summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2011-09-10 10:19:15 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2011-09-10 10:19:15 -0700
commit290a1cc4f725a53076e0fda804cd4fea84ee4564 (patch)
treeca7c8f8d78dd7afda036ea1e7a1362093b1578e8
parented2888e906b56769b4ffabb9c577190438aa68b8 (diff)
parent27a7b260f71439c40546b43588448faac01adb93 (diff)
Merge branch 'for-linus' of git://neil.brown.name/md
* 'for-linus' of git://neil.brown.name/md: md: Fix handling for devices from 2TB to 4TB in 0.90 metadata. md/raid1,10: Remove use-after-free bug in make_request. md/raid10: unify handling of write completion. Avoid dereferencing a 'request_queue' after last close.
-rw-r--r--drivers/md/md.c12
-rw-r--r--drivers/md/raid1.c14
-rw-r--r--drivers/md/raid10.c47
-rw-r--r--fs/block_dev.c7
4 files changed, 48 insertions, 32 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 3742ce8b0ac..5404b229582 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1138,8 +1138,11 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
ret = 0;
}
rdev->sectors = rdev->sb_start;
+ /* Limit to 4TB as metadata cannot record more than that */
+ if (rdev->sectors >= (2ULL << 32))
+ rdev->sectors = (2ULL << 32) - 2;
- if (rdev->sectors < sb->size * 2 && sb->level > 1)
+ if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
/* "this cannot possibly happen" ... */
ret = -EINVAL;
@@ -1173,7 +1176,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
mddev->clevel[0] = 0;
mddev->layout = sb->layout;
mddev->raid_disks = sb->raid_disks;
- mddev->dev_sectors = sb->size * 2;
+ mddev->dev_sectors = ((sector_t)sb->size) * 2;
mddev->events = ev1;
mddev->bitmap_info.offset = 0;
mddev->bitmap_info.default_offset = MD_SB_BYTES >> 9;
@@ -1415,6 +1418,11 @@ super_90_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
rdev->sb_start = calc_dev_sboffset(rdev);
if (!num_sectors || num_sectors > rdev->sb_start)
num_sectors = rdev->sb_start;
+ /* Limit to 4TB as metadata cannot record more than that.
+ * 4TB == 2^32 KB, or 2*2^32 sectors.
+ */
+ if (num_sectors >= (2ULL << 32))
+ num_sectors = (2ULL << 32) - 2;
md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
rdev->sb_page);
md_super_wait(rdev->mddev);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 32323f0afd8..f4622dd8fc5 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1099,12 +1099,11 @@ read_again:
bio_list_add(&conf->pending_bio_list, mbio);
spin_unlock_irqrestore(&conf->device_lock, flags);
}
- r1_bio_write_done(r1_bio);
-
- /* In case raid1d snuck in to freeze_array */
- wake_up(&conf->wait_barrier);
-
+ /* Mustn't call r1_bio_write_done before this next test,
+ * as it could result in the bio being freed.
+ */
if (sectors_handled < (bio->bi_size >> 9)) {
+ r1_bio_write_done(r1_bio);
/* We need another r1_bio. It has already been counted
* in bio->bi_phys_segments
*/
@@ -1117,6 +1116,11 @@ read_again:
goto retry_write;
}
+ r1_bio_write_done(r1_bio);
+
+ /* In case raid1d snuck in to freeze_array */
+ wake_up(&conf->wait_barrier);
+
if (do_sync || !bitmap || !plugged)
md_wakeup_thread(mddev->thread);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 8b29cd4f01c..d7a8468ddea 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -337,6 +337,21 @@ static void close_write(r10bio_t *r10_bio)
md_write_end(r10_bio->mddev);
}
+static void one_write_done(r10bio_t *r10_bio)
+{
+ if (atomic_dec_and_test(&r10_bio->remaining)) {
+ if (test_bit(R10BIO_WriteError, &r10_bio->state))
+ reschedule_retry(r10_bio);
+ else {
+ close_write(r10_bio);
+ if (test_bit(R10BIO_MadeGood, &r10_bio->state))
+ reschedule_retry(r10_bio);
+ else
+ raid_end_bio_io(r10_bio);
+ }
+ }
+}
+
static void raid10_end_write_request(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
@@ -387,17 +402,7 @@ static void raid10_end_write_request(struct bio *bio, int error)
* Let's see if all mirrored write operations have finished
* already.
*/
- if (atomic_dec_and_test(&r10_bio->remaining)) {
- if (test_bit(R10BIO_WriteError, &r10_bio->state))
- reschedule_retry(r10_bio);
- else {
- close_write(r10_bio);
- if (test_bit(R10BIO_MadeGood, &r10_bio->state))
- reschedule_retry(r10_bio);
- else
- raid_end_bio_io(r10_bio);
- }
- }
+ one_write_done(r10_bio);
if (dec_rdev)
rdev_dec_pending(conf->mirrors[dev].rdev, conf->mddev);
}
@@ -1127,20 +1132,12 @@ retry_write:
spin_unlock_irqrestore(&conf->device_lock, flags);
}
- if (atomic_dec_and_test(&r10_bio->remaining)) {
- /* This matches the end of raid10_end_write_request() */
- bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector,
- r10_bio->sectors,
- !test_bit(R10BIO_Degraded, &r10_bio->state),
- 0);
- md_write_end(mddev);
- raid_end_bio_io(r10_bio);
- }
-
- /* In case raid10d snuck in to freeze_array */
- wake_up(&conf->wait_barrier);
+ /* Don't remove the bias on 'remaining' (one_write_done) until
+ * after checking if we need to go around again.
+ */
if (sectors_handled < (bio->bi_size >> 9)) {
+ one_write_done(r10_bio);
/* We need another r10_bio. It has already been counted
* in bio->bi_phys_segments.
*/
@@ -1154,6 +1151,10 @@ retry_write:
r10_bio->state = 0;
goto retry_write;
}
+ one_write_done(r10_bio);
+
+ /* In case raid10d snuck in to freeze_array */
+ wake_up(&conf->wait_barrier);
if (do_sync || !mddev->bitmap || !plugged)
md_wakeup_thread(mddev->thread);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index ff77262e887..95f786ec7f0 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1429,6 +1429,11 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
WARN_ON_ONCE(bdev->bd_holders);
sync_blockdev(bdev);
kill_bdev(bdev);
+ /* ->release can cause the old bdi to disappear,
+ * so must switch it out first
+ */
+ bdev_inode_switch_bdi(bdev->bd_inode,
+ &default_backing_dev_info);
}
if (bdev->bd_contains == bdev) {
if (disk->fops->release)
@@ -1442,8 +1447,6 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
disk_put_part(bdev->bd_part);
bdev->bd_part = NULL;
bdev->bd_disk = NULL;
- bdev_inode_switch_bdi(bdev->bd_inode,
- &default_backing_dev_info);
if (bdev != bdev->bd_contains)
victim = bdev->bd_contains;
bdev->bd_contains = NULL;