1 files changed, 480 insertions, 330 deletions

diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index b0d2cda6ec0a..ebbb78b842de 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /* AF_RXRPC sendmsg() implementation.
  *
  * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -21,165 +17,299 @@
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
 
-enum rxrpc_command {
-	RXRPC_CMD_SEND_DATA,		/* send data message */
-	RXRPC_CMD_SEND_ABORT,		/* request abort generation */
-	RXRPC_CMD_ACCEPT,		/* [server] accept incoming call */
-	RXRPC_CMD_REJECT_BUSY,		/* [server] reject a call as busy */
-};
-
-struct rxrpc_send_params {
-	s64			tx_total_len;	/* Total Tx data length (if send data) */
-	unsigned long		user_call_ID;	/* User's call ID */
-	u32			abort_code;	/* Abort code to Tx (if abort) */
-	enum rxrpc_command	command : 8;	/* The command to implement */
-	bool			exclusive;	/* Shared or exclusive call */
-	bool			upgrade;	/* If the connection is upgradeable */
-};
+/*
+ * Propose an abort to be made in the I/O thread.
+ */
+bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error,
+			 enum rxrpc_abort_reason why)
+{
+	_enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why);
+
+	if (!call->send_abort && !rxrpc_call_is_complete(call)) {
+		call->send_abort_why = why;
+		call->send_abort_err = error;
+		call->send_abort_seq = 0;
+		trace_rxrpc_abort_call(call, abort_code);
+		/* Request abort locklessly vs rxrpc_input_call_event(). */
+		smp_store_release(&call->send_abort, abort_code);
+		rxrpc_poke_call(call, rxrpc_call_poke_abort);
+		return true;
+	}
+
+	return false;
+}
 
 /*
- * wait for space to appear in the transmit/ACK window
- * - caller holds the socket locked
+ * Wait for a call to become connected.  Interruption here doesn't cause the
+ * call to be aborted.
  */
-static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
-				    struct rxrpc_call *call,
-				    long *timeo)
+static int rxrpc_wait_to_be_connected(struct rxrpc_call *call, long *timeo)
 {
 	DECLARE_WAITQUEUE(myself, current);
-	int ret;
+	int ret = 0;
 
-	_enter(",{%u,%u,%u}",
-	       call->tx_hard_ack, call->tx_top, call->tx_winsize);
+	_enter("%d", call->debug_id);
 
-	add_wait_queue(&call->waitq, &myself);
+	if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN)
+		goto no_wait;
+
+	add_wait_queue_exclusive(&call->waitq, &myself);
 
 	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		ret = 0;
-		if (call->tx_top - call->tx_hard_ack <
-		    min_t(unsigned int, call->tx_winsize,
-			  call->cong_cwnd + call->cong_extra))
-			break;
-		if (call->state >= RXRPC_CALL_COMPLETE) {
-			ret = -call->error;
+		switch (call->interruptibility) {
+		case RXRPC_INTERRUPTIBLE:
+		case RXRPC_PREINTERRUPTIBLE:
+			set_current_state(TASK_INTERRUPTIBLE);
 			break;
-		}
-		if (signal_pending(current)) {
-			ret = sock_intr_errno(*timeo);
+		case RXRPC_UNINTERRUPTIBLE:
+		default:
+			set_current_state(TASK_UNINTERRUPTIBLE);
 			break;
 		}
 
-		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
-		mutex_unlock(&call->user_mutex);
-		*timeo = schedule_timeout(*timeo);
-		if (mutex_lock_interruptible(&call->user_mutex) < 0) {
+		if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN)
+			break;
+		if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
+		     call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
+		    signal_pending(current)) {
 			ret = sock_intr_errno(*timeo);
 			break;
 		}
+		*timeo = schedule_timeout(*timeo);
 	}
 
 	remove_wait_queue(&call->waitq, &myself);
-	set_current_state(TASK_RUNNING);
+	__set_current_state(TASK_RUNNING);
+
+no_wait:
+	if (ret == 0 && rxrpc_call_is_complete(call))
+		ret = call->error;
+
 	_leave(" = %d", ret);
 	return ret;
 }
 
 /*
- * Schedule an instant Tx resend.
+ * Return true if there's sufficient Tx queue space.
+ */
+static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win)
+{
+	rxrpc_seq_t tx_bottom = READ_ONCE(call->tx_bottom);
+
+	if (_tx_win)
+		*_tx_win = tx_bottom;
+	return call->send_top - tx_bottom < 256;
+}
+
+/*
+ * Wait for space to appear in the Tx queue or a signal to occur.
+ */
+static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
+					 struct rxrpc_call *call,
+					 long *timeo)
+{
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (rxrpc_check_tx_space(call, NULL))
+			return 0;
+
+		if (rxrpc_call_is_complete(call))
+			return call->error;
+
+		if (signal_pending(current))
+			return sock_intr_errno(*timeo);
+
+		trace_rxrpc_txqueue(call, rxrpc_txqueue_wait);
+		*timeo = schedule_timeout(*timeo);
+	}
+}
+
+/*
+ * Wait for space to appear in the Tx queue uninterruptibly, but with
+ * a timeout of 2*RTT if no progress was made and a signal occurred.
+ */
+static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,
+					    struct rxrpc_call *call)
+{
+	rxrpc_seq_t tx_start, tx_win;
+	signed long rtt, timeout;
+
+	rtt = READ_ONCE(call->srtt_us) >> 3;
+	rtt = usecs_to_jiffies(rtt) * 2;
+	if (rtt < 2)
+		rtt = 2;
+
+	timeout = rtt;
+	tx_start = READ_ONCE(call->tx_bottom);
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+
+		if (rxrpc_check_tx_space(call, &tx_win))
+			return 0;
+
+		if (rxrpc_call_is_complete(call))
+			return call->error;
+
+		if (timeout == 0 &&
+		    tx_win == tx_start && signal_pending(current))
+			return -EINTR;
+
+		if (tx_win != tx_start) {
+			timeout = rtt;
+			tx_start = tx_win;
+		}
+
+		trace_rxrpc_txqueue(call, rxrpc_txqueue_wait);
+		timeout = schedule_timeout(timeout);
+	}
+}
+
+/*
+ * Wait for space to appear in the Tx queue uninterruptibly.
  */
-static inline void rxrpc_instant_resend(struct rxrpc_call *call, int ix)
+static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
+					    struct rxrpc_call *call,
+					    long *timeo)
 {
-	spin_lock_bh(&call->lock);
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (rxrpc_check_tx_space(call, NULL))
+			return 0;
+
+		if (rxrpc_call_is_complete(call))
+			return call->error;
 
-	if (call->state < RXRPC_CALL_COMPLETE) {
-		call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS;
-		if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events))
-			rxrpc_queue_call(call);
+		trace_rxrpc_txqueue(call, rxrpc_txqueue_wait);
+		*timeo = schedule_timeout(*timeo);
 	}
+}
 
-	spin_unlock_bh(&call->lock);
+/*
+ * wait for space to appear in the transmit/ACK window
+ * - caller holds the socket locked
+ */
+static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
+				    struct rxrpc_call *call,
+				    long *timeo,
+				    bool waitall)
+{
+	DECLARE_WAITQUEUE(myself, current);
+	int ret;
+
+	_enter(",{%u,%u,%u}",
+	       call->tx_bottom, call->tx_top, call->tx_winsize);
+
+	add_wait_queue(&call->waitq, &myself);
+
+	switch (call->interruptibility) {
+	case RXRPC_INTERRUPTIBLE:
+		if (waitall)
+			ret = rxrpc_wait_for_tx_window_waitall(rx, call);
+		else
+			ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
+		break;
+	case RXRPC_PREINTERRUPTIBLE:
+	case RXRPC_UNINTERRUPTIBLE:
+	default:
+		ret = rxrpc_wait_for_tx_window_nonintr(rx, call, timeo);
+		break;
+	}
+
+	remove_wait_queue(&call->waitq, &myself);
+	set_current_state(TASK_RUNNING);
+	_leave(" = %d", ret);
+	return ret;
 }
 
 /*
- * Queue a DATA packet for transmission, set the resend timeout and send the
- * packet immediately
+ * Notify the owner of the call that the transmit phase is ended and the last
+ * packet has been queued.
  */
-static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
-			       bool last)
+static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call,
+				rxrpc_notify_end_tx_t notify_end_tx)
 {
-	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-	rxrpc_seq_t seq = sp->hdr.seq;
-	int ret, ix;
-	u8 annotation = RXRPC_TX_ANNO_UNACK;
+	if (notify_end_tx)
+		notify_end_tx(&rx->sk, call, call->user_call_ID);
+}
 
-	_net("queue skb %p [%d]", skb, seq);
+/*
+ * Queue a DATA packet for transmission, set the resend timeout and send
+ * the packet immediately.  Returns the error from rxrpc_send_data_packet()
+ * in case the caller wants to do something with it.
+ */
+static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
+			       struct rxrpc_txbuf *txb,
+			       rxrpc_notify_end_tx_t notify_end_tx)
+{
+	struct rxrpc_txqueue *sq = call->send_queue;
+	rxrpc_seq_t seq = txb->seq;
+	bool poke, last = txb->flags & RXRPC_LAST_PACKET;
+	int ix = seq & RXRPC_TXQ_MASK;
+	rxrpc_inc_stat(call->rxnet, stat_tx_data);
 
-	ASSERTCMP(seq, ==, call->tx_top + 1);
+	ASSERTCMP(txb->seq, ==, call->send_top + 1);
 
 	if (last)
-		annotation |= RXRPC_TX_ANNO_LAST;
-
-	/* We have to set the timestamp before queueing as the retransmit
-	 * algorithm can see the packet as soon as we queue it.
-	 */
-	skb->tstamp = ktime_get_real();
-
-	ix = seq & RXRPC_RXTX_BUFF_MASK;
-	rxrpc_get_skb(skb, rxrpc_skb_tx_got);
-	call->rxtx_annotations[ix] = annotation;
-	smp_wmb();
-	call->rxtx_buffer[ix] = skb;
-	call->tx_top = seq;
-	if (last)
-		trace_rxrpc_transmit(call, rxrpc_transmit_queue_last);
+		trace_rxrpc_txqueue(call, rxrpc_txqueue_queue_last);
 	else
-		trace_rxrpc_transmit(call, rxrpc_transmit_queue);
-
-	if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) {
-		_debug("________awaiting reply/ACK__________");
-		write_lock_bh(&call->state_lock);
-		switch (call->state) {
-		case RXRPC_CALL_CLIENT_SEND_REQUEST:
-			call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
-			break;
-		case RXRPC_CALL_SERVER_ACK_REQUEST:
-			call->state = RXRPC_CALL_SERVER_SEND_REPLY;
-			call->ack_at = call->expire_at;
-			if (call->ackr_reason == RXRPC_ACK_DELAY)
-				call->ackr_reason = 0;
-			__rxrpc_set_timer(call, rxrpc_timer_init_for_send_reply,
-					  ktime_get_real());
-			if (!last)
-				break;
-		case RXRPC_CALL_SERVER_SEND_REPLY:
-			call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
-			break;
-		default:
-			break;
-		}
-		write_unlock_bh(&call->state_lock);
+		trace_rxrpc_txqueue(call, rxrpc_txqueue_queue);
+
+	if (WARN_ON_ONCE(sq->bufs[ix]))
+		trace_rxrpc_tq(call, sq, seq, rxrpc_tq_queue_dup);
+	else
+		trace_rxrpc_tq(call, sq, seq, rxrpc_tq_queue);
+
+	/* Add the packet to the call's output buffer */
+	poke = (READ_ONCE(call->tx_bottom) == call->send_top);
+	sq->bufs[ix] = txb;
+	/* Order send_top after the queue->next pointer and txb content. */
+	smp_store_release(&call->send_top, seq);
+	if (last) {
+		set_bit(RXRPC_CALL_TX_NO_MORE, &call->flags);
+		rxrpc_notify_end_tx(rx, call, notify_end_tx);
+		call->send_queue = NULL;
 	}
 
-	if (seq == 1 && rxrpc_is_client_call(call))
-		rxrpc_expose_client_call(call);
+	if (poke)
+		rxrpc_poke_call(call, rxrpc_call_poke_start);
+}
 
-	ret = rxrpc_send_data_packet(call, skb, false);
-	if (ret < 0) {
-		_debug("need instant resend %d", ret);
-		rxrpc_instant_resend(call, ix);
+/*
+ * Allocate a new txqueue unit and add it to the transmission queue.
+ */
+static int rxrpc_alloc_txqueue(struct sock *sk, struct rxrpc_call *call)
+{
+	struct rxrpc_txqueue *tq;
+
+	tq = kzalloc(sizeof(*tq), sk->sk_allocation);
+	if (!tq)
+		return -ENOMEM;
+
+	tq->xmit_ts_base = KTIME_MIN;
+	for (int i = 0; i < RXRPC_NR_TXQUEUE; i++)
+		tq->segment_xmit_ts[i] = UINT_MAX;
+
+	if (call->send_queue) {
+		tq->qbase = call->send_top + 1;
+		call->send_queue->next = tq;
+		call->send_queue = tq;
+	} else if (WARN_ON(call->tx_queue)) {
+		kfree(tq);
+		return -ENOMEM;
 	} else {
-		ktime_t now = ktime_get_real(), resend_at;
-
-		resend_at = ktime_add_ms(now, rxrpc_resend_timeout);
-
-		if (ktime_before(resend_at, call->resend_at)) {
-			call->resend_at = resend_at;
-			rxrpc_set_timer(call, rxrpc_timer_set_for_send, now);
-		}
+		/* We start at seq 1, so pretend seq 0 is hard-acked. */
+		tq->nr_reported_acks = 1;
+		tq->segment_acked = 1UL;
+		tq->qbase = 0;
+		call->tx_qbase = 0;
+		call->send_queue = tq;
+		call->tx_qtail = tq;
+		call->tx_queue = tq;
 	}
 
-	rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
-	_leave("");
+	trace_rxrpc_tq(call, tq, call->send_top, rxrpc_tq_alloc);
+	return 0;
 }
 
 /*
@@ -189,123 +319,113 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
  */
 static int rxrpc_send_data(struct rxrpc_sock *rx,
 			   struct rxrpc_call *call,
-			   struct msghdr *msg, size_t len)
+			   struct msghdr *msg, size_t len,
+			   rxrpc_notify_end_tx_t notify_end_tx,
+			   bool *_dropped_lock)
 {
-	struct rxrpc_skb_priv *sp;
-	struct sk_buff *skb;
+	struct rxrpc_txbuf *txb;
 	struct sock *sk = &rx->sk;
+	enum rxrpc_call_state state;
 	long timeo;
-	bool more;
-	int ret, copied;
+	bool more = msg->msg_flags & MSG_MORE;
+	int ret, copied = 0;
+
+	if (test_bit(RXRPC_CALL_TX_NO_MORE, &call->flags)) {
+		trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send,
+				  call->cid, call->call_id, call->rx_consumed,
+				  0, -EPROTO);
+		return -EPROTO;
+	}
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
+	ret = rxrpc_wait_to_be_connected(call, &timeo);
+	if (ret < 0)
+		return ret;
+
+	if (call->conn->state == RXRPC_CONN_CLIENT_UNSECURED) {
+		ret = rxrpc_init_client_conn_security(call->conn);
+		if (ret < 0)
+			return ret;
+	}
+
 	/* this should be in poll */
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
-	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
-		return -EPIPE;
-
-	more = msg->msg_flags & MSG_MORE;
+reload:
+	txb = call->tx_pending;
+	call->tx_pending = NULL;
+	if (txb)
+		rxrpc_see_txbuf(txb, rxrpc_txbuf_see_send_more);
+
+	ret = -EPIPE;
+	if (sk->sk_shutdown & SEND_SHUTDOWN)
+		goto maybe_error;
+	state = rxrpc_call_state(call);
+	ret = -ESHUTDOWN;
+	if (state >= RXRPC_CALL_COMPLETE)
+		goto maybe_error;
+	ret = -EPROTO;
+	if (state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
+	    state != RXRPC_CALL_SERVER_ACK_REQUEST &&
+	    state != RXRPC_CALL_SERVER_SEND_REPLY) {
+		/* Request phase complete for this client call */
+		trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send,
+				  call->cid, call->call_id, call->rx_consumed,
+				  0, -EPROTO);
+		goto maybe_error;
+	}
 
+	ret = -EMSGSIZE;
 	if (call->tx_total_len != -1) {
-		if (len > call->tx_total_len)
-			return -EMSGSIZE;
-		if (!more && len != call->tx_total_len)
-			return -EMSGSIZE;
+		if (len - copied > call->tx_total_len)
+			goto maybe_error;
+		if (!more && len - copied != call->tx_total_len)
+			goto maybe_error;
 	}
 
-	skb = call->tx_pending;
-	call->tx_pending = NULL;
-	rxrpc_see_skb(skb, rxrpc_skb_tx_seen);
-
-	copied = 0;
 	do {
-		/* Check to see if there's a ping ACK to reply to. */
-		if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE)
-			rxrpc_send_ack_packet(call, false);
-
-		if (!skb) {
-			size_t size, chunk, max, space;
+		if (!txb) {
+			size_t remain;
 
 			_debug("alloc");
 
-			if (call->tx_top - call->tx_hard_ack >=
-			    min_t(unsigned int, call->tx_winsize,
-				  call->cong_cwnd + call->cong_extra)) {
-				ret = -EAGAIN;
-				if (msg->msg_flags & MSG_DONTWAIT)
-					goto maybe_error;
-				ret = rxrpc_wait_for_tx_window(rx, call,
-							       &timeo);
+			if (!rxrpc_check_tx_space(call, NULL))
+				goto wait_for_space;
+
+			/* See if we need to begin/extend the Tx queue. */
+			if (!call->send_queue || !((call->send_top + 1) & RXRPC_TXQ_MASK)) {
+				ret = rxrpc_alloc_txqueue(sk, call);
 				if (ret < 0)
 					goto maybe_error;
 			}
 
-			max = RXRPC_JUMBO_DATALEN;
-			max -= call->conn->security_size;
-			max &= ~(call->conn->size_align - 1UL);
-
-			chunk = max;
-			if (chunk > msg_data_left(msg) && !more)
-				chunk = msg_data_left(msg);
-
-			space = chunk + call->conn->size_align;
-			space &= ~(call->conn->size_align - 1UL);
-
-			size = space + call->conn->security_size;
-
-			_debug("SIZE: %zu/%zu/%zu", chunk, space, size);
-
-			/* create a buffer that we can retain until it's ACK'd */
-			skb = sock_alloc_send_skb(
-				sk, size, msg->msg_flags & MSG_DONTWAIT, &ret);
-			if (!skb)
+			/* Work out the maximum size of a packet.  Assume that
+			 * the security header is going to be in the padded
+			 * region (enc blocksize), but the trailer is not.
+			 */
+			remain = more ? INT_MAX : msg_data_left(msg);
+			txb = call->conn->security->alloc_txbuf(call, remain, sk->sk_allocation);
+			if (!txb) {
+				ret = -ENOMEM;
 				goto maybe_error;
-
-			rxrpc_new_skb(skb, rxrpc_skb_tx_new);
-
-			_debug("ALLOC SEND %p", skb);
-
-			ASSERTCMP(skb->mark, ==, 0);
-
-			_debug("HS: %u", call->conn->security_size);
-			skb_reserve(skb, call->conn->security_size);
-			skb->len += call->conn->security_size;
-
-			sp = rxrpc_skb(skb);
-			sp->remain = chunk;
-			if (sp->remain > skb_tailroom(skb))
-				sp->remain = skb_tailroom(skb);
-
-			_net("skb: hr %d, tr %d, hl %d, rm %d",
-			       skb_headroom(skb),
-			       skb_tailroom(skb),
-			       skb_headlen(skb),
-			       sp->remain);
-
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			}
 		}
 
 		_debug("append");
-		sp = rxrpc_skb(skb);
 
 		/* append next segment of data to the current buffer */
 		if (msg_data_left(msg) > 0) {
-			int copy = skb_tailroom(skb);
-			ASSERTCMP(copy, >, 0);
-			if (copy > msg_data_left(msg))
-				copy = msg_data_left(msg);
-			if (copy > sp->remain)
-				copy = sp->remain;
-
-			_debug("add");
-			ret = skb_add_data(skb, &msg->msg_iter, copy);
-			_debug("added");
-			if (ret < 0)
+			size_t copy = umin(txb->space, msg_data_left(msg));
+
+			_debug("add %zu", copy);
+			if (!copy_from_iter_full(txb->data + txb->offset,
+						 copy, &msg->msg_iter))
 				goto efault;
-			sp->remain -= copy;
-			skb->mark += copy;
+			_debug("added");
+			txb->space -= copy;
+			txb->len += copy;
+			txb->offset += copy;
 			copied += copy;
 			if (call->tx_total_len != -1)
 				call->tx_total_len -= copy;
@@ -313,59 +433,37 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 
 		/* check for the far side aborting the call or a network error
 		 * occurring */
-		if (call->state == RXRPC_CALL_COMPLETE)
+		if (rxrpc_call_is_complete(call))
 			goto call_terminated;
 
 		/* add the packet to the send queue if it's now full */
-		if (sp->remain <= 0 ||
+		if (!txb->space ||
 		    (msg_data_left(msg) == 0 && !more)) {
-			struct rxrpc_connection *conn = call->conn;
-			uint32_t seq;
-			size_t pad;
-
-			/* pad out if we're using security */
-			if (conn->security_ix) {
-				pad = conn->security_size + skb->mark;
-				pad = conn->size_align - pad;
-				pad &= conn->size_align - 1;
-				_debug("pad %zu", pad);
-				if (pad)
-					skb_put_zero(skb, pad);
-			}
-
-			seq = call->tx_top + 1;
-
-			sp->hdr.seq	= seq;
-			sp->hdr._rsvd	= 0;
-			sp->hdr.flags	= conn->out_clientflag;
-
 			if (msg_data_left(msg) == 0 && !more)
-				sp->hdr.flags |= RXRPC_LAST_PACKET;
-			else if (call->tx_top - call->tx_hard_ack <
-				 call->tx_winsize)
-				sp->hdr.flags |= RXRPC_MORE_PACKETS;
+				txb->flags |= RXRPC_LAST_PACKET;
 
-			ret = conn->security->secure_packet(
-				call, skb, skb->mark, skb->head);
+			ret = call->security->secure_packet(call, txb);
 			if (ret < 0)
 				goto out;
-
-			rxrpc_queue_packet(call, skb, !msg_data_left(msg) && !more);
-			skb = NULL;
+			rxrpc_queue_packet(rx, call, txb, notify_end_tx);
+			txb = NULL;
 		}
 	} while (msg_data_left(msg) > 0);
 
 success:
 	ret = copied;
+	if (rxrpc_call_is_complete(call) &&
+	    call->error < 0)
+		ret = call->error;
 out:
-	call->tx_pending = skb;
+	call->tx_pending = txb;
 	_leave(" = %d", ret);
 	return ret;
 
 call_terminated:
-	rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
-	_leave(" = %d", -call->error);
-	return -call->error;
+	rxrpc_put_txbuf(txb, rxrpc_txbuf_put_send_aborted);
+	_leave(" = %d", call->error);
+	return call->error;
 
 maybe_error:
 	if (copied)
@@ -375,6 +473,27 @@ maybe_error:
 efault:
 	ret = -EFAULT;
 	goto out;
+
+wait_for_space:
+	ret = -EAGAIN;
+	if (msg->msg_flags & MSG_DONTWAIT)
+		goto maybe_error;
+	mutex_unlock(&call->user_mutex);
+	*_dropped_lock = true;
+	ret = rxrpc_wait_for_tx_window(rx, call, &timeo,
+				       msg->msg_flags & MSG_WAITALL);
+	if (ret < 0)
+		goto maybe_error;
+	if (call->interruptibility == RXRPC_INTERRUPTIBLE) {
+		if (mutex_lock_interruptible(&call->user_mutex) < 0) {
+			ret = sock_intr_errno(timeo);
+			goto maybe_error;
+		}
+	} else {
+		mutex_lock(&call->user_mutex);
+	}
+	*_dropped_lock = false;
+	goto reload;
 }
 
 /*
@@ -405,11 +524,11 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p)
 			if (msg->msg_flags & MSG_CMSG_COMPAT) {
 				if (len != sizeof(u32))
 					return -EINVAL;
-				p->user_call_ID = *(u32 *)CMSG_DATA(cmsg);
+				p->call.user_call_ID = *(u32 *)CMSG_DATA(cmsg);
 			} else {
 				if (len != sizeof(unsigned long))
 					return -EINVAL;
-				p->user_call_ID = *(unsigned long *)
+				p->call.user_call_ID = *(unsigned long *)
 					CMSG_DATA(cmsg);
 			}
 			got_user_ID = true;
@@ -426,10 +545,10 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p)
 				return -EINVAL;
 			break;
 
-		case RXRPC_ACCEPT:
+		case RXRPC_CHARGE_ACCEPT:
 			if (p->command != RXRPC_CMD_SEND_DATA)
 				return -EINVAL;
-			p->command = RXRPC_CMD_ACCEPT;
+			p->command = RXRPC_CMD_CHARGE_ACCEPT;
 			if (len != 0)
 				return -EINVAL;
 			break;
@@ -447,11 +566,24 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p)
 			break;
 
 		case RXRPC_TX_LENGTH:
-			if (p->tx_total_len != -1 || len != sizeof(__s64))
+			if (p->call.tx_total_len != -1 || len != sizeof(__s64))
+				return -EINVAL;
+			p->call.tx_total_len = *(__s64 *)CMSG_DATA(cmsg);
+			if (p->call.tx_total_len < 0)
 				return -EINVAL;
-			p->tx_total_len = *(__s64 *)CMSG_DATA(cmsg);
-			if (p->tx_total_len < 0)
+			break;
+
+		case RXRPC_SET_CALL_TIMEOUT:
+			if (len & 3 || len < 4 || len > 12)
 				return -EINVAL;
+			memcpy(&p->call.timeouts, CMSG_DATA(cmsg), len);
+			p->call.nr_timeouts = len / 4;
+			if (p->call.timeouts.hard > INT_MAX / HZ)
+				return -ERANGE;
+			if (p->call.nr_timeouts >= 2 && p->call.timeouts.idle > 60 * 60 * 1000)
+				return -ERANGE;
+			if (p->call.nr_timeouts >= 3 && p->call.timeouts.normal > 60 * 60 * 1000)
+				return -ERANGE;
 			break;
 
 		default:
@@ -461,7 +593,7 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p)
 
 	if (!got_user_ID)
 		return -EINVAL;
-	if (p->tx_total_len != -1 && p->command != RXRPC_CMD_SEND_DATA)
+	if (p->call.tx_total_len != -1 && p->command != RXRPC_CMD_SEND_DATA)
 		return -EINVAL;
 	_leave(" = 0");
 	return 0;
@@ -475,9 +607,11 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p)
 static struct rxrpc_call *
 rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 				  struct rxrpc_send_params *p)
-	__releases(&rx->sk.sk_lock.slock)
+	__releases(&rx->sk.sk_lock)
+	__acquires(&call->user_mutex)
 {
 	struct rxrpc_conn_parameters cp;
+	struct rxrpc_peer *peer;
 	struct rxrpc_call *call;
 	struct key *key;
 
@@ -490,21 +624,29 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
 		return ERR_PTR(-EDESTADDRREQ);
 	}
 
+	peer = rxrpc_lookup_peer(rx->local, srx, GFP_KERNEL);
+	if (!peer) {
+		release_sock(&rx->sk);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	key = rx->key;
 	if (key && !rx->key->payload.data[0])
 		key = NULL;
 
 	memset(&cp, 0, sizeof(cp));
 	cp.local		= rx->local;
+	cp.peer			= peer;
 	cp.key			= rx->key;
 	cp.security_level	= rx->min_sec_level;
 	cp.exclusive		= rx->exclusive | p->exclusive;
 	cp.upgrade		= p->upgrade;
 	cp.service_id		= srx->srx_service;
-	call = rxrpc_new_client_call(rx, &cp, srx, p->user_call_ID,
-				     p->tx_total_len, GFP_KERNEL);
+	call = rxrpc_new_client_call(rx, &cp, &p->call, GFP_KERNEL,
+				     atomic_inc_return(&rxrpc_debug_id));
 	/* The socket is now unlocked */
 
+	rxrpc_put_peer(peer, rxrpc_peer_put_application);
 	_leave(" = %p\n", call);
 	return call;
 }
@@ -515,19 +657,20 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
  * - the socket may be either a client socket or a server socket
  */
 int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
-	__releases(&rx->sk.sk_lock.slock)
 {
-	enum rxrpc_call_state state;
 	struct rxrpc_call *call;
+	bool dropped_lock = false;
 	int ret;
 
 	struct rxrpc_send_params p = {
-		.tx_total_len	= -1,
-		.user_call_ID	= 0,
-		.abort_code	= 0,
-		.command	= RXRPC_CMD_SEND_DATA,
-		.exclusive	= false,
-		.upgrade	= true,
+		.call.tx_total_len	= -1,
+		.call.user_call_ID	= 0,
+		.call.nr_timeouts	= 0,
+		.call.interruptibility	= RXRPC_INTERRUPTIBLE,
+		.abort_code		= 0,
+		.command		= RXRPC_CMD_SEND_DATA,
+		.exclusive		= false,
+		.upgrade		= false,
 	};
 
 	_enter("");
@@ -536,19 +679,15 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 	if (ret < 0)
 		goto error_release_sock;
 
-	if (p.command == RXRPC_CMD_ACCEPT) {
+	if (p.command == RXRPC_CMD_CHARGE_ACCEPT) {
 		ret = -EINVAL;
 		if (rx->sk.sk_state != RXRPC_SERVER_LISTENING)
 			goto error_release_sock;
-		call = rxrpc_accept_call(rx, p.user_call_ID, NULL);
-		/* The socket is now unlocked. */
-		if (IS_ERR(call))
-			return PTR_ERR(call);
-		rxrpc_put_call(call, rxrpc_call_put);
-		return 0;
+		ret = rxrpc_user_charge_accept(rx, p.call.user_call_ID);
+		goto error_release_sock;
 	}
 
-	call = rxrpc_find_call_by_user_ID(rx, p.user_call_ID);
+	call = rxrpc_find_call_by_user_ID(rx, p.call.user_call_ID);
 	if (!call) {
 		ret = -EBADSLT;
 		if (p.command != RXRPC_CMD_SEND_DATA)
@@ -558,13 +697,20 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		if (IS_ERR(call))
 			return PTR_ERR(call);
 		/* ... and we have the call lock. */
+		p.call.nr_timeouts = 0;
+		ret = 0;
+		if (rxrpc_call_is_complete(call))
+			goto out_put_unlock;
 	} else {
-		switch (READ_ONCE(call->state)) {
-		case RXRPC_CALL_UNINITIALISED:
+		switch (rxrpc_call_state(call)) {
 		case RXRPC_CALL_CLIENT_AWAIT_CONN:
+		case RXRPC_CALL_SERVER_RECV_REQUEST:
+			if (p.command == RXRPC_CMD_SEND_ABORT)
+				break;
+			fallthrough;
+		case RXRPC_CALL_UNINITIALISED:
 		case RXRPC_CALL_SERVER_PREALLOC:
-		case RXRPC_CALL_SERVER_SECURING:
-		case RXRPC_CALL_SERVER_ACCEPTING:
+			rxrpc_put_call(call, rxrpc_call_put_sendmsg);
 			ret = -EBUSY;
 			goto error_release_sock;
 		default:
@@ -578,45 +724,62 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 			goto error_put;
 		}
 
-		if (p.tx_total_len != -1) {
+		if (p.call.tx_total_len != -1) {
 			ret = -EINVAL;
 			if (call->tx_total_len != -1 ||
 			    call->tx_pending ||
 			    call->tx_top != 0)
-				goto error_put;
-			call->tx_total_len = p.tx_total_len;
+				goto out_put_unlock;
+			call->tx_total_len = p.call.tx_total_len;
 		}
 	}
 
-	state = READ_ONCE(call->state);
-	_debug("CALL %d USR %lx ST %d on CONN %p",
-	       call->debug_id, call->user_call_ID, state, call->conn);
+	switch (p.call.nr_timeouts) {
+	case 3:
+		WRITE_ONCE(call->next_rx_timo, p.call.timeouts.normal);
+		fallthrough;
+	case 2:
+		WRITE_ONCE(call->next_req_timo, p.call.timeouts.idle);
+		fallthrough;
+	case 1:
+		if (p.call.timeouts.hard > 0) {
+			ktime_t delay = ms_to_ktime(p.call.timeouts.hard * MSEC_PER_SEC);
+
+			WRITE_ONCE(call->expect_term_by,
+				   ktime_add(p.call.timeouts.hard,
+					     ktime_get_real()));
+			trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard);
+			rxrpc_poke_call(call, rxrpc_call_poke_set_timeout);
+
+		}
+		break;
+	}
 
-	if (state >= RXRPC_CALL_COMPLETE) {
+	if (rxrpc_call_is_complete(call)) {
 		/* it's too late for this call */
 		ret = -ESHUTDOWN;
-	} else if (p.command == RXRPC_CMD_SEND_ABORT) {
+		goto out_put_unlock;
+	}
+
+	switch (p.command) {
+	case RXRPC_CMD_SEND_ABORT:
+		rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED,
+				    rxrpc_abort_call_sendmsg);
 		ret = 0;
-		if (rxrpc_abort_call("CMD", call, 0, p.abort_code, -ECONNABORTED))
-			ret = rxrpc_send_abort_packet(call);
-	} else if (p.command != RXRPC_CMD_SEND_DATA) {
+		break;
+	case RXRPC_CMD_SEND_DATA:
+		ret = rxrpc_send_data(rx, call, msg, len, NULL, &dropped_lock);
+		break;
+	default:
 		ret = -EINVAL;
-	} else if (rxrpc_is_client_call(call) &&
-		   state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
-		/* request phase complete for this client call */
-		ret = -EPROTO;
-	} else if (rxrpc_is_service_call(call) &&
-		   state != RXRPC_CALL_SERVER_ACK_REQUEST &&
-		   state != RXRPC_CALL_SERVER_SEND_REPLY) {
-		/* Reply phase not begun or not complete for service call. */
-		ret = -EPROTO;
-	} else {
-		ret = rxrpc_send_data(rx, call, msg, len);
+		break;
 	}
 
-	mutex_unlock(&call->user_mutex);
+out_put_unlock:
+	if (!dropped_lock)
+		mutex_unlock(&call->user_mutex);
 error_put:
-	rxrpc_put_call(call, rxrpc_call_put);
+	rxrpc_put_call(call, rxrpc_call_put_sendmsg);
 	_leave(" = %d", ret);
 	return ret;
 
@@ -631,46 +794,36 @@ error_release_sock:
  * @call: The call to send data through
  * @msg: The data to send
  * @len: The amount of data to send
+ * @notify_end_tx: Notification that the last packet is queued.
  *
  * Allow a kernel service to send data on a call.  The call must be in an state
  * appropriate to sending data.  No control data should be supplied in @msg,
  * nor should an address be supplied.  MSG_MORE should be flagged if there's
  * more data to come, otherwise this data will end the transmission phase.
+ *
+ * Return: %0 if successful and a negative error code otherwise.
  */
 int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
-			   struct msghdr *msg, size_t len)
+			   struct msghdr *msg, size_t len,
+			   rxrpc_notify_end_tx_t notify_end_tx)
 {
+	bool dropped_lock = false;
 	int ret;
 
-	_enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
+	_enter("{%d},", call->debug_id);
 
 	ASSERTCMP(msg->msg_name, ==, NULL);
 	ASSERTCMP(msg->msg_control, ==, NULL);
 
 	mutex_lock(&call->user_mutex);
 
-	_debug("CALL %d USR %lx ST %d on CONN %p",
-	       call->debug_id, call->user_call_ID, call->state, call->conn);
+	ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
+			      notify_end_tx, &dropped_lock);
+	if (ret == -ESHUTDOWN)
+		ret = call->error;
 
-	switch (READ_ONCE(call->state)) {
-	case RXRPC_CALL_CLIENT_SEND_REQUEST:
-	case RXRPC_CALL_SERVER_ACK_REQUEST:
-	case RXRPC_CALL_SERVER_SEND_REPLY:
-		ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len);
-		break;
-	case RXRPC_CALL_COMPLETE:
-		read_lock_bh(&call->state_lock);
-		ret = -call->error;
-		read_unlock_bh(&call->state_lock);
-		break;
-	default:
-		/* Request phase complete for this client call */
-		trace_rxrpc_rx_eproto(call, 0, tracepoint_string("late_send"));
-		ret = -EPROTO;
-		break;
-	}
-
-	mutex_unlock(&call->user_mutex);
+	if (!dropped_lock)
+		mutex_unlock(&call->user_mutex);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -682,24 +835,21 @@ EXPORT_SYMBOL(rxrpc_kernel_send_data);
  * @call: The call to be aborted
  * @abort_code: The abort code to stick into the ABORT packet
  * @error: Local error value
- * @why: 3-char string indicating why.
+ * @why: Indication as to why.
  *
- * Allow a kernel service to abort a call, if it's still in an abortable state
- * and return true if the call was aborted, false if it was already complete.
+ * Allow a kernel service to abort a call if it's still in an abortable state.
+ *
+ * Return: %true if the call was aborted, %false if it was already complete.
  */
 bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
-			     u32 abort_code, int error, const char *why)
+			     u32 abort_code, int error, enum rxrpc_abort_reason why)
 {
 	bool aborted;
 
-	_enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
+	_enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why);
 
 	mutex_lock(&call->user_mutex);
-
-	aborted = rxrpc_abort_call(why, call, 0, abort_code, error);
-	if (aborted)
-		rxrpc_send_abort_packet(call);
-
+	aborted = rxrpc_propose_abort(call, abort_code, error, why);
 	mutex_unlock(&call->user_mutex);
 	return aborted;
 }