X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fmd%2Fraid5.c;h=a5ba080d303b93bb3a4d764ea621f4bf9bc191d0;hb=d08ca2ca743f324eceba59e93188f9439e966bce;hp=29fc06b47d4e07b4bdd64c025eae6180f9a1f5ca;hpb=b4c4c7b8095298ff4ce20b40bf180ada070812d0;p=safe%2Fjmp%2Flinux-2.6 diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 29fc06b..a5ba080 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -43,15 +43,11 @@ * miss any bits. */ -#include -#include -#include -#include #include -#include #include "raid6.h" #include +#include /* * Stripe cache @@ -62,6 +58,7 @@ #define STRIPE_SHIFT (PAGE_SHIFT - 9) #define STRIPE_SECTORS (STRIPE_SIZE>>9) #define IO_THRESHOLD 1 +#define BYPASS_THRESHOLD 1 #define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head)) #define HASH_MASK (NR_HASH - 1) @@ -80,7 +77,6 @@ /* * The following can be used to debug the driver */ -#define RAID5_DEBUG 0 #define RAID5_PARANOIA 1 #if RAID5_PARANOIA && defined(CONFIG_SMP) # define CHECK_DEVLOCK() assert_spin_locked(&conf->device_lock) @@ -88,24 +84,80 @@ # define CHECK_DEVLOCK() #endif -#define PRINTK(x...) ((void)(RAID5_DEBUG && printk(x))) -#if RAID5_DEBUG +#ifdef DEBUG #define inline #define __inline__ #endif +#define printk_rl(args...) ((void) (printk_ratelimit() && printk(args))) + #if !RAID6_USE_EMPTY_ZERO_PAGE /* In .bss so it's zeroed */ const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256))); #endif +/* + * We maintain a biased count of active stripes in the bottom 16 bits of + * bi_phys_segments, and a count of processed stripes in the upper 16 bits + */ +static inline int raid5_bi_phys_segments(struct bio *bio) +{ + return bio->bi_phys_segments & 0xffff; +} + +static inline int raid5_bi_hw_segments(struct bio *bio) +{ + return (bio->bi_phys_segments >> 16) & 0xffff; +} + +static inline int raid5_dec_bi_phys_segments(struct bio *bio) +{ + --bio->bi_phys_segments; + return raid5_bi_phys_segments(bio); +} + +static inline int raid5_dec_bi_hw_segments(struct bio *bio) +{ + unsigned short val = raid5_bi_hw_segments(bio); + + --val; + bio->bi_phys_segments = (val << 16) | raid5_bi_phys_segments(bio); + return val; +} + +static inline void raid5_set_bi_hw_segments(struct bio *bio, unsigned int cnt) +{ + bio->bi_phys_segments = raid5_bi_phys_segments(bio) || (cnt << 16); +} + static inline int raid6_next_disk(int disk, int raid_disks) { disk++; return (disk < raid_disks) ? disk : 0; } + +static void return_io(struct bio *return_bi) +{ + struct bio *bi = return_bi; + while (bi) { + + return_bi = bi->bi_next; + bi->bi_next = NULL; + bi->bi_size = 0; + bio_endio(bi, 0); + bi = return_bi; + } +} + static void print_raid5_conf (raid5_conf_t *conf); +static int stripe_operations_active(struct stripe_head *sh) +{ + return sh->check_state || sh->reconstruct_state || + test_bit(STRIPE_BIOFILL_RUN, &sh->state) || + test_bit(STRIPE_COMPUTE_RUN, &sh->state); +} + static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh) { if (atomic_dec_and_test(&sh->count)) { @@ -125,6 +177,7 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh) } md_wakeup_thread(conf->mddev->thread); } else { + BUG_ON(stripe_operations_active(sh)); if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { atomic_dec(&conf->preread_active_stripes); if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) @@ -152,7 +205,8 @@ static void release_stripe(struct stripe_head *sh) static inline void remove_hash(struct stripe_head *sh) { - PRINTK("remove_hash(), stripe %llu\n", (unsigned long long)sh->sector); + pr_debug("remove_hash(), stripe %llu\n", + (unsigned long long)sh->sector); hlist_del_init(&sh->hash); } @@ -161,7 +215,8 @@ static inline void insert_hash(raid5_conf_t *conf, struct stripe_head *sh) { struct hlist_head *hp = stripe_hash(conf, sh->sector); - PRINTK("insert_hash(), stripe %llu\n", (unsigned long long)sh->sector); + pr_debug("insert_hash(), stripe %llu\n", + (unsigned long long)sh->sector); CHECK_DEVLOCK(); hlist_add_head(&sh->hash, hp); @@ -215,7 +270,7 @@ static int grow_buffers(struct stripe_head *sh, int num) return 0; } -static void raid5_build_block (struct stripe_head *sh, int i); +static void raid5_build_block(struct stripe_head *sh, int i); static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int disks) { @@ -224,9 +279,10 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int BUG_ON(atomic_read(&sh->count) != 0); BUG_ON(test_bit(STRIPE_HANDLE, &sh->state)); - + BUG_ON(stripe_operations_active(sh)); + CHECK_DEVLOCK(); - PRINTK("init_stripe called, stripe %llu\n", + pr_debug("init_stripe called, stripe %llu\n", (unsigned long long)sh->sector); remove_hash(sh); @@ -240,11 +296,11 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int for (i = sh->disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - if (dev->toread || dev->towrite || dev->written || + if (dev->toread || dev->read || dev->towrite || dev->written || test_bit(R5_LOCKED, &dev->flags)) { - printk("sector=%llx i=%d %p %p %p %d\n", + printk(KERN_ERR "sector=%llx i=%d %p %p %p %p %d\n", (unsigned long long)sh->sector, i, dev->toread, - dev->towrite, dev->written, + dev->read, dev->towrite, dev->written, test_bit(R5_LOCKED, &dev->flags)); BUG(); } @@ -260,23 +316,23 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, in struct hlist_node *hn; CHECK_DEVLOCK(); - PRINTK("__find_stripe, sector %llu\n", (unsigned long long)sector); + pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector); hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash) if (sh->sector == sector && sh->disks == disks) return sh; - PRINTK("__stripe %llu not in cache\n", (unsigned long long)sector); + pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector); return NULL; } static void unplug_slaves(mddev_t *mddev); -static void raid5_unplug_device(request_queue_t *q); +static void raid5_unplug_device(struct request_queue *q); static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector, int disks, int pd_idx, int noblock) { struct stripe_head *sh; - PRINTK("get_stripe, sector %llu\n", (unsigned long long)sector); + pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector); spin_lock_irq(&conf->device_lock); @@ -324,153 +380,641 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector return sh; } -static int grow_one_stripe(raid5_conf_t *conf) +static void +raid5_end_read_request(struct bio *bi, int error); +static void +raid5_end_write_request(struct bio *bi, int error); + +static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) { - struct stripe_head *sh; - sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL); - if (!sh) - return 0; - memset(sh, 0, sizeof(*sh) + (conf->raid_disks-1)*sizeof(struct r5dev)); - sh->raid_conf = conf; - spin_lock_init(&sh->lock); + raid5_conf_t *conf = sh->raid_conf; + int i, disks = sh->disks; - if (grow_buffers(sh, conf->raid_disks)) { - shrink_buffers(sh, conf->raid_disks); - kmem_cache_free(conf->slab_cache, sh); - return 0; - } - sh->disks = conf->raid_disks; - /* we just created an active stripe so... */ - atomic_set(&sh->count, 1); - atomic_inc(&conf->active_stripes); - INIT_LIST_HEAD(&sh->lru); - release_stripe(sh); - return 1; -} + might_sleep(); -static int grow_stripes(raid5_conf_t *conf, int num) -{ - struct kmem_cache *sc; - int devs = conf->raid_disks; + for (i = disks; i--; ) { + int rw; + struct bio *bi; + mdk_rdev_t *rdev; + if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) + rw = WRITE; + else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags)) + rw = READ; + else + continue; - sprintf(conf->cache_name[0], "raid5/%s", mdname(conf->mddev)); - sprintf(conf->cache_name[1], "raid5/%s-alt", mdname(conf->mddev)); - conf->active_name = 0; - sc = kmem_cache_create(conf->cache_name[conf->active_name], - sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev), - 0, 0, NULL, NULL); - if (!sc) - return 1; - conf->slab_cache = sc; - conf->pool_size = devs; - while (num--) - if (!grow_one_stripe(conf)) - return 1; - return 0; + bi = &sh->dev[i].req; + + bi->bi_rw = rw; + if (rw == WRITE) + bi->bi_end_io = raid5_end_write_request; + else + bi->bi_end_io = raid5_end_read_request; + + rcu_read_lock(); + rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev && test_bit(Faulty, &rdev->flags)) + rdev = NULL; + if (rdev) + atomic_inc(&rdev->nr_pending); + rcu_read_unlock(); + + if (rdev) { + if (s->syncing || s->expanding || s->expanded) + md_sync_acct(rdev->bdev, STRIPE_SECTORS); + + set_bit(STRIPE_IO_STARTED, &sh->state); + + bi->bi_bdev = rdev->bdev; + pr_debug("%s: for %llu schedule op %ld on disc %d\n", + __func__, (unsigned long long)sh->sector, + bi->bi_rw, i); + atomic_inc(&sh->count); + bi->bi_sector = sh->sector + rdev->data_offset; + bi->bi_flags = 1 << BIO_UPTODATE; + bi->bi_vcnt = 1; + bi->bi_max_vecs = 1; + bi->bi_idx = 0; + bi->bi_io_vec = &sh->dev[i].vec; + bi->bi_io_vec[0].bv_len = STRIPE_SIZE; + bi->bi_io_vec[0].bv_offset = 0; + bi->bi_size = STRIPE_SIZE; + bi->bi_next = NULL; + if (rw == WRITE && + test_bit(R5_ReWrite, &sh->dev[i].flags)) + atomic_add(STRIPE_SECTORS, + &rdev->corrected_errors); + generic_make_request(bi); + } else { + if (rw == WRITE) + set_bit(STRIPE_DEGRADED, &sh->state); + pr_debug("skip op %ld on disc %d for sector %llu\n", + bi->bi_rw, i, (unsigned long long)sh->sector); + clear_bit(R5_LOCKED, &sh->dev[i].flags); + set_bit(STRIPE_HANDLE, &sh->state); + } + } } -#ifdef CONFIG_MD_RAID5_RESHAPE -static int resize_stripes(raid5_conf_t *conf, int newsize) +static struct dma_async_tx_descriptor * +async_copy_data(int frombio, struct bio *bio, struct page *page, + sector_t sector, struct dma_async_tx_descriptor *tx) { - /* Make all the stripes able to hold 'newsize' devices. - * New slots in each stripe get 'page' set to a new page. - * - * This happens in stages: - * 1/ create a new kmem_cache and allocate the required number of - * stripe_heads. - * 2/ gather all the old stripe_heads and tranfer the pages across - * to the new stripe_heads. This will have the side effect of - * freezing the array as once all stripe_heads have been collected, - * no IO will be possible. Old stripe heads are freed once their - * pages have been transferred over, and the old kmem_cache is - * freed when all stripes are done. - * 3/ reallocate conf->disks to be suitable bigger. If this fails, - * we simple return a failre status - no need to clean anything up. - * 4/ allocate new pages for the new slots in the new stripe_heads. - * If this fails, we don't bother trying the shrink the - * stripe_heads down again, we just leave them as they are. - * As each stripe_head is processed the new one is released into - * active service. - * - * Once step2 is started, we cannot afford to wait for a write, - * so we use GFP_NOIO allocations. - */ - struct stripe_head *osh, *nsh; - LIST_HEAD(newstripes); - struct disk_info *ndisks; - int err = 0; - struct kmem_cache *sc; + struct bio_vec *bvl; + struct page *bio_page; int i; + int page_offset; - if (newsize <= conf->pool_size) - return 0; /* never bother to shrink */ + if (bio->bi_sector >= sector) + page_offset = (signed)(bio->bi_sector - sector) * 512; + else + page_offset = (signed)(sector - bio->bi_sector) * -512; + bio_for_each_segment(bvl, bio, i) { + int len = bio_iovec_idx(bio, i)->bv_len; + int clen; + int b_offset = 0; - md_allow_write(conf->mddev); + if (page_offset < 0) { + b_offset = -page_offset; + page_offset += b_offset; + len -= b_offset; + } - /* Step 1 */ - sc = kmem_cache_create(conf->cache_name[1-conf->active_name], - sizeof(struct stripe_head)+(newsize-1)*sizeof(struct r5dev), - 0, 0, NULL, NULL); - if (!sc) - return -ENOMEM; + if (len > 0 && page_offset + len > STRIPE_SIZE) + clen = STRIPE_SIZE - page_offset; + else + clen = len; - for (i = conf->max_nr_stripes; i; i--) { - nsh = kmem_cache_alloc(sc, GFP_KERNEL); - if (!nsh) + if (clen > 0) { + b_offset += bio_iovec_idx(bio, i)->bv_offset; + bio_page = bio_iovec_idx(bio, i)->bv_page; + if (frombio) + tx = async_memcpy(page, bio_page, page_offset, + b_offset, clen, + ASYNC_TX_DEP_ACK, + tx, NULL, NULL); + else + tx = async_memcpy(bio_page, page, b_offset, + page_offset, clen, + ASYNC_TX_DEP_ACK, + tx, NULL, NULL); + } + if (clen < len) /* hit end of page */ break; + page_offset += len; + } - memset(nsh, 0, sizeof(*nsh) + (newsize-1)*sizeof(struct r5dev)); + return tx; +} - nsh->raid_conf = conf; - spin_lock_init(&nsh->lock); +static void ops_complete_biofill(void *stripe_head_ref) +{ + struct stripe_head *sh = stripe_head_ref; + struct bio *return_bi = NULL; + raid5_conf_t *conf = sh->raid_conf; + int i; - list_add(&nsh->lru, &newstripes); - } - if (i) { - /* didn't get enough, give up */ - while (!list_empty(&newstripes)) { - nsh = list_entry(newstripes.next, struct stripe_head, lru); - list_del(&nsh->lru); - kmem_cache_free(sc, nsh); + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + /* clear completed biofills */ + spin_lock_irq(&conf->device_lock); + for (i = sh->disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + + /* acknowledge completion of a biofill operation */ + /* and check if we need to reply to a read request, + * new R5_Wantfill requests are held off until + * !STRIPE_BIOFILL_RUN + */ + if (test_and_clear_bit(R5_Wantfill, &dev->flags)) { + struct bio *rbi, *rbi2; + + BUG_ON(!dev->read); + rbi = dev->read; + dev->read = NULL; + while (rbi && rbi->bi_sector < + dev->sector + STRIPE_SECTORS) { + rbi2 = r5_next_bio(rbi, dev->sector); + if (!raid5_dec_bi_phys_segments(rbi)) { + rbi->bi_next = return_bi; + return_bi = rbi; + } + rbi = rbi2; + } } - kmem_cache_destroy(sc); - return -ENOMEM; - } - /* Step 2 - Must use GFP_NOIO now. - * OK, we have enough stripes, start collecting inactive - * stripes and copying them over - */ - list_for_each_entry(nsh, &newstripes, lru) { - spin_lock_irq(&conf->device_lock); - wait_event_lock_irq(conf->wait_for_stripe, - !list_empty(&conf->inactive_list), - conf->device_lock, - unplug_slaves(conf->mddev) - ); - osh = get_free_stripe(conf); - spin_unlock_irq(&conf->device_lock); - atomic_set(&nsh->count, 1); - for(i=0; ipool_size; i++) - nsh->dev[i].page = osh->dev[i].page; - for( ; idev[i].page = NULL; - kmem_cache_free(conf->slab_cache, osh); } - kmem_cache_destroy(conf->slab_cache); + spin_unlock_irq(&conf->device_lock); + clear_bit(STRIPE_BIOFILL_RUN, &sh->state); - /* Step 3. - * At this point, we are holding all the stripes so the array - * is completely stalled, so now is a good time to resize - * conf->disks. - */ - ndisks = kzalloc(newsize * sizeof(struct disk_info), GFP_NOIO); - if (ndisks) { - for (i=0; iraid_disks; i++) - ndisks[i] = conf->disks[i]; - kfree(conf->disks); - conf->disks = ndisks; - } else - err = -ENOMEM; + return_io(return_bi); + + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); +} + +static void ops_run_biofill(struct stripe_head *sh) +{ + struct dma_async_tx_descriptor *tx = NULL; + raid5_conf_t *conf = sh->raid_conf; + int i; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + for (i = sh->disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (test_bit(R5_Wantfill, &dev->flags)) { + struct bio *rbi; + spin_lock_irq(&conf->device_lock); + dev->read = rbi = dev->toread; + dev->toread = NULL; + spin_unlock_irq(&conf->device_lock); + while (rbi && rbi->bi_sector < + dev->sector + STRIPE_SECTORS) { + tx = async_copy_data(0, rbi, dev->page, + dev->sector, tx); + rbi = r5_next_bio(rbi, dev->sector); + } + } + } + + atomic_inc(&sh->count); + async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx, + ops_complete_biofill, sh); +} + +static void ops_complete_compute5(void *stripe_head_ref) +{ + struct stripe_head *sh = stripe_head_ref; + int target = sh->ops.target; + struct r5dev *tgt = &sh->dev[target]; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + set_bit(R5_UPTODATE, &tgt->flags); + BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags)); + clear_bit(R5_Wantcompute, &tgt->flags); + clear_bit(STRIPE_COMPUTE_RUN, &sh->state); + if (sh->check_state == check_state_compute_run) + sh->check_state = check_state_compute_result; + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); +} + +static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh) +{ + /* kernel stack size limits the total number of disks */ + int disks = sh->disks; + struct page *xor_srcs[disks]; + int target = sh->ops.target; + struct r5dev *tgt = &sh->dev[target]; + struct page *xor_dest = tgt->page; + int count = 0; + struct dma_async_tx_descriptor *tx; + int i; + + pr_debug("%s: stripe %llu block: %d\n", + __func__, (unsigned long long)sh->sector, target); + BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags)); + + for (i = disks; i--; ) + if (i != target) + xor_srcs[count++] = sh->dev[i].page; + + atomic_inc(&sh->count); + + if (unlikely(count == 1)) + tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, + 0, NULL, ops_complete_compute5, sh); + else + tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, + ASYNC_TX_XOR_ZERO_DST, NULL, + ops_complete_compute5, sh); + + return tx; +} + +static void ops_complete_prexor(void *stripe_head_ref) +{ + struct stripe_head *sh = stripe_head_ref; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); +} + +static struct dma_async_tx_descriptor * +ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) +{ + /* kernel stack size limits the total number of disks */ + int disks = sh->disks; + struct page *xor_srcs[disks]; + int count = 0, pd_idx = sh->pd_idx, i; + + /* existing parity data subtracted */ + struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + /* Only process blocks that are known to be uptodate */ + if (test_bit(R5_Wantdrain, &dev->flags)) + xor_srcs[count++] = dev->page; + } + + tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, + ASYNC_TX_DEP_ACK | ASYNC_TX_XOR_DROP_DST, tx, + ops_complete_prexor, sh); + + return tx; +} + +static struct dma_async_tx_descriptor * +ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) +{ + int disks = sh->disks; + int i; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + struct bio *chosen; + + if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) { + struct bio *wbi; + + spin_lock(&sh->lock); + chosen = dev->towrite; + dev->towrite = NULL; + BUG_ON(dev->written); + wbi = dev->written = chosen; + spin_unlock(&sh->lock); + + while (wbi && wbi->bi_sector < + dev->sector + STRIPE_SECTORS) { + tx = async_copy_data(1, wbi, dev->page, + dev->sector, tx); + wbi = r5_next_bio(wbi, dev->sector); + } + } + } + + return tx; +} + +static void ops_complete_postxor(void *stripe_head_ref) +{ + struct stripe_head *sh = stripe_head_ref; + int disks = sh->disks, i, pd_idx = sh->pd_idx; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (dev->written || i == pd_idx) + set_bit(R5_UPTODATE, &dev->flags); + } + + if (sh->reconstruct_state == reconstruct_state_drain_run) + sh->reconstruct_state = reconstruct_state_drain_result; + else if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) + sh->reconstruct_state = reconstruct_state_prexor_drain_result; + else { + BUG_ON(sh->reconstruct_state != reconstruct_state_run); + sh->reconstruct_state = reconstruct_state_result; + } + + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); +} + +static void +ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx) +{ + /* kernel stack size limits the total number of disks */ + int disks = sh->disks; + struct page *xor_srcs[disks]; + + int count = 0, pd_idx = sh->pd_idx, i; + struct page *xor_dest; + int prexor = 0; + unsigned long flags; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + /* check if prexor is active which means only process blocks + * that are part of a read-modify-write (written) + */ + if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) { + prexor = 1; + xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (dev->written) + xor_srcs[count++] = dev->page; + } + } else { + xor_dest = sh->dev[pd_idx].page; + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (i != pd_idx) + xor_srcs[count++] = dev->page; + } + } + + /* 1/ if we prexor'd then the dest is reused as a source + * 2/ if we did not prexor then we are redoing the parity + * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST + * for the synchronous xor case + */ + flags = ASYNC_TX_DEP_ACK | ASYNC_TX_ACK | + (prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST); + + atomic_inc(&sh->count); + + if (unlikely(count == 1)) { + flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST); + tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, + flags, tx, ops_complete_postxor, sh); + } else + tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, + flags, tx, ops_complete_postxor, sh); +} + +static void ops_complete_check(void *stripe_head_ref) +{ + struct stripe_head *sh = stripe_head_ref; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + sh->check_state = check_state_check_result; + set_bit(STRIPE_HANDLE, &sh->state); + release_stripe(sh); +} + +static void ops_run_check(struct stripe_head *sh) +{ + /* kernel stack size limits the total number of disks */ + int disks = sh->disks; + struct page *xor_srcs[disks]; + struct dma_async_tx_descriptor *tx; + + int count = 0, pd_idx = sh->pd_idx, i; + struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page; + + pr_debug("%s: stripe %llu\n", __func__, + (unsigned long long)sh->sector); + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (i != pd_idx) + xor_srcs[count++] = dev->page; + } + + tx = async_xor_zero_sum(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, + &sh->ops.zero_sum_result, 0, NULL, NULL, NULL); + + atomic_inc(&sh->count); + tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx, + ops_complete_check, sh); +} + +static void raid5_run_ops(struct stripe_head *sh, unsigned long ops_request) +{ + int overlap_clear = 0, i, disks = sh->disks; + struct dma_async_tx_descriptor *tx = NULL; + + if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { + ops_run_biofill(sh); + overlap_clear++; + } + + if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request)) { + tx = ops_run_compute5(sh); + /* terminate the chain if postxor is not set to be run */ + if (tx && !test_bit(STRIPE_OP_POSTXOR, &ops_request)) + async_tx_ack(tx); + } + + if (test_bit(STRIPE_OP_PREXOR, &ops_request)) + tx = ops_run_prexor(sh, tx); + + if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) { + tx = ops_run_biodrain(sh, tx); + overlap_clear++; + } + + if (test_bit(STRIPE_OP_POSTXOR, &ops_request)) + ops_run_postxor(sh, tx); + + if (test_bit(STRIPE_OP_CHECK, &ops_request)) + ops_run_check(sh); + + if (overlap_clear) + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (test_and_clear_bit(R5_Overlap, &dev->flags)) + wake_up(&sh->raid_conf->wait_for_overlap); + } +} + +static int grow_one_stripe(raid5_conf_t *conf) +{ + struct stripe_head *sh; + sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL); + if (!sh) + return 0; + memset(sh, 0, sizeof(*sh) + (conf->raid_disks-1)*sizeof(struct r5dev)); + sh->raid_conf = conf; + spin_lock_init(&sh->lock); + + if (grow_buffers(sh, conf->raid_disks)) { + shrink_buffers(sh, conf->raid_disks); + kmem_cache_free(conf->slab_cache, sh); + return 0; + } + sh->disks = conf->raid_disks; + /* we just created an active stripe so... */ + atomic_set(&sh->count, 1); + atomic_inc(&conf->active_stripes); + INIT_LIST_HEAD(&sh->lru); + release_stripe(sh); + return 1; +} + +static int grow_stripes(raid5_conf_t *conf, int num) +{ + struct kmem_cache *sc; + int devs = conf->raid_disks; + + sprintf(conf->cache_name[0], "raid5-%s", mdname(conf->mddev)); + sprintf(conf->cache_name[1], "raid5-%s-alt", mdname(conf->mddev)); + conf->active_name = 0; + sc = kmem_cache_create(conf->cache_name[conf->active_name], + sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev), + 0, 0, NULL); + if (!sc) + return 1; + conf->slab_cache = sc; + conf->pool_size = devs; + while (num--) + if (!grow_one_stripe(conf)) + return 1; + return 0; +} + +#ifdef CONFIG_MD_RAID5_RESHAPE +static int resize_stripes(raid5_conf_t *conf, int newsize) +{ + /* Make all the stripes able to hold 'newsize' devices. + * New slots in each stripe get 'page' set to a new page. + * + * This happens in stages: + * 1/ create a new kmem_cache and allocate the required number of + * stripe_heads. + * 2/ gather all the old stripe_heads and tranfer the pages across + * to the new stripe_heads. This will have the side effect of + * freezing the array as once all stripe_heads have been collected, + * no IO will be possible. Old stripe heads are freed once their + * pages have been transferred over, and the old kmem_cache is + * freed when all stripes are done. + * 3/ reallocate conf->disks to be suitable bigger. If this fails, + * we simple return a failre status - no need to clean anything up. + * 4/ allocate new pages for the new slots in the new stripe_heads. + * If this fails, we don't bother trying the shrink the + * stripe_heads down again, we just leave them as they are. + * As each stripe_head is processed the new one is released into + * active service. + * + * Once step2 is started, we cannot afford to wait for a write, + * so we use GFP_NOIO allocations. + */ + struct stripe_head *osh, *nsh; + LIST_HEAD(newstripes); + struct disk_info *ndisks; + int err; + struct kmem_cache *sc; + int i; + + if (newsize <= conf->pool_size) + return 0; /* never bother to shrink */ + + err = md_allow_write(conf->mddev); + if (err) + return err; + + /* Step 1 */ + sc = kmem_cache_create(conf->cache_name[1-conf->active_name], + sizeof(struct stripe_head)+(newsize-1)*sizeof(struct r5dev), + 0, 0, NULL); + if (!sc) + return -ENOMEM; + + for (i = conf->max_nr_stripes; i; i--) { + nsh = kmem_cache_alloc(sc, GFP_KERNEL); + if (!nsh) + break; + + memset(nsh, 0, sizeof(*nsh) + (newsize-1)*sizeof(struct r5dev)); + + nsh->raid_conf = conf; + spin_lock_init(&nsh->lock); + + list_add(&nsh->lru, &newstripes); + } + if (i) { + /* didn't get enough, give up */ + while (!list_empty(&newstripes)) { + nsh = list_entry(newstripes.next, struct stripe_head, lru); + list_del(&nsh->lru); + kmem_cache_free(sc, nsh); + } + kmem_cache_destroy(sc); + return -ENOMEM; + } + /* Step 2 - Must use GFP_NOIO now. + * OK, we have enough stripes, start collecting inactive + * stripes and copying them over + */ + list_for_each_entry(nsh, &newstripes, lru) { + spin_lock_irq(&conf->device_lock); + wait_event_lock_irq(conf->wait_for_stripe, + !list_empty(&conf->inactive_list), + conf->device_lock, + unplug_slaves(conf->mddev) + ); + osh = get_free_stripe(conf); + spin_unlock_irq(&conf->device_lock); + atomic_set(&nsh->count, 1); + for(i=0; ipool_size; i++) + nsh->dev[i].page = osh->dev[i].page; + for( ; idev[i].page = NULL; + kmem_cache_free(conf->slab_cache, osh); + } + kmem_cache_destroy(conf->slab_cache); + + /* Step 3. + * At this point, we are holding all the stripes so the array + * is completely stalled, so now is a good time to resize + * conf->disks. + */ + ndisks = kzalloc(newsize * sizeof(struct disk_info), GFP_NOIO); + if (ndisks) { + for (i=0; iraid_disks; i++) + ndisks[i] = conf->disks[i]; + kfree(conf->disks); + conf->disks = ndisks; + } else + err = -ENOMEM; /* Step 4, return new stripes to service */ while(!list_empty(&newstripes)) { @@ -520,8 +1064,7 @@ static void shrink_stripes(raid5_conf_t *conf) conf->slab_cache = NULL; } -static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done, - int error) +static void raid5_end_read_request(struct bio * bi, int error) { struct stripe_head *sh = bi->bi_private; raid5_conf_t *conf = sh->raid_conf; @@ -530,29 +1073,29 @@ static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done, char b[BDEVNAME_SIZE]; mdk_rdev_t *rdev; - if (bi->bi_size) - return 1; for (i=0 ; idev[i].req) break; - PRINTK("end_read_request %llu/%d, count: %d, uptodate %d.\n", - (unsigned long long)sh->sector, i, atomic_read(&sh->count), + pr_debug("end_read_request %llu/%d, count: %d, uptodate %d.\n", + (unsigned long long)sh->sector, i, atomic_read(&sh->count), uptodate); if (i == disks) { BUG(); - return 0; + return; } if (uptodate) { set_bit(R5_UPTODATE, &sh->dev[i].flags); if (test_bit(R5_ReadError, &sh->dev[i].flags)) { rdev = conf->disks[i].rdev; - printk(KERN_INFO "raid5:%s: read error corrected (%lu sectors at %llu on %s)\n", - mdname(conf->mddev), STRIPE_SECTORS, - (unsigned long long)sh->sector + rdev->data_offset, - bdevname(rdev->bdev, b)); + printk_rl(KERN_INFO "raid5:%s: read error corrected" + " (%lu sectors at %llu on %s)\n", + mdname(conf->mddev), STRIPE_SECTORS, + (unsigned long long)(sh->sector + + rdev->data_offset), + bdevname(rdev->bdev, b)); clear_bit(R5_ReadError, &sh->dev[i].flags); clear_bit(R5_ReWrite, &sh->dev[i].flags); } @@ -566,16 +1109,22 @@ static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done, clear_bit(R5_UPTODATE, &sh->dev[i].flags); atomic_inc(&rdev->read_errors); if (conf->mddev->degraded) - printk(KERN_WARNING "raid5:%s: read error not correctable (sector %llu on %s).\n", - mdname(conf->mddev), - (unsigned long long)sh->sector + rdev->data_offset, - bdn); + printk_rl(KERN_WARNING + "raid5:%s: read error not correctable " + "(sector %llu on %s).\n", + mdname(conf->mddev), + (unsigned long long)(sh->sector + + rdev->data_offset), + bdn); else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) /* Oh, no!!! */ - printk(KERN_WARNING "raid5:%s: read error NOT corrected!! (sector %llu on %s).\n", - mdname(conf->mddev), - (unsigned long long)sh->sector + rdev->data_offset, - bdn); + printk_rl(KERN_WARNING + "raid5:%s: read error NOT corrected!! " + "(sector %llu on %s).\n", + mdname(conf->mddev), + (unsigned long long)(sh->sector + + rdev->data_offset), + bdn); else if (atomic_read(&rdev->read_errors) > conf->max_nr_stripes) printk(KERN_WARNING @@ -595,30 +1144,25 @@ static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done, clear_bit(R5_LOCKED, &sh->dev[i].flags); set_bit(STRIPE_HANDLE, &sh->state); release_stripe(sh); - return 0; } -static int raid5_end_write_request (struct bio *bi, unsigned int bytes_done, - int error) +static void raid5_end_write_request(struct bio *bi, int error) { struct stripe_head *sh = bi->bi_private; raid5_conf_t *conf = sh->raid_conf; int disks = sh->disks, i; int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); - if (bi->bi_size) - return 1; - for (i=0 ; idev[i].req) break; - PRINTK("end_write_request %llu/%d, count %d, uptodate: %d.\n", + pr_debug("end_write_request %llu/%d, count %d, uptodate: %d.\n", (unsigned long long)sh->sector, i, atomic_read(&sh->count), uptodate); if (i == disks) { BUG(); - return 0; + return; } if (!uptodate) @@ -629,13 +1173,12 @@ static int raid5_end_write_request (struct bio *bi, unsigned int bytes_done, clear_bit(R5_LOCKED, &sh->dev[i].flags); set_bit(STRIPE_HANDLE, &sh->state); release_stripe(sh); - return 0; } static sector_t compute_blocknr(struct stripe_head *sh, int i); -static void raid5_build_block (struct stripe_head *sh, int i) +static void raid5_build_block(struct stripe_head *sh, int i) { struct r5dev *dev = &sh->dev[i]; @@ -658,7 +1201,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) { char b[BDEVNAME_SIZE]; raid5_conf_t *conf = (raid5_conf_t *) mddev->private; - PRINTK("raid5: error called\n"); + pr_debug("raid5: error called\n"); if (!test_bit(Faulty, &rdev->flags)) { set_bit(MD_CHANGE_DEVS, &mddev->flags); @@ -670,13 +1213,13 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) /* * if recovery was running, make sure it aborts. */ - set_bit(MD_RECOVERY_ERR, &mddev->recovery); + set_bit(MD_RECOVERY_INTR, &mddev->recovery); } set_bit(Faulty, &rdev->flags); - printk (KERN_ALERT - "raid5: Disk failure on %s, disabling device." - " Operation continuing on %d devices\n", - bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded); + printk(KERN_ALERT + "raid5: Disk failure on %s, disabling device.\n" + "raid5: Operation continuing on %d devices.\n", + bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded); } } @@ -772,8 +1315,8 @@ static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks, *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks; break; default: - printk (KERN_CRIT "raid6: unsupported algorithm %d\n", - conf->algorithm); + printk(KERN_CRIT "raid6: unsupported algorithm %d\n", + conf->algorithm); } break; } @@ -848,8 +1391,8 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i) } break; default: - printk (KERN_CRIT "raid6: unsupported algorithm %d\n", - conf->algorithm); + printk(KERN_CRIT "raid6: unsupported algorithm %d\n", + conf->algorithm); } break; } @@ -857,7 +1400,7 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i) chunk_number = stripe * data_disks + i; r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset; - check = raid5_compute_sector (r_sector, raid_disks, data_disks, &dummy1, &dummy2, conf); + check = raid5_compute_sector(r_sector, raid_disks, data_disks, &dummy1, &dummy2, conf); if (check != sh->sector || dummy1 != dd_idx || dummy2 != sh->pd_idx) { printk(KERN_ERR "compute_blocknr: map not correct\n"); return 0; @@ -916,141 +1459,17 @@ static void copy_data(int frombio, struct bio *bio, } } -#define check_xor() do { \ - if (count == MAX_XOR_BLOCKS) { \ - xor_block(count, STRIPE_SIZE, ptr); \ - count = 1; \ - } \ +#define check_xor() do { \ + if (count == MAX_XOR_BLOCKS) { \ + xor_blocks(count, STRIPE_SIZE, dest, ptr);\ + count = 0; \ + } \ } while(0) - -static void compute_block(struct stripe_head *sh, int dd_idx) -{ - int i, count, disks = sh->disks; - void *ptr[MAX_XOR_BLOCKS], *p; - - PRINTK("compute_block, stripe %llu, idx %d\n", - (unsigned long long)sh->sector, dd_idx); - - ptr[0] = page_address(sh->dev[dd_idx].page); - memset(ptr[0], 0, STRIPE_SIZE); - count = 1; - for (i = disks ; i--; ) { - if (i == dd_idx) - continue; - p = page_address(sh->dev[i].page); - if (test_bit(R5_UPTODATE, &sh->dev[i].flags)) - ptr[count++] = p; - else - printk(KERN_ERR "compute_block() %d, stripe %llu, %d" - " not present\n", dd_idx, - (unsigned long long)sh->sector, i); - - check_xor(); - } - if (count != 1) - xor_block(count, STRIPE_SIZE, ptr); - set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags); -} - -static void compute_parity5(struct stripe_head *sh, int method) -{ - raid5_conf_t *conf = sh->raid_conf; - int i, pd_idx = sh->pd_idx, disks = sh->disks, count; - void *ptr[MAX_XOR_BLOCKS]; - struct bio *chosen; - - PRINTK("compute_parity5, stripe %llu, method %d\n", - (unsigned long long)sh->sector, method); - - count = 1; - ptr[0] = page_address(sh->dev[pd_idx].page); - switch(method) { - case READ_MODIFY_WRITE: - BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags)); - for (i=disks ; i-- ;) { - if (i==pd_idx) - continue; - if (sh->dev[i].towrite && - test_bit(R5_UPTODATE, &sh->dev[i].flags)) { - ptr[count++] = page_address(sh->dev[i].page); - chosen = sh->dev[i].towrite; - sh->dev[i].towrite = NULL; - - if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) - wake_up(&conf->wait_for_overlap); - - BUG_ON(sh->dev[i].written); - sh->dev[i].written = chosen; - check_xor(); - } - } - break; - case RECONSTRUCT_WRITE: - memset(ptr[0], 0, STRIPE_SIZE); - for (i= disks; i-- ;) - if (i!=pd_idx && sh->dev[i].towrite) { - chosen = sh->dev[i].towrite; - sh->dev[i].towrite = NULL; - - if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) - wake_up(&conf->wait_for_overlap); - - BUG_ON(sh->dev[i].written); - sh->dev[i].written = chosen; - } - break; - case CHECK_PARITY: - break; - } - if (count>1) { - xor_block(count, STRIPE_SIZE, ptr); - count = 1; - } - - for (i = disks; i--;) - if (sh->dev[i].written) { - sector_t sector = sh->dev[i].sector; - struct bio *wbi = sh->dev[i].written; - while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) { - copy_data(1, wbi, sh->dev[i].page, sector); - wbi = r5_next_bio(wbi, sector); - } - - set_bit(R5_LOCKED, &sh->dev[i].flags); - set_bit(R5_UPTODATE, &sh->dev[i].flags); - } - - switch(method) { - case RECONSTRUCT_WRITE: - case CHECK_PARITY: - for (i=disks; i--;) - if (i != pd_idx) { - ptr[count++] = page_address(sh->dev[i].page); - check_xor(); - } - break; - case READ_MODIFY_WRITE: - for (i = disks; i--;) - if (sh->dev[i].written) { - ptr[count++] = page_address(sh->dev[i].page); - check_xor(); - } - } - if (count != 1) - xor_block(count, STRIPE_SIZE, ptr); - - if (method != CHECK_PARITY) { - set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags); - set_bit(R5_LOCKED, &sh->dev[pd_idx].flags); - } else - clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags); -} - static void compute_parity6(struct stripe_head *sh, int method) { raid6_conf_t *conf = sh->raid_conf; - int i, pd_idx = sh->pd_idx, qd_idx, d0_idx, disks = conf->raid_disks, count; + int i, pd_idx = sh->pd_idx, qd_idx, d0_idx, disks = sh->disks, count; struct bio *chosen; /**** FIX THIS: This could be very bad if disks is close to 256 ****/ void *ptrs[disks]; @@ -1058,7 +1477,7 @@ static void compute_parity6(struct stripe_head *sh, int method) qd_idx = raid6_next_disk(pd_idx, disks); d0_idx = raid6_next_disk(qd_idx, disks); - PRINTK("compute_parity, stripe %llu, method %d\n", + pr_debug("compute_parity, stripe %llu, method %d\n", (unsigned long long)sh->sector, method); switch(method) { @@ -1131,22 +1550,21 @@ static void compute_parity6(struct stripe_head *sh, int method) /* Compute one missing block */ static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero) { - raid6_conf_t *conf = sh->raid_conf; - int i, count, disks = conf->raid_disks; - void *ptr[MAX_XOR_BLOCKS], *p; + int i, count, disks = sh->disks; + void *ptr[MAX_XOR_BLOCKS], *dest, *p; int pd_idx = sh->pd_idx; int qd_idx = raid6_next_disk(pd_idx, disks); - PRINTK("compute_block_1, stripe %llu, idx %d\n", + pr_debug("compute_block_1, stripe %llu, idx %d\n", (unsigned long long)sh->sector, dd_idx); if ( dd_idx == qd_idx ) { /* We're actually computing the Q drive */ compute_parity6(sh, UPDATE_PARITY); } else { - ptr[0] = page_address(sh->dev[dd_idx].page); - if (!nozero) memset(ptr[0], 0, STRIPE_SIZE); - count = 1; + dest = page_address(sh->dev[dd_idx].page); + if (!nozero) memset(dest, 0, STRIPE_SIZE); + count = 0; for (i = disks ; i--; ) { if (i == dd_idx || i == qd_idx) continue; @@ -1160,8 +1578,8 @@ static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero) check_xor(); } - if (count != 1) - xor_block(count, STRIPE_SIZE, ptr); + if (count) + xor_blocks(count, STRIPE_SIZE, dest, ptr); if (!nozero) set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags); else clear_bit(R5_UPTODATE, &sh->dev[dd_idx].flags); } @@ -1170,8 +1588,7 @@ static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero) /* Compute two missing blocks */ static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2) { - raid6_conf_t *conf = sh->raid_conf; - int i, count, disks = conf->raid_disks; + int i, count, disks = sh->disks; int pd_idx = sh->pd_idx; int qd_idx = raid6_next_disk(pd_idx, disks); int d0_idx = raid6_next_disk(qd_idx, disks); @@ -1185,7 +1602,7 @@ static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2) BUG_ON(faila == failb); if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; } - PRINTK("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n", + pr_debug("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n", (unsigned long long)sh->sector, dd_idx1, dd_idx2, faila, failb); if ( failb == disks-1 ) { @@ -1225,13 +1642,81 @@ static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2) raid6_2data_recov(disks, STRIPE_SIZE, faila, failb, ptrs); } - /* Both the above update both missing blocks */ - set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags); - set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags); + /* Both the above update both missing blocks */ + set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags); + set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags); + } +} + +static void +schedule_reconstruction5(struct stripe_head *sh, struct stripe_head_state *s, + int rcw, int expand) +{ + int i, pd_idx = sh->pd_idx, disks = sh->disks; + + if (rcw) { + /* if we are not expanding this is a proper write request, and + * there will be bios with new data to be drained into the + * stripe cache + */ + if (!expand) { + sh->reconstruct_state = reconstruct_state_drain_run; + set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); + } else + sh->reconstruct_state = reconstruct_state_run; + + set_bit(STRIPE_OP_POSTXOR, &s->ops_request); + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + + if (dev->towrite) { + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantdrain, &dev->flags); + if (!expand) + clear_bit(R5_UPTODATE, &dev->flags); + s->locked++; + } + } + if (s->locked + 1 == disks) + if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state)) + atomic_inc(&sh->raid_conf->pending_full_writes); + } else { + BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) || + test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags))); + + sh->reconstruct_state = reconstruct_state_prexor_drain_run; + set_bit(STRIPE_OP_PREXOR, &s->ops_request); + set_bit(STRIPE_OP_BIODRAIN, &s->ops_request); + set_bit(STRIPE_OP_POSTXOR, &s->ops_request); + + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (i == pd_idx) + continue; + + if (dev->towrite && + (test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags))) { + set_bit(R5_Wantdrain, &dev->flags); + set_bit(R5_LOCKED, &dev->flags); + clear_bit(R5_UPTODATE, &dev->flags); + s->locked++; + } + } } -} + /* keep the parity disk locked while asynchronous operations + * are in flight + */ + set_bit(R5_LOCKED, &sh->dev[pd_idx].flags); + clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags); + s->locked++; + pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n", + __func__, (unsigned long long)sh->sector, + s->locked, s->ops_request); +} /* * Each stripe/dev can have one or more bion attached. @@ -1244,7 +1729,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in raid5_conf_t *conf = sh->raid_conf; int firstwrite=0; - PRINTK("adding bh b#%llu to stripe s#%llu\n", + pr_debug("adding bh b#%llu to stripe s#%llu\n", (unsigned long long)bi->bi_sector, (unsigned long long)sh->sector); @@ -1269,11 +1754,11 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in if (*bip) bi->bi_next = *bip; *bip = bi; - bi->bi_phys_segments ++; + bi->bi_phys_segments++; spin_unlock_irq(&conf->device_lock); spin_unlock(&sh->lock); - PRINTK("added bi b#%llu to stripe s#%llu, disk %d.\n", + pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n", (unsigned long long)bi->bi_sector, (unsigned long long)sh->sector, dd_idx); @@ -1294,38 +1779,743 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in if (bi->bi_sector + (bi->bi_size>>9) >= sector) sector = bi->bi_sector + (bi->bi_size>>9); } - if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS) - set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags); - } - return 1; + if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS) + set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags); + } + return 1; + + overlap: + set_bit(R5_Overlap, &sh->dev[dd_idx].flags); + spin_unlock_irq(&conf->device_lock); + spin_unlock(&sh->lock); + return 0; +} + +static void end_reshape(raid5_conf_t *conf); + +static int page_is_zero(struct page *p) +{ + char *a = page_address(p); + return ((*(u32*)a) == 0 && + memcmp(a, a+4, STRIPE_SIZE-4)==0); +} + +static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks) +{ + int sectors_per_chunk = conf->chunk_size >> 9; + int pd_idx, dd_idx; + int chunk_offset = sector_div(stripe, sectors_per_chunk); + + raid5_compute_sector(stripe * (disks - conf->max_degraded) + *sectors_per_chunk + chunk_offset, + disks, disks - conf->max_degraded, + &dd_idx, &pd_idx, conf); + return pd_idx; +} + +static void +handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh, + struct stripe_head_state *s, int disks, + struct bio **return_bi) +{ + int i; + for (i = disks; i--; ) { + struct bio *bi; + int bitmap_end = 0; + + if (test_bit(R5_ReadError, &sh->dev[i].flags)) { + mdk_rdev_t *rdev; + rcu_read_lock(); + rdev = rcu_dereference(conf->disks[i].rdev); + if (rdev && test_bit(In_sync, &rdev->flags)) + /* multiple read failures in one stripe */ + md_error(conf->mddev, rdev); + rcu_read_unlock(); + } + spin_lock_irq(&conf->device_lock); + /* fail all writes first */ + bi = sh->dev[i].towrite; + sh->dev[i].towrite = NULL; + if (bi) { + s->to_write--; + bitmap_end = 1; + } + + if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) + wake_up(&conf->wait_for_overlap); + + while (bi && bi->bi_sector < + sh->dev[i].sector + STRIPE_SECTORS) { + struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector); + clear_bit(BIO_UPTODATE, &bi->bi_flags); + if (!raid5_dec_bi_phys_segments(bi)) { + md_write_end(conf->mddev); + bi->bi_next = *return_bi; + *return_bi = bi; + } + bi = nextbi; + } + /* and fail all 'written' */ + bi = sh->dev[i].written; + sh->dev[i].written = NULL; + if (bi) bitmap_end = 1; + while (bi && bi->bi_sector < + sh->dev[i].sector + STRIPE_SECTORS) { + struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector); + clear_bit(BIO_UPTODATE, &bi->bi_flags); + if (!raid5_dec_bi_phys_segments(bi)) { + md_write_end(conf->mddev); + bi->bi_next = *return_bi; + *return_bi = bi; + } + bi = bi2; + } + + /* fail any reads if this device is non-operational and + * the data has not reached the cache yet. + */ + if (!test_bit(R5_Wantfill, &sh->dev[i].flags) && + (!test_bit(R5_Insync, &sh->dev[i].flags) || + test_bit(R5_ReadError, &sh->dev[i].flags))) { + bi = sh->dev[i].toread; + sh->dev[i].toread = NULL; + if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) + wake_up(&conf->wait_for_overlap); + if (bi) s->to_read--; + while (bi && bi->bi_sector < + sh->dev[i].sector + STRIPE_SECTORS) { + struct bio *nextbi = + r5_next_bio(bi, sh->dev[i].sector); + clear_bit(BIO_UPTODATE, &bi->bi_flags); + if (!raid5_dec_bi_phys_segments(bi)) { + bi->bi_next = *return_bi; + *return_bi = bi; + } + bi = nextbi; + } + } + spin_unlock_irq(&conf->device_lock); + if (bitmap_end) + bitmap_endwrite(conf->mddev->bitmap, sh->sector, + STRIPE_SECTORS, 0, 0); + } + + if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state)) + if (atomic_dec_and_test(&conf->pending_full_writes)) + md_wakeup_thread(conf->mddev->thread); +} + +/* fetch_block5 - checks the given member device to see if its data needs + * to be read or computed to satisfy a request. + * + * Returns 1 when no more member devices need to be checked, otherwise returns + * 0 to tell the loop in handle_stripe_fill5 to continue + */ +static int fetch_block5(struct stripe_head *sh, struct stripe_head_state *s, + int disk_idx, int disks) +{ + struct r5dev *dev = &sh->dev[disk_idx]; + struct r5dev *failed_dev = &sh->dev[s->failed_num]; + + /* is the data in this block needed, and can we get it? */ + if (!test_bit(R5_LOCKED, &dev->flags) && + !test_bit(R5_UPTODATE, &dev->flags) && + (dev->toread || + (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) || + s->syncing || s->expanding || + (s->failed && + (failed_dev->toread || + (failed_dev->towrite && + !test_bit(R5_OVERWRITE, &failed_dev->flags)))))) { + /* We would like to get this block, possibly by computing it, + * otherwise read it if the backing disk is insync + */ + if ((s->uptodate == disks - 1) && + (s->failed && disk_idx == s->failed_num)) { + set_bit(STRIPE_COMPUTE_RUN, &sh->state); + set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request); + set_bit(R5_Wantcompute, &dev->flags); + sh->ops.target = disk_idx; + s->req_compute = 1; + /* Careful: from this point on 'uptodate' is in the eye + * of raid5_run_ops which services 'compute' operations + * before writes. R5_Wantcompute flags a block that will + * be R5_UPTODATE by the time it is needed for a + * subsequent operation. + */ + s->uptodate++; + return 1; /* uptodate + compute == disks */ + } else if (test_bit(R5_Insync, &dev->flags)) { + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantread, &dev->flags); + s->locked++; + pr_debug("Reading block %d (sync=%d)\n", disk_idx, + s->syncing); + } + } + + return 0; +} + +/** + * handle_stripe_fill5 - read or compute data to satisfy pending requests. + */ +static void handle_stripe_fill5(struct stripe_head *sh, + struct stripe_head_state *s, int disks) +{ + int i; + + /* look for blocks to read/compute, skip this if a compute + * is already in flight, or if the stripe contents are in the + * midst of changing due to a write + */ + if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state && + !sh->reconstruct_state) + for (i = disks; i--; ) + if (fetch_block5(sh, s, i, disks)) + break; + set_bit(STRIPE_HANDLE, &sh->state); +} + +static void handle_stripe_fill6(struct stripe_head *sh, + struct stripe_head_state *s, struct r6_state *r6s, + int disks) +{ + int i; + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (!test_bit(R5_LOCKED, &dev->flags) && + !test_bit(R5_UPTODATE, &dev->flags) && + (dev->toread || (dev->towrite && + !test_bit(R5_OVERWRITE, &dev->flags)) || + s->syncing || s->expanding || + (s->failed >= 1 && + (sh->dev[r6s->failed_num[0]].toread || + s->to_write)) || + (s->failed >= 2 && + (sh->dev[r6s->failed_num[1]].toread || + s->to_write)))) { + /* we would like to get this block, possibly + * by computing it, but we might not be able to + */ + if ((s->uptodate == disks - 1) && + (s->failed && (i == r6s->failed_num[0] || + i == r6s->failed_num[1]))) { + pr_debug("Computing stripe %llu block %d\n", + (unsigned long long)sh->sector, i); + compute_block_1(sh, i, 0); + s->uptodate++; + } else if ( s->uptodate == disks-2 && s->failed >= 2 ) { + /* Computing 2-failure is *very* expensive; only + * do it if failed >= 2 + */ + int other; + for (other = disks; other--; ) { + if (other == i) + continue; + if (!test_bit(R5_UPTODATE, + &sh->dev[other].flags)) + break; + } + BUG_ON(other < 0); + pr_debug("Computing stripe %llu blocks %d,%d\n", + (unsigned long long)sh->sector, + i, other); + compute_block_2(sh, i, other); + s->uptodate += 2; + } else if (test_bit(R5_Insync, &dev->flags)) { + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantread, &dev->flags); + s->locked++; + pr_debug("Reading block %d (sync=%d)\n", + i, s->syncing); + } + } + } + set_bit(STRIPE_HANDLE, &sh->state); +} + + +/* handle_stripe_clean_event + * any written block on an uptodate or failed drive can be returned. + * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but + * never LOCKED, so we don't need to test 'failed' directly. + */ +static void handle_stripe_clean_event(raid5_conf_t *conf, + struct stripe_head *sh, int disks, struct bio **return_bi) +{ + int i; + struct r5dev *dev; + + for (i = disks; i--; ) + if (sh->dev[i].written) { + dev = &sh->dev[i]; + if (!test_bit(R5_LOCKED, &dev->flags) && + test_bit(R5_UPTODATE, &dev->flags)) { + /* We can return any write requests */ + struct bio *wbi, *wbi2; + int bitmap_end = 0; + pr_debug("Return write for disc %d\n", i); + spin_lock_irq(&conf->device_lock); + wbi = dev->written; + dev->written = NULL; + while (wbi && wbi->bi_sector < + dev->sector + STRIPE_SECTORS) { + wbi2 = r5_next_bio(wbi, dev->sector); + if (!raid5_dec_bi_phys_segments(wbi)) { + md_write_end(conf->mddev); + wbi->bi_next = *return_bi; + *return_bi = wbi; + } + wbi = wbi2; + } + if (dev->towrite == NULL) + bitmap_end = 1; + spin_unlock_irq(&conf->device_lock); + if (bitmap_end) + bitmap_endwrite(conf->mddev->bitmap, + sh->sector, + STRIPE_SECTORS, + !test_bit(STRIPE_DEGRADED, &sh->state), + 0); + } + } + + if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state)) + if (atomic_dec_and_test(&conf->pending_full_writes)) + md_wakeup_thread(conf->mddev->thread); +} + +static void handle_stripe_dirtying5(raid5_conf_t *conf, + struct stripe_head *sh, struct stripe_head_state *s, int disks) +{ + int rmw = 0, rcw = 0, i; + for (i = disks; i--; ) { + /* would I have to read this buffer for read_modify_write */ + struct r5dev *dev = &sh->dev[i]; + if ((dev->towrite || i == sh->pd_idx) && + !test_bit(R5_LOCKED, &dev->flags) && + !(test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags))) { + if (test_bit(R5_Insync, &dev->flags)) + rmw++; + else + rmw += 2*disks; /* cannot read it */ + } + /* Would I have to read this buffer for reconstruct_write */ + if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_idx && + !test_bit(R5_LOCKED, &dev->flags) && + !(test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags))) { + if (test_bit(R5_Insync, &dev->flags)) rcw++; + else + rcw += 2*disks; + } + } + pr_debug("for sector %llu, rmw=%d rcw=%d\n", + (unsigned long long)sh->sector, rmw, rcw); + set_bit(STRIPE_HANDLE, &sh->state); + if (rmw < rcw && rmw > 0) + /* prefer read-modify-write, but need to get some data */ + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if ((dev->towrite || i == sh->pd_idx) && + !test_bit(R5_LOCKED, &dev->flags) && + !(test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags)) && + test_bit(R5_Insync, &dev->flags)) { + if ( + test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { + pr_debug("Read_old block " + "%d for r-m-w\n", i); + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantread, &dev->flags); + s->locked++; + } else { + set_bit(STRIPE_DELAYED, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + } + } + } + if (rcw <= rmw && rcw > 0) + /* want reconstruct write, but need to get some data */ + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (!test_bit(R5_OVERWRITE, &dev->flags) && + i != sh->pd_idx && + !test_bit(R5_LOCKED, &dev->flags) && + !(test_bit(R5_UPTODATE, &dev->flags) || + test_bit(R5_Wantcompute, &dev->flags)) && + test_bit(R5_Insync, &dev->flags)) { + if ( + test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { + pr_debug("Read_old block " + "%d for Reconstruct\n", i); + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantread, &dev->flags); + s->locked++; + } else { + set_bit(STRIPE_DELAYED, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + } + } + } + /* now if nothing is locked, and if we have enough data, + * we can start a write request + */ + /* since handle_stripe can be called at any time we need to handle the + * case where a compute block operation has been submitted and then a + * subsequent call wants to start a write request. raid5_run_ops only + * handles the case where compute block and postxor are requested + * simultaneously. If this is not the case then new writes need to be + * held off until the compute completes. + */ + if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) && + (s->locked == 0 && (rcw == 0 || rmw == 0) && + !test_bit(STRIPE_BIT_DELAY, &sh->state))) + schedule_reconstruction5(sh, s, rcw == 0, 0); +} + +static void handle_stripe_dirtying6(raid5_conf_t *conf, + struct stripe_head *sh, struct stripe_head_state *s, + struct r6_state *r6s, int disks) +{ + int rcw = 0, must_compute = 0, pd_idx = sh->pd_idx, i; + int qd_idx = r6s->qd_idx; + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + /* Would I have to read this buffer for reconstruct_write */ + if (!test_bit(R5_OVERWRITE, &dev->flags) + && i != pd_idx && i != qd_idx + && (!test_bit(R5_LOCKED, &dev->flags) + ) && + !test_bit(R5_UPTODATE, &dev->flags)) { + if (test_bit(R5_Insync, &dev->flags)) rcw++; + else { + pr_debug("raid6: must_compute: " + "disk %d flags=%#lx\n", i, dev->flags); + must_compute++; + } + } + } + pr_debug("for sector %llu, rcw=%d, must_compute=%d\n", + (unsigned long long)sh->sector, rcw, must_compute); + set_bit(STRIPE_HANDLE, &sh->state); + + if (rcw > 0) + /* want reconstruct write, but need to get some data */ + for (i = disks; i--; ) { + struct r5dev *dev = &sh->dev[i]; + if (!test_bit(R5_OVERWRITE, &dev->flags) + && !(s->failed == 0 && (i == pd_idx || i == qd_idx)) + && !test_bit(R5_LOCKED, &dev->flags) && + !test_bit(R5_UPTODATE, &dev->flags) && + test_bit(R5_Insync, &dev->flags)) { + if ( + test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { + pr_debug("Read_old stripe %llu " + "block %d for Reconstruct\n", + (unsigned long long)sh->sector, i); + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantread, &dev->flags); + s->locked++; + } else { + pr_debug("Request delayed stripe %llu " + "block %d for Reconstruct\n", + (unsigned long long)sh->sector, i); + set_bit(STRIPE_DELAYED, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + } + } + } + /* now if nothing is locked, and if we have enough data, we can start a + * write request + */ + if (s->locked == 0 && rcw == 0 && + !test_bit(STRIPE_BIT_DELAY, &sh->state)) { + if (must_compute > 0) { + /* We have failed blocks and need to compute them */ + switch (s->failed) { + case 0: + BUG(); + case 1: + compute_block_1(sh, r6s->failed_num[0], 0); + break; + case 2: + compute_block_2(sh, r6s->failed_num[0], + r6s->failed_num[1]); + break; + default: /* This request should have been failed? */ + BUG(); + } + } + + pr_debug("Computing parity for stripe %llu\n", + (unsigned long long)sh->sector); + compute_parity6(sh, RECONSTRUCT_WRITE); + /* now every locked buffer is ready to be written */ + for (i = disks; i--; ) + if (test_bit(R5_LOCKED, &sh->dev[i].flags)) { + pr_debug("Writing stripe %llu block %d\n", + (unsigned long long)sh->sector, i); + s->locked++; + set_bit(R5_Wantwrite, &sh->dev[i].flags); + } + if (s->locked == disks) + if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state)) + atomic_inc(&conf->pending_full_writes); + /* after a RECONSTRUCT_WRITE, the stripe MUST be in-sync */ + set_bit(STRIPE_INSYNC, &sh->state); + + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { + atomic_dec(&conf->preread_active_stripes); + if (atomic_read(&conf->preread_active_stripes) < + IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); + } + } +} + +static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh, + struct stripe_head_state *s, int disks) +{ + struct r5dev *dev = NULL; + + set_bit(STRIPE_HANDLE, &sh->state); + + switch (sh->check_state) { + case check_state_idle: + /* start a new check operation if there are no failures */ + if (s->failed == 0) { + BUG_ON(s->uptodate != disks); + sh->check_state = check_state_run; + set_bit(STRIPE_OP_CHECK, &s->ops_request); + clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags); + s->uptodate--; + break; + } + dev = &sh->dev[s->failed_num]; + /* fall through */ + case check_state_compute_result: + sh->check_state = check_state_idle; + if (!dev) + dev = &sh->dev[sh->pd_idx]; + + /* check that a write has not made the stripe insync */ + if (test_bit(STRIPE_INSYNC, &sh->state)) + break; + + /* either failed parity check, or recovery is happening */ + BUG_ON(!test_bit(R5_UPTODATE, &dev->flags)); + BUG_ON(s->uptodate != disks); + + set_bit(R5_LOCKED, &dev->flags); + s->locked++; + set_bit(R5_Wantwrite, &dev->flags); + + clear_bit(STRIPE_DEGRADED, &sh->state); + set_bit(STRIPE_INSYNC, &sh->state); + break; + case check_state_run: + break; /* we will be called again upon completion */ + case check_state_check_result: + sh->check_state = check_state_idle; + + /* if a failure occurred during the check operation, leave + * STRIPE_INSYNC not set and let the stripe be handled again + */ + if (s->failed) + break; + + /* handle a successful check operation, if parity is correct + * we are done. Otherwise update the mismatch count and repair + * parity if !MD_RECOVERY_CHECK + */ + if (sh->ops.zero_sum_result == 0) + /* parity is correct (on disc, + * not in buffer any more) + */ + set_bit(STRIPE_INSYNC, &sh->state); + else { + conf->mddev->resync_mismatches += STRIPE_SECTORS; + if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) + /* don't try to repair!! */ + set_bit(STRIPE_INSYNC, &sh->state); + else { + sh->check_state = check_state_compute_run; + set_bit(STRIPE_COMPUTE_RUN, &sh->state); + set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request); + set_bit(R5_Wantcompute, + &sh->dev[sh->pd_idx].flags); + sh->ops.target = sh->pd_idx; + s->uptodate++; + } + } + break; + case check_state_compute_run: + break; + default: + printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n", + __func__, sh->check_state, + (unsigned long long) sh->sector); + BUG(); + } +} + + +static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh, + struct stripe_head_state *s, + struct r6_state *r6s, struct page *tmp_page, + int disks) +{ + int update_p = 0, update_q = 0; + struct r5dev *dev; + int pd_idx = sh->pd_idx; + int qd_idx = r6s->qd_idx; + + set_bit(STRIPE_HANDLE, &sh->state); + + BUG_ON(s->failed > 2); + BUG_ON(s->uptodate < disks); + /* Want to check and possibly repair P and Q. + * However there could be one 'failed' device, in which + * case we can only check one of them, possibly using the + * other to generate missing data + */ + + /* If !tmp_page, we cannot do the calculations, + * but as we have set STRIPE_HANDLE, we will soon be called + * by stripe_handle with a tmp_page - just wait until then. + */ + if (tmp_page) { + if (s->failed == r6s->q_failed) { + /* The only possible failed device holds 'Q', so it + * makes sense to check P (If anything else were failed, + * we would have used P to recreate it). + */ + compute_block_1(sh, pd_idx, 1); + if (!page_is_zero(sh->dev[pd_idx].page)) { + compute_block_1(sh, pd_idx, 0); + update_p = 1; + } + } + if (!r6s->q_failed && s->failed < 2) { + /* q is not failed, and we didn't use it to generate + * anything, so it makes sense to check it + */ + memcpy(page_address(tmp_page), + page_address(sh->dev[qd_idx].page), + STRIPE_SIZE); + compute_parity6(sh, UPDATE_PARITY); + if (memcmp(page_address(tmp_page), + page_address(sh->dev[qd_idx].page), + STRIPE_SIZE) != 0) { + clear_bit(STRIPE_INSYNC, &sh->state); + update_q = 1; + } + } + if (update_p || update_q) { + conf->mddev->resync_mismatches += STRIPE_SECTORS; + if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) + /* don't try to repair!! */ + update_p = update_q = 0; + } + + /* now write out any block on a failed drive, + * or P or Q if they need it + */ + + if (s->failed == 2) { + dev = &sh->dev[r6s->failed_num[1]]; + s->locked++; + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantwrite, &dev->flags); + } + if (s->failed >= 1) { + dev = &sh->dev[r6s->failed_num[0]]; + s->locked++; + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantwrite, &dev->flags); + } + + if (update_p) { + dev = &sh->dev[pd_idx]; + s->locked++; + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantwrite, &dev->flags); + } + if (update_q) { + dev = &sh->dev[qd_idx]; + s->locked++; + set_bit(R5_LOCKED, &dev->flags); + set_bit(R5_Wantwrite, &dev->flags); + } + clear_bit(STRIPE_DEGRADED, &sh->state); - overlap: - set_bit(R5_Overlap, &sh->dev[dd_idx].flags); - spin_unlock_irq(&conf->device_lock); - spin_unlock(&sh->lock); - return 0; + set_bit(STRIPE_INSYNC, &sh->state); + } } -static void end_reshape(raid5_conf_t *conf); - -static int page_is_zero(struct page *p) +static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh, + struct r6_state *r6s) { - char *a = page_address(p); - return ((*(u32*)a) == 0 && - memcmp(a, a+4, STRIPE_SIZE-4)==0); -} + int i; -static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks) -{ - int sectors_per_chunk = conf->chunk_size >> 9; - int pd_idx, dd_idx; - int chunk_offset = sector_div(stripe, sectors_per_chunk); + /* We have read all the blocks in this stripe and now we need to + * copy some of them into a target stripe for expand. + */ + struct dma_async_tx_descriptor *tx = NULL; + clear_bit(STRIPE_EXPAND_SOURCE, &sh->state); + for (i = 0; i < sh->disks; i++) + if (i != sh->pd_idx && (!r6s || i != r6s->qd_idx)) { + int dd_idx, pd_idx, j; + struct stripe_head *sh2; + + sector_t bn = compute_blocknr(sh, i); + sector_t s = raid5_compute_sector(bn, conf->raid_disks, + conf->raid_disks - + conf->max_degraded, &dd_idx, + &pd_idx, conf); + sh2 = get_active_stripe(conf, s, conf->raid_disks, + pd_idx, 1); + if (sh2 == NULL) + /* so far only the early blocks of this stripe + * have been requested. When later blocks + * get requested, we will try again + */ + continue; + if (!test_bit(STRIPE_EXPANDING, &sh2->state) || + test_bit(R5_Expanded, &sh2->dev[dd_idx].flags)) { + /* must have already done this block */ + release_stripe(sh2); + continue; + } - raid5_compute_sector(stripe * (disks - conf->max_degraded) - *sectors_per_chunk + chunk_offset, - disks, disks - conf->max_degraded, - &dd_idx, &pd_idx, conf); - return pd_idx; + /* place all the copies on one channel */ + tx = async_memcpy(sh2->dev[dd_idx].page, + sh->dev[i].page, 0, 0, STRIPE_SIZE, + ASYNC_TX_DEP_ACK, tx, NULL, NULL); + + set_bit(R5_Expanded, &sh2->dev[dd_idx].flags); + set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags); + for (j = 0; j < conf->raid_disks; j++) + if (j != sh2->pd_idx && + (!r6s || j != raid6_next_disk(sh2->pd_idx, + sh2->disks)) && + !test_bit(R5_Expanded, &sh2->dev[j].flags)) + break; + if (j == conf->raid_disks) { + set_bit(STRIPE_EXPAND_READY, &sh2->state); + set_bit(STRIPE_HANDLE, &sh2->state); + } + release_stripe(sh2); + + } + /* done submitting copies, wait for them to complete */ + if (tx) { + async_tx_ack(tx); + dma_wait_for_async_tx(tx); + } } @@ -1341,82 +2531,77 @@ static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks) * schedule a write of some buffers * return confirmation of parity correctness * - * Parity calculations are done inside the stripe lock * buffers are taken off read_list or write_list, and bh_cache buffers * get BH_Lock set before the stripe lock is released. * */ - -static void handle_stripe5(struct stripe_head *sh) + +static bool handle_stripe5(struct stripe_head *sh) { raid5_conf_t *conf = sh->raid_conf; - int disks = sh->disks; - struct bio *return_bi= NULL; - struct bio *bi; - int i; - int syncing, expanding, expanded; - int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0; - int non_overwrite = 0; - int failed_num=0; + int disks = sh->disks, i; + struct bio *return_bi = NULL; + struct stripe_head_state s; struct r5dev *dev; + mdk_rdev_t *blocked_rdev = NULL; + int prexor; - PRINTK("handling stripe %llu, cnt=%d, pd_idx=%d\n", - (unsigned long long)sh->sector, atomic_read(&sh->count), - sh->pd_idx); + memset(&s, 0, sizeof(s)); + pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d " + "reconstruct:%d\n", (unsigned long long)sh->sector, sh->state, + atomic_read(&sh->count), sh->pd_idx, sh->check_state, + sh->reconstruct_state); spin_lock(&sh->lock); clear_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); - syncing = test_bit(STRIPE_SYNCING, &sh->state); - expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state); - expanded = test_bit(STRIPE_EXPAND_READY, &sh->state); - /* Now to look around and see what can be done */ + s.syncing = test_bit(STRIPE_SYNCING, &sh->state); + s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state); + s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state); + /* Now to look around and see what can be done */ rcu_read_lock(); for (i=disks; i--; ) { mdk_rdev_t *rdev; - dev = &sh->dev[i]; + struct r5dev *dev = &sh->dev[i]; clear_bit(R5_Insync, &dev->flags); - PRINTK("check %d: state 0x%lx read %p write %p written %p\n", - i, dev->flags, dev->toread, dev->towrite, dev->written); - /* maybe we can reply to a read */ - if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) { - struct bio *rbi, *rbi2; - PRINTK("Return read for disc %d\n", i); - spin_lock_irq(&conf->device_lock); - rbi = dev->toread; - dev->toread = NULL; - if (test_and_clear_bit(R5_Overlap, &dev->flags)) - wake_up(&conf->wait_for_overlap); - spin_unlock_irq(&conf->device_lock); - while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) { - copy_data(0, rbi, dev->page, dev->sector); - rbi2 = r5_next_bio(rbi, dev->sector); - spin_lock_irq(&conf->device_lock); - if (--rbi->bi_phys_segments == 0) { - rbi->bi_next = return_bi; - return_bi = rbi; - } - spin_unlock_irq(&conf->device_lock); - rbi = rbi2; - } - } + pr_debug("check %d: state 0x%lx toread %p read %p write %p " + "written %p\n", i, dev->flags, dev->toread, dev->read, + dev->towrite, dev->written); - /* now count some things */ - if (test_bit(R5_LOCKED, &dev->flags)) locked++; - if (test_bit(R5_UPTODATE, &dev->flags)) uptodate++; + /* maybe we can request a biofill operation + * + * new wantfill requests are only permitted while + * ops_complete_biofill is guaranteed to be inactive + */ + if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread && + !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) + set_bit(R5_Wantfill, &dev->flags); - - if (dev->toread) to_read++; + /* now count some things */ + if (test_bit(R5_LOCKED, &dev->flags)) s.locked++; + if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++; + if (test_bit(R5_Wantcompute, &dev->flags)) s.compute++; + + if (test_bit(R5_Wantfill, &dev->flags)) + s.to_fill++; + else if (dev->toread) + s.to_read++; if (dev->towrite) { - to_write++; + s.to_write++; if (!test_bit(R5_OVERWRITE, &dev->flags)) - non_overwrite++; + s.non_overwrite++; } - if (dev->written) written++; + if (dev->written) + s.written++; rdev = rcu_dereference(conf->disks[i].rdev); + if (blocked_rdev == NULL && + rdev && unlikely(test_bit(Blocked, &rdev->flags))) { + blocked_rdev = rdev; + atomic_inc(&rdev->nr_pending); + } if (!rdev || !test_bit(In_sync, &rdev->flags)) { /* The ReadError flag will just be confusing now */ clear_bit(R5_ReadError, &dev->flags); @@ -1424,306 +2609,119 @@ static void handle_stripe5(struct stripe_head *sh) } if (!rdev || !test_bit(In_sync, &rdev->flags) || test_bit(R5_ReadError, &dev->flags)) { - failed++; - failed_num = i; + s.failed++; + s.failed_num = i; } else set_bit(R5_Insync, &dev->flags); } rcu_read_unlock(); - PRINTK("locked=%d uptodate=%d to_read=%d" + + if (unlikely(blocked_rdev)) { + if (s.syncing || s.expanding || s.expanded || + s.to_write || s.written) { + set_bit(STRIPE_HANDLE, &sh->state); + goto unlock; + } + /* There is nothing for the blocked_rdev to block */ + rdev_dec_pending(blocked_rdev, conf->mddev); + blocked_rdev = NULL; + } + + if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) { + set_bit(STRIPE_OP_BIOFILL, &s.ops_request); + set_bit(STRIPE_BIOFILL_RUN, &sh->state); + } + + pr_debug("locked=%d uptodate=%d to_read=%d" " to_write=%d failed=%d failed_num=%d\n", - locked, uptodate, to_read, to_write, failed, failed_num); + s.locked, s.uptodate, s.to_read, s.to_write, + s.failed, s.failed_num); /* check if the array has lost two devices and, if so, some requests might * need to be failed */ - if (failed > 1 && to_read+to_write+written) { - for (i=disks; i--; ) { - int bitmap_end = 0; - - if (test_bit(R5_ReadError, &sh->dev[i].flags)) { - mdk_rdev_t *rdev; - rcu_read_lock(); - rdev = rcu_dereference(conf->disks[i].rdev); - if (rdev && test_bit(In_sync, &rdev->flags)) - /* multiple read failures in one stripe */ - md_error(conf->mddev, rdev); - rcu_read_unlock(); - } - - spin_lock_irq(&conf->device_lock); - /* fail all writes first */ - bi = sh->dev[i].towrite; - sh->dev[i].towrite = NULL; - if (bi) { to_write--; bitmap_end = 1; } - - if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) - wake_up(&conf->wait_for_overlap); - - while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){ - struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector); - clear_bit(BIO_UPTODATE, &bi->bi_flags); - if (--bi->bi_phys_segments == 0) { - md_write_end(conf->mddev); - bi->bi_next = return_bi; - return_bi = bi; - } - bi = nextbi; - } - /* and fail all 'written' */ - bi = sh->dev[i].written; - sh->dev[i].written = NULL; - if (bi) bitmap_end = 1; - while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) { - struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector); - clear_bit(BIO_UPTODATE, &bi->bi_flags); - if (--bi->bi_phys_segments == 0) { - md_write_end(conf->mddev); - bi->bi_next = return_bi; - return_bi = bi; - } - bi = bi2; - } - - /* fail any reads if this device is non-operational */ - if (!test_bit(R5_Insync, &sh->dev[i].flags) || - test_bit(R5_ReadError, &sh->dev[i].flags)) { - bi = sh->dev[i].toread; - sh->dev[i].toread = NULL; - if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) - wake_up(&conf->wait_for_overlap); - if (bi) to_read--; - while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){ - struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector); - clear_bit(BIO_UPTODATE, &bi->bi_flags); - if (--bi->bi_phys_segments == 0) { - bi->bi_next = return_bi; - return_bi = bi; - } - bi = nextbi; - } - } - spin_unlock_irq(&conf->device_lock); - if (bitmap_end) - bitmap_endwrite(conf->mddev->bitmap, sh->sector, - STRIPE_SECTORS, 0, 0); - } - } - if (failed > 1 && syncing) { + if (s.failed > 1 && s.to_read+s.to_write+s.written) + handle_failed_stripe(conf, sh, &s, disks, &return_bi); + if (s.failed > 1 && s.syncing) { md_done_sync(conf->mddev, STRIPE_SECTORS,0); clear_bit(STRIPE_SYNCING, &sh->state); - syncing = 0; + s.syncing = 0; } /* might be able to return some write requests if the parity block * is safe, or on a failed drive */ dev = &sh->dev[sh->pd_idx]; - if ( written && - ( (test_bit(R5_Insync, &dev->flags) && !test_bit(R5_LOCKED, &dev->flags) && - test_bit(R5_UPTODATE, &dev->flags)) - || (failed == 1 && failed_num == sh->pd_idx)) - ) { - /* any written block on an uptodate or failed drive can be returned. - * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but - * never LOCKED, so we don't need to test 'failed' directly. - */ - for (i=disks; i--; ) - if (sh->dev[i].written) { - dev = &sh->dev[i]; - if (!test_bit(R5_LOCKED, &dev->flags) && - test_bit(R5_UPTODATE, &dev->flags) ) { - /* We can return any write requests */ - struct bio *wbi, *wbi2; - int bitmap_end = 0; - PRINTK("Return write for disc %d\n", i); - spin_lock_irq(&conf->device_lock); - wbi = dev->written; - dev->written = NULL; - while (wbi && wbi->bi_sector < dev->sector + STRIPE_SECTORS) { - wbi2 = r5_next_bio(wbi, dev->sector); - if (--wbi->bi_phys_segments == 0) { - md_write_end(conf->mddev); - wbi->bi_next = return_bi; - return_bi = wbi; - } - wbi = wbi2; - } - if (dev->towrite == NULL) - bitmap_end = 1; - spin_unlock_irq(&conf->device_lock); - if (bitmap_end) - bitmap_endwrite(conf->mddev->bitmap, sh->sector, - STRIPE_SECTORS, - !test_bit(STRIPE_DEGRADED, &sh->state), 0); - } - } - } + if ( s.written && + ((test_bit(R5_Insync, &dev->flags) && + !test_bit(R5_LOCKED, &dev->flags) && + test_bit(R5_UPTODATE, &dev->flags)) || + (s.failed == 1 && s.failed_num == sh->pd_idx))) + handle_stripe_clean_event(conf, sh, disks, &return_bi); /* Now we might consider reading some blocks, either to check/generate * parity, or to satisfy requests * or to load a block that is being partially written. */ - if (to_read || non_overwrite || (syncing && (uptodate < disks)) || expanding) { - for (i=disks; i--;) { - dev = &sh->dev[i]; - if (!test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) && - (dev->toread || - (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) || - syncing || - expanding || - (failed && (sh->dev[failed_num].toread || - (sh->dev[failed_num].towrite && !test_bit(R5_OVERWRITE, &sh->dev[failed_num].flags)))) - ) - ) { - /* we would like to get this block, possibly - * by computing it, but we might not be able to - */ - if (uptodate == disks-1) { - PRINTK("Computing block %d\n", i); - compute_block(sh, i); - uptodate++; - } else if (test_bit(R5_Insync, &dev->flags)) { - set_bit(R5_LOCKED, &dev->flags); - set_bit(R5_Wantread, &dev->flags); - locked++; - PRINTK("Reading block %d (sync=%d)\n", - i, syncing); - } - } - } - set_bit(STRIPE_HANDLE, &sh->state); - } + if (s.to_read || s.non_overwrite || + (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding) + handle_stripe_fill5(sh, &s, disks); - /* now to consider writing and what else, if anything should be read */ - if (to_write) { - int rmw=0, rcw=0; - for (i=disks ; i--;) { - /* would I have to read this buffer for read_modify_write */ + /* Now we check to see if any write operations have recently + * completed + */ + prexor = 0; + if (sh->reconstruct_state == reconstruct_state_prexor_drain_result) + prexor = 1; + if (sh->reconstruct_state == reconstruct_state_drain_result || + sh->reconstruct_state == reconstruct_state_prexor_drain_result) { + sh->reconstruct_state = reconstruct_state_idle; + + /* All the 'written' buffers and the parity block are ready to + * be written back to disk + */ + BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags)); + for (i = disks; i--; ) { dev = &sh->dev[i]; - if ((dev->towrite || i == sh->pd_idx) && - (!test_bit(R5_LOCKED, &dev->flags) - ) && - !test_bit(R5_UPTODATE, &dev->flags)) { - if (test_bit(R5_Insync, &dev->flags) -/* && !(!mddev->insync && i == sh->pd_idx) */ - ) - rmw++; - else rmw += 2*disks; /* cannot read it */ - } - /* Would I have to read this buffer for reconstruct_write */ - if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_idx && - (!test_bit(R5_LOCKED, &dev->flags) - ) && - !test_bit(R5_UPTODATE, &dev->flags)) { - if (test_bit(R5_Insync, &dev->flags)) rcw++; - else rcw += 2*disks; + if (test_bit(R5_LOCKED, &dev->flags) && + (i == sh->pd_idx || dev->written)) { + pr_debug("Writing block %d\n", i); + set_bit(R5_Wantwrite, &dev->flags); + if (prexor) + continue; + if (!test_bit(R5_Insync, &dev->flags) || + (i == sh->pd_idx && s.failed == 0)) + set_bit(STRIPE_INSYNC, &sh->state); } } - PRINTK("for sector %llu, rmw=%d rcw=%d\n", - (unsigned long long)sh->sector, rmw, rcw); - set_bit(STRIPE_HANDLE, &sh->state); - if (rmw < rcw && rmw > 0) - /* prefer read-modify-write, but need to get some data */ - for (i=disks; i--;) { - dev = &sh->dev[i]; - if ((dev->towrite || i == sh->pd_idx) && - !test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) && - test_bit(R5_Insync, &dev->flags)) { - if (test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) - { - PRINTK("Read_old block %d for r-m-w\n", i); - set_bit(R5_LOCKED, &dev->flags); - set_bit(R5_Wantread, &dev->flags); - locked++; - } else { - set_bit(STRIPE_DELAYED, &sh->state); - set_bit(STRIPE_HANDLE, &sh->state); - } - } - } - if (rcw <= rmw && rcw > 0) - /* want reconstruct write, but need to get some data */ - for (i=disks; i--;) { - dev = &sh->dev[i]; - if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_idx && - !test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) && - test_bit(R5_Insync, &dev->flags)) { - if (test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) - { - PRINTK("Read_old block %d for Reconstruct\n", i); - set_bit(R5_LOCKED, &dev->flags); - set_bit(R5_Wantread, &dev->flags); - locked++; - } else { - set_bit(STRIPE_DELAYED, &sh->state); - set_bit(STRIPE_HANDLE, &sh->state); - } - } - } - /* now if nothing is locked, and if we have enough data, we can start a write request */ - if (locked == 0 && (rcw == 0 ||rmw == 0) && - !test_bit(STRIPE_BIT_DELAY, &sh->state)) { - PRINTK("Computing parity...\n"); - compute_parity5(sh, rcw==0 ? RECONSTRUCT_WRITE : READ_MODIFY_WRITE); - /* now every locked buffer is ready to be written */ - for (i=disks; i--;) - if (test_bit(R5_LOCKED, &sh->dev[i].flags)) { - PRINTK("Writing block %d\n", i); - locked++; - set_bit(R5_Wantwrite, &sh->dev[i].flags); - if (!test_bit(R5_Insync, &sh->dev[i].flags) - || (i==sh->pd_idx && failed == 0)) - set_bit(STRIPE_INSYNC, &sh->state); - } - if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { - atomic_dec(&conf->preread_active_stripes); - if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) - md_wakeup_thread(conf->mddev->thread); - } + if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { + atomic_dec(&conf->preread_active_stripes); + if (atomic_read(&conf->preread_active_stripes) < + IO_THRESHOLD) + md_wakeup_thread(conf->mddev->thread); } } + /* Now to consider new write requests and what else, if anything + * should be read. We do not handle new writes when: + * 1/ A 'write' operation (copy+xor) is already in flight. + * 2/ A 'check' operation is in flight, as it may clobber the parity + * block. + */ + if (s.to_write && !sh->reconstruct_state && !sh->check_state) + handle_stripe_dirtying5(conf, sh, &s, disks); + /* maybe we need to check and possibly fix the parity for this stripe - * Any reads will already have been scheduled, so we just see if enough data - * is available + * Any reads will already have been scheduled, so we just see if enough + * data is available. The parity check is held off while parity + * dependent operations are in flight. */ - if (syncing && locked == 0 && - !test_bit(STRIPE_INSYNC, &sh->state)) { - set_bit(STRIPE_HANDLE, &sh->state); - if (failed == 0) { - BUG_ON(uptodate != disks); - compute_parity5(sh, CHECK_PARITY); - uptodate--; - if (page_is_zero(sh->dev[sh->pd_idx].page)) { - /* parity is correct (on disc, not in buffer any more) */ - set_bit(STRIPE_INSYNC, &sh->state); - } else { - conf->mddev->resync_mismatches += STRIPE_SECTORS; - if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) - /* don't try to repair!! */ - set_bit(STRIPE_INSYNC, &sh->state); - else { - compute_block(sh, sh->pd_idx); - uptodate++; - } - } - } - if (!test_bit(STRIPE_INSYNC, &sh->state)) { - /* either failed parity check, or recovery is happening */ - if (failed==0) - failed_num = sh->pd_idx; - dev = &sh->dev[failed_num]; - BUG_ON(!test_bit(R5_UPTODATE, &dev->flags)); - BUG_ON(uptodate != disks); + if (sh->check_state || + (s.syncing && s.locked == 0 && + !test_bit(STRIPE_COMPUTE_RUN, &sh->state) && + !test_bit(STRIPE_INSYNC, &sh->state))) + handle_parity_checks5(conf, sh, &s, disks); - set_bit(R5_LOCKED, &dev->flags); - set_bit(R5_Wantwrite, &dev->flags); - clear_bit(STRIPE_DEGRADED, &sh->state); - locked++; - set_bit(STRIPE_INSYNC, &sh->state); - } - } - if (syncing && locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) { + if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) { md_done_sync(conf->mddev, STRIPE_SECTORS,1); clear_bit(STRIPE_SYNCING, &sh->state); } @@ -1731,184 +2729,96 @@ static void handle_stripe5(struct stripe_head *sh) /* If the failed drive is just a ReadError, then we might need to progress * the repair/check process */ - if (failed == 1 && ! conf->mddev->ro && - test_bit(R5_ReadError, &sh->dev[failed_num].flags) - && !test_bit(R5_LOCKED, &sh->dev[failed_num].flags) - && test_bit(R5_UPTODATE, &sh->dev[failed_num].flags) + if (s.failed == 1 && !conf->mddev->ro && + test_bit(R5_ReadError, &sh->dev[s.failed_num].flags) + && !test_bit(R5_LOCKED, &sh->dev[s.failed_num].flags) + && test_bit(R5_UPTODATE, &sh->dev[s.failed_num].flags) ) { - dev = &sh->dev[failed_num]; + dev = &sh->dev[s.failed_num]; if (!test_bit(R5_ReWrite, &dev->flags)) { set_bit(R5_Wantwrite, &dev->flags); set_bit(R5_ReWrite, &dev->flags); set_bit(R5_LOCKED, &dev->flags); - locked++; + s.locked++; } else { /* let's read it back */ set_bit(R5_Wantread, &dev->flags); set_bit(R5_LOCKED, &dev->flags); - locked++; + s.locked++; } } - if (expanded && test_bit(STRIPE_EXPANDING, &sh->state)) { - /* Need to write out all blocks after computing parity */ - sh->disks = conf->raid_disks; - sh->pd_idx = stripe_to_pdidx(sh->sector, conf, conf->raid_disks); - compute_parity5(sh, RECONSTRUCT_WRITE); - for (i= conf->raid_disks; i--;) { - set_bit(R5_LOCKED, &sh->dev[i].flags); - locked++; + /* Finish reconstruct operations initiated by the expansion process */ + if (sh->reconstruct_state == reconstruct_state_result) { + sh->reconstruct_state = reconstruct_state_idle; + clear_bit(STRIPE_EXPANDING, &sh->state); + for (i = conf->raid_disks; i--; ) { set_bit(R5_Wantwrite, &sh->dev[i].flags); + set_bit(R5_LOCKED, &sh->dev[i].flags); + s.locked++; } - clear_bit(STRIPE_EXPANDING, &sh->state); - } else if (expanded) { + } + + if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) && + !sh->reconstruct_state) { + /* Need to write out all blocks after computing parity */ + sh->disks = conf->raid_disks; + sh->pd_idx = stripe_to_pdidx(sh->sector, conf, + conf->raid_disks); + schedule_reconstruction5(sh, &s, 1, 1); + } else if (s.expanded && !sh->reconstruct_state && s.locked == 0) { clear_bit(STRIPE_EXPAND_READY, &sh->state); atomic_dec(&conf->reshape_stripes); wake_up(&conf->wait_for_overlap); md_done_sync(conf->mddev, STRIPE_SECTORS, 1); } - if (expanding && locked == 0) { - /* We have read all the blocks in this stripe and now we need to - * copy some of them into a target stripe for expand. - */ - clear_bit(STRIPE_EXPAND_SOURCE, &sh->state); - for (i=0; i< sh->disks; i++) - if (i != sh->pd_idx) { - int dd_idx, pd_idx, j; - struct stripe_head *sh2; - - sector_t bn = compute_blocknr(sh, i); - sector_t s = raid5_compute_sector(bn, conf->raid_disks, - conf->raid_disks-1, - &dd_idx, &pd_idx, conf); - sh2 = get_active_stripe(conf, s, conf->raid_disks, pd_idx, 1); - if (sh2 == NULL) - /* so far only the early blocks of this stripe - * have been requested. When later blocks - * get requested, we will try again - */ - continue; - if(!test_bit(STRIPE_EXPANDING, &sh2->state) || - test_bit(R5_Expanded, &sh2->dev[dd_idx].flags)) { - /* must have already done this block */ - release_stripe(sh2); - continue; - } - memcpy(page_address(sh2->dev[dd_idx].page), - page_address(sh->dev[i].page), - STRIPE_SIZE); - set_bit(R5_Expanded, &sh2->dev[dd_idx].flags); - set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags); - for (j=0; jraid_disks; j++) - if (j != sh2->pd_idx && - !test_bit(R5_Expanded, &sh2->dev[j].flags)) - break; - if (j == conf->raid_disks) { - set_bit(STRIPE_EXPAND_READY, &sh2->state); - set_bit(STRIPE_HANDLE, &sh2->state); - } - release_stripe(sh2); - } - } + if (s.expanding && s.locked == 0 && + !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) + handle_stripe_expansion(conf, sh, NULL); + unlock: spin_unlock(&sh->lock); - while ((bi=return_bi)) { - int bytes = bi->bi_size; + /* wait for this device to become unblocked */ + if (unlikely(blocked_rdev)) + md_wait_for_blocked_rdev(blocked_rdev, conf->mddev); - return_bi = bi->bi_next; - bi->bi_next = NULL; - bi->bi_size = 0; - bi->bi_end_io(bi, bytes, - test_bit(BIO_UPTODATE, &bi->bi_flags) - ? 0 : -EIO); - } - for (i=disks; i-- ;) { - int rw; - struct bio *bi; - mdk_rdev_t *rdev; - if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) - rw = WRITE; - else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags)) - rw = READ; - else - continue; - - bi = &sh->dev[i].req; - - bi->bi_rw = rw; - if (rw == WRITE) - bi->bi_end_io = raid5_end_write_request; - else - bi->bi_end_io = raid5_end_read_request; - - rcu_read_lock(); - rdev = rcu_dereference(conf->disks[i].rdev); - if (rdev && test_bit(Faulty, &rdev->flags)) - rdev = NULL; - if (rdev) - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - - if (rdev) { - if (syncing || expanding || expanded) - md_sync_acct(rdev->bdev, STRIPE_SECTORS); + if (s.ops_request) + raid5_run_ops(sh, s.ops_request); - bi->bi_bdev = rdev->bdev; - PRINTK("for %llu schedule op %ld on disc %d\n", - (unsigned long long)sh->sector, bi->bi_rw, i); - atomic_inc(&sh->count); - bi->bi_sector = sh->sector + rdev->data_offset; - bi->bi_flags = 1 << BIO_UPTODATE; - bi->bi_vcnt = 1; - bi->bi_max_vecs = 1; - bi->bi_idx = 0; - bi->bi_io_vec = &sh->dev[i].vec; - bi->bi_io_vec[0].bv_len = STRIPE_SIZE; - bi->bi_io_vec[0].bv_offset = 0; - bi->bi_size = STRIPE_SIZE; - bi->bi_next = NULL; - if (rw == WRITE && - test_bit(R5_ReWrite, &sh->dev[i].flags)) - atomic_add(STRIPE_SECTORS, &rdev->corrected_errors); - generic_make_request(bi); - } else { - if (rw == WRITE) - set_bit(STRIPE_DEGRADED, &sh->state); - PRINTK("skip op %ld on disc %d for sector %llu\n", - bi->bi_rw, i, (unsigned long long)sh->sector); - clear_bit(R5_LOCKED, &sh->dev[i].flags); - set_bit(STRIPE_HANDLE, &sh->state); - } - } + ops_run_io(sh, &s); + + return_io(return_bi); + + return blocked_rdev == NULL; } -static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) +static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page) { raid6_conf_t *conf = sh->raid_conf; - int disks = conf->raid_disks; - struct bio *return_bi= NULL; - struct bio *bi; - int i; - int syncing; - int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0; - int non_overwrite = 0; - int failed_num[2] = {0, 0}; + int disks = sh->disks; + struct bio *return_bi = NULL; + int i, pd_idx = sh->pd_idx; + struct stripe_head_state s; + struct r6_state r6s; struct r5dev *dev, *pdev, *qdev; - int pd_idx = sh->pd_idx; - int qd_idx = raid6_next_disk(pd_idx, disks); - int p_failed, q_failed; + mdk_rdev_t *blocked_rdev = NULL; - PRINTK("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d, qd_idx=%d\n", - (unsigned long long)sh->sector, sh->state, atomic_read(&sh->count), - pd_idx, qd_idx); + r6s.qd_idx = raid6_next_disk(pd_idx, disks); + pr_debug("handling stripe %llu, state=%#lx cnt=%d, " + "pd_idx=%d, qd_idx=%d\n", + (unsigned long long)sh->sector, sh->state, + atomic_read(&sh->count), pd_idx, r6s.qd_idx); + memset(&s, 0, sizeof(s)); spin_lock(&sh->lock); clear_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); - syncing = test_bit(STRIPE_SYNCING, &sh->state); + s.syncing = test_bit(STRIPE_SYNCING, &sh->state); + s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state); + s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state); /* Now to look around and see what can be done */ rcu_read_lock(); @@ -1917,12 +2827,12 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) dev = &sh->dev[i]; clear_bit(R5_Insync, &dev->flags); - PRINTK("check %d: state 0x%lx read %p write %p written %p\n", + pr_debug("check %d: state 0x%lx read %p write %p written %p\n", i, dev->flags, dev->toread, dev->towrite, dev->written); /* maybe we can reply to a read */ if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) { struct bio *rbi, *rbi2; - PRINTK("Return read for disc %d\n", i); + pr_debug("Return read for disc %d\n", i); spin_lock_irq(&conf->device_lock); rbi = dev->toread; dev->toread = NULL; @@ -1933,7 +2843,7 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) copy_data(0, rbi, dev->page, dev->sector); rbi2 = r5_next_bio(rbi, dev->sector); spin_lock_irq(&conf->device_lock); - if (--rbi->bi_phys_segments == 0) { + if (!raid5_dec_bi_phys_segments(rbi)) { rbi->bi_next = return_bi; return_bi = rbi; } @@ -1943,18 +2853,25 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) } /* now count some things */ - if (test_bit(R5_LOCKED, &dev->flags)) locked++; - if (test_bit(R5_UPTODATE, &dev->flags)) uptodate++; + if (test_bit(R5_LOCKED, &dev->flags)) s.locked++; + if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++; - if (dev->toread) to_read++; + if (dev->toread) + s.to_read++; if (dev->towrite) { - to_write++; + s.to_write++; if (!test_bit(R5_OVERWRITE, &dev->flags)) - non_overwrite++; + s.non_overwrite++; } - if (dev->written) written++; + if (dev->written) + s.written++; rdev = rcu_dereference(conf->disks[i].rdev); + if (blocked_rdev == NULL && + rdev && unlikely(test_bit(Blocked, &rdev->flags))) { + blocked_rdev = rdev; + atomic_inc(&rdev->nr_pending); + } if (!rdev || !test_bit(In_sync, &rdev->flags)) { /* The ReadError flag will just be confusing now */ clear_bit(R5_ReadError, &dev->flags); @@ -1962,96 +2879,38 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) } if (!rdev || !test_bit(In_sync, &rdev->flags) || test_bit(R5_ReadError, &dev->flags)) { - if ( failed < 2 ) - failed_num[failed] = i; - failed++; + if (s.failed < 2) + r6s.failed_num[s.failed] = i; + s.failed++; } else set_bit(R5_Insync, &dev->flags); } rcu_read_unlock(); - PRINTK("locked=%d uptodate=%d to_read=%d" - " to_write=%d failed=%d failed_num=%d,%d\n", - locked, uptodate, to_read, to_write, failed, - failed_num[0], failed_num[1]); - /* check if the array has lost >2 devices and, if so, some requests might - * need to be failed - */ - if (failed > 2 && to_read+to_write+written) { - for (i=disks; i--; ) { - int bitmap_end = 0; - - if (test_bit(R5_ReadError, &sh->dev[i].flags)) { - mdk_rdev_t *rdev; - rcu_read_lock(); - rdev = rcu_dereference(conf->disks[i].rdev); - if (rdev && test_bit(In_sync, &rdev->flags)) - /* multiple read failures in one stripe */ - md_error(conf->mddev, rdev); - rcu_read_unlock(); - } - - spin_lock_irq(&conf->device_lock); - /* fail all writes first */ - bi = sh->dev[i].towrite; - sh->dev[i].towrite = NULL; - if (bi) { to_write--; bitmap_end = 1; } - - if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) - wake_up(&conf->wait_for_overlap); - - while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){ - struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector); - clear_bit(BIO_UPTODATE, &bi->bi_flags); - if (--bi->bi_phys_segments == 0) { - md_write_end(conf->mddev); - bi->bi_next = return_bi; - return_bi = bi; - } - bi = nextbi; - } - /* and fail all 'written' */ - bi = sh->dev[i].written; - sh->dev[i].written = NULL; - if (bi) bitmap_end = 1; - while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) { - struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector); - clear_bit(BIO_UPTODATE, &bi->bi_flags); - if (--bi->bi_phys_segments == 0) { - md_write_end(conf->mddev); - bi->bi_next = return_bi; - return_bi = bi; - } - bi = bi2; - } - /* fail any reads if this device is non-operational */ - if (!test_bit(R5_Insync, &sh->dev[i].flags) || - test_bit(R5_ReadError, &sh->dev[i].flags)) { - bi = sh->dev[i].toread; - sh->dev[i].toread = NULL; - if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) - wake_up(&conf->wait_for_overlap); - if (bi) to_read--; - while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){ - struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector); - clear_bit(BIO_UPTODATE, &bi->bi_flags); - if (--bi->bi_phys_segments == 0) { - bi->bi_next = return_bi; - return_bi = bi; - } - bi = nextbi; - } - } - spin_unlock_irq(&conf->device_lock); - if (bitmap_end) - bitmap_endwrite(conf->mddev->bitmap, sh->sector, - STRIPE_SECTORS, 0, 0); + if (unlikely(blocked_rdev)) { + if (s.syncing || s.expanding || s.expanded || + s.to_write || s.written) { + set_bit(STRIPE_HANDLE, &sh->state); + goto unlock; } + /* There is nothing for the blocked_rdev to block */ + rdev_dec_pending(blocked_rdev, conf->mddev); + blocked_rdev = NULL; } - if (failed > 2 && syncing) { + + pr_debug("locked=%d uptodate=%d to_read=%d" + " to_write=%d failed=%d failed_num=%d,%d\n", + s.locked, s.uptodate, s.to_read, s.to_write, s.failed, + r6s.failed_num[0], r6s.failed_num[1]); + /* check if the array has lost >2 devices and, if so, some requests + * might need to be failed + */ + if (s.failed > 2 && s.to_read+s.to_write+s.written) + handle_failed_stripe(conf, sh, &s, disks, &return_bi); + if (s.failed > 2 && s.syncing) { md_done_sync(conf->mddev, STRIPE_SECTORS,0); clear_bit(STRIPE_SYNCING, &sh->state); - syncing = 0; + s.syncing = 0; } /* @@ -2059,277 +2918,41 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) * are safe, or on a failed drive */ pdev = &sh->dev[pd_idx]; - p_failed = (failed >= 1 && failed_num[0] == pd_idx) - || (failed >= 2 && failed_num[1] == pd_idx); - qdev = &sh->dev[qd_idx]; - q_failed = (failed >= 1 && failed_num[0] == qd_idx) - || (failed >= 2 && failed_num[1] == qd_idx); - - if ( written && - ( p_failed || ((test_bit(R5_Insync, &pdev->flags) + r6s.p_failed = (s.failed >= 1 && r6s.failed_num[0] == pd_idx) + || (s.failed >= 2 && r6s.failed_num[1] == pd_idx); + qdev = &sh->dev[r6s.qd_idx]; + r6s.q_failed = (s.failed >= 1 && r6s.failed_num[0] == r6s.qd_idx) + || (s.failed >= 2 && r6s.failed_num[1] == r6s.qd_idx); + + if ( s.written && + ( r6s.p_failed || ((test_bit(R5_Insync, &pdev->flags) && !test_bit(R5_LOCKED, &pdev->flags) - && test_bit(R5_UPTODATE, &pdev->flags))) ) && - ( q_failed || ((test_bit(R5_Insync, &qdev->flags) + && test_bit(R5_UPTODATE, &pdev->flags)))) && + ( r6s.q_failed || ((test_bit(R5_Insync, &qdev->flags) && !test_bit(R5_LOCKED, &qdev->flags) - && test_bit(R5_UPTODATE, &qdev->flags))) ) ) { - /* any written block on an uptodate or failed drive can be - * returned. Note that if we 'wrote' to a failed drive, - * it will be UPTODATE, but never LOCKED, so we don't need - * to test 'failed' directly. - */ - for (i=disks; i--; ) - if (sh->dev[i].written) { - dev = &sh->dev[i]; - if (!test_bit(R5_LOCKED, &dev->flags) && - test_bit(R5_UPTODATE, &dev->flags) ) { - /* We can return any write requests */ - int bitmap_end = 0; - struct bio *wbi, *wbi2; - PRINTK("Return write for stripe %llu disc %d\n", - (unsigned long long)sh->sector, i); - spin_lock_irq(&conf->device_lock); - wbi = dev->written; - dev->written = NULL; - while (wbi && wbi->bi_sector < dev->sector + STRIPE_SECTORS) { - wbi2 = r5_next_bio(wbi, dev->sector); - if (--wbi->bi_phys_segments == 0) { - md_write_end(conf->mddev); - wbi->bi_next = return_bi; - return_bi = wbi; - } - wbi = wbi2; - } - if (dev->towrite == NULL) - bitmap_end = 1; - spin_unlock_irq(&conf->device_lock); - if (bitmap_end) - bitmap_endwrite(conf->mddev->bitmap, sh->sector, - STRIPE_SECTORS, - !test_bit(STRIPE_DEGRADED, &sh->state), 0); - } - } - } + && test_bit(R5_UPTODATE, &qdev->flags))))) + handle_stripe_clean_event(conf, sh, disks, &return_bi); /* Now we might consider reading some blocks, either to check/generate * parity, or to satisfy requests * or to load a block that is being partially written. */ - if (to_read || non_overwrite || (to_write && failed) || (syncing && (uptodate < disks))) { - for (i=disks; i--;) { - dev = &sh->dev[i]; - if (!test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) && - (dev->toread || - (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) || - syncing || - (failed >= 1 && (sh->dev[failed_num[0]].toread || to_write)) || - (failed >= 2 && (sh->dev[failed_num[1]].toread || to_write)) - ) - ) { - /* we would like to get this block, possibly - * by computing it, but we might not be able to - */ - if (uptodate == disks-1) { - PRINTK("Computing stripe %llu block %d\n", - (unsigned long long)sh->sector, i); - compute_block_1(sh, i, 0); - uptodate++; - } else if ( uptodate == disks-2 && failed >= 2 ) { - /* Computing 2-failure is *very* expensive; only do it if failed >= 2 */ - int other; - for (other=disks; other--;) { - if ( other == i ) - continue; - if ( !test_bit(R5_UPTODATE, &sh->dev[other].flags) ) - break; - } - BUG_ON(other < 0); - PRINTK("Computing stripe %llu blocks %d,%d\n", - (unsigned long long)sh->sector, i, other); - compute_block_2(sh, i, other); - uptodate += 2; - } else if (test_bit(R5_Insync, &dev->flags)) { - set_bit(R5_LOCKED, &dev->flags); - set_bit(R5_Wantread, &dev->flags); - locked++; - PRINTK("Reading block %d (sync=%d)\n", - i, syncing); - } - } - } - set_bit(STRIPE_HANDLE, &sh->state); - } + if (s.to_read || s.non_overwrite || (s.to_write && s.failed) || + (s.syncing && (s.uptodate < disks)) || s.expanding) + handle_stripe_fill6(sh, &s, &r6s, disks); /* now to consider writing and what else, if anything should be read */ - if (to_write) { - int rcw=0, must_compute=0; - for (i=disks ; i--;) { - dev = &sh->dev[i]; - /* Would I have to read this buffer for reconstruct_write */ - if (!test_bit(R5_OVERWRITE, &dev->flags) - && i != pd_idx && i != qd_idx - && (!test_bit(R5_LOCKED, &dev->flags) - ) && - !test_bit(R5_UPTODATE, &dev->flags)) { - if (test_bit(R5_Insync, &dev->flags)) rcw++; - else { - PRINTK("raid6: must_compute: disk %d flags=%#lx\n", i, dev->flags); - must_compute++; - } - } - } - PRINTK("for sector %llu, rcw=%d, must_compute=%d\n", - (unsigned long long)sh->sector, rcw, must_compute); - set_bit(STRIPE_HANDLE, &sh->state); - - if (rcw > 0) - /* want reconstruct write, but need to get some data */ - for (i=disks; i--;) { - dev = &sh->dev[i]; - if (!test_bit(R5_OVERWRITE, &dev->flags) - && !(failed == 0 && (i == pd_idx || i == qd_idx)) - && !test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) && - test_bit(R5_Insync, &dev->flags)) { - if (test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) - { - PRINTK("Read_old stripe %llu block %d for Reconstruct\n", - (unsigned long long)sh->sector, i); - set_bit(R5_LOCKED, &dev->flags); - set_bit(R5_Wantread, &dev->flags); - locked++; - } else { - PRINTK("Request delayed stripe %llu block %d for Reconstruct\n", - (unsigned long long)sh->sector, i); - set_bit(STRIPE_DELAYED, &sh->state); - set_bit(STRIPE_HANDLE, &sh->state); - } - } - } - /* now if nothing is locked, and if we have enough data, we can start a write request */ - if (locked == 0 && rcw == 0 && - !test_bit(STRIPE_BIT_DELAY, &sh->state)) { - if ( must_compute > 0 ) { - /* We have failed blocks and need to compute them */ - switch ( failed ) { - case 0: BUG(); - case 1: compute_block_1(sh, failed_num[0], 0); break; - case 2: compute_block_2(sh, failed_num[0], failed_num[1]); break; - default: BUG(); /* This request should have been failed? */ - } - } - - PRINTK("Computing parity for stripe %llu\n", (unsigned long long)sh->sector); - compute_parity6(sh, RECONSTRUCT_WRITE); - /* now every locked buffer is ready to be written */ - for (i=disks; i--;) - if (test_bit(R5_LOCKED, &sh->dev[i].flags)) { - PRINTK("Writing stripe %llu block %d\n", - (unsigned long long)sh->sector, i); - locked++; - set_bit(R5_Wantwrite, &sh->dev[i].flags); - } - /* after a RECONSTRUCT_WRITE, the stripe MUST be in-sync */ - set_bit(STRIPE_INSYNC, &sh->state); - - if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { - atomic_dec(&conf->preread_active_stripes); - if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) - md_wakeup_thread(conf->mddev->thread); - } - } - } + if (s.to_write) + handle_stripe_dirtying6(conf, sh, &s, &r6s, disks); /* maybe we need to check and possibly fix the parity for this stripe - * Any reads will already have been scheduled, so we just see if enough data - * is available + * Any reads will already have been scheduled, so we just see if enough + * data is available */ - if (syncing && locked == 0 && !test_bit(STRIPE_INSYNC, &sh->state)) { - int update_p = 0, update_q = 0; - struct r5dev *dev; - - set_bit(STRIPE_HANDLE, &sh->state); - - BUG_ON(failed>2); - BUG_ON(uptodate < disks); - /* Want to check and possibly repair P and Q. - * However there could be one 'failed' device, in which - * case we can only check one of them, possibly using the - * other to generate missing data - */ - - /* If !tmp_page, we cannot do the calculations, - * but as we have set STRIPE_HANDLE, we will soon be called - * by stripe_handle with a tmp_page - just wait until then. - */ - if (tmp_page) { - if (failed == q_failed) { - /* The only possible failed device holds 'Q', so it makes - * sense to check P (If anything else were failed, we would - * have used P to recreate it). - */ - compute_block_1(sh, pd_idx, 1); - if (!page_is_zero(sh->dev[pd_idx].page)) { - compute_block_1(sh,pd_idx,0); - update_p = 1; - } - } - if (!q_failed && failed < 2) { - /* q is not failed, and we didn't use it to generate - * anything, so it makes sense to check it - */ - memcpy(page_address(tmp_page), - page_address(sh->dev[qd_idx].page), - STRIPE_SIZE); - compute_parity6(sh, UPDATE_PARITY); - if (memcmp(page_address(tmp_page), - page_address(sh->dev[qd_idx].page), - STRIPE_SIZE)!= 0) { - clear_bit(STRIPE_INSYNC, &sh->state); - update_q = 1; - } - } - if (update_p || update_q) { - conf->mddev->resync_mismatches += STRIPE_SECTORS; - if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) - /* don't try to repair!! */ - update_p = update_q = 0; - } - - /* now write out any block on a failed drive, - * or P or Q if they need it - */ - - if (failed == 2) { - dev = &sh->dev[failed_num[1]]; - locked++; - set_bit(R5_LOCKED, &dev->flags); - set_bit(R5_Wantwrite, &dev->flags); - } - if (failed >= 1) { - dev = &sh->dev[failed_num[0]]; - locked++; - set_bit(R5_LOCKED, &dev->flags); - set_bit(R5_Wantwrite, &dev->flags); - } - - if (update_p) { - dev = &sh->dev[pd_idx]; - locked ++; - set_bit(R5_LOCKED, &dev->flags); - set_bit(R5_Wantwrite, &dev->flags); - } - if (update_q) { - dev = &sh->dev[qd_idx]; - locked++; - set_bit(R5_LOCKED, &dev->flags); - set_bit(R5_Wantwrite, &dev->flags); - } - clear_bit(STRIPE_DEGRADED, &sh->state); - - set_bit(STRIPE_INSYNC, &sh->state); - } - } + if (s.syncing && s.locked == 0 && !test_bit(STRIPE_INSYNC, &sh->state)) + handle_parity_checks6(conf, sh, &s, &r6s, tmp_page, disks); - if (syncing && locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) { + if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) { md_done_sync(conf->mddev, STRIPE_SECTORS,1); clear_bit(STRIPE_SYNCING, &sh->state); } @@ -2337,9 +2960,9 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) /* If the failed drives are just a ReadError, then we might need * to progress the repair/check process */ - if (failed <= 2 && ! conf->mddev->ro) - for (i=0; idev[failed_num[i]]; + if (s.failed <= 2 && !conf->mddev->ro) + for (i = 0; i < s.failed; i++) { + dev = &sh->dev[r6s.failed_num[i]]; if (test_bit(R5_ReadError, &dev->flags) && !test_bit(R5_LOCKED, &dev->flags) && test_bit(R5_UPTODATE, &dev->flags) @@ -2355,84 +2978,51 @@ static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page) } } } - spin_unlock(&sh->lock); - - while ((bi=return_bi)) { - int bytes = bi->bi_size; - return_bi = bi->bi_next; - bi->bi_next = NULL; - bi->bi_size = 0; - bi->bi_end_io(bi, bytes, - test_bit(BIO_UPTODATE, &bi->bi_flags) - ? 0 : -EIO); + if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) { + /* Need to write out all blocks after computing P&Q */ + sh->disks = conf->raid_disks; + sh->pd_idx = stripe_to_pdidx(sh->sector, conf, + conf->raid_disks); + compute_parity6(sh, RECONSTRUCT_WRITE); + for (i = conf->raid_disks ; i-- ; ) { + set_bit(R5_LOCKED, &sh->dev[i].flags); + s.locked++; + set_bit(R5_Wantwrite, &sh->dev[i].flags); + } + clear_bit(STRIPE_EXPANDING, &sh->state); + } else if (s.expanded) { + clear_bit(STRIPE_EXPAND_READY, &sh->state); + atomic_dec(&conf->reshape_stripes); + wake_up(&conf->wait_for_overlap); + md_done_sync(conf->mddev, STRIPE_SECTORS, 1); } - for (i=disks; i-- ;) { - int rw; - struct bio *bi; - mdk_rdev_t *rdev; - if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) - rw = WRITE; - else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags)) - rw = READ; - else - continue; - bi = &sh->dev[i].req; + if (s.expanding && s.locked == 0 && + !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) + handle_stripe_expansion(conf, sh, &r6s); - bi->bi_rw = rw; - if (rw == WRITE) - bi->bi_end_io = raid5_end_write_request; - else - bi->bi_end_io = raid5_end_read_request; + unlock: + spin_unlock(&sh->lock); - rcu_read_lock(); - rdev = rcu_dereference(conf->disks[i].rdev); - if (rdev && test_bit(Faulty, &rdev->flags)) - rdev = NULL; - if (rdev) - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); + /* wait for this device to become unblocked */ + if (unlikely(blocked_rdev)) + md_wait_for_blocked_rdev(blocked_rdev, conf->mddev); - if (rdev) { - if (syncing) - md_sync_acct(rdev->bdev, STRIPE_SECTORS); + ops_run_io(sh, &s); - bi->bi_bdev = rdev->bdev; - PRINTK("for %llu schedule op %ld on disc %d\n", - (unsigned long long)sh->sector, bi->bi_rw, i); - atomic_inc(&sh->count); - bi->bi_sector = sh->sector + rdev->data_offset; - bi->bi_flags = 1 << BIO_UPTODATE; - bi->bi_vcnt = 1; - bi->bi_max_vecs = 1; - bi->bi_idx = 0; - bi->bi_io_vec = &sh->dev[i].vec; - bi->bi_io_vec[0].bv_len = STRIPE_SIZE; - bi->bi_io_vec[0].bv_offset = 0; - bi->bi_size = STRIPE_SIZE; - bi->bi_next = NULL; - if (rw == WRITE && - test_bit(R5_ReWrite, &sh->dev[i].flags)) - atomic_add(STRIPE_SECTORS, &rdev->corrected_errors); - generic_make_request(bi); - } else { - if (rw == WRITE) - set_bit(STRIPE_DEGRADED, &sh->state); - PRINTK("skip op %ld on disc %d for sector %llu\n", - bi->bi_rw, i, (unsigned long long)sh->sector); - clear_bit(R5_LOCKED, &sh->dev[i].flags); - set_bit(STRIPE_HANDLE, &sh->state); - } - } + return_io(return_bi); + + return blocked_rdev == NULL; } -static void handle_stripe(struct stripe_head *sh, struct page *tmp_page) +/* returns true if the stripe was handled */ +static bool handle_stripe(struct stripe_head *sh, struct page *tmp_page) { if (sh->raid_conf->level == 6) - handle_stripe6(sh, tmp_page); + return handle_stripe6(sh, tmp_page); else - handle_stripe5(sh); + return handle_stripe5(sh); } @@ -2448,9 +3038,10 @@ static void raid5_activate_delayed(raid5_conf_t *conf) clear_bit(STRIPE_DELAYED, &sh->state); if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); - list_add_tail(&sh->lru, &conf->handle_list); + list_add_tail(&sh->lru, &conf->hold_list); } - } + } else + blk_plug_device(conf->mddev->queue); } static void activate_bit_delay(raid5_conf_t *conf) @@ -2476,13 +3067,12 @@ static void unplug_slaves(mddev_t *mddev) for (i=0; iraid_disks; i++) { mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) { - request_queue_t *r_queue = bdev_get_queue(rdev->bdev); + struct request_queue *r_queue = bdev_get_queue(rdev->bdev); atomic_inc(&rdev->nr_pending); rcu_read_unlock(); - if (r_queue->unplug_fn) - r_queue->unplug_fn(r_queue); + blk_unplug(r_queue); rdev_dec_pending(rdev, mddev); rcu_read_lock(); @@ -2491,7 +3081,7 @@ static void unplug_slaves(mddev_t *mddev) rcu_read_unlock(); } -static void raid5_unplug_device(request_queue_t *q) +static void raid5_unplug_device(struct request_queue *q) { mddev_t *mddev = q->queuedata; raid5_conf_t *conf = mddev_to_conf(mddev); @@ -2510,36 +3100,6 @@ static void raid5_unplug_device(request_queue_t *q) unplug_slaves(mddev); } -static int raid5_issue_flush(request_queue_t *q, struct gendisk *disk, - sector_t *error_sector) -{ - mddev_t *mddev = q->queuedata; - raid5_conf_t *conf = mddev_to_conf(mddev); - int i, ret = 0; - - rcu_read_lock(); - for (i=0; iraid_disks && ret == 0; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct block_device *bdev = rdev->bdev; - request_queue_t *r_queue = bdev_get_queue(bdev); - - if (!r_queue->issue_flush_fn) - ret = -EOPNOTSUPP; - else { - atomic_inc(&rdev->nr_pending); - rcu_read_unlock(); - ret = r_queue->issue_flush_fn(r_queue, bdev->bd_disk, - error_sector); - rdev_dec_pending(rdev, mddev); - rcu_read_lock(); - } - } - } - rcu_read_unlock(); - return ret; -} - static int raid5_congested(void *data, int bits) { mddev_t *mddev = data; @@ -2561,15 +3121,17 @@ static int raid5_congested(void *data, int bits) /* We want read requests to align with chunks where possible, * but write requests don't need to. */ -static int raid5_mergeable_bvec(request_queue_t *q, struct bio *bio, struct bio_vec *biovec) +static int raid5_mergeable_bvec(struct request_queue *q, + struct bvec_merge_data *bvm, + struct bio_vec *biovec) { mddev_t *mddev = q->queuedata; - sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev); + sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev); int max; unsigned int chunk_sectors = mddev->chunk_size >> 9; - unsigned int bio_sectors = bio->bi_size >> 9; + unsigned int bio_sectors = bvm->bi_size >> 9; - if (bio_data_dir(bio) == WRITE) + if ((bvm->bi_rw & 1) == WRITE) return biovec->bv_len; /* always allow writes to be mergeable */ max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9; @@ -2622,8 +3184,11 @@ static struct bio *remove_bio_from_retry(raid5_conf_t *conf) if(bi) { conf->retry_read_aligned_list = bi->bi_next; bi->bi_next = NULL; + /* + * this sets the active strip count to 1 and the processed + * strip count to zero (upper 8 bits) + */ bi->bi_phys_segments = 1; /* biased count of active stripes */ - bi->bi_hw_segments = 0; /* count of processed stripes */ } return bi; @@ -2636,7 +3201,7 @@ static struct bio *remove_bio_from_retry(raid5_conf_t *conf) * first). * If the read failed.. */ -static int raid5_align_endio(struct bio *bi, unsigned int bytes, int error) +static void raid5_align_endio(struct bio *bi, int error) { struct bio* raid_bi = bi->bi_private; mddev_t *mddev; @@ -2644,8 +3209,6 @@ static int raid5_align_endio(struct bio *bi, unsigned int bytes, int error) int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); mdk_rdev_t *rdev; - if (bi->bi_size) - return 1; bio_put(bi); mddev = raid_bi->bi_bdev->bd_disk->queue->queuedata; @@ -2656,28 +3219,26 @@ static int raid5_align_endio(struct bio *bi, unsigned int bytes, int error) rdev_dec_pending(rdev, conf->mddev); if (!error && uptodate) { - bio_endio(raid_bi, bytes, 0); + bio_endio(raid_bi, 0); if (atomic_dec_and_test(&conf->active_aligned_reads)) wake_up(&conf->wait_for_stripe); - return 0; + return; } - PRINTK("raid5_align_endio : io error...handing IO for a retry\n"); + pr_debug("raid5_align_endio : io error...handing IO for a retry\n"); add_bio_to_retry(raid_bi, conf); - return 0; } static int bio_fits_rdev(struct bio *bi) { - request_queue_t *q = bdev_get_queue(bi->bi_bdev); + struct request_queue *q = bdev_get_queue(bi->bi_bdev); if ((bi->bi_size>>9) > q->max_sectors) return 0; blk_recount_segments(q, bi); - if (bi->bi_phys_segments > q->max_phys_segments || - bi->bi_hw_segments > q->max_hw_segments) + if (bi->bi_phys_segments > q->max_phys_segments) return 0; if (q->merge_bvec_fn) @@ -2690,7 +3251,7 @@ static int bio_fits_rdev(struct bio *bi) } -static int chunk_aligned_read(request_queue_t *q, struct bio * raid_bio) +static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio) { mddev_t *mddev = q->queuedata; raid5_conf_t *conf = mddev_to_conf(mddev); @@ -2701,7 +3262,7 @@ static int chunk_aligned_read(request_queue_t *q, struct bio * raid_bio) mdk_rdev_t *rdev; if (!in_chunk_boundary(mddev, raid_bio)) { - PRINTK("chunk_aligned_read : non aligned\n"); + pr_debug("chunk_aligned_read : non aligned\n"); return 0; } /* @@ -2759,8 +3320,60 @@ static int chunk_aligned_read(request_queue_t *q, struct bio * raid_bio) } } +/* __get_priority_stripe - get the next stripe to process + * + * Full stripe writes are allowed to pass preread active stripes up until + * the bypass_threshold is exceeded. In general the bypass_count + * increments when the handle_list is handled before the hold_list; however, it + * will not be incremented when STRIPE_IO_STARTED is sampled set signifying a + * stripe with in flight i/o. The bypass_count will be reset when the + * head of the hold_list has changed, i.e. the head was promoted to the + * handle_list. + */ +static struct stripe_head *__get_priority_stripe(raid5_conf_t *conf) +{ + struct stripe_head *sh; + + pr_debug("%s: handle: %s hold: %s full_writes: %d bypass_count: %d\n", + __func__, + list_empty(&conf->handle_list) ? "empty" : "busy", + list_empty(&conf->hold_list) ? "empty" : "busy", + atomic_read(&conf->pending_full_writes), conf->bypass_count); + + if (!list_empty(&conf->handle_list)) { + sh = list_entry(conf->handle_list.next, typeof(*sh), lru); + + if (list_empty(&conf->hold_list)) + conf->bypass_count = 0; + else if (!test_bit(STRIPE_IO_STARTED, &sh->state)) { + if (conf->hold_list.next == conf->last_hold) + conf->bypass_count++; + else { + conf->last_hold = conf->hold_list.next; + conf->bypass_count -= conf->bypass_threshold; + if (conf->bypass_count < 0) + conf->bypass_count = 0; + } + } + } else if (!list_empty(&conf->hold_list) && + ((conf->bypass_threshold && + conf->bypass_count > conf->bypass_threshold) || + atomic_read(&conf->pending_full_writes) == 0)) { + sh = list_entry(conf->hold_list.next, + typeof(*sh), lru); + conf->bypass_count -= conf->bypass_threshold; + if (conf->bypass_count < 0) + conf->bypass_count = 0; + } else + return NULL; + + list_del_init(&sh->lru); + atomic_inc(&sh->count); + BUG_ON(atomic_read(&sh->count) != 1); + return sh; +} -static int make_request(request_queue_t *q, struct bio * bi) +static int make_request(struct request_queue *q, struct bio * bi) { mddev_t *mddev = q->queuedata; raid5_conf_t *conf = mddev_to_conf(mddev); @@ -2769,17 +3382,20 @@ static int make_request(request_queue_t *q, struct bio * bi) sector_t logical_sector, last_sector; struct stripe_head *sh; const int rw = bio_data_dir(bi); - int remaining; + int cpu, remaining; if (unlikely(bio_barrier(bi))) { - bio_endio(bi, bi->bi_size, -EOPNOTSUPP); + bio_endio(bi, -EOPNOTSUPP); return 0; } md_write_start(mddev, bi); - disk_stat_inc(mddev->gendisk, ios[rw]); - disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bi)); + cpu = part_stat_lock(); + part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]); + part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], + bio_sectors(bi)); + part_stat_unlock(); if (rw == READ && mddev->reshape_position == MaxSector && @@ -2825,7 +3441,7 @@ static int make_request(request_queue_t *q, struct bio * bi) new_sector = raid5_compute_sector(logical_sector, disks, data_disks, &dd_idx, &pd_idx, conf); - PRINTK("raid5: make_request, sector %llu logical %llu\n", + pr_debug("raid5: make_request, sector %llu logical %llu\n", (unsigned long long)new_sector, (unsigned long long)logical_sector); @@ -2874,7 +3490,8 @@ static int make_request(request_queue_t *q, struct bio * bi) goto retry; } finish_wait(&conf->wait_for_overlap, &w); - handle_stripe(sh, NULL); + set_bit(STRIPE_HANDLE, &sh->state); + clear_bit(STRIPE_DELAYED, &sh->state); release_stripe(sh); } else { /* cannot get stripe for read-ahead, just give-up */ @@ -2885,17 +3502,14 @@ static int make_request(request_queue_t *q, struct bio * bi) } spin_lock_irq(&conf->device_lock); - remaining = --bi->bi_phys_segments; + remaining = raid5_dec_bi_phys_segments(bi); spin_unlock_irq(&conf->device_lock); if (remaining == 0) { - int bytes = bi->bi_size; if ( rw == WRITE ) md_write_end(mddev); - bi->bi_size = 0; - bi->bi_end_io(bi, bytes, - test_bit(BIO_UPTODATE, &bi->bi_flags) - ? 0 : -EIO); + + bio_endio(bi, 0); } return 0; } @@ -2915,8 +3529,9 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped struct stripe_head *sh; int pd_idx; sector_t first_sector, last_sector; - int raid_disks; - int data_disks; + int raid_disks = conf->previous_raid_disks; + int data_disks = raid_disks - conf->max_degraded; + int new_data_disks = conf->raid_disks - conf->max_degraded; int i; int dd_idx; sector_t writepos, safepos, gap; @@ -2925,7 +3540,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped conf->expand_progress != 0) { /* restarting in the middle, skip the initial sectors */ sector_nr = conf->expand_progress; - sector_div(sector_nr, conf->raid_disks-1); + sector_div(sector_nr, new_data_disks); *skipped = 1; return sector_nr; } @@ -2939,14 +3554,14 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped * to after where expand_lo old_maps to */ writepos = conf->expand_progress + - conf->chunk_size/512*(conf->raid_disks-1); - sector_div(writepos, conf->raid_disks-1); + conf->chunk_size/512*(new_data_disks); + sector_div(writepos, new_data_disks); safepos = conf->expand_lo; - sector_div(safepos, conf->previous_raid_disks-1); + sector_div(safepos, data_disks); gap = conf->expand_progress - conf->expand_lo; if (writepos >= safepos || - gap > (conf->raid_disks-1)*3000*2 /*3Meg*/) { + gap > (new_data_disks)*3000*2 /*3Meg*/) { /* Cannot proceed until we've updated the superblock... */ wait_event(conf->wait_for_overlap, atomic_read(&conf->reshape_stripes)==0); @@ -2976,8 +3591,11 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped sector_t s; if (j == sh->pd_idx) continue; + if (conf->level == 6 && + j == raid6_next_disk(sh->pd_idx, sh->disks)) + continue; s = compute_blocknr(sh, j); - if (s < (mddev->array_size<<1)) { + if (s < mddev->array_sectors) { skipped = 1; continue; } @@ -2992,28 +3610,27 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped release_stripe(sh); } spin_lock_irq(&conf->device_lock); - conf->expand_progress = (sector_nr + i)*(conf->raid_disks-1); + conf->expand_progress = (sector_nr + i) * new_data_disks; spin_unlock_irq(&conf->device_lock); /* Ok, those stripe are ready. We can start scheduling * reads on the source stripes. * The source stripes are determined by mapping the first and last * block on the destination stripes. */ - raid_disks = conf->previous_raid_disks; - data_disks = raid_disks - 1; first_sector = - raid5_compute_sector(sector_nr*(conf->raid_disks-1), + raid5_compute_sector(sector_nr*(new_data_disks), raid_disks, data_disks, &dd_idx, &pd_idx, conf); last_sector = raid5_compute_sector((sector_nr+conf->chunk_size/512) - *(conf->raid_disks-1) -1, + *(new_data_disks) -1, raid_disks, data_disks, &dd_idx, &pd_idx, conf); if (last_sector >= (mddev->size<<1)) last_sector = (mddev->size<<1)-1; while (first_sector <= last_sector) { - pd_idx = stripe_to_pdidx(first_sector, conf, conf->previous_raid_disks); + pd_idx = stripe_to_pdidx(first_sector, conf, + conf->previous_raid_disks); sh = get_active_stripe(conf, first_sector, conf->previous_raid_disks, pd_idx, 0); set_bit(STRIPE_EXPAND_SOURCE, &sh->state); @@ -3021,6 +3638,25 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped release_stripe(sh); first_sector += STRIPE_SECTORS; } + /* If this takes us to the resync_max point where we have to pause, + * then we need to write out the superblock. + */ + sector_nr += conf->chunk_size>>9; + if (sector_nr >= mddev->resync_max) { + /* Cannot proceed until we've updated the superblock... */ + wait_event(conf->wait_for_overlap, + atomic_read(&conf->reshape_stripes) == 0); + mddev->reshape_position = conf->expand_progress; + set_bit(MD_CHANGE_DEVS, &mddev->flags); + md_wakeup_thread(mddev->thread); + wait_event(mddev->sb_wait, + !test_bit(MD_CHANGE_DEVS, &mddev->flags) + || kthread_should_stop()); + spin_lock_irq(&conf->device_lock); + conf->expand_lo = mddev->reshape_position; + spin_unlock_irq(&conf->device_lock); + wake_up(&conf->wait_for_overlap); + } return conf->chunk_size>>9; } @@ -3057,6 +3693,12 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) return reshape_request(mddev, sector_nr, skipped); + /* No need to check resync_max as we never do more than one + * stripe, and as resync_max will always be on a chunk boundary, + * if the check in md_do_sync didn't fire, there is no chance + * of overstepping resync_max here + */ + /* if there is too many failed drives and we are trying * to resync, then assert that we are finished, because there is * nothing we can do. @@ -3076,6 +3718,9 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */ } + + bitmap_cond_end_sync(mddev->bitmap, sector_nr); + pd_idx = stripe_to_pdidx(sector_nr, conf, raid_disks); sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 1); if (sh == NULL) { @@ -3100,7 +3745,9 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski clear_bit(STRIPE_INSYNC, &sh->state); spin_unlock(&sh->lock); - handle_stripe(sh, NULL); + /* wait for any blocked device to be handled */ + while(unlikely(!handle_stripe(sh, NULL))) + ; release_stripe(sh); return STRIPE_SECTORS; @@ -3139,7 +3786,7 @@ static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio) sector += STRIPE_SECTORS, scnt++) { - if (scnt < raid_bio->bi_hw_segments) + if (scnt < raid5_bi_hw_segments(raid_bio)) /* already done this stripe */ continue; @@ -3147,7 +3794,7 @@ static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio) if (!sh) { /* failed to get a stripe - must wait */ - raid_bio->bi_hw_segments = scnt; + raid5_set_bi_hw_segments(raid_bio, scnt); conf->retry_read_aligned = raid_bio; return handled; } @@ -3155,7 +3802,7 @@ static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio) set_bit(R5_ReadError, &sh->dev[dd_idx].flags); if (!add_stripe_bio(sh, raid_bio, dd_idx, 0)) { release_stripe(sh); - raid_bio->bi_hw_segments = scnt; + raid5_set_bi_hw_segments(raid_bio, scnt); conf->retry_read_aligned = raid_bio; return handled; } @@ -3165,16 +3812,10 @@ static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio) handled++; } spin_lock_irq(&conf->device_lock); - remaining = --raid_bio->bi_phys_segments; + remaining = raid5_dec_bi_phys_segments(raid_bio); spin_unlock_irq(&conf->device_lock); - if (remaining == 0) { - int bytes = raid_bio->bi_size; - - raid_bio->bi_size = 0; - raid_bio->bi_end_io(raid_bio, bytes, - test_bit(BIO_UPTODATE, &raid_bio->bi_flags) - ? 0 : -EIO); - } + if (remaining == 0) + bio_endio(raid_bio, 0); if (atomic_dec_and_test(&conf->active_aligned_reads)) wake_up(&conf->wait_for_stripe); return handled; @@ -3189,20 +3830,19 @@ static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio) * During the scan, completed stripes are saved for us by the interrupt * handler, so that they will not have to wait for our next wakeup. */ -static void raid5d (mddev_t *mddev) +static void raid5d(mddev_t *mddev) { struct stripe_head *sh; raid5_conf_t *conf = mddev_to_conf(mddev); int handled; - PRINTK("+++ raid5d active\n"); + pr_debug("+++ raid5d active\n"); md_check_recovery(mddev); handled = 0; spin_lock_irq(&conf->device_lock); while (1) { - struct list_head *first; struct bio *bio; if (conf->seq_flush != conf->seq_write) { @@ -3214,12 +3854,6 @@ static void raid5d (mddev_t *mddev) activate_bit_delay(conf); } - if (list_empty(&conf->handle_list) && - atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD && - !blk_queue_plugged(mddev->queue) && - !list_empty(&conf->delayed_list)) - raid5_activate_delayed(conf); - while ((bio = remove_bio_from_retry(conf))) { int ok; spin_unlock_irq(&conf->device_lock); @@ -3230,15 +3864,10 @@ static void raid5d (mddev_t *mddev) handled++; } - if (list_empty(&conf->handle_list)) - break; - - first = conf->handle_list.next; - sh = list_entry(first, struct stripe_head, lru); + sh = __get_priority_stripe(conf); - list_del_init(first); - atomic_inc(&sh->count); - BUG_ON(atomic_read(&sh->count)!= 1); + if (!sh) + break; spin_unlock_irq(&conf->device_lock); handled++; @@ -3247,13 +3876,14 @@ static void raid5d (mddev_t *mddev) spin_lock_irq(&conf->device_lock); } - PRINTK("%d stripes handled\n", handled); + pr_debug("%d stripes handled\n", handled); spin_unlock_irq(&conf->device_lock); + async_tx_issue_pending_all(); unplug_slaves(mddev); - PRINTK("--- raid5d inactive\n"); + pr_debug("--- raid5d inactive\n"); } static ssize_t @@ -3270,15 +3900,15 @@ static ssize_t raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len) { raid5_conf_t *conf = mddev_to_conf(mddev); - char *end; - int new; + unsigned long new; + int err; + if (len >= PAGE_SIZE) return -EINVAL; if (!conf) return -ENODEV; - new = simple_strtoul(page, &end, 10); - if (!*page || (*end && *end != '\n') ) + if (strict_strtoul(page, 10, &new)) return -EINVAL; if (new <= 16 || new > 32768) return -EINVAL; @@ -3288,7 +3918,9 @@ raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len) else break; } - md_allow_write(mddev); + err = md_allow_write(mddev); + if (err) + return err; while (new > conf->max_nr_stripes) { if (grow_one_stripe(conf)) conf->max_nr_stripes++; @@ -3303,6 +3935,40 @@ raid5_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR, raid5_store_stripe_cache_size); static ssize_t +raid5_show_preread_threshold(mddev_t *mddev, char *page) +{ + raid5_conf_t *conf = mddev_to_conf(mddev); + if (conf) + return sprintf(page, "%d\n", conf->bypass_threshold); + else + return 0; +} + +static ssize_t +raid5_store_preread_threshold(mddev_t *mddev, const char *page, size_t len) +{ + raid5_conf_t *conf = mddev_to_conf(mddev); + unsigned long new; + if (len >= PAGE_SIZE) + return -EINVAL; + if (!conf) + return -ENODEV; + + if (strict_strtoul(page, 10, &new)) + return -EINVAL; + if (new > conf->max_nr_stripes) + return -EINVAL; + conf->bypass_threshold = new; + return len; +} + +static struct md_sysfs_entry +raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold, + S_IRUGO | S_IWUSR, + raid5_show_preread_threshold, + raid5_store_preread_threshold); + +static ssize_t stripe_cache_active_show(mddev_t *mddev, char *page) { raid5_conf_t *conf = mddev_to_conf(mddev); @@ -3318,6 +3984,7 @@ raid5_stripecache_active = __ATTR_RO(stripe_cache_active); static struct attribute *raid5_attrs[] = { &raid5_stripecache_size.attr, &raid5_stripecache_active.attr, + &raid5_preread_bypass_threshold.attr, NULL, }; static struct attribute_group raid5_attrs_group = { @@ -3331,7 +3998,6 @@ static int run(mddev_t *mddev) int raid_disk, memory; mdk_rdev_t *rdev; struct disk_info *disk; - struct list_head *tmp; int working_disks = 0; if (mddev->level != 5 && mddev->level != 4 && mddev->level != 6) { @@ -3340,6 +4006,13 @@ static int run(mddev_t *mddev) return -EIO; } + if (mddev->chunk_size < PAGE_SIZE) { + printk(KERN_ERR "md/raid5: chunk_size must be at least " + "PAGE_SIZE but %d < %ld\n", + mddev->chunk_size, PAGE_SIZE); + return -EINVAL; + } + if (mddev->reshape_position != MaxSector) { /* Check that we can continue the reshape. * Currently only disks can change, it must @@ -3348,35 +4021,44 @@ static int run(mddev_t *mddev) */ sector_t here_new, here_old; int old_disks; + int max_degraded = (mddev->level == 5 ? 1 : 2); if (mddev->new_level != mddev->level || mddev->new_layout != mddev->layout || mddev->new_chunk != mddev->chunk_size) { - printk(KERN_ERR "raid5: %s: unsupported reshape required - aborting.\n", + printk(KERN_ERR "raid5: %s: unsupported reshape " + "required - aborting.\n", mdname(mddev)); return -EINVAL; } if (mddev->delta_disks <= 0) { - printk(KERN_ERR "raid5: %s: unsupported reshape (reduce disks) required - aborting.\n", + printk(KERN_ERR "raid5: %s: unsupported reshape " + "(reduce disks) required - aborting.\n", mdname(mddev)); return -EINVAL; } old_disks = mddev->raid_disks - mddev->delta_disks; /* reshape_position must be on a new-stripe boundary, and one - * further up in new geometry must map after here in old geometry. + * further up in new geometry must map after here in old + * geometry. */ here_new = mddev->reshape_position; - if (sector_div(here_new, (mddev->chunk_size>>9)*(mddev->raid_disks-1))) { - printk(KERN_ERR "raid5: reshape_position not on a stripe boundary\n"); + if (sector_div(here_new, (mddev->chunk_size>>9)* + (mddev->raid_disks - max_degraded))) { + printk(KERN_ERR "raid5: reshape_position not " + "on a stripe boundary\n"); return -EINVAL; } /* here_new is the stripe we will write to */ here_old = mddev->reshape_position; - sector_div(here_old, (mddev->chunk_size>>9)*(old_disks-1)); - /* here_old is the first stripe that we might need to read from */ + sector_div(here_old, (mddev->chunk_size>>9)* + (old_disks-max_degraded)); + /* here_old is the first stripe that we might need to read + * from */ if (here_new >= here_old) { /* Reading from the same stripe as writing to - bad */ - printk(KERN_ERR "raid5: reshape_position too early for auto-recovery - aborting.\n"); + printk(KERN_ERR "raid5: reshape_position too early for " + "auto-recovery - aborting.\n"); return -EINVAL; } printk(KERN_INFO "raid5: reshape will continue\n"); @@ -3410,19 +4092,22 @@ static int run(mddev_t *mddev) goto abort; } spin_lock_init(&conf->device_lock); + mddev->queue->queue_lock = &conf->device_lock; init_waitqueue_head(&conf->wait_for_stripe); init_waitqueue_head(&conf->wait_for_overlap); INIT_LIST_HEAD(&conf->handle_list); + INIT_LIST_HEAD(&conf->hold_list); INIT_LIST_HEAD(&conf->delayed_list); INIT_LIST_HEAD(&conf->bitmap_list); INIT_LIST_HEAD(&conf->inactive_list); atomic_set(&conf->active_stripes, 0); atomic_set(&conf->preread_active_stripes, 0); atomic_set(&conf->active_aligned_reads, 0); + conf->bypass_threshold = BYPASS_THRESHOLD; - PRINTK("raid5: run(%s) called.\n", mdname(mddev)); + pr_debug("raid5: run(%s) called.\n", mdname(mddev)); - ITERATE_RDEV(mddev,rdev,tmp) { + list_for_each_entry(rdev, &mddev->disks, same_set) { raid_disk = rdev->raid_disk; if (raid_disk >= conf->raid_disks || raid_disk < 0) @@ -3437,7 +4122,9 @@ static int run(mddev_t *mddev) " disk %d\n", bdevname(rdev->bdev,b), raid_disk); working_disks++; - } + } else + /* Cannot rely on bitmap to complete recovery */ + conf->fullsync = 1; } /* @@ -3555,14 +4242,16 @@ static int run(mddev_t *mddev) } /* Ok, everything is just fine now */ - sysfs_create_group(&mddev->kobj, &raid5_attrs_group); + if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group)) + printk(KERN_WARNING + "raid5: failed to create sysfs attributes for %s\n", + mdname(mddev)); mddev->queue->unplug_fn = raid5_unplug_device; - mddev->queue->issue_flush_fn = raid5_issue_flush; - mddev->queue->backing_dev_info.congested_fn = raid5_congested; mddev->queue->backing_dev_info.congested_data = mddev; + mddev->queue->backing_dev_info.congested_fn = raid5_congested; - mddev->array_size = mddev->size * (conf->previous_raid_disks - + mddev->array_sectors = 2 * mddev->size * (conf->previous_raid_disks - conf->max_degraded); blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec); @@ -3591,6 +4280,7 @@ static int stop(mddev_t *mddev) mddev->thread = NULL; shrink_stripes(conf); kfree(conf->stripe_hashtbl); + mddev->queue->backing_dev_info.congested_fn = NULL; blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/ sysfs_remove_group(&mddev->kobj, &raid5_attrs_group); kfree(conf->disks); @@ -3599,8 +4289,8 @@ static int stop(mddev_t *mddev) return 0; } -#if RAID5_DEBUG -static void print_sh (struct seq_file *seq, struct stripe_head *sh) +#ifdef DEBUG +static void print_sh(struct seq_file *seq, struct stripe_head *sh) { int i; @@ -3616,7 +4306,7 @@ static void print_sh (struct seq_file *seq, struct stripe_head *sh) seq_printf(seq, "\n"); } -static void printall (struct seq_file *seq, raid5_conf_t *conf) +static void printall(struct seq_file *seq, raid5_conf_t *conf) { struct stripe_head *sh; struct hlist_node *hn; @@ -3634,7 +4324,7 @@ static void printall (struct seq_file *seq, raid5_conf_t *conf) } #endif -static void status (struct seq_file *seq, mddev_t *mddev) +static void status(struct seq_file *seq, mddev_t *mddev) { raid5_conf_t *conf = (raid5_conf_t *) mddev->private; int i; @@ -3646,7 +4336,7 @@ static void status (struct seq_file *seq, mddev_t *mddev) conf->disks[i].rdev && test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_"); seq_printf (seq, "]"); -#if RAID5_DEBUG +#ifdef DEBUG seq_printf (seq, "\n"); printall(seq, conf); #endif @@ -3711,6 +4401,14 @@ static int raid5_remove_disk(mddev_t *mddev, int number) err = -EBUSY; goto abort; } + /* Only remove non-faulty devices if recovery + * isn't possible. + */ + if (!test_bit(Faulty, &rdev->flags) && + mddev->degraded <= conf->max_degraded) { + err = -EBUSY; + goto abort; + } p->rdev = NULL; synchronize_rcu(); if (atomic_read(&rdev->nr_pending)) { @@ -3728,35 +4426,41 @@ abort: static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) { raid5_conf_t *conf = mddev->private; - int found = 0; + int err = -EEXIST; int disk; struct disk_info *p; + int first = 0; + int last = conf->raid_disks - 1; if (mddev->degraded > conf->max_degraded) /* no point adding a device */ - return 0; + return -EINVAL; + + if (rdev->raid_disk >= 0) + first = last = rdev->raid_disk; /* * find the disk ... but prefer rdev->saved_raid_disk * if possible. */ if (rdev->saved_raid_disk >= 0 && + rdev->saved_raid_disk >= first && conf->disks[rdev->saved_raid_disk].rdev == NULL) disk = rdev->saved_raid_disk; else - disk = 0; - for ( ; disk < conf->raid_disks; disk++) + disk = first; + for ( ; disk <= last ; disk++) if ((p=conf->disks + disk)->rdev == NULL) { clear_bit(In_sync, &rdev->flags); rdev->raid_disk = disk; - found = 1; + err = 0; if (rdev->saved_raid_disk != disk) conf->fullsync = 1; rcu_assign_pointer(p->rdev, rdev); break; } print_raid5_conf(conf); - return found; + return err; } static int raid5_resize(mddev_t *mddev, sector_t sectors) @@ -3771,8 +4475,9 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors) raid5_conf_t *conf = mddev_to_conf(mddev); sectors &= ~((sector_t)mddev->chunk_size/512 - 1); - mddev->array_size = (sectors * (mddev->raid_disks-conf->max_degraded))>>1; - set_capacity(mddev->gendisk, mddev->array_size << 1); + mddev->array_sectors = sectors * (mddev->raid_disks + - conf->max_degraded); + set_capacity(mddev->gendisk, mddev->array_sectors); mddev->changed = 1; if (sectors/2 > mddev->size && mddev->recovery_cp == MaxSector) { mddev->recovery_cp = mddev->size << 1; @@ -3794,6 +4499,9 @@ static int raid5_check_reshape(mddev_t *mddev) return -EINVAL; /* Cannot shrink array or change level yet */ if (mddev->delta_disks == 0) return 0; /* nothing to do */ + if (mddev->bitmap) + /* Cannot grow a bitmap yet */ + return -EBUSY; /* Can only proceed if there are plenty of stripe_heads. * We need a minimum of one full stripe,, and for sensible progress @@ -3824,21 +4532,19 @@ static int raid5_start_reshape(mddev_t *mddev) { raid5_conf_t *conf = mddev_to_conf(mddev); mdk_rdev_t *rdev; - struct list_head *rtmp; int spares = 0; int added_devices = 0; unsigned long flags; - if (mddev->degraded || - test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; - ITERATE_RDEV(mddev, rdev, rtmp) + list_for_each_entry(rdev, &mddev->disks, same_set) if (rdev->raid_disk < 0 && !test_bit(Faulty, &rdev->flags)) spares++; - if (spares < mddev->delta_disks-1) + if (spares - mddev->degraded < mddev->delta_disks - conf->max_degraded) /* Not enough devices even to make a degraded array * of that size */ @@ -3855,16 +4561,21 @@ static int raid5_start_reshape(mddev_t *mddev) /* Add some new drives, as many as will fit. * We know there are enough to make the newly sized array work. */ - ITERATE_RDEV(mddev, rdev, rtmp) + list_for_each_entry(rdev, &mddev->disks, same_set) if (rdev->raid_disk < 0 && !test_bit(Faulty, &rdev->flags)) { - if (raid5_add_disk(mddev, rdev)) { + if (raid5_add_disk(mddev, rdev) == 0) { char nm[20]; set_bit(In_sync, &rdev->flags); added_devices++; rdev->recovery_offset = 0; sprintf(nm, "rd%d", rdev->raid_disk); - sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); + if (sysfs_create_link(&mddev->kobj, + &rdev->kobj, nm)) + printk(KERN_WARNING + "raid5: failed to create " + " link %s for %s\n", + nm, mdname(mddev)); } else break; } @@ -3901,14 +4612,16 @@ static void end_reshape(raid5_conf_t *conf) struct block_device *bdev; if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) { - conf->mddev->array_size = conf->mddev->size * (conf->raid_disks-1); - set_capacity(conf->mddev->gendisk, conf->mddev->array_size << 1); + conf->mddev->array_sectors = 2 * conf->mddev->size * + (conf->raid_disks - conf->max_degraded); + set_capacity(conf->mddev->gendisk, conf->mddev->array_sectors); conf->mddev->changed = 1; bdev = bdget_disk(conf->mddev->gendisk, 0); if (bdev) { mutex_lock(&bdev->bd_inode->i_mutex); - i_size_write(bdev->bd_inode, (loff_t)conf->mddev->array_size << 10); + i_size_write(bdev->bd_inode, + (loff_t)conf->mddev->array_sectors << 9); mutex_unlock(&bdev->bd_inode->i_mutex); bdput(bdev); } @@ -3974,6 +4687,10 @@ static struct mdk_personality raid6_personality = .spare_active = raid5_spare_active, .sync_request = sync_request, .resize = raid5_resize, +#ifdef CONFIG_MD_RAID5_RESHAPE + .check_reshape = raid5_check_reshape, + .start_reshape = raid5_start_reshape, +#endif .quiesce = raid5_quiesce, }; static struct mdk_personality raid5_personality = @@ -4013,6 +4730,10 @@ static struct mdk_personality raid4_personality = .spare_active = raid5_spare_active, .sync_request = sync_request, .resize = raid5_resize, +#ifdef CONFIG_MD_RAID5_RESHAPE + .check_reshape = raid5_check_reshape, + .start_reshape = raid5_start_reshape, +#endif .quiesce = raid5_quiesce, };