/*
* Copyright (C) 2015 Shaohua Li <shli@fb.com>
+ * Copyright (C) 2016 Song Liu <songliubraving@fb.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
#include <linux/raid/md_p.h>
#include <linux/crc32c.h>
#include <linux/random.h>
+#include <linux/kthread.h>
#include "md.h"
#include "raid5.h"
#include "bitmap.h"
/*
* raid5 cache state machine
*
- * With rhe RAID cache, each stripe works in two phases:
+ * With the RAID cache, each stripe works in two phases:
* - caching phase
* - writing-out phase
*
u64 seq; /* log head sequence */
sector_t next_checkpoint;
- u64 next_cp_seq;
struct mutex io_mutex;
struct r5l_io_unit *current_io; /* current io_unit accepting new data */
spinlock_t stripe_in_journal_lock;
atomic_t stripe_in_journal_count;
+
+ /* to submit async io_units, to fulfill ordering of flush */
+ struct work_struct deferred_io_work;
};
/*
int state;
bool need_split_bio;
+ struct bio *split_bio;
+
+ unsigned int has_flush:1; /* include flush request */
+ unsigned int has_fua:1; /* include fua request */
+ unsigned int has_null_flush:1; /* include empty flush request */
+ /*
+ * io isn't sent yet, flush/fua request can only be submitted till it's
+ * the first IO in running_ios list
+ */
+ unsigned int io_deferred:1;
+
+ struct bio_list flush_barriers; /* size == 0 flush bios */
};
/* r5l_io_unit state */
}
}
+static void __r5l_stripe_write_finished(struct r5l_io_unit *io);
static void r5l_log_endio(struct bio *bio)
{
struct r5l_io_unit *io = bio->bi_private;
+ struct r5l_io_unit *io_deferred;
struct r5l_log *log = io->log;
unsigned long flags;
r5l_move_to_end_ios(log);
else
r5l_log_run_stripes(log);
+ if (!list_empty(&log->running_ios)) {
+ /*
+ * FLUSH/FUA io_unit is deferred because of ordering, now we
+ * can dispatch it
+ */
+ io_deferred = list_first_entry(&log->running_ios,
+ struct r5l_io_unit, log_sibling);
+ if (io_deferred->io_deferred)
+ schedule_work(&log->deferred_io_work);
+ }
+
spin_unlock_irqrestore(&log->io_list_lock, flags);
if (log->need_cache_flush)
md_wakeup_thread(log->rdev->mddev->thread);
+
+ if (io->has_null_flush) {
+ struct bio *bi;
+
+ WARN_ON(bio_list_empty(&io->flush_barriers));
+ while ((bi = bio_list_pop(&io->flush_barriers)) != NULL) {
+ bio_endio(bi);
+ atomic_dec(&io->pending_stripe);
+ }
+ if (atomic_read(&io->pending_stripe) == 0)
+ __r5l_stripe_write_finished(io);
+ }
+}
+
+static void r5l_do_submit_io(struct r5l_log *log, struct r5l_io_unit *io)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&log->io_list_lock, flags);
+ __r5l_set_io_unit_state(io, IO_UNIT_IO_START);
+ spin_unlock_irqrestore(&log->io_list_lock, flags);
+
+ if (io->has_flush)
+ bio_set_op_attrs(io->current_bio, REQ_OP_WRITE, WRITE_FLUSH);
+ if (io->has_fua)
+ bio_set_op_attrs(io->current_bio, REQ_OP_WRITE, WRITE_FUA);
+ submit_bio(io->current_bio);
+
+ if (!io->split_bio)
+ return;
+
+ if (io->has_flush)
+ bio_set_op_attrs(io->split_bio, REQ_OP_WRITE, WRITE_FLUSH);
+ if (io->has_fua)
+ bio_set_op_attrs(io->split_bio, REQ_OP_WRITE, WRITE_FUA);
+ submit_bio(io->split_bio);
+}
+
+/* deferred io_unit will be dispatched here */
+static void r5l_submit_io_async(struct work_struct *work)
+{
+ struct r5l_log *log = container_of(work, struct r5l_log,
+ deferred_io_work);
+ struct r5l_io_unit *io = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&log->io_list_lock, flags);
+ if (!list_empty(&log->running_ios)) {
+ io = list_first_entry(&log->running_ios, struct r5l_io_unit,
+ log_sibling);
+ if (!io->io_deferred)
+ io = NULL;
+ else
+ io->io_deferred = 0;
+ }
+ spin_unlock_irqrestore(&log->io_list_lock, flags);
+ if (io)
+ r5l_do_submit_io(log, io);
}
static void r5l_submit_current_io(struct r5l_log *log)
{
struct r5l_io_unit *io = log->current_io;
+ struct bio *bio;
struct r5l_meta_block *block;
unsigned long flags;
u32 crc;
+ bool do_submit = true;
if (!io)
return;
block->meta_size = cpu_to_le32(io->meta_offset);
crc = crc32c_le(log->uuid_checksum, block, PAGE_SIZE);
block->checksum = cpu_to_le32(crc);
+ bio = io->current_bio;
log->current_io = NULL;
spin_lock_irqsave(&log->io_list_lock, flags);
- __r5l_set_io_unit_state(io, IO_UNIT_IO_START);
+ if (io->has_flush || io->has_fua) {
+ if (io != list_first_entry(&log->running_ios,
+ struct r5l_io_unit, log_sibling)) {
+ io->io_deferred = 1;
+ do_submit = false;
+ }
+ }
spin_unlock_irqrestore(&log->io_list_lock, flags);
-
- submit_bio(io->current_bio);
+ if (do_submit)
+ r5l_do_submit_io(log, io);
}
static struct bio *r5l_bio_alloc(struct r5l_log *log)
io->log = log;
INIT_LIST_HEAD(&io->log_sibling);
INIT_LIST_HEAD(&io->stripe_list);
+ bio_list_init(&io->flush_barriers);
io->state = IO_UNIT_RUNNING;
io->meta_page = mempool_alloc(log->meta_pool, GFP_NOIO);
struct r5l_io_unit *io = log->current_io;
if (io->need_split_bio) {
- struct bio *prev = io->current_bio;
-
+ BUG_ON(io->split_bio);
+ io->split_bio = io->current_bio;
io->current_bio = r5l_bio_alloc(log);
- bio_chain(io->current_bio, prev);
-
- submit_bio(prev);
+ bio_chain(io->current_bio, io->split_bio);
+ io->need_split_bio = false;
}
if (!bio_add_page(io->current_bio, page, PAGE_SIZE, 0))
io = log->current_io;
+ if (test_and_clear_bit(STRIPE_R5C_PREFLUSH, &sh->state))
+ io->has_flush = 1;
+
for (i = 0; i < sh->disks; i++) {
if (!test_bit(R5_Wantwrite, &sh->dev[i].flags) ||
test_bit(R5_InJournal, &sh->dev[i].flags))
continue;
if (i == sh->pd_idx || i == sh->qd_idx)
continue;
+ if (test_bit(R5_WantFUA, &sh->dev[i].flags) &&
+ log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK) {
+ io->has_fua = 1;
+ /*
+ * we need to flush journal to make sure recovery can
+ * reach the data with fua flag
+ */
+ io->has_flush = 1;
+ }
r5l_append_payload_meta(log, R5LOG_PAYLOAD_DATA,
raid5_compute_blocknr(sh, i, 0),
sh->dev[i].log_checksum, 0, false);
{
if (!log)
return -ENODEV;
- /*
- * we flush log disk cache first, then write stripe data to raid disks.
- * So if bio is finished, the log disk cache is flushed already. The
- * recovery guarantees we can recovery the bio from log disk, so we
- * don't need to flush again
- */
- if (bio->bi_iter.bi_size == 0) {
- bio_endio(bio);
- return 0;
+
+ if (log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH) {
+ /*
+ * in write through (journal only)
+ * we flush log disk cache first, then write stripe data to
+ * raid disks. So if bio is finished, the log disk cache is
+ * flushed already. The recovery guarantees we can recovery
+ * the bio from log disk, so we don't need to flush again
+ */
+ if (bio->bi_iter.bi_size == 0) {
+ bio_endio(bio);
+ return 0;
+ }
+ bio->bi_opf &= ~REQ_PREFLUSH;
+ } else {
+ /* write back (with cache) */
+ if (bio->bi_iter.bi_size == 0) {
+ mutex_lock(&log->io_mutex);
+ r5l_get_meta(log, 0);
+ bio_list_add(&log->current_io->flush_barriers, bio);
+ log->current_io->has_flush = 1;
+ log->current_io->has_null_flush = 1;
+ atomic_inc(&log->current_io->pending_stripe);
+ r5l_submit_current_io(log);
+ mutex_unlock(&log->io_mutex);
+ return 0;
+ }
}
- bio->bi_opf &= ~REQ_PREFLUSH;
return -EAGAIN;
}
spin_lock_irqsave(&log->stripe_in_journal_lock, flags);
if (list_empty(&conf->log->stripe_in_journal_list)) {
/* all stripes flushed */
- spin_unlock(&log->stripe_in_journal_lock);
+ spin_unlock_irqrestore(&log->stripe_in_journal_lock, flags);
return log->next_checkpoint;
}
sh = list_first_entry(&conf->log->stripe_in_journal_list,
break;
log->next_checkpoint = io->log_start;
- log->next_cp_seq = io->seq;
list_del(&io->log_sibling);
mempool_free(io, log->io_pool);
atomic_inc(&conf->active_stripes);
r5c_make_stripe_write_out(sh);
- if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
- atomic_inc(&conf->preread_active_stripes);
raid5_release_stripe(sh);
}
struct mddev *mddev;
if (!log || state == 2)
return;
- if (state == 0) {
- /*
- * This is a special case for hotadd. In suspend, the array has
- * no journal. In resume, journal is initialized as well as the
- * reclaim thread.
- */
- if (log->reclaim_thread)
- return;
- log->reclaim_thread = md_register_thread(r5l_reclaim_thread,
- log->rdev->mddev, "reclaim");
- log->reclaim_thread->timeout = R5C_RECLAIM_WAKEUP_INTERVAL;
- } else if (state == 1) {
+ if (state == 0)
+ kthread_unpark(log->reclaim_thread->tsk);
+ else if (state == 1) {
/* make sure r5l_write_super_and_discard_space exits */
mddev = log->rdev->mddev;
wake_up(&mddev->sb_wait);
+ kthread_park(log->reclaim_thread->tsk);
r5l_wake_reclaim(log, MaxSector);
- md_unregister_thread(&log->reclaim_thread);
r5l_do_reclaim(log);
}
}
sector_t meta_total_blocks; /* total size of current meta and data */
sector_t pos; /* recovery position */
u64 seq; /* recovery position seq */
+ int data_parity_stripes; /* number of data_parity stripes */
+ int data_only_stripes; /* number of data_only stripes */
+ struct list_head cached_list;
};
-static int r5l_read_meta_block(struct r5l_log *log,
- struct r5l_recovery_ctx *ctx)
+static int r5l_recovery_read_meta_block(struct r5l_log *log,
+ struct r5l_recovery_ctx *ctx)
{
struct page *page = ctx->meta_page;
struct r5l_meta_block *mb;
return 0;
}
-static int r5l_recovery_flush_one_stripe(struct r5l_log *log,
- struct r5l_recovery_ctx *ctx,
- sector_t stripe_sect,
- int *offset)
+static void
+r5l_recovery_create_empty_meta_block(struct r5l_log *log,
+ struct page *page,
+ sector_t pos, u64 seq)
{
- struct r5conf *conf = log->rdev->mddev->private;
- struct stripe_head *sh;
- struct r5l_payload_data_parity *payload;
- int disk_index;
+ struct r5l_meta_block *mb;
+ u32 crc;
- sh = raid5_get_active_stripe(conf, stripe_sect, 0, 0, 0);
- while (1) {
- sector_t log_offset = r5l_ring_add(log, ctx->pos,
- ctx->meta_total_blocks);
- payload = page_address(ctx->meta_page) + *offset;
+ mb = page_address(page);
+ clear_page(mb);
+ mb->magic = cpu_to_le32(R5LOG_MAGIC);
+ mb->version = R5LOG_VERSION;
+ mb->meta_size = cpu_to_le32(sizeof(struct r5l_meta_block));
+ mb->seq = cpu_to_le64(seq);
+ mb->position = cpu_to_le64(pos);
+ crc = crc32c_le(log->uuid_checksum, mb, PAGE_SIZE);
+ mb->checksum = cpu_to_le32(crc);
+}
+
+static int r5l_log_write_empty_meta_block(struct r5l_log *log, sector_t pos,
+ u64 seq)
+{
+ struct page *page;
- if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_DATA) {
- raid5_compute_sector(conf,
- le64_to_cpu(payload->location), 0,
- &disk_index, sh);
+ page = alloc_page(GFP_KERNEL);
+ if (!page)
+ return -ENOMEM;
+ r5l_recovery_create_empty_meta_block(log, page, pos, seq);
+ if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, REQ_OP_WRITE,
+ WRITE_FUA, false)) {
+ __free_page(page);
+ return -EIO;
+ }
+ __free_page(page);
+ return 0;
+}
- sync_page_io(log->rdev, log_offset, PAGE_SIZE,
- sh->dev[disk_index].page, REQ_OP_READ, 0,
- false);
- sh->dev[disk_index].log_checksum =
- le32_to_cpu(payload->checksum[0]);
- set_bit(R5_Wantwrite, &sh->dev[disk_index].flags);
- } else {
- disk_index = sh->pd_idx;
- sync_page_io(log->rdev, log_offset, PAGE_SIZE,
- sh->dev[disk_index].page, REQ_OP_READ, 0,
- false);
- sh->dev[disk_index].log_checksum =
- le32_to_cpu(payload->checksum[0]);
- set_bit(R5_Wantwrite, &sh->dev[disk_index].flags);
-
- if (sh->qd_idx >= 0) {
- disk_index = sh->qd_idx;
- sync_page_io(log->rdev,
- r5l_ring_add(log, log_offset, BLOCK_SECTORS),
- PAGE_SIZE, sh->dev[disk_index].page,
- REQ_OP_READ, 0, false);
- sh->dev[disk_index].log_checksum =
- le32_to_cpu(payload->checksum[1]);
- set_bit(R5_Wantwrite,
- &sh->dev[disk_index].flags);
- }
- }
+/*
+ * r5l_recovery_load_data and r5l_recovery_load_parity uses flag R5_Wantwrite
+ * to mark valid (potentially not flushed) data in the journal.
+ *
+ * We already verified checksum in r5l_recovery_verify_data_checksum_for_mb,
+ * so there should not be any mismatch here.
+ */
+static void r5l_recovery_load_data(struct r5l_log *log,
+ struct stripe_head *sh,
+ struct r5l_recovery_ctx *ctx,
+ struct r5l_payload_data_parity *payload,
+ sector_t log_offset)
+{
+ struct mddev *mddev = log->rdev->mddev;
+ struct r5conf *conf = mddev->private;
+ int dd_idx;
- ctx->meta_total_blocks += le32_to_cpu(payload->size);
- *offset += sizeof(struct r5l_payload_data_parity) +
- sizeof(__le32) *
- (le32_to_cpu(payload->size) >> (PAGE_SHIFT - 9));
- if (le16_to_cpu(payload->header.type) == R5LOG_PAYLOAD_PARITY)
- break;
+ raid5_compute_sector(conf,
+ le64_to_cpu(payload->location), 0,
+ &dd_idx, sh);
+ sync_page_io(log->rdev, log_offset, PAGE_SIZE,
+ sh->dev[dd_idx].page, REQ_OP_READ, 0, false);
+ sh->dev[dd_idx].log_checksum =
+ le32_to_cpu(payload->checksum[0]);
+ ctx->meta_total_blocks += BLOCK_SECTORS;
+
+ set_bit(R5_Wantwrite, &sh->dev[dd_idx].flags);
+ set_bit(STRIPE_R5C_CACHING, &sh->state);
+}
+
+static void r5l_recovery_load_parity(struct r5l_log *log,
+ struct stripe_head *sh,
+ struct r5l_recovery_ctx *ctx,
+ struct r5l_payload_data_parity *payload,
+ sector_t log_offset)
+{
+ struct mddev *mddev = log->rdev->mddev;
+ struct r5conf *conf = mddev->private;
+
+ ctx->meta_total_blocks += BLOCK_SECTORS * conf->max_degraded;
+ sync_page_io(log->rdev, log_offset, PAGE_SIZE,
+ sh->dev[sh->pd_idx].page, REQ_OP_READ, 0, false);
+ sh->dev[sh->pd_idx].log_checksum =
+ le32_to_cpu(payload->checksum[0]);
+ set_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags);
+
+ if (sh->qd_idx >= 0) {
+ sync_page_io(log->rdev,
+ r5l_ring_add(log, log_offset, BLOCK_SECTORS),
+ PAGE_SIZE, sh->dev[sh->qd_idx].page,
+ REQ_OP_READ, 0, false);
+ sh->dev[sh->qd_idx].log_checksum =
+ le32_to_cpu(payload->checksum[1]);
+ set_bit(R5_Wantwrite, &sh->dev[sh->qd_idx].flags);
}
+ clear_bit(STRIPE_R5C_CACHING, &sh->state);
+}
- for (disk_index = 0; disk_index < sh->disks; disk_index++) {
- void *addr;
- u32 checksum;
+static void r5l_recovery_reset_stripe(struct stripe_head *sh)
+{
+ int i;
+
+ sh->state = 0;
+ sh->log_start = MaxSector;
+ for (i = sh->disks; i--; )
+ sh->dev[i].flags = 0;
+}
+
+static void
+r5l_recovery_replay_one_stripe(struct r5conf *conf,
+ struct stripe_head *sh,
+ struct r5l_recovery_ctx *ctx)
+{
+ struct md_rdev *rdev, *rrdev;
+ int disk_index;
+ int data_count = 0;
+ for (disk_index = 0; disk_index < sh->disks; disk_index++) {
if (!test_bit(R5_Wantwrite, &sh->dev[disk_index].flags))
continue;
- addr = kmap_atomic(sh->dev[disk_index].page);
- checksum = crc32c_le(log->uuid_checksum, addr, PAGE_SIZE);
- kunmap_atomic(addr);
- if (checksum != sh->dev[disk_index].log_checksum)
- goto error;
+ if (disk_index == sh->qd_idx || disk_index == sh->pd_idx)
+ continue;
+ data_count++;
}
- for (disk_index = 0; disk_index < sh->disks; disk_index++) {
- struct md_rdev *rdev, *rrdev;
+ /*
+ * stripes that only have parity must have been flushed
+ * before the crash that we are now recovering from, so
+ * there is nothing more to recovery.
+ */
+ if (data_count == 0)
+ goto out;
- if (!test_and_clear_bit(R5_Wantwrite,
- &sh->dev[disk_index].flags))
+ for (disk_index = 0; disk_index < sh->disks; disk_index++) {
+ if (!test_bit(R5_Wantwrite, &sh->dev[disk_index].flags))
continue;
/* in case device is broken */
if (rdev) {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
- sync_page_io(rdev, stripe_sect, PAGE_SIZE,
+ sync_page_io(rdev, sh->sector, PAGE_SIZE,
sh->dev[disk_index].page, REQ_OP_WRITE, 0,
false);
rdev_dec_pending(rdev, rdev->mddev);
if (rrdev) {
atomic_inc(&rrdev->nr_pending);
rcu_read_unlock();
- sync_page_io(rrdev, stripe_sect, PAGE_SIZE,
+ sync_page_io(rrdev, sh->sector, PAGE_SIZE,
sh->dev[disk_index].page, REQ_OP_WRITE, 0,
false);
rdev_dec_pending(rrdev, rrdev->mddev);
}
rcu_read_unlock();
}
- raid5_release_stripe(sh);
+ ctx->data_parity_stripes++;
+out:
+ r5l_recovery_reset_stripe(sh);
+}
+
+static struct stripe_head *
+r5c_recovery_alloc_stripe(struct r5conf *conf,
+ sector_t stripe_sect,
+ sector_t log_start)
+{
+ struct stripe_head *sh;
+
+ sh = raid5_get_active_stripe(conf, stripe_sect, 0, 1, 0);
+ if (!sh)
+ return NULL; /* no more stripe available */
+
+ r5l_recovery_reset_stripe(sh);
+ sh->log_start = log_start;
+
+ return sh;
+}
+
+static struct stripe_head *
+r5c_recovery_lookup_stripe(struct list_head *list, sector_t sect)
+{
+ struct stripe_head *sh;
+
+ list_for_each_entry(sh, list, lru)
+ if (sh->sector == sect)
+ return sh;
+ return NULL;
+}
+
+static void
+r5c_recovery_drop_stripes(struct list_head *cached_stripe_list,
+ struct r5l_recovery_ctx *ctx)
+{
+ struct stripe_head *sh, *next;
+
+ list_for_each_entry_safe(sh, next, cached_stripe_list, lru) {
+ r5l_recovery_reset_stripe(sh);
+ list_del_init(&sh->lru);
+ raid5_release_stripe(sh);
+ }
+}
+
+static void
+r5c_recovery_replay_stripes(struct list_head *cached_stripe_list,
+ struct r5l_recovery_ctx *ctx)
+{
+ struct stripe_head *sh, *next;
+
+ list_for_each_entry_safe(sh, next, cached_stripe_list, lru)
+ if (!test_bit(STRIPE_R5C_CACHING, &sh->state)) {
+ r5l_recovery_replay_one_stripe(sh->raid_conf, sh, ctx);
+ list_del_init(&sh->lru);
+ raid5_release_stripe(sh);
+ }
+}
+
+/* if matches return 0; otherwise return -EINVAL */
+static int
+r5l_recovery_verify_data_checksum(struct r5l_log *log, struct page *page,
+ sector_t log_offset, __le32 log_checksum)
+{
+ void *addr;
+ u32 checksum;
+
+ sync_page_io(log->rdev, log_offset, PAGE_SIZE,
+ page, REQ_OP_READ, 0, false);
+ addr = kmap_atomic(page);
+ checksum = crc32c_le(log->uuid_checksum, addr, PAGE_SIZE);
+ kunmap_atomic(addr);
+ return (le32_to_cpu(log_checksum) == checksum) ? 0 : -EINVAL;
+}
+
+/*
+ * before loading data to stripe cache, we need verify checksum for all data,
+ * if there is mismatch for any data page, we drop all data in the mata block
+ */
+static int
+r5l_recovery_verify_data_checksum_for_mb(struct r5l_log *log,
+ struct r5l_recovery_ctx *ctx)
+{
+ struct mddev *mddev = log->rdev->mddev;
+ struct r5conf *conf = mddev->private;
+ struct r5l_meta_block *mb = page_address(ctx->meta_page);
+ sector_t mb_offset = sizeof(struct r5l_meta_block);
+ sector_t log_offset = r5l_ring_add(log, ctx->pos, BLOCK_SECTORS);
+ struct page *page;
+ struct r5l_payload_data_parity *payload;
+
+ page = alloc_page(GFP_KERNEL);
+ if (!page)
+ return -ENOMEM;
+
+ while (mb_offset < le32_to_cpu(mb->meta_size)) {
+ payload = (void *)mb + mb_offset;
+
+ if (payload->header.type == R5LOG_PAYLOAD_DATA) {
+ if (r5l_recovery_verify_data_checksum(
+ log, page, log_offset,
+ payload->checksum[0]) < 0)
+ goto mismatch;
+ } else if (payload->header.type == R5LOG_PAYLOAD_PARITY) {
+ if (r5l_recovery_verify_data_checksum(
+ log, page, log_offset,
+ payload->checksum[0]) < 0)
+ goto mismatch;
+ if (conf->max_degraded == 2 && /* q for RAID 6 */
+ r5l_recovery_verify_data_checksum(
+ log, page,
+ r5l_ring_add(log, log_offset,
+ BLOCK_SECTORS),
+ payload->checksum[1]) < 0)
+ goto mismatch;
+ } else /* not R5LOG_PAYLOAD_DATA or R5LOG_PAYLOAD_PARITY */
+ goto mismatch;
+
+ log_offset = r5l_ring_add(log, log_offset,
+ le32_to_cpu(payload->size));
+
+ mb_offset += sizeof(struct r5l_payload_data_parity) +
+ sizeof(__le32) *
+ (le32_to_cpu(payload->size) >> (PAGE_SHIFT - 9));
+ }
+
+ put_page(page);
return 0;
-error:
- for (disk_index = 0; disk_index < sh->disks; disk_index++)
- sh->dev[disk_index].flags = 0;
- raid5_release_stripe(sh);
+mismatch:
+ put_page(page);
return -EINVAL;
}
-static int r5l_recovery_flush_one_meta(struct r5l_log *log,
- struct r5l_recovery_ctx *ctx)
+/*
+ * Analyze all data/parity pages in one meta block
+ * Returns:
+ * 0 for success
+ * -EINVAL for unknown playload type
+ * -EAGAIN for checksum mismatch of data page
+ * -ENOMEM for run out of memory (alloc_page failed or run out of stripes)
+ */
+static int
+r5c_recovery_analyze_meta_block(struct r5l_log *log,
+ struct r5l_recovery_ctx *ctx,
+ struct list_head *cached_stripe_list)
{
- struct r5conf *conf = log->rdev->mddev->private;
- struct r5l_payload_data_parity *payload;
+ struct mddev *mddev = log->rdev->mddev;
+ struct r5conf *conf = mddev->private;
struct r5l_meta_block *mb;
- int offset;
- sector_t stripe_sector;
+ struct r5l_payload_data_parity *payload;
+ int mb_offset;
+ sector_t log_offset;
+ sector_t stripe_sect;
+ struct stripe_head *sh;
+ int ret;
+
+ /*
+ * for mismatch in data blocks, we will drop all data in this mb, but
+ * we will still read next mb for other data with FLUSH flag, as
+ * io_unit could finish out of order.
+ */
+ ret = r5l_recovery_verify_data_checksum_for_mb(log, ctx);
+ if (ret == -EINVAL)
+ return -EAGAIN;
+ else if (ret)
+ return ret; /* -ENOMEM duo to alloc_page() failed */
mb = page_address(ctx->meta_page);
- offset = sizeof(struct r5l_meta_block);
+ mb_offset = sizeof(struct r5l_meta_block);
+ log_offset = r5l_ring_add(log, ctx->pos, BLOCK_SECTORS);
- while (offset < le32_to_cpu(mb->meta_size)) {
+ while (mb_offset < le32_to_cpu(mb->meta_size)) {
int dd;
- payload = (void *)mb + offset;
- stripe_sector = raid5_compute_sector(conf,
- le64_to_cpu(payload->location), 0, &dd, NULL);
- if (r5l_recovery_flush_one_stripe(log, ctx, stripe_sector,
- &offset))
+ payload = (void *)mb + mb_offset;
+ stripe_sect = (payload->header.type == R5LOG_PAYLOAD_DATA) ?
+ raid5_compute_sector(
+ conf, le64_to_cpu(payload->location), 0, &dd,
+ NULL)
+ : le64_to_cpu(payload->location);
+
+ sh = r5c_recovery_lookup_stripe(cached_stripe_list,
+ stripe_sect);
+
+ if (!sh) {
+ sh = r5c_recovery_alloc_stripe(conf, stripe_sect, ctx->pos);
+ /*
+ * cannot get stripe from raid5_get_active_stripe
+ * try replay some stripes
+ */
+ if (!sh) {
+ r5c_recovery_replay_stripes(
+ cached_stripe_list, ctx);
+ sh = r5c_recovery_alloc_stripe(
+ conf, stripe_sect, ctx->pos);
+ }
+ if (!sh) {
+ pr_debug("md/raid:%s: Increasing stripe cache size to %d to recovery data on journal.\n",
+ mdname(mddev),
+ conf->min_nr_stripes * 2);
+ raid5_set_cache_size(mddev,
+ conf->min_nr_stripes * 2);
+ sh = r5c_recovery_alloc_stripe(
+ conf, stripe_sect, ctx->pos);
+ }
+ if (!sh) {
+ pr_err("md/raid:%s: Cannot get enough stripes due to memory pressure. Recovery failed.\n",
+ mdname(mddev));
+ return -ENOMEM;
+ }
+ list_add_tail(&sh->lru, cached_stripe_list);
+ }
+
+ if (payload->header.type == R5LOG_PAYLOAD_DATA) {
+ if (!test_bit(STRIPE_R5C_CACHING, &sh->state) &&
+ test_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags)) {
+ r5l_recovery_replay_one_stripe(conf, sh, ctx);
+ sh->log_start = ctx->pos;
+ list_move_tail(&sh->lru, cached_stripe_list);
+ }
+ r5l_recovery_load_data(log, sh, ctx, payload,
+ log_offset);
+ } else if (payload->header.type == R5LOG_PAYLOAD_PARITY)
+ r5l_recovery_load_parity(log, sh, ctx, payload,
+ log_offset);
+ else
return -EINVAL;
+
+ log_offset = r5l_ring_add(log, log_offset,
+ le32_to_cpu(payload->size));
+
+ mb_offset += sizeof(struct r5l_payload_data_parity) +
+ sizeof(__le32) *
+ (le32_to_cpu(payload->size) >> (PAGE_SHIFT - 9));
}
+
return 0;
}
-/* copy data/parity from log to raid disks */
-static void r5l_recovery_flush_log(struct r5l_log *log,
- struct r5l_recovery_ctx *ctx)
+/*
+ * Load the stripe into cache. The stripe will be written out later by
+ * the stripe cache state machine.
+ */
+static void r5c_recovery_load_one_stripe(struct r5l_log *log,
+ struct stripe_head *sh)
+{
+ struct r5dev *dev;
+ int i;
+
+ for (i = sh->disks; i--; ) {
+ dev = sh->dev + i;
+ if (test_and_clear_bit(R5_Wantwrite, &dev->flags)) {
+ set_bit(R5_InJournal, &dev->flags);
+ set_bit(R5_UPTODATE, &dev->flags);
+ }
+ }
+ list_add_tail(&sh->r5c, &log->stripe_in_journal_list);
+ atomic_inc(&log->stripe_in_journal_count);
+}
+
+/*
+ * Scan through the log for all to-be-flushed data
+ *
+ * For stripes with data and parity, namely Data-Parity stripe
+ * (STRIPE_R5C_CACHING == 0), we simply replay all the writes.
+ *
+ * For stripes with only data, namely Data-Only stripe
+ * (STRIPE_R5C_CACHING == 1), we load them to stripe cache state machine.
+ *
+ * For a stripe, if we see data after parity, we should discard all previous
+ * data and parity for this stripe, as these data are already flushed to
+ * the array.
+ *
+ * At the end of the scan, we return the new journal_tail, which points to
+ * first data-only stripe on the journal device, or next invalid meta block.
+ */
+static int r5c_recovery_flush_log(struct r5l_log *log,
+ struct r5l_recovery_ctx *ctx)
{
+ struct stripe_head *sh;
+ int ret = 0;
+
+ /* scan through the log */
while (1) {
- if (r5l_read_meta_block(log, ctx))
- return;
- if (r5l_recovery_flush_one_meta(log, ctx))
- return;
+ if (r5l_recovery_read_meta_block(log, ctx))
+ break;
+
+ ret = r5c_recovery_analyze_meta_block(log, ctx,
+ &ctx->cached_list);
+ /*
+ * -EAGAIN means mismatch in data block, in this case, we still
+ * try scan the next metablock
+ */
+ if (ret && ret != -EAGAIN)
+ break; /* ret == -EINVAL or -ENOMEM */
ctx->seq++;
ctx->pos = r5l_ring_add(log, ctx->pos, ctx->meta_total_blocks);
}
+
+ if (ret == -ENOMEM) {
+ r5c_recovery_drop_stripes(&ctx->cached_list, ctx);
+ return ret;
+ }
+
+ /* replay data-parity stripes */
+ r5c_recovery_replay_stripes(&ctx->cached_list, ctx);
+
+ /* load data-only stripes to stripe cache */
+ list_for_each_entry(sh, &ctx->cached_list, lru) {
+ WARN_ON(!test_bit(STRIPE_R5C_CACHING, &sh->state));
+ r5c_recovery_load_one_stripe(log, sh);
+ ctx->data_only_stripes++;
+ }
+
+ return 0;
}
-static int r5l_log_write_empty_meta_block(struct r5l_log *log, sector_t pos,
- u64 seq)
+/*
+ * we did a recovery. Now ctx.pos points to an invalid meta block. New
+ * log will start here. but we can't let superblock point to last valid
+ * meta block. The log might looks like:
+ * | meta 1| meta 2| meta 3|
+ * meta 1 is valid, meta 2 is invalid. meta 3 could be valid. If
+ * superblock points to meta 1, we write a new valid meta 2n. if crash
+ * happens again, new recovery will start from meta 1. Since meta 2n is
+ * valid now, recovery will think meta 3 is valid, which is wrong.
+ * The solution is we create a new meta in meta2 with its seq == meta
+ * 1's seq + 10 and let superblock points to meta2. The same recovery will
+ * not think meta 3 is a valid meta, because its seq doesn't match
+ */
+
+/*
+ * Before recovery, the log looks like the following
+ *
+ * ---------------------------------------------
+ * | valid log | invalid log |
+ * ---------------------------------------------
+ * ^
+ * |- log->last_checkpoint
+ * |- log->last_cp_seq
+ *
+ * Now we scan through the log until we see invalid entry
+ *
+ * ---------------------------------------------
+ * | valid log | invalid log |
+ * ---------------------------------------------
+ * ^ ^
+ * |- log->last_checkpoint |- ctx->pos
+ * |- log->last_cp_seq |- ctx->seq
+ *
+ * From this point, we need to increase seq number by 10 to avoid
+ * confusing next recovery.
+ *
+ * ---------------------------------------------
+ * | valid log | invalid log |
+ * ---------------------------------------------
+ * ^ ^
+ * |- log->last_checkpoint |- ctx->pos+1
+ * |- log->last_cp_seq |- ctx->seq+11
+ *
+ * However, it is not safe to start the state machine yet, because data only
+ * parities are not yet secured in RAID. To save these data only parities, we
+ * rewrite them from seq+11.
+ *
+ * -----------------------------------------------------------------
+ * | valid log | data only stripes | invalid log |
+ * -----------------------------------------------------------------
+ * ^ ^
+ * |- log->last_checkpoint |- ctx->pos+n
+ * |- log->last_cp_seq |- ctx->seq+10+n
+ *
+ * If failure happens again during this process, the recovery can safe start
+ * again from log->last_checkpoint.
+ *
+ * Once data only stripes are rewritten to journal, we move log_tail
+ *
+ * -----------------------------------------------------------------
+ * | old log | data only stripes | invalid log |
+ * -----------------------------------------------------------------
+ * ^ ^
+ * |- log->last_checkpoint |- ctx->pos+n
+ * |- log->last_cp_seq |- ctx->seq+10+n
+ *
+ * Then we can safely start the state machine. If failure happens from this
+ * point on, the recovery will start from new log->last_checkpoint.
+ */
+static int
+r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
+ struct r5l_recovery_ctx *ctx)
{
+ struct stripe_head *sh, *next;
+ struct mddev *mddev = log->rdev->mddev;
struct page *page;
- struct r5l_meta_block *mb;
- u32 crc;
- page = alloc_page(GFP_KERNEL | __GFP_ZERO);
- if (!page)
+ page = alloc_page(GFP_KERNEL);
+ if (!page) {
+ pr_err("md/raid:%s: cannot allocate memory to rewrite data only stripes\n",
+ mdname(mddev));
return -ENOMEM;
- mb = page_address(page);
- mb->magic = cpu_to_le32(R5LOG_MAGIC);
- mb->version = R5LOG_VERSION;
- mb->meta_size = cpu_to_le32(sizeof(struct r5l_meta_block));
- mb->seq = cpu_to_le64(seq);
- mb->position = cpu_to_le64(pos);
- crc = crc32c_le(log->uuid_checksum, mb, PAGE_SIZE);
- mb->checksum = cpu_to_le32(crc);
+ }
- if (!sync_page_io(log->rdev, pos, PAGE_SIZE, page, REQ_OP_WRITE,
- WRITE_FUA, false)) {
- __free_page(page);
- return -EIO;
+ ctx->seq += 10;
+ list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
+ struct r5l_meta_block *mb;
+ int i;
+ int offset;
+ sector_t write_pos;
+
+ WARN_ON(!test_bit(STRIPE_R5C_CACHING, &sh->state));
+ r5l_recovery_create_empty_meta_block(log, page,
+ ctx->pos, ctx->seq);
+ mb = page_address(page);
+ offset = le32_to_cpu(mb->meta_size);
+ write_pos = r5l_ring_add(log, ctx->pos, BLOCK_SECTORS);
+
+ for (i = sh->disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ struct r5l_payload_data_parity *payload;
+ void *addr;
+
+ if (test_bit(R5_InJournal, &dev->flags)) {
+ payload = (void *)mb + offset;
+ payload->header.type = cpu_to_le16(
+ R5LOG_PAYLOAD_DATA);
+ payload->size = BLOCK_SECTORS;
+ payload->location = cpu_to_le64(
+ raid5_compute_blocknr(sh, i, 0));
+ addr = kmap_atomic(dev->page);
+ payload->checksum[0] = cpu_to_le32(
+ crc32c_le(log->uuid_checksum, addr,
+ PAGE_SIZE));
+ kunmap_atomic(addr);
+ sync_page_io(log->rdev, write_pos, PAGE_SIZE,
+ dev->page, REQ_OP_WRITE, 0, false);
+ write_pos = r5l_ring_add(log, write_pos,
+ BLOCK_SECTORS);
+ offset += sizeof(__le32) +
+ sizeof(struct r5l_payload_data_parity);
+
+ }
+ }
+ mb->meta_size = cpu_to_le32(offset);
+ mb->checksum = crc32c_le(log->uuid_checksum, mb, PAGE_SIZE);
+ sync_page_io(log->rdev, ctx->pos, PAGE_SIZE, page,
+ REQ_OP_WRITE, WRITE_FUA, false);
+ sh->log_start = ctx->pos;
+ ctx->pos = write_pos;
+ ctx->seq += 1;
+
+ list_del_init(&sh->lru);
+ raid5_release_stripe(sh);
}
__free_page(page);
return 0;
static int r5l_recovery_log(struct r5l_log *log)
{
+ struct mddev *mddev = log->rdev->mddev;
struct r5l_recovery_ctx ctx;
+ int ret;
ctx.pos = log->last_checkpoint;
ctx.seq = log->last_cp_seq;
ctx.meta_page = alloc_page(GFP_KERNEL);
+ ctx.data_only_stripes = 0;
+ ctx.data_parity_stripes = 0;
+ INIT_LIST_HEAD(&ctx.cached_list);
+
if (!ctx.meta_page)
return -ENOMEM;
- r5l_recovery_flush_log(log, &ctx);
+ ret = r5c_recovery_flush_log(log, &ctx);
__free_page(ctx.meta_page);
- /*
- * we did a recovery. Now ctx.pos points to an invalid meta block. New
- * log will start here. but we can't let superblock point to last valid
- * meta block. The log might looks like:
- * | meta 1| meta 2| meta 3|
- * meta 1 is valid, meta 2 is invalid. meta 3 could be valid. If
- * superblock points to meta 1, we write a new valid meta 2n. if crash
- * happens again, new recovery will start from meta 1. Since meta 2n is
- * valid now, recovery will think meta 3 is valid, which is wrong.
- * The solution is we create a new meta in meta2 with its seq == meta
- * 1's seq + 10 and let superblock points to meta2. The same recovery will
- * not think meta 3 is a valid meta, because its seq doesn't match
- */
- if (ctx.seq > log->last_cp_seq) {
- int ret;
-
- ret = r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq + 10);
- if (ret)
- return ret;
- log->seq = ctx.seq + 11;
- log->log_start = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
- r5l_write_super(log, ctx.pos);
- log->last_checkpoint = ctx.pos;
- log->next_checkpoint = ctx.pos;
- } else {
- log->log_start = ctx.pos;
- log->seq = ctx.seq;
+ if (ret)
+ return ret;
+
+ if ((ctx.data_only_stripes == 0) && (ctx.data_parity_stripes == 0))
+ pr_debug("md/raid:%s: starting from clean shutdown\n",
+ mdname(mddev));
+ else {
+ pr_debug("md/raid:%s: recoverying %d data-only stripes and %d data-parity stripes\n",
+ mdname(mddev), ctx.data_only_stripes,
+ ctx.data_parity_stripes);
+
+ if (ctx.data_only_stripes > 0)
+ if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) {
+ pr_err("md/raid:%s: failed to rewrite stripes to journal\n",
+ mdname(mddev));
+ return -EIO;
+ }
}
+
+ log->log_start = ctx.pos;
+ log->next_checkpoint = ctx.pos;
+ log->seq = ctx.seq;
+ r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq);
+ r5l_write_super(log, ctx.pos);
return 0;
}
*/
void r5c_release_extra_page(struct stripe_head *sh)
{
+ struct r5conf *conf = sh->raid_conf;
int i;
+ bool using_disk_info_extra_page;
+
+ using_disk_info_extra_page =
+ sh->dev[0].orig_page == conf->disks[0].extra_page;
for (i = sh->disks; i--; )
if (sh->dev[i].page != sh->dev[i].orig_page) {
struct page *p = sh->dev[i].orig_page;
sh->dev[i].orig_page = sh->dev[i].page;
- put_page(p);
+ if (!using_disk_info_extra_page)
+ put_page(p);
}
+
+ if (using_disk_info_extra_page) {
+ clear_bit(R5C_EXTRA_PAGE_IN_USE, &conf->cache_state);
+ md_wakeup_thread(conf->mddev->thread);
+ }
+}
+
+void r5c_use_extra_page(struct stripe_head *sh)
+{
+ struct r5conf *conf = sh->raid_conf;
+ int i;
+ struct r5dev *dev;
+
+ for (i = sh->disks; i--; ) {
+ dev = &sh->dev[i];
+ if (dev->orig_page != dev->page)
+ put_page(dev->orig_page);
+ dev->orig_page = conf->disks[i].extra_page;
+ }
}
/*
INIT_LIST_HEAD(&log->no_space_stripes);
spin_lock_init(&log->no_space_stripes_lock);
+ INIT_WORK(&log->deferred_io_work, r5l_submit_io_async);
+
log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
INIT_LIST_HEAD(&log->stripe_in_journal_list);
spin_lock_init(&log->stripe_in_journal_lock);