1 files changed, 94 insertions, 155 deletions

diff --git a/fs/super.c b/fs/super.c
index cd352530eca9..8d39e4f11cfa 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -31,7 +31,6 @@
 #include <linux/mutex.h>
 #include <linux/backing-dev.h>
 #include <linux/rculist_bl.h>
-#include <linux/cleancache.h>
 #include <linux/fscrypt.h>
 #include <linux/fsnotify.h>
 #include <linux/lockdep.h>
@@ -260,14 +259,13 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 	s->s_time_gran = 1000000000;
 	s->s_time_min = TIME64_MIN;
 	s->s_time_max = TIME64_MAX;
-	s->cleancache_poolid = CLEANCACHE_NO_POOL;
 
 	s->s_shrink.seeks = DEFAULT_SEEKS;
 	s->s_shrink.scan_objects = super_cache_scan;
 	s->s_shrink.count_objects = super_cache_count;
 	s->s_shrink.batch = 1024;
 	s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
-	if (prealloc_shrinker(&s->s_shrink))
+	if (prealloc_shrinker(&s->s_shrink, "sb-%s", type->name))
 		goto fail;
 	if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink))
 		goto fail;
@@ -293,7 +291,7 @@ static void __put_super(struct super_block *s)
 		WARN_ON(s->s_inode_lru.node);
 		WARN_ON(!list_empty(&s->s_mounts));
 		security_sb_free(s);
-		fscrypt_sb_free(s);
+		fscrypt_destroy_keyring(s);
 		put_user_ns(s->s_user_ns);
 		kfree(s->s_subtype);
 		call_rcu(&s->rcu, destroy_super_rcu);
@@ -307,7 +305,7 @@ static void __put_super(struct super_block *s)
  *	Drops a temporary reference, frees superblock if there's no
  *	references left.
  */
-static void put_super(struct super_block *sb)
+void put_super(struct super_block *sb)
 {
 	spin_lock(&sb_lock);
 	__put_super(sb);
@@ -330,7 +328,6 @@ void deactivate_locked_super(struct super_block *s)
 {
 	struct file_system_type *fs = s->s_type;
 	if (atomic_dec_and_test(&s->s_active)) {
-		cleancache_invalidate_fs(s);
 		unregister_shrinker(&s->s_shrink);
 		fs->kill_sb(s);
 
@@ -361,7 +358,7 @@ EXPORT_SYMBOL(deactivate_locked_super);
  */
 void deactivate_super(struct super_block *s)
 {
-        if (!atomic_add_unless(&s->s_active, -1, 1)) {
+	if (!atomic_add_unless(&s->s_active, -1, 1)) {
 		down_write(&s->s_umount);
 		deactivate_locked_super(s);
 	}
@@ -426,6 +423,35 @@ bool trylock_super(struct super_block *sb)
 }
 
 /**
+ *	retire_super	-	prevents superblock from being reused
+ *	@sb: superblock to retire
+ *
+ *	The function marks superblock to be ignored in superblock test, which
+ *	prevents it from being reused for any new mounts.  If the superblock has
+ *	a private bdi, it also unregisters it, but doesn't reduce the refcount
+ *	of the superblock to prevent potential races.  The refcount is reduced
+ *	by generic_shutdown_super().  The function can not be called
+ *	concurrently with generic_shutdown_super().  It is safe to call the
+ *	function multiple times, subsequent calls have no effect.
+ *
+ *	The marker will affect the re-use only for block-device-based
+ *	superblocks.  Other superblocks will still get marked if this function
+ *	is used, but that will not affect their reusability.
+ */
+void retire_super(struct super_block *sb)
+{
+	WARN_ON(!sb->s_bdev);
+	down_write(&sb->s_umount);
+	if (sb->s_iflags & SB_I_PERSB_BDI) {
+		bdi_unregister(sb->s_bdi);
+		sb->s_iflags &= ~SB_I_PERSB_BDI;
+	}
+	sb->s_iflags |= SB_I_RETIRED;
+	up_write(&sb->s_umount);
+}
+EXPORT_SYMBOL(retire_super);
+
+/**
  *	generic_shutdown_super	-	common helper for ->kill_sb()
  *	@sb: superblock to kill
  *
@@ -454,6 +480,8 @@ void generic_shutdown_super(struct super_block *sb)
 		evict_inodes(sb);
 		/* only nonzero refcount inodes can have marks */
 		fsnotify_sb_delete(sb);
+		fscrypt_destroy_keyring(sb);
+		security_sb_delete(sb);
 
 		if (sb->s_dio_done_wq) {
 			destroy_workqueue(sb->s_dio_done_wq);
@@ -475,6 +503,8 @@ void generic_shutdown_super(struct super_block *sb)
 	spin_unlock(&sb_lock);
 	up_write(&sb->s_umount);
 	if (sb->s_bdi != &noop_backing_dev_info) {
+		if (sb->s_iflags & SB_I_PERSB_BDI)
+			bdi_unregister(sb->s_bdi);
 		bdi_put(sb->s_bdi);
 		sb->s_bdi = &noop_backing_dev_info;
 	}
@@ -740,7 +770,14 @@ void iterate_supers_type(struct file_system_type *type,
 
 EXPORT_SYMBOL(iterate_supers_type);
 
-static struct super_block *__get_super(struct block_device *bdev, bool excl)
+/**
+ * get_super - get the superblock of a device
+ * @bdev: device to get the superblock for
+ *
+ * Scans the superblock list and finds the superblock of the file system
+ * mounted on the device given. %NULL is returned if no match is found.
+ */
+struct super_block *get_super(struct block_device *bdev)
 {
 	struct super_block *sb;
 
@@ -755,17 +792,11 @@ rescan:
 		if (sb->s_bdev == bdev) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
-			if (!excl)
-				down_read(&sb->s_umount);
-			else
-				down_write(&sb->s_umount);
+			down_read(&sb->s_umount);
 			/* still alive? */
 			if (sb->s_root && (sb->s_flags & SB_BORN))
 				return sb;
-			if (!excl)
-				up_read(&sb->s_umount);
-			else
-				up_write(&sb->s_umount);
+			up_read(&sb->s_umount);
 			/* nope, got unmounted */
 			spin_lock(&sb_lock);
 			__put_super(sb);
@@ -777,66 +808,6 @@ rescan:
 }
 
 /**
- *	get_super - get the superblock of a device
- *	@bdev: device to get the superblock for
- *
- *	Scans the superblock list and finds the superblock of the file system
- *	mounted on the device given. %NULL is returned if no match is found.
- */
-struct super_block *get_super(struct block_device *bdev)
-{
-	return __get_super(bdev, false);
-}
-EXPORT_SYMBOL(get_super);
-
-static struct super_block *__get_super_thawed(struct block_device *bdev,
-					      bool excl)
-{
-	while (1) {
-		struct super_block *s = __get_super(bdev, excl);
-		if (!s || s->s_writers.frozen == SB_UNFROZEN)
-			return s;
-		if (!excl)
-			up_read(&s->s_umount);
-		else
-			up_write(&s->s_umount);
-		wait_event(s->s_writers.wait_unfrozen,
-			   s->s_writers.frozen == SB_UNFROZEN);
-		put_super(s);
-	}
-}
-
-/**
- *	get_super_thawed - get thawed superblock of a device
- *	@bdev: device to get the superblock for
- *
- *	Scans the superblock list and finds the superblock of the file system
- *	mounted on the device. The superblock is returned once it is thawed
- *	(or immediately if it was not frozen). %NULL is returned if no match
- *	is found.
- */
-struct super_block *get_super_thawed(struct block_device *bdev)
-{
-	return __get_super_thawed(bdev, false);
-}
-EXPORT_SYMBOL(get_super_thawed);
-
-/**
- *	get_super_exclusive_thawed - get thawed superblock of a device
- *	@bdev: device to get the superblock for
- *
- *	Scans the superblock list and finds the superblock of the file system
- *	mounted on the device. The superblock is returned once it is thawed
- *	(or immediately if it was not frozen) and s_umount semaphore is held
- *	in exclusive mode. %NULL is returned if no match is found.
- */
-struct super_block *get_super_exclusive_thawed(struct block_device *bdev)
-{
-	return __get_super_thawed(bdev, true);
-}
-EXPORT_SYMBOL(get_super_exclusive_thawed);
-
-/**
  * get_active_super - get an active reference to the superblock of a device
  * @bdev: device to get the superblock for
  *
@@ -867,7 +838,7 @@ restart:
 	return NULL;
 }
 
-struct super_block *user_get_super(dev_t dev)
+struct super_block *user_get_super(dev_t dev, bool excl)
 {
 	struct super_block *sb;
 
@@ -879,11 +850,17 @@ rescan:
 		if (sb->s_dev ==  dev) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
-			down_read(&sb->s_umount);
+			if (excl)
+				down_write(&sb->s_umount);
+			else
+				down_read(&sb->s_umount);
 			/* still alive? */
 			if (sb->s_root && (sb->s_flags & SB_BORN))
 				return sb;
-			up_read(&sb->s_umount);
+			if (excl)
+				up_write(&sb->s_umount);
+			else
+				up_read(&sb->s_umount);
 			/* nope, got unmounted */
 			spin_lock(&sb_lock);
 			__put_super(sb);
@@ -918,7 +895,8 @@ int reconfigure_super(struct fs_context *fc)
 
 	if (fc->sb_flags_mask & SB_RDONLY) {
 #ifdef CONFIG_BLOCK
-		if (!(fc->sb_flags & SB_RDONLY) && bdev_read_only(sb->s_bdev))
+		if (!(fc->sb_flags & SB_RDONLY) && sb->s_bdev &&
+		    bdev_read_only(sb->s_bdev))
 			return -EACCES;
 #endif
 
@@ -1254,8 +1232,10 @@ static int set_bdev_super(struct super_block *s, void *data)
 {
 	s->s_bdev = data;
 	s->s_dev = s->s_bdev->bd_dev;
-	s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
+	s->s_bdi = bdi_get(s->s_bdev->bd_disk->bdi);
 
+	if (bdev_stable_writes(s->s_bdev))
+		s->s_iflags |= SB_I_STABLE_WRITES;
 	return 0;
 }
 
@@ -1266,7 +1246,7 @@ static int set_bdev_super_fc(struct super_block *s, struct fs_context *fc)
 
 static int test_bdev_super_fc(struct super_block *s, struct fs_context *fc)
 {
-	return s->s_bdev == fc->sget_key;
+	return !(s->s_iflags & SB_I_RETIRED) && s->s_bdev == fc->sget_key;
 }
 
 /**
@@ -1302,8 +1282,8 @@ int get_tree_bdev(struct fs_context *fc,
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
 	if (bdev->bd_fsfreeze_count > 0) {
 		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		blkdev_put(bdev, mode);
 		warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
+		blkdev_put(bdev, mode);
 		return -EBUSY;
 	}
 
@@ -1326,9 +1306,9 @@ int get_tree_bdev(struct fs_context *fc,
 		}
 
 		/*
-		 * s_umount nests inside bd_mutex during
+		 * s_umount nests inside open_mutex during
 		 * __invalidate_device().  blkdev_put() acquires
-		 * bd_mutex and can't be called under s_umount.  Drop
+		 * open_mutex and can't be called under s_umount.  Drop
 		 * s_umount temporarily.  This is safe as we're
 		 * holding an active reference.
 		 */
@@ -1338,6 +1318,8 @@ int get_tree_bdev(struct fs_context *fc,
 	} else {
 		s->s_mode = mode;
 		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
+		shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
+					fc->fs_type->name, s->s_id);
 		sb_set_blocksize(s, block_size(bdev));
 		error = fill_super(s, fc);
 		if (error) {
@@ -1357,7 +1339,7 @@ EXPORT_SYMBOL(get_tree_bdev);
 
 static int test_bdev_super(struct super_block *s, void *data)
 {
-	return (void *)s->s_bdev == data;
+	return !(s->s_iflags & SB_I_RETIRED) && (void *)s->s_bdev == data;
 }
 
 struct dentry *mount_bdev(struct file_system_type *fs_type,
@@ -1401,9 +1383,9 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 		}
 
 		/*
-		 * s_umount nests inside bd_mutex during
+		 * s_umount nests inside open_mutex during
 		 * __invalidate_device().  blkdev_put() acquires
-		 * bd_mutex and can't be called under s_umount.  Drop
+		 * open_mutex and can't be called under s_umount.  Drop
 		 * s_umount temporarily.  This is safe as we're
 		 * holding an active reference.
 		 */
@@ -1413,6 +1395,8 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 	} else {
 		s->s_mode = mode;
 		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
+		shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
+					fs_type->name, s->s_id);
 		sb_set_blocksize(s, block_size(bdev));
 		error = fill_super(s, data, flags & SB_SILENT ? 1 : 0);
 		if (error) {
@@ -1470,8 +1454,8 @@ struct dentry *mount_nodev(struct file_system_type *fs_type,
 }
 EXPORT_SYMBOL(mount_nodev);
 
-static int reconfigure_single(struct super_block *s,
-			      int flags, void *data)
+int reconfigure_single(struct super_block *s,
+		       int flags, void *data)
 {
 	struct fs_context *fc;
 	int ret;
@@ -1598,12 +1582,10 @@ int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
 	int err;
 	va_list args;
 
-	bdi = bdi_alloc(GFP_KERNEL);
+	bdi = bdi_alloc(NUMA_NO_NODE);
 	if (!bdi)
 		return -ENOMEM;
 
-	bdi->name = sb->s_type->name;
-
 	va_start(args, fmt);
 	err = bdi_register_va(bdi, fmt, args);
 	va_end(args);
@@ -1613,6 +1595,7 @@ int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
 	}
 	WARN_ON(sb->s_bdi != &noop_backing_dev_info);
 	sb->s_bdi = bdi;
+	sb->s_iflags |= SB_I_PERSB_BDI;
 
 	return 0;
 }
@@ -1631,55 +1614,6 @@ int super_setup_bdi(struct super_block *sb)
 }
 EXPORT_SYMBOL(super_setup_bdi);
 
-/*
- * This is an internal function, please use sb_end_{write,pagefault,intwrite}
- * instead.
- */
-void __sb_end_write(struct super_block *sb, int level)
-{
-	percpu_up_read(sb->s_writers.rw_sem + level-1);
-}
-EXPORT_SYMBOL(__sb_end_write);
-
-/*
- * This is an internal function, please use sb_start_{write,pagefault,intwrite}
- * instead.
- */
-int __sb_start_write(struct super_block *sb, int level, bool wait)
-{
-	bool force_trylock = false;
-	int ret = 1;
-
-#ifdef CONFIG_LOCKDEP
-	/*
-	 * We want lockdep to tell us about possible deadlocks with freezing
-	 * but it's it bit tricky to properly instrument it. Getting a freeze
-	 * protection works as getting a read lock but there are subtle
-	 * problems. XFS for example gets freeze protection on internal level
-	 * twice in some cases, which is OK only because we already hold a
-	 * freeze protection also on higher level. Due to these cases we have
-	 * to use wait == F (trylock mode) which must not fail.
-	 */
-	if (wait) {
-		int i;
-
-		for (i = 0; i < level - 1; i++)
-			if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) {
-				force_trylock = true;
-				break;
-			}
-	}
-#endif
-	if (wait && !force_trylock)
-		percpu_down_read(sb->s_writers.rw_sem + level-1);
-	else
-		ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);
-
-	WARN_ON(force_trylock && !ret);
-	return ret;
-}
-EXPORT_SYMBOL(__sb_start_write);
-
 /**
  * sb_wait_write - wait until all writers to given file system finish
  * @sb: the super for which we wait
@@ -1716,11 +1650,9 @@ static void lockdep_sb_freeze_acquire(struct super_block *sb)
 		percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
 }
 
-static void sb_freeze_unlock(struct super_block *sb)
+static void sb_freeze_unlock(struct super_block *sb, int level)
 {
-	int level;
-
-	for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
+	for (level--; level >= 0; level--)
 		percpu_up_write(sb->s_writers.rw_sem + level);
 }
 
@@ -1791,7 +1723,14 @@ int freeze_super(struct super_block *sb)
 	sb_wait_write(sb, SB_FREEZE_PAGEFAULT);
 
 	/* All writers are done so after syncing there won't be dirty data */
-	sync_filesystem(sb);
+	ret = sync_filesystem(sb);
+	if (ret) {
+		sb->s_writers.frozen = SB_UNFROZEN;
+		sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT);
+		wake_up(&sb->s_writers.wait_unfrozen);
+		deactivate_locked_super(sb);
+		return ret;
+	}
 
 	/* Now wait for internal filesystem counter */
 	sb->s_writers.frozen = SB_FREEZE_FS;
@@ -1803,7 +1742,7 @@ int freeze_super(struct super_block *sb)
 			printk(KERN_ERR
 				"VFS:Filesystem freeze failed\n");
 			sb->s_writers.frozen = SB_UNFROZEN;
-			sb_freeze_unlock(sb);
+			sb_freeze_unlock(sb, SB_FREEZE_FS);
 			wake_up(&sb->s_writers.wait_unfrozen);
 			deactivate_locked_super(sb);
 			return ret;
@@ -1820,12 +1759,6 @@ int freeze_super(struct super_block *sb)
 }
 EXPORT_SYMBOL(freeze_super);
 
-/**
- * thaw_super -- unlock filesystem
- * @sb: the super to thaw
- *
- * Unlocks the filesystem and marks it writeable again after freeze_super().
- */
 static int thaw_super_locked(struct super_block *sb)
 {
 	int error;
@@ -1854,13 +1787,19 @@ static int thaw_super_locked(struct super_block *sb)
 	}
 
 	sb->s_writers.frozen = SB_UNFROZEN;
-	sb_freeze_unlock(sb);
+	sb_freeze_unlock(sb, SB_FREEZE_FS);
 out:
 	wake_up(&sb->s_writers.wait_unfrozen);
 	deactivate_locked_super(sb);
 	return 0;
 }
 
+/**
+ * thaw_super -- unlock filesystem
+ * @sb: the super to thaw
+ *
+ * Unlocks the filesystem and marks it writeable again after freeze_super().
+ */
 int thaw_super(struct super_block *sb)
 {
 	down_write(&sb->s_umount);