This patch set fix two issues introduced by prior commit.
[PATCH 1/2] loop: do not print warn message if partition scan is successful
[PATCH 1/2] fixes d57f3374ba48 ("loop: Move special partition reread
handling in loop_clr_fd()") to not always print warn message even when
partition scan is successful.
[PATCH 2/2] loop: set GENHD_FL_NO_PART_SCAN after blkdev_reread_part()
[PATCH 2/2] fixes 0da03cab87e6 ("loop: Fix deadlock when calling
blkdev_reread_part()") to not set GENHD_FL_NO_PART_SCAN before partition
scan when detaching loop device from the file.
Thank you very much!
Dongli Zhang
Commit 0da03cab87e6
("loop: Fix deadlock when calling blkdev_reread_part()") moves
blkdev_reread_part() out of the loop_ctl_mutex. However,
GENHD_FL_NO_PART_SCAN is set before __blkdev_reread_part(). As a result,
__blkdev_reread_part() will fail the check of GENHD_FL_NO_PART_SCAN and
will not rescan the loop device to delete all partitions.
Below are steps to reproduce the issue:
step1 # dd if=/dev/zero of=tmp.raw bs=1M count=100
step2 # losetup -P /dev/loop0 tmp.raw
step3 # parted /dev/loop0 mklabel gpt
step4 # parted -a none -s /dev/loop0 mkpart primary 64s 1
step5 # losetup -d /dev/loop0
Step5 will not be able to delete /dev/loop0p1 (introduced by step4) and
there is below kernel warning message:
[ 464.414043] __loop_clr_fd: partition scan of loop0 failed (rc=-22)
This patch sets GENHD_FL_NO_PART_SCAN after blkdev_reread_part().
Fixes: 0da03cab87e6 ("loop: Fix deadlock when calling blkdev_reread_part()")
Signed-off-by: Dongli Zhang <[email protected]>
---
drivers/block/loop.c | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 7908673..736e55b 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1034,6 +1034,15 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
return err;
}
+static void loop_disable_partscan(struct loop_device *lo)
+{
+ mutex_lock(&loop_ctl_mutex);
+ lo->lo_flags = 0;
+ if (!part_shift)
+ lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
+ mutex_unlock(&loop_ctl_mutex);
+}
+
static int __loop_clr_fd(struct loop_device *lo, bool release)
{
struct file *filp = NULL;
@@ -1096,9 +1105,6 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev;
lo_number = lo->lo_number;
- lo->lo_flags = 0;
- if (!part_shift)
- lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
loop_unprepare_queue(lo);
out_unlock:
mutex_unlock(&loop_ctl_mutex);
@@ -1121,6 +1127,9 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
/* Device is gone, no point in returning error */
err = 0;
}
+
+ loop_disable_partscan(lo);
+
/*
* Need not hold loop_ctl_mutex to fput backing file.
* Calling fput holding loop_ctl_mutex triggers a circular
--
2.7.4
Do not print warn message when the partition scan returns 0.
Fixes: d57f3374ba48 ("loop: Move special partition reread handling in loop_clr_fd()")
Signed-off-by: Dongli Zhang <[email protected]>
---
drivers/block/loop.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index cf55389..7908673 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1115,8 +1115,9 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
err = __blkdev_reread_part(bdev);
else
err = blkdev_reread_part(bdev);
- pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
- __func__, lo_number, err);
+ if (err)
+ pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
+ __func__, lo_number, err);
/* Device is gone, no point in returning error */
err = 0;
}
--
2.7.4
On Thu 21-02-19 12:17:34, Dongli Zhang wrote:
> Do not print warn message when the partition scan returns 0.
>
> Fixes: d57f3374ba48 ("loop: Move special partition reread handling in loop_clr_fd()")
> Signed-off-by: Dongli Zhang <[email protected]>
Yeah, thanks for the fix! Not sure how come I didn't see this in my
testing. You can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
> drivers/block/loop.c | 5 +++--
> 1 file changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/block/loop.c b/drivers/block/loop.c
> index cf55389..7908673 100644
> --- a/drivers/block/loop.c
> +++ b/drivers/block/loop.c
> @@ -1115,8 +1115,9 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
> err = __blkdev_reread_part(bdev);
> else
> err = blkdev_reread_part(bdev);
> - pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
> - __func__, lo_number, err);
> + if (err)
> + pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
> + __func__, lo_number, err);
> /* Device is gone, no point in returning error */
> err = 0;
> }
> --
> 2.7.4
>
--
Jan Kara <[email protected]>
SUSE Labs, CR
On Thu 21-02-19 12:17:35, Dongli Zhang wrote:
> Commit 0da03cab87e6
> ("loop: Fix deadlock when calling blkdev_reread_part()") moves
> blkdev_reread_part() out of the loop_ctl_mutex. However,
> GENHD_FL_NO_PART_SCAN is set before __blkdev_reread_part(). As a result,
> __blkdev_reread_part() will fail the check of GENHD_FL_NO_PART_SCAN and
> will not rescan the loop device to delete all partitions.
>
> Below are steps to reproduce the issue:
>
> step1 # dd if=/dev/zero of=tmp.raw bs=1M count=100
> step2 # losetup -P /dev/loop0 tmp.raw
> step3 # parted /dev/loop0 mklabel gpt
> step4 # parted -a none -s /dev/loop0 mkpart primary 64s 1
> step5 # losetup -d /dev/loop0
Can you perhaps write a blktest for this? Thanks!
> Step5 will not be able to delete /dev/loop0p1 (introduced by step4) and
> there is below kernel warning message:
>
> [ 464.414043] __loop_clr_fd: partition scan of loop0 failed (rc=-22)
>
> This patch sets GENHD_FL_NO_PART_SCAN after blkdev_reread_part().
>
> Fixes: 0da03cab87e6 ("loop: Fix deadlock when calling blkdev_reread_part()")
> Signed-off-by: Dongli Zhang <[email protected]>
> ---
> drivers/block/loop.c | 15 ++++++++++++---
> 1 file changed, 12 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/block/loop.c b/drivers/block/loop.c
> index 7908673..736e55b 100644
> --- a/drivers/block/loop.c
> +++ b/drivers/block/loop.c
> @@ -1034,6 +1034,15 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
> return err;
> }
>
> +static void loop_disable_partscan(struct loop_device *lo)
> +{
> + mutex_lock(&loop_ctl_mutex);
> + lo->lo_flags = 0;
> + if (!part_shift)
> + lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
> + mutex_unlock(&loop_ctl_mutex);
> +}
> +
> static int __loop_clr_fd(struct loop_device *lo, bool release)
> {
> struct file *filp = NULL;
> @@ -1096,9 +1105,6 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
>
> partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev;
> lo_number = lo->lo_number;
> - lo->lo_flags = 0;
> - if (!part_shift)
> - lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
> loop_unprepare_queue(lo);
> out_unlock:
> mutex_unlock(&loop_ctl_mutex);
> @@ -1121,6 +1127,9 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
> /* Device is gone, no point in returning error */
> err = 0;
> }
> +
> + loop_disable_partscan(lo);
> +
> /*
> * Need not hold loop_ctl_mutex to fput backing file.
> * Calling fput holding loop_ctl_mutex triggers a circular
So I don't think this change is actually correct. The problem is that once
lo->lo_state is set to Lo_unbound and loop_ctl_mutex is unlocked, the loop
device structure can be reused for a new device (bound to a new file). So
you cannot safely manipulate flags on lo->lo_disk anymore. But I think we
can just move the setting of lo->lo_state to Lo_unbound after partscan has
finished as well. There cannot be anybody else entering __loop_clr_fd() as
lo->lo_backing_file is already cleared and Lo_rundown state protects us
from all the other places trying to change the 'lo' device (please make
this last sentence into a comment in the code explaining why setting
lo->lo_state so late is fine). Thanks!
Honza
--
Jan Kara <[email protected]>
SUSE Labs, CR
On 02/21/2019 07:30 PM, Jan Kara wrote:
> On Thu 21-02-19 12:17:35, Dongli Zhang wrote:
>> Commit 0da03cab87e6
>> ("loop: Fix deadlock when calling blkdev_reread_part()") moves
>> blkdev_reread_part() out of the loop_ctl_mutex. However,
>> GENHD_FL_NO_PART_SCAN is set before __blkdev_reread_part(). As a result,
>> __blkdev_reread_part() will fail the check of GENHD_FL_NO_PART_SCAN and
>> will not rescan the loop device to delete all partitions.
>>
>> Below are steps to reproduce the issue:
>>
>> step1 # dd if=/dev/zero of=tmp.raw bs=1M count=100
>> step2 # losetup -P /dev/loop0 tmp.raw
>> step3 # parted /dev/loop0 mklabel gpt
>> step4 # parted -a none -s /dev/loop0 mkpart primary 64s 1
>> step5 # losetup -d /dev/loop0
>
> Can you perhaps write a blktest for this? Thanks!
I will write a blktest for above case. Thanks for the suggestion.
>
>> Step5 will not be able to delete /dev/loop0p1 (introduced by step4) and
>> there is below kernel warning message:
>>
>> [ 464.414043] __loop_clr_fd: partition scan of loop0 failed (rc=-22)
>>
>> This patch sets GENHD_FL_NO_PART_SCAN after blkdev_reread_part().
>>
>> Fixes: 0da03cab87e6 ("loop: Fix deadlock when calling blkdev_reread_part()")
>> Signed-off-by: Dongli Zhang <[email protected]>
>> ---
>> drivers/block/loop.c | 15 ++++++++++++---
>> 1 file changed, 12 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/block/loop.c b/drivers/block/loop.c
>> index 7908673..736e55b 100644
>> --- a/drivers/block/loop.c
>> +++ b/drivers/block/loop.c
>> @@ -1034,6 +1034,15 @@ loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
>> return err;
>> }
>>
>> +static void loop_disable_partscan(struct loop_device *lo)
>> +{
>> + mutex_lock(&loop_ctl_mutex);
>> + lo->lo_flags = 0;
>> + if (!part_shift)
>> + lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
>> + mutex_unlock(&loop_ctl_mutex);
>> +}
>> +
>> static int __loop_clr_fd(struct loop_device *lo, bool release)
>> {
>> struct file *filp = NULL;
>> @@ -1096,9 +1105,6 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
>>
>> partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev;
>> lo_number = lo->lo_number;
>> - lo->lo_flags = 0;
>> - if (!part_shift)
>> - lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
>> loop_unprepare_queue(lo);
>> out_unlock:
>> mutex_unlock(&loop_ctl_mutex);
>> @@ -1121,6 +1127,9 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
>> /* Device is gone, no point in returning error */
>> err = 0;
>> }
>> +
>> + loop_disable_partscan(lo);
>> +
>> /*
>> * Need not hold loop_ctl_mutex to fput backing file.
>> * Calling fput holding loop_ctl_mutex triggers a circular
>
> So I don't think this change is actually correct. The problem is that once
> lo->lo_state is set to Lo_unbound and loop_ctl_mutex is unlocked, the loop
> device structure can be reused for a new device (bound to a new file). So
> you cannot safely manipulate flags on lo->lo_disk anymore. But I think we
> can just move the setting of lo->lo_state to Lo_unbound after partscan has
> finished as well. There cannot be anybody else entering __loop_clr_fd() as
> lo->lo_backing_file is already cleared and Lo_rundown state protects us
> from all the other places trying to change the 'lo' device (please make
> this last sentence into a comment in the code explaining why setting
> lo->lo_state so late is fine). Thanks!
I will set lo->lo_state to Lo_unbound after partscan in v2.
Thank you very much!
Dongli Zhang
>
> Honza
>