summaryrefslogtreecommitdiffstats
path: root/drivers/md/raid5.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/raid5.c')
-rw-r--r--drivers/md/raid5.c114
1 files changed, 63 insertions, 51 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d874abfc18..ff9f4751c0 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -36,7 +36,6 @@
*/
#include <linux/blkdev.h>
-#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/async_tx.h>
@@ -156,7 +155,7 @@ static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
return slot;
}
-static void print_raid5_conf (struct r5conf *conf);
+static void print_raid5_conf(struct r5conf *conf);
static int stripe_operations_active(struct stripe_head *sh)
{
@@ -5900,6 +5899,39 @@ out:
return ret;
}
+enum reshape_loc {
+ LOC_NO_RESHAPE,
+ LOC_AHEAD_OF_RESHAPE,
+ LOC_INSIDE_RESHAPE,
+ LOC_BEHIND_RESHAPE,
+};
+
+static enum reshape_loc get_reshape_loc(struct mddev *mddev,
+ struct r5conf *conf, sector_t logical_sector)
+{
+ sector_t reshape_progress, reshape_safe;
+ /*
+ * Spinlock is needed as reshape_progress may be
+ * 64bit on a 32bit platform, and so it might be
+ * possible to see a half-updated value
+ * Of course reshape_progress could change after
+ * the lock is dropped, so once we get a reference
+ * to the stripe that we think it is, we will have
+ * to check again.
+ */
+ spin_lock_irq(&conf->device_lock);
+ reshape_progress = conf->reshape_progress;
+ reshape_safe = conf->reshape_safe;
+ spin_unlock_irq(&conf->device_lock);
+ if (reshape_progress == MaxSector)
+ return LOC_NO_RESHAPE;
+ if (ahead_of_reshape(mddev, logical_sector, reshape_progress))
+ return LOC_AHEAD_OF_RESHAPE;
+ if (ahead_of_reshape(mddev, logical_sector, reshape_safe))
+ return LOC_INSIDE_RESHAPE;
+ return LOC_BEHIND_RESHAPE;
+}
+
static enum stripe_result make_stripe_request(struct mddev *mddev,
struct r5conf *conf, struct stripe_request_ctx *ctx,
sector_t logical_sector, struct bio *bi)
@@ -5914,28 +5946,14 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
seq = read_seqcount_begin(&conf->gen_lock);
if (unlikely(conf->reshape_progress != MaxSector)) {
- /*
- * Spinlock is needed as reshape_progress may be
- * 64bit on a 32bit platform, and so it might be
- * possible to see a half-updated value
- * Of course reshape_progress could change after
- * the lock is dropped, so once we get a reference
- * to the stripe that we think it is, we will have
- * to check again.
- */
- spin_lock_irq(&conf->device_lock);
- if (ahead_of_reshape(mddev, logical_sector,
- conf->reshape_progress)) {
- previous = 1;
- } else {
- if (ahead_of_reshape(mddev, logical_sector,
- conf->reshape_safe)) {
- spin_unlock_irq(&conf->device_lock);
- ret = STRIPE_SCHEDULE_AND_RETRY;
- goto out;
- }
+ enum reshape_loc loc = get_reshape_loc(mddev, conf,
+ logical_sector);
+ if (loc == LOC_INSIDE_RESHAPE) {
+ ret = STRIPE_SCHEDULE_AND_RETRY;
+ goto out;
}
- spin_unlock_irq(&conf->device_lock);
+ if (loc == LOC_AHEAD_OF_RESHAPE)
+ previous = 1;
}
new_sector = raid5_compute_sector(conf, logical_sector, previous,
@@ -6079,8 +6097,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
ctx.do_flush = bi->bi_opf & REQ_PREFLUSH;
}
- if (!md_write_start(mddev, bi))
- return false;
+ md_write_start(mddev, bi);
/*
* If array is degraded, better not do chunk aligned read because
* later we might have to read it again in order to reconstruct
@@ -6114,8 +6131,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
/* Bail out if conflicts with reshape and REQ_NOWAIT is set */
if ((bi->bi_opf & REQ_NOWAIT) &&
(conf->reshape_progress != MaxSector) &&
- !ahead_of_reshape(mddev, logical_sector, conf->reshape_progress) &&
- ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) {
+ get_reshape_loc(mddev, conf, logical_sector) == LOC_INSIDE_RESHAPE) {
bio_wouldblock_error(bi);
if (rw == WRITE)
md_write_end(mddev);
@@ -6256,7 +6272,9 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
safepos = conf->reshape_safe;
sector_div(safepos, data_disks);
if (mddev->reshape_backwards) {
- BUG_ON(writepos < reshape_sectors);
+ if (WARN_ON(writepos < reshape_sectors))
+ return MaxSector;
+
writepos -= reshape_sectors;
readpos += reshape_sectors;
safepos += reshape_sectors;
@@ -6274,14 +6292,18 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
* to set 'stripe_addr' which is where we will write to.
*/
if (mddev->reshape_backwards) {
- BUG_ON(conf->reshape_progress == 0);
+ if (WARN_ON(conf->reshape_progress == 0))
+ return MaxSector;
+
stripe_addr = writepos;
- BUG_ON((mddev->dev_sectors &
- ~((sector_t)reshape_sectors - 1))
- - reshape_sectors - stripe_addr
- != sector_nr);
+ if (WARN_ON((mddev->dev_sectors &
+ ~((sector_t)reshape_sectors - 1)) -
+ reshape_sectors - stripe_addr != sector_nr))
+ return MaxSector;
} else {
- BUG_ON(writepos != sector_nr + reshape_sectors);
+ if (WARN_ON(writepos != sector_nr + reshape_sectors))
+ return MaxSector;
+
stripe_addr = sector_nr;
}
@@ -6734,6 +6756,9 @@ static void raid5d(struct md_thread *thread)
int batch_size, released;
unsigned int offset;
+ if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
+ break;
+
released = release_stripe_list(conf, conf->temp_inactive_list);
if (released)
clear_bit(R5_DID_ALLOC, &conf->cache_state);
@@ -6770,18 +6795,7 @@ static void raid5d(struct md_thread *thread)
spin_unlock_irq(&conf->device_lock);
md_check_recovery(mddev);
spin_lock_irq(&conf->device_lock);
-
- /*
- * Waiting on MD_SB_CHANGE_PENDING below may deadlock
- * seeing md_check_recovery() is needed to clear
- * the flag when using mdmon.
- */
- continue;
}
-
- wait_event_lock_irq(mddev->sb_wait,
- !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags),
- conf->device_lock);
}
pr_debug("%d stripes handled\n", handled);
@@ -7571,11 +7585,11 @@ static struct r5conf *setup_conf(struct mddev *mddev)
if (test_bit(Replacement, &rdev->flags)) {
if (disk->replacement)
goto abort;
- RCU_INIT_POINTER(disk->replacement, rdev);
+ disk->replacement = rdev;
} else {
if (disk->rdev)
goto abort;
- RCU_INIT_POINTER(disk->rdev, rdev);
+ disk->rdev = rdev;
}
if (test_bit(In_sync, &rdev->flags)) {
@@ -8057,7 +8071,7 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev)
seq_printf (seq, "]");
}
-static void print_raid5_conf (struct r5conf *conf)
+static void print_raid5_conf(struct r5conf *conf)
{
struct md_rdev *rdev;
int i;
@@ -8071,15 +8085,13 @@ static void print_raid5_conf (struct r5conf *conf)
conf->raid_disks,
conf->raid_disks - conf->mddev->degraded);
- rcu_read_lock();
for (i = 0; i < conf->raid_disks; i++) {
- rdev = rcu_dereference(conf->disks[i].rdev);
+ rdev = conf->disks[i].rdev;
if (rdev)
pr_debug(" disk %d, o:%d, dev:%pg\n",
i, !test_bit(Faulty, &rdev->flags),
rdev->bdev);
}
- rcu_read_unlock();
}
static int raid5_spare_active(struct mddev *mddev)
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-10 21:39:16 +0000