1 files changed, 171 insertions, 226 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 54ca8dcbfb43..7ef728324e4e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -337,6 +337,7 @@ struct sk_filter;
   *	@sk_txtime_report_errors: set report errors mode for SO_TXTIME
   *	@sk_txtime_unused: unused txtime flags
   *	@ns_tracker: tracker for netns reference
+  *	@sk_user_frags: xarray of pages the user is holding a reference on.
   */
 struct sock {
 	/*
@@ -378,14 +379,10 @@ struct sock {
 #define sk_flags		__sk_common.skc_flags
 #define sk_rxhash		__sk_common.skc_rxhash
 
-	/* early demux fields */
-	struct dst_entry __rcu	*sk_rx_dst;
-	int			sk_rx_dst_ifindex;
-	u32			sk_rx_dst_cookie;
+	__cacheline_group_begin(sock_write_rx);
 
-	socket_lock_t		sk_lock;
 	atomic_t		sk_drops;
-	int			sk_rcvlowat;
+	__s32			sk_peek_off;
 	struct sk_buff_head	sk_error_queue;
 	struct sk_buff_head	sk_receive_queue;
 	/*
@@ -402,18 +399,24 @@ struct sock {
 		struct sk_buff	*head;
 		struct sk_buff	*tail;
 	} sk_backlog;
-
 #define sk_rmem_alloc sk_backlog.rmem_alloc
 
-	int			sk_forward_alloc;
-	u32			sk_reserved_mem;
+	__cacheline_group_end(sock_write_rx);
+
+	__cacheline_group_begin(sock_read_rx);
+	/* early demux fields */
+	struct dst_entry __rcu	*sk_rx_dst;
+	int			sk_rx_dst_ifindex;
+	u32			sk_rx_dst_cookie;
+
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	unsigned int		sk_ll_usec;
-	/* ===== mostly read cache line ===== */
 	unsigned int		sk_napi_id;
+	u16			sk_busy_poll_budget;
+	u8			sk_prefer_busy_poll;
 #endif
+	u8			sk_userlocks;
 	int			sk_rcvbuf;
-	int			sk_disconnects;
 
 	struct sk_filter __rcu	*sk_filter;
 	union {
@@ -422,15 +425,33 @@ struct sock {
 		struct socket_wq	*sk_wq_raw;
 		/* public: */
 	};
+
+	void			(*sk_data_ready)(struct sock *sk);
+	long			sk_rcvtimeo;
+	int			sk_rcvlowat;
+	__cacheline_group_end(sock_read_rx);
+
+	__cacheline_group_begin(sock_read_rxtx);
+	int			sk_err;
+	struct socket		*sk_socket;
+	struct mem_cgroup	*sk_memcg;
 #ifdef CONFIG_XFRM
 	struct xfrm_policy __rcu *sk_policy[2];
 #endif
+	__cacheline_group_end(sock_read_rxtx);
 
-	struct dst_entry __rcu	*sk_dst_cache;
+	__cacheline_group_begin(sock_write_rxtx);
+	socket_lock_t		sk_lock;
+	u32			sk_reserved_mem;
+	int			sk_forward_alloc;
+	u32			sk_tsflags;
+	__cacheline_group_end(sock_write_rxtx);
+
+	__cacheline_group_begin(sock_write_tx);
+	int			sk_write_pending;
 	atomic_t		sk_omem_alloc;
 	int			sk_sndbuf;
 
-	/* ===== cache line for TX ===== */
 	int			sk_wmem_queued;
 	refcount_t		sk_wmem_alloc;
 	unsigned long		sk_tsq_flags;
@@ -439,22 +460,36 @@ struct sock {
 		struct rb_root	tcp_rtx_queue;
 	};
 	struct sk_buff_head	sk_write_queue;
-	__s32			sk_peek_off;
-	int			sk_write_pending;
-	__u32			sk_dst_pending_confirm;
+	u32			sk_dst_pending_confirm;
 	u32			sk_pacing_status; /* see enum sk_pacing */
-	long			sk_sndtimeo;
+	struct page_frag	sk_frag;
 	struct timer_list	sk_timer;
-	__u32			sk_priority;
-	__u32			sk_mark;
+
 	unsigned long		sk_pacing_rate; /* bytes per second */
+	atomic_t		sk_zckey;
+	atomic_t		sk_tskey;
+	__cacheline_group_end(sock_write_tx);
+
+	__cacheline_group_begin(sock_read_tx);
 	unsigned long		sk_max_pacing_rate;
-	struct page_frag	sk_frag;
+	long			sk_sndtimeo;
+	u32			sk_priority;
+	u32			sk_mark;
+	struct dst_entry __rcu	*sk_dst_cache;
 	netdev_features_t	sk_route_caps;
-	int			sk_gso_type;
+#ifdef CONFIG_SOCK_VALIDATE_XMIT
+	struct sk_buff*		(*sk_validate_xmit_skb)(struct sock *sk,
+							struct net_device *dev,
+							struct sk_buff *skb);
+#endif
+	u16			sk_gso_type;
+	u16			sk_gso_max_segs;
 	unsigned int		sk_gso_max_size;
 	gfp_t			sk_allocation;
-	__u32			sk_txhash;
+	u32			sk_txhash;
+	u8			sk_pacing_shift;
+	bool			sk_use_task_frag;
+	__cacheline_group_end(sock_read_tx);
 
 	/*
 	 * Because of non atomicity rules, all
@@ -463,64 +498,44 @@ struct sock {
 	u8			sk_gso_disabled : 1,
 				sk_kern_sock : 1,
 				sk_no_check_tx : 1,
-				sk_no_check_rx : 1,
-				sk_userlocks : 4;
-	u8			sk_pacing_shift;
+				sk_no_check_rx : 1;
+	u8			sk_shutdown;
 	u16			sk_type;
 	u16			sk_protocol;
-	u16			sk_gso_max_segs;
 	unsigned long	        sk_lingertime;
 	struct proto		*sk_prot_creator;
 	rwlock_t		sk_callback_lock;
-	int			sk_err,
-				sk_err_soft;
+	int			sk_err_soft;
 	u32			sk_ack_backlog;
 	u32			sk_max_ack_backlog;
 	kuid_t			sk_uid;
-	u8			sk_txrehash;
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	u8			sk_prefer_busy_poll;
-	u16			sk_busy_poll_budget;
-#endif
 	spinlock_t		sk_peer_lock;
 	int			sk_bind_phc;
 	struct pid		*sk_peer_pid;
 	const struct cred	*sk_peer_cred;
 
-	long			sk_rcvtimeo;
 	ktime_t			sk_stamp;
 #if BITS_PER_LONG==32
 	seqlock_t		sk_stamp_seq;
 #endif
-	atomic_t		sk_tskey;
-	atomic_t		sk_zckey;
-	u32			sk_tsflags;
-	u8			sk_shutdown;
+	int			sk_disconnects;
 
+	u8			sk_txrehash;
 	u8			sk_clockid;
 	u8			sk_txtime_deadline_mode : 1,
 				sk_txtime_report_errors : 1,
 				sk_txtime_unused : 6;
-	bool			sk_use_task_frag;
 
-	struct socket		*sk_socket;
 	void			*sk_user_data;
 #ifdef CONFIG_SECURITY
 	void			*sk_security;
 #endif
 	struct sock_cgroup_data	sk_cgrp_data;
-	struct mem_cgroup	*sk_memcg;
 	void			(*sk_state_change)(struct sock *sk);
-	void			(*sk_data_ready)(struct sock *sk);
 	void			(*sk_write_space)(struct sock *sk);
 	void			(*sk_error_report)(struct sock *sk);
 	int			(*sk_backlog_rcv)(struct sock *sk,
 						  struct sk_buff *skb);
-#ifdef CONFIG_SOCK_VALIDATE_XMIT
-	struct sk_buff*		(*sk_validate_xmit_skb)(struct sock *sk,
-							struct net_device *dev,
-							struct sk_buff *skb);
-#endif
 	void                    (*sk_destruct)(struct sock *sk);
 	struct sock_reuseport __rcu	*sk_reuseport_cb;
 #ifdef CONFIG_BPF_SYSCALL
@@ -528,6 +543,12 @@ struct sock {
 #endif
 	struct rcu_head		sk_rcu;
 	netns_tracker		ns_tracker;
+	struct xarray		sk_user_frags;
+};
+
+struct sock_bh_locked {
+	struct sock *sock;
+	local_lock_t bh_lock;
 };
 
 enum sk_pacing {
@@ -873,6 +894,8 @@ static inline void sk_add_bind_node(struct sock *sk,
 	hlist_for_each_entry_safe(__sk, tmp, list, sk_node)
 #define sk_for_each_bound(__sk, list) \
 	hlist_for_each_entry(__sk, list, sk_bind_node)
+#define sk_for_each_bound_safe(__sk, tmp, list) \
+	hlist_for_each_entry_safe(__sk, tmp, list, sk_bind_node)
 
 /**
  * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset
@@ -930,9 +953,16 @@ enum sock_flags {
 	SOCK_XDP, /* XDP is attached */
 	SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */
 	SOCK_RCVMARK, /* Receive SO_MARK  ancillary data with packet */
+	SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
+/*
+ * The highest bit of sk_tsflags is reserved for kernel-internal
+ * SOCKCM_FLAG_TS_OPT_ID. There is a check in core/sock.c to control that
+ * SOF_TIMESTAMPING* values do not reach this reserved area
+ */
+#define SOCKCM_FLAG_TS_OPT_ID	BIT(31)
 
 static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk)
 {
@@ -1103,41 +1133,6 @@ static inline void sk_incoming_cpu_update(struct sock *sk)
 		WRITE_ONCE(sk->sk_incoming_cpu, cpu);
 }
 
-static inline void sock_rps_record_flow_hash(__u32 hash)
-{
-#ifdef CONFIG_RPS
-	struct rps_sock_flow_table *sock_flow_table;
-
-	rcu_read_lock();
-	sock_flow_table = rcu_dereference(rps_sock_flow_table);
-	rps_record_sock_flow(sock_flow_table, hash);
-	rcu_read_unlock();
-#endif
-}
-
-static inline void sock_rps_record_flow(const struct sock *sk)
-{
-#ifdef CONFIG_RPS
-	if (static_branch_unlikely(&rfs_needed)) {
-		/* Reading sk->sk_rxhash might incur an expensive cache line
-		 * miss.
-		 *
-		 * TCP_ESTABLISHED does cover almost all states where RFS
-		 * might be useful, and is cheaper [1] than testing :
-		 *	IPv4: inet_sk(sk)->inet_daddr
-		 * 	IPv6: ipv6_addr_any(&sk->sk_v6_daddr)
-		 * OR	an additional socket flag
-		 * [1] : sk_state and sk_prot are in the same cache line.
-		 */
-		if (sk->sk_state == TCP_ESTABLISHED) {
-			/* This READ_ONCE() is paired with the WRITE_ONCE()
-			 * from sock_rps_save_rxhash() and sock_rps_reset_rxhash().
-			 */
-			sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash));
-		}
-	}
-#endif
-}
 
 static inline void sock_rps_save_rxhash(struct sock *sk,
 					const struct sk_buff *skb)
@@ -1215,6 +1210,13 @@ static inline void sk_prot_clear_nulls(struct sock *sk, int size)
 	       size - offsetof(struct sock, sk_node.pprev));
 }
 
+struct proto_accept_arg {
+	int flags;
+	int err;
+	int is_empty;
+	bool kern;
+};
+
 /* Networking protocol blocks we attach to sockets.
  * socket layer -> transport layer interface
  */
@@ -1229,8 +1231,8 @@ struct proto {
 					int addr_len);
 	int			(*disconnect)(struct sock *sk, int flags);
 
-	struct sock *		(*accept)(struct sock *sk, int flags, int *err,
-					  bool kern);
+	struct sock *		(*accept)(struct sock *sk,
+					  struct proto_accept_arg *arg);
 
 	int			(*ioctl)(struct sock *sk, int cmd,
 					 int *karg);
@@ -1392,72 +1394,6 @@ static inline int sk_under_cgroup_hierarchy(struct sock *sk,
 #endif
 }
 
-static inline bool sk_has_memory_pressure(const struct sock *sk)
-{
-	return sk->sk_prot->memory_pressure != NULL;
-}
-
-static inline bool sk_under_global_memory_pressure(const struct sock *sk)
-{
-	return sk->sk_prot->memory_pressure &&
-		!!READ_ONCE(*sk->sk_prot->memory_pressure);
-}
-
-static inline bool sk_under_memory_pressure(const struct sock *sk)
-{
-	if (!sk->sk_prot->memory_pressure)
-		return false;
-
-	if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
-	    mem_cgroup_under_socket_pressure(sk->sk_memcg))
-		return true;
-
-	return !!READ_ONCE(*sk->sk_prot->memory_pressure);
-}
-
-static inline long
-proto_memory_allocated(const struct proto *prot)
-{
-	return max(0L, atomic_long_read(prot->memory_allocated));
-}
-
-static inline long
-sk_memory_allocated(const struct sock *sk)
-{
-	return proto_memory_allocated(sk->sk_prot);
-}
-
-/* 1 MB per cpu, in page units */
-#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT))
-
-static inline void
-sk_memory_allocated_add(struct sock *sk, int amt)
-{
-	int local_reserve;
-
-	preempt_disable();
-	local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt);
-	if (local_reserve >= SK_MEMORY_PCPU_RESERVE) {
-		__this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve);
-		atomic_long_add(local_reserve, sk->sk_prot->memory_allocated);
-	}
-	preempt_enable();
-}
-
-static inline void
-sk_memory_allocated_sub(struct sock *sk, int amt)
-{
-	int local_reserve;
-
-	preempt_disable();
-	local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt);
-	if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) {
-		__this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve);
-		atomic_long_add(local_reserve, sk->sk_prot->memory_allocated);
-	}
-	preempt_enable();
-}
-
 #define SK_ALLOC_PERCPU_COUNTER_BATCH 16
 
 static inline void sk_sockets_allocated_dec(struct sock *sk)
@@ -1484,15 +1420,6 @@ proto_sockets_allocated_sum_positive(struct proto *prot)
 	return percpu_counter_sum_positive(prot->sockets_allocated);
 }
 
-static inline bool
-proto_memory_pressure(struct proto *prot)
-{
-	if (!prot->memory_pressure)
-		return false;
-	return !!READ_ONCE(*prot->memory_pressure);
-}
-
-
 #ifdef CONFIG_PROC_FS
 #define PROTO_INUSE_NR	64	/* should be enough for the first time */
 struct prot_inuse {
@@ -1601,7 +1528,7 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size)
 }
 
 static inline bool
-sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
+__sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc)
 {
 	int delta;
 
@@ -1609,7 +1536,13 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
 		return true;
 	delta = size - sk->sk_forward_alloc;
 	return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) ||
-		skb_pfmemalloc(skb);
+	       pfmemalloc;
+}
+
+static inline bool
+sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size)
+{
+	return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb));
 }
 
 static inline int sk_unused_reserved_mem(const struct sock *sk)
@@ -1708,7 +1641,7 @@ bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock);
  * lock_sock_fast - fast version of lock_sock
  * @sk: socket
  *
- * This version should be used for very small section, where process wont block
+ * This version should be used for very small section, where process won't block
  * return false if fast path is taken:
  *
  *   sk_lock.slock locked, owned = 0, BH disabled
@@ -1779,6 +1712,13 @@ static inline void sock_owned_by_me(const struct sock *sk)
 #endif
 }
 
+static inline void sock_not_owned_by_me(const struct sock *sk)
+{
+#ifdef CONFIG_LOCKDEP
+	WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks);
+#endif
+}
+
 static inline bool sock_owned_by_user(const struct sock *sk)
 {
 	sock_owned_by_me(sk);
@@ -1811,6 +1751,7 @@ static inline bool sock_allow_reclassification(const struct sock *csk)
 struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		      struct proto *prot, int kern);
 void sk_free(struct sock *sk);
+void sk_net_refcnt_upgrade(struct sock *sk);
 void sk_destruct(struct sock *sk);
 struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
 void sk_free_unlock_clone(struct sock *sk);
@@ -1827,6 +1768,15 @@ void sock_efree(struct sk_buff *skb);
 #ifdef CONFIG_INET
 void sock_edemux(struct sk_buff *skb);
 void sock_pfree(struct sk_buff *skb);
+
+static inline void skb_set_owner_edemux(struct sk_buff *skb, struct sock *sk)
+{
+	skb_orphan(skb);
+	if (refcount_inc_not_zero(&sk->sk_refcnt)) {
+		skb->sk = sk;
+		skb->destructor = sock_edemux;
+	}
+}
 #else
 #define sock_edemux sock_efree
 #endif
@@ -1871,13 +1821,16 @@ struct sockcm_cookie {
 	u64 transmit_time;
 	u32 mark;
 	u32 tsflags;
+	u32 ts_opt_id;
+	u32 priority;
 };
 
 static inline void sockcm_init(struct sockcm_cookie *sockc,
 			       const struct sock *sk)
 {
 	*sockc = (struct sockcm_cookie) {
-		.tsflags = READ_ONCE(sk->sk_tsflags)
+		.tsflags = READ_ONCE(sk->sk_tsflags),
+		.priority = READ_ONCE(sk->sk_priority),
 	};
 }
 
@@ -1893,7 +1846,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
 int sock_no_bind(struct socket *, struct sockaddr *, int);
 int sock_no_connect(struct socket *, struct sockaddr *, int, int);
 int sock_no_socketpair(struct socket *, struct socket *);
-int sock_no_accept(struct socket *, struct socket *, int, bool);
+int sock_no_accept(struct socket *, struct socket *, struct proto_accept_arg *);
 int sock_no_getname(struct socket *, struct sockaddr *, int);
 int sock_no_ioctl(struct socket *, unsigned int, unsigned long);
 int sock_no_listen(struct socket *, int);
@@ -2145,17 +2098,10 @@ 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)
@@ -2184,7 +2130,7 @@ sk_dst_set(struct sock *sk, struct dst_entry *dst)
 
 	sk_tx_queue_clear(sk);
 	WRITE_ONCE(sk->sk_dst_pending_confirm, 0);
-	old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
+	old_dst = unrcu_pointer(xchg(&sk->sk_dst_cache, RCU_INITIALIZER(dst)));
 	dst_release(old_dst);
 }
 
@@ -2355,7 +2301,7 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq)
 }
 
 /**
- * sock_poll_wait - place memory barrier behind the poll_wait call.
+ * sock_poll_wait - wrapper for the poll_wait call.
  * @filp:           file
  * @sock:           socket to wait on
  * @p:              poll_table
@@ -2365,15 +2311,12 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq)
 static inline void sock_poll_wait(struct file *filp, struct socket *sock,
 				  poll_table *p)
 {
-	if (!poll_does_not_wait(p)) {
-		poll_wait(filp, &sock->wq.wait, p);
-		/* We need to be sure we are in sync with the
-		 * socket flags modification.
-		 *
-		 * This memory barrier is paired in the wq_has_sleeper.
-		 */
-		smp_mb();
-	}
+	/* Provides a barrier we need to be sure we are in sync
+	 * with the socket flags modification.
+	 *
+	 * This memory barrier is paired in the wq_has_sleeper.
+	 */
+	poll_wait(filp, &sock->wq.wait, p);
 }
 
 static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk)
@@ -2526,6 +2469,12 @@ static inline void sk_wake_async(const struct sock *sk, int how, int band)
 	}
 }
 
+static inline void sk_wake_async_rcu(const struct sock *sk, int how, int band)
+{
+	if (unlikely(sock_flag(sk, SOCK_FASYNC)))
+		sock_wake_async(rcu_dereference(sk->sk_wq), how, band);
+}
+
 /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might
  * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak.
  * Note: for send buffers, TCP works better if we can build two skbs at
@@ -2624,7 +2573,7 @@ struct sock_skb_cb {
 
 /* Store sock_skb_cb at the end of skb->cb[] so protocol families
  * using skb->cb[] would keep using it directly and utilize its
- * alignement guarantee.
+ * alignment guarantee.
  */
 #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \
 			    sizeof(struct sock_skb_cb)))
@@ -2716,7 +2665,8 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 {
 #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL)			| \
 			   (1UL << SOCK_RCVTSTAMP)			| \
-			   (1UL << SOCK_RCVMARK))
+			   (1UL << SOCK_RCVMARK)			|\
+			   (1UL << SOCK_RCVPRIORITY))
 #define TSFLAGS_ANY	  (SOF_TIMESTAMPING_SOFTWARE			| \
 			   SOF_TIMESTAMPING_RAW_HARDWARE)
 
@@ -2729,39 +2679,48 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 		sock_write_timestamp(sk, 0);
 }
 
-void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);
+void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags);
 
 /**
  * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
  * @sk:		socket sending this packet
- * @tsflags:	timestamping flags to use
+ * @sockc:	pointer to socket cmsg cookie to get timestamping info
  * @tx_flags:	completed with instructions for time stamping
  * @tskey:      filled in with next sk_tskey (not for TCP, which uses seqno)
  *
  * Note: callers should take care of initial ``*tx_flags`` value (usually 0)
  */
-static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags,
+static inline void _sock_tx_timestamp(struct sock *sk,
+				      const struct sockcm_cookie *sockc,
 				      __u8 *tx_flags, __u32 *tskey)
 {
+	__u32 tsflags = sockc->tsflags;
+
 	if (unlikely(tsflags)) {
 		__sock_tx_timestamp(tsflags, tx_flags);
 		if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey &&
-		    tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK)
-			*tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+		    tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) {
+			if (tsflags & SOCKCM_FLAG_TS_OPT_ID)
+				*tskey = sockc->ts_opt_id;
+			else
+				*tskey = atomic_inc_return(&sk->sk_tskey) - 1;
+		}
 	}
 	if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS)))
 		*tx_flags |= SKBTX_WIFI_STATUS;
 }
 
-static inline void sock_tx_timestamp(struct sock *sk, __u16 tsflags,
+static inline void sock_tx_timestamp(struct sock *sk,
+				     const struct sockcm_cookie *sockc,
 				     __u8 *tx_flags)
 {
-	_sock_tx_timestamp(sk, tsflags, tx_flags, NULL);
+	_sock_tx_timestamp(sk, sockc, tx_flags, NULL);
 }
 
-static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags)
+static inline void skb_setup_tx_timestamp(struct sk_buff *skb,
+					  const struct sockcm_cookie *sockc)
 {
-	_sock_tx_timestamp(skb->sk, tsflags, &skb_shinfo(skb)->tx_flags,
+	_sock_tx_timestamp(skb->sk, sockc, &skb_shinfo(skb)->tx_flags,
 			   &skb_shinfo(skb)->tskey);
 }
 
@@ -2791,6 +2750,11 @@ static inline bool sk_is_stream_unix(const struct sock *sk)
 	return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM;
 }
 
+static inline bool sk_is_vsock(const struct sock *sk)
+{
+	return sk->sk_family == AF_VSOCK;
+}
+
 /**
  * sk_eat_skb - Release a skb if it is no longer needed
  * @sk: socket to eat this skb from
@@ -2830,31 +2794,6 @@ sk_is_refcounted(struct sock *sk)
 	return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE);
 }
 
-/**
- * skb_steal_sock - steal a socket from an sk_buff
- * @skb: sk_buff to steal the socket from
- * @refcounted: is set to true if the socket is reference-counted
- * @prefetched: is set to true if the socket was assigned from bpf
- */
-static inline struct sock *
-skb_steal_sock(struct sk_buff *skb, bool *refcounted, bool *prefetched)
-{
-	if (skb->sk) {
-		struct sock *sk = skb->sk;
-
-		*refcounted = true;
-		*prefetched = skb_sk_is_prefetched(skb);
-		if (*prefetched)
-			*refcounted = sk_is_refcounted(sk);
-		skb->destructor = NULL;
-		skb->sk = NULL;
-		return sk;
-	}
-	*prefetched = false;
-	*refcounted = false;
-	return NULL;
-}
-
 /* Checks if this SKB belongs to an HW offloaded socket
  * and whether any SW fallbacks are required based on dev.
  * Check decrypted mark in case skb_orphan() cleared socket.
@@ -2867,12 +2806,10 @@ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb,
 
 	if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) {
 		skb = sk->sk_validate_xmit_skb(sk, dev, skb);
-#ifdef CONFIG_TLS_DEVICE
-	} else if (unlikely(skb->decrypted)) {
+	} else if (unlikely(skb_is_decrypted(skb))) {
 		pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n");
 		kfree_skb(skb);
 		skb = NULL;
-#endif
 	}
 #endif
 
@@ -2887,6 +2824,16 @@ static inline bool sk_listener(const struct sock *sk)
 	return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);
 }
 
+/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV or TIME_WAIT
+ * TCP SYNACK messages can be attached to LISTEN or NEW_SYN_RECV (depending on SYNCOOKIE)
+ * TCP RST and ACK can be attached to TIME_WAIT.
+ */
+static inline bool sk_listener_or_tw(const struct sock *sk)
+{
+	return (1 << READ_ONCE(sk->sk_state)) &
+	       (TCPF_LISTEN | TCPF_NEW_SYN_RECV | TCPF_TIME_WAIT);
+}
+
 void sock_enable_timestamp(struct sock *sk, enum sock_flags flag);
 int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level,
 		       int type);
@@ -2911,8 +2858,6 @@ void sk_get_meminfo(const struct sock *sk, u32 *meminfo);
 extern __u32 sysctl_wmem_max;
 extern __u32 sysctl_rmem_max;
 
-extern int sysctl_tstamp_allow_data;
-
 extern __u32 sysctl_wmem_default;
 extern __u32 sysctl_rmem_default;