fs: fix leaked psi pressure state

When psi annotations were added to to btrfs compression reads, the psi
state tracking over add_ra_bio_pages and btrfs_submit_compressed_read was
faulty.  A pressure state, once entered, is never left.  This results in
incorrectly elevated pressure, which triggers OOM kills.

pflags record the *previous* memstall state when we enter a new one.  The
code tried to initialize pflags to 1, and then optimize the leave call
when we either didn't enter a memstall, or were already inside a nested
stall.  However, there can be multiple PageWorkingset pages in the bio, at
which point it's that path itself that enters repeatedly and overwrites
pflags.  This causes us to miss the exit.

Enter the stall only once if needed, then unwind correctly.

erofs has the same problem, fix that up too.  And move the memstall exit
past submit_bio() to restore submit accounting originally added by
b8e24a9300b0 ("block: annotate refault stalls from IO submission").

Link: https://lkml.kernel.org/r/Y2UHRqthNUwuIQGS@cmpxchg.org
Fixes: 4088a47e78f9 ("btrfs: add manual PSI accounting for compressed reads")
Fixes: 99486c511f68 ("erofs: add manual PSI accounting for the compressed address space")
Fixes: 118f3663fbc6 ("block: remove PSI accounting from the bio layer")
Link: https://lore.kernel.org/r/d20a0a85-e415-cf78-27f9-77dd7a94bc8d@leemhuis.info/
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Thorsten Leemhuis <linux@leemhuis.info>
Tested-by: Thorsten Leemhuis <linux@leemhuis.info>
Cc: Chao Yu <chao@kernel.org>
Cc: Chris Mason <clm@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Sterba <dsterba@suse.com>
Cc: Gao Xiang <xiang@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 19 insertions, 13 deletions

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index f1f051ad3147..e6635fe70067 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -512,7 +512,7 @@ static u64 bio_end_offset(struct bio *bio)
 static noinline int add_ra_bio_pages(struct inode *inode,
 				     u64 compressed_end,
 				     struct compressed_bio *cb,
-				     unsigned long *pflags)
+				     int *memstall, unsigned long *pflags)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	unsigned long end_index;
@@ -581,8 +581,10 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			continue;
 		}
 
-		if (PageWorkingset(page))
+		if (!*memstall && PageWorkingset(page)) {
 			psi_memstall_enter(pflags);
+			*memstall = 1;
+		}
 
 		ret = set_page_extent_mapped(page);
 		if (ret < 0) {
@@ -670,8 +672,8 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	u64 em_len;
 	u64 em_start;
 	struct extent_map *em;
-	/* Initialize to 1 to make skip psi_memstall_leave unless needed */
-	unsigned long pflags = 1;
+	unsigned long pflags;
+	int memstall = 0;
 	blk_status_t ret;
 	int ret2;
 	int i;
@@ -727,7 +729,7 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		goto fail;
 	}
 
-	add_ra_bio_pages(inode, em_start + em_len, cb, &pflags);
+	add_ra_bio_pages(inode, em_start + em_len, cb, &memstall, &pflags);
 
 	/* include any pages we added in add_ra-bio_pages */
 	cb->len = bio->bi_iter.bi_size;
@@ -807,7 +809,7 @@ void btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		}
 	}
 
-	if (!pflags)
+	if (memstall)
 		psi_memstall_leave(&pflags);
 
 	if (refcount_dec_and_test(&cb->pending_ios))
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index c7f24fc7efd5..064a166324a7 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1412,8 +1412,8 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 	struct block_device *last_bdev;
 	unsigned int nr_bios = 0;
 	struct bio *bio = NULL;
-	/* initialize to 1 to make skip psi_memstall_leave unless needed */
-	unsigned long pflags = 1;
+	unsigned long pflags;
+	int memstall = 0;
 
 	bi_private = jobqueueset_init(sb, q, fgq, force_fg);
 	qtail[JQ_BYPASS] = &q[JQ_BYPASS]->head;
@@ -1463,14 +1463,18 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
 			if (bio && (cur != last_index + 1 ||
 				    last_bdev != mdev.m_bdev)) {
 submit_bio_retry:
-				if (!pflags)
-					psi_memstall_leave(&pflags);
 				submit_bio(bio);
+				if (memstall) {
+					psi_memstall_leave(&pflags);
+					memstall = 0;
+				}
 				bio = NULL;
 			}
 
-			if (unlikely(PageWorkingset(page)))
+			if (unlikely(PageWorkingset(page)) && !memstall) {
 				psi_memstall_enter(&pflags);
+				memstall = 1;
+			}
 
 			if (!bio) {
 				bio = bio_alloc(mdev.m_bdev, BIO_MAX_VECS,
@@ -1500,9 +1504,9 @@ submit_bio_retry:
 	} while (owned_head != Z_EROFS_PCLUSTER_TAIL);
 
 	if (bio) {
-		if (!pflags)
-			psi_memstall_leave(&pflags);
 		submit_bio(bio);
+		if (memstall)
+			psi_memstall_leave(&pflags);
 	}
 
 	/*