Adding upstream version 6.9.7.upstream/6.9.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 64 insertions, 117 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 54a7967613..944f71a8ab 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -378,14 +378,10 @@ 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 +398,24 @@ 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 +424,33 @@ 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 +459,36 @@ 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 +497,44 @@ 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
@@ -1103,41 +1117,6 @@ 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)
@@ -2155,17 +2134,10 @@ 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)
@@ -2840,31 +2812,6 @@ 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.