This set fix reported problem:
https://lore.kernel.org/all/CAJpMwyjmHQLvm6zg1cmQErttNNQPDAAXPKM3xgTjMhbfts9... https://lore.kernel.org/all/ADF7D720-5764-4AF3-B68E-1845988737AA@flyingcircu...
See details in patch 5.
Yu Kuai (5): md/md-bitmap: factor behind write counters out from bitmap_{start/end}write() md/md-bitmap: remove the last parameter for bimtap_ops->endwrite() md: add a new callback pers->bitmap_sector() md/raid5: implement pers->bitmap_sector() md/md-bitmap: move bitmap_{start, end}write to md upper layer
drivers/md/md-bitmap.c | 74 ++++++++++++++++---------- drivers/md/md-bitmap.h | 7 ++- drivers/md/md.c | 29 ++++++++++ drivers/md/md.h | 5 ++ drivers/md/raid1.c | 34 +++--------- drivers/md/raid1.h | 1 - drivers/md/raid10.c | 26 +-------- drivers/md/raid10.h | 1 - drivers/md/raid5-cache.c | 4 -- drivers/md/raid5.c | 111 ++++++++++++++++++++------------------- drivers/md/raid5.h | 4 -- 11 files changed, 149 insertions(+), 147 deletions(-)
From: Yu Kuai yukuai3@huawei.com
commit 08c50142a128dcb2d7060aa3b4c5db8837f7a46a upstream.
behind_write is only used in raid1, prepare to refactor bitmap_{start/end}write(), there are no functional changes.
Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Xiao Ni xni@redhat.com Link: https://lore.kernel.org/r/20250109015145.158868-2-yukuai1@huaweicloud.com Signed-off-by: Song Liu song@kernel.org Signed-off-by: Yu Kuai yukuai1@huaweicloud.com --- drivers/md/md-bitmap.c | 57 +++++++++++++++++++++++++--------------- drivers/md/md-bitmap.h | 7 +++-- drivers/md/raid1.c | 12 +++++---- drivers/md/raid10.c | 6 ++--- drivers/md/raid5-cache.c | 3 +-- drivers/md/raid5.c | 11 ++++---- 6 files changed, 56 insertions(+), 40 deletions(-)
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index c3a42dd66ce5..84fb4cc67d5e 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -1671,24 +1671,13 @@ __acquires(bitmap->lock) }
static int bitmap_startwrite(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool behind) + unsigned long sectors) { struct bitmap *bitmap = mddev->bitmap;
if (!bitmap) return 0;
- if (behind) { - int bw; - atomic_inc(&bitmap->behind_writes); - bw = atomic_read(&bitmap->behind_writes); - if (bw > bitmap->behind_writes_used) - bitmap->behind_writes_used = bw; - - pr_debug("inc write-behind count %d/%lu\n", - bw, bitmap->mddev->bitmap_info.max_write_behind); - } - while (sectors) { sector_t blocks; bitmap_counter_t *bmc; @@ -1737,21 +1726,13 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset, }
static void bitmap_endwrite(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool success, bool behind) + unsigned long sectors, bool success) { struct bitmap *bitmap = mddev->bitmap;
if (!bitmap) return;
- if (behind) { - if (atomic_dec_and_test(&bitmap->behind_writes)) - wake_up(&bitmap->behind_wait); - pr_debug("dec write-behind count %d/%lu\n", - atomic_read(&bitmap->behind_writes), - bitmap->mddev->bitmap_info.max_write_behind); - } - while (sectors) { sector_t blocks; unsigned long flags; @@ -2062,6 +2043,37 @@ static void md_bitmap_free(void *data) kfree(bitmap); }
+static void bitmap_start_behind_write(struct mddev *mddev) +{ + struct bitmap *bitmap = mddev->bitmap; + int bw; + + if (!bitmap) + return; + + atomic_inc(&bitmap->behind_writes); + bw = atomic_read(&bitmap->behind_writes); + if (bw > bitmap->behind_writes_used) + bitmap->behind_writes_used = bw; + + pr_debug("inc write-behind count %d/%lu\n", + bw, bitmap->mddev->bitmap_info.max_write_behind); +} + +static void bitmap_end_behind_write(struct mddev *mddev) +{ + struct bitmap *bitmap = mddev->bitmap; + + if (!bitmap) + return; + + if (atomic_dec_and_test(&bitmap->behind_writes)) + wake_up(&bitmap->behind_wait); + pr_debug("dec write-behind count %d/%lu\n", + atomic_read(&bitmap->behind_writes), + bitmap->mddev->bitmap_info.max_write_behind); +} + static void bitmap_wait_behind_writes(struct mddev *mddev) { struct bitmap *bitmap = mddev->bitmap; @@ -2981,6 +2993,9 @@ static struct bitmap_operations bitmap_ops = { .dirty_bits = bitmap_dirty_bits, .unplug = bitmap_unplug, .daemon_work = bitmap_daemon_work, + + .start_behind_write = bitmap_start_behind_write, + .end_behind_write = bitmap_end_behind_write, .wait_behind_writes = bitmap_wait_behind_writes,
.startwrite = bitmap_startwrite, diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 662e6fc141a7..e87a1f493d3c 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -84,12 +84,15 @@ struct bitmap_operations { unsigned long e); void (*unplug)(struct mddev *mddev, bool sync); void (*daemon_work)(struct mddev *mddev); + + void (*start_behind_write)(struct mddev *mddev); + void (*end_behind_write)(struct mddev *mddev); void (*wait_behind_writes)(struct mddev *mddev);
int (*startwrite)(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool behind); + unsigned long sectors); void (*endwrite)(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool success, bool behind); + unsigned long sectors, bool success); bool (*start_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks, bool degraded); void (*end_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 519c56f0ee3d..15ba7a001f30 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -420,10 +420,11 @@ static void close_write(struct r1bio *r1_bio) r1_bio->behind_master_bio = NULL; }
+ if (test_bit(R1BIO_BehindIO, &r1_bio->state)) + mddev->bitmap_ops->end_behind_write(mddev); /* clear the bitmap if all writes complete successfully */ mddev->bitmap_ops->endwrite(mddev, r1_bio->sector, r1_bio->sectors, - !test_bit(R1BIO_Degraded, &r1_bio->state), - test_bit(R1BIO_BehindIO, &r1_bio->state)); + !test_bit(R1BIO_Degraded, &r1_bio->state)); md_write_end(mddev); }
@@ -1645,9 +1646,10 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, stats.behind_writes < max_write_behind) alloc_behind_master_bio(r1_bio, bio);
- mddev->bitmap_ops->startwrite( - mddev, r1_bio->sector, r1_bio->sectors, - test_bit(R1BIO_BehindIO, &r1_bio->state)); + if (test_bit(R1BIO_BehindIO, &r1_bio->state)) + mddev->bitmap_ops->start_behind_write(mddev); + mddev->bitmap_ops->startwrite(mddev, r1_bio->sector, + r1_bio->sectors); first_clone = 0; }
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 7d7a8a2524dc..c3a93b2a26a6 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -430,8 +430,7 @@ static void close_write(struct r10bio *r10_bio)
/* clear the bitmap if all writes complete successfully */ mddev->bitmap_ops->endwrite(mddev, r10_bio->sector, r10_bio->sectors, - !test_bit(R10BIO_Degraded, &r10_bio->state), - false); + !test_bit(R10BIO_Degraded, &r10_bio->state)); md_write_end(mddev); }
@@ -1519,8 +1518,7 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, md_account_bio(mddev, &bio); r10_bio->master_bio = bio; atomic_set(&r10_bio->remaining, 1); - mddev->bitmap_ops->startwrite(mddev, r10_bio->sector, r10_bio->sectors, - false); + mddev->bitmap_ops->startwrite(mddev, r10_bio->sector, r10_bio->sectors);
for (i = 0; i < conf->copies; i++) { if (r10_bio->devs[i].bio) diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index b4f7b79fd187..4c7ecdd5c1f3 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -315,8 +315,7 @@ void r5c_handle_cached_data_endio(struct r5conf *conf, r5c_return_dev_pending_writes(conf, &sh->dev[i]); conf->mddev->bitmap_ops->endwrite(conf->mddev, sh->sector, RAID5_STRIPE_SECTORS(conf), - !test_bit(STRIPE_DEGRADED, &sh->state), - false); + !test_bit(STRIPE_DEGRADED, &sh->state)); } } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index f09e7677ee9f..93cc7e252dd4 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3564,7 +3564,7 @@ static void __add_stripe_bio(struct stripe_head *sh, struct bio *bi, set_bit(STRIPE_BITMAP_PENDING, &sh->state); spin_unlock_irq(&sh->stripe_lock); conf->mddev->bitmap_ops->startwrite(conf->mddev, sh->sector, - RAID5_STRIPE_SECTORS(conf), false); + RAID5_STRIPE_SECTORS(conf)); spin_lock_irq(&sh->stripe_lock); clear_bit(STRIPE_BITMAP_PENDING, &sh->state); if (!sh->batch_head) { @@ -3665,7 +3665,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, if (bitmap_end) conf->mddev->bitmap_ops->endwrite(conf->mddev, sh->sector, RAID5_STRIPE_SECTORS(conf), - false, false); + false); bitmap_end = 0; /* and fail all 'written' */ bi = sh->dev[i].written; @@ -3712,7 +3712,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, if (bitmap_end) conf->mddev->bitmap_ops->endwrite(conf->mddev, sh->sector, RAID5_STRIPE_SECTORS(conf), - false, false); + false); /* If we were in the middle of a write the parity block might * still be locked - so just clear all R5_LOCKED flags */ @@ -4063,8 +4063,7 @@ static void handle_stripe_clean_event(struct r5conf *conf, } conf->mddev->bitmap_ops->endwrite(conf->mddev, sh->sector, RAID5_STRIPE_SECTORS(conf), - !test_bit(STRIPE_DEGRADED, &sh->state), - false); + !test_bit(STRIPE_DEGRADED, &sh->state)); if (head_sh->batch_head) { sh = list_first_entry(&sh->batch_list, struct stripe_head, @@ -5787,7 +5786,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) for (d = 0; d < conf->raid_disks - conf->max_degraded; d++) mddev->bitmap_ops->startwrite(mddev, sh->sector, - RAID5_STRIPE_SECTORS(conf), false); + RAID5_STRIPE_SECTORS(conf)); sh->bm_seq = conf->seq_flush + 1; set_bit(STRIPE_BIT_DELAY, &sh->state); }
[ Sasha's backport helper bot ]
Hi,
The upstream commit SHA1 provided is correct: 08c50142a128dcb2d7060aa3b4c5db8837f7a46a
WARNING: Author mismatch between patch and upstream commit: Backport author: Yu Kuaiyukuai1@huaweicloud.com Commit author: Yu Kuaiyukuai3@huawei.com
Status in newer kernel trees: 6.12.y | Not found
Note: The patch differs from the upstream commit: --- 1: 08c50142a128d ! 1: c5f3371866713 md/md-bitmap: factor behind write counters out from bitmap_{start/end}write() @@ Metadata ## Commit message ## md/md-bitmap: factor behind write counters out from bitmap_{start/end}write()
+ commit 08c50142a128dcb2d7060aa3b4c5db8837f7a46a upstream. + behind_write is only used in raid1, prepare to refactor bitmap_{start/end}write(), there are no functional changes.
@@ Commit message Reviewed-by: Xiao Ni xni@redhat.com Link: https://lore.kernel.org/r/20250109015145.158868-2-yukuai1@huaweicloud.com Signed-off-by: Song Liu song@kernel.org + Signed-off-by: Yu Kuai yukuai1@huaweicloud.com
## drivers/md/md-bitmap.c ## @@ drivers/md/md-bitmap.c: __acquires(bitmap->lock) ---
Results of testing on various branches:
| Branch | Patch Apply | Build Test | |---------------------------|-------------|------------| | stable/linux-6.12.y | Success | Success | | stable/linux-6.6.y | Failed | N/A | | stable/linux-6.1.y | Failed | N/A | | stable/linux-5.15.y | Failed | N/A | | stable/linux-5.10.y | Failed | N/A | | stable/linux-5.4.y | Failed | N/A |
From: Yu Kuai yukuai3@huawei.com
commit 4f0e7d0e03b7b80af84759a9e7cfb0f81ac4adae upstream.
For the case that IO failed for one rdev, the bit will be mark as NEEDED in following cases:
1) If badblocks is set and rdev is not faulty; 2) If rdev is faulty;
Case 1) is useless because synchronize data to badblocks make no sense. Case 2) can be replaced with mddev->degraded.
Also remove R1BIO_Degraded, R10BIO_Degraded and STRIPE_DEGRADED since case 2) no longer use them.
Signed-off-by: Yu Kuai yukuai3@huawei.com Link: https://lore.kernel.org/r/20250109015145.158868-3-yukuai1@huaweicloud.com Signed-off-by: Song Liu song@kernel.org Signed-off-by: Yu Kuai yukuai1@huaweicloud.com --- drivers/md/md-bitmap.c | 19 ++++++++++--------- drivers/md/md-bitmap.h | 2 +- drivers/md/raid1.c | 26 +++----------------------- drivers/md/raid1.h | 1 - drivers/md/raid10.c | 23 +++-------------------- drivers/md/raid10.h | 1 - drivers/md/raid5-cache.c | 3 +-- drivers/md/raid5.c | 15 +++------------ drivers/md/raid5.h | 1 - 9 files changed, 21 insertions(+), 70 deletions(-)
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 84fb4cc67d5e..b40a84b01085 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -1726,7 +1726,7 @@ static int bitmap_startwrite(struct mddev *mddev, sector_t offset, }
static void bitmap_endwrite(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool success) + unsigned long sectors) { struct bitmap *bitmap = mddev->bitmap;
@@ -1745,15 +1745,16 @@ static void bitmap_endwrite(struct mddev *mddev, sector_t offset, return; }
- if (success && !bitmap->mddev->degraded && - bitmap->events_cleared < bitmap->mddev->events) { - bitmap->events_cleared = bitmap->mddev->events; - bitmap->need_sync = 1; - sysfs_notify_dirent_safe(bitmap->sysfs_can_clear); - } - - if (!success && !NEEDED(*bmc)) + if (!bitmap->mddev->degraded) { + if (bitmap->events_cleared < bitmap->mddev->events) { + bitmap->events_cleared = bitmap->mddev->events; + bitmap->need_sync = 1; + sysfs_notify_dirent_safe( + bitmap->sysfs_can_clear); + } + } else if (!NEEDED(*bmc)) { *bmc |= NEEDED_MASK; + }
if (COUNTER(*bmc) == COUNTER_MAX) wake_up(&bitmap->overflow_wait); diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index e87a1f493d3c..31c93019c76b 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -92,7 +92,7 @@ struct bitmap_operations { int (*startwrite)(struct mddev *mddev, sector_t offset, unsigned long sectors); void (*endwrite)(struct mddev *mddev, sector_t offset, - unsigned long sectors, bool success); + unsigned long sectors); bool (*start_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks, bool degraded); void (*end_sync)(struct mddev *mddev, sector_t offset, sector_t *blocks); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 15ba7a001f30..4d09d85321b6 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -423,8 +423,7 @@ static void close_write(struct r1bio *r1_bio) if (test_bit(R1BIO_BehindIO, &r1_bio->state)) mddev->bitmap_ops->end_behind_write(mddev); /* clear the bitmap if all writes complete successfully */ - mddev->bitmap_ops->endwrite(mddev, r1_bio->sector, r1_bio->sectors, - !test_bit(R1BIO_Degraded, &r1_bio->state)); + mddev->bitmap_ops->endwrite(mddev, r1_bio->sector, r1_bio->sectors); md_write_end(mddev); }
@@ -481,8 +480,6 @@ static void raid1_end_write_request(struct bio *bio) if (!test_bit(Faulty, &rdev->flags)) set_bit(R1BIO_WriteError, &r1_bio->state); else { - /* Fail the request */ - set_bit(R1BIO_Degraded, &r1_bio->state); /* Finished with this branch */ r1_bio->bios[mirror] = NULL; to_put = bio; @@ -1536,11 +1533,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, write_behind = true;
r1_bio->bios[i] = NULL; - if (!rdev || test_bit(Faulty, &rdev->flags)) { - if (i < conf->raid_disks) - set_bit(R1BIO_Degraded, &r1_bio->state); + if (!rdev || test_bit(Faulty, &rdev->flags)) continue; - }
atomic_inc(&rdev->nr_pending); if (test_bit(WriteErrorSeen, &rdev->flags)) { @@ -1559,16 +1553,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, */ max_sectors = bad_sectors; rdev_dec_pending(rdev, mddev); - /* We don't set R1BIO_Degraded as that - * only applies if the disk is - * missing, so it might be re-added, - * and we want to know to recover this - * chunk. - * In this case the device is here, - * and the fact that this chunk is not - * in-sync is recorded in the bad - * block log - */ continue; } if (is_bad) { @@ -2616,12 +2600,10 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) * errors. */ fail = true; - if (!narrow_write_error(r1_bio, m)) { + if (!narrow_write_error(r1_bio, m)) md_error(conf->mddev, conf->mirrors[m].rdev); /* an I/O failed, we can't clear the bitmap */ - set_bit(R1BIO_Degraded, &r1_bio->state); - } rdev_dec_pending(conf->mirrors[m].rdev, conf->mddev); } @@ -2712,8 +2694,6 @@ static void raid1d(struct md_thread *thread) list_del(&r1_bio->retry_list); idx = sector_to_idx(r1_bio->sector); atomic_dec(&conf->nr_queued[idx]); - if (mddev->degraded) - set_bit(R1BIO_Degraded, &r1_bio->state); if (test_bit(R1BIO_WriteError, &r1_bio->state)) close_write(r1_bio); raid_end_bio_io(r1_bio); diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index 5300cbaa58a4..33f318fcc268 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -188,7 +188,6 @@ struct r1bio { enum r1bio_state { R1BIO_Uptodate, R1BIO_IsSync, - R1BIO_Degraded, R1BIO_BehindIO, /* Set ReadError on bios that experience a readerror so that * raid1d knows what to do with them. diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index c3a93b2a26a6..340a4710c222 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -429,8 +429,7 @@ static void close_write(struct r10bio *r10_bio) struct mddev *mddev = r10_bio->mddev;
/* clear the bitmap if all writes complete successfully */ - mddev->bitmap_ops->endwrite(mddev, r10_bio->sector, r10_bio->sectors, - !test_bit(R10BIO_Degraded, &r10_bio->state)); + mddev->bitmap_ops->endwrite(mddev, r10_bio->sector, r10_bio->sectors); md_write_end(mddev); }
@@ -500,7 +499,6 @@ static void raid10_end_write_request(struct bio *bio) set_bit(R10BIO_WriteError, &r10_bio->state); else { /* Fail the request */ - set_bit(R10BIO_Degraded, &r10_bio->state); r10_bio->devs[slot].bio = NULL; to_put = bio; dec_rdev = 1; @@ -1437,10 +1435,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, r10_bio->devs[i].bio = NULL; r10_bio->devs[i].repl_bio = NULL;
- if (!rdev && !rrdev) { - set_bit(R10BIO_Degraded, &r10_bio->state); + if (!rdev && !rrdev) continue; - } if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) { sector_t first_bad; sector_t dev_sector = r10_bio->devs[i].addr; @@ -1457,14 +1453,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, * to other devices yet */ max_sectors = bad_sectors; - /* We don't set R10BIO_Degraded as that - * only applies if the disk is missing, - * so it might be re-added, and we want to - * know to recover this chunk. - * In this case the device is here, and the - * fact that this chunk is not in-sync is - * recorded in the bad block log. - */ continue; } if (is_bad) { @@ -2964,11 +2952,8 @@ static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) rdev_dec_pending(rdev, conf->mddev); } else if (bio != NULL && bio->bi_status) { fail = true; - if (!narrow_write_error(r10_bio, m)) { + if (!narrow_write_error(r10_bio, m)) md_error(conf->mddev, rdev); - set_bit(R10BIO_Degraded, - &r10_bio->state); - } rdev_dec_pending(rdev, conf->mddev); } bio = r10_bio->devs[m].repl_bio; @@ -3027,8 +3012,6 @@ static void raid10d(struct md_thread *thread) r10_bio = list_first_entry(&tmp, struct r10bio, retry_list); list_del(&r10_bio->retry_list); - if (mddev->degraded) - set_bit(R10BIO_Degraded, &r10_bio->state);
if (test_bit(R10BIO_WriteError, &r10_bio->state)) diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 2e75e88d0802..3f16ad6904a9 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -161,7 +161,6 @@ enum r10bio_state { R10BIO_IsSync, R10BIO_IsRecover, R10BIO_IsReshape, - R10BIO_Degraded, /* Set ReadError on bios that experience a read error * so that raid10d knows what to do with them. */ diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 4c7ecdd5c1f3..ba4f9577c737 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -314,8 +314,7 @@ void r5c_handle_cached_data_endio(struct r5conf *conf, set_bit(R5_UPTODATE, &sh->dev[i].flags); r5c_return_dev_pending_writes(conf, &sh->dev[i]); conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - !test_bit(STRIPE_DEGRADED, &sh->state)); + sh->sector, RAID5_STRIPE_SECTORS(conf)); } } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 93cc7e252dd4..a5a619400d8f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1345,8 +1345,6 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) submit_bio_noacct(rbi); } if (!rdev && !rrdev) { - if (op_is_write(op)) - set_bit(STRIPE_DEGRADED, &sh->state); pr_debug("skip op %d on disc %d for sector %llu\n", bi->bi_opf, i, (unsigned long long)sh->sector); clear_bit(R5_LOCKED, &sh->dev[i].flags); @@ -2884,7 +2882,6 @@ static void raid5_end_write_request(struct bio *bi) set_bit(R5_MadeGoodRepl, &sh->dev[i].flags); } else { if (bi->bi_status) { - set_bit(STRIPE_DEGRADED, &sh->state); set_bit(WriteErrorSeen, &rdev->flags); set_bit(R5_WriteError, &sh->dev[i].flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) @@ -3664,8 +3661,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, } if (bitmap_end) conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - false); + sh->sector, RAID5_STRIPE_SECTORS(conf)); bitmap_end = 0; /* and fail all 'written' */ bi = sh->dev[i].written; @@ -3711,8 +3707,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, } if (bitmap_end) conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - false); + sh->sector, RAID5_STRIPE_SECTORS(conf)); /* If we were in the middle of a write the parity block might * still be locked - so just clear all R5_LOCKED flags */ @@ -4062,8 +4057,7 @@ static void handle_stripe_clean_event(struct r5conf *conf, wbi = wbi2; } conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf), - !test_bit(STRIPE_DEGRADED, &sh->state)); + sh->sector, RAID5_STRIPE_SECTORS(conf)); if (head_sh->batch_head) { sh = list_first_entry(&sh->batch_list, struct stripe_head, @@ -4340,7 +4334,6 @@ static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh, s->locked++; set_bit(R5_Wantwrite, &dev->flags);
- clear_bit(STRIPE_DEGRADED, &sh->state); set_bit(STRIPE_INSYNC, &sh->state); break; case check_state_run: @@ -4497,7 +4490,6 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, clear_bit(R5_Wantwrite, &dev->flags); s->locked--; } - clear_bit(STRIPE_DEGRADED, &sh->state);
set_bit(STRIPE_INSYNC, &sh->state); break; @@ -4899,7 +4891,6 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,
set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS | (1 << STRIPE_PREREAD_ACTIVE) | - (1 << STRIPE_DEGRADED) | (1 << STRIPE_ON_UNPLUG_LIST)), head_sh->state & (1 << STRIPE_INSYNC));
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index d174e586698f..69000fb90bd5 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -358,7 +358,6 @@ enum { STRIPE_REPLACED, STRIPE_PREREAD_ACTIVE, STRIPE_DELAYED, - STRIPE_DEGRADED, STRIPE_BIT_DELAY, STRIPE_EXPANDING, STRIPE_EXPAND_SOURCE,
From: Yu Kuai yukuai3@huawei.com
commit 0c984a283a3ea3f10bebecd6c57c1d41b2e4f518 upstream.
This callback will be used in raid5 to convert io ranges from array to bitmap.
Signed-off-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Xiao Ni xni@redhat.com Link: https://lore.kernel.org/r/20250109015145.158868-4-yukuai1@huaweicloud.com Signed-off-by: Song Liu song@kernel.org Signed-off-by: Yu Kuai yukuai1@huaweicloud.com --- drivers/md/md.h | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/drivers/md/md.h b/drivers/md/md.h index 4ba93af36126..de6dadb9a40b 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -746,6 +746,9 @@ struct md_personality void *(*takeover) (struct mddev *mddev); /* Changes the consistency policy of an active array. */ int (*change_consistency_policy)(struct mddev *mddev, const char *buf); + /* convert io ranges from array to bitmap */ + void (*bitmap_sector)(struct mddev *mddev, sector_t *offset, + unsigned long *sectors); };
struct md_sysfs_entry {
From: Yu Kuai yukuai3@huawei.com
commit 9c89f604476cf15c31fbbdb043cff7fbf1dbe0cb upstream.
Bitmap is used for the whole array for raid1/raid10, hence IO for the array can be used directly for bitmap. However, bitmap is used for underlying disks for raid5, hence IO for the array can't be used directly for bitmap.
Implement pers->bitmap_sector() for raid5 to convert IO ranges from the array to the underlying disks.
Signed-off-by: Yu Kuai yukuai3@huawei.com Link: https://lore.kernel.org/r/20250109015145.158868-5-yukuai1@huaweicloud.com Signed-off-by: Song Liu song@kernel.org Signed-off-by: Yu Kuai yukuai1@huaweicloud.com --- drivers/md/raid5.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index a5a619400d8f..a08f49b47b7e 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5918,6 +5918,54 @@ static enum reshape_loc get_reshape_loc(struct mddev *mddev, return LOC_BEHIND_RESHAPE; }
+static void raid5_bitmap_sector(struct mddev *mddev, sector_t *offset, + unsigned long *sectors) +{ + struct r5conf *conf = mddev->private; + sector_t start = *offset; + sector_t end = start + *sectors; + sector_t prev_start = start; + sector_t prev_end = end; + int sectors_per_chunk; + enum reshape_loc loc; + int dd_idx; + + sectors_per_chunk = conf->chunk_sectors * + (conf->raid_disks - conf->max_degraded); + start = round_down(start, sectors_per_chunk); + end = round_up(end, sectors_per_chunk); + + start = raid5_compute_sector(conf, start, 0, &dd_idx, NULL); + end = raid5_compute_sector(conf, end, 0, &dd_idx, NULL); + + /* + * For LOC_INSIDE_RESHAPE, this IO will wait for reshape to make + * progress, hence it's the same as LOC_BEHIND_RESHAPE. + */ + loc = get_reshape_loc(mddev, conf, prev_start); + if (likely(loc != LOC_AHEAD_OF_RESHAPE)) { + *offset = start; + *sectors = end - start; + return; + } + + sectors_per_chunk = conf->prev_chunk_sectors * + (conf->previous_raid_disks - conf->max_degraded); + prev_start = round_down(prev_start, sectors_per_chunk); + prev_end = round_down(prev_end, sectors_per_chunk); + + prev_start = raid5_compute_sector(conf, prev_start, 1, &dd_idx, NULL); + prev_end = raid5_compute_sector(conf, prev_end, 1, &dd_idx, NULL); + + /* + * for LOC_AHEAD_OF_RESHAPE, reshape can make progress before this IO + * is handled in make_stripe_request(), we can't know this here hence + * we set bits for both. + */ + *offset = min(start, prev_start); + *sectors = max(end, prev_end) - *offset; +} + static enum stripe_result make_stripe_request(struct mddev *mddev, struct r5conf *conf, struct stripe_request_ctx *ctx, sector_t logical_sector, struct bio *bi) @@ -8966,6 +9014,7 @@ static struct md_personality raid6_personality = .takeover = raid6_takeover, .change_consistency_policy = raid5_change_consistency_policy, .prepare_suspend = raid5_prepare_suspend, + .bitmap_sector = raid5_bitmap_sector, }; static struct md_personality raid5_personality = { @@ -8991,6 +9040,7 @@ static struct md_personality raid5_personality = .takeover = raid5_takeover, .change_consistency_policy = raid5_change_consistency_policy, .prepare_suspend = raid5_prepare_suspend, + .bitmap_sector = raid5_bitmap_sector, };
static struct md_personality raid4_personality = @@ -9017,6 +9067,7 @@ static struct md_personality raid4_personality = .takeover = raid4_takeover, .change_consistency_policy = raid5_change_consistency_policy, .prepare_suspend = raid5_prepare_suspend, + .bitmap_sector = raid5_bitmap_sector, };
static int __init raid5_init(void)
From: Yu Kuai yukuai3@huawei.com
commit cd5fc653381811f1e0ba65f5d169918cab61476f upstream.
There are two BUG reports that raid5 will hang at bitmap_startwrite([1],[2]), root cause is that bitmap start write and end write is unbalanced, it's not quite clear where, and while reviewing raid5 code, it's found that bitmap operations can be optimized. For example, for a 4 disks raid5, with chunksize=8k, if user issue a IO (0 + 48k) to the array:
┌────────────────────────────────────────────────────────────┐ │chunk 0 │ │ ┌────────────┬─────────────┬─────────────┬────────────┼ │ sh0 │A0: 0 + 4k │A1: 8k + 4k │A2: 16k + 4k │A3: P │ │ ┼────────────┼─────────────┼─────────────┼────────────┼ │ sh1 │B0: 4k + 4k │B1: 12k + 4k │B2: 20k + 4k │B3: P │ ┼──────┴────────────┴─────────────┴─────────────┴────────────┼ │chunk 1 │ │ ┌────────────┬─────────────┬─────────────┬────────────┤ │ sh2 │C0: 24k + 4k│C1: 32k + 4k │C2: P │C3: 40k + 4k│ │ ┼────────────┼─────────────┼─────────────┼────────────┼ │ sh3 │D0: 28k + 4k│D1: 36k + 4k │D2: P │D3: 44k + 4k│ └──────┴────────────┴─────────────┴─────────────┴────────────┘
Before this patch, 4 stripe head will be used, and each sh will attach bio for 3 disks, and each attached bio will trigger bitmap_startwrite() once, which means total 12 times. - 3 times (0 + 4k), for (A0, A1 and A2) - 3 times (4 + 4k), for (B0, B1 and B2) - 3 times (8 + 4k), for (C0, C1 and C3) - 3 times (12 + 4k), for (D0, D1 and D3)
After this patch, md upper layer will calculate that IO range (0 + 48k) is corresponding to the bitmap (0 + 16k), and call bitmap_startwrite() just once.
Noted that this patch will align bitmap ranges to the chunks, for example, if user issue a IO (0 + 4k) to array:
- Before this patch, 1 time (0 + 4k), for A0; - After this patch, 1 time (0 + 8k) for chunk 0;
Usually, one bitmap bit will represent more than one disk chunk, and this doesn't have any difference. And even if user really created a array that one chunk contain multiple bits, the overhead is that more data will be recovered after power failure.
Also remove STRIPE_BITMAP_PENDING since it's not used anymore.
[1] https://lore.kernel.org/all/CAJpMwyjmHQLvm6zg1cmQErttNNQPDAAXPKM3xgTjMhbfts9... [2] https://lore.kernel.org/all/ADF7D720-5764-4AF3-B68E-1845988737AA@flyingcircu...
Signed-off-by: Yu Kuai yukuai3@huawei.com Link: https://lore.kernel.org/r/20250109015145.158868-6-yukuai1@huaweicloud.com Signed-off-by: Song Liu song@kernel.org Signed-off-by: Yu Kuai yukuai1@huaweicloud.com --- drivers/md/md.c | 29 +++++++++++++++++++++++ drivers/md/md.h | 2 ++ drivers/md/raid1.c | 4 ---- drivers/md/raid10.c | 3 --- drivers/md/raid5-cache.c | 2 -- drivers/md/raid5.c | 50 +++++----------------------------------- drivers/md/raid5.h | 3 --- 7 files changed, 37 insertions(+), 56 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c index aebe12b0ee27..c60ae2c70102 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8745,12 +8745,32 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, } EXPORT_SYMBOL_GPL(md_submit_discard_bio);
+static void md_bitmap_start(struct mddev *mddev, + struct md_io_clone *md_io_clone) +{ + if (mddev->pers->bitmap_sector) + mddev->pers->bitmap_sector(mddev, &md_io_clone->offset, + &md_io_clone->sectors); + + mddev->bitmap_ops->startwrite(mddev, md_io_clone->offset, + md_io_clone->sectors); +} + +static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone) +{ + mddev->bitmap_ops->endwrite(mddev, md_io_clone->offset, + md_io_clone->sectors); +} + static void md_end_clone_io(struct bio *bio) { struct md_io_clone *md_io_clone = bio->bi_private; struct bio *orig_bio = md_io_clone->orig_bio; struct mddev *mddev = md_io_clone->mddev;
+ if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap) + md_bitmap_end(mddev, md_io_clone); + if (bio->bi_status && !orig_bio->bi_status) orig_bio->bi_status = bio->bi_status;
@@ -8775,6 +8795,12 @@ static void md_clone_bio(struct mddev *mddev, struct bio **bio) if (blk_queue_io_stat(bdev->bd_disk->queue)) md_io_clone->start_time = bio_start_io_acct(*bio);
+ if (bio_data_dir(*bio) == WRITE && mddev->bitmap) { + md_io_clone->offset = (*bio)->bi_iter.bi_sector; + md_io_clone->sectors = bio_sectors(*bio); + md_bitmap_start(mddev, md_io_clone); + } + clone->bi_end_io = md_end_clone_io; clone->bi_private = md_io_clone; *bio = clone; @@ -8793,6 +8819,9 @@ void md_free_cloned_bio(struct bio *bio) struct bio *orig_bio = md_io_clone->orig_bio; struct mddev *mddev = md_io_clone->mddev;
+ if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap) + md_bitmap_end(mddev, md_io_clone); + if (bio->bi_status && !orig_bio->bi_status) orig_bio->bi_status = bio->bi_status;
diff --git a/drivers/md/md.h b/drivers/md/md.h index de6dadb9a40b..def808064ad8 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -831,6 +831,8 @@ struct md_io_clone { struct mddev *mddev; struct bio *orig_bio; unsigned long start_time; + sector_t offset; + unsigned long sectors; struct bio bio_clone; };
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 4d09d85321b6..a5cd6522fc2d 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -422,8 +422,6 @@ static void close_write(struct r1bio *r1_bio)
if (test_bit(R1BIO_BehindIO, &r1_bio->state)) mddev->bitmap_ops->end_behind_write(mddev); - /* clear the bitmap if all writes complete successfully */ - mddev->bitmap_ops->endwrite(mddev, r1_bio->sector, r1_bio->sectors); md_write_end(mddev); }
@@ -1632,8 +1630,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
if (test_bit(R1BIO_BehindIO, &r1_bio->state)) mddev->bitmap_ops->start_behind_write(mddev); - mddev->bitmap_ops->startwrite(mddev, r1_bio->sector, - r1_bio->sectors); first_clone = 0; }
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 340a4710c222..e1e6cd7fb125 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -428,8 +428,6 @@ static void close_write(struct r10bio *r10_bio) { struct mddev *mddev = r10_bio->mddev;
- /* clear the bitmap if all writes complete successfully */ - mddev->bitmap_ops->endwrite(mddev, r10_bio->sector, r10_bio->sectors); md_write_end(mddev); }
@@ -1506,7 +1504,6 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, md_account_bio(mddev, &bio); r10_bio->master_bio = bio; atomic_set(&r10_bio->remaining, 1); - mddev->bitmap_ops->startwrite(mddev, r10_bio->sector, r10_bio->sectors);
for (i = 0; i < conf->copies; i++) { if (r10_bio->devs[i].bio) diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index ba4f9577c737..011246e16a99 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -313,8 +313,6 @@ void r5c_handle_cached_data_endio(struct r5conf *conf, if (sh->dev[i].written) { set_bit(R5_UPTODATE, &sh->dev[i].flags); r5c_return_dev_pending_writes(conf, &sh->dev[i]); - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf)); } } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index a08f49b47b7e..5c79429acc64 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -906,8 +906,7 @@ static bool stripe_can_batch(struct stripe_head *sh) if (raid5_has_log(conf) || raid5_has_ppl(conf)) return false; return test_bit(STRIPE_BATCH_READY, &sh->state) && - !test_bit(STRIPE_BITMAP_PENDING, &sh->state) && - is_full_stripe_write(sh); + is_full_stripe_write(sh); }
/* we only do back search */ @@ -3545,29 +3544,9 @@ static void __add_stripe_bio(struct stripe_head *sh, struct bio *bi, (*bip)->bi_iter.bi_sector, sh->sector, dd_idx, sh->dev[dd_idx].sector);
- if (conf->mddev->bitmap && firstwrite) { - /* Cannot hold spinlock over bitmap_startwrite, - * but must ensure this isn't added to a batch until - * we have added to the bitmap and set bm_seq. - * So set STRIPE_BITMAP_PENDING to prevent - * batching. - * If multiple __add_stripe_bio() calls race here they - * much all set STRIPE_BITMAP_PENDING. So only the first one - * to complete "bitmap_startwrite" gets to set - * STRIPE_BIT_DELAY. This is important as once a stripe - * is added to a batch, STRIPE_BIT_DELAY cannot be changed - * any more. - */ - set_bit(STRIPE_BITMAP_PENDING, &sh->state); - spin_unlock_irq(&sh->stripe_lock); - conf->mddev->bitmap_ops->startwrite(conf->mddev, sh->sector, - RAID5_STRIPE_SECTORS(conf)); - spin_lock_irq(&sh->stripe_lock); - clear_bit(STRIPE_BITMAP_PENDING, &sh->state); - if (!sh->batch_head) { - sh->bm_seq = conf->seq_flush+1; - set_bit(STRIPE_BIT_DELAY, &sh->state); - } + if (conf->mddev->bitmap && firstwrite && !sh->batch_head) { + sh->bm_seq = conf->seq_flush+1; + set_bit(STRIPE_BIT_DELAY, &sh->state); } }
@@ -3618,7 +3597,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, BUG_ON(sh->batch_head); for (i = disks; i--; ) { struct bio *bi; - int bitmap_end = 0;
if (test_bit(R5_ReadError, &sh->dev[i].flags)) { struct md_rdev *rdev = conf->disks[i].rdev; @@ -3643,8 +3621,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, sh->dev[i].towrite = NULL; sh->overwrite_disks = 0; spin_unlock_irq(&sh->stripe_lock); - if (bi) - bitmap_end = 1;
log_stripe_write_finished(sh);
@@ -3659,10 +3635,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, bio_io_error(bi); bi = nextbi; } - if (bitmap_end) - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf)); - bitmap_end = 0; /* and fail all 'written' */ bi = sh->dev[i].written; sh->dev[i].written = NULL; @@ -3671,7 +3643,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, sh->dev[i].page = sh->dev[i].orig_page; }
- if (bi) bitmap_end = 1; while (bi && bi->bi_iter.bi_sector < sh->dev[i].sector + RAID5_STRIPE_SECTORS(conf)) { struct bio *bi2 = r5_next_bio(conf, bi, sh->dev[i].sector); @@ -3705,9 +3676,6 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, bi = nextbi; } } - if (bitmap_end) - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf)); /* If we were in the middle of a write the parity block might * still be locked - so just clear all R5_LOCKED flags */ @@ -4056,8 +4024,7 @@ static void handle_stripe_clean_event(struct r5conf *conf, bio_endio(wbi); wbi = wbi2; } - conf->mddev->bitmap_ops->endwrite(conf->mddev, - sh->sector, RAID5_STRIPE_SECTORS(conf)); + if (head_sh->batch_head) { sh = list_first_entry(&sh->batch_list, struct stripe_head, @@ -4882,8 +4849,7 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, (1 << STRIPE_COMPUTE_RUN) | (1 << STRIPE_DISCARD) | (1 << STRIPE_BATCH_READY) | - (1 << STRIPE_BATCH_ERR) | - (1 << STRIPE_BITMAP_PENDING)), + (1 << STRIPE_BATCH_ERR)), "stripe state: %lx\n", sh->state); WARN_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) | (1 << STRIPE_REPLACED)), @@ -5774,10 +5740,6 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi) } spin_unlock_irq(&sh->stripe_lock); if (conf->mddev->bitmap) { - for (d = 0; d < conf->raid_disks - conf->max_degraded; - d++) - mddev->bitmap_ops->startwrite(mddev, sh->sector, - RAID5_STRIPE_SECTORS(conf)); sh->bm_seq = conf->seq_flush + 1; set_bit(STRIPE_BIT_DELAY, &sh->state); } diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 69000fb90bd5..eafc6e9ed6ee 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -371,9 +371,6 @@ enum { STRIPE_ON_RELEASE_LIST, STRIPE_BATCH_READY, STRIPE_BATCH_ERR, - STRIPE_BITMAP_PENDING, /* Being added to bitmap, don't add - * to batch yet. - */ STRIPE_LOG_TRAPPED, /* trapped into log (see raid5-cache.c) * this bit is used in two scenarios: *
On Mon, Jan 27, 2025 at 04:49:23PM +0800, Yu Kuai wrote:
This set fix reported problem:
https://lore.kernel.org/all/CAJpMwyjmHQLvm6zg1cmQErttNNQPDAAXPKM3xgTjMhbfts9... https://lore.kernel.org/all/ADF7D720-5764-4AF3-B68E-1845988737AA@flyingcircu...
See details in patch 5.
Why were these all not properly taggeed for stable inclusion to start with?
confused,
greg k-h
On Mon, Jan 27, 2025 at 10:11:30AM +0100, Greg KH wrote:
On Mon, Jan 27, 2025 at 04:49:23PM +0800, Yu Kuai wrote:
This set fix reported problem:
https://lore.kernel.org/all/CAJpMwyjmHQLvm6zg1cmQErttNNQPDAAXPKM3xgTjMhbfts9... https://lore.kernel.org/all/ADF7D720-5764-4AF3-B68E-1845988737AA@flyingcircu...
See details in patch 5.
Why were these all not properly taggeed for stable inclusion to start with?
Also, as these are not in a released kernel just yet, why should we include them in one now before 6.14-rc1 is out?
thanks,
greg k-h
Hi,
在 2025/01/27 20:45, Greg KH 写道:
On Mon, Jan 27, 2025 at 10:11:30AM +0100, Greg KH wrote:
On Mon, Jan 27, 2025 at 04:49:23PM +0800, Yu Kuai wrote:
This set fix reported problem:
https://lore.kernel.org/all/CAJpMwyjmHQLvm6zg1cmQErttNNQPDAAXPKM3xgTjMhbfts9... https://lore.kernel.org/all/ADF7D720-5764-4AF3-B68E-1845988737AA@flyingcircu...
See details in patch 5.
Why were these all not properly taggeed for stable inclusion to start with?
Because the orignal problem in raid5 is not 100% clear, I don't know what's the exact fix tag here, raid5 is quite complicated :(
So this set fix the problem by refactor, removing all related code in raid5, and reimplement the logical in md.c. Please notice this refactor can also improve performance for raid5.
I can't reporduce this problem myself, however, it's tested by other folks that v4.19 is still affected, while I don't think this *refactor* will be possible in that version. I'll suggest people to upgrade their kernel to v6.6+ first if they're really affected...
Also, as these are not in a released kernel just yet, why should we include them in one now before 6.14-rc1 is out?
I just want to send v6.6 version before the Chinese New Year, becaue 6.14-rc1 will be released while I'm on vacation.
Thanks, Kuai
thanks,
greg k-h .
linux-stable-mirror@lists.linaro.org
-
Greg KH -
Sasha Levin -
Yu Kuai