Merge tag 'net-6.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from bpf and netfilter.

  Current release - regressions:

   - gro: initialize network_offset in network layer

   - tcp: reduce accepted window in NEW_SYN_RECV state

  Current release - new code bugs:

   - eth: mlx5e: do not use ptp structure for tx ts stats when not
     initialized

   - eth: ice: check for unregistering correct number of devlink params

  Previous releases - regressions:

   - bpf: Allow delete from sockmap/sockhash only if update is allowed

   - sched: taprio: extend minimum interval restriction to entire cycle
     too

   - netfilter: ipset: add list flush to cancel_gc

   - ipv4: fix address dump when IPv4 is disabled on an interface

   - sock_map: avoid race between sock_map_close and sk_psock_put

   - eth: mlx5: use mlx5_ipsec_rx_status_destroy to correctly delete
     status rules

  Previous releases - always broken:

   - core: fix __dst_negative_advice() race

   - bpf:
       - fix multi-uprobe PID filtering logic
       - fix pkt_type override upon netkit pass verdict

   - netfilter: tproxy: bail out if IP has been disabled on the device

   - af_unix: annotate data-race around unix_sk(sk)->addr

   - eth: mlx5e: fix UDP GSO for encapsulated packets

   - eth: idpf: don't enable NAPI and interrupts prior to allocating Rx
     buffers

   - eth: i40e: fully suspend and resume IO operations in EEH case

   - eth: octeontx2-pf: free send queue buffers incase of leaf to inner

   - eth: ipvlan: dont Use skb->sk in ipvlan_process_v{4,6}_outbound"

* tag 'net-6.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (69 commits)
  netdev: add qstat for csum complete
  ipvlan: Dont Use skb->sk in ipvlan_process_v{4,6}_outbound
  net: ena: Fix redundant device NUMA node override
  ice: check for unregistering correct number of devlink params
  ice: fix 200G PHY types to link speed mapping
  i40e: Fully suspend and resume IO operations in EEH case
  i40e: factoring out i40e_suspend/i40e_resume
  e1000e: move force SMBUS near the end of enable_ulp function
  net: dsa: microchip: fix RGMII error in KSZ DSA driver
  ipv4: correctly iterate over the target netns in inet_dump_ifaddr()
  net: fix __dst_negative_advice() race
  nfc/nci: Add the inconsistency check between the input data length and count
  MAINTAINERS: dwmac: starfive: update Maintainer
  net/sched: taprio: extend minimum interval restriction to entire cycle too
  net/sched: taprio: make q->picos_per_byte available to fill_sched_entry()
  netfilter: nft_fib: allow from forward/input without iif selector
  netfilter: tproxy: bail out if IP has been disabled on the device
  netfilter: nft_payload: skbuff vlan metadata mangle support
  net: ti: icssg-prueth: Fix start counter for ft1 filter
  sock_map: avoid race between sock_map_close and sk_psock_put
  ...

8 files changed, 31 insertions, 17 deletions

diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 2ad1ffa4ccb9..0ed47d00549b 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -636,6 +636,14 @@ static inline void eth_skb_pkt_type(struct sk_buff *skb,
 	}
 }
 
+static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb)
+{
+	struct ethhdr *eth = (struct ethhdr *)skb->data;
+
+	skb_pull_inline(skb, ETH_HLEN);
+	return eth;
+}
+
 /**
  * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame
  * @skb: Buffer to pad
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index f468763478ae..5df52e15f7d6 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10308,9 +10308,9 @@ struct mlx5_ifc_mcam_access_reg_bits {
 	u8         mfrl[0x1];
 	u8         regs_39_to_32[0x8];
 
-	u8         regs_31_to_10[0x16];
+	u8         regs_31_to_11[0x15];
 	u8         mtmp[0x1];
-	u8         regs_8_to_0[0x9];
+	u8         regs_9_to_0[0xa];
 };
 
 struct mlx5_ifc_mcam_access_reg_bits1 {
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 6d1c8541183d..3a9001a042a5 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -24,7 +24,7 @@ struct dst_ops {
 	void			(*destroy)(struct dst_entry *);
 	void			(*ifdown)(struct dst_entry *,
 					  struct net_device *dev);
-	struct dst_entry *	(*negative_advice)(struct dst_entry *);
+	void			(*negative_advice)(struct sock *sk, struct dst_entry *);
 	void			(*link_failure)(struct sk_buff *);
 	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
 					       struct sk_buff *skb, u32 mtu,
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index b088d131aeb0..7e8477057f3d 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -45,16 +45,17 @@ struct pp_alloc_cache {
 
 /**
  * struct page_pool_params - page pool parameters
+ * @fast:	params accessed frequently on hotpath
  * @order:	2^order pages on allocation
  * @pool_size:	size of the ptr_ring
  * @nid:	NUMA node id to allocate from pages from
  * @dev:	device, for DMA pre-mapping purposes
- * @netdev:	netdev this pool will serve (leave as NULL if none or multiple)
  * @napi:	NAPI which is the sole consumer of pages, otherwise NULL
  * @dma_dir:	DMA mapping direction
  * @max_len:	max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV
  * @offset:	DMA sync address offset for PP_FLAG_DMA_SYNC_DEV
- * @netdev:	corresponding &net_device for Netlink introspection
+ * @slow:	params with slowpath access only (initialization and Netlink)
+ * @netdev:	netdev this pool will serve (leave as NULL if none or multiple)
  * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL
  */
 struct page_pool_params {
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index d88c0dfc2d46..ebcb8896bffc 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -285,4 +285,16 @@ static inline int reqsk_queue_len_young(const struct request_sock_queue *queue)
 	return atomic_read(&queue->young);
 }
 
+/* RFC 7323 2.3 Using the Window Scale Option
+ *  The window field (SEG.WND) of every outgoing segment, with the
+ *  exception of <SYN> segments, MUST be right-shifted by
+ *  Rcv.Wind.Shift bits.
+ *
+ * This means the SEG.WND carried in SYNACK can not exceed 65535.
+ * We use this property to harden TCP stack while in NEW_SYN_RECV state.
+ */
+static inline u32 tcp_synack_window(const struct request_sock *req)
+{
+	return min(req->rsk_rcv_wnd, 65535U);
+}
 #endif /* _REQUEST_SOCK_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 5f4d0629348f..953c8dc4e259 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2063,17 +2063,10 @@ sk_dst_get(const struct sock *sk)
 
 static inline void __dst_negative_advice(struct sock *sk)
 {
-	struct dst_entry *ndst, *dst = __sk_dst_get(sk);
+	struct dst_entry *dst = __sk_dst_get(sk);
 
-	if (dst && dst->ops->negative_advice) {
-		ndst = dst->ops->negative_advice(dst);
-
-		if (ndst != dst) {
-			rcu_assign_pointer(sk->sk_dst_cache, ndst);
-			sk_tx_queue_clear(sk);
-			WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
-		}
-	}
+	if (dst && dst->ops->negative_advice)
+		dst->ops->negative_advice(sk, dst);
 }
 
 static inline void dst_negative_advice(struct sock *sk)
diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h
index f2afb7cc4926..18e3745b86cd 100644
--- a/include/uapi/linux/cn_proc.h
+++ b/include/uapi/linux/cn_proc.h
@@ -69,8 +69,7 @@ struct proc_input {
 
 static inline enum proc_cn_event valid_event(enum proc_cn_event ev_type)
 {
-	ev_type &= PROC_EVENT_ALL;
-	return ev_type;
+	return (enum proc_cn_event)(ev_type & PROC_EVENT_ALL);
 }
 
 /*
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index a8188202413e..43742ac5b00d 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -148,6 +148,7 @@ enum {
 	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
 	NETDEV_A_QSTATS_RX_HW_DROPS,
 	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+	NETDEV_A_QSTATS_RX_CSUM_COMPLETE,
 	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
 	NETDEV_A_QSTATS_RX_CSUM_NONE,
 	NETDEV_A_QSTATS_RX_CSUM_BAD,