btrfs: Wait for in-flight bios before freeing target device for raid56

When raid56 dev-replace is cancelled by running scrub, we will free
target device without waiting for in-flight bios, causing the following
NULL pointer deference or general protection failure.

 BUG: unable to handle kernel NULL pointer dereference at 00000000000005e0
 IP: generic_make_request_checks+0x4d/0x610
 CPU: 1 PID: 11676 Comm: kworker/u4:14 Tainted: G  O    4.11.0-rc2 #72
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.10.2-20170228_101828-anatol 04/01/2014
 Workqueue: btrfs-endio-raid56 btrfs_endio_raid56_helper [btrfs]
 task: ffff88002875b4c0 task.stack: ffffc90001334000
 RIP: 0010:generic_make_request_checks+0x4d/0x610
 Call Trace:
  ? generic_make_request+0xc7/0x360
  generic_make_request+0x24/0x360
  ? generic_make_request+0xc7/0x360
  submit_bio+0x64/0x120
  ? page_in_rbio+0x4d/0x80 [btrfs]
  ? rbio_orig_end_io+0x80/0x80 [btrfs]
  finish_rmw+0x3f4/0x540 [btrfs]
  validate_rbio_for_rmw+0x36/0x40 [btrfs]
  raid_rmw_end_io+0x7a/0x90 [btrfs]
  bio_endio+0x56/0x60
  end_workqueue_fn+0x3c/0x40 [btrfs]
  btrfs_scrubparity_helper+0xef/0x620 [btrfs]
  btrfs_endio_raid56_helper+0xe/0x10 [btrfs]
  process_one_work+0x2af/0x720
  ? process_one_work+0x22b/0x720
  worker_thread+0x4b/0x4f0
  kthread+0x10f/0x150
  ? process_one_work+0x720/0x720
  ? kthread_create_on_node+0x40/0x40
  ret_from_fork+0x2e/0x40
 RIP: generic_make_request_checks+0x4d/0x610 RSP: ffffc90001337bb8

In btrfs_dev_replace_finishing(), we will call
btrfs_rm_dev_replace_blocked() to wait bios before destroying the target
device when scrub is finished normally.

However when dev-replace is aborted, either due to error or cancelled by
scrub, we didn't wait for bios, this can lead to use-after-free if there
are bios holding the target device.

Furthermore, for raid56 scrub, at least 2 places are calling
btrfs_map_sblock() without protection of bio_counter, leading to the
problem.

This patch fixes the problem:
1) Wait for bio_counter before freeing target device when canceling
   replace
2) When calling btrfs_map_sblock() for raid56, use bio_counter to
   protect the call.

Cc: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 5 insertions, 0 deletions

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 26dbe563fed0..e9612016325f 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2191,6 +2191,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 	int ret;
 	int i;
 
+	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
 			&length, &bbio);
 	if (ret || !bbio || !bbio->raid_map)
@@ -2235,6 +2236,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 rbio_out:
 	bio_put(bio);
 bbio_out:
+	btrfs_bio_counter_dec(fs_info);
 	btrfs_put_bbio(bbio);
 	spin_lock(&sctx->stat_lock);
 	sctx->stat.malloc_errors++;
@@ -2778,6 +2780,8 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 		goto out;
 
 	length = sparity->logic_end - sparity->logic_start;
+
+	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_sblock(fs_info, BTRFS_MAP_WRITE, sparity->logic_start,
 			       &length, &bbio);
 	if (ret || !bbio || !bbio->raid_map)
@@ -2805,6 +2809,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 rbio_out:
 	bio_put(bio);
 bbio_out:
+	btrfs_bio_counter_dec(fs_info);
 	btrfs_put_bbio(bbio);
 	bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap,
 		  sparity->nsectors);