1 files changed, 46 insertions, 115 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index c148b630215..225815197a3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -36,7 +36,7 @@
 #include <linux/blkdev.h>
 #include <linux/sysctl.h>
 #include <linux/seq_file.h>
-#include <linux/smp_lock.h>
+#include <linux/mutex.h>
 #include <linux/buffer_head.h> /* for invalidate_bdev */
 #include <linux/poll.h>
 #include <linux/ctype.h>
@@ -57,6 +57,7 @@
 #define DEBUG 0
 #define dprintk(x...) ((void)(DEBUG && printk(x)))
 
+static DEFINE_MUTEX(md_mutex);
 
 #ifndef MODULE
 static void autostart_arrays(int part);
@@ -226,12 +227,12 @@ static int md_make_request(struct request_queue *q, struct bio *bio)
 		return 0;
 	}
 	rcu_read_lock();
-	if (mddev->suspended || mddev->barrier) {
+	if (mddev->suspended) {
 		DEFINE_WAIT(__wait);
 		for (;;) {
 			prepare_to_wait(&mddev->sb_wait, &__wait,
 					TASK_UNINTERRUPTIBLE);
-			if (!mddev->suspended && !mddev->barrier)
+			if (!mddev->suspended)
 				break;
 			rcu_read_unlock();
 			schedule();
@@ -282,40 +283,29 @@ EXPORT_SYMBOL_GPL(mddev_resume);
 
 int mddev_congested(mddev_t *mddev, int bits)
 {
-	if (mddev->barrier)
-		return 1;
 	return mddev->suspended;
 }
 EXPORT_SYMBOL(mddev_congested);
 
 /*
- * Generic barrier handling for md
+ * Generic flush handling for md
  */
 
-#define POST_REQUEST_BARRIER ((void*)1)
-
-static void md_end_barrier(struct bio *bio, int err)
+static void md_end_flush(struct bio *bio, int err)
 {
 	mdk_rdev_t *rdev = bio->bi_private;
 	mddev_t *mddev = rdev->mddev;
-	if (err == -EOPNOTSUPP && mddev->barrier != POST_REQUEST_BARRIER)
-		set_bit(BIO_EOPNOTSUPP, &mddev->barrier->bi_flags);
 
 	rdev_dec_pending(rdev, mddev);
 
 	if (atomic_dec_and_test(&mddev->flush_pending)) {
-		if (mddev->barrier == POST_REQUEST_BARRIER) {
-			/* This was a post-request barrier */
-			mddev->barrier = NULL;
-			wake_up(&mddev->sb_wait);
-		} else
-			/* The pre-request barrier has finished */
-			schedule_work(&mddev->barrier_work);
+		/* The pre-request flush has finished */
+		schedule_work(&mddev->flush_work);
 	}
 	bio_put(bio);
 }
 
-static void submit_barriers(mddev_t *mddev)
+static void submit_flushes(mddev_t *mddev)
 {
 	mdk_rdev_t *rdev;
 
@@ -332,60 +322,56 @@ static void submit_barriers(mddev_t *mddev)
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
 			bi = bio_alloc(GFP_KERNEL, 0);
-			bi->bi_end_io = md_end_barrier;
+			bi->bi_end_io = md_end_flush;
 			bi->bi_private = rdev;
 			bi->bi_bdev = rdev->bdev;
 			atomic_inc(&mddev->flush_pending);
-			submit_bio(WRITE_BARRIER, bi);
+			submit_bio(WRITE_FLUSH, bi);
 			rcu_read_lock();
 			rdev_dec_pending(rdev, mddev);
 		}
 	rcu_read_unlock();
 }
 
-static void md_submit_barrier(struct work_struct *ws)
+static void md_submit_flush_data(struct work_struct *ws)
 {
-	mddev_t *mddev = container_of(ws, mddev_t, barrier_work);
-	struct bio *bio = mddev->barrier;
+	mddev_t *mddev = container_of(ws, mddev_t, flush_work);
+	struct bio *bio = mddev->flush_bio;
 
 	atomic_set(&mddev->flush_pending, 1);
 
-	if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags))
-		bio_endio(bio, -EOPNOTSUPP);
-	else if (bio->bi_size == 0)
+	if (bio->bi_size == 0)
 		/* an empty barrier - all done */
 		bio_endio(bio, 0);
 	else {
-		bio->bi_rw &= ~REQ_HARDBARRIER;
+		bio->bi_rw &= ~REQ_FLUSH;
 		if (mddev->pers->make_request(mddev, bio))
 			generic_make_request(bio);
-		mddev->barrier = POST_REQUEST_BARRIER;
-		submit_barriers(mddev);
 	}
 	if (atomic_dec_and_test(&mddev->flush_pending)) {
-		mddev->barrier = NULL;
+		mddev->flush_bio = NULL;
 		wake_up(&mddev->sb_wait);
 	}
 }
 
-void md_barrier_request(mddev_t *mddev, struct bio *bio)
+void md_flush_request(mddev_t *mddev, struct bio *bio)
 {
 	spin_lock_irq(&mddev->write_lock);
 	wait_event_lock_irq(mddev->sb_wait,
-			    !mddev->barrier,
+			    !mddev->flush_bio,
 			    mddev->write_lock, /*nothing*/);
-	mddev->barrier = bio;
+	mddev->flush_bio = bio;
 	spin_unlock_irq(&mddev->write_lock);
 
 	atomic_set(&mddev->flush_pending, 1);
-	INIT_WORK(&mddev->barrier_work, md_submit_barrier);
+	INIT_WORK(&mddev->flush_work, md_submit_flush_data);
 
-	submit_barriers(mddev);
+	submit_flushes(mddev);
 
 	if (atomic_dec_and_test(&mddev->flush_pending))
-		schedule_work(&mddev->barrier_work);
+		schedule_work(&mddev->flush_work);
 }
-EXPORT_SYMBOL(md_barrier_request);
+EXPORT_SYMBOL(md_flush_request);
 
 /* Support for plugging.
  * This mirrors the plugging support in request_queue, but does not
@@ -696,31 +682,6 @@ static void super_written(struct bio *bio, int error)
 	bio_put(bio);
 }
 
-static void super_written_barrier(struct bio *bio, int error)
-{
-	struct bio *bio2 = bio->bi_private;
-	mdk_rdev_t *rdev = bio2->bi_private;
-	mddev_t *mddev = rdev->mddev;
-
-	if (!test_bit(BIO_UPTODATE, &bio->bi_flags) &&
-	    error == -EOPNOTSUPP) {
-		unsigned long flags;
-		/* barriers don't appear to be supported :-( */
-		set_bit(BarriersNotsupp, &rdev->flags);
-		mddev->barriers_work = 0;
-		spin_lock_irqsave(&mddev->write_lock, flags);
-		bio2->bi_next = mddev->biolist;
-		mddev->biolist = bio2;
-		spin_unlock_irqrestore(&mddev->write_lock, flags);
-		wake_up(&mddev->sb_wait);
-		bio_put(bio);
-	} else {
-		bio_put(bio2);
-		bio->bi_private = rdev;
-		super_written(bio, error);
-	}
-}
-
 void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
 		   sector_t sector, int size, struct page *page)
 {
@@ -729,51 +690,28 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
 	 * and decrement it on completion, waking up sb_wait
 	 * if zero is reached.
 	 * If an error occurred, call md_error
-	 *
-	 * As we might need to resubmit the request if REQ_HARDBARRIER
-	 * causes ENOTSUPP, we allocate a spare bio...
 	 */
 	struct bio *bio = bio_alloc(GFP_NOIO, 1);
-	int rw = REQ_WRITE | REQ_SYNC | REQ_UNPLUG;
 
 	bio->bi_bdev = rdev->bdev;
 	bio->bi_sector = sector;
 	bio_add_page(bio, page, size, 0);
 	bio->bi_private = rdev;
 	bio->bi_end_io = super_written;
-	bio->bi_rw = rw;
 
 	atomic_inc(&mddev->pending_writes);
-	if (!test_bit(BarriersNotsupp, &rdev->flags)) {
-		struct bio *rbio;
-		rw |= REQ_HARDBARRIER;
-		rbio = bio_clone(bio, GFP_NOIO);
-		rbio->bi_private = bio;
-		rbio->bi_end_io = super_written_barrier;
-		submit_bio(rw, rbio);
-	} else
-		submit_bio(rw, bio);
+	submit_bio(REQ_WRITE | REQ_SYNC | REQ_UNPLUG | REQ_FLUSH | REQ_FUA,
+		   bio);
 }
 
 void md_super_wait(mddev_t *mddev)
 {
-	/* wait for all superblock writes that were scheduled to complete.
-	 * if any had to be retried (due to BARRIER problems), retry them
-	 */
+	/* wait for all superblock writes that were scheduled to complete */
 	DEFINE_WAIT(wq);
 	for(;;) {
 		prepare_to_wait(&mddev->sb_wait, &wq, TASK_UNINTERRUPTIBLE);
 		if (atomic_read(&mddev->pending_writes)==0)
 			break;
-		while (mddev->biolist) {
-			struct bio *bio;
-			spin_lock_irq(&mddev->write_lock);
-			bio = mddev->biolist;
-			mddev->biolist = bio->bi_next ;
-			bio->bi_next = NULL;
-			spin_unlock_irq(&mddev->write_lock);
-			submit_bio(bio->bi_rw, bio);
-		}
 		schedule();
 	}
 	finish_wait(&mddev->sb_wait, &wq);
@@ -1070,7 +1008,6 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 	clear_bit(Faulty, &rdev->flags);
 	clear_bit(In_sync, &rdev->flags);
 	clear_bit(WriteMostly, &rdev->flags);
-	clear_bit(BarriersNotsupp, &rdev->flags);
 
 	if (mddev->raid_disks == 0) {
 		mddev->major_version = 0;
@@ -1485,7 +1422,6 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 	clear_bit(Faulty, &rdev->flags);
 	clear_bit(In_sync, &rdev->flags);
 	clear_bit(WriteMostly, &rdev->flags);
-	clear_bit(BarriersNotsupp, &rdev->flags);
 
 	if (mddev->raid_disks == 0) {
 		mddev->major_version = 1;
@@ -1643,7 +1579,9 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 		bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1;
 		if (rdev->sb_size & bmask)
 			rdev->sb_size = (rdev->sb_size | bmask) + 1;
-	}
+	} else
+		max_dev = le32_to_cpu(sb->max_dev);
+
 	for (i=0; i<max_dev;i++)
 		sb->dev_roles[i] = cpu_to_le16(0xfffe);
 	
@@ -2167,9 +2105,9 @@ repeat:
 				rdev->recovery_offset = mddev->curr_resync_completed;
 
 	}	
-	if (mddev->external || !mddev->persistent) {
-		clear_bit(MD_CHANGE_DEVS, &mddev->flags);
+	if (!mddev->persistent) {
 		clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
+		clear_bit(MD_CHANGE_DEVS, &mddev->flags);
 		wake_up(&mddev->sb_wait);
 		return;
 	}
@@ -2178,7 +2116,6 @@ repeat:
 
 	mddev->utime = get_seconds();
 
-	set_bit(MD_CHANGE_PENDING, &mddev->flags);
 	if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags))
 		force_change = 1;
 	if (test_and_clear_bit(MD_CHANGE_CLEAN, &mddev->flags))
@@ -3371,7 +3308,7 @@ array_state_show(mddev_t *mddev, char *page)
 		case 0:
 			if (mddev->in_sync)
 				st = clean;
-			else if (test_bit(MD_CHANGE_CLEAN, &mddev->flags))
+			else if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
 				st = write_pending;
 			else if (mddev->safemode)
 				st = active_idle;
@@ -3452,9 +3389,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
 					mddev->in_sync = 1;
 					if (mddev->safemode == 1)
 						mddev->safemode = 0;
-					if (mddev->persistent)
-						set_bit(MD_CHANGE_CLEAN,
-							&mddev->flags);
+					set_bit(MD_CHANGE_CLEAN, &mddev->flags);
 				}
 				err = 0;
 			} else
@@ -3466,8 +3401,7 @@ array_state_store(mddev_t *mddev, const char *buf, size_t len)
 	case active:
 		if (mddev->pers) {
 			restart_array(mddev);
-			if (mddev->external)
-				clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
+			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
 			wake_up(&mddev->sb_wait);
 			err = 0;
 		} else {
@@ -4506,7 +4440,6 @@ int md_run(mddev_t *mddev)
 	/* may be over-ridden by personality */
 	mddev->resync_max_sectors = mddev->dev_sectors;
 
-	mddev->barriers_work = 1;
 	mddev->ok_start_degraded = start_dirty_degraded;
 
 	if (start_readonly && mddev->ro == 0)
@@ -4685,7 +4618,6 @@ static void md_clean(mddev_t *mddev)
 	mddev->recovery = 0;
 	mddev->in_sync = 0;
 	mddev->degraded = 0;
-	mddev->barriers_work = 0;
 	mddev->safemode = 0;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
@@ -5953,7 +5885,7 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 	mddev_t *mddev = mddev_find(bdev->bd_dev);
 	int err;
 
-	lock_kernel();
+	mutex_lock(&md_mutex);
 	if (mddev->gendisk != bdev->bd_disk) {
 		/* we are racing with mddev_put which is discarding this
 		 * bd_disk.
@@ -5962,7 +5894,7 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 		/* Wait until bdev->bd_disk is definitely gone */
 		flush_scheduled_work();
 		/* Then retry the open from the top */
-		unlock_kernel();
+		mutex_unlock(&md_mutex);
 		return -ERESTARTSYS;
 	}
 	BUG_ON(mddev != bdev->bd_disk->private_data);
@@ -5976,7 +5908,7 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 
 	check_disk_size_change(mddev->gendisk, bdev);
  out:
-	unlock_kernel();
+	mutex_unlock(&md_mutex);
 	return err;
 }
 
@@ -5985,10 +5917,10 @@ static int md_release(struct gendisk *disk, fmode_t mode)
  	mddev_t *mddev = disk->private_data;
 
 	BUG_ON(!mddev);
-	lock_kernel();
+	mutex_lock(&md_mutex);
 	atomic_dec(&mddev->openers);
 	mddev_put(mddev);
-	unlock_kernel();
+	mutex_unlock(&md_mutex);
 
 	return 0;
 }
@@ -6572,6 +6504,7 @@ void md_write_start(mddev_t *mddev, struct bio *bi)
 		if (mddev->in_sync) {
 			mddev->in_sync = 0;
 			set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+			set_bit(MD_CHANGE_PENDING, &mddev->flags);
 			md_wakeup_thread(mddev->thread);
 			did_change = 1;
 		}
@@ -6580,7 +6513,6 @@ void md_write_start(mddev_t *mddev, struct bio *bi)
 	if (did_change)
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
 	wait_event(mddev->sb_wait,
-		   !test_bit(MD_CHANGE_CLEAN, &mddev->flags) &&
 		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
 }
 
@@ -6616,6 +6548,7 @@ int md_allow_write(mddev_t *mddev)
 	if (mddev->in_sync) {
 		mddev->in_sync = 0;
 		set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+		set_bit(MD_CHANGE_PENDING, &mddev->flags);
 		if (mddev->safemode_delay &&
 		    mddev->safemode == 0)
 			mddev->safemode = 1;
@@ -6625,7 +6558,7 @@ int md_allow_write(mddev_t *mddev)
 	} else
 		spin_unlock_irq(&mddev->write_lock);
 
-	if (test_bit(MD_CHANGE_CLEAN, &mddev->flags))
+	if (test_bit(MD_CHANGE_PENDING, &mddev->flags))
 		return -EAGAIN;
 	else
 		return 0;
@@ -6823,8 +6756,7 @@ void md_do_sync(mddev_t *mddev)
 				   atomic_read(&mddev->recovery_active) == 0);
 			mddev->curr_resync_completed =
 				mddev->curr_resync;
-			if (mddev->persistent)
-				set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+			set_bit(MD_CHANGE_CLEAN, &mddev->flags);
 			sysfs_notify(&mddev->kobj, NULL, "sync_completed");
 		}
 
@@ -7073,7 +7005,7 @@ void md_check_recovery(mddev_t *mddev)
 	if (mddev->ro && !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
 		return;
 	if ( ! (
-		(mddev->flags && !mddev->external) ||
+		(mddev->flags & ~ (1<<MD_CHANGE_PENDING)) ||
 		test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
 		test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
 		(mddev->external == 0 && mddev->safemode == 1) ||
@@ -7103,8 +7035,7 @@ void md_check_recovery(mddev_t *mddev)
 			    mddev->recovery_cp == MaxSector) {
 				mddev->in_sync = 1;
 				did_change = 1;
-				if (mddev->persistent)
-					set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+				set_bit(MD_CHANGE_CLEAN, &mddev->flags);
 			}
 			if (mddev->safemode == 1)
 				mddev->safemode = 0;