1 files changed, 19 insertions, 12 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 90380064afc7..7143dbd2a38c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2058,8 +2058,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 	struct raid5_percpu *percpu;
 	unsigned long cpu;
 
-	cpu = get_cpu();
+	cpu = get_cpu_light();
 	percpu = per_cpu_ptr(conf->percpu, cpu);
+	spin_lock(&percpu->lock);
 	if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
 		ops_run_biofill(sh);
 		overlap_clear++;
@@ -2118,7 +2119,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 			if (test_and_clear_bit(R5_Overlap, &dev->flags))
 				wake_up(&sh->raid_conf->wait_for_overlap);
 		}
-	put_cpu();
+	spin_unlock(&percpu->lock);
+	put_cpu_light();
 }
 
 static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh)
@@ -2228,14 +2230,19 @@ static int grow_stripes(struct r5conf *conf, int num)
  * of the P and Q blocks.
  */
 static int scribble_alloc(struct raid5_percpu *percpu,
-			  int num, int cnt, gfp_t flags)
+			  int num, int cnt)
 {
 	size_t obj_size =
 		sizeof(struct page *) * (num+2) +
 		sizeof(addr_conv_t) * (num+2);
 	void *scribble;
 
-	scribble = kvmalloc_array(cnt, obj_size, flags);
+	/*
+	 * If here is in raid array suspend context, it is in memalloc noio
+	 * context as well, there is no potential recursive memory reclaim
+	 * I/Os with the GFP_KERNEL flag.
+	 */
+	scribble = kvmalloc_array(cnt, obj_size, GFP_KERNEL);
 	if (!scribble)
 		return -ENOMEM;
 
@@ -2267,8 +2274,7 @@ static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
 
 		percpu = per_cpu_ptr(conf->percpu, cpu);
 		err = scribble_alloc(percpu, new_disks,
-				     new_sectors / STRIPE_SECTORS,
-				     GFP_NOIO);
+				     new_sectors / STRIPE_SECTORS);
 		if (err)
 			break;
 	}
@@ -3594,6 +3600,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 	 * is missing/faulty, then we need to read everything we can.
 	 */
 	if (sh->raid_conf->level != 6 &&
+	    sh->raid_conf->rmw_level != PARITY_DISABLE_RMW &&
 	    sh->sector < sh->raid_conf->mddev->recovery_cp)
 		/* reconstruct-write isn't being forced */
 		return 0;
@@ -4830,7 +4837,7 @@ static void handle_stripe(struct stripe_head *sh)
 	 * or to load a block that is being partially written.
 	 */
 	if (s.to_read || s.non_overwrite
-	    || (conf->level == 6 && s.to_write && s.failed)
+	    || (s.to_write && s.failed)
 	    || (s.syncing && (s.uptodate + s.compute < disks))
 	    || s.replacing
 	    || s.expanding)
@@ -5588,8 +5595,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 		if (ret == 0)
 			return true;
 		if (ret == -ENODEV) {
-			md_flush_request(mddev, bi);
-			return true;
+			if (md_flush_request(mddev, bi))
+				return true;
 		}
 		/* ret == -EAGAIN, fallback */
 		/*
@@ -5722,7 +5729,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 				do_flush = false;
 			}
 
-			if (!sh->batch_head)
+			if (!sh->batch_head || sh == sh->batch_head)
 				set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			if ((!sh->batch_head || sh == sh->batch_head) &&
@@ -6761,8 +6768,7 @@ static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu
 			       conf->previous_raid_disks),
 			   max(conf->chunk_sectors,
 			       conf->prev_chunk_sectors)
-			   / STRIPE_SECTORS,
-			   GFP_KERNEL)) {
+			   / STRIPE_SECTORS)) {
 		free_scratch_buffer(conf, percpu);
 		return -ENOMEM;
 	}
@@ -6817,6 +6823,7 @@ static int raid456_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
 			__func__, cpu);
 		return -ENOMEM;
 	}
+	spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock);
 	return 0;
 }