From 5528f911b4c43a5de5da34bcbd7e3f2a62503617 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 9 Jun 2006 09:34:17 -0400 Subject: VFS: Add shrink_submounts() Allow a submount to be marked as being 'shrinkable' by means of the vfsmount->mnt_flags, and then add a function 'shrink_submounts()' which attempts to recursively unmount these submounts. Signed-off-by: Trond Myklebust --- fs/namespace.c | 124 +++++++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 99 insertions(+), 25 deletions(-) (limited to 'fs/namespace.c') diff --git a/fs/namespace.c b/fs/namespace.c index bf478addb852..b22e469ab560 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1162,6 +1162,40 @@ static void expire_mount(struct vfsmount *mnt, struct list_head *mounts, } } +/* + * go through the vfsmounts we've just consigned to the graveyard to + * - check that they're still dead + * - delete the vfsmount from the appropriate namespace under lock + * - dispose of the corpse + */ +static void expire_mount_list(struct list_head *graveyard, struct list_head *mounts) +{ + struct namespace *namespace; + struct vfsmount *mnt; + + while (!list_empty(graveyard)) { + LIST_HEAD(umounts); + mnt = list_entry(graveyard->next, struct vfsmount, mnt_expire); + list_del_init(&mnt->mnt_expire); + + /* don't do anything if the namespace is dead - all the + * vfsmounts from it are going away anyway */ + namespace = mnt->mnt_namespace; + if (!namespace || !namespace->root) + continue; + get_namespace(namespace); + + spin_unlock(&vfsmount_lock); + down_write(&namespace_sem); + expire_mount(mnt, mounts, &umounts); + up_write(&namespace_sem); + release_mounts(&umounts); + mntput(mnt); + put_namespace(namespace); + spin_lock(&vfsmount_lock); + } +} + /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came @@ -1169,7 +1203,6 @@ static void expire_mount(struct vfsmount *mnt, struct list_head *mounts, */ void mark_mounts_for_expiry(struct list_head *mounts) { - struct namespace *namespace; struct vfsmount *mnt, *next; LIST_HEAD(graveyard); @@ -1193,38 +1226,79 @@ void mark_mounts_for_expiry(struct list_head *mounts) list_move(&mnt->mnt_expire, &graveyard); } - /* - * go through the vfsmounts we've just consigned to the graveyard to - * - check that they're still dead - * - delete the vfsmount from the appropriate namespace under lock - * - dispose of the corpse - */ - while (!list_empty(&graveyard)) { - LIST_HEAD(umounts); - mnt = list_entry(graveyard.next, struct vfsmount, mnt_expire); - list_del_init(&mnt->mnt_expire); + expire_mount_list(&graveyard, mounts); - /* don't do anything if the namespace is dead - all the - * vfsmounts from it are going away anyway */ - namespace = mnt->mnt_namespace; - if (!namespace || !namespace->root) + spin_unlock(&vfsmount_lock); +} + +EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); + +/* + * Ripoff of 'select_parent()' + * + * search the list of submounts for a given mountpoint, and move any + * shrinkable submounts to the 'graveyard' list. + */ +static int select_submounts(struct vfsmount *parent, struct list_head *graveyard) +{ + struct vfsmount *this_parent = parent; + struct list_head *next; + int found = 0; + +repeat: + next = this_parent->mnt_mounts.next; +resume: + while (next != &this_parent->mnt_mounts) { + struct list_head *tmp = next; + struct vfsmount *mnt = list_entry(tmp, struct vfsmount, mnt_child); + + next = tmp->next; + if (!(mnt->mnt_flags & MNT_SHRINKABLE)) continue; - get_namespace(namespace); + /* + * Descend a level if the d_mounts list is non-empty. + */ + if (!list_empty(&mnt->mnt_mounts)) { + this_parent = mnt; + goto repeat; + } - spin_unlock(&vfsmount_lock); - down_write(&namespace_sem); - expire_mount(mnt, mounts, &umounts); - up_write(&namespace_sem); - release_mounts(&umounts); - mntput(mnt); - put_namespace(namespace); - spin_lock(&vfsmount_lock); + if (!propagate_mount_busy(mnt, 1)) { + mntget(mnt); + list_move_tail(&mnt->mnt_expire, graveyard); + found++; + } } + /* + * All done at this level ... ascend and resume the search + */ + if (this_parent != parent) { + next = this_parent->mnt_child.next; + this_parent = this_parent->mnt_parent; + goto resume; + } + return found; +} + +/* + * process a list of expirable mountpoints with the intent of discarding any + * submounts of a specific parent mountpoint + */ +void shrink_submounts(struct vfsmount *mountpoint, struct list_head *mounts) +{ + LIST_HEAD(graveyard); + int found; + + spin_lock(&vfsmount_lock); + + /* extract submounts of 'mountpoint' from the expiration list */ + while ((found = select_submounts(mountpoint, &graveyard)) != 0) + expire_mount_list(&graveyard, mounts); spin_unlock(&vfsmount_lock); } -EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); +EXPORT_SYMBOL_GPL(shrink_submounts); /* * Some copy_from_user() implementations do not return the exact number of -- cgit v1.2.1 From 8b512d9a88875affe584bb3d2a7a235f84343b9e Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 9 Jun 2006 09:34:18 -0400 Subject: VFS: Remove dependency of ->umount_begin() call on MNT_FORCE Allow filesystems to decide to perform pre-umount processing whether or not MNT_FORCE is set. Signed-off-by: Trond Myklebust --- fs/namespace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/namespace.c') diff --git a/fs/namespace.c b/fs/namespace.c index b22e469ab560..6bb0b85293e7 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -576,8 +576,8 @@ static int do_umount(struct vfsmount *mnt, int flags) */ lock_kernel(); - if ((flags & MNT_FORCE) && sb->s_op->umount_begin) - sb->s_op->umount_begin(sb); + if (sb->s_op->umount_begin) + sb->s_op->umount_begin(mnt, flags); unlock_kernel(); /* -- cgit v1.2.1 From 454e2398be9b9fa30433fccc548db34d19aa9958 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 23 Jun 2006 02:02:57 -0700 Subject: [PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells Acked-by: Al Viro Cc: Nathan Scott Cc: Roland Dreier Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/namespace.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'fs/namespace.c') diff --git a/fs/namespace.c b/fs/namespace.c index bf478addb852..c13072a5f1ee 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -86,6 +86,15 @@ struct vfsmount *alloc_vfsmnt(const char *name) return mnt; } +int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb) +{ + mnt->mnt_sb = sb; + mnt->mnt_root = dget(sb->s_root); + return 0; +} + +EXPORT_SYMBOL(simple_set_mnt); + void free_vfsmnt(struct vfsmount *mnt) { kfree(mnt->mnt_devname); -- cgit v1.2.1 From 1bfba4e8ea0e555e3a0296051517d96253660ccc Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Mon, 26 Jun 2006 00:24:40 -0700 Subject: [PATCH] core: use list_move() This patch converts the combination of list_del(A) and list_add(A, B) to list_move(A, B). Cc: Greg Kroah-Hartman Cc: Ram Pai Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/namespace.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'fs/namespace.c') diff --git a/fs/namespace.c b/fs/namespace.c index 866430bb024d..b3ed212ea416 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -526,10 +526,8 @@ void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill) { struct vfsmount *p; - for (p = mnt; p; p = next_mnt(p, mnt)) { - list_del(&p->mnt_hash); - list_add(&p->mnt_hash, kill); - } + for (p = mnt; p; p = next_mnt(p, mnt)) + list_move(&p->mnt_hash, kill); if (propagate) propagate_umount(kill); -- cgit v1.2.1 From 6ab3d5624e172c553004ecc862bfeac16d9d68b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=B6rn=20Engel?= Date: Fri, 30 Jun 2006 19:25:36 +0200 Subject: Remove obsolete #include MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Jörn Engel Signed-off-by: Adrian Bunk --- fs/namespace.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/namespace.c') diff --git a/fs/namespace.c b/fs/namespace.c index b3ed212ea416..fa7ed6a9fc2d 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -8,7 +8,6 @@ * Heavily rewritten. */ -#include #include #include #include -- cgit v1.2.1