Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull vfs fixes from Al Viro:
"Tmpfs readdir throughput regression fix (this cycle) + some -stable
fodder all over the place.
One missing bit is Miklos' tonight locks.c fix - NFS folks had already
grabbed that one by the time I woke up ;-)"
[ The locks.c fix came through the nfsd tree just moments ago ]
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
namespace: update event counter when umounting a deleted dentry
9p: use file_dentry()
ceph: fix d_obtain_alias() misuses
lockless next_positive()
libfs.c: new helper - next_positive()
dcache_{readdir,dir_lseek}(): don't bother with nested ->d_lock
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index b84c291..d7b78d5 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -74,7 +74,7 @@
v9fs_proto_dotu(v9ses));
fid = file->private_data;
if (!fid) {
- fid = v9fs_fid_clone(file->f_path.dentry);
+ fid = v9fs_fid_clone(file_dentry(file));
if (IS_ERR(fid))
return PTR_ERR(fid);
@@ -100,7 +100,7 @@
* because we want write after unlink usecase
* to work.
*/
- fid = v9fs_writeback_fid(file->f_path.dentry);
+ fid = v9fs_writeback_fid(file_dentry(file));
if (IS_ERR(fid)) {
err = PTR_ERR(fid);
mutex_unlock(&v9inode->v_mutex);
@@ -516,7 +516,7 @@
* because we want write after unlink usecase
* to work.
*/
- fid = v9fs_writeback_fid(filp->f_path.dentry);
+ fid = v9fs_writeback_fid(file_dentry(filp));
if (IS_ERR(fid)) {
retval = PTR_ERR(fid);
mutex_unlock(&v9inode->v_mutex);
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 6e72c98..1780218 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -95,10 +95,8 @@
}
dentry = d_obtain_alias(inode);
- if (IS_ERR(dentry)) {
- iput(inode);
+ if (IS_ERR(dentry))
return dentry;
- }
err = ceph_init_dentry(dentry);
if (err < 0) {
dput(dentry);
@@ -167,10 +165,8 @@
return ERR_PTR(-ENOENT);
dentry = d_obtain_alias(inode);
- if (IS_ERR(dentry)) {
- iput(inode);
+ if (IS_ERR(dentry))
return dentry;
- }
err = ceph_init_dentry(dentry);
if (err < 0) {
dput(dentry);
@@ -210,7 +206,7 @@
dout("fh_to_parent %llx\n", cfh->parent_ino);
dentry = __get_parent(sb, NULL, cfh->ino);
- if (IS_ERR(dentry) && PTR_ERR(dentry) == -ENOENT)
+ if (unlikely(dentry == ERR_PTR(-ENOENT)))
dentry = __fh_to_dentry(sb, cfh->parent_ino);
return dentry;
}
diff --git a/fs/libfs.c b/fs/libfs.c
index cedeacb..74dc8b9 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -84,6 +84,61 @@
}
EXPORT_SYMBOL(dcache_dir_close);
+/* parent is locked at least shared */
+static struct dentry *next_positive(struct dentry *parent,
+ struct list_head *from,
+ int count)
+{
+ unsigned *seq = &parent->d_inode->i_dir_seq, n;
+ struct dentry *res;
+ struct list_head *p;
+ bool skipped;
+ int i;
+
+retry:
+ i = count;
+ skipped = false;
+ n = smp_load_acquire(seq) & ~1;
+ res = NULL;
+ rcu_read_lock();
+ for (p = from->next; p != &parent->d_subdirs; p = p->next) {
+ struct dentry *d = list_entry(p, struct dentry, d_child);
+ if (!simple_positive(d)) {
+ skipped = true;
+ } else if (!--i) {
+ res = d;
+ break;
+ }
+ }
+ rcu_read_unlock();
+ if (skipped) {
+ smp_rmb();
+ if (unlikely(*seq != n))
+ goto retry;
+ }
+ return res;
+}
+
+static void move_cursor(struct dentry *cursor, struct list_head *after)
+{
+ struct dentry *parent = cursor->d_parent;
+ unsigned n, *seq = &parent->d_inode->i_dir_seq;
+ spin_lock(&parent->d_lock);
+ for (;;) {
+ n = *seq;
+ if (!(n & 1) && cmpxchg(seq, n, n + 1) == n)
+ break;
+ cpu_relax();
+ }
+ __list_del(cursor->d_child.prev, cursor->d_child.next);
+ if (after)
+ list_add(&cursor->d_child, after);
+ else
+ list_add_tail(&cursor->d_child, &parent->d_subdirs);
+ smp_store_release(seq, n + 2);
+ spin_unlock(&parent->d_lock);
+}
+
loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
{
struct dentry *dentry = file->f_path.dentry;
@@ -99,25 +154,14 @@
if (offset != file->f_pos) {
file->f_pos = offset;
if (file->f_pos >= 2) {
- struct list_head *p;
struct dentry *cursor = file->private_data;
+ struct dentry *to;
loff_t n = file->f_pos - 2;
- spin_lock(&dentry->d_lock);
- /* d_lock not required for cursor */
- list_del(&cursor->d_child);
- p = dentry->d_subdirs.next;
- while (n && p != &dentry->d_subdirs) {
- struct dentry *next;
- next = list_entry(p, struct dentry, d_child);
- spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
- if (simple_positive(next))
- n--;
- spin_unlock(&next->d_lock);
- p = p->next;
- }
- list_add_tail(&cursor->d_child, p);
- spin_unlock(&dentry->d_lock);
+ inode_lock_shared(dentry->d_inode);
+ to = next_positive(dentry, &dentry->d_subdirs, n);
+ move_cursor(cursor, to ? &to->d_child : NULL);
+ inode_unlock_shared(dentry->d_inode);
}
}
return offset;
@@ -140,36 +184,25 @@
{
struct dentry *dentry = file->f_path.dentry;
struct dentry *cursor = file->private_data;
- struct list_head *p, *q = &cursor->d_child;
+ struct list_head *p = &cursor->d_child;
+ struct dentry *next;
+ bool moved = false;
if (!dir_emit_dots(file, ctx))
return 0;
- spin_lock(&dentry->d_lock);
+
if (ctx->pos == 2)
- list_move(q, &dentry->d_subdirs);
-
- for (p = q->next; p != &dentry->d_subdirs; p = p->next) {
- struct dentry *next = list_entry(p, struct dentry, d_child);
- spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
- if (!simple_positive(next)) {
- spin_unlock(&next->d_lock);
- continue;
- }
-
- spin_unlock(&next->d_lock);
- spin_unlock(&dentry->d_lock);
+ p = &dentry->d_subdirs;
+ while ((next = next_positive(dentry, p, 1)) != NULL) {
if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
d_inode(next)->i_ino, dt_type(d_inode(next))))
- return 0;
- spin_lock(&dentry->d_lock);
- spin_lock_nested(&next->d_lock, DENTRY_D_LOCK_NESTED);
- /* next is still alive */
- list_move(q, p);
- spin_unlock(&next->d_lock);
- p = q;
+ break;
+ moved = true;
+ p = &next->d_child;
ctx->pos++;
}
- spin_unlock(&dentry->d_lock);
+ if (moved)
+ move_cursor(cursor, p);
return 0;
}
EXPORT_SYMBOL(dcache_readdir);
diff --git a/fs/namespace.c b/fs/namespace.c
index 783004a..419f746 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1562,6 +1562,7 @@
goto out_unlock;
lock_mount_hash();
+ event++;
while (!hlist_empty(&mp->m_list)) {
mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
if (mnt->mnt.mnt_flags & MNT_UMOUNT) {