summaryrefslogtreecommitdiff
path: root/fs/btrfs/raid56.c
diff options
context:
space:
mode:
authorQu Wenruo <quwenruo@cn.fujitsu.com>2017-03-29 04:33:21 +0300
committerDavid Sterba <dsterba@suse.com>2017-04-18 15:07:26 +0300
commitae6529c35bcc1c65c12131cef2aea63d8e2ea950 (patch)
treec1d613fb1076079758db18ac81f15a09d359d184 /fs/btrfs/raid56.c
parent9a33944bdf075ca93062cde206cb25e62044890e (diff)
downloadlinux-ae6529c35bcc1c65c12131cef2aea63d8e2ea950.tar.xz
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>
Diffstat (limited to 'fs/btrfs/raid56.c')
-rw-r--r--fs/btrfs/raid56.c14
1 files changed, 14 insertions, 0 deletions
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 7bf65d9a9bd3..d8ea0eb76325 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -2198,6 +2198,8 @@ static void read_rebuild_work(struct btrfs_work *work)
/*
* The following code is used to scrub/replace the parity stripe
*
+ * Caller must have already increased bio_counter for getting @bbio.
+ *
* Note: We need make sure all the pages that add into the scrub/replace
* raid bio are correct and not be changed during the scrub/replace. That
* is those pages just hold metadata or file data with checksum.
@@ -2235,6 +2237,12 @@ raid56_parity_alloc_scrub_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
ASSERT(rbio->stripe_npages == stripe_nsectors);
bitmap_copy(rbio->dbitmap, dbitmap, stripe_nsectors);
+ /*
+ * We have already increased bio_counter when getting bbio, record it
+ * so we can free it at rbio_orig_end_io().
+ */
+ rbio->generic_bio_cnt = 1;
+
return rbio;
}
@@ -2677,6 +2685,12 @@ raid56_alloc_missing_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
return NULL;
}
+ /*
+ * When we get bbio, we have already increased bio_counter, record it
+ * so we can free it at rbio_orig_end_io()
+ */
+ rbio->generic_bio_cnt = 1;
+
return rbio;
}