Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull md updates from Shaohua Li:
 "Mainly fixes bugs and improves performance:

   - Improve scalability for raid1 from Coly

   - Improve raid5-cache read performance, disk efficiency and IO
     pattern from Song and me

   - Fix a race condition of disk hotplug for linear from Coly

   - A few cleanup patches from Ming and Byungchul

   - Fix a memory leak from Neil

   - Fix WRITE SAME IO failure from me

   - Add doc for raid5-cache from me"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (23 commits)
  md/raid1: fix write behind issues introduced by bio_clone_bioset_partial
  md/raid1: handle flush request correctly
  md/linear: shutup lockdep warnning
  md/raid1: fix a use-after-free bug
  RAID1: avoid unnecessary spin locks in I/O barrier code
  RAID1: a new I/O barrier implementation to remove resync window
  md/raid5: Don't reinvent the wheel but use existing llist API
  md: fast clone bio in bio_clone_mddev()
  md: remove unnecessary check on mddev
  md/raid1: use bio_clone_bioset_partial() in case of write behind
  md: fail if mddev->bio_set can't be created
  block: introduce bio_clone_bioset_partial()
  md: disable WRITE SAME if it fails in underlayer disks
  md/raid5-cache: exclude reclaiming stripes in reclaim check
  md/raid5-cache: stripe reclaim only counts valid stripes
  MD: add doc for raid5-cache
  Documentation: move MD related doc into a separate dir
  md: ensure md devices are freed before module is unloaded.
  md/r5cache: improve journal device efficiency
  md/r5cache: enable chunk_aligned_read with write back cache
  ...

1 files changed, 36 insertions, 5 deletions

diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index f1c7bbac31a5..3e38e0207a3e 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -53,18 +53,26 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 	return conf->disks + lo;
 }
 
+/*
+ * In linear_congested() conf->raid_disks is used as a copy of
+ * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks
+ * and conf->disks[] are created in linear_conf(), they are always
+ * consitent with each other, but mddev->raid_disks does not.
+ */
 static int linear_congested(struct mddev *mddev, int bits)
 {
 	struct linear_conf *conf;
 	int i, ret = 0;
 
-	conf = mddev->private;
+	rcu_read_lock();
+	conf = rcu_dereference(mddev->private);
 
-	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
+	for (i = 0; i < conf->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
 		ret |= bdi_congested(q->backing_dev_info, bits);
 	}
 
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -144,6 +152,19 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 			conf->disks[i-1].end_sector +
 			conf->disks[i].rdev->sectors;
 
+	/*
+	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
+	 * keep a copy of mddev->raid_disks in struct linear_conf is,
+	 * mddev->raid_disks may not be consistent with pointers number of
+	 * conf->disks[] when it is updated in linear_add() and used to
+	 * iterate old conf->disks[] earray in linear_congested().
+	 * Here conf->raid_disks is always consitent with number of
+	 * pointers in conf->disks[] array, and mddev->private is updated
+	 * with rcu_assign_pointer() in linear_addr(), such race can be
+	 * avoided.
+	 */
+	conf->raid_disks = raid_disks;
+
 	return conf;
 
 out:
@@ -196,15 +217,24 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	if (!newconf)
 		return -ENOMEM;
 
+	/* newconf->raid_disks already keeps a copy of * the increased
+	 * value of mddev->raid_disks, WARN_ONCE() is just used to make
+	 * sure of this. It is possible that oldconf is still referenced
+	 * in linear_congested(), therefore kfree_rcu() is used to free
+	 * oldconf until no one uses it anymore.
+	 */
 	mddev_suspend(mddev);
-	oldconf = mddev->private;
+	oldconf = rcu_dereference_protected(mddev->private,
+			lockdep_is_held(&mddev->reconfig_mutex));
 	mddev->raid_disks++;
-	mddev->private = newconf;
+	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
+		"copied raid_disks doesn't match mddev->raid_disks");
+	rcu_assign_pointer(mddev->private, newconf);
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev_resume(mddev);
 	revalidate_disk(mddev->gendisk);
-	kfree(oldconf);
+	kfree_rcu(oldconf, rcu);
 	return 0;
 }
 
@@ -262,6 +292,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 				trace_block_bio_remap(bdev_get_queue(split->bi_bdev),
 						      split, disk_devt(mddev->gendisk),
 						      bio_sector);
+			mddev_check_writesame(mddev, split);
 			generic_make_request(split);
 		}
 	} while (split != bio);