Merge tag 'md/3.13' of git://neil.brown.name/md

Pull md update from Neil Brown:
 "Mostly optimisations and obscure bug fixes.
   - raid5 gets less lock contention
   - raid1 gets less contention between normal-io and resync-io during
     resync"

* tag 'md/3.13' of git://neil.brown.name/md:
  md/raid5: Use conf->device_lock protect changing of multi-thread resources.
  md/raid5: Before freeing old multi-thread worker, it should flush them.
  md/raid5: For stripe with R5_ReadNoMerge, we replace REQ_FLUSH with REQ_NOMERGE.
  UAPI: include <asm/byteorder.h> in linux/raid/md_p.h
  raid1: Rewrite the implementation of iobarrier.
  raid1: Add some macros to make code clearly.
  raid1: Replace raise_barrier/lower_barrier with freeze_array/unfreeze_array when reconfiguring the array.
  raid1: Add a field array_frozen to indicate whether raid in freeze state.
  md: Convert use of typedef ctl_table to struct ctl_table
  md/raid5: avoid deadlock when raid5 array has unack badblocks during md_stop_writes.
  md: use MD_RECOVERY_INTR instead of kthread_should_stop in resync thread.
  md: fix some places where mddev_lock return value is not checked.
  raid5: Retry R5_ReadNoMerge flag when hit a read error.
  raid5: relieve lock contention in get_active_stripe()
  raid5: relieve lock contention in get_active_stripe()
  wait: add wait_event_cmd()
  md/raid5.c: add proper locking to error path of raid5_start_reshape.
  md: fix calculation of stacking limits on level change.
  raid5: Use slow_path to release stripe when mddev->thread is null

1 files changed, 15 insertions, 1 deletions

diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index b42e6b462eda..01ad8ae8f578 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -205,6 +205,7 @@ struct stripe_head {
         short                   pd_idx;         /* parity disk index */
         short                   qd_idx;         /* 'Q' disk index for raid6 */
         short                   ddf_layout;/* use DDF ordering to calculate Q */
+        short                   hash_lock_index;
         unsigned long           state;          /* state flags */
         atomic_t                count;        /* nr of active thread/requests */
         int                     bm_seq; /* sequence number for bitmap flushes */
@@ -367,9 +368,18 @@ struct disk_info {
         struct md_rdev  *rdev, *replacement;
 };
 
+/* NOTE NR_STRIPE_HASH_LOCKS must remain below 64.
+ * This is because we sometimes take all the spinlocks
+ * and creating that much locking depth can cause
+ * problems.
+ */
+#define NR_STRIPE_HASH_LOCKS 8
+#define STRIPE_HASH_LOCKS_MASK (NR_STRIPE_HASH_LOCKS - 1)
+
 struct r5worker {
         struct work_struct work;
         struct r5worker_group *group;
+        struct list_head temp_inactive_list[NR_STRIPE_HASH_LOCKS];
         bool working;
 };
 
@@ -382,6 +392,8 @@ struct r5worker_group {
 
 struct r5conf {
         struct hlist_head       *stripe_hashtbl;
+        /* only protect corresponding hash list and inactive_list */
+        spinlock_t              hash_locks[NR_STRIPE_HASH_LOCKS];
         struct mddev            *mddev;
         int                     chunk_sectors;
         int                     level, algorithm;
@@ -462,7 +474,8 @@ struct r5conf {
          * Free stripes pool
          */
         atomic_t                active_stripes;
-        struct list_head        inactive_list;
+        struct list_head        inactive_list[NR_STRIPE_HASH_LOCKS];
+        atomic_t                empty_inactive_list_nr;
         struct llist_head       released_stripes;
         wait_queue_head_t       wait_for_stripe;
         wait_queue_head_t       wait_for_overlap;
@@ -477,6 +490,7 @@ struct r5conf {
          * the new thread here until we fully activate the array.
          */
         struct md_thread        *thread;
+        struct list_head        temp_inactive_list[NR_STRIPE_HASH_LOCKS];
         struct r5worker_group   *worker_groups;
         int                     group_cnt;
         int                     worker_cnt_per_group;