raid5: add a per-stripe lock

Add a per-stripe lock to protect stripe specific data. The purpose is to reduce lock contention of conf->device_lock.

stripe ->toread, ->towrite are protected by per-stripe lock. Accessing bio list of the stripe is always serialized by this lock, so adding bio to the lists (add_stripe_bio()) and removing bio from the lists (like ops_run_biofill()) not race.

If bio in ->read, ->written ... list are not shared by multiple stripes, we don't need any lock to protect ->read, ->written, because STRIPE_ACTIVE will protect them. If the bio are shared, there are two protections:
1. bi_phys_segments acts as a reference count
2. traverse the list uses r5_next_bio, which makes traverse never access bio not belonging to the stripe

Let's have an example:

|  stripe1 |  stripe2    |  stripe3  |
...bio1......|bio2|bio3|....bio4.....

stripe2 has 4 bios, when it's finished, it will decrement bi_phys_segments for all bios, but only end_bio for bio2 and bio3. bio1->bi_next still points to bio2, but this doesn't matter. When stripe1 is finished, it will not touch bio2 because of r5_next_bio check. Next time stripe1 will end_bio for bio1 and stripe3 will end_bio bio4.

before add_stripe_bio() addes a bio to a stripe, we already increament the bio bi_phys_segments, so don't worry other stripes release the bio.

Signed-off-by Shaohua Li <[email protected]>

---
drivers/md/raid5.c | 35 +++++++++++++++++++----------------
drivers/md/raid5.h | 1 +

2 files changed, 20 insertions(+), 16 deletions(-)

Index: linux/drivers/md/raid5.c
===================================================================

drivers/md/raid5.c +19 -16

@@ -755,14 +755,12 @@ static void ops_complete_biofill(void *s
 {
 	struct stripe_head *sh = stripe_head_ref;
 	struct bio *return_bi = NULL;
-	struct r5conf *conf = sh->raid_conf;
 	int i;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
 	/* clear completed biofills */
-	spin_lock_irq(&conf->device_lock);
 	for (i = sh->disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 

@@ -788,7 +786,6 @@ static void ops_complete_biofill(void *s
 			}
 		}
 	}
-	spin_unlock_irq(&conf->device_lock);
 	clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
 
 	return_io(return_bi);

@@ -800,7 +797,6 @@ static void ops_complete_biofill(void *s
 static void ops_run_biofill(struct stripe_head *sh)
 {
 	struct dma_async_tx_descriptor *tx = NULL;
-	struct r5conf *conf = sh->raid_conf;
 	struct async_submit_ctl submit;
 	int i;
 

@@ -811,10 +807,10 @@ static void ops_run_biofill(struct strip
 		struct r5dev *dev = &sh->dev[i];
 		if (test_bit(R5_Wantfill, &dev->flags)) {
 			struct bio *rbi;
-			spin_lock_irq(&conf->device_lock);
+			spin_lock_irq(&sh->stripe_lock);
 			dev->read = rbi = dev->toread;
 			dev->toread = NULL;
-			spin_unlock_irq(&conf->device_lock);
+			spin_unlock_irq(&sh->stripe_lock);
 			while (rbi && rbi->bi_sector <
 				dev->sector + STRIPE_SECTORS) {
 				tx = async_copy_data(0, rbi, dev->page,

@@ -1150,12 +1146,12 @@ ops_run_biodrain(struct stripe_head *sh,
 		if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
 			struct bio *wbi;
 
-			spin_lock_irq(&sh->raid_conf->device_lock);
+			spin_lock_irq(&sh->stripe_lock);
 			chosen = dev->towrite;
 			dev->towrite = NULL;
 			BUG_ON(dev->written);
 			wbi = dev->written = chosen;
-			spin_unlock_irq(&sh->raid_conf->device_lock);
+			spin_unlock_irq(&sh->stripe_lock);
 
 			while (wbi && wbi->bi_sector <
 				dev->sector + STRIPE_SECTORS) {

@@ -1460,6 +1456,8 @@ static int grow_one_stripe(struct r5conf
 	init_waitqueue_head(&sh->ops.wait_for_ops);
 	#endif
 
+	spin_lock_init(&sh->stripe_lock);
+
 	if (grow_buffers(sh)) {
 		shrink_buffers(sh);
 		kmem_cache_free(conf->slab_cache, sh);

@@ -2346,8 +2344,15 @@ static int add_stripe_bio(struct stripe_
 		(unsigned long long)bi->bi_sector,
 		(unsigned long long)sh->sector);
 
-
-	spin_lock_irq(&conf->device_lock);
+	/*
+	 * If several bio share a stripe. The bio bi_phys_segments acts as a
+	 * reference count to avoid race. The reference count should already be
+	 * increased before this function is called (for example, in
+	 * make_request()), so other bio sharing this stripe will not free the
+	 * stripe. If a stripe is owned by one stripe, the stripe lock will
+	 * protect it.
+	 */
+	spin_lock_irq(&sh->stripe_lock);
 	if (forwrite) {
 		bip = &sh->dev[dd_idx].towrite;
 		if (*bip == NULL)

@@ -2381,7 +2386,7 @@ static int add_stripe_bio(struct stripe_
 		if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
 			set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
 	}
-	spin_unlock_irq(&conf->device_lock);
+	spin_unlock_irq(&sh->stripe_lock);
 
 	pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
 		(unsigned long long)(*bip)->bi_sector,

@@ -2397,7 +2402,7 @@ static int add_stripe_bio(struct stripe_
 
 overlap:
 	set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
-	spin_unlock_irq(&conf->device_lock);
+	spin_unlock_irq(&sh->stripe_lock);
 	return 0;
 }
 

@@ -2447,7 +2452,7 @@ handle_failed_stripe(struct r5conf *conf
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 		}
-		spin_lock_irq(&conf->device_lock);
+		spin_lock_irq(&sh->stripe_lock);
 		/* fail all writes first */
 		bi = sh->dev[i].towrite;
 		sh->dev[i].towrite = NULL;

@@ -2455,7 +2460,7 @@ handle_failed_stripe(struct r5conf *conf
 			s->to_write--;
 			bitmap_end = 1;
 		}
-		spin_unlock_irq(&conf->device_lock);
+		spin_unlock_irq(&sh->stripe_lock);
 
 		if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 			wake_up(&conf->wait_for_overlap);

@@ -3185,7 +3190,6 @@ static void analyse_stripe(struct stripe
 
 	/* Now to look around and see what can be done */
 	rcu_read_lock();
-	spin_lock_irq(&conf->device_lock);
 	for (i=disks; i--; ) {
 		struct md_rdev *rdev;
 		sector_t first_bad;

@@ -3331,7 +3335,6 @@ static void analyse_stripe(struct stripe
 				do_recovery = 1;
 		}
 	}
-	spin_unlock_irq(&conf->device_lock);
 	if (test_bit(STRIPE_SYNCING, &sh->state)) {
 		/* If there is a failed device being replaced,
 		 *     we must be recovering.

Index: linux/drivers/md/raid5.h
===================================================================