1 files changed, 368 insertions, 257 deletions

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f05cce7c8b8d..1999533b52be 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -34,6 +34,7 @@
 #include "disk-io.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
+#include "direct-io.h"
 #include "props.h"
 #include "xattr.h"
 #include "bio.h"
@@ -81,12 +82,15 @@ struct btrfs_fs_context {
 	u32 commit_interval;
 	u32 metadata_ratio;
 	u32 thread_pool_size;
-	unsigned long mount_opt;
+	unsigned long long mount_opt;
 	unsigned long compress_type:4;
-	unsigned int compress_level;
+	int compress_level;
 	refcount_t refs;
 };
 
+static void btrfs_emit_options(struct btrfs_fs_info *info,
+			       struct btrfs_fs_context *old);
+
 enum {
 	Opt_acl,
 	Opt_clear_cache,
@@ -124,18 +128,13 @@ enum {
 	/* Rescue options */
 	Opt_rescue,
 	Opt_usebackuproot,
-	Opt_nologreplay,
-	Opt_ignorebadroots,
-	Opt_ignoredatacsums,
-	Opt_rescue_all,
 
 	/* Debugging options */
 	Opt_enospc_debug,
 #ifdef CONFIG_BTRFS_DEBUG
 	Opt_fragment, Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all,
-#endif
-#ifdef CONFIG_BTRFS_FS_REF_VERIFY
 	Opt_ref_verify,
+	Opt_ref_tracker,
 #endif
 	Opt_err,
 };
@@ -178,6 +177,8 @@ enum {
 	Opt_rescue_nologreplay,
 	Opt_rescue_ignorebadroots,
 	Opt_rescue_ignoredatacsums,
+	Opt_rescue_ignoremetacsums,
+	Opt_rescue_ignoresuperflags,
 	Opt_rescue_parameter_all,
 };
 
@@ -187,7 +188,11 @@ static const struct constant_table btrfs_parameter_rescue[] = {
 	{ "ignorebadroots", Opt_rescue_ignorebadroots },
 	{ "ibadroots", Opt_rescue_ignorebadroots },
 	{ "ignoredatacsums", Opt_rescue_ignoredatacsums },
+	{ "ignoremetacsums", Opt_rescue_ignoremetacsums},
+	{ "ignoresuperflags", Opt_rescue_ignoresuperflags},
 	{ "idatacsums", Opt_rescue_ignoredatacsums },
+	{ "imetacsums", Opt_rescue_ignoremetacsums},
+	{ "isuperflags", Opt_rescue_ignoresuperflags},
 	{ "all", Opt_rescue_parameter_all },
 	{}
 };
@@ -242,8 +247,6 @@ static const struct fs_parameter_spec btrfs_fs_parameters[] = {
 
 	/* Rescue options. */
 	fsparam_enum("rescue", Opt_rescue, btrfs_parameter_rescue),
-	/* Deprecated, with alias rescue=nologreplay */
-	__fsparam(NULL, "nologreplay", Opt_nologreplay, fs_param_deprecated, NULL),
 	/* Deprecated, with alias rescue=usebackuproot */
 	__fsparam(NULL, "usebackuproot", Opt_usebackuproot, fs_param_deprecated, NULL),
 	/* For compatibility only, alias for "rescue=nologreplay". */
@@ -253,17 +256,85 @@ static const struct fs_parameter_spec btrfs_fs_parameters[] = {
 	fsparam_flag_no("enospc_debug", Opt_enospc_debug),
 #ifdef CONFIG_BTRFS_DEBUG
 	fsparam_enum("fragment", Opt_fragment, btrfs_parameter_fragment),
-#endif
-#ifdef CONFIG_BTRFS_FS_REF_VERIFY
+	fsparam_flag("ref_tracker", Opt_ref_tracker),
 	fsparam_flag("ref_verify", Opt_ref_verify),
 #endif
 	{}
 };
 
-/* No support for restricting writes to btrfs devices yet... */
-static inline blk_mode_t btrfs_open_mode(struct fs_context *fc)
+static bool btrfs_match_compress_type(const char *string, const char *type, bool may_have_level)
 {
-	return sb_open_mode(fc->sb_flags) & ~BLK_OPEN_RESTRICT_WRITES;
+	const int len = strlen(type);
+
+	return (strncmp(string, type, len) == 0) &&
+		((may_have_level && string[len] == ':') || string[len] == '\0');
+}
+
+static int btrfs_parse_compress(struct btrfs_fs_context *ctx,
+				const struct fs_parameter *param, int opt)
+{
+	const char *string = param->string;
+	int ret;
+
+	/*
+	 * Provide the same semantics as older kernels that don't use fs
+	 * context, specifying the "compress" option clears "force-compress"
+	 * without the need to pass "compress-force=[no|none]" before
+	 * specifying "compress".
+	 */
+	if (opt != Opt_compress_force && opt != Opt_compress_force_type)
+		btrfs_clear_opt(ctx->mount_opt, FORCE_COMPRESS);
+
+	if (opt == Opt_compress || opt == Opt_compress_force) {
+		ctx->compress_type = BTRFS_COMPRESS_ZLIB;
+		ctx->compress_level = BTRFS_ZLIB_DEFAULT_LEVEL;
+		btrfs_set_opt(ctx->mount_opt, COMPRESS);
+		btrfs_clear_opt(ctx->mount_opt, NODATACOW);
+		btrfs_clear_opt(ctx->mount_opt, NODATASUM);
+	} else if (btrfs_match_compress_type(string, "zlib", true)) {
+		ctx->compress_type = BTRFS_COMPRESS_ZLIB;
+		ret = btrfs_compress_str2level(BTRFS_COMPRESS_ZLIB, string + 4,
+					       &ctx->compress_level);
+		if (ret < 0)
+			goto error;
+		btrfs_set_opt(ctx->mount_opt, COMPRESS);
+		btrfs_clear_opt(ctx->mount_opt, NODATACOW);
+		btrfs_clear_opt(ctx->mount_opt, NODATASUM);
+	} else if (btrfs_match_compress_type(string, "lzo", true)) {
+		ctx->compress_type = BTRFS_COMPRESS_LZO;
+		ret = btrfs_compress_str2level(BTRFS_COMPRESS_LZO, string + 3,
+					       &ctx->compress_level);
+		if (ret < 0)
+			goto error;
+		if (string[3] == ':' && string[4])
+			btrfs_warn(NULL, "Compression level ignored for LZO");
+		btrfs_set_opt(ctx->mount_opt, COMPRESS);
+		btrfs_clear_opt(ctx->mount_opt, NODATACOW);
+		btrfs_clear_opt(ctx->mount_opt, NODATASUM);
+	} else if (btrfs_match_compress_type(string, "zstd", true)) {
+		ctx->compress_type = BTRFS_COMPRESS_ZSTD;
+		ret = btrfs_compress_str2level(BTRFS_COMPRESS_ZSTD, string + 4,
+					       &ctx->compress_level);
+		if (ret < 0)
+			goto error;
+		btrfs_set_opt(ctx->mount_opt, COMPRESS);
+		btrfs_clear_opt(ctx->mount_opt, NODATACOW);
+		btrfs_clear_opt(ctx->mount_opt, NODATASUM);
+	} else if (btrfs_match_compress_type(string, "no", false) ||
+		   btrfs_match_compress_type(string, "none", false)) {
+		ctx->compress_level = 0;
+		ctx->compress_type = 0;
+		btrfs_clear_opt(ctx->mount_opt, COMPRESS);
+		btrfs_clear_opt(ctx->mount_opt, FORCE_COMPRESS);
+	} else {
+		ret = -EINVAL;
+		goto error;
+	}
+	return 0;
+error:
+	btrfs_err(NULL, "failed to parse compression option '%s'", string);
+	return ret;
+
 }
 
 static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
@@ -302,10 +373,9 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		break;
 	case Opt_device: {
 		struct btrfs_device *device;
-		blk_mode_t mode = btrfs_open_mode(fc);
 
 		mutex_lock(&uuid_mutex);
-		device = btrfs_scan_one_device(param->string, mode, false);
+		device = btrfs_scan_one_device(param->string, false);
 		mutex_unlock(&uuid_mutex);
 		if (IS_ERR(device))
 			return PTR_ERR(device);
@@ -335,44 +405,8 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		fallthrough;
 	case Opt_compress:
 	case Opt_compress_type:
-		if (opt == Opt_compress || opt == Opt_compress_force) {
-			ctx->compress_type = BTRFS_COMPRESS_ZLIB;
-			ctx->compress_level = BTRFS_ZLIB_DEFAULT_LEVEL;
-			btrfs_set_opt(ctx->mount_opt, COMPRESS);
-			btrfs_clear_opt(ctx->mount_opt, NODATACOW);
-			btrfs_clear_opt(ctx->mount_opt, NODATASUM);
-		} else if (strncmp(param->string, "zlib", 4) == 0) {
-			ctx->compress_type = BTRFS_COMPRESS_ZLIB;
-			ctx->compress_level =
-				btrfs_compress_str2level(BTRFS_COMPRESS_ZLIB,
-							 param->string + 4);
-			btrfs_set_opt(ctx->mount_opt, COMPRESS);
-			btrfs_clear_opt(ctx->mount_opt, NODATACOW);
-			btrfs_clear_opt(ctx->mount_opt, NODATASUM);
-		} else if (strncmp(param->string, "lzo", 3) == 0) {
-			ctx->compress_type = BTRFS_COMPRESS_LZO;
-			ctx->compress_level = 0;
-			btrfs_set_opt(ctx->mount_opt, COMPRESS);
-			btrfs_clear_opt(ctx->mount_opt, NODATACOW);
-			btrfs_clear_opt(ctx->mount_opt, NODATASUM);
-		} else if (strncmp(param->string, "zstd", 4) == 0) {
-			ctx->compress_type = BTRFS_COMPRESS_ZSTD;
-			ctx->compress_level =
-				btrfs_compress_str2level(BTRFS_COMPRESS_ZSTD,
-							 param->string + 4);
-			btrfs_set_opt(ctx->mount_opt, COMPRESS);
-			btrfs_clear_opt(ctx->mount_opt, NODATACOW);
-			btrfs_clear_opt(ctx->mount_opt, NODATASUM);
-		} else if (strncmp(param->string, "no", 2) == 0) {
-			ctx->compress_level = 0;
-			ctx->compress_type = 0;
-			btrfs_clear_opt(ctx->mount_opt, COMPRESS);
-			btrfs_clear_opt(ctx->mount_opt, FORCE_COMPRESS);
-		} else {
-			btrfs_err(NULL, "unrecognized compression value %s",
-				  param->string);
+		if (btrfs_parse_compress(ctx, param, opt))
 			return -EINVAL;
-		}
 		break;
 	case Opt_ssd:
 		if (result.negated) {
@@ -436,11 +470,6 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		else
 			btrfs_clear_opt(ctx->mount_opt, NOTREELOG);
 		break;
-	case Opt_nologreplay:
-		btrfs_warn(NULL,
-		"'nologreplay' is deprecated, use 'rescue=nologreplay' instead");
-		btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
-		break;
 	case Opt_norecovery:
 		btrfs_info(NULL,
 "'norecovery' is for compatibility only, recommended to use 'rescue=nologreplay'");
@@ -556,6 +585,10 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		break;
 	case Opt_commit_interval:
 		ctx->commit_interval = result.uint_32;
+		if (ctx->commit_interval > BTRFS_WARNING_COMMIT_INTERVAL) {
+			btrfs_warn(NULL, "excessive commit interval %u, use with care",
+				   ctx->commit_interval);
+		}
 		if (ctx->commit_interval == 0)
 			ctx->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
 		break;
@@ -573,8 +606,16 @@ 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_ignoresuperflags:
+			btrfs_set_opt(ctx->mount_opt, IGNORESUPERFLAGS);
+			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, IGNORESUPERFLAGS);
 			btrfs_set_opt(ctx->mount_opt, IGNOREBADROOTS);
 			btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
 			break;
@@ -603,11 +644,12 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 			return -EINVAL;
 		}
 		break;
-#endif
-#ifdef CONFIG_BTRFS_FS_REF_VERIFY
 	case Opt_ref_verify:
 		btrfs_set_opt(ctx->mount_opt, REF_VERIFY);
 		break;
+	case Opt_ref_tracker:
+		btrfs_set_opt(ctx->mount_opt, REF_TRACKER);
+		break;
 #endif
 	default:
 		btrfs_err(NULL, "unrecognized mount option '%s'", param->key);
@@ -629,8 +671,8 @@ static void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info)
 	btrfs_clear_opt(fs_info->mount_opt, NOSPACECACHE);
 }
 
-static bool check_ro_option(struct btrfs_fs_info *fs_info,
-			    unsigned long mount_opt, unsigned long opt,
+static bool check_ro_option(const struct btrfs_fs_info *fs_info,
+			    unsigned long long mount_opt, unsigned long long opt,
 			    const char *opt_name)
 {
 	if (mount_opt & opt) {
@@ -641,7 +683,8 @@ static bool check_ro_option(struct btrfs_fs_info *fs_info,
 	return false;
 }
 
-bool btrfs_check_options(struct btrfs_fs_info *info, unsigned long *mount_opt,
+bool btrfs_check_options(const struct btrfs_fs_info *info,
+			 unsigned long long *mount_opt,
 			 unsigned long flags)
 {
 	bool ret = true;
@@ -649,7 +692,9 @@ bool btrfs_check_options(struct btrfs_fs_info *info, unsigned long *mount_opt,
 	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") ||
+	     check_ro_option(info, *mount_opt, BTRFS_MOUNT_IGNORESUPERFLAGS, "ignoresuperflags")))
 		ret = false;
 
 	if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE) &&
@@ -668,10 +713,10 @@ bool btrfs_check_options(struct btrfs_fs_info *info, unsigned long *mount_opt,
 		ret = false;
 
 	if (!test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state)) {
-		if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE))
-			btrfs_info(info, "disk space caching is enabled");
-		if (btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE))
-			btrfs_info(info, "using free-space-tree");
+		if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE)) {
+			btrfs_warn(info,
+"space cache v1 is being deprecated and will be removed in a future release, please use -o space_cache=v2");
+		}
 	}
 
 	return ret;
@@ -762,17 +807,15 @@ char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
 	struct btrfs_root_ref *root_ref;
 	struct btrfs_inode_ref *inode_ref;
 	struct btrfs_key key;
-	struct btrfs_path *path = NULL;
+	BTRFS_PATH_AUTO_FREE(path);
 	char *name = NULL, *ptr;
 	u64 dirid;
 	int len;
 	int ret;
 
 	path = btrfs_alloc_path();
-	if (!path) {
-		ret = -ENOMEM;
-		goto err;
-	}
+	if (!path)
+		return ERR_PTR(-ENOMEM);
 
 	name = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (!name) {
@@ -860,7 +903,6 @@ char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
 		fs_root = NULL;
 	}
 
-	btrfs_free_path(path);
 	if (ptr == name + PATH_MAX - 1) {
 		name[0] = '/';
 		name[1] = '\0';
@@ -871,7 +913,6 @@ char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
 
 err:
 	btrfs_put_root(fs_root);
-	btrfs_free_path(path);
 	kfree(name);
 	return ERR_PTR(ret);
 }
@@ -880,7 +921,7 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec
 {
 	struct btrfs_root *root = fs_info->tree_root;
 	struct btrfs_dir_item *di;
-	struct btrfs_path *path;
+	BTRFS_PATH_AUTO_FREE(path);
 	struct btrfs_key location;
 	struct fscrypt_str name = FSTR_INIT("default", 7);
 	u64 dir_id;
@@ -897,7 +938,6 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec
 	dir_id = btrfs_super_root_dir(fs_info->super_copy);
 	di = btrfs_lookup_dir_item(NULL, root, path, dir_id, &name, 0);
 	if (IS_ERR(di)) {
-		btrfs_free_path(path);
 		return PTR_ERR(di);
 	}
 	if (!di) {
@@ -906,59 +946,58 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec
 		 * it's always been there, but don't freak out, just try and
 		 * mount the top-level subvolume.
 		 */
-		btrfs_free_path(path);
 		*objectid = BTRFS_FS_TREE_OBJECTID;
 		return 0;
 	}
 
 	btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location);
-	btrfs_free_path(path);
 	*objectid = location.objectid;
 	return 0;
 }
 
 static int btrfs_fill_super(struct super_block *sb,
-			    struct btrfs_fs_devices *fs_devices,
-			    void *data)
+			    struct btrfs_fs_devices *fs_devices)
 {
-	struct inode *inode;
+	struct btrfs_inode *inode;
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
-	int err;
+	int ret;
 
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_magic = BTRFS_SUPER_MAGIC;
 	sb->s_op = &btrfs_super_ops;
-	sb->s_d_op = &btrfs_dentry_operations;
+	set_default_d_op(sb, &btrfs_dentry_operations);
 	sb->s_export_op = &btrfs_export_ops;
 #ifdef CONFIG_FS_VERITY
 	sb->s_vop = &btrfs_verityops;
 #endif
 	sb->s_xattr = btrfs_xattr_handlers;
 	sb->s_time_gran = 1;
-	sb->s_iflags |= SB_I_CGROUPWB;
+	sb->s_iflags |= SB_I_CGROUPWB | SB_I_ALLOW_HSM;
 
-	err = super_setup_bdi(sb);
-	if (err) {
+	ret = super_setup_bdi(sb);
+	if (ret) {
 		btrfs_err(fs_info, "super_setup_bdi failed");
-		return err;
+		return ret;
 	}
 
-	err = open_ctree(sb, fs_devices, (char *)data);
-	if (err) {
-		btrfs_err(fs_info, "open_ctree failed");
-		return err;
+	ret = open_ctree(sb, fs_devices);
+	if (ret) {
+		btrfs_err(fs_info, "open_ctree failed: %d", ret);
+		return ret;
 	}
 
-	inode = btrfs_iget(sb, BTRFS_FIRST_FREE_OBJECTID, fs_info->fs_root);
+	btrfs_emit_options(fs_info, NULL);
+
+	inode = btrfs_iget(BTRFS_FIRST_FREE_OBJECTID, fs_info->fs_root);
 	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
-		btrfs_handle_fs_error(fs_info, err, NULL);
+		ret = PTR_ERR(inode);
+		btrfs_handle_fs_error(fs_info, ret, NULL);
 		goto fail_close;
 	}
 
-	sb->s_root = d_make_root(inode);
+	sb->s_root = d_make_root(&inode->vfs_inode);
 	if (!sb->s_root) {
-		err = -ENOMEM;
+		ret = -ENOMEM;
 		goto fail_close;
 	}
 
@@ -967,7 +1006,7 @@ static int btrfs_fill_super(struct super_block *sb,
 
 fail_close:
 	close_ctree(fs_info);
-	return err;
+	return ret;
 }
 
 int btrfs_sync_fs(struct super_block *sb, int wait)
@@ -983,7 +1022,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 		return 0;
 	}
 
-	btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
+	btrfs_wait_ordered_roots(fs_info, U64_MAX, NULL);
 
 	trans = btrfs_attach_transaction_barrier(root);
 	if (IS_ERR(trans)) {
@@ -1046,7 +1085,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 			seq_printf(seq, ",compress-force=%s", compress_type);
 		else
 			seq_printf(seq, ",compress=%s", compress_type);
-		if (info->compress_level)
+		if (info->compress_level && info->compress_type != BTRFS_COMPRESS_LZO)
 			seq_printf(seq, ":%d", info->compress_level);
 	}
 	if (btrfs_test_opt(info, NOSSD))
@@ -1065,6 +1104,10 @@ 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, IGNORESUPERFLAGS))
+		print_rescue_option(seq, "ignoresuperflags", &printed);
 	if (btrfs_test_opt(info, FLUSHONCOMMIT))
 		seq_puts(seq, ",flushoncommit");
 	if (btrfs_test_opt(info, DISCARD_SYNC))
@@ -1105,12 +1148,13 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 #endif
 	if (btrfs_test_opt(info, REF_VERIFY))
 		seq_puts(seq, ",ref_verify");
+	if (btrfs_test_opt(info, REF_TRACKER))
+		seq_puts(seq, ",ref_tracker");
 	seq_printf(seq, ",subvolid=%llu", btrfs_root_id(BTRFS_I(d_inode(dentry))->root));
 	subvol_name = btrfs_get_subvol_name_from_objectid(info,
 			btrfs_root_id(BTRFS_I(d_inode(dentry))->root));
 	if (!IS_ERR(subvol_name)) {
-		seq_puts(seq, ",subvol=");
-		seq_escape(seq, subvol_name, " \t\n\\");
+		seq_show_option(seq, "subvol", subvol_name);
 		kfree(subvol_name);
 	}
 	return 0;
@@ -1119,11 +1163,11 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 /*
  * subvolumes are identified by ino 256
  */
-static inline int is_subvolume_inode(struct inode *inode)
+static inline bool is_subvolume_inode(struct inode *inode)
 {
 	if (inode && inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)
-		return 1;
-	return 0;
+		return true;
+	return false;
 }
 
 static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid,
@@ -1213,7 +1257,7 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
 }
 
 static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info,
-				       unsigned long old_opts, int flags)
+				       unsigned long long old_opts, int flags)
 {
 	if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
 	    (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
@@ -1227,12 +1271,12 @@ static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info,
 }
 
 static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
-					 unsigned long old_opts)
+					 unsigned long long old_opts)
 {
 	const bool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE);
 
 	/*
-	 * We need to cleanup all defragable inodes if the autodefragment is
+	 * We need to cleanup all defraggable inodes if the autodefragment is
 	 * close or the filesystem is read only.
 	 */
 	if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
@@ -1403,7 +1447,7 @@ static void btrfs_emit_options(struct btrfs_fs_info *info,
 {
 	btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum");
 	btrfs_info_if_set(info, old, DEGRADED, "allowing degraded mounts");
-	btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum");
+	btrfs_info_if_set(info, old, NODATACOW, "setting nodatacow");
 	btrfs_info_if_set(info, old, SSD, "enabling ssd optimizations");
 	btrfs_info_if_set(info, old, SSD_SPREAD, "using spread ssd allocation scheme");
 	btrfs_info_if_set(info, old, NOBARRIER, "turning off barriers");
@@ -1422,11 +1466,14 @@ 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_set(info, old, IGNORESUPERFLAGS, "ignoring unknown super block flags");
 
+	btrfs_info_if_unset(info, old, NODATASUM, "setting datasum");
 	btrfs_info_if_unset(info, old, NODATACOW, "setting datacow");
 	btrfs_info_if_unset(info, old, SSD, "not using ssd optimizations");
 	btrfs_info_if_unset(info, old, SSD_SPREAD, "not using spread ssd allocation scheme");
-	btrfs_info_if_unset(info, old, NOBARRIER, "turning off barriers");
+	btrfs_info_if_unset(info, old, NOBARRIER, "turning on barriers");
 	btrfs_info_if_unset(info, old, NOTREELOG, "enabling tree log");
 	btrfs_info_if_unset(info, old, SPACE_CACHE, "disabling disk space caching");
 	btrfs_info_if_unset(info, old, FREE_SPACE_TREE, "disabling free space tree");
@@ -1473,8 +1520,7 @@ static int btrfs_reconfigure(struct fs_context *fc)
 	sync_filesystem(sb);
 	set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
 
-	if (!mount_reconfigure &&
-	    !btrfs_check_options(fs_info, &ctx->mount_opt, fc->sb_flags))
+	if (!btrfs_check_options(fs_info, &ctx->mount_opt, fc->sb_flags))
 		return -EINVAL;
 
 	ret = btrfs_check_features(fs_info, !(fc->sb_flags & SB_RDONLY));
@@ -1564,7 +1610,7 @@ static inline void btrfs_descending_sort_devices(
 static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 					      u64 *free_bytes)
 {
-	struct btrfs_device_info *devices_info;
+	struct btrfs_device_info AUTO_KFREE(devices_info);
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
 	u64 type;
@@ -1662,7 +1708,6 @@ static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 		nr_devices--;
 	}
 
-	kfree(devices_info);
 	*free_bytes = avail_space;
 	return 0;
 }
@@ -1800,10 +1845,9 @@ static int btrfs_get_tree_super(struct fs_context *fc)
 	struct btrfs_fs_info *fs_info = fc->s_fs_info;
 	struct btrfs_fs_context *ctx = fc->fs_private;
 	struct btrfs_fs_devices *fs_devices = NULL;
-	struct block_device *bdev;
 	struct btrfs_device *device;
 	struct super_block *sb;
-	blk_mode_t mode = btrfs_open_mode(fc);
+	blk_mode_t mode = sb_open_mode(fc->sb_flags);
 	int ret;
 
 	btrfs_ctx_to_info(fs_info, ctx);
@@ -1813,69 +1857,103 @@ static int btrfs_get_tree_super(struct fs_context *fc)
 	 * With 'true' passed to btrfs_scan_one_device() (mount time) we expect
 	 * either a valid device or an error.
 	 */
-	device = btrfs_scan_one_device(fc->source, mode, true);
+	device = btrfs_scan_one_device(fc->source, true);
 	ASSERT(device != NULL);
 	if (IS_ERR(device)) {
 		mutex_unlock(&uuid_mutex);
 		return PTR_ERR(device);
 	}
-
 	fs_devices = device->fs_devices;
+	/*
+	 * We cannot hold uuid_mutex calling sget_fc(), it will lead to a
+	 * locking order reversal with s_umount.
+	 *
+	 * So here we increase the holding number of fs_devices, this will ensure
+	 * the fs_devices itself won't be freed.
+	 */
+	btrfs_fs_devices_inc_holding(fs_devices);
 	fs_info->fs_devices = fs_devices;
-
-	ret = btrfs_open_devices(fs_devices, mode, &btrfs_fs_type);
 	mutex_unlock(&uuid_mutex);
-	if (ret)
-		return ret;
 
-	if (!(fc->sb_flags & SB_RDONLY) && fs_devices->rw_devices == 0) {
-		ret = -EACCES;
-		goto error;
-	}
-
-	bdev = fs_devices->latest_dev->bdev;
 
-	/*
-	 * From now on the error handling is not straightforward.
-	 *
-	 * If successful, this will transfer the fs_info into the super block,
-	 * and fc->s_fs_info will be NULL.  However if there's an existing
-	 * super, we'll still have fc->s_fs_info populated.  If we error
-	 * completely out it'll be cleaned up when we drop the fs_context,
-	 * otherwise it's tied to the lifetime of the super_block.
-	 */
 	sb = sget_fc(fc, btrfs_fc_test_super, set_anon_super_fc);
 	if (IS_ERR(sb)) {
-		ret = PTR_ERR(sb);
-		goto error;
+		mutex_lock(&uuid_mutex);
+		btrfs_fs_devices_dec_holding(fs_devices);
+		/*
+		 * Since the fs_devices is not opened, it can be freed at any
+		 * time after unlocking uuid_mutex.  We need to avoid double
+		 * free through put_fs_context()->btrfs_free_fs_info().
+		 * So here we reset fs_info->fs_devices to NULL, and let the
+		 * regular fs_devices reclaim path to handle it.
+		 *
+		 * This applies to all later branches where no fs_devices is
+		 * opened.
+		 */
+		fs_info->fs_devices = NULL;
+		mutex_unlock(&uuid_mutex);
+		return PTR_ERR(sb);
 	}
 
-	set_device_specific_options(fs_info);
-
 	if (sb->s_root) {
-		btrfs_close_devices(fs_devices);
-		if ((fc->sb_flags ^ sb->s_flags) & SB_RDONLY)
-			ret = -EBUSY;
+		/*
+		 * Not the first mount of the fs thus got an existing super block.
+		 * Will reuse the returned super block, fs_info and fs_devices.
+		 *
+		 * fc->s_fs_info is not touched and will be later freed by
+		 * put_fs_context() through btrfs_free_fs_context().
+		 */
+		ASSERT(fc->s_fs_info == fs_info);
+
+		mutex_lock(&uuid_mutex);
+		btrfs_fs_devices_dec_holding(fs_devices);
+		fs_info->fs_devices = NULL;
+		mutex_unlock(&uuid_mutex);
+		/*
+		 * At this stage we may have RO flag mismatch between
+		 * fc->sb_flags and sb->s_flags.  Caller should detect such
+		 * mismatch and reconfigure with sb->s_umount rwsem held if
+		 * needed.
+		 */
 	} else {
+		struct block_device *bdev;
+
+		/*
+		 * The first mount of the fs thus a new superblock, fc->s_fs_info
+		 * must be NULL, and the ownership of our fs_info and fs_devices is
+		 * transferred to the super block.
+		 */
+		ASSERT(fc->s_fs_info == NULL);
+
+		mutex_lock(&uuid_mutex);
+		btrfs_fs_devices_dec_holding(fs_devices);
+		ret = btrfs_open_devices(fs_devices, mode, sb);
+		if (ret < 0)
+			fs_info->fs_devices = NULL;
+		mutex_unlock(&uuid_mutex);
+		if (ret < 0) {
+			deactivate_locked_super(sb);
+			return ret;
+		}
+		if (!(fc->sb_flags & SB_RDONLY) && fs_devices->rw_devices == 0) {
+			deactivate_locked_super(sb);
+			return -EACCES;
+		}
+		set_device_specific_options(fs_info);
+		bdev = fs_devices->latest_dev->bdev;
 		snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev);
 		shrinker_debugfs_rename(sb->s_shrink, "sb-btrfs:%s", sb->s_id);
-		btrfs_sb(sb)->bdev_holder = &btrfs_fs_type;
-		ret = btrfs_fill_super(sb, fs_devices, NULL);
-	}
-
-	if (ret) {
-		deactivate_locked_super(sb);
-		return ret;
+		ret = btrfs_fill_super(sb, fs_devices);
+		if (ret) {
+			deactivate_locked_super(sb);
+			return ret;
+		}
 	}
 
 	btrfs_clear_oneshot_options(fs_info);
 
 	fc->root = dget(sb->s_root);
 	return 0;
-
-error:
-	btrfs_close_devices(fs_devices);
-	return ret;
 }
 
 /*
@@ -1946,59 +2024,19 @@ error:
  *     fsconfig(FSCONFIG_SET_FLAG, "ro"). This option is seen by the filesystem
  *     in fc->sb_flags.
  *
- * This disambiguation has rather positive consequences.  Mounting a subvolume
- * ro will not also turn the superblock ro. Only the mount for the subvolume
- * will become ro.
- *
- * So, if the superblock creation request comes from the new mount API the
- * caller must have explicitly done:
- *
- *      fsconfig(FSCONFIG_SET_FLAG, "ro")
- *      fsmount/mount_setattr(MOUNT_ATTR_RDONLY)
- *
- * IOW, at some point the caller must have explicitly turned the whole
- * superblock ro and we shouldn't just undo it like we did for the old mount
- * API. In any case, it lets us avoid the hack in the new mount API.
- *
- * Consequently, the remounting hack must only be used for requests originating
- * from the old mount API and should be marked for full deprecation so it can be
- * turned off in a couple of years.
- *
- * The new mount API has no reason to support this hack.
+ * But, currently the util-linux mount command already utilizes the new mount
+ * API and is still setting fsconfig(FSCONFIG_SET_FLAG, "ro") no matter if it's
+ * btrfs or not, setting the whole super block RO.  To make per-subvolume mounting
+ * work with different options work we need to keep backward compatibility.
  */
-static struct vfsmount *btrfs_reconfigure_for_mount(struct fs_context *fc)
+static int btrfs_reconfigure_for_mount(struct fs_context *fc)
 {
-	struct vfsmount *mnt;
-	int ret;
-	const bool ro2rw = !(fc->sb_flags & SB_RDONLY);
-
-	/*
-	 * We got an EBUSY because our SB_RDONLY flag didn't match the existing
-	 * super block, so invert our setting here and retry the mount so we
-	 * can get our vfsmount.
-	 */
-	if (ro2rw)
-		fc->sb_flags |= SB_RDONLY;
-	else
-		fc->sb_flags &= ~SB_RDONLY;
-
-	mnt = fc_mount(fc);
-	if (IS_ERR(mnt))
-		return mnt;
+	int ret = 0;
 
-	if (!fc->oldapi || !ro2rw)
-		return mnt;
+	if (!(fc->sb_flags & SB_RDONLY) && (fc->root->d_sb->s_flags & SB_RDONLY))
+		ret = btrfs_reconfigure(fc);
 
-	/* We need to convert to rw, call reconfigure. */
-	fc->sb_flags &= ~SB_RDONLY;
-	down_write(&mnt->mnt_sb->s_umount);
-	ret = btrfs_reconfigure(fc);
-	up_write(&mnt->mnt_sb->s_umount);
-	if (ret) {
-		mntput(mnt);
-		return ERR_PTR(ret);
-	}
-	return mnt;
+	return ret;
 }
 
 static int btrfs_get_tree_subvol(struct fs_context *fc)
@@ -2008,6 +2046,7 @@ static int btrfs_get_tree_subvol(struct fs_context *fc)
 	struct fs_context *dup_fc;
 	struct dentry *dentry;
 	struct vfsmount *mnt;
+	int ret = 0;
 
 	/*
 	 * Setup a dummy root and fs_info for test/set super.  This is because
@@ -2024,7 +2063,13 @@ static int btrfs_get_tree_subvol(struct fs_context *fc)
 	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
 	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
 	if (!fs_info->super_copy || !fs_info->super_for_commit) {
-		btrfs_free_fs_info(fs_info);
+		/*
+		 * Dont call btrfs_free_fs_info() to free it as it's still
+		 * initialized partially.
+		 */
+		kfree(fs_info->super_copy);
+		kfree(fs_info->super_for_commit);
+		kvfree(fs_info);
 		return -ENOMEM;
 	}
 	btrfs_init_fs_info(fs_info);
@@ -2041,17 +2086,15 @@ static int btrfs_get_tree_subvol(struct fs_context *fc)
 	 */
 	dup_fc->s_fs_info = fs_info;
 
-	/*
-	 * We'll do the security settings in our btrfs_get_tree_super() mount
-	 * loop, they were duplicated into dup_fc, we can drop the originals
-	 * here.
-	 */
-	security_free_mnt_opts(&fc->security);
-	fc->security = NULL;
+	ret = btrfs_get_tree_super(dup_fc);
+	if (ret)
+		goto error;
 
-	mnt = fc_mount(dup_fc);
-	if (PTR_ERR_OR_ZERO(mnt) == -EBUSY)
-		mnt = btrfs_reconfigure_for_mount(dup_fc);
+	ret = btrfs_reconfigure_for_mount(dup_fc);
+	up_write(&dup_fc->root->d_sb->s_umount);
+	if (ret)
+		goto error;
+	mnt = vfs_create_mount(dup_fc);
 	put_fs_context(dup_fc);
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);
@@ -2068,25 +2111,15 @@ static int btrfs_get_tree_subvol(struct fs_context *fc)
 
 	fc->root = dentry;
 	return 0;
+error:
+	put_fs_context(dup_fc);
+	return ret;
 }
 
 static int btrfs_get_tree(struct fs_context *fc)
 {
-	/*
-	 * Since we use mount_subtree to mount the default/specified subvol, we
-	 * have to do mounts in two steps.
-	 *
-	 * First pass through we call btrfs_get_tree_subvol(), this is just a
-	 * wrapper around fc_mount() to call back into here again, and this time
-	 * we'll call btrfs_get_tree_super().  This will do the open_ctree() and
-	 * everything to open the devices and file system.  Then we return back
-	 * with a fully constructed vfsmount in btrfs_get_tree_subvol(), and
-	 * from there we can do our mount_subvol() call, which will lookup
-	 * whichever subvol we're mounting and setup this fc with the
-	 * appropriate dentry for the subvol.
-	 */
-	if (fc->s_fs_info)
-		return btrfs_get_tree_super(fc);
+	ASSERT(fc->s_fs_info == NULL);
+
 	return btrfs_get_tree_subvol(fc);
 }
 
@@ -2173,7 +2206,8 @@ static struct file_system_type btrfs_fs_type = {
 	.init_fs_context	= btrfs_init_fs_context,
 	.parameters		= btrfs_fs_parameters,
 	.kill_sb		= btrfs_kill_super,
-	.fs_flags		= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | FS_ALLOW_IDMAP,
+	.fs_flags		= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA |
+				  FS_ALLOW_IDMAP | FS_MGTIME,
  };
 
 MODULE_ALIAS_FS("btrfs");
@@ -2217,7 +2251,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 		 * Scanning outside of mount can return NULL which would turn
 		 * into 0 error code.
 		 */
-		device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ, false);
+		device = btrfs_scan_one_device(vol->name, false);
 		ret = PTR_ERR_OR_ZERO(device);
 		mutex_unlock(&uuid_mutex);
 		break;
@@ -2235,10 +2269,10 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 		 * Scanning outside of mount can return NULL which would turn
 		 * into 0 error code.
 		 */
-		device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ, false);
+		device = btrfs_scan_one_device(vol->name, false);
 		if (IS_ERR_OR_NULL(device)) {
 			mutex_unlock(&uuid_mutex);
-			ret = PTR_ERR(device);
+			ret = PTR_ERR_OR_ZERO(device);
 			break;
 		}
 		ret = !(device->fs_devices->num_devices ==
@@ -2257,9 +2291,7 @@ out:
 
 static int btrfs_freeze(struct super_block *sb)
 {
-	struct btrfs_trans_handle *trans;
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
-	struct btrfs_root *root = fs_info->tree_root;
 
 	set_bit(BTRFS_FS_FROZEN, &fs_info->flags);
 	/*
@@ -2268,14 +2300,7 @@ static int btrfs_freeze(struct super_block *sb)
 	 * we want to avoid on a frozen filesystem), or do the commit
 	 * ourselves.
 	 */
-	trans = btrfs_attach_transaction_barrier(root);
-	if (IS_ERR(trans)) {
-		/* no transaction, don't bother */
-		if (PTR_ERR(trans) == -ENOENT)
-			return 0;
-		return PTR_ERR(trans);
-	}
-	return btrfs_commit_transaction(trans);
+	return btrfs_commit_current_transaction(fs_info->tree_root);
 }
 
 static int check_dev_super(struct btrfs_device *dev)
@@ -2294,20 +2319,20 @@ static int check_dev_super(struct btrfs_device *dev)
 		return 0;
 
 	/* Only need to check the primary super block. */
-	sb = btrfs_read_dev_one_super(dev->bdev, 0, true);
+	sb = btrfs_read_disk_super(dev->bdev, 0, true);
 	if (IS_ERR(sb))
 		return PTR_ERR(sb);
 
 	/* Verify the checksum. */
 	csum_type = btrfs_super_csum_type(sb);
-	if (csum_type != btrfs_super_csum_type(fs_info->super_copy)) {
+	if (unlikely(csum_type != btrfs_super_csum_type(fs_info->super_copy))) {
 		btrfs_err(fs_info, "csum type changed, has %u expect %u",
 			  csum_type, btrfs_super_csum_type(fs_info->super_copy));
 		ret = -EUCLEAN;
 		goto out;
 	}
 
-	if (btrfs_check_super_csum(fs_info, sb)) {
+	if (unlikely(btrfs_check_super_csum(fs_info, sb))) {
 		btrfs_err(fs_info, "csum for on-disk super block no longer matches");
 		ret = -EUCLEAN;
 		goto out;
@@ -2319,7 +2344,7 @@ static int check_dev_super(struct btrfs_device *dev)
 		goto out;
 
 	last_trans = btrfs_get_last_trans_committed(fs_info);
-	if (btrfs_super_generation(sb) != last_trans) {
+	if (unlikely(btrfs_super_generation(sb) != last_trans)) {
 		btrfs_err(fs_info, "transid mismatch, has %llu expect %llu",
 			  btrfs_super_generation(sb), last_trans);
 		ret = -EUCLEAN;
@@ -2394,8 +2419,71 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont
 	const long nr_to_scan = min_t(unsigned long, LONG_MAX, sc->nr_to_scan);
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 
-	return btrfs_free_extent_maps(fs_info, nr_to_scan);
+	btrfs_free_extent_maps(fs_info, nr_to_scan);
+
+	/* The extent map shrinker runs asynchronously, so always return 0. */
+	return 0;
+}
+
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+static int btrfs_remove_bdev(struct super_block *sb, struct block_device *bdev)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+	struct btrfs_device *device;
+	struct btrfs_dev_lookup_args lookup_args = { .devt = bdev->bd_dev };
+	bool can_rw;
+
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	device = btrfs_find_device(fs_info->fs_devices, &lookup_args);
+	if (!device) {
+		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+		/* Device not found, should not affect the running fs, just give a warning. */
+		btrfs_warn(fs_info, "unable to find btrfs device for block device '%pg'", bdev);
+		return 0;
+	}
+	/*
+	 * The to-be-removed device is already missing?
+	 *
+	 * That's weird but no special handling needed and can exit right now.
+	 */
+	if (unlikely(test_and_set_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))) {
+		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+		btrfs_warn(fs_info, "btrfs device id %llu is already missing", device->devid);
+		return 0;
+	}
+
+	device->fs_devices->missing_devices++;
+	if (test_and_clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
+		list_del_init(&device->dev_alloc_list);
+		WARN_ON(device->fs_devices->rw_devices < 1);
+		device->fs_devices->rw_devices--;
+	}
+	can_rw = btrfs_check_rw_degradable(fs_info, device);
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	/*
+	 * Now device is considered missing, btrfs_device_name() won't give a
+	 * meaningful result anymore, so only output the devid.
+	 */
+	if (unlikely(!can_rw)) {
+		btrfs_crit(fs_info,
+		"btrfs device id %llu has gone missing, can not maintain read-write",
+			   device->devid);
+		return -EIO;
+	}
+	btrfs_warn(fs_info,
+		   "btrfs device id %llu has gone missing, continue as degraded",
+		   device->devid);
+	btrfs_set_opt(fs_info->mount_opt, DEGRADED);
+	return 0;
+}
+
+static void btrfs_shutdown(struct super_block *sb)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
+	btrfs_force_shutdown(fs_info);
 }
+#endif
 
 static const struct super_operations btrfs_super_ops = {
 	.drop_inode	= btrfs_drop_inode,
@@ -2412,6 +2500,10 @@ static const struct super_operations btrfs_super_ops = {
 	.unfreeze_fs	= btrfs_unfreeze,
 	.nr_cached_objects = btrfs_nr_cached_objects,
 	.free_cached_objects = btrfs_free_cached_objects,
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+	.remove_bdev	= btrfs_remove_bdev,
+	.shutdown	= btrfs_shutdown,
+#endif
 };
 
 static const struct file_operations btrfs_ctl_fops = {
@@ -2444,15 +2536,15 @@ static __cold void btrfs_interface_exit(void)
 static int __init btrfs_print_mod_info(void)
 {
 	static const char options[] = ""
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+			", experimental=on"
+#endif
 #ifdef CONFIG_BTRFS_DEBUG
 			", debug=on"
 #endif
 #ifdef CONFIG_BTRFS_ASSERT
 			", assert=on"
 #endif
-#ifdef CONFIG_BTRFS_FS_REF_VERIFY
-			", ref-verify=on"
-#endif
 #ifdef CONFIG_BLK_DEV_ZONED
 			", zoned=yes"
 #else
@@ -2464,7 +2556,17 @@ static int __init btrfs_print_mod_info(void)
 			", fsverity=no"
 #endif
 			;
+
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+	if (btrfs_get_mod_read_policy() == NULL)
+		pr_info("Btrfs loaded%s\n", options);
+	else
+		pr_info("Btrfs loaded%s, read_policy=%s\n",
+			 options, btrfs_get_mod_read_policy());
+#else
 	pr_info("Btrfs loaded%s\n", options);
+#endif
+
 	return 0;
 }
 
@@ -2499,6 +2601,9 @@ static const struct init_sequence mod_init_seq[] = {
 		.init_func = btrfs_init_cachep,
 		.exit_func = btrfs_destroy_cachep,
 	}, {
+		.init_func = btrfs_init_dio,
+		.exit_func = btrfs_destroy_dio,
+	}, {
 		.init_func = btrfs_transaction_init,
 		.exit_func = btrfs_transaction_exit,
 	}, {
@@ -2508,8 +2613,8 @@ static const struct init_sequence mod_init_seq[] = {
 		.init_func = btrfs_free_space_init,
 		.exit_func = btrfs_free_space_exit,
 	}, {
-		.init_func = extent_state_init_cachep,
-		.exit_func = extent_state_free_cachep,
+		.init_func = btrfs_extent_state_init_cachep,
+		.exit_func = btrfs_extent_state_free_cachep,
 	}, {
 		.init_func = extent_buffer_init_cachep,
 		.exit_func = extent_buffer_free_cachep,
@@ -2517,8 +2622,13 @@ static const struct init_sequence mod_init_seq[] = {
 		.init_func = btrfs_bioset_init,
 		.exit_func = btrfs_bioset_exit,
 	}, {
-		.init_func = extent_map_init,
-		.exit_func = extent_map_exit,
+		.init_func = btrfs_extent_map_init,
+		.exit_func = btrfs_extent_map_exit,
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
+	}, {
+		.init_func = btrfs_read_policy_init,
+		.exit_func = NULL,
+#endif
 	}, {
 		.init_func = ordered_data_init,
 		.exit_func = ordered_data_exit,
@@ -2590,6 +2700,7 @@ static int __init init_btrfs_fs(void)
 late_initcall(init_btrfs_fs);
 module_exit(exit_btrfs_fs)
 
+MODULE_DESCRIPTION("B-Tree File System (BTRFS)");
 MODULE_LICENSE("GPL");
 MODULE_SOFTDEP("pre: crc32c");
 MODULE_SOFTDEP("pre: xxhash64");