1 files changed, 80 insertions, 104 deletions

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 926d7a9ed99d..a0c65adce1ab 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -28,7 +28,6 @@
 #include <linux/btrfs.h>
 #include <linux/security.h>
 #include <linux/fs_parser.h>
-#include <linux/swap.h>
 #include "messages.h"
 #include "delayed-inode.h"
 #include "ctree.h"
@@ -85,7 +84,7 @@ struct btrfs_fs_context {
 	u32 thread_pool_size;
 	unsigned long long mount_opt;
 	unsigned long compress_type:4;
-	unsigned int compress_level;
+	int compress_level;
 	refcount_t refs;
 };
 
@@ -126,7 +125,6 @@ enum {
 	/* Rescue options */
 	Opt_rescue,
 	Opt_usebackuproot,
-	Opt_nologreplay,
 
 	/* Debugging options */
 	Opt_enospc_debug,
@@ -247,8 +245,6 @@ 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". */
@@ -450,11 +446,6 @@ 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'");
@@ -570,6 +561,10 @@ 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;
@@ -946,10 +941,9 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec
 }
 
 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;
 
@@ -963,7 +957,7 @@ static int btrfs_fill_super(struct super_block *sb,
 #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) {
@@ -971,9 +965,9 @@ static int btrfs_fill_super(struct super_block *sb,
 		return err;
 	}
 
-	err = open_ctree(sb, fs_devices, (char *)data);
+	err = open_ctree(sb, fs_devices);
 	if (err) {
-		btrfs_err(fs_info, "open_ctree failed");
+		btrfs_err(fs_info, "open_ctree failed: %d", err);
 		return err;
 	}
 
@@ -984,7 +978,7 @@ static int btrfs_fill_super(struct super_block *sb,
 		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;
 		goto fail_close;
@@ -1141,8 +1135,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 	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;
@@ -1151,11 +1144,11 @@ 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,
@@ -1887,18 +1880,21 @@ static int btrfs_get_tree_super(struct fs_context *fc)
 
 	if (sb->s_root) {
 		btrfs_close_devices(fs_devices);
-		if ((fc->sb_flags ^ sb->s_flags) & SB_RDONLY)
-			ret = -EBUSY;
+		/*
+		 * 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 {
 		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);
@@ -1979,59 +1975,23 @@ 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)
 {
-	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)
+		return ret;
 
-	/* We need to convert to rw, call reconfigure. */
-	fc->sb_flags &= ~SB_RDONLY;
 	down_write(&mnt->mnt_sb->s_umount);
-	ret = btrfs_reconfigure(fc);
+	if (!(fc->sb_flags & SB_RDONLY) && (mnt->mnt_sb->s_flags & SB_RDONLY))
+		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)
@@ -2041,6 +2001,7 @@ 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
@@ -2083,11 +2044,16 @@ static int btrfs_get_tree_subvol(struct fs_context *fc)
 	fc->security = NULL;
 
 	mnt = fc_mount(dup_fc);
-	if (PTR_ERR_OR_ZERO(mnt) == -EBUSY)
-		mnt = btrfs_reconfigure_for_mount(dup_fc);
-	put_fs_context(dup_fc);
-	if (IS_ERR(mnt))
+	if (IS_ERR(mnt)) {
+		put_fs_context(dup_fc);
 		return PTR_ERR(mnt);
+	}
+	ret = btrfs_reconfigure_for_mount(dup_fc, mnt);
+	put_fs_context(dup_fc);
+	if (ret) {
+		mntput(mnt);
+		return ret;
+	}
 
 	/*
 	 * This free's ->subvol_name, because if it isn't set we have to
@@ -2206,7 +2172,8 @@ 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");
@@ -2271,7 +2238,10 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 		device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ, false);
 		if (IS_ERR_OR_NULL(device)) {
 			mutex_unlock(&uuid_mutex);
-			ret = PTR_ERR(device);
+			if (IS_ERR(device))
+				ret = PTR_ERR(device);
+			else
+				ret = 0;
 			break;
 		}
 		ret = !(device->fs_devices->num_devices ==
@@ -2318,7 +2288,7 @@ 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);
 
@@ -2410,13 +2380,7 @@ static long btrfs_nr_cached_objects(struct super_block *sb, struct shrink_contro
 
 	trace_btrfs_extent_map_shrinker_count(fs_info, nr);
 
-	/*
-	 * Only report the real number for DEBUG builds, as there are reports of
-	 * serious performance degradation caused by too frequent shrinks.
-	 */
-	if (IS_ENABLED(CONFIG_BTRFS_DEBUG))
-		return nr;
-	return 0;
+	return nr;
 }
 
 static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_control *sc)
@@ -2424,16 +2388,10 @@ 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);
 
-	/*
-	 * We may be called from any task trying to allocate memory and we don't
-	 * want to slow it down with scanning and dropping extent maps. It would
-	 * also cause heavy lock contention if many tasks concurrently enter
-	 * here. Therefore only allow kswapd tasks to scan and drop extent maps.
-	 */
-	if (!current_is_kswapd())
-		return 0;
+	btrfs_free_extent_maps(fs_info, nr_to_scan);
 
-	return btrfs_free_extent_maps(fs_info, nr_to_scan);
+	/* The extent map shrinker runs asynchronously, so always return 0. */
+	return 0;
 }
 
 static const struct super_operations btrfs_super_ops = {
@@ -2483,6 +2441,9 @@ 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
@@ -2503,7 +2464,17 @@ 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;
 }
 
@@ -2550,8 +2521,8 @@ 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,
@@ -2559,8 +2530,13 @@ 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,