Btrfs: add RAID 5/6 BTRFS_RBIO_REBUILD_MISSING operation

The current RAID 5/6 recovery code isn't quite prepared to handle
missing devices. In particular, it expects a bio that we previously
attempted to use in the read path, meaning that it has valid pages
allocated. However, missing devices have a NULL blkdev, and we can't
call bio_add_page() on a bio with a NULL blkdev. We could do manual
manipulation of bio->bi_io_vec, but that's pretty gross. So instead, add
a separate path that allows us to manually add pages to the rbio.

Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Chris Mason <clm@fb.com>

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index fa72068bd256018e27a13fbc8326b82ce49b207b..6fe2613ef288dcc746ce9ce1e557c1f54aa9ddda 100644 (file)
--- 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 @@ static int rbio_can_merge(struct btrfs_raid_bio *last,
            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 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
 
                        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) {
@@ -1809,7 +1817,8 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
        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);
@@ -1834,7 +1843,8 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
                         * 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 {
@@ -1943,7 +1953,8 @@ pstripe:
                         * 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 {
@@ -1964,6 +1975,8 @@ cleanup_io:
                else
                        clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
 
+               rbio_orig_end_io(rbio, err, err == 0);
+       } else if (rbio->operation == BTRFS_RBIO_REBUILD_MISSING) {
                rbio_orig_end_io(rbio, err, err == 0);
        } else if (err == 0) {
                rbio->faila = -1;
@@ -2101,7 +2114,8 @@ out:
        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, 0);
        return -EIO;
 }
@@ -2232,8 +2246,9 @@ raid56_parity_alloc_scrub_rbio(struct btrfs_root *root, struct bio *bio,
        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;
@@ -2668,3 +2683,55 @@ void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio)
        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);
+}

diff --git a/fs/btrfs/raid56.h b/fs/btrfs/raid56.h
index 2b5d7977d83b2248e40d7331e4fd7d6d831ef1d6..8b694699d502cef12ee8881f092741a78561afd9 100644 (file)
--- a/fs/btrfs/raid56.h
+++ b/fs/btrfs/raid56.h
@@ -48,15 +48,21 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
 int raid56_parity_write(struct btrfs_root *root, struct bio *bio,
                               struct btrfs_bio *bbio, u64 stripe_len);
 
+void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page,
+                           u64 logical);
+
 struct btrfs_raid_bio *
 raid56_parity_alloc_scrub_rbio(struct btrfs_root *root, struct bio *bio,
                               struct btrfs_bio *bbio, u64 stripe_len,
                               struct btrfs_device *scrub_dev,
                               unsigned long *dbitmap, int stripe_nsectors);
-void raid56_parity_add_scrub_pages(struct btrfs_raid_bio *rbio,
-                                  struct page *page, u64 logical);
 void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio);
 
+struct btrfs_raid_bio *
+raid56_alloc_missing_rbio(struct btrfs_root *root, struct bio *bio,
+                         struct btrfs_bio *bbio, u64 length);
+void raid56_submit_missing_rbio(struct btrfs_raid_bio *rbio);
+
 int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info);
 void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info);
 #endif

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index a12c450e55fa92ecbc883d280cb1cfb9312aee58..038162456cfad0dac07f5e1b56f80c63f1517e84 100644 (file)
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2720,8 +2720,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
                goto rbio_out;
 
        list_for_each_entry(spage, &sparity->spages, list)
-               raid56_parity_add_scrub_pages(rbio, spage->page,
-                                             spage->logical);
+               raid56_add_scrub_pages(rbio, spage->page, spage->logical);
 
        scrub_pending_bio_inc(sctx);
        raid56_parity_submit_scrub_rbio(rbio);