Merge tag 'rxrpc-fixes-20200319' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

David Howells says:

====================
rxrpc, afs: Interruptibility fixes

Here are a number of fixes for AF_RXRPC and AFS that make AFS system calls
less interruptible and so less likely to leave the filesystem in an
uncertain state.  There's also a miscellaneous patch to make tracing
consistent.

 (1) Firstly, abstract out the Tx space calculation in sendmsg.  Much the
     same code is replicated in a number of places that subsequent patches
     are going to alter, including adding another copy.

 (2) Fix Tx interruptibility by allowing a kernel service, such as AFS, to
     request that a call be interruptible only when waiting for a call slot
     to become available (ie. the call has not taken place yet) or that a
     call be not interruptible at all (e.g. when we want to do writeback
     and don't want a signal interrupting a VM-induced writeback).

 (3) Increase the minimum delay on MSG_WAITALL for userspace sendmsg() when
     waiting for Tx buffer space as a 2*RTT delay is really small over 10G
     ethernet and a 1 jiffy timeout might be essentially 0 if at the end of
     the jiffy period.

 (4) Fix some tracing output in AFS to make it consistent with rxrpc.

 (5) Make sure aborted asynchronous AFS operations are tidied up properly
     so we don't end up with stuck rxrpc calls.

 (6) Make AFS client calls uninterruptible in the Rx phase.  If we don't
     wait for the reply to be fully gathered, we can't update the local VFS
     state and we end up in an indeterminate state with respect to the
     server.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 74 insertions, 60 deletions

diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index fe42f986cd94..15ee92d79581 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -285,7 +285,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 					   gfp_t gfp,
 					   rxrpc_notify_rx_t notify_rx,
 					   bool upgrade,
-					   bool intr,
+					   enum rxrpc_interruptibility interruptibility,
 					   unsigned int debug_id)
 {
 	struct rxrpc_conn_parameters cp;
@@ -310,7 +310,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 	memset(&p, 0, sizeof(p));
 	p.user_call_ID = user_call_ID;
 	p.tx_total_len = tx_total_len;
-	p.intr = intr;
+	p.interruptibility = interruptibility;
 
 	memset(&cp, 0, sizeof(cp));
 	cp.local		= rx->local;
@@ -371,45 +371,18 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call);
  * rxrpc_kernel_check_life - Check to see whether a call is still alive
  * @sock: The socket the call is on
  * @call: The call to check
- * @_life: Where to store the life value
  *
- * Allow a kernel service to find out whether a call is still alive - ie. we're
- * getting ACKs from the server.  Passes back in *_life a number representing
- * the life state which can be compared to that returned by a previous call and
- * return true if the call is still alive.
- *
- * If the life state stalls, rxrpc_kernel_probe_life() should be called and
- * then 2RTT waited.
+ * Allow a kernel service to find out whether a call is still alive -
+ * ie. whether it has completed.
  */
 bool rxrpc_kernel_check_life(const struct socket *sock,
-			     const struct rxrpc_call *call,
-			     u32 *_life)
+			     const struct rxrpc_call *call)
 {
-	*_life = call->acks_latest;
 	return call->state != RXRPC_CALL_COMPLETE;
 }
 EXPORT_SYMBOL(rxrpc_kernel_check_life);
 
 /**
- * rxrpc_kernel_probe_life - Poke the peer to see if it's still alive
- * @sock: The socket the call is on
- * @call: The call to check
- *
- * In conjunction with rxrpc_kernel_check_life(), allow a kernel service to
- * find out whether a call is still alive by pinging it.  This should cause the
- * life state to be bumped in about 2*RTT.
- *
- * The must be called in TASK_RUNNING state on pain of might_sleep() objecting.
- */
-void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call)
-{
-	rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
-			  rxrpc_propose_ack_ping_for_check_life);
-	rxrpc_send_ack_packet(call, true, NULL);
-}
-EXPORT_SYMBOL(rxrpc_kernel_probe_life);
-
-/**
  * rxrpc_kernel_get_epoch - Retrieve the epoch value from a call.
  * @sock: The socket the call is on
  * @call: The call to query
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 7d730c438404..3eb1ab40ca5c 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -489,7 +489,6 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_BEGAN_RX_TIMER,	/* We began the expect_rx_by timer */
 	RXRPC_CALL_RX_HEARD,		/* The peer responded at least once to this call */
 	RXRPC_CALL_RX_UNDERRUN,		/* Got data underrun */
-	RXRPC_CALL_IS_INTR,		/* The call is interruptible */
 	RXRPC_CALL_DISCONNECTED,	/* The call has been disconnected */
 };
 
@@ -598,6 +597,7 @@ struct rxrpc_call {
 	atomic_t		usage;
 	u16			service_id;	/* service ID */
 	u8			security_ix;	/* Security type */
+	enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */
 	u32			call_id;	/* call ID on connection  */
 	u32			cid;		/* connection ID plus channel index */
 	int			debug_id;	/* debug ID for printks */
@@ -675,7 +675,6 @@ struct rxrpc_call {
 
 	/* transmission-phase ACK management */
 	ktime_t			acks_latest_ts;	/* Timestamp of latest ACK received */
-	rxrpc_serial_t		acks_latest;	/* serial number of latest ACK received */
 	rxrpc_seq_t		acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */
 	rxrpc_seq_t		acks_lost_top;	/* tx_top at the time lost-ack ping sent */
 	rxrpc_serial_t		acks_lost_ping;	/* Serial number of probe ACK */
@@ -721,7 +720,7 @@ struct rxrpc_call_params {
 		u32		normal;		/* Max time since last call packet (msec) */
 	} timeouts;
 	u8			nr_timeouts;	/* Number of timeouts specified */
-	bool			intr;		/* The call is interruptible */
+	enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */
 };
 
 struct rxrpc_send_params {
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index c9f34b0a11df..f07970207b54 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -237,8 +237,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 		return call;
 	}
 
-	if (p->intr)
-		__set_bit(RXRPC_CALL_IS_INTR, &call->flags);
+	call->interruptibility = p->interruptibility;
 	call->tx_total_len = p->tx_total_len;
 	trace_rxrpc_call(call->debug_id, rxrpc_call_new_client,
 			 atomic_read(&call->usage),
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index ea7d4c21f889..f2a1a5dbb5a7 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -655,13 +655,20 @@ static int rxrpc_wait_for_channel(struct rxrpc_call *call, gfp_t gfp)
 
 		add_wait_queue_exclusive(&call->waitq, &myself);
 		for (;;) {
-			if (test_bit(RXRPC_CALL_IS_INTR, &call->flags))
+			switch (call->interruptibility) {
+			case RXRPC_INTERRUPTIBLE:
+			case RXRPC_PREINTERRUPTIBLE:
 				set_current_state(TASK_INTERRUPTIBLE);
-			else
+				break;
+			case RXRPC_UNINTERRUPTIBLE:
+			default:
 				set_current_state(TASK_UNINTERRUPTIBLE);
+				break;
+			}
 			if (call->call_id)
 				break;
-			if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) &&
+			if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
+			     call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
 			    signal_pending(current)) {
 				ret = -ERESTARTSYS;
 				break;
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index ef10fbf71b15..69e09d69c896 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -882,7 +882,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
 	    before(prev_pkt, call->ackr_prev_seq))
 		goto out;
 	call->acks_latest_ts = skb->tstamp;
-	call->acks_latest = sp->hdr.serial;
 
 	call->ackr_first_seq = first_soft_ack;
 	call->ackr_prev_seq = prev_pkt;
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 813fd6888142..0fcf157aa09f 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -18,6 +18,21 @@
 #include "ar-internal.h"
 
 /*
+ * Return true if there's sufficient Tx queue space.
+ */
+static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win)
+{
+	unsigned int win_size =
+		min_t(unsigned int, call->tx_winsize,
+		      call->cong_cwnd + call->cong_extra);
+	rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack);
+
+	if (_tx_win)
+		*_tx_win = tx_win;
+	return call->tx_top - tx_win < win_size;
+}
+
+/*
  * 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,
@@ -26,9 +41,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
 {
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
-		if (call->tx_top - call->tx_hard_ack <
-		    min_t(unsigned int, call->tx_winsize,
-			  call->cong_cwnd + call->cong_extra))
+		if (rxrpc_check_tx_space(call, NULL))
 			return 0;
 
 		if (call->state >= RXRPC_CALL_COMPLETE)
@@ -49,7 +62,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,
  * 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_nonintr(struct rxrpc_sock *rx,
+static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,
 					    struct rxrpc_call *call)
 {
 	rxrpc_seq_t tx_start, tx_win;
@@ -58,8 +71,8 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
 
 	rtt = READ_ONCE(call->peer->rtt);
 	rtt2 = nsecs_to_jiffies64(rtt) * 2;
-	if (rtt2 < 1)
-		rtt2 = 1;
+	if (rtt2 < 2)
+		rtt2 = 2;
 
 	timeout = rtt2;
 	tx_start = READ_ONCE(call->tx_hard_ack);
@@ -68,16 +81,13 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
 		set_current_state(TASK_UNINTERRUPTIBLE);
 
 		tx_win = READ_ONCE(call->tx_hard_ack);
-		if (call->tx_top - tx_win <
-		    min_t(unsigned int, call->tx_winsize,
-			  call->cong_cwnd + call->cong_extra))
+		if (rxrpc_check_tx_space(call, &tx_win))
 			return 0;
 
 		if (call->state >= RXRPC_CALL_COMPLETE)
 			return call->error;
 
-		if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) &&
-		    timeout == 0 &&
+		if (timeout == 0 &&
 		    tx_win == tx_start && signal_pending(current))
 			return -EINTR;
 
@@ -92,6 +102,26 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
 }
 
 /*
+ * Wait for space to appear in the Tx queue uninterruptibly.
+ */
+static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,
+					    struct rxrpc_call *call,
+					    long *timeo)
+{
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (rxrpc_check_tx_space(call, NULL))
+			return 0;
+
+		if (call->state >= RXRPC_CALL_COMPLETE)
+			return call->error;
+
+		trace_rxrpc_transmit(call, rxrpc_transmit_wait);
+		*timeo = schedule_timeout(*timeo);
+	}
+}
+
+/*
  * wait for space to appear in the transmit/ACK window
  * - caller holds the socket locked
  */
@@ -108,10 +138,19 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,
 
 	add_wait_queue(&call->waitq, &myself);
 
-	if (waitall)
-		ret = rxrpc_wait_for_tx_window_nonintr(rx, call);
-	else
-		ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
+	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);
@@ -302,9 +341,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 
 			_debug("alloc");
 
-			if (call->tx_top - call->tx_hard_ack >=
-			    min_t(unsigned int, call->tx_winsize,
-				  call->cong_cwnd + call->cong_extra)) {
+			if (!rxrpc_check_tx_space(call, NULL)) {
 				ret = -EAGAIN;
 				if (msg->msg_flags & MSG_DONTWAIT)
 					goto maybe_error;
@@ -619,7 +656,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		.call.tx_total_len	= -1,
 		.call.user_call_ID	= 0,
 		.call.nr_timeouts	= 0,
-		.call.intr		= true,
+		.call.interruptibility	= RXRPC_INTERRUPTIBLE,
 		.abort_code		= 0,
 		.command		= RXRPC_CMD_SEND_DATA,
 		.exclusive		= false,