From e57b225c28b270d46c84ec4742607eab4093ae7c Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:26:59 +0800 Subject: [PATCH 01/24] md/md-bitmap: remove the parameter 'init' for bitmap_ops->resize() It's set to 'false' for all callers, hence it's useless and can be removed. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-3-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/dm-raid.c | 2 +- drivers/md/md-bitmap.c | 5 ++--- drivers/md/md-bitmap.h | 3 +-- drivers/md/md-cluster.c | 2 +- drivers/md/raid1.c | 2 +- drivers/md/raid10.c | 8 ++++---- drivers/md/raid5.c | 2 +- 7 files changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 79ea85d18e24..05811316dedd 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -4071,7 +4071,7 @@ static int raid_preresume(struct dm_target *ti) int chunksize = to_bytes(rs->requested_bitmap_chunk_sectors) ?: mddev->bitmap_info.chunksize; r = mddev->bitmap_ops->resize(mddev, mddev->dev_sectors, - chunksize, false); + chunksize); if (r) DMERR("Failed to resize bitmap"); } diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 334b71404930..4b87a09589d5 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2593,15 +2593,14 @@ err: return ret; } -static int bitmap_resize(struct mddev *mddev, sector_t blocks, int chunksize, - bool init) +static int bitmap_resize(struct mddev *mddev, sector_t blocks, int chunksize) { struct bitmap *bitmap = mddev->bitmap; if (!bitmap) return 0; - return __bitmap_resize(bitmap, blocks, chunksize, init); + return __bitmap_resize(bitmap, blocks, chunksize, false); } static ssize_t diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 59e9dd45cfde..28c1f1c1cc83 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -64,8 +64,7 @@ struct md_bitmap_stats { struct bitmap_operations { bool (*enabled)(struct mddev *mddev); int (*create)(struct mddev *mddev); - int (*resize)(struct mddev *mddev, sector_t blocks, int chunksize, - bool init); + int (*resize)(struct mddev *mddev, sector_t blocks, int chunksize); int (*load)(struct mddev *mddev); void (*destroy)(struct mddev *mddev); diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 5497eaee96e7..6a7deb7e545b 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -630,7 +630,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg) if (le64_to_cpu(msg->high) != mddev->pers->size(mddev, 0, 0)) ret = mddev->bitmap_ops->resize(mddev, le64_to_cpu(msg->high), - 0, false); + 0); break; default: ret = -1; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 408c26398321..ce24e3d01d4a 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -3330,7 +3330,7 @@ static int raid1_resize(struct mddev *mddev, sector_t sectors) mddev->array_sectors > newsize) return -EINVAL; - ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false); + ret = mddev->bitmap_ops->resize(mddev, newsize, 0); if (ret) return ret; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b60c30bfb6c7..269187faa011 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4239,7 +4239,7 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors) mddev->array_sectors > size) return -EINVAL; - ret = mddev->bitmap_ops->resize(mddev, size, 0, false); + ret = mddev->bitmap_ops->resize(mddev, size, 0); if (ret) return ret; @@ -4508,7 +4508,7 @@ static int raid10_start_reshape(struct mddev *mddev) newsize = raid10_size(mddev, 0, conf->geo.raid_disks); if (!mddev_is_clustered(mddev)) { - ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false); + ret = mddev->bitmap_ops->resize(mddev, newsize, 0); if (ret) goto abort; else @@ -4530,13 +4530,13 @@ static int raid10_start_reshape(struct mddev *mddev) MD_FEATURE_RESHAPE_ACTIVE)) || (oldsize == newsize)) goto out; - ret = mddev->bitmap_ops->resize(mddev, newsize, 0, false); + ret = mddev->bitmap_ops->resize(mddev, newsize, 0); if (ret) goto abort; ret = mddev->cluster_ops->resize_bitmaps(mddev, newsize, oldsize); if (ret) { - mddev->bitmap_ops->resize(mddev, oldsize, 0, false); + mddev->bitmap_ops->resize(mddev, oldsize, 0); goto abort; } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 023649fe2476..bb95069e31f3 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -8322,7 +8322,7 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors) mddev->array_sectors > newsize) return -EINVAL; - ret = mddev->bitmap_ops->resize(mddev, sectors, 0, false); + ret = mddev->bitmap_ops->resize(mddev, sectors, 0); if (ret) return ret; From 9307dbac0ea3fea977677d6c590b49f35a8203fc Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:00 +0800 Subject: [PATCH 02/24] md/md-bitmap: merge md_bitmap_group into bitmap_operations Now that all bitmap implementations are internal, it doesn't make sense to export md_bitmap_group anymore. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-5-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/md-bitmap.c | 5 ++++- drivers/md/md-bitmap.h | 2 ++ drivers/md/md.c | 6 +++++- drivers/md/md.h | 1 - 4 files changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 4b87a09589d5..30b6b42b9a48 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2989,7 +2989,8 @@ static struct attribute *md_bitmap_attrs[] = { &max_backlog_used.attr, NULL }; -const struct attribute_group md_bitmap_group = { + +static struct attribute_group md_bitmap_group = { .name = "bitmap", .attrs = md_bitmap_attrs, }; @@ -3025,6 +3026,8 @@ static struct bitmap_operations bitmap_ops = { .copy_from_slot = bitmap_copy_from_slot, .set_pages = bitmap_set_pages, .free = md_bitmap_free, + + .group = &md_bitmap_group, }; void mddev_set_bitmap_ops(struct mddev *mddev) diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 28c1f1c1cc83..0ceb9e97d21f 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -100,6 +100,8 @@ struct bitmap_operations { sector_t *hi, bool clear_bits); void (*set_pages)(void *data, unsigned long pages); void (*free)(void *data); + + struct attribute_group *group; }; /* the bitmap API */ diff --git a/drivers/md/md.c b/drivers/md/md.c index a9b31f02a9c7..ee1454948fc5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5801,7 +5801,6 @@ static const struct attribute_group md_redundancy_group = { static const struct attribute_group *md_attr_groups[] = { &md_default_group, - &md_bitmap_group, NULL, }; @@ -6055,6 +6054,11 @@ struct mddev *md_alloc(dev_t dev, char *name) return ERR_PTR(error); } + if (mddev->bitmap_ops && mddev->bitmap_ops->group) + if (sysfs_create_group(&mddev->kobj, mddev->bitmap_ops->group)) + pr_warn("md: cannot register extra bitmap attributes for %s\n", + mdname(mddev)); + kobject_uevent(&mddev->kobj, KOBJ_ADD); mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state"); mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level"); diff --git a/drivers/md/md.h b/drivers/md/md.h index 51af29a03079..06364e15e8d1 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -796,7 +796,6 @@ struct md_sysfs_entry { ssize_t (*show)(struct mddev *, char *); ssize_t (*store)(struct mddev *, const char *, size_t); }; -extern const struct attribute_group md_bitmap_group; static inline struct kernfs_node *sysfs_get_dirent_safe(struct kernfs_node *sd, char *name) { From 9c41ead04ec0d3ee54505039879aee20cf495e0a Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:01 +0800 Subject: [PATCH 03/24] md/md-bitmap: add a new parameter 'flush' to bitmap_ops->enabled The method is only used from raid1/raid10 IO path, to check if write bio should be pluged, the parameter is always set to true for now, following patch will use this helper in other context like updating superblock. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-6-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/md-bitmap.c | 19 +++++++++++++------ drivers/md/md-bitmap.h | 2 +- drivers/md/raid1-10.c | 2 +- 3 files changed, 15 insertions(+), 8 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 30b6b42b9a48..69e4a43c38b4 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -232,20 +232,27 @@ static inline char *bmname(struct bitmap *bitmap) return bitmap->mddev ? mdname(bitmap->mddev) : "mdX"; } -static bool __bitmap_enabled(struct bitmap *bitmap) +static bool __bitmap_enabled(struct bitmap *bitmap, bool flush) { - return bitmap->storage.filemap && - !test_bit(BITMAP_STALE, &bitmap->flags); + if (!flush) + return true; + + /* + * If caller want to flush bitmap pages to underlying disks, check if + * there are cached pages in filemap. + */ + return !test_bit(BITMAP_STALE, &bitmap->flags) && + bitmap->storage.filemap != NULL; } -static bool bitmap_enabled(struct mddev *mddev) +static bool bitmap_enabled(struct mddev *mddev, bool flush) { struct bitmap *bitmap = mddev->bitmap; if (!bitmap) return false; - return __bitmap_enabled(bitmap); + return __bitmap_enabled(bitmap, flush); } /* @@ -1244,7 +1251,7 @@ static void __bitmap_unplug(struct bitmap *bitmap) int dirty, need_write; int writing = 0; - if (!__bitmap_enabled(bitmap)) + if (!__bitmap_enabled(bitmap, true)) return; /* look at each page to see if there are any set bits that need to be diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 0ceb9e97d21f..63d91831655f 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -62,7 +62,7 @@ struct md_bitmap_stats { }; struct bitmap_operations { - bool (*enabled)(struct mddev *mddev); + bool (*enabled)(struct mddev *mddev, bool flush); int (*create)(struct mddev *mddev); int (*resize)(struct mddev *mddev, sector_t blocks, int chunksize); diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index 52881e6032da..f3c3376cdd06 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -140,7 +140,7 @@ static inline bool raid1_add_bio_to_plug(struct mddev *mddev, struct bio *bio, * If bitmap is not enabled, it's safe to submit the io directly, and * this can get optimal performance. */ - if (!mddev->bitmap_ops->enabled(mddev)) { + if (!mddev->bitmap_ops->enabled(mddev, true)) { raid1_submit_write(bio); return true; } From 110332074dc6ad2f07a3cf9cc45b03adbce0e54f Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:02 +0800 Subject: [PATCH 04/24] md/md-bitmap: add md_bitmap_registered/enabled() helper There are no functional changes, prepare to handle the case that mddev->bitmap_ops can be NULL, which is possible after introducing CONFIG_MD_BITMAP. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-7-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/md-bitmap.c | 16 ++++------------ drivers/md/md-bitmap.h | 19 ++++++++++++++++++- drivers/md/raid1-10.c | 2 +- 3 files changed, 23 insertions(+), 14 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 69e4a43c38b4..613e767578aa 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -232,8 +232,10 @@ static inline char *bmname(struct bitmap *bitmap) return bitmap->mddev ? mdname(bitmap->mddev) : "mdX"; } -static bool __bitmap_enabled(struct bitmap *bitmap, bool flush) +static bool bitmap_enabled(void *data, bool flush) { + struct bitmap *bitmap = data; + if (!flush) return true; @@ -245,16 +247,6 @@ static bool __bitmap_enabled(struct bitmap *bitmap, bool flush) bitmap->storage.filemap != NULL; } -static bool bitmap_enabled(struct mddev *mddev, bool flush) -{ - struct bitmap *bitmap = mddev->bitmap; - - if (!bitmap) - return false; - - return __bitmap_enabled(bitmap, flush); -} - /* * check a page and, if necessary, allocate it (or hijack it if the alloc fails) * @@ -1251,7 +1243,7 @@ static void __bitmap_unplug(struct bitmap *bitmap) int dirty, need_write; int writing = 0; - if (!__bitmap_enabled(bitmap, true)) + if (!bitmap_enabled(bitmap, true)) return; /* look at each page to see if there are any set bits that need to be diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 63d91831655f..a36ed32ec0d5 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -62,7 +62,7 @@ struct md_bitmap_stats { }; struct bitmap_operations { - bool (*enabled)(struct mddev *mddev, bool flush); + bool (*enabled)(void *data, bool flush); int (*create)(struct mddev *mddev); int (*resize)(struct mddev *mddev, sector_t blocks, int chunksize); @@ -107,4 +107,21 @@ struct bitmap_operations { /* the bitmap API */ void mddev_set_bitmap_ops(struct mddev *mddev); +static inline bool md_bitmap_registered(struct mddev *mddev) +{ + return mddev->bitmap_ops != NULL; +} + +static inline bool md_bitmap_enabled(struct mddev *mddev, bool flush) +{ + /* bitmap_ops must be registered before creating bitmap. */ + if (!md_bitmap_registered(mddev)) + return false; + + if (!mddev->bitmap) + return false; + + return mddev->bitmap_ops->enabled(mddev->bitmap, flush); +} + #endif diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c index f3c3376cdd06..521625756128 100644 --- a/drivers/md/raid1-10.c +++ b/drivers/md/raid1-10.c @@ -140,7 +140,7 @@ static inline bool raid1_add_bio_to_plug(struct mddev *mddev, struct bio *bio, * If bitmap is not enabled, it's safe to submit the io directly, and * this can get optimal performance. */ - if (!mddev->bitmap_ops->enabled(mddev, true)) { + if (!md_bitmap_enabled(mddev, true)) { raid1_submit_write(bio); return true; } From 5ae58d1500e3fc16df3267fad810955c949afdb2 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:03 +0800 Subject: [PATCH 05/24] md/md-bitmap: handle the case bitmap is not enabled before start_sync() This case can be handled without knowing internal implementation. Prepare to introduce CONFIG_MD_BITMAP. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-8-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/md-bitmap.c | 8 +------- drivers/md/md-bitmap.h | 12 ++++++++++++ drivers/md/raid1.c | 6 +++--- drivers/md/raid10.c | 15 ++++++--------- drivers/md/raid5.c | 7 ++----- 5 files changed, 24 insertions(+), 24 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 613e767578aa..625f74115352 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -1787,15 +1787,9 @@ static bool __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, bool degraded) { bitmap_counter_t *bmc; - bool rv; + bool rv = false; - if (bitmap == NULL) {/* FIXME or bitmap set as 'failed' */ - *blocks = 1024; - return true; /* always resync if no bitmap */ - } spin_lock_irq(&bitmap->counts.lock); - - rv = false; bmc = md_bitmap_get_counter(&bitmap->counts, offset, blocks, 0); if (bmc) { /* locked */ diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index a36ed32ec0d5..7a16de62ee35 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -124,4 +124,16 @@ static inline bool md_bitmap_enabled(struct mddev *mddev, bool flush) return mddev->bitmap_ops->enabled(mddev->bitmap, flush); } +static inline bool md_bitmap_start_sync(struct mddev *mddev, sector_t offset, + sector_t *blocks, bool degraded) +{ + /* always resync if no bitmap */ + if (!md_bitmap_enabled(mddev, false)) { + *blocks = 1024; + return true; + } + + return mddev->bitmap_ops->start_sync(mddev, offset, blocks, degraded); +} + #endif diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ce24e3d01d4a..1485c3ffe577 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2829,7 +2829,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, /* before building a request, check if we can skip these blocks.. * This call the bitmap_start_sync doesn't actually record anything */ - if (!mddev->bitmap_ops->start_sync(mddev, sector_nr, &sync_blocks, true) && + if (!md_bitmap_start_sync(mddev, sector_nr, &sync_blocks, true) && !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { /* We can skip this block, and probably several more */ *skipped = 1; @@ -3004,8 +3004,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, if (len == 0) break; if (sync_blocks == 0) { - if (!mddev->bitmap_ops->start_sync(mddev, sector_nr, - &sync_blocks, still_degraded) && + if (!md_bitmap_start_sync(mddev, sector_nr, + &sync_blocks, still_degraded) && !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) break; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 269187faa011..eeaf7eaf8a07 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3351,9 +3351,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, * we only need to recover the block if it is set in * the bitmap */ - must_sync = mddev->bitmap_ops->start_sync(mddev, sect, - &sync_blocks, - true); + must_sync = md_bitmap_start_sync(mddev, sect, + &sync_blocks, true); if (sync_blocks < max_sync) max_sync = sync_blocks; if (!must_sync && @@ -3396,9 +3395,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, } } - must_sync = mddev->bitmap_ops->start_sync(mddev, sect, - &sync_blocks, still_degraded); - + md_bitmap_start_sync(mddev, sect, &sync_blocks, + still_degraded); any_working = 0; for (j=0; jcopies;j++) { int k; @@ -3574,9 +3572,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high)); - if (!mddev->bitmap_ops->start_sync(mddev, sector_nr, - &sync_blocks, - mddev->degraded) && + if (!md_bitmap_start_sync(mddev, sector_nr, &sync_blocks, + mddev->degraded) && !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { /* We can skip this block */ diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index bb95069e31f3..dbbf9290417a 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6525,8 +6525,7 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n } if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && !conf->fullsync && - !mddev->bitmap_ops->start_sync(mddev, sector_nr, &sync_blocks, - true) && + !md_bitmap_start_sync(mddev, sector_nr, &sync_blocks, true) && sync_blocks >= RAID5_STRIPE_SECTORS(conf)) { /* we can skip this block, and probably more */ do_div(sync_blocks, RAID5_STRIPE_SECTORS(conf)); @@ -6557,9 +6556,7 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n still_degraded = true; } - mddev->bitmap_ops->start_sync(mddev, sector_nr, &sync_blocks, - still_degraded); - + md_bitmap_start_sync(mddev, sector_nr, &sync_blocks, still_degraded); set_bit(STRIPE_SYNC_REQUESTED, &sh->state); set_bit(STRIPE_HANDLE, &sh->state); From bb74b093c33cf20876e23ad8aa0d206b537ccb69 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:04 +0800 Subject: [PATCH 06/24] md/md-bitmap: handle the case bitmap is not enabled before end_sync() This case can be handled without knowing internal implementation. Prepare to introduce CONFIG_MD_BITMAP. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-9-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/md-bitmap.c | 4 ---- drivers/md/md-bitmap.h | 11 +++++++++++ drivers/md/raid1.c | 6 +++--- drivers/md/raid10.c | 8 +++----- drivers/md/raid5.c | 4 ++-- 5 files changed, 19 insertions(+), 14 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 625f74115352..62b0eac28a7d 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -1838,10 +1838,6 @@ static void __bitmap_end_sync(struct bitmap *bitmap, sector_t offset, bitmap_counter_t *bmc; unsigned long flags; - if (bitmap == NULL) { - *blocks = 1024; - return; - } spin_lock_irqsave(&bitmap->counts.lock, flags); bmc = md_bitmap_get_counter(&bitmap->counts, offset, blocks, 0); if (bmc == NULL) diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 7a16de62ee35..61cfc650c69c 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -136,4 +136,15 @@ static inline bool md_bitmap_start_sync(struct mddev *mddev, sector_t offset, return mddev->bitmap_ops->start_sync(mddev, offset, blocks, degraded); } +static inline void md_bitmap_end_sync(struct mddev *mddev, sector_t offset, + sector_t *blocks) +{ + if (!md_bitmap_enabled(mddev, false)) { + *blocks = 1024; + return; + } + + mddev->bitmap_ops->end_sync(mddev, offset, blocks); +} + #endif diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 1485c3ffe577..0864da7d9adc 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2057,7 +2057,7 @@ static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio) /* make sure these bits don't get cleared. */ do { - mddev->bitmap_ops->end_sync(mddev, s, &sync_blocks); + md_bitmap_end_sync(mddev, s, &sync_blocks); s += sync_blocks; sectors_to_go -= sync_blocks; } while (sectors_to_go > 0); @@ -2804,8 +2804,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, * We can find the current addess in mddev->curr_resync */ if (mddev->curr_resync < max_sector) /* aborted */ - mddev->bitmap_ops->end_sync(mddev, mddev->curr_resync, - &sync_blocks); + md_bitmap_end_sync(mddev, mddev->curr_resync, + &sync_blocks); else /* completed sync */ conf->fullsync = 0; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index eeaf7eaf8a07..d047e9dfdb85 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3221,15 +3221,13 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, if (mddev->curr_resync < max_sector) { /* aborted */ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) - mddev->bitmap_ops->end_sync(mddev, - mddev->curr_resync, - &sync_blocks); + md_bitmap_end_sync(mddev, mddev->curr_resync, + &sync_blocks); else for (i = 0; i < conf->geo.raid_disks; i++) { sector_t sect = raid10_find_virt(conf, mddev->curr_resync, i); - mddev->bitmap_ops->end_sync(mddev, sect, - &sync_blocks); + md_bitmap_end_sync(mddev, sect, &sync_blocks); } } else { /* completed sync */ diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index dbbf9290417a..955906bd4778 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6492,8 +6492,8 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n } if (mddev->curr_resync < max_sector) /* aborted */ - mddev->bitmap_ops->end_sync(mddev, mddev->curr_resync, - &sync_blocks); + md_bitmap_end_sync(mddev, mddev->curr_resync, + &sync_blocks); else /* completed sync */ conf->fullsync = 0; mddev->bitmap_ops->close_sync(mddev); From 20cecae877a634ffc49b4cd7b0f6927209badbab Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:05 +0800 Subject: [PATCH 07/24] md/raid1: check bitmap before behind write behind write rely on bitmap, because the number of IO are recorded in bitmap->behind_writes, and callers rely on bitmap_wait_behind_writes() to wait for IO to be done. However, currently callers doesn't check if bitmap is enabeld before calling into behind methods. Hence if behind write start without bitmap, readers will not wait for slow write IO to be done and old data can be read in some corner cases. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-10-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/md-bitmap.c | 6 ------ drivers/md/raid1.c | 45 ++++++++++++++++++++++++++---------------- 2 files changed, 28 insertions(+), 23 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 62b0eac28a7d..29de99e0de3e 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2049,9 +2049,6 @@ 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) @@ -2065,9 +2062,6 @@ 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", diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 0864da7d9adc..5599dcbd2991 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1366,7 +1366,8 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, (unsigned long long)r1_bio->sector, mirror->rdev->bdev); - if (test_bit(WriteMostly, &mirror->rdev->flags)) { + if (test_bit(WriteMostly, &mirror->rdev->flags) && + md_bitmap_enabled(mddev, false)) { /* * Reading from a write-mostly device must take care not to * over-take any writes that are 'behind' @@ -1452,6 +1453,30 @@ retry: return true; } +static void raid1_start_write_behind(struct mddev *mddev, struct r1bio *r1_bio, + struct bio *bio) +{ + unsigned long max_write_behind = mddev->bitmap_info.max_write_behind; + struct md_bitmap_stats stats; + int err; + + /* behind write rely on bitmap, see bitmap_operations */ + if (!md_bitmap_enabled(mddev, false)) + return; + + err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats); + if (err) + return; + + /* Don't do behind IO if reader is waiting, or there are too many. */ + if (!stats.behind_wait && stats.behind_writes < max_write_behind) + alloc_behind_master_bio(r1_bio, bio); + + if (test_bit(R1BIO_BehindIO, &r1_bio->state)) + mddev->bitmap_ops->start_behind_write(mddev); + +} + static void raid1_write_request(struct mddev *mddev, struct bio *bio, int max_write_sectors) { @@ -1612,22 +1637,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, continue; if (first_clone) { - unsigned long max_write_behind = - mddev->bitmap_info.max_write_behind; - struct md_bitmap_stats stats; - int err; - - /* do behind I/O ? - * Not if there are too many, or cannot - * allocate memory, or a reader on WriteMostly - * is waiting for behind writes to flush */ - err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats); - if (!err && write_behind && !stats.behind_wait && - stats.behind_writes < max_write_behind) - alloc_behind_master_bio(r1_bio, bio); - - if (test_bit(R1BIO_BehindIO, &r1_bio->state)) - mddev->bitmap_ops->start_behind_write(mddev); + if (write_behind) + raid1_start_write_behind(mddev, r1_bio, bio); first_clone = 0; } From 8d31ed3b776eb2a4c4397f96dc92643f57e2e447 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:06 +0800 Subject: [PATCH 08/24] md/raid1: check before referencing mddev->bitmap_ops Prepare to introduce CONFIG_MD_BITMAP. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-11-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/raid1.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 5599dcbd2991..0e792b9bfff8 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2820,7 +2820,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, else /* completed sync */ conf->fullsync = 0; - mddev->bitmap_ops->close_sync(mddev); + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->close_sync(mddev); close_sync(conf); if (mddev_is_clustered(mddev)) { @@ -2857,10 +2858,11 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, /* we are incrementing sector_nr below. To be safe, we check against * sector_nr + two times RESYNC_SECTORS */ - - mddev->bitmap_ops->cond_end_sync(mddev, sector_nr, - mddev_is_clustered(mddev) && - (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high)); + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->cond_end_sync(mddev, sector_nr, + mddev_is_clustered(mddev) && + (sector_nr + 2 * RESYNC_SECTORS > + conf->cluster_sync_high)); if (raise_barrier(conf, sector_nr)) return 0; @@ -3335,15 +3337,17 @@ static int raid1_resize(struct mddev *mddev, sector_t sectors) * worth it. */ sector_t newsize = raid1_size(mddev, sectors, 0); - int ret; if (mddev->external_size && mddev->array_sectors > newsize) return -EINVAL; - ret = mddev->bitmap_ops->resize(mddev, newsize, 0); - if (ret) - return ret; + if (md_bitmap_enabled(mddev, false)) { + int ret = mddev->bitmap_ops->resize(mddev, newsize, 0); + + if (ret) + return ret; + } md_set_array_sectors(mddev, newsize); if (sectors > mddev->dev_sectors && From 969f996243ae1d7b95b95368262f5e3a6e8bb0b4 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:07 +0800 Subject: [PATCH 09/24] md/raid10: check before referencing mddev->bitmap_ops Prepare to introduce CONFIG_MD_BITMAP. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-12-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/raid10.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index d047e9dfdb85..2411399a7352 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3247,7 +3247,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, } conf->fullsync = 0; } - mddev->bitmap_ops->close_sync(mddev); + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->close_sync(mddev); close_sync(conf); *skipped = 1; return sectors_skipped; @@ -3566,7 +3567,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, * safety reason, which ensures curr_resync_completed is * updated in bitmap_cond_end_sync. */ - mddev->bitmap_ops->cond_end_sync(mddev, sector_nr, + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->cond_end_sync(mddev, sector_nr, mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high)); @@ -4220,7 +4222,6 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors) */ struct r10conf *conf = mddev->private; sector_t oldsize, size; - int ret; if (mddev->reshape_position != MaxSector) return -EBUSY; @@ -4234,9 +4235,12 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors) mddev->array_sectors > size) return -EINVAL; - ret = mddev->bitmap_ops->resize(mddev, size, 0); - if (ret) - return ret; + if (md_bitmap_enabled(mddev, false)) { + int ret = mddev->bitmap_ops->resize(mddev, size, 0); + + if (ret) + return ret; + } md_set_array_sectors(mddev, size); if (sectors > mddev->dev_sectors && @@ -4502,7 +4506,8 @@ static int raid10_start_reshape(struct mddev *mddev) oldsize = raid10_size(mddev, 0, 0); newsize = raid10_size(mddev, 0, conf->geo.raid_disks); - if (!mddev_is_clustered(mddev)) { + if (!mddev_is_clustered(mddev) && + md_bitmap_enabled(mddev, false)) { ret = mddev->bitmap_ops->resize(mddev, newsize, 0); if (ret) goto abort; @@ -4525,6 +4530,7 @@ static int raid10_start_reshape(struct mddev *mddev) MD_FEATURE_RESHAPE_ACTIVE)) || (oldsize == newsize)) goto out; + /* cluster can't be setup without bitmap */ ret = mddev->bitmap_ops->resize(mddev, newsize, 0); if (ret) goto abort; From bb9317b13ade9e5e550aa2efecbd209ff96697ff Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:08 +0800 Subject: [PATCH 10/24] md/raid5: check before referencing mddev->bitmap_ops Prepare to introduce CONFIG_MD_BITMAP. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-13-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/raid5.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 955906bd4778..5285e72341a2 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6496,7 +6496,8 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n &sync_blocks); else /* completed sync */ conf->fullsync = 0; - mddev->bitmap_ops->close_sync(mddev); + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->close_sync(mddev); return 0; } @@ -6534,7 +6535,8 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n return sync_blocks * RAID5_STRIPE_SECTORS(conf); } - mddev->bitmap_ops->cond_end_sync(mddev, sector_nr, false); + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->cond_end_sync(mddev, sector_nr, false); sh = raid5_get_active_stripe(conf, NULL, sector_nr, R5_GAS_NOBLOCK); @@ -6760,7 +6762,8 @@ static void raid5d(struct md_thread *thread) /* Now is a good time to flush some bitmap updates */ conf->seq_flush++; spin_unlock_irq(&conf->device_lock); - mddev->bitmap_ops->unplug(mddev, true); + if (md_bitmap_enabled(mddev, true)) + mddev->bitmap_ops->unplug(mddev, true); spin_lock_irq(&conf->device_lock); conf->seq_write = conf->seq_flush; activate_bit_delay(conf, conf->temp_inactive_list); @@ -8309,7 +8312,6 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors) */ sector_t newsize; struct r5conf *conf = mddev->private; - int ret; if (raid5_has_log(conf) || raid5_has_ppl(conf)) return -EINVAL; @@ -8319,9 +8321,12 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors) mddev->array_sectors > newsize) return -EINVAL; - ret = mddev->bitmap_ops->resize(mddev, sectors, 0); - if (ret) - return ret; + if (md_bitmap_enabled(mddev, false)) { + int ret = mddev->bitmap_ops->resize(mddev, sectors, 0); + + if (ret) + return ret; + } md_set_array_sectors(mddev, newsize); if (sectors > mddev->dev_sectors && From 0e18745420e332870eabed5a9d7efb45c0283bf0 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:09 +0800 Subject: [PATCH 11/24] md/dm-raid: check before referencing mddev->bitmap_ops Prepare to introduce CONFIG_MD_BITMAP. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-14-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/dm-raid.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 05811316dedd..967d72929909 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3953,9 +3953,11 @@ static int __load_dirty_region_bitmap(struct raid_set *rs) !test_and_set_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags)) { struct mddev *mddev = &rs->md; - r = mddev->bitmap_ops->load(mddev); - if (r) - DMERR("Failed to load bitmap"); + if (md_bitmap_enabled(mddev, false)) { + r = mddev->bitmap_ops->load(mddev); + if (r) + DMERR("Failed to load bitmap"); + } } return r; @@ -4070,10 +4072,12 @@ static int raid_preresume(struct dm_target *ti) mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)))) { int chunksize = to_bytes(rs->requested_bitmap_chunk_sectors) ?: mddev->bitmap_info.chunksize; - r = mddev->bitmap_ops->resize(mddev, mddev->dev_sectors, - chunksize); - if (r) - DMERR("Failed to resize bitmap"); + if (md_bitmap_enabled(mddev, false)) { + r = mddev->bitmap_ops->resize(mddev, mddev->dev_sectors, + chunksize); + if (r) + DMERR("Failed to resize bitmap"); + } } /* Check for any resize/reshape on @rs and adjust/initiate */ From 26292657add33b8cb627bd582e7097755e85a3ac Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:10 +0800 Subject: [PATCH 12/24] md: check before referencing mddev->bitmap_ops Prepare to introduce CONFIG_MD_BITMAP. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-15-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/md.c | 68 ++++++++++++++++++++++++++++++++++--------------- 1 file changed, 48 insertions(+), 20 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index ee1454948fc5..e750ae4883e6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1356,6 +1356,9 @@ static u64 md_bitmap_events_cleared(struct mddev *mddev) struct md_bitmap_stats stats; int err; + if (!md_bitmap_enabled(mddev, false)) + return 0; + err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats); if (err) return 0; @@ -2313,13 +2316,15 @@ static int super_1_allow_new_offset(struct md_rdev *rdev, unsigned long long new_offset) { + struct mddev *mddev = rdev->mddev; + /* All necessary checks on new >= old have been done */ if (new_offset >= rdev->data_offset) return 1; /* with 1.0 metadata, there is no metadata to tread on * so we can always move back */ - if (rdev->mddev->minor_version == 0) + if (mddev->minor_version == 0) return 1; /* otherwise we must be sure not to step on @@ -2331,8 +2336,7 @@ super_1_allow_new_offset(struct md_rdev *rdev, if (rdev->sb_start + (32+4)*2 > new_offset) return 0; - if (!rdev->mddev->bitmap_info.file) { - struct mddev *mddev = rdev->mddev; + if (md_bitmap_registered(mddev) && !mddev->bitmap_info.file) { struct md_bitmap_stats stats; int err; @@ -2804,7 +2808,8 @@ repeat: mddev_add_trace_msg(mddev, "md md_update_sb"); rewrite: - mddev->bitmap_ops->update_sb(mddev->bitmap); + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->update_sb(mddev->bitmap); rdev_for_each(rdev, mddev) { if (rdev->sb_loaded != 1) continue; /* no noise on spare devices */ @@ -4680,6 +4685,9 @@ bitmap_store(struct mddev *mddev, const char *buf, size_t len) unsigned long chunk, end_chunk; int err; + if (!md_bitmap_enabled(mddev, false)) + return len; + err = mddev_lock(mddev); if (err) return err; @@ -6054,7 +6062,7 @@ struct mddev *md_alloc(dev_t dev, char *name) return ERR_PTR(error); } - if (mddev->bitmap_ops && mddev->bitmap_ops->group) + if (md_bitmap_registered(mddev) && mddev->bitmap_ops->group) if (sysfs_create_group(&mddev->kobj, mddev->bitmap_ops->group)) pr_warn("md: cannot register extra bitmap attributes for %s\n", mdname(mddev)); @@ -6301,7 +6309,7 @@ int md_run(struct mddev *mddev) (unsigned long long)pers->size(mddev, 0, 0) / 2); err = -EINVAL; } - if (err == 0 && pers->sync_request && + if (err == 0 && pers->sync_request && md_bitmap_registered(mddev) && (mddev->bitmap_info.file || mddev->bitmap_info.offset)) { err = mddev->bitmap_ops->create(mddev); if (err) @@ -6376,7 +6384,8 @@ bitmap_abort: pers->free(mddev, mddev->private); mddev->private = NULL; put_pers(pers); - mddev->bitmap_ops->destroy(mddev); + if (md_bitmap_registered(mddev)) + mddev->bitmap_ops->destroy(mddev); abort: bioset_exit(&mddev->io_clone_set); exit_sync_set: @@ -6396,10 +6405,12 @@ int do_md_run(struct mddev *mddev) if (err) goto out; - err = mddev->bitmap_ops->load(mddev); - if (err) { - mddev->bitmap_ops->destroy(mddev); - goto out; + if (md_bitmap_registered(mddev)) { + err = mddev->bitmap_ops->load(mddev); + if (err) { + mddev->bitmap_ops->destroy(mddev); + goto out; + } } if (mddev_is_clustered(mddev)) @@ -6550,7 +6561,8 @@ static void __md_stop_writes(struct mddev *mddev) mddev->pers->quiesce(mddev, 0); } - mddev->bitmap_ops->flush(mddev); + if (md_bitmap_enabled(mddev, true)) + mddev->bitmap_ops->flush(mddev); if (md_is_rdwr(mddev) && ((!mddev->in_sync && !mddev_is_clustered(mddev)) || @@ -6577,7 +6589,8 @@ EXPORT_SYMBOL_GPL(md_stop_writes); static void mddev_detach(struct mddev *mddev) { - mddev->bitmap_ops->wait_behind_writes(mddev); + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->wait_behind_writes(mddev); if (mddev->pers && mddev->pers->quiesce && !is_md_suspended(mddev)) { mddev->pers->quiesce(mddev, 1); mddev->pers->quiesce(mddev, 0); @@ -6593,7 +6606,8 @@ static void __md_stop(struct mddev *mddev) { struct md_personality *pers = mddev->pers; - mddev->bitmap_ops->destroy(mddev); + if (md_bitmap_registered(mddev)) + mddev->bitmap_ops->destroy(mddev); mddev_detach(mddev); spin_lock(&mddev->lock); mddev->pers = NULL; @@ -7311,6 +7325,9 @@ static int set_bitmap_file(struct mddev *mddev, int fd) { int err = 0; + if (!md_bitmap_registered(mddev)) + return -EINVAL; + if (mddev->pers) { if (!mddev->pers->quiesce || !mddev->thread) return -EBUSY; @@ -7661,6 +7678,14 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) rv = update_raid_disks(mddev, info->raid_disks); if ((state ^ info->state) & (1<pers->quiesce == NULL || mddev->thread == NULL) { rv = -EINVAL; goto err; @@ -8495,6 +8520,9 @@ static void md_bitmap_status(struct seq_file *seq, struct mddev *mddev) unsigned long chunk_kb; int err; + if (!md_bitmap_enabled(mddev, false)) + return; + err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats); if (err) return; @@ -8897,7 +8925,7 @@ static void md_end_clone_io(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) + if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, false)) md_bitmap_end(mddev, md_io_clone); if (bio->bi_status && !orig_bio->bi_status) @@ -8924,7 +8952,7 @@ 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) { + if (bio_data_dir(*bio) == WRITE && md_bitmap_enabled(mddev, false)) { md_io_clone->offset = (*bio)->bi_iter.bi_sector; md_io_clone->sectors = bio_sectors(*bio); md_bitmap_start(mddev, md_io_clone); @@ -8948,7 +8976,7 @@ 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) + if (bio_data_dir(orig_bio) == WRITE && md_bitmap_enabled(mddev, false)) md_bitmap_end(mddev, md_io_clone); if (bio->bi_status && !orig_bio->bi_status) @@ -9681,7 +9709,7 @@ static void md_start_sync(struct work_struct *ws) * We are adding a device or devices to an array which has the bitmap * stored on all devices. So make sure all bitmap pages get written. */ - if (spares) + if (spares && md_bitmap_enabled(mddev, true)) mddev->bitmap_ops->write_all(mddev); name = test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ? @@ -9769,7 +9797,7 @@ static void unregister_sync_thread(struct mddev *mddev) */ void md_check_recovery(struct mddev *mddev) { - if (mddev->bitmap) + if (md_bitmap_enabled(mddev, false)) mddev->bitmap_ops->daemon_work(mddev); if (signal_pending(current)) { @@ -10149,7 +10177,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) ret = mddev->pers->resize(mddev, le64_to_cpu(sb->size)); if (ret) pr_info("md-cluster: resize failed\n"); - else + else if (md_bitmap_enabled(mddev, false)) mddev->bitmap_ops->update_sb(mddev->bitmap); } From c27474ac1d4609af3c1c38ccac252c2575b47b9e Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Mon, 7 Jul 2025 09:27:11 +0800 Subject: [PATCH 13/24] md/md-bitmap: introduce CONFIG_MD_BITMAP Now that all implementations are internal, it's sensible to add a config option for md-bitmap, and it's a good way for isolation. Link: https://lore.kernel.org/linux-raid/20250707012711.376844-16-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni --- drivers/md/Kconfig | 18 ++++++++++++++++++ drivers/md/Makefile | 3 ++- drivers/md/md-bitmap.c | 23 +++++++++++++++++++++-- drivers/md/md-bitmap.h | 17 +++++++++++++++-- drivers/md/md.c | 40 ++++++++++++++++++++++++++++------------ drivers/md/md.h | 3 +-- 6 files changed, 85 insertions(+), 19 deletions(-) diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index ddb37f6670de..f913579e731c 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -37,6 +37,21 @@ config BLK_DEV_MD If unsure, say N. +config MD_BITMAP + bool "MD RAID bitmap support" + default y + depends on BLK_DEV_MD + help + If you say Y here, support for the write intent bitmap will be + enabled. The bitmap can be used to optimize resync speed after power + failure or readding a disk, limiting it to recorded dirty sectors in + bitmap. + + This feature can be added to existing MD array or MD array can be + created with bitmap via mdadm(8). + + If unsure, say Y. + config MD_AUTODETECT bool "Autodetect RAID arrays during kernel boot" depends on BLK_DEV_MD=y @@ -54,6 +69,7 @@ config MD_AUTODETECT config MD_BITMAP_FILE bool "MD bitmap file support (deprecated)" default y + depends on MD_BITMAP help If you say Y here, support for write intent bitmaps in files on an external file system is enabled. This is an alternative to the internal @@ -174,6 +190,7 @@ config MD_RAID456 config MD_CLUSTER tristate "Cluster Support for MD" + select MD_BITMAP depends on BLK_DEV_MD depends on DLM default n @@ -393,6 +410,7 @@ config DM_RAID select MD_RAID1 select MD_RAID10 select MD_RAID456 + select MD_BITMAP select BLK_DEV_MD help A dm target that supports RAID1, RAID10, RAID4, RAID5 and RAID6 mappings diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 87bdfc9fe14c..2e18147a9c40 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -27,7 +27,8 @@ dm-clone-y += dm-clone-target.o dm-clone-metadata.o dm-verity-y += dm-verity-target.o dm-zoned-y += dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o -md-mod-y += md.o md-bitmap.o +md-mod-y += md.o +md-mod-$(CONFIG_MD_BITMAP) += md-bitmap.o raid456-y += raid5.o raid5-cache.o raid5-ppl.o linear-y += md-linear.o diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 29de99e0de3e..5f62f2fd8f3f 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -224,6 +224,8 @@ struct bitmap { int cluster_slot; }; +static struct workqueue_struct *md_bitmap_wq; + static int __bitmap_resize(struct bitmap *bitmap, sector_t blocks, int chunksize, bool init); @@ -2979,6 +2981,12 @@ static struct attribute_group md_bitmap_group = { }; static struct bitmap_operations bitmap_ops = { + .head = { + .type = MD_BITMAP, + .id = ID_BITMAP, + .name = "bitmap", + }, + .enabled = bitmap_enabled, .create = bitmap_create, .resize = bitmap_resize, @@ -3013,7 +3021,18 @@ static struct bitmap_operations bitmap_ops = { .group = &md_bitmap_group, }; -void mddev_set_bitmap_ops(struct mddev *mddev) +int md_bitmap_init(void) { - mddev->bitmap_ops = &bitmap_ops; + md_bitmap_wq = alloc_workqueue("md_bitmap", WQ_MEM_RECLAIM | WQ_UNBOUND, + 0); + if (!md_bitmap_wq) + return -ENOMEM; + + return register_md_submodule(&bitmap_ops.head); +} + +void md_bitmap_exit(void) +{ + destroy_workqueue(md_bitmap_wq); + unregister_md_submodule(&bitmap_ops.head); } diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 61cfc650c69c..42f91755a341 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -62,6 +62,8 @@ struct md_bitmap_stats { }; struct bitmap_operations { + struct md_submodule_head head; + bool (*enabled)(void *data, bool flush); int (*create)(struct mddev *mddev); int (*resize)(struct mddev *mddev, sector_t blocks, int chunksize); @@ -105,8 +107,6 @@ struct bitmap_operations { }; /* the bitmap API */ -void mddev_set_bitmap_ops(struct mddev *mddev); - static inline bool md_bitmap_registered(struct mddev *mddev) { return mddev->bitmap_ops != NULL; @@ -147,4 +147,17 @@ static inline void md_bitmap_end_sync(struct mddev *mddev, sector_t offset, mddev->bitmap_ops->end_sync(mddev, offset, blocks); } +#ifdef CONFIG_MD_BITMAP +int md_bitmap_init(void); +void md_bitmap_exit(void); +#else +static inline int md_bitmap_init(void) +{ + return 0; +} +static inline void md_bitmap_exit(void) +{ +} +#endif + #endif diff --git a/drivers/md/md.c b/drivers/md/md.c index e750ae4883e6..fbc107b52819 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -94,7 +94,6 @@ static struct workqueue_struct *md_wq; * workqueue whith reconfig_mutex grabbed. */ static struct workqueue_struct *md_misc_wq; -struct workqueue_struct *md_bitmap_wq; static int remove_and_add_spares(struct mddev *mddev, struct md_rdev *this); @@ -677,15 +676,34 @@ static void active_io_release(struct percpu_ref *ref) static void no_op(struct percpu_ref *r) {} +static void mddev_set_bitmap_ops(struct mddev *mddev, enum md_submodule_id id) +{ + xa_lock(&md_submodule); + mddev->bitmap_ops = xa_load(&md_submodule, id); + xa_unlock(&md_submodule); + if (!mddev->bitmap_ops) + pr_warn_once("md: can't find bitmap id %d\n", id); +} + +static void mddev_clear_bitmap_ops(struct mddev *mddev) +{ + mddev->bitmap_ops = NULL; +} + int mddev_init(struct mddev *mddev) { + /* TODO: support more versions */ + mddev_set_bitmap_ops(mddev, ID_BITMAP); if (percpu_ref_init(&mddev->active_io, active_io_release, - PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { + mddev_clear_bitmap_ops(mddev); return -ENOMEM; + } if (percpu_ref_init(&mddev->writes_pending, no_op, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { + mddev_clear_bitmap_ops(mddev); percpu_ref_exit(&mddev->active_io); return -ENOMEM; } @@ -713,7 +731,6 @@ int mddev_init(struct mddev *mddev) mddev->resync_min = 0; mddev->resync_max = MaxSector; mddev->level = LEVEL_NONE; - mddev_set_bitmap_ops(mddev); INIT_WORK(&mddev->sync_work, md_start_sync); INIT_WORK(&mddev->del_work, mddev_delayed_delete); @@ -724,6 +741,7 @@ EXPORT_SYMBOL_GPL(mddev_init); void mddev_destroy(struct mddev *mddev) { + mddev_clear_bitmap_ops(mddev); percpu_ref_exit(&mddev->active_io); percpu_ref_exit(&mddev->writes_pending); } @@ -10121,8 +10139,12 @@ static void md_geninit(void) static int __init md_init(void) { - int ret = -ENOMEM; + int ret = md_bitmap_init(); + if (ret) + return ret; + + ret = -ENOMEM; md_wq = alloc_workqueue("md", WQ_MEM_RECLAIM, 0); if (!md_wq) goto err_wq; @@ -10131,11 +10153,6 @@ static int __init md_init(void) if (!md_misc_wq) goto err_misc_wq; - md_bitmap_wq = alloc_workqueue("md_bitmap", WQ_MEM_RECLAIM | WQ_UNBOUND, - 0); - if (!md_bitmap_wq) - goto err_bitmap_wq; - ret = __register_blkdev(MD_MAJOR, "md", md_probe); if (ret < 0) goto err_md; @@ -10154,12 +10171,11 @@ static int __init md_init(void) err_mdp: unregister_blkdev(MD_MAJOR, "md"); err_md: - destroy_workqueue(md_bitmap_wq); -err_bitmap_wq: destroy_workqueue(md_misc_wq); err_misc_wq: destroy_workqueue(md_wq); err_wq: + md_bitmap_exit(); return ret; } @@ -10465,8 +10481,8 @@ static __exit void md_exit(void) spin_unlock(&all_mddevs_lock); destroy_workqueue(md_misc_wq); - destroy_workqueue(md_bitmap_wq); destroy_workqueue(md_wq); + md_bitmap_exit(); } subsys_initcall(md_init); diff --git a/drivers/md/md.h b/drivers/md/md.h index 06364e15e8d1..081152c8de1f 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -38,7 +38,7 @@ enum md_submodule_id { ID_RAID6 = 6, ID_RAID10 = 10, ID_CLUSTER, - ID_BITMAP, /* TODO */ + ID_BITMAP, ID_LLBITMAP, /* TODO */ }; @@ -1012,7 +1012,6 @@ struct mdu_array_info_s; struct mdu_disk_info_s; extern int mdp_major; -extern struct workqueue_struct *md_bitmap_wq; void md_autostart_arrays(int part); int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info); int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info); From d01acbce391767318c94fb1f6d648cfabb428f9d Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:16 +0800 Subject: [PATCH 14/24] md: add a new parameter 'offset' to md_super_write() The parameter is always set to 0 for now, following patches will use this helper to write llbitmap to underlying disks, allow writing dirty sectors instead of the whole page. Also rename md_super_write to md_write_metadata since there is nothing super-block specific. Link: https://lore.kernel.org/linux-raid/20250829080426.1441678-2-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Li Nan --- drivers/md/md-bitmap.c | 3 ++- drivers/md/md.c | 50 +++++++++++++++++++++++++----------------- drivers/md/md.h | 5 +++-- 3 files changed, 35 insertions(+), 23 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 5f62f2fd8f3f..b157119de123 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -485,7 +485,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap, return -EINVAL; } - md_super_write(mddev, rdev, sboff + ps, (int)min(size, bitmap_limit), page); + md_write_metadata(mddev, rdev, sboff + ps, (int)min(size, bitmap_limit), + page, 0); return 0; } diff --git a/drivers/md/md.c b/drivers/md/md.c index fbc107b52819..528c99396458 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1038,15 +1038,26 @@ static void super_written(struct bio *bio) wake_up(&mddev->sb_wait); } -void md_super_write(struct mddev *mddev, struct md_rdev *rdev, - sector_t sector, int size, struct page *page) +/** + * md_write_metadata - write metadata to underlying disk, including + * array superblock, badblocks, bitmap superblock and bitmap bits. + * @mddev: the array to write + * @rdev: the underlying disk to write + * @sector: the offset to @rdev + * @size: the length of the metadata + * @page: the metadata + * @offset: the offset to @page + * + * Write @size bytes of @page start from @offset, to @sector of @rdev, Increment + * mddev->pending_writes before returning, and decrement it on completion, + * waking up sb_wait. Caller must call md_super_wait() after issuing io to all + * rdev. If an error occurred, md_error() will be called, and the @rdev will be + * kicked out from @mddev. + */ +void md_write_metadata(struct mddev *mddev, struct md_rdev *rdev, + sector_t sector, int size, struct page *page, + unsigned int offset) { - /* write first size bytes of page to sector of rdev - * Increment mddev->pending_writes before returning - * and decrement it on completion, waking up sb_wait - * if zero is reached. - * If an error occurred, call md_error - */ struct bio *bio; if (!page) @@ -1064,7 +1075,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, atomic_inc(&rdev->nr_pending); bio->bi_iter.bi_sector = sector; - __bio_add_page(bio, page, size, 0); + __bio_add_page(bio, page, size, offset); bio->bi_private = rdev; bio->bi_end_io = super_written; @@ -1674,8 +1685,8 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) if ((u64)num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1) num_sectors = (sector_t)(2ULL << 32) - 2; do { - md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size, - rdev->sb_page); + md_write_metadata(rdev->mddev, rdev, rdev->sb_start, + rdev->sb_size, rdev->sb_page, 0); } while (md_super_wait(rdev->mddev) < 0); return num_sectors; } @@ -2323,8 +2334,8 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) sb->super_offset = cpu_to_le64(rdev->sb_start); sb->sb_csum = calc_sb_1_csum(sb); do { - md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size, - rdev->sb_page); + md_write_metadata(rdev->mddev, rdev, rdev->sb_start, + rdev->sb_size, rdev->sb_page, 0); } while (md_super_wait(rdev->mddev) < 0); return num_sectors; @@ -2833,18 +2844,17 @@ rewrite: continue; /* no noise on spare devices */ if (!test_bit(Faulty, &rdev->flags)) { - md_super_write(mddev,rdev, - rdev->sb_start, rdev->sb_size, - rdev->sb_page); + md_write_metadata(mddev, rdev, rdev->sb_start, + rdev->sb_size, rdev->sb_page, 0); pr_debug("md: (write) %pg's sb offset: %llu\n", rdev->bdev, (unsigned long long)rdev->sb_start); rdev->sb_events = mddev->events; if (rdev->badblocks.size) { - md_super_write(mddev, rdev, - rdev->badblocks.sector, - rdev->badblocks.size << 9, - rdev->bb_page); + md_write_metadata(mddev, rdev, + rdev->badblocks.sector, + rdev->badblocks.size << 9, + rdev->bb_page, 0); rdev->badblocks.size = 0; } diff --git a/drivers/md/md.h b/drivers/md/md.h index 081152c8de1f..cadd9bc99938 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -908,8 +908,9 @@ void md_account_bio(struct mddev *mddev, struct bio **bio); void md_free_cloned_bio(struct bio *bio); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); -extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, - sector_t sector, int size, struct page *page); +void md_write_metadata(struct mddev *mddev, struct md_rdev *rdev, + sector_t sector, int size, struct page *page, + unsigned int offset); extern int md_super_wait(struct mddev *mddev); extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, struct page *page, blk_opf_t opf, bool metadata_op); From 7797da149d4622bbe803eaee6eaf22a7f62f44ab Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:17 +0800 Subject: [PATCH 15/24] md: factor out a helper raid_is_456() There are no functional changes, the helper will be used by llbitmap in following patches. Link: https://lore.kernel.org/linux-raid/20250829080426.1441678-3-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Li Nan --- drivers/md/md.c | 9 +-------- drivers/md/md.h | 6 ++++++ 2 files changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 528c99396458..4bc35362f4d0 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -9121,19 +9121,12 @@ static sector_t md_sync_position(struct mddev *mddev, enum sync_action action) static bool sync_io_within_limit(struct mddev *mddev) { - int io_sectors; - /* * For raid456, sync IO is stripe(4k) per IO, for other levels, it's * RESYNC_PAGES(64k) per IO. */ - if (mddev->level == 4 || mddev->level == 5 || mddev->level == 6) - io_sectors = 8; - else - io_sectors = 128; - return atomic_read(&mddev->recovery_active) < - io_sectors * sync_io_depth(mddev); + (raid_is_456(mddev) ? 8 : 128) * sync_io_depth(mddev); } #define SYNC_MARKS 10 diff --git a/drivers/md/md.h b/drivers/md/md.h index cadd9bc99938..5ef73109d14d 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -1033,6 +1033,12 @@ static inline bool mddev_is_dm(struct mddev *mddev) return !mddev->gendisk; } +static inline bool raid_is_456(struct mddev *mddev) +{ + return mddev->level == ID_RAID4 || mddev->level == ID_RAID5 || + mddev->level == ID_RAID6; +} + static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio, sector_t sector) { From ac9dad8faaa7b2a7c7c6de0017f2d7d54525d33c Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:18 +0800 Subject: [PATCH 16/24] md/md-bitmap: support discard for bitmap ops Use two new methods {start, end}_discard in bitmap_ops and a new field 'rw' in struct md_io_clone to handle discard IO, prepare to support new md bitmap. Since all bitmap functions to hanlde write IO are the same, also add typedef to make code cleaner. Link: https://lore.kernel.org/linux-raid/20250829080426.1441678-4-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni Reviewed-by: Hannes Reinecke Reviewed-by: Li Nan --- drivers/md/md-bitmap.c | 3 +++ drivers/md/md-bitmap.h | 12 ++++++++---- drivers/md/md.c | 15 +++++++++++---- drivers/md/md.h | 1 + 4 files changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index b157119de123..dc050ff94d5b 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -3005,6 +3005,9 @@ static struct bitmap_operations bitmap_ops = { .start_write = bitmap_start_write, .end_write = bitmap_end_write, + .start_discard = bitmap_start_write, + .end_discard = bitmap_end_write, + .start_sync = bitmap_start_sync, .end_sync = bitmap_end_sync, .cond_end_sync = bitmap_cond_end_sync, diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 42f91755a341..8616ced49077 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -61,6 +61,9 @@ struct md_bitmap_stats { struct file *file; }; +typedef void (md_bitmap_fn)(struct mddev *mddev, sector_t offset, + unsigned long sectors); + struct bitmap_operations { struct md_submodule_head head; @@ -81,10 +84,11 @@ struct bitmap_operations { void (*end_behind_write)(struct mddev *mddev); void (*wait_behind_writes)(struct mddev *mddev); - void (*start_write)(struct mddev *mddev, sector_t offset, - unsigned long sectors); - void (*end_write)(struct mddev *mddev, sector_t offset, - unsigned long sectors); + md_bitmap_fn *start_write; + md_bitmap_fn *end_write; + md_bitmap_fn *start_discard; + md_bitmap_fn *end_discard; + 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/md.c b/drivers/md/md.c index 4bc35362f4d0..8a89dca8209c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -8933,18 +8933,24 @@ EXPORT_SYMBOL_GPL(md_submit_discard_bio); static void md_bitmap_start(struct mddev *mddev, struct md_io_clone *md_io_clone) { + md_bitmap_fn *fn = unlikely(md_io_clone->rw == STAT_DISCARD) ? + mddev->bitmap_ops->start_discard : + mddev->bitmap_ops->start_write; + if (mddev->pers->bitmap_sector) mddev->pers->bitmap_sector(mddev, &md_io_clone->offset, &md_io_clone->sectors); - mddev->bitmap_ops->start_write(mddev, md_io_clone->offset, - md_io_clone->sectors); + fn(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->end_write(mddev, md_io_clone->offset, - md_io_clone->sectors); + md_bitmap_fn *fn = unlikely(md_io_clone->rw == STAT_DISCARD) ? + mddev->bitmap_ops->end_discard : + mddev->bitmap_ops->end_write; + + fn(mddev, md_io_clone->offset, md_io_clone->sectors); } static void md_end_clone_io(struct bio *bio) @@ -8983,6 +8989,7 @@ static void md_clone_bio(struct mddev *mddev, struct bio **bio) if (bio_data_dir(*bio) == WRITE && md_bitmap_enabled(mddev, false)) { md_io_clone->offset = (*bio)->bi_iter.bi_sector; md_io_clone->sectors = bio_sectors(*bio); + md_io_clone->rw = op_stat_group(bio_op(*bio)); md_bitmap_start(mddev, md_io_clone); } diff --git a/drivers/md/md.h b/drivers/md/md.h index 5ef73109d14d..1b767b5320cf 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -872,6 +872,7 @@ struct md_io_clone { unsigned long start_time; sector_t offset; unsigned long sectors; + enum stat_group rw; struct bio bio_clone; }; From 300bffa870c5dfaae87c169b1d5edc9c285a81a6 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:19 +0800 Subject: [PATCH 17/24] md: add a new mddev field 'bitmap_id' Prepare to store the bitmap id selected by user, also refactor mddev_set_bitmap_ops a bit in case the value is invalid. Link: https://lore.kernel.org/linux-raid/20250829080426.1441678-5-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Hannes Reinecke Reviewed-by: Li Nan Reviewed-by: Xiao Ni --- drivers/md/md.c | 37 +++++++++++++++++++++++++++++++------ drivers/md/md.h | 2 ++ 2 files changed, 33 insertions(+), 6 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 8a89dca8209c..806fa7fb25a5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -676,13 +676,33 @@ static void active_io_release(struct percpu_ref *ref) static void no_op(struct percpu_ref *r) {} -static void mddev_set_bitmap_ops(struct mddev *mddev, enum md_submodule_id id) +static bool mddev_set_bitmap_ops(struct mddev *mddev) { + struct md_submodule_head *head; + + if (mddev->bitmap_id == ID_BITMAP_NONE) + return true; + xa_lock(&md_submodule); - mddev->bitmap_ops = xa_load(&md_submodule, id); + head = xa_load(&md_submodule, mddev->bitmap_id); + + if (!head) { + pr_warn("md: can't find bitmap id %d\n", mddev->bitmap_id); + goto err; + } + + if (head->type != MD_BITMAP) { + pr_warn("md: invalid bitmap id %d\n", mddev->bitmap_id); + goto err; + } + + mddev->bitmap_ops = (void *)head; xa_unlock(&md_submodule); - if (!mddev->bitmap_ops) - pr_warn_once("md: can't find bitmap id %d\n", id); + return true; + +err: + xa_unlock(&md_submodule); + return false; } static void mddev_clear_bitmap_ops(struct mddev *mddev) @@ -692,8 +712,13 @@ static void mddev_clear_bitmap_ops(struct mddev *mddev) int mddev_init(struct mddev *mddev) { - /* TODO: support more versions */ - mddev_set_bitmap_ops(mddev, ID_BITMAP); + if (!IS_ENABLED(CONFIG_MD_BITMAP)) { + mddev->bitmap_id = ID_BITMAP_NONE; + } else { + mddev->bitmap_id = ID_BITMAP; + if (!mddev_set_bitmap_ops(mddev)) + return -EINVAL; + } if (percpu_ref_init(&mddev->active_io, active_io_release, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { diff --git a/drivers/md/md.h b/drivers/md/md.h index 1b767b5320cf..4fa5a3e68a0c 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -40,6 +40,7 @@ enum md_submodule_id { ID_CLUSTER, ID_BITMAP, ID_LLBITMAP, /* TODO */ + ID_BITMAP_NONE, }; struct md_submodule_head { @@ -565,6 +566,7 @@ struct mddev { struct percpu_ref writes_pending; int sync_checkers; /* # of threads checking writes_pending */ + enum md_submodule_id bitmap_id; void *bitmap; /* the bitmap for the device */ struct bitmap_operations *bitmap_ops; struct { From 180b82c1c7b2c2c5bffc1642239bed36d7e83f76 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:20 +0800 Subject: [PATCH 18/24] md/md-bitmap: add a new sysfs api bitmap_type The api will be used by mdadm to set bitmap_type while creating new array or assembling array, prepare to add a new bitmap. Currently available options are: cat /sys/block/md0/md/bitmap_type none [bitmap] Link: https://lore.kernel.org/linux-raid/20250829080426.1441678-6-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Hannes Reinecke Reviewed-by: Xiao Ni Reviewed-by: Li Nan --- Documentation/admin-guide/md.rst | 73 ++++++++++++++++------------ drivers/md/md.c | 81 ++++++++++++++++++++++++++++++++ 2 files changed, 124 insertions(+), 30 deletions(-) diff --git a/Documentation/admin-guide/md.rst b/Documentation/admin-guide/md.rst index 4ff2cc291d18..356d2a344f08 100644 --- a/Documentation/admin-guide/md.rst +++ b/Documentation/admin-guide/md.rst @@ -347,6 +347,49 @@ All md devices contain: active-idle like active, but no writes have been seen for a while (safe_mode_delay). + consistency_policy + This indicates how the array maintains consistency in case of unexpected + shutdown. It can be: + + none + Array has no redundancy information, e.g. raid0, linear. + + resync + Full resync is performed and all redundancy is regenerated when the + array is started after unclean shutdown. + + bitmap + Resync assisted by a write-intent bitmap. + + journal + For raid4/5/6, journal device is used to log transactions and replay + after unclean shutdown. + + ppl + For raid5 only, Partial Parity Log is used to close the write hole and + eliminate resync. + + The accepted values when writing to this file are ``ppl`` and ``resync``, + used to enable and disable PPL. + + uuid + This indicates the UUID of the array in the following format: + xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx + + bitmap_type + [RW] When read, this file will display the current and available + bitmap for this array. The currently active bitmap will be enclosed + in [] brackets. Writing an bitmap name or ID to this file will switch + control of this array to that new bitmap. Note that writing a new + bitmap for created array is forbidden. + + none + No bitmap + bitmap + The default internal bitmap + +If bitmap_type is bitmap, then the md device will also contain: + bitmap/location This indicates where the write-intent bitmap for the array is stored. @@ -401,36 +444,6 @@ All md devices contain: once the array becomes non-degraded, and this fact has been recorded in the metadata. - consistency_policy - This indicates how the array maintains consistency in case of unexpected - shutdown. It can be: - - none - Array has no redundancy information, e.g. raid0, linear. - - resync - Full resync is performed and all redundancy is regenerated when the - array is started after unclean shutdown. - - bitmap - Resync assisted by a write-intent bitmap. - - journal - For raid4/5/6, journal device is used to log transactions and replay - after unclean shutdown. - - ppl - For raid5 only, Partial Parity Log is used to close the write hole and - eliminate resync. - - The accepted values when writing to this file are ``ppl`` and ``resync``, - used to enable and disable PPL. - - uuid - This indicates the UUID of the array in the following format: - xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx - - As component devices are added to an md array, they appear in the ``md`` directory as new directories named:: diff --git a/drivers/md/md.c b/drivers/md/md.c index 806fa7fb25a5..17cb33054ecf 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4207,6 +4207,86 @@ new_level_store(struct mddev *mddev, const char *buf, size_t len) static struct md_sysfs_entry md_new_level = __ATTR(new_level, 0664, new_level_show, new_level_store); +static ssize_t +bitmap_type_show(struct mddev *mddev, char *page) +{ + struct md_submodule_head *head; + unsigned long i; + ssize_t len = 0; + + if (mddev->bitmap_id == ID_BITMAP_NONE) + len += sprintf(page + len, "[none] "); + else + len += sprintf(page + len, "none "); + + xa_lock(&md_submodule); + xa_for_each(&md_submodule, i, head) { + if (head->type != MD_BITMAP) + continue; + + if (mddev->bitmap_id == head->id) + len += sprintf(page + len, "[%s] ", head->name); + else + len += sprintf(page + len, "%s ", head->name); + } + xa_unlock(&md_submodule); + + len += sprintf(page + len, "\n"); + return len; +} + +static ssize_t +bitmap_type_store(struct mddev *mddev, const char *buf, size_t len) +{ + struct md_submodule_head *head; + enum md_submodule_id id; + unsigned long i; + int err = 0; + + xa_lock(&md_submodule); + + if (mddev->bitmap_ops) { + err = -EBUSY; + goto out; + } + + if (cmd_match(buf, "none")) { + mddev->bitmap_id = ID_BITMAP_NONE; + goto out; + } + + xa_for_each(&md_submodule, i, head) { + if (head->type == MD_BITMAP && cmd_match(buf, head->name)) { + mddev->bitmap_id = head->id; + goto out; + } + } + + err = kstrtoint(buf, 10, &id); + if (err) + goto out; + + if (id == ID_BITMAP_NONE) { + mddev->bitmap_id = id; + goto out; + } + + head = xa_load(&md_submodule, id); + if (head && head->type == MD_BITMAP) { + mddev->bitmap_id = id; + goto out; + } + + err = -ENOENT; + +out: + xa_unlock(&md_submodule); + return err ? err : len; +} + +static struct md_sysfs_entry md_bitmap_type = +__ATTR(bitmap_type, 0664, bitmap_type_show, bitmap_type_store); + static ssize_t layout_show(struct mddev *mddev, char *page) { @@ -5813,6 +5893,7 @@ __ATTR(serialize_policy, S_IRUGO | S_IWUSR, serialize_policy_show, static struct attribute *md_default_attrs[] = { &md_level.attr, &md_new_level.attr, + &md_bitmap_type.attr, &md_layout.attr, &md_raid_disks.attr, &md_uuid.attr, From fb8cc3b0d9db94817a5aae2bcaf78dd079a89e52 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:21 +0800 Subject: [PATCH 19/24] md/md-bitmap: delay registration of bitmap_ops until creating bitmap Currently bitmap_ops is registered while allocating mddev, this is fine when there is only one bitmap_ops. Delay setting bitmap_ops until creating bitmap, so that user can choose which bitmap to use before running the array. Link: https://lore.kernel.org/linux-raid/20250721171557.34587-7-yukuai@kernel.org Signed-off-by: Yu Kuai Reviewed-by: Hannes Reinecke Reviewed-by: Li Nan Reviewed-by: Xiao Ni --- Documentation/admin-guide/md.rst | 3 ++ drivers/md/md.c | 90 +++++++++++++++++++------------- 2 files changed, 56 insertions(+), 37 deletions(-) diff --git a/Documentation/admin-guide/md.rst b/Documentation/admin-guide/md.rst index 356d2a344f08..001363f81850 100644 --- a/Documentation/admin-guide/md.rst +++ b/Documentation/admin-guide/md.rst @@ -388,6 +388,9 @@ All md devices contain: bitmap The default internal bitmap +If bitmap_type is not none, then additional bitmap attributes bitmap/xxx or +llbitmap/xxx will be created after md device KOBJ_CHANGE event. + If bitmap_type is bitmap, then the md device will also contain: bitmap/location diff --git a/drivers/md/md.c b/drivers/md/md.c index 17cb33054ecf..51dee0a98af1 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -678,9 +678,11 @@ static void no_op(struct percpu_ref *r) {} static bool mddev_set_bitmap_ops(struct mddev *mddev) { + struct bitmap_operations *old = mddev->bitmap_ops; struct md_submodule_head *head; - if (mddev->bitmap_id == ID_BITMAP_NONE) + if (mddev->bitmap_id == ID_BITMAP_NONE || + (old && old->head.id == mddev->bitmap_id)) return true; xa_lock(&md_submodule); @@ -698,6 +700,18 @@ static bool mddev_set_bitmap_ops(struct mddev *mddev) mddev->bitmap_ops = (void *)head; xa_unlock(&md_submodule); + + if (!mddev_is_dm(mddev) && mddev->bitmap_ops->group) { + if (sysfs_create_group(&mddev->kobj, mddev->bitmap_ops->group)) + pr_warn("md: cannot register extra bitmap attributes for %s\n", + mdname(mddev)); + else + /* + * Inform user with KOBJ_CHANGE about new bitmap + * attributes. + */ + kobject_uevent(&mddev->kobj, KOBJ_CHANGE); + } return true; err: @@ -707,28 +721,26 @@ err: static void mddev_clear_bitmap_ops(struct mddev *mddev) { + if (!mddev_is_dm(mddev) && mddev->bitmap_ops && + mddev->bitmap_ops->group) + sysfs_remove_group(&mddev->kobj, mddev->bitmap_ops->group); + mddev->bitmap_ops = NULL; } int mddev_init(struct mddev *mddev) { - if (!IS_ENABLED(CONFIG_MD_BITMAP)) { + if (!IS_ENABLED(CONFIG_MD_BITMAP)) mddev->bitmap_id = ID_BITMAP_NONE; - } else { + else mddev->bitmap_id = ID_BITMAP; - if (!mddev_set_bitmap_ops(mddev)) - return -EINVAL; - } if (percpu_ref_init(&mddev->active_io, active_io_release, - PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { - mddev_clear_bitmap_ops(mddev); + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) return -ENOMEM; - } if (percpu_ref_init(&mddev->writes_pending, no_op, PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { - mddev_clear_bitmap_ops(mddev); percpu_ref_exit(&mddev->active_io); return -ENOMEM; } @@ -766,7 +778,6 @@ EXPORT_SYMBOL_GPL(mddev_init); void mddev_destroy(struct mddev *mddev) { - mddev_clear_bitmap_ops(mddev); percpu_ref_exit(&mddev->active_io); percpu_ref_exit(&mddev->writes_pending); } @@ -6196,11 +6207,6 @@ struct mddev *md_alloc(dev_t dev, char *name) return ERR_PTR(error); } - if (md_bitmap_registered(mddev) && mddev->bitmap_ops->group) - if (sysfs_create_group(&mddev->kobj, mddev->bitmap_ops->group)) - pr_warn("md: cannot register extra bitmap attributes for %s\n", - mdname(mddev)); - kobject_uevent(&mddev->kobj, KOBJ_ADD); mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state"); mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level"); @@ -6279,6 +6285,26 @@ static void md_safemode_timeout(struct timer_list *t) static int start_dirty_degraded; +static int md_bitmap_create(struct mddev *mddev) +{ + if (mddev->bitmap_id == ID_BITMAP_NONE) + return -EINVAL; + + if (!mddev_set_bitmap_ops(mddev)) + return -ENOENT; + + return mddev->bitmap_ops->create(mddev); +} + +static void md_bitmap_destroy(struct mddev *mddev) +{ + if (!md_bitmap_registered(mddev)) + return; + + mddev->bitmap_ops->destroy(mddev); + mddev_clear_bitmap_ops(mddev); +} + int md_run(struct mddev *mddev) { int err; @@ -6443,9 +6469,9 @@ int md_run(struct mddev *mddev) (unsigned long long)pers->size(mddev, 0, 0) / 2); err = -EINVAL; } - if (err == 0 && pers->sync_request && md_bitmap_registered(mddev) && + if (err == 0 && pers->sync_request && (mddev->bitmap_info.file || mddev->bitmap_info.offset)) { - err = mddev->bitmap_ops->create(mddev); + err = md_bitmap_create(mddev); if (err) pr_warn("%s: failed to create bitmap (%d)\n", mdname(mddev), err); @@ -6518,8 +6544,7 @@ bitmap_abort: pers->free(mddev, mddev->private); mddev->private = NULL; put_pers(pers); - if (md_bitmap_registered(mddev)) - mddev->bitmap_ops->destroy(mddev); + md_bitmap_destroy(mddev); abort: bioset_exit(&mddev->io_clone_set); exit_sync_set: @@ -6542,7 +6567,7 @@ int do_md_run(struct mddev *mddev) if (md_bitmap_registered(mddev)) { err = mddev->bitmap_ops->load(mddev); if (err) { - mddev->bitmap_ops->destroy(mddev); + md_bitmap_destroy(mddev); goto out; } } @@ -6740,8 +6765,7 @@ static void __md_stop(struct mddev *mddev) { struct md_personality *pers = mddev->pers; - if (md_bitmap_registered(mddev)) - mddev->bitmap_ops->destroy(mddev); + md_bitmap_destroy(mddev); mddev_detach(mddev); spin_lock(&mddev->lock); mddev->pers = NULL; @@ -7518,16 +7542,16 @@ static int set_bitmap_file(struct mddev *mddev, int fd) err = 0; if (mddev->pers) { if (fd >= 0) { - err = mddev->bitmap_ops->create(mddev); + err = md_bitmap_create(mddev); if (!err) err = mddev->bitmap_ops->load(mddev); if (err) { - mddev->bitmap_ops->destroy(mddev); + md_bitmap_destroy(mddev); fd = -1; } } else if (fd < 0) { - mddev->bitmap_ops->destroy(mddev); + md_bitmap_destroy(mddev); } } @@ -7812,14 +7836,6 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) rv = update_raid_disks(mddev, info->raid_disks); if ((state ^ info->state) & (1<pers->quiesce == NULL || mddev->thread == NULL) { rv = -EINVAL; goto err; @@ -7842,12 +7858,12 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) mddev->bitmap_info.default_offset; mddev->bitmap_info.space = mddev->bitmap_info.default_space; - rv = mddev->bitmap_ops->create(mddev); + rv = md_bitmap_create(mddev); if (!rv) rv = mddev->bitmap_ops->load(mddev); if (rv) - mddev->bitmap_ops->destroy(mddev); + md_bitmap_destroy(mddev); } else { struct md_bitmap_stats stats; @@ -7873,7 +7889,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) put_cluster_ops(mddev); mddev->safemode_delay = DEFAULT_SAFEMODE_DELAY; } - mddev->bitmap_ops->destroy(mddev); + md_bitmap_destroy(mddev); mddev->bitmap_info.offset = 0; } } From f196d72888640e35002ac3511757cefaa9c5e339 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:22 +0800 Subject: [PATCH 20/24] md/md-bitmap: add a new method skip_sync_blocks() in bitmap_operations This method is used to check if blocks can be skipped before calling into pers->sync_request(), llbitmap will use this method to skip resync for unwritten/clean data blocks, and recovery/check/repair for unwritten data blocks; Link: https://lore.kernel.org/linux-raid/20250829080426.1441678-8-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Christoph Hellwig Reviewed-by: Xiao Ni Reviewed-by: Hannes Reinecke Reviewed-by: Li Nan --- drivers/md/md-bitmap.h | 1 + drivers/md/md.c | 7 +++++++ 2 files changed, 8 insertions(+) diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 8616ced49077..95453696c68e 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -89,6 +89,7 @@ struct bitmap_operations { md_bitmap_fn *start_discard; md_bitmap_fn *end_discard; + sector_t (*skip_sync_blocks)(struct mddev *mddev, sector_t offset); 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/md.c b/drivers/md/md.c index 51dee0a98af1..ec80c8d6cbcb 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -9460,6 +9460,12 @@ void md_do_sync(struct md_thread *thread) if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) break; + if (mddev->bitmap_ops && mddev->bitmap_ops->skip_sync_blocks) { + sectors = mddev->bitmap_ops->skip_sync_blocks(mddev, j); + if (sectors) + goto update; + } + sectors = mddev->pers->sync_request(mddev, j, max_sectors, &skipped); if (sectors == 0) { @@ -9475,6 +9481,7 @@ void md_do_sync(struct md_thread *thread) if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) break; +update: j += sectors; if (j > max_sectors) /* when skipping, extra large numbers can be returned. */ From a4dd9ba39ba4f86ae8848c63945d443f0569efb1 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:23 +0800 Subject: [PATCH 21/24] md/md-bitmap: add a new method blocks_synced() in bitmap_operations Currently, raid456 must perform a whole array initial recovery to build initail xor data, then IO to the array won't have to read all the blocks in underlying disks. This behavior will affect IO performance a lot, and nowadays there are huge disks and the initial recovery can take a long time. Hence llbitmap will support lazy initial recovery in following patches. This method is used to check if data blocks is synced or not, if not then IO will still have to read all blocks for raid456. Link: https://lore.kernel.org/linux-raid/20250829080426.1441678-9-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai --- drivers/md/md-bitmap.h | 1 + drivers/md/raid5.c | 15 +++++++++++---- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 95453696c68e..5f41724cbcd8 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -90,6 +90,7 @@ struct bitmap_operations { md_bitmap_fn *end_discard; sector_t (*skip_sync_blocks)(struct mddev *mddev, sector_t offset); + bool (*blocks_synced)(struct mddev *mddev, sector_t offset); 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/raid5.c b/drivers/md/raid5.c index 5285e72341a2..672ab226e43c 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4097,7 +4097,8 @@ static int handle_stripe_dirtying(struct r5conf *conf, int disks) { int rmw = 0, rcw = 0, i; - sector_t resync_offset = conf->mddev->resync_offset; + struct mddev *mddev = conf->mddev; + sector_t resync_offset = mddev->resync_offset; /* Check whether resync is now happening or should start. * If yes, then the array is dirty (after unclean shutdown or @@ -4116,6 +4117,12 @@ static int handle_stripe_dirtying(struct r5conf *conf, pr_debug("force RCW rmw_level=%u, resync_offset=%llu sh->sector=%llu\n", conf->rmw_level, (unsigned long long)resync_offset, (unsigned long long)sh->sector); + } else if (mddev->bitmap_ops && mddev->bitmap_ops->blocks_synced && + !mddev->bitmap_ops->blocks_synced(mddev, sh->sector)) { + /* The initial recover is not done, must read everything */ + rcw = 1; rmw = 2; + pr_debug("force RCW by lazy recovery, sh->sector=%llu\n", + sh->sector); } else for (i = disks; i--; ) { /* would I have to read this buffer for read_modify_write */ struct r5dev *dev = &sh->dev[i]; @@ -4148,7 +4155,7 @@ static int handle_stripe_dirtying(struct r5conf *conf, set_bit(STRIPE_HANDLE, &sh->state); if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_PREFER_RMW)) && rmw > 0) { /* prefer read-modify-write, but need to get some data */ - mddev_add_trace_msg(conf->mddev, "raid5 rmw %llu %d", + mddev_add_trace_msg(mddev, "raid5 rmw %llu %d", sh->sector, rmw); for (i = disks; i--; ) { @@ -4227,8 +4234,8 @@ static int handle_stripe_dirtying(struct r5conf *conf, set_bit(STRIPE_DELAYED, &sh->state); } } - if (rcw && !mddev_is_dm(conf->mddev)) - blk_add_trace_msg(conf->mddev->gendisk->queue, + if (rcw && !mddev_is_dm(mddev)) + blk_add_trace_msg(mddev->gendisk->queue, "raid5 rcw %llu %d %d %d", (unsigned long long)sh->sector, rcw, qread, test_bit(STRIPE_DELAYED, &sh->state)); From c951ccf0bf2df4f39b45dc77998dd71da7a85369 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:24 +0800 Subject: [PATCH 22/24] md: add a new recovery_flag MD_RECOVERY_LAZY_RECOVER This flag is used by llbitmap in later patches to skip raid456 initial recover and delay building initial xor data to first write. https://lore.kernel.org/linux-raid/20250829080426.1441678-10-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai --- drivers/md/md.c | 47 +++++++++++++++++++++++++++++++++++++++++++++- drivers/md/md.h | 2 ++ drivers/md/raid5.c | 19 +++++++++++++++---- 3 files changed, 63 insertions(+), 5 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index ec80c8d6cbcb..f5d002537989 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -9199,6 +9199,39 @@ static sector_t md_sync_max_sectors(struct mddev *mddev, } } +/* + * If lazy recovery is requested and all rdevs are in sync, select the rdev with + * the higest index to perfore recovery to build initial xor data, this is the + * same as old bitmap. + */ +static bool mddev_select_lazy_recover_rdev(struct mddev *mddev) +{ + struct md_rdev *recover_rdev = NULL; + struct md_rdev *rdev; + bool ret = false; + + rcu_read_lock(); + rdev_for_each_rcu(rdev, mddev) { + if (rdev->raid_disk < 0) + continue; + + if (test_bit(Faulty, &rdev->flags) || + !test_bit(In_sync, &rdev->flags)) + break; + + if (!recover_rdev || recover_rdev->raid_disk < rdev->raid_disk) + recover_rdev = rdev; + } + + if (recover_rdev) { + clear_bit(In_sync, &recover_rdev->flags); + ret = true; + } + + rcu_read_unlock(); + return ret; +} + static sector_t md_sync_position(struct mddev *mddev, enum sync_action action) { sector_t start = 0; @@ -9230,6 +9263,14 @@ static sector_t md_sync_position(struct mddev *mddev, enum sync_action action) start = rdev->recovery_offset; rcu_read_unlock(); + /* + * If there are no spares, and raid456 lazy initial recover is + * requested. + */ + if (test_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery) && + start == MaxSector && mddev_select_lazy_recover_rdev(mddev)) + start = 0; + /* If there is a bitmap, we need to make sure all * writes that started before we added a spare * complete before we start doing a recovery. @@ -9791,6 +9832,7 @@ static bool md_choose_sync_action(struct mddev *mddev, int *spares) set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); + clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery); return true; } @@ -9799,6 +9841,7 @@ static bool md_choose_sync_action(struct mddev *mddev, int *spares) remove_spares(mddev, NULL); set_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); + clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery); return true; } @@ -9808,7 +9851,7 @@ static bool md_choose_sync_action(struct mddev *mddev, int *spares) * re-add. */ *spares = remove_and_add_spares(mddev, NULL); - if (*spares) { + if (*spares || test_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery)) { clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); @@ -10021,6 +10064,7 @@ void md_check_recovery(struct mddev *mddev) } clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery); + clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery); clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags); @@ -10131,6 +10175,7 @@ void md_reap_sync_thread(struct mddev *mddev) clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); + clear_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery); /* * We call mddev->cluster_ops->update_size here because sync_size could * be changed by md_update_sb, and MD_RECOVERY_RESHAPE is cleared, diff --git a/drivers/md/md.h b/drivers/md/md.h index 4fa5a3e68a0c..7b6357879a84 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -667,6 +667,8 @@ enum recovery_flags { MD_RECOVERY_RESHAPE, /* remote node is running resync thread */ MD_RESYNCING_REMOTE, + /* raid456 lazy initial recover */ + MD_RECOVERY_LAZY_RECOVER, }; enum md_ro_state { diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 672ab226e43c..5112658ef5f6 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -4705,10 +4705,21 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) } } else if (test_bit(In_sync, &rdev->flags)) set_bit(R5_Insync, &dev->flags); - else if (sh->sector + RAID5_STRIPE_SECTORS(conf) <= rdev->recovery_offset) - /* in sync if before recovery_offset */ - set_bit(R5_Insync, &dev->flags); - else if (test_bit(R5_UPTODATE, &dev->flags) && + else if (sh->sector + RAID5_STRIPE_SECTORS(conf) <= + rdev->recovery_offset) { + /* + * in sync if: + * - normal IO, or + * - resync IO that is not lazy recovery + * + * For lazy recovery, we have to mark the rdev without + * In_sync as failed, to build initial xor data. + */ + if (!test_bit(STRIPE_SYNCING, &sh->state) || + !test_bit(MD_RECOVERY_LAZY_RECOVER, + &conf->mddev->recovery)) + set_bit(R5_Insync, &dev->flags); + } else if (test_bit(R5_UPTODATE, &dev->flags) && test_bit(R5_Expanded, &dev->flags)) /* If we've reshaped into here, we assume it is Insync. * We will shortly update recovery_offset to make From 66be318e6659d10e90f487e2610409cef659dbfe Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:25 +0800 Subject: [PATCH 23/24] md/md-bitmap: make method bitmap_ops->daemon_work optional daemon_work() will be called by daemon thread, on the one hand, daemon thread doesn't have strict wake-up time; on the other hand, too much work are put to daemon thread, like handle sync IO, handle failed or specail normal IO, handle recovery, and so on. Hence daemon thread may be too busy to clear dirty bits in time. Make bitmap_ops->daemon_work() optional and following patches will use separate async work to clear dirty bits for the new bitmap. Link: https://lore.kernel.org/linux-raid/20250829080426.1441678-11-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Li Nan --- drivers/md/md.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index f5d002537989..2f1907f3bc25 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -9997,7 +9997,7 @@ static void unregister_sync_thread(struct mddev *mddev) */ void md_check_recovery(struct mddev *mddev) { - if (md_bitmap_enabled(mddev, false)) + if (md_bitmap_enabled(mddev, false) && mddev->bitmap_ops->daemon_work) mddev->bitmap_ops->daemon_work(mddev); if (signal_pending(current)) { From 5ab829f1971dc99f2aac10846c378e67fc875abc Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Fri, 29 Aug 2025 16:04:26 +0800 Subject: [PATCH 24/24] md/md-llbitmap: introduce new lockless bitmap Redundant data is used to enhance data fault tolerance, and the storage method for redundant data vary depending on the RAID levels. And it's important to maintain the consistency of redundant data. Bitmap is used to record which data blocks have been synchronized and which ones need to be resynchronized or recovered. Each bit in the bitmap represents a segment of data in the array. When a bit is set, it indicates that the multiple redundant copies of that data segment may not be consistent. Data synchronization can be performed based on the bitmap after power failure or readding a disk. If there is no bitmap, a full disk synchronization is required. Due to known performance issues with md-bitmap and the unreasonable implementations: - self-managed IO submitting like filemap_write_page(); - global spin_lock I have decided not to continue optimizing based on the current bitmap implementation, this new bitmap is invented without locking from IO fast path and can be used with fast disks. For designs and details, see the comments in drivers/md-llbitmap.c. Link: https://lore.kernel.org/linux-raid/20250829080426.1441678-12-yukuai1@huaweicloud.com Signed-off-by: Yu Kuai Reviewed-by: Li Nan --- Documentation/admin-guide/md.rst | 20 + drivers/md/Kconfig | 11 + drivers/md/Makefile | 1 + drivers/md/md-bitmap.c | 9 - drivers/md/md-bitmap.h | 31 +- drivers/md/md-llbitmap.c | 1626 ++++++++++++++++++++++++++++++ drivers/md/md.c | 6 + drivers/md/md.h | 4 +- 8 files changed, 1696 insertions(+), 12 deletions(-) create mode 100644 drivers/md/md-llbitmap.c diff --git a/Documentation/admin-guide/md.rst b/Documentation/admin-guide/md.rst index 001363f81850..1c2eacc94758 100644 --- a/Documentation/admin-guide/md.rst +++ b/Documentation/admin-guide/md.rst @@ -387,6 +387,8 @@ All md devices contain: No bitmap bitmap The default internal bitmap + llbitmap + The lockless internal bitmap If bitmap_type is not none, then additional bitmap attributes bitmap/xxx or llbitmap/xxx will be created after md device KOBJ_CHANGE event. @@ -447,6 +449,24 @@ If bitmap_type is bitmap, then the md device will also contain: once the array becomes non-degraded, and this fact has been recorded in the metadata. +If bitmap_type is llbitmap, then the md device will also contain: + + llbitmap/bits + This is read-only, show status of bitmap bits, the number of each + value. + + llbitmap/metadata + This is read-only, show bitmap metadata, include chunksize, chunkshift, + chunks, offset and daemon_sleep. + + llbitmap/daemon_sleep + This is read-write, time in seconds that daemon function will be + triggered to clear dirty bits. + + llbitmap/barrier_idle + This is read-write, time in seconds that page barrier will be idled, + means dirty bits in the page will be cleared. + As component devices are added to an md array, they appear in the ``md`` directory as new directories named:: diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index f913579e731c..07c19b2182ca 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -52,6 +52,17 @@ config MD_BITMAP If unsure, say Y. +config MD_LLBITMAP + bool "MD RAID lockless bitmap support" + depends on BLK_DEV_MD + help + If you say Y here, support for the lockless write intent bitmap will + be enabled. + + Note, this is an experimental feature. + + If unsure, say N. + config MD_AUTODETECT bool "Autodetect RAID arrays during kernel boot" depends on BLK_DEV_MD=y diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 2e18147a9c40..5a51b3408b70 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -29,6 +29,7 @@ dm-zoned-y += dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o md-mod-y += md.o md-mod-$(CONFIG_MD_BITMAP) += md-bitmap.o +md-mod-$(CONFIG_MD_LLBITMAP) += md-llbitmap.o raid456-y += raid5.o raid5-cache.o raid5-ppl.o linear-y += md-linear.o diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index dc050ff94d5b..84b7e2af6dba 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -34,15 +34,6 @@ #include "md-bitmap.h" #include "md-cluster.h" -#define BITMAP_MAJOR_LO 3 -/* version 4 insists the bitmap is in little-endian order - * with version 3, it is host-endian which is non-portable - * Version 5 is currently set only for clustered devices - */ -#define BITMAP_MAJOR_HI 4 -#define BITMAP_MAJOR_CLUSTERED 5 -#define BITMAP_MAJOR_HOSTENDIAN 3 - /* * in-memory bitmap: * diff --git a/drivers/md/md-bitmap.h b/drivers/md/md-bitmap.h index 5f41724cbcd8..b42a28fa83a0 100644 --- a/drivers/md/md-bitmap.h +++ b/drivers/md/md-bitmap.h @@ -9,10 +9,26 @@ #define BITMAP_MAGIC 0x6d746962 +/* + * version 3 is host-endian order, this is deprecated and not used for new + * array + */ +#define BITMAP_MAJOR_LO 3 +#define BITMAP_MAJOR_HOSTENDIAN 3 +/* version 4 is little-endian order, the default value */ +#define BITMAP_MAJOR_HI 4 +/* version 5 is only used for cluster */ +#define BITMAP_MAJOR_CLUSTERED 5 +/* version 6 is only used for lockless bitmap */ +#define BITMAP_MAJOR_LOCKLESS 6 + /* use these for bitmap->flags and bitmap->sb->state bit-fields */ enum bitmap_state { - BITMAP_STALE = 1, /* the bitmap file is out of date or had -EIO */ + BITMAP_STALE = 1, /* the bitmap file is out of date or had -EIO */ BITMAP_WRITE_ERROR = 2, /* A write error has occurred */ + BITMAP_FIRST_USE = 3, /* llbitmap is just created */ + BITMAP_CLEAN = 4, /* llbitmap is created with assume_clean */ + BITMAP_DAEMON_BUSY = 5, /* llbitmap daemon is not finished after daemon_sleep */ BITMAP_HOSTENDIAN =15, }; @@ -166,4 +182,17 @@ static inline void md_bitmap_exit(void) } #endif +#ifdef CONFIG_MD_LLBITMAP +int md_llbitmap_init(void); +void md_llbitmap_exit(void); +#else +static inline int md_llbitmap_init(void) +{ + return 0; +} +static inline void md_llbitmap_exit(void) +{ +} +#endif + #endif diff --git a/drivers/md/md-llbitmap.c b/drivers/md/md-llbitmap.c new file mode 100644 index 000000000000..3337d5c7e7e5 --- /dev/null +++ b/drivers/md/md-llbitmap.c @@ -0,0 +1,1626 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "md.h" +#include "md-bitmap.h" + +/* + * #### Background + * + * Redundant data is used to enhance data fault tolerance, and the storage + * methods for redundant data vary depending on the RAID levels. And it's + * important to maintain the consistency of redundant data. + * + * Bitmap is used to record which data blocks have been synchronized and which + * ones need to be resynchronized or recovered. Each bit in the bitmap + * represents a segment of data in the array. When a bit is set, it indicates + * that the multiple redundant copies of that data segment may not be + * consistent. Data synchronization can be performed based on the bitmap after + * power failure or readding a disk. If there is no bitmap, a full disk + * synchronization is required. + * + * #### Key Features + * + * - IO fastpath is lockless, if user issues lots of write IO to the same + * bitmap bit in a short time, only the first write has additional overhead + * to update bitmap bit, no additional overhead for the following writes; + * - support only resync or recover written data, means in the case creating + * new array or replacing with a new disk, there is no need to do a full disk + * resync/recovery; + * + * #### Key Concept + * + * ##### State Machine + * + * Each bit is one byte, contain 6 different states, see llbitmap_state. And + * there are total 8 different actions, see llbitmap_action, can change state: + * + * llbitmap state machine: transitions between states + * + * | | Startwrite | Startsync | Endsync | Abortsync| + * | --------- | ---------- | --------- | ------- | ------- | + * | Unwritten | Dirty | x | x | x | + * | Clean | Dirty | x | x | x | + * | Dirty | x | x | x | x | + * | NeedSync | x | Syncing | x | x | + * | Syncing | x | Syncing | Dirty | NeedSync | + * + * | | Reload | Daemon | Discard | Stale | + * | --------- | -------- | ------ | --------- | --------- | + * | Unwritten | x | x | x | x | + * | Clean | x | x | Unwritten | NeedSync | + * | Dirty | NeedSync | Clean | Unwritten | NeedSync | + * | NeedSync | x | x | Unwritten | x | + * | Syncing | NeedSync | x | Unwritten | NeedSync | + * + * Typical scenarios: + * + * 1) Create new array + * All bits will be set to Unwritten by default, if --assume-clean is set, + * all bits will be set to Clean instead. + * + * 2) write data, raid1/raid10 have full copy of data, while raid456 doesn't and + * rely on xor data + * + * 2.1) write new data to raid1/raid10: + * Unwritten --StartWrite--> Dirty + * + * 2.2) write new data to raid456: + * Unwritten --StartWrite--> NeedSync + * + * Because the initial recover for raid456 is skipped, the xor data is not built + * yet, the bit must be set to NeedSync first and after lazy initial recover is + * finished, the bit will finally set to Dirty(see 5.1 and 5.4); + * + * 2.3) cover write + * Clean --StartWrite--> Dirty + * + * 3) daemon, if the array is not degraded: + * Dirty --Daemon--> Clean + * + * 4) discard + * {Clean, Dirty, NeedSync, Syncing} --Discard--> Unwritten + * + * 5) resync and recover + * + * 5.1) common process + * NeedSync --Startsync--> Syncing --Endsync--> Dirty --Daemon--> Clean + * + * 5.2) resync after power failure + * Dirty --Reload--> NeedSync + * + * 5.3) recover while replacing with a new disk + * By default, the old bitmap framework will recover all data, and llbitmap + * implements this by a new helper, see llbitmap_skip_sync_blocks: + * + * skip recover for bits other than dirty or clean; + * + * 5.4) lazy initial recover for raid5: + * By default, the old bitmap framework will only allow new recover when there + * are spares(new disk), a new recovery flag MD_RECOVERY_LAZY_RECOVER is added + * to perform raid456 lazy recover for set bits(from 2.2). + * + * 6. special handling for degraded array: + * + * - Dirty bits will never be cleared, daemon will just do nothing, so that if + * a disk is readded, Clean bits can be skipped with recovery; + * - Dirty bits will convert to Syncing from start write, to do data recovery + * for new added disks; + * - New write will convert bits to NeedSync directly; + * + * ##### Bitmap IO + * + * ##### Chunksize + * + * The default bitmap size is 128k, incluing 1k bitmap super block, and + * the default size of segment of data in the array each bit(chunksize) is 64k, + * and chunksize will adjust to twice the old size each time if the total number + * bits is not less than 127k.(see llbitmap_init) + * + * ##### READ + * + * While creating bitmap, all pages will be allocated and read for llbitmap, + * there won't be read afterwards + * + * ##### WRITE + * + * WRITE IO is divided into logical_block_size of the array, the dirty state + * of each block is tracked independently, for example: + * + * each page is 4k, contain 8 blocks; each block is 512 bytes contain 512 bit; + * + * | page0 | page1 | ... | page 31 | + * | | + * | \-----------------------\ + * | | + * | block0 | block1 | ... | block 8| + * | | + * | \-----------------\ + * | | + * | bit0 | bit1 | ... | bit511 | + * + * From IO path, if one bit is changed to Dirty or NeedSync, the corresponding + * subpage will be marked dirty, such block must write first before the IO is + * issued. This behaviour will affect IO performance, to reduce the impact, if + * multiple bits are changed in the same block in a short time, all bits in this + * block will be changed to Dirty/NeedSync, so that there won't be any overhead + * until daemon clears dirty bits. + * + * ##### Dirty Bits synchronization + * + * IO fast path will set bits to dirty, and those dirty bits will be cleared + * by daemon after IO is done. llbitmap_page_ctl is used to synchronize between + * IO path and daemon; + * + * IO path: + * 1) try to grab a reference, if succeed, set expire time after 5s and return; + * 2) if failed to grab a reference, wait for daemon to finish clearing dirty + * bits; + * + * Daemon (Daemon will be woken up every daemon_sleep seconds): + * For each page: + * 1) check if page expired, if not skip this page; for expired page: + * 2) suspend the page and wait for inflight write IO to be done; + * 3) change dirty page to clean; + * 4) resume the page; + */ + +#define BITMAP_DATA_OFFSET 1024 + +/* 64k is the max IO size of sync IO for raid1/raid10 */ +#define MIN_CHUNK_SIZE (64 * 2) + +/* By default, daemon will be woken up every 30s */ +#define DEFAULT_DAEMON_SLEEP 30 + +/* + * Dirtied bits that have not been accessed for more than 5s will be cleared + * by daemon. + */ +#define DEFAULT_BARRIER_IDLE 5 + +enum llbitmap_state { + /* No valid data, init state after assemble the array */ + BitUnwritten = 0, + /* data is consistent */ + BitClean, + /* data will be consistent after IO is done, set directly for writes */ + BitDirty, + /* + * data need to be resynchronized: + * 1) set directly for writes if array is degraded, prevent full disk + * synchronization after readding a disk; + * 2) reassemble the array after power failure, and dirty bits are + * found after reloading the bitmap; + * 3) set for first write for raid5, to build initial xor data lazily + */ + BitNeedSync, + /* data is synchronizing */ + BitSyncing, + BitStateCount, + BitNone = 0xff, +}; + +enum llbitmap_action { + /* User write new data, this is the only action from IO fast path */ + BitmapActionStartwrite = 0, + /* Start recovery */ + BitmapActionStartsync, + /* Finish recovery */ + BitmapActionEndsync, + /* Failed recovery */ + BitmapActionAbortsync, + /* Reassemble the array */ + BitmapActionReload, + /* Daemon thread is trying to clear dirty bits */ + BitmapActionDaemon, + /* Data is deleted */ + BitmapActionDiscard, + /* + * Bitmap is stale, mark all bits in addition to BitUnwritten to + * BitNeedSync. + */ + BitmapActionStale, + BitmapActionCount, + /* Init state is BitUnwritten */ + BitmapActionInit, +}; + +enum llbitmap_page_state { + LLPageFlush = 0, + LLPageDirty, +}; + +struct llbitmap_page_ctl { + char *state; + struct page *page; + unsigned long expire; + unsigned long flags; + wait_queue_head_t wait; + struct percpu_ref active; + /* Per block size dirty state, maximum 64k page / 1 sector = 128 */ + unsigned long dirty[]; +}; + +struct llbitmap { + struct mddev *mddev; + struct llbitmap_page_ctl **pctl; + + unsigned int nr_pages; + unsigned int io_size; + unsigned int blocks_per_page; + + /* shift of one chunk */ + unsigned long chunkshift; + /* size of one chunk in sector */ + unsigned long chunksize; + /* total number of chunks */ + unsigned long chunks; + unsigned long last_end_sync; + /* + * time in seconds that dirty bits will be cleared if the page is not + * accessed. + */ + unsigned long barrier_idle; + /* fires on first BitDirty state */ + struct timer_list pending_timer; + struct work_struct daemon_work; + + unsigned long flags; + __u64 events_cleared; + + /* for slow disks */ + atomic_t behind_writes; + wait_queue_head_t behind_wait; +}; + +struct llbitmap_unplug_work { + struct work_struct work; + struct llbitmap *llbitmap; + struct completion *done; +}; + +static struct workqueue_struct *md_llbitmap_io_wq; +static struct workqueue_struct *md_llbitmap_unplug_wq; + +static char state_machine[BitStateCount][BitmapActionCount] = { + [BitUnwritten] = { + [BitmapActionStartwrite] = BitDirty, + [BitmapActionStartsync] = BitNone, + [BitmapActionEndsync] = BitNone, + [BitmapActionAbortsync] = BitNone, + [BitmapActionReload] = BitNone, + [BitmapActionDaemon] = BitNone, + [BitmapActionDiscard] = BitNone, + [BitmapActionStale] = BitNone, + }, + [BitClean] = { + [BitmapActionStartwrite] = BitDirty, + [BitmapActionStartsync] = BitNone, + [BitmapActionEndsync] = BitNone, + [BitmapActionAbortsync] = BitNone, + [BitmapActionReload] = BitNone, + [BitmapActionDaemon] = BitNone, + [BitmapActionDiscard] = BitUnwritten, + [BitmapActionStale] = BitNeedSync, + }, + [BitDirty] = { + [BitmapActionStartwrite] = BitNone, + [BitmapActionStartsync] = BitNone, + [BitmapActionEndsync] = BitNone, + [BitmapActionAbortsync] = BitNone, + [BitmapActionReload] = BitNeedSync, + [BitmapActionDaemon] = BitClean, + [BitmapActionDiscard] = BitUnwritten, + [BitmapActionStale] = BitNeedSync, + }, + [BitNeedSync] = { + [BitmapActionStartwrite] = BitNone, + [BitmapActionStartsync] = BitSyncing, + [BitmapActionEndsync] = BitNone, + [BitmapActionAbortsync] = BitNone, + [BitmapActionReload] = BitNone, + [BitmapActionDaemon] = BitNone, + [BitmapActionDiscard] = BitUnwritten, + [BitmapActionStale] = BitNone, + }, + [BitSyncing] = { + [BitmapActionStartwrite] = BitNone, + [BitmapActionStartsync] = BitSyncing, + [BitmapActionEndsync] = BitDirty, + [BitmapActionAbortsync] = BitNeedSync, + [BitmapActionReload] = BitNeedSync, + [BitmapActionDaemon] = BitNone, + [BitmapActionDiscard] = BitUnwritten, + [BitmapActionStale] = BitNeedSync, + }, +}; + +static void __llbitmap_flush(struct mddev *mddev); + +static enum llbitmap_state llbitmap_read(struct llbitmap *llbitmap, loff_t pos) +{ + unsigned int idx; + unsigned int offset; + + pos += BITMAP_DATA_OFFSET; + idx = pos >> PAGE_SHIFT; + offset = offset_in_page(pos); + + return llbitmap->pctl[idx]->state[offset]; +} + +/* set all the bits in the subpage as dirty */ +static void llbitmap_infect_dirty_bits(struct llbitmap *llbitmap, + struct llbitmap_page_ctl *pctl, + unsigned int block) +{ + bool level_456 = raid_is_456(llbitmap->mddev); + unsigned int io_size = llbitmap->io_size; + int pos; + + for (pos = block * io_size; pos < (block + 1) * io_size; pos++) { + switch (pctl->state[pos]) { + case BitUnwritten: + pctl->state[pos] = level_456 ? BitNeedSync : BitDirty; + break; + case BitClean: + pctl->state[pos] = BitDirty; + break; + }; + } +} + +static void llbitmap_set_page_dirty(struct llbitmap *llbitmap, int idx, + int offset) +{ + struct llbitmap_page_ctl *pctl = llbitmap->pctl[idx]; + unsigned int io_size = llbitmap->io_size; + int block = offset / io_size; + int pos; + + if (!test_bit(LLPageDirty, &pctl->flags)) + set_bit(LLPageDirty, &pctl->flags); + + /* + * For degraded array, dirty bits will never be cleared, and we must + * resync all the dirty bits, hence skip infect new dirty bits to + * prevent resync unnecessary data. + */ + if (llbitmap->mddev->degraded) { + set_bit(block, pctl->dirty); + return; + } + + /* + * The subpage usually contains a total of 512 bits. If any single bit + * within the subpage is marked as dirty, the entire sector will be + * written. To avoid impacting write performance, when multiple bits + * within the same sector are modified within llbitmap->barrier_idle, + * all bits in the sector will be collectively marked as dirty at once. + */ + if (test_and_set_bit(block, pctl->dirty)) { + llbitmap_infect_dirty_bits(llbitmap, pctl, block); + return; + } + + for (pos = block * io_size; pos < (block + 1) * io_size; pos++) { + if (pos == offset) + continue; + if (pctl->state[pos] == BitDirty || + pctl->state[pos] == BitNeedSync) { + llbitmap_infect_dirty_bits(llbitmap, pctl, block); + return; + } + } +} + +static void llbitmap_write(struct llbitmap *llbitmap, enum llbitmap_state state, + loff_t pos) +{ + unsigned int idx; + unsigned int bit; + + pos += BITMAP_DATA_OFFSET; + idx = pos >> PAGE_SHIFT; + bit = offset_in_page(pos); + + llbitmap->pctl[idx]->state[bit] = state; + if (state == BitDirty || state == BitNeedSync) + llbitmap_set_page_dirty(llbitmap, idx, bit); +} + +static struct page *llbitmap_read_page(struct llbitmap *llbitmap, int idx) +{ + struct mddev *mddev = llbitmap->mddev; + struct page *page = NULL; + struct md_rdev *rdev; + + if (llbitmap->pctl && llbitmap->pctl[idx]) + page = llbitmap->pctl[idx]->page; + if (page) + return page; + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!page) + return ERR_PTR(-ENOMEM); + + rdev_for_each(rdev, mddev) { + sector_t sector; + + if (rdev->raid_disk < 0 || test_bit(Faulty, &rdev->flags)) + continue; + + sector = mddev->bitmap_info.offset + + (idx << PAGE_SECTORS_SHIFT); + + if (sync_page_io(rdev, sector, PAGE_SIZE, page, REQ_OP_READ, + true)) + return page; + + md_error(mddev, rdev); + } + + __free_page(page); + return ERR_PTR(-EIO); +} + +static void llbitmap_write_page(struct llbitmap *llbitmap, int idx) +{ + struct page *page = llbitmap->pctl[idx]->page; + struct mddev *mddev = llbitmap->mddev; + struct md_rdev *rdev; + int block; + + for (block = 0; block < llbitmap->blocks_per_page; block++) { + struct llbitmap_page_ctl *pctl = llbitmap->pctl[idx]; + + if (!test_and_clear_bit(block, pctl->dirty)) + continue; + + rdev_for_each(rdev, mddev) { + sector_t sector; + sector_t bit_sector = llbitmap->io_size >> SECTOR_SHIFT; + + if (rdev->raid_disk < 0 || test_bit(Faulty, &rdev->flags)) + continue; + + sector = mddev->bitmap_info.offset + rdev->sb_start + + (idx << PAGE_SECTORS_SHIFT) + + block * bit_sector; + md_write_metadata(mddev, rdev, sector, + llbitmap->io_size, page, + block * llbitmap->io_size); + } + } +} + +static void active_release(struct percpu_ref *ref) +{ + struct llbitmap_page_ctl *pctl = + container_of(ref, struct llbitmap_page_ctl, active); + + wake_up(&pctl->wait); +} + +static void llbitmap_free_pages(struct llbitmap *llbitmap) +{ + int i; + + if (!llbitmap->pctl) + return; + + for (i = 0; i < llbitmap->nr_pages; i++) { + struct llbitmap_page_ctl *pctl = llbitmap->pctl[i]; + + if (!pctl || !pctl->page) + break; + + __free_page(pctl->page); + percpu_ref_exit(&pctl->active); + } + + kfree(llbitmap->pctl[0]); + kfree(llbitmap->pctl); + llbitmap->pctl = NULL; +} + +static int llbitmap_cache_pages(struct llbitmap *llbitmap) +{ + struct llbitmap_page_ctl *pctl; + unsigned int nr_pages = DIV_ROUND_UP(llbitmap->chunks + + BITMAP_DATA_OFFSET, PAGE_SIZE); + unsigned int size = struct_size(pctl, dirty, BITS_TO_LONGS( + llbitmap->blocks_per_page)); + int i; + + llbitmap->pctl = kmalloc_array(nr_pages, sizeof(void *), + GFP_KERNEL | __GFP_ZERO); + if (!llbitmap->pctl) + return -ENOMEM; + + size = round_up(size, cache_line_size()); + pctl = kmalloc_array(nr_pages, size, GFP_KERNEL | __GFP_ZERO); + if (!pctl) { + kfree(llbitmap->pctl); + return -ENOMEM; + } + + llbitmap->nr_pages = nr_pages; + + for (i = 0; i < nr_pages; i++, pctl = (void *)pctl + size) { + struct page *page = llbitmap_read_page(llbitmap, i); + + llbitmap->pctl[i] = pctl; + + if (IS_ERR(page)) { + llbitmap_free_pages(llbitmap); + return PTR_ERR(page); + } + + if (percpu_ref_init(&pctl->active, active_release, + PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) { + __free_page(page); + llbitmap_free_pages(llbitmap); + return -ENOMEM; + } + + pctl->page = page; + pctl->state = page_address(page); + init_waitqueue_head(&pctl->wait); + } + + return 0; +} + +static void llbitmap_init_state(struct llbitmap *llbitmap) +{ + enum llbitmap_state state = BitUnwritten; + unsigned long i; + + if (test_and_clear_bit(BITMAP_CLEAN, &llbitmap->flags)) + state = BitClean; + + for (i = 0; i < llbitmap->chunks; i++) + llbitmap_write(llbitmap, state, i); +} + +/* The return value is only used from resync, where @start == @end. */ +static enum llbitmap_state llbitmap_state_machine(struct llbitmap *llbitmap, + unsigned long start, + unsigned long end, + enum llbitmap_action action) +{ + struct mddev *mddev = llbitmap->mddev; + enum llbitmap_state state = BitNone; + bool level_456 = raid_is_456(llbitmap->mddev); + bool need_resync = false; + bool need_recovery = false; + + if (test_bit(BITMAP_WRITE_ERROR, &llbitmap->flags)) + return BitNone; + + if (action == BitmapActionInit) { + llbitmap_init_state(llbitmap); + return BitNone; + } + + while (start <= end) { + enum llbitmap_state c = llbitmap_read(llbitmap, start); + + if (c < 0 || c >= BitStateCount) { + pr_err("%s: invalid bit %lu state %d action %d, forcing resync\n", + __func__, start, c, action); + state = BitNeedSync; + goto write_bitmap; + } + + if (c == BitNeedSync) + need_resync = !mddev->degraded; + + state = state_machine[c][action]; + +write_bitmap: + if (unlikely(mddev->degraded)) { + /* For degraded array, mark new data as need sync. */ + if (state == BitDirty && + action == BitmapActionStartwrite) + state = BitNeedSync; + /* + * For degraded array, resync dirty data as well, noted + * if array is still degraded after resync is done, all + * new data will still be dirty until array is clean. + */ + else if (c == BitDirty && + action == BitmapActionStartsync) + state = BitSyncing; + } else if (c == BitUnwritten && state == BitDirty && + action == BitmapActionStartwrite && level_456) { + /* Delay raid456 initial recovery to first write. */ + state = BitNeedSync; + } + + if (state == BitNone) { + start++; + continue; + } + + llbitmap_write(llbitmap, state, start); + + if (state == BitNeedSync) + need_resync = !mddev->degraded; + else if (state == BitDirty && + !timer_pending(&llbitmap->pending_timer)) + mod_timer(&llbitmap->pending_timer, + jiffies + mddev->bitmap_info.daemon_sleep * HZ); + + start++; + } + + if (need_resync && level_456) + need_recovery = true; + + if (need_recovery) { + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + set_bit(MD_RECOVERY_LAZY_RECOVER, &mddev->recovery); + md_wakeup_thread(mddev->thread); + } else if (need_resync) { + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + set_bit(MD_RECOVERY_SYNC, &mddev->recovery); + md_wakeup_thread(mddev->thread); + } + + return state; +} + +static void llbitmap_raise_barrier(struct llbitmap *llbitmap, int page_idx) +{ + struct llbitmap_page_ctl *pctl = llbitmap->pctl[page_idx]; + +retry: + if (likely(percpu_ref_tryget_live(&pctl->active))) { + WRITE_ONCE(pctl->expire, jiffies + llbitmap->barrier_idle * HZ); + return; + } + + wait_event(pctl->wait, !percpu_ref_is_dying(&pctl->active)); + goto retry; +} + +static void llbitmap_release_barrier(struct llbitmap *llbitmap, int page_idx) +{ + struct llbitmap_page_ctl *pctl = llbitmap->pctl[page_idx]; + + percpu_ref_put(&pctl->active); +} + +static int llbitmap_suspend_timeout(struct llbitmap *llbitmap, int page_idx) +{ + struct llbitmap_page_ctl *pctl = llbitmap->pctl[page_idx]; + + percpu_ref_kill(&pctl->active); + + if (!wait_event_timeout(pctl->wait, percpu_ref_is_zero(&pctl->active), + llbitmap->mddev->bitmap_info.daemon_sleep * HZ)) + return -ETIMEDOUT; + + return 0; +} + +static void llbitmap_resume(struct llbitmap *llbitmap, int page_idx) +{ + struct llbitmap_page_ctl *pctl = llbitmap->pctl[page_idx]; + + pctl->expire = LONG_MAX; + percpu_ref_resurrect(&pctl->active); + wake_up(&pctl->wait); +} + +static int llbitmap_check_support(struct mddev *mddev) +{ + if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) { + pr_notice("md/llbitmap: %s: array with journal cannot have bitmap\n", + mdname(mddev)); + return -EBUSY; + } + + if (mddev->bitmap_info.space == 0) { + if (mddev->bitmap_info.default_space == 0) { + pr_notice("md/llbitmap: %s: no space for bitmap\n", + mdname(mddev)); + return -ENOSPC; + } + } + + if (!mddev->persistent) { + pr_notice("md/llbitmap: %s: array must be persistent\n", + mdname(mddev)); + return -EOPNOTSUPP; + } + + if (mddev->bitmap_info.file) { + pr_notice("md/llbitmap: %s: doesn't support bitmap file\n", + mdname(mddev)); + return -EOPNOTSUPP; + } + + if (mddev->bitmap_info.external) { + pr_notice("md/llbitmap: %s: doesn't support external metadata\n", + mdname(mddev)); + return -EOPNOTSUPP; + } + + if (mddev_is_dm(mddev)) { + pr_notice("md/llbitmap: %s: doesn't support dm-raid\n", + mdname(mddev)); + return -EOPNOTSUPP; + } + + return 0; +} + +static int llbitmap_init(struct llbitmap *llbitmap) +{ + struct mddev *mddev = llbitmap->mddev; + sector_t blocks = mddev->resync_max_sectors; + unsigned long chunksize = MIN_CHUNK_SIZE; + unsigned long chunks = DIV_ROUND_UP(blocks, chunksize); + unsigned long space = mddev->bitmap_info.space << SECTOR_SHIFT; + int ret; + + while (chunks > space) { + chunksize = chunksize << 1; + chunks = DIV_ROUND_UP(blocks, chunksize); + } + + llbitmap->barrier_idle = DEFAULT_BARRIER_IDLE; + llbitmap->chunkshift = ffz(~chunksize); + llbitmap->chunksize = chunksize; + llbitmap->chunks = chunks; + mddev->bitmap_info.daemon_sleep = DEFAULT_DAEMON_SLEEP; + + ret = llbitmap_cache_pages(llbitmap); + if (ret) + return ret; + + llbitmap_state_machine(llbitmap, 0, llbitmap->chunks - 1, + BitmapActionInit); + /* flush initial llbitmap to disk */ + __llbitmap_flush(mddev); + + return 0; +} + +static int llbitmap_read_sb(struct llbitmap *llbitmap) +{ + struct mddev *mddev = llbitmap->mddev; + unsigned long daemon_sleep; + unsigned long chunksize; + unsigned long events; + struct page *sb_page; + bitmap_super_t *sb; + int ret = -EINVAL; + + if (!mddev->bitmap_info.offset) { + pr_err("md/llbitmap: %s: no super block found", mdname(mddev)); + return -EINVAL; + } + + sb_page = llbitmap_read_page(llbitmap, 0); + if (IS_ERR(sb_page)) { + pr_err("md/llbitmap: %s: read super block failed", + mdname(mddev)); + return -EIO; + } + + sb = kmap_local_page(sb_page); + if (sb->magic != cpu_to_le32(BITMAP_MAGIC)) { + pr_err("md/llbitmap: %s: invalid super block magic number", + mdname(mddev)); + goto out_put_page; + } + + if (sb->version != cpu_to_le32(BITMAP_MAJOR_LOCKLESS)) { + pr_err("md/llbitmap: %s: invalid super block version", + mdname(mddev)); + goto out_put_page; + } + + if (memcmp(sb->uuid, mddev->uuid, 16)) { + pr_err("md/llbitmap: %s: bitmap superblock UUID mismatch\n", + mdname(mddev)); + goto out_put_page; + } + + if (mddev->bitmap_info.space == 0) { + int room = le32_to_cpu(sb->sectors_reserved); + + if (room) + mddev->bitmap_info.space = room; + else + mddev->bitmap_info.space = mddev->bitmap_info.default_space; + } + llbitmap->flags = le32_to_cpu(sb->state); + if (test_and_clear_bit(BITMAP_FIRST_USE, &llbitmap->flags)) { + ret = llbitmap_init(llbitmap); + goto out_put_page; + } + + chunksize = le32_to_cpu(sb->chunksize); + if (!is_power_of_2(chunksize)) { + pr_err("md/llbitmap: %s: chunksize not a power of 2", + mdname(mddev)); + goto out_put_page; + } + + if (chunksize < DIV_ROUND_UP(mddev->resync_max_sectors, + mddev->bitmap_info.space << SECTOR_SHIFT)) { + pr_err("md/llbitmap: %s: chunksize too small %lu < %llu / %lu", + mdname(mddev), chunksize, mddev->resync_max_sectors, + mddev->bitmap_info.space); + goto out_put_page; + } + + daemon_sleep = le32_to_cpu(sb->daemon_sleep); + if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT / HZ) { + pr_err("md/llbitmap: %s: daemon sleep %lu period out of range", + mdname(mddev), daemon_sleep); + goto out_put_page; + } + + events = le64_to_cpu(sb->events); + if (events < mddev->events) { + pr_warn("md/llbitmap :%s: bitmap file is out of date (%lu < %llu) -- forcing full recovery", + mdname(mddev), events, mddev->events); + set_bit(BITMAP_STALE, &llbitmap->flags); + } + + sb->sync_size = cpu_to_le64(mddev->resync_max_sectors); + mddev->bitmap_info.chunksize = chunksize; + mddev->bitmap_info.daemon_sleep = daemon_sleep; + + llbitmap->barrier_idle = DEFAULT_BARRIER_IDLE; + llbitmap->chunksize = chunksize; + llbitmap->chunks = DIV_ROUND_UP(mddev->resync_max_sectors, chunksize); + llbitmap->chunkshift = ffz(~chunksize); + ret = llbitmap_cache_pages(llbitmap); + +out_put_page: + __free_page(sb_page); + kunmap_local(sb); + return ret; +} + +static void llbitmap_pending_timer_fn(struct timer_list *pending_timer) +{ + struct llbitmap *llbitmap = + container_of(pending_timer, struct llbitmap, pending_timer); + + if (work_busy(&llbitmap->daemon_work)) { + pr_warn("md/llbitmap: %s daemon_work not finished in %lu seconds\n", + mdname(llbitmap->mddev), + llbitmap->mddev->bitmap_info.daemon_sleep); + set_bit(BITMAP_DAEMON_BUSY, &llbitmap->flags); + return; + } + + queue_work(md_llbitmap_io_wq, &llbitmap->daemon_work); +} + +static void md_llbitmap_daemon_fn(struct work_struct *work) +{ + struct llbitmap *llbitmap = + container_of(work, struct llbitmap, daemon_work); + unsigned long start; + unsigned long end; + bool restart; + int idx; + + if (llbitmap->mddev->degraded) + return; +retry: + start = 0; + end = min(llbitmap->chunks, PAGE_SIZE - BITMAP_DATA_OFFSET) - 1; + restart = false; + + for (idx = 0; idx < llbitmap->nr_pages; idx++) { + struct llbitmap_page_ctl *pctl = llbitmap->pctl[idx]; + + if (idx > 0) { + start = end + 1; + end = min(end + PAGE_SIZE, llbitmap->chunks - 1); + } + + if (!test_bit(LLPageFlush, &pctl->flags) && + time_before(jiffies, pctl->expire)) { + restart = true; + continue; + } + + if (llbitmap_suspend_timeout(llbitmap, idx) < 0) { + pr_warn("md/llbitmap: %s: %s waiting for page %d timeout\n", + mdname(llbitmap->mddev), __func__, idx); + continue; + } + + llbitmap_state_machine(llbitmap, start, end, BitmapActionDaemon); + llbitmap_resume(llbitmap, idx); + } + + /* + * If the daemon took a long time to finish, retry to prevent missing + * clearing dirty bits. + */ + if (test_and_clear_bit(BITMAP_DAEMON_BUSY, &llbitmap->flags)) + goto retry; + + /* If some page is dirty but not expired, setup timer again */ + if (restart) + mod_timer(&llbitmap->pending_timer, + jiffies + llbitmap->mddev->bitmap_info.daemon_sleep * HZ); +} + +static int llbitmap_create(struct mddev *mddev) +{ + struct llbitmap *llbitmap; + int ret; + + ret = llbitmap_check_support(mddev); + if (ret) + return ret; + + llbitmap = kzalloc(sizeof(*llbitmap), GFP_KERNEL); + if (!llbitmap) + return -ENOMEM; + + llbitmap->mddev = mddev; + llbitmap->io_size = bdev_logical_block_size(mddev->gendisk->part0); + llbitmap->blocks_per_page = PAGE_SIZE / llbitmap->io_size; + + timer_setup(&llbitmap->pending_timer, llbitmap_pending_timer_fn, 0); + INIT_WORK(&llbitmap->daemon_work, md_llbitmap_daemon_fn); + atomic_set(&llbitmap->behind_writes, 0); + init_waitqueue_head(&llbitmap->behind_wait); + + mutex_lock(&mddev->bitmap_info.mutex); + mddev->bitmap = llbitmap; + ret = llbitmap_read_sb(llbitmap); + mutex_unlock(&mddev->bitmap_info.mutex); + if (ret) { + kfree(llbitmap); + mddev->bitmap = NULL; + } + + return ret; +} + +static int llbitmap_resize(struct mddev *mddev, sector_t blocks, int chunksize) +{ + struct llbitmap *llbitmap = mddev->bitmap; + unsigned long chunks; + + if (chunksize == 0) + chunksize = llbitmap->chunksize; + + /* If there is enough space, leave the chunksize unchanged. */ + chunks = DIV_ROUND_UP(blocks, chunksize); + while (chunks > mddev->bitmap_info.space << SECTOR_SHIFT) { + chunksize = chunksize << 1; + chunks = DIV_ROUND_UP(blocks, chunksize); + } + + llbitmap->chunkshift = ffz(~chunksize); + llbitmap->chunksize = chunksize; + llbitmap->chunks = chunks; + + return 0; +} + +static int llbitmap_load(struct mddev *mddev) +{ + enum llbitmap_action action = BitmapActionReload; + struct llbitmap *llbitmap = mddev->bitmap; + + if (test_and_clear_bit(BITMAP_STALE, &llbitmap->flags)) + action = BitmapActionStale; + + llbitmap_state_machine(llbitmap, 0, llbitmap->chunks - 1, action); + return 0; +} + +static void llbitmap_destroy(struct mddev *mddev) +{ + struct llbitmap *llbitmap = mddev->bitmap; + + if (!llbitmap) + return; + + mutex_lock(&mddev->bitmap_info.mutex); + + timer_delete_sync(&llbitmap->pending_timer); + flush_workqueue(md_llbitmap_io_wq); + flush_workqueue(md_llbitmap_unplug_wq); + + mddev->bitmap = NULL; + llbitmap_free_pages(llbitmap); + kfree(llbitmap); + mutex_unlock(&mddev->bitmap_info.mutex); +} + +static void llbitmap_start_write(struct mddev *mddev, sector_t offset, + unsigned long sectors) +{ + struct llbitmap *llbitmap = mddev->bitmap; + unsigned long start = offset >> llbitmap->chunkshift; + unsigned long end = (offset + sectors - 1) >> llbitmap->chunkshift; + int page_start = (start + BITMAP_DATA_OFFSET) >> PAGE_SHIFT; + int page_end = (end + BITMAP_DATA_OFFSET) >> PAGE_SHIFT; + + llbitmap_state_machine(llbitmap, start, end, BitmapActionStartwrite); + + while (page_start <= page_end) { + llbitmap_raise_barrier(llbitmap, page_start); + page_start++; + } +} + +static void llbitmap_end_write(struct mddev *mddev, sector_t offset, + unsigned long sectors) +{ + struct llbitmap *llbitmap = mddev->bitmap; + unsigned long start = offset >> llbitmap->chunkshift; + unsigned long end = (offset + sectors - 1) >> llbitmap->chunkshift; + int page_start = (start + BITMAP_DATA_OFFSET) >> PAGE_SHIFT; + int page_end = (end + BITMAP_DATA_OFFSET) >> PAGE_SHIFT; + + while (page_start <= page_end) { + llbitmap_release_barrier(llbitmap, page_start); + page_start++; + } +} + +static void llbitmap_start_discard(struct mddev *mddev, sector_t offset, + unsigned long sectors) +{ + struct llbitmap *llbitmap = mddev->bitmap; + unsigned long start = DIV_ROUND_UP(offset, llbitmap->chunksize); + unsigned long end = (offset + sectors - 1) >> llbitmap->chunkshift; + int page_start = (start + BITMAP_DATA_OFFSET) >> PAGE_SHIFT; + int page_end = (end + BITMAP_DATA_OFFSET) >> PAGE_SHIFT; + + llbitmap_state_machine(llbitmap, start, end, BitmapActionDiscard); + + while (page_start <= page_end) { + llbitmap_raise_barrier(llbitmap, page_start); + page_start++; + } +} + +static void llbitmap_end_discard(struct mddev *mddev, sector_t offset, + unsigned long sectors) +{ + struct llbitmap *llbitmap = mddev->bitmap; + unsigned long start = DIV_ROUND_UP(offset, llbitmap->chunksize); + unsigned long end = (offset + sectors - 1) >> llbitmap->chunkshift; + int page_start = (start + BITMAP_DATA_OFFSET) >> PAGE_SHIFT; + int page_end = (end + BITMAP_DATA_OFFSET) >> PAGE_SHIFT; + + while (page_start <= page_end) { + llbitmap_release_barrier(llbitmap, page_start); + page_start++; + } +} + +static void llbitmap_unplug_fn(struct work_struct *work) +{ + struct llbitmap_unplug_work *unplug_work = + container_of(work, struct llbitmap_unplug_work, work); + struct llbitmap *llbitmap = unplug_work->llbitmap; + struct blk_plug plug; + int i; + + blk_start_plug(&plug); + + for (i = 0; i < llbitmap->nr_pages; i++) { + if (!test_bit(LLPageDirty, &llbitmap->pctl[i]->flags) || + !test_and_clear_bit(LLPageDirty, &llbitmap->pctl[i]->flags)) + continue; + + llbitmap_write_page(llbitmap, i); + } + + blk_finish_plug(&plug); + md_super_wait(llbitmap->mddev); + complete(unplug_work->done); +} + +static bool llbitmap_dirty(struct llbitmap *llbitmap) +{ + int i; + + for (i = 0; i < llbitmap->nr_pages; i++) + if (test_bit(LLPageDirty, &llbitmap->pctl[i]->flags)) + return true; + + return false; +} + +static void llbitmap_unplug(struct mddev *mddev, bool sync) +{ + DECLARE_COMPLETION_ONSTACK(done); + struct llbitmap *llbitmap = mddev->bitmap; + struct llbitmap_unplug_work unplug_work = { + .llbitmap = llbitmap, + .done = &done, + }; + + if (!llbitmap_dirty(llbitmap)) + return; + + /* + * Issue new bitmap IO under submit_bio() context will deadlock: + * - the bio will wait for bitmap bio to be done, before it can be + * issued; + * - bitmap bio will be added to current->bio_list and wait for this + * bio to be issued; + */ + INIT_WORK_ONSTACK(&unplug_work.work, llbitmap_unplug_fn); + queue_work(md_llbitmap_unplug_wq, &unplug_work.work); + wait_for_completion(&done); + destroy_work_on_stack(&unplug_work.work); +} + +/* + * Force to write all bitmap pages to disk, called when stopping the array, or + * every daemon_sleep seconds when sync_thread is running. + */ +static void __llbitmap_flush(struct mddev *mddev) +{ + struct llbitmap *llbitmap = mddev->bitmap; + struct blk_plug plug; + int i; + + blk_start_plug(&plug); + for (i = 0; i < llbitmap->nr_pages; i++) { + struct llbitmap_page_ctl *pctl = llbitmap->pctl[i]; + + /* mark all blocks as dirty */ + set_bit(LLPageDirty, &pctl->flags); + bitmap_fill(pctl->dirty, llbitmap->blocks_per_page); + llbitmap_write_page(llbitmap, i); + } + blk_finish_plug(&plug); + md_super_wait(llbitmap->mddev); +} + +static void llbitmap_flush(struct mddev *mddev) +{ + struct llbitmap *llbitmap = mddev->bitmap; + int i; + + for (i = 0; i < llbitmap->nr_pages; i++) + set_bit(LLPageFlush, &llbitmap->pctl[i]->flags); + + timer_delete_sync(&llbitmap->pending_timer); + queue_work(md_llbitmap_io_wq, &llbitmap->daemon_work); + flush_work(&llbitmap->daemon_work); + + __llbitmap_flush(mddev); +} + +/* This is used for raid5 lazy initial recovery */ +static bool llbitmap_blocks_synced(struct mddev *mddev, sector_t offset) +{ + struct llbitmap *llbitmap = mddev->bitmap; + unsigned long p = offset >> llbitmap->chunkshift; + enum llbitmap_state c = llbitmap_read(llbitmap, p); + + return c == BitClean || c == BitDirty; +} + +static sector_t llbitmap_skip_sync_blocks(struct mddev *mddev, sector_t offset) +{ + struct llbitmap *llbitmap = mddev->bitmap; + unsigned long p = offset >> llbitmap->chunkshift; + int blocks = llbitmap->chunksize - (offset & (llbitmap->chunksize - 1)); + enum llbitmap_state c = llbitmap_read(llbitmap, p); + + /* always skip unwritten blocks */ + if (c == BitUnwritten) + return blocks; + + /* For degraded array, don't skip */ + if (mddev->degraded) + return 0; + + /* For resync also skip clean/dirty blocks */ + if ((c == BitClean || c == BitDirty) && + test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && + !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) + return blocks; + + return 0; +} + +static bool llbitmap_start_sync(struct mddev *mddev, sector_t offset, + sector_t *blocks, bool degraded) +{ + struct llbitmap *llbitmap = mddev->bitmap; + unsigned long p = offset >> llbitmap->chunkshift; + + /* + * Handle one bit at a time, this is much simpler. And it doesn't matter + * if md_do_sync() loop more times. + */ + *blocks = llbitmap->chunksize - (offset & (llbitmap->chunksize - 1)); + return llbitmap_state_machine(llbitmap, p, p, + BitmapActionStartsync) == BitSyncing; +} + +/* Something is wrong, sync_thread stop at @offset */ +static void llbitmap_end_sync(struct mddev *mddev, sector_t offset, + sector_t *blocks) +{ + struct llbitmap *llbitmap = mddev->bitmap; + unsigned long p = offset >> llbitmap->chunkshift; + + *blocks = llbitmap->chunksize - (offset & (llbitmap->chunksize - 1)); + llbitmap_state_machine(llbitmap, p, llbitmap->chunks - 1, + BitmapActionAbortsync); +} + +/* A full sync_thread is finished */ +static void llbitmap_close_sync(struct mddev *mddev) +{ + struct llbitmap *llbitmap = mddev->bitmap; + int i; + + for (i = 0; i < llbitmap->nr_pages; i++) { + struct llbitmap_page_ctl *pctl = llbitmap->pctl[i]; + + /* let daemon_fn clear dirty bits immediately */ + WRITE_ONCE(pctl->expire, jiffies); + } + + llbitmap_state_machine(llbitmap, 0, llbitmap->chunks - 1, + BitmapActionEndsync); +} + +/* + * sync_thread have reached @sector, update metadata every daemon_sleep seconds, + * just in case sync_thread have to restart after power failure. + */ +static void llbitmap_cond_end_sync(struct mddev *mddev, sector_t sector, + bool force) +{ + struct llbitmap *llbitmap = mddev->bitmap; + + if (sector == 0) { + llbitmap->last_end_sync = jiffies; + return; + } + + if (time_before(jiffies, llbitmap->last_end_sync + + HZ * mddev->bitmap_info.daemon_sleep)) + return; + + wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); + + mddev->curr_resync_completed = sector; + set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags); + llbitmap_state_machine(llbitmap, 0, sector >> llbitmap->chunkshift, + BitmapActionEndsync); + __llbitmap_flush(mddev); + + llbitmap->last_end_sync = jiffies; + sysfs_notify_dirent_safe(mddev->sysfs_completed); +} + +static bool llbitmap_enabled(void *data, bool flush) +{ + struct llbitmap *llbitmap = data; + + return llbitmap && !test_bit(BITMAP_WRITE_ERROR, &llbitmap->flags); +} + +static void llbitmap_dirty_bits(struct mddev *mddev, unsigned long s, + unsigned long e) +{ + llbitmap_state_machine(mddev->bitmap, s, e, BitmapActionStartwrite); +} + +static void llbitmap_write_sb(struct llbitmap *llbitmap) +{ + int nr_blocks = DIV_ROUND_UP(BITMAP_DATA_OFFSET, llbitmap->io_size); + + bitmap_fill(llbitmap->pctl[0]->dirty, nr_blocks); + llbitmap_write_page(llbitmap, 0); + md_super_wait(llbitmap->mddev); +} + +static void llbitmap_update_sb(void *data) +{ + struct llbitmap *llbitmap = data; + struct mddev *mddev = llbitmap->mddev; + struct page *sb_page; + bitmap_super_t *sb; + + if (test_bit(BITMAP_WRITE_ERROR, &llbitmap->flags)) + return; + + sb_page = llbitmap_read_page(llbitmap, 0); + if (IS_ERR(sb_page)) { + pr_err("%s: %s: read super block failed", __func__, + mdname(mddev)); + set_bit(BITMAP_WRITE_ERROR, &llbitmap->flags); + return; + } + + if (mddev->events < llbitmap->events_cleared) + llbitmap->events_cleared = mddev->events; + + sb = kmap_local_page(sb_page); + sb->events = cpu_to_le64(mddev->events); + sb->state = cpu_to_le32(llbitmap->flags); + sb->chunksize = cpu_to_le32(llbitmap->chunksize); + sb->sync_size = cpu_to_le64(mddev->resync_max_sectors); + sb->events_cleared = cpu_to_le64(llbitmap->events_cleared); + sb->sectors_reserved = cpu_to_le32(mddev->bitmap_info.space); + sb->daemon_sleep = cpu_to_le32(mddev->bitmap_info.daemon_sleep); + + kunmap_local(sb); + llbitmap_write_sb(llbitmap); +} + +static int llbitmap_get_stats(void *data, struct md_bitmap_stats *stats) +{ + struct llbitmap *llbitmap = data; + + memset(stats, 0, sizeof(*stats)); + + stats->missing_pages = 0; + stats->pages = llbitmap->nr_pages; + stats->file_pages = llbitmap->nr_pages; + + stats->behind_writes = atomic_read(&llbitmap->behind_writes); + stats->behind_wait = wq_has_sleeper(&llbitmap->behind_wait); + stats->events_cleared = llbitmap->events_cleared; + + return 0; +} + +/* just flag all pages as needing to be written */ +static void llbitmap_write_all(struct mddev *mddev) +{ + int i; + struct llbitmap *llbitmap = mddev->bitmap; + + for (i = 0; i < llbitmap->nr_pages; i++) { + struct llbitmap_page_ctl *pctl = llbitmap->pctl[i]; + + set_bit(LLPageDirty, &pctl->flags); + bitmap_fill(pctl->dirty, llbitmap->blocks_per_page); + } +} + +static void llbitmap_start_behind_write(struct mddev *mddev) +{ + struct llbitmap *llbitmap = mddev->bitmap; + + atomic_inc(&llbitmap->behind_writes); +} + +static void llbitmap_end_behind_write(struct mddev *mddev) +{ + struct llbitmap *llbitmap = mddev->bitmap; + + if (atomic_dec_and_test(&llbitmap->behind_writes)) + wake_up(&llbitmap->behind_wait); +} + +static void llbitmap_wait_behind_writes(struct mddev *mddev) +{ + struct llbitmap *llbitmap = mddev->bitmap; + + if (!llbitmap) + return; + + wait_event(llbitmap->behind_wait, + atomic_read(&llbitmap->behind_writes) == 0); + +} + +static ssize_t bits_show(struct mddev *mddev, char *page) +{ + struct llbitmap *llbitmap; + int bits[BitStateCount] = {0}; + loff_t start = 0; + + mutex_lock(&mddev->bitmap_info.mutex); + llbitmap = mddev->bitmap; + if (!llbitmap || !llbitmap->pctl) { + mutex_unlock(&mddev->bitmap_info.mutex); + return sprintf(page, "no bitmap\n"); + } + + if (test_bit(BITMAP_WRITE_ERROR, &llbitmap->flags)) { + mutex_unlock(&mddev->bitmap_info.mutex); + return sprintf(page, "bitmap io error\n"); + } + + while (start < llbitmap->chunks) { + enum llbitmap_state c = llbitmap_read(llbitmap, start); + + if (c < 0 || c >= BitStateCount) + pr_err("%s: invalid bit %llu state %d\n", + __func__, start, c); + else + bits[c]++; + start++; + } + + mutex_unlock(&mddev->bitmap_info.mutex); + return sprintf(page, "unwritten %d\nclean %d\ndirty %d\nneed sync %d\nsyncing %d\n", + bits[BitUnwritten], bits[BitClean], bits[BitDirty], + bits[BitNeedSync], bits[BitSyncing]); +} + +static struct md_sysfs_entry llbitmap_bits = __ATTR_RO(bits); + +static ssize_t metadata_show(struct mddev *mddev, char *page) +{ + struct llbitmap *llbitmap; + ssize_t ret; + + mutex_lock(&mddev->bitmap_info.mutex); + llbitmap = mddev->bitmap; + if (!llbitmap) { + mutex_unlock(&mddev->bitmap_info.mutex); + return sprintf(page, "no bitmap\n"); + } + + ret = sprintf(page, "chunksize %lu\nchunkshift %lu\nchunks %lu\noffset %llu\ndaemon_sleep %lu\n", + llbitmap->chunksize, llbitmap->chunkshift, + llbitmap->chunks, mddev->bitmap_info.offset, + llbitmap->mddev->bitmap_info.daemon_sleep); + mutex_unlock(&mddev->bitmap_info.mutex); + + return ret; +} + +static struct md_sysfs_entry llbitmap_metadata = __ATTR_RO(metadata); + +static ssize_t +daemon_sleep_show(struct mddev *mddev, char *page) +{ + return sprintf(page, "%lu\n", mddev->bitmap_info.daemon_sleep); +} + +static ssize_t +daemon_sleep_store(struct mddev *mddev, const char *buf, size_t len) +{ + unsigned long timeout; + int rv = kstrtoul(buf, 10, &timeout); + + if (rv) + return rv; + + mddev->bitmap_info.daemon_sleep = timeout; + return len; +} + +static struct md_sysfs_entry llbitmap_daemon_sleep = __ATTR_RW(daemon_sleep); + +static ssize_t +barrier_idle_show(struct mddev *mddev, char *page) +{ + struct llbitmap *llbitmap = mddev->bitmap; + + return sprintf(page, "%lu\n", llbitmap->barrier_idle); +} + +static ssize_t +barrier_idle_store(struct mddev *mddev, const char *buf, size_t len) +{ + struct llbitmap *llbitmap = mddev->bitmap; + unsigned long timeout; + int rv = kstrtoul(buf, 10, &timeout); + + if (rv) + return rv; + + llbitmap->barrier_idle = timeout; + return len; +} + +static struct md_sysfs_entry llbitmap_barrier_idle = __ATTR_RW(barrier_idle); + +static struct attribute *md_llbitmap_attrs[] = { + &llbitmap_bits.attr, + &llbitmap_metadata.attr, + &llbitmap_daemon_sleep.attr, + &llbitmap_barrier_idle.attr, + NULL +}; + +static struct attribute_group md_llbitmap_group = { + .name = "llbitmap", + .attrs = md_llbitmap_attrs, +}; + +static struct bitmap_operations llbitmap_ops = { + .head = { + .type = MD_BITMAP, + .id = ID_LLBITMAP, + .name = "llbitmap", + }, + + .enabled = llbitmap_enabled, + .create = llbitmap_create, + .resize = llbitmap_resize, + .load = llbitmap_load, + .destroy = llbitmap_destroy, + + .start_write = llbitmap_start_write, + .end_write = llbitmap_end_write, + .start_discard = llbitmap_start_discard, + .end_discard = llbitmap_end_discard, + .unplug = llbitmap_unplug, + .flush = llbitmap_flush, + + .start_behind_write = llbitmap_start_behind_write, + .end_behind_write = llbitmap_end_behind_write, + .wait_behind_writes = llbitmap_wait_behind_writes, + + .blocks_synced = llbitmap_blocks_synced, + .skip_sync_blocks = llbitmap_skip_sync_blocks, + .start_sync = llbitmap_start_sync, + .end_sync = llbitmap_end_sync, + .close_sync = llbitmap_close_sync, + .cond_end_sync = llbitmap_cond_end_sync, + + .update_sb = llbitmap_update_sb, + .get_stats = llbitmap_get_stats, + .dirty_bits = llbitmap_dirty_bits, + .write_all = llbitmap_write_all, + + .group = &md_llbitmap_group, +}; + +int md_llbitmap_init(void) +{ + md_llbitmap_io_wq = alloc_workqueue("md_llbitmap_io", + WQ_MEM_RECLAIM | WQ_UNBOUND, 0); + if (!md_llbitmap_io_wq) + return -ENOMEM; + + md_llbitmap_unplug_wq = alloc_workqueue("md_llbitmap_unplug", + WQ_MEM_RECLAIM | WQ_UNBOUND, 0); + if (!md_llbitmap_unplug_wq) { + destroy_workqueue(md_llbitmap_io_wq); + md_llbitmap_io_wq = NULL; + return -ENOMEM; + } + + return register_md_submodule(&llbitmap_ops.head); +} + +void md_llbitmap_exit(void) +{ + destroy_workqueue(md_llbitmap_io_wq); + md_llbitmap_io_wq = NULL; + destroy_workqueue(md_llbitmap_unplug_wq); + md_llbitmap_unplug_wq = NULL; + unregister_md_submodule(&llbitmap_ops.head); +} diff --git a/drivers/md/md.c b/drivers/md/md.c index 2f1907f3bc25..1de550108756 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -10328,6 +10328,10 @@ static int __init md_init(void) if (ret) return ret; + ret = md_llbitmap_init(); + if (ret) + goto err_bitmap; + ret = -ENOMEM; md_wq = alloc_workqueue("md", WQ_MEM_RECLAIM, 0); if (!md_wq) @@ -10359,6 +10363,8 @@ err_md: err_misc_wq: destroy_workqueue(md_wq); err_wq: + md_llbitmap_exit(); +err_bitmap: md_bitmap_exit(); return ret; } diff --git a/drivers/md/md.h b/drivers/md/md.h index 7b6357879a84..1979c2d4fe89 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -26,7 +26,7 @@ enum md_submodule_type { MD_PERSONALITY = 0, MD_CLUSTER, - MD_BITMAP, /* TODO */ + MD_BITMAP, }; enum md_submodule_id { @@ -39,7 +39,7 @@ enum md_submodule_id { ID_RAID10 = 10, ID_CLUSTER, ID_BITMAP, - ID_LLBITMAP, /* TODO */ + ID_LLBITMAP, ID_BITMAP_NONE, };