iomap: protect read_bytes_pending with the state_lock

Perform one atomic operation (acquiring the spinlock) instead of two
(spinlock & atomic_sub) per read completion.

Link: https://lkml.kernel.org/r/20231004165317.1061855-3-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 25 insertions, 12 deletions

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 6e780ca64ce3..4a996c5327ef 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -29,9 +29,9 @@ typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length);
  * and I/O completions.
  */
 struct iomap_folio_state {
-	atomic_t		read_bytes_pending;
-	atomic_t		write_bytes_pending;
 	spinlock_t		state_lock;
+	unsigned int		read_bytes_pending;
+	atomic_t		write_bytes_pending;
 
 	/*
 	 * Each block has two bits in this bitmap:
@@ -183,7 +183,7 @@ static void ifs_free(struct folio *folio)
 
 	if (!ifs)
 		return;
-	WARN_ON_ONCE(atomic_read(&ifs->read_bytes_pending));
+	WARN_ON_ONCE(ifs->read_bytes_pending != 0);
 	WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending));
 	WARN_ON_ONCE(ifs_is_fully_uptodate(folio, ifs) !=
 			folio_test_uptodate(folio));
@@ -250,19 +250,29 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
 	*lenp = plen;
 }
 
-static void iomap_finish_folio_read(struct folio *folio, size_t offset,
+static void iomap_finish_folio_read(struct folio *folio, size_t off,
 		size_t len, int error)
 {
 	struct iomap_folio_state *ifs = folio->private;
+	bool uptodate = !error;
+	bool finished = true;
 
-	if (unlikely(error)) {
-		folio_clear_uptodate(folio);
-		folio_set_error(folio);
-	} else {
-		iomap_set_range_uptodate(folio, offset, len);
+	if (ifs) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&ifs->state_lock, flags);
+		if (!error)
+			uptodate = ifs_set_range_uptodate(folio, ifs, off, len);
+		ifs->read_bytes_pending -= len;
+		finished = !ifs->read_bytes_pending;
+		spin_unlock_irqrestore(&ifs->state_lock, flags);
 	}
 
-	if (!ifs || atomic_sub_and_test(len, &ifs->read_bytes_pending))
+	if (error)
+		folio_set_error(folio);
+	if (uptodate)
+		folio_mark_uptodate(folio);
+	if (finished)
 		folio_unlock(folio);
 }
 
@@ -360,8 +370,11 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
 	}
 
 	ctx->cur_folio_in_bio = true;
-	if (ifs)
-		atomic_add(plen, &ifs->read_bytes_pending);
+	if (ifs) {
+		spin_lock_irq(&ifs->state_lock);
+		ifs->read_bytes_pending += plen;
+		spin_unlock_irq(&ifs->state_lock);
+	}
 
 	sector = iomap_sector(iomap, pos);
 	if (!ctx->bio ||