diff options
Diffstat (limited to 'drivers/md/raid1.c')
| -rw-r--r-- | drivers/md/raid1.c | 994 |
1 files changed, 614 insertions, 380 deletions
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 29e2df5cd77b..fbc2d7851b49 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -37,10 +37,18 @@ #include <linux/module.h> #include <linux/seq_file.h> #include <linux/ratelimit.h> +#include <linux/sched/signal.h> + +#include <trace/events/block.h> + #include "md.h" #include "raid1.h" #include "bitmap.h" +#define UNSUPPORTED_MDDEV_FLAGS \ + ((1L << MD_HAS_JOURNAL) | \ + (1L << MD_JOURNAL_CLEAN)) + /* * Number of guaranteed r1bios in case of extreme VM load: */ @@ -66,9 +74,11 @@ */ static int max_queued_requests = 1024; -static void allow_barrier(struct r1conf *conf, sector_t start_next_window, - sector_t bi_sector); -static void lower_barrier(struct r1conf *conf); +static void allow_barrier(struct r1conf *conf, sector_t sector_nr); +static void lower_barrier(struct r1conf *conf, sector_t sector_nr); + +#define raid1_log(md, fmt, args...) \ + do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0) static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data) { @@ -92,7 +102,6 @@ static void r1bio_pool_free(void *r1_bio, void *data) #define RESYNC_WINDOW_SECTORS (RESYNC_WINDOW >> 9) #define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW) #define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9) -#define NEXT_NORMALIO_DISTANCE (3 * RESYNC_WINDOW_SECTORS) static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) { @@ -197,6 +206,7 @@ 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++) { @@ -207,7 +217,7 @@ static void put_buf(struct r1bio *r1_bio) mempool_free(r1_bio, conf->r1buf_pool); - lower_barrier(conf); + lower_barrier(conf, sect); } static void reschedule_retry(struct r1bio *r1_bio) @@ -215,10 +225,12 @@ 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); @@ -235,7 +247,6 @@ 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; - sector_t start_next_window = r1_bio->start_next_window; sector_t bi_sector = bio->bi_iter.bi_sector; if (bio->bi_phys_segments) { @@ -261,7 +272,7 @@ static void call_bio_endio(struct r1bio *r1_bio) * Wake up any possible resync thread that waits for the device * to go idle. */ - allow_barrier(conf, start_next_window, bi_sector); + allow_barrier(conf, bi_sector); } } @@ -325,6 +336,11 @@ static void raid1_end_read_request(struct bio *bio) if (uptodate) set_bit(R1BIO_Uptodate, &r1_bio->state); + 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 all other devices have failed, we want to return * the error upwards rather than fail the last device. @@ -347,13 +363,10 @@ static void raid1_end_read_request(struct bio *bio) * oops, read error: */ char b[BDEVNAME_SIZE]; - printk_ratelimited( - KERN_ERR "md/raid1:%s: %s: " - "rescheduling sector %llu\n", - mdname(conf->mddev), - bdevname(rdev->bdev, - b), - (unsigned long long)r1_bio->sector); + pr_err_ratelimited("md/raid1:%s: %s: rescheduling sector %llu\n", + mdname(conf->mddev), + bdevname(rdev->bdev, b), + (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 */ @@ -416,7 +429,24 @@ static void raid1_end_write_request(struct bio *bio) 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); + if (!test_bit(Faulty, &rdev->flags)) + /* This is the only remaining device, + * We need to retry the write without + * FailFast + */ + set_bit(R1BIO_WriteError, &r1_bio->state); + else { + /* Finished with this branch */ + r1_bio->bios[mirror] = NULL; + to_put = bio; + } + } else + set_bit(R1BIO_WriteError, &r1_bio->state); } else { /* * Set R1BIO_Uptodate in our master bio, so that we @@ -490,6 +520,25 @@ static void raid1_end_write_request(struct bio *bio) bio_put(to_put); } +static sector_t align_to_barrier_unit_end(sector_t start_sector, + sector_t sectors) +{ + sector_t len; + + WARN_ON(sectors == 0); + /* + * len is the number of sectors from start_sector to end of the + * barrier unit which start_sector belongs to. + */ + len = round_up(start_sector + 1, BARRIER_UNIT_SECTOR_SIZE) - + start_sector; + + if (len > sectors) + len = sectors; + + return len; +} + /* * This routine returns the disk from which the requested read should * be done. There is a per-array 'next expected sequential IO' sector @@ -534,6 +583,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect best_good_sectors = 0; has_nonrot_disk = 0; choose_next_idle = 0; + clear_bit(R1BIO_FailFast, &r1_bio->state); if ((conf->mddev->recovery_cp < this_sector + sectors) || (mddev_is_clustered(conf->mddev) && @@ -607,6 +657,10 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect } else best_good_sectors = sectors; + if (best_disk >= 0) + /* At least two disks to choose from so failfast is OK */ + set_bit(R1BIO_FailFast, &r1_bio->state); + nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev)); has_nonrot_disk |= nonrot; pending = atomic_read(&rdev->nr_pending); @@ -645,11 +699,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect } break; } - /* If device is idle, use it */ - if (pending == 0) { - best_disk = disk; - break; - } if (choose_next_idle) continue; @@ -672,7 +721,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect * mixed ratation/non-rotational disks depending on workload. */ if (best_disk == -1) { - if (has_nonrot_disk) + if (has_nonrot_disk || min_pending == 0) best_disk = best_pending_disk; else best_disk = best_dist_disk; @@ -717,9 +766,9 @@ static int raid1_congested(struct mddev *mddev, int bits) * non-congested targets, it can be removed */ if ((bits & (1 << WB_async_congested)) || 1) - ret |= bdi_congested(&q->backing_dev_info, bits); + ret |= bdi_congested(q->backing_dev_info, bits); else - ret &= bdi_congested(&q->backing_dev_info, bits); + ret &= bdi_congested(q->backing_dev_info, bits); } } rcu_read_unlock(); @@ -745,9 +794,14 @@ static void flush_pending_writes(struct r1conf *conf) while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; + struct md_rdev *rdev = (void*)bio->bi_bdev; bio->bi_next = NULL; - if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) + bio->bi_bdev = rdev->bdev; + if (test_bit(Faulty, &rdev->flags)) { + bio->bi_error = -EIO; + bio_endio(bio); + } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && + !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) /* Just ignore it */ bio_endio(bio); else @@ -781,166 +835,228 @@ static void flush_pending_writes(struct r1conf *conf) */ static void 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++; - conf->next_resync = sector_nr; + 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 barrier >= RESYNC_DEPTH, meaning resync reach - * the max count which allowed. - * C: next_resync + RESYNC_SECTORS > start_next_window, meaning - * next resync will reach to the window which normal bios are - * handling. - * D: while there are any active requests in the current window. + * 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->array_frozen && - conf->barrier < RESYNC_DEPTH && - conf->current_window_requests == 0 && - (conf->start_next_window >= - conf->next_resync + RESYNC_SECTORS), + !atomic_read(&conf->nr_pending[idx]) && + atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH, conf->resync_lock); - conf->nr_pending++; + atomic_inc(&conf->nr_pending[idx]); spin_unlock_irq(&conf->resync_lock); } -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--; - conf->nr_pending--; - 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_pending[idx]); wake_up(&conf->wait_barrier); } -static bool need_to_wait_for_sync(struct r1conf *conf, struct bio *bio) +static void _wait_barrier(struct r1conf *conf, int idx) { - bool wait = false; + /* + * 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(); - if (conf->array_frozen || !bio) - wait = true; - else if (conf->barrier && bio_data_dir(bio) == WRITE) { - if ((conf->mddev->curr_resync_completed - >= bio_end_sector(bio)) || - (conf->next_resync + NEXT_NORMALIO_DISTANCE - <= bio->bi_iter.bi_sector)) - wait = false; - else - wait = true; - } + /* + * 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; - return wait; + /* + * 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); + 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(&conf->wait_barrier); + /* Wait for the barrier in same barrier unit bucket to drop. */ + wait_event_lock_irq(conf->wait_barrier, + !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); } -static sector_t wait_barrier(struct r1conf *conf, struct bio *bio) +static void wait_read_barrier(struct r1conf *conf, sector_t sector_nr) { - sector_t sector = 0; + int idx = sector_to_idx(sector_nr); - spin_lock_irq(&conf->resync_lock); - if (need_to_wait_for_sync(conf, bio)) { - conf->nr_waiting++; - /* Wait for the barrier to drop. - * However if there are already pending - * requests (preventing the barrier from - * rising completely), and the - * per-process bio queue isn't empty, - * then don't wait, as we need to empty - * that queue to allow conf->start_next_window - * to increase. - */ - wait_event_lock_irq(conf->wait_barrier, - !conf->array_frozen && - (!conf->barrier || - ((conf->start_next_window < - conf->next_resync + RESYNC_SECTORS) && - current->bio_list && - !bio_list_empty(current->bio_list))), - conf->resync_lock); - conf->nr_waiting--; - } - - if (bio && bio_data_dir(bio) == WRITE) { - if (bio->bi_iter.bi_sector >= conf->next_resync) { - if (conf->start_next_window == MaxSector) - conf->start_next_window = - conf->next_resync + - NEXT_NORMALIO_DISTANCE; - - if ((conf->start_next_window + NEXT_NORMALIO_DISTANCE) - <= bio->bi_iter.bi_sector) - conf->next_window_requests++; - else - conf->current_window_requests++; - sector = conf->start_next_window; - } - } + /* + * 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]); - conf->nr_pending++; + if (!READ_ONCE(conf->array_frozen)) + return; + + 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(&conf->wait_barrier); + /* Wait for array to be unfrozen */ + 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 sector; } -static void allow_barrier(struct r1conf *conf, sector_t start_next_window, - sector_t bi_sector) +static void wait_barrier(struct r1conf *conf, sector_t sector_nr) { - unsigned long flags; + int idx = sector_to_idx(sector_nr); - spin_lock_irqsave(&conf->resync_lock, flags); - conf->nr_pending--; - if (start_next_window) { - if (start_next_window == conf->start_next_window) { - if (conf->start_next_window + NEXT_NORMALIO_DISTANCE - <= bi_sector) - conf->next_window_requests--; - else - conf->current_window_requests--; - } else - conf->current_window_requests--; - - if (!conf->current_window_requests) { - if (conf->next_window_requests) { - conf->current_window_requests = - conf->next_window_requests; - conf->next_window_requests = 0; - conf->start_next_window += - NEXT_NORMALIO_DISTANCE; - } else - conf->start_next_window = MaxSector; - } - } - spin_unlock_irqrestore(&conf->resync_lock, flags); + _wait_barrier(conf, idx); +} + +static void wait_all_barriers(struct r1conf *conf) +{ + int idx; + + for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++) + _wait_barrier(conf, idx); +} + +static void _allow_barrier(struct r1conf *conf, int idx) +{ + atomic_dec(&conf->nr_pending[idx]); wake_up(&conf->wait_barrier); } +static void allow_barrier(struct r1conf *conf, sector_t sector_nr) +{ + int idx = sector_to_idx(sector_nr); + + _allow_barrier(conf, idx); +} + +static void allow_all_barriers(struct r1conf *conf) +{ + int idx; + + for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++) + _allow_barrier(conf, idx); +} + +/* conf->resync_lock should be held */ +static int get_unqueued_pending(struct r1conf *conf) +{ + int idx, ret; + + for (ret = 0, 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 + /* Stop sync I/O and normal I/O and wait for everything to * go quite. - * We 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. + * 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->array_frozen = 1; - wait_event_lock_irq_cmd(conf->wait_barrier, - conf->nr_pending == conf->nr_queued+extra, - conf->resync_lock, - flush_pending_writes(conf)); + raid1_log(conf->mddev, "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) @@ -948,8 +1064,8 @@ static void unfreeze_array(struct r1conf *conf) /* reverse the effect of the freeze */ spin_lock_irq(&conf->resync_lock); conf->array_frozen = 0; - wake_up(&conf->wait_barrier); spin_unlock_irq(&conf->resync_lock); + wake_up(&conf->wait_barrier); } /* duplicate the data pages for behind I/O @@ -1019,9 +1135,14 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; + struct md_rdev *rdev = (void*)bio->bi_bdev; bio->bi_next = NULL; - if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) + bio->bi_bdev = rdev->bdev; + if (test_bit(Faulty, &rdev->flags)) { + bio->bi_error = -EIO; + bio_endio(bio); + } else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && + !blk_queue_discard(bdev_get_queue(bio->bi_bdev)))) /* Just ignore it */ bio_endio(bio); else @@ -1031,27 +1152,143 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) kfree(plug); } -static void raid1_make_request(struct mddev *mddev, struct bio * bio) +static inline struct r1bio * +alloc_r1bio(struct mddev *mddev, struct bio *bio, sector_t sectors_handled) +{ + struct r1conf *conf = mddev->private; + struct r1bio *r1_bio; + + 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_iter.bi_sector + sectors_handled; + + return r1_bio; +} + +static void raid1_read_request(struct mddev *mddev, struct bio *bio) { struct r1conf *conf = mddev->private; struct raid1_info *mirror; struct r1bio *r1_bio; struct bio *read_bio; - int i, disks; - struct bitmap *bitmap; - unsigned long flags; + struct bitmap *bitmap = mddev->bitmap; const int op = bio_op(bio); - const int rw = bio_data_dir(bio); const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); - const unsigned long do_flush_fua = (bio->bi_opf & - (REQ_PREFLUSH | REQ_FUA)); + int sectors_handled; + int max_sectors; + int rdisk; + + /* + * Still need barrier for READ in case that whole + * array is frozen. + */ + wait_read_barrier(conf, bio->bi_iter.bi_sector); + + r1_bio = alloc_r1bio(mddev, bio, 0); + + /* + * 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; + bio_clear_flag(bio, BIO_SEG_VALID); + + /* + * make_request() can abort the operation when read-ahead is being + * used and no empty request is available. + */ +read_again: + rdisk = read_balance(conf, r1_bio, &max_sectors); + + if (rdisk < 0) { + /* couldn't find anywhere to read from */ + raid_end_bio_io(r1_bio); + return; + } + 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' + */ + raid1_log(mddev, "wait behind writes"); + wait_event(bitmap->behind_wait, + atomic_read(&bitmap->behind_writes) == 0); + } + r1_bio->read_disk = rdisk; + + read_bio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set); + bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector, + max_sectors); + + r1_bio->bios[rdisk] = read_bio; + + read_bio->bi_iter.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; + bio_set_op_attrs(read_bio, op, do_sync); + 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; + + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev), + read_bio, disk_devt(mddev->gendisk), + r1_bio->sector); + + if (max_sectors < r1_bio->sectors) { + /* + * could not read all from this device, so we will need another + * r1_bio. + */ + sectors_handled = (r1_bio->sector + max_sectors + - bio->bi_iter.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); + + r1_bio = alloc_r1bio(mddev, bio, sectors_handled); + goto read_again; + } else + generic_make_request(read_bio); +} + +static void raid1_write_request(struct mddev *mddev, struct bio *bio) +{ + struct r1conf *conf = mddev->private; + struct r1bio *r1_bio; + int i, disks; + struct bitmap *bitmap = mddev->bitmap; + unsigned long flags; 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; - sector_t start_next_window; /* * Register the new request and wait if the reconstruction @@ -1061,15 +1298,15 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio) md_write_start(mddev, bio); /* wait on superblock update early */ - if (bio_data_dir(bio) == WRITE && - ((bio_end_sector(bio) > mddev->suspend_lo && + if ((bio_end_sector(bio) > mddev->suspend_lo && bio->bi_iter.bi_sector < mddev->suspend_hi) || (mddev_is_clustered(mddev) && md_cluster_ops->area_resyncing(mddev, WRITE, - bio->bi_iter.bi_sector, bio_end_sector(bio))))) { - /* As the suspend_* range is controlled by - * userspace, we want an interruptible - * wait. + bio->bi_iter.bi_sector, bio_end_sector(bio)))) { + + /* + * As the suspend_* range is controlled by userspace, we want + * an interruptible wait. */ DEFINE_WAIT(w); for (;;) { @@ -1080,33 +1317,20 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio) bio->bi_iter.bi_sector >= mddev->suspend_hi || (mddev_is_clustered(mddev) && !md_cluster_ops->area_resyncing(mddev, WRITE, - bio->bi_iter.bi_sector, bio_end_sector(bio)))) + bio->bi_iter.bi_sector, + bio_end_sector(bio)))) break; schedule(); } finish_wait(&conf->wait_barrier, &w); } + wait_barrier(conf, bio->bi_iter.bi_sector); - start_next_window = wait_barrier(conf, bio); + r1_bio = alloc_r1bio(mddev, bio, 0); - bitmap = mddev->bitmap; - - /* - * 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); - - 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; - - /* We might need to issue multiple reads to different + /* We might need to issue multiple writes to different * devices if there are bad blocks around, so we keep - * track of the number of reads in bio->bi_phys_segments. + * track of the number of writes 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. @@ -1114,87 +1338,9 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio) bio->bi_phys_segments = 0; bio_clear_flag(bio, BIO_SEG_VALID); - if (rw == READ) { - /* - * read balancing logic: - */ - int rdisk; - -read_again: - rdisk = read_balance(conf, r1_bio, &max_sectors); - - if (rdisk < 0) { - /* couldn't find anywhere to read from */ - raid_end_bio_io(r1_bio); - return; - } - 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->start_next_window = 0; - - read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev); - bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector, - max_sectors); - - r1_bio->bios[rdisk] = read_bio; - - read_bio->bi_iter.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; - bio_set_op_attrs(read_bio, op, do_sync); - read_bio->bi_private = r1_bio; - - if (max_sectors < r1_bio->sectors) { - /* could not read all from this device, so we will - * need another r1_bio. - */ - - sectors_handled = (r1_bio->sector + max_sectors - - bio->bi_iter.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); - - 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_iter.bi_sector + - sectors_handled; - goto read_again; - } else - generic_make_request(read_bio); - return; - } - - /* - * WRITE: - */ if (conf->pending_count >= max_queued_requests) { md_wakeup_thread(mddev->thread); + raid1_log(mddev, "wait queued"); wait_event(conf->wait_barrier, conf->pending_count < max_queued_requests); } @@ -1211,7 +1357,6 @@ read_again: disks = conf->raid_disks * 2; retry_write: - r1_bio->start_next_window = start_next_window; blocked_rdev = NULL; rcu_read_lock(); max_sectors = r1_bio->sectors; @@ -1235,8 +1380,7 @@ read_again: int 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 @@ -1279,24 +1423,15 @@ read_again: if (unlikely(blocked_rdev)) { /* Wait for this device to become unblocked */ int j; - sector_t old = start_next_window; 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, start_next_window, bio->bi_iter.bi_sector); + allow_barrier(conf, bio->bi_iter.bi_sector); + raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk); md_wait_for_blocked_rdev(blocked_rdev, mddev); - start_next_window = wait_barrier(conf, bio); - /* - * We must make sure the multi r1bios of bio have - * the same value of bi_phys_segments - */ - if (bio->bi_phys_segments && old && - old != start_next_window) - /* Wait for the former r1bio(s) to complete */ - wait_event(conf->wait_barrier, - bio->bi_phys_segments == 1); + wait_barrier(conf, bio->bi_iter.bi_sector); goto retry_write; } @@ -1319,12 +1454,12 @@ read_again: first_clone = 1; for (i = 0; i < disks; i++) { - struct bio *mbio; + struct bio *mbio = NULL; + sector_t offset; if (!r1_bio->bios[i]) continue; - mbio = bio_clone_mddev(bio, GFP_NOIO, mddev); - bio_trim(mbio, r1_bio->sector - bio->bi_iter.bi_sector, max_sectors); + offset = r1_bio->sector - bio->bi_iter.bi_sector; if (first_clone) { /* do behind I/O ? @@ -1334,8 +1469,13 @@ read_again: if (bitmap && (atomic_read(&bitmap->behind_writes) < mddev->bitmap_info.max_write_behind) && - !waitqueue_active(&bitmap->behind_wait)) + !waitqueue_active(&bitmap->behind_wait)) { + mbio = bio_clone_bioset_partial(bio, GFP_NOIO, + mddev->bio_set, + offset << 9, + max_sectors << 9); alloc_behind_pages(mbio, r1_bio); + } bitmap_startwrite(bitmap, r1_bio->sector, r1_bio->sectors, @@ -1343,6 +1483,19 @@ read_again: &r1_bio->state)); first_clone = 0; } + + if (!mbio) { + if (r1_bio->behind_bvecs) + mbio = bio_clone_bioset_partial(bio, GFP_NOIO, + mddev->bio_set, + offset << 9, + max_sectors << 9); + else { + mbio = bio_clone_fast(bio, GFP_NOIO, mddev->bio_set); + bio_trim(mbio, offset, max_sectors); + } + } + if (r1_bio->behind_bvecs) { struct bio_vec *bvec; int j; @@ -1362,11 +1515,22 @@ read_again: conf->mirrors[i].rdev->data_offset); mbio->bi_bdev = conf->mirrors[i].rdev->bdev; mbio->bi_end_io = raid1_end_write_request; - bio_set_op_attrs(mbio, op, do_flush_fua | do_sync); + mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA)); + if (test_bit(FailFast, &conf->mirrors[i].rdev->flags) && + !test_bit(WriteMostly, &conf->mirrors[i].rdev->flags) && + conf->raid_disks - mddev->degraded > 1) + mbio->bi_opf |= MD_FAILFAST; mbio->bi_private = r1_bio; atomic_inc(&r1_bio->remaining); + if (mddev->gendisk) + trace_block_bio_remap(bdev_get_queue(mbio->bi_bdev), + mbio, disk_devt(mddev->gendisk), + r1_bio->sector); + /* flush_pending_writes() needs access to the rdev so...*/ + mbio->bi_bdev = (void*)conf->mirrors[i].rdev; + cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug)); if (cb) plug = container_of(cb, struct raid1_plug_cb, cb); @@ -1392,12 +1556,7 @@ read_again: /* 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_iter.bi_sector + sectors_handled; + r1_bio = alloc_r1bio(mddev, bio, sectors_handled); goto retry_write; } @@ -1407,6 +1566,34 @@ read_again: wake_up(&conf->wait_barrier); } +static void raid1_make_request(struct mddev *mddev, struct bio *bio) +{ + struct bio *split; + sector_t sectors; + + if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { + md_flush_request(mddev, bio); + return; + } + + /* if bio exceeds barrier unit boundary, split it */ + do { + sectors = align_to_barrier_unit_end( + bio->bi_iter.bi_sector, bio_sectors(bio)); + if (sectors < bio_sectors(bio)) { + split = bio_split(bio, sectors, GFP_NOIO, fs_bio_set); + bio_chain(split, bio); + } else { + split = bio; + } + + if (bio_data_dir(split) == READ) + raid1_read_request(mddev, split); + else + raid1_write_request(mddev, split); + } while (split != bio); +} + static void raid1_status(struct seq_file *seq, struct mddev *mddev) { struct r1conf *conf = mddev->private; @@ -1436,6 +1623,7 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev) * next level up know. * else mark the drive as failed */ + spin_lock_irqsave(&conf->device_lock, flags); if (test_bit(In_sync, &rdev->flags) && (conf->raid_disks - mddev->degraded) == 1) { /* @@ -1445,10 +1633,10 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev) * it is very likely to fail. */ conf->recovery_disabled = mddev->recovery_disabled; + spin_unlock_irqrestore(&conf->device_lock, flags); return; } set_bit(Blocked, &rdev->flags); - spin_lock_irqsave(&conf->device_lock, flags); if (test_and_clear_bit(In_sync, &rdev->flags)) { mddev->degraded++; set_bit(Faulty, &rdev->flags); @@ -1459,55 +1647,46 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev) * if recovery is running, make sure it aborts. */ set_bit(MD_RECOVERY_INTR, &mddev->recovery); - set_mask_bits(&mddev->flags, 0, - BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING)); - 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_mask_bits(&mddev->sb_flags, 0, + BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING)); + pr_crit("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); } 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(); for (i = 0; i < conf->raid_disks; i++) { char b[BDEVNAME_SIZE]; struct md_rdev *rdev = rcu_dereference(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:%s\n", + i, !test_bit(In_sync, &rdev->flags), + !test_bit(Faulty, &rdev->flags), + bdevname(rdev->bdev,b)); } rcu_read_unlock(); } static void close_sync(struct r1conf *conf) { - wait_barrier(conf, NULL); - allow_barrier(conf, 0, 0); + wait_all_barriers(conf); + allow_all_barriers(conf); mempool_destroy(conf->r1buf_pool); conf->r1buf_pool = NULL; - - spin_lock_irq(&conf->resync_lock); - conf->next_resync = MaxSector - 2 * NEXT_NORMALIO_DISTANCE; - conf->start_next_window = MaxSector; - conf->current_window_requests += - conf->next_window_requests; - conf->next_window_requests = 0; - spin_unlock_irq(&conf->resync_lock); } static int raid1_spare_active(struct mddev *mddev) @@ -1788,12 +1967,24 @@ static int fix_sync_read_error(struct r1bio *r1_bio) 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)) @@ -1825,11 +2016,10 @@ static int fix_sync_read_error(struct r1bio *r1_bio) * 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: %s: unrecoverable I/O read error for block %llu\n", + mdname(mddev), + bdevname(bio->bi_bdev, b), + (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)) @@ -2013,6 +2203,9 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) continue; bio_set_op_attrs(wbio, REQ_OP_WRITE, 0); + if (test_bit(FailFast, &conf->mirrors[i].rdev->flags)) + wbio->bi_opf |= MD_FAILFAST; + wbio->bi_end_io = end_sync_write; atomic_inc(&r1_bio->remaining); md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio)); @@ -2122,13 +2315,11 @@ static void fix_read_error(struct r1conf *conf, int read_disk, if (r1_sync_page_io(rdev, sect, s, conf->tmppage, 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 %s)\n", + mdname(mddev), s, + (unsigned long long)(sect + + rdev->data_offset), + bdevname(rdev->bdev, b)); } rdev_dec_pending(rdev, mddev); } else @@ -2192,7 +2383,8 @@ static int narrow_write_error(struct r1bio *r1_bio, int i) wbio->bi_vcnt = vcnt; } else { - wbio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev); + wbio = bio_clone_fast(r1_bio->master_bio, GFP_NOIO, + mddev->bio_set); } bio_set_op_attrs(wbio, REQ_OP_WRITE, 0); @@ -2242,8 +2434,9 @@ 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; @@ -2269,8 +2462,14 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) if (fail) { spin_lock_irq(&conf->device_lock); list_add(&r1_bio->retry_list, &conf->bio_end_io_list); - conf->nr_queued++; + 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)) @@ -2287,6 +2486,8 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio) struct bio *bio; char b[BDEVNAME_SIZE]; struct md_rdev *rdev; + dev_t bio_dev; + sector_t bio_sector; clear_bit(R1BIO_ReadError, &r1_bio->state); /* we got a read error. Maybe the drive is bad. Maybe just @@ -2300,10 +2501,14 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio) bio = r1_bio->bios[r1_bio->read_disk]; bdevname(bio->bi_bdev, b); + bio_dev = bio->bi_bdev->bd_dev; + bio_sector = conf->mirrors[r1_bio->read_disk].rdev->data_offset + r1_bio->sector; bio_put(bio); r1_bio->bios[r1_bio->read_disk] = NULL; - if (mddev->ro == 0) { + 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->read_disk, r1_bio->sector, r1_bio->sectors); @@ -2312,34 +2517,35 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio) r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED; } - rdev_dec_pending(conf->mirrors[r1_bio->read_disk].rdev, conf->mddev); + rdev_dec_pending(rdev, conf->mddev); 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); + pr_crit_ratelimited("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_opf & REQ_SYNC; r1_bio->read_disk = disk; - bio = bio_clone_mddev(r1_bio->master_bio, GFP_NOIO, mddev); + bio = bio_clone_fast(r1_bio->master_bio, GFP_NOIO, + mddev->bio_set); bio_trim(bio, r1_bio->sector - bio->bi_iter.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)); + pr_info_ratelimited("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_iter.bi_sector = r1_bio->sector + rdev->data_offset; bio->bi_bdev = rdev->bdev; bio->bi_end_io = raid1_end_read_request; bio_set_op_attrs(bio, REQ_OP_READ, do_sync); + if (test_bit(FailFast, &rdev->flags) && + test_bit(R1BIO_FailFast, &r1_bio->state)) + bio->bi_opf |= MD_FAILFAST; bio->bi_private = r1_bio; if (max_sectors < r1_bio->sectors) { /* Drat - have to split this up more */ @@ -2353,22 +2559,20 @@ read_more: else mbio->bi_phys_segments++; spin_unlock_irq(&conf->device_lock); + trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), + bio, bio_dev, bio_sector); generic_make_request(bio); bio = NULL; - r1_bio = mempool_alloc(conf->r1bio_pool, GFP_NOIO); - - r1_bio->master_bio = mbio; - r1_bio->sectors = bio_sectors(mbio) - sectors_handled; - r1_bio->state = 0; + r1_bio = alloc_r1bio(mddev, mbio, sectors_handled); set_bit(R1BIO_ReadError, &r1_bio->state); - r1_bio->mddev = mddev; - r1_bio->sector = mbio->bi_iter.bi_sector + - sectors_handled; goto read_more; - } else + } else { + trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), + bio, bio_dev, bio_sector); generic_make_request(bio); + } } } @@ -2380,24 +2584,23 @@ 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_CHANGE_PENDING, &mddev->flags)) { + !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) { LIST_HEAD(tmp); spin_lock_irqsave(&conf->device_lock, flags); - if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) { - while (!list_empty(&conf->bio_end_io_list)) { - list_move(conf->bio_end_io_list.prev, &tmp); - conf->nr_queued--; - } - } + 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 (mddev->degraded) set_bit(R1BIO_Degraded, &r1_bio->state); if (test_bit(R1BIO_WriteError, &r1_bio->state)) @@ -2418,7 +2621,8 @@ 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; @@ -2441,7 +2645,7 @@ static void raid1d(struct md_thread *thread) generic_make_request(r1_bio->bios[r1_bio->read_disk]); 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); @@ -2457,7 +2661,6 @@ static int init_resync(struct r1conf *conf) conf->poolinfo); if (!conf->r1buf_pool) return -ENOMEM; - conf->next_resync = 0; return 0; } @@ -2486,6 +2689,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, int still_degraded = 0; 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); if (!conf->r1buf_pool) if (init_resync(conf)) @@ -2535,7 +2739,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, * If there is non-resync activity waiting for a turn, then let it * though before starting on this new sync request. */ - if (conf->nr_waiting) + if (atomic_read(&conf->nr_waiting[idx])) schedule_timeout_uninterruptible(1); /* we are incrementing sector_nr below. To be safe, we check against @@ -2562,6 +2766,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, 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; @@ -2623,6 +2829,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, bio->bi_iter.bi_sector = sector_nr + rdev->data_offset; bio->bi_bdev = rdev->bdev; bio->bi_private = r1_bio; + if (test_bit(FailFast, &rdev->flags)) + bio->bi_opf |= MD_FAILFAST; } } rcu_read_unlock(); @@ -2642,7 +2850,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, 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); @@ -2753,6 +2961,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, if (bio->bi_end_io == end_sync_read) { read_targets--; md_sync_acct(bio->bi_bdev, nr_sectors); + if (read_targets == 1) + bio->bi_opf &= ~MD_FAILFAST; generic_make_request(bio); } } @@ -2760,6 +2970,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr, atomic_set(&r1_bio->remaining, 1); bio = r1_bio->bios[r1_bio->read_disk]; md_sync_acct(bio->bi_bdev, nr_sectors); + if (read_targets == 1) + bio->bi_opf &= ~MD_FAILFAST; generic_make_request(bio); } @@ -2786,6 +2998,26 @@ static struct r1conf *setup_conf(struct mddev *mddev) if (!conf) goto abort; + 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(sizeof(struct raid1_info) * mddev->raid_disks * 2, GFP_KERNEL); @@ -2841,9 +3073,6 @@ static struct r1conf *setup_conf(struct mddev *mddev) conf->pending_count = 0; conf->recovery_disabled = mddev->recovery_disabled - 1; - conf->start_next_window = MaxSector; - conf->current_window_requests = conf->next_window_requests = 0; - err = -EIO; for (i = 0; i < conf->raid_disks * 2; i++) { @@ -2875,12 +3104,8 @@ 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)); + if (!conf->thread) goto abort; - } return conf; @@ -2890,6 +3115,10 @@ static struct r1conf *setup_conf(struct mddev *mddev) 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); kfree(conf); } return ERR_PTR(err); @@ -2905,13 +3134,13 @@ static int raid1_run(struct mddev *mddev) 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; } /* @@ -2950,11 +3179,9 @@ static int raid1_run(struct mddev *mddev) 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", + 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); @@ -2964,6 +3191,7 @@ static int raid1_run(struct mddev *mddev) mddev->thread = conf->thread; conf->thread = NULL; mddev->private = conf; + set_bit(MD_FAILFAST_SUPPORTED, &mddev->flags); md_set_array_sectors(mddev, raid1_size(mddev, 0, 0)); @@ -2992,6 +3220,10 @@ static void raid1_free(struct mddev *mddev, void *priv) 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); kfree(conf); } @@ -3107,9 +3339,8 @@ 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; @@ -3163,9 +3394,12 @@ static void *raid1_takeover(struct mddev *mddev) mddev->new_layout = 0; mddev->new_chunk_sectors = 0; conf = setup_conf(mddev); - if (!IS_ERR(conf)) + 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); |