Merge branch 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull the big VFS changes from Al Viro:
 "This one is *big* and changes quite a few things around VFS.  What's in there:

   - the first of two really major architecture changes - death to open
     intents.

     The former is finally there; it was very long in making, but with
     Miklos getting through really hard and messy final push in
     fs/namei.c, we finally have it.  Unlike his variant, this one
     doesn't introduce struct opendata; what we have instead is
     ->atomic_open() taking preallocated struct file * and passing
     everything via its fields.

     Instead of returning struct file *, it returns -E...  on error, 0
     on success and 1 in "deal with it yourself" case (e.g.  symlink
     found on server, etc.).

     See comments before fs/namei.c:atomic_open().  That made a lot of
     goodies finally possible and quite a few are in that pile:
     ->lookup(), ->d_revalidate() and ->create() do not get struct
     nameidata * anymore; ->lookup() and ->d_revalidate() get lookup
     flags instead, ->create() gets "do we want it exclusive" flag.

     With the introduction of new helper (kern_path_locked()) we are rid
     of all struct nameidata instances outside of fs/namei.c; it's still
     visible in namei.h, but not for long.  Come the next cycle,
     declaration will move either to fs/internal.h or to fs/namei.c
     itself.  [me, miklos, hch]

   - The second major change: behaviour of final fput().  Now we have
     __fput() done without any locks held by caller *and* not from deep
     in call stack.

     That obviously lifts a lot of constraints on the locking in there.
     Moreover, it's legal now to call fput() from atomic contexts (which
     has immediately simplified life for aio.c).  We also don't need
     anti-recursion logics in __scm_destroy() anymore.

     There is a price, though - the damn thing has become partially
     asynchronous.  For fput() from normal process we are guaranteed
     that pending __fput() will be done before the caller returns to
     userland, exits or gets stopped for ptrace.

     For kernel threads and atomic contexts it's done via
     schedule_work(), so theoretically we might need a way to make sure
     it's finished; so far only one such place had been found, but there
     might be more.

     There's flush_delayed_fput() (do all pending __fput()) and there's
     __fput_sync() (fput() analog doing __fput() immediately).  I hope
     we won't need them often; see warnings in fs/file_table.c for
     details.  [me, based on task_work series from Oleg merged last
     cycle]

   - sync series from Jan

   - large part of "death to sync_supers()" work from Artem; the only
     bits missing here are exofs and ext4 ones.  As far as I understand,
     those are going via the exofs and ext4 trees resp.; once they are
     in, we can put ->write_super() to the rest, along with the thread
     calling it.

   - preparatory bits from unionmount series (from dhowells).

   - assorted cleanups and fixes all over the place, as usual.

  This is not the last pile for this cycle; there's at least jlayton's
  ESTALE work and fsfreeze series (the latter - in dire need of fixes,
  so I'm not sure it'll make the cut this cycle).  I'll probably throw
  symlink/hardlink restrictions stuff from Kees into the next pile, too.
  Plus there's a lot of misc patches I hadn't thrown into that one -
  it's large enough as it is..."

* 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (127 commits)
  ext4: switch EXT4_IOC_RESIZE_FS to mnt_want_write_file()
  btrfs: switch btrfs_ioctl_balance() to mnt_want_write_file()
  switch dentry_open() to struct path, make it grab references itself
  spufs: shift dget/mntget towards dentry_open()
  zoran: don't bother with struct file * in zoran_map
  ecryptfs: don't reinvent the wheels, please - use struct completion
  don't expose I_NEW inodes via dentry->d_inode
  tidy up namei.c a bit
  unobfuscate follow_up() a bit
  ext3: pass custom EOF to generic_file_llseek_size()
  ext4: use core vfs llseek code for dir seeks
  vfs: allow custom EOF in generic_file_llseek code
  vfs: Avoid unnecessary WB_SYNC_NONE writeback during sys_sync and reorder sync passes
  vfs: Remove unnecessary flushing of block devices
  vfs: Make sys_sync writeout also block device inodes
  vfs: Create function for iterating over block devices
  vfs: Reorder operations during sys_sync
  quota: Move quota syncing to ->sync_fs method
  quota: Split dquot_quota_sync() to writeback and cache flushing part
  vfs: Move noop_backing_dev_info check from sync into writeback
  ...

kernel/audit_tree.c

@@ -595,7 +595,7 @@ void audit_trim_trees(void)
 
 		root_mnt = collect_mounts(&path);
 		path_put(&path);
-		if (!root_mnt)
+		if (IS_ERR(root_mnt))
 			goto skip_it;
 
 		spin_lock(&hash_lock);
@@ -669,8 +669,8 @@ int audit_add_tree_rule(struct audit_krule *rule)
 		goto Err;
 	mnt = collect_mounts(&path);
 	path_put(&path);
-	if (!mnt) {
-		err = -ENOMEM;
+	if (IS_ERR(mnt)) {
+		err = PTR_ERR(mnt);
 		goto Err;
 	}
 
@@ -719,8 +719,8 @@ int audit_tag_tree(char *old, char *new)
 		return err;
 	tagged = collect_mounts(&path2);
 	path_put(&path2);
-	if (!tagged)
-		return -ENOMEM;
+	if (IS_ERR(tagged))
+		return PTR_ERR(tagged);
 
 	err = kern_path(old, 0, &path1);
 	if (err) {

kernel/audit_watch.c

@@ -355,34 +355,15 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 /* Get path information necessary for adding watches. */
 static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 {
-	struct nameidata nd;
-	struct dentry *d;
-	int err;
-
-	err = kern_path_parent(watch->path, &nd);
-	if (err)
-		return err;
-
-	if (nd.last_type != LAST_NORM) {
-		path_put(&nd.path);
-		return -EINVAL;
-	}
-
-	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
-	d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
-	if (IS_ERR(d)) {
-		mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
-		path_put(&nd.path);
+	struct dentry *d = kern_path_locked(watch->path, parent);
+	if (IS_ERR(d))
 		return PTR_ERR(d);
-	}
+	mutex_unlock(&parent->dentry->d_inode->i_mutex);
 	if (d->d_inode) {
 		/* update watch filter fields */
 		watch->dev = d->d_inode->i_sb->s_dev;
 		watch->ino = d->d_inode->i_ino;
 	}
-	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
-
-	*parent = nd.path;
 	dput(d);
 	return 0;
 }

kernel/cgroup.c

@@ -822,7 +822,7 @@ EXPORT_SYMBOL_GPL(cgroup_unlock);
  */
 
 static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
-static struct dentry *cgroup_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry *cgroup_lookup(struct inode *, struct dentry *, unsigned int);
 static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
 static int cgroup_populate_dir(struct cgroup *cgrp);
 static const struct inode_operations cgroup_dir_inode_operations;
@@ -1587,7 +1587,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	opts.new_root = new_root;
 
 	/* Locate an existing or new sb for this hierarchy */
-	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, &opts);
+	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts);
 	if (IS_ERR(sb)) {
 		ret = PTR_ERR(sb);
 		cgroup_drop_root(opts.new_root);
@@ -2570,7 +2570,7 @@ static const struct inode_operations cgroup_dir_inode_operations = {
 	.rename = cgroup_rename,
 };
 
-static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 {
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);

kernel/exit.c

@@ -953,14 +953,11 @@ void do_exit(long code)
 	exit_signals(tsk);  /* sets PF_EXITING */
 	/*
 	 * tsk->flags are checked in the futex code to protect against
-	 * an exiting task cleaning up the robust pi futexes, and in
-	 * task_work_add() to avoid the race with exit_task_work().
+	 * an exiting task cleaning up the robust pi futexes.
 	 */
 	smp_mb();
 	raw_spin_unlock_wait(&tsk->pi_lock);
 
-	exit_task_work(tsk);
-
 	if (unlikely(in_atomic()))
 		printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
 				current->comm, task_pid_nr(current),
@@ -995,6 +992,7 @@ void do_exit(long code)
 	exit_shm(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
+	exit_task_work(tsk);
 	check_stack_usage();
 	exit_thread();
 

kernel/fork.c

@@ -1420,7 +1420,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 */
 	p->group_leader = p;
 	INIT_LIST_HEAD(&p->thread_group);
-	INIT_HLIST_HEAD(&p->task_works);
+	p->task_works = NULL;
 
 	/* Now that the task is set up, run cgroup callbacks if
 	 * necessary. We need to run them before the task is visible

kernel/irq/manage.c

@@ -781,7 +781,7 @@ static void wake_threads_waitq(struct irq_desc *desc)
 		wake_up(&desc->wait_for_threads);
 }
 
-static void irq_thread_dtor(struct task_work *unused)
+static void irq_thread_dtor(struct callback_head *unused)
 {
 	struct task_struct *tsk = current;
 	struct irq_desc *desc;
@@ -813,7 +813,7 @@ static void irq_thread_dtor(struct task_work *unused)
  */
 static int irq_thread(void *data)
 {
-	struct task_work on_exit_work;
+	struct callback_head on_exit_work;
 	static const struct sched_param param = {
 		.sched_priority = MAX_USER_RT_PRIO/2,
 	};
@@ -830,7 +830,7 @@ static int irq_thread(void *data)
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
 
-	init_task_work(&on_exit_work, irq_thread_dtor, NULL);
+	init_task_work(&on_exit_work, irq_thread_dtor);
 	task_work_add(current, &on_exit_work, false);
 
 	while (!irq_wait_for_interrupt(action)) {

kernel/signal.c

@@ -1971,6 +1971,13 @@ static void ptrace_do_notify(int signr, int exit_code, int why)
 void ptrace_notify(int exit_code)
 {
 	BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP);
+	if (unlikely(current->task_works)) {
+		if (test_and_clear_ti_thread_flag(current_thread_info(),
+						   TIF_NOTIFY_RESUME)) {
+			smp_mb__after_clear_bit();
+			task_work_run();
+		}
+	}
 
 	spin_lock_irq(&current->sighand->siglock);
 	ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED);
@@ -2191,6 +2198,14 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
 	struct signal_struct *signal = current->signal;
 	int signr;
 
+	if (unlikely(current->task_works)) {
+		if (test_and_clear_ti_thread_flag(current_thread_info(),
+						   TIF_NOTIFY_RESUME)) {
+			smp_mb__after_clear_bit();
+			task_work_run();
+		}
+	}
+
 	if (unlikely(uprobe_deny_signal()))
 		return 0;
 

kernel/task_work.c

@@ -3,82 +3,78 @@
 #include <linux/tracehook.h>
 
 int
-task_work_add(struct task_struct *task, struct task_work *twork, bool notify)
+task_work_add(struct task_struct *task, struct callback_head *twork, bool notify)
 {
+	struct callback_head *last, *first;
 	unsigned long flags;
-	int err = -ESRCH;
 
-#ifndef TIF_NOTIFY_RESUME
-	if (notify)
-		return -ENOTSUPP;
-#endif
 	/*
-	 * We must not insert the new work if the task has already passed
-	 * exit_task_work(). We rely on do_exit()->raw_spin_unlock_wait()
-	 * and check PF_EXITING under pi_lock.
+	 * Not inserting the new work if the task has already passed
+	 * exit_task_work() is the responisbility of callers.
 	 */
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
-	if (likely(!(task->flags & PF_EXITING))) {
-		hlist_add_head(&twork->hlist, &task->task_works);
-		err = 0;
-	}
+	last = task->task_works;
+	first = last ? last->next : twork;
+	twork->next = first;
+	if (last)
+		last->next = twork;
+	task->task_works = twork;
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	/* test_and_set_bit() implies mb(), see tracehook_notify_resume(). */
-	if (likely(!err) && notify)
+	if (notify)
 		set_notify_resume(task);
-	return err;
+	return 0;
 }
 
-struct task_work *
+struct callback_head *
 task_work_cancel(struct task_struct *task, task_work_func_t func)
 {
 	unsigned long flags;
-	struct task_work *twork;
-	struct hlist_node *pos;
+	struct callback_head *last, *res = NULL;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
-	hlist_for_each_entry(twork, pos, &task->task_works, hlist) {
-		if (twork->func == func) {
-			hlist_del(&twork->hlist);
-			goto found;
+	last = task->task_works;
+	if (last) {
+		struct callback_head *q = last, *p = q->next;
+		while (1) {
+			if (p->func == func) {
+				q->next = p->next;
+				if (p == last)
+					task->task_works = q == p ? NULL : q;
+				res = p;
+				break;
+			}
+			if (p == last)
+				break;
+			q = p;
+			p = q->next;
 		}
 	}
-	twork = NULL;
- found:
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-
-	return twork;
+	return res;
 }
 
 void task_work_run(void)
 {
 	struct task_struct *task = current;
-	struct hlist_head task_works;
-	struct hlist_node *pos;
+	struct callback_head *p, *q;
 
-	raw_spin_lock_irq(&task->pi_lock);
-	hlist_move_list(&task->task_works, &task_works);
-	raw_spin_unlock_irq(&task->pi_lock);
+	while (1) {
+		raw_spin_lock_irq(&task->pi_lock);
+		p = task->task_works;
+		task->task_works = NULL;
+		raw_spin_unlock_irq(&task->pi_lock);
 
-	if (unlikely(hlist_empty(&task_works)))
-		return;
-	/*
-	 * We use hlist to save the space in task_struct, but we want fifo.
-	 * Find the last entry, the list should be short, then process them
-	 * in reverse order.
-	 */
-	for (pos = task_works.first; pos->next; pos = pos->next)
-		;
+		if (unlikely(!p))
+			return;
 
-	for (;;) {
-		struct hlist_node **pprev = pos->pprev;
-		struct task_work *twork = container_of(pos, struct task_work,
-							hlist);
-		twork->func(twork);
-
-		if (pprev == &task_works.first)
-			break;
-		pos = container_of(pprev, struct hlist_node, next);
+		q = p->next; /* head */
+		p->next = NULL; /* cut it */
+		while (q) {
+			p = q->next;
+			q->func(q);
+			q = p;
+		}
 	}
 }