summaryrefslogtreecommitdiff
path: root/drivers/md/raid10.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/raid10.c')
-rw-r--r--drivers/md/raid10.c76
1 files changed, 42 insertions, 34 deletions
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 03724992cdf2..a88aeb5198c7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -799,12 +799,12 @@ static int make_request(mddev_t *mddev, struct bio * bio)
int i;
int chunk_sects = conf->chunk_mask + 1;
const int rw = bio_data_dir(bio);
- const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
+ const bool do_sync = (bio->bi_rw & REQ_SYNC);
struct bio_list bl;
unsigned long flags;
mdk_rdev_t *blocked_rdev;
- if (unlikely(bio_rw_flagged(bio, BIO_RW_BARRIER))) {
+ if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
md_barrier_request(mddev, bio);
return 0;
}
@@ -825,11 +825,29 @@ static int make_request(mddev_t *mddev, struct bio * bio)
*/
bp = bio_split(bio,
chunk_sects - (bio->bi_sector & (chunk_sects - 1)) );
+
+ /* Each of these 'make_request' calls will call 'wait_barrier'.
+ * If the first succeeds but the second blocks due to the resync
+ * thread raising the barrier, we will deadlock because the
+ * IO to the underlying device will be queued in generic_make_request
+ * and will never complete, so will never reduce nr_pending.
+ * So increment nr_waiting here so no new raise_barriers will
+ * succeed, and so the second wait_barrier cannot block.
+ */
+ spin_lock_irq(&conf->resync_lock);
+ conf->nr_waiting++;
+ spin_unlock_irq(&conf->resync_lock);
+
if (make_request(mddev, &bp->bio1))
generic_make_request(&bp->bio1);
if (make_request(mddev, &bp->bio2))
generic_make_request(&bp->bio2);
+ spin_lock_irq(&conf->resync_lock);
+ conf->nr_waiting--;
+ wake_up(&conf->wait_barrier);
+ spin_unlock_irq(&conf->resync_lock);
+
bio_pair_release(bp);
return 0;
bad_map:
@@ -879,7 +897,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
mirror->rdev->data_offset;
read_bio->bi_bdev = mirror->rdev->bdev;
read_bio->bi_end_io = raid10_end_read_request;
- read_bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
+ read_bio->bi_rw = READ | do_sync;
read_bio->bi_private = r10_bio;
generic_make_request(read_bio);
@@ -947,7 +965,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
conf->mirrors[d].rdev->data_offset;
mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | (do_sync << BIO_RW_SYNCIO);
+ mbio->bi_rw = WRITE | do_sync;
mbio->bi_private = r10_bio;
atomic_inc(&r10_bio->remaining);
@@ -1482,14 +1500,14 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
int sectors = r10_bio->sectors;
mdk_rdev_t*rdev;
int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
+ int d = r10_bio->devs[r10_bio->read_slot].devnum;
rcu_read_lock();
- {
- int d = r10_bio->devs[r10_bio->read_slot].devnum;
+ rdev = rcu_dereference(conf->mirrors[d].rdev);
+ if (rdev) { /* If rdev is not NULL */
char b[BDEVNAME_SIZE];
int cur_read_error_count = 0;
- rdev = rcu_dereference(conf->mirrors[d].rdev);
bdevname(rdev->bdev, b);
if (test_bit(Faulty, &rdev->flags)) {
@@ -1530,7 +1548,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
rcu_read_lock();
do {
- int d = r10_bio->devs[sl].devnum;
+ d = r10_bio->devs[sl].devnum;
rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev &&
test_bit(In_sync, &rdev->flags)) {
@@ -1564,7 +1582,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
rcu_read_lock();
while (sl != r10_bio->read_slot) {
char b[BDEVNAME_SIZE];
- int d;
+
if (sl==0)
sl = conf->copies;
sl--;
@@ -1601,7 +1619,7 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
}
sl = start;
while (sl != r10_bio->read_slot) {
- int d;
+
if (sl==0)
sl = conf->copies;
sl--;
@@ -1716,7 +1734,7 @@ static void raid10d(mddev_t *mddev)
raid_end_bio_io(r10_bio);
bio_put(bio);
} else {
- const bool do_sync = bio_rw_flagged(r10_bio->master_bio, BIO_RW_SYNCIO);
+ const bool do_sync = (r10_bio->master_bio->bi_rw & REQ_SYNC);
bio_put(bio);
rdev = conf->mirrors[mirror].rdev;
if (printk_ratelimit())
@@ -1730,7 +1748,7 @@ static void raid10d(mddev_t *mddev)
bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr
+ rdev->data_offset;
bio->bi_bdev = rdev->bdev;
- bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
+ bio->bi_rw = READ | do_sync;
bio->bi_private = r10_bio;
bio->bi_end_io = raid10_end_read_request;
unplug = 1;
@@ -2161,22 +2179,22 @@ static conf_t *setup_conf(mddev_t *mddev)
sector_t stride, size;
int err = -EINVAL;
- if (mddev->chunk_sectors < (PAGE_SIZE >> 9) ||
- !is_power_of_2(mddev->chunk_sectors)) {
+ if (mddev->new_chunk_sectors < (PAGE_SIZE >> 9) ||
+ !is_power_of_2(mddev->new_chunk_sectors)) {
printk(KERN_ERR "md/raid10:%s: chunk size must be "
"at least PAGE_SIZE(%ld) and be a power of 2.\n",
mdname(mddev), PAGE_SIZE);
goto out;
}
- nc = mddev->layout & 255;
- fc = (mddev->layout >> 8) & 255;
- fo = mddev->layout & (1<<16);
+ nc = mddev->new_layout & 255;
+ fc = (mddev->new_layout >> 8) & 255;
+ fo = mddev->new_layout & (1<<16);
if ((nc*fc) <2 || (nc*fc) > mddev->raid_disks ||
- (mddev->layout >> 17)) {
+ (mddev->new_layout >> 17)) {
printk(KERN_ERR "md/raid10:%s: unsupported raid10 layout: 0x%8x\n",
- mdname(mddev), mddev->layout);
+ mdname(mddev), mddev->new_layout);
goto out;
}
@@ -2241,7 +2259,6 @@ static conf_t *setup_conf(mddev_t *mddev)
if (!conf->thread)
goto out;
- conf->scale_disks = 0;
conf->mddev = mddev;
return conf;
@@ -2300,11 +2317,6 @@ static int run(mddev_t *mddev)
if (disk_idx >= conf->raid_disks
|| disk_idx < 0)
continue;
- if (conf->scale_disks) {
- disk_idx *= conf->scale_disks;
- rdev->raid_disk = disk_idx;
- /* MOVE 'rd%d' link !! */
- }
disk = conf->mirrors + disk_idx;
disk->rdev = rdev;
@@ -2435,26 +2447,22 @@ static void *raid10_takeover_raid0(mddev_t *mddev)
return ERR_PTR(-EINVAL);
}
- /* Update slot numbers to obtain
- * degraded raid10 with missing mirrors
- */
- list_for_each_entry(rdev, &mddev->disks, same_set) {
- rdev->raid_disk *= 2;
- }
-
/* Set new parameters */
mddev->new_level = 10;
/* new layout: far_copies = 1, near_copies = 2 */
mddev->new_layout = (1<<8) + 2;
mddev->new_chunk_sectors = mddev->chunk_sectors;
mddev->delta_disks = mddev->raid_disks;
- mddev->degraded = mddev->raid_disks;
mddev->raid_disks *= 2;
/* make sure it will be not marked as dirty */
mddev->recovery_cp = MaxSector;
conf = setup_conf(mddev);
- conf->scale_disks = 2;
+ if (!IS_ERR(conf))
+ list_for_each_entry(rdev, &mddev->disks, same_set)
+ if (rdev->raid_disk >= 0)
+ rdev->new_raid_disk = rdev->raid_disk * 2;
+
return conf;
}
generated by cgit v1.2.3 (git 2.39.0) at 2025-02-23 19:26:50 +0300