From: Li Nan <linan666@huaweicloud.com>
To: Xiao Ni <xni@redhat.com>, linan666@huaweicloud.com
Cc: corbet@lwn.net, song@kernel.org, yukuai@fnnas.com, hare@suse.de,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-raid@vger.kernel.org, yangerkun@huawei.com,
yi.zhang@huawei.com
Subject: Re: [PATCH v8 2/4] md: init bioset in mddev_init
Date: Mon, 3 Nov 2025 20:32:23 +0800 [thread overview]
Message-ID: <2d4c41f5-6886-98a3-8ccc-54d8a4f89fdc@huaweicloud.com> (raw)
In-Reply-To: <CALTww28LKk6bH4tuEA4DD3uAJScCVAQUBn0d0JYu3AvVjxetzQ@mail.gmail.com>
在 2025/11/3 9:23, Xiao Ni 写道:
> On Thu, Oct 30, 2025 at 2:36 PM <linan666@huaweicloud.com> wrote:
>>
>> From: Li Nan <linan122@huawei.com>
>>
>> IO operations may be needed before md_run(), such as updating metadata
>> after writing sysfs. Without bioset, this triggers a NULL pointer
>> dereference as below:
>>
>> BUG: kernel NULL pointer dereference, address: 0000000000000020
>> Call Trace:
>> md_update_sb+0x658/0xe00
>> new_level_store+0xc5/0x120
>> md_attr_store+0xc9/0x1e0
>> sysfs_kf_write+0x6f/0xa0
>> kernfs_fop_write_iter+0x141/0x2a0
>> vfs_write+0x1fc/0x5a0
>> ksys_write+0x79/0x180
>> __x64_sys_write+0x1d/0x30
>> x64_sys_call+0x2818/0x2880
>> do_syscall_64+0xa9/0x580
>> entry_SYSCALL_64_after_hwframe+0x4b/0x53
>>
>> Reproducer
>> ```
>> mdadm -CR /dev/md0 -l1 -n2 /dev/sd[cd]
>> echo inactive > /sys/block/md0/md/array_state
>> echo 10 > /sys/block/md0/md/new_level
>> ```
>>
>
> Hi Li Nan
>
>> mddev_init() can only be called once per mddev, no need to test if bioset
>> has been initialized anymore.
>
> The patch looks good to me. But I don't understand the message here.
> This patch changes the alloc/free bioset positions. What's the meaning
> of "no need to test if bioset has been initialized anymore"?
>
> Regards
> Xiao
Hi Xiao
Thanks for your review.
Sorry for causing any misunderstanding.
Old code:
- if (!bioset_initialized(&mddev->bio_set)) {
- err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
New code:
+ err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
bioset_initialized() is removed. Can I describe it as:
mddev_init() can only be called once per mddev, thus bioset_initialized()
can be removed.
>>
>> Fixes: d981ed841930 ("md: Add new_level sysfs interface")
>> Signed-off-by: Li Nan <linan122@huawei.com>
>> ---
>> drivers/md/md.c | 69 +++++++++++++++++++++++--------------------------
>> 1 file changed, 33 insertions(+), 36 deletions(-)
>>
>> diff --git a/drivers/md/md.c b/drivers/md/md.c
>> index f6fd55a1637b..dffc6a482181 100644
>> --- a/drivers/md/md.c
>> +++ b/drivers/md/md.c
>> @@ -730,6 +730,8 @@ static void mddev_clear_bitmap_ops(struct mddev *mddev)
>>
>> int mddev_init(struct mddev *mddev)
>> {
>> + int err = 0;
>> +
>> if (!IS_ENABLED(CONFIG_MD_BITMAP))
>> mddev->bitmap_id = ID_BITMAP_NONE;
>> else
>> @@ -741,10 +743,23 @@ int mddev_init(struct mddev *mddev)
>>
>> if (percpu_ref_init(&mddev->writes_pending, no_op,
>> PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
>> - percpu_ref_exit(&mddev->active_io);
>> - return -ENOMEM;
>> + err = -ENOMEM;
>> + goto exit_acitve_io;
>> }
>>
>> + err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
>> + if (err)
>> + goto exit_writes_pending;
>> +
>> + err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
>> + if (err)
>> + goto exit_bio_set;
>> +
>> + err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE,
>> + offsetof(struct md_io_clone, bio_clone), 0);
>> + if (err)
>> + goto exit_sync_set;
>> +
>> /* We want to start with the refcount at zero */
>> percpu_ref_put(&mddev->writes_pending);
>>
>> @@ -773,11 +788,24 @@ int mddev_init(struct mddev *mddev)
>> INIT_WORK(&mddev->del_work, mddev_delayed_delete);
>>
>> return 0;
>> +
>> +exit_sync_set:
>> + bioset_exit(&mddev->sync_set);
>> +exit_bio_set:
>> + bioset_exit(&mddev->bio_set);
>> +exit_writes_pending:
>> + percpu_ref_exit(&mddev->writes_pending);
>> +exit_acitve_io:
>> + percpu_ref_exit(&mddev->active_io);
>> + return err;
>> }
>> EXPORT_SYMBOL_GPL(mddev_init);
>>
>> void mddev_destroy(struct mddev *mddev)
>> {
>> + bioset_exit(&mddev->bio_set);
>> + bioset_exit(&mddev->sync_set);
>> + bioset_exit(&mddev->io_clone_set);
>> percpu_ref_exit(&mddev->active_io);
>> percpu_ref_exit(&mddev->writes_pending);
>> }
>> @@ -6393,29 +6421,9 @@ int md_run(struct mddev *mddev)
>> nowait = nowait && bdev_nowait(rdev->bdev);
>> }
>>
>> - if (!bioset_initialized(&mddev->bio_set)) {
>> - err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
>> - if (err)
>> - return err;
>> - }
>> - if (!bioset_initialized(&mddev->sync_set)) {
>> - err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
>> - if (err)
>> - goto exit_bio_set;
>> - }
>> -
>> - if (!bioset_initialized(&mddev->io_clone_set)) {
>> - err = bioset_init(&mddev->io_clone_set, BIO_POOL_SIZE,
>> - offsetof(struct md_io_clone, bio_clone), 0);
>> - if (err)
>> - goto exit_sync_set;
>> - }
>> -
>> pers = get_pers(mddev->level, mddev->clevel);
>> - if (!pers) {
>> - err = -EINVAL;
>> - goto abort;
>> - }
>> + if (!pers)
>> + return -EINVAL;
>> if (mddev->level != pers->head.id) {
>> mddev->level = pers->head.id;
>> mddev->new_level = pers->head.id;
>> @@ -6426,8 +6434,7 @@ int md_run(struct mddev *mddev)
>> pers->start_reshape == NULL) {
>> /* This personality cannot handle reshaping... */
>> put_pers(pers);
>> - err = -EINVAL;
>> - goto abort;
>> + return -EINVAL;
>> }
>>
>> if (pers->sync_request) {
>> @@ -6554,12 +6561,6 @@ int md_run(struct mddev *mddev)
>> mddev->private = NULL;
>> put_pers(pers);
>> md_bitmap_destroy(mddev);
>> -abort:
>> - bioset_exit(&mddev->io_clone_set);
>> -exit_sync_set:
>> - bioset_exit(&mddev->sync_set);
>> -exit_bio_set:
>> - bioset_exit(&mddev->bio_set);
>> return err;
>> }
>> EXPORT_SYMBOL_GPL(md_run);
>> @@ -6784,10 +6785,6 @@ static void __md_stop(struct mddev *mddev)
>> mddev->private = NULL;
>> put_pers(pers);
>> clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
>> -
>> - bioset_exit(&mddev->bio_set);
>> - bioset_exit(&mddev->sync_set);
>> - bioset_exit(&mddev->io_clone_set);
>> }
>>
>> void md_stop(struct mddev *mddev)
>> --
>> 2.39.2
>>
>
>
> .
--
Thanks,
Nan
next prev parent reply other threads:[~2025-11-03 12:32 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-30 6:28 [PATCH v8 0/4] make logical block size configurable linan666
2025-10-30 6:28 ` [PATCH v8 1/4] md: delete md_redundancy_group when array is becoming inactive linan666
2025-11-03 0:27 ` Xiao Ni
2025-10-30 6:28 ` [PATCH v8 2/4] md: init bioset in mddev_init linan666
2025-11-03 1:23 ` Xiao Ni
2025-11-03 12:32 ` Li Nan [this message]
2025-11-04 1:20 ` Xiao Ni
2025-10-30 6:28 ` [PATCH v8 3/4] md/raid0: Move queue limit setup before r0conf initialization linan666
2025-11-03 1:47 ` Xiao Ni
2025-10-30 6:28 ` [PATCH v8 4/4] md: allow configuring logical block size linan666
2025-11-03 3:11 ` Xiao Ni
2025-11-03 13:09 ` Li Nan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=2d4c41f5-6886-98a3-8ccc-54d8a4f89fdc@huaweicloud.com \
--to=linan666@huaweicloud.com \
--cc=corbet@lwn.net \
--cc=hare@suse.de \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=song@kernel.org \
--cc=xni@redhat.com \
--cc=yangerkun@huawei.com \
--cc=yi.zhang@huawei.com \
--cc=yukuai@fnnas.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).