The Linux Kernel Mailing List
 help / color / mirror / Atom feed
* Re: [PATCH v3 6/8] md/raid1,raid10: use folio for sync path IO
       [not found] <CALTww29duRpWZkYQjRJM45DAG=gLiPzbtn9x+CHAFcF3XJXRTg@mail.gmail.com>
@ 2026-05-07  7:13 ` 李楠 Magic Li
  0 siblings, 0 replies; only message in thread
From: 李楠 Magic Li @ 2026-05-07  7:13 UTC (permalink / raw)
  To: Xiao Ni, linan666@huaweicloud.com
  Cc: song@kernel.org, yukuai@fnnas.com, linux-raid@vger.kernel.org,
	linux-kernel@vger.kernel.org, yangerkun@huawei.com,
	yi.zhang@huawei.com, 张同浩 Tonghao Zhang

On Thu Apr 30, 2026 at 9:54 AM CST, Xiao Ni wrote:
> Hi Nan
>
> On Thu, Apr 16, 2026 at 11:55 AM <linan666@huaweicloud.com> wrote:
>>
>> From: Li Nan <linan122@huawei.com>
>>
>> Convert all IO on the sync path to use folios, and rename page-related
>> identifiers to match folio.
>>
>> Since RESYNC_BLOCK_SIZE (64K) has higher allocation failure chance than 4k,
>> retry with lower orders to improve allocation reliability. A r1/10_bio may
>> have different rf->folio orders, so use minimum order as r1/10_bio sectors
>> to prevent exceeding size when adding folio to IO later.
>>
>> Clean up:
>> 1. Remove resync_get_all_folio() and invoke folio_get() directly instead.
>> 2. Clean up redundant while(0) loop in md_bio_reset_resync_folio().
>> 3. Clean up bio variable by directly referencing r10_bio->devs[j].bio
>>    instead in r1buf_pool_alloc() and r10buf_pool_alloc().
>> 4. Clean up RESYNC_PAGES.
>> 5. Remove resync_fetch_folio(), access 'rf->folio' directly.
>> 6. Remove resync_free_folio(), call folio_put() directly.
>> 7. clean up sync IO size calculation in raid1/10_sync_request.
>>
>> Signed-off-by: Li Nan <linan122@huawei.com>
>> ---
>>  drivers/md/md.c       |   2 +-
>>  drivers/md/raid1-10.c |  80 ++++---------
>>  drivers/md/raid1.c    | 209 +++++++++++++++-------------------
>>  drivers/md/raid10.c   | 254 +++++++++++++++++++++---------------------
>>  4 files changed, 240 insertions(+), 305 deletions(-)
>>
>> diff --git a/drivers/md/md.c b/drivers/md/md.c
>> index 5e83914d5c14..6554b849ac74 100644
>> --- a/drivers/md/md.c
>> +++ b/drivers/md/md.c
>> @@ -9440,7 +9440,7 @@ static bool sync_io_within_limit(struct mddev *mddev)
>>  {
>>         /*
>>          * For raid456, sync IO is stripe(4k) per IO, for other levels, it's
>> -        * RESYNC_PAGES(64k) per IO.
>> +        * RESYNC_BLOCK_SIZE(64k) per IO.
>>          */
>>         return atomic_read(&mddev->recovery_active) <
>>                (raid_is_456(mddev) ? 8 : 128) * sync_io_depth(mddev);
>> diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
>> index cda531d0720b..10200b0a3fd2 100644
>> --- a/drivers/md/raid1-10.c
>> +++ b/drivers/md/raid1-10.c
>> @@ -1,7 +1,6 @@
>>  // SPDX-License-Identifier: GPL-2.0
>>  /* Maximum size of each resync request */
>>  #define RESYNC_BLOCK_SIZE (64*1024)
>> -#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
>>  #define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
>>
>>  /* when we get a read error on a read-only array, we redirect to another
>> @@ -20,9 +19,9 @@
>>  #define MAX_PLUG_BIO 32
>>
>>  /* for managing resync I/O pages */
>> -struct resync_pages {
>> +struct resync_folio {
>>         void            *raid_bio;
>> -       struct page     *pages[RESYNC_PAGES];
>> +       struct folio    *folio;
>>  };
>>
>>  struct raid1_plug_cb {
>> @@ -36,77 +35,44 @@ static void rbio_pool_free(void *rbio, void *data)
>>         kfree(rbio);
>>  }
>>
>> -static inline int resync_alloc_pages(struct resync_pages *rp,
>> -                                    gfp_t gfp_flags)
>> +static inline int resync_alloc_folio(struct resync_folio *rf,
>> +                                    gfp_t gfp_flags, int *order)
>>  {
>> -       int i;
>> +       struct folio *folio;
>>
>> -       for (i = 0; i < RESYNC_PAGES; i++) {
>> -               rp->pages[i] = alloc_page(gfp_flags);
>> -               if (!rp->pages[i])
>> -                       goto out_free;
>> -       }
>> +       do {
>> +               folio = folio_alloc(gfp_flags, *order);
>> +               if (folio)
>> +                       break;
>> +       } while (--(*order) > 0);
>
> It has a problem here. If it can't allocate a big page, the sync
> request unit will be smaller and sync performance may decrease. This
> can happen when the system lacks sufficient continuous memory. This
> change looks good to me. I just want to throw this problem out for an
> open discussion.
>

Yeah, it can be easily reproduced in qemu. We have a few options:
  1. Alloc smaller folio 
  2. Return -ENOMEM directly
  3. Alloc multiple small folios to assemble a larger one. It is not and
     good idea, as it will make the code much more complex.

IMO, 1 seems like the best choice.

>>
>> +       if (!folio)
>> +               return -ENOMEM;
>> +
>> +       rf->folio = folio;
>>         return 0;
>> -
>> -out_free:
>> -       while (--i >= 0)
>> -               put_page(rp->pages[i]);
>> -       return -ENOMEM;
>> -}
>> -
>> -static inline void resync_free_pages(struct resync_pages *rp)
>> -{
>> -       int i;
>> -
>> -       for (i = 0; i < RESYNC_PAGES; i++)
>> -               put_page(rp->pages[i]);
>> -}
>> -
>> -static inline void resync_get_all_pages(struct resync_pages *rp)
>> -{
>> -       int i;
>> -
>> -       for (i = 0; i < RESYNC_PAGES; i++)
>> -               get_page(rp->pages[i]);
>> -}
>> -
>> -static inline struct page *resync_fetch_page(struct resync_pages *rp,
>> -                                            unsigned idx)
>> -{
>> -       if (WARN_ON_ONCE(idx >= RESYNC_PAGES))
>> -               return NULL;
>> -       return rp->pages[idx];
>>  }
>>
>>  /*
>> - * 'strct resync_pages' stores actual pages used for doing the resync
>> + * 'strct resync_folio' stores actual pages used for doing the resync
>>   *  IO, and it is per-bio, so make .bi_private points to it.
>>   */
>> -static inline struct resync_pages *get_resync_pages(struct bio *bio)
>> +static inline struct resync_folio *get_resync_folio(struct bio *bio)
>>  {
>>         return bio->bi_private;
>>  }
>>
>>  /* generally called after bio_reset() for reseting bvec */
>> -static void md_bio_reset_resync_pages(struct bio *bio, struct resync_pages *rp,
>> +static void md_bio_reset_resync_folio(struct bio *bio, struct resync_folio *rf,
>>                                int size)
>>  {
>> -       int idx = 0;
>> -
>>         /* initialize bvec table again */
>> -       do {
>> -               struct page *page = resync_fetch_page(rp, idx);
>> -               int len = min_t(int, size, PAGE_SIZE);
>> -
>> -               if (WARN_ON(!bio_add_page(bio, page, len, 0))) {
>> -                       bio->bi_status = BLK_STS_RESOURCE;
>> -                       bio_endio(bio);
>> -                       return;
>> -               }
>> -
>> -               size -= len;
>> -       } while (idx++ < RESYNC_PAGES && size > 0);
>> +       if (WARN_ON(!bio_add_folio(bio, rf->folio,
>> +                                  min_t(int, size, RESYNC_BLOCK_SIZE),
>> +                                  0))) {
>> +               bio->bi_status = BLK_STS_RESOURCE;
>> +               bio_endio(bio);
>> +       }
>>  }
>>
>>
>> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
>> index a72abdc37a2d..724fd4f2cc3a 100644
>> --- a/drivers/md/raid1.c
>> +++ b/drivers/md/raid1.c
>> @@ -120,11 +120,11 @@ static void remove_serial(struct md_rdev *rdev, sector_t lo, sector_t hi)
>>
>>  /*
>>   * for resync bio, r1bio pointer can be retrieved from the per-bio
>> - * 'struct resync_pages'.
>> + * 'struct resync_folio'.
>>   */
>>  static inline struct r1bio *get_resync_r1bio(struct bio *bio)
>>  {
>> -       return get_resync_pages(bio)->raid_bio;
>> +       return get_resync_folio(bio)->raid_bio;
>>  }
>>
>>  static void *r1bio_pool_alloc(gfp_t gfp_flags, struct r1conf *conf)
>> @@ -146,70 +146,69 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
>>         struct r1conf *conf = data;
>>         struct r1bio *r1_bio;
>>         struct bio *bio;
>> -       int need_pages;
>> +       int need_folio;
>
> The name need_folio is confusing. Can we keep the same style as the
> old version? How about need_folios?
>

Agree, I will rename it in v2.

>>         int j;
>> -       struct resync_pages *rps;
>> +       struct resync_folio *rfs;
>> +       int order = get_order(RESYNC_BLOCK_SIZE);
>>
>>         r1_bio = r1bio_pool_alloc(gfp_flags, conf);
>>         if (!r1_bio)
>>                 return NULL;
>>
>> -       rps = kmalloc_array(conf->raid_disks * 2, sizeof(struct resync_pages),
>> +       rfs = kmalloc_array(conf->raid_disks * 2, sizeof(struct resync_folio),
>>                             gfp_flags);
>> -       if (!rps)
>> +       if (!rfs)
>>                 goto out_free_r1bio;
>>
>>         /*
>>          * Allocate bios : 1 for reading, n-1 for writing
>>          */
>>         for (j = conf->raid_disks * 2; j-- ; ) {
>> -               bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
>> +               bio = bio_kmalloc(1, gfp_flags);
>>                 if (!bio)
>>                         goto out_free_bio;
>> -               bio_init_inline(bio, NULL, RESYNC_PAGES, 0);
>> +               bio_init_inline(bio, NULL, 1, 0);
>>                 r1_bio->bios[j] = bio;
>>         }
>>         /*
>> -        * Allocate RESYNC_PAGES data pages and attach them to
>> -        * the first bio.
>> +        * Allocate data folio and attach it to the first bio.
>>          * If this is a user-requested check/repair, allocate
>> -        * RESYNC_PAGES for each bio.
>> +        * folio for each bio.
>>          */
>>         if (test_bit(MD_RECOVERY_REQUESTED, &conf->mddev->recovery))
>> -               need_pages = conf->raid_disks * 2;
>> +               need_folio = conf->raid_disks * 2;
>>         else
>> -               need_pages = 1;
>> +               need_folio = 1;
>>         for (j = 0; j < conf->raid_disks * 2; j++) {
>> -               struct resync_pages *rp = &rps[j];
>> +               struct resync_folio *rf = &rfs[j];
>>
>> -               bio = r1_bio->bios[j];
>> -
>> -               if (j < need_pages) {
>> -                       if (resync_alloc_pages(rp, gfp_flags))
>> -                               goto out_free_pages;
>> +               if (j < need_folio) {
>> +                       if (resync_alloc_folio(rf, gfp_flags, &order))
>> +                               goto out_free_folio;
>>                 } else {
>> -                       memcpy(rp, &rps[0], sizeof(*rp));
>> -                       resync_get_all_pages(rp);
>> +                       memcpy(rf, &rfs[0], sizeof(*rf));
>> +                       folio_get(rf->folio);
>>                 }
>>
>> -               rp->raid_bio = r1_bio;
>> -               bio->bi_private = rp;
>> +               rf->raid_bio = r1_bio;
>> +               r1_bio->bios[j]->bi_private = rf;
>>         }
>>
>> +       r1_bio->sectors = 1 << (order + PAGE_SECTORS_SHIFT);
>>         r1_bio->master_bio = NULL;
>>
>>         return r1_bio;
>>
>> -out_free_pages:
>> +out_free_folio:
>>         while (--j >= 0)
>> -               resync_free_pages(&rps[j]);
>> +               folio_put(rfs[j].folio);
>>
>>  out_free_bio:
>>         while (++j < conf->raid_disks * 2) {
>>                 bio_uninit(r1_bio->bios[j]);
>>                 kfree(r1_bio->bios[j]);
>>         }
>> -       kfree(rps);
>> +       kfree(rfs);
>>
>>  out_free_r1bio:
>>         rbio_pool_free(r1_bio, data);
>> @@ -221,17 +220,17 @@ static void r1buf_pool_free(void *__r1_bio, void *data)
>>         struct r1conf *conf = data;
>>         int i;
>>         struct r1bio *r1bio = __r1_bio;
>> -       struct resync_pages *rp = NULL;
>> +       struct resync_folio *rf = NULL;
>>
>>         for (i = conf->raid_disks * 2; i--; ) {
>> -               rp = get_resync_pages(r1bio->bios[i]);
>> -               resync_free_pages(rp);
>> +               rf = get_resync_folio(r1bio->bios[i]);
>> +               folio_put(rf->folio);
>>                 bio_uninit(r1bio->bios[i]);
>>                 kfree(r1bio->bios[i]);
>>         }
>>
>> -       /* resync pages array stored in the 1st bio's .bi_private */
>> -       kfree(rp);
>> +       /* resync folio stored in the 1st bio's .bi_private */
>> +       kfree(rf);
>>
>>         rbio_pool_free(r1bio, data);
>>  }
>> @@ -2095,10 +2094,10 @@ static void end_sync_write(struct bio *bio)
>>         put_sync_write_buf(r1_bio);
>>  }
>>
>> -static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
>> -                          int sectors, struct page *page, blk_opf_t rw)
>> +static int r1_sync_folio_io(struct md_rdev *rdev, sector_t sector, int sectors,
>> +                           int off, struct folio *folio, blk_opf_t rw)
>>  {
>> -       if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
>> +       if (sync_folio_io(rdev, sector, sectors << 9, off, folio, rw, false))
>>                 /* success */
>>                 return 1;
>>         if (rw == REQ_OP_WRITE) {
>> @@ -2129,10 +2128,10 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
>>         struct mddev *mddev = r1_bio->mddev;
>>         struct r1conf *conf = mddev->private;
>>         struct bio *bio = r1_bio->bios[r1_bio->read_disk];
>> -       struct page **pages = get_resync_pages(bio)->pages;
>> +       struct folio *folio = get_resync_folio(bio)->folio;
>>         sector_t sect = r1_bio->sector;
>>         int sectors = r1_bio->sectors;
>> -       int idx = 0;
>> +       int off = 0;
>>         struct md_rdev *rdev;
>>
>>         rdev = conf->mirrors[r1_bio->read_disk].rdev;
>> @@ -2162,9 +2161,8 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
>>                                  * active, and resync is currently active
>>                                  */
>>                                 rdev = conf->mirrors[d].rdev;
>> -                               if (sync_page_io(rdev, sect, s<<9,
>> -                                                pages[idx],
>> -                                                REQ_OP_READ, false)) {
>> +                               if (sync_folio_io(rdev, sect, s<<9, off, folio,
>> +                                                 REQ_OP_READ, false)) {
>>                                         success = 1;
>>                                         break;
>>                                 }
>> @@ -2197,7 +2195,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
>>                         /* Try next page */
>>                         sectors -= s;
>>                         sect += s;
>> -                       idx++;
>> +                       off += s << 9;
>>                         continue;
>>                 }
>>
>> @@ -2210,8 +2208,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
>>                         if (r1_bio->bios[d]->bi_end_io != end_sync_read)
>>                                 continue;
>>                         rdev = conf->mirrors[d].rdev;
>> -                       if (r1_sync_page_io(rdev, sect, s,
>> -                                           pages[idx],
>> +                       if (r1_sync_folio_io(rdev, sect, s, off, folio,
>>                                             REQ_OP_WRITE) == 0) {
>>                                 r1_bio->bios[d]->bi_end_io = NULL;
>>                                 rdev_dec_pending(rdev, mddev);
>> @@ -2225,14 +2222,13 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
>>                         if (r1_bio->bios[d]->bi_end_io != end_sync_read)
>>                                 continue;
>>                         rdev = conf->mirrors[d].rdev;
>> -                       if (r1_sync_page_io(rdev, sect, s,
>> -                                           pages[idx],
>> +                       if (r1_sync_folio_io(rdev, sect, s, off, folio,
>>                                             REQ_OP_READ) != 0)
>>                                 atomic_add(s, &rdev->corrected_errors);
>>                 }
>>                 sectors -= s;
>>                 sect += s;
>> -               idx ++;
>> +               off += s << 9;
>>         }
>>         set_bit(R1BIO_Uptodate, &r1_bio->state);
>>         bio->bi_status = 0;
>> @@ -2252,14 +2248,12 @@ static void process_checks(struct r1bio *r1_bio)
>>         struct r1conf *conf = mddev->private;
>>         int primary;
>>         int i;
>> -       int vcnt;
>>
>>         /* Fix variable parts of all bios */
>> -       vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9);
>>         for (i = 0; i < conf->raid_disks * 2; i++) {
>>                 blk_status_t status;
>>                 struct bio *b = r1_bio->bios[i];
>> -               struct resync_pages *rp = get_resync_pages(b);
>> +               struct resync_folio *rf = get_resync_folio(b);
>>                 if (b->bi_end_io != end_sync_read)
>>                         continue;
>>                 /* fixup the bio for reuse, but preserve errno */
>> @@ -2269,11 +2263,11 @@ static void process_checks(struct r1bio *r1_bio)
>>                 b->bi_iter.bi_sector = r1_bio->sector +
>>                         conf->mirrors[i].rdev->data_offset;
>>                 b->bi_end_io = end_sync_read;
>> -               rp->raid_bio = r1_bio;
>> -               b->bi_private = rp;
>> +               rf->raid_bio = r1_bio;
>> +               b->bi_private = rf;
>>
>>                 /* initialize bvec table again */
>> -               md_bio_reset_resync_pages(b, rp, r1_bio->sectors << 9);
>> +               md_bio_reset_resync_folio(b, rf, r1_bio->sectors << 9);
>>         }
>>         for (primary = 0; primary < conf->raid_disks * 2; primary++)
>>                 if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
>> @@ -2284,44 +2278,39 @@ static void process_checks(struct r1bio *r1_bio)
>>                 }
>>         r1_bio->read_disk = primary;
>>         for (i = 0; i < conf->raid_disks * 2; i++) {
>> -               int j = 0;
>>                 struct bio *pbio = r1_bio->bios[primary];
>>                 struct bio *sbio = r1_bio->bios[i];
>>                 blk_status_t status = sbio->bi_status;
>> -               struct page **ppages = get_resync_pages(pbio)->pages;
>> -               struct page **spages = get_resync_pages(sbio)->pages;
>> -               struct bio_vec *bi;
>> -               int page_len[RESYNC_PAGES] = { 0 };
>> -               struct bvec_iter_all iter_all;
>> +               struct folio *pfolio = get_resync_folio(pbio)->folio;
>> +               struct folio *sfolio = get_resync_folio(sbio)->folio;
>>
>>                 if (sbio->bi_end_io != end_sync_read)
>>                         continue;
>>                 /* Now we can 'fixup' the error value */
>>                 sbio->bi_status = 0;
>>
>> -               bio_for_each_segment_all(bi, sbio, iter_all)
>> -                       page_len[j++] = bi->bv_len;
>> -
>> -               if (!status) {
>> -                       for (j = vcnt; j-- ; ) {
>> -                               if (memcmp(page_address(ppages[j]),
>> -                                          page_address(spages[j]),
>> -                                          page_len[j]))
>> -                                       break;
>> -                       }
>> -               } else
>> -                       j = 0;
>> -               if (j >= 0)
>> +               /*
>> +                * Copy data and submit write in two cases:
>> +                * - IO error (non-zero status)
>> +                * - Data inconsistency and not a CHECK operation.
>> +                */
>> +               if (status) {
>>                         atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
>> -               if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
>> -                             && !status)) {
>> -                       /* No need to write to this device. */
>> -                       sbio->bi_end_io = NULL;
>> -                       rdev_dec_pending(conf->mirrors[i].rdev, mddev);
>> +                       bio_copy_data(sbio, pbio);
>>                         continue;
>> +               } else if (memcmp(folio_address(pfolio),
>> +                       folio_address(sfolio),
>> +                       r1_bio->sectors << 9)) {
>> +                       atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
>> +                       if (!test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
>> +                               bio_copy_data(sbio, pbio);
>> +                               continue;
>> +                       }
>>                 }
>>
>> -               bio_copy_data(sbio, pbio);
>> +               /* No need to write to this device. */
>> +               sbio->bi_end_io = NULL;
>> +               rdev_dec_pending(conf->mirrors[i].rdev, mddev);
>>         }
>>  }
>>
>> @@ -2446,9 +2435,8 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
>>                         if (rdev &&
>>                             !test_bit(Faulty, &rdev->flags)) {
>>                                 atomic_inc(&rdev->nr_pending);
>> -                               r1_sync_page_io(rdev, sect, s,
>> -                                               folio_page(conf->tmpfolio, 0),
>> -                                               REQ_OP_WRITE);
>> +                               r1_sync_folio_io(rdev, sect, s, 0,
>> +                                               conf->tmpfolio, REQ_OP_WRITE);
>>                                 rdev_dec_pending(rdev, mddev);
>>                         }
>>                 }
>> @@ -2461,9 +2449,8 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
>>                         if (rdev &&
>>                             !test_bit(Faulty, &rdev->flags)) {
>>                                 atomic_inc(&rdev->nr_pending);
>> -                               if (r1_sync_page_io(rdev, sect, s,
>> -                                               folio_page(conf->tmpfolio, 0),
>> -                                               REQ_OP_READ)) {
>> +                               if (r1_sync_folio_io(rdev, sect, s, 0,
>> +                                               conf->tmpfolio, REQ_OP_READ)) {
>>                                         atomic_add(s, &rdev->corrected_errors);
>>                                         pr_info("md/raid1:%s: read error corrected (%d sectors at %llu on %pg)\n",
>>                                                 mdname(mddev), s,
>> @@ -2738,15 +2725,15 @@ static int init_resync(struct r1conf *conf)
>>  static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
>>  {
>>         struct r1bio *r1bio = mempool_alloc(&conf->r1buf_pool, GFP_NOIO);
>> -       struct resync_pages *rps;
>> +       struct resync_folio *rfs;
>>         struct bio *bio;
>>         int i;
>>
>>         for (i = conf->raid_disks * 2; i--; ) {
>>                 bio = r1bio->bios[i];
>> -               rps = bio->bi_private;
>> +               rfs = bio->bi_private;
>>                 bio_reset(bio, NULL, 0);
>> -               bio->bi_private = rps;
>> +               bio->bi_private = rfs;
>>         }
>>         r1bio->master_bio = NULL;
>>         return r1bio;
>> @@ -2775,10 +2762,9 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
>>         int write_targets = 0, read_targets = 0;
>>         sector_t sync_blocks;
>>         bool still_degraded = false;
>> -       int good_sectors = RESYNC_SECTORS;
>> +       int good_sectors;
>>         int min_bad = 0; /* number of sectors that are bad in all devices */
>>         int idx = sector_to_idx(sector_nr);
>> -       int page_idx = 0;
>>
>>         if (!mempool_initialized(&conf->r1buf_pool))
>>                 if (init_resync(conf))
>> @@ -2858,8 +2844,11 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
>>         r1_bio->sector = sector_nr;
>>         r1_bio->state = 0;
>>         set_bit(R1BIO_IsSync, &r1_bio->state);
>> -       /* make sure good_sectors won't go across barrier unit boundary */
>> -       good_sectors = align_to_barrier_unit_end(sector_nr, good_sectors);
>> +       /*
>> +        * make sure good_sectors won't go across barrier unit boundary.
>> +        * r1_bio->sectors <= RESYNC_SECTORS.
>> +        */
>> +       good_sectors = align_to_barrier_unit_end(sector_nr, r1_bio->sectors);
>>
>>         for (i = 0; i < conf->raid_disks * 2; i++) {
>>                 struct md_rdev *rdev;
>> @@ -2979,44 +2968,28 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
>>                 max_sector = mddev->resync_max; /* Don't do IO beyond here */
>>         if (max_sector > sector_nr + good_sectors)
>>                 max_sector = sector_nr + good_sectors;
>> -       nr_sectors = 0;
>> -       sync_blocks = 0;
>>         do {
>> -               struct page *page;
>> -               int len = PAGE_SIZE;
>> -               if (sector_nr + (len>>9) > max_sector)
>> -                       len = (max_sector - sector_nr) << 9;
>> -               if (len == 0)
>> +               nr_sectors = max_sector - sector_nr;
>> +               if (nr_sectors == 0)
>>                         break;
>> -               if (sync_blocks == 0) {
>> -                       if (!md_bitmap_start_sync(mddev, sector_nr,
>> -                                                 &sync_blocks, still_degraded) &&
>> -                           !conf->fullsync &&
>> -                           !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
>> -                               break;
>> -                       if ((len >> 9) > sync_blocks)
>> -                               len = sync_blocks<<9;
>> -               }
>> +               if (!md_bitmap_start_sync(mddev, sector_nr,
>> +                                         &sync_blocks, still_degraded) &&
>> +                   !conf->fullsync &&
>> +                   !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
>> +                       break;
>> +               if (nr_sectors > sync_blocks)
>> +                       nr_sectors = sync_blocks;
>>
>>                 for (i = 0 ; i < conf->raid_disks * 2; i++) {
>> -                       struct resync_pages *rp;
>> -
>>                         bio = r1_bio->bios[i];
>> -                       rp = get_resync_pages(bio);
>>                         if (bio->bi_end_io) {
>> -                               page = resync_fetch_page(rp, page_idx);
>> +                               struct resync_folio *rf = get_resync_folio(bio);
>>
>> -                               /*
>> -                                * won't fail because the vec table is big
>> -                                * enough to hold all these pages
>> -                                */
>> -                               __bio_add_page(bio, page, len, 0);
>> +                               bio_add_folio_nofail(bio, rf->folio, nr_sectors << 9, 0);
>>                         }
>>                 }
>> -               nr_sectors += len>>9;
>> -               sector_nr += len>>9;
>> -               sync_blocks -= (len>>9);
>> -       } while (++page_idx < RESYNC_PAGES);
>> +               sector_nr += nr_sectors;
>> +       } while (0);
>
> Now it can handle all pages in one go via a folio. It's strange to
> keep while(0) here.
>

I tried cleanning up while(0), it made 'if' and 'break' statements
unreadable. So I kept while(0) here.

>
>>
>>         r1_bio->sectors = nr_sectors;
>
>
> This patch is a little big. Is it better to split this patch here?
>

It can't be splitted. The changes in raid1.c and raid10.c are entirely about
resync_pages -> resync_folio. We have to change declaration and its usage in
one patch.

>>
>> diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
>> index 26f93040cd13..3638e00fe420 100644
>> --- a/drivers/md/raid10.c
>> +++ b/drivers/md/raid10.c
>> @@ -96,11 +96,11 @@ static void end_reshape(struct r10conf *conf);
>>
>>  /*
>>   * for resync bio, r10bio pointer can be retrieved from the per-bio
>> - * 'struct resync_pages'.
>> + * 'struct resync_folio'.
>>   */
>>  static inline struct r10bio *get_resync_r10bio(struct bio *bio)
>>  {
>> -       return get_resync_pages(bio)->raid_bio;
>> +       return get_resync_folio(bio)->raid_bio;
>>  }
>>
>>  static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
>> @@ -133,8 +133,9 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
>>         struct r10bio *r10_bio;
>>         struct bio *bio;
>>         int j;
>> -       int nalloc, nalloc_rp;
>> -       struct resync_pages *rps;
>> +       int nalloc, nalloc_rf;
>> +       struct resync_folio *rfs;
>> +       int order = get_order(RESYNC_BLOCK_SIZE);
>>
>>         r10_bio = r10bio_pool_alloc(gfp_flags, conf);
>>         if (!r10_bio)
>> @@ -148,66 +149,64 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
>>
>>         /* allocate once for all bios */
>>         if (!conf->have_replacement)
>> -               nalloc_rp = nalloc;
>> +               nalloc_rf = nalloc;
>>         else
>> -               nalloc_rp = nalloc * 2;
>> -       rps = kmalloc_array(nalloc_rp, sizeof(struct resync_pages), gfp_flags);
>> -       if (!rps)
>> +               nalloc_rf = nalloc * 2;
>> +       rfs = kmalloc_array(nalloc_rf, sizeof(struct resync_folio), gfp_flags);
>> +       if (!rfs)
>>                 goto out_free_r10bio;
>>
>>         /*
>>          * Allocate bios.
>>          */
>>         for (j = nalloc ; j-- ; ) {
>> -               bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
>> +               bio = bio_kmalloc(1, gfp_flags);
>>                 if (!bio)
>>                         goto out_free_bio;
>> -               bio_init_inline(bio, NULL, RESYNC_PAGES, 0);
>> +               bio_init_inline(bio, NULL, 1, 0);
>>                 r10_bio->devs[j].bio = bio;
>>                 if (!conf->have_replacement)
>>                         continue;
>> -               bio = bio_kmalloc(RESYNC_PAGES, gfp_flags);
>> +               bio = bio_kmalloc(1, gfp_flags);
>>                 if (!bio)
>>                         goto out_free_bio;
>> -               bio_init_inline(bio, NULL, RESYNC_PAGES, 0);
>> +               bio_init_inline(bio, NULL, 1, 0);
>>                 r10_bio->devs[j].repl_bio = bio;
>>         }
>>         /*
>> -        * Allocate RESYNC_PAGES data pages and attach them
>> -        * where needed.
>> +        * Allocate data folio and attach it where needed.
>>          */
>>         for (j = 0; j < nalloc; j++) {
>>                 struct bio *rbio = r10_bio->devs[j].repl_bio;
>> -               struct resync_pages *rp, *rp_repl;
>> +               struct resync_folio *rf, *rf_repl;
>>
>> -               rp = &rps[j];
>> +               rf = &rfs[j];
>>                 if (rbio)
>> -                       rp_repl = &rps[nalloc + j];
>> -
>> -               bio = r10_bio->devs[j].bio;
>> +                       rf_repl = &rfs[nalloc + j];
>>
>>                 if (!j || test_bit(MD_RECOVERY_SYNC,
>>                                    &conf->mddev->recovery)) {
>> -                       if (resync_alloc_pages(rp, gfp_flags))
>> -                               goto out_free_pages;
>> +                       if (resync_alloc_folio(rf, gfp_flags, &order))
>> +                               goto out_free_folio;
>>                 } else {
>> -                       memcpy(rp, &rps[0], sizeof(*rp));
>> -                       resync_get_all_pages(rp);
>> +                       memcpy(rf, &rfs[0], sizeof(*rf));
>> +                       folio_get(rf->folio);
>>                 }
>>
>> -               rp->raid_bio = r10_bio;
>> -               bio->bi_private = rp;
>> +               rf->raid_bio = r10_bio;
>> +               r10_bio->devs[j].bio->bi_private = rf;
>>                 if (rbio) {
>> -                       memcpy(rp_repl, rp, sizeof(*rp));
>> -                       rbio->bi_private = rp_repl;
>> +                       memcpy(rf_repl, rf, sizeof(*rf));
>> +                       rbio->bi_private = rf_repl;
>>                 }
>>         }
>>
>> +       r10_bio->sectors = 1 << (order + PAGE_SECTORS_SHIFT);
>>         return r10_bio;
>>
>> -out_free_pages:
>> +out_free_folio:
>>         while (--j >= 0)
>> -               resync_free_pages(&rps[j]);
>> +               folio_put(rfs[j].folio);
>>
>>         j = 0;
>>  out_free_bio:
>> @@ -219,7 +218,7 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
>>                         bio_uninit(r10_bio->devs[j].repl_bio);
>>                 kfree(r10_bio->devs[j].repl_bio);
>>         }
>> -       kfree(rps);
>> +       kfree(rfs);
>>  out_free_r10bio:
>>         rbio_pool_free(r10_bio, conf);
>>         return NULL;
>> @@ -230,14 +229,14 @@ static void r10buf_pool_free(void *__r10_bio, void *data)
>>         struct r10conf *conf = data;
>>         struct r10bio *r10bio = __r10_bio;
>>         int j;
>> -       struct resync_pages *rp = NULL;
>> +       struct resync_folio *rf = NULL;
>>
>>         for (j = conf->copies; j--; ) {
>>                 struct bio *bio = r10bio->devs[j].bio;
>>
>>                 if (bio) {
>> -                       rp = get_resync_pages(bio);
>> -                       resync_free_pages(rp);
>> +                       rf = get_resync_folio(bio);
>> +                       folio_put(rf->folio);
>>                         bio_uninit(bio);
>>                         kfree(bio);
>>                 }
>> @@ -250,7 +249,7 @@ static void r10buf_pool_free(void *__r10_bio, void *data)
>>         }
>>
>>         /* resync pages array stored in the 1st bio's .bi_private */
>> -       kfree(rp);
>> +       kfree(rf);
>>
>>         rbio_pool_free(r10bio, conf);
>>  }
>> @@ -2342,8 +2341,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
>>         struct r10conf *conf = mddev->private;
>>         int i, first;
>>         struct bio *tbio, *fbio;
>> -       int vcnt;
>> -       struct page **tpages, **fpages;
>> +       struct folio *tfolio, *ffolio;
>>
>>         atomic_set(&r10_bio->remaining, 1);
>>
>> @@ -2359,14 +2357,13 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
>>         fbio = r10_bio->devs[i].bio;
>>         fbio->bi_iter.bi_size = r10_bio->sectors << 9;
>>         fbio->bi_iter.bi_idx = 0;
>> -       fpages = get_resync_pages(fbio)->pages;
>> +       ffolio = get_resync_folio(fbio)->folio;
>>
>> -       vcnt = (r10_bio->sectors + (PAGE_SIZE >> 9) - 1) >> (PAGE_SHIFT - 9);
>>         /* now find blocks with errors */
>>         for (i=0 ; i < conf->copies ; i++) {
>> -               int  j, d;
>> +               int  d;
>>                 struct md_rdev *rdev;
>> -               struct resync_pages *rp;
>> +               struct resync_folio *rf;
>>
>>                 tbio = r10_bio->devs[i].bio;
>>
>> @@ -2375,31 +2372,23 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
>>                 if (i == first)
>>                         continue;
>>
>> -               tpages = get_resync_pages(tbio)->pages;
>> +               tfolio = get_resync_folio(tbio)->folio;
>>                 d = r10_bio->devs[i].devnum;
>>                 rdev = conf->mirrors[d].rdev;
>>                 if (!r10_bio->devs[i].bio->bi_status) {
>>                         /* We know that the bi_io_vec layout is the same for
>>                          * both 'first' and 'i', so we just compare them.
>> -                        * All vec entries are PAGE_SIZE;
>>                          */
>> -                       int sectors = r10_bio->sectors;
>> -                       for (j = 0; j < vcnt; j++) {
>> -                               int len = PAGE_SIZE;
>> -                               if (sectors < (len / 512))
>> -                                       len = sectors * 512;
>> -                               if (memcmp(page_address(fpages[j]),
>> -                                          page_address(tpages[j]),
>> -                                          len))
>> -                                       break;
>> -                               sectors -= len/512;
>> +                       if (memcmp(folio_address(ffolio),
>> +                                  folio_address(tfolio),
>> +                                  r10_bio->sectors << 9)) {
>> +                               atomic64_add(r10_bio->sectors,
>> +                                            &mddev->resync_mismatches);
>> +                               if (test_bit(MD_RECOVERY_CHECK,
>> +                                            &mddev->recovery))
>> +                                       /* Don't fix anything. */
>> +                                       continue;
>>                         }
>> -                       if (j == vcnt)
>> -                               continue;
>> -                       atomic64_add(r10_bio->sectors, &mddev->resync_mismatches);
>> -                       if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
>> -                               /* Don't fix anything. */
>> -                               continue;
>>                 } else if (test_bit(FailFast, &rdev->flags)) {
>>                         /* Just give up on this device */
>>                         md_error(rdev->mddev, rdev);
>> @@ -2410,13 +2399,13 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
>>                  * First we need to fixup bv_offset, bv_len and
>>                  * bi_vecs, as the read request might have corrupted these
>>                  */
>> -               rp = get_resync_pages(tbio);
>> +               rf = get_resync_folio(tbio);
>>                 bio_reset(tbio, conf->mirrors[d].rdev->bdev, REQ_OP_WRITE);
>>
>> -               md_bio_reset_resync_pages(tbio, rp, fbio->bi_iter.bi_size);
>> +               md_bio_reset_resync_folio(tbio, rf, fbio->bi_iter.bi_size);
>>
>> -               rp->raid_bio = r10_bio;
>> -               tbio->bi_private = rp;
>> +               rf->raid_bio = r10_bio;
>> +               tbio->bi_private = rf;
>>                 tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
>>                 tbio->bi_end_io = end_sync_write;
>>
>> @@ -2476,10 +2465,9 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
>>         struct bio *bio = r10_bio->devs[0].bio;
>>         sector_t sect = 0;
>>         int sectors = r10_bio->sectors;
>> -       int idx = 0;
>>         int dr = r10_bio->devs[0].devnum;
>>         int dw = r10_bio->devs[1].devnum;
>> -       struct page **pages = get_resync_pages(bio)->pages;
>> +       struct folio *folio = get_resync_folio(bio)->folio;
>>
>>         while (sectors) {
>>                 int s = sectors;
>> @@ -2492,19 +2480,21 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
>>
>>                 rdev = conf->mirrors[dr].rdev;
>>                 addr = r10_bio->devs[0].addr + sect;
>> -               ok = sync_page_io(rdev,
>> -                                 addr,
>> -                                 s << 9,
>> -                                 pages[idx],
>> -                                 REQ_OP_READ, false);
>> +               ok = sync_folio_io(rdev,
>> +                                  addr,
>> +                                  s << 9,
>> +                                  sect << 9,
>> +                                  folio,
>> +                                  REQ_OP_READ, false);
>>                 if (ok) {
>>                         rdev = conf->mirrors[dw].rdev;
>>                         addr = r10_bio->devs[1].addr + sect;
>> -                       ok = sync_page_io(rdev,
>> -                                         addr,
>> -                                         s << 9,
>> -                                         pages[idx],
>> -                                         REQ_OP_WRITE, false);
>> +                       ok = sync_folio_io(rdev,
>> +                                          addr,
>> +                                          s << 9,
>> +                                          sect << 9,
>> +                                          folio,
>> +                                          REQ_OP_WRITE, false);
>>                         if (!ok) {
>>                                 set_bit(WriteErrorSeen, &rdev->flags);
>>                                 if (!test_and_set_bit(WantReplacement,
>> @@ -2539,7 +2529,6 @@ static void fix_recovery_read_error(struct r10bio *r10_bio)
>>
>>                 sectors -= s;
>>                 sect += s;
>> -               idx++;
>>         }
>>  }
>>
>> @@ -3050,7 +3039,7 @@ static int init_resync(struct r10conf *conf)
>>  static struct r10bio *raid10_alloc_init_r10buf(struct r10conf *conf)
>>  {
>>         struct r10bio *r10bio = mempool_alloc(&conf->r10buf_pool, GFP_NOIO);
>> -       struct rsync_pages *rp;
>> +       struct resync_folio *rf;
>>         struct bio *bio;
>>         int nalloc;
>>         int i;
>> @@ -3063,14 +3052,14 @@ static struct r10bio *raid10_alloc_init_r10buf(struct r10conf *conf)
>>
>>         for (i = 0; i < nalloc; i++) {
>>                 bio = r10bio->devs[i].bio;
>> -               rp = bio->bi_private;
>> +               rf = bio->bi_private;
>>                 bio_reset(bio, NULL, 0);
>> -               bio->bi_private = rp;
>> +               bio->bi_private = rf;
>>                 bio = r10bio->devs[i].repl_bio;
>>                 if (bio) {
>> -                       rp = bio->bi_private;
>> +                       rf = bio->bi_private;
>>                         bio_reset(bio, NULL, 0);
>> -                       bio->bi_private = rp;
>> +                       bio->bi_private = rf;
>>                 }
>>         }
>>         return r10bio;
>> @@ -3156,7 +3145,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
>>         int max_sync = RESYNC_SECTORS;
>>         sector_t sync_blocks;
>>         sector_t chunk_mask = conf->geo.chunk_mask;
>> -       int page_idx = 0;
>>
>>         /*
>>          * Allow skipping a full rebuild for incremental assembly
>> @@ -3376,6 +3364,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
>>                                                 continue;
>>                                         }
>>                                 }
>> +
>> +                               /*
>> +                                * RESYNC_BLOCK_SIZE folio might alloc failed in
>> +                                * resync_alloc_folio(). Fall back to smaller sync
>> +                                * size if needed.
>> +                                */
>> +                               if (max_sync > r10_bio->sectors)
>> +                                       max_sync = r10_bio->sectors;
>> +
>>                                 any_working = 1;
>>                                 bio = r10_bio->devs[0].bio;
>>                                 bio->bi_next = biolist;
>> @@ -3527,7 +3524,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
>>                 }
>>                 if (sync_blocks < max_sync)
>>                         max_sync = sync_blocks;
>> +
>>                 r10_bio = raid10_alloc_init_r10buf(conf);
>> +               /*
>> +                * RESYNC_BLOCK_SIZE folio might alloc failed in resync_alloc_folio().
>> +                * Fall back to smaller sync size if needed.
>> +                */
>> +               if (max_sync > r10_bio->sectors)
>> +                       max_sync = r10_bio->sectors;
>> +
>>                 r10_bio->state = 0;
>>
>>                 r10_bio->mddev = mddev;
>> @@ -3620,29 +3625,25 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
>>                 }
>>         }
>>
>> -       nr_sectors = 0;
>>         if (sector_nr + max_sync < max_sector)
>>                 max_sector = sector_nr + max_sync;
>>         do {
>> -               struct page *page;
>> -               int len = PAGE_SIZE;
>> -               if (sector_nr + (len>>9) > max_sector)
>> -                       len = (max_sector - sector_nr) << 9;
>> -               if (len == 0)
>> +               nr_sectors = max_sector - sector_nr;
>> +
>> +               if (nr_sectors == 0)
>>                         break;
>>                 for (bio= biolist ; bio ; bio=bio->bi_next) {
>> -                       struct resync_pages *rp = get_resync_pages(bio);
>> -                       page = resync_fetch_page(rp, page_idx);
>> -                       if (WARN_ON(!bio_add_page(bio, page, len, 0))) {
>> +                       struct resync_folio *rf = get_resync_folio(bio);
>> +
>> +                       if (WARN_ON(!bio_add_folio(bio, rf->folio, nr_sectors << 9, 0))) {
>>                                 bio->bi_status = BLK_STS_RESOURCE;
>>                                 bio_endio(bio);
>>                                 *skipped = 1;
>> -                               return max_sync;
>> +                               return nr_sectors << 9;
>>                         }
>>                 }
>> -               nr_sectors += len>>9;
>> -               sector_nr += len>>9;
>> -       } while (++page_idx < RESYNC_PAGES);
>> +               sector_nr += nr_sectors;
>> +       } while (0);
>>         r10_bio->sectors = nr_sectors;
>>
>>         if (mddev_is_clustered(mddev) &&
>> @@ -4560,7 +4561,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
>>                                 int *skipped)
>>  {
>>         /* We simply copy at most one chunk (smallest of old and new)
>> -        * at a time, possibly less if that exceeds RESYNC_PAGES,
>> +        * at a time, possibly less if that exceeds RESYNC_BLOCK_SIZE,
>>          * or we hit a bad block or something.
>>          * This might mean we pause for normal IO in the middle of
>>          * a chunk, but that is not a problem as mddev->reshape_position
>> @@ -4600,14 +4601,13 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
>>         struct r10bio *r10_bio;
>>         sector_t next, safe, last;
>>         int max_sectors;
>> -       int nr_sectors;
>>         int s;
>>         struct md_rdev *rdev;
>>         int need_flush = 0;
>>         struct bio *blist;
>>         struct bio *bio, *read_bio;
>>         int sectors_done = 0;
>> -       struct page **pages;
>> +       struct folio *folio;
>>
>>         if (sector_nr == 0) {
>>                 /* If restarting in the middle, skip the initial sectors */
>> @@ -4709,7 +4709,12 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
>>         r10_bio->mddev = mddev;
>>         r10_bio->sector = sector_nr;
>>         set_bit(R10BIO_IsReshape, &r10_bio->state);
>> -       r10_bio->sectors = last - sector_nr + 1;
>> +       /*
>> +        * RESYNC_BLOCK_SIZE folio might alloc failed in
>> +        * resync_alloc_folio(). Fall back to smaller sync
>> +        * size if needed.
>> +        */
>> +       r10_bio->sectors = min_t(int, r10_bio->sectors, last - sector_nr + 1);
>>         rdev = read_balance(conf, r10_bio, &max_sectors);
>>         BUG_ON(!test_bit(R10BIO_Previous, &r10_bio->state));
>>
>> @@ -4723,7 +4728,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
>>                 return sectors_done;
>>         }
>>
>> -       read_bio = bio_alloc_bioset(rdev->bdev, RESYNC_PAGES, REQ_OP_READ,
>> +       read_bio = bio_alloc_bioset(rdev->bdev, 1, REQ_OP_READ,
>>                                     GFP_KERNEL, &mddev->bio_set);
>>         read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr
>>                                + rdev->data_offset);
>> @@ -4787,32 +4792,23 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
>>                 blist = b;
>>         }
>>
>> -       /* Now add as many pages as possible to all of these bios. */
>> +       /* Now add folio to all of these bios. */
>>
>> -       nr_sectors = 0;
>> -       pages = get_resync_pages(r10_bio->devs[0].bio)->pages;
>> -       for (s = 0 ; s < max_sectors; s += PAGE_SIZE >> 9) {
>> -               struct page *page = pages[s / (PAGE_SIZE >> 9)];
>> -               int len = (max_sectors - s) << 9;
>> -               if (len > PAGE_SIZE)
>> -                       len = PAGE_SIZE;
>> -               for (bio = blist; bio ; bio = bio->bi_next) {
>> -                       if (WARN_ON(!bio_add_page(bio, page, len, 0))) {
>> -                               bio->bi_status = BLK_STS_RESOURCE;
>> -                               bio_endio(bio);
>> -                               return sectors_done;
>> -                       }
>> +       folio = get_resync_folio(r10_bio->devs[0].bio)->folio;
>> +       for (bio = blist; bio ; bio = bio->bi_next) {
>> +               if (WARN_ON(!bio_add_folio(bio, folio, max_sectors, 0))) {
>> +                       bio->bi_status = BLK_STS_RESOURCE;
>> +                       bio_endio(bio);
>> +                       return sectors_done;
>
> In fact, the original codes don't clean up before returning.
> bio_add_folio_nofail is used in raid1 and can we use
> bio_add_folio_nofail here as well?
>

Agree, I will clean it up before this patch.

>>                 }
>> -               sector_nr += len >> 9;
>> -               nr_sectors += len >> 9;
>>         }
>> -       r10_bio->sectors = nr_sectors;
>> +       r10_bio->sectors = max_sectors >> 9;
>>
>>         /* Now submit the read */
>>         atomic_inc(&r10_bio->remaining);
>>         read_bio->bi_next = NULL;
>>         submit_bio_noacct(read_bio);
>> -       sectors_done += nr_sectors;
>> +       sectors_done += max_sectors;
>>         if (sector_nr <= last)
>>                 goto read_more;
>>
>> @@ -4914,8 +4910,8 @@ static int handle_reshape_read_error(struct mddev *mddev,
>>         struct r10conf *conf = mddev->private;
>>         struct r10bio *r10b;
>>         int slot = 0;
>> -       int idx = 0;
>> -       struct page **pages;
>> +       int sect = 0;
>> +       struct folio *folio;
>>
>>         r10b = kmalloc(struct_size(r10b, devs, conf->copies), GFP_NOIO);
>>         if (!r10b) {
>> @@ -4923,8 +4919,8 @@ static int handle_reshape_read_error(struct mddev *mddev,
>>                 return -ENOMEM;
>>         }
>>
>> -       /* reshape IOs share pages from .devs[0].bio */
>> -       pages = get_resync_pages(r10_bio->devs[0].bio)->pages;
>> +       /* reshape IOs share folio from .devs[0].bio */
>> +       folio = get_resync_folio(r10_bio->devs[0].bio)->folio;
>>
>>         r10b->sector = r10_bio->sector;
>>         __raid10_find_phys(&conf->prev, r10b);
>> @@ -4940,19 +4936,19 @@ static int handle_reshape_read_error(struct mddev *mddev,
>>                 while (!success) {
>>                         int d = r10b->devs[slot].devnum;
>>                         struct md_rdev *rdev = conf->mirrors[d].rdev;
>> -                       sector_t addr;
>>                         if (rdev == NULL ||
>>                             test_bit(Faulty, &rdev->flags) ||
>>                             !test_bit(In_sync, &rdev->flags))
>>                                 goto failed;
>>
>> -                       addr = r10b->devs[slot].addr + idx * PAGE_SIZE;
>>                         atomic_inc(&rdev->nr_pending);
>> -                       success = sync_page_io(rdev,
>> -                                              addr,
>> -                                              s << 9,
>> -                                              pages[idx],
>> -                                              REQ_OP_READ, false);
>> +                       success = sync_folio_io(rdev,
>> +                                               r10b->devs[slot].addr +
>> +                                               sect,
>> +                                               s << 9,
>> +                                               sect << 9,
>> +                                               folio,
>> +                                               REQ_OP_READ, false);
>>                         rdev_dec_pending(rdev, mddev);
>>                         if (success)
>>                                 break;
>> @@ -4971,7 +4967,7 @@ static int handle_reshape_read_error(struct mddev *mddev,
>>                         return -EIO;
>>                 }
>>                 sectors -= s;
>> -               idx++;
>> +               sect += s;
>>         }
>>         kfree(r10b);
>>         return 0;
>> --
>> 2.39.2
>>
>>
>
> Regards
> Xiao

--
Thansk
Nan

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2026-05-07  7:13 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
     [not found] <CALTww29duRpWZkYQjRJM45DAG=gLiPzbtn9x+CHAFcF3XJXRTg@mail.gmail.com>
2026-05-07  7:13 ` [PATCH v3 6/8] md/raid1,raid10: use folio for sync path IO 李楠 Magic Li

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox