diff options
Diffstat (limited to 'drivers/md/raid1.c')
| -rw-r--r-- | drivers/md/raid1.c | 3197 |
1 files changed, 1814 insertions, 1383 deletions
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ec734588a1c6..57d50465eed1 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * raid1.c : Multiple Devices driver for Linux * @@ -20,15 +21,6 @@ * * Additions to bitmap code, (C) 2003-2004 Paul Clements, SteelEye Technology: * - persistent bitmap code - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * You should have received a copy of the GNU General Public License - * (for example /usr/src/linux/COPYING); if not, write to the Free - * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/slab.h> @@ -37,76 +29,145 @@ #include <linux/module.h> #include <linux/seq_file.h> #include <linux/ratelimit.h> +#include <linux/interval_tree_generic.h> + +#include <trace/events/block.h> + #include "md.h" #include "raid1.h" -#include "bitmap.h" +#include "md-bitmap.h" +#include "md-cluster.h" -/* - * Number of guaranteed r1bios in case of extreme VM load: - */ -#define NR_RAID1_BIOS 256 +#define UNSUPPORTED_MDDEV_FLAGS \ + ((1L << MD_HAS_JOURNAL) | \ + (1L << MD_JOURNAL_CLEAN) | \ + (1L << MD_HAS_PPL) | \ + (1L << MD_HAS_MULTIPLE_PPLS)) -/* when we get a read error on a read-only array, we redirect to another - * device without failing the first device, or trying to over-write to - * correct the read error. To keep track of bad blocks on a per-bio - * level, we store IO_BLOCKED in the appropriate 'bios' pointer - */ -#define IO_BLOCKED ((struct bio *)1) -/* When we successfully write to a known bad-block, we need to remove the - * bad-block marking which must be done from process context. So we record - * the success by setting devs[n].bio to IO_MADE_GOOD - */ -#define IO_MADE_GOOD ((struct bio *)2) +static void allow_barrier(struct r1conf *conf, sector_t sector_nr); +static void lower_barrier(struct r1conf *conf, sector_t sector_nr); +static void raid1_free(struct mddev *mddev, void *priv); -#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2) +#define RAID_1_10_NAME "raid1" +#include "raid1-10.c" -/* When there are this many requests queue to be written by - * the raid1 thread, we become 'congested' to provide back-pressure - * for writeback. - */ -static int max_queued_requests = 1024; +#define START(node) ((node)->start) +#define LAST(node) ((node)->last) +INTERVAL_TREE_DEFINE(struct serial_info, node, sector_t, _subtree_last, + START, LAST, static inline, raid1_rb); -static void allow_barrier(struct r1conf *conf); -static void lower_barrier(struct r1conf *conf); +static int check_and_add_serial(struct md_rdev *rdev, struct r1bio *r1_bio, + struct serial_info *si, int idx) +{ + unsigned long flags; + int ret = 0; + sector_t lo = r1_bio->sector; + sector_t hi = lo + r1_bio->sectors; + struct serial_in_rdev *serial = &rdev->serial[idx]; + + spin_lock_irqsave(&serial->serial_lock, flags); + /* collision happened */ + if (raid1_rb_iter_first(&serial->serial_rb, lo, hi)) + ret = -EBUSY; + else { + si->start = lo; + si->last = hi; + raid1_rb_insert(si, &serial->serial_rb); + } + spin_unlock_irqrestore(&serial->serial_lock, flags); -static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data) + return ret; +} + +static void wait_for_serialization(struct md_rdev *rdev, struct r1bio *r1_bio) { - struct pool_info *pi = data; - int size = offsetof(struct r1bio, bios[pi->raid_disks]); + struct mddev *mddev = rdev->mddev; + struct serial_info *si; + int idx = sector_to_idx(r1_bio->sector); + struct serial_in_rdev *serial = &rdev->serial[idx]; - /* allocate a r1bio with room for raid_disks entries in the bios array */ - return kzalloc(size, gfp_flags); + if (WARN_ON(!mddev->serial_info_pool)) + return; + si = mempool_alloc(mddev->serial_info_pool, GFP_NOIO); + wait_event(serial->serial_io_wait, + check_and_add_serial(rdev, r1_bio, si, idx) == 0); +} + +static void remove_serial(struct md_rdev *rdev, sector_t lo, sector_t hi) +{ + struct serial_info *si; + unsigned long flags; + int found = 0; + struct mddev *mddev = rdev->mddev; + int idx = sector_to_idx(lo); + struct serial_in_rdev *serial = &rdev->serial[idx]; + + spin_lock_irqsave(&serial->serial_lock, flags); + for (si = raid1_rb_iter_first(&serial->serial_rb, lo, hi); + si; si = raid1_rb_iter_next(si, lo, hi)) { + if (si->start == lo && si->last == hi) { + raid1_rb_remove(si, &serial->serial_rb); + mempool_free(si, mddev->serial_info_pool); + found = 1; + break; + } + } + if (!found) + WARN(1, "The write IO is not recorded for serialization\n"); + spin_unlock_irqrestore(&serial->serial_lock, flags); + wake_up(&serial->serial_io_wait); +} + +/* + * for resync bio, r1bio pointer can be retrieved from the per-bio + * 'struct resync_pages'. + */ +static inline struct r1bio *get_resync_r1bio(struct bio *bio) +{ + return get_resync_pages(bio)->raid_bio; } -static void r1bio_pool_free(void *r1_bio, void *data) +static void *r1bio_pool_alloc(gfp_t gfp_flags, struct r1conf *conf) { - kfree(r1_bio); + int size = offsetof(struct r1bio, bios[conf->raid_disks * 2]); + + /* allocate a r1bio with room for raid_disks entries in the bios array */ + return kzalloc(size, gfp_flags); } -#define RESYNC_BLOCK_SIZE (64*1024) -//#define RESYNC_BLOCK_SIZE PAGE_SIZE +#define RESYNC_DEPTH 32 #define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9) -#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE) -#define RESYNC_WINDOW (2048*1024) +#define RESYNC_WINDOW (RESYNC_BLOCK_SIZE * RESYNC_DEPTH) +#define RESYNC_WINDOW_SECTORS (RESYNC_WINDOW >> 9) +#define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW) +#define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9) static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) { - struct pool_info *pi = data; + struct r1conf *conf = data; struct r1bio *r1_bio; struct bio *bio; - int i, j; + int need_pages; + int j; + struct resync_pages *rps; - r1_bio = r1bio_pool_alloc(gfp_flags, pi); + r1_bio = r1bio_pool_alloc(gfp_flags, conf); if (!r1_bio) return NULL; + rps = kmalloc_array(conf->raid_disks * 2, sizeof(struct resync_pages), + gfp_flags); + if (!rps) + goto out_free_r1bio; + /* * Allocate bios : 1 for reading, n-1 for writing */ - for (j = pi->raid_disks ; j-- ; ) { - bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); + for (j = conf->raid_disks * 2; j-- ; ) { + bio = bio_kmalloc(RESYNC_PAGES, gfp_flags); if (!bio) goto out_free_bio; + bio_init_inline(bio, NULL, RESYNC_PAGES, 0); r1_bio->bios[j] = bio; } /* @@ -115,53 +176,65 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) * If this is a user-requested check/repair, allocate * RESYNC_PAGES for each bio. */ - if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) - j = pi->raid_disks; + if (test_bit(MD_RECOVERY_REQUESTED, &conf->mddev->recovery)) + need_pages = conf->raid_disks * 2; else - j = 1; - while(j--) { + need_pages = 1; + for (j = 0; j < conf->raid_disks * 2; j++) { + struct resync_pages *rp = &rps[j]; + bio = r1_bio->bios[j]; - bio->bi_vcnt = RESYNC_PAGES; - if (bio_alloc_pages(bio, gfp_flags)) - goto out_free_bio; - } - /* If not user-requests, copy the page pointers to all bios */ - if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) { - for (i=0; i<RESYNC_PAGES ; i++) - for (j=1; j<pi->raid_disks; j++) - r1_bio->bios[j]->bi_io_vec[i].bv_page = - r1_bio->bios[0]->bi_io_vec[i].bv_page; + if (j < need_pages) { + if (resync_alloc_pages(rp, gfp_flags)) + goto out_free_pages; + } else { + memcpy(rp, &rps[0], sizeof(*rp)); + resync_get_all_pages(rp); + } + + rp->raid_bio = r1_bio; + bio->bi_private = rp; } r1_bio->master_bio = NULL; return r1_bio; +out_free_pages: + while (--j >= 0) + resync_free_pages(&rps[j]); + out_free_bio: - while (++j < pi->raid_disks) - bio_put(r1_bio->bios[j]); - r1bio_pool_free(r1_bio, data); + while (++j < conf->raid_disks * 2) { + bio_uninit(r1_bio->bios[j]); + kfree(r1_bio->bios[j]); + } + kfree(rps); + +out_free_r1bio: + rbio_pool_free(r1_bio, data); return NULL; } static void r1buf_pool_free(void *__r1_bio, void *data) { - struct pool_info *pi = data; - int i,j; + struct r1conf *conf = data; + int i; struct r1bio *r1bio = __r1_bio; + struct resync_pages *rp = NULL; - for (i = 0; i < RESYNC_PAGES; i++) - for (j = pi->raid_disks; j-- ;) { - if (j == 0 || - r1bio->bios[j]->bi_io_vec[i].bv_page != - r1bio->bios[0]->bi_io_vec[i].bv_page) - safe_put_page(r1bio->bios[j]->bi_io_vec[i].bv_page); - } - for (i=0 ; i < pi->raid_disks; i++) - bio_put(r1bio->bios[i]); + for (i = conf->raid_disks * 2; i--; ) { + rp = get_resync_pages(r1bio->bios[i]); + resync_free_pages(rp); + bio_uninit(r1bio->bios[i]); + kfree(r1bio->bios[i]); + } - r1bio_pool_free(r1bio, data); + /* resync pages array stored in the 1st bio's .bi_private */ + kfree(rp); + + rbio_pool_free(r1bio, data); } static void put_all_bios(struct r1conf *conf, struct r1bio *r1_bio) @@ -187,6 +260,7 @@ static void free_r1bio(struct r1bio *r1_bio) static void put_buf(struct r1bio *r1_bio) { struct r1conf *conf = r1_bio->mddev->private; + sector_t sect = r1_bio->sector; int i; for (i = 0; i < conf->raid_disks * 2; i++) { @@ -195,9 +269,9 @@ static void put_buf(struct r1bio *r1_bio) rdev_dec_pending(conf->mirrors[i].rdev, r1_bio->mddev); } - mempool_free(r1_bio, conf->r1buf_pool); + mempool_free(r1_bio, &conf->r1buf_pool); - lower_barrier(conf); + lower_barrier(conf, sect); } static void reschedule_retry(struct r1bio *r1_bio) @@ -205,10 +279,12 @@ static void reschedule_retry(struct r1bio *r1_bio) unsigned long flags; struct mddev *mddev = r1_bio->mddev; struct r1conf *conf = mddev->private; + int idx; + idx = sector_to_idx(r1_bio->sector); spin_lock_irqsave(&conf->device_lock, flags); list_add(&r1_bio->retry_list, &conf->retry_list); - conf->nr_queued ++; + atomic_inc(&conf->nr_queued[idx]); spin_unlock_irqrestore(&conf->device_lock, flags); wake_up(&conf->wait_barrier); @@ -223,45 +299,35 @@ static void reschedule_retry(struct r1bio *r1_bio) static void call_bio_endio(struct r1bio *r1_bio) { struct bio *bio = r1_bio->master_bio; - int done; - struct r1conf *conf = r1_bio->mddev->private; - - if (bio->bi_phys_segments) { - unsigned long flags; - spin_lock_irqsave(&conf->device_lock, flags); - bio->bi_phys_segments--; - done = (bio->bi_phys_segments == 0); - spin_unlock_irqrestore(&conf->device_lock, flags); - } else - done = 1; if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) - clear_bit(BIO_UPTODATE, &bio->bi_flags); - if (done) { - bio_endio(bio, 0); - /* - * Wake up any possible resync thread that waits for the device - * to go idle. - */ - allow_barrier(conf); - } + bio->bi_status = BLK_STS_IOERR; + + bio_endio(bio); } static void raid_end_bio_io(struct r1bio *r1_bio) { struct bio *bio = r1_bio->master_bio; + struct r1conf *conf = r1_bio->mddev->private; + sector_t sector = r1_bio->sector; /* if nobody has done the final endio yet, do it now */ if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) { pr_debug("raid1: sync end %s on sectors %llu-%llu\n", (bio_data_dir(bio) == WRITE) ? "write" : "read", - (unsigned long long) bio->bi_sector, - (unsigned long long) bio->bi_sector + - bio_sectors(bio) - 1); + (unsigned long long) bio->bi_iter.bi_sector, + (unsigned long long) bio_end_sector(bio) - 1); call_bio_endio(r1_bio); } + free_r1bio(r1_bio); + /* + * Wake up any possible resync thread that waits for the device + * to go idle. All I/Os, even write-behind writes, are done. + */ + allow_barrier(conf, sector); } /* @@ -294,22 +360,28 @@ static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio) return mirror; } -static void raid1_end_read_request(struct bio *bio, int error) +static void raid1_end_read_request(struct bio *bio) { - int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + int uptodate = !bio->bi_status; struct r1bio *r1_bio = bio->bi_private; - int mirror; struct r1conf *conf = r1_bio->mddev->private; + struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev; - mirror = r1_bio->read_disk; /* * this branch is our 'one mirror IO has finished' event handler: */ - update_head_pos(mirror, r1_bio); + update_head_pos(r1_bio->read_disk, r1_bio); - if (uptodate) + if (uptodate) { set_bit(R1BIO_Uptodate, &r1_bio->state); - else { + } else if (test_bit(FailFast, &rdev->flags) && + test_bit(R1BIO_FailFast, &r1_bio->state)) { + /* This was a fail-fast read so we definitely + * want to retry */ + ; + } else if (!raid1_should_handle_error(bio)) { + uptodate = 1; + } else { /* If all other devices have failed, we want to return * the error upwards rather than fail the last device. * Here we redefine "uptodate" to mean "Don't want to retry" @@ -318,26 +390,22 @@ static void raid1_end_read_request(struct bio *bio, int error) spin_lock_irqsave(&conf->device_lock, flags); if (r1_bio->mddev->degraded == conf->raid_disks || (r1_bio->mddev->degraded == conf->raid_disks-1 && - !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags))) + test_bit(In_sync, &rdev->flags))) uptodate = 1; spin_unlock_irqrestore(&conf->device_lock, flags); } if (uptodate) { raid_end_bio_io(r1_bio); - rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev); + rdev_dec_pending(rdev, conf->mddev); } else { /* * oops, read error: */ - char b[BDEVNAME_SIZE]; - printk_ratelimited( - KERN_ERR "md/raid1:%s: %s: " - "rescheduling sector %llu\n", - mdname(conf->mddev), - bdevname(conf->mirrors[mirror].rdev->bdev, - b), - (unsigned long long)r1_bio->sector); + pr_err_ratelimited("md/raid1:%s: %pg: rescheduling sector %llu\n", + mdname(conf->mddev), + rdev->bdev, + (unsigned long long)r1_bio->sector); set_bit(R1BIO_ReadError, &r1_bio->state); reschedule_retry(r1_bio); /* don't drop the reference on read_disk yet */ @@ -346,21 +414,18 @@ static void raid1_end_read_request(struct bio *bio, int error) static void close_write(struct r1bio *r1_bio) { + struct mddev *mddev = r1_bio->mddev; + /* it really is the end of this request */ if (test_bit(R1BIO_BehindIO, &r1_bio->state)) { - /* free extra copy of the data pages */ - int i = r1_bio->behind_page_count; - while (i--) - safe_put_page(r1_bio->behind_bvecs[i].bv_page); - kfree(r1_bio->behind_bvecs); - r1_bio->behind_bvecs = NULL; + bio_free_pages(r1_bio->behind_master_bio); + bio_put(r1_bio->behind_master_bio); + r1_bio->behind_master_bio = NULL; } - /* clear the bitmap if all writes complete successfully */ - bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector, - r1_bio->sectors, - !test_bit(R1BIO_Degraded, &r1_bio->state), - test_bit(R1BIO_BehindIO, &r1_bio->state)); - md_write_end(r1_bio->mddev); + + if (test_bit(R1BIO_BehindIO, &r1_bio->state)) + mddev->bitmap_ops->end_behind_write(mddev); + md_write_end(mddev); } static void r1_bio_write_done(struct r1bio *r1_bio) @@ -379,28 +444,46 @@ static void r1_bio_write_done(struct r1bio *r1_bio) } } -static void raid1_end_write_request(struct bio *bio, int error) +static void raid1_end_write_request(struct bio *bio) { - int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct r1bio *r1_bio = bio->bi_private; - int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state); + int behind = test_bit(R1BIO_BehindIO, &r1_bio->state); struct r1conf *conf = r1_bio->mddev->private; struct bio *to_put = NULL; - - mirror = find_bio_disk(r1_bio, bio); + int mirror = find_bio_disk(r1_bio, bio); + struct md_rdev *rdev = conf->mirrors[mirror].rdev; + sector_t lo = r1_bio->sector; + sector_t hi = r1_bio->sector + r1_bio->sectors; + bool ignore_error = !raid1_should_handle_error(bio) || + (bio->bi_status && bio_op(bio) == REQ_OP_DISCARD); /* * 'one mirror IO has finished' event handler: */ - if (!uptodate) { - set_bit(WriteErrorSeen, - &conf->mirrors[mirror].rdev->flags); - if (!test_and_set_bit(WantReplacement, - &conf->mirrors[mirror].rdev->flags)) + if (bio->bi_status && !ignore_error) { + set_bit(WriteErrorSeen, &rdev->flags); + if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, & conf->mddev->recovery); - set_bit(R1BIO_WriteError, &r1_bio->state); + if (test_bit(FailFast, &rdev->flags) && + (bio->bi_opf & MD_FAILFAST) && + /* We never try FailFast to WriteMostly devices */ + !test_bit(WriteMostly, &rdev->flags)) { + md_error(r1_bio->mddev, rdev); + } + + /* + * When the device is faulty, it is not necessary to + * handle write error. + */ + if (!test_bit(Faulty, &rdev->flags)) + set_bit(R1BIO_WriteError, &r1_bio->state); + else { + /* Finished with this branch */ + r1_bio->bios[mirror] = NULL; + to_put = bio; + } } else { /* * Set R1BIO_Uptodate in our master bio, so that we @@ -412,9 +495,6 @@ static void raid1_end_write_request(struct bio *bio, int error) * to user-side. So if something waits for IO, then it * will wait for the 'master' bio. */ - sector_t first_bad; - int bad_sectors; - r1_bio->bios[mirror] = NULL; to_put = bio; /* @@ -425,21 +505,22 @@ static void raid1_end_write_request(struct bio *bio, int error) * before rdev->recovery_offset, but for simplicity we don't * check this here. */ - if (test_bit(In_sync, &conf->mirrors[mirror].rdev->flags) && - !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)) + if (test_bit(In_sync, &rdev->flags) && + !test_bit(Faulty, &rdev->flags)) set_bit(R1BIO_Uptodate, &r1_bio->state); /* Maybe we can clear some bad blocks. */ - if (is_badblock(conf->mirrors[mirror].rdev, - r1_bio->sector, r1_bio->sectors, - &first_bad, &bad_sectors)) { + if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) && + !ignore_error) { r1_bio->bios[mirror] = IO_MADE_GOOD; set_bit(R1BIO_MadeGood, &r1_bio->state); } } if (behind) { - if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags)) + if (test_bit(CollisionCheck, &rdev->flags)) + remove_serial(rdev, lo, hi); + if (test_bit(WriteMostly, &rdev->flags)) atomic_dec(&r1_bio->behind_remaining); /* @@ -456,16 +537,15 @@ static void raid1_end_write_request(struct bio *bio, int error) struct bio *mbio = r1_bio->master_bio; pr_debug("raid1: behind end write sectors" " %llu-%llu\n", - (unsigned long long) mbio->bi_sector, - (unsigned long long) mbio->bi_sector + - bio_sectors(mbio) - 1); + (unsigned long long) mbio->bi_iter.bi_sector, + (unsigned long long) bio_end_sector(mbio) - 1); call_bio_endio(r1_bio); } } - } + } else if (rdev->mddev->serialize_policy) + remove_serial(rdev, lo, hi); if (r1_bio->bios[mirror] == NULL) - rdev_dec_pending(conf->mirrors[mirror].rdev, - conf->mddev); + rdev_dec_pending(rdev, conf->mddev); /* * Let's see if all mirrored write operations have finished @@ -477,288 +557,359 @@ static void raid1_end_write_request(struct bio *bio, int error) bio_put(to_put); } - -/* - * This routine returns the disk from which the requested read should - * be done. There is a per-array 'next expected sequential IO' sector - * number - if this matches on the next IO then we use the last disk. - * There is also a per-disk 'last know head position' sector that is - * maintained from IRQ contexts, both the normal and the resync IO - * completion handlers update this position correctly. If there is no - * perfect sequential match then we pick the disk whose head is closest. - * - * If there are 2 mirrors in the same 2 devices, performance degrades - * because position is mirror, not device based. - * - * The rdev for the device selected will have nr_pending incremented. - */ -static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors) +static sector_t align_to_barrier_unit_end(sector_t start_sector, + sector_t sectors) { - const sector_t this_sector = r1_bio->sector; - int sectors; - int best_good_sectors; - int best_disk, best_dist_disk, best_pending_disk; - int has_nonrot_disk; - int disk; - sector_t best_dist; - unsigned int min_pending; - struct md_rdev *rdev; - int choose_first; - int choose_next_idle; + sector_t len; - rcu_read_lock(); + WARN_ON(sectors == 0); /* - * Check if we can balance. We can balance on the whole - * device if no resync is going on, or below the resync window. - * We take the first readable disk when above the resync window. + * len is the number of sectors from start_sector to end of the + * barrier unit which start_sector belongs to. */ - retry: - sectors = r1_bio->sectors; - best_disk = -1; - best_dist_disk = -1; - best_dist = MaxSector; - best_pending_disk = -1; - min_pending = UINT_MAX; - best_good_sectors = 0; - has_nonrot_disk = 0; - choose_next_idle = 0; - - if (conf->mddev->recovery_cp < MaxSector && - (this_sector + sectors >= conf->next_resync)) - choose_first = 1; - else - choose_first = 0; + len = round_up(start_sector + 1, BARRIER_UNIT_SECTOR_SIZE) - + start_sector; + + if (len > sectors) + len = sectors; + + return len; +} + +static void update_read_sectors(struct r1conf *conf, int disk, + sector_t this_sector, int len) +{ + struct raid1_info *info = &conf->mirrors[disk]; + + atomic_inc(&info->rdev->nr_pending); + if (info->next_seq_sect != this_sector) + info->seq_start = this_sector; + info->next_seq_sect = this_sector + len; +} + +static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio, + int *max_sectors) +{ + sector_t this_sector = r1_bio->sector; + int len = r1_bio->sectors; + int disk; for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { - sector_t dist; - sector_t first_bad; - int bad_sectors; - unsigned int pending; - bool nonrot; + struct md_rdev *rdev; + int read_len; - rdev = rcu_dereference(conf->mirrors[disk].rdev); - if (r1_bio->bios[disk] == IO_BLOCKED - || rdev == NULL - || test_bit(Unmerged, &rdev->flags) - || test_bit(Faulty, &rdev->flags)) - continue; - if (!test_bit(In_sync, &rdev->flags) && - rdev->recovery_offset < this_sector + sectors) + if (r1_bio->bios[disk] == IO_BLOCKED) continue; - if (test_bit(WriteMostly, &rdev->flags)) { - /* Don't balance among write-mostly, just - * use the first as a last resort */ - if (best_disk < 0) { - if (is_badblock(rdev, this_sector, sectors, - &first_bad, &bad_sectors)) { - if (first_bad < this_sector) - /* Cannot use this */ - continue; - best_good_sectors = first_bad - this_sector; - } else - best_good_sectors = sectors; - best_disk = disk; - } + + rdev = conf->mirrors[disk].rdev; + if (!rdev || test_bit(Faulty, &rdev->flags)) continue; + + /* choose the first disk even if it has some bad blocks. */ + read_len = raid1_check_read_range(rdev, this_sector, &len); + if (read_len > 0) { + update_read_sectors(conf, disk, this_sector, read_len); + *max_sectors = read_len; + return disk; } - /* This is a reasonable device to use. It might - * even be best. - */ - if (is_badblock(rdev, this_sector, sectors, - &first_bad, &bad_sectors)) { - if (best_dist < MaxSector) - /* already have a better device */ - continue; - if (first_bad <= this_sector) { - /* cannot read here. If this is the 'primary' - * device, then we must not read beyond - * bad_sectors from another device.. - */ - bad_sectors -= (this_sector - first_bad); - if (choose_first && sectors > bad_sectors) - sectors = bad_sectors; - if (best_good_sectors > sectors) - best_good_sectors = sectors; - - } else { - sector_t good_sectors = first_bad - this_sector; - if (good_sectors > best_good_sectors) { - best_good_sectors = good_sectors; - best_disk = disk; - } - if (choose_first) - break; - } + } + + return -1; +} + +static bool rdev_in_recovery(struct md_rdev *rdev, struct r1bio *r1_bio) +{ + return !test_bit(In_sync, &rdev->flags) && + rdev->recovery_offset < r1_bio->sector + r1_bio->sectors; +} + +static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio, + int *max_sectors) +{ + sector_t this_sector = r1_bio->sector; + int best_disk = -1; + int best_len = 0; + int disk; + + for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { + struct md_rdev *rdev; + int len; + int read_len; + + if (r1_bio->bios[disk] == IO_BLOCKED) continue; - } else - best_good_sectors = sectors; - nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev)); - has_nonrot_disk |= nonrot; - pending = atomic_read(&rdev->nr_pending); - dist = abs(this_sector - conf->mirrors[disk].head_position); - if (choose_first) { - best_disk = disk; - break; - } - /* Don't change to another disk for sequential reads */ - if (conf->mirrors[disk].next_seq_sect == this_sector - || dist == 0) { - int opt_iosize = bdev_io_opt(rdev->bdev) >> 9; - struct raid1_info *mirror = &conf->mirrors[disk]; + rdev = conf->mirrors[disk].rdev; + if (!rdev || test_bit(Faulty, &rdev->flags) || + rdev_in_recovery(rdev, r1_bio) || + test_bit(WriteMostly, &rdev->flags)) + continue; + /* keep track of the disk with the most readable sectors. */ + len = r1_bio->sectors; + read_len = raid1_check_read_range(rdev, this_sector, &len); + if (read_len > best_len) { best_disk = disk; - /* - * If buffered sequential IO size exceeds optimal - * iosize, check if there is idle disk. If yes, choose - * the idle disk. read_balance could already choose an - * idle disk before noticing it's a sequential IO in - * this disk. This doesn't matter because this disk - * will idle, next time it will be utilized after the - * first disk has IO size exceeds optimal iosize. In - * this way, iosize of the first disk will be optimal - * iosize at least. iosize of the second disk might be - * small, but not a big deal since when the second disk - * starts IO, the first disk is likely still busy. - */ - if (nonrot && opt_iosize > 0 && - mirror->seq_start != MaxSector && - mirror->next_seq_sect > opt_iosize && - mirror->next_seq_sect - opt_iosize >= - mirror->seq_start) { - choose_next_idle = 1; - continue; - } - break; - } - /* If device is idle, use it */ - if (pending == 0) { - best_disk = disk; - break; + best_len = read_len; } + } + + if (best_disk != -1) { + *max_sectors = best_len; + update_read_sectors(conf, best_disk, this_sector, best_len); + } + + return best_disk; +} + +static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio, + int *max_sectors) +{ + sector_t this_sector = r1_bio->sector; + int bb_disk = -1; + int bb_read_len = 0; + int disk; + + for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { + struct md_rdev *rdev; + int len; + int read_len; - if (choose_next_idle) + if (r1_bio->bios[disk] == IO_BLOCKED) continue; - if (min_pending > pending) { - min_pending = pending; - best_pending_disk = disk; + rdev = conf->mirrors[disk].rdev; + if (!rdev || test_bit(Faulty, &rdev->flags) || + !test_bit(WriteMostly, &rdev->flags) || + rdev_in_recovery(rdev, r1_bio)) + continue; + + /* there are no bad blocks, we can use this disk */ + len = r1_bio->sectors; + read_len = raid1_check_read_range(rdev, this_sector, &len); + if (read_len == r1_bio->sectors) { + *max_sectors = read_len; + update_read_sectors(conf, disk, this_sector, read_len); + return disk; } - if (dist < best_dist) { - best_dist = dist; - best_dist_disk = disk; + /* + * there are partial bad blocks, choose the rdev with largest + * read length. + */ + if (read_len > bb_read_len) { + bb_disk = disk; + bb_read_len = read_len; } } - /* - * If all disks are rotational, choose the closest disk. If any disk is - * non-rotational, choose the disk with less pending request even the - * disk is rotational, which might/might not be optimal for raids with - * mixed ratation/non-rotational disks depending on workload. - */ - if (best_disk == -1) { - if (has_nonrot_disk) - best_disk = best_pending_disk; - else - best_disk = best_dist_disk; + if (bb_disk != -1) { + *max_sectors = bb_read_len; + update_read_sectors(conf, bb_disk, this_sector, bb_read_len); } - if (best_disk >= 0) { - rdev = rcu_dereference(conf->mirrors[best_disk].rdev); - if (!rdev) - goto retry; - atomic_inc(&rdev->nr_pending); - if (test_bit(Faulty, &rdev->flags)) { - /* cannot risk returning a device that failed - * before we inc'ed nr_pending - */ - rdev_dec_pending(rdev, conf->mddev); - goto retry; - } - sectors = best_good_sectors; + return bb_disk; +} - if (conf->mirrors[best_disk].next_seq_sect != this_sector) - conf->mirrors[best_disk].seq_start = this_sector; +static bool is_sequential(struct r1conf *conf, int disk, struct r1bio *r1_bio) +{ + /* TODO: address issues with this check and concurrency. */ + return conf->mirrors[disk].next_seq_sect == r1_bio->sector || + conf->mirrors[disk].head_position == r1_bio->sector; +} - conf->mirrors[best_disk].next_seq_sect = this_sector + sectors; - } - rcu_read_unlock(); - *max_sectors = sectors; +/* + * If buffered sequential IO size exceeds optimal iosize, check if there is idle + * disk. If yes, choose the idle disk. + */ +static bool should_choose_next(struct r1conf *conf, int disk) +{ + struct raid1_info *mirror = &conf->mirrors[disk]; + int opt_iosize; - return best_disk; + if (!test_bit(Nonrot, &mirror->rdev->flags)) + return false; + + opt_iosize = bdev_io_opt(mirror->rdev->bdev) >> 9; + return opt_iosize > 0 && mirror->seq_start != MaxSector && + mirror->next_seq_sect > opt_iosize && + mirror->next_seq_sect - opt_iosize >= mirror->seq_start; } -static int raid1_mergeable_bvec(struct request_queue *q, - struct bvec_merge_data *bvm, - struct bio_vec *biovec) +static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio) { - struct mddev *mddev = q->queuedata; - struct r1conf *conf = mddev->private; - sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev); - int max = biovec->bv_len; - - if (mddev->merge_check_needed) { - int disk; - rcu_read_lock(); - for (disk = 0; disk < conf->raid_disks * 2; disk++) { - struct md_rdev *rdev = rcu_dereference( - conf->mirrors[disk].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct request_queue *q = - bdev_get_queue(rdev->bdev); - if (q->merge_bvec_fn) { - bvm->bi_sector = sector + - rdev->data_offset; - bvm->bi_bdev = rdev->bdev; - max = min(max, q->merge_bvec_fn( - q, bvm, biovec)); - } - } - } - rcu_read_unlock(); - } - return max; + if (!rdev || test_bit(Faulty, &rdev->flags)) + return false; + + if (rdev_in_recovery(rdev, r1_bio)) + return false; + /* don't read from slow disk unless have to */ + if (test_bit(WriteMostly, &rdev->flags)) + return false; + + /* don't split IO for bad blocks unless have to */ + if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors)) + return false; + + return true; } -int md_raid1_congested(struct mddev *mddev, int bits) +struct read_balance_ctl { + sector_t closest_dist; + int closest_dist_disk; + int min_pending; + int min_pending_disk; + int sequential_disk; + int readable_disks; +}; + +static int choose_best_rdev(struct r1conf *conf, struct r1bio *r1_bio) { - struct r1conf *conf = mddev->private; - int i, ret = 0; + int disk; + struct read_balance_ctl ctl = { + .closest_dist_disk = -1, + .closest_dist = MaxSector, + .min_pending_disk = -1, + .min_pending = UINT_MAX, + .sequential_disk = -1, + }; - if ((bits & (1 << BDI_async_congested)) && - conf->pending_count >= max_queued_requests) - return 1; + for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) { + struct md_rdev *rdev; + sector_t dist; + unsigned int pending; - rcu_read_lock(); - for (i = 0; i < conf->raid_disks * 2; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct request_queue *q = bdev_get_queue(rdev->bdev); + if (r1_bio->bios[disk] == IO_BLOCKED) + continue; + + rdev = conf->mirrors[disk].rdev; + if (!rdev_readable(rdev, r1_bio)) + continue; + + /* At least two disks to choose from so failfast is OK */ + if (ctl.readable_disks++ == 1) + set_bit(R1BIO_FailFast, &r1_bio->state); + + pending = atomic_read(&rdev->nr_pending); + dist = abs(r1_bio->sector - conf->mirrors[disk].head_position); - BUG_ON(!q); + /* Don't change to another disk for sequential reads */ + if (is_sequential(conf, disk, r1_bio)) { + if (!should_choose_next(conf, disk)) + return disk; - /* Note the '|| 1' - when read_balance prefers - * non-congested targets, it can be removed + /* + * Add 'pending' to avoid choosing this disk if + * there is other idle disk. */ - if ((bits & (1<<BDI_async_congested)) || 1) - ret |= bdi_congested(&q->backing_dev_info, bits); - else - ret &= bdi_congested(&q->backing_dev_info, bits); + pending++; + /* + * If there is no other idle disk, this disk + * will be chosen. + */ + ctl.sequential_disk = disk; + } + + if (ctl.min_pending > pending) { + ctl.min_pending = pending; + ctl.min_pending_disk = disk; + } + + if (ctl.closest_dist > dist) { + ctl.closest_dist = dist; + ctl.closest_dist_disk = disk; } } - rcu_read_unlock(); - return ret; + + /* + * sequential IO size exceeds optimal iosize, however, there is no other + * idle disk, so choose the sequential disk. + */ + if (ctl.sequential_disk != -1 && ctl.min_pending != 0) + return ctl.sequential_disk; + + /* + * If all disks are rotational, choose the closest disk. If any disk is + * non-rotational, choose the disk with less pending request even the + * disk is rotational, which might/might not be optimal for raids with + * mixed ratation/non-rotational disks depending on workload. + */ + if (ctl.min_pending_disk != -1 && + (READ_ONCE(conf->nonrot_disks) || ctl.min_pending == 0)) + return ctl.min_pending_disk; + else + return ctl.closest_dist_disk; +} + +/* + * This routine returns the disk from which the requested read should be done. + * + * 1) If resync is in progress, find the first usable disk and use it even if it + * has some bad blocks. + * + * 2) Now that there is no resync, loop through all disks and skipping slow + * disks and disks with bad blocks for now. Only pay attention to key disk + * choice. + * + * 3) If we've made it this far, now look for disks with bad blocks and choose + * the one with most number of sectors. + * + * 4) If we are all the way at the end, we have no choice but to use a disk even + * if it is write mostly. + * + * The rdev for the device selected will have nr_pending incremented. + */ +static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, + int *max_sectors) +{ + int disk; + + clear_bit(R1BIO_FailFast, &r1_bio->state); + + if (raid1_should_read_first(conf->mddev, r1_bio->sector, + r1_bio->sectors)) + return choose_first_rdev(conf, r1_bio, max_sectors); + + disk = choose_best_rdev(conf, r1_bio); + if (disk >= 0) { + *max_sectors = r1_bio->sectors; + update_read_sectors(conf, disk, r1_bio->sector, + r1_bio->sectors); + return disk; + } + + /* + * If we are here it means we didn't find a perfectly good disk so + * now spend a bit more time trying to find one with the most good + * sectors. + */ + disk = choose_bb_rdev(conf, r1_bio, max_sectors); + if (disk >= 0) + return disk; + + return choose_slow_rdev(conf, r1_bio, max_sectors); } -EXPORT_SYMBOL_GPL(md_raid1_congested); -static int raid1_congested(void *data, int bits) +static void wake_up_barrier(struct r1conf *conf) { - struct mddev *mddev = data; + if (wq_has_sleeper(&conf->wait_barrier)) + wake_up(&conf->wait_barrier); +} + +static void flush_bio_list(struct r1conf *conf, struct bio *bio) +{ + /* flush any pending bitmap writes to disk before proceeding w/ I/O */ + raid1_prepare_flush_writes(conf->mddev); + wake_up_barrier(conf); + + while (bio) { /* submit pending writes */ + struct bio *next = bio->bi_next; - return mddev_congested(mddev, bits) || - md_raid1_congested(mddev, bits); + raid1_submit_write(bio); + bio = next; + cond_resched(); + } } static void flush_pending_writes(struct r1conf *conf) @@ -769,26 +920,25 @@ static void flush_pending_writes(struct r1conf *conf) spin_lock_irq(&conf->device_lock); if (conf->pending_bio_list.head) { + struct blk_plug plug; struct bio *bio; + bio = bio_list_get(&conf->pending_bio_list); - conf->pending_count = 0; spin_unlock_irq(&conf->device_lock); - /* flush any pending bitmap writes to - * disk before proceeding w/ I/O */ - bitmap_unplug(conf->mddev->bitmap); - wake_up(&conf->wait_barrier); - while (bio) { /* submit pending writes */ - struct bio *next = bio->bi_next; - bio->bi_next = NULL; - if (unlikely((bio->bi_rw & REQ_DISCARD) && - !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) - /* Just ignore it */ - bio_endio(bio, 0); - else - generic_make_request(bio); - bio = next; - } + /* + * As this is called in a wait_event() loop (see freeze_array), + * current->state might be TASK_UNINTERRUPTIBLE which will + * cause a warning when we prepare to wait again. As it is + * rare that this path is taken, it is perfectly safe to force + * us to go around the wait_event() loop again, so the warning + * is a false-positive. Silence the warning by resetting + * thread state + */ + __set_current_state(TASK_RUNNING); + blk_start_plug(&plug); + flush_bio_list(conf, bio); + blk_finish_plug(&plug); } else spin_unlock_irq(&conf->device_lock); } @@ -813,147 +963,308 @@ static void flush_pending_writes(struct r1conf *conf) * backgroup IO calls must call raise_barrier. Once that returns * there is no normal IO happeing. It must arrange to call * lower_barrier when the particular background IO completes. + * + * If resync/recovery is interrupted, returns -EINTR; + * Otherwise, returns 0. */ -#define RESYNC_DEPTH 32 - -static void raise_barrier(struct r1conf *conf) +static int raise_barrier(struct r1conf *conf, sector_t sector_nr) { + int idx = sector_to_idx(sector_nr); + spin_lock_irq(&conf->resync_lock); /* Wait until no block IO is waiting */ - wait_event_lock_irq(conf->wait_barrier, !conf->nr_waiting, + wait_event_lock_irq(conf->wait_barrier, + !atomic_read(&conf->nr_waiting[idx]), conf->resync_lock); /* block any new IO from starting */ - conf->barrier++; - - /* Now wait for all pending IO to complete */ + atomic_inc(&conf->barrier[idx]); + /* + * In raise_barrier() we firstly increase conf->barrier[idx] then + * check conf->nr_pending[idx]. In _wait_barrier() we firstly + * increase conf->nr_pending[idx] then check conf->barrier[idx]. + * A memory barrier here to make sure conf->nr_pending[idx] won't + * be fetched before conf->barrier[idx] is increased. Otherwise + * there will be a race between raise_barrier() and _wait_barrier(). + */ + smp_mb__after_atomic(); + + /* For these conditions we must wait: + * A: while the array is in frozen state + * B: while conf->nr_pending[idx] is not 0, meaning regular I/O + * existing in corresponding I/O barrier bucket. + * C: while conf->barrier[idx] >= RESYNC_DEPTH, meaning reaches + * max resync count which allowed on current I/O barrier bucket. + */ wait_event_lock_irq(conf->wait_barrier, - !conf->nr_pending && conf->barrier < RESYNC_DEPTH, + (!conf->array_frozen && + !atomic_read(&conf->nr_pending[idx]) && + atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH) || + test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery), conf->resync_lock); + if (test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) { + atomic_dec(&conf->barrier[idx]); + spin_unlock_irq(&conf->resync_lock); + wake_up(&conf->wait_barrier); + return -EINTR; + } + + atomic_inc(&conf->nr_sync_pending); spin_unlock_irq(&conf->resync_lock); + + return 0; } -static void lower_barrier(struct r1conf *conf) +static void lower_barrier(struct r1conf *conf, sector_t sector_nr) { - unsigned long flags; - BUG_ON(conf->barrier <= 0); - spin_lock_irqsave(&conf->resync_lock, flags); - conf->barrier--; - spin_unlock_irqrestore(&conf->resync_lock, flags); + int idx = sector_to_idx(sector_nr); + + BUG_ON(atomic_read(&conf->barrier[idx]) <= 0); + + atomic_dec(&conf->barrier[idx]); + atomic_dec(&conf->nr_sync_pending); wake_up(&conf->wait_barrier); } -static void wait_barrier(struct r1conf *conf) +static bool _wait_barrier(struct r1conf *conf, int idx, bool nowait) { + bool ret = true; + + /* + * We need to increase conf->nr_pending[idx] very early here, + * then raise_barrier() can be blocked when it waits for + * conf->nr_pending[idx] to be 0. Then we can avoid holding + * conf->resync_lock when there is no barrier raised in same + * barrier unit bucket. Also if the array is frozen, I/O + * should be blocked until array is unfrozen. + */ + atomic_inc(&conf->nr_pending[idx]); + /* + * In _wait_barrier() we firstly increase conf->nr_pending[idx], then + * check conf->barrier[idx]. In raise_barrier() we firstly increase + * conf->barrier[idx], then check conf->nr_pending[idx]. A memory + * barrier is necessary here to make sure conf->barrier[idx] won't be + * fetched before conf->nr_pending[idx] is increased. Otherwise there + * will be a race between _wait_barrier() and raise_barrier(). + */ + smp_mb__after_atomic(); + + /* + * Don't worry about checking two atomic_t variables at same time + * here. If during we check conf->barrier[idx], the array is + * frozen (conf->array_frozen is 1), and chonf->barrier[idx] is + * 0, it is safe to return and make the I/O continue. Because the + * array is frozen, all I/O returned here will eventually complete + * or be queued, no race will happen. See code comment in + * frozen_array(). + */ + if (!READ_ONCE(conf->array_frozen) && + !atomic_read(&conf->barrier[idx])) + return ret; + + /* + * After holding conf->resync_lock, conf->nr_pending[idx] + * should be decreased before waiting for barrier to drop. + * Otherwise, we may encounter a race condition because + * raise_barrer() might be waiting for conf->nr_pending[idx] + * to be 0 at same time. + */ spin_lock_irq(&conf->resync_lock); - if (conf->barrier) { - conf->nr_waiting++; - /* Wait for the barrier to drop. - * However if there are already pending - * requests (preventing the barrier from - * rising completely), and the - * pre-process bio queue isn't empty, - * then don't wait, as we need to empty - * that queue to get the nr_pending - * count down. - */ + atomic_inc(&conf->nr_waiting[idx]); + atomic_dec(&conf->nr_pending[idx]); + /* + * In case freeze_array() is waiting for + * get_unqueued_pending() == extra + */ + wake_up_barrier(conf); + /* Wait for the barrier in same barrier unit bucket to drop. */ + + /* Return false when nowait flag is set */ + if (nowait) { + ret = false; + } else { wait_event_lock_irq(conf->wait_barrier, - !conf->barrier || - (conf->nr_pending && - current->bio_list && - !bio_list_empty(current->bio_list)), - conf->resync_lock); - conf->nr_waiting--; - } - conf->nr_pending++; + !conf->array_frozen && + !atomic_read(&conf->barrier[idx]), + conf->resync_lock); + atomic_inc(&conf->nr_pending[idx]); + } + + atomic_dec(&conf->nr_waiting[idx]); spin_unlock_irq(&conf->resync_lock); + return ret; } -static void allow_barrier(struct r1conf *conf) +static bool wait_read_barrier(struct r1conf *conf, sector_t sector_nr, bool nowait) { - unsigned long flags; - spin_lock_irqsave(&conf->resync_lock, flags); - conf->nr_pending--; - spin_unlock_irqrestore(&conf->resync_lock, flags); - wake_up(&conf->wait_barrier); + int idx = sector_to_idx(sector_nr); + bool ret = true; + + /* + * Very similar to _wait_barrier(). The difference is, for read + * I/O we don't need wait for sync I/O, but if the whole array + * is frozen, the read I/O still has to wait until the array is + * unfrozen. Since there is no ordering requirement with + * conf->barrier[idx] here, memory barrier is unnecessary as well. + */ + atomic_inc(&conf->nr_pending[idx]); + + if (!READ_ONCE(conf->array_frozen)) + return ret; + + spin_lock_irq(&conf->resync_lock); + atomic_inc(&conf->nr_waiting[idx]); + atomic_dec(&conf->nr_pending[idx]); + /* + * In case freeze_array() is waiting for + * get_unqueued_pending() == extra + */ + wake_up_barrier(conf); + /* Wait for array to be unfrozen */ + + /* Return false when nowait flag is set */ + if (nowait) { + /* Return false when nowait flag is set */ + ret = false; + } else { + wait_event_lock_irq(conf->wait_barrier, + !conf->array_frozen, + conf->resync_lock); + atomic_inc(&conf->nr_pending[idx]); + } + + atomic_dec(&conf->nr_waiting[idx]); + spin_unlock_irq(&conf->resync_lock); + return ret; +} + +static bool wait_barrier(struct r1conf *conf, sector_t sector_nr, bool nowait) +{ + int idx = sector_to_idx(sector_nr); + + return _wait_barrier(conf, idx, nowait); +} + +static void _allow_barrier(struct r1conf *conf, int idx) +{ + atomic_dec(&conf->nr_pending[idx]); + wake_up_barrier(conf); +} + +static void allow_barrier(struct r1conf *conf, sector_t sector_nr) +{ + int idx = sector_to_idx(sector_nr); + + _allow_barrier(conf, idx); +} + +/* conf->resync_lock should be held */ +static int get_unqueued_pending(struct r1conf *conf) +{ + int idx, ret; + + ret = atomic_read(&conf->nr_sync_pending); + for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++) + ret += atomic_read(&conf->nr_pending[idx]) - + atomic_read(&conf->nr_queued[idx]); + + return ret; } static void freeze_array(struct r1conf *conf, int extra) { - /* stop syncio and normal IO and wait for everything to - * go quite. - * We increment barrier and nr_waiting, and then - * wait until nr_pending match nr_queued+extra - * This is called in the context of one normal IO request - * that has failed. Thus any sync request that might be pending - * will be blocked by nr_pending, and we need to wait for - * pending IO requests to complete or be queued for re-try. - * Thus the number queued (nr_queued) plus this request (extra) - * must match the number of pending IOs (nr_pending) before - * we continue. + /* Stop sync I/O and normal I/O and wait for everything to + * go quiet. + * This is called in two situations: + * 1) management command handlers (reshape, remove disk, quiesce). + * 2) one normal I/O request failed. + + * After array_frozen is set to 1, new sync IO will be blocked at + * raise_barrier(), and new normal I/O will blocked at _wait_barrier() + * or wait_read_barrier(). The flying I/Os will either complete or be + * queued. When everything goes quite, there are only queued I/Os left. + + * Every flying I/O contributes to a conf->nr_pending[idx], idx is the + * barrier bucket index which this I/O request hits. When all sync and + * normal I/O are queued, sum of all conf->nr_pending[] will match sum + * of all conf->nr_queued[]. But normal I/O failure is an exception, + * in handle_read_error(), we may call freeze_array() before trying to + * fix the read error. In this case, the error read I/O is not queued, + * so get_unqueued_pending() == 1. + * + * Therefore before this function returns, we need to wait until + * get_unqueued_pendings(conf) gets equal to extra. For + * normal I/O context, extra is 1, in rested situations extra is 0. */ spin_lock_irq(&conf->resync_lock); - conf->barrier++; - conf->nr_waiting++; - wait_event_lock_irq_cmd(conf->wait_barrier, - conf->nr_pending == conf->nr_queued+extra, - conf->resync_lock, - flush_pending_writes(conf)); + conf->array_frozen = 1; + mddev_add_trace_msg(conf->mddev, "raid1 wait freeze"); + wait_event_lock_irq_cmd( + conf->wait_barrier, + get_unqueued_pending(conf) == extra, + conf->resync_lock, + flush_pending_writes(conf)); spin_unlock_irq(&conf->resync_lock); } static void unfreeze_array(struct r1conf *conf) { /* reverse the effect of the freeze */ spin_lock_irq(&conf->resync_lock); - conf->barrier--; - conf->nr_waiting--; - wake_up(&conf->wait_barrier); + conf->array_frozen = 0; spin_unlock_irq(&conf->resync_lock); + wake_up(&conf->wait_barrier); } - -/* duplicate the data pages for behind I/O - */ -static void alloc_behind_pages(struct bio *bio, struct r1bio *r1_bio) +static void alloc_behind_master_bio(struct r1bio *r1_bio, + struct bio *bio) { - int i; - struct bio_vec *bvec; - struct bio_vec *bvecs = kzalloc(bio->bi_vcnt * sizeof(struct bio_vec), - GFP_NOIO); - if (unlikely(!bvecs)) - return; + int size = bio->bi_iter.bi_size; + unsigned vcnt = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + int i = 0; + struct bio *behind_bio = NULL; - bio_for_each_segment_all(bvec, bio, i) { - bvecs[i] = *bvec; - bvecs[i].bv_page = alloc_page(GFP_NOIO); - if (unlikely(!bvecs[i].bv_page)) - goto do_sync_io; - memcpy(kmap(bvecs[i].bv_page) + bvec->bv_offset, - kmap(bvec->bv_page) + bvec->bv_offset, bvec->bv_len); - kunmap(bvecs[i].bv_page); - kunmap(bvec->bv_page); - } - r1_bio->behind_bvecs = bvecs; - r1_bio->behind_page_count = bio->bi_vcnt; + behind_bio = bio_alloc_bioset(NULL, vcnt, bio->bi_opf, GFP_NOIO, + &r1_bio->mddev->bio_set); + + /* discard op, we don't support writezero/writesame yet */ + if (!bio_has_data(bio)) { + behind_bio->bi_iter.bi_size = size; + goto skip_copy; + } + + while (i < vcnt && size) { + struct page *page; + int len = min_t(int, PAGE_SIZE, size); + + page = alloc_page(GFP_NOIO); + if (unlikely(!page)) + goto free_pages; + + if (!bio_add_page(behind_bio, page, len, 0)) { + put_page(page); + goto free_pages; + } + + size -= len; + i++; + } + + bio_copy_data(behind_bio, bio); +skip_copy: + r1_bio->behind_master_bio = behind_bio; set_bit(R1BIO_BehindIO, &r1_bio->state); + return; -do_sync_io: - for (i = 0; i < bio->bi_vcnt; i++) - if (bvecs[i].bv_page) - put_page(bvecs[i].bv_page); - kfree(bvecs); - pr_debug("%dB behind alloc failed, doing sync I/O\n", bio->bi_size); +free_pages: + pr_debug("%dB behind alloc failed, doing sync I/O\n", + bio->bi_iter.bi_size); + bio_free_pages(behind_bio); + bio_put(behind_bio); } -struct raid1_plug_cb { - struct blk_plug_cb cb; - struct bio_list pending; - int pending_cnt; -}; - static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) { struct raid1_plug_cb *plug = container_of(cb, struct raid1_plug_cb, @@ -962,12 +1273,11 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) struct r1conf *conf = mddev->private; struct bio *bio; - if (from_schedule || current->bio_list) { + if (from_schedule) { spin_lock_irq(&conf->device_lock); bio_list_merge(&conf->pending_bio_list, &plug->pending); - conf->pending_count += plug->pending_cnt; spin_unlock_irq(&conf->device_lock); - wake_up(&conf->wait_barrier); + wake_up_barrier(conf); md_wakeup_thread(mddev->thread); kfree(plug); return; @@ -975,181 +1285,245 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) /* we aren't scheduling, so we can do the write-out directly. */ bio = bio_list_get(&plug->pending); - bitmap_unplug(mddev->bitmap); - wake_up(&conf->wait_barrier); - - while (bio) { /* submit pending writes */ - struct bio *next = bio->bi_next; - bio->bi_next = NULL; - if (unlikely((bio->bi_rw & REQ_DISCARD) && - !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) - /* Just ignore it */ - bio_endio(bio, 0); - else - generic_make_request(bio); - bio = next; - } + flush_bio_list(conf, bio); kfree(plug); } -static void make_request(struct mddev *mddev, struct bio * bio) +static void init_r1bio(struct r1bio *r1_bio, struct mddev *mddev, struct bio *bio) +{ + r1_bio->master_bio = bio; + r1_bio->sectors = bio_sectors(bio); + r1_bio->state = 0; + r1_bio->mddev = mddev; + r1_bio->sector = bio->bi_iter.bi_sector; +} + +static inline struct r1bio * +alloc_r1bio(struct mddev *mddev, struct bio *bio) { struct r1conf *conf = mddev->private; - struct raid1_info *mirror; struct r1bio *r1_bio; + + r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO); + memset(r1_bio, 0, offsetof(struct r1bio, bios[conf->raid_disks * 2])); + init_r1bio(r1_bio, mddev, bio); + return r1_bio; +} + +static void raid1_read_request(struct mddev *mddev, struct bio *bio, + int max_read_sectors, struct r1bio *r1_bio) +{ + struct r1conf *conf = mddev->private; + struct raid1_info *mirror; struct bio *read_bio; - int i, disks; - struct bitmap *bitmap; - unsigned long flags; - const int rw = bio_data_dir(bio); - const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); - const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA)); - const unsigned long do_discard = (bio->bi_rw - & (REQ_DISCARD | REQ_SECURE)); - const unsigned long do_same = (bio->bi_rw & REQ_WRITE_SAME); - struct md_rdev *blocked_rdev; - struct blk_plug_cb *cb; - struct raid1_plug_cb *plug = NULL; - int first_clone; - int sectors_handled; int max_sectors; + int rdisk; + bool r1bio_existed = !!r1_bio; /* - * Register the new request and wait if the reconstruction - * thread has put up a bar for new requests. - * Continue immediately if no resync is active currently. + * If r1_bio is set, we are blocking the raid1d thread + * so there is a tiny risk of deadlock. So ask for + * emergency memory if needed. */ + gfp_t gfp = r1_bio ? (GFP_NOIO | __GFP_HIGH) : GFP_NOIO; - md_write_start(mddev, bio); /* wait on superblock update early */ - - if (bio_data_dir(bio) == WRITE && - bio_end_sector(bio) > mddev->suspend_lo && - bio->bi_sector < mddev->suspend_hi) { - /* As the suspend_* range is controlled by - * userspace, we want an interruptible - * wait. - */ - DEFINE_WAIT(w); - for (;;) { - flush_signals(current); - prepare_to_wait(&conf->wait_barrier, - &w, TASK_INTERRUPTIBLE); - if (bio_end_sector(bio) <= mddev->suspend_lo || - bio->bi_sector >= mddev->suspend_hi) - break; - schedule(); - } - finish_wait(&conf->wait_barrier, &w); + /* + * Still need barrier for READ in case that whole + * array is frozen. + */ + if (!wait_read_barrier(conf, bio->bi_iter.bi_sector, + bio->bi_opf & REQ_NOWAIT)) { + bio_wouldblock_error(bio); + return; } - wait_barrier(conf); - - bitmap = mddev->bitmap; + if (!r1_bio) + r1_bio = alloc_r1bio(mddev, bio); + else + init_r1bio(r1_bio, mddev, bio); + r1_bio->sectors = max_read_sectors; /* - * make_request() can abort the operation when READA is being + * make_request() can abort the operation when read-ahead is being * used and no empty request is available. - * */ - r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO); + rdisk = read_balance(conf, r1_bio, &max_sectors); + if (rdisk < 0) { + /* couldn't find anywhere to read from */ + if (r1bio_existed) + pr_crit_ratelimited("md/raid1:%s: %pg: unrecoverable I/O read error for block %llu\n", + mdname(mddev), + conf->mirrors[r1_bio->read_disk].rdev->bdev, + r1_bio->sector); + raid_end_bio_io(r1_bio); + return; + } + mirror = conf->mirrors + rdisk; - r1_bio->master_bio = bio; - r1_bio->sectors = bio_sectors(bio); - r1_bio->state = 0; - r1_bio->mddev = mddev; - r1_bio->sector = bio->bi_sector; - - /* We might need to issue multiple reads to different - * devices if there are bad blocks around, so we keep - * track of the number of reads in bio->bi_phys_segments. - * If this is 0, there is only one r1_bio and no locking - * will be needed when requests complete. If it is - * non-zero, then it is the number of not-completed requests. - */ - bio->bi_phys_segments = 0; - clear_bit(BIO_SEG_VALID, &bio->bi_flags); + if (r1bio_existed) + pr_info_ratelimited("md/raid1:%s: redirecting sector %llu to other mirror: %pg\n", + mdname(mddev), + (unsigned long long)r1_bio->sector, + mirror->rdev->bdev); - if (rw == READ) { + if (test_bit(WriteMostly, &mirror->rdev->flags) && + md_bitmap_enabled(mddev, false)) { /* - * read balancing logic: + * Reading from a write-mostly device must take care not to + * over-take any writes that are 'behind' */ - int rdisk; - -read_again: - rdisk = read_balance(conf, r1_bio, &max_sectors); + mddev_add_trace_msg(mddev, "raid1 wait behind writes"); + mddev->bitmap_ops->wait_behind_writes(mddev); + } - if (rdisk < 0) { - /* couldn't find anywhere to read from */ - raid_end_bio_io(r1_bio); - return; + if (max_sectors < bio_sectors(bio)) { + bio = bio_submit_split_bioset(bio, max_sectors, + &conf->bio_split); + if (!bio) { + set_bit(R1BIO_Returned, &r1_bio->state); + goto err_handle; } - mirror = conf->mirrors + rdisk; - if (test_bit(WriteMostly, &mirror->rdev->flags) && - bitmap) { - /* Reading from a write-mostly device must - * take care not to over-take any writes - * that are 'behind' - */ - wait_event(bitmap->behind_wait, - atomic_read(&bitmap->behind_writes) == 0); - } - r1_bio->read_disk = rdisk; + r1_bio->master_bio = bio; + r1_bio->sectors = max_sectors; + } + + r1_bio->read_disk = rdisk; + if (!r1bio_existed) { + md_account_bio(mddev, &bio); + r1_bio->master_bio = bio; + } + read_bio = bio_alloc_clone(mirror->rdev->bdev, bio, gfp, + &mddev->bio_set); + read_bio->bi_opf &= ~REQ_NOWAIT; + r1_bio->bios[rdisk] = read_bio; + + read_bio->bi_iter.bi_sector = r1_bio->sector + + mirror->rdev->data_offset; + read_bio->bi_end_io = raid1_end_read_request; + if (test_bit(FailFast, &mirror->rdev->flags) && + test_bit(R1BIO_FailFast, &r1_bio->state)) + read_bio->bi_opf |= MD_FAILFAST; + read_bio->bi_private = r1_bio; + mddev_trace_remap(mddev, read_bio, r1_bio->sector); + submit_bio_noacct(read_bio); + return; - read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); - md_trim_bio(read_bio, r1_bio->sector - bio->bi_sector, - max_sectors); +err_handle: + atomic_dec(&mirror->rdev->nr_pending); + raid_end_bio_io(r1_bio); +} - r1_bio->bios[rdisk] = read_bio; +static bool wait_blocked_rdev(struct mddev *mddev, struct bio *bio) +{ + struct r1conf *conf = mddev->private; + int disks = conf->raid_disks * 2; + int i; - read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset; - read_bio->bi_bdev = mirror->rdev->bdev; - read_bio->bi_end_io = raid1_end_read_request; - read_bio->bi_rw = READ | do_sync; - read_bio->bi_private = r1_bio; +retry: + for (i = 0; i < disks; i++) { + struct md_rdev *rdev = conf->mirrors[i].rdev; - if (max_sectors < r1_bio->sectors) { - /* could not read all from this device, so we will - * need another r1_bio. - */ + if (!rdev) + continue; - sectors_handled = (r1_bio->sector + max_sectors - - bio->bi_sector); - r1_bio->sectors = max_sectors; - spin_lock_irq(&conf->device_lock); - if (bio->bi_phys_segments == 0) - bio->bi_phys_segments = 2; - else - bio->bi_phys_segments++; - spin_unlock_irq(&conf->device_lock); - /* Cannot call generic_make_request directly - * as that will be queued in __make_request - * and subsequent mempool_alloc might block waiting - * for it. So hand bio over to raid1d. - */ - reschedule_retry(r1_bio); + /* don't write here until the bad block is acknowledged */ + if (test_bit(WriteErrorSeen, &rdev->flags) && + rdev_has_badblock(rdev, bio->bi_iter.bi_sector, + bio_sectors(bio)) < 0) + set_bit(BlockedBadBlocks, &rdev->flags); - r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO); + if (rdev_blocked(rdev)) { + if (bio->bi_opf & REQ_NOWAIT) + return false; - r1_bio->master_bio = bio; - r1_bio->sectors = bio_sectors(bio) - sectors_handled; - r1_bio->state = 0; - r1_bio->mddev = mddev; - r1_bio->sector = bio->bi_sector + sectors_handled; - goto read_again; - } else - generic_make_request(read_bio); + mddev_add_trace_msg(rdev->mddev, "raid1 wait rdev %d blocked", + rdev->raid_disk); + atomic_inc(&rdev->nr_pending); + md_wait_for_blocked_rdev(rdev, rdev->mddev); + goto retry; + } + } + + return true; +} + +static void raid1_start_write_behind(struct mddev *mddev, struct r1bio *r1_bio, + struct bio *bio) +{ + unsigned long max_write_behind = mddev->bitmap_info.max_write_behind; + struct md_bitmap_stats stats; + int err; + + /* behind write rely on bitmap, see bitmap_operations */ + if (!md_bitmap_enabled(mddev, false)) + return; + + err = mddev->bitmap_ops->get_stats(mddev->bitmap, &stats); + if (err) return; + + /* Don't do behind IO if reader is waiting, or there are too many. */ + if (!stats.behind_wait && stats.behind_writes < max_write_behind) + alloc_behind_master_bio(r1_bio, bio); + + if (test_bit(R1BIO_BehindIO, &r1_bio->state)) + mddev->bitmap_ops->start_behind_write(mddev); + +} + +static void raid1_write_request(struct mddev *mddev, struct bio *bio, + int max_write_sectors) +{ + struct r1conf *conf = mddev->private; + struct r1bio *r1_bio; + int i, disks, k; + unsigned long flags; + int first_clone; + int max_sectors; + bool write_behind = false; + bool is_discard = (bio_op(bio) == REQ_OP_DISCARD); + + if (mddev_is_clustered(mddev) && + mddev->cluster_ops->area_resyncing(mddev, WRITE, + bio->bi_iter.bi_sector, bio_end_sector(bio))) { + + DEFINE_WAIT(w); + if (bio->bi_opf & REQ_NOWAIT) { + bio_wouldblock_error(bio); + return; + } + for (;;) { + prepare_to_wait(&conf->wait_barrier, + &w, TASK_IDLE); + if (!mddev->cluster_ops->area_resyncing(mddev, WRITE, + bio->bi_iter.bi_sector, + bio_end_sector(bio))) + break; + schedule(); + } + finish_wait(&conf->wait_barrier, &w); } /* - * WRITE: + * Register the new request and wait if the reconstruction + * thread has put up a bar for new requests. + * Continue immediately if no resync is active currently. */ - if (conf->pending_count >= max_queued_requests) { - md_wakeup_thread(mddev->thread); - wait_event(conf->wait_barrier, - conf->pending_count < max_queued_requests); + if (!wait_barrier(conf, bio->bi_iter.bi_sector, + bio->bi_opf & REQ_NOWAIT)) { + bio_wouldblock_error(bio); + return; + } + + if (!wait_blocked_rdev(mddev, bio)) { + bio_wouldblock_error(bio); + return; } + + r1_bio = alloc_r1bio(mddev, bio); + r1_bio->sectors = max_write_sectors; + /* first select target devices under rcu_lock and * inc refcount on their rdev. Record them by setting * bios[x] to bio @@ -1162,41 +1536,30 @@ read_again: */ disks = conf->raid_disks * 2; - retry_write: - blocked_rdev = NULL; - rcu_read_lock(); max_sectors = r1_bio->sectors; for (i = 0; i < disks; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); - if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { - atomic_inc(&rdev->nr_pending); - blocked_rdev = rdev; - break; - } + struct md_rdev *rdev = conf->mirrors[i].rdev; + + /* + * The write-behind io is only attempted on drives marked as + * write-mostly, which means we could allocate write behind + * bio later. + */ + if (!is_discard && rdev && test_bit(WriteMostly, &rdev->flags)) + write_behind = true; + r1_bio->bios[i] = NULL; - if (!rdev || test_bit(Faulty, &rdev->flags) - || test_bit(Unmerged, &rdev->flags)) { - if (i < conf->raid_disks) - set_bit(R1BIO_Degraded, &r1_bio->state); + if (!rdev || test_bit(Faulty, &rdev->flags)) continue; - } atomic_inc(&rdev->nr_pending); if (test_bit(WriteErrorSeen, &rdev->flags)) { sector_t first_bad; - int bad_sectors; + sector_t bad_sectors; int is_bad; - is_bad = is_badblock(rdev, r1_bio->sector, - max_sectors, + is_bad = is_badblock(rdev, r1_bio->sector, max_sectors, &first_bad, &bad_sectors); - if (is_bad < 0) { - /* mustn't write here until the bad block is - * acknowledged*/ - set_bit(BlockedBadBlocks, &rdev->flags); - blocked_rdev = rdev; - break; - } if (is_bad && first_bad <= r1_bio->sector) { /* Cannot write here at all */ bad_sectors -= (r1_bio->sector - first_bad); @@ -1206,243 +1569,252 @@ read_again: */ max_sectors = bad_sectors; rdev_dec_pending(rdev, mddev); - /* We don't set R1BIO_Degraded as that - * only applies if the disk is - * missing, so it might be re-added, - * and we want to know to recover this - * chunk. - * In this case the device is here, - * and the fact that this chunk is not - * in-sync is recorded in the bad - * block log - */ continue; } if (is_bad) { - int good_sectors = first_bad - r1_bio->sector; + int good_sectors; + + /* + * We cannot atomically write this, so just + * error in that case. It could be possible to + * atomically write other mirrors, but the + * complexity of supporting that is not worth + * the benefit. + */ + if (bio->bi_opf & REQ_ATOMIC) + goto err_handle; + + good_sectors = first_bad - r1_bio->sector; if (good_sectors < max_sectors) max_sectors = good_sectors; } } r1_bio->bios[i] = bio; } - rcu_read_unlock(); - - if (unlikely(blocked_rdev)) { - /* Wait for this device to become unblocked */ - int j; - for (j = 0; j < i; j++) - if (r1_bio->bios[j]) - rdev_dec_pending(conf->mirrors[j].rdev, mddev); - r1_bio->state = 0; - allow_barrier(conf); - md_wait_for_blocked_rdev(blocked_rdev, mddev); - wait_barrier(conf); - goto retry_write; - } + /* + * When using a bitmap, we may call alloc_behind_master_bio below. + * alloc_behind_master_bio allocates a copy of the data payload a page + * at a time and thus needs a new bio that can fit the whole payload + * this bio in page sized chunks. + */ + if (write_behind && mddev->bitmap) + max_sectors = min_t(int, max_sectors, + BIO_MAX_VECS * (PAGE_SIZE >> 9)); + if (max_sectors < bio_sectors(bio)) { + bio = bio_submit_split_bioset(bio, max_sectors, + &conf->bio_split); + if (!bio) { + set_bit(R1BIO_Returned, &r1_bio->state); + goto err_handle; + } - if (max_sectors < r1_bio->sectors) { - /* We are splitting this write into multiple parts, so - * we need to prepare for allocating another r1_bio. - */ + r1_bio->master_bio = bio; r1_bio->sectors = max_sectors; - spin_lock_irq(&conf->device_lock); - if (bio->bi_phys_segments == 0) - bio->bi_phys_segments = 2; - else - bio->bi_phys_segments++; - spin_unlock_irq(&conf->device_lock); } - sectors_handled = r1_bio->sector + max_sectors - bio->bi_sector; + md_account_bio(mddev, &bio); + r1_bio->master_bio = bio; atomic_set(&r1_bio->remaining, 1); atomic_set(&r1_bio->behind_remaining, 0); first_clone = 1; + for (i = 0; i < disks; i++) { - struct bio *mbio; + struct bio *mbio = NULL; + struct md_rdev *rdev = conf->mirrors[i].rdev; if (!r1_bio->bios[i]) continue; - mbio = bio_clone_mddev(bio, GFP_NOIO, mddev); - md_trim_bio(mbio, r1_bio->sector - bio->bi_sector, max_sectors); - if (first_clone) { - /* do behind I/O ? - * Not if there are too many, or cannot - * allocate memory, or a reader on WriteMostly - * is waiting for behind writes to flush */ - if (bitmap && - (atomic_read(&bitmap->behind_writes) - < mddev->bitmap_info.max_write_behind) && - !waitqueue_active(&bitmap->behind_wait)) - alloc_behind_pages(mbio, r1_bio); - - bitmap_startwrite(bitmap, r1_bio->sector, - r1_bio->sectors, - test_bit(R1BIO_BehindIO, - &r1_bio->state)); + if (write_behind) + raid1_start_write_behind(mddev, r1_bio, bio); first_clone = 0; } - if (r1_bio->behind_bvecs) { - struct bio_vec *bvec; - int j; - /* - * We trimmed the bio, so _all is legit - */ - bio_for_each_segment_all(bvec, mbio, j) - bvec->bv_page = r1_bio->behind_bvecs[j].bv_page; - if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags)) + if (r1_bio->behind_master_bio) { + mbio = bio_alloc_clone(rdev->bdev, + r1_bio->behind_master_bio, + GFP_NOIO, &mddev->bio_set); + if (test_bit(CollisionCheck, &rdev->flags)) + wait_for_serialization(rdev, r1_bio); + if (test_bit(WriteMostly, &rdev->flags)) atomic_inc(&r1_bio->behind_remaining); + } else { + mbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, + &mddev->bio_set); + + if (mddev->serialize_policy) + wait_for_serialization(rdev, r1_bio); } + mbio->bi_opf &= ~REQ_NOWAIT; r1_bio->bios[i] = mbio; - mbio->bi_sector = (r1_bio->sector + - conf->mirrors[i].rdev->data_offset); - mbio->bi_bdev = conf->mirrors[i].rdev->bdev; + mbio->bi_iter.bi_sector = (r1_bio->sector + rdev->data_offset); mbio->bi_end_io = raid1_end_write_request; - mbio->bi_rw = - WRITE | do_flush_fua | do_sync | do_discard | do_same; + if (test_bit(FailFast, &rdev->flags) && + !test_bit(WriteMostly, &rdev->flags) && + conf->raid_disks - mddev->degraded > 1) + mbio->bi_opf |= MD_FAILFAST; mbio->bi_private = r1_bio; atomic_inc(&r1_bio->remaining); - - cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug)); - if (cb) - plug = container_of(cb, struct raid1_plug_cb, cb); - else - plug = NULL; - spin_lock_irqsave(&conf->device_lock, flags); - if (plug) { - bio_list_add(&plug->pending, mbio); - plug->pending_cnt++; - } else { + mddev_trace_remap(mddev, mbio, r1_bio->sector); + /* flush_pending_writes() needs access to the rdev so...*/ + mbio->bi_bdev = (void *)rdev; + if (!raid1_add_bio_to_plug(mddev, mbio, raid1_unplug, disks)) { + spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); - conf->pending_count++; - } - spin_unlock_irqrestore(&conf->device_lock, flags); - if (!plug) + spin_unlock_irqrestore(&conf->device_lock, flags); md_wakeup_thread(mddev->thread); - } - /* Mustn't call r1_bio_write_done before this next test, - * as it could result in the bio being freed. - */ - if (sectors_handled < bio_sectors(bio)) { - r1_bio_write_done(r1_bio); - /* We need another r1_bio. It has already been counted - * in bio->bi_phys_segments - */ - r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO); - r1_bio->master_bio = bio; - r1_bio->sectors = bio_sectors(bio) - sectors_handled; - r1_bio->state = 0; - r1_bio->mddev = mddev; - r1_bio->sector = bio->bi_sector + sectors_handled; - goto retry_write; + } } r1_bio_write_done(r1_bio); /* In case raid1d snuck in to freeze_array */ - wake_up(&conf->wait_barrier); + wake_up_barrier(conf); + return; +err_handle: + for (k = 0; k < i; k++) { + if (r1_bio->bios[k]) { + rdev_dec_pending(conf->mirrors[k].rdev, mddev); + r1_bio->bios[k] = NULL; + } + } + + raid_end_bio_io(r1_bio); } -static void status(struct seq_file *seq, struct mddev *mddev) +static bool raid1_make_request(struct mddev *mddev, struct bio *bio) +{ + sector_t sectors; + + if (unlikely(bio->bi_opf & REQ_PREFLUSH) + && md_flush_request(mddev, bio)) + return true; + + /* + * There is a limit to the maximum size, but + * the read/write handler might find a lower limit + * due to bad blocks. To avoid multiple splits, + * we pass the maximum number of sectors down + * and let the lower level perform the split. + */ + sectors = align_to_barrier_unit_end( + bio->bi_iter.bi_sector, bio_sectors(bio)); + + if (bio_data_dir(bio) == READ) + raid1_read_request(mddev, bio, sectors, NULL); + else { + md_write_start(mddev,bio); + raid1_write_request(mddev, bio, sectors); + } + return true; +} + +static void raid1_status(struct seq_file *seq, struct mddev *mddev) { struct r1conf *conf = mddev->private; int i; + lockdep_assert_held(&mddev->lock); + seq_printf(seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded); - rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); + struct md_rdev *rdev = READ_ONCE(conf->mirrors[i].rdev); + seq_printf(seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_"); } - rcu_read_unlock(); seq_printf(seq, "]"); } - -static void error(struct mddev *mddev, struct md_rdev *rdev) +/** + * raid1_error() - RAID1 error handler. + * @mddev: affected md device. + * @rdev: member device to fail. + * + * The routine acknowledges &rdev failure and determines new @mddev state. + * If it failed, then: + * - &MD_BROKEN flag is set in &mddev->flags. + * - recovery is disabled. + * Otherwise, it must be degraded: + * - recovery is interrupted. + * - &mddev->degraded is bumped. + * + * @rdev is marked as &Faulty excluding case when array is failed and + * &mddev->fail_last_dev is off. + */ +static void raid1_error(struct mddev *mddev, struct md_rdev *rdev) { - char b[BDEVNAME_SIZE]; struct r1conf *conf = mddev->private; + unsigned long flags; - /* - * If it is not operational, then we have already marked it as dead - * else if it is the last working disks, ignore the error, let the - * next level up know. - * else mark the drive as failed - */ - if (test_bit(In_sync, &rdev->flags) - && (conf->raid_disks - mddev->degraded) == 1) { - /* - * Don't fail the drive, act as though we were just a - * normal single drive. - * However don't try a recovery from this drive as - * it is very likely to fail. - */ - conf->recovery_disabled = mddev->recovery_disabled; - return; + spin_lock_irqsave(&conf->device_lock, flags); + + if (test_bit(In_sync, &rdev->flags) && + (conf->raid_disks - mddev->degraded) == 1) { + set_bit(MD_BROKEN, &mddev->flags); + + if (!mddev->fail_last_dev) { + conf->recovery_disabled = mddev->recovery_disabled; + spin_unlock_irqrestore(&conf->device_lock, flags); + return; + } } set_bit(Blocked, &rdev->flags); - if (test_and_clear_bit(In_sync, &rdev->flags)) { - unsigned long flags; - spin_lock_irqsave(&conf->device_lock, flags); + if (test_and_clear_bit(In_sync, &rdev->flags)) mddev->degraded++; - set_bit(Faulty, &rdev->flags); - spin_unlock_irqrestore(&conf->device_lock, flags); - /* - * if recovery is running, make sure it aborts. - */ - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - } else - set_bit(Faulty, &rdev->flags); - set_bit(MD_CHANGE_DEVS, &mddev->flags); - printk(KERN_ALERT - "md/raid1:%s: Disk failure on %s, disabling device.\n" - "md/raid1:%s: Operation continuing on %d devices.\n", - mdname(mddev), bdevname(rdev->bdev, b), - mdname(mddev), conf->raid_disks - mddev->degraded); + set_bit(Faulty, &rdev->flags); + spin_unlock_irqrestore(&conf->device_lock, flags); + /* + * if recovery is running, make sure it aborts. + */ + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + set_mask_bits(&mddev->sb_flags, 0, + BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING)); + pr_crit("md/raid1:%s: Disk failure on %pg, disabling device.\n" + "md/raid1:%s: Operation continuing on %d devices.\n", + mdname(mddev), rdev->bdev, + mdname(mddev), conf->raid_disks - mddev->degraded); } static void print_conf(struct r1conf *conf) { int i; - printk(KERN_DEBUG "RAID1 conf printout:\n"); + pr_debug("RAID1 conf printout:\n"); if (!conf) { - printk(KERN_DEBUG "(!conf)\n"); + pr_debug("(!conf)\n"); return; } - printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded, - conf->raid_disks); + pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded, + conf->raid_disks); - rcu_read_lock(); + lockdep_assert_held(&conf->mddev->reconfig_mutex); for (i = 0; i < conf->raid_disks; i++) { - char b[BDEVNAME_SIZE]; - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); + struct md_rdev *rdev = conf->mirrors[i].rdev; if (rdev) - printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n", - i, !test_bit(In_sync, &rdev->flags), - !test_bit(Faulty, &rdev->flags), - bdevname(rdev->bdev,b)); + pr_debug(" disk %d, wo:%d, o:%d, dev:%pg\n", + i, !test_bit(In_sync, &rdev->flags), + !test_bit(Faulty, &rdev->flags), + rdev->bdev); } - rcu_read_unlock(); } static void close_sync(struct r1conf *conf) { - wait_barrier(conf); - allow_barrier(conf); + int idx; + + for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++) { + _wait_barrier(conf, idx, false); + _allow_barrier(conf, idx); + } - mempool_destroy(conf->r1buf_pool); - conf->r1buf_pool = NULL; + mempool_exit(&conf->r1buf_pool); } static int raid1_spare_active(struct mddev *mddev) @@ -1453,14 +1825,18 @@ static int raid1_spare_active(struct mddev *mddev) unsigned long flags; /* - * Find all failed disks within the RAID1 configuration + * Find all failed disks within the RAID1 configuration * and mark them readable. * Called under mddev lock, so rcu protection not needed. + * device_lock used to avoid races with raid1_end_read_request + * which expects 'In_sync' flags and ->degraded to be consistent. */ + spin_lock_irqsave(&conf->device_lock, flags); for (i = 0; i < conf->raid_disks; i++) { struct md_rdev *rdev = conf->mirrors[i].rdev; struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev; if (repl + && !test_bit(Candidate, &repl->flags) && repl->recovery_offset == MaxSector && !test_bit(Faulty, &repl->flags) && !test_and_set_bit(In_sync, &repl->flags)) { @@ -1479,13 +1855,13 @@ static int raid1_spare_active(struct mddev *mddev) } } if (rdev + && rdev->recovery_offset == MaxSector && !test_bit(Faulty, &rdev->flags) && !test_and_set_bit(In_sync, &rdev->flags)) { count++; sysfs_notify_dirent_safe(rdev->sysfs_state); } } - spin_lock_irqsave(&conf->device_lock, flags); mddev->degraded -= count; spin_unlock_irqrestore(&conf->device_lock, flags); @@ -1493,16 +1869,60 @@ static int raid1_spare_active(struct mddev *mddev) return count; } +static bool raid1_add_conf(struct r1conf *conf, struct md_rdev *rdev, int disk, + bool replacement) +{ + struct raid1_info *info = conf->mirrors + disk; + + if (replacement) + info += conf->raid_disks; + + if (info->rdev) + return false; + + if (bdev_nonrot(rdev->bdev)) { + set_bit(Nonrot, &rdev->flags); + WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks + 1); + } + + rdev->raid_disk = disk; + info->head_position = 0; + info->seq_start = MaxSector; + WRITE_ONCE(info->rdev, rdev); + + return true; +} + +static bool raid1_remove_conf(struct r1conf *conf, int disk) +{ + struct raid1_info *info = conf->mirrors + disk; + struct md_rdev *rdev = info->rdev; + + if (!rdev || test_bit(In_sync, &rdev->flags) || + atomic_read(&rdev->nr_pending)) + return false; + + /* Only remove non-faulty devices if recovery is not possible. */ + if (!test_bit(Faulty, &rdev->flags) && + rdev->mddev->recovery_disabled != conf->recovery_disabled && + rdev->mddev->degraded < conf->raid_disks) + return false; + + if (test_and_clear_bit(Nonrot, &rdev->flags)) + WRITE_ONCE(conf->nonrot_disks, conf->nonrot_disks - 1); + + WRITE_ONCE(info->rdev, NULL); + return true; +} static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) { struct r1conf *conf = mddev->private; int err = -EEXIST; - int mirror = 0; + int mirror = 0, repl_slot = -1; struct raid1_info *p; int first = 0; int last = conf->raid_disks - 1; - struct request_queue *q = bdev_get_queue(rdev->bdev); if (mddev->recovery_disabled == conf->recovery_disabled) return -EBUSY; @@ -1510,58 +1930,45 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) if (rdev->raid_disk >= 0) first = last = rdev->raid_disk; - if (q->merge_bvec_fn) { - set_bit(Unmerged, &rdev->flags); - mddev->merge_check_needed = 1; - } + /* + * find the disk ... but prefer rdev->saved_raid_disk + * if possible. + */ + if (rdev->saved_raid_disk >= 0 && + rdev->saved_raid_disk >= first && + rdev->saved_raid_disk < conf->raid_disks && + conf->mirrors[rdev->saved_raid_disk].rdev == NULL) + first = last = rdev->saved_raid_disk; for (mirror = first; mirror <= last; mirror++) { - p = conf->mirrors+mirror; + p = conf->mirrors + mirror; if (!p->rdev) { + err = mddev_stack_new_rdev(mddev, rdev); + if (err) + return err; - if (mddev->gendisk) - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - - p->head_position = 0; - rdev->raid_disk = mirror; - err = 0; + raid1_add_conf(conf, rdev, mirror, false); /* As all devices are equivalent, we don't need a full recovery * if this was recently any drive of the array */ if (rdev->saved_raid_disk < 0) conf->fullsync = 1; - rcu_assign_pointer(p->rdev, rdev); break; } if (test_bit(WantReplacement, &p->rdev->flags) && - p[conf->raid_disks].rdev == NULL) { - /* Add this device as a replacement */ - clear_bit(In_sync, &rdev->flags); - set_bit(Replacement, &rdev->flags); - rdev->raid_disk = mirror; - err = 0; - conf->fullsync = 1; - rcu_assign_pointer(p[conf->raid_disks].rdev, rdev); - break; - } + p[conf->raid_disks].rdev == NULL && repl_slot < 0) + repl_slot = mirror; } - if (err == 0 && test_bit(Unmerged, &rdev->flags)) { - /* Some requests might not have seen this new - * merge_bvec_fn. We must wait for them to complete - * before merging the device fully. - * First we make sure any code which has tested - * our function has submitted the request, then - * we wait for all outstanding requests to complete. - */ - synchronize_sched(); - freeze_array(conf, 0); - unfreeze_array(conf); - clear_bit(Unmerged, &rdev->flags); + + if (err && repl_slot >= 0) { + /* Add this device as a replacement */ + clear_bit(In_sync, &rdev->flags); + set_bit(Replacement, &rdev->flags); + raid1_add_conf(conf, rdev, repl_slot, true); + err = 0; + conf->fullsync = 1; } - md_integrity_add_rdev(rdev, mddev); - if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev))) - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue); + print_conf(conf); return err; } @@ -1573,33 +1980,23 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) int number = rdev->raid_disk; struct raid1_info *p = conf->mirrors + number; - if (rdev != p->rdev) - p = conf->mirrors + conf->raid_disks + number; + if (unlikely(number >= conf->raid_disks)) + goto abort; + + if (rdev != p->rdev) { + number += conf->raid_disks; + p = conf->mirrors + number; + } print_conf(conf); if (rdev == p->rdev) { - if (test_bit(In_sync, &rdev->flags) || - atomic_read(&rdev->nr_pending)) { + if (!raid1_remove_conf(conf, number)) { err = -EBUSY; goto abort; } - /* Only remove non-faulty devices if recovery - * is not possible. - */ - if (!test_bit(Faulty, &rdev->flags) && - mddev->recovery_disabled != conf->recovery_disabled && - mddev->degraded < conf->raid_disks) { - err = -EBUSY; - goto abort; - } - p->rdev = NULL; - synchronize_rcu(); - if (atomic_read(&rdev->nr_pending)) { - /* lost the race, try later */ - err = -EBUSY; - p->rdev = rdev; - goto abort; - } else if (conf->mirrors[conf->raid_disks + number].rdev) { + + if (number < conf->raid_disks && + conf->mirrors[conf->raid_disks + number].rdev) { /* We just removed a device that is being replaced. * Move down the replacement. We drain all IO before * doing this to avoid confusion. @@ -1607,13 +2004,24 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) struct md_rdev *repl = conf->mirrors[conf->raid_disks + number].rdev; freeze_array(conf, 0); + if (atomic_read(&repl->nr_pending)) { + /* It means that some queued IO of retry_list + * hold repl. Thus, we cannot set replacement + * as NULL, avoiding rdev NULL pointer + * dereference in sync_request_write and + * handle_write_finished. + */ + err = -EBUSY; + unfreeze_array(conf); + goto abort; + } clear_bit(Replacement, &repl->flags); - p->rdev = repl; + WRITE_ONCE(p->rdev, repl); conf->mirrors[conf->raid_disks + number].rdev = NULL; unfreeze_array(conf); - clear_bit(WantReplacement, &rdev->flags); - } else - clear_bit(WantReplacement, &rdev->flags); + } + + clear_bit(WantReplacement, &rdev->flags); err = md_integrity_register(mddev); } abort: @@ -1622,10 +2030,9 @@ abort: return err; } - -static void end_sync_read(struct bio *bio, int error) +static void end_sync_read(struct bio *bio) { - struct r1bio *r1_bio = bio->bi_private; + struct r1bio *r1_bio = get_resync_r1bio(bio); update_head_pos(r1_bio->read_disk, r1_bio); @@ -1634,56 +2041,33 @@ static void end_sync_read(struct bio *bio, int error) * or re-read if the read failed. * We don't do much here, just schedule handling by raid1d */ - if (test_bit(BIO_UPTODATE, &bio->bi_flags)) + if (!bio->bi_status) set_bit(R1BIO_Uptodate, &r1_bio->state); if (atomic_dec_and_test(&r1_bio->remaining)) reschedule_retry(r1_bio); } -static void end_sync_write(struct bio *bio, int error) +static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio) { - int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - struct r1bio *r1_bio = bio->bi_private; - struct mddev *mddev = r1_bio->mddev; - struct r1conf *conf = mddev->private; - int mirror=0; - sector_t first_bad; - int bad_sectors; - - mirror = find_bio_disk(r1_bio, bio); + sector_t sync_blocks = 0; + sector_t s = r1_bio->sector; + long sectors_to_go = r1_bio->sectors; - if (!uptodate) { - sector_t sync_blocks = 0; - sector_t s = r1_bio->sector; - long sectors_to_go = r1_bio->sectors; - /* make sure these bits doesn't get cleared. */ - do { - bitmap_end_sync(mddev->bitmap, s, - &sync_blocks, 1); - s += sync_blocks; - sectors_to_go -= sync_blocks; - } while (sectors_to_go > 0); - set_bit(WriteErrorSeen, - &conf->mirrors[mirror].rdev->flags); - if (!test_and_set_bit(WantReplacement, - &conf->mirrors[mirror].rdev->flags)) - set_bit(MD_RECOVERY_NEEDED, & - mddev->recovery); - set_bit(R1BIO_WriteError, &r1_bio->state); - } else if (is_badblock(conf->mirrors[mirror].rdev, - r1_bio->sector, - r1_bio->sectors, - &first_bad, &bad_sectors) && - !is_badblock(conf->mirrors[r1_bio->read_disk].rdev, - r1_bio->sector, - r1_bio->sectors, - &first_bad, &bad_sectors) - ) - set_bit(R1BIO_MadeGood, &r1_bio->state); + /* make sure these bits don't get cleared. */ + do { + md_bitmap_end_sync(mddev, s, &sync_blocks); + s += sync_blocks; + sectors_to_go -= sync_blocks; + } while (sectors_to_go > 0); +} +static void put_sync_write_buf(struct r1bio *r1_bio, int uptodate) +{ if (atomic_dec_and_test(&r1_bio->remaining)) { + struct mddev *mddev = r1_bio->mddev; int s = r1_bio->sectors; + if (test_bit(R1BIO_MadeGood, &r1_bio->state) || test_bit(R1BIO_WriteError, &r1_bio->state)) reschedule_retry(r1_bio); @@ -1694,13 +2078,37 @@ static void end_sync_write(struct bio *bio, int error) } } +static void end_sync_write(struct bio *bio) +{ + int uptodate = !bio->bi_status; + struct r1bio *r1_bio = get_resync_r1bio(bio); + struct mddev *mddev = r1_bio->mddev; + struct r1conf *conf = mddev->private; + struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev; + + if (!uptodate) { + abort_sync_write(mddev, r1_bio); + set_bit(WriteErrorSeen, &rdev->flags); + if (!test_and_set_bit(WantReplacement, &rdev->flags)) + set_bit(MD_RECOVERY_NEEDED, & + mddev->recovery); + set_bit(R1BIO_WriteError, &r1_bio->state); + } else if (rdev_has_badblock(rdev, r1_bio->sector, r1_bio->sectors) && + !rdev_has_badblock(conf->mirrors[r1_bio->read_disk].rdev, + r1_bio->sector, r1_bio->sectors)) { + set_bit(R1BIO_MadeGood, &r1_bio->state); + } + + put_sync_write_buf(r1_bio, uptodate); +} + static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector, - int sectors, struct page *page, int rw) + int sectors, struct page *page, blk_opf_t rw) { if (sync_page_io(rdev, sector, sectors << 9, page, rw, false)) /* success */ return 1; - if (rw == WRITE) { + if (rw == REQ_OP_WRITE) { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) @@ -1729,15 +2137,28 @@ static int fix_sync_read_error(struct r1bio *r1_bio) struct mddev *mddev = r1_bio->mddev; struct r1conf *conf = mddev->private; struct bio *bio = r1_bio->bios[r1_bio->read_disk]; + struct page **pages = get_resync_pages(bio)->pages; sector_t sect = r1_bio->sector; int sectors = r1_bio->sectors; int idx = 0; + struct md_rdev *rdev; + + rdev = conf->mirrors[r1_bio->read_disk].rdev; + if (test_bit(FailFast, &rdev->flags)) { + /* Don't try recovering from here - just fail it + * ... unless it is the last working device of course */ + md_error(mddev, rdev); + if (test_bit(Faulty, &rdev->flags)) + /* Don't try to read from here, but make sure + * put_buf does it's thing + */ + bio->bi_end_io = end_sync_write; + } while(sectors) { int s = sectors; int d = r1_bio->read_disk; int success = 0; - struct md_rdev *rdev; int start; if (s > (PAGE_SIZE>>9)) @@ -1750,8 +2171,8 @@ static int fix_sync_read_error(struct r1bio *r1_bio) */ rdev = conf->mirrors[d].rdev; if (sync_page_io(rdev, sect, s<<9, - bio->bi_io_vec[idx].bv_page, - READ, false)) { + pages[idx], + REQ_OP_READ, false)) { success = 1; break; } @@ -1762,18 +2183,15 @@ static int fix_sync_read_error(struct r1bio *r1_bio) } while (!success && d != r1_bio->read_disk); if (!success) { - char b[BDEVNAME_SIZE]; int abort = 0; /* Cannot read from anywhere, this block is lost. * Record a bad block on each device. If that doesn't * work just disable and interrupt the recovery. * Don't fail devices as that won't really help. */ - printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O read error" - " for block %llu\n", - mdname(mddev), - bdevname(bio->bi_bdev, b), - (unsigned long long)r1_bio->sector); + pr_crit_ratelimited("md/raid1:%s: %pg: unrecoverable I/O read error for block %llu\n", + mdname(mddev), bio->bi_bdev, + (unsigned long long)r1_bio->sector); for (d = 0; d < conf->raid_disks * 2; d++) { rdev = conf->mirrors[d].rdev; if (!rdev || test_bit(Faulty, &rdev->flags)) @@ -1781,14 +2199,9 @@ static int fix_sync_read_error(struct r1bio *r1_bio) if (!rdev_set_badblocks(rdev, sect, s, 0)) abort = 1; } - if (abort) { - conf->recovery_disabled = - mddev->recovery_disabled; - set_bit(MD_RECOVERY_INTR, &mddev->recovery); - md_done_sync(mddev, r1_bio->sectors, 0); - put_buf(r1_bio); + if (abort) return 0; - } + /* Try next page */ sectors -= s; sect += s; @@ -1806,8 +2219,8 @@ static int fix_sync_read_error(struct r1bio *r1_bio) continue; rdev = conf->mirrors[d].rdev; if (r1_sync_page_io(rdev, sect, s, - bio->bi_io_vec[idx].bv_page, - WRITE) == 0) { + pages[idx], + REQ_OP_WRITE) == 0) { r1_bio->bios[d]->bi_end_io = NULL; rdev_dec_pending(rdev, mddev); } @@ -1821,8 +2234,8 @@ static int fix_sync_read_error(struct r1bio *r1_bio) continue; rdev = conf->mirrors[d].rdev; if (r1_sync_page_io(rdev, sect, s, - bio->bi_io_vec[idx].bv_page, - READ) != 0) + pages[idx], + REQ_OP_READ) != 0) atomic_add(s, &rdev->corrected_errors); } sectors -= s; @@ -1830,11 +2243,11 @@ static int fix_sync_read_error(struct r1bio *r1_bio) idx ++; } set_bit(R1BIO_Uptodate, &r1_bio->state); - set_bit(BIO_UPTODATE, &bio->bi_flags); + bio->bi_status = 0; return 1; } -static int process_checks(struct r1bio *r1_bio) +static void process_checks(struct r1bio *r1_bio) { /* We have read all readable devices. If we haven't * got the block, then there is no hope left. @@ -1849,32 +2262,59 @@ static int process_checks(struct r1bio *r1_bio) int i; int vcnt; + /* Fix variable parts of all bios */ + vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9); + for (i = 0; i < conf->raid_disks * 2; i++) { + blk_status_t status; + struct bio *b = r1_bio->bios[i]; + struct resync_pages *rp = get_resync_pages(b); + if (b->bi_end_io != end_sync_read) + continue; + /* fixup the bio for reuse, but preserve errno */ + status = b->bi_status; + bio_reset(b, conf->mirrors[i].rdev->bdev, REQ_OP_READ); + b->bi_status = status; + b->bi_iter.bi_sector = r1_bio->sector + + conf->mirrors[i].rdev->data_offset; + b->bi_end_io = end_sync_read; + rp->raid_bio = r1_bio; + b->bi_private = rp; + + /* initialize bvec table again */ + md_bio_reset_resync_pages(b, rp, r1_bio->sectors << 9); + } for (primary = 0; primary < conf->raid_disks * 2; primary++) if (r1_bio->bios[primary]->bi_end_io == end_sync_read && - test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) { + !r1_bio->bios[primary]->bi_status) { r1_bio->bios[primary]->bi_end_io = NULL; rdev_dec_pending(conf->mirrors[primary].rdev, mddev); break; } r1_bio->read_disk = primary; - vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9); for (i = 0; i < conf->raid_disks * 2; i++) { - int j; + int j = 0; struct bio *pbio = r1_bio->bios[primary]; struct bio *sbio = r1_bio->bios[i]; - int size; + blk_status_t status = sbio->bi_status; + struct page **ppages = get_resync_pages(pbio)->pages; + struct page **spages = get_resync_pages(sbio)->pages; + struct bio_vec *bi; + int page_len[RESYNC_PAGES] = { 0 }; + struct bvec_iter_all iter_all; if (sbio->bi_end_io != end_sync_read) continue; + /* Now we can 'fixup' the error value */ + sbio->bi_status = 0; - if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) { + bio_for_each_segment_all(bi, sbio, iter_all) + page_len[j++] = bi->bv_len; + + if (!status) { for (j = vcnt; j-- ; ) { - struct page *p, *s; - p = pbio->bi_io_vec[j].bv_page; - s = sbio->bi_io_vec[j].bv_page; - if (memcmp(page_address(p), - page_address(s), - sbio->bi_io_vec[j].bv_len)) + if (memcmp(page_address(ppages[j]), + page_address(spages[j]), + page_len[j])) break; } } else @@ -1882,37 +2322,15 @@ static int process_checks(struct r1bio *r1_bio) if (j >= 0) atomic64_add(r1_bio->sectors, &mddev->resync_mismatches); if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery) - && test_bit(BIO_UPTODATE, &sbio->bi_flags))) { + && !status)) { /* No need to write to this device. */ sbio->bi_end_io = NULL; rdev_dec_pending(conf->mirrors[i].rdev, mddev); continue; } - /* fixup the bio for reuse */ - bio_reset(sbio); - sbio->bi_vcnt = vcnt; - sbio->bi_size = r1_bio->sectors << 9; - sbio->bi_sector = r1_bio->sector + - conf->mirrors[i].rdev->data_offset; - sbio->bi_bdev = conf->mirrors[i].rdev->bdev; - sbio->bi_end_io = end_sync_read; - sbio->bi_private = r1_bio; - - size = sbio->bi_size; - for (j = 0; j < vcnt ; j++) { - struct bio_vec *bi; - bi = &sbio->bi_io_vec[j]; - bi->bv_offset = 0; - if (size > PAGE_SIZE) - bi->bv_len = PAGE_SIZE; - else - bi->bv_len = size; - size -= PAGE_SIZE; - } bio_copy_data(sbio, pbio); } - return 0; } static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) @@ -1920,18 +2338,27 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) struct r1conf *conf = mddev->private; int i; int disks = conf->raid_disks * 2; - struct bio *bio, *wbio; - - bio = r1_bio->bios[r1_bio->read_disk]; + struct bio *wbio; - if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) - /* ouch - failed to read all of that. */ - if (!fix_sync_read_error(r1_bio)) + if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) { + /* + * ouch - failed to read all of that. + * No need to fix read error for check/repair + * because all member disks are read. + */ + if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) || + !fix_sync_read_error(r1_bio)) { + conf->recovery_disabled = mddev->recovery_disabled; + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + md_done_sync(mddev, r1_bio->sectors, 0); + put_buf(r1_bio); return; + } + } if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) - if (process_checks(r1_bio) < 0) - return; + process_checks(r1_bio); + /* * schedule writes */ @@ -1943,26 +2370,22 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) (i == r1_bio->read_disk || !test_bit(MD_RECOVERY_SYNC, &mddev->recovery)))) continue; + if (test_bit(Faulty, &conf->mirrors[i].rdev->flags)) { + abort_sync_write(mddev, r1_bio); + continue; + } + + wbio->bi_opf = REQ_OP_WRITE; + if (test_bit(FailFast, &conf->mirrors[i].rdev->flags)) + wbio->bi_opf |= MD_FAILFAST; - wbio->bi_rw = WRITE; wbio->bi_end_io = end_sync_write; atomic_inc(&r1_bio->remaining); - md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio)); - generic_make_request(wbio); + submit_bio_noacct(wbio); } - if (atomic_dec_and_test(&r1_bio->remaining)) { - /* if we're here, all write(s) have completed, so clean up */ - int s = r1_bio->sectors; - if (test_bit(R1BIO_MadeGood, &r1_bio->state) || - test_bit(R1BIO_WriteError, &r1_bio->state)) - reschedule_retry(r1_bio); - else { - put_buf(r1_bio); - md_done_sync(mddev, s, 1); - } - } + put_sync_write_buf(r1_bio, 1); } /* @@ -1973,45 +2396,48 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) * 3. Performs writes following reads for array synchronising. */ -static void fix_read_error(struct r1conf *conf, int read_disk, - sector_t sect, int sectors) +static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio) { + sector_t sect = r1_bio->sector; + int sectors = r1_bio->sectors; + int read_disk = r1_bio->read_disk; struct mddev *mddev = conf->mddev; + struct md_rdev *rdev = conf->mirrors[read_disk].rdev; + + if (exceed_read_errors(mddev, rdev)) { + r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED; + return; + } + while(sectors) { int s = sectors; int d = read_disk; int success = 0; int start; - struct md_rdev *rdev; if (s > (PAGE_SIZE>>9)) s = PAGE_SIZE >> 9; do { - /* Note: no rcu protection needed here - * as this is synchronous in the raid1d thread - * which is the thread that might remove - * a device. If raid1d ever becomes multi-threaded.... - */ - sector_t first_bad; - int bad_sectors; - rdev = conf->mirrors[d].rdev; if (rdev && (test_bit(In_sync, &rdev->flags) || (!test_bit(Faulty, &rdev->flags) && rdev->recovery_offset >= sect + s)) && - is_badblock(rdev, sect, s, - &first_bad, &bad_sectors) == 0 && - sync_page_io(rdev, sect, s<<9, - conf->tmppage, READ, false)) - success = 1; - else { - d++; - if (d == conf->raid_disks * 2) - d = 0; + rdev_has_badblock(rdev, sect, s) == 0) { + atomic_inc(&rdev->nr_pending); + if (sync_page_io(rdev, sect, s<<9, + conf->tmppage, REQ_OP_READ, false)) + success = 1; + rdev_dec_pending(rdev, mddev); + if (success) + break; } - } while (!success && d != read_disk); + + d++; + if (d == conf->raid_disks * 2) + d = 0; + } while (d != read_disk); if (!success) { /* Cannot read from anywhere - mark it bad */ @@ -2028,30 +2454,32 @@ static void fix_read_error(struct r1conf *conf, int read_disk, d--; rdev = conf->mirrors[d].rdev; if (rdev && - test_bit(In_sync, &rdev->flags)) + !test_bit(Faulty, &rdev->flags)) { + atomic_inc(&rdev->nr_pending); r1_sync_page_io(rdev, sect, s, - conf->tmppage, WRITE); + conf->tmppage, REQ_OP_WRITE); + rdev_dec_pending(rdev, mddev); + } } d = start; while (d != read_disk) { - char b[BDEVNAME_SIZE]; if (d==0) d = conf->raid_disks * 2; d--; rdev = conf->mirrors[d].rdev; if (rdev && - test_bit(In_sync, &rdev->flags)) { + !test_bit(Faulty, &rdev->flags)) { + atomic_inc(&rdev->nr_pending); if (r1_sync_page_io(rdev, sect, s, - conf->tmppage, READ)) { + conf->tmppage, REQ_OP_READ)) { atomic_add(s, &rdev->corrected_errors); - printk(KERN_INFO - "md/raid1:%s: read error corrected " - "(%d sectors at %llu on %s)\n", - mdname(mddev), s, - (unsigned long long)(sect + - rdev->data_offset), - bdevname(rdev->bdev, b)); + pr_info("md/raid1:%s: read error corrected (%d sectors at %llu on %pg)\n", + mdname(mddev), s, + (unsigned long long)(sect + + rdev->data_offset), + rdev->bdev); } + rdev_dec_pending(rdev, mddev); } } sectors -= s; @@ -2059,7 +2487,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk, } } -static int narrow_write_error(struct r1bio *r1_bio, int i) +static bool narrow_write_error(struct r1bio *r1_bio, int i) { struct mddev *mddev = r1_bio->mddev; struct r1conf *conf = mddev->private; @@ -2080,12 +2508,13 @@ static int narrow_write_error(struct r1bio *r1_bio, int i) sector_t sector; int sectors; int sect_to_write = r1_bio->sectors; - int ok = 1; + bool ok = true; if (rdev->badblocks.shift < 0) - return 0; + return false; - block_sectors = 1 << rdev->badblocks.shift; + block_sectors = roundup(1 << rdev->badblocks.shift, + bdev_logical_block_size(rdev->bdev) >> 9); sector = r1_bio->sector; sectors = ((sector + block_sectors) & ~(sector_t)(block_sectors - 1)) @@ -2098,30 +2527,22 @@ static int narrow_write_error(struct r1bio *r1_bio, int i) /* Write at 'sector' for 'sectors'*/ if (test_bit(R1BIO_BehindIO, &r1_bio->state)) { - unsigned vcnt = r1_bio->behind_page_count; - struct bio_vec *vec = r1_bio->behind_bvecs; - - while (!vec->bv_page) { - vec++; - vcnt--; - } - - wbio = bio_alloc_mddev(GFP_NOIO, vcnt, mddev); - memcpy(wbio->bi_io_vec, vec, vcnt * sizeof(struct bio_vec)); - - wbio->bi_vcnt = vcnt; + wbio = bio_alloc_clone(rdev->bdev, + r1_bio->behind_master_bio, + GFP_NOIO, &mddev->bio_set); } else { - wbio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev); + wbio = bio_alloc_clone(rdev->bdev, r1_bio->master_bio, + GFP_NOIO, &mddev->bio_set); } - wbio->bi_rw = WRITE; - wbio->bi_sector = r1_bio->sector; - wbio->bi_size = r1_bio->sectors << 9; + wbio->bi_opf = REQ_OP_WRITE; + wbio->bi_iter.bi_sector = r1_bio->sector; + wbio->bi_iter.bi_size = r1_bio->sectors << 9; + + bio_trim(wbio, sector - r1_bio->sector, sectors); + wbio->bi_iter.bi_sector += rdev->data_offset; - md_trim_bio(wbio, sector - r1_bio->sector, sectors); - wbio->bi_sector += rdev->data_offset; - wbio->bi_bdev = rdev->bdev; - if (submit_bio_wait(WRITE, wbio) == 0) + if (submit_bio_wait(wbio) < 0) /* failure! */ ok = rdev_set_badblocks(rdev, sector, sectors, 0) @@ -2144,11 +2565,11 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio struct bio *bio = r1_bio->bios[m]; if (bio->bi_end_io == NULL) continue; - if (test_bit(BIO_UPTODATE, &bio->bi_flags) && + if (!bio->bi_status && test_bit(R1BIO_MadeGood, &r1_bio->state)) { rdev_clear_badblocks(rdev, r1_bio->sector, s, 0); } - if (!test_bit(BIO_UPTODATE, &bio->bi_flags) && + if (bio->bi_status && test_bit(R1BIO_WriteError, &r1_bio->state)) { if (!rdev_set_badblocks(rdev, r1_bio->sector, s, 0)) md_error(conf->mddev, rdev); @@ -2160,7 +2581,9 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) { - int m; + int m, idx; + bool fail = false; + for (m = 0; m < conf->raid_disks * 2 ; m++) if (r1_bio->bios[m] == IO_MADE_GOOD) { struct md_rdev *rdev = conf->mirrors[m].rdev; @@ -2173,28 +2596,39 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) * narrow down and record precise write * errors. */ - if (!narrow_write_error(r1_bio, m)) { + fail = true; + if (!narrow_write_error(r1_bio, m)) md_error(conf->mddev, conf->mirrors[m].rdev); /* an I/O failed, we can't clear the bitmap */ - set_bit(R1BIO_Degraded, &r1_bio->state); - } rdev_dec_pending(conf->mirrors[m].rdev, conf->mddev); } - if (test_bit(R1BIO_WriteError, &r1_bio->state)) - close_write(r1_bio); - raid_end_bio_io(r1_bio); + if (fail) { + spin_lock_irq(&conf->device_lock); + list_add(&r1_bio->retry_list, &conf->bio_end_io_list); + idx = sector_to_idx(r1_bio->sector); + atomic_inc(&conf->nr_queued[idx]); + spin_unlock_irq(&conf->device_lock); + /* + * In case freeze_array() is waiting for condition + * get_unqueued_pending() == extra to be true. + */ + wake_up(&conf->wait_barrier); + md_wakeup_thread(conf->mddev->thread); + } else { + if (test_bit(R1BIO_WriteError, &r1_bio->state)) + close_write(r1_bio); + raid_end_bio_io(r1_bio); + } } static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio) { - int disk; - int max_sectors; struct mddev *mddev = conf->mddev; struct bio *bio; - char b[BDEVNAME_SIZE]; struct md_rdev *rdev; + sector_t sector; clear_bit(R1BIO_ReadError, &r1_bio->state); /* we got a read error. Maybe the drive is bad. Maybe just @@ -2205,76 +2639,31 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio) * This is all done synchronously while the array is * frozen */ - if (mddev->ro == 0) { - freeze_array(conf, 1); - fix_read_error(conf, r1_bio->read_disk, - r1_bio->sector, r1_bio->sectors); - unfreeze_array(conf); - } else - md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev); - rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev); bio = r1_bio->bios[r1_bio->read_disk]; - bdevname(bio->bi_bdev, b); -read_more: - disk = read_balance(conf, r1_bio, &max_sectors); - if (disk == -1) { - printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O" - " read error for block %llu\n", - mdname(mddev), b, (unsigned long long)r1_bio->sector); - raid_end_bio_io(r1_bio); - } else { - const unsigned long do_sync - = r1_bio->master_bio->bi_rw & REQ_SYNC; - if (bio) { - r1_bio->bios[r1_bio->read_disk] = - mddev->ro ? IO_BLOCKED : NULL; - bio_put(bio); - } - r1_bio->read_disk = disk; - bio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev); - md_trim_bio(bio, r1_bio->sector - bio->bi_sector, max_sectors); - r1_bio->bios[r1_bio->read_disk] = bio; - rdev = conf->mirrors[disk].rdev; - printk_ratelimited(KERN_ERR - "md/raid1:%s: redirecting sector %llu" - " to other mirror: %s\n", - mdname(mddev), - (unsigned long long)r1_bio->sector, - bdevname(rdev->bdev, b)); - bio->bi_sector = r1_bio->sector + rdev->data_offset; - bio->bi_bdev = rdev->bdev; - bio->bi_end_io = raid1_end_read_request; - bio->bi_rw = READ | do_sync; - bio->bi_private = r1_bio; - if (max_sectors < r1_bio->sectors) { - /* Drat - have to split this up more */ - struct bio *mbio = r1_bio->master_bio; - int sectors_handled = (r1_bio->sector + max_sectors - - mbio->bi_sector); - r1_bio->sectors = max_sectors; - spin_lock_irq(&conf->device_lock); - if (mbio->bi_phys_segments == 0) - mbio->bi_phys_segments = 2; - else - mbio->bi_phys_segments++; - spin_unlock_irq(&conf->device_lock); - generic_make_request(bio); - bio = NULL; + bio_put(bio); + r1_bio->bios[r1_bio->read_disk] = NULL; - r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO); + rdev = conf->mirrors[r1_bio->read_disk].rdev; + if (mddev->ro == 0 + && !test_bit(FailFast, &rdev->flags)) { + freeze_array(conf, 1); + fix_read_error(conf, r1_bio); + unfreeze_array(conf); + } else if (mddev->ro == 0 && test_bit(FailFast, &rdev->flags)) { + md_error(mddev, rdev); + } else { + r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED; + } - r1_bio->master_bio = mbio; - r1_bio->sectors = bio_sectors(mbio) - sectors_handled; - r1_bio->state = 0; - set_bit(R1BIO_ReadError, &r1_bio->state); - r1_bio->mddev = mddev; - r1_bio->sector = mbio->bi_sector + sectors_handled; + rdev_dec_pending(rdev, conf->mddev); + sector = r1_bio->sector; + bio = r1_bio->master_bio; - goto read_more; - } else - generic_make_request(bio); - } + /* Reuse the old r1_bio so that the IO_BLOCKED settings are preserved */ + r1_bio->state = 0; + raid1_read_request(mddev, bio, r1_bio->sectors, r1_bio); + allow_barrier(conf, sector); } static void raid1d(struct md_thread *thread) @@ -2285,9 +2674,29 @@ static void raid1d(struct md_thread *thread) struct r1conf *conf = mddev->private; struct list_head *head = &conf->retry_list; struct blk_plug plug; + int idx; md_check_recovery(mddev); + if (!list_empty_careful(&conf->bio_end_io_list) && + !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) { + LIST_HEAD(tmp); + spin_lock_irqsave(&conf->device_lock, flags); + if (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) + list_splice_init(&conf->bio_end_io_list, &tmp); + spin_unlock_irqrestore(&conf->device_lock, flags); + while (!list_empty(&tmp)) { + r1_bio = list_first_entry(&tmp, struct r1bio, + retry_list); + list_del(&r1_bio->retry_list); + idx = sector_to_idx(r1_bio->sector); + atomic_dec(&conf->nr_queued[idx]); + if (test_bit(R1BIO_WriteError, &r1_bio->state)) + close_write(r1_bio); + raid_end_bio_io(r1_bio); + } + } + blk_start_plug(&plug); for (;;) { @@ -2300,7 +2709,8 @@ static void raid1d(struct md_thread *thread) } r1_bio = list_entry(head->prev, struct r1bio, retry_list); list_del(head->prev); - conf->nr_queued--; + idx = sector_to_idx(r1_bio->sector); + atomic_dec(&conf->nr_queued[idx]); spin_unlock_irqrestore(&conf->device_lock, flags); mddev = r1_bio->mddev; @@ -2317,31 +2727,41 @@ static void raid1d(struct md_thread *thread) else if (test_bit(R1BIO_ReadError, &r1_bio->state)) handle_read_error(conf, r1_bio); else - /* just a partial read to be scheduled from separate - * context - */ - generic_make_request(r1_bio->bios[r1_bio->read_disk]); + WARN_ON_ONCE(1); cond_resched(); - if (mddev->flags & ~(1<<MD_CHANGE_PENDING)) + if (mddev->sb_flags & ~(1<<MD_SB_CHANGE_PENDING)) md_check_recovery(mddev); } blk_finish_plug(&plug); } - static int init_resync(struct r1conf *conf) { int buffs; buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE; - BUG_ON(conf->r1buf_pool); - conf->r1buf_pool = mempool_create(buffs, r1buf_pool_alloc, r1buf_pool_free, - conf->poolinfo); - if (!conf->r1buf_pool) - return -ENOMEM; - conf->next_resync = 0; - return 0; + BUG_ON(mempool_initialized(&conf->r1buf_pool)); + + return mempool_init(&conf->r1buf_pool, buffs, r1buf_pool_alloc, + r1buf_pool_free, conf); +} + +static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf) +{ + struct r1bio *r1bio = mempool_alloc(&conf->r1buf_pool, GFP_NOIO); + struct resync_pages *rps; + struct bio *bio; + int i; + + for (i = conf->raid_disks * 2; i--; ) { + bio = r1bio->bios[i]; + rps = bio->bi_private; + bio_reset(bio, NULL, 0); + bio->bi_private = rps; + } + r1bio->master_bio = NULL; + return r1bio; } /* @@ -2354,26 +2774,28 @@ static int init_resync(struct r1conf *conf) * that can be installed to exclude normal IO requests. */ -static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster) +static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, + sector_t max_sector, int *skipped) { struct r1conf *conf = mddev->private; struct r1bio *r1_bio; struct bio *bio; - sector_t max_sector, nr_sectors; + sector_t nr_sectors; int disk = -1; int i; int wonly = -1; int write_targets = 0, read_targets = 0; sector_t sync_blocks; - int still_degraded = 0; + bool still_degraded = false; int good_sectors = RESYNC_SECTORS; int min_bad = 0; /* number of sectors that are bad in all devices */ + int idx = sector_to_idx(sector_nr); + int page_idx = 0; - if (!conf->r1buf_pool) + if (!mempool_initialized(&conf->r1buf_pool)) if (init_resync(conf)) return 0; - max_sector = mddev->dev_sectors; if (sector_nr >= max_sector) { /* If we aborted, we need to abort the * sync on the 'current' bitmap chunk (there will @@ -2381,18 +2803,24 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp * We can find the current addess in mddev->curr_resync */ if (mddev->curr_resync < max_sector) /* aborted */ - bitmap_end_sync(mddev->bitmap, mddev->curr_resync, - &sync_blocks, 1); + md_bitmap_end_sync(mddev, mddev->curr_resync, + &sync_blocks); else /* completed sync */ conf->fullsync = 0; - bitmap_close_sync(mddev->bitmap); + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->close_sync(mddev); close_sync(conf); + + if (mddev_is_clustered(mddev)) { + conf->cluster_sync_low = 0; + conf->cluster_sync_high = 0; + } return 0; } if (mddev->bitmap == NULL && - mddev->recovery_cp == MaxSector && + mddev->resync_offset == MaxSector && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) && conf->fullsync == 0) { *skipped = 1; @@ -2401,27 +2829,34 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp /* before building a request, check if we can skip these blocks.. * This call the bitmap_start_sync doesn't actually record anything */ - if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) && + if (!md_bitmap_start_sync(mddev, sector_nr, &sync_blocks, true) && !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) { /* We can skip this block, and probably several more */ *skipped = 1; return sync_blocks; } + /* - * If there is non-resync activity waiting for a turn, - * and resync is going fast enough, - * then let it though before starting on this new sync request. + * If there is non-resync activity waiting for a turn, then let it + * though before starting on this new sync request. */ - if (!go_faster && conf->nr_waiting) - msleep_interruptible(1000); + if (atomic_read(&conf->nr_waiting[idx])) + schedule_timeout_uninterruptible(1); - bitmap_cond_end_sync(mddev->bitmap, sector_nr); - r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO); - raise_barrier(conf); + /* we are incrementing sector_nr below. To be safe, we check against + * sector_nr + two times RESYNC_SECTORS + */ + if (md_bitmap_enabled(mddev, false)) + mddev->bitmap_ops->cond_end_sync(mddev, sector_nr, + mddev_is_clustered(mddev) && + (sector_nr + 2 * RESYNC_SECTORS > + conf->cluster_sync_high)); + + if (raise_barrier(conf, sector_nr)) + return 0; - conf->next_resync = sector_nr; + r1_bio = raid1_alloc_init_r1buf(conf); - rcu_read_lock(); /* * If we get a correctably read error during resync or recovery, * we might want to read from a different device. So we @@ -2435,25 +2870,26 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp r1_bio->sector = sector_nr; r1_bio->state = 0; set_bit(R1BIO_IsSync, &r1_bio->state); + /* make sure good_sectors won't go across barrier unit boundary */ + good_sectors = align_to_barrier_unit_end(sector_nr, good_sectors); for (i = 0; i < conf->raid_disks * 2; i++) { struct md_rdev *rdev; bio = r1_bio->bios[i]; - bio_reset(bio); - rdev = rcu_dereference(conf->mirrors[i].rdev); + rdev = conf->mirrors[i].rdev; if (rdev == NULL || test_bit(Faulty, &rdev->flags)) { if (i < conf->raid_disks) - still_degraded = 1; + still_degraded = true; } else if (!test_bit(In_sync, &rdev->flags)) { - bio->bi_rw = WRITE; + bio->bi_opf = REQ_OP_WRITE; bio->bi_end_io = end_sync_write; write_targets ++; } else { /* may need to read from here */ sector_t first_bad = MaxSector; - int bad_sectors; + sector_t bad_sectors; if (is_badblock(rdev, sector_nr, good_sectors, &first_bad, &bad_sectors)) { @@ -2474,7 +2910,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp if (disk < 0) disk = i; } - bio->bi_rw = READ; + bio->bi_opf = REQ_OP_READ; bio->bi_end_io = end_sync_read; read_targets++; } else if (!test_bit(WriteErrorSeen, &rdev->flags) && @@ -2486,19 +2922,19 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp * if we are doing resync or repair. Otherwise, leave * this device alone for this sync request. */ - bio->bi_rw = WRITE; + bio->bi_opf = REQ_OP_WRITE; bio->bi_end_io = end_sync_write; write_targets++; } } - if (bio->bi_end_io) { + if (rdev && bio->bi_end_io) { atomic_inc(&rdev->nr_pending); - bio->bi_sector = sector_nr + rdev->data_offset; - bio->bi_bdev = rdev->bdev; - bio->bi_private = r1_bio; + bio->bi_iter.bi_sector = sector_nr + rdev->data_offset; + bio_set_dev(bio, rdev->bdev); + if (test_bit(FailFast, &rdev->flags)) + bio->bi_opf |= MD_FAILFAST; } } - rcu_read_unlock(); if (disk < 0) disk = wonly; r1_bio->read_disk = disk; @@ -2515,7 +2951,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp min_bad, 0 ) && ok; } - set_bit(MD_CHANGE_DEVS, &mddev->flags); + set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); *skipped = 1; put_buf(r1_bio); @@ -2569,44 +3005,47 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp if (len == 0) break; if (sync_blocks == 0) { - if (!bitmap_start_sync(mddev->bitmap, sector_nr, - &sync_blocks, still_degraded) && + if (!md_bitmap_start_sync(mddev, sector_nr, + &sync_blocks, still_degraded) && !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) break; - BUG_ON(sync_blocks < (PAGE_SIZE>>9)); if ((len >> 9) > sync_blocks) len = sync_blocks<<9; } for (i = 0 ; i < conf->raid_disks * 2; i++) { + struct resync_pages *rp; + bio = r1_bio->bios[i]; + rp = get_resync_pages(bio); if (bio->bi_end_io) { - page = bio->bi_io_vec[bio->bi_vcnt].bv_page; - if (bio_add_page(bio, page, len, 0) == 0) { - /* stop here */ - bio->bi_io_vec[bio->bi_vcnt].bv_page = page; - while (i > 0) { - i--; - bio = r1_bio->bios[i]; - if (bio->bi_end_io==NULL) - continue; - /* remove last page from this bio */ - bio->bi_vcnt--; - bio->bi_size -= len; - bio->bi_flags &= ~(1<< BIO_SEG_VALID); - } - goto bio_full; - } + page = resync_fetch_page(rp, page_idx); + + /* + * won't fail because the vec table is big + * enough to hold all these pages + */ + __bio_add_page(bio, page, len, 0); } } nr_sectors += len>>9; sector_nr += len>>9; sync_blocks -= (len>>9); - } while (r1_bio->bios[disk]->bi_vcnt < RESYNC_PAGES); - bio_full: + } while (++page_idx < RESYNC_PAGES); + r1_bio->sectors = nr_sectors; + if (mddev_is_clustered(mddev) && + conf->cluster_sync_high < sector_nr + nr_sectors) { + conf->cluster_sync_low = mddev->curr_resync_completed; + conf->cluster_sync_high = conf->cluster_sync_low + CLUSTER_RESYNC_WINDOW_SECTORS; + /* Send resync message */ + mddev->cluster_ops->resync_info_update(mddev, + conf->cluster_sync_low, + conf->cluster_sync_high); + } + /* For a user-requested sync, we read all readable devices and do a * compare */ @@ -2616,16 +3055,17 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp bio = r1_bio->bios[i]; if (bio->bi_end_io == end_sync_read) { read_targets--; - md_sync_acct(bio->bi_bdev, nr_sectors); - generic_make_request(bio); + if (read_targets == 1) + bio->bi_opf &= ~MD_FAILFAST; + submit_bio_noacct(bio); } } } else { atomic_set(&r1_bio->remaining, 1); bio = r1_bio->bios[r1_bio->read_disk]; - md_sync_acct(bio->bi_bdev, nr_sectors); - generic_make_request(bio); - + if (read_targets == 1) + bio->bi_opf &= ~MD_FAILFAST; + submit_bio_noacct(bio); } return nr_sectors; } @@ -2644,15 +3084,36 @@ static struct r1conf *setup_conf(struct mddev *mddev) int i; struct raid1_info *disk; struct md_rdev *rdev; + size_t r1bio_size; int err = -ENOMEM; conf = kzalloc(sizeof(struct r1conf), GFP_KERNEL); if (!conf) goto abort; - conf->mirrors = kzalloc(sizeof(struct raid1_info) - * mddev->raid_disks * 2, - GFP_KERNEL); + conf->nr_pending = kcalloc(BARRIER_BUCKETS_NR, + sizeof(atomic_t), GFP_KERNEL); + if (!conf->nr_pending) + goto abort; + + conf->nr_waiting = kcalloc(BARRIER_BUCKETS_NR, + sizeof(atomic_t), GFP_KERNEL); + if (!conf->nr_waiting) + goto abort; + + conf->nr_queued = kcalloc(BARRIER_BUCKETS_NR, + sizeof(atomic_t), GFP_KERNEL); + if (!conf->nr_queued) + goto abort; + + conf->barrier = kcalloc(BARRIER_BUCKETS_NR, + sizeof(atomic_t), GFP_KERNEL); + if (!conf->barrier) + goto abort; + + conf->mirrors = kzalloc(array3_size(sizeof(struct raid1_info), + mddev->raid_disks, 2), + GFP_KERNEL); if (!conf->mirrors) goto abort; @@ -2660,50 +3121,36 @@ static struct r1conf *setup_conf(struct mddev *mddev) if (!conf->tmppage) goto abort; - conf->poolinfo = kzalloc(sizeof(*conf->poolinfo), GFP_KERNEL); - if (!conf->poolinfo) - goto abort; - conf->poolinfo->raid_disks = mddev->raid_disks * 2; - conf->r1bio_pool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc, - r1bio_pool_free, - conf->poolinfo); + r1bio_size = offsetof(struct r1bio, bios[mddev->raid_disks * 2]); + conf->r1bio_pool = mempool_create_kmalloc_pool(NR_RAID_BIOS, r1bio_size); if (!conf->r1bio_pool) goto abort; - conf->poolinfo->mddev = mddev; + err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0); + if (err) + goto abort; err = -EINVAL; spin_lock_init(&conf->device_lock); + conf->raid_disks = mddev->raid_disks; rdev_for_each(rdev, mddev) { - struct request_queue *q; int disk_idx = rdev->raid_disk; - if (disk_idx >= mddev->raid_disks - || disk_idx < 0) + + if (disk_idx >= conf->raid_disks || disk_idx < 0) continue; - if (test_bit(Replacement, &rdev->flags)) - disk = conf->mirrors + mddev->raid_disks + disk_idx; - else - disk = conf->mirrors + disk_idx; - if (disk->rdev) + if (!raid1_add_conf(conf, rdev, disk_idx, + test_bit(Replacement, &rdev->flags))) goto abort; - disk->rdev = rdev; - q = bdev_get_queue(rdev->bdev); - if (q->merge_bvec_fn) - mddev->merge_check_needed = 1; - - disk->head_position = 0; - disk->seq_start = MaxSector; } - conf->raid_disks = mddev->raid_disks; conf->mddev = mddev; INIT_LIST_HEAD(&conf->retry_list); + INIT_LIST_HEAD(&conf->bio_end_io_list); spin_lock_init(&conf->resync_lock); init_waitqueue_head(&conf->wait_barrier); bio_list_init(&conf->pending_bio_list); - conf->pending_count = 0; conf->recovery_disabled = mddev->recovery_disabled - 1; err = -EIO; @@ -2736,51 +3183,65 @@ static struct r1conf *setup_conf(struct mddev *mddev) } err = -ENOMEM; - conf->thread = md_register_thread(raid1d, mddev, "raid1"); - if (!conf->thread) { - printk(KERN_ERR - "md/raid1:%s: couldn't allocate thread\n", - mdname(mddev)); + rcu_assign_pointer(conf->thread, + md_register_thread(raid1d, mddev, "raid1")); + if (!conf->thread) goto abort; - } return conf; abort: if (conf) { - if (conf->r1bio_pool) - mempool_destroy(conf->r1bio_pool); + mempool_destroy(conf->r1bio_pool); kfree(conf->mirrors); safe_put_page(conf->tmppage); - kfree(conf->poolinfo); + kfree(conf->nr_pending); + kfree(conf->nr_waiting); + kfree(conf->nr_queued); + kfree(conf->barrier); + bioset_exit(&conf->bio_split); kfree(conf); } return ERR_PTR(err); } -static int stop(struct mddev *mddev); -static int run(struct mddev *mddev) +static int raid1_set_limits(struct mddev *mddev) +{ + struct queue_limits lim; + int err; + + md_init_stacking_limits(&lim); + lim.max_write_zeroes_sectors = 0; + lim.max_hw_wzeroes_unmap_sectors = 0; + lim.logical_block_size = mddev->logical_block_size; + lim.features |= BLK_FEAT_ATOMIC_WRITES; + err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); + if (err) + return err; + return queue_limits_set(mddev->gendisk->queue, &lim); +} + +static int raid1_run(struct mddev *mddev) { struct r1conf *conf; int i; - struct md_rdev *rdev; int ret; - bool discard_supported = false; if (mddev->level != 1) { - printk(KERN_ERR "md/raid1:%s: raid level not set to mirroring (%d)\n", - mdname(mddev), mddev->level); + pr_warn("md/raid1:%s: raid level not set to mirroring (%d)\n", + mdname(mddev), mddev->level); return -EIO; } if (mddev->reshape_position != MaxSector) { - printk(KERN_ERR "md/raid1:%s: reshape_position set but not supported\n", - mdname(mddev)); + pr_warn("md/raid1:%s: reshape_position set but not supported\n", + mdname(mddev)); return -EIO; } + /* * copy the already verified devices into our private RAID1 * bookkeeping area. [whatever we allocate in run(), - * should be freed in stop()] + * should be freed in raid1_free()] */ if (mddev->private == NULL) conf = setup_conf(mddev); @@ -2790,91 +3251,70 @@ static int run(struct mddev *mddev) if (IS_ERR(conf)) return PTR_ERR(conf); - if (mddev->queue) - blk_queue_max_write_same_sectors(mddev->queue, 0); - - rdev_for_each(rdev, mddev) { - if (!mddev->gendisk) - continue; - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - if (blk_queue_discard(bdev_get_queue(rdev->bdev))) - discard_supported = true; + if (!mddev_is_dm(mddev)) { + ret = raid1_set_limits(mddev); + if (ret) { + if (!mddev->private) + raid1_free(mddev, conf); + return ret; + } } mddev->degraded = 0; - for (i=0; i < conf->raid_disks; i++) + for (i = 0; i < conf->raid_disks; i++) if (conf->mirrors[i].rdev == NULL || !test_bit(In_sync, &conf->mirrors[i].rdev->flags) || test_bit(Faulty, &conf->mirrors[i].rdev->flags)) mddev->degraded++; + /* + * RAID1 needs at least one disk in active + */ + if (conf->raid_disks - mddev->degraded < 1) { + md_unregister_thread(mddev, &conf->thread); + if (!mddev->private) + raid1_free(mddev, conf); + return -EINVAL; + } if (conf->raid_disks - mddev->degraded == 1) - mddev->recovery_cp = MaxSector; - - if (mddev->recovery_cp != MaxSector) - printk(KERN_NOTICE "md/raid1:%s: not clean" - " -- starting background reconstruction\n", - mdname(mddev)); - printk(KERN_INFO - "md/raid1:%s: active with %d out of %d mirrors\n", - mdname(mddev), mddev->raid_disks - mddev->degraded, + mddev->resync_offset = MaxSector; + + if (mddev->resync_offset != MaxSector) + pr_info("md/raid1:%s: not clean -- starting background reconstruction\n", + mdname(mddev)); + pr_info("md/raid1:%s: active with %d out of %d mirrors\n", + mdname(mddev), mddev->raid_disks - mddev->degraded, mddev->raid_disks); /* * Ok, everything is just fine now */ - mddev->thread = conf->thread; - conf->thread = NULL; + rcu_assign_pointer(mddev->thread, conf->thread); + rcu_assign_pointer(conf->thread, NULL); mddev->private = conf; + set_bit(MD_FAILFAST_SUPPORTED, &mddev->flags); md_set_array_sectors(mddev, raid1_size(mddev, 0, 0)); - if (mddev->queue) { - mddev->queue->backing_dev_info.congested_fn = raid1_congested; - mddev->queue->backing_dev_info.congested_data = mddev; - blk_queue_merge_bvec(mddev->queue, raid1_mergeable_bvec); - - if (discard_supported) - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, - mddev->queue); - else - queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, - mddev->queue); - } - - ret = md_integrity_register(mddev); + ret = md_integrity_register(mddev); if (ret) - stop(mddev); + md_unregister_thread(mddev, &mddev->thread); return ret; } -static int stop(struct mddev *mddev) +static void raid1_free(struct mddev *mddev, void *priv) { - struct r1conf *conf = mddev->private; - struct bitmap *bitmap = mddev->bitmap; + struct r1conf *conf = priv; - /* wait for behind writes to complete */ - if (bitmap && atomic_read(&bitmap->behind_writes) > 0) { - printk(KERN_INFO "md/raid1:%s: behind writes in progress - waiting to stop.\n", - mdname(mddev)); - /* need to kick something here to make sure I/O goes? */ - wait_event(bitmap->behind_wait, - atomic_read(&bitmap->behind_writes) == 0); - } - - raise_barrier(conf); - lower_barrier(conf); - - md_unregister_thread(&mddev->thread); - if (conf->r1bio_pool) - mempool_destroy(conf->r1bio_pool); + mempool_destroy(conf->r1bio_pool); kfree(conf->mirrors); safe_put_page(conf->tmppage); - kfree(conf->poolinfo); + kfree(conf->nr_pending); + kfree(conf->nr_waiting); + kfree(conf->nr_queued); + kfree(conf->barrier); + bioset_exit(&conf->bio_split); kfree(conf); - mddev->private = NULL; - return 0; } static int raid1_resize(struct mddev *mddev, sector_t sectors) @@ -2887,20 +3327,22 @@ static int raid1_resize(struct mddev *mddev, sector_t sectors) * worth it. */ sector_t newsize = raid1_size(mddev, sectors, 0); + if (mddev->external_size && mddev->array_sectors > newsize) return -EINVAL; - if (mddev->bitmap) { - int ret = bitmap_resize(mddev->bitmap, newsize, 0, 0); + + if (md_bitmap_enabled(mddev, false)) { + int ret = mddev->bitmap_ops->resize(mddev, newsize, 0); + if (ret) return ret; } + md_set_array_sectors(mddev, newsize); - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); if (sectors > mddev->dev_sectors && - mddev->recovery_cp > mddev->dev_sectors) { - mddev->recovery_cp = mddev->dev_sectors; + mddev->resync_offset > mddev->dev_sectors) { + mddev->resync_offset = mddev->dev_sectors; set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } mddev->dev_sectors = sectors; @@ -2922,12 +3364,12 @@ static int raid1_reshape(struct mddev *mddev) * devices have the higher raid_disk numbers. */ mempool_t *newpool, *oldpool; - struct pool_info *newpoolinfo; + size_t new_r1bio_size; struct raid1_info *newmirrors; struct r1conf *conf = mddev->private; int cnt, raid_disks; unsigned long flags; - int d, d2, err; + int d, d2; /* Cannot change chunk_size, layout, or level */ if (mddev->chunk_sectors != mddev->new_chunk_sectors || @@ -2939,9 +3381,8 @@ static int raid1_reshape(struct mddev *mddev) return -EINVAL; } - err = md_allow_write(mddev); - if (err) - return err; + if (!mddev_is_clustered(mddev)) + md_allow_write(mddev); raid_disks = mddev->raid_disks + mddev->delta_disks; @@ -2954,22 +3395,15 @@ static int raid1_reshape(struct mddev *mddev) return -EBUSY; } - newpoolinfo = kmalloc(sizeof(*newpoolinfo), GFP_KERNEL); - if (!newpoolinfo) - return -ENOMEM; - newpoolinfo->mddev = mddev; - newpoolinfo->raid_disks = raid_disks * 2; - - newpool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc, - r1bio_pool_free, newpoolinfo); + new_r1bio_size = offsetof(struct r1bio, bios[raid_disks * 2]); + newpool = mempool_create_kmalloc_pool(NR_RAID_BIOS, new_r1bio_size); if (!newpool) { - kfree(newpoolinfo); return -ENOMEM; } - newmirrors = kzalloc(sizeof(struct raid1_info) * raid_disks * 2, + newmirrors = kzalloc(array3_size(sizeof(struct raid1_info), + raid_disks, 2), GFP_KERNEL); if (!newmirrors) { - kfree(newpoolinfo); mempool_destroy(newpool); return -ENOMEM; } @@ -2987,17 +3421,14 @@ static int raid1_reshape(struct mddev *mddev) rdev->raid_disk = d2; sysfs_unlink_rdev(mddev, rdev); if (sysfs_link_rdev(mddev, rdev)) - printk(KERN_WARNING - "md/raid1:%s: cannot register rd%d\n", - mdname(mddev), rdev->raid_disk); + pr_warn("md/raid1:%s: cannot register rd%d\n", + mdname(mddev), rdev->raid_disk); } if (rdev) newmirrors[d2++].rdev = rdev; } kfree(conf->mirrors); conf->mirrors = newmirrors; - kfree(conf->poolinfo); - conf->poolinfo = newpoolinfo; spin_lock_irqsave(&conf->device_lock, flags); mddev->degraded += (raid_disks - conf->raid_disks); @@ -3007,6 +3438,7 @@ static int raid1_reshape(struct mddev *mddev) unfreeze_array(conf); + set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); @@ -3014,21 +3446,14 @@ static int raid1_reshape(struct mddev *mddev) return 0; } -static void raid1_quiesce(struct mddev *mddev, int state) +static void raid1_quiesce(struct mddev *mddev, int quiesce) { struct r1conf *conf = mddev->private; - switch(state) { - case 2: /* wake for suspend */ - wake_up(&conf->wait_barrier); - break; - case 1: - raise_barrier(conf); - break; - case 0: - lower_barrier(conf); - break; - } + if (quiesce) + freeze_array(conf, 0); + else + unfreeze_array(conf); } static void *raid1_takeover(struct mddev *mddev) @@ -3042,8 +3467,12 @@ static void *raid1_takeover(struct mddev *mddev) mddev->new_layout = 0; mddev->new_chunk_sectors = 0; conf = setup_conf(mddev); - if (!IS_ERR(conf)) - conf->barrier = 1; + if (!IS_ERR(conf)) { + /* Array must appear to be quiesced */ + conf->array_frozen = 1; + mddev_clear_unsupported_flags(mddev, + UNSUPPORTED_MDDEV_FLAGS); + } return conf; } return ERR_PTR(-EINVAL); @@ -3051,18 +3480,22 @@ static void *raid1_takeover(struct mddev *mddev) static struct md_personality raid1_personality = { - .name = "raid1", - .level = 1, - .owner = THIS_MODULE, - .make_request = make_request, - .run = run, - .stop = stop, - .status = status, - .error_handler = error, + .head = { + .type = MD_PERSONALITY, + .id = ID_RAID1, + .name = "raid1", + .owner = THIS_MODULE, + }, + + .make_request = raid1_make_request, + .run = raid1_run, + .free = raid1_free, + .status = raid1_status, + .error_handler = raid1_error, .hot_add_disk = raid1_add_disk, .hot_remove_disk= raid1_remove_disk, .spare_active = raid1_spare_active, - .sync_request = sync_request, + .sync_request = raid1_sync_request, .resize = raid1_resize, .size = raid1_size, .check_reshape = raid1_reshape, @@ -3070,22 +3503,20 @@ static struct md_personality raid1_personality = .takeover = raid1_takeover, }; -static int __init raid_init(void) +static int __init raid1_init(void) { - return register_md_personality(&raid1_personality); + return register_md_submodule(&raid1_personality.head); } -static void raid_exit(void) +static void __exit raid1_exit(void) { - unregister_md_personality(&raid1_personality); + unregister_md_submodule(&raid1_personality.head); } -module_init(raid_init); -module_exit(raid_exit); +module_init(raid1_init); +module_exit(raid1_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("RAID1 (mirroring) personality for MD"); MODULE_ALIAS("md-personality-3"); /* RAID1 */ MODULE_ALIAS("md-raid1"); MODULE_ALIAS("md-level-1"); - -module_param(max_queued_requests, int, S_IRUGO|S_IWUSR); |