block: fix mis-synchronisation in blkdev_issue_zeroout()

BZ29402
https://bugzilla.kernel.org/show_bug.cgi?id=29402

We can hit serious mis-synchronization in bio completion path of
blkdev_issue_zeroout() leading to a panic.

The problem is that when we are going to wait_for_completion() in
blkdev_issue_zeroout() we check if the bb.done equals issued (number of
submitted bios). If it does, we can skip the wait_for_completition()
and just out of the function since there is nothing to wait for.
However, there is a ordering problem because bio_batch_end_io() is
calling atomic_inc(&bb->done) before complete(), hence it might seem to
blkdev_issue_zeroout() that all bios has been completed and exit. At
this point when bio_batch_end_io() is going to call complete(bb->wait),
bb and wait does not longer exist since it was allocated on stack in
blkdev_issue_zeroout() ==> panic!

(thread 1)                      (thread 2)
bio_batch_end_io()              blkdev_issue_zeroout()
  if(bb) {                      ...
    if (bb->end_io)             ...
      bb->end_io(bio, err);     ...
    atomic_inc(&bb->done);      ...
    ...                         while (issued != atomic_read(&bb.done))
    ...                         (let issued == bb.done)
    ...                         (do the rest of the function)
    ...                         return ret;
    complete(bb->wait);
    ^^^^^^^^
    panic

We can fix this easily by simplifying bio_batch and completion counting.

Also remove bio_end_io_t *end_io since it is not used.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Reported-by: Eric Whitney <eric.whitney@hp.com>
Tested-by: Eric Whitney <eric.whitney@hp.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
CC: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

diff --git a/block/blk-lib.c b/block/blk-lib.c
index eec78becb35500d8c5a922c91f5ea94c16336ee9..bd3e8df4d5e2b45a0ae89d90de025cfbaa12eed9 100644 (file)
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -109,7 +109,6 @@ struct bio_batch
        atomic_t                done;
        unsigned long           flags;
        struct completion       *wait;
-       bio_end_io_t            *end_io;
 };
 
 static void bio_batch_end_io(struct bio *bio, int err)
@@ -122,12 +121,9 @@ static void bio_batch_end_io(struct bio *bio, int err)
                else
                        clear_bit(BIO_UPTODATE, &bb->flags);
        }
-       if (bb) {
-               if (bb->end_io)
-                       bb->end_io(bio, err);
-               atomic_inc(&bb->done);
-               complete(bb->wait);
-       }
+       if (bb)
+               if (atomic_dec_and_test(&bb->done))
+                       complete(bb->wait);
        bio_put(bio);
 }
 
@@ -150,13 +146,12 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
        int ret;
        struct bio *bio;
        struct bio_batch bb;
-       unsigned int sz, issued = 0;
+       unsigned int sz;
        DECLARE_COMPLETION_ONSTACK(wait);
 
-       atomic_set(&bb.done, 0);
+       atomic_set(&bb.done, 1);
        bb.flags = 1 << BIO_UPTODATE;
        bb.wait = &wait;
-       bb.end_io = NULL;
 
 submit:
        ret = 0;
@@ -185,12 +180,12 @@ submit:
                                break;
                }
                ret = 0;
-               issued++;
+               atomic_inc(&bb.done);
                submit_bio(WRITE, bio);
        }
 
        /* Wait for bios in-flight */
-       while (issued != atomic_read(&bb.done))
+       if (!atomic_dec_and_test(&bb.done))
                wait_for_completion(&wait);
 
        if (!test_bit(BIO_UPTODATE, &bb.flags))