Merge patch series "netfs, cifs: Fixes to retry-related code"

David Howells <[email protected]> says:

Here are some miscellaneous fixes and changes for netfslib and cifs, if you
could consider pulling them.

Many of these were found because a bug in Samba was causing smbd to crash
and restart after about 1-2s and this was vigorously and abruptly
exercising the netfslib retry paths.

Subsequent testing of the cifs RDMA support showed up some more bugs, but
the fixes for those went via the cifs tree and have been removed from this set
as they're now upstream.

First, there are some netfs fixes:

 (1) Fix a hang due to missing case in final DIO read result collection
     not breaking out of a loop if the request finished, but there were no
     subrequests being processed and NETFS_RREQ_ALL_QUEUED wasn't yet set.

 (2) Fix a double put of the netfs_io_request struct if completion happened
     in the pause loop.

 (3) Provide some helpers to abstract out NETFS_RREQ_IN_PROGRESS flag
     wrangling.

 (4) Fix infinite looping in netfs_wait_for_pause/request() which wa caused
     by a loop waiting for NETFS_RREQ_ALL_QUEUED to get set - but which
     wouldn't get set until the looping function returned.  This uses patch
     (3) above.

 (5) Fix a ref leak on an extra subrequest inserted into a request's list
     of subreqs because more subreq records were needed for retrying than
     were needed for the original request (say, for instance, that the
     amount of cifs credit available was reduced and, subsequently, the ops
     had to be smaller).

Then a bunch of cifs fixes, some of which are from other people:

 (6-8) cifs: Fix various RPC callbacks to set NETFS_SREQ_NEED_RETRY if a
     subrequest fails retriably.

(10) Fix a warning in the workqueue code when reconnecting a channel.

Followed by some patches to deal with i_size handling:

(11) Fix the updating of i_size to use a lock to avoid a race between
     testing if we should have extended the file with a DIO write and
     changing i_size.

(12) A follow-up patch to (11) to merge the places in netfslib that update
     i_size on write.

And finally a couple of patches to improve tracing output, but that should
otherwise not affect functionality:

(13) Renumber the NETFS_RREQ_* flags to make the hex values easier to
     interpret by eye, including moving the main status flags down to the
     lowest bits, with IN_PROGRESS in bit 0.

(14) Update the tracepoints in a number of ways, including adding more
     tracepoints into the cifs read/write RPC callback so that differend
     MID_RESPONSE_* values can be differentiated.

* patches from https://lore.kernel.org/[email protected]:
  netfs: Update tracepoints in a number of ways
  netfs: Renumber the NETFS_RREQ_* flags to make traces easier to read
  netfs: Merge i_size update functions
  netfs: Fix i_size updating
  smb: client: set missing retry flag in cifs_writev_callback()
  smb: client: set missing retry flag in cifs_readv_callback()
  smb: client: set missing retry flag in smb2_writev_callback()
  netfs: Fix ref leak on inserted extra subreq in write retry
  netfs: Fix looping in wait functions
  netfs: Provide helpers to perform NETFS_RREQ_IN_PROGRESS flag wangling
  netfs: Fix double put of request
  netfs: Fix hang due to missing case in final DIO read result collection

Link: https://lore.kernel.org/[email protected]
Signed-off-by: Christian Brauner <[email protected]>

1 files changed, 31 insertions, 19 deletions

diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 43b67a28a8fa..20748bcfbf59 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -356,22 +356,22 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq,
 	DEFINE_WAIT(myself);
 
 	list_for_each_entry(subreq, &stream->subrequests, rreq_link) {
-		if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags))
+		if (!netfs_check_subreq_in_progress(subreq))
 			continue;
 
-		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_quiesce);
 		for (;;) {
 			prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
 
-			if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags))
+			if (!netfs_check_subreq_in_progress(subreq))
 				break;
 
 			trace_netfs_sreq(subreq, netfs_sreq_trace_wait_for);
 			schedule();
-			trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
 		}
 	}
 
+	trace_netfs_rreq(rreq, netfs_rreq_trace_waited_quiesce);
 	finish_wait(&rreq->waitq, &myself);
 }
 
@@ -381,7 +381,12 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq,
 static int netfs_collect_in_app(struct netfs_io_request *rreq,
 				bool (*collector)(struct netfs_io_request *rreq))
 {
-	bool need_collect = false, inactive = true;
+	bool need_collect = false, inactive = true, done = true;
+
+	if (!netfs_check_rreq_in_progress(rreq)) {
+		trace_netfs_rreq(rreq, netfs_rreq_trace_recollect);
+		return 1; /* Done */
+	}
 
 	for (int i = 0; i < NR_IO_STREAMS; i++) {
 		struct netfs_io_subrequest *subreq;
@@ -395,14 +400,16 @@ static int netfs_collect_in_app(struct netfs_io_request *rreq,
 						  struct netfs_io_subrequest,
 						  rreq_link);
 		if (subreq &&
-		    (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags) ||
+		    (!netfs_check_subreq_in_progress(subreq) ||
 		     test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags))) {
 			need_collect = true;
 			break;
 		}
+		if (subreq || !test_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags))
+			done = false;
 	}
 
-	if (!need_collect && !inactive)
+	if (!need_collect && !inactive && !done)
 		return 0; /* Sleep */
 
 	__set_current_state(TASK_RUNNING);
@@ -423,14 +430,13 @@ static int netfs_collect_in_app(struct netfs_io_request *rreq,
 /*
  * Wait for a request to complete, successfully or otherwise.
  */
-static ssize_t netfs_wait_for_request(struct netfs_io_request *rreq,
-				      bool (*collector)(struct netfs_io_request *rreq))
+static ssize_t netfs_wait_for_in_progress(struct netfs_io_request *rreq,
+					  bool (*collector)(struct netfs_io_request *rreq))
 {
 	DEFINE_WAIT(myself);
 	ssize_t ret;
 
 	for (;;) {
-		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
 		prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
 
 		if (!test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) {
@@ -440,18 +446,22 @@ static ssize_t netfs_wait_for_request(struct netfs_io_request *rreq,
 			case 1:
 				goto all_collected;
 			case 2:
+				if (!netfs_check_rreq_in_progress(rreq))
+					break;
+				cond_resched();
 				continue;
 			}
 		}
 
-		if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags))
+		if (!netfs_check_rreq_in_progress(rreq))
 			break;
 
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip);
 		schedule();
-		trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
 	}
 
 all_collected:
+	trace_netfs_rreq(rreq, netfs_rreq_trace_waited_ip);
 	finish_wait(&rreq->waitq, &myself);
 
 	ret = rreq->error;
@@ -478,12 +488,12 @@ all_collected:
 
 ssize_t netfs_wait_for_read(struct netfs_io_request *rreq)
 {
-	return netfs_wait_for_request(rreq, netfs_read_collection);
+	return netfs_wait_for_in_progress(rreq, netfs_read_collection);
 }
 
 ssize_t netfs_wait_for_write(struct netfs_io_request *rreq)
 {
-	return netfs_wait_for_request(rreq, netfs_write_collection);
+	return netfs_wait_for_in_progress(rreq, netfs_write_collection);
 }
 
 /*
@@ -494,10 +504,8 @@ static void netfs_wait_for_pause(struct netfs_io_request *rreq,
 {
 	DEFINE_WAIT(myself);
 
-	trace_netfs_rreq(rreq, netfs_rreq_trace_wait_pause);
-
 	for (;;) {
-		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_pause);
 		prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
 
 		if (!test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) {
@@ -507,19 +515,23 @@ static void netfs_wait_for_pause(struct netfs_io_request *rreq,
 			case 1:
 				goto all_collected;
 			case 2:
+				if (!netfs_check_rreq_in_progress(rreq) ||
+				    !test_bit(NETFS_RREQ_PAUSE, &rreq->flags))
+					break;
+				cond_resched();
 				continue;
 			}
 		}
 
-		if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags) ||
+		if (!netfs_check_rreq_in_progress(rreq) ||
 		    !test_bit(NETFS_RREQ_PAUSE, &rreq->flags))
 			break;
 
 		schedule();
-		trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
 	}
 
 all_collected:
+	trace_netfs_rreq(rreq, netfs_rreq_trace_waited_pause);
 	finish_wait(&rreq->waitq, &myself);
 }