diff mbox series

[OLK-5.10,v3,3/4] md/raid10: fix wrong setting of max_corr_read_errors

Message ID 20230515134808.3936750-4-linan666@huaweicloud.com
State New
Headers
Series md: bugfix of writing raid sysfs |

Commit Message

Li Nan May 15, 2023, 1:48 p.m. UTC 
  From: Li Nan <linan122@huawei.com>

max_corr_read_errors should not be negative number. Change it to
unsigned int where use it.

Fixes: 1e50915fe0bb ("raid: improve MD/raid10 handling of correctable read errors.")
Signed-off-by: Li Nan <linan122@huawei.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/md.c     | 2 +-
 drivers/md/raid10.c | 5 +++--
 2 files changed, 4 insertions(+), 3 deletions(-)

Comments

Song Liu May 19, 2023, 10:06 p.m. UTC | #1 
On Mon, May 15, 2023 at 6:49 AM <linan666@huaweicloud.com> wrote:
>
> From: Li Nan <linan122@huawei.com>
>
> max_corr_read_errors should not be negative number. Change it to
> unsigned int where use it.
>
> Fixes: 1e50915fe0bb ("raid: improve MD/raid10 handling of correctable read errors.")
> Signed-off-by: Li Nan <linan122@huawei.com>
> Reviewed-by: Yu Kuai <yukuai3@huawei.com>
> ---
>  drivers/md/md.c     | 2 +-
>  drivers/md/raid10.c | 5 +++--
>  2 files changed, 4 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 5bba071ea907..b69ddfb1662a 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -4484,7 +4484,7 @@ __ATTR_PREALLOC(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_stor
>
>  static ssize_t
>  max_corrected_read_errors_show(struct mddev *mddev, char *page) {
> -       return sprintf(page, "%d\n",
> +       return sprintf(page, "%u\n",
>                        atomic_read(&mddev->max_corr_read_errors));
>  }

max_corr_read_errors is atomic_t, so a signed integer. So these
signed => unsigned changes are pretty error prone. Can we just
add check in max_corrected_read_errors_store() so we never store
a negative value?

Thanks,
Song

>
> diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
> index 4fcfcb350d2b..4d615fcc6a50 100644
> --- a/drivers/md/raid10.c
> +++ b/drivers/md/raid10.c
> @@ -2727,7 +2727,8 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
>         int sect = 0; /* Offset from r10_bio->sector */
>         int sectors = r10_bio->sectors;
>         struct md_rdev *rdev;
> -       int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
> +       unsigned int max_read_errors =
> +                       atomic_read(&mddev->max_corr_read_errors);
>         int d = r10_bio->devs[r10_bio->read_slot].devnum;
>
>         /* still own a reference to this rdev, so it cannot
> @@ -2743,7 +2744,7 @@ static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
>         check_decay_read_errors(mddev, rdev);
>         atomic_inc(&rdev->read_errors);
>         if (atomic_read(&rdev->read_errors) > max_read_errors) {
> -               pr_notice("md/raid10:%s: %pg: Raid device exceeded read_error threshold [cur %d:max %d]\n",
> +               pr_notice("md/raid10:%s: %pg: Raid device exceeded read_error threshold [cur %u:max %u]\n",
>                           mdname(mddev), rdev->bdev,
>                           atomic_read(&rdev->read_errors), max_read_errors);
>                 pr_notice("md/raid10:%s: %pg: Failing raid device\n",
> --
> 2.31.1
>
Li Nan May 20, 2023, 12:46 a.m. UTC | #2 
在 2023/5/20 6:06, Song Liu 写道:
> On Mon, May 15, 2023 at 6:49 AM <linan666@huaweicloud.com> wrote:
>>
>> From: Li Nan <linan122@huawei.com>
>>
>> max_corr_read_errors should not be negative number. Change it to
>> unsigned int where use it.
>>
>> Fixes: 1e50915fe0bb ("raid: improve MD/raid10 handling of correctable read errors.")
>> Signed-off-by: Li Nan <linan122@huawei.com>
>> Reviewed-by: Yu Kuai <yukuai3@huawei.com>
>> ---
>>   drivers/md/md.c     | 2 +-
>>   drivers/md/raid10.c | 5 +++--
>>   2 files changed, 4 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/md/md.c b/drivers/md/md.c
>> index 5bba071ea907..b69ddfb1662a 100644
>> --- a/drivers/md/md.c
>> +++ b/drivers/md/md.c
>> @@ -4484,7 +4484,7 @@ __ATTR_PREALLOC(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_stor
>>
>>   static ssize_t
>>   max_corrected_read_errors_show(struct mddev *mddev, char *page) {
>> -       return sprintf(page, "%d\n",
>> +       return sprintf(page, "%u\n",
>>                         atomic_read(&mddev->max_corr_read_errors));
>>   }
> 
> max_corr_read_errors is atomic_t, so a signed integer. So these
> signed => unsigned changes are pretty error prone. Can we just
> add check in max_corrected_read_errors_store() so we never store
> a negative value?
> 
> Thanks,
> Song
> 

I will check input in v4
diff mbox series

Patch

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 5bba071ea907..b69ddfb1662a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4484,7 +4484,7 @@  __ATTR_PREALLOC(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_stor
 
 static ssize_t
 max_corrected_read_errors_show(struct mddev *mddev, char *page) {
-	return sprintf(page, "%d\n",
+	return sprintf(page, "%u\n",
 		       atomic_read(&mddev->max_corr_read_errors));
 }
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 4fcfcb350d2b..4d615fcc6a50 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2727,7 +2727,8 @@  static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 	int sect = 0; /* Offset from r10_bio->sector */
 	int sectors = r10_bio->sectors;
 	struct md_rdev *rdev;
-	int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
+	unsigned int max_read_errors =
+			atomic_read(&mddev->max_corr_read_errors);
 	int d = r10_bio->devs[r10_bio->read_slot].devnum;
 
 	/* still own a reference to this rdev, so it cannot
@@ -2743,7 +2744,7 @@  static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10
 	check_decay_read_errors(mddev, rdev);
 	atomic_inc(&rdev->read_errors);
 	if (atomic_read(&rdev->read_errors) > max_read_errors) {
-		pr_notice("md/raid10:%s: %pg: Raid device exceeded read_error threshold [cur %d:max %d]\n",
+		pr_notice("md/raid10:%s: %pg: Raid device exceeded read_error threshold [cur %u:max %u]\n",
 			  mdname(mddev), rdev->bdev,
 			  atomic_read(&rdev->read_errors), max_read_errors);
 		pr_notice("md/raid10:%s: %pg: Failing raid device\n",