btrfs: count super block write errors in device instead of tracking folio error state

Currently the error status of super block write is tracked in page/folio
status bit Error. For that we need to keep the reference for the whole
duration of write and wait.

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 as it's the last mention
of the page Error state.

Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
Reviewed-by: David Sterba <[email protected]>
Signed-off-by: David Sterba <[email protected]>

Author: Matthew Wilcox (Oracle)

fs/btrfs/disk-io.c

@@ -3634,11 +3634,15 @@ static void btrfs_end_super_write(struct bio *bio)
 				"lost super block 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 the primary sb fails. */
+			if (bio->bi_opf & REQ_FUA)
+				atomic_add(BTRFS_SUPER_PRIMARY_WRITE_ERROR,
+					   &device->sb_write_errors);
+			else
+				atomic_inc(&device->sb_write_errors);
 		}
-
 		folio_unlock(fi.folio);
 		folio_put(fi.folio);
 	}
@@ -3742,10 +3746,11 @@ static int write_dev_supers(struct btrfs_device *device,
 	struct address_space *mapping = device->bdev->bd_inode->i_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_write_errors, 0);
+
 	if (max_mirrors == 0)
 		max_mirrors = BTRFS_SUPER_MIRROR_MAX;
 
@@ -3765,7 +3770,7 @@ 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_write_errors);
 			continue;
 		}
 		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
@@ -3785,14 +3790,11 @@ 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_write_errors);
 			continue;
 		}
 		ASSERT(folio_order(folio) == 0);
 
-		/* 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);
@@ -3820,16 +3822,17 @@ static int write_dev_supers(struct btrfs_device *device,
 		submit_bio(bio);
 
 		if (btrfs_advance_sb_log(device, i))
-			errors++;
+			atomic_inc(&device->sb_write_errors);
 	}
-	return errors < i ? 0 : -1;
+	return atomic_read(&device->sb_write_errors) < i ? 0 : -1;
 }
 
 /*
  * Wait for write completion of superblocks done by write_dev_supers,
  * @max_mirrors same for write and wait phases.
  *
- * Return number of errors when folio is not found or not marked up to date.
+ * Return -1 if primary super block write failed or when there were no super block
+ * copies written. Otherwise 0.
  */
 static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
 {
@@ -3860,30 +3863,19 @@ static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
 
 		folio = filemap_get_folio(device->bdev->bd_inode->i_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;
-		}
 		ASSERT(folio_order(folio) == 0);
 
 		/* Folio will be unlocked once the write 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);
 	}
 
-	/* log error, force error return */
+	errors += atomic_read(&device->sb_write_errors);
+	if (errors >= BTRFS_SUPER_PRIMARY_WRITE_ERROR)
+		primary_failed = true;
 	if (primary_failed) {
 		btrfs_err(device->fs_info, "error writing primary super block to device %llu",
 			  device->devid);

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

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)
 
+/* Special value encoding failure to write primary super block. */
+#define BTRFS_SUPER_PRIMARY_WRITE_ERROR		(INT_MAX / 2)
+
 struct btrfs_fs_devices;
 
 struct btrfs_device {
@@ -142,6 +145,12 @@ struct btrfs_device {
 	/* type and info about this device */
 	u64 type;
 
+	/*
+	 * Counter of super block write errors, values larger than
+	 * BTRFS_SUPER_PRIMARY_WRITE_ERROR encode primary super block write failure.
+	 */
+	atomic_t sb_write_errors;
+
 	/* minimal io size for this device */
 	u32 sector_size;