Merge tag 'net-7.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "This is again larger than usual: the backlog accumulated in the past weeks
  is not done yet. I'm not aware of any known pending regression.

  Including fixes from netfilter, Bluetooth, WiFi and CAN.

  Current release - regressions:

   - bluetooth: remove unnecessary hci_conn_get in create_conn_sync

   - can: isotp: fix timer drain order, wakeup handling and tx_gen
     ordering

   - eth:
       - tun/vhost: revert avoid ptr_ring tail-drop when a qdisc is
         present

  Previous releases - regressions:

   - core: do not send ICMP/NDISC Redirects when peer allocation fails

   - ipv6: take nexthop lock for f6i_list walks in replace check and
     notify

   - wifi: fix an ath12k MLO regression impacting WCN7850/QCC2072.

   - netfilter: nf_tables: make nft_object rhltable per table

   - af_unix: fix listen() succeeding on sockets in the wrong state

   - openvswitch: fix potential UAF on meter attach failure

   - bluetooth:
       - fix advertising data UAFs
       - avoid deadlocks in iso_sock_timeout

   - smc: fix socket use-after-free during link group termination

   - dpll: use pin owner's dpll ref for pin-level attribute reporting

   - eth:
       - veth: convert frag_list skbs before running XDP
       - ice: wait for reset completion in ice_resume()
       - igc: remove napi_synchronize() in igc_down()
       - vxlan: use pskb_network_may_pull() for transmit path header pulls

  Previous releases - always broken:

   - xsk: fix AF_XDP multi-buffer Tx descriptor reclaim

   - psp: fix NULL genl_sock deref race with concurrent netns teardown

   - netfilter: widen NAT rewrite delta to s32 in sip_help_tcp()

   - can: peak_usb: fix double free of transfer buffer on URB submit error

   - dibs: fix use-after-free of dmb_node in loopback attach/detach/unregister

   - sctp: prevent peer transport count overflow

   - dsa: mt7530: error out on failed reads in MT7531 PHY polling

   - eth:
       - idpf: bound interrupt-vector register fill to the allocated array"

* tag 'net-7.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (156 commits)
  qede: sync udp_tunnel ports outside qede_lock in the recovery path
  net: openvswitch: fix potential UAF on meter attach failure
  octeontx2-pf: Set correct sequence for carrier off and tx queue stop
  net: libwx: fix FDIR ATR queue mismatch for software VLAN packets
  net: dsa: realtek: use devm_mutex_init for l2_lock
  net: dsa: realtek: use devm_mutex_init for vlan_lock
  net: dsa: realtek: use devm_mutex_init for regmap lock
  net: dsa: realtek: rtl8365mb: use devm_mutex_init for mib_lock
  ptp: netc: fix potential interrupt storm caused by incorrect unbind order
  net: mana: Return error code from mana_create_rxq()
  net: openvswitch: fix skb leak on flow key update failure during ct
  net: openvswitch: fix skb leak on flow key update failure during recirculation
  net: stmmac: Fix E2E delay mechanism
  net: dsa: mt7530: error out on failed reads in MT7531 PHY polling
  net: dsa: mt7530: error out on failed reads in ATC/VTCR command polling
  net: dsa: mt7530: check bus->read() errors in the MDIO regmap backend
  Revert "tun/tap: add ptr_ring consume helper with netdev queue wakeup"
  Revert "vhost-net: wake queue of tun/tap after ptr_ring consume"
  Revert "ptr_ring: move free-space check into separate helper"
  Revert "tun/tap & vhost-net: avoid ptr_ring tail-drop when a qdisc is present"
  ...

10 files changed, 58 insertions, 34 deletions

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 5d491a98265e..12683b5d125e 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -562,6 +562,7 @@ struct ethtool_fec_hist {
 		u64 per_lane[ETHTOOL_MAX_LANES];
 	} values[ETHTOOL_FEC_HIST_MAX];
 	const struct ethtool_fec_hist_range *ranges;
+	struct ethtool_fec_hist_range ranges_buf[ETHTOOL_FEC_HIST_MAX];
 };
 /**
  * struct ethtool_fec_stats - statistics for IEEE 802.3 FEC
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 5f3e206c7a73..80166eb62f41 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -22,7 +22,6 @@ struct tun_msg_ctl {
 #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE)
 struct socket *tun_get_socket(struct file *);
 struct ptr_ring *tun_get_tx_ring(struct file *file);
-void tun_wake_queue(struct file *file, int consumed);
 
 static inline bool tun_is_xdp_frame(void *ptr)
 {
@@ -56,8 +55,6 @@ static inline struct ptr_ring *tun_get_tx_ring(struct file *f)
 	return ERR_PTR(-EINVAL);
 }
 
-static inline void tun_wake_queue(struct file *f, int consumed) {}
-
 static inline bool tun_is_xdp_frame(void *ptr)
 {
 	return false;
diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h
index dbc614dfe0d5..aafa0c04f917 100644
--- a/include/linux/netfilter/nf_conntrack_sip.h
+++ b/include/linux/netfilter/nf_conntrack_sip.h
@@ -115,7 +115,7 @@ struct nf_nat_sip_hooks {
 			    unsigned int *datalen);
 
 	void (*seq_adjust)(struct sk_buff *skb,
-			   unsigned int protoff, s16 off);
+			   unsigned int protoff, s32 off);
 
 	unsigned int (*expect)(struct sk_buff *skb,
 			       unsigned int protoff,
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index c95e891903f0..d2c3629bbe45 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -98,29 +98,13 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r)
 
 /* Note: callers invoking this in a loop must use a compiler barrier,
  * for example cpu_relax(). Callers must hold producer_lock.
- */
-static inline int __ptr_ring_check_produce(struct ptr_ring *r)
-{
-	if (unlikely(!r->size))
-		return -EINVAL;
-
-	if (data_race(r->queue[r->producer]))
-		return -ENOSPC;
-
-	return 0;
-}
-
-/* Note: callers invoking this in a loop must use a compiler barrier,
- * for example cpu_relax(). Callers must hold producer_lock.
  * Callers are responsible for making sure pointer that is being queued
  * points to a valid data.
  */
 static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
 {
-	int p = __ptr_ring_check_produce(r);
-
-	if (p)
-		return p;
+	if (unlikely(!r->size) || data_race(r->queue[r->producer]))
+		return -ENOSPC;
 
 	/* Make sure the pointer we are storing points to a valid data. */
 	/* Pairs with the dependency ordering in __ptr_ring_consume. */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index e7133ff87fbf..3df59849dcbe 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -767,9 +767,11 @@ struct hci_conn {
 	struct dentry	*debugfs;
 
 	struct hci_dev	*hdev;
+
+	spinlock_t	proto_lock; /* lock guarding protocol data */
 	void		*l2cap_data;
 	void		*sco_data;
-	void		*iso_data;
+	void		*iso_data __guarded_by(&proto_lock);
 
 	struct list_head link_list;
 	struct hci_conn	*parent;
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 417ff51f62fc..e6ca930a3507 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -25,7 +25,9 @@
 #include <linux/netfilter.h>		/* for union nf_inet_addr */
 #include <linux/ip.h>
 #include <linux/ipv6.h>			/* for struct ipv6hdr */
+#include <net/route.h>
 #include <net/ipv6.h>
+#include <net/ip6_fib.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <net/netfilter/nf_conntrack.h>
 #endif
@@ -1972,8 +1974,8 @@ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
-		    struct ip_vs_protocol *pp, int offset,
-		    unsigned int hooknum, struct ip_vs_iphdr *iph);
+		    struct ip_vs_protocol *pp, unsigned int toff,
+		    unsigned int hooknum, struct ip_vs_iphdr *ciph);
 void ip_vs_dest_dst_rcu_free(struct rcu_head *head);
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -1986,8 +1988,8 @@ int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
 int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
-		       struct ip_vs_protocol *pp, int offset,
-		       unsigned int hooknum, struct ip_vs_iphdr *iph);
+		       struct ip_vs_protocol *pp, unsigned int toff,
+		       unsigned int hooknum, struct ip_vs_iphdr *ciph);
 #endif
 
 #ifdef CONFIG_SYSCTL
@@ -2059,15 +2061,15 @@ static inline bool ip_vs_conn_use_hash2(struct ip_vs_conn *cp)
 }
 
 void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
-		    struct ip_vs_conn *cp, int dir);
+		    struct ip_vs_conn *cp, int dir, unsigned int toff,
+		    bool has_ports);
 
 #ifdef CONFIG_IP_VS_IPV6
 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
-		       struct ip_vs_conn *cp, int dir);
+		       struct ip_vs_conn *cp, int dir, unsigned int toff,
+		       bool has_ports, struct ip_vs_iphdr *ciph);
 #endif
 
-__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset);
-
 static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum)
 {
 	__be32 diff[2] = { ~old, new };
@@ -2093,6 +2095,33 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
 	return csum_partial(diff, sizeof(diff), oldsum);
 }
 
+static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af)
+{
+	/* Checksum unnecessary or already validated? */
+	if (skb_csum_unnecessary(skb))
+		return false;
+	/* LOCAL_OUT ? */
+	if (!skb->dev || skb->dev->flags & IFF_LOOPBACK)
+		return false;
+	/* !LOCAL_IN (FORWARD) ? */
+	if (af == AF_INET6) {
+		if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL))
+			return false;
+	} else {
+		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
+			return false;
+	}
+	return true;
+}
+
+static inline bool ip_vs_checksum_common_check(struct sk_buff *skb,
+					       int offset, int proto, int af)
+{
+	if (!ip_vs_checksum_needed(skb, af))
+		return true;
+	return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af);
+}
+
 /* Forget current conntrack (unconfirmed) and attach notrack entry */
 static inline void ip_vs_notrack(struct sk_buff *skb)
 {
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index c024345c9bd8..26d6babd92fc 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -161,6 +161,9 @@ static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect,
 	return nf_ct_expect_related_report(expect, 0, 0, flags);
 }
 
+int nf_ct_expect_related_pair(struct nf_conntrack_expect *expect[],
+			      unsigned int flag);
+
 struct nf_conn_help;
 void nf_ct_expectation_gc(struct nf_conn_help *master_help);
 
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 9d844354c4d9..3be612145c13 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1294,6 +1294,7 @@ static inline void nft_use_inc_restore(u32 *use)
  *	@sets: sets in the table
  *	@objects: stateful objects in the table
  *	@flowtables: flow tables in the table
+ *	@objname_ht: hashtable for objects lookup by name
  *	@hgenerator: handle generator state
  *	@handle: table handle
  *	@use: number of chain references to this table
@@ -1313,6 +1314,7 @@ struct nft_table {
 	struct list_head		sets;
 	struct list_head		objects;
 	struct list_head		flowtables;
+	struct rhltable			objname_ht;
 	u64				hgenerator;
 	u64				handle;
 	u32				use;
@@ -1400,7 +1402,7 @@ static inline void *nft_obj_data(const struct nft_object *obj)
 #define nft_expr_obj(expr)	*((struct nft_object **)nft_expr_priv(expr))
 
 struct nft_object *nft_obj_lookup(const struct net *net,
-				  const struct nft_table *table,
+				  struct nft_table *table,
 				  const struct nlattr *nla, u32 objtype,
 				  u8 genmask);
 
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index ebac60a3d8a1..8b51876efbed 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -80,6 +80,7 @@ struct xdp_sock {
 	 * call of __xsk_generic_xmit().
 	 */
 	struct sk_buff *skb;
+	bool drain_cont;
 
 	struct list_head map_list;
 	/* Protects map_list */
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index ccb3b350001f..2bb1d122b1bc 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -78,6 +78,9 @@ struct xsk_buff_pool {
 	u32 chunk_size;
 	u32 chunk_shift;
 	u32 frame_len;
+	u32 tx_descs_nentries;
+	u32 reclaim_descs;
+	u32 tx_zc_pending_descs;
 	u32 xdp_zc_max_segs;
 	u8 tx_metadata_len; /* inherited from umem */
 	u8 cached_need_wakeup;
@@ -102,12 +105,14 @@ struct xsk_buff_pool {
 
 /* AF_XDP core. */
 struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
-						struct xdp_umem *umem);
+						struct xdp_umem *umem,
+						u32 max_segs);
 int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
 		  u16 queue_id, u16 flags);
 int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_sock *umem_xs,
 			 struct net_device *dev, u16 queue_id);
-int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs);
+int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs,
+		      u32 max_segs);
 void xp_destroy(struct xsk_buff_pool *pool);
 void xp_get_pool(struct xsk_buff_pool *pool);
 bool xp_put_pool(struct xsk_buff_pool *pool);