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

Pull MD update from Shaohua Li:
 "This update mostly includes bug fixes:

   - md-cluster now supports raid10 from Guoqing

   - raid5 PPL fixes from Artur

   - badblock regression fix from Bo

   - suspend hang related fixes from Neil

   - raid5 reshape fixes from Neil

   - raid1 freeze deadlock fix from Nate

   - memleak fixes from Zdenek

   - bitmap related fixes from Me and Tao

   - other fixes and cleanups"

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (33 commits)
  md: free unused memory after bitmap resize
  md: release allocated bitset sync_set
  md/bitmap: clear BITMAP_WRITE_ERROR bit before writing it to sb
  md: be cautious about using ->curr_resync_completed for ->recovery_offset
  badblocks: fix wrong return value in badblocks_set if badblocks are disabled
  md: don't check MD_SB_CHANGE_CLEAN in md_allow_write
  md-cluster: update document for raid10
  md: remove redundant variable q
  raid1: remove obsolete code in raid1_write_request
  md-cluster: Use a small window for raid10 resync
  md-cluster: Suspend writes in RAID10 if within range
  md-cluster/raid10: set "do_balance = 0" if area is resyncing
  md: use lockdep_assert_held
  raid1: prevent freeze_array/wait_all_barriers deadlock
  md: use TASK_IDLE instead of blocking signals
  md: remove special meaning of ->quiesce(.., 2)
  md: allow metadata update while suspending.
  md: use mddev_suspend/resume instead of ->quiesce()
  md: move suspend_hi/lo handling into core md code
  md: don't call bitmap_create() while array is quiesced.
  ...

1 files changed, 42 insertions, 37 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7d9a50eed9db..31dc25e2871a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -55,7 +55,6 @@
 #include <linux/ratelimit.h>
 #include <linux/nodemask.h>
 #include <linux/flex_array.h>
-#include <linux/sched/signal.h>
 
 #include <trace/events/block.h>
 #include <linux/list_sort.h>
@@ -63,7 +62,7 @@
 #include "md.h"
 #include "raid5.h"
 #include "raid0.h"
-#include "bitmap.h"
+#include "md-bitmap.h"
 #include "raid5-log.h"
 
 #define UNSUPPORTED_MDDEV_FLAGS	(1L << MD_FAILFAST_SUPPORTED)
@@ -1818,8 +1817,11 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
 		struct r5dev *dev = &sh->dev[i];
 
 		if (dev->written || i == pd_idx || i == qd_idx) {
-			if (!discard && !test_bit(R5_SkipCopy, &dev->flags))
+			if (!discard && !test_bit(R5_SkipCopy, &dev->flags)) {
 				set_bit(R5_UPTODATE, &dev->flags);
+				if (test_bit(STRIPE_EXPAND_READY, &sh->state))
+					set_bit(R5_Expanded, &dev->flags);
+			}
 			if (fua)
 				set_bit(R5_WantFUA, &dev->flags);
 			if (sync)
@@ -5682,28 +5684,6 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 				goto retry;
 			}
 
-			if (rw == WRITE &&
-			    logical_sector >= mddev->suspend_lo &&
-			    logical_sector < mddev->suspend_hi) {
-				raid5_release_stripe(sh);
-				/* As the suspend_* range is controlled by
-				 * userspace, we want an interruptible
-				 * wait.
-				 */
-				prepare_to_wait(&conf->wait_for_overlap,
-						&w, TASK_INTERRUPTIBLE);
-				if (logical_sector >= mddev->suspend_lo &&
-				    logical_sector < mddev->suspend_hi) {
-					sigset_t full, old;
-					sigfillset(&full);
-					sigprocmask(SIG_BLOCK, &full, &old);
-					schedule();
-					sigprocmask(SIG_SETMASK, &old, NULL);
-					do_prepare = true;
-				}
-				goto retry;
-			}
-
 			if (test_bit(STRIPE_EXPANDING, &sh->state) ||
 			    !add_stripe_bio(sh, bi, dd_idx, rw, previous)) {
 				/* Stripe is busy expanding or
@@ -5758,6 +5738,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	 */
 	struct r5conf *conf = mddev->private;
 	struct stripe_head *sh;
+	struct md_rdev *rdev;
 	sector_t first_sector, last_sector;
 	int raid_disks = conf->previous_raid_disks;
 	int data_disks = raid_disks - conf->max_degraded;
@@ -5880,6 +5861,15 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 			return 0;
 		mddev->reshape_position = conf->reshape_progress;
 		mddev->curr_resync_completed = sector_nr;
+		if (!mddev->reshape_backwards)
+			/* Can update recovery_offset */
+			rdev_for_each(rdev, mddev)
+				if (rdev->raid_disk >= 0 &&
+				    !test_bit(Journal, &rdev->flags) &&
+				    !test_bit(In_sync, &rdev->flags) &&
+				    rdev->recovery_offset < sector_nr)
+					rdev->recovery_offset = sector_nr;
+
 		conf->reshape_checkpoint = jiffies;
 		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		md_wakeup_thread(mddev->thread);
@@ -5978,6 +5968,14 @@ finish:
 			goto ret;
 		mddev->reshape_position = conf->reshape_progress;
 		mddev->curr_resync_completed = sector_nr;
+		if (!mddev->reshape_backwards)
+			/* Can update recovery_offset */
+			rdev_for_each(rdev, mddev)
+				if (rdev->raid_disk >= 0 &&
+				    !test_bit(Journal, &rdev->flags) &&
+				    !test_bit(In_sync, &rdev->flags) &&
+				    rdev->recovery_offset < sector_nr)
+					rdev->recovery_offset = sector_nr;
 		conf->reshape_checkpoint = jiffies;
 		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		md_wakeup_thread(mddev->thread);
@@ -7156,6 +7154,13 @@ static int raid5_run(struct mddev *mddev)
 			min_offset_diff = diff;
 	}
 
+	if ((test_bit(MD_HAS_JOURNAL, &mddev->flags) || journal_dev) &&
+	    (mddev->bitmap_info.offset || mddev->bitmap_info.file)) {
+		pr_notice("md/raid:%s: array cannot have both journal and bitmap\n",
+			  mdname(mddev));
+		return -EINVAL;
+	}
+
 	if (mddev->reshape_position != MaxSector) {
 		/* Check that we can continue the reshape.
 		 * Difficulties arise if the stripe we would write to
@@ -7958,6 +7963,7 @@ static void end_reshape(struct r5conf *conf)
 {
 
 	if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
+		struct md_rdev *rdev;
 
 		spin_lock_irq(&conf->device_lock);
 		conf->previous_raid_disks = conf->raid_disks;
@@ -7965,6 +7971,11 @@ static void end_reshape(struct r5conf *conf)
 		smp_wmb();
 		conf->reshape_progress = MaxSector;
 		conf->mddev->reshape_position = MaxSector;
+		rdev_for_each(rdev, conf->mddev)
+			if (rdev->raid_disk >= 0 &&
+			    !test_bit(Journal, &rdev->flags) &&
+			    !test_bit(In_sync, &rdev->flags))
+				rdev->recovery_offset = MaxSector;
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 
@@ -8020,16 +8031,12 @@ static void raid5_finish_reshape(struct mddev *mddev)
 	}
 }
 
-static void raid5_quiesce(struct mddev *mddev, int state)
+static void raid5_quiesce(struct mddev *mddev, int quiesce)
 {
 	struct r5conf *conf = mddev->private;
 
-	switch(state) {
-	case 2: /* resume for a suspend */
-		wake_up(&conf->wait_for_overlap);
-		break;
-
-	case 1: /* stop all writes */
+	if (quiesce) {
+		/* stop all writes */
 		lock_all_device_hash_locks_irq(conf);
 		/* '2' tells resync/reshape to pause so that all
 		 * active stripes can drain
@@ -8045,17 +8052,15 @@ static void raid5_quiesce(struct mddev *mddev, int state)
 		unlock_all_device_hash_locks_irq(conf);
 		/* allow reshape to continue */
 		wake_up(&conf->wait_for_overlap);
-		break;
-
-	case 0: /* re-enable writes */
+	} else {
+		/* re-enable writes */
 		lock_all_device_hash_locks_irq(conf);
 		conf->quiesce = 0;
 		wake_up(&conf->wait_for_quiescent);
 		wake_up(&conf->wait_for_overlap);
 		unlock_all_device_hash_locks_irq(conf);
-		break;
 	}
-	r5l_quiesce(conf->log, state);
+	r5l_quiesce(conf->log, quiesce);
 }
 
 static void *raid45_takeover_raid0(struct mddev *mddev, int level)