}
}
+/*
+ * Read repair runs in bio completion context: btrfs_check_read_bio() is called
+ * by the btrfs-endio workers and, for RAID56, by the btrfs-rmw worker that
+ * completes the rbio. The repair read and the write-back of the good copy both
+ * take the bio counter, which waits while device replace is finishing, and
+ * replace finishing waits for every counted bio to complete. Counted bios
+ * complete in those same workers too (RAID56 bios in btrfs-rmw, mirrored writes
+ * in btrfs-endio), and both pools have only thread_pool workers: once all of a
+ * pool's workers wait for replace, the counted bios queued behind them never
+ * complete and replace never finishes.
+ *
+ * So the parts of read repair that take the bio counter run in
+ * fs_info->repair_workers, which no bio completion waits for. A repair bbio
+ * is not in flight while it is queued there, so its end_io_work is free.
+ */
+static void btrfs_repair_read_work(struct work_struct *work)
+{
+ struct btrfs_bio *repair_bbio = container_of(work, struct btrfs_bio, end_io_work);
+
+ btrfs_submit_bbio(repair_bbio, repair_bbio->mirror_num);
+}
+
+static void btrfs_queue_repair_read(struct btrfs_bio *repair_bbio, int mirror)
+{
+ struct btrfs_fs_info *fs_info = repair_bbio->inode->root->fs_info;
+
+ repair_bbio->mirror_num = mirror;
+ INIT_WORK(&repair_bbio->end_io_work, btrfs_repair_read_work);
+ queue_work(fs_info->repair_workers, &repair_bbio->end_io_work);
+}
+
+/* Write the good copy in @repair_bbio back to the mirrors that failed before it. */
+static void btrfs_repair_write_work(struct work_struct *work)
+{
+ struct btrfs_bio *repair_bbio = container_of(work, struct btrfs_bio, end_io_work);
+ struct btrfs_failed_bio *fbio = repair_bbio->private;
+ struct btrfs_fs_info *fs_info = repair_bbio->inode->root->fs_info;
+ int mirror = repair_bbio->mirror_num;
+
+ do {
+ mirror = prev_repair_mirror(fbio, mirror);
+ btrfs_repair_bbio_failure(repair_bbio, &repair_bbio->saved_iter,
+ fs_info->sectorsize, mirror);
+ } while (mirror != fbio->bbio->mirror_num);
+
+ btrfs_repair_done(fbio);
+ bio_put(&repair_bbio->bio);
+}
+
static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio,
struct btrfs_device *dev)
{
if (mirror == fbio->bbio->mirror_num) {
btrfs_debug(fs_info, "no mirror left");
fbio->bbio->bio.bi_status = BLK_STS_IOERR;
- goto done;
+ btrfs_repair_done(fbio);
+ bio_put(&repair_bbio->bio);
+ return;
}
- btrfs_submit_bbio(repair_bbio, mirror);
+ btrfs_queue_repair_read(repair_bbio, mirror);
return;
}
- do {
- mirror = prev_repair_mirror(fbio, mirror);
- btrfs_repair_bbio_failure(repair_bbio, &repair_bbio->saved_iter,
- fs_info->sectorsize, mirror);
- } while (mirror != fbio->bbio->mirror_num);
-
-done:
- btrfs_repair_done(fbio);
- bio_put(&repair_bbio->bio);
+ INIT_WORK(&repair_bbio->end_io_work, btrfs_repair_write_work);
+ queue_work(fs_info->repair_workers, &repair_bbio->end_io_work);
}
/*
mirror = next_repair_mirror(fbio, failed_bbio->mirror_num);
btrfs_debug(fs_info, "submitting repair read to mirror %d", mirror);
- btrfs_submit_bbio(repair_bbio, mirror);
+ btrfs_queue_repair_read(repair_bbio, mirror);
return fbio;
}
destroy_workqueue(fs_info->endio_workers);
if (fs_info->rmw_workers)
destroy_workqueue(fs_info->rmw_workers);
+ if (fs_info->repair_workers)
+ destroy_workqueue(fs_info->repair_workers);
btrfs_destroy_workqueue(fs_info->endio_write_workers);
btrfs_destroy_workqueue(fs_info->delayed_workers);
btrfs_destroy_workqueue(fs_info->caching_workers);
fs_info->endio_meta_workers =
alloc_workqueue("btrfs-endio-meta", flags, max_active);
fs_info->rmw_workers = alloc_workqueue("btrfs-rmw", flags, max_active);
+ fs_info->repair_workers = alloc_workqueue("btrfs-repair", flags, max_active);
fs_info->endio_write_workers =
btrfs_alloc_workqueue(fs_info, "endio-write", flags,
max_active, 2);
fs_info->delalloc_workers && fs_info->flush_workers &&
fs_info->endio_workers && fs_info->endio_meta_workers &&
fs_info->endio_write_workers && fs_info->rmw_workers &&
+ fs_info->repair_workers &&
fs_info->caching_workers && fs_info->fixup_workers &&
fs_info->delayed_workers && fs_info->qgroup_rescan_workers &&
fs_info->discard_ctl.discard_workers)) {