[PATCH v5 22/40] netfs: Make the refcounting of netfs_begin_read() easier to use

[David Howells]

Make the refcounting of netfs_begin_read() easier to use by not eating the
caller's ref on the netfs_io_request it's given.  This makes it easier to
use when we need to look in the request struct after.

Signed-off-by: David Howells <dhowells at redhat.com>
Reviewed-by: Jeff Layton <jlayton at kernel.org>
cc: linux-cachefs at redhat.com
cc: linux-fsdevel at vger.kernel.org
cc: linux-mm at kvack.org
---
 fs/netfs/buffered_read.c     |  6 +++++-
 fs/netfs/io.c                | 28 +++++++++++++---------------
 include/trace/events/netfs.h |  9 +++++----
 3 files changed, 23 insertions(+), 20 deletions(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 751556faa70b..6b9a44cafbac 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -210,6 +210,7 @@ void netfs_readahead(struct readahead_control *ractl)
 		;
 
 	netfs_begin_read(rreq, false);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
 	return;
 
 cleanup_free:
@@ -260,7 +261,9 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
 			rreq->start, rreq->len);
 
-	return netfs_begin_read(rreq, true);
+	ret = netfs_begin_read(rreq, true);
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	return ret;
 
 discard:
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
@@ -429,6 +432,7 @@ int netfs_write_begin(struct netfs_inode *ctx,
 	ret = netfs_begin_read(rreq, true);
 	if (ret < 0)
 		goto error;
+	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
 
 have_folio:
 	ret = folio_wait_fscache_killable(folio);
diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index e228bfb530ea..e83ef5835d25 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -362,6 +362,7 @@ static void netfs_rreq_assess(struct netfs_io_request *rreq, bool was_async)
 
 	netfs_rreq_unlock_folios(rreq);
 
+	trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
 	wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
 
@@ -657,7 +658,6 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 
 	if (rreq->len == 0) {
 		pr_err("Zero-sized read [R=%x]\n", rreq->debug_id);
-		netfs_put_request(rreq, false, netfs_rreq_trace_put_zero_len);
 		return -EIO;
 	}
 
@@ -665,12 +665,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 
 	INIT_WORK(&rreq->work, netfs_rreq_work);
 
-	if (sync)
-		netfs_get_request(rreq, netfs_rreq_trace_get_hold);
-
 	/* Chop the read into slices according to what the cache and the netfs
 	 * want and submit each one.
 	 */
+	netfs_get_request(rreq, netfs_rreq_trace_get_for_outstanding);
 	atomic_set(&rreq->nr_outstanding, 1);
 	io_iter = rreq->io_iter;
 	do {
@@ -680,25 +678,25 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 	} while (rreq->submitted < rreq->len);
 
 	if (sync) {
-		/* Keep nr_outstanding incremented so that the ref always belongs to
-		 * us, and the service code isn't punted off to a random thread pool to
-		 * process.
+		/* Keep nr_outstanding incremented so that the ref always
+		 * belongs to us, and the service code isn't punted off to a
+		 * random thread pool to process.  Note that this might start
+		 * further work, such as writing to the cache.
 		 */
-		for (;;) {
-			wait_var_event(&rreq->nr_outstanding,
-				       atomic_read(&rreq->nr_outstanding) == 1);
+		wait_var_event(&rreq->nr_outstanding,
+			       atomic_read(&rreq->nr_outstanding) == 1);
+		if (atomic_dec_and_test(&rreq->nr_outstanding))
 			netfs_rreq_assess(rreq, false);
-			if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags))
-				break;
-			cond_resched();
-		}
+
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip);
+		wait_on_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS,
+			    TASK_UNINTERRUPTIBLE);
 
 		ret = rreq->error;
 		if (ret == 0 && rreq->submitted < rreq->len) {
 			trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
 			ret = -EIO;
 		}
-		netfs_put_request(rreq, false, netfs_rreq_trace_put_hold);
 	} else {
 		/* If we decrement nr_outstanding to 0, the ref belongs to us. */
 		if (atomic_dec_and_test(&rreq->nr_outstanding))
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 4ea4e34d279f..6daadf2aac8a 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -34,7 +34,9 @@
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
 	EM(netfs_rreq_trace_resubmit,		"RESUBMT")	\
 	EM(netfs_rreq_trace_unlock,		"UNLOCK ")	\
-	E_(netfs_rreq_trace_unmark,		"UNMARK ")
+	EM(netfs_rreq_trace_unmark,		"UNMARK ")	\
+	EM(netfs_rreq_trace_wait_ip,		"WAIT-IP")	\
+	E_(netfs_rreq_trace_wake_ip,		"WAKE-IP")
 
 #define netfs_sreq_sources					\
 	EM(NETFS_FILL_WITH_ZEROES,		"ZERO")		\
@@ -65,14 +67,13 @@
 	E_(netfs_fail_prepare_write,		"prep-write")
 
 #define netfs_rreq_ref_traces					\
-	EM(netfs_rreq_trace_get_hold,		"GET HOLD   ")	\
+	EM(netfs_rreq_trace_get_for_outstanding,"GET OUTSTND")	\
 	EM(netfs_rreq_trace_get_subreq,		"GET SUBREQ ")	\
 	EM(netfs_rreq_trace_put_complete,	"PUT COMPLT ")	\
 	EM(netfs_rreq_trace_put_discard,	"PUT DISCARD")	\
 	EM(netfs_rreq_trace_put_failed,		"PUT FAILED ")	\
-	EM(netfs_rreq_trace_put_hold,		"PUT HOLD   ")	\
+	EM(netfs_rreq_trace_put_return,		"PUT RETURN ")	\
 	EM(netfs_rreq_trace_put_subreq,		"PUT SUBREQ ")	\
-	EM(netfs_rreq_trace_put_zero_len,	"PUT ZEROLEN")	\
 	E_(netfs_rreq_trace_new,		"NEW        ")
 
 #define netfs_sreq_ref_traces					\