Merge tag 'md/4.4' of git://neil.brown.name/md

Pull md updates from Neil Brown:
 "Two major components to this update.

   1) The clustered-raid1 support from SUSE is nearly complete.  There
      are a few outstanding issues being worked on.  Maybe half a dozen
      patches will bring this to a usable state.

   2) The first stage of journalled-raid5 support from Facebook makes an
      appearance.  With a journal device configured (typically NVRAM or
      SSD), the "RAID5 write hole" should be closed - a crash during
      degraded operations cannot result in data corruption.

      The next stage will be to use the journal as a write-behind cache
      so that latency can be reduced and in some cases throughput
      increased by performing more full-stripe writes.

* tag 'md/4.4' of git://neil.brown.name/md: (66 commits)
  MD: when RAID journal is missing/faulty, block RESTART_ARRAY_RW
  MD: set journal disk ->raid_disk
  MD: kick out journal disk if it's not fresh
  raid5-cache: start raid5 readonly if journal is missing
  MD: add new bit to indicate raid array with journal
  raid5-cache: IO error handling
  raid5: journal disk can't be removed
  raid5-cache: add trim support for log
  MD: fix info output for journal disk
  raid5-cache: use bio chaining
  raid5-cache: small log->seq cleanup
  raid5-cache: new helper: r5_reserve_log_entry
  raid5-cache: inline r5l_alloc_io_unit into r5l_new_meta
  raid5-cache: take rdev->data_offset into account early on
  raid5-cache: refactor bio allocation
  raid5-cache: clean up r5l_get_meta
  raid5-cache: simplify state machine when caches flushes are not needed
  raid5-cache: factor out a helper to run all stripes for an I/O unit
  raid5-cache: rename flushed_ios to finished_ios
  raid5-cache: free I/O units earlier
  ...

1 files changed, 15 insertions, 2 deletions

diff --git a/drivers/md/md.h b/drivers/md/md.h
index ab339571e57f..2bea51edfab7 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -87,10 +87,16 @@ struct md_rdev {
 					 * array and could again if we did a partial
 					 * resync from the bitmap
 					 */
-	sector_t	recovery_offset;/* If this device has been partially
+	union {
+		sector_t recovery_offset;/* If this device has been partially
 					 * recovered, this is where we were
 					 * up to.
 					 */
+		sector_t journal_tail;	/* If this device is a journal device,
+					 * this is the journal tail (journal
+					 * recovery start point)
+					 */
+	};
 
 	atomic_t	nr_pending;	/* number of pending requests.
 					 * only maintained for arrays that
@@ -172,6 +178,11 @@ enum flag_bits {
 				 * This device is seen locally but not
 				 * by the whole cluster
 				 */
+	Journal,		/* This device is used as journal for
+				 * raid-5/6.
+				 * Usually, this device should be faster
+				 * than other devices in the array
+				 */
 };
 
 #define BB_LEN_MASK	(0x00000000000001FFULL)
@@ -221,6 +232,8 @@ struct mddev {
 #define MD_STILL_CLOSED	4	/* If set, then array has not been opened since
 				 * md_ioctl checked on it.
 				 */
+#define MD_JOURNAL_CLEAN 5	/* A raid with journal is already clean */
+#define MD_HAS_JOURNAL	6	/* The raid array has journal feature set */
 
 	int				suspended;
 	atomic_t			active_io;
@@ -658,7 +671,7 @@ extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 				   struct mddev *mddev);
 
 extern void md_unplug(struct blk_plug_cb *cb, bool from_schedule);
-extern void md_reload_sb(struct mddev *mddev);
+extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
 extern void md_kick_rdev_from_array(struct md_rdev * rdev);
 struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);