Merge tag 'net-7.3-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from Bluetooth, NFC and Netfilter.

  Every week in this release is record-setting for number of posted
  patches. It doesn't seem like we're creating any regressions with all
  these fixes, three 'Fixes' tags here point to 7.2 commits but none are
  true regression fixes. We're trying to keep the count down,
  nonetheless.

  Previous releases - regressions:

   - net: don't require the hwtstamp NDOs when a PHY provides
     timestamping

   - ipv6: fix dst leak for uncached routes

   - vrf: stop corrupting skb->csum when capturing CHECKSUM_COMPLETE
     packets

  Previous releases - always broken:

   - packet: use ubuf_info completion for TX_RING packets

   - arp: terminate device name before lookup

   - ipv6: do not let ipv6_find_hdr() return an offset past the packet
     end

   - udp: remove a disconnected socket from the 4-tuple hash table

   - sctp: discard the rest of the packet on a stale-cookie error

   - eth: mlx5: Bridge, fix remaining switchdev ownership gaps on merged
     eswitch"

[ And lots of other random network driver fixes ]

* tag 'net-7.3-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (189 commits)
  tcp: prevent collapsing skbs across boundary in rtx queue
  vlan: ensure sufficient headroom in vlan_dev_hard_header()
  net/sched: sch_teql: fix shadowed err in __teql_resolve()
  bridge: check llc_mac_hdr_init() return value in br_send_bpdu()
  llc: fix skb UAF and leaks on llc_mac_hdr_init() failure
  llc: reserve device headroom for allocated frames
  gve: DQO: reject TSO packets with an out of range MSS
  gve: fix TX drop when GSO MSS is too small for hw
  gve: DQO: fix header length used by gve_can_send_tso() for UDP GSO
  net: flush skb_defer_nodes in dev_cpu_dead()
  net: ethernet: stmmac: dwmac-rk: fix bulk clock leak when the PHY clock fails
  af_packet: fix integer overflow in prb_calc_retire_blk_tmo()
  tipc: Fix a data race on mon->peer_cnt in mon_timeout()
  net: phy: intel-xway: workaround 100BASE-TX Link-Up issue
  net/smc: fix UAF on lgr list traversal in smcr_port_err()
  net/rds: size a connection's path set by the transport it ends up with
  nfp: hold IPsec RX state under the XArray lock
  net: ena: fix MMIO read buffer leak on probe failure
  net: ena: fix PHC cleanup on probe failure
  net/sched: act_ct: fix helper UAF due to extensions realloc
  ...

10 files changed, 35 insertions, 29 deletions

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 253600c0eccd..c4c9ce038611 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -944,6 +944,7 @@ struct kernel_ethtool_ts_info {
 #define ETHTOOL_OP_NEEDS_RTNL_SPAUSEPARAM	BIT(6)
 #define ETHTOOL_OP_NEEDS_RTNL_RSS		BIT(7)
 #define ETHTOOL_OP_NEEDS_RTNL_GLINK		BIT(8)
+#define ETHTOOL_OP_NEEDS_RTNL_TEST		BIT(9)
 
 /**
  * struct ethtool_ops - optional netdev operations
@@ -981,6 +982,7 @@ struct kernel_ethtool_ts_info {
  *	 - netdev_update_features()
  *	 - netif_set_real_num_tx_queues()
  *	 - ethtool_op_get_link() (syncs link watch under rtnl_lock)
+ *	 - netif_open() / netif_close() (used by @self_test)
  *
  * @get_drvinfo: Report driver/device information. Modern drivers no
  *	longer have to implement this callback. Most fields are
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 20cc16ea4e5a..4846032bf4ff 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -365,6 +365,9 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb,
 	const u8 meta_len = mac_len > ETH_TLEN ? skb_metadata_len(skb) : 0;
 	struct vlan_ethhdr *veth;
 
+	if (unlikely(!pskb_may_pull(skb, mac_len)))
+		return -EINVAL;
+
 	if (skb_cow_head(skb, meta_len + VLAN_HLEN) < 0)
 		return -ENOMEM;
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c8e21903074c..84308498a3a8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1834,22 +1834,6 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg,
 	}
 }
 
-static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val)
-{
-	skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL);
-	skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG;
-}
-
-static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb)
-{
-	return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL;
-}
-
-static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb)
-{
-	return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL);
-}
-
 static inline void net_zcopy_put(struct ubuf_info *uarg)
 {
 	if (uarg)
@@ -1872,8 +1856,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success)
 	struct ubuf_info *uarg = skb_zcopy(skb);
 
 	if (uarg) {
-		if (!skb_zcopy_is_nouarg(skb))
-			uarg->ops->complete(skb, uarg, zerocopy_success);
+		uarg->ops->complete(skb, uarg, zerocopy_success);
 
 		skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY;
 	}
diff --git a/include/net/dst.h b/include/net/dst.h
index 307073eae7f8..dbedfe72e1fd 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -455,7 +455,8 @@ static inline unsigned int dst_dev_overhead(struct dst_entry *dst,
 					    struct sk_buff *skb)
 {
 	if (likely(dst))
-		return LL_RESERVED_SPACE(dst->dev);
+		return max_t(unsigned int, skb->mac_len,
+			     LL_RESERVED_SPACE(dst->dev));
 
 	return skb->mac_len;
 }
diff --git a/include/net/gue.h b/include/net/gue.h
index caefd6da8693..d377155fd0b3 100644
--- a/include/net/gue.h
+++ b/include/net/gue.h
@@ -84,8 +84,9 @@ static inline size_t guehdr_priv_flags_len(__be32 flags)
 }
 
 /* Validate standard and private flags. Returns non-zero (meaning invalid)
- * if there is an unknown standard or private flags, or the options length for
- * the flags exceeds the options length specific in hlen of the GUE header.
+ * if there is an unknown standard or private flags, if the options length for
+ * the flags exceeds the options length specified in hlen of the GUE header, or
+ * if a private option contains invalid data.
  */
 static inline int validate_gue_flags(struct guehdr *guehdr, size_t optlen)
 {
@@ -103,8 +104,8 @@ static inline int validate_gue_flags(struct guehdr *guehdr, size_t optlen)
 		/* Private flags are last four bytes accounted in
 		 * guehdr_flags_len
 		 */
-		__be32 pflags = *(__be32 *)((void *)&guehdr[1] +
-					    len - GUE_LEN_PRIV);
+		void *data = (void *)&guehdr[1] + len;
+		__be32 pflags = *(__be32 *)(data - GUE_LEN_PRIV);
 
 		if (pflags & ~GUE_PFLAGS_ALL)
 			return 1;
@@ -112,6 +113,16 @@ static inline int validate_gue_flags(struct guehdr *guehdr, size_t optlen)
 		len += guehdr_priv_flags_len(pflags);
 		if (len > optlen)
 			return 1;
+
+		if (pflags & GUE_PFLAG_REMCSUM) {
+			__be16 *pd = data;
+
+			/* The field offset pd[1] must not be less
+			 * than the start pd[0].
+			 */
+			if (ntohs(pd[1]) < ntohs(pd[0]))
+				return 1;
+		}
 	}
 
 	return 0;
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index b9e8d2b759e9..0f9b7a260d25 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -101,12 +101,12 @@ static inline struct dst_entry *ip6_route_output(struct net *net,
 }
 
 /* Only conditionally release dst if flags indicates
- * !RT6_LOOKUP_F_DST_NOREF or dst is in uncached_list.
+ * !RT6_LOOKUP_F_DST_NOREF or dst is uncached.
  */
 static inline void ip6_rt_put_flags(struct rt6_info *rt, int flags)
 {
 	if (!(flags & RT6_LOOKUP_F_DST_NOREF) ||
-	    !list_empty(&rt->dst.rt_uncached))
+	    rt->dst.rt_uncached_list)
 		ip6_rt_put(rt);
 }
 
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index bc42dd0e10e6..c39425e54d87 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -185,6 +185,11 @@ static inline void nf_ct_put(struct nf_conn *ct)
 		nf_ct_destroy(&ct->ct_general);
 }
 
+static inline bool nf_ct_shared(const struct nf_conn *ct)
+{
+	return refcount_read(&ct->ct_general.use) > 1;
+}
+
 /* load module; enable/disable conntrack in this namespace */
 int nf_ct_netns_get(struct net *net, u8 nfproto);
 void nf_ct_netns_put(struct net *net, u8 nfproto);
diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 756c11084f65..86ed63e5d533 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -144,7 +144,7 @@ struct nfc_hci_dev {
 	data_exchange_cb_t async_cb;
 	void *async_cb_context;
 
-	u8 *gb;
+	u8 gb[NFC_MAX_GT_LEN];
 	size_t gb_len;
 
 	unsigned long quirks;
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index c54df042db6b..bcafab5c53e5 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -273,7 +273,8 @@ struct sk_buff *nfc_alloc_recv_skb(unsigned int size, gfp_t gfp);
 
 int nfc_set_remote_general_bytes(struct nfc_dev *dev,
 				 const u8 *gt, u8 gt_len);
-u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, size_t *gb_len);
+u8 *nfc_get_local_general_bytes(struct nfc_dev *dev, u8 *out_gb,
+				size_t gb_max_len, size_t *gb_len);
 
 int nfc_fw_download_done(struct nfc_dev *dev, const char *firmware_name,
 			 u32 result);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 436495ff2271..4416cdf9bf30 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1232,9 +1232,9 @@ static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb)
 static inline bool tcp_skb_can_collapse(const struct sk_buff *to,
 					const struct sk_buff *from)
 {
-	/* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */
 	return likely(tcp_skb_can_collapse_to(to) &&
 		      mptcp_skb_can_collapse(to, from) &&
+		      !skb_cmp_decrypted(to, from) &&
 		      skb_pure_zcopy_same(to, from) &&
 		      skb_frags_readable(to) == skb_frags_readable(from));
 }
@@ -2327,7 +2327,7 @@ static inline void tcp_rtx_queue_unlink_and_free(struct sk_buff *skb, struct soc
 
 static inline void tcp_write_collapse_fence(struct sock *sk)
 {
-	struct sk_buff *skb = tcp_write_queue_tail(sk);
+	struct sk_buff *skb = tcp_write_queue_tail(sk) ?: tcp_rtx_queue_tail(sk);
 
 	if (skb)
 		TCP_SKB_CB(skb)->eor = 1;