If create a loop device with a backing NVMe SSD, current loop device
driver doesn't correctly set its queue's limits.discard_granularity and
leaves it as 0. If a discard request at LBA 0 on this loop device, in
__blkdev_issue_discard() the calculated req_sects will be 0, and a zero
length discard request will trigger a BUG() panic in generic block layer
code at block/blk-mq.c:563.
[ 955.565006][ C39] ------------[ cut here ]------------
[ 955.559660][ C39] invalid opcode: 0000 [#1] SMP NOPTI
[ 955.622171][ C39] CPU: 39 PID: 248 Comm: ksoftirqd/39 Tainted: G E 5.8.0-default+ #40
[ 955.622171][ C39] Hardware name: Lenovo ThinkSystem SR650 -[7X05CTO1WW]-/-[7X05CTO1WW]-, BIOS -[IVE160M-2.70]- 07/17/2020
[ 955.622175][ C39] RIP: 0010:blk_mq_end_request+0x107/0x110
[ 955.622177][ C39] Code: 48 8b 03 e9 59 ff ff ff 48 89 df 5b 5d 41 5c e9 9f ed ff ff 48 8b 35 98 3c f4 00 48 83 c7 10 48 83 c6 19 e8 cb 56 c9 ff eb cb <0f> 0b 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 56 41 54
[ 955.622179][ C39] RSP: 0018:ffffb1288701fe28 EFLAGS: 00010202
[ 955.749277][ C39] RAX: 0000000000000001 RBX: ffff956fffba5080 RCX: 0000000000004003
[ 955.749278][ C39] RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000000
[ 955.749279][ C39] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
[ 955.749279][ C39] R10: ffffb1288701fd28 R11: 0000000000000001 R12: ffffffffa8e05160
[ 955.749280][ C39] R13: 0000000000000004 R14: 0000000000000004 R15: ffffffffa7ad3a1e
[ 955.749281][ C39] FS: 0000000000000000(0000) GS:ffff95bfbda00000(0000) knlGS:0000000000000000
[ 955.749282][ C39] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 955.749282][ C39] CR2: 00007f6f0ef766a8 CR3: 0000005a37012002 CR4: 00000000007606e0
[ 955.749283][ C39] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 955.749284][ C39] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 955.749284][ C39] PKRU: 55555554
[ 955.749285][ C39] Call Trace:
[ 955.749290][ C39] blk_done_softirq+0x99/0xc0
[ 957.550669][ C39] __do_softirq+0xd3/0x45f
[ 957.550677][ C39] ? smpboot_thread_fn+0x2f/0x1e0
[ 957.550679][ C39] ? smpboot_thread_fn+0x74/0x1e0
[ 957.550680][ C39] ? smpboot_thread_fn+0x14e/0x1e0
[ 957.550684][ C39] run_ksoftirqd+0x30/0x60
[ 957.550687][ C39] smpboot_thread_fn+0x149/0x1e0
[ 957.886225][ C39] ? sort_range+0x20/0x20
[ 957.886226][ C39] kthread+0x137/0x160
[ 957.886228][ C39] ? kthread_park+0x90/0x90
[ 957.886231][ C39] ret_from_fork+0x22/0x30
[ 959.117120][ C39] ---[ end trace 3dacdac97e2ed164 ]---
This is the procedure to reproduce the panic,
# modprobe scsi_debug delay=0 dev_size_mb=2048 max_queue=1
# losetup -f /dev/nvme0n1 --direct-io=on
# blkdiscard /dev/loop0 -o 0 -l 0x200
This patch fixes the issue by checking q->limits.discard_granularity in
__blkdev_issue_discard() before composing the discard bio. If the value
is 0, then prints a warning oops information and returns -EOPNOTSUPP to
the caller to indicate that this buggy device driver doesn't support
discard request.
Fixes: 9b15d109a6b2 ("block: improve discard bio alignment in __blkdev_issue_discard()")
Fixes: c52abf563049 ("loop: Better discard support for block devices")
Reported-and-suggested-by: Ming Lei <[email protected]>
Signed-off-by: Coly Li <[email protected]>
Reviewed-by: Ming Lei <[email protected]>
Cc: Bart Van Assche <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Enzo Matsumiya <[email protected]>
Cc: Evan Green <[email protected]>
Cc: Hannes Reinecke <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Martin K. Petersen <[email protected]>
Cc: Xiao Ni <[email protected]>
---
Changelog:
v3: print device name assocated with the buggy driver.
v2: fix typo of the wrong return error code.
v1: first version.
block/blk-lib.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 019e09bb9c0e..d3bbb3d9fac3 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -47,6 +47,15 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
op = REQ_OP_DISCARD;
}
+ /* In case the discard granularity isn't set by buggy device driver */
+ if (WARN_ON_ONCE(!q->limits.discard_granularity)) {
+ char dev_name[BDEVNAME_SIZE];
+
+ bdevname(bdev, dev_name);
+ pr_err("%s: Error: discard_granularity is 0.\n", dev_name);
+ return -EOPNOTSUPP;
+ }
+
bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
if ((sector | nr_sects) & bs_mask)
return -EINVAL;
--
2.26.2
On 8/5/20 8:31 AM, Coly Li wrote:
> If create a loop device with a backing NVMe SSD, current loop device
> driver doesn't correctly set its queue's limits.discard_granularity and
> leaves it as 0. If a discard request at LBA 0 on this loop device, in
> __blkdev_issue_discard() the calculated req_sects will be 0, and a zero
> length discard request will trigger a BUG() panic in generic block layer
> code at block/blk-mq.c:563.
>
> [ 955.565006][ C39] ------------[ cut here ]------------
> [ 955.559660][ C39] invalid opcode: 0000 [#1] SMP NOPTI
> [ 955.622171][ C39] CPU: 39 PID: 248 Comm: ksoftirqd/39 Tainted: G E 5.8.0-default+ #40
> [ 955.622171][ C39] Hardware name: Lenovo ThinkSystem SR650 -[7X05CTO1WW]-/-[7X05CTO1WW]-, BIOS -[IVE160M-2.70]- 07/17/2020
> [ 955.622175][ C39] RIP: 0010:blk_mq_end_request+0x107/0x110
> [ 955.622177][ C39] Code: 48 8b 03 e9 59 ff ff ff 48 89 df 5b 5d 41 5c e9 9f ed ff ff 48 8b 35 98 3c f4 00 48 83 c7 10 48 83 c6 19 e8 cb 56 c9 ff eb cb <0f> 0b 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 56 41 54
> [ 955.622179][ C39] RSP: 0018:ffffb1288701fe28 EFLAGS: 00010202
> [ 955.749277][ C39] RAX: 0000000000000001 RBX: ffff956fffba5080 RCX: 0000000000004003
> [ 955.749278][ C39] RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000000
> [ 955.749279][ C39] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
> [ 955.749279][ C39] R10: ffffb1288701fd28 R11: 0000000000000001 R12: ffffffffa8e05160
> [ 955.749280][ C39] R13: 0000000000000004 R14: 0000000000000004 R15: ffffffffa7ad3a1e
> [ 955.749281][ C39] FS: 0000000000000000(0000) GS:ffff95bfbda00000(0000) knlGS:0000000000000000
> [ 955.749282][ C39] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 955.749282][ C39] CR2: 00007f6f0ef766a8 CR3: 0000005a37012002 CR4: 00000000007606e0
> [ 955.749283][ C39] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> [ 955.749284][ C39] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> [ 955.749284][ C39] PKRU: 55555554
> [ 955.749285][ C39] Call Trace:
> [ 955.749290][ C39] blk_done_softirq+0x99/0xc0
> [ 957.550669][ C39] __do_softirq+0xd3/0x45f
> [ 957.550677][ C39] ? smpboot_thread_fn+0x2f/0x1e0
> [ 957.550679][ C39] ? smpboot_thread_fn+0x74/0x1e0
> [ 957.550680][ C39] ? smpboot_thread_fn+0x14e/0x1e0
> [ 957.550684][ C39] run_ksoftirqd+0x30/0x60
> [ 957.550687][ C39] smpboot_thread_fn+0x149/0x1e0
> [ 957.886225][ C39] ? sort_range+0x20/0x20
> [ 957.886226][ C39] kthread+0x137/0x160
> [ 957.886228][ C39] ? kthread_park+0x90/0x90
> [ 957.886231][ C39] ret_from_fork+0x22/0x30
> [ 959.117120][ C39] ---[ end trace 3dacdac97e2ed164 ]---
>
> This is the procedure to reproduce the panic,
> # modprobe scsi_debug delay=0 dev_size_mb=2048 max_queue=1
> # losetup -f /dev/nvme0n1 --direct-io=on
> # blkdiscard /dev/loop0 -o 0 -l 0x200
>
> This patch fixes the issue by checking q->limits.discard_granularity in
> __blkdev_issue_discard() before composing the discard bio. If the value
> is 0, then prints a warning oops information and returns -EOPNOTSUPP to
> the caller to indicate that this buggy device driver doesn't support
> discard request.
>
> Fixes: 9b15d109a6b2 ("block: improve discard bio alignment in __blkdev_issue_discard()")
> Fixes: c52abf563049 ("loop: Better discard support for block devices")
> Reported-and-suggested-by: Ming Lei <[email protected]>
> Signed-off-by: Coly Li <[email protected]>
> Reviewed-by: Ming Lei <[email protected]>
> Cc: Bart Van Assche <[email protected]>
> Cc: Christoph Hellwig <[email protected]>
> Cc: Enzo Matsumiya <[email protected]>
> Cc: Evan Green <[email protected]>
> Cc: Hannes Reinecke <[email protected]>
> Cc: Jens Axboe <[email protected]>
> Cc: Martin K. Petersen <[email protected]>
> Cc: Xiao Ni <[email protected]>
> ---
> Changelog:
> v3: print device name assocated with the buggy driver.
> v2: fix typo of the wrong return error code.
> v1: first version.
>
> block/blk-lib.c | 9 +++++++++
> 1 file changed, 9 insertions(+)
>
> diff --git a/block/blk-lib.c b/block/blk-lib.c
> index 019e09bb9c0e..d3bbb3d9fac3 100644
> --- a/block/blk-lib.c
> +++ b/block/blk-lib.c
> @@ -47,6 +47,15 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
> op = REQ_OP_DISCARD;
> }
>
> + /* In case the discard granularity isn't set by buggy device driver */
> + if (WARN_ON_ONCE(!q->limits.discard_granularity)) {
> + char dev_name[BDEVNAME_SIZE];
> +
> + bdevname(bdev, dev_name);
> + pr_err("%s: Error: discard_granularity is 0.\n", dev_name);
> + return -EOPNOTSUPP;
> + }
> +
> bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
> if ((sector | nr_sects) & bs_mask)
> return -EINVAL;
>
Reviewed-by: Hannes Reinecke <[email protected]>
Cheers,
Hannes
--
Dr. Hannes Reinecke Teamlead Storage & Networking
[email protected] +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Felix Imendörffer
Hi Coly,
one question below:
Coly Li <[email protected]> 于2020年8月5日周三 上午8:36写道：
>
> If create a loop device with a backing NVMe SSD, current loop device
> driver doesn't correctly set its queue's limits.discard_granularity and
> leaves it as 0. If a discard request at LBA 0 on this loop device, in
> __blkdev_issue_discard() the calculated req_sects will be 0, and a zero
> length discard request will trigger a BUG() panic in generic block layer
> code at block/blk-mq.c:563.
>
> [ 955.565006][ C39] ------------[ cut here ]------------
> [ 955.559660][ C39] invalid opcode: 0000 [#1] SMP NOPTI
> [ 955.622171][ C39] CPU: 39 PID: 248 Comm: ksoftirqd/39 Tainted: G E 5.8.0-default+ #40
> [ 955.622171][ C39] Hardware name: Lenovo ThinkSystem SR650 -[7X05CTO1WW]-/-[7X05CTO1WW]-, BIOS -[IVE160M-2.70]- 07/17/2020
> [ 955.622175][ C39] RIP: 0010:blk_mq_end_request+0x107/0x110
> [ 955.622177][ C39] Code: 48 8b 03 e9 59 ff ff ff 48 89 df 5b 5d 41 5c e9 9f ed ff ff 48 8b 35 98 3c f4 00 48 83 c7 10 48 83 c6 19 e8 cb 56 c9 ff eb cb <0f> 0b 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 56 41 54
> [ 955.622179][ C39] RSP: 0018:ffffb1288701fe28 EFLAGS: 00010202
> [ 955.749277][ C39] RAX: 0000000000000001 RBX: ffff956fffba5080 RCX: 0000000000004003
> [ 955.749278][ C39] RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000000
> [ 955.749279][ C39] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
> [ 955.749279][ C39] R10: ffffb1288701fd28 R11: 0000000000000001 R12: ffffffffa8e05160
> [ 955.749280][ C39] R13: 0000000000000004 R14: 0000000000000004 R15: ffffffffa7ad3a1e
> [ 955.749281][ C39] FS: 0000000000000000(0000) GS:ffff95bfbda00000(0000) knlGS:0000000000000000
> [ 955.749282][ C39] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 955.749282][ C39] CR2: 00007f6f0ef766a8 CR3: 0000005a37012002 CR4: 00000000007606e0
> [ 955.749283][ C39] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> [ 955.749284][ C39] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> [ 955.749284][ C39] PKRU: 55555554
> [ 955.749285][ C39] Call Trace:
> [ 955.749290][ C39] blk_done_softirq+0x99/0xc0
> [ 957.550669][ C39] __do_softirq+0xd3/0x45f
> [ 957.550677][ C39] ? smpboot_thread_fn+0x2f/0x1e0
> [ 957.550679][ C39] ? smpboot_thread_fn+0x74/0x1e0
> [ 957.550680][ C39] ? smpboot_thread_fn+0x14e/0x1e0
> [ 957.550684][ C39] run_ksoftirqd+0x30/0x60
> [ 957.550687][ C39] smpboot_thread_fn+0x149/0x1e0
> [ 957.886225][ C39] ? sort_range+0x20/0x20
> [ 957.886226][ C39] kthread+0x137/0x160
> [ 957.886228][ C39] ? kthread_park+0x90/0x90
> [ 957.886231][ C39] ret_from_fork+0x22/0x30
> [ 959.117120][ C39] ---[ end trace 3dacdac97e2ed164 ]---
>
> This is the procedure to reproduce the panic,
> # modprobe scsi_debug delay=0 dev_size_mb=2048 max_queue=1
Why do you need scsi_debug here, it's not relevant and not used?
> # losetup -f /dev/nvme0n1 --direct-io=on
> # blkdiscard /dev/loop0 -o 0 -l 0x200
>
> This patch fixes the issue by checking q->limits.discard_granularity in
> __blkdev_issue_discard() before composing the discard bio. If the value
> is 0, then prints a warning oops information and returns -EOPNOTSUPP to
> the caller to indicate that this buggy device driver doesn't support
> discard request.
The patch itself looks correct to me.
>
> Fixes: 9b15d109a6b2 ("block: improve discard bio alignment in __blkdev_issue_discard()")
> Fixes: c52abf563049 ("loop: Better discard support for block devices")
> Reported-and-suggested-by: Ming Lei <[email protected]>
> Signed-off-by: Coly Li <[email protected]>
> Reviewed-by: Ming Lei <[email protected]>
> Cc: Bart Van Assche <[email protected]>
> Cc: Christoph Hellwig <[email protected]>
> Cc: Enzo Matsumiya <[email protected]>
> Cc: Evan Green <[email protected]>
> Cc: Hannes Reinecke <[email protected]>
> Cc: Jens Axboe <[email protected]>
> Cc: Martin K. Petersen <[email protected]>
> Cc: Xiao Ni <[email protected]>
Reviewed-by: Jack Wang <[email protected]>
Thanks
> ---
> Changelog:
> v3: print device name assocated with the buggy driver.
> v2: fix typo of the wrong return error code.
> v1: first version.
>
> block/blk-lib.c | 9 +++++++++
> 1 file changed, 9 insertions(+)
>
> diff --git a/block/blk-lib.c b/block/blk-lib.c
> index 019e09bb9c0e..d3bbb3d9fac3 100644
> --- a/block/blk-lib.c
> +++ b/block/blk-lib.c
> @@ -47,6 +47,15 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
> op = REQ_OP_DISCARD;
> }
>
> + /* In case the discard granularity isn't set by buggy device driver */
> + if (WARN_ON_ONCE(!q->limits.discard_granularity)) {
> + char dev_name[BDEVNAME_SIZE];
> +
> + bdevname(bdev, dev_name);
> + pr_err("%s: Error: discard_granularity is 0.\n", dev_name);
> + return -EOPNOTSUPP;
> + }
> +
> bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
> if ((sector | nr_sects) & bs_mask)
> return -EINVAL;
> --
> 2.26.2
>
On 2020/8/5 17:22, Jinpu Wang wrote:
> Hi Coly,
>
> one question below:
> Coly Li <[email protected]> 于2020年8月5日周三 上午8:36写道：
>>
>> If create a loop device with a backing NVMe SSD, current loop device
>> driver doesn't correctly set its queue's limits.discard_granularity and
>> leaves it as 0. If a discard request at LBA 0 on this loop device, in
>> __blkdev_issue_discard() the calculated req_sects will be 0, and a zero
>> length discard request will trigger a BUG() panic in generic block layer
>> code at block/blk-mq.c:563.
>>
>> [ 955.565006][ C39] ------------[ cut here ]------------
>> [ 955.559660][ C39] invalid opcode: 0000 [#1] SMP NOPTI
>> [ 955.622171][ C39] CPU: 39 PID: 248 Comm: ksoftirqd/39 Tainted: G E 5.8.0-default+ #40
>> [ 955.622171][ C39] Hardware name: Lenovo ThinkSystem SR650 -[7X05CTO1WW]-/-[7X05CTO1WW]-, BIOS -[IVE160M-2.70]- 07/17/2020
>> [ 955.622175][ C39] RIP: 0010:blk_mq_end_request+0x107/0x110
>> [ 955.622177][ C39] Code: 48 8b 03 e9 59 ff ff ff 48 89 df 5b 5d 41 5c e9 9f ed ff ff 48 8b 35 98 3c f4 00 48 83 c7 10 48 83 c6 19 e8 cb 56 c9 ff eb cb <0f> 0b 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 56 41 54
>> [ 955.622179][ C39] RSP: 0018:ffffb1288701fe28 EFLAGS: 00010202
>> [ 955.749277][ C39] RAX: 0000000000000001 RBX: ffff956fffba5080 RCX: 0000000000004003
>> [ 955.749278][ C39] RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000000
>> [ 955.749279][ C39] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
>> [ 955.749279][ C39] R10: ffffb1288701fd28 R11: 0000000000000001 R12: ffffffffa8e05160
>> [ 955.749280][ C39] R13: 0000000000000004 R14: 0000000000000004 R15: ffffffffa7ad3a1e
>> [ 955.749281][ C39] FS: 0000000000000000(0000) GS:ffff95bfbda00000(0000) knlGS:0000000000000000
>> [ 955.749282][ C39] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>> [ 955.749282][ C39] CR2: 00007f6f0ef766a8 CR3: 0000005a37012002 CR4: 00000000007606e0
>> [ 955.749283][ C39] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
>> [ 955.749284][ C39] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
>> [ 955.749284][ C39] PKRU: 55555554
>> [ 955.749285][ C39] Call Trace:
>> [ 955.749290][ C39] blk_done_softirq+0x99/0xc0
>> [ 957.550669][ C39] __do_softirq+0xd3/0x45f
>> [ 957.550677][ C39] ? smpboot_thread_fn+0x2f/0x1e0
>> [ 957.550679][ C39] ? smpboot_thread_fn+0x74/0x1e0
>> [ 957.550680][ C39] ? smpboot_thread_fn+0x14e/0x1e0
>> [ 957.550684][ C39] run_ksoftirqd+0x30/0x60
>> [ 957.550687][ C39] smpboot_thread_fn+0x149/0x1e0
>> [ 957.886225][ C39] ? sort_range+0x20/0x20
>> [ 957.886226][ C39] kthread+0x137/0x160
>> [ 957.886228][ C39] ? kthread_park+0x90/0x90
>> [ 957.886231][ C39] ret_from_fork+0x22/0x30
>> [ 959.117120][ C39] ---[ end trace 3dacdac97e2ed164 ]---
>>
>> This is the procedure to reproduce the panic,
>> # modprobe scsi_debug delay=0 dev_size_mb=2048 max_queue=1
> Why do you need scsi_debug here, it's not relevant and not used?
If I don't config SCSI_DEBUG this panic cannot be triggered in my
environment, I don't know why. Maybe it is unnecessary, but in case
other people has similar configuration as mine, I add this command line
in the commit log.
>> # losetup -f /dev/nvme0n1 --direct-io=on
>> # blkdiscard /dev/loop0 -o 0 -l 0x200
>>
>> This patch fixes the issue by checking q->limits.discard_granularity in
>> __blkdev_issue_discard() before composing the discard bio. If the value
>> is 0, then prints a warning oops information and returns -EOPNOTSUPP to
>> the caller to indicate that this buggy device driver doesn't support
>> discard request.
> The patch itself looks correct to me.
>>
>> Fixes: 9b15d109a6b2 ("block: improve discard bio alignment in __blkdev_issue_discard()")
>> Fixes: c52abf563049 ("loop: Better discard support for block devices")
>> Reported-and-suggested-by: Ming Lei <[email protected]>
>> Signed-off-by: Coly Li <[email protected]>
>> Reviewed-by: Ming Lei <[email protected]>
>> Cc: Bart Van Assche <[email protected]>
>> Cc: Christoph Hellwig <[email protected]>
>> Cc: Enzo Matsumiya <[email protected]>
>> Cc: Evan Green <[email protected]>
>> Cc: Hannes Reinecke <[email protected]>
>> Cc: Jens Axboe <[email protected]>
>> Cc: Martin K. Petersen <[email protected]>
>> Cc: Xiao Ni <[email protected]>
> Reviewed-by: Jack Wang <[email protected]>
[snipped]
Thanks.
Coly Li
On 2020/8/5 23:48, Darrick J. Wong wrote:
> On Wed, Aug 05, 2020 at 02:31:50PM +0800, Coly Li wrote:
>> If create a loop device with a backing NVMe SSD, current loop device
>> driver doesn't correctly set its queue's limits.discard_granularity and
>> leaves it as 0. If a discard request at LBA 0 on this loop device, in
>> __blkdev_issue_discard() the calculated req_sects will be 0, and a zero
>> length discard request will trigger a BUG() panic in generic block layer
>> code at block/blk-mq.c:563.
>>
>> [ 955.565006][ C39] ------------[ cut here ]------------
>> [ 955.559660][ C39] invalid opcode: 0000 [#1] SMP NOPTI
>> [ 955.622171][ C39] CPU: 39 PID: 248 Comm: ksoftirqd/39 Tainted: G E 5.8.0-default+ #40
>> [ 955.622171][ C39] Hardware name: Lenovo ThinkSystem SR650 -[7X05CTO1WW]-/-[7X05CTO1WW]-, BIOS -[IVE160M-2.70]- 07/17/2020
>> [ 955.622175][ C39] RIP: 0010:blk_mq_end_request+0x107/0x110
>> [ 955.622177][ C39] Code: 48 8b 03 e9 59 ff ff ff 48 89 df 5b 5d 41 5c e9 9f ed ff ff 48 8b 35 98 3c f4 00 48 83 c7 10 48 83 c6 19 e8 cb 56 c9 ff eb cb <0f> 0b 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 56 41 54
>> [ 955.622179][ C39] RSP: 0018:ffffb1288701fe28 EFLAGS: 00010202
>> [ 955.749277][ C39] RAX: 0000000000000001 RBX: ffff956fffba5080 RCX: 0000000000004003
>> [ 955.749278][ C39] RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000000
>> [ 955.749279][ C39] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
>> [ 955.749279][ C39] R10: ffffb1288701fd28 R11: 0000000000000001 R12: ffffffffa8e05160
>> [ 955.749280][ C39] R13: 0000000000000004 R14: 0000000000000004 R15: ffffffffa7ad3a1e
>> [ 955.749281][ C39] FS: 0000000000000000(0000) GS:ffff95bfbda00000(0000) knlGS:0000000000000000
>> [ 955.749282][ C39] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>> [ 955.749282][ C39] CR2: 00007f6f0ef766a8 CR3: 0000005a37012002 CR4: 00000000007606e0
>> [ 955.749283][ C39] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
>> [ 955.749284][ C39] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
>> [ 955.749284][ C39] PKRU: 55555554
>> [ 955.749285][ C39] Call Trace:
>> [ 955.749290][ C39] blk_done_softirq+0x99/0xc0
>> [ 957.550669][ C39] __do_softirq+0xd3/0x45f
>> [ 957.550677][ C39] ? smpboot_thread_fn+0x2f/0x1e0
>> [ 957.550679][ C39] ? smpboot_thread_fn+0x74/0x1e0
>> [ 957.550680][ C39] ? smpboot_thread_fn+0x14e/0x1e0
>> [ 957.550684][ C39] run_ksoftirqd+0x30/0x60
>> [ 957.550687][ C39] smpboot_thread_fn+0x149/0x1e0
>> [ 957.886225][ C39] ? sort_range+0x20/0x20
>> [ 957.886226][ C39] kthread+0x137/0x160
>> [ 957.886228][ C39] ? kthread_park+0x90/0x90
>> [ 957.886231][ C39] ret_from_fork+0x22/0x30
>> [ 959.117120][ C39] ---[ end trace 3dacdac97e2ed164 ]---
>>
>> This is the procedure to reproduce the panic,
>> # modprobe scsi_debug delay=0 dev_size_mb=2048 max_queue=1
>> # losetup -f /dev/nvme0n1 --direct-io=on
>> # blkdiscard /dev/loop0 -o 0 -l 0x200
>>
>> This patch fixes the issue by checking q->limits.discard_granularity in
>> __blkdev_issue_discard() before composing the discard bio. If the value
>> is 0, then prints a warning oops information and returns -EOPNOTSUPP to
>> the caller to indicate that this buggy device driver doesn't support
>> discard request.
>>
>> Fixes: 9b15d109a6b2 ("block: improve discard bio alignment in __blkdev_issue_discard()")
>> Fixes: c52abf563049 ("loop: Better discard support for block devices")
>> Reported-and-suggested-by: Ming Lei <[email protected]>
>> Signed-off-by: Coly Li <[email protected]>
>> Reviewed-by: Ming Lei <[email protected]>
>> Cc: Bart Van Assche <[email protected]>
>> Cc: Christoph Hellwig <[email protected]>
>> Cc: Enzo Matsumiya <[email protected]>
>> Cc: Evan Green <[email protected]>
>> Cc: Hannes Reinecke <[email protected]>
>> Cc: Jens Axboe <[email protected]>
>> Cc: Martin K. Petersen <[email protected]>
>> Cc: Xiao Ni <[email protected]>
>> ---
>> Changelog:
>> v3: print device name assocated with the buggy driver.
>> v2: fix typo of the wrong return error code.
>> v1: first version.
>>
>> block/blk-lib.c | 9 +++++++++
>> 1 file changed, 9 insertions(+)
>>
>> diff --git a/block/blk-lib.c b/block/blk-lib.c
>> index 019e09bb9c0e..d3bbb3d9fac3 100644
>> --- a/block/blk-lib.c
>> +++ b/block/blk-lib.c
>> @@ -47,6 +47,15 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
>> op = REQ_OP_DISCARD;
>> }
>>
>> + /* In case the discard granularity isn't set by buggy device driver */
>> + if (WARN_ON_ONCE(!q->limits.discard_granularity)) {
>> + char dev_name[BDEVNAME_SIZE];
>> +
>> + bdevname(bdev, dev_name);
>> + pr_err("%s: Error: discard_granularity is 0.\n", dev_name);
>
> Hm, you might want to ratelimit this, before some buggy device +
> careless program flood dmesg.
>
Sure, I will use pr_err_ratelimit() in next version.
> Also, why is it necessary to WARN_ON_ONCE /and/ pr_err the same
> condition?
>
The WARN_ON_ONCE() just though the warning message, but does not point
out which device is buggy. Indeed this is a serious problem, so current
kernel message is a warning oops info and followed by "loop: Error:
discard_granularity is 0."
Thanks.
Coly Li
On Wed, Aug 05, 2020 at 02:31:50PM +0800, Coly Li wrote:
> If create a loop device with a backing NVMe SSD, current loop device
> driver doesn't correctly set its queue's limits.discard_granularity and
> leaves it as 0. If a discard request at LBA 0 on this loop device, in
> __blkdev_issue_discard() the calculated req_sects will be 0, and a zero
> length discard request will trigger a BUG() panic in generic block layer
> code at block/blk-mq.c:563.
>
> [ 955.565006][ C39] ------------[ cut here ]------------
> [ 955.559660][ C39] invalid opcode: 0000 [#1] SMP NOPTI
> [ 955.622171][ C39] CPU: 39 PID: 248 Comm: ksoftirqd/39 Tainted: G E 5.8.0-default+ #40
> [ 955.622171][ C39] Hardware name: Lenovo ThinkSystem SR650 -[7X05CTO1WW]-/-[7X05CTO1WW]-, BIOS -[IVE160M-2.70]- 07/17/2020
> [ 955.622175][ C39] RIP: 0010:blk_mq_end_request+0x107/0x110
> [ 955.622177][ C39] Code: 48 8b 03 e9 59 ff ff ff 48 89 df 5b 5d 41 5c e9 9f ed ff ff 48 8b 35 98 3c f4 00 48 83 c7 10 48 83 c6 19 e8 cb 56 c9 ff eb cb <0f> 0b 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 56 41 54
> [ 955.622179][ C39] RSP: 0018:ffffb1288701fe28 EFLAGS: 00010202
> [ 955.749277][ C39] RAX: 0000000000000001 RBX: ffff956fffba5080 RCX: 0000000000004003
> [ 955.749278][ C39] RDX: 0000000000000003 RSI: 0000000000000000 RDI: 0000000000000000
> [ 955.749279][ C39] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
> [ 955.749279][ C39] R10: ffffb1288701fd28 R11: 0000000000000001 R12: ffffffffa8e05160
> [ 955.749280][ C39] R13: 0000000000000004 R14: 0000000000000004 R15: ffffffffa7ad3a1e
> [ 955.749281][ C39] FS: 0000000000000000(0000) GS:ffff95bfbda00000(0000) knlGS:0000000000000000
> [ 955.749282][ C39] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 955.749282][ C39] CR2: 00007f6f0ef766a8 CR3: 0000005a37012002 CR4: 00000000007606e0
> [ 955.749283][ C39] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> [ 955.749284][ C39] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> [ 955.749284][ C39] PKRU: 55555554
> [ 955.749285][ C39] Call Trace:
> [ 955.749290][ C39] blk_done_softirq+0x99/0xc0
> [ 957.550669][ C39] __do_softirq+0xd3/0x45f
> [ 957.550677][ C39] ? smpboot_thread_fn+0x2f/0x1e0
> [ 957.550679][ C39] ? smpboot_thread_fn+0x74/0x1e0
> [ 957.550680][ C39] ? smpboot_thread_fn+0x14e/0x1e0
> [ 957.550684][ C39] run_ksoftirqd+0x30/0x60
> [ 957.550687][ C39] smpboot_thread_fn+0x149/0x1e0
> [ 957.886225][ C39] ? sort_range+0x20/0x20
> [ 957.886226][ C39] kthread+0x137/0x160
> [ 957.886228][ C39] ? kthread_park+0x90/0x90
> [ 957.886231][ C39] ret_from_fork+0x22/0x30
> [ 959.117120][ C39] ---[ end trace 3dacdac97e2ed164 ]---
>
> This is the procedure to reproduce the panic,
> # modprobe scsi_debug delay=0 dev_size_mb=2048 max_queue=1
> # losetup -f /dev/nvme0n1 --direct-io=on
> # blkdiscard /dev/loop0 -o 0 -l 0x200
>
> This patch fixes the issue by checking q->limits.discard_granularity in
> __blkdev_issue_discard() before composing the discard bio. If the value
> is 0, then prints a warning oops information and returns -EOPNOTSUPP to
> the caller to indicate that this buggy device driver doesn't support
> discard request.
>
> Fixes: 9b15d109a6b2 ("block: improve discard bio alignment in __blkdev_issue_discard()")
> Fixes: c52abf563049 ("loop: Better discard support for block devices")
> Reported-and-suggested-by: Ming Lei <[email protected]>
> Signed-off-by: Coly Li <[email protected]>
> Reviewed-by: Ming Lei <[email protected]>
> Cc: Bart Van Assche <[email protected]>
> Cc: Christoph Hellwig <[email protected]>
> Cc: Enzo Matsumiya <[email protected]>
> Cc: Evan Green <[email protected]>
> Cc: Hannes Reinecke <[email protected]>
> Cc: Jens Axboe <[email protected]>
> Cc: Martin K. Petersen <[email protected]>
> Cc: Xiao Ni <[email protected]>
> ---
> Changelog:
> v3: print device name assocated with the buggy driver.
> v2: fix typo of the wrong return error code.
> v1: first version.
>
> block/blk-lib.c | 9 +++++++++
> 1 file changed, 9 insertions(+)
>
> diff --git a/block/blk-lib.c b/block/blk-lib.c
> index 019e09bb9c0e..d3bbb3d9fac3 100644
> --- a/block/blk-lib.c
> +++ b/block/blk-lib.c
> @@ -47,6 +47,15 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
> op = REQ_OP_DISCARD;
> }
>
> + /* In case the discard granularity isn't set by buggy device driver */
> + if (WARN_ON_ONCE(!q->limits.discard_granularity)) {
> + char dev_name[BDEVNAME_SIZE];
> +
> + bdevname(bdev, dev_name);
> + pr_err("%s: Error: discard_granularity is 0.\n", dev_name);
Hm, you might want to ratelimit this, before some buggy device +
careless program flood dmesg.
Also, why is it necessary to WARN_ON_ONCE /and/ pr_err the same
condition?
--D
> + return -EOPNOTSUPP;
> + }
> +
> bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
> if ((sector | nr_sects) & bs_mask)
> return -EINVAL;
> --
> 2.26.2
>