ext4: completed_io locking cleanup

Current unwritten extent conversion state-machine is very fuzzy.
- For unknown reason it performs conversion under i_mutex. What for?
  My diagnosis:
  We already protect extent tree with i_data_sem, truncate and punch_hole
  should wait for DIO, so the only data we have to protect is end_io->flags
  modification, but only flush_completed_IO and end_io_work modified this
  flags and we can serialize them via i_completed_io_lock.

  Currently all these games with mutex_trylock result in the following deadlock
   truncate:                          kworker:
    ext4_setattr                       ext4_end_io_work
    mutex_lock(i_mutex)
    inode_dio_wait(inode)  ->BLOCK
                             DEADLOCK<- mutex_trylock()
                                        inode_dio_done()
  #TEST_CASE1_BEGIN
  MNT=/mnt_scrach
  unlink $MNT/file
  fallocate -l $((1024*1024*1024)) $MNT/file
  aio-stress -I 100000 -O -s 100m -n -t 1 -c 10 -o 2 -o 3 $MNT/file
  sleep 2
  truncate -s 0 $MNT/file
  #TEST_CASE1_END

Or use 286's xfstests https://github.com/dmonakhov/xfstests/blob/devel/286

This patch makes state machine simple and clean:

(1) xxx_end_io schedule final extent conversion simply by calling
    ext4_add_complete_io(), which append it to ei->i_completed_io_list
    NOTE1: because of (2A) work should be queued only if
    ->i_completed_io_list was empty, otherwise the work is scheduled already.

(2) ext4_flush_completed_IO is responsible for handling all pending
    end_io from ei->i_completed_io_list
    Flushing sequence consists of following stages:
    A) LOCKED: Atomically drain completed_io_list to local_list
    B) Perform extents conversion
    C) LOCKED: move converted io's to to_free list for final deletion
       	     This logic depends on context which we was called from.
    D) Final end_io context destruction
    NOTE1: i_mutex is no longer required because end_io->flags modification
    is protected by ei->ext4_complete_io_lock

Full list of changes:
- Move all completion end_io related routines to page-io.c in order to improve
  logic locality
- Move open coded logic from various xx_end_xx routines to ext4_add_complete_io()
- remove EXT4_IO_END_FSYNC
- Improve SMP scalability by removing useless i_mutex which does not
  protect io->flags anymore.
- Reduce lock contention on i_completed_io_lock by optimizing list walk.
- Rename ext4_end_io_nolock to end4_end_io and make it static
- Check flush completion status to ext4_ext_punch_hole(). Because it is
  not good idea to punch blocks from corrupted inode.

Changes since V3 (in request to Jan's comments):
  Fall back to active flush_completed_IO() approach in order to prevent
  performance issues with nolocked DIO reads.
Changes since V2:
  Fix use-after-free caused by race truncate vs end_io_work

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

1 files changed, 0 insertions, 81 deletions

diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 323eb15c2d9..460000868b8 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -34,87 +34,6 @@
 
 #include <trace/events/ext4.h>
 
-static void dump_completed_IO(struct inode * inode)
-{
-#ifdef	EXT4FS_DEBUG
-	struct list_head *cur, *before, *after;
-	ext4_io_end_t *io, *io0, *io1;
-	unsigned long flags;
-
-	if (list_empty(&EXT4_I(inode)->i_completed_io_list)){
-		ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino);
-		return;
-	}
-
-	ext4_debug("Dump inode %lu completed_io list \n", inode->i_ino);
-	spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
-	list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list){
-		cur = &io->list;
-		before = cur->prev;
-		io0 = container_of(before, ext4_io_end_t, list);
-		after = cur->next;
-		io1 = container_of(after, ext4_io_end_t, list);
-
-		ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
-			    io, inode->i_ino, io0, io1);
-	}
-	spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags);
-#endif
-}
-
-/*
- * This function is called from ext4_sync_file().
- *
- * When IO is completed, the work to convert unwritten extents to
- * written is queued on workqueue but may not get immediately
- * scheduled. When fsync is called, we need to ensure the
- * conversion is complete before fsync returns.
- * The inode keeps track of a list of pending/completed IO that
- * might needs to do the conversion. This function walks through
- * the list and convert the related unwritten extents for completed IO
- * to written.
- * The function return the number of pending IOs on success.
- */
-int ext4_flush_completed_IO(struct inode *inode)
-{
-	ext4_io_end_t *io;
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	unsigned long flags;
-	int ret = 0;
-	int ret2 = 0;
-
-	dump_completed_IO(inode);
-	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-	while (!list_empty(&ei->i_completed_io_list)){
-		io = list_entry(ei->i_completed_io_list.next,
-				ext4_io_end_t, list);
-		list_del_init(&io->list);
-		io->flag |= EXT4_IO_END_IN_FSYNC;
-		/*
-		 * Calling ext4_end_io_nolock() to convert completed
-		 * IO to written.
-		 *
-		 * When ext4_sync_file() is called, run_queue() may already
-		 * about to flush the work corresponding to this io structure.
-		 * It will be upset if it founds the io structure related
-		 * to the work-to-be schedule is freed.
-		 *
-		 * Thus we need to keep the io structure still valid here after
-		 * conversion finished. The io structure has a flag to
-		 * avoid double converting from both fsync and background work
-		 * queue work.
-		 */
-		spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-		ret = ext4_end_io_nolock(io);
-		if (ret < 0)
-			ret2 = ret;
-		spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-		io->flag &= ~EXT4_IO_END_IN_FSYNC;
-	}
-	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
-	return (ret2 < 0) ? ret2 : 0;
-}
-
 /*
  * If we're not journaling and this is a just-created file, we have to
  * sync our parent directory (if it was freshly created) since