Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

1 files changed, 185 insertions, 149 deletions

diff --git a/fs/super.c b/fs/super.c
index 1527e6a0ee35..5c35bc7a499e 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -22,23 +22,14 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <linux/acct.h>
 #include <linux/blkdev.h>
-#include <linux/quotaops.h>
-#include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/security.h>
-#include <linux/syscalls.h>
-#include <linux/vfs.h>
 #include <linux/writeback.h>		/* for the emergency remount stuff */
 #include <linux/idr.h>
-#include <linux/kobject.h>
 #include <linux/mutex.h>
-#include <linux/file.h>
 #include <linux/backing-dev.h>
-#include <asm/uaccess.h>
 #include "internal.h"
 
 
@@ -93,16 +84,15 @@ static struct super_block *alloc_super(struct file_system_type *type)
 		 * subclass.
 		 */
 		down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING);
-		s->s_count = S_BIAS;
+		s->s_count = 1;
 		atomic_set(&s->s_active, 1);
 		mutex_init(&s->s_vfs_rename_mutex);
+		lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);
 		mutex_init(&s->s_dquot.dqio_mutex);
 		mutex_init(&s->s_dquot.dqonoff_mutex);
 		init_rwsem(&s->s_dquot.dqptr_sem);
 		init_waitqueue_head(&s->s_wait_unfrozen);
 		s->s_maxbytes = MAX_NON_LFS;
-		s->dq_op = sb_dquot_ops;
-		s->s_qcop = sb_quotactl_ops;
 		s->s_op = &default_op;
 		s->s_time_gran = 1000000000;
 	}
@@ -127,39 +117,14 @@ static inline void destroy_super(struct super_block *s)
 /* Superblock refcounting  */
 
 /*
- * Drop a superblock's refcount.  Returns non-zero if the superblock was
- * destroyed.  The caller must hold sb_lock.
+ * Drop a superblock's refcount.  The caller must hold sb_lock.
  */
-static int __put_super(struct super_block *sb)
+void __put_super(struct super_block *sb)
 {
-	int ret = 0;
-
 	if (!--sb->s_count) {
+		list_del_init(&sb->s_list);
 		destroy_super(sb);
-		ret = 1;
-	}
-	return ret;
-}
-
-/*
- * Drop a superblock's refcount.
- * Returns non-zero if the superblock is about to be destroyed and
- * at least is already removed from super_blocks list, so if we are
- * making a loop through super blocks then we need to restart.
- * The caller must hold sb_lock.
- */
-int __put_super_and_need_restart(struct super_block *sb)
-{
-	/* check for race with generic_shutdown_super() */
-	if (list_empty(&sb->s_list)) {
-		/* super block is removed, need to restart... */
-		__put_super(sb);
-		return 1;
 	}
-	/* can't be the last, since s_list is still in use */
-	sb->s_count--;
-	BUG_ON(sb->s_count == 0);
-	return 0;
 }
 
 /**
@@ -178,57 +143,47 @@ void put_super(struct super_block *sb)
 
 
 /**
- *	deactivate_super	-	drop an active reference to superblock
+ *	deactivate_locked_super	-	drop an active reference to superblock
  *	@s: superblock to deactivate
  *
- *	Drops an active reference to superblock, acquiring a temprory one if
- *	there is no active references left.  In that case we lock superblock,
+ *	Drops an active reference to superblock, converting it into a temprory
+ *	one if there is no other active references left.  In that case we
  *	tell fs driver to shut it down and drop the temporary reference we
  *	had just acquired.
+ *
+ *	Caller holds exclusive lock on superblock; that lock is released.
  */
-void deactivate_super(struct super_block *s)
+void deactivate_locked_super(struct super_block *s)
 {
 	struct file_system_type *fs = s->s_type;
-	if (atomic_dec_and_lock(&s->s_active, &sb_lock)) {
-		s->s_count -= S_BIAS-1;
-		spin_unlock(&sb_lock);
-		vfs_dq_off(s, 0);
-		down_write(&s->s_umount);
+	if (atomic_dec_and_test(&s->s_active)) {
 		fs->kill_sb(s);
 		put_filesystem(fs);
 		put_super(s);
+	} else {
+		up_write(&s->s_umount);
 	}
 }
 
-EXPORT_SYMBOL(deactivate_super);
+EXPORT_SYMBOL(deactivate_locked_super);
 
 /**
- *	deactivate_locked_super	-	drop an active reference to superblock
+ *	deactivate_super	-	drop an active reference to superblock
  *	@s: superblock to deactivate
  *
- *	Equivalent of up_write(&s->s_umount); deactivate_super(s);, except that
- *	it does not unlock it until it's all over.  As the result, it's safe to
- *	use to dispose of new superblock on ->get_sb() failure exits - nobody
- *	will see the sucker until it's all over.  Equivalent using up_write +
- *	deactivate_super is safe for that purpose only if superblock is either
- *	safe to use or has NULL ->s_root when we unlock.
+ *	Variant of deactivate_locked_super(), except that superblock is *not*
+ *	locked by caller.  If we are going to drop the final active reference,
+ *	lock will be acquired prior to that.
  */
-void deactivate_locked_super(struct super_block *s)
+void deactivate_super(struct super_block *s)
 {
-	struct file_system_type *fs = s->s_type;
-	if (atomic_dec_and_lock(&s->s_active, &sb_lock)) {
-		s->s_count -= S_BIAS-1;
-		spin_unlock(&sb_lock);
-		vfs_dq_off(s, 0);
-		fs->kill_sb(s);
-		put_filesystem(fs);
-		put_super(s);
-	} else {
-		up_write(&s->s_umount);
+        if (!atomic_add_unless(&s->s_active, -1, 1)) {
+		down_write(&s->s_umount);
+		deactivate_locked_super(s);
 	}
 }
 
-EXPORT_SYMBOL(deactivate_locked_super);
+EXPORT_SYMBOL(deactivate_super);
 
 /**
  *	grab_super - acquire an active reference
@@ -243,22 +198,17 @@ EXPORT_SYMBOL(deactivate_locked_super);
  */
 static int grab_super(struct super_block *s) __releases(sb_lock)
 {
+	if (atomic_inc_not_zero(&s->s_active)) {
+		spin_unlock(&sb_lock);
+		return 1;
+	}
+	/* it's going away */
 	s->s_count++;
 	spin_unlock(&sb_lock);
+	/* wait for it to die */
 	down_write(&s->s_umount);
-	if (s->s_root) {
-		spin_lock(&sb_lock);
-		if (s->s_count > S_BIAS) {
-			atomic_inc(&s->s_active);
-			s->s_count--;
-			spin_unlock(&sb_lock);
-			return 1;
-		}
-		spin_unlock(&sb_lock);
-	}
 	up_write(&s->s_umount);
 	put_super(s);
-	yield();
 	return 0;
 }
 
@@ -321,8 +271,7 @@ void generic_shutdown_super(struct super_block *sb)
 	}
 	spin_lock(&sb_lock);
 	/* should be initialized for __put_super_and_need_restart() */
-	list_del_init(&sb->s_list);
-	list_del(&sb->s_instances);
+	list_del_init(&sb->s_instances);
 	spin_unlock(&sb_lock);
 	up_write(&sb->s_umount);
 }
@@ -357,6 +306,7 @@ retry:
 				up_write(&s->s_umount);
 				destroy_super(s);
 			}
+			down_write(&old->s_umount);
 			return old;
 		}
 	}
@@ -408,11 +358,12 @@ EXPORT_SYMBOL(drop_super);
  */
 void sync_supers(void)
 {
-	struct super_block *sb;
+	struct super_block *sb, *n;
 
 	spin_lock(&sb_lock);
-restart:
-	list_for_each_entry(sb, &super_blocks, s_list) {
+	list_for_each_entry_safe(sb, n, &super_blocks, s_list) {
+		if (list_empty(&sb->s_instances))
+			continue;
 		if (sb->s_op->write_super && sb->s_dirt) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
@@ -423,14 +374,43 @@ restart:
 			up_read(&sb->s_umount);
 
 			spin_lock(&sb_lock);
-			if (__put_super_and_need_restart(sb))
-				goto restart;
+			__put_super(sb);
 		}
 	}
 	spin_unlock(&sb_lock);
 }
 
 /**
+ *	iterate_supers - call function for all active superblocks
+ *	@f: function to call
+ *	@arg: argument to pass to it
+ *
+ *	Scans the superblock list and calls given function, passing it
+ *	locked superblock and given argument.
+ */
+void iterate_supers(void (*f)(struct super_block *, void *), void *arg)
+{
+	struct super_block *sb, *n;
+
+	spin_lock(&sb_lock);
+	list_for_each_entry_safe(sb, n, &super_blocks, s_list) {
+		if (list_empty(&sb->s_instances))
+			continue;
+		sb->s_count++;
+		spin_unlock(&sb_lock);
+
+		down_read(&sb->s_umount);
+		if (sb->s_root)
+			f(sb, arg);
+		up_read(&sb->s_umount);
+
+		spin_lock(&sb_lock);
+		__put_super(sb);
+	}
+	spin_unlock(&sb_lock);
+}
+
+/**
  *	get_super - get the superblock of a device
  *	@bdev: device to get the superblock for
  *	
@@ -438,7 +418,7 @@ restart:
  *	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 *get_super(struct block_device *bdev)
 {
 	struct super_block *sb;
 
@@ -448,17 +428,20 @@ struct super_block * get_super(struct block_device *bdev)
 	spin_lock(&sb_lock);
 rescan:
 	list_for_each_entry(sb, &super_blocks, s_list) {
+		if (list_empty(&sb->s_instances))
+			continue;
 		if (sb->s_bdev == bdev) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
 			down_read(&sb->s_umount);
+			/* still alive? */
 			if (sb->s_root)
 				return sb;
 			up_read(&sb->s_umount);
-			/* restart only when sb is no longer on the list */
+			/* nope, got unmounted */
 			spin_lock(&sb_lock);
-			if (__put_super_and_need_restart(sb))
-				goto rescan;
+			__put_super(sb);
+			goto rescan;
 		}
 	}
 	spin_unlock(&sb_lock);
@@ -473,7 +456,7 @@ EXPORT_SYMBOL(get_super);
  *
  * Scans the superblock list and finds the superblock of the file system
  * mounted on the device given.  Returns the superblock with an active
- * reference and s_umount held exclusively or %NULL if none was found.
+ * reference or %NULL if none was found.
  */
 struct super_block *get_active_super(struct block_device *bdev)
 {
@@ -482,81 +465,49 @@ struct super_block *get_active_super(struct block_device *bdev)
 	if (!bdev)
 		return NULL;
 
+restart:
 	spin_lock(&sb_lock);
 	list_for_each_entry(sb, &super_blocks, s_list) {
-		if (sb->s_bdev != bdev)
+		if (list_empty(&sb->s_instances))
 			continue;
-
-		sb->s_count++;
-		spin_unlock(&sb_lock);
-		down_write(&sb->s_umount);
-		if (sb->s_root) {
-			spin_lock(&sb_lock);
-			if (sb->s_count > S_BIAS) {
-				atomic_inc(&sb->s_active);
-				sb->s_count--;
-				spin_unlock(&sb_lock);
+		if (sb->s_bdev == bdev) {
+			if (grab_super(sb)) /* drops sb_lock */
 				return sb;
-			}
-			spin_unlock(&sb_lock);
+			else
+				goto restart;
 		}
-		up_write(&sb->s_umount);
-		put_super(sb);
-		yield();
-		spin_lock(&sb_lock);
 	}
 	spin_unlock(&sb_lock);
 	return NULL;
 }
  
-struct super_block * user_get_super(dev_t dev)
+struct super_block *user_get_super(dev_t dev)
 {
 	struct super_block *sb;
 
 	spin_lock(&sb_lock);
 rescan:
 	list_for_each_entry(sb, &super_blocks, s_list) {
+		if (list_empty(&sb->s_instances))
+			continue;
 		if (sb->s_dev ==  dev) {
 			sb->s_count++;
 			spin_unlock(&sb_lock);
 			down_read(&sb->s_umount);
+			/* still alive? */
 			if (sb->s_root)
 				return sb;
 			up_read(&sb->s_umount);
-			/* restart only when sb is no longer on the list */
+			/* nope, got unmounted */
 			spin_lock(&sb_lock);
-			if (__put_super_and_need_restart(sb))
-				goto rescan;
+			__put_super(sb);
+			goto rescan;
 		}
 	}
 	spin_unlock(&sb_lock);
 	return NULL;
 }
 
-SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf)
-{
-        struct super_block *s;
-        struct ustat tmp;
-        struct kstatfs sbuf;
-	int err = -EINVAL;
-
-        s = user_get_super(new_decode_dev(dev));
-        if (s == NULL)
-                goto out;
-	err = vfs_statfs(s->s_root, &sbuf);
-	drop_super(s);
-	if (err)
-		goto out;
-
-        memset(&tmp,0,sizeof(struct ustat));
-        tmp.f_tfree = sbuf.f_bfree;
-        tmp.f_tinode = sbuf.f_ffree;
-
-        err = copy_to_user(ubuf,&tmp,sizeof(struct ustat)) ? -EFAULT : 0;
-out:
-	return err;
-}
-
 /**
  *	do_remount_sb - asks filesystem to change mount options.
  *	@sb:	superblock in question
@@ -569,7 +520,7 @@ out:
 int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 {
 	int retval;
-	int remount_rw, remount_ro;
+	int remount_ro;
 
 	if (sb->s_frozen != SB_UNFROZEN)
 		return -EBUSY;
@@ -585,7 +536,6 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 	sync_filesystem(sb);
 
 	remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY);
-	remount_rw = !(flags & MS_RDONLY) && (sb->s_flags & MS_RDONLY);
 
 	/* If we are remounting RDONLY and current sb is read/write,
 	   make sure there are no rw files opened */
@@ -594,9 +544,6 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 			mark_files_ro(sb);
 		else if (!fs_may_remount_ro(sb))
 			return -EBUSY;
-		retval = vfs_dq_off(sb, 1);
-		if (retval < 0 && retval != -ENOSYS)
-			return -EBUSY;
 	}
 
 	if (sb->s_op->remount_fs) {
@@ -605,8 +552,7 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 			return retval;
 	}
 	sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK);
-	if (remount_rw)
-		vfs_dq_quota_on_remount(sb);
+
 	/*
 	 * Some filesystems modify their metadata via some other path than the
 	 * bdev buffer cache (eg. use a private mapping, or directories in
@@ -622,24 +568,24 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 
 static void do_emergency_remount(struct work_struct *work)
 {
-	struct super_block *sb;
+	struct super_block *sb, *n;
 
 	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &super_blocks, s_list) {
+	list_for_each_entry_safe(sb, n, &super_blocks, s_list) {
+		if (list_empty(&sb->s_instances))
+			continue;
 		sb->s_count++;
 		spin_unlock(&sb_lock);
 		down_write(&sb->s_umount);
 		if (sb->s_root && sb->s_bdev && !(sb->s_flags & MS_RDONLY)) {
 			/*
-			 * ->remount_fs needs lock_kernel().
-			 *
 			 * What lock protects sb->s_flags??
 			 */
 			do_remount_sb(sb, MS_RDONLY, NULL, 1);
 		}
 		up_write(&sb->s_umount);
-		put_super(sb);
 		spin_lock(&sb_lock);
+		__put_super(sb);
 	}
 	spin_unlock(&sb_lock);
 	kfree(work);
@@ -990,6 +936,96 @@ out:
 
 EXPORT_SYMBOL_GPL(vfs_kern_mount);
 
+/**
+ * freeze_super - lock the filesystem and force it into a consistent state
+ * @sb: the super to lock
+ *
+ * Syncs the super to make sure the filesystem is consistent and calls the fs's
+ * freeze_fs.  Subsequent calls to this without first thawing the fs will return
+ * -EBUSY.
+ */
+int freeze_super(struct super_block *sb)
+{
+	int ret;
+
+	atomic_inc(&sb->s_active);
+	down_write(&sb->s_umount);
+	if (sb->s_frozen) {
+		deactivate_locked_super(sb);
+		return -EBUSY;
+	}
+
+	if (sb->s_flags & MS_RDONLY) {
+		sb->s_frozen = SB_FREEZE_TRANS;
+		smp_wmb();
+		up_write(&sb->s_umount);
+		return 0;
+	}
+
+	sb->s_frozen = SB_FREEZE_WRITE;
+	smp_wmb();
+
+	sync_filesystem(sb);
+
+	sb->s_frozen = SB_FREEZE_TRANS;
+	smp_wmb();
+
+	sync_blockdev(sb->s_bdev);
+	if (sb->s_op->freeze_fs) {
+		ret = sb->s_op->freeze_fs(sb);
+		if (ret) {
+			printk(KERN_ERR
+				"VFS:Filesystem freeze failed\n");
+			sb->s_frozen = SB_UNFROZEN;
+			deactivate_locked_super(sb);
+			return ret;
+		}
+	}
+	up_write(&sb->s_umount);
+	return 0;
+}
+EXPORT_SYMBOL(freeze_super);
+
+/**
+ * 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)
+{
+	int error;
+
+	down_write(&sb->s_umount);
+	if (sb->s_frozen == SB_UNFROZEN) {
+		up_write(&sb->s_umount);
+		return -EINVAL;
+	}
+
+	if (sb->s_flags & MS_RDONLY)
+		goto out;
+
+	if (sb->s_op->unfreeze_fs) {
+		error = sb->s_op->unfreeze_fs(sb);
+		if (error) {
+			printk(KERN_ERR
+				"VFS:Filesystem thaw failed\n");
+			sb->s_frozen = SB_FREEZE_TRANS;
+			up_write(&sb->s_umount);
+			return error;
+		}
+	}
+
+out:
+	sb->s_frozen = SB_UNFROZEN;
+	smp_wmb();
+	wake_up(&sb->s_wait_unfrozen);
+	deactivate_locked_super(sb);
+
+	return 0;
+}
+EXPORT_SYMBOL(thaw_super);
+
 static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
 {
 	int err;