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

Pull networking fixes from David Miller:

 1) Fix free/alloc races in batmanadv, from Sven Eckelmann.

 2) Several leaks and other fixes in kTLS support of mlx5 driver, from
    Tariq Toukan.

 3) BPF devmap_hash cost calculation can overflow on 32-bit, from Toke
    Høiland-Jørgensen.

 4) Add an r8152 device ID, from Kazutoshi Noguchi.

 5) Missing include in ipv6's addrconf.c, from Ben Dooks.

 6) Use siphash in flow dissector, from Eric Dumazet. Attackers can
    easily infer the 32-bit secret otherwise etc.

 7) Several netdevice nesting depth fixes from Taehee Yoo.

 8) Fix several KCSAN reported errors, from Eric Dumazet. For example,
    when doing lockless skb_queue_empty() checks, and accessing
    sk_napi_id/sk_incoming_cpu lockless as well.

 9) Fix jumbo packet handling in RXRPC, from David Howells.

10) Bump SOMAXCONN and tcp_max_syn_backlog values, from Eric Dumazet.

11) Fix DMA synchronization in gve driver, from Yangchun Fu.

12) Several bpf offload fixes, from Jakub Kicinski.

13) Fix sk_page_frag() recursion during memory reclaim, from Tejun Heo.

14) Fix ping latency during high traffic rates in hisilicon driver, from
    Jiangfent Xiao.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (146 commits)
  net: fix installing orphaned programs
  net: cls_bpf: fix NULL deref on offload filter removal
  selftests: bpf: Skip write only files in debugfs
  selftests: net: reuseport_dualstack: fix uninitalized parameter
  r8169: fix wrong PHY ID issue with RTL8168dp
  net: dsa: bcm_sf2: Fix IMP setup for port different than 8
  net: phylink: Fix phylink_dbg() macro
  gve: Fixes DMA synchronization.
  inet: stop leaking jiffies on the wire
  ixgbe: Remove duplicate clear_bit() call
  Documentation: networking: device drivers: Remove stray asterisks
  e1000: fix memory leaks
  i40e: Fix receive buffer starvation for AF_XDP
  igb: Fix constant media auto sense switching when no cable is connected
  net: ethernet: arc: add the missed clk_disable_unprepare
  igb: Enable media autosense for the i350.
  igb/igc: Don't warn on fatal read failures when the device is removed
  tcp: increase tcp_max_syn_backlog max value
  net: increase SOMAXCONN to 4096
  netdevsim: Fix use-after-free during device dismantle
  ...

10 files changed, 85 insertions, 60 deletions

diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 6c809440f319..4cf02ecd67de 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -204,6 +204,12 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val,
 	do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0)
 #define dynamic_dev_dbg(dev, fmt, ...)					\
 	do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0)
+#define dynamic_hex_dump(prefix_str, prefix_type, rowsize,		\
+			 groupsize, buf, len, ascii)			\
+	do { if (0)							\
+		print_hex_dump(KERN_DEBUG, prefix_str, prefix_type,	\
+				rowsize, groupsize, buf, len, ascii);	\
+	} while (0)
 #endif
 
 #endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 2ce57645f3cd..0367a75f873b 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1099,7 +1099,6 @@ static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
 
 #endif /* CONFIG_BPF_JIT */
 
-void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp);
 void bpf_prog_kallsyms_del_all(struct bpf_prog *fp);
 
 #define BPF_ANC		BIT(15)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index fb07b503dc45..61f2f6ff9467 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -325,6 +325,29 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
 	return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
 }
 
+/**
+ * gfpflags_normal_context - is gfp_flags a normal sleepable context?
+ * @gfp_flags: gfp_flags to test
+ *
+ * Test whether @gfp_flags indicates that the allocation is from the
+ * %current context and allowed to sleep.
+ *
+ * An allocation being allowed to block doesn't mean it owns the %current
+ * context.  When direct reclaim path tries to allocate memory, the
+ * allocation context is nested inside whatever %current was doing at the
+ * time of the original allocation.  The nested allocation may be allowed
+ * to block but modifying anything %current owns can corrupt the outer
+ * context's expectations.
+ *
+ * %true result from this function indicates that the allocation context
+ * can sleep and use anything that's associated with %current.
+ */
+static inline bool gfpflags_normal_context(const gfp_t gfp_flags)
+{
+	return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) ==
+		__GFP_DIRECT_RECLAIM;
+}
+
 #ifdef CONFIG_HIGHMEM
 #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
 #else
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 2e55e4cdbd8a..a367ead4bf4b 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -29,7 +29,6 @@ struct macvlan_dev {
 	netdev_features_t	set_features;
 	enum macvlan_mode	mode;
 	u16			flags;
-	int			nest_level;
 	unsigned int		macaddr_count;
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	struct netpoll		*netpoll;
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index 06faa066496f..ec7e4bd07f82 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -223,6 +223,7 @@ struct team {
 		atomic_t count_pending;
 		struct delayed_work dw;
 	} mcast_rejoin;
+	struct lock_class_key team_lock_key;
 	long mode_priv[TEAM_MODE_PRIV_LONGS];
 };
 
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 244278d5c222..b05e855f1ddd 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -182,7 +182,6 @@ struct vlan_dev_priv {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	struct netpoll				*netpoll;
 #endif
-	unsigned int				nest_level;
 };
 
 static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
@@ -221,11 +220,6 @@ extern void vlan_vids_del_by_dev(struct net_device *dev,
 
 extern bool vlan_uses_dev(const struct net_device *dev);
 
-static inline int vlan_get_encap_level(struct net_device *dev)
-{
-	BUG_ON(!is_vlan_dev(dev));
-	return vlan_dev_priv(dev)->nest_level;
-}
 #else
 static inline struct net_device *
 __vlan_find_dev_deep_rcu(struct net_device *real_dev,
@@ -295,11 +289,6 @@ static inline bool vlan_uses_dev(const struct net_device *dev)
 {
 	return false;
 }
-static inline int vlan_get_encap_level(struct net_device *dev)
-{
-	BUG();
-	return 0;
-}
 #endif
 
 /**
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 138c50d5a353..0836fe232f97 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1545,9 +1545,8 @@ struct mlx5_ifc_extended_dest_format_bits {
 };
 
 union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits {
-	struct mlx5_ifc_dest_format_struct_bits dest_format_struct;
+	struct mlx5_ifc_extended_dest_format_bits extended_dest_format;
 	struct mlx5_ifc_flow_counter_list_bits flow_counter_list;
-	u8         reserved_at_0[0x40];
 };
 
 struct mlx5_ifc_fte_match_param_bits {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9eda1c31d1f7..c20f190b4c18 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -925,6 +925,7 @@ struct dev_ifalias {
 struct devlink;
 struct tlsdev_ops;
 
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -1421,7 +1422,6 @@ struct net_device_ops {
 	void			(*ndo_dfwd_del_station)(struct net_device *pdev,
 							void *priv);
 
-	int			(*ndo_get_lock_subclass)(struct net_device *dev);
 	int			(*ndo_set_tx_maxrate)(struct net_device *dev,
 						      int queue_index,
 						      u32 maxrate);
@@ -1649,6 +1649,8 @@ enum netdev_priv_flags {
  * 	@perm_addr:		Permanent hw address
  * 	@addr_assign_type:	Hw address assignment type
  * 	@addr_len:		Hardware address length
+ *	@upper_level:		Maximum depth level of upper devices.
+ *	@lower_level:		Maximum depth level of lower devices.
  *	@neigh_priv_len:	Used in neigh_alloc()
  * 	@dev_id:		Used to differentiate devices that share
  * 				the same link layer address
@@ -1758,9 +1760,13 @@ enum netdev_priv_flags {
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
  *	@sfp_bus:	attached &struct sfp_bus structure.
- *
- *	@qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
- *	@qdisc_running_key: lockdep class annotating Qdisc->running seqcount
+ *	@qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock
+				spinlock
+ *	@qdisc_running_key:	lockdep class annotating Qdisc->running seqcount
+ *	@qdisc_xmit_lock_key:	lockdep class annotating
+ *				netdev_queue->_xmit_lock spinlock
+ *	@addr_list_lock_key:	lockdep class annotating
+ *				net_device->addr_list_lock spinlock
  *
  *	@proto_down:	protocol port state information can be sent to the
  *			switch driver and used to set the phys state of the
@@ -1875,6 +1881,8 @@ struct net_device {
 	unsigned char		perm_addr[MAX_ADDR_LEN];
 	unsigned char		addr_assign_type;
 	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;
@@ -2045,8 +2053,10 @@ struct net_device {
 #endif
 	struct phy_device	*phydev;
 	struct sfp_bus		*sfp_bus;
-	struct lock_class_key	*qdisc_tx_busylock;
-	struct lock_class_key	*qdisc_running_key;
+	struct lock_class_key	qdisc_tx_busylock_key;
+	struct lock_class_key	qdisc_running_key;
+	struct lock_class_key	qdisc_xmit_lock_key;
+	struct lock_class_key	addr_list_lock_key;
 	bool			proto_down;
 	unsigned		wol_enabled:1;
 };
@@ -2124,23 +2134,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 		f(dev, &dev->_tx[i], arg);
 }
 
-#define netdev_lockdep_set_classes(dev)				\
-{								\
-	static struct lock_class_key qdisc_tx_busylock_key;	\
-	static struct lock_class_key qdisc_running_key;		\
-	static struct lock_class_key qdisc_xmit_lock_key;	\
-	static struct lock_class_key dev_addr_list_lock_key;	\
-	unsigned int i;						\
-								\
-	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
-	(dev)->qdisc_running_key = &qdisc_running_key;		\
-	lockdep_set_class(&(dev)->addr_list_lock,		\
-			  &dev_addr_list_lock_key); 		\
-	for (i = 0; i < (dev)->num_tx_queues; i++)		\
-		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
-				  &qdisc_xmit_lock_key);	\
-}
-
 u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev);
 struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
@@ -3139,6 +3132,7 @@ static inline void netif_stop_queue(struct net_device *dev)
 }
 
 void netif_tx_stop_all_queues(struct net_device *dev);
+void netdev_update_lockdep_key(struct net_device *dev);
 
 static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
 {
@@ -4056,16 +4050,6 @@ static inline void netif_addr_lock(struct net_device *dev)
 	spin_lock(&dev->addr_list_lock);
 }
 
-static inline void netif_addr_lock_nested(struct net_device *dev)
-{
-	int subclass = SINGLE_DEPTH_NESTING;
-
-	if (dev->netdev_ops->ndo_get_lock_subclass)
-		subclass = dev->netdev_ops->ndo_get_lock_subclass(dev);
-
-	spin_lock_nested(&dev->addr_list_lock, subclass);
-}
-
 static inline void netif_addr_lock_bh(struct net_device *dev)
 {
 	spin_lock_bh(&dev->addr_list_lock);
@@ -4329,6 +4313,16 @@ int netdev_master_upper_dev_link(struct net_device *dev,
 				 struct netlink_ext_ack *extack);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev);
+int netdev_adjacent_change_prepare(struct net_device *old_dev,
+				   struct net_device *new_dev,
+				   struct net_device *dev,
+				   struct netlink_ext_ack *extack);
+void netdev_adjacent_change_commit(struct net_device *old_dev,
+				   struct net_device *new_dev,
+				   struct net_device *dev);
+void netdev_adjacent_change_abort(struct net_device *old_dev,
+				  struct net_device *new_dev,
+				  struct net_device *dev);
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
 void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);
@@ -4340,7 +4334,6 @@ void netdev_lower_state_changed(struct net_device *lower_dev,
 extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly;
 void netdev_rss_key_fill(void *buffer, size_t len);
 
-int dev_get_nest_level(struct net_device *dev);
 int skb_checksum_help(struct sk_buff *skb);
 int skb_crc32c_csum_help(struct sk_buff *skb);
 int skb_csum_hwoffload_help(struct sk_buff *skb,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7914fdaf4226..64a395c7f689 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1354,7 +1354,8 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6
 	return skb->hash;
 }
 
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb);
+__u32 skb_get_hash_perturb(const struct sk_buff *skb,
+			   const siphash_key_t *perturb);
 
 static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
 {
@@ -1495,6 +1496,19 @@ static inline int skb_queue_empty(const struct sk_buff_head *list)
 }
 
 /**
+ *	skb_queue_empty_lockless - check if a queue is empty
+ *	@list: queue head
+ *
+ *	Returns true if the queue is empty, false otherwise.
+ *	This variant can be used in lockless contexts.
+ */
+static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list)
+{
+	return READ_ONCE(list->next) == (const struct sk_buff *) list;
+}
+
+
+/**
  *	skb_queue_is_last - check if skb is the last entry in the queue
  *	@list: queue head
  *	@skb: buffer
@@ -1847,9 +1861,11 @@ static inline void __skb_insert(struct sk_buff *newsk,
 				struct sk_buff *prev, struct sk_buff *next,
 				struct sk_buff_head *list)
 {
-	newsk->next = next;
-	newsk->prev = prev;
-	next->prev  = prev->next = newsk;
+	/* see skb_queue_empty_lockless() for the opposite READ_ONCE() */
+	WRITE_ONCE(newsk->next, next);
+	WRITE_ONCE(newsk->prev, prev);
+	WRITE_ONCE(next->prev, newsk);
+	WRITE_ONCE(prev->next, newsk);
 	list->qlen++;
 }
 
@@ -1860,11 +1876,11 @@ static inline void __skb_queue_splice(const struct sk_buff_head *list,
 	struct sk_buff *first = list->next;
 	struct sk_buff *last = list->prev;
 
-	first->prev = prev;
-	prev->next = first;
+	WRITE_ONCE(first->prev, prev);
+	WRITE_ONCE(prev->next, first);
 
-	last->next = next;
-	next->prev = last;
+	WRITE_ONCE(last->next, next);
+	WRITE_ONCE(next->prev, last);
 }
 
 /**
@@ -2005,8 +2021,8 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
 	next	   = skb->next;
 	prev	   = skb->prev;
 	skb->next  = skb->prev = NULL;
-	next->prev = prev;
-	prev->next = next;
+	WRITE_ONCE(next->prev, prev);
+	WRITE_ONCE(prev->next, next);
 }
 
 /**
diff --git a/include/linux/socket.h b/include/linux/socket.h
index fc0bed59fc84..4049d9755cf1 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -263,7 +263,7 @@ struct ucred {
 #define PF_MAX		AF_MAX
 
 /* Maximum queue length specifiable by listen.  */
-#define SOMAXCONN	128
+#define SOMAXCONN	4096
 
 /* Flags we can use with send/ and recv.
    Added those for 1003.1g not all are supported yet