[PATCH v6 2/3] md/raid10: resize r10bio_pool for reshape
From: Chen Cheng
Date: Tue Jun 23 2026 - 08:40:32 EST
From: Chen Cheng <chencheng@xxxxxxxxx>
When reshape grows raid_disks, the pool must also switch to new geometry
object size , and allocate a new geometry size pool and replace the old.
But not for shrinking reshape, because regular I/O can still use the
prev geo for sectors that have not crossed reshape_progress yet.
Signed-off-by: Chen Cheng <chencheng@xxxxxxxxx>
---
drivers/md/raid10.c | 44 +++++++++++++++++++++++++++++++++-----------
drivers/md/raid10.h | 2 +-
2 files changed, 34 insertions(+), 12 deletions(-)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index cee5a253a281..d740744a9746 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -101,14 +101,25 @@ static void end_reshape(struct r10conf *conf);
static inline struct r10bio *get_resync_r10bio(struct bio *bio)
{
return get_resync_pages(bio)->raid_bio;
}
-static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
+static inline int calc_r10bio_size(unsigned int raid_disks)
{
- struct r10conf *conf = data;
- int size = offsetof(struct r10bio, devs[conf->geo.raid_disks]);
+ return offsetof(struct r10bio, devs[raid_disks]);
+}
+
+static mempool_t *create_r10bio_pool(unsigned int raid_disks)
+{
+ int size = calc_r10bio_size(raid_disks);
+
+ return mempool_create_kmalloc_pool(NR_RAID_BIOS, size);
+}
+
+static struct r10bio *alloc_r10bio(unsigned int raid_disks, gfp_t gfp_flags)
+{
+ int size = calc_r10bio_size(raid_disks);
/* allocate a r10bio with room for raid_disks entries in the
* bios array */
return kzalloc(size, gfp_flags);
}
@@ -135,11 +146,11 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
struct bio *bio;
int j;
int nalloc, nalloc_rp;
struct resync_pages *rps;
- r10_bio = r10bio_pool_alloc(gfp_flags, conf);
+ r10_bio = alloc_r10bio(conf->geo.raid_disks, gfp_flags);
if (!r10_bio)
return NULL;
if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery) ||
test_bit(MD_RECOVERY_RESHAPE, &conf->mddev->recovery))
@@ -275,11 +286,11 @@ static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio)
static void free_r10bio(struct r10bio *r10_bio)
{
struct r10conf *conf = r10_bio->mddev->private;
put_all_bios(conf, r10_bio);
- mempool_free(r10_bio, &conf->r10bio_pool);
+ mempool_free(r10_bio, conf->r10bio_pool);
}
static void put_buf(struct r10bio *r10_bio)
{
struct r10conf *conf = r10_bio->mddev->private;
@@ -1537,11 +1548,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
{
struct r10conf *conf = mddev->private;
struct r10bio *r10_bio;
- r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
+ r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
r10_bio->master_bio = bio;
r10_bio->sectors = sectors;
r10_bio->mddev = mddev;
@@ -1729,11 +1740,11 @@ static int raid10_handle_discard(struct mddev *mddev, struct bio *bio)
last_stripe_index *= geo->far_copies;
end_disk_offset = (bio_end & geo->chunk_mask) +
(last_stripe_index << geo->chunk_shift);
retry_discard:
- r10_bio = mempool_alloc(&conf->r10bio_pool, GFP_NOIO);
+ r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
r10_bio->mddev = mddev;
r10_bio->state = 0;
r10_bio->sectors = 0;
r10_bio->read_slot = -1;
memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * geo->raid_disks);
@@ -3830,11 +3841,11 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new)
static void raid10_free_conf(struct r10conf *conf)
{
if (!conf)
return;
- mempool_exit(&conf->r10bio_pool);
+ mempool_destroy(conf->r10bio_pool);
kfree(conf->mirrors);
kfree(conf->mirrors_old);
kfree(conf->mirrors_new);
safe_put_page(conf->tmppage);
bioset_exit(&conf->bio_split);
@@ -3877,13 +3888,12 @@ static struct r10conf *setup_conf(struct mddev *mddev)
if (!conf->tmppage)
goto out;
conf->geo = geo;
conf->copies = copies;
- err = mempool_init(&conf->r10bio_pool, NR_RAID_BIOS, r10bio_pool_alloc,
- rbio_pool_free, conf);
- if (err)
+ conf->r10bio_pool = create_r10bio_pool(conf->geo.raid_disks);
+ if (!conf->r10bio_pool)
goto out;
err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
if (err)
goto out;
@@ -4373,10 +4383,11 @@ static int raid10_start_reshape(struct mddev *mddev)
struct geom new;
struct r10conf *conf = mddev->private;
struct md_rdev *rdev;
int spares = 0;
int ret;
+ mempool_t *new_pool = NULL;
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return -EBUSY;
if (setup_geo(&new, mddev, geo_start) != conf->copies)
@@ -4409,10 +4420,15 @@ static int raid10_start_reshape(struct mddev *mddev)
if (spares < mddev->delta_disks)
return -EINVAL;
conf->offset_diff = min_offset_diff;
+ if (mddev->delta_disks > 0) {
+ new_pool = create_r10bio_pool(new.raid_disks);
+ if (!new_pool)
+ return -ENOMEM;
+ }
spin_lock_irq(&conf->device_lock);
if (conf->mirrors_new) {
memcpy(conf->mirrors_new, conf->mirrors,
sizeof(struct raid10_info)*conf->prev.raid_disks);
smp_mb();
@@ -4509,10 +4525,14 @@ static int raid10_start_reshape(struct mddev *mddev)
mddev->degraded = calc_degraded(conf);
spin_unlock_irq(&conf->device_lock);
mddev->raid_disks = conf->geo.raid_disks;
mddev->reshape_position = conf->reshape_progress;
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
+ if (new_pool) {
+ mempool_destroy(conf->r10bio_pool);
+ conf->r10bio_pool = new_pool;
+ }
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
@@ -4531,10 +4551,12 @@ static int raid10_start_reshape(struct mddev *mddev)
smp_wmb();
conf->reshape_progress = MaxSector;
conf->reshape_safe = MaxSector;
mddev->reshape_position = MaxSector;
spin_unlock_irq(&conf->device_lock);
+ if (new_pool)
+ mempool_destroy(new_pool);
return ret;
}
/* Calculate the last device-address that could contain
* any block from the chunk that includes the array-address 's'
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index ec79d87fb92f..b711626a5db7 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -85,11 +85,11 @@ struct r10conf {
int have_replacement; /* There is at least one
* replacement device.
*/
wait_queue_head_t wait_barrier;
- mempool_t r10bio_pool;
+ mempool_t *r10bio_pool;
mempool_t r10buf_pool;
struct page *tmppage;
struct bio_set bio_split;
/* When taking over an array from a different personality, we store
--
2.54.0