diff options
Diffstat (limited to 'drivers/md/raid5.c')
-rw-r--r-- | drivers/md/raid5.c | 1494 |
1 files changed, 1055 insertions, 439 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index a5ba080d303..3bbc6d64704 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -43,11 +43,14 @@ * miss any bits. */ +#include <linux/blkdev.h> #include <linux/kthread.h> -#include "raid6.h" - -#include <linux/raid/bitmap.h> +#include <linux/raid/pq.h> #include <linux/async_tx.h> +#include <linux/seq_file.h> +#include "md.h" +#include "raid5.h" +#include "bitmap.h" /* * Stripe cache @@ -91,11 +94,6 @@ #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 @@ -130,12 +128,42 @@ 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); } +/* Find first data disk in a raid6 stripe */ +static inline int raid6_d0(struct stripe_head *sh) +{ + if (sh->ddf_layout) + /* ddf always start from first device */ + return 0; + /* md starts just after Q block */ + if (sh->qd_idx == sh->disks - 1) + return 0; + else + return sh->qd_idx + 1; +} static inline int raid6_next_disk(int disk, int raid_disks) { disk++; return (disk < raid_disks) ? disk : 0; } +/* When walking through the disks in a raid5, starting at raid6_d0, + * We need to map each disk to a 'slot', where the data disks are slot + * 0 .. raid_disks-3, the parity disk is raid_disks-2 and the Q disk + * is raid_disks-1. This help does that mapping. + */ +static int raid6_idx_to_slot(int idx, struct stripe_head *sh, + int *count, int syndrome_disks) +{ + int slot; + + if (idx == sh->pd_idx) + return syndrome_disks; + if (idx == sh->qd_idx) + return syndrome_disks + 1; + slot = (*count)++; + return slot; +} + static void return_io(struct bio *return_bi) { struct bio *bi = return_bi; @@ -193,6 +221,7 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh) } } } + static void release_stripe(struct stripe_head *sh) { raid5_conf_t *conf = sh->raid_conf; @@ -270,9 +299,11 @@ 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, int previous); +static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous, + struct stripe_head *sh); -static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int disks) +static void init_stripe(struct stripe_head *sh, sector_t sector, int previous) { raid5_conf_t *conf = sh->raid_conf; int i; @@ -287,11 +318,12 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int remove_hash(sh); + sh->generation = conf->generation - previous; + sh->disks = previous ? conf->previous_raid_disks : conf->raid_disks; sh->sector = sector; - sh->pd_idx = pd_idx; + stripe_set_idx(sector, conf, previous, sh); sh->state = 0; - sh->disks = disks; for (i = sh->disks; i--; ) { struct r5dev *dev = &sh->dev[i]; @@ -305,12 +337,13 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int BUG(); } dev->flags = 0; - raid5_build_block(sh, i); + raid5_build_block(sh, i, previous); } insert_hash(conf, sh); } -static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, int disks) +static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, + short generation) { struct stripe_head *sh; struct hlist_node *hn; @@ -318,7 +351,7 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, in CHECK_DEVLOCK(); 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) + if (sh->sector == sector && sh->generation == generation) return sh; pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector); return NULL; @@ -327,8 +360,9 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, in static void unplug_slaves(mddev_t *mddev); 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) +static struct stripe_head * +get_active_stripe(raid5_conf_t *conf, sector_t sector, + int previous, int noblock) { struct stripe_head *sh; @@ -340,7 +374,7 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector wait_event_lock_irq(conf->wait_for_stripe, conf->quiesce == 0, conf->device_lock, /* nothing */); - sh = __find_stripe(conf, sector, disks); + sh = __find_stripe(conf, sector, conf->generation - previous); if (!sh) { if (!conf->inactive_blocked) sh = get_free_stripe(conf); @@ -358,10 +392,11 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector ); conf->inactive_blocked = 0; } else - init_stripe(sh, sector, pd_idx, disks); + init_stripe(sh, sector, previous); } else { if (atomic_read(&sh->count)) { - BUG_ON(!list_empty(&sh->lru)); + BUG_ON(!list_empty(&sh->lru) + && !test_bit(STRIPE_EXPANDING, &sh->state)); } else { if (!test_bit(STRIPE_HANDLE, &sh->state)) atomic_inc(&conf->active_stripes); @@ -895,8 +930,10 @@ 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)); + sprintf(conf->cache_name[0], + "raid%d-%s", conf->level, mdname(conf->mddev)); + sprintf(conf->cache_name[1], + "raid%d-%s-alt", conf->level, 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), @@ -911,7 +948,6 @@ static int grow_stripes(raid5_conf_t *conf, int num) 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. @@ -1036,7 +1072,6 @@ static int resize_stripes(raid5_conf_t *conf, int newsize) conf->pool_size = newsize; return err; } -#endif static int drop_one_stripe(raid5_conf_t *conf) { @@ -1066,7 +1101,7 @@ static void shrink_stripes(raid5_conf_t *conf) static void raid5_end_read_request(struct bio * bi, int error) { - struct stripe_head *sh = bi->bi_private; + 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); @@ -1148,7 +1183,7 @@ static void raid5_end_read_request(struct bio * bi, int error) static void raid5_end_write_request(struct bio *bi, int error) { - struct stripe_head *sh = bi->bi_private; + 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); @@ -1176,9 +1211,9 @@ static void raid5_end_write_request(struct bio *bi, int error) } -static sector_t compute_blocknr(struct stripe_head *sh, int i); +static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous); -static void raid5_build_block(struct stripe_head *sh, int i) +static void raid5_build_block(struct stripe_head *sh, int i, int previous) { struct r5dev *dev = &sh->dev[i]; @@ -1194,7 +1229,7 @@ static void raid5_build_block(struct stripe_head *sh, int i) dev->req.bi_private = sh; dev->flags = 0; - dev->sector = compute_blocknr(sh, i); + dev->sector = compute_blocknr(sh, i, previous); } static void error(mddev_t *mddev, mdk_rdev_t *rdev) @@ -1227,15 +1262,23 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) * Input: a 'big' sector number, * Output: index of the data and parity disk, and the sector # in them. */ -static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks, - unsigned int data_disks, unsigned int * dd_idx, - unsigned int * pd_idx, raid5_conf_t *conf) +static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, + int previous, int *dd_idx, + struct stripe_head *sh) { long stripe; unsigned long chunk_number; unsigned int chunk_offset; + int pd_idx, qd_idx; + int ddf_layout = 0; sector_t new_sector; - int sectors_per_chunk = conf->chunk_size >> 9; + int algorithm = previous ? conf->prev_algo + : conf->algorithm; + int sectors_per_chunk = previous ? (conf->prev_chunk >> 9) + : (conf->chunk_size >> 9); + int raid_disks = previous ? conf->previous_raid_disks + : conf->raid_disks; + int data_disks = raid_disks - conf->max_degraded; /* First compute the information on this sector */ @@ -1259,68 +1302,170 @@ static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks, /* * Select the parity disk based on the user selected algorithm. */ + pd_idx = qd_idx = ~0; switch(conf->level) { case 4: - *pd_idx = data_disks; + pd_idx = data_disks; break; case 5: - switch (conf->algorithm) { + switch (algorithm) { case ALGORITHM_LEFT_ASYMMETRIC: - *pd_idx = data_disks - stripe % raid_disks; - if (*dd_idx >= *pd_idx) + pd_idx = data_disks - stripe % raid_disks; + if (*dd_idx >= pd_idx) (*dd_idx)++; break; case ALGORITHM_RIGHT_ASYMMETRIC: - *pd_idx = stripe % raid_disks; - if (*dd_idx >= *pd_idx) + pd_idx = stripe % raid_disks; + if (*dd_idx >= pd_idx) (*dd_idx)++; break; case ALGORITHM_LEFT_SYMMETRIC: - *pd_idx = data_disks - stripe % raid_disks; - *dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks; + pd_idx = data_disks - stripe % raid_disks; + *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; break; case ALGORITHM_RIGHT_SYMMETRIC: - *pd_idx = stripe % raid_disks; - *dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks; + pd_idx = stripe % raid_disks; + *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; + break; + case ALGORITHM_PARITY_0: + pd_idx = 0; + (*dd_idx)++; + break; + case ALGORITHM_PARITY_N: + pd_idx = data_disks; break; default: printk(KERN_ERR "raid5: unsupported algorithm %d\n", - conf->algorithm); + algorithm); + BUG(); } break; case 6: - /**** FIX THIS ****/ - switch (conf->algorithm) { + switch (algorithm) { case ALGORITHM_LEFT_ASYMMETRIC: - *pd_idx = raid_disks - 1 - (stripe % raid_disks); - if (*pd_idx == raid_disks-1) - (*dd_idx)++; /* Q D D D P */ - else if (*dd_idx >= *pd_idx) + pd_idx = raid_disks - 1 - (stripe % raid_disks); + qd_idx = pd_idx + 1; + if (pd_idx == raid_disks-1) { + (*dd_idx)++; /* Q D D D P */ + qd_idx = 0; + } else if (*dd_idx >= pd_idx) (*dd_idx) += 2; /* D D P Q D */ break; case ALGORITHM_RIGHT_ASYMMETRIC: - *pd_idx = stripe % raid_disks; - if (*pd_idx == raid_disks-1) - (*dd_idx)++; /* Q D D D P */ - else if (*dd_idx >= *pd_idx) + pd_idx = stripe % raid_disks; + qd_idx = pd_idx + 1; + if (pd_idx == raid_disks-1) { + (*dd_idx)++; /* Q D D D P */ + qd_idx = 0; + } else if (*dd_idx >= pd_idx) (*dd_idx) += 2; /* D D P Q D */ break; case ALGORITHM_LEFT_SYMMETRIC: - *pd_idx = raid_disks - 1 - (stripe % raid_disks); - *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks; + pd_idx = raid_disks - 1 - (stripe % raid_disks); + qd_idx = (pd_idx + 1) % raid_disks; + *dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks; break; case ALGORITHM_RIGHT_SYMMETRIC: - *pd_idx = stripe % raid_disks; - *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks; + pd_idx = stripe % raid_disks; + qd_idx = (pd_idx + 1) % raid_disks; + *dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks; + break; + + case ALGORITHM_PARITY_0: + pd_idx = 0; + qd_idx = 1; + (*dd_idx) += 2; + break; + case ALGORITHM_PARITY_N: + pd_idx = data_disks; + qd_idx = data_disks + 1; break; + + case ALGORITHM_ROTATING_ZERO_RESTART: + /* Exactly the same as RIGHT_ASYMMETRIC, but or + * of blocks for computing Q is different. + */ + pd_idx = stripe % raid_disks; + qd_idx = pd_idx + 1; + if (pd_idx == raid_disks-1) { + (*dd_idx)++; /* Q D D D P */ + qd_idx = 0; + } else if (*dd_idx >= pd_idx) + (*dd_idx) += 2; /* D D P Q D */ + ddf_layout = 1; + break; + + case ALGORITHM_ROTATING_N_RESTART: + /* Same a left_asymmetric, by first stripe is + * D D D P Q rather than + * Q D D D P + */ + pd_idx = raid_disks - 1 - ((stripe + 1) % raid_disks); + qd_idx = pd_idx + 1; + if (pd_idx == raid_disks-1) { + (*dd_idx)++; /* Q D D D P */ + qd_idx = 0; + } else if (*dd_idx >= pd_idx) + (*dd_idx) += 2; /* D D P Q D */ + ddf_layout = 1; + break; + + case ALGORITHM_ROTATING_N_CONTINUE: + /* Same as left_symmetric but Q is before P */ + pd_idx = raid_disks - 1 - (stripe % raid_disks); + qd_idx = (pd_idx + raid_disks - 1) % raid_disks; + *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks; + ddf_layout = 1; + break; + + case ALGORITHM_LEFT_ASYMMETRIC_6: + /* RAID5 left_asymmetric, with Q on last device */ + pd_idx = data_disks - stripe % (raid_disks-1); + if (*dd_idx >= pd_idx) + (*dd_idx)++; + qd_idx = raid_disks - 1; + break; + + case ALGORITHM_RIGHT_ASYMMETRIC_6: + pd_idx = stripe % (raid_disks-1); + if (*dd_idx >= pd_idx) + (*dd_idx)++; + qd_idx = raid_disks - 1; + break; + + case ALGORITHM_LEFT_SYMMETRIC_6: + pd_idx = data_disks - stripe % (raid_disks-1); + *dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1); + qd_idx = raid_disks - 1; + break; + + case ALGORITHM_RIGHT_SYMMETRIC_6: + pd_idx = stripe % (raid_disks-1); + *dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1); + qd_idx = raid_disks - 1; + break; + + case ALGORITHM_PARITY_0_6: + pd_idx = 0; + (*dd_idx)++; + qd_idx = raid_disks - 1; + break; + + default: printk(KERN_CRIT "raid6: unsupported algorithm %d\n", - conf->algorithm); + algorithm); + BUG(); } break; } + if (sh) { + sh->pd_idx = pd_idx; + sh->qd_idx = qd_idx; + sh->ddf_layout = ddf_layout; + } /* * Finally, compute the new sector number */ @@ -1329,17 +1474,21 @@ static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks, } -static sector_t compute_blocknr(struct stripe_head *sh, int i) +static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous) { raid5_conf_t *conf = sh->raid_conf; int raid_disks = sh->disks; int data_disks = raid_disks - conf->max_degraded; sector_t new_sector = sh->sector, check; - int sectors_per_chunk = conf->chunk_size >> 9; + int sectors_per_chunk = previous ? (conf->prev_chunk >> 9) + : (conf->chunk_size >> 9); + int algorithm = previous ? conf->prev_algo + : conf->algorithm; sector_t stripe; int chunk_offset; - int chunk_number, dummy1, dummy2, dd_idx = i; + int chunk_number, dummy1, dd_idx = i; sector_t r_sector; + struct stripe_head sh2; chunk_offset = sector_div(new_sector, sectors_per_chunk); @@ -1351,7 +1500,7 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i) switch(conf->level) { case 4: break; case 5: - switch (conf->algorithm) { + switch (algorithm) { case ALGORITHM_LEFT_ASYMMETRIC: case ALGORITHM_RIGHT_ASYMMETRIC: if (i > sh->pd_idx) @@ -1363,19 +1512,27 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i) i += raid_disks; i -= (sh->pd_idx + 1); break; + case ALGORITHM_PARITY_0: + i -= 1; + break; + case ALGORITHM_PARITY_N: + break; default: printk(KERN_ERR "raid5: unsupported algorithm %d\n", - conf->algorithm); + algorithm); + BUG(); } break; case 6: - if (i == raid6_next_disk(sh->pd_idx, raid_disks)) + if (i == sh->qd_idx) return 0; /* It is the Q disk */ - switch (conf->algorithm) { + switch (algorithm) { case ALGORITHM_LEFT_ASYMMETRIC: case ALGORITHM_RIGHT_ASYMMETRIC: - if (sh->pd_idx == raid_disks-1) - i--; /* Q D D D P */ + case ALGORITHM_ROTATING_ZERO_RESTART: + case ALGORITHM_ROTATING_N_RESTART: + if (sh->pd_idx == raid_disks-1) + i--; /* Q D D D P */ else if (i > sh->pd_idx) i -= 2; /* D D P Q D */ break; @@ -1390,9 +1547,35 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i) i -= (sh->pd_idx + 2); } break; + case ALGORITHM_PARITY_0: + i -= 2; + break; + case ALGORITHM_PARITY_N: + break; + case ALGORITHM_ROTATING_N_CONTINUE: + if (sh->pd_idx == 0) + i--; /* P D D D Q */ + else if (i > sh->pd_idx) + i -= 2; /* D D Q P D */ + break; + case ALGORITHM_LEFT_ASYMMETRIC_6: + case ALGORITHM_RIGHT_ASYMMETRIC_6: + if (i > sh->pd_idx) + i--; + break; + case ALGORITHM_LEFT_SYMMETRIC_6: + case ALGORITHM_RIGHT_SYMMETRIC_6: + if (i < sh->pd_idx) + i += data_disks + 1; + i -= (sh->pd_idx + 1); + break; + case ALGORITHM_PARITY_0_6: + i -= 1; + break; default: printk(KERN_CRIT "raid6: unsupported algorithm %d\n", - conf->algorithm); + algorithm); + BUG(); } break; } @@ -1400,8 +1583,10 @@ 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); - if (check != sh->sector || dummy1 != dd_idx || dummy2 != sh->pd_idx) { + check = raid5_compute_sector(conf, r_sector, + previous, &dummy1, &sh2); + if (check != sh->sector || dummy1 != dd_idx || sh2.pd_idx != sh->pd_idx + || sh2.qd_idx != sh->qd_idx) { printk(KERN_ERR "compute_blocknr: map not correct\n"); return 0; } @@ -1468,14 +1653,16 @@ static void copy_data(int frombio, struct bio *bio, 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 = sh->disks, count; + raid5_conf_t *conf = sh->raid_conf; + int i, pd_idx, qd_idx, d0_idx, disks = sh->disks, count; + int syndrome_disks = sh->ddf_layout ? disks : (disks - 2); struct bio *chosen; /**** FIX THIS: This could be very bad if disks is close to 256 ****/ - void *ptrs[disks]; + void *ptrs[syndrome_disks+2]; - qd_idx = raid6_next_disk(pd_idx, disks); - d0_idx = raid6_next_disk(qd_idx, disks); + pd_idx = sh->pd_idx; + qd_idx = sh->qd_idx; + d0_idx = raid6_d0(sh); pr_debug("compute_parity, stripe %llu, method %d\n", (unsigned long long)sh->sector, method); @@ -1513,24 +1700,29 @@ static void compute_parity6(struct stripe_head *sh, int method) set_bit(R5_UPTODATE, &sh->dev[i].flags); } -// switch(method) { -// case RECONSTRUCT_WRITE: -// case CHECK_PARITY: -// case UPDATE_PARITY: - /* Note that unlike RAID-5, the ordering of the disks matters greatly. */ - /* FIX: Is this ordering of drives even remotely optimal? */ - count = 0; - i = d0_idx; - do { - ptrs[count++] = page_address(sh->dev[i].page); - if (count <= disks-2 && !test_bit(R5_UPTODATE, &sh->dev[i].flags)) - printk("block %d/%d not uptodate on parity calc\n", i,count); - i = raid6_next_disk(i, disks); - } while ( i != d0_idx ); -// break; -// } - - raid6_call.gen_syndrome(disks, STRIPE_SIZE, ptrs); + /* Note that unlike RAID-5, the ordering of the disks matters greatly.*/ + + for (i = 0; i < disks; i++) + ptrs[i] = (void *)raid6_empty_zero_page; + + count = 0; + i = d0_idx; + do { + int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks); + + ptrs[slot] = page_address(sh->dev[i].page); + if (slot < syndrome_disks && + !test_bit(R5_UPTODATE, &sh->dev[i].flags)) { + printk(KERN_ERR "block %d/%d not uptodate " + "on parity calc\n", i, count); + BUG(); + } + + i = raid6_next_disk(i, disks); + } while (i != d0_idx); + BUG_ON(count != syndrome_disks); + + raid6_call.gen_syndrome(syndrome_disks+2, STRIPE_SIZE, ptrs); switch(method) { case RECONSTRUCT_WRITE: @@ -1552,8 +1744,7 @@ static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero) { 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); + int qd_idx = sh->qd_idx; pr_debug("compute_block_1, stripe %llu, idx %d\n", (unsigned long long)sh->sector, dd_idx); @@ -1589,63 +1780,65 @@ static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero) static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2) { 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); - int faila, failb; + int syndrome_disks = sh->ddf_layout ? disks : disks-2; + int d0_idx = raid6_d0(sh); + int faila = -1, failb = -1; + /**** FIX THIS: This could be very bad if disks is close to 256 ****/ + void *ptrs[syndrome_disks+2]; - /* faila and failb are disk numbers relative to d0_idx */ - /* pd_idx become disks-2 and qd_idx become disks-1 */ - faila = (dd_idx1 < d0_idx) ? dd_idx1+(disks-d0_idx) : dd_idx1-d0_idx; - failb = (dd_idx2 < d0_idx) ? dd_idx2+(disks-d0_idx) : dd_idx2-d0_idx; + for (i = 0; i < disks ; i++) + ptrs[i] = (void *)raid6_empty_zero_page; + count = 0; + i = d0_idx; + do { + int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks); + + ptrs[slot] = page_address(sh->dev[i].page); + + if (i == dd_idx1) + faila = slot; + if (i == dd_idx2) + failb = slot; + i = raid6_next_disk(i, disks); + } while (i != d0_idx); + BUG_ON(count != syndrome_disks); BUG_ON(faila == failb); if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; } pr_debug("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n", - (unsigned long long)sh->sector, dd_idx1, dd_idx2, faila, failb); + (unsigned long long)sh->sector, dd_idx1, dd_idx2, + faila, failb); - if ( failb == disks-1 ) { + if (failb == syndrome_disks+1) { /* Q disk is one of the missing disks */ - if ( faila == disks-2 ) { + if (faila == syndrome_disks) { /* Missing P+Q, just recompute */ compute_parity6(sh, UPDATE_PARITY); return; } else { /* We're missing D+Q; recompute D from P */ - compute_block_1(sh, (dd_idx1 == qd_idx) ? dd_idx2 : dd_idx1, 0); + compute_block_1(sh, ((dd_idx1 == sh->qd_idx) ? + dd_idx2 : dd_idx1), + 0); compute_parity6(sh, UPDATE_PARITY); /* Is this necessary? */ return; } } - /* We're missing D+P or D+D; build pointer table */ - { - /**** FIX THIS: This could be very bad if disks is close to 256 ****/ - void *ptrs[disks]; - - count = 0; - i = d0_idx; - do { - ptrs[count++] = page_address(sh->dev[i].page); - i = raid6_next_disk(i, disks); - if (i != dd_idx1 && i != dd_idx2 && - !test_bit(R5_UPTODATE, &sh->dev[i].flags)) - printk("compute_2 with missing block %d/%d\n", count, i); - } while ( i != d0_idx ); - - if ( failb == disks-2 ) { - /* We're missing D+P. */ - raid6_datap_recov(disks, STRIPE_SIZE, faila, ptrs); - } else { - /* We're missing D+D. */ - 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); + /* We're missing D+P or D+D; */ + if (failb == syndrome_disks) { + /* We're missing D+P. */ + raid6_datap_recov(syndrome_disks+2, STRIPE_SIZE, faila, ptrs); + } else { + /* We're missing D+D. */ + raid6_2data_recov(syndrome_disks+2, 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); } static void @@ -1800,17 +1993,21 @@ static int page_is_zero(struct page *p) memcmp(a, a+4, STRIPE_SIZE-4)==0); } -static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks) +static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous, + struct stripe_head *sh) { - int sectors_per_chunk = conf->chunk_size >> 9; - int pd_idx, dd_idx; + int sectors_per_chunk = + previous ? (conf->prev_chunk >> 9) + : (conf->chunk_size >> 9); + int dd_idx; int chunk_offset = sector_div(stripe, sectors_per_chunk); + int disks = previous ? conf->previous_raid_disks : conf->raid_disks; - raid5_compute_sector(stripe * (disks - conf->max_degraded) + raid5_compute_sector(conf, + stripe * (disks - conf->max_degraded) *sectors_per_chunk + chunk_offset, - disks, disks - conf->max_degraded, - &dd_idx, &pd_idx, conf); - return pd_idx; + previous, + &dd_idx, sh); } static void @@ -2181,7 +2378,7 @@ static void handle_stripe_dirtying6(raid5_conf_t *conf, struct r6_state *r6s, int disks) { int rcw = 0, must_compute = 0, pd_idx = sh->pd_idx, i; - int qd_idx = r6s->qd_idx; + int qd_idx = sh->qd_idx; for (i = disks; i--; ) { struct r5dev *dev = &sh->dev[i]; /* Would I have to read this buffer for reconstruct_write */ @@ -2371,7 +2568,7 @@ static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh, int update_p = 0, update_q = 0; struct r5dev *dev; int pd_idx = sh->pd_idx; - int qd_idx = r6s->qd_idx; + int qd_idx = sh->qd_idx; set_bit(STRIPE_HANDLE, &sh->state); @@ -2467,17 +2664,14 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh, 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; + if (i != sh->pd_idx && i != sh->qd_idx) { + int dd_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); + sector_t bn = compute_blocknr(sh, i, 1); + sector_t s = raid5_compute_sector(conf, bn, 0, + &dd_idx, NULL); + sh2 = get_active_stripe(conf, s, 0, 1); if (sh2 == NULL) /* so far only the early blocks of this stripe * have been requested. When later blocks @@ -2500,8 +2694,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh, 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)) && + (!r6s || j != sh2->qd_idx) && !test_bit(R5_Expanded, &sh2->dev[j].flags)) break; if (j == conf->raid_disks) { @@ -2750,6 +2943,23 @@ static bool handle_stripe5(struct stripe_head *sh) /* Finish reconstruct operations initiated by the expansion process */ if (sh->reconstruct_state == reconstruct_state_result) { + struct stripe_head *sh2 + = get_active_stripe(conf, sh->sector, 1, 1); + if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) { + /* sh cannot be written until sh2 has been read. + * so arrange for sh to be delayed a little + */ + set_bit(STRIPE_DELAYED, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, + &sh2->state)) + atomic_inc(&conf->preread_active_stripes); + release_stripe(sh2); + goto unlock; + } + if (sh2) + release_stripe(sh2); + sh->reconstruct_state = reconstruct_state_idle; clear_bit(STRIPE_EXPANDING, &sh->state); for (i = conf->raid_disks; i--; ) { @@ -2763,8 +2973,7 @@ static bool handle_stripe5(struct stripe_head *sh) !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); + stripe_set_idx(sh->sector, conf, 0, sh); schedule_reconstruction5(sh, &s, 1, 1); } else if (s.expanded && !sh->reconstruct_state && s.locked == 0) { clear_bit(STRIPE_EXPAND_READY, &sh->state); @@ -2796,20 +3005,19 @@ static bool handle_stripe5(struct stripe_head *sh) static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page) { - raid6_conf_t *conf = sh->raid_conf; + raid5_conf_t *conf = sh->raid_conf; int disks = sh->disks; struct bio *return_bi = NULL; - int i, pd_idx = sh->pd_idx; + int i, pd_idx = sh->pd_idx, qd_idx = sh->qd_idx; struct stripe_head_state s; struct r6_state r6s; struct r5dev *dev, *pdev, *qdev; mdk_rdev_t *blocked_rdev = NULL; - 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); + atomic_read(&sh->count), pd_idx, qd_idx); memset(&s, 0, sizeof(s)); spin_lock(&sh->lock); @@ -2920,9 +3128,9 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page) pdev = &sh->dev[pd_idx]; 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); + qdev = &sh->dev[qd_idx]; + r6s.q_failed = (s.failed >= 1 && r6s.failed_num[0] == qd_idx) + || (s.failed >= 2 && r6s.failed_num[1] == qd_idx); if ( s.written && ( r6s.p_failed || ((test_bit(R5_Insync, &pdev->flags) @@ -2980,10 +3188,26 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page) } if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) { + struct stripe_head *sh2 + = get_active_stripe(conf, sh->sector, 1, 1); + if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) { + /* sh cannot be written until sh2 has been read. + * so arrange for sh to be delayed a little + */ + set_bit(STRIPE_DELAYED, &sh->state); + set_bit(STRIPE_HANDLE, &sh->state); + if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, + &sh2->state)) + atomic_inc(&conf->preread_active_stripes); + release_stripe(sh2); + goto unlock; + } + if (sh2) + release_stripe(sh2); + /* 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); + stripe_set_idx(sh->sector, conf, 0, sh); compute_parity6(sh, RECONSTRUCT_WRITE); for (i = conf->raid_disks ; i-- ; ) { set_bit(R5_LOCKED, &sh->dev[i].flags); @@ -3134,6 +3358,8 @@ static int raid5_mergeable_bvec(struct request_queue *q, if ((bvm->bi_rw & 1) == WRITE) return biovec->bv_len; /* always allow writes to be mergeable */ + if (mddev->new_chunk < mddev->chunk_size) + chunk_sectors = mddev->new_chunk >> 9; max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9; if (max < 0) max = 0; if (max <= biovec->bv_len && bio_sectors == 0) @@ -3149,6 +3375,8 @@ static int in_chunk_boundary(mddev_t *mddev, struct bio *bio) unsigned int chunk_sectors = mddev->chunk_size >> 9; unsigned int bio_sectors = bio->bi_size >> 9; + if (mddev->new_chunk < mddev->chunk_size) + chunk_sectors = mddev->new_chunk >> 9; return chunk_sectors >= ((sector & (chunk_sectors - 1)) + bio_sectors); } @@ -3255,9 +3483,7 @@ 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); - const unsigned int raid_disks = conf->raid_disks; - const unsigned int data_disks = raid_disks - conf->max_degraded; - unsigned int dd_idx, pd_idx; + unsigned int dd_idx; struct bio* align_bi; mdk_rdev_t *rdev; @@ -3266,7 +3492,7 @@ static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio) return 0; } /* - * use bio_clone to make a copy of the bio + * use bio_clone to make a copy of the bio */ align_bi = bio_clone(raid_bio, GFP_NOIO); if (!align_bi) @@ -3280,12 +3506,9 @@ static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio) /* * compute position */ - align_bi->bi_sector = raid5_compute_sector(raid_bio->bi_sector, - raid_disks, - data_disks, - &dd_idx, - &pd_idx, - conf); + align_bi->bi_sector = raid5_compute_sector(conf, raid_bio->bi_sector, + 0, + &dd_idx, NULL); rcu_read_lock(); rdev = rcu_dereference(conf->disks[dd_idx].rdev); @@ -3377,7 +3600,7 @@ static int make_request(struct request_queue *q, struct bio * bi) { mddev_t *mddev = q->queuedata; raid5_conf_t *conf = mddev_to_conf(mddev); - unsigned int dd_idx, pd_idx; + int dd_idx; sector_t new_sector; sector_t logical_sector, last_sector; struct stripe_head *sh; @@ -3400,7 +3623,7 @@ static int make_request(struct request_queue *q, struct bio * bi) if (rw == READ && mddev->reshape_position == MaxSector && chunk_aligned_read(q,bi)) - return 0; + return 0; logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1); last_sector = bi->bi_sector + (bi->bi_size>>9); @@ -3410,26 +3633,31 @@ static int make_request(struct request_queue *q, struct bio * bi) for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) { DEFINE_WAIT(w); int disks, data_disks; + int previous; retry: + previous = 0; + disks = conf->raid_disks; prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); - if (likely(conf->expand_progress == MaxSector)) - disks = conf->raid_disks; - else { - /* spinlock is needed as expand_progress may be + if (unlikely(conf->reshape_progress != MaxSector)) { + /* spinlock is needed as reshape_progress may be * 64bit on a 32bit platform, and so it might be * possible to see a half-updated value - * Ofcourse expand_progress could change after + * Ofcourse reshape_progress could change after * the lock is dropped, so once we get a reference * to the stripe that we think it is, we will have * to check again. */ spin_lock_irq(&conf->device_lock); - disks = conf->raid_disks; - if (logical_sector >= conf->expand_progress) + if (mddev->delta_disks < 0 + ? logical_sector < conf->reshape_progress + : logical_sector >= conf->reshape_progress) { disks = conf->previous_raid_disks; - else { - if (logical_sector >= conf->expand_lo) { + previous = 1; + } else { + if (mddev->delta_disks < 0 + ? logical_sector < conf->reshape_safe + : logical_sector >= conf->reshape_safe) { spin_unlock_irq(&conf->device_lock); schedule(); goto retry; @@ -3439,15 +3667,17 @@ static int make_request(struct request_queue *q, struct bio * bi) } |