1 files changed, 187 insertions, 161 deletions

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 3a4dce153645..6e71a2a78363 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -61,12 +61,21 @@
 #include "tests/btrfs-tests.h"
 
 #include "qgroup.h"
-#include "backref.h"
 #define CREATE_TRACE_POINTS
 #include <trace/events/btrfs.h>
 
 static const struct super_operations btrfs_super_ops;
+
+/*
+ * Types for mounting the default subvolume and a subvolume explicitly
+ * requested by subvol=/path. That way the callchain is straightforward and we
+ * don't have to play tricks with the mount options and recursive calls to
+ * btrfs_mount.
+ *
+ * The new btrfs_root_fs_type also servers as a tag for the bdev_holder.
+ */
 static struct file_system_type btrfs_fs_type;
+static struct file_system_type btrfs_root_fs_type;
 
 static int btrfs_remount(struct super_block *sb, int *flags, char *data);
 
@@ -98,30 +107,6 @@ const char *btrfs_decode_error(int errno)
 	return errstr;
 }
 
-/* btrfs handle error by forcing the filesystem readonly */
-static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
-{
-	struct super_block *sb = fs_info->sb;
-
-	if (sb_rdonly(sb))
-		return;
-
-	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
-		sb->s_flags |= SB_RDONLY;
-		btrfs_info(fs_info, "forced readonly");
-		/*
-		 * Note that a running device replace operation is not
-		 * canceled here although there is no way to update
-		 * the progress. It would add the risk of a deadlock,
-		 * therefore the canceling is omitted. The only penalty
-		 * is that some I/O remains active until the procedure
-		 * completes. The next time when the filesystem is
-		 * mounted writeable again, the device replace
-		 * operation continues.
-		 */
-	}
-}
-
 /*
  * __btrfs_handle_fs_error decodes expected errors from the caller and
  * invokes the approciate error response.
@@ -168,8 +153,23 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function
 	set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
 
 	/* Don't go through full error handling during mount */
-	if (sb->s_flags & SB_BORN)
-		btrfs_handle_error(fs_info);
+	if (!(sb->s_flags & SB_BORN))
+		return;
+
+	if (sb_rdonly(sb))
+		return;
+
+	/* btrfs handle error by forcing the filesystem readonly */
+	sb->s_flags |= SB_RDONLY;
+	btrfs_info(fs_info, "forced readonly");
+	/*
+	 * Note that a running device replace operation is not canceled here
+	 * although there is no way to update the progress. It would add the
+	 * risk of a deadlock, therefore the canceling is omitted. The only
+	 * penalty is that some I/O remains active until the procedure
+	 * completes. The next time when the filesystem is mounted writeable
+	 * again, the device replace operation continues.
+	 */
 }
 
 #ifdef CONFIG_PRINTK
@@ -405,7 +405,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			unsigned long new_flags)
 {
 	substring_t args[MAX_OPT_ARGS];
-	char *p, *num, *orig = NULL;
+	char *p, *num;
 	u64 cache_gen;
 	int intarg;
 	int ret = 0;
@@ -428,16 +428,6 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 	if (!options)
 		goto check;
 
-	/*
-	 * strsep changes the string, duplicate it because parse_options
-	 * gets called twice
-	 */
-	options = kstrdup(options, GFP_KERNEL);
-	if (!options)
-		return -ENOMEM;
-
-	orig = options;
-
 	while ((p = strsep(&options, ",")) != NULL) {
 		int token;
 		if (!*p)
@@ -454,7 +444,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_subvolrootid:
 		case Opt_device:
 			/*
-			 * These are parsed by btrfs_parse_early_options
+			 * These are parsed by btrfs_parse_subvol_options
+			 * and btrfs_parse_early_options
 			 * and can be happily ignored here.
 			 */
 			break;
@@ -877,7 +868,6 @@ out:
 		btrfs_info(info, "disk space caching is enabled");
 	if (!ret && btrfs_test_opt(info, FREE_SPACE_TREE))
 		btrfs_info(info, "using free space tree");
-	kfree(orig);
 	return ret;
 }
 
@@ -888,11 +878,60 @@ out:
  * only when we need to allocate a new super block.
  */
 static int btrfs_parse_early_options(const char *options, fmode_t flags,
-		void *holder, char **subvol_name, u64 *subvol_objectid,
-		struct btrfs_fs_devices **fs_devices)
+		void *holder, struct btrfs_fs_devices **fs_devices)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *device_name, *opts, *orig, *p;
+	int error = 0;
+
+	if (!options)
+		return 0;
+
+	/*
+	 * strsep changes the string, duplicate it because btrfs_parse_options
+	 * gets called later
+	 */
+	opts = kstrdup(options, GFP_KERNEL);
+	if (!opts)
+		return -ENOMEM;
+	orig = opts;
+
+	while ((p = strsep(&opts, ",")) != NULL) {
+		int token;
+
+		if (!*p)
+			continue;
+
+		token = match_token(p, tokens, args);
+		if (token == Opt_device) {
+			device_name = match_strdup(&args[0]);
+			if (!device_name) {
+				error = -ENOMEM;
+				goto out;
+			}
+			error = btrfs_scan_one_device(device_name,
+					flags, holder, fs_devices);
+			kfree(device_name);
+			if (error)
+				goto out;
+		}
+	}
+
+out:
+	kfree(orig);
+	return error;
+}
+
+/*
+ * Parse mount options that are related to subvolume id
+ *
+ * The value is later passed to mount_subvol()
+ */
+static int btrfs_parse_subvol_options(const char *options, fmode_t flags,
+		char **subvol_name, u64 *subvol_objectid)
+{
+	substring_t args[MAX_OPT_ARGS];
+	char *opts, *orig, *p;
 	char *num = NULL;
 	int error = 0;
 
@@ -900,8 +939,8 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 		return 0;
 
 	/*
-	 * strsep changes the string, duplicate it because parse_options
-	 * gets called twice
+	 * strsep changes the string, duplicate it because
+	 * btrfs_parse_early_options gets called later
 	 */
 	opts = kstrdup(options, GFP_KERNEL);
 	if (!opts)
@@ -940,18 +979,6 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 		case Opt_subvolrootid:
 			pr_warn("BTRFS: 'subvolrootid' mount option is deprecated and has no effect\n");
 			break;
-		case Opt_device:
-			device_name = match_strdup(&args[0]);
-			if (!device_name) {
-				error = -ENOMEM;
-				goto out;
-			}
-			error = btrfs_scan_one_device(device_name,
-					flags, holder, fs_devices);
-			kfree(device_name);
-			if (error)
-				goto out;
-			break;
 		default:
 			break;
 		}
@@ -1243,7 +1270,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 {
 	struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb);
-	char *compress_type;
+	const char *compress_type;
 
 	if (btrfs_test_opt(info, DEGRADED))
 		seq_puts(seq, ",degraded");
@@ -1259,12 +1286,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 					     num_online_cpus() + 2, 8))
 		seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
 	if (btrfs_test_opt(info, COMPRESS)) {
-		if (info->compress_type == BTRFS_COMPRESS_ZLIB)
-			compress_type = "zlib";
-		else if (info->compress_type == BTRFS_COMPRESS_LZO)
-			compress_type = "lzo";
-		else
-			compress_type = "zstd";
+		compress_type = btrfs_compress_type2str(info->compress_type);
 		if (btrfs_test_opt(info, FORCE_COMPRESS))
 			seq_printf(seq, ",compress-force=%s", compress_type);
 		else
@@ -1365,86 +1387,12 @@ static inline int is_subvolume_inode(struct inode *inode)
 	return 0;
 }
 
-/*
- * This will add subvolid=0 to the argument string while removing any subvol=
- * and subvolid= arguments to make sure we get the top-level root for path
- * walking to the subvol we want.
- */
-static char *setup_root_args(char *args)
-{
-	char *buf, *dst, *sep;
-
-	if (!args)
-		return kstrdup("subvolid=0", GFP_KERNEL);
-
-	/* The worst case is that we add ",subvolid=0" to the end. */
-	buf = dst = kmalloc(strlen(args) + strlen(",subvolid=0") + 1,
-			GFP_KERNEL);
-	if (!buf)
-		return NULL;
-
-	while (1) {
-		sep = strchrnul(args, ',');
-		if (!strstarts(args, "subvol=") &&
-		    !strstarts(args, "subvolid=")) {
-			memcpy(dst, args, sep - args);
-			dst += sep - args;
-			*dst++ = ',';
-		}
-		if (*sep)
-			args = sep + 1;
-		else
-			break;
-	}
-	strcpy(dst, "subvolid=0");
-
-	return buf;
-}
-
 static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid,
-				   int flags, const char *device_name,
-				   char *data)
+				   const char *device_name, struct vfsmount *mnt)
 {
 	struct dentry *root;
-	struct vfsmount *mnt = NULL;
-	char *newargs;
 	int ret;
 
-	newargs = setup_root_args(data);
-	if (!newargs) {
-		root = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name, newargs);
-	if (PTR_ERR_OR_ZERO(mnt) == -EBUSY) {
-		if (flags & SB_RDONLY) {
-			mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~SB_RDONLY,
-					     device_name, newargs);
-		} else {
-			mnt = vfs_kern_mount(&btrfs_fs_type, flags | SB_RDONLY,
-					     device_name, newargs);
-			if (IS_ERR(mnt)) {
-				root = ERR_CAST(mnt);
-				mnt = NULL;
-				goto out;
-			}
-
-			down_write(&mnt->mnt_sb->s_umount);
-			ret = btrfs_remount(mnt->mnt_sb, &flags, NULL);
-			up_write(&mnt->mnt_sb->s_umount);
-			if (ret < 0) {
-				root = ERR_PTR(ret);
-				goto out;
-			}
-		}
-	}
-	if (IS_ERR(mnt)) {
-		root = ERR_CAST(mnt);
-		mnt = NULL;
-		goto out;
-	}
-
 	if (!subvol_name) {
 		if (!subvol_objectid) {
 			ret = get_default_subvol_objectid(btrfs_sb(mnt->mnt_sb),
@@ -1500,7 +1448,6 @@ static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid,
 
 out:
 	mntput(mnt);
-	kfree(newargs);
 	kfree(subvol_name);
 	return root;
 }
@@ -1558,11 +1505,11 @@ static int setup_security_options(struct btrfs_fs_info *fs_info,
 /*
  * Find a superblock for the given device / mount point.
  *
- * Note:  This is based on get_sb_bdev from fs/super.c with a few additions
- *	  for multiple device setup.  Make sure to keep it in sync.
+ * Note: This is based on mount_bdev from fs/super.c with a few additions
+ *       for multiple device setup.  Make sure to keep it in sync.
  */
-static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
-		const char *device_name, void *data)
+static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
+		int flags, const char *device_name, void *data)
 {
 	struct block_device *bdev = NULL;
 	struct super_block *s;
@@ -1570,27 +1517,17 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	struct btrfs_fs_info *fs_info = NULL;
 	struct security_mnt_opts new_sec_opts;
 	fmode_t mode = FMODE_READ;
-	char *subvol_name = NULL;
-	u64 subvol_objectid = 0;
 	int error = 0;
 
 	if (!(flags & SB_RDONLY))
 		mode |= FMODE_WRITE;
 
 	error = btrfs_parse_early_options(data, mode, fs_type,
-					  &subvol_name, &subvol_objectid,
 					  &fs_devices);
 	if (error) {
-		kfree(subvol_name);
 		return ERR_PTR(error);
 	}
 
-	if (subvol_name || subvol_objectid != BTRFS_FS_TREE_OBJECTID) {
-		/* mount_subvol() will free subvol_name. */
-		return mount_subvol(subvol_name, subvol_objectid, flags,
-				    device_name, data);
-	}
-
 	security_init_mnt_opts(&new_sec_opts);
 	if (data) {
 		error = parse_security_options(data, &new_sec_opts);
@@ -1674,6 +1611,84 @@ error_sec_opts:
 	return ERR_PTR(error);
 }
 
+/*
+ * Mount function which is called by VFS layer.
+ *
+ * In order to allow mounting a subvolume directly, btrfs uses mount_subtree()
+ * which needs vfsmount* of device's root (/).  This means device's root has to
+ * be mounted internally in any case.
+ *
+ * Operation flow:
+ *   1. Parse subvol id related options for later use in mount_subvol().
+ *
+ *   2. Mount device's root (/) by calling vfs_kern_mount().
+ *
+ *      NOTE: vfs_kern_mount() is used by VFS to call btrfs_mount() in the
+ *      first place. In order to avoid calling btrfs_mount() again, we use
+ *      different file_system_type which is not registered to VFS by
+ *      register_filesystem() (btrfs_root_fs_type). As a result,
+ *      btrfs_mount_root() is called. The return value will be used by
+ *      mount_subtree() in mount_subvol().
+ *
+ *   3. Call mount_subvol() to get the dentry of subvolume. Since there is
+ *      "btrfs subvolume set-default", mount_subvol() is called always.
+ */
+static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
+		const char *device_name, void *data)
+{
+	struct vfsmount *mnt_root;
+	struct dentry *root;
+	fmode_t mode = FMODE_READ;
+	char *subvol_name = NULL;
+	u64 subvol_objectid = 0;
+	int error = 0;
+
+	if (!(flags & SB_RDONLY))
+		mode |= FMODE_WRITE;
+
+	error = btrfs_parse_subvol_options(data, mode,
+					  &subvol_name, &subvol_objectid);
+	if (error) {
+		kfree(subvol_name);
+		return ERR_PTR(error);
+	}
+
+	/* mount device's root (/) */
+	mnt_root = vfs_kern_mount(&btrfs_root_fs_type, flags, device_name, data);
+	if (PTR_ERR_OR_ZERO(mnt_root) == -EBUSY) {
+		if (flags & SB_RDONLY) {
+			mnt_root = vfs_kern_mount(&btrfs_root_fs_type,
+				flags & ~SB_RDONLY, device_name, data);
+		} else {
+			mnt_root = vfs_kern_mount(&btrfs_root_fs_type,
+				flags | SB_RDONLY, device_name, data);
+			if (IS_ERR(mnt_root)) {
+				root = ERR_CAST(mnt_root);
+				goto out;
+			}
+
+			down_write(&mnt_root->mnt_sb->s_umount);
+			error = btrfs_remount(mnt_root->mnt_sb, &flags, NULL);
+			up_write(&mnt_root->mnt_sb->s_umount);
+			if (error < 0) {
+				root = ERR_PTR(error);
+				mntput(mnt_root);
+				goto out;
+			}
+		}
+	}
+	if (IS_ERR(mnt_root)) {
+		root = ERR_CAST(mnt_root);
+		goto out;
+	}
+
+	/* mount_subvol() will free subvol_name and mnt_root */
+	root = mount_subvol(subvol_name, subvol_objectid, device_name, mnt_root);
+
+out:
+	return root;
+}
+
 static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
 				     int new_pool_size, int old_pool_size)
 {
@@ -1820,7 +1835,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 			goto restore;
 		}
 
-		if (!btrfs_check_rw_degradable(fs_info)) {
+		if (!btrfs_check_rw_degradable(fs_info, NULL)) {
 			btrfs_warn(fs_info,
 				"too many missing devices, writeable remount is not allowed");
 			ret = -EACCES;
@@ -1972,8 +1987,10 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
-		if (!device->in_fs_metadata || !device->bdev ||
-		    device->is_tgtdev_for_dev_replace)
+		if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA,
+						&device->dev_state) ||
+		    !device->bdev ||
+		    test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state))
 			continue;
 
 		if (i >= nr_devices)
@@ -2174,6 +2191,15 @@ static struct file_system_type btrfs_fs_type = {
 	.kill_sb	= btrfs_kill_super,
 	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA,
 };
+
+static struct file_system_type btrfs_root_fs_type = {
+	.owner		= THIS_MODULE,
+	.name		= "btrfs",
+	.mount		= btrfs_mount_root,
+	.kill_sb	= btrfs_kill_super,
+	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA,
+};
+
 MODULE_ALIAS_FS("btrfs");
 
 static int btrfs_control_open(struct inode *inode, struct file *file)
@@ -2207,11 +2233,11 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 	switch (cmd) {
 	case BTRFS_IOC_SCAN_DEV:
 		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
-					    &btrfs_fs_type, &fs_devices);
+					    &btrfs_root_fs_type, &fs_devices);
 		break;
 	case BTRFS_IOC_DEVICES_READY:
 		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
-					    &btrfs_fs_type, &fs_devices);
+					    &btrfs_root_fs_type, &fs_devices);
 		if (ret)
 			break;
 		ret = !(fs_devices->num_devices == fs_devices->total_devices);
@@ -2269,7 +2295,7 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 	while (cur_devices) {
 		head = &cur_devices->devices;
 		list_for_each_entry(dev, head, dev_list) {
-			if (dev->missing)
+			if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state))
 				continue;
 			if (!dev->name)
 				continue;
@@ -2324,7 +2350,7 @@ static struct miscdevice btrfs_misc = {
 MODULE_ALIAS_MISCDEV(BTRFS_MINOR);
 MODULE_ALIAS("devname:btrfs-control");
 
-static int btrfs_interface_init(void)
+static int __init btrfs_interface_init(void)
 {
 	return misc_register(&btrfs_misc);
 }
@@ -2334,7 +2360,7 @@ static void btrfs_interface_exit(void)
 	misc_deregister(&btrfs_misc);
 }
 
-static void btrfs_print_mod_info(void)
+static void __init btrfs_print_mod_info(void)
 {
 	pr_info("Btrfs loaded, crc32c=%s"
 #ifdef CONFIG_BTRFS_DEBUG