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
  ...

1 files changed, 71 insertions, 10 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
index a305d9e2d1b2..b3fc4d67a26b 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -23,6 +23,8 @@
 #include <linux/lglock.h>
 #include <linux/percpu_counter.h>
 #include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <linux/task_work.h>
 #include <linux/ima.h>
 
 #include <linux/atomic.h>
@@ -251,7 +253,6 @@ static void __fput(struct file *file)
 	}
 	fops_put(file->f_op);
 	put_pid(file->f_owner.pid);
-	file_sb_list_del(file);
 	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_dec(inode);
 	if (file->f_mode & FMODE_WRITE)
@@ -263,10 +264,77 @@ static void __fput(struct file *file)
 	mntput(mnt);
 }
 
+static DEFINE_SPINLOCK(delayed_fput_lock);
+static LIST_HEAD(delayed_fput_list);
+static void delayed_fput(struct work_struct *unused)
+{
+	LIST_HEAD(head);
+	spin_lock_irq(&delayed_fput_lock);
+	list_splice_init(&delayed_fput_list, &head);
+	spin_unlock_irq(&delayed_fput_lock);
+	while (!list_empty(&head)) {
+		struct file *f = list_first_entry(&head, struct file, f_u.fu_list);
+		list_del_init(&f->f_u.fu_list);
+		__fput(f);
+	}
+}
+
+static void ____fput(struct callback_head *work)
+{
+	__fput(container_of(work, struct file, f_u.fu_rcuhead));
+}
+
+/*
+ * If kernel thread really needs to have the final fput() it has done
+ * to complete, call this.  The only user right now is the boot - we
+ * *do* need to make sure our writes to binaries on initramfs has
+ * not left us with opened struct file waiting for __fput() - execve()
+ * won't work without that.  Please, don't add more callers without
+ * very good reasons; in particular, never call that with locks
+ * held and never call that from a thread that might need to do
+ * some work on any kind of umount.
+ */
+void flush_delayed_fput(void)
+{
+	delayed_fput(NULL);
+}
+
+static DECLARE_WORK(delayed_fput_work, delayed_fput);
+
 void fput(struct file *file)
 {
-	if (atomic_long_dec_and_test(&file->f_count))
+	if (atomic_long_dec_and_test(&file->f_count)) {
+		struct task_struct *task = current;
+		file_sb_list_del(file);
+		if (unlikely(in_interrupt() || task->flags & PF_KTHREAD)) {
+			unsigned long flags;
+			spin_lock_irqsave(&delayed_fput_lock, flags);
+			list_add(&file->f_u.fu_list, &delayed_fput_list);
+			schedule_work(&delayed_fput_work);
+			spin_unlock_irqrestore(&delayed_fput_lock, flags);
+			return;
+		}
+		init_task_work(&file->f_u.fu_rcuhead, ____fput);
+		task_work_add(task, &file->f_u.fu_rcuhead, true);
+	}
+}
+
+/*
+ * synchronous analog of fput(); for kernel threads that might be needed
+ * in some umount() (and thus can't use flush_delayed_fput() without
+ * risking deadlocks), need to wait for completion of __fput() and know
+ * for this specific struct file it won't involve anything that would
+ * need them.  Use only if you really need it - at the very least,
+ * don't blindly convert fput() by kernel thread to that.
+ */
+void __fput_sync(struct file *file)
+{
+	if (atomic_long_dec_and_test(&file->f_count)) {
+		struct task_struct *task = current;
+		file_sb_list_del(file);
+		BUG_ON(!(task->flags & PF_KTHREAD));
 		__fput(file);
+	}
 }
 
 EXPORT_SYMBOL(fput);
@@ -483,10 +551,8 @@ void mark_files_ro(struct super_block *sb)
 {
 	struct file *f;
 
-retry:
 	lg_global_lock(&files_lglock);
 	do_file_list_for_each_entry(sb, f) {
-		struct vfsmount *mnt;
 		if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
 		       continue;
 		if (!file_count(f))
@@ -499,12 +565,7 @@ retry:
 		if (file_check_writeable(f) != 0)
 			continue;
 		file_release_write(f);
-		mnt = mntget(f->f_path.mnt);
-		/* This can sleep, so we can't hold the spinlock. */
-		lg_global_unlock(&files_lglock);
-		mnt_drop_write(mnt);
-		mntput(mnt);
-		goto retry;
+		mnt_drop_write_file(f);
 	} while_file_list_for_each_entry;
 	lg_global_unlock(&files_lglock);
 }