Count the number of superblock writeback errors in the btrfs_device.
That means we don't need the folio to stay around until it's waited for,
and can avoid the extra call to folio_get/put.
Also remove a mention of PageError in a comment.
Cc: Chris Mason <clm@xxxxxx>
Cc: Josef Bacik <josef@xxxxxxxxxxxxxx>
Cc: David Sterba <dsterba@xxxxxxxx>
Cc: linux-btrfs@xxxxxxxxxxxxxxx
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
---
fs/btrfs/disk-io.c | 44 ++++++++++++++++++--------------------------
fs/btrfs/extent_io.c | 2 +-
fs/btrfs/volumes.h | 5 +++++
3 files changed, 24 insertions(+), 27 deletions(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 18c47bf3f383..3fa073f969d8 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3635,11 +3635,15 @@ static void btrfs_end_super_write(struct bio *bio)
"lost sb write due to IO error on %s (%d)",
btrfs_dev_name(device),
blk_status_to_errno(bio->bi_status));
- folio_set_error(fi.folio);
btrfs_dev_stat_inc_and_print(device,
BTRFS_DEV_STAT_WRITE_ERRS);
+ /* Ensure failure if a primary sb fails */
+ if (bio->bi_opf & REQ_FUA)
+ atomic_set(&device->sb_wb_errors,
+ BTRFS_DEV_PRIMARY_ERROR);
+ else
+ atomic_inc(&device->sb_wb_errors);
}
-
folio_unlock(fi.folio);
folio_put(fi.folio);
}
@@ -3743,10 +3747,11 @@ static int write_dev_supers(struct btrfs_device *device,
struct address_space *mapping = device->bdev->bd_mapping;
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
int i;
- int errors = 0;
int ret;
u64 bytenr, bytenr_orig;
+ atomic_set(&device->sb_wb_errors, 0);
+
if (max_mirrors == 0)
max_mirrors = BTRFS_SUPER_MIRROR_MAX;
@@ -3766,7 +3771,7 @@ static int write_dev_supers(struct btrfs_device *device,
btrfs_err(device->fs_info,
"couldn't get super block location for mirror %d",
i);
- errors++;
+ atomic_inc(&device->sb_wb_errors);
continue;
}
if (bytenr + BTRFS_SUPER_INFO_SIZE >=
@@ -3785,13 +3790,10 @@ static int write_dev_supers(struct btrfs_device *device,
btrfs_err(device->fs_info,
"couldn't get super block page for bytenr %llu",
bytenr);
- errors++;
+ atomic_inc(&device->sb_wb_errors);
continue;
}
- /* Bump the refcount for wait_dev_supers() */
- folio_get(folio);
-
offset = offset_in_folio(folio, bytenr);
disk_super = folio_address(folio) + offset;
memcpy(disk_super, sb, BTRFS_SUPER_INFO_SIZE);
@@ -3819,9 +3821,9 @@ static int write_dev_supers(struct btrfs_device *device,
submit_bio(bio);
if (btrfs_advance_sb_log(device, i))
- errors++;
+ atomic_inc(&device->sb_wb_errors);
}
- return errors < i ? 0 : -1;
+ return atomic_read(&device->sb_wb_errors) < i ? 0 : -1;
}
/*
@@ -3860,27 +3862,17 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
folio = filemap_get_folio(device->bdev->bd_mapping,
bytenr >> PAGE_SHIFT);
- if (IS_ERR(folio)) {
- errors++;
- if (i == 0)
- primary_failed = true;
+ /* If the folio has been removed, then we know it completed */
+ if (IS_ERR(folio))
continue;
- }
- /* Folio is unlocked once the write completes */
+ /* Folio is unlocked once the IO completes */
folio_wait_locked(folio);
- if (folio_test_error(folio)) {
- errors++;
- if (i == 0)
- primary_failed = true;
- }
-
- /* Drop our reference */
- folio_put(folio);
-
- /* Drop the reference from the writing run */
folio_put(folio);
}
+ errors += atomic_read(&device->sb_wb_errors);
+ if (errors >= BTRFS_DEV_PRIMARY_ERROR)
+ primary_failed = true;
/* log error, force error return */
if (primary_failed) {
btrfs_err(device->fs_info, "error writing primary super block to device %llu",
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 7b10f47d8f83..7a1bd23833e5 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1602,7 +1602,7 @@ static void set_btree_ioerr(struct extent_buffer *eb)
* can be no longer dirty nor marked anymore for writeback (if a
* subsequent modification to the extent buffer didn't happen before the
* transaction commit), which makes filemap_fdata[write|wait]_range not
- * able to find the pages tagged with SetPageError at transaction
+ * able to find the pages which contain errors at transaction
* commit time. So if this happens we must abort the transaction,
* otherwise we commit a super block with btree roots that point to
* btree nodes/leafs whose content on disk is invalid - either garbage
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index cf555f5b47ce..cdab144410a8 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -92,6 +92,9 @@ enum btrfs_raid_types {
#define BTRFS_DEV_STATE_FLUSH_SENT (4)
#define BTRFS_DEV_STATE_NO_READA (5)
+/* We'll never have this many superblocks */
+#define BTRFS_DEV_PRIMARY_ERROR (INT_MAX / 2)
+
struct btrfs_fs_devices;
struct btrfs_device {
@@ -142,6 +145,8 @@ struct btrfs_device {
/* type and info about this device */
u64 type;
+ atomic_t sb_wb_errors;
+
/* minimal io size for this device */
u32 sector_size;
--
2.43.0
