summaryrefslogtreecommitdiff
path: root/drivers/md/raid5.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/raid5.c')
-rw-r--r--drivers/md/raid5.c143
1 files changed, 89 insertions, 54 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 8dc98f545969..8854e024f311 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -56,7 +56,11 @@
#include "md-bitmap.h"
#include "raid5-log.h"
-#define UNSUPPORTED_MDDEV_FLAGS (1L << MD_FAILFAST_SUPPORTED)
+#define UNSUPPORTED_MDDEV_FLAGS \
+ ((1L << MD_FAILFAST_SUPPORTED) | \
+ (1L << MD_FAILLAST_DEV) | \
+ (1L << MD_SERIALIZE_POLICY))
+
#define cpu_to_group(cpu) cpu_to_node(cpu)
#define ANY_GROUP NUMA_NO_NODE
@@ -773,14 +777,14 @@ struct stripe_request_ctx {
/* last sector in the request */
sector_t last_sector;
+ /* the request had REQ_PREFLUSH, cleared after the first stripe_head */
+ bool do_flush;
+
/*
* bitmap to track stripe sectors that have been added to stripes
* add one to account for unaligned requests
*/
- DECLARE_BITMAP(sectors_to_do, RAID5_MAX_REQ_STRIPES + 1);
-
- /* the request had REQ_PREFLUSH, cleared after the first stripe_head */
- bool do_flush;
+ unsigned long sectors_to_do[];
};
/*
@@ -2817,11 +2821,9 @@ static void raid5_end_read_request(struct bio * bi)
else {
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
- if (!(set_bad
- && test_bit(In_sync, &rdev->flags)
- && rdev_set_badblocks(
- rdev, sh->sector, RAID5_STRIPE_SECTORS(conf), 0)))
- md_error(conf->mddev, rdev);
+ if (!(set_bad && test_bit(In_sync, &rdev->flags)))
+ rdev_set_badblocks(rdev, sh->sector,
+ RAID5_STRIPE_SECTORS(conf), 0);
}
}
rdev_dec_pending(rdev, conf->mddev);
@@ -2920,7 +2922,6 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
if (has_failed(conf)) {
set_bit(MD_BROKEN, &conf->mddev->flags);
- conf->recovery_disabled = mddev->recovery_disabled;
pr_crit("md/raid:%s: Cannot continue operation (%d/%d failed).\n",
mdname(mddev), mddev->degraded, conf->raid_disks);
@@ -3599,11 +3600,10 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
else
rdev = NULL;
if (rdev) {
- if (!rdev_set_badblocks(
- rdev,
- sh->sector,
- RAID5_STRIPE_SECTORS(conf), 0))
- md_error(conf->mddev, rdev);
+ rdev_set_badblocks(rdev,
+ sh->sector,
+ RAID5_STRIPE_SECTORS(conf),
+ 0);
rdev_dec_pending(rdev, conf->mddev);
}
}
@@ -3723,11 +3723,11 @@ handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
RAID5_STRIPE_SECTORS(conf), 0))
abort = 1;
}
- if (abort)
- conf->recovery_disabled =
- conf->mddev->recovery_disabled;
}
- md_done_sync(conf->mddev, RAID5_STRIPE_SECTORS(conf), !abort);
+ md_done_sync(conf->mddev, RAID5_STRIPE_SECTORS(conf));
+
+ if (abort)
+ md_sync_error(conf->mddev);
}
static int want_replace(struct stripe_head *sh, int disk_idx)
@@ -3751,9 +3751,14 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
struct r5dev *dev = &sh->dev[disk_idx];
struct r5dev *fdev[2] = { &sh->dev[s->failed_num[0]],
&sh->dev[s->failed_num[1]] };
+ struct mddev *mddev = sh->raid_conf->mddev;
+ bool force_rcw = false;
int i;
- bool force_rcw = (sh->raid_conf->rmw_level == PARITY_DISABLE_RMW);
+ if (sh->raid_conf->rmw_level == PARITY_DISABLE_RMW ||
+ (mddev->bitmap_ops && mddev->bitmap_ops->blocks_synced &&
+ !mddev->bitmap_ops->blocks_synced(mddev, sh->sector)))
+ force_rcw = true;
if (test_bit(R5_LOCKED, &dev->flags) ||
test_bit(R5_UPTODATE, &dev->flags))
@@ -5157,7 +5162,7 @@ static void handle_stripe(struct stripe_head *sh)
if ((s.syncing || s.replacing) && s.locked == 0 &&
!test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
test_bit(STRIPE_INSYNC, &sh->state)) {
- md_done_sync(conf->mddev, RAID5_STRIPE_SECTORS(conf), 1);
+ md_done_sync(conf->mddev, RAID5_STRIPE_SECTORS(conf));
clear_bit(STRIPE_SYNCING, &sh->state);
if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags))
wake_up_bit(&sh->dev[sh->pd_idx].flags, R5_Overlap);
@@ -5224,7 +5229,7 @@ static void handle_stripe(struct stripe_head *sh)
clear_bit(STRIPE_EXPAND_READY, &sh->state);
atomic_dec(&conf->reshape_stripes);
wake_up(&conf->wait_for_reshape);
- md_done_sync(conf->mddev, RAID5_STRIPE_SECTORS(conf), 1);
+ md_done_sync(conf->mddev, RAID5_STRIPE_SECTORS(conf));
}
if (s.expanding && s.locked == 0 &&
@@ -5253,9 +5258,8 @@ finish:
if (test_and_clear_bit(R5_WriteError, &dev->flags)) {
/* We own a safe reference to the rdev */
rdev = conf->disks[i].rdev;
- if (!rdev_set_badblocks(rdev, sh->sector,
- RAID5_STRIPE_SECTORS(conf), 0))
- md_error(conf->mddev, rdev);
+ rdev_set_badblocks(rdev, sh->sector,
+ RAID5_STRIPE_SECTORS(conf), 0);
rdev_dec_pending(rdev, conf->mddev);
}
if (test_and_clear_bit(R5_MadeGood, &dev->flags)) {
@@ -6080,13 +6084,13 @@ static sector_t raid5_bio_lowest_chunk_sector(struct r5conf *conf,
static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
- bool on_wq;
struct r5conf *conf = mddev->private;
- sector_t logical_sector;
- struct stripe_request_ctx ctx = {};
const int rw = bio_data_dir(bi);
+ struct stripe_request_ctx *ctx;
+ sector_t logical_sector;
enum stripe_result res;
int s, stripe_cnt;
+ bool on_wq;
if (unlikely(bi->bi_opf & REQ_PREFLUSH)) {
int ret = log_handle_flush_request(conf, bi);
@@ -6098,11 +6102,6 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
return true;
}
/* ret == -EAGAIN, fallback */
- /*
- * if r5l_handle_flush_request() didn't clear REQ_PREFLUSH,
- * we need to flush journal device
- */
- ctx.do_flush = bi->bi_opf & REQ_PREFLUSH;
}
md_write_start(mddev, bi);
@@ -6125,16 +6124,25 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
}
logical_sector = bi->bi_iter.bi_sector & ~((sector_t)RAID5_STRIPE_SECTORS(conf)-1);
- ctx.first_sector = logical_sector;
- ctx.last_sector = bio_end_sector(bi);
bi->bi_next = NULL;
- stripe_cnt = DIV_ROUND_UP_SECTOR_T(ctx.last_sector - logical_sector,
+ ctx = mempool_alloc(conf->ctx_pool, GFP_NOIO);
+ memset(ctx, 0, conf->ctx_size);
+ ctx->first_sector = logical_sector;
+ ctx->last_sector = bio_end_sector(bi);
+ /*
+ * if r5l_handle_flush_request() didn't clear REQ_PREFLUSH,
+ * we need to flush journal device
+ */
+ if (unlikely(bi->bi_opf & REQ_PREFLUSH))
+ ctx->do_flush = true;
+
+ stripe_cnt = DIV_ROUND_UP_SECTOR_T(ctx->last_sector - logical_sector,
RAID5_STRIPE_SECTORS(conf));
- bitmap_set(ctx.sectors_to_do, 0, stripe_cnt);
+ bitmap_set(ctx->sectors_to_do, 0, stripe_cnt);
pr_debug("raid456: %s, logical %llu to %llu\n", __func__,
- bi->bi_iter.bi_sector, ctx.last_sector);
+ bi->bi_iter.bi_sector, ctx->last_sector);
/* Bail out if conflicts with reshape and REQ_NOWAIT is set */
if ((bi->bi_opf & REQ_NOWAIT) &&
@@ -6142,6 +6150,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
bio_wouldblock_error(bi);
if (rw == WRITE)
md_write_end(mddev);
+ mempool_free(ctx, conf->ctx_pool);
return true;
}
md_account_bio(mddev, &bi);
@@ -6160,10 +6169,10 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
add_wait_queue(&conf->wait_for_reshape, &wait);
on_wq = true;
}
- s = (logical_sector - ctx.first_sector) >> RAID5_STRIPE_SHIFT(conf);
+ s = (logical_sector - ctx->first_sector) >> RAID5_STRIPE_SHIFT(conf);
while (1) {
- res = make_stripe_request(mddev, conf, &ctx, logical_sector,
+ res = make_stripe_request(mddev, conf, ctx, logical_sector,
bi);
if (res == STRIPE_FAIL || res == STRIPE_WAIT_RESHAPE)
break;
@@ -6180,9 +6189,9 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
* raid5_activate_delayed() from making progress
* and thus deadlocking.
*/
- if (ctx.batch_last) {
- raid5_release_stripe(ctx.batch_last);
- ctx.batch_last = NULL;
+ if (ctx->batch_last) {
+ raid5_release_stripe(ctx->batch_last);
+ ctx->batch_last = NULL;
}
wait_woken(&wait, TASK_UNINTERRUPTIBLE,
@@ -6190,21 +6199,23 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
continue;
}
- s = find_next_bit_wrap(ctx.sectors_to_do, stripe_cnt, s);
+ s = find_next_bit_wrap(ctx->sectors_to_do, stripe_cnt, s);
if (s == stripe_cnt)
break;
- logical_sector = ctx.first_sector +
+ logical_sector = ctx->first_sector +
(s << RAID5_STRIPE_SHIFT(conf));
}
if (unlikely(on_wq))
remove_wait_queue(&conf->wait_for_reshape, &wait);
- if (ctx.batch_last)
- raid5_release_stripe(ctx.batch_last);
+ if (ctx->batch_last)
+ raid5_release_stripe(ctx->batch_last);
if (rw == WRITE)
md_write_end(mddev);
+
+ mempool_free(ctx, conf->ctx_pool);
if (res == STRIPE_WAIT_RESHAPE) {
md_free_cloned_bio(bi);
return false;
@@ -7374,6 +7385,9 @@ static void free_conf(struct r5conf *conf)
bioset_exit(&conf->bio_split);
kfree(conf->stripe_hashtbl);
kfree(conf->pending_data);
+
+ mempool_destroy(conf->ctx_pool);
+
kfree(conf);
}
@@ -7536,8 +7550,6 @@ static struct r5conf *setup_conf(struct mddev *mddev)
}
conf->bypass_threshold = BYPASS_THRESHOLD;
- conf->recovery_disabled = mddev->recovery_disabled - 1;
-
conf->raid_disks = mddev->raid_disks;
if (mddev->reshape_position == MaxSector)
conf->previous_raid_disks = mddev->raid_disks;
@@ -7729,6 +7741,25 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
return 0;
}
+static int raid5_create_ctx_pool(struct r5conf *conf)
+{
+ struct stripe_request_ctx *ctx;
+ int size;
+
+ if (mddev_is_dm(conf->mddev))
+ size = BITS_TO_LONGS(RAID5_MAX_REQ_STRIPES);
+ else
+ size = BITS_TO_LONGS(
+ queue_max_hw_sectors(conf->mddev->gendisk->queue) >>
+ RAID5_STRIPE_SHIFT(conf));
+
+ conf->ctx_size = struct_size(ctx, sectors_to_do, size);
+ conf->ctx_pool = mempool_create_kmalloc_pool(NR_RAID_BIOS,
+ conf->ctx_size);
+
+ return conf->ctx_pool ? 0 : -ENOMEM;
+}
+
static int raid5_set_limits(struct mddev *mddev)
{
struct r5conf *conf = mddev->private;
@@ -7785,6 +7816,8 @@ static int raid5_set_limits(struct mddev *mddev)
* Limit the max sectors based on this.
*/
lim.max_hw_sectors = RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf);
+ if ((lim.max_hw_sectors << 9) < lim.io_opt)
+ lim.max_hw_sectors = lim.io_opt >> 9;
/* No restrictions on the number of segments in the request */
lim.max_segments = USHRT_MAX;
@@ -8057,7 +8090,12 @@ static int raid5_run(struct mddev *mddev)
goto abort;
}
- if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
+ ret = raid5_create_ctx_pool(conf);
+ if (ret)
+ goto abort;
+
+ ret = log_init(conf, journal_dev, raid5_has_ppl(conf));
+ if (ret)
goto abort;
return 0;
@@ -8211,7 +8249,6 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
* isn't possible.
*/
if (!test_bit(Faulty, &rdev->flags) &&
- mddev->recovery_disabled != conf->recovery_disabled &&
!has_failed(conf) &&
(!p->replacement || p->replacement == rdev) &&
number < conf->raid_disks) {
@@ -8272,8 +8309,6 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
return 0;
}
- if (mddev->recovery_disabled == conf->recovery_disabled)
- return -EBUSY;
if (rdev->saved_raid_disk < 0 && has_failed(conf))
/* no point adding a device */
generated by cgit v1.2.3 (git 2.25.1) at 2026-08-05 14:34:57 +0000