From: Jack Wang <jinpu.wang@ionos.com>
To: Song Liu <song@kernel.org>, Yu Kuai <yukuai@fygo.io>,
linux-raid@vger.kernel.org, Nilay Shroff <nilay@linux.ibm.com>,
abd.masalkhi@gmail.com
Cc: linux-block@vger.kernel.org, Jens Axboe <axboe@kernel.dk>,
Christoph Hellwig <hch@lst.de>,
Damien Le Moal <dlemoal@kernel.org>,
Ming Lei <tom.leiming@gmail.com>, Xiao Ni <xiao@kernel.org>,
Li Nan <magiclinan@didiglobal.com>,
Mike Snitzer <snitzer@kernel.org>,
Mikulas Patocka <mpatocka@redhat.com>,
dm-devel@lists.linux.dev, linux-kernel@vger.kernel.org,
Jack Wang <jinpu.wang@cloud.ionos.com>
Subject: [PATCH v2 1/8] md: pass a queue_limits down to ->hot_add_disk()
Date: Thu, 10 Sep 2026 10:11:06 +0200 [thread overview]
Message-ID: <20260910081114.1605746-2-jinpu.wang@ionos.com> (raw)
In-Reply-To: <20260910081114.1605746-1-jinpu.wang@ionos.com>
From: Jack Wang <jinpu.wang@cloud.ionos.com>
Adding a leg stacks its queue limits, which mddev_stack_new_rdev() does
by taking q->limits_lock itself. Callers holding reconfig_mutex or a
suspended array cannot allow that, and must own the update instead.
Give ->hot_add_disk(), remove_and_add_spares() and
md_choose_sync_action() a struct queue_limits argument with three
states: an update to stack into, NULL to let the personality take the
lock as before, or MDDEV_STACK_SKIP to add the leg without touching the
limits, for callers that can do neither. mddev_stack_rdev_into() stacks
into a caller-owned update without the lock.
Every caller still passes NULL and nothing passes the sentinel yet, so
there is no functional change; the users follow.
Assisted-by: LLM
Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
---
drivers/md/dm-raid.c | 2 +-
drivers/md/md-linear.c | 28 ++++++++++++++----
drivers/md/md.c | 66 ++++++++++++++++++++++++++++++++----------
drivers/md/md.h | 11 ++++++-
drivers/md/raid1.c | 10 +++++--
drivers/md/raid10.c | 19 +++++++++---
drivers/md/raid5.c | 5 ++--
7 files changed, 110 insertions(+), 31 deletions(-)
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 8f5a5e1342a9..21a1922bee4f 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3923,7 +3923,7 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs)
clear_bit(Faulty, &r->flags);
clear_bit(WriteErrorSeen, &r->flags);
- if (mddev->pers->hot_add_disk(mddev, r)) {
+ if (mddev->pers->hot_add_disk(mddev, r, NULL)) {
/* Failed to revive this device, try next */
r->raid_disk = r->saved_raid_disk = -1;
r->flags = flags;
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 73b367b61b87..da82c313d459 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -65,11 +65,16 @@ static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disk
return array_sectors;
}
-static int linear_set_limits(struct mddev *mddev)
+static int linear_set_limits(struct mddev *mddev,
+ struct queue_limits *caller_lim)
{
struct queue_limits lim;
int err;
+ /* the caller can neither stack nor take q->limits_lock */
+ if (caller_lim == MDDEV_STACK_SKIP)
+ return 0;
+
md_init_stacking_limits(&lim);
lim.features |= BLK_FEAT_NOWAIT;
lim.max_hw_sectors = mddev->chunk_sectors;
@@ -82,10 +87,20 @@ static int linear_set_limits(struct mddev *mddev)
if (err)
return err;
+ /*
+ * The caller owns an update and commits it itself; taking
+ * q->limits_lock here would take it a second time.
+ */
+ if (caller_lim) {
+ *caller_lim = lim;
+ return 0;
+ }
+
return queue_limits_set(mddev->gendisk->queue, &lim);
}
-static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
+static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks,
+ struct queue_limits *lim)
{
struct linear_conf *conf;
struct md_rdev *rdev;
@@ -151,7 +166,7 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
conf->disks[i].rdev->sectors;
if (!mddev_is_dm(mddev)) {
- ret = linear_set_limits(mddev);
+ ret = linear_set_limits(mddev, lim);
if (ret)
goto out;
}
@@ -171,7 +186,7 @@ static int linear_run(struct mddev *mddev)
if (md_check_no_bitmap(mddev))
return -EINVAL;
- conf = linear_conf(mddev, mddev->raid_disks);
+ conf = linear_conf(mddev, mddev->raid_disks, NULL);
if (IS_ERR(conf))
return PTR_ERR(conf);
@@ -186,7 +201,8 @@ static int linear_run(struct mddev *mddev)
return ret;
}
-static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
+static int linear_add(struct mddev *mddev, struct md_rdev *rdev,
+ struct queue_limits *lim)
{
/* Adding a drive to a linear array allows the array to grow.
* It is permitted if the new drive has a matching superblock
@@ -204,7 +220,7 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
rdev->raid_disk = rdev->saved_raid_disk;
rdev->saved_raid_disk = -1;
- newconf = linear_conf(mddev, mddev->raid_disks + 1);
+ newconf = linear_conf(mddev, mddev->raid_disks + 1, lim);
if (IS_ERR(newconf))
return PTR_ERR(newconf);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 680b34a63cb3..28fc903ffeea 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -94,8 +94,8 @@ static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
*/
static struct workqueue_struct *md_misc_wq;
-static int remove_and_add_spares(struct mddev *mddev,
- struct md_rdev *this);
+static int remove_and_add_spares(struct mddev *mddev, struct md_rdev *this,
+ struct queue_limits *lim);
static void mddev_detach(struct mddev *mddev);
static void export_rdev(struct md_rdev *rdev);
static void md_wakeup_thread_directly(struct md_thread __rcu **thread);
@@ -2994,7 +2994,7 @@ static int add_bound_rdev(struct md_rdev *rdev)
*/
super_types[mddev->major_version].
validate_super(mddev, NULL/*freshest*/, rdev);
- err = mddev->pers->hot_add_disk(mddev, rdev);
+ err = mddev->pers->hot_add_disk(mddev, rdev, NULL);
if (err) {
md_kick_rdev_from_array(rdev);
return err;
@@ -3110,7 +3110,7 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
} else if (cmd_match(buf, "remove")) {
if (rdev->mddev->pers) {
clear_bit(Blocked, &rdev->flags);
- remove_and_add_spares(rdev->mddev, rdev);
+ remove_and_add_spares(rdev->mddev, rdev, NULL);
}
if (rdev->raid_disk >= 0)
err = -EBUSY;
@@ -3314,7 +3314,7 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
if (rdev->mddev->pers->hot_remove_disk == NULL)
return -EINVAL;
clear_bit(Blocked, &rdev->flags);
- remove_and_add_spares(rdev->mddev, rdev);
+ remove_and_add_spares(rdev->mddev, rdev, NULL);
if (rdev->raid_disk >= 0)
return -EBUSY;
set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
@@ -3344,7 +3344,8 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
rdev->saved_raid_disk = -1;
clear_bit(In_sync, &rdev->flags);
clear_bit(Bitmap_sync, &rdev->flags);
- err = rdev->mddev->pers->hot_add_disk(rdev->mddev, rdev);
+ err = rdev->mddev->pers->hot_add_disk(rdev->mddev, rdev,
+ NULL);
if (err) {
rdev->raid_disk = -1;
return err;
@@ -6275,6 +6276,40 @@ int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev)
}
EXPORT_SYMBOL_GPL(mddev_stack_new_rdev);
+/*
+ * Stack a new rdev into limits the caller already holds limits_lock for and
+ * will commit itself. Used from paths that must take limits_lock before
+ * quiescing the array, see md_start_sync().
+ */
+int mddev_stack_rdev_into(struct mddev *mddev, struct md_rdev *rdev,
+ struct queue_limits *lim)
+{
+ struct queue_limits tmp = *lim;
+
+ if (mddev_is_dm(mddev))
+ return 0;
+
+ if (queue_logical_block_size(rdev->bdev->bd_disk->queue) >
+ queue_logical_block_size(mddev->gendisk->queue)) {
+ pr_err("%s: incompatible logical_block_size, can not add\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+
+ queue_limits_stack_bdev(&tmp, rdev->bdev, rdev->data_offset,
+ mddev->gendisk->disk_name);
+
+ if (!queue_limits_stack_integrity_bdev(&tmp, rdev->bdev)) {
+ pr_err("%s: incompatible integrity profile for %pg\n",
+ mdname(mddev), rdev->bdev);
+ return -ENXIO;
+ }
+
+ *lim = tmp;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mddev_stack_rdev_into);
+
/* update the optimal I/O size after a reshape */
void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes)
{
@@ -7706,7 +7741,7 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev)
goto kick_rdev;
clear_bit(Blocked, &rdev->flags);
- remove_and_add_spares(mddev, rdev);
+ remove_and_add_spares(mddev, rdev, NULL);
if (rdev->raid_disk >= 0)
goto busy;
@@ -10167,8 +10202,8 @@ static int remove_spares(struct mddev *mddev, struct md_rdev *this)
return removed;
}
-static int remove_and_add_spares(struct mddev *mddev,
- struct md_rdev *this)
+static int remove_and_add_spares(struct mddev *mddev, struct md_rdev *this,
+ struct queue_limits *lim)
{
struct md_rdev *rdev;
int spares = 0;
@@ -10191,7 +10226,7 @@ static int remove_and_add_spares(struct mddev *mddev,
continue;
if (!test_bit(Journal, &rdev->flags))
rdev->recovery_offset = 0;
- if (mddev->pers->hot_add_disk(mddev, rdev) == 0) {
+ if (mddev->pers->hot_add_disk(mddev, rdev, lim) == 0) {
/* failure here is OK */
sysfs_link_rdev(mddev, rdev);
if (!test_bit(Journal, &rdev->flags))
@@ -10206,7 +10241,8 @@ static int remove_and_add_spares(struct mddev *mddev,
return spares;
}
-static bool md_choose_sync_action(struct mddev *mddev, int *spares)
+static bool md_choose_sync_action(struct mddev *mddev, int *spares,
+ struct queue_limits *lim)
{
/* Check if reshape is in progress first. */
if (mddev->reshape_position != MaxSector) {
@@ -10234,7 +10270,7 @@ static bool md_choose_sync_action(struct mddev *mddev, int *spares)
* also removed and re-added, to allow the personality to fail the
* re-add.
*/
- *spares = remove_and_add_spares(mddev, NULL);
+ *spares = remove_and_add_spares(mddev, NULL, lim);
if (*spares || test_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery)) {
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
@@ -10294,11 +10330,11 @@ static void md_start_sync(struct work_struct *ws)
* As we only add devices that are already in-sync, we can
* activate the spares immediately.
*/
- remove_and_add_spares(mddev, NULL);
+ remove_and_add_spares(mddev, NULL, NULL);
goto not_running;
}
- if (!md_choose_sync_action(mddev, &spares))
+ if (!md_choose_sync_action(mddev, &spares, NULL))
goto not_running;
if (!mddev->pers->sync_request)
@@ -10849,7 +10885,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
rdev2->saved_raid_disk = -1;
else
rdev2->saved_raid_disk = role;
- ret = remove_and_add_spares(mddev, rdev2);
+ ret = remove_and_add_spares(mddev, rdev2, NULL);
pr_info("Activated spare: %pg\n",
rdev2->bdev);
/* wakeup mddev->thread here, so array could
diff --git a/drivers/md/md.h b/drivers/md/md.h
index b6d2e8929a0f..ebdd57677062 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -765,7 +765,8 @@ struct md_personality
* if appropriate, and should abort recovery if needed
*/
void (*error_handler)(struct mddev *mddev, struct md_rdev *rdev);
- int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev);
+ int (*hot_add_disk)(struct mddev *mddev, struct md_rdev *rdev,
+ struct queue_limits *lim);
int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev);
int (*spare_active) (struct mddev *mddev);
sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr,
@@ -1047,6 +1048,14 @@ int do_md_run(struct mddev *mddev);
int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
unsigned int flags);
int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev);
+int mddev_stack_rdev_into(struct mddev *mddev, struct md_rdev *rdev,
+ struct queue_limits *lim);
+/*
+ * Sentinel for the queue_limits argument of ->hot_add_disk(). The caller has
+ * no update to stack into and must not take q->limits_lock itself, so the leg
+ * is added with the array's current limits.
+ */
+#define MDDEV_STACK_SKIP ((struct queue_limits *)ERR_PTR(-EAGAIN))
void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes);
extern const struct block_device_operations md_fops;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index f0646fb24371..78effcac138d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1898,7 +1898,8 @@ static bool raid1_remove_conf(struct r1conf *conf, int disk)
return true;
}
-static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
+static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev,
+ struct queue_limits *lim)
{
struct r1conf *conf = mddev->private;
int err = -EEXIST;
@@ -1923,7 +1924,12 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
for (mirror = first; mirror <= last; mirror++) {
p = conf->mirrors + mirror;
if (!p->rdev) {
- err = mddev_stack_new_rdev(mddev, rdev);
+ if (lim == MDDEV_STACK_SKIP)
+ err = 0;
+ else if (lim)
+ err = mddev_stack_rdev_into(mddev, rdev, lim);
+ else
+ err = mddev_stack_new_rdev(mddev, rdev);
if (err)
return err;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 1093c798d9dd..222bd7badcff 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2095,7 +2095,8 @@ static int raid10_spare_active(struct mddev *mddev)
return count;
}
-static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
+static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev,
+ struct queue_limits *lim)
{
struct r10conf *conf = mddev->private;
int err = -EEXIST;
@@ -2130,7 +2131,12 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
continue;
}
- err = mddev_stack_new_rdev(mddev, rdev);
+ if (lim == MDDEV_STACK_SKIP)
+ err = 0;
+ else if (lim)
+ err = mddev_stack_rdev_into(mddev, rdev, lim);
+ else
+ err = mddev_stack_new_rdev(mddev, rdev);
if (err)
return err;
p->head_position = 0;
@@ -2147,7 +2153,12 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
clear_bit(In_sync, &rdev->flags);
set_bit(Replacement, &rdev->flags);
rdev->raid_disk = repl_slot;
- err = mddev_stack_new_rdev(mddev, rdev);
+ if (lim == MDDEV_STACK_SKIP)
+ err = 0;
+ else if (lim)
+ err = mddev_stack_rdev_into(mddev, rdev, lim);
+ else
+ err = mddev_stack_new_rdev(mddev, rdev);
if (err)
return err;
conf->fullsync = 1;
@@ -4484,7 +4495,7 @@ static int raid10_start_reshape(struct mddev *mddev)
rdev_for_each(rdev, mddev)
if (rdev->raid_disk < 0 &&
!test_bit(Faulty, &rdev->flags)) {
- if (raid10_add_disk(mddev, rdev) == 0) {
+ if (raid10_add_disk(mddev, rdev, NULL) == 0) {
if (rdev->raid_disk >=
conf->prev.raid_disks)
set_bit(In_sync, &rdev->flags);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b91545ce090d..0ec555ada64a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -8441,7 +8441,8 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
return err;
}
-static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
+static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev,
+ struct queue_limits *lim)
{
struct r5conf *conf = mddev->private;
int ret, err = -EEXIST;
@@ -8728,7 +8729,7 @@ static int raid5_start_reshape(struct mddev *mddev)
rdev_for_each(rdev, mddev)
if (rdev->raid_disk < 0 &&
!test_bit(Faulty, &rdev->flags)) {
- if (raid5_add_disk(mddev, rdev) == 0) {
+ if (raid5_add_disk(mddev, rdev, NULL) == 0) {
if (rdev->raid_disk
>= conf->previous_raid_disks)
set_bit(In_sync, &rdev->flags);
--
2.43.0
next prev parent reply other threads:[~2026-09-10 8:11 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-10 8:11 [PATCH v2 0/8] md: don't wait for q->limits_lock while md holds back I/O Jack Wang
2026-09-10 8:11 ` Jack Wang [this message]
2026-09-11 10:46 ` [PATCH v2 1/8] md: pass a queue_limits down to ->hot_add_disk() Nilay Shroff
2026-09-10 8:11 ` [PATCH v2 2/8] md: don't wait for q->limits_lock in check_sb_changes() Jack Wang
2026-09-10 8:11 ` [PATCH v2 3/8] md: pass a queue_limits through the rdev sysfs stores Jack Wang
2026-09-10 8:11 ` [PATCH v2 4/8] md: defer the io_opt update out of the sync thread Jack Wang
2026-09-10 8:11 ` [PATCH v2 5/8] md: take q->limits_lock before locking and suspending the array Jack Wang
2026-09-10 8:11 ` [PATCH v2 6/8] md: pass a queue_limits through ->run() Jack Wang
2026-09-11 10:54 ` Nilay Shroff
2026-09-10 8:11 ` [PATCH v2 7/8] md: open new legs before locking the array Jack Wang
2026-09-10 8:11 ` [PATCH v2 8/8] md: link a new leg's holder " Jack Wang
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=20260910081114.1605746-2-jinpu.wang@ionos.com \
--to=jinpu.wang@ionos.com \
--cc=abd.masalkhi@gmail.com \
--cc=axboe@kernel.dk \
--cc=dlemoal@kernel.org \
--cc=dm-devel@lists.linux.dev \
--cc=hch@lst.de \
--cc=jinpu.wang@cloud.ionos.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=magiclinan@didiglobal.com \
--cc=mpatocka@redhat.com \
--cc=nilay@linux.ibm.com \
--cc=snitzer@kernel.org \
--cc=song@kernel.org \
--cc=tom.leiming@gmail.com \
--cc=xiao@kernel.org \
--cc=yukuai@fygo.io \
/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
all inboxes | Powered by JetHome®