Merge branch 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs fixes from Al Viro:
 "Assorted fixes that sat in -next for a while, all over the place"

* 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  aio: Fix locking in aio_poll()
  exec: Fix mem leak in kernel_read_file
  copy_mount_string: Limit string length to PATH_MAX
  cgroup: saner refcounting for cgroup_root
  fix cgroup_do_mount() handling of failure exits

7 files changed, 44 insertions, 65 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 82c08422b0f4..3d9669d011b9 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1666,6 +1666,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
 	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
 	__poll_t mask = key_to_poll(key);
+	unsigned long flags;
 
 	req->woken = true;
 
@@ -1674,10 +1675,15 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 		if (!(mask & req->events))
 			return 0;
 
-		/* try to complete the iocb inline if we can: */
-		if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
+		/*
+		 * Try to complete the iocb inline if we can. Use
+		 * irqsave/irqrestore because not all filesystems (e.g. fuse)
+		 * call this function with IRQs disabled and because IRQs
+		 * have to be disabled before ctx_lock is obtained.
+		 */
+		if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
 			list_del(&iocb->ki_list);
-			spin_unlock(&iocb->ki_ctx->ctx_lock);
+			spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags);
 
 			list_del_init(&req->wait.entry);
 			aio_poll_complete(iocb, mask);
diff --git a/fs/exec.c b/fs/exec.c
index fb72d36f7823..bcf383730bea 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -932,7 +932,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size,
 		bytes = kernel_read(file, *buf + pos, i_size - pos, &pos);
 		if (bytes < 0) {
 			ret = bytes;
-			goto out;
+			goto out_free;
 		}
 
 		if (bytes == 0)
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index fdf527b6d79c..d71c9405874a 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -196,8 +196,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 		return dentry;
 
 	knparent = find_next_ancestor(kn, NULL);
-	if (WARN_ON(!knparent))
+	if (WARN_ON(!knparent)) {
+		dput(dentry);
 		return ERR_PTR(-EINVAL);
+	}
 
 	do {
 		struct dentry *dtmp;
@@ -206,8 +208,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 		if (kn == knparent)
 			return dentry;
 		kntmp = find_next_ancestor(kn, knparent);
-		if (WARN_ON(!kntmp))
+		if (WARN_ON(!kntmp)) {
+			dput(dentry);
 			return ERR_PTR(-EINVAL);
+		}
 		dtmp = lookup_one_len_unlocked(kntmp->name, dentry,
 					       strlen(kntmp->name));
 		dput(dentry);
diff --git a/fs/namespace.c b/fs/namespace.c
index 678ef175d63a..c4e83d94840c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2744,7 +2744,7 @@ void *copy_mount_options(const void __user * data)
 
 char *copy_mount_string(const void __user *data)
 {
-	return data ? strndup_user(data, PAGE_SIZE) : NULL;
+	return data ? strndup_user(data, PATH_MAX) : NULL;
 }
 
 /*
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index c950864016e2..c9a35f09e4b9 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -198,7 +198,7 @@ int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
 
 void cgroup_free_root(struct cgroup_root *root);
 void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts);
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags);
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask);
 int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask);
 struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
 			       struct cgroup_root *root, unsigned long magic,
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 583b969b0c0e..f94a7229974e 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1116,13 +1116,11 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 			     void *data, unsigned long magic,
 			     struct cgroup_namespace *ns)
 {
-	struct super_block *pinned_sb = NULL;
 	struct cgroup_sb_opts opts;
 	struct cgroup_root *root;
 	struct cgroup_subsys *ss;
 	struct dentry *dentry;
 	int i, ret;
-	bool new_root = false;
 
 	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
 
@@ -1184,29 +1182,6 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 		if (root->flags ^ opts.flags)
 			pr_warn("new mount options do not match the existing superblock, will be ignored\n");
 
-		/*
-		 * We want to reuse @root whose lifetime is governed by its
-		 * ->cgrp.  Let's check whether @root is alive and keep it
-		 * that way.  As cgroup_kill_sb() can happen anytime, we
-		 * want to block it by pinning the sb so that @root doesn't
-		 * get killed before mount is complete.
-		 *
-		 * With the sb pinned, tryget_live can reliably indicate
-		 * whether @root can be reused.  If it's being killed,
-		 * drain it.  We can use wait_queue for the wait but this
-		 * path is super cold.  Let's just sleep a bit and retry.
-		 */
-		pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
-		if (IS_ERR(pinned_sb) ||
-		    !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
-			mutex_unlock(&cgroup_mutex);
-			if (!IS_ERR_OR_NULL(pinned_sb))
-				deactivate_super(pinned_sb);
-			msleep(10);
-			ret = restart_syscall();
-			goto out_free;
-		}
-
 		ret = 0;
 		goto out_unlock;
 	}
@@ -1232,15 +1207,20 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 		ret = -ENOMEM;
 		goto out_unlock;
 	}
-	new_root = true;
 
 	init_cgroup_root(root, &opts);
 
-	ret = cgroup_setup_root(root, opts.subsys_mask, PERCPU_REF_INIT_DEAD);
+	ret = cgroup_setup_root(root, opts.subsys_mask);
 	if (ret)
 		cgroup_free_root(root);
 
 out_unlock:
+	if (!ret && !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
+		mutex_unlock(&cgroup_mutex);
+		msleep(10);
+		ret = restart_syscall();
+		goto out_free;
+	}
 	mutex_unlock(&cgroup_mutex);
 out_free:
 	kfree(opts.release_agent);
@@ -1252,25 +1232,13 @@ out_free:
 	dentry = cgroup_do_mount(&cgroup_fs_type, flags, root,
 				 CGROUP_SUPER_MAGIC, ns);
 
-	/*
-	 * There's a race window after we release cgroup_mutex and before
-	 * allocating a superblock. Make sure a concurrent process won't
-	 * be able to re-use the root during this window by delaying the
-	 * initialization of root refcnt.
-	 */
-	if (new_root) {
-		mutex_lock(&cgroup_mutex);
-		percpu_ref_reinit(&root->cgrp.self.refcnt);
-		mutex_unlock(&cgroup_mutex);
+	if (!IS_ERR(dentry) && percpu_ref_is_dying(&root->cgrp.self.refcnt)) {
+		struct super_block *sb = dentry->d_sb;
+		dput(dentry);
+		deactivate_locked_super(sb);
+		msleep(10);
+		dentry = ERR_PTR(restart_syscall());
 	}
-
-	/*
-	 * If @pinned_sb, we're reusing an existing root and holding an
-	 * extra ref on its sb.  Mount is complete.  Put the extra ref.
-	 */
-	if (pinned_sb)
-		deactivate_super(pinned_sb);
-
 	return dentry;
 }
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index f31bd61c9466..7fd9f22e406d 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1927,7 +1927,7 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
 
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 {
 	LIST_HEAD(tmp_links);
 	struct cgroup *root_cgrp = &root->cgrp;
@@ -1944,7 +1944,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
 	root_cgrp->ancestor_ids[0] = ret;
 
 	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release,
-			      ref_flags, GFP_KERNEL);
+			      0, GFP_KERNEL);
 	if (ret)
 		goto out;
 
@@ -2033,7 +2033,7 @@ struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
 			       struct cgroup_namespace *ns)
 {
 	struct dentry *dentry;
-	bool new_sb;
+	bool new_sb = false;
 
 	dentry = kernfs_mount(fs_type, flags, root->kf_root, magic, &new_sb);
 
@@ -2043,6 +2043,7 @@ struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
 	 */
 	if (!IS_ERR(dentry) && ns != &init_cgroup_ns) {
 		struct dentry *nsdentry;
+		struct super_block *sb = dentry->d_sb;
 		struct cgroup *cgrp;
 
 		mutex_lock(&cgroup_mutex);
@@ -2053,12 +2054,14 @@ struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
 		spin_unlock_irq(&css_set_lock);
 		mutex_unlock(&cgroup_mutex);
 
-		nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
+		nsdentry = kernfs_node_dentry(cgrp->kn, sb);
 		dput(dentry);
+		if (IS_ERR(nsdentry))
+			deactivate_locked_super(sb);
 		dentry = nsdentry;
 	}
 
-	if (IS_ERR(dentry) || !new_sb)
+	if (!new_sb)
 		cgroup_put(&root->cgrp);
 
 	return dentry;
@@ -2118,18 +2121,16 @@ static void cgroup_kill_sb(struct super_block *sb)
 	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 
 	/*
-	 * If @root doesn't have any mounts or children, start killing it.
+	 * If @root doesn't have any children, start killing it.
 	 * This prevents new mounts by disabling percpu_ref_tryget_live().
 	 * cgroup_mount() may wait for @root's release.
 	 *
 	 * And don't kill the default root.
 	 */
-	if (!list_empty(&root->cgrp.self.children) ||
-	    root == &cgrp_dfl_root)
-		cgroup_put(&root->cgrp);
-	else
+	if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
+	    !percpu_ref_is_dying(&root->cgrp.self.refcnt))
 		percpu_ref_kill(&root->cgrp.self.refcnt);
-
+	cgroup_put(&root->cgrp);
 	kernfs_kill_sb(sb);
 }
 
@@ -5399,7 +5400,7 @@ int __init cgroup_init(void)
 	hash_add(css_set_table, &init_css_set.hlist,
 		 css_set_hash(init_css_set.subsys));
 
-	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0, 0));
+	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
 
 	mutex_unlock(&cgroup_mutex);