1 files changed, 454 insertions, 76 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c82dc42f57c6..57df7c1d2faa 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -272,13 +272,20 @@
 #include <net/inet_common.h>
 #include <net/tcp.h>
 #include <net/mptcp.h>
+#include <net/proto_memory.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
 #include <net/sock.h>
+#include <net/rstreason.h>
 
 #include <linux/uaccess.h>
 #include <asm/ioctls.h>
 #include <net/busy_poll.h>
+#include <net/hotdata.h>
+#include <trace/events/tcp.h>
+#include <net/rps.h>
+
+#include "../core/devmem.h"
 
 /* Track pending CMSGs. */
 enum {
@@ -289,6 +296,9 @@ enum {
 DEFINE_PER_CPU(unsigned int, tcp_orphan_count);
 EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count);
 
+DEFINE_PER_CPU(u32, tcp_tw_isn);
+EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn);
+
 long sysctl_tcp_mem[3] __read_mostly;
 EXPORT_SYMBOL(sysctl_tcp_mem);
 
@@ -413,6 +423,7 @@ void tcp_init_sock(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	int rto_min_us;
 
 	tp->out_of_order_queue = RB_ROOT;
 	sk->tcp_rtx_queue = RB_ROOT;
@@ -421,7 +432,8 @@ void tcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
-	icsk->icsk_rto_min = TCP_RTO_MIN;
+	rto_min_us = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_min_us);
+	icsk->icsk_rto_min = usecs_to_jiffies(rto_min_us);
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
@@ -461,18 +473,20 @@ void tcp_init_sock(struct sock *sk)
 
 	set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
 	sk_sockets_allocated_inc(sk);
+	xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1);
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
-static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
+static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc)
 {
 	struct sk_buff *skb = tcp_write_queue_tail(sk);
+	u32 tsflags = sockc->tsflags;
 
 	if (tsflags && skb) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 		struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
 
-		sock_tx_timestamp(sk, tsflags, &shinfo->tx_flags);
+		sock_tx_timestamp(sk, sockc, &shinfo->tx_flags);
 		if (tsflags & SOF_TIMESTAMPING_TX_ACK)
 			tcb->txstamp_ack = 1;
 		if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK)
@@ -591,7 +605,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		 */
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	}
-	/* This barrier is coupled with smp_wmb() in tcp_reset() */
+	/* This barrier is coupled with smp_wmb() in tcp_done_with_error() */
 	smp_rmb();
 	if (READ_ONCE(sk->sk_err) ||
 	    !skb_queue_empty_lockless(&sk->sk_error_queue))
@@ -974,7 +988,7 @@ int tcp_wmem_schedule(struct sock *sk, int copy)
 	 * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0]
 	 * to guarantee some progress.
 	 */
-	left = sock_net(sk)->ipv4.sysctl_tcp_wmem[0] - sk->sk_wmem_queued;
+	left = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[0]) - sk->sk_wmem_queued;
 	if (left > 0)
 		sk_forced_mem_schedule(sk, min(left, copy));
 	return min(copy, sk->sk_forward_alloc);
@@ -1158,6 +1172,9 @@ new_segment:
 
 			process_backlog++;
 
+#ifdef CONFIG_SKB_DECRYPTED
+			skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
 			tcp_skb_entail(sk, skb);
 			copy = size_goal;
 
@@ -1183,7 +1200,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i >= READ_ONCE(sysctl_max_skb_frags)) {
+				if (i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
@@ -1305,7 +1322,7 @@ wait_for_space:
 
 out:
 	if (copied) {
-		tcp_tx_timestamp(sk, sockc.tsflags);
+		tcp_tx_timestamp(sk, &sockc);
 		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
 	}
 out_nopush:
@@ -1415,8 +1432,6 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
 	struct sk_buff *skb;
 	int copied = 0, err = 0;
 
-	/* XXX -- need to support SO_PEEK_OFF */
-
 	skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
 		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
 		if (err)
@@ -1550,12 +1565,13 @@ EXPORT_SYMBOL(tcp_recv_skb);
  *	  or for 'peeking' the socket using this routine
  *	  (although both would be easy to implement).
  */
-int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
-		  sk_read_actor_t recv_actor)
+static int __tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
+			   sk_read_actor_t recv_actor, bool noack,
+			   u32 *copied_seq)
 {
 	struct sk_buff *skb;
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 seq = tp->copied_seq;
+	u32 seq = *copied_seq;
 	u32 offset;
 	int copied = 0;
 
@@ -1609,9 +1625,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		tcp_eat_recv_skb(sk, skb);
 		if (!desc->count)
 			break;
-		WRITE_ONCE(tp->copied_seq, seq);
+		WRITE_ONCE(*copied_seq, seq);
 	}
-	WRITE_ONCE(tp->copied_seq, seq);
+	WRITE_ONCE(*copied_seq, seq);
+
+	if (noack)
+		goto out;
 
 	tcp_rcv_space_adjust(sk);
 
@@ -1620,10 +1639,25 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		tcp_recv_skb(sk, seq, &offset);
 		tcp_cleanup_rbuf(sk, copied);
 	}
+out:
 	return copied;
 }
+
+int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
+		  sk_read_actor_t recv_actor)
+{
+	return __tcp_read_sock(sk, desc, recv_actor, false,
+			       &tcp_sk(sk)->copied_seq);
+}
 EXPORT_SYMBOL(tcp_read_sock);
 
+int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc,
+			sk_read_actor_t recv_actor, bool noack,
+			u32 *copied_seq)
+{
+	return __tcp_read_sock(sk, desc, recv_actor, noack, copied_seq);
+}
+
 int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
 	struct sk_buff *skb;
@@ -1720,7 +1754,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	space = tcp_space_from_win(sk, val);
 	if (space > sk->sk_rcvbuf) {
 		WRITE_ONCE(sk->sk_rcvbuf, space);
-		tcp_sk(sk)->window_clamp = val;
+		WRITE_ONCE(tcp_sk(sk)->window_clamp, val);
 	}
 	return 0;
 }
@@ -2149,6 +2183,9 @@ static int tcp_zerocopy_receive(struct sock *sk,
 				skb = tcp_recv_skb(sk, seq, &offset);
 			}
 
+			if (!skb_frags_readable(skb))
+				break;
+
 			if (TCP_SKB_CB(skb)->has_rxtstamp) {
 				tcp_update_recv_tstamps(skb, tss);
 				zc->msg_flags |= TCP_CMSG_TS;
@@ -2166,6 +2203,9 @@ static int tcp_zerocopy_receive(struct sock *sk,
 			break;
 		}
 		page = skb_frag_page(frags);
+		if (WARN_ON_ONCE(!page))
+			break;
+
 		prefetchw(page);
 		pages[pages_to_map++] = page;
 		length += PAGE_SIZE;
@@ -2224,6 +2264,7 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
 			struct scm_timestamping_internal *tss)
 {
 	int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
+	u32 tsflags = READ_ONCE(sk->sk_tsflags);
 	bool has_timestamping = false;
 
 	if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) {
@@ -2263,14 +2304,18 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
 			}
 		}
 
-		if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE)
+		if (tsflags & SOF_TIMESTAMPING_SOFTWARE &&
+		    (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE ||
+		     !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER)))
 			has_timestamping = true;
 		else
 			tss->ts[0] = (struct timespec64) {0};
 	}
 
 	if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) {
-		if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE)
+		if (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE &&
+		    (tsflags & SOF_TIMESTAMPING_RX_HARDWARE ||
+		     !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER)))
 			has_timestamping = true;
 		else
 			tss->ts[2] = (struct timespec64) {0};
@@ -2306,6 +2351,214 @@ static int tcp_inq_hint(struct sock *sk)
 	return inq;
 }
 
+/* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */
+struct tcp_xa_pool {
+	u8		max; /* max <= MAX_SKB_FRAGS */
+	u8		idx; /* idx <= max */
+	__u32		tokens[MAX_SKB_FRAGS];
+	netmem_ref	netmems[MAX_SKB_FRAGS];
+};
+
+static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p)
+{
+	int i;
+
+	/* Commit part that has been copied to user space. */
+	for (i = 0; i < p->idx; i++)
+		__xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY,
+			     (__force void *)p->netmems[i], GFP_KERNEL);
+	/* Rollback what has been pre-allocated and is no longer needed. */
+	for (; i < p->max; i++)
+		__xa_erase(&sk->sk_user_frags, p->tokens[i]);
+
+	p->max = 0;
+	p->idx = 0;
+}
+
+static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p)
+{
+	if (!p->max)
+		return;
+
+	xa_lock_bh(&sk->sk_user_frags);
+
+	tcp_xa_pool_commit_locked(sk, p);
+
+	xa_unlock_bh(&sk->sk_user_frags);
+}
+
+static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p,
+			      unsigned int max_frags)
+{
+	int err, k;
+
+	if (p->idx < p->max)
+		return 0;
+
+	xa_lock_bh(&sk->sk_user_frags);
+
+	tcp_xa_pool_commit_locked(sk, p);
+
+	for (k = 0; k < max_frags; k++) {
+		err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k],
+				 XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL);
+		if (err)
+			break;
+	}
+
+	xa_unlock_bh(&sk->sk_user_frags);
+
+	p->max = k;
+	p->idx = 0;
+	return k ? 0 : err;
+}
+
+/* On error, returns the -errno. On success, returns number of bytes sent to the
+ * user. May not consume all of @remaining_len.
+ */
+static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
+			      unsigned int offset, struct msghdr *msg,
+			      int remaining_len)
+{
+	struct dmabuf_cmsg dmabuf_cmsg = { 0 };
+	struct tcp_xa_pool tcp_xa_pool;
+	unsigned int start;
+	int i, copy, n;
+	int sent = 0;
+	int err = 0;
+
+	tcp_xa_pool.max = 0;
+	tcp_xa_pool.idx = 0;
+	do {
+		start = skb_headlen(skb);
+
+		if (skb_frags_readable(skb)) {
+			err = -ENODEV;
+			goto out;
+		}
+
+		/* Copy header. */
+		copy = start - offset;
+		if (copy > 0) {
+			copy = min(copy, remaining_len);
+
+			n = copy_to_iter(skb->data + offset, copy,
+					 &msg->msg_iter);
+			if (n != copy) {
+				err = -EFAULT;
+				goto out;
+			}
+
+			offset += copy;
+			remaining_len -= copy;
+
+			/* First a dmabuf_cmsg for # bytes copied to user
+			 * buffer.
+			 */
+			memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg));
+			dmabuf_cmsg.frag_size = copy;
+			err = put_cmsg_notrunc(msg, SOL_SOCKET,
+					       SO_DEVMEM_LINEAR,
+					       sizeof(dmabuf_cmsg),
+					       &dmabuf_cmsg);
+			if (err)
+				goto out;
+
+			sent += copy;
+
+			if (remaining_len == 0)
+				goto out;
+		}
+
+		/* after that, send information of dmabuf pages through a
+		 * sequence of cmsg
+		 */
+		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			struct net_iov *niov;
+			u64 frag_offset;
+			int end;
+
+			/* !skb_frags_readable() should indicate that ALL the
+			 * frags in this skb are dmabuf net_iovs. We're checking
+			 * for that flag above, but also check individual frags
+			 * here. If the tcp stack is not setting
+			 * skb_frags_readable() correctly, we still don't want
+			 * to crash here.
+			 */
+			if (!skb_frag_net_iov(frag)) {
+				net_err_ratelimited("Found non-dmabuf skb with net_iov");
+				err = -ENODEV;
+				goto out;
+			}
+
+			niov = skb_frag_net_iov(frag);
+			end = start + skb_frag_size(frag);
+			copy = end - offset;
+
+			if (copy > 0) {
+				copy = min(copy, remaining_len);
+
+				frag_offset = net_iov_virtual_addr(niov) +
+					      skb_frag_off(frag) + offset -
+					      start;
+				dmabuf_cmsg.frag_offset = frag_offset;
+				dmabuf_cmsg.frag_size = copy;
+				err = tcp_xa_pool_refill(sk, &tcp_xa_pool,
+							 skb_shinfo(skb)->nr_frags - i);
+				if (err)
+					goto out;
+
+				/* Will perform the exchange later */
+				dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx];
+				dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov);
+
+				offset += copy;
+				remaining_len -= copy;
+
+				err = put_cmsg_notrunc(msg, SOL_SOCKET,
+						       SO_DEVMEM_DMABUF,
+						       sizeof(dmabuf_cmsg),
+						       &dmabuf_cmsg);
+				if (err)
+					goto out;
+
+				atomic_long_inc(&niov->pp_ref_count);
+				tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag);
+
+				sent += copy;
+
+				if (remaining_len == 0)
+					goto out;
+			}
+			start = end;
+		}
+
+		tcp_xa_pool_commit(sk, &tcp_xa_pool);
+		if (!remaining_len)
+			goto out;
+
+		/* if remaining_len is not satisfied yet, we need to go to the
+		 * next frag in the frag_list to satisfy remaining_len.
+		 */
+		skb = skb_shinfo(skb)->frag_list ?: skb->next;
+
+		offset = offset - start;
+	} while (skb);
+
+	if (remaining_len) {
+		err = -EFAULT;
+		goto out;
+	}
+
+out:
+	tcp_xa_pool_commit(sk, &tcp_xa_pool);
+	if (!sent)
+		sent = err;
+
+	return sent;
+}
+
 /*
  *	This routine copies from a sock struct into the user buffer.
  *
@@ -2319,6 +2572,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 			      int *cmsg_flags)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	int last_copied_dmabuf = -1; /* uninitialized */
 	int copied = 0;
 	u32 peek_seq;
 	u32 *seq;
@@ -2327,6 +2581,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	int target;		/* Read at least this many bytes */
 	long timeo;
 	struct sk_buff *skb, *last;
+	u32 peek_offset = 0;
 	u32 urg_hole = 0;
 
 	err = -ENOTCONN;
@@ -2360,7 +2615,8 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 
 	seq = &tp->copied_seq;
 	if (flags & MSG_PEEK) {
-		peek_seq = tp->copied_seq;
+		peek_offset = max(sk_peek_offset(sk, flags), 0);
+		peek_seq = tp->copied_seq + peek_offset;
 		seq = &peek_seq;
 	}
 
@@ -2463,11 +2719,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 
 		if ((flags & MSG_PEEK) &&
-		    (peek_seq - copied - urg_hole != tp->copied_seq)) {
+		    (peek_seq - peek_offset - copied - urg_hole != tp->copied_seq)) {
 			net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n",
 					    current->comm,
 					    task_pid_nr(current));
-			peek_seq = tp->copied_seq;
+			peek_seq = tp->copied_seq + peek_offset;
 		}
 		continue;
 
@@ -2496,19 +2752,51 @@ found_ok_skb:
 		}
 
 		if (!(flags & MSG_TRUNC)) {
-			err = skb_copy_datagram_msg(skb, offset, msg, used);
-			if (err) {
-				/* Exception. Bailout! */
-				if (!copied)
-					copied = -EFAULT;
+			if (last_copied_dmabuf != -1 &&
+			    last_copied_dmabuf != !skb_frags_readable(skb))
 				break;
+
+			if (skb_frags_readable(skb)) {
+				err = skb_copy_datagram_msg(skb, offset, msg,
+							    used);
+				if (err) {
+					/* Exception. Bailout! */
+					if (!copied)
+						copied = -EFAULT;
+					break;
+				}
+			} else {
+				if (!(flags & MSG_SOCK_DEVMEM)) {
+					/* dmabuf skbs can only be received
+					 * with the MSG_SOCK_DEVMEM flag.
+					 */
+					if (!copied)
+						copied = -EFAULT;
+
+					break;
+				}
+
+				err = tcp_recvmsg_dmabuf(sk, skb, offset, msg,
+							 used);
+				if (err <= 0) {
+					if (!copied)
+						copied = -EFAULT;
+
+					break;
+				}
+				used = err;
 			}
 		}
 
+		last_copied_dmabuf = !skb_frags_readable(skb);
+
 		WRITE_ONCE(*seq, *seq + used);
 		copied += used;
 		len -= used;
-
+		if (flags & MSG_PEEK)
+			sk_peek_offset_fwd(sk, used);
+		else
+			sk_peek_offset_bwd(sk, used);
 		tcp_rcv_space_adjust(sk);
 
 skip_copy:
@@ -2636,6 +2924,10 @@ void tcp_set_state(struct sock *sk, int state)
 		if (oldstate != TCP_ESTABLISHED)
 			TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
 		break;
+	case TCP_CLOSE_WAIT:
+		if (oldstate == TCP_SYN_RECV)
+			TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
+		break;
 
 	case TCP_CLOSE:
 		if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
@@ -2647,7 +2939,7 @@ void tcp_set_state(struct sock *sk, int state)
 			inet_put_port(sk);
 		fallthrough;
 	default:
-		if (oldstate == TCP_ESTABLISHED)
+		if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT)
 			TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
 	}
 
@@ -2709,7 +3001,7 @@ void tcp_shutdown(struct sock *sk, int how)
 	/* If we've already sent a FIN, or it's a closed state, skip this. */
 	if ((1 << sk->sk_state) &
 	    (TCPF_ESTABLISHED | TCPF_SYN_SENT |
-	     TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) {
+	     TCPF_CLOSE_WAIT)) {
 		/* Clear out any half completed packets.  FIN if needed. */
 		if (tcp_close_state(sk))
 			tcp_send_fin(sk);
@@ -2743,7 +3035,15 @@ static bool tcp_too_many_orphans(int shift)
 		READ_ONCE(sysctl_tcp_max_orphans);
 }
 
-bool tcp_check_oom(struct sock *sk, int shift)
+static bool tcp_out_of_memory(const struct sock *sk)
+{
+	if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
+	    sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2))
+		return true;
+	return false;
+}
+
+bool tcp_check_oom(const struct sock *sk, int shift)
 {
 	bool too_many_orphans, out_of_socket_memory;
 
@@ -2804,7 +3104,8 @@ void __tcp_close(struct sock *sk, long timeout)
 		/* Unread data was tossed, zap the connection. */
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
 		tcp_set_state(sk, TCP_CLOSE);
-		tcp_send_active_reset(sk, sk->sk_allocation);
+		tcp_send_active_reset(sk, sk->sk_allocation,
+				      SK_RST_REASON_TCP_ABORT_ON_CLOSE);
 	} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
 		/* Check zero linger _after_ checking for unread data. */
 		sk->sk_prot->disconnect(sk, 0);
@@ -2818,7 +3119,7 @@ void __tcp_close(struct sock *sk, long timeout)
 		 * machine. State transitions:
 		 *
 		 * TCP_ESTABLISHED -> TCP_FIN_WAIT1
-		 * TCP_SYN_RECV	-> TCP_FIN_WAIT1 (forget it, it's impossible)
+		 * TCP_SYN_RECV	-> TCP_FIN_WAIT1 (it is difficult)
 		 * TCP_CLOSE_WAIT -> TCP_LAST_ACK
 		 *
 		 * are legal only when FIN has been sent (i.e. in window),
@@ -2878,7 +3179,8 @@ adjudge_to_death:
 		struct tcp_sock *tp = tcp_sk(sk);
 		if (READ_ONCE(tp->linger2) < 0) {
 			tcp_set_state(sk, TCP_CLOSE);
-			tcp_send_active_reset(sk, GFP_ATOMIC);
+			tcp_send_active_reset(sk, GFP_ATOMIC,
+					      SK_RST_REASON_TCP_ABORT_ON_LINGER);
 			__NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPABORTONLINGER);
 		} else {
@@ -2896,7 +3198,8 @@ adjudge_to_death:
 	if (sk->sk_state != TCP_CLOSE) {
 		if (tcp_check_oom(sk, 0)) {
 			tcp_set_state(sk, TCP_CLOSE);
-			tcp_send_active_reset(sk, GFP_ATOMIC);
+			tcp_send_active_reset(sk, GFP_ATOMIC,
+					      SK_RST_REASON_TCP_ABORT_ON_MEMORY);
 			__NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPABORTONMEMORY);
 		} else if (!check_net(sock_net(sk))) {
@@ -2930,6 +3233,8 @@ void tcp_close(struct sock *sk, long timeout)
 	lock_sock(sk);
 	__tcp_close(sk, timeout);
 	release_sock(sk);
+	if (!sk->sk_net_refcnt)
+		inet_csk_clear_xmit_timers_sync(sk);
 	sock_put(sk);
 }
 EXPORT_SYMBOL(tcp_close);
@@ -2992,13 +3297,16 @@ int tcp_disconnect(struct sock *sk, int flags)
 		inet_csk_listen_stop(sk);
 	} else if (unlikely(tp->repair)) {
 		WRITE_ONCE(sk->sk_err, ECONNABORTED);
-	} else if (tcp_need_reset(old_state) ||
-		   (tp->snd_nxt != tp->write_seq &&
-		    (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) {
+	} else if (tcp_need_reset(old_state)) {
+		tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE);
+		WRITE_ONCE(sk->sk_err, ECONNRESET);
+	} else if (tp->snd_nxt != tp->write_seq &&
+		   (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) {
 		/* The last check adjusts for discrepancy of Linux wrt. RFC
 		 * states
 		 */
-		tcp_send_active_reset(sk, gfp_any());
+		tcp_send_active_reset(sk, gfp_any(),
+				      SK_RST_REASON_TCP_DISCONNECT_WITH_DATA);
 		WRITE_ONCE(sk->sk_err, ECONNRESET);
 	} else if (old_state == TCP_SYN_SENT)
 		WRITE_ONCE(sk->sk_err, ECONNRESET);
@@ -3007,6 +3315,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	__skb_queue_purge(&sk->sk_receive_queue);
 	WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 	WRITE_ONCE(tp->urg_data, 0);
+	sk_set_peek_off(sk, -1);
 	tcp_write_queue_purge(sk);
 	tcp_fastopen_active_disable_ofo_check(sk);
 	skb_rbtree_purge(&tp->out_of_order_queue);
@@ -3040,7 +3349,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->window_clamp = 0;
 	tp->delivered = 0;
 	tp->delivered_ce = 0;
-	if (icsk->icsk_ca_ops->release)
+	if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release)
 		icsk->icsk_ca_ops->release(sk);
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 	icsk->icsk_ca_initialized = 0;
@@ -3055,7 +3364,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
-	dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL));
+	dst_release(unrcu_pointer(xchg(&sk->sk_rx_dst, NULL)));
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
 	tp->segs_in = 0;
@@ -3376,7 +3685,7 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 	if (!val) {
 		if (sk->sk_state != TCP_CLOSE)
 			return -EINVAL;
-		tp->window_clamp = 0;
+		WRITE_ONCE(tp->window_clamp, 0);
 	} else {
 		u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp;
 		u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
@@ -3385,7 +3694,7 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 		if (new_window_clamp == old_window_clamp)
 			return 0;
 
-		tp->window_clamp = new_window_clamp;
+		WRITE_ONCE(tp->window_clamp, new_window_clamp);
 		if (new_window_clamp < old_window_clamp) {
 			/* need to apply the reserved mem provisioning only
 			 * when shrinking the window clamp
@@ -4010,11 +4319,11 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 	if (copy_from_sockptr(&len, optlen, sizeof(int)))
 		return -EFAULT;
 
-	len = min_t(unsigned int, len, sizeof(int));
-
 	if (len < 0)
 		return -EINVAL;
 
+	len = min_t(unsigned int, len, sizeof(int));
+
 	switch (optname) {
 	case TCP_MAXSEG:
 		val = tp->mss_cache;
@@ -4054,7 +4363,7 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 				      TCP_RTO_MAX / HZ);
 		break;
 	case TCP_WINDOW_CLAMP:
-		val = tp->window_clamp;
+		val = READ_ONCE(tp->window_clamp);
 		break;
 	case TCP_INFO: {
 		struct tcp_info info;
@@ -4339,6 +4648,9 @@ zerocopy_rcv_out:
 
 		return err;
 	}
+	case TCP_IS_MPTCP:
+		val = 0;
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -4427,7 +4739,7 @@ int tcp_md5_hash_key(struct tcp_sigpool *hp,
 EXPORT_SYMBOL(tcp_md5_hash_key);
 
 /* Called with rcu_read_lock() */
-enum skb_drop_reason
+static enum skb_drop_reason
 tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 		     const void *saddr, const void *daddr,
 		     int family, int l3index, const __u8 *hash_location)
@@ -4447,7 +4759,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 
 	if (!key && hash_location) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
-		tcp_hash_fail("Unexpected MD5 Hash found", family, skb, "");
+		trace_tcp_hash_md5_unexpected(sk, skb);
 		return SKB_DROP_REASON_TCP_MD5UNEXPECTED;
 	}
 
@@ -4462,29 +4774,90 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 							 NULL, skb);
 	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
-		if (family == AF_INET) {
-			tcp_hash_fail("MD5 Hash failed", AF_INET, skb, "%s L3 index %d",
-				      genhash ? "tcp_v4_calc_md5_hash failed"
-				      : "", l3index);
-		} else {
-			if (genhash) {
-				tcp_hash_fail("MD5 Hash failed",
-					      AF_INET6, skb, "L3 index %d",
-					      l3index);
-			} else {
-				tcp_hash_fail("MD5 Hash mismatch",
-					      AF_INET6, skb, "L3 index %d",
-					      l3index);
-			}
-		}
+		trace_tcp_hash_md5_mismatch(sk, skb);
 		return SKB_DROP_REASON_TCP_MD5FAILURE;
 	}
 	return SKB_NOT_DROPPED_YET;
 }
-EXPORT_SYMBOL(tcp_inbound_md5_hash);
+#else
+static inline enum skb_drop_reason
+tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
+		     const void *saddr, const void *daddr,
+		     int family, int l3index, const __u8 *hash_location)
+{
+	return SKB_NOT_DROPPED_YET;
+}
 
 #endif
 
+/* Called with rcu_read_lock() */
+enum skb_drop_reason
+tcp_inbound_hash(struct sock *sk, const struct request_sock *req,
+		 const struct sk_buff *skb,
+		 const void *saddr, const void *daddr,
+		 int family, int dif, int sdif)
+{
+	const struct tcphdr *th = tcp_hdr(skb);
+	const struct tcp_ao_hdr *aoh;
+	const __u8 *md5_location;
+	int l3index;
+
+	/* Invalid option or two times meet any of auth options */
+	if (tcp_parse_auth_options(th, &md5_location, &aoh)) {
+		trace_tcp_hash_bad_header(sk, skb);
+		return SKB_DROP_REASON_TCP_AUTH_HDR;
+	}
+
+	if (req) {
+		if (tcp_rsk_used_ao(req) != !!aoh) {
+			u8 keyid, rnext, maclen;
+
+			if (aoh) {
+				keyid = aoh->keyid;
+				rnext = aoh->rnext_keyid;
+				maclen = tcp_ao_hdr_maclen(aoh);
+			} else {
+				keyid = rnext = maclen = 0;
+			}
+
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD);
+			trace_tcp_ao_handshake_failure(sk, skb, keyid, rnext, maclen);
+			return SKB_DROP_REASON_TCP_AOFAILURE;
+		}
+	}
+
+	/* sdif set, means packet ingressed via a device
+	 * in an L3 domain and dif is set to the l3mdev
+	 */
+	l3index = sdif ? dif : 0;
+
+	/* Fast path: unsigned segments */
+	if (likely(!md5_location && !aoh)) {
+		/* Drop if there's TCP-MD5 or TCP-AO key with any rcvid/sndid
+		 * for the remote peer. On TCP-AO established connection
+		 * the last key is impossible to remove, so there's
+		 * always at least one current_key.
+		 */
+		if (tcp_ao_required(sk, saddr, family, l3index, true)) {
+			trace_tcp_hash_ao_required(sk, skb);
+			return SKB_DROP_REASON_TCP_AONOTFOUND;
+		}
+		if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) {
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
+			trace_tcp_hash_md5_required(sk, skb);
+			return SKB_DROP_REASON_TCP_MD5NOTFOUND;
+		}
+		return SKB_NOT_DROPPED_YET;
+	}
+
+	if (aoh)
+		return tcp_inbound_ao_hash(sk, skb, family, req, l3index, aoh);
+
+	return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family,
+				    l3index, md5_location);
+}
+EXPORT_SYMBOL_GPL(tcp_inbound_hash);
+
 void tcp_done(struct sock *sk)
 {
 	struct request_sock *req;
@@ -4539,6 +4912,13 @@ int tcp_abort(struct sock *sk, int err)
 		/* Don't race with userspace socket closes such as tcp_close. */
 		lock_sock(sk);
 
+	/* Avoid closing the same socket twice. */
+	if (sk->sk_state == TCP_CLOSE) {
+		if (!has_current_bpf_ctx())
+			release_sock(sk);
+		return -ENOENT;
+	}
+
 	if (sk->sk_state == TCP_LISTEN) {
 		tcp_set_state(sk, TCP_CLOSE);
 		inet_csk_listen_stop(sk);
@@ -4548,19 +4928,13 @@ int tcp_abort(struct sock *sk, int err)
 	local_bh_disable();
 	bh_lock_sock(sk);
 
-	if (!sock_flag(sk, SOCK_DEAD)) {
-		WRITE_ONCE(sk->sk_err, err);
-		/* This barrier is coupled with smp_rmb() in tcp_poll() */
-		smp_wmb();
-		sk_error_report(sk);
-		if (tcp_need_reset(sk->sk_state))
-			tcp_send_active_reset(sk, GFP_ATOMIC);
-		tcp_done(sk);
-	}
+	if (tcp_need_reset(sk->sk_state))
+		tcp_send_active_reset(sk, GFP_ATOMIC,
+				      SK_RST_REASON_TCP_STATE);
+	tcp_done_with_error(sk, err);
 
 	bh_unlock_sock(sk);
 	local_bh_enable();
-	tcp_write_queue_purge(sk);
 	if (!has_current_bpf_ctx())
 		release_sock(sk);
 	return 0;
@@ -4645,16 +5019,16 @@ static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns);
-	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_clock_cache);
-	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_mstamp);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags);
-	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 113);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 89);
 
 	/* TXRX read-write hotpath cache lines */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_clock_cache);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_mstamp);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una);
@@ -4667,7 +5041,11 @@ static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt);
-	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 76);
+
+	/* 32bit arches with 8byte alignment on u64 fields might need padding
+	 * before tcp_clock_cache.
+	 */
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 92 + 4);
 
 	/* RX read-write hotpath cache lines */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received);