1 files changed, 41 insertions, 44 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 56e24c072b62..40b35be34f8d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -494,7 +494,6 @@ static void raid1_end_write_request(struct bio *bio, int error)
 		bio_put(to_put);
 }
 
-
 /*
  * This routine returns the disk from which the requested read should
  * be done. There is a per-array 'next expected sequential IO' sector
@@ -540,11 +539,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	has_nonrot_disk = 0;
 	choose_next_idle = 0;
 
-	if (conf->mddev->recovery_cp < MaxSector &&
-	    (this_sector + sectors >= conf->next_resync))
-		choose_first = 1;
-	else
-		choose_first = 0;
+	choose_first = (conf->mddev->recovery_cp < this_sector + sectors);
 
 	for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
 		sector_t dist;
@@ -831,7 +826,7 @@ static void flush_pending_writes(struct r1conf *conf)
  *    there is no normal IO happeing.  It must arrange to call
  *    lower_barrier when the particular background IO completes.
  */
-static void raise_barrier(struct r1conf *conf)
+static void raise_barrier(struct r1conf *conf, sector_t sector_nr)
 {
 	spin_lock_irq(&conf->resync_lock);
 
@@ -841,6 +836,7 @@ static void raise_barrier(struct r1conf *conf)
 
 	/* block any new IO from starting */
 	conf->barrier++;
+	conf->next_resync = sector_nr;
 
 	/* For these conditions we must wait:
 	 * A: while the array is in frozen state
@@ -849,14 +845,17 @@ static void raise_barrier(struct r1conf *conf)
 	 * C: next_resync + RESYNC_SECTORS > start_next_window, meaning
 	 *    next resync will reach to the window which normal bios are
 	 *    handling.
+	 * D: while there are any active requests in the current window.
 	 */
 	wait_event_lock_irq(conf->wait_barrier,
 			    !conf->array_frozen &&
 			    conf->barrier < RESYNC_DEPTH &&
+			    conf->current_window_requests == 0 &&
 			    (conf->start_next_window >=
 			     conf->next_resync + RESYNC_SECTORS),
 			    conf->resync_lock);
 
+	conf->nr_pending++;
 	spin_unlock_irq(&conf->resync_lock);
 }
 
@@ -866,6 +865,7 @@ static void lower_barrier(struct r1conf *conf)
 	BUG_ON(conf->barrier <= 0);
 	spin_lock_irqsave(&conf->resync_lock, flags);
 	conf->barrier--;
+	conf->nr_pending--;
 	spin_unlock_irqrestore(&conf->resync_lock, flags);
 	wake_up(&conf->wait_barrier);
 }
@@ -877,12 +877,10 @@ static bool need_to_wait_for_sync(struct r1conf *conf, struct bio *bio)
 	if (conf->array_frozen || !bio)
 		wait = true;
 	else if (conf->barrier && bio_data_dir(bio) == WRITE) {
-		if (conf->next_resync < RESYNC_WINDOW_SECTORS)
-			wait = true;
-		else if ((conf->next_resync - RESYNC_WINDOW_SECTORS
-				>= bio_end_sector(bio)) ||
-			 (conf->next_resync + NEXT_NORMALIO_DISTANCE
-				<= bio->bi_iter.bi_sector))
+		if ((conf->mddev->curr_resync_completed
+		     >= bio_end_sector(bio)) ||
+		    (conf->next_resync + NEXT_NORMALIO_DISTANCE
+		     <= bio->bi_iter.bi_sector))
 			wait = false;
 		else
 			wait = true;
@@ -902,25 +900,25 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 		 * However if there are already pending
 		 * requests (preventing the barrier from
 		 * rising completely), and the
-		 * pre-process bio queue isn't empty,
+		 * per-process bio queue isn't empty,
 		 * then don't wait, as we need to empty
-		 * that queue to get the nr_pending
-		 * count down.
+		 * that queue to allow conf->start_next_window
+		 * to increase.
 		 */
 		wait_event_lock_irq(conf->wait_barrier,
 				    !conf->array_frozen &&
 				    (!conf->barrier ||
-				    ((conf->start_next_window <
-				      conf->next_resync + RESYNC_SECTORS) &&
-				     current->bio_list &&
-				     !bio_list_empty(current->bio_list))),
+				     ((conf->start_next_window <
+				       conf->next_resync + RESYNC_SECTORS) &&
+				      current->bio_list &&
+				      !bio_list_empty(current->bio_list))),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 	}
 
 	if (bio && bio_data_dir(bio) == WRITE) {
-		if (conf->next_resync + NEXT_NORMALIO_DISTANCE
-		    <= bio->bi_iter.bi_sector) {
+		if (bio->bi_iter.bi_sector >=
+		    conf->mddev->curr_resync_completed) {
 			if (conf->start_next_window == MaxSector)
 				conf->start_next_window =
 					conf->next_resync +
@@ -1002,8 +1000,7 @@ static void unfreeze_array(struct r1conf *conf)
 	spin_unlock_irq(&conf->resync_lock);
 }
 
-
-/* duplicate the data pages for behind I/O 
+/* duplicate the data pages for behind I/O
  */
 static void alloc_behind_pages(struct bio *bio, struct r1bio *r1_bio)
 {
@@ -1186,6 +1183,7 @@ read_again:
 				   atomic_read(&bitmap->behind_writes) == 0);
 		}
 		r1_bio->read_disk = rdisk;
+		r1_bio->start_next_window = 0;
 
 		read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
 		bio_trim(read_bio, r1_bio->sector - bio->bi_iter.bi_sector,
@@ -1471,7 +1469,6 @@ static void status(struct seq_file *seq, struct mddev *mddev)
 	seq_printf(seq, "]");
 }
 
-
 static void error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
@@ -1501,12 +1498,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 		mddev->degraded++;
 		set_bit(Faulty, &rdev->flags);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
-		/*
-		 * if recovery is running, make sure it aborts.
-		 */
-		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	} else
 		set_bit(Faulty, &rdev->flags);
+	/*
+	 * if recovery is running, make sure it aborts.
+	 */
+	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	printk(KERN_ALERT
 	       "md/raid1:%s: Disk failure on %s, disabling device.\n"
@@ -1548,8 +1545,13 @@ static void close_sync(struct r1conf *conf)
 	mempool_destroy(conf->r1buf_pool);
 	conf->r1buf_pool = NULL;
 
+	spin_lock_irq(&conf->resync_lock);
 	conf->next_resync = 0;
 	conf->start_next_window = MaxSector;
+	conf->current_window_requests +=
+		conf->next_window_requests;
+	conf->next_window_requests = 0;
+	spin_unlock_irq(&conf->resync_lock);
 }
 
 static int raid1_spare_active(struct mddev *mddev)
@@ -1560,7 +1562,7 @@ static int raid1_spare_active(struct mddev *mddev)
 	unsigned long flags;
 
 	/*
-	 * Find all failed disks within the RAID1 configuration 
+	 * Find all failed disks within the RAID1 configuration
 	 * and mark them readable.
 	 * Called under mddev lock, so rcu protection not needed.
 	 */
@@ -1601,7 +1603,6 @@ static int raid1_spare_active(struct mddev *mddev)
 	return count;
 }
 
-
 static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
 	struct r1conf *conf = mddev->private;
@@ -1730,7 +1731,6 @@ abort:
 	return err;
 }
 
-
 static void end_sync_read(struct bio *bio, int error)
 {
 	struct r1bio *r1_bio = bio->bi_private;
@@ -1942,7 +1942,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 	return 1;
 }
 
-static int process_checks(struct r1bio *r1_bio)
+static void process_checks(struct r1bio *r1_bio)
 {
 	/* We have read all readable devices.  If we haven't
 	 * got the block, then there is no hope left.
@@ -2034,7 +2034,6 @@ static int process_checks(struct r1bio *r1_bio)
 
 		bio_copy_data(sbio, pbio);
 	}
-	return 0;
 }
 
 static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
@@ -2052,8 +2051,8 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
 			return;
 
 	if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
-		if (process_checks(r1_bio) < 0)
-			return;
+		process_checks(r1_bio);
+
 	/*
 	 * schedule writes
 	 */
@@ -2150,7 +2149,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			d--;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
-			    test_bit(In_sync, &rdev->flags))
+			    !test_bit(Faulty, &rdev->flags))
 				r1_sync_page_io(rdev, sect, s,
 						conf->tmppage, WRITE);
 		}
@@ -2162,7 +2161,7 @@ static void fix_read_error(struct r1conf *conf, int read_disk,
 			d--;
 			rdev = conf->mirrors[d].rdev;
 			if (rdev &&
-			    test_bit(In_sync, &rdev->flags)) {
+			    !test_bit(Faulty, &rdev->flags)) {
 				if (r1_sync_page_io(rdev, sect, s,
 						    conf->tmppage, READ)) {
 					atomic_add(s, &rdev->corrected_errors);
@@ -2453,7 +2452,6 @@ static void raid1d(struct md_thread *thread)
 	blk_finish_plug(&plug);
 }
 
-
 static int init_resync(struct r1conf *conf)
 {
 	int buffs;
@@ -2541,9 +2539,8 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 
 	bitmap_cond_end_sync(mddev->bitmap, sector_nr);
 	r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
-	raise_barrier(conf);
 
-	conf->next_resync = sector_nr;
+	raise_barrier(conf, sector_nr);
 
 	rcu_read_lock();
 	/*
@@ -2718,7 +2715,7 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 						/* remove last page from this bio */
 						bio->bi_vcnt--;
 						bio->bi_iter.bi_size -= len;
-						bio->bi_flags &= ~(1<< BIO_SEG_VALID);
+						__clear_bit(BIO_SEG_VALID, &bio->bi_flags);
 					}
 					goto bio_full;
 				}
@@ -2943,9 +2940,9 @@ static int run(struct mddev *mddev)
 		printk(KERN_NOTICE "md/raid1:%s: not clean"
 		       " -- starting background reconstruction\n",
 		       mdname(mddev));
-	printk(KERN_INFO 
+	printk(KERN_INFO
 		"md/raid1:%s: active with %d out of %d mirrors\n",
-		mdname(mddev), mddev->raid_disks - mddev->degraded, 
+		mdname(mddev), mddev->raid_disks - mddev->degraded,
 		mddev->raid_disks);
 
 	/*