Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

 1) Make sure SKB control block is in the proper state during IPSEC
    ESP-in-TCP encapsulation. From Sabrina Dubroca.

 2) Various kinds of attributes were not being cloned properly when we
    build new xfrm_state objects from existing ones. Fix from Antony
    Antony.

 3) Make sure to keep BTF sections, from Tony Ambardar.

 4) TX DMA channels need proper locking in lantiq driver, from Hauke
    Mehrtens.

 5) Honour route MTU during forwarding, always. From Maciej
    Żenczykowski.

 6) Fix races in kTLS which can result in crashes, from Rohit
    Maheshwari.

 7) Skip TCP DSACKs with rediculous sequence ranges, from Priyaranjan
    Jha.

 8) Use correct address family in xfrm state lookups, from Herbert Xu.

 9) A bridge FDB flush should not clear out user managed fdb entries
    with the ext_learn flag set, from Nikolay Aleksandrov.

10) Fix nested locking of netdev address lists, from Taehee Yoo.

11) Fix handling of 32-bit DATA_FIN values in mptcp, from Mat Martineau.

12) Fix r8169 data corruptions on RTL8402 chips, from Heiner Kallweit.

13) Don't free command entries in mlx5 while comp handler could still be
    running, from Eran Ben Elisha.

14) Error flow of request_irq() in mlx5 is busted, due to an off by one
    we try to free and IRQ never allocated. From Maor Gottlieb.

15) Fix leak when dumping netlink policies, from Johannes Berg.

16) Sendpage cannot be performed when a page is a slab page, or the page
    count is < 1. Some subsystems such as nvme were doing so. Create a
    "sendpage_ok()" helper and use it as needed, from Coly Li.

17) Don't leak request socket when using syncookes with mptcp, from
    Paolo Abeni.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (111 commits)
  net/core: check length before updating Ethertype in skb_mpls_{push,pop}
  net: mvneta: fix double free of txq->buf
  net_sched: check error pointer in tcf_dump_walker()
  net: team: fix memory leak in __team_options_register
  net: typhoon: Fix a typo Typoon --> Typhoon
  net: hinic: fix DEVLINK build errors
  net: stmmac: Modify configuration method of EEE timers
  tcp: fix syn cookied MPTCP request socket leak
  libceph: use sendpage_ok() in ceph_tcp_sendpage()
  scsi: libiscsi: use sendpage_ok() in iscsi_tcp_segment_map()
  drbd: code cleanup by using sendpage_ok() to check page for kernel_sendpage()
  tcp: use sendpage_ok() to detect misused .sendpage
  nvme-tcp: check page by sendpage_ok() before calling kernel_sendpage()
  net: add WARN_ONCE in kernel_sendpage() for improper zero-copy send
  net: introduce helper sendpage_ok() in include/linux/net.h
  net: usb: pegasus: Proper error handing when setting pegasus' MAC address
  net: core: document two new elements of struct net_device
  netlink: fix policy dump leak
  net/mlx5e: Fix race condition on nhe->n pointer in neigh update
  net/mlx5e: Fix VLAN create flow
  ...

11 files changed, 99 insertions, 32 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 5430febd34be..7636bc71c71f 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -661,7 +661,7 @@
 #define BTF								\
 	.BTF : AT(ADDR(.BTF) - LOAD_OFFSET) {				\
 		__start_BTF = .;					\
-		*(.BTF)							\
+		KEEP(*(.BTF))						\
 		__stop_BTF = .;						\
 	}								\
 	. = ALIGN(4);							\
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c145de0473bc..372100c755e7 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -767,6 +767,8 @@ struct mlx5_cmd_work_ent {
 	u64			ts2;
 	u16			op;
 	bool			polling;
+	/* Track the max comp handlers */
+	refcount_t              refcnt;
 };
 
 struct mlx5_pas {
@@ -933,6 +935,7 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
 			  void *out, int out_size);
 void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome);
+bool mlx5_cmd_is_down(struct mlx5_core_dev *dev);
 
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
diff --git a/include/linux/net.h b/include/linux/net.h
index d48ff1180879..ae713c851342 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -21,6 +21,7 @@
 #include <linux/rcupdate.h>
 #include <linux/once.h>
 #include <linux/fs.h>
+#include <linux/mm.h>
 #include <linux/sockptr.h>
 
 #include <uapi/linux/net.h>
@@ -286,6 +287,21 @@ do {									\
 #define net_get_random_once_wait(buf, nbytes)			\
 	get_random_once_wait((buf), (nbytes))
 
+/*
+ * E.g. XFS meta- & log-data is in slab pages, or bcache meta
+ * data pages, or other high order pages allocated by
+ * __get_free_pages() without __GFP_COMP, which have a page_count
+ * of 0 and/or have PageSlab() set. We cannot use send_page for
+ * those, as that does get_page(); put_page(); and would cause
+ * either a VM_BUG directly, or __page_cache_release a page that
+ * would actually still be referenced by someone, leading to some
+ * obscure delayed Oops somewhere else.
+ */
+static inline bool sendpage_ok(struct page *page)
+{
+	return !PageSlab(page) && page_count(page) >= 1;
+}
+
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
 		   size_t num, size_t len);
 int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7bd4fcdd0738..18dec08439f9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1851,6 +1851,11 @@ enum netdev_priv_flags {
  *	@udp_tunnel_nic:	UDP tunnel offload state
  *	@xdp_state:		stores info on attached XDP BPF programs
  *
+ *	@nested_level:	Used as as a parameter of spin_lock_nested() of
+ *			dev->addr_list_lock.
+ *	@unlink_list:	As netif_addr_lock() can be called recursively,
+ *			keep a list of interfaces to be deleted.
+ *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
  */
@@ -1955,6 +1960,7 @@ struct net_device {
 	unsigned short		type;
 	unsigned short		hard_header_len;
 	unsigned char		min_header_len;
+	unsigned char		name_assign_type;
 
 	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;
@@ -1965,12 +1971,12 @@ struct net_device {
 	unsigned char		addr_len;
 	unsigned char		upper_level;
 	unsigned char		lower_level;
+
 	unsigned short		neigh_priv_len;
 	unsigned short          dev_id;
 	unsigned short          dev_port;
 	spinlock_t		addr_list_lock;
-	unsigned char		name_assign_type;
-	bool			uc_promisc;
+
 	struct netdev_hw_addr_list	uc;
 	struct netdev_hw_addr_list	mc;
 	struct netdev_hw_addr_list	dev_addrs;
@@ -1978,8 +1984,15 @@ struct net_device {
 #ifdef CONFIG_SYSFS
 	struct kset		*queues_kset;
 #endif
+#ifdef CONFIG_LOCKDEP
+	struct list_head	unlink_list;
+#endif
 	unsigned int		promiscuity;
 	unsigned int		allmulti;
+	bool			uc_promisc;
+#ifdef CONFIG_LOCKDEP
+	unsigned char		nested_level;
+#endif
 
 
 	/* Protocol-specific pointers */
@@ -4260,17 +4273,23 @@ static inline void netif_tx_disable(struct net_device *dev)
 
 static inline void netif_addr_lock(struct net_device *dev)
 {
-	spin_lock(&dev->addr_list_lock);
-}
+	unsigned char nest_level = 0;
 
-static inline void netif_addr_lock_nested(struct net_device *dev)
-{
-	spin_lock_nested(&dev->addr_list_lock, dev->lower_level);
+#ifdef CONFIG_LOCKDEP
+	nest_level = dev->nested_level;
+#endif
+	spin_lock_nested(&dev->addr_list_lock, nest_level);
 }
 
 static inline void netif_addr_lock_bh(struct net_device *dev)
 {
-	spin_lock_bh(&dev->addr_list_lock);
+	unsigned char nest_level = 0;
+
+#ifdef CONFIG_LOCKDEP
+	nest_level = dev->nested_level;
+#endif
+	local_bh_disable();
+	spin_lock_nested(&dev->addr_list_lock, nest_level);
 }
 
 static inline void netif_addr_unlock(struct net_device *dev)
@@ -4455,12 +4474,38 @@ extern int		dev_rx_weight;
 extern int		dev_tx_weight;
 extern int		gro_normal_batch;
 
+enum {
+	NESTED_SYNC_IMM_BIT,
+	NESTED_SYNC_TODO_BIT,
+};
+
+#define __NESTED_SYNC_BIT(bit)	((u32)1 << (bit))
+#define __NESTED_SYNC(name)	__NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT)
+
+#define NESTED_SYNC_IMM		__NESTED_SYNC(IMM)
+#define NESTED_SYNC_TODO	__NESTED_SYNC(TODO)
+
+struct netdev_nested_priv {
+	unsigned char flags;
+	void *data;
+};
+
 bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
 struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
 						     struct list_head **iter);
 struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 						     struct list_head **iter);
 
+#ifdef CONFIG_LOCKDEP
+static LIST_HEAD(net_unlink_list);
+
+static inline void net_unlink_todo(struct net_device *dev)
+{
+	if (list_empty(&dev->unlink_list))
+		list_add_tail(&dev->unlink_list, &net_unlink_list);
+}
+#endif
+
 /* iterate through upper list, must be called under RCU read lock */
 #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \
 	for (iter = &(dev)->adj_list.upper, \
@@ -4470,8 +4515,8 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 
 int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
 				  int (*fn)(struct net_device *upper_dev,
-					    void *data),
-				  void *data);
+					    struct netdev_nested_priv *priv),
+				  struct netdev_nested_priv *priv);
 
 bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
 				  struct net_device *upper_dev);
@@ -4508,12 +4553,12 @@ struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 					     struct list_head **iter);
 int netdev_walk_all_lower_dev(struct net_device *dev,
 			      int (*fn)(struct net_device *lower_dev,
-					void *data),
-			      void *data);
+					struct netdev_nested_priv *priv),
+			      struct netdev_nested_priv *priv);
 int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
 				  int (*fn)(struct net_device *lower_dev,
-					    void *data),
-				  void *data);
+					    struct netdev_nested_priv *priv),
+				  struct netdev_nested_priv *priv);
 
 void *netdev_adjacent_get_private(struct list_head *adj_list);
 void *netdev_lower_get_first_private_rcu(struct net_device *dev);
diff --git a/include/net/act_api.h b/include/net/act_api.h
index cb382a89ea58..87214927314a 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -166,8 +166,6 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
 			      struct nlattr *est, struct tc_action **a,
 			      const struct tc_action_ops *ops, int bind,
 			      u32 flags);
-void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
-
 void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
 int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
 			struct tc_action **a, int bind);
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 6e5f1e1aa822..8899d7429ccb 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -138,6 +138,7 @@ genl_dumpit_info(struct netlink_callback *cb)
  * @cmd: command identifier
  * @internal_flags: flags used by the family
  * @flags: flags
+ * @validate: validation flags from enum genl_validate_flags
  * @doit: standard command callback
  * @start: start callback for dumps
  * @dumpit: callback for dumpers
diff --git a/include/net/ip.h b/include/net/ip.h
index b09c48d862cc..2a52787db64a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -436,12 +436,18 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 						    bool forwarding)
 {
 	struct net *net = dev_net(dst->dev);
+	unsigned int mtu;
 
 	if (net->ipv4.sysctl_ip_fwd_use_pmtu ||
 	    ip_mtu_locked(dst) ||
 	    !forwarding)
 		return dst_mtu(dst);
 
+	/* 'forwarding = true' case should always honour route mtu */
+	mtu = dst_metric_raw(dst, RTAX_MTU);
+	if (mtu)
+		return mtu;
+
 	return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU);
 }
 
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 8e0eb2c9c528..271620f6bc7f 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1934,7 +1934,8 @@ void nla_get_range_signed(const struct nla_policy *pt,
 int netlink_policy_dump_start(const struct nla_policy *policy,
 			      unsigned int maxtype,
 			      unsigned long *state);
-bool netlink_policy_dump_loop(unsigned long *state);
+bool netlink_policy_dump_loop(unsigned long state);
 int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state);
+void netlink_policy_dump_free(unsigned long state);
 
 #endif
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 2737d24ec244..9e806c781025 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1773,21 +1773,17 @@ static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_es
 static inline int xfrm_replay_clone(struct xfrm_state *x,
 				     struct xfrm_state *orig)
 {
-	x->replay_esn = kzalloc(xfrm_replay_state_esn_len(orig->replay_esn),
+
+	x->replay_esn = kmemdup(orig->replay_esn,
+				xfrm_replay_state_esn_len(orig->replay_esn),
 				GFP_KERNEL);
 	if (!x->replay_esn)
 		return -ENOMEM;
-
-	x->replay_esn->bmp_len = orig->replay_esn->bmp_len;
-	x->replay_esn->replay_window = orig->replay_esn->replay_window;
-
-	x->preplay_esn = kmemdup(x->replay_esn,
-				 xfrm_replay_state_esn_len(x->replay_esn),
+	x->preplay_esn = kmemdup(orig->preplay_esn,
+				 xfrm_replay_state_esn_len(orig->preplay_esn),
 				 GFP_KERNEL);
-	if (!x->preplay_esn) {
-		kfree(x->replay_esn);
+	if (!x->preplay_esn)
 		return -ENOMEM;
-	}
 
 	return 0;
 }
diff --git a/include/soc/mscc/ocelot_ana.h b/include/soc/mscc/ocelot_ana.h
index 841c6ec22b64..1669481d9779 100644
--- a/include/soc/mscc/ocelot_ana.h
+++ b/include/soc/mscc/ocelot_ana.h
@@ -252,10 +252,10 @@
 #define ANA_SG_CONFIG_REG_3_LIST_LENGTH_M                 GENMASK(18, 16)
 #define ANA_SG_CONFIG_REG_3_LIST_LENGTH_X(x)              (((x) & GENMASK(18, 16)) >> 16)
 #define ANA_SG_CONFIG_REG_3_GATE_ENABLE                   BIT(20)
-#define ANA_SG_CONFIG_REG_3_INIT_IPS(x)                   (((x) << 24) & GENMASK(27, 24))
-#define ANA_SG_CONFIG_REG_3_INIT_IPS_M                    GENMASK(27, 24)
-#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x)                 (((x) & GENMASK(27, 24)) >> 24)
-#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE               BIT(28)
+#define ANA_SG_CONFIG_REG_3_INIT_IPS(x)                   (((x) << 21) & GENMASK(24, 21))
+#define ANA_SG_CONFIG_REG_3_INIT_IPS_M                    GENMASK(24, 21)
+#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x)                 (((x) & GENMASK(24, 21)) >> 21)
+#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE               BIT(25)
 
 #define ANA_SG_GCL_GS_CONFIG_RSZ                          0x4
 
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index cee9f8e6fce3..f84e7bcad6de 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -288,6 +288,7 @@ enum
 	LINUX_MIB_TCPTIMEOUTREHASH,		/* TCPTimeoutRehash */
 	LINUX_MIB_TCPDUPLICATEDATAREHASH,	/* TCPDuplicateDataRehash */
 	LINUX_MIB_TCPDSACKRECVSEGS,		/* TCPDSACKRecvSegs */
+	LINUX_MIB_TCPDSACKIGNOREDDUBIOUS,	/* TCPDSACKIgnoredDubious */
 	__LINUX_MIB_MAX
 };