Merge branch 'for-linus-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs
Pull btrfs updates from Chris Mason:
"This has Jeff Mahoney's long standing trim patch that fixes corners
where trims were missing. Omar has some raid5/6 fixes, especially for
using scrub and device replace when devices are missing.
Zhao Lie continues cleaning and fixing things, this series fixes some
really hard to hit corners in xfstests. I had to pull it last merge
window due to some deadlocks, but those are now resolved.
I added support for Tejun's new blkio controllers. It seems to work
well for single devices, we'll expand to multi-device as well"
* 'for-linus-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (47 commits)
btrfs: fix compile when block cgroups are not enabled
Btrfs: fix file read corruption after extent cloning and fsync
Btrfs: check if previous transaction aborted to avoid fs corruption
btrfs: use __GFP_NOFAIL in alloc_btrfs_bio
btrfs: Prevent from early transaction abort
btrfs: Remove unused arguments in tree-log.c
btrfs: Remove useless condition in start_log_trans()
Btrfs: add support for blkio controllers
Btrfs: remove unused mutex from struct 'btrfs_fs_info'
Btrfs: fix parity scrub of RAID 5/6 with missing device
Btrfs: fix device replace of a missing RAID 5/6 device
Btrfs: add RAID 5/6 BTRFS_RBIO_REBUILD_MISSING operation
Btrfs: count devices correctly in readahead during RAID 5/6 replace
Btrfs: remove misleading handling of missing device scrub
btrfs: fix clone / extent-same deadlocks
Btrfs: fix defrag to merge tail file extent
Btrfs: fix warning in backref walking
btrfs: Add WARN_ON() for double lock in btrfs_tree_lock()
btrfs: Remove root argument in extent_data_ref_count()
btrfs: Fix wrong comment of btrfs_alloc_tree_block()
...
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 0a02e24..fcf7265 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -61,9 +61,10 @@
#define RBIO_CACHE_SIZE 1024
enum btrfs_rbio_ops {
- BTRFS_RBIO_WRITE = 0,
- BTRFS_RBIO_READ_REBUILD = 1,
- BTRFS_RBIO_PARITY_SCRUB = 2,
+ BTRFS_RBIO_WRITE,
+ BTRFS_RBIO_READ_REBUILD,
+ BTRFS_RBIO_PARITY_SCRUB,
+ BTRFS_RBIO_REBUILD_MISSING,
};
struct btrfs_raid_bio {
@@ -602,6 +603,10 @@
cur->operation == BTRFS_RBIO_PARITY_SCRUB)
return 0;
+ if (last->operation == BTRFS_RBIO_REBUILD_MISSING ||
+ cur->operation == BTRFS_RBIO_REBUILD_MISSING)
+ return 0;
+
return 1;
}
@@ -793,7 +798,10 @@
if (next->operation == BTRFS_RBIO_READ_REBUILD)
async_read_rebuild(next);
- else if (next->operation == BTRFS_RBIO_WRITE) {
+ else if (next->operation == BTRFS_RBIO_REBUILD_MISSING) {
+ steal_rbio(rbio, next);
+ async_read_rebuild(next);
+ } else if (next->operation == BTRFS_RBIO_WRITE) {
steal_rbio(rbio, next);
async_rmw_stripe(next);
} else if (next->operation == BTRFS_RBIO_PARITY_SCRUB) {
@@ -1805,7 +1813,8 @@
faila = rbio->faila;
failb = rbio->failb;
- if (rbio->operation == BTRFS_RBIO_READ_REBUILD) {
+ if (rbio->operation == BTRFS_RBIO_READ_REBUILD ||
+ rbio->operation == BTRFS_RBIO_REBUILD_MISSING) {
spin_lock_irq(&rbio->bio_list_lock);
set_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags);
spin_unlock_irq(&rbio->bio_list_lock);
@@ -1830,7 +1839,8 @@
* if we're rebuilding a read, we have to use
* pages from the bio list
*/
- if (rbio->operation == BTRFS_RBIO_READ_REBUILD &&
+ if ((rbio->operation == BTRFS_RBIO_READ_REBUILD ||
+ rbio->operation == BTRFS_RBIO_REBUILD_MISSING) &&
(stripe == faila || stripe == failb)) {
page = page_in_rbio(rbio, stripe, pagenr, 0);
} else {
@@ -1939,7 +1949,8 @@
* if we're rebuilding a read, we have to use
* pages from the bio list
*/
- if (rbio->operation == BTRFS_RBIO_READ_REBUILD &&
+ if ((rbio->operation == BTRFS_RBIO_READ_REBUILD ||
+ rbio->operation == BTRFS_RBIO_REBUILD_MISSING) &&
(stripe == faila || stripe == failb)) {
page = page_in_rbio(rbio, stripe, pagenr, 0);
} else {
@@ -1961,6 +1972,8 @@
clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
rbio_orig_end_io(rbio, err);
+ } else if (rbio->operation == BTRFS_RBIO_REBUILD_MISSING) {
+ rbio_orig_end_io(rbio, err);
} else if (err == 0) {
rbio->faila = -1;
rbio->failb = -1;
@@ -2096,7 +2109,8 @@
return 0;
cleanup:
- if (rbio->operation == BTRFS_RBIO_READ_REBUILD)
+ if (rbio->operation == BTRFS_RBIO_READ_REBUILD ||
+ rbio->operation == BTRFS_RBIO_REBUILD_MISSING)
rbio_orig_end_io(rbio, -EIO);
return -EIO;
}
@@ -2227,8 +2241,9 @@
return rbio;
}
-void raid56_parity_add_scrub_pages(struct btrfs_raid_bio *rbio,
- struct page *page, u64 logical)
+/* Used for both parity scrub and missing. */
+void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page,
+ u64 logical)
{
int stripe_offset;
int index;
@@ -2662,3 +2677,55 @@
if (!lock_stripe_add(rbio))
async_scrub_parity(rbio);
}
+
+/* The following code is used for dev replace of a missing RAID 5/6 device. */
+
+struct btrfs_raid_bio *
+raid56_alloc_missing_rbio(struct btrfs_root *root, struct bio *bio,
+ struct btrfs_bio *bbio, u64 length)
+{
+ struct btrfs_raid_bio *rbio;
+
+ rbio = alloc_rbio(root, bbio, length);
+ if (IS_ERR(rbio))
+ return NULL;
+
+ rbio->operation = BTRFS_RBIO_REBUILD_MISSING;
+ bio_list_add(&rbio->bio_list, bio);
+ /*
+ * This is a special bio which is used to hold the completion handler
+ * and make the scrub rbio is similar to the other types
+ */
+ ASSERT(!bio->bi_iter.bi_size);
+
+ rbio->faila = find_logical_bio_stripe(rbio, bio);
+ if (rbio->faila == -1) {
+ BUG();
+ kfree(rbio);
+ return NULL;
+ }
+
+ return rbio;
+}
+
+static void missing_raid56_work(struct btrfs_work *work)
+{
+ struct btrfs_raid_bio *rbio;
+
+ rbio = container_of(work, struct btrfs_raid_bio, work);
+ __raid56_parity_recover(rbio);
+}
+
+static void async_missing_raid56(struct btrfs_raid_bio *rbio)
+{
+ btrfs_init_work(&rbio->work, btrfs_rmw_helper,
+ missing_raid56_work, NULL, NULL);
+
+ btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
+}
+
+void raid56_submit_missing_rbio(struct btrfs_raid_bio *rbio)
+{
+ if (!lock_stripe_add(rbio))
+ async_missing_raid56(rbio);
+}