netfs: Fix missing wakeup after issuing writes

After dividing up a proposed write into subrequests, netfslib sets
NETFS_RREQ_ALL_QUEUED to indicate to the collector that it can move on to
the final cleanup once it has emptied the subrequest queues.

Now, whilst the collector will normally end up running at least once after
this bit is set just because it takes a while to process all the write
subrequests before the collector runs out of subrequests, there exists the
possibility that the issuing thread will be forced to sleep and the
collector thread will clean up all the subrequests before ALL_QUEUED gets
set.

In such a case, the collector thread will not get triggered again and will
never clear NETFS_RREQ_IN_PROGRESS thus leaving a request uncompleted and
causing a potential futute hang.

Fix this by scheduling the write collector if all the subrequest queues are
empty (and thus no writes pending issuance).

Note that we'd do this ideally before queuing the subrequest, but in the
case of buffered writeback, at least, we can't find out that we've run out
of folios until after we've called writeback_iter() and it has returned
NULL - at which point we might not actually have any subrequests still
under construction.

Fixes: 288ace2f57c9 ("netfs: New writeback implementation")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/3317784.1727880350@warthog.procyon.org.uk
cc: Jeff Layton <jlayton@kernel.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 6293f547e4c307a8370d54972782e12c577c275d..bf6d507578e531ff8d4ff1c5a8ec2e6682edf964 100644 (file)
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -508,6 +508,30 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
        return 0;
 }
 
+/*
+ * End the issuing of writes, letting the collector know we're done.
+ */
+static void netfs_end_issue_write(struct netfs_io_request *wreq)
+{
+       bool needs_poke = true;
+
+       smp_wmb(); /* Write subreq lists before ALL_QUEUED. */
+       set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags);
+
+       for (int s = 0; s < NR_IO_STREAMS; s++) {
+               struct netfs_io_stream *stream = &wreq->io_streams[s];
+
+               if (!stream->active)
+                       continue;
+               if (!list_empty(&stream->subrequests))
+                       needs_poke = false;
+               netfs_issue_write(wreq, stream);
+       }
+
+       if (needs_poke)
+               netfs_wake_write_collector(wreq, false);
+}
+
 /*
  * Write some of the pending data back to the server
  */
@@ -559,10 +583,7 @@ int netfs_writepages(struct address_space *mapping,
                        break;
        } while ((folio = writeback_iter(mapping, wbc, folio, &error)));
 
-       for (int s = 0; s < NR_IO_STREAMS; s++)
-               netfs_issue_write(wreq, &wreq->io_streams[s]);
-       smp_wmb(); /* Write lists before ALL_QUEUED. */
-       set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags);
+       netfs_end_issue_write(wreq);
 
        mutex_unlock(&ictx->wb_lock);
 
@@ -650,10 +671,7 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr
        if (writethrough_cache)
                netfs_write_folio(wreq, wbc, writethrough_cache);
 
-       netfs_issue_write(wreq, &wreq->io_streams[0]);
-       netfs_issue_write(wreq, &wreq->io_streams[1]);
-       smp_wmb(); /* Write lists before ALL_QUEUED. */
-       set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags);
+       netfs_end_issue_write(wreq);
 
        mutex_unlock(&ictx->wb_lock);
 
@@ -699,13 +717,7 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t
                        break;
        }
 
-       netfs_issue_write(wreq, upload);
-
-       smp_wmb(); /* Write lists before ALL_QUEUED. */
-       set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags);
-       if (list_empty(&upload->subrequests))
-               netfs_wake_write_collector(wreq, false);
-
+       netfs_end_issue_write(wreq);
        _leave(" = %d", error);
        return error;
 }