set, void *elem);
 
-/**
- *	struct nft_set_gc_batch_head - nf_tables set garbage collection batch
- *
- *	@rcu: rcu head
- *	@set: set the elements belong to
- *	@cnt: count of elements
- */
-struct nft_set_gc_batch_head {
-	struct rcu_head			rcu;
-	const struct nft_set		*set;
-	unsigned int			cnt;
-};
-
-#define NFT_SET_GC_BATCH_SIZE	((PAGE_SIZE -				  \
-				  sizeof(struct nft_set_gc_batch_head)) / \
-				 sizeof(void *))
-
-/**
- *	struct nft_set_gc_batch - nf_tables set garbage collection batch
- *
- * 	@head: GC batch head
- * 	@elems: garbage collection elements
- */
-struct nft_set_gc_batch {
-	struct nft_set_gc_batch_head	head;
-	void				*elems[NFT_SET_GC_BATCH_SIZE];
-};
-
-struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set,
-						gfp_t gfp);
-void nft_set_gc_batch_release(struct rcu_head *rcu);
-
-static inline void nft_set_gc_batch_complete(struct nft_set_gc_batch *gcb)
-{
-	if (gcb != NULL)
-		call_rcu(&gcb->head.rcu, nft_set_gc_batch_release);
-}
-
-static inline struct nft_set_gc_batch *
-nft_set_gc_batch_check(const struct nft_set *set, struct nft_set_gc_batch *gcb,
-		       gfp_t gfp)
-{
-	if (gcb != NULL) {
-		if (gcb->head.cnt + 1 < ARRAY_SIZE(gcb->elems))
-			return gcb;
-		nft_set_gc_batch_complete(gcb);
-	}
-	return nft_set_gc_batch_alloc(set, gfp);
-}
-
-static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb,
-					void *elem)
-{
-	gcb->elems[gcb->head.cnt++] = elem;
-}
-
 struct nft_expr_ops;
 /**
  *	struct nft_expr_type - nf_tables expression type
@@ -1557,39 +1503,30 @@ static inline void nft_set_elem_change_active(const struct net *net,
 
 #endif /* IS_ENABLED(CONFIG_NF_TABLES) */
 
-/*
- * We use a free bit in the genmask field to indicate the element
- * is busy, meaning it is currently being processed either by
- * the netlink API or GC.
- *
- * Even though the genmask is only a single byte wide, this works
- * because the extension structure if fully constant once initialized,
- * so there are no non-atomic write accesses unless it is already
- * marked busy.
- */
-#define NFT_SET_ELEM_BUSY_MASK	(1 << 2)
+#define NFT_SET_ELEM_DEAD_MASK	(1 << 2)
 
 #if defined(__LITTLE_ENDIAN_BITFIELD)
-#define NFT_SET_ELEM_BUSY_BIT	2
+#define NFT_SET_ELEM_DEAD_BIT	2
 #elif defined(__BIG_ENDIAN_BITFIELD)
-#define NFT_SET_ELEM_BUSY_BIT	(BITS_PER_LONG - BITS_PER_BYTE + 2)
+#define NFT_SET_ELEM_DEAD_BIT	(BITS_PER_LONG - BITS_PER_BYTE + 2)
 #else
 #error
 #endif
 
-static inline int nft_set_elem_mark_busy(struct nft_set_ext *ext)
+static inline void nft_set_elem_dead(struct nft_set_ext *ext)
 {
 	unsigned long *word = (unsigned long *)ext;
 
 	BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0);
-	return test_and_set_bit(NFT_SET_ELEM_BUSY_BIT, word);
+	set_bit(NFT_SET_ELEM_DEAD_BIT, word);
 }
 
-static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext)
+static inline int nft_set_elem_is_dead(const struct nft_set_ext *ext)
 {
 	unsigned long *word = (unsigned long *)ext;
 
-	clear_bit(NFT_SET_ELEM_BUSY_BIT, word);
+	BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0);
+	return test_bit(NFT_SET_ELEM_DEAD_BIT, word);
 }
 
 /**
@@ -1732,6 +1669,38 @@ struct nft_trans_flowtable {
 #define nft_trans_flowtable_flags(trans)	\
 	(((struct nft_trans_flowtable *)trans->data)->flags)
 
+#define NFT_TRANS_GC_BATCHCOUNT	256
+
+struct nft_trans_gc {
+	struct list_head	list;
+	struct net		*net;
+	struct nft_set		*set;
+	u32			seq;
+	u8			count;
+	void			*priv[NFT_TRANS_GC_BATCHCOUNT];
+	struct rcu_head		rcu;
+};
+
+struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set,
+					unsigned int gc_seq, gfp_t gfp);
+void nft_trans_gc_destroy(struct nft_trans_gc *trans);
+
+struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc,
+					      unsigned int gc_seq, gfp_t gfp);
+void nft_trans_gc_queue_async_done(struct nft_trans_gc *gc);
+
+struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp);
+void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans);
+
+void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv);
+
+struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc,
+					   unsigned int gc_seq);
+
+void nft_setelem_data_deactivate(const struct net *net,
+				 const struct nft_set *set,
+				 struct nft_set_elem *elem);
+
 int __init nft_chain_filter_init(void);
 void nft_chain_filter_fini(void);
 
@@ -1758,6 +1727,7 @@ struct nftables_pernet {
 	struct mutex		commit_mutex;
 	u64			table_handle;
 	unsigned int		base_seq;
+	unsigned int		gc_seq;
 };
 
 extern unsigned int nf_tables_net_id;
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index bf06db8d2046..7b1ddffa3dfc 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -381,6 +381,7 @@ TRACE_EVENT(tcp_cong_state_set,
 		__field(const void *, skaddr)
 		__field(__u16, sport)
 		__field(__u16, dport)
+		__field(__u16, family)
 		__array(__u8, saddr, 4)
 		__array(__u8, daddr, 4)
 		__array(__u8, saddr_v6, 16)
@@ -396,6 +397,7 @@ TRACE_EVENT(tcp_cong_state_set,
 
 		__entry->sport = ntohs(inet->inet_sport);
 		__entry->dport = ntohs(inet->inet_dport);
+		__entry->family = sk->sk_family;
 
 		p32 = (__be32 *) __entry->saddr;
 		*p32 = inet->inet_saddr;
@@ -409,7 +411,8 @@ TRACE_EVENT(tcp_cong_state_set,
 		__entry->cong_state = ca_state;
 	),
 
-	TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u",
+	TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u",
+		  show_family_name(__entry->family),
 		  __entry->sport, __entry->dport,
 		  __entry->saddr, __entry->daddr,
 		  __entry->saddr_v6, __entry->daddr_v6,