Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull third set of VFS updates from Al Viro:
 "Misc stuff all over the place.  There will be one more pile in a
  couple of days"

This is an "evil merge" that also uses the new d_count helper in
fs/configfs/dir.c, missed by commit 84d08fa888e7 ("helper for reading
->d_count")

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  ncpfs: fix error return code in ncp_parse_options()
  locks: move file_lock_list to a set of percpu hlist_heads and convert file_lock_lock to an lglock
  seq_file: add seq_list_*_percpu helpers
  f2fs: fix readdir incorrectness
  mode_t whack-a-mole...
  lustre: kill the pointless wrapper
  helper for reading ->d_count

14 files changed, 138 insertions, 51 deletions

diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 13ddec92341..3d9d3f5d5dd 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -109,7 +109,7 @@ cont:
 
 	spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED);
 	/* Already gone or negative dentry (under construction) - try next */
-	if (q->d_count == 0 || !simple_positive(q)) {
+	if (!d_count(q) || !simple_positive(q)) {
 		spin_unlock(&q->d_lock);
 		next = q->d_u.d_child.next;
 		goto cont;
@@ -267,7 +267,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
 			else
 				ino_count++;
 
-			if (p->d_count > ino_count) {
+			if (d_count(p) > ino_count) {
 				top_ino->last_used = jiffies;
 				dput(p);
 				return 1;
@@ -409,7 +409,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 		if (!exp_leaves) {
 			/* Path walk currently on this dentry? */
 			ino_count = atomic_read(&ino->count) + 1;
-			if (dentry->d_count > ino_count)
+			if (d_count(dentry) > ino_count)
 				goto next;
 
 			if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) {
@@ -423,7 +423,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 		} else {
 			/* Path walk currently on this dentry? */
 			ino_count = atomic_read(&ino->count) + 1;
-			if (dentry->d_count > ino_count)
+			if (d_count(dentry) > ino_count)
 				goto next;
 
 			expired = autofs4_check_leaves(mnt, dentry, timeout, do_now);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index ca8e55548d9..92ef341ba0c 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -179,7 +179,7 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
 		spin_lock(&active->d_lock);
 
 		/* Already gone? */
-		if (active->d_count == 0)
+		if (!d_count(active))
 			goto next;
 
 		qstr = &active->d_name;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index be0f7e20d62..bd2289a4f40 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -903,8 +903,8 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 	} else if (realdn) {
 		dout("dn %p (%d) spliced with %p (%d) "
 		     "inode %p ino %llx.%llx\n",
-		     dn, dn->d_count,
-		     realdn, realdn->d_count,
+		     dn, d_count(dn),
+		     realdn, d_count(realdn),
 		     realdn->d_inode, ceph_vinop(realdn->d_inode));
 		dput(dn);
 		dn = realdn;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 74fd2898b2a..99890b02a10 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1553,7 +1553,7 @@ retry:
 	*base = ceph_ino(temp->d_inode);
 	*plen = len;
 	dout("build_path on %p %d built %llx '%.*s'\n",
-	     dentry, dentry->d_count, *base, len, path);
+	     dentry, d_count(dentry), *base, len, path);
 	return path;
 }
 
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 14a14808320..190effc6a6f 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -526,7 +526,7 @@ static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
 	if (cii->c_flags & C_FLUSH) 
 		coda_flag_inode_children(inode, C_FLUSH);
 
-	if (de->d_count > 1)
+	if (d_count(de) > 1)
 		/* pretend it's valid, but don't change the flags */
 		goto out;
 
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 64e5323cbbb..5e7c60c1cb6 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -387,7 +387,7 @@ static void remove_dir(struct dentry * d)
 	if (d->d_inode)
 		simple_rmdir(parent->d_inode,d);
 
-	pr_debug(" o %s removing done (%d)\n",d->d_name.name, d->d_count);
+	pr_debug(" o %s removing done (%d)\n",d->d_name.name, d_count(d));
 
 	dput(parent);
 }
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index a2f2bb2c256..67e9b633969 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -358,7 +358,7 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
 
 	lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent));
 	fsstack_copy_attr_atime(dir_inode, lower_dentry->d_parent->d_inode);
-	BUG_ON(!lower_dentry->d_count);
+	BUG_ON(!d_count(lower_dentry));
 
 	ecryptfs_set_dentry_private(dentry, dentry_info);
 	ecryptfs_set_dentry_lower(dentry, lower_dentry);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 9d1cd423450..62f0d5977c6 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -610,13 +610,12 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct inode *inode = file_inode(file);
 	unsigned long npages = dir_blocks(inode);
-	unsigned int bit_pos = 0, start_bit_pos = 0;
+	unsigned int bit_pos = 0;
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	struct f2fs_dir_entry *de = NULL;
 	struct page *dentry_page = NULL;
 	unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
 	unsigned char d_type = DT_UNKNOWN;
-	int slots;
 
 	bit_pos = ((unsigned long)ctx->pos % NR_DENTRY_IN_BLOCK);
 
@@ -625,7 +624,6 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 		if (IS_ERR(dentry_page))
 			continue;
 
-		start_bit_pos = bit_pos;
 		dentry_blk = kmap(dentry_page);
 		while (bit_pos < NR_DENTRY_IN_BLOCK) {
 			bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
@@ -634,19 +632,19 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 			if (bit_pos >= NR_DENTRY_IN_BLOCK)
 				break;
 
-			ctx->pos += bit_pos - start_bit_pos;
 			de = &dentry_blk->dentry[bit_pos];
 			if (de->file_type < F2FS_FT_MAX)
 				d_type = f2fs_filetype_table[de->file_type];
 			else
 				d_type = DT_UNKNOWN;
 			if (!dir_emit(ctx,
-				      dentry_blk->filename[bit_pos],
-				      le16_to_cpu(de->name_len),
-				      le32_to_cpu(de->ino), d_type))
-				goto success;
-			slots = GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
-			bit_pos += slots;
+					dentry_blk->filename[bit_pos],
+					le16_to_cpu(de->name_len),
+					le32_to_cpu(de->ino), d_type))
+				goto stop;
+
+			bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+			ctx->pos = n * NR_DENTRY_IN_BLOCK + bit_pos;
 		}
 		bit_pos = 0;
 		ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK;
@@ -654,7 +652,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 		f2fs_put_page(dentry_page, 1);
 		dentry_page = NULL;
 	}
-success:
+stop:
 	if (dentry_page && !IS_ERR(dentry_page)) {
 		kunmap(dentry_page);
 		f2fs_put_page(dentry_page, 1);
diff --git a/fs/locks.c b/fs/locks.c
index 04e2c1fdb15..b27a3005d78 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -127,6 +127,8 @@
 #include <linux/rcupdate.h>
 #include <linux/pid_namespace.h>
 #include <linux/hashtable.h>
+#include <linux/percpu.h>
+#include <linux/lglock.h>
 
 #include <asm/uaccess.h>
 
@@ -155,11 +157,13 @@ int lease_break_time = 45;
 	for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next)
 
 /*
- * The global file_lock_list is only used for displaying /proc/locks. Protected
- * by the file_lock_lock.
+ * The global file_lock_list is only used for displaying /proc/locks, so we
+ * keep a list on each CPU, with each list protected by its own spinlock via
+ * the file_lock_lglock. Note that alterations to the list also require that
+ * the relevant i_lock is held.
  */
-static HLIST_HEAD(file_lock_list);
-static DEFINE_SPINLOCK(file_lock_lock);
+DEFINE_STATIC_LGLOCK(file_lock_lglock);
+static DEFINE_PER_CPU(struct hlist_head, file_lock_list);
 
 /*
  * The blocked_hash is used to find POSIX lock loops for deadlock detection.
@@ -506,20 +510,30 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
 	return fl1->fl_owner == fl2->fl_owner;
 }
 
+/* Must be called with the i_lock held! */
 static inline void
 locks_insert_global_locks(struct file_lock *fl)
 {
-	spin_lock(&file_lock_lock);
-	hlist_add_head(&fl->fl_link, &file_lock_list);
-	spin_unlock(&file_lock_lock);
+	lg_local_lock(&file_lock_lglock);
+	fl->fl_link_cpu = smp_processor_id();
+	hlist_add_head(&fl->fl_link, this_cpu_ptr(&file_lock_list));
+	lg_local_unlock(&file_lock_lglock);
 }
 
+/* Must be called with the i_lock held! */
 static inline void
 locks_delete_global_locks(struct file_lock *fl)
 {
-	spin_lock(&file_lock_lock);
+	/*
+	 * Avoid taking lock if already unhashed. This is safe since this check
+	 * is done while holding the i_lock, and new insertions into the list
+	 * also require that it be held.
+	 */
+	if (hlist_unhashed(&fl->fl_link))
+		return;
+	lg_local_lock_cpu(&file_lock_lglock, fl->fl_link_cpu);
 	hlist_del_init(&fl->fl_link);
-	spin_unlock(&file_lock_lock);
+	lg_local_unlock_cpu(&file_lock_lglock, fl->fl_link_cpu);
 }
 
 static unsigned long
@@ -1454,7 +1468,7 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
 		goto out;
 	if ((arg == F_WRLCK)
-	    && ((dentry->d_count > 1)
+	    && ((d_count(dentry) > 1)
 		|| (atomic_read(&inode->i_count) > 1)))
 		goto out;
 
@@ -2243,6 +2257,11 @@ EXPORT_SYMBOL_GPL(vfs_cancel_lock);
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
+struct locks_iterator {
+	int	li_cpu;
+	loff_t	li_pos;
+};
+
 static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 			    loff_t id, char *pfx)
 {
@@ -2316,39 +2335,41 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 
 static int locks_show(struct seq_file *f, void *v)
 {
+	struct locks_iterator *iter = f->private;
 	struct file_lock *fl, *bfl;
 
 	fl = hlist_entry(v, struct file_lock, fl_link);
 
-	lock_get_status(f, fl, *((loff_t *)f->private), "");
+	lock_get_status(f, fl, iter->li_pos, "");
 
 	list_for_each_entry(bfl, &fl->fl_block, fl_block)
-		lock_get_status(f, bfl, *((loff_t *)f->private), " ->");
+		lock_get_status(f, bfl, iter->li_pos, " ->");
 
 	return 0;
 }
 
 static void *locks_start(struct seq_file *f, loff_t *pos)
 {
-	loff_t *p = f->private;
+	struct locks_iterator *iter = f->private;
 
-	spin_lock(&file_lock_lock);
+	iter->li_pos = *pos + 1;
+	lg_global_lock(&file_lock_lglock);
 	spin_lock(&blocked_lock_lock);
-	*p = (*pos + 1);
-	return seq_hlist_start(&file_lock_list, *pos);
+	return seq_hlist_start_percpu(&file_lock_list, &iter->li_cpu, *pos);
 }
 
 static void *locks_next(struct seq_file *f, void *v, loff_t *pos)
 {
-	loff_t *p = f->private;
-	++*p;
-	return seq_hlist_next(v, &file_lock_list, pos);
+	struct locks_iterator *iter = f->private;
+
+	++iter->li_pos;
+	return seq_hlist_next_percpu(v, &file_lock_list, &iter->li_cpu, pos);
 }
 
 static void locks_stop(struct seq_file *f, void *v)
 {
 	spin_unlock(&blocked_lock_lock);
-	spin_unlock(&file_lock_lock);
+	lg_global_unlock(&file_lock_lglock);
 }
 
 static const struct seq_operations locks_seq_operations = {
@@ -2360,7 +2381,8 @@ static const struct seq_operations locks_seq_operations = {
 
 static int locks_open(struct inode *inode, struct file *filp)
 {
-	return seq_open_private(filp, &locks_seq_operations, sizeof(loff_t));
+	return seq_open_private(filp, &locks_seq_operations,
+					sizeof(struct locks_iterator));
 }
 
 static const struct file_operations proc_locks_operations = {
@@ -2460,9 +2482,16 @@ EXPORT_SYMBOL(lock_may_write);
 
 static int __init filelock_init(void)
 {
+	int i;
+
 	filelock_cache = kmem_cache_create("file_lock_cache",
 			sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
 
+	lg_lock_init(&file_lock_lglock, "file_lock_lglock");
+
+	for_each_possible_cpu(i)
+		INIT_HLIST_HEAD(per_cpu_ptr(&file_lock_list, i));
+
 	return 0;
 }
 
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 0765ad12c38..4659da67e7f 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -403,18 +403,24 @@ static int ncp_parse_options(struct ncp_mount_data_kernel *data, char *options)
 		switch (optval) {
 			case 'u':
 				data->uid = make_kuid(current_user_ns(), optint);
-				if (!uid_valid(data->uid))
+				if (!uid_valid(data->uid)) {
+					ret = -EINVAL;
 					goto err;
+				}
 				break;
 			case 'g':
 				data->gid = make_kgid(current_user_ns(), optint);
-				if (!gid_valid(data->gid))
+				if (!gid_valid(data->gid)) {
+					ret = -EINVAL;
 					goto err;
+				}
 				break;
 			case 'o':
 				data->mounted_uid = make_kuid(current_user_ns(), optint);
-				if (!uid_valid(data->mounted_uid))
+				if (!uid_valid(data->mounted_uid)) {
+					ret = -EINVAL;
 					goto err;
+				}
 				break;
 			case 'm':
 				data->file_mode = optint;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index d7ed697133f..c933bdfbcb1 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1721,7 +1721,7 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry)
 		dir->i_ino, dentry->d_name.name);
 
 	spin_lock(&dentry->d_lock);
-	if (dentry->d_count > 1) {
+	if (d_count(dentry) > 1) {
 		spin_unlock(&dentry->d_lock);
 		/* Start asynchronous writeout of the inode */
 		write_inode_now(dentry->d_inode, 0);
@@ -1866,7 +1866,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	dfprintk(VFS, "NFS: rename(%s/%s -> %s/%s, ct=%d)\n",
 		 old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
 		 new_dentry->d_parent->d_name.name, new_dentry->d_name.name,
-		 new_dentry->d_count);
+		 d_count(new_dentry));
 
 	/*
 	 * For non-directories, check whether the target is busy and if so,
@@ -1884,7 +1884,7 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			rehash = new_dentry;
 		}
 
-		if (new_dentry->d_count > 2) {
+		if (d_count(new_dentry) > 2) {
 			int err;
 
 			/* copy the target dentry's name */
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 1f1f38f0c5d..60395ad3a2e 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -479,7 +479,7 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 
 	dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
-		dentry->d_count);
+		d_count(dentry));
 	nfs_inc_stats(dir, NFSIOS_SILLYRENAME);
 
 	/*
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 1427de5ebf4..af3ba0478cd 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -996,7 +996,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 
 static int nilfs_tree_was_touched(struct dentry *root_dentry)
 {
-	return root_dentry->d_count > 1;
+	return d_count(root_dentry) > 1;
 }
 
 /**
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 774c1eb7f1c..3135c2525c7 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -921,3 +921,57 @@ struct hlist_node *seq_hlist_next_rcu(void *v,
 		return rcu_dereference(node->next);
 }
 EXPORT_SYMBOL(seq_hlist_next_rcu);
+
+/**
+ * seq_hlist_start_precpu - start an iteration of a percpu hlist array
+ * @head: pointer to percpu array of struct hlist_heads
+ * @cpu:  pointer to cpu "cursor"
+ * @pos:  start position of sequence
+ *
+ * Called at seq_file->op->start().
+ */
+struct hlist_node *
+seq_hlist_start_percpu(struct hlist_head __percpu *head, int *cpu, loff_t pos)
+{
+	struct hlist_node *node;
+
+	for_each_possible_cpu(*cpu) {
+		hlist_for_each(node, per_cpu_ptr(head, *cpu)) {
+			if (pos-- == 0)
+				return node;
+		}
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(seq_hlist_start_percpu);
+
+/**
+ * seq_hlist_next_percpu - move to the next position of the percpu hlist array
+ * @v:    pointer to current hlist_node
+ * @head: pointer to percpu array of struct hlist_heads
+ * @cpu:  pointer to cpu "cursor"
+ * @pos:  start position of sequence
+ *
+ * Called at seq_file->op->next().
+ */
+struct hlist_node *
+seq_hlist_next_percpu(void *v, struct hlist_head __percpu *head,
+			int *cpu, loff_t *pos)
+{
+	struct hlist_node *node = v;
+
+	++*pos;
+
+	if (node->next)
+		return node->next;
+
+	for (*cpu = cpumask_next(*cpu, cpu_possible_mask); *cpu < nr_cpu_ids;
+	     *cpu = cpumask_next(*cpu, cpu_possible_mask)) {
+		struct hlist_head *bucket = per_cpu_ptr(head, *cpu);
+
+		if (!hlist_empty(bucket))
+			return bucket->first;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(seq_hlist_next_percpu);