diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/bitmap.c | 3 | ||||
-rw-r--r-- | drivers/md/dm-cache-policy-cleaner.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-crypt.c | 17 | ||||
-rw-r--r-- | drivers/md/dm-raid.c | 3 | ||||
-rw-r--r-- | drivers/md/dm-thin.c | 2 | ||||
-rw-r--r-- | drivers/md/dm.c | 6 | ||||
-rw-r--r-- | drivers/md/md.c | 5 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-btree-internal.h | 6 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-btree-remove.c | 29 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-btree-spine.c | 37 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-btree.c | 9 | ||||
-rw-r--r-- | drivers/md/raid0.c | 75 | ||||
-rw-r--r-- | drivers/md/raid1.c | 2 | ||||
-rw-r--r-- | drivers/md/raid10.c | 7 | ||||
-rw-r--r-- | drivers/md/raid5.c | 40 | ||||
-rw-r--r-- | drivers/md/raid5.h | 3 |
16 files changed, 162 insertions, 84 deletions
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index c90118e90708..a7621a258936 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -2000,7 +2000,8 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks, if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file) ret = bitmap_storage_alloc(&store, chunks, !bitmap->mddev->bitmap_info.external, - bitmap->cluster_slot); + mddev_is_clustered(bitmap->mddev) + ? bitmap->cluster_slot : 0); if (ret) goto err; diff --git a/drivers/md/dm-cache-policy-cleaner.c b/drivers/md/dm-cache-policy-cleaner.c index 004e463c9423..8308f4b434ec 100644 --- a/drivers/md/dm-cache-policy-cleaner.c +++ b/drivers/md/dm-cache-policy-cleaner.c @@ -435,7 +435,7 @@ static struct dm_cache_policy *wb_create(dm_cblock_t cache_size, static struct dm_cache_policy_type wb_policy_type = { .name = "cleaner", .version = {1, 0, 0}, - .hint_size = 0, + .hint_size = 4, .owner = THIS_MODULE, .create = wb_create }; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 5503e43e5f28..049282e6482f 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -955,7 +955,8 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone); /* * Generate a new unfragmented bio with the given size - * This should never violate the device limitations + * This should never violate the device limitations (but only because + * max_segment_size is being constrained to PAGE_SIZE). * * This function may be called concurrently. If we allocate from the mempool * concurrently, there is a possibility of deadlock. For example, if we have @@ -2040,9 +2041,20 @@ static int crypt_iterate_devices(struct dm_target *ti, return fn(ti, cc->dev, cc->start, ti->len, data); } +static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) +{ + /* + * Unfortunate constraint that is required to avoid the potential + * for exceeding underlying device's max_segments limits -- due to + * crypt_alloc_buffer() possibly allocating pages for the encryption + * bio that are not as physically contiguous as the original bio. + */ + limits->max_segment_size = PAGE_SIZE; +} + static struct target_type crypt_target = { .name = "crypt", - .version = {1, 14, 0}, + .version = {1, 14, 1}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, @@ -2054,6 +2066,7 @@ static struct target_type crypt_target = { .message = crypt_message, .merge = crypt_merge, .iterate_devices = crypt_iterate_devices, + .io_hints = crypt_io_hints, }; static int __init dm_crypt_init(void) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 88e4c7f24986..2c1f2e13719e 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -327,8 +327,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size) */ if (min_region_size > (1 << 13)) { /* If not a power of 2, make it the next power of 2 */ - if (min_region_size & (min_region_size - 1)) - region_size = 1 << fls(region_size); + region_size = roundup_pow_of_two(min_region_size); DMINFO("Choosing default region size of %lu sectors", region_size); } else { diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index e22e6c892b8a..7073b22d4cb4 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2959,7 +2959,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) metadata_low_callback, pool); if (r) - goto out_free_pt; + goto out_flags_changed; pt->callbacks.congested_fn = pool_is_congested; dm_table_add_target_callbacks(ti->table, &pt->callbacks); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 98347e2cf04b..cffdd9aa0dcf 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2925,8 +2925,6 @@ static void __dm_destroy(struct mapped_device *md, bool wait) might_sleep(); - map = dm_get_live_table(md, &srcu_idx); - spin_lock(&_minor_lock); idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md)))); set_bit(DMF_FREEING, &md->flags); @@ -2940,14 +2938,14 @@ static void __dm_destroy(struct mapped_device *md, bool wait) * do not race with internal suspend. */ mutex_lock(&md->suspend_lock); + map = dm_get_live_table(md, &srcu_idx); if (!dm_suspended_md(md)) { dm_table_presuspend_targets(map); dm_table_postsuspend_targets(map); } - mutex_unlock(&md->suspend_lock); - /* dm_put_live_table must be before msleep, otherwise deadlock is possible */ dm_put_live_table(md, srcu_idx); + mutex_unlock(&md->suspend_lock); /* * Rare, but there may be I/O requests still going to complete, diff --git a/drivers/md/md.c b/drivers/md/md.c index e4621511d118..78c1f77e7903 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5365,6 +5365,8 @@ static void __md_stop(struct mddev *mddev) { struct md_personality *pers = mddev->pers; mddev_detach(mddev); + /* Ensure ->event_work is done */ + flush_workqueue(md_misc_wq); spin_lock(&mddev->lock); mddev->ready = 0; mddev->pers = NULL; @@ -8011,8 +8013,7 @@ static int remove_and_add_spares(struct mddev *mddev, !test_bit(Bitmap_sync, &rdev->flags))) continue; - if (rdev->saved_raid_disk < 0) - rdev->recovery_offset = 0; + rdev->recovery_offset = 0; if (mddev->pers-> hot_add_disk(mddev, rdev) == 0) { if (sysfs_link_rdev(mddev, rdev)) diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index bf2b80d5c470..8731b6ea026b 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -138,4 +138,10 @@ int lower_bound(struct btree_node *n, uint64_t key); extern struct dm_block_validator btree_node_validator; +/* + * Value type for upper levels of multi-level btrees. + */ +extern void init_le64_type(struct dm_transaction_manager *tm, + struct dm_btree_value_type *vt); + #endif /* DM_BTREE_INTERNAL_H */ diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index a03178e91a79..92cd09f3c69b 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -301,11 +301,16 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, { int s; uint32_t max_entries = le32_to_cpu(left->header.max_entries); - unsigned target = (nr_left + nr_center + nr_right) / 3; - BUG_ON(target > max_entries); + unsigned total = nr_left + nr_center + nr_right; + unsigned target_right = total / 3; + unsigned remainder = (target_right * 3) != total; + unsigned target_left = target_right + remainder; + + BUG_ON(target_left > max_entries); + BUG_ON(target_right > max_entries); if (nr_left < nr_right) { - s = nr_left - target; + s = nr_left - target_left; if (s < 0 && nr_center < -s) { /* not enough in central node */ @@ -316,10 +321,10 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, } else shift(left, center, s); - shift(center, right, target - nr_right); + shift(center, right, target_right - nr_right); } else { - s = target - nr_right; + s = target_right - nr_right; if (s > 0 && nr_center < s) { /* not enough in central node */ shift(center, right, nr_center); @@ -329,7 +334,7 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent, } else shift(center, right, s); - shift(left, center, nr_left - target); + shift(left, center, nr_left - target_left); } *key_ptr(parent, c->index) = center->keys[0]; @@ -544,14 +549,6 @@ static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info, return r; } -static struct dm_btree_value_type le64_type = { - .context = NULL, - .size = sizeof(__le64), - .inc = NULL, - .dec = NULL, - .equal = NULL -}; - int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, uint64_t *keys, dm_block_t *new_root) { @@ -559,12 +556,14 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, int index = 0, r = 0; struct shadow_spine spine; struct btree_node *n; + struct dm_btree_value_type le64_vt; + init_le64_type(info->tm, &le64_vt); init_shadow_spine(&spine, info); for (level = 0; level < info->levels; level++) { r = remove_raw(&spine, info, (level == last_level ? - &info->value_type : &le64_type), + &info->value_type : &le64_vt), root, keys[level], (unsigned *)&index); if (r < 0) break; diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index 1b5e13ec7f96..0dee514ba4c5 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -249,3 +249,40 @@ int shadow_root(struct shadow_spine *s) { return s->root; } + +static void le64_inc(void *context, const void *value_le) +{ + struct dm_transaction_manager *tm = context; + __le64 v_le; + + memcpy(&v_le, value_le, sizeof(v_le)); + dm_tm_inc(tm, le64_to_cpu(v_le)); +} + +static void le64_dec(void *context, const void *value_le) +{ + struct dm_transaction_manager *tm = context; + __le64 v_le; + + memcpy(&v_le, value_le, sizeof(v_le)); + dm_tm_dec(tm, le64_to_cpu(v_le)); +} + +static int le64_equal(void *context, const void *value1_le, const void *value2_le) +{ + __le64 v1_le, v2_le; + + memcpy(&v1_le, value1_le, sizeof(v1_le)); + memcpy(&v2_le, value2_le, sizeof(v2_le)); + return v1_le == v2_le; +} + +void init_le64_type(struct dm_transaction_manager *tm, + struct dm_btree_value_type *vt) +{ + vt->context = tm; + vt->size = sizeof(__le64); + vt->inc = le64_inc; + vt->dec = le64_dec; + vt->equal = le64_equal; +} diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index fdd3793e22f9..d6e47033b5e0 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -523,7 +523,7 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key) r = new_block(s->info, &right); if (r < 0) { - /* FIXME: put left */ + unlock_block(s->info, left); return r; } @@ -667,12 +667,7 @@ static int insert(struct dm_btree_info *info, dm_block_t root, struct btree_node *n; struct dm_btree_value_type le64_type; - le64_type.context = NULL; - le64_type.size = sizeof(__le64); - le64_type.inc = NULL; - le64_type.dec = NULL; - le64_type.equal = NULL; - + init_le64_type(info->tm, &le64_type); init_shadow_spine(&spine, info); for (level = 0; level < (info->levels - 1); level++) { diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index efb654eb5399..0875e5e7e09a 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -83,7 +83,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) char b[BDEVNAME_SIZE]; char b2[BDEVNAME_SIZE]; struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL); - bool discard_supported = false; + unsigned short blksize = 512; if (!conf) return -ENOMEM; @@ -98,6 +98,9 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) sector_div(sectors, mddev->chunk_sectors); rdev1->sectors = sectors * mddev->chunk_sectors; + blksize = max(blksize, queue_logical_block_size( + rdev1->bdev->bd_disk->queue)); + rdev_for_each(rdev2, mddev) { pr_debug("md/raid0:%s: comparing %s(%llu)" " with %s(%llu)\n", @@ -134,6 +137,18 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) } pr_debug("md/raid0:%s: FINAL %d zones\n", mdname(mddev), conf->nr_strip_zones); + /* + * now since we have the hard sector sizes, we can make sure + * chunk size is a multiple of that sector size + */ + if ((mddev->chunk_sectors << 9) % blksize) { + printk(KERN_ERR "md/raid0:%s: chunk_size of %d not multiple of block size %d\n", + mdname(mddev), + mddev->chunk_sectors << 9, blksize); + err = -EINVAL; + goto abort; + } + err = -ENOMEM; conf->strip_zone = kzalloc(sizeof(struct strip_zone)* conf->nr_strip_zones, GFP_KERNEL); @@ -188,19 +203,12 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) } dev[j] = rdev1; - if (mddev->queue) - disk_stack_limits(mddev->gendisk, rdev1->bdev, - rdev1->data_offset << 9); - if (rdev1->bdev->bd_disk->queue->merge_bvec_fn) conf->has_merge_bvec = 1; if (!smallest || (rdev1->sectors < smallest->sectors)) smallest = rdev1; cnt++; - - if (blk_queue_discard(bdev_get_queue(rdev1->bdev))) - discard_supported = true; } if (cnt != mddev->raid_disks) { printk(KERN_ERR "md/raid0:%s: too few disks (%d of %d) - " @@ -261,28 +269,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) (unsigned long long)smallest->sectors); } - /* - * now since we have the hard sector sizes, we can make sure - * chunk size is a multiple of that sector size - */ - if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) { - printk(KERN_ERR "md/raid0:%s: chunk_size of %d not valid\n", - mdname(mddev), - mddev->chunk_sectors << 9); - goto abort; - } - - if (mddev->queue) { - blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); - blk_queue_io_opt(mddev->queue, - (mddev->chunk_sectors << 9) * mddev->raid_disks); - - if (!discard_supported) - queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); - else - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); - } - pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; @@ -433,12 +419,6 @@ static int raid0_run(struct mddev *mddev) if (md_check_no_bitmap(mddev)) return -EINVAL; - if (mddev->queue) { - blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); - blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); - } - /* if private is not null, we are here after takeover */ if (mddev->private == NULL) { ret = create_strip_zones(mddev, &conf); @@ -447,6 +427,29 @@ static int raid0_run(struct mddev *mddev) mddev->private = conf; } conf = mddev->private; + if (mddev->queue) { + struct md_rdev *rdev; + bool discard_supported = false; + + blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); + + blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9); + blk_queue_io_opt(mddev->queue, + (mddev->chunk_sectors << 9) * mddev->raid_disks); + + rdev_for_each(rdev, mddev) { + disk_stack_limits(mddev->gendisk, rdev->bdev, + rdev->data_offset << 9); + if (blk_queue_discard(bdev_get_queue(rdev->bdev))) + discard_supported = true; + } + if (!discard_supported) + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + else + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + } /* calculate array device size */ md_set_array_sectors(mddev, raid0_size(mddev, 0, 0)); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 5ce3cd5c4e1d..bff6c1c7fecb 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2248,7 +2248,7 @@ static int narrow_write_error(struct r1bio *r1_bio, int i) bio_trim(wbio, sector - r1_bio->sector, sectors); wbio->bi_iter.bi_sector += rdev->data_offset; wbio->bi_bdev = rdev->bdev; - if (submit_bio_wait(WRITE, wbio) == 0) + if (submit_bio_wait(WRITE, wbio) < 0) /* failure! */ ok = rdev_set_badblocks(rdev, sector, sectors, 0) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index f55c3f35b746..adfc83a0f023 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -2590,7 +2590,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i) choose_data_offset(r10_bio, rdev) + (sector - r10_bio->sector)); wbio->bi_bdev = rdev->bdev; - if (submit_bio_wait(WRITE, wbio) == 0) + if (submit_bio_wait(WRITE, wbio) < 0) /* Failure! */ ok = rdev_set_badblocks(rdev, sector, sectors, 0) @@ -3566,6 +3566,7 @@ static struct r10conf *setup_conf(struct mddev *mddev) /* far_copies must be 1 */ conf->prev.stride = conf->dev_sectors; } + conf->reshape_safe = conf->reshape_progress; spin_lock_init(&conf->device_lock); INIT_LIST_HEAD(&conf->retry_list); @@ -3770,7 +3771,6 @@ static int run(struct mddev *mddev) } conf->offset_diff = min_offset_diff; - conf->reshape_safe = conf->reshape_progress; clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); @@ -4113,6 +4113,7 @@ static int raid10_start_reshape(struct mddev *mddev) conf->reshape_progress = size; } else conf->reshape_progress = 0; + conf->reshape_safe = conf->reshape_progress; spin_unlock_irq(&conf->device_lock); if (mddev->delta_disks && mddev->bitmap) { @@ -4180,6 +4181,7 @@ abort: rdev->new_data_offset = rdev->data_offset; smp_wmb(); conf->reshape_progress = MaxSector; + conf->reshape_safe = MaxSector; mddev->reshape_position = MaxSector; spin_unlock_irq(&conf->device_lock); return ret; @@ -4534,6 +4536,7 @@ static void end_reshape(struct r10conf *conf) md_finish_reshape(conf->mddev); smp_wmb(); conf->reshape_progress = MaxSector; + conf->reshape_safe = MaxSector; spin_unlock_irq(&conf->device_lock); /* read-ahead size must cover two whole stripes, which is diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 47413f7f02b9..17cd4efc8ea5 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2153,6 +2153,9 @@ static int resize_stripes(struct r5conf *conf, int newsize) if (!sc) return -ENOMEM; + /* Need to ensure auto-resizing doesn't interfere */ + mutex_lock(&conf->cache_size_mutex); + for (i = conf->max_nr_stripes; i; i--) { nsh = alloc_stripe(sc, GFP_KERNEL); if (!nsh) @@ -2169,6 +2172,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) kmem_cache_free(sc, nsh); } kmem_cache_destroy(sc); + mutex_unlock(&conf->cache_size_mutex); return -ENOMEM; } /* Step 2 - Must use GFP_NOIO now. @@ -2215,6 +2219,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) } else err = -ENOMEM; + mutex_unlock(&conf->cache_size_mutex); /* Step 4, return new stripes to service */ while(!list_empty(&newstripes)) { nsh = list_entry(newstripes.next, struct stripe_head, lru); @@ -2242,7 +2247,7 @@ static int resize_stripes(struct r5conf *conf, int newsize) static int drop_one_stripe(struct r5conf *conf) { struct stripe_head *sh; - int hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS; + int hash = (conf->max_nr_stripes - 1) & STRIPE_HASH_LOCKS_MASK; spin_lock_irq(conf->hash_locks + hash); sh = get_free_stripe(conf, hash); @@ -3491,6 +3496,7 @@ returnbi: } if (!discard_pending && test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) { + int hash; clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags); clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags); if (sh->qd_idx >= 0) { @@ -3504,16 +3510,17 @@ returnbi: * no updated data, so remove it from hash list and the stripe * will be reinitialized */ - spin_lock_irq(&conf->device_lock); unhash: + hash = sh->hash_lock_index; + spin_lock_irq(conf->hash_locks + hash); remove_hash(sh); + spin_unlock_irq(conf->hash_locks + hash); if (head_sh->batch_head) { sh = list_first_entry(&sh->batch_list, struct stripe_head, batch_list); if (sh != head_sh) goto unhash; } - spin_unlock_irq(&conf->device_lock); sh = head_sh; if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) @@ -5848,12 +5855,14 @@ static void raid5d(struct md_thread *thread) pr_debug("%d stripes handled\n", handled); spin_unlock_irq(&conf->device_lock); - if (test_and_clear_bit(R5_ALLOC_MORE, &conf->cache_state)) { + if (test_and_clear_bit(R5_ALLOC_MORE, &conf->cache_state) && + mutex_trylock(&conf->cache_size_mutex)) { grow_one_stripe(conf, __GFP_NOWARN); /* Set flag even if allocation failed. This helps * slow down allocation requests when mem is short */ set_bit(R5_DID_ALLOC, &conf->cache_state); + mutex_unlock(&conf->cache_size_mutex); } async_tx_issue_pending_all(); @@ -5885,18 +5894,22 @@ raid5_set_cache_size(struct mddev *mddev, int size) return -EINVAL; conf->min_nr_stripes = size; + mutex_lock(&conf->cache_size_mutex); while (size < conf->max_nr_stripes && drop_one_stripe(conf)) ; + mutex_unlock(&conf->cache_size_mutex); err = md_allow_write(mddev); if (err) return err; + mutex_lock(&conf->cache_size_mutex); while (size > conf->max_nr_stripes) if (!grow_one_stripe(conf, GFP_KERNEL)) break; + mutex_unlock(&conf->cache_size_mutex); return 0; } @@ -6363,11 +6376,19 @@ static unsigned long raid5_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { struct r5conf *conf = container_of(shrink, struct r5conf, shrinker); - int ret = 0; - while (ret < sc->nr_to_scan) { - if (drop_one_stripe(conf) == 0) - return SHRINK_STOP; - ret++; + unsigned long ret = SHRINK_STOP; + + if (mutex_trylock(&conf->cache_size_mutex)) { + ret= 0; + while (ret < sc->nr_to_scan && + conf->max_nr_stripes > conf->min_nr_stripes) { + if (drop_one_stripe(conf) == 0) { + ret = SHRINK_STOP; + break; + } + ret++; + } + mutex_unlock(&conf->cache_size_mutex); } return ret; } @@ -6436,6 +6457,7 @@ static struct r5conf *setup_conf(struct mddev *mddev) goto abort; spin_lock_init(&conf->device_lock); seqcount_init(&conf->gen_lock); + mutex_init(&conf->cache_size_mutex); init_waitqueue_head(&conf->wait_for_stripe); init_waitqueue_head(&conf->wait_for_overlap); INIT_LIST_HEAD(&conf->handle_list); diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 66199a494235..584c7bd62123 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -482,7 +482,8 @@ struct r5conf { */ int active_name; char cache_name[2][32]; - struct kmem_cache *slab_cache; /* for allocating stripes */ + struct kmem_cache *slab_cache; /* for allocating stripes */ + struct mutex cache_size_mutex; /* Protect changes to cache size */ int seq_flush, seq_write; int quiesce; |