Merge branch 'for-linus' of git://neil.brown.name/md

* 'for-linus' of git://neil.brown.name/md:
  md: cancel check/repair requests when recovery is needed
  Allow raid10 resync to happening in larger chunks.
  Allow faulty devices to be removed from a readonly array.
  Don't let a blocked_rdev interfere with read request in raid5/6
  Fail safely when trying to grow an array with a write-intent bitmap.
  Restore force switch of md array to readonly at reboot time.
  Make writes to md/safe_mode_delay immediately effective.

3 files changed, 59 insertions, 15 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index c7aae66c6f9b..8cfadc5bd2ba 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2393,6 +2393,8 @@ static void analyze_sbs(mddev_t * mddev)
 
 }
 
+static void md_safemode_timeout(unsigned long data);
+
 static ssize_t
 safe_delay_show(mddev_t *mddev, char *page)
 {
@@ -2432,9 +2434,12 @@ safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len)
 	if (msec == 0)
 		mddev->safemode_delay = 0;
 	else {
+		unsigned long old_delay = mddev->safemode_delay;
 		mddev->safemode_delay = (msec*HZ)/1000;
 		if (mddev->safemode_delay == 0)
 			mddev->safemode_delay = 1;
+		if (mddev->safemode_delay < old_delay)
+			md_safemode_timeout((unsigned long)mddev);
 	}
 	return len;
 }
@@ -4634,6 +4639,11 @@ static int update_size(mddev_t *mddev, sector_t num_sectors)
 	 */
 	if (mddev->sync_thread)
 		return -EBUSY;
+	if (mddev->bitmap)
+		/* Sorry, cannot grow a bitmap yet, just remove it,
+		 * grow, and re-add.
+		 */
+		return -EBUSY;
 	rdev_for_each(rdev, tmp, mddev) {
 		sector_t avail;
 		avail = rdev->size * 2;
@@ -5993,7 +6003,7 @@ static int remove_and_add_spares(mddev_t *mddev)
 			}
 		}
 
-	if (mddev->degraded) {
+	if (mddev->degraded && ! mddev->ro) {
 		rdev_for_each(rdev, rtmp, mddev) {
 			if (rdev->raid_disk >= 0 &&
 			    !test_bit(In_sync, &rdev->flags) &&
@@ -6067,6 +6077,8 @@ void md_check_recovery(mddev_t *mddev)
 		flush_signals(current);
 	}
 
+	if (mddev->ro && !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
+		return;
 	if ( ! (
 		(mddev->flags && !mddev->external) ||
 		test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
@@ -6080,6 +6092,15 @@ void md_check_recovery(mddev_t *mddev)
 	if (mddev_trylock(mddev)) {
 		int spares = 0;
 
+		if (mddev->ro) {
+			/* Only thing we do on a ro array is remove
+			 * failed devices.
+			 */
+			remove_and_add_spares(mddev);
+			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			goto unlock;
+		}
+
 		if (!mddev->external) {
 			int did_change = 0;
 			spin_lock_irq(&mddev->write_lock);
@@ -6117,7 +6138,8 @@ void md_check_recovery(mddev_t *mddev)
 			/* resync has finished, collect result */
 			md_unregister_thread(mddev->sync_thread);
 			mddev->sync_thread = NULL;
-			if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+			if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
+			    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
 				/* success...*/
 				/* activate any spares */
 				if (mddev->pers->spare_active(mddev))
@@ -6169,6 +6191,7 @@ void md_check_recovery(mddev_t *mddev)
 		} else if ((spares = remove_and_add_spares(mddev))) {
 			clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 			clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+			clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
 			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		} else if (mddev->recovery_cp < MaxSector) {
 			set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
@@ -6232,7 +6255,11 @@ static int md_notify_reboot(struct notifier_block *this,
 
 		for_each_mddev(mddev, tmp)
 			if (mddev_trylock(mddev)) {
-				do_md_stop (mddev, 1, 0);
+				/* Force a switch to readonly even array
+				 * appears to still be in use.  Hence
+				 * the '100'.
+				 */
+				do_md_stop (mddev, 1, 100);
 				mddev_unlock(mddev);
 			}
 		/*
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index d41bebb6da0f..e34cd0e62473 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -76,11 +76,13 @@ static void r10bio_pool_free(void *r10_bio, void *data)
 	kfree(r10_bio);
 }
 
+/* Maximum size of each resync request */
 #define RESYNC_BLOCK_SIZE (64*1024)
-//#define RESYNC_BLOCK_SIZE PAGE_SIZE
-#define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
 #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
-#define RESYNC_WINDOW (2048*1024)
+/* amount of memory to reserve for resync requests */
+#define RESYNC_WINDOW (1024*1024)
+/* maximum number of concurrent requests, memory permitting */
+#define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE)
 
 /*
  * When performing a resync, we need to read and compare, so
@@ -690,7 +692,6 @@ static int flush_pending_writes(conf_t *conf)
  *    there is no normal IO happeing.  It must arrange to call
  *    lower_barrier when the particular background IO completes.
  */
-#define RESYNC_DEPTH 32
 
 static void raise_barrier(conf_t *conf, int force)
 {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 40e939675657..224de022e7c5 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2568,10 +2568,10 @@ static bool handle_stripe5(struct stripe_head *sh)
 		if (dev->written)
 			s.written++;
 		rdev = rcu_dereference(conf->disks[i].rdev);
-		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+		if (blocked_rdev == NULL &&
+		    rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
 			blocked_rdev = rdev;
 			atomic_inc(&rdev->nr_pending);
-			break;
 		}
 		if (!rdev || !test_bit(In_sync, &rdev->flags)) {
 			/* The ReadError flag will just be confusing now */
@@ -2588,8 +2588,14 @@ static bool handle_stripe5(struct stripe_head *sh)
 	rcu_read_unlock();
 
 	if (unlikely(blocked_rdev)) {
-		set_bit(STRIPE_HANDLE, &sh->state);
-		goto unlock;
+		if (s.syncing || s.expanding || s.expanded ||
+		    s.to_write || s.written) {
+			set_bit(STRIPE_HANDLE, &sh->state);
+			goto unlock;
+		}
+		/* There is nothing for the blocked_rdev to block */
+		rdev_dec_pending(blocked_rdev, conf->mddev);
+		blocked_rdev = NULL;
 	}
 
 	if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
@@ -2832,10 +2838,10 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 		if (dev->written)
 			s.written++;
 		rdev = rcu_dereference(conf->disks[i].rdev);
-		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+		if (blocked_rdev == NULL &&
+		    rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
 			blocked_rdev = rdev;
 			atomic_inc(&rdev->nr_pending);
-			break;
 		}
 		if (!rdev || !test_bit(In_sync, &rdev->flags)) {
 			/* The ReadError flag will just be confusing now */
@@ -2853,9 +2859,16 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	rcu_read_unlock();
 
 	if (unlikely(blocked_rdev)) {
-		set_bit(STRIPE_HANDLE, &sh->state);
-		goto unlock;
+		if (s.syncing || s.expanding || s.expanded ||
+		    s.to_write || s.written) {
+			set_bit(STRIPE_HANDLE, &sh->state);
+			goto unlock;
+		}
+		/* There is nothing for the blocked_rdev to block */
+		rdev_dec_pending(blocked_rdev, conf->mddev);
+		blocked_rdev = NULL;
 	}
+
 	pr_debug("locked=%d uptodate=%d to_read=%d"
 	       " to_write=%d failed=%d failed_num=%d,%d\n",
 	       s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
@@ -4446,6 +4459,9 @@ static int raid5_check_reshape(mddev_t *mddev)
 		return -EINVAL; /* Cannot shrink array or change level yet */
 	if (mddev->delta_disks == 0)
 		return 0; /* nothing to do */
+	if (mddev->bitmap)
+		/* Cannot grow a bitmap yet */
+		return -EBUSY;
 
 	/* Can only proceed if there are plenty of stripe_heads.
 	 * We need a minimum of one full stripe,, and for sensible progress