btrfs: introduce new "rescue=ignoremetacsums" mount option

Introduce "rescue=ignoremetacsums" to ignore metadata csums, all the
other metadata sanity checks are still kept as is.

This new mount option is mostly to allow the kernel to mount an
interrupted checksum conversion (at the metadata csum overwrite stage).

And since the main part of metadata sanity checks is inside
tree-checker, we shouldn't lose much safety, and the new mount option is
rescue mount option it requires full read-only mount.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

Author: adam900710

fs/btrfs/bio.c

@@ -732,7 +732,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 		 * point, so they are handled as part of the no-checksum case.
 		 */
 		if (inode && !(inode->flags & BTRFS_INODE_NODATASUM) &&
-		    !test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state) &&
+		    !test_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state) &&
 		    !btrfs_is_data_reloc_root(inode->root)) {
 			if (should_async_write(bbio) &&
 			    btrfs_wq_submit_bio(bbio, bioc, &smap, mirror_num))

fs/btrfs/disk-io.c

@@ -367,6 +367,7 @@ int btrfs_validate_extent_buffer(struct extent_buffer *eb,
 	u8 result[BTRFS_CSUM_SIZE];
 	const u8 *header_csum;
 	int ret = 0;
+	const bool ignore_csum = btrfs_test_opt(fs_info, IGNOREMETACSUMS);
 
 	ASSERT(check);
 
@@ -399,13 +400,16 @@ int btrfs_validate_extent_buffer(struct extent_buffer *eb,
 
 	if (memcmp(result, header_csum, csum_size) != 0) {
 		btrfs_warn_rl(fs_info,
-"checksum verify failed on logical %llu mirror %u wanted " CSUM_FMT " found " CSUM_FMT " level %d",
+"checksum verify failed on logical %llu mirror %u wanted " CSUM_FMT " found " CSUM_FMT " level %d%s",
 			      eb->start, eb->read_mirror,
 			      CSUM_FMT_VALUE(csum_size, header_csum),
 			      CSUM_FMT_VALUE(csum_size, result),
-			      btrfs_header_level(eb));
-		ret = -EUCLEAN;
-		goto out;
+			      btrfs_header_level(eb),
+			      ignore_csum ? ", ignored" : "");
+		if (!ignore_csum) {
+			ret = -EUCLEAN;
+			goto out;
+		}
 	}
 
 	if (found_level != check->level) {
@@ -2131,7 +2135,7 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root,
 	/* If we have IGNOREDATACSUMS skip loading these roots. */
 	if (objectid == BTRFS_CSUM_TREE_OBJECTID &&
 	    btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
-		set_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state);
+		set_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state);
 		return 0;
 	}
 
@@ -2184,7 +2188,7 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root,
 
 	if (!found || ret) {
 		if (objectid == BTRFS_CSUM_TREE_OBJECTID)
-			set_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state);
+			set_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state);
 
 		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS))
 			ret = ret ? ret : -ENOENT;
@@ -2865,6 +2869,8 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block
 
 	if (sb_rdonly(sb))
 		set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);
+	if (btrfs_test_opt(fs_info, IGNOREMETACSUMS))
+		set_bit(BTRFS_FS_STATE_SKIP_META_CSUMS, &fs_info->fs_state);
 
 	return btrfs_alloc_stripe_hash_table(fs_info);
 }

fs/btrfs/file-item.c

@@ -353,7 +353,7 @@ blk_status_t btrfs_lookup_bio_sums(struct btrfs_bio *bbio)
 	u32 bio_offset = 0;
 
 	if ((inode->flags & BTRFS_INODE_NODATASUM) ||
-	    test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state))
+	    test_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state))
 		return BLK_STS_OK;
 
 	/*

fs/btrfs/fs.h

@@ -98,7 +98,9 @@ enum {
 	/* The btrfs_fs_info created for self-tests */
 	BTRFS_FS_STATE_DUMMY_FS_INFO,
 
-	BTRFS_FS_STATE_NO_CSUMS,
+	/* Checksum errors are ignored. */
+	BTRFS_FS_STATE_NO_DATA_CSUMS,
+	BTRFS_FS_STATE_SKIP_META_CSUMS,
 
 	/* Indicates there was an error cleaning up a log tree. */
 	BTRFS_FS_STATE_LOG_CLEANUP_ERROR,
@@ -224,6 +226,7 @@ enum {
 	BTRFS_MOUNT_IGNOREDATACSUMS		= (1UL << 28),
 	BTRFS_MOUNT_NODISCARD			= (1UL << 29),
 	BTRFS_MOUNT_NOSPACECACHE		= (1UL << 30),
+	BTRFS_MOUNT_IGNOREMETACSUMS		= (1UL << 31),
 };
 
 /*

fs/btrfs/messages.c

@@ -20,7 +20,8 @@ static const char fs_state_chars[] = {
 	[BTRFS_FS_STATE_TRANS_ABORTED]		= 'A',
 	[BTRFS_FS_STATE_DEV_REPLACING]		= 'R',
 	[BTRFS_FS_STATE_DUMMY_FS_INFO]		= 0,
-	[BTRFS_FS_STATE_NO_CSUMS]		= 'C',
+	[BTRFS_FS_STATE_NO_DATA_CSUMS]		= 'C',
+	[BTRFS_FS_STATE_SKIP_META_CSUMS]	= 'S',
 	[BTRFS_FS_STATE_LOG_CLEANUP_ERROR]	= 'L',
 };
 

fs/btrfs/super.c

@@ -176,6 +176,7 @@ enum {
 	Opt_rescue_nologreplay,
 	Opt_rescue_ignorebadroots,
 	Opt_rescue_ignoredatacsums,
+	Opt_rescue_ignoremetacsums,
 	Opt_rescue_parameter_all,
 };
 
@@ -185,7 +186,9 @@ static const struct constant_table btrfs_parameter_rescue[] = {
 	{ "ignorebadroots", Opt_rescue_ignorebadroots },
 	{ "ibadroots", Opt_rescue_ignorebadroots },
 	{ "ignoredatacsums", Opt_rescue_ignoredatacsums },
+	{ "ignoremetacsums", Opt_rescue_ignoremetacsums},
 	{ "idatacsums", Opt_rescue_ignoredatacsums },
+	{ "imetacsums", Opt_rescue_ignoremetacsums},
 	{ "all", Opt_rescue_parameter_all },
 	{}
 };
@@ -571,8 +574,12 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		case Opt_rescue_ignoredatacsums:
 			btrfs_set_opt(ctx->mount_opt, IGNOREDATACSUMS);
 			break;
+		case Opt_rescue_ignoremetacsums:
+			btrfs_set_opt(ctx->mount_opt, IGNOREMETACSUMS);
+			break;
 		case Opt_rescue_parameter_all:
 			btrfs_set_opt(ctx->mount_opt, IGNOREDATACSUMS);
+			btrfs_set_opt(ctx->mount_opt, IGNOREMETACSUMS);
 			btrfs_set_opt(ctx->mount_opt, IGNOREBADROOTS);
 			btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
 			break;
@@ -647,7 +654,8 @@ bool btrfs_check_options(const struct btrfs_fs_info *info, unsigned long *mount_
 	if (!(flags & SB_RDONLY) &&
 	    (check_ro_option(info, *mount_opt, BTRFS_MOUNT_NOLOGREPLAY, "nologreplay") ||
 	     check_ro_option(info, *mount_opt, BTRFS_MOUNT_IGNOREBADROOTS, "ignorebadroots") ||
-	     check_ro_option(info, *mount_opt, BTRFS_MOUNT_IGNOREDATACSUMS, "ignoredatacsums")))
+	     check_ro_option(info, *mount_opt, BTRFS_MOUNT_IGNOREDATACSUMS, "ignoredatacsums") ||
+	     check_ro_option(info, *mount_opt, BTRFS_MOUNT_IGNOREMETACSUMS, "ignoremetacsums")))
 		ret = false;
 
 	if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE) &&
@@ -1063,6 +1071,8 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		print_rescue_option(seq, "ignorebadroots", &printed);
 	if (btrfs_test_opt(info, IGNOREDATACSUMS))
 		print_rescue_option(seq, "ignoredatacsums", &printed);
+	if (btrfs_test_opt(info, IGNOREMETACSUMS))
+		print_rescue_option(seq, "ignoremetacsums", &printed);
 	if (btrfs_test_opt(info, FLUSHONCOMMIT))
 		seq_puts(seq, ",flushoncommit");
 	if (btrfs_test_opt(info, DISCARD_SYNC))
@@ -1420,6 +1430,7 @@ static void btrfs_emit_options(struct btrfs_fs_info *info,
 	btrfs_info_if_set(info, old, USEBACKUPROOT, "trying to use backup root at mount time");
 	btrfs_info_if_set(info, old, IGNOREBADROOTS, "ignoring bad roots");
 	btrfs_info_if_set(info, old, IGNOREDATACSUMS, "ignoring data csums");
+	btrfs_info_if_set(info, old, IGNOREMETACSUMS, "ignoring meta csums");
 
 	btrfs_info_if_unset(info, old, NODATACOW, "setting datacow");
 	btrfs_info_if_unset(info, old, SSD, "not using ssd optimizations");

fs/btrfs/sysfs.c

@@ -385,6 +385,7 @@ static const char *rescue_opts[] = {
 	"nologreplay",
 	"ignorebadroots",
 	"ignoredatacsums",
+	"ignoremetacsums",
 	"all",
 };
 

fs/btrfs/zoned.c

@@ -1844,7 +1844,7 @@ void btrfs_finish_ordered_zoned(struct btrfs_ordered_extent *ordered)
 	 * here so that we don't attempt to log the csums later.
 	 */
 	if ((inode->flags & BTRFS_INODE_NODATASUM) ||
-	    test_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state)) {
+	    test_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state)) {
 		while ((sum = list_first_entry_or_null(&ordered->list,
 						       typeof(*sum), list))) {
 			list_del(&sum->list);