1 files changed, 151 insertions, 195 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 859bd3ffe435..378a25894c57 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -31,6 +31,7 @@
  * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/blkdev.h>
 #include <linux/seq_file.h>
@@ -262,7 +263,7 @@ static inline void update_head_pos(int disk, r1bio_t *r1_bio)
 static void raid1_end_read_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+	r1bio_t *r1_bio = bio->bi_private;
 	int mirror;
 	conf_t *conf = r1_bio->mddev->private;
 
@@ -296,7 +297,8 @@ static void raid1_end_read_request(struct bio *bio, int error)
 		 */
 		char b[BDEVNAME_SIZE];
 		if (printk_ratelimit())
-			printk(KERN_ERR "raid1: %s: rescheduling sector %llu\n",
+			printk(KERN_ERR "md/raid1:%s: %s: rescheduling sector %llu\n",
+			       mdname(conf->mddev),
 			       bdevname(conf->mirrors[mirror].rdev->bdev,b), (unsigned long long)r1_bio->sector);
 		reschedule_retry(r1_bio);
 	}
@@ -307,7 +309,7 @@ static void raid1_end_read_request(struct bio *bio, int error)
 static void raid1_end_write_request(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+	r1bio_t *r1_bio = bio->bi_private;
 	int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
 	conf_t *conf = r1_bio->mddev->private;
 	struct bio *to_put = NULL;
@@ -317,83 +319,74 @@ static void raid1_end_write_request(struct bio *bio, int error)
 		if (r1_bio->bios[mirror] == bio)
 			break;
 
-	if (error == -EOPNOTSUPP && test_bit(R1BIO_Barrier, &r1_bio->state)) {
-		set_bit(BarriersNotsupp, &conf->mirrors[mirror].rdev->flags);
-		set_bit(R1BIO_BarrierRetry, &r1_bio->state);
-		r1_bio->mddev->barriers_work = 0;
-		/* Don't rdev_dec_pending in this branch - keep it for the retry */
-	} else {
+	/*
+	 * 'one mirror IO has finished' event handler:
+	 */
+	r1_bio->bios[mirror] = NULL;
+	to_put = bio;
+	if (!uptodate) {
+		md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
+		/* an I/O failed, we can't clear the bitmap */
+		set_bit(R1BIO_Degraded, &r1_bio->state);
+	} else
 		/*
-		 * this branch is our 'one mirror IO has finished' event handler:
+		 * Set R1BIO_Uptodate in our master bio, so that we
+		 * will return a good error code for to the higher
+		 * levels even if IO on some other mirrored buffer
+		 * fails.
+		 *
+		 * The 'master' represents the composite IO operation
+		 * to user-side. So if something waits for IO, then it
+		 * will wait for the 'master' bio.
 		 */
-		r1_bio->bios[mirror] = NULL;
-		to_put = bio;
-		if (!uptodate) {
-			md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
-			/* an I/O failed, we can't clear the bitmap */
-			set_bit(R1BIO_Degraded, &r1_bio->state);
-		} else
-			/*
-			 * Set R1BIO_Uptodate in our master bio, so that
-			 * we will return a good error code for to the higher
-			 * levels even if IO on some other mirrored buffer fails.
-			 *
-			 * The 'master' represents the composite IO operation to
-			 * user-side. So if something waits for IO, then it will
-			 * wait for the 'master' bio.
-			 */
-			set_bit(R1BIO_Uptodate, &r1_bio->state);
-
-		update_head_pos(mirror, r1_bio);
-
-		if (behind) {
-			if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
-				atomic_dec(&r1_bio->behind_remaining);
-
-			/* In behind mode, we ACK the master bio once the I/O has safely
-			 * reached all non-writemostly disks. Setting the Returned bit
-			 * ensures that this gets done only once -- we don't ever want to
-			 * return -EIO here, instead we'll wait */
-
-			if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
-			    test_bit(R1BIO_Uptodate, &r1_bio->state)) {
-				/* Maybe we can return now */
-				if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
-					struct bio *mbio = r1_bio->master_bio;
-					PRINTK(KERN_DEBUG "raid1: behind end write sectors %llu-%llu\n",
-					       (unsigned long long) mbio->bi_sector,
-					       (unsigned long long) mbio->bi_sector +
-					       (mbio->bi_size >> 9) - 1);
-					bio_endio(mbio, 0);
-				}
+		set_bit(R1BIO_Uptodate, &r1_bio->state);
+
+	update_head_pos(mirror, r1_bio);
+
+	if (behind) {
+		if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
+			atomic_dec(&r1_bio->behind_remaining);
+
+		/*
+		 * In behind mode, we ACK the master bio once the I/O
+		 * has safely reached all non-writemostly
+		 * disks. Setting the Returned bit ensures that this
+		 * gets done only once -- we don't ever want to return
+		 * -EIO here, instead we'll wait
+		 */
+		if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
+		    test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+			/* Maybe we can return now */
+			if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
+				struct bio *mbio = r1_bio->master_bio;
+				PRINTK(KERN_DEBUG "raid1: behind end write sectors %llu-%llu\n",
+				       (unsigned long long) mbio->bi_sector,
+				       (unsigned long long) mbio->bi_sector +
+				       (mbio->bi_size >> 9) - 1);
+				bio_endio(mbio, 0);
 			}
 		}
-		rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
 	}
+	rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
+
 	/*
-	 *
 	 * Let's see if all mirrored write operations have finished
 	 * already.
 	 */
 	if (atomic_dec_and_test(&r1_bio->remaining)) {
-		if (test_bit(R1BIO_BarrierRetry, &r1_bio->state))
-			reschedule_retry(r1_bio);
-		else {
-			/* it really is the end of this request */
-			if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
-				/* free extra copy of the data pages */
-				int i = bio->bi_vcnt;
-				while (i--)
-					safe_put_page(bio->bi_io_vec[i].bv_page);
-			}
-			/* clear the bitmap if all writes complete successfully */
-			bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
-					r1_bio->sectors,
-					!test_bit(R1BIO_Degraded, &r1_bio->state),
-					behind);
-			md_write_end(r1_bio->mddev);
-			raid_end_bio_io(r1_bio);
+		if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
+			/* free extra copy of the data pages */
+			int i = bio->bi_vcnt;
+			while (i--)
+				safe_put_page(bio->bi_io_vec[i].bv_page);
 		}
+		/* clear the bitmap if all writes complete successfully */
+		bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
+				r1_bio->sectors,
+				!test_bit(R1BIO_Degraded, &r1_bio->state),
+				behind);
+		md_write_end(r1_bio->mddev);
+		raid_end_bio_io(r1_bio);
 	}
 
 	if (to_put)
@@ -417,7 +410,7 @@ static void raid1_end_write_request(struct bio *bio, int error)
  */
 static int read_balance(conf_t *conf, r1bio_t *r1_bio)
 {
-	const unsigned long this_sector = r1_bio->sector;
+	const sector_t this_sector = r1_bio->sector;
 	int new_disk = conf->last_used, disk = new_disk;
 	int wonly_disk = -1;
 	const int sectors = r1_bio->sectors;
@@ -433,7 +426,7 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio)
  retry:
 	if (conf->mddev->recovery_cp < MaxSector &&
 	    (this_sector + sectors >= conf->next_resync)) {
-		/* Choose the first operation device, for consistancy */
+		/* Choose the first operational device, for consistancy */
 		new_disk = 0;
 
 		for (rdev = rcu_dereference(conf->mirrors[new_disk].rdev);
@@ -773,9 +766,8 @@ do_sync_io:
 	return NULL;
 }
 
-static int make_request(struct request_queue *q, struct bio * bio)
+static int make_request(mddev_t *mddev, struct bio * bio)
 {
-	mddev_t *mddev = q->queuedata;
 	conf_t *conf = mddev->private;
 	mirror_info_t *mirror;
 	r1bio_t *r1_bio;
@@ -786,18 +778,14 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	struct bio_list bl;
 	struct page **behind_pages = NULL;
 	const int rw = bio_data_dir(bio);
-	const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
-	int cpu;
-	bool do_barriers;
+	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
+	const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA));
 	mdk_rdev_t *blocked_rdev;
 
 	/*
 	 * Register the new request and wait if the reconstruction
 	 * thread has put up a bar for new requests.
 	 * Continue immediately if no resync is active currently.
-	 * We test barriers_work *after* md_write_start as md_write_start
-	 * may cause the first superblock write, and that will check out
-	 * if barriers work.
 	 */
 
 	md_write_start(mddev, bio); /* wait on superblock update early */
@@ -821,24 +809,11 @@ static int make_request(struct request_queue *q, struct bio * bio)
 		}
 		finish_wait(&conf->wait_barrier, &w);
 	}
-	if (unlikely(!mddev->barriers_work &&
-		     bio_rw_flagged(bio, BIO_RW_BARRIER))) {
-		if (rw == WRITE)
-			md_write_end(mddev);
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
-	}
 
 	wait_barrier(conf);
 
 	bitmap = mddev->bitmap;
 
-	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bio));
-	part_stat_unlock();
-
 	/*
 	 * make_request() can abort the operation when READA is being
 	 * used and no empty request is available.
@@ -865,6 +840,15 @@ static int make_request(struct request_queue *q, struct bio * bio)
 		}
 		mirror = conf->mirrors + rdisk;
 
+		if (test_bit(WriteMostly, &mirror->rdev->flags) &&
+		    bitmap) {
+			/* Reading from a write-mostly device must
+			 * take care not to over-take any writes
+			 * that are 'behind'
+			 */
+			wait_event(bitmap->behind_wait,
+				   atomic_read(&bitmap->behind_writes) == 0);
+		}
 		r1_bio->read_disk = rdisk;
 
 		read_bio = bio_clone(bio, GFP_NOIO);
@@ -874,7 +858,7 @@ static int make_request(struct request_queue *q, struct bio * bio)
 		read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset;
 		read_bio->bi_bdev = mirror->rdev->bdev;
 		read_bio->bi_end_io = raid1_end_read_request;
-		read_bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
+		read_bio->bi_rw = READ | do_sync;
 		read_bio->bi_private = r1_bio;
 
 		generic_make_request(read_bio);
@@ -911,9 +895,10 @@ static int make_request(struct request_queue *q, struct bio * bio)
 			if (test_bit(Faulty, &rdev->flags)) {
 				rdev_dec_pending(rdev, mddev);
 				r1_bio->bios[i] = NULL;
-			} else
+			} else {
 				r1_bio->bios[i] = bio;
-			targets++;
+				targets++;
+			}
 		} else
 			r1_bio->bios[i] = NULL;
 	}
@@ -941,20 +926,20 @@ static int make_request(struct request_queue *q, struct bio * bio)
 		set_bit(R1BIO_Degraded, &r1_bio->state);
 	}
 
-	/* do behind I/O ? */
+	/* do behind I/O ?
+	 * Not if there are too many, or cannot allocate memory,
+	 * or a reader on WriteMostly is waiting for behind writes 
+	 * to flush */
 	if (bitmap &&
 	    (atomic_read(&bitmap->behind_writes)
 	     < mddev->bitmap_info.max_write_behind) &&
+	    !waitqueue_active(&bitmap->behind_wait) &&
 	    (behind_pages = alloc_behind_pages(bio)) != NULL)
 		set_bit(R1BIO_BehindIO, &r1_bio->state);
 
 	atomic_set(&r1_bio->remaining, 0);
 	atomic_set(&r1_bio->behind_remaining, 0);
 
-	do_barriers = bio_rw_flagged(bio, BIO_RW_BARRIER);
-	if (do_barriers)
-		set_bit(R1BIO_Barrier, &r1_bio->state);
-
 	bio_list_init(&bl);
 	for (i = 0; i < disks; i++) {
 		struct bio *mbio;
@@ -967,8 +952,7 @@ static int make_request(struct request_queue *q, struct bio * bio)
 		mbio->bi_sector	= r1_bio->sector + conf->mirrors[i].rdev->data_offset;
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= raid1_end_write_request;
-		mbio->bi_rw = WRITE | (do_barriers << BIO_RW_BARRIER) |
-			(do_sync << BIO_RW_SYNCIO);
+		mbio->bi_rw = WRITE | do_flush_fua | do_sync;
 		mbio->bi_private = r1_bio;
 
 		if (behind_pages) {
@@ -1069,21 +1053,22 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 	} else
 		set_bit(Faulty, &rdev->flags);
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
-	printk(KERN_ALERT "raid1: Disk failure on %s, disabling device.\n"
-		"raid1: Operation continuing on %d devices.\n",
-		bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
+	printk(KERN_ALERT "md/raid1:%s: Disk failure on %s, disabling device.\n"
+	       KERN_ALERT "md/raid1:%s: Operation continuing on %d devices.\n",
+	       mdname(mddev), bdevname(rdev->bdev, b),
+	       mdname(mddev), conf->raid_disks - mddev->degraded);
 }
 
 static void print_conf(conf_t *conf)
 {
 	int i;
 
-	printk("RAID1 conf printout:\n");
+	printk(KERN_DEBUG "RAID1 conf printout:\n");
 	if (!conf) {
-		printk("(!conf)\n");
+		printk(KERN_DEBUG "(!conf)\n");
 		return;
 	}
-	printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
+	printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
 		conf->raid_disks);
 
 	rcu_read_lock();
@@ -1091,7 +1076,7 @@ static void print_conf(conf_t *conf)
 		char b[BDEVNAME_SIZE];
 		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev)
-			printk(" disk %d, wo:%d, o:%d, dev:%s\n",
+			printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n",
 			       i, !test_bit(In_sync, &rdev->flags),
 			       !test_bit(Faulty, &rdev->flags),
 			       bdevname(rdev->bdev,b));
@@ -1112,6 +1097,8 @@ static int raid1_spare_active(mddev_t *mddev)
 {
 	int i;
 	conf_t *conf = mddev->private;
+	int count = 0;
+	unsigned long flags;
 
 	/*
 	 * Find all failed disks within the RAID1 configuration 
@@ -1123,15 +1110,16 @@ static int raid1_spare_active(mddev_t *mddev)
 		if (rdev
 		    && !test_bit(Faulty, &rdev->flags)
 		    && !test_and_set_bit(In_sync, &rdev->flags)) {
-			unsigned long flags;
-			spin_lock_irqsave(&conf->device_lock, flags);
-			mddev->degraded--;
-			spin_unlock_irqrestore(&conf->device_lock, flags);
+			count++;
+			sysfs_notify_dirent(rdev->sysfs_state);
 		}
 	}
+	spin_lock_irqsave(&conf->device_lock, flags);
+	mddev->degraded -= count;
+	spin_unlock_irqrestore(&conf->device_lock, flags);
 
 	print_conf(conf);
-	return 0;
+	return count;
 }
 
 
@@ -1152,13 +1140,17 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 
 			disk_stack_limits(mddev->gendisk, rdev->bdev,
 					  rdev->data_offset << 9);
-			/* as we don't honour merge_bvec_fn, we must never risk
-			 * violating it, so limit ->max_sector to one PAGE, as
-			 * a one page request is never in violation.
+			/* as we don't honour merge_bvec_fn, we must
+			 * never risk violating it, so limit
+			 * ->max_segments to one lying with a single
+			 * page, as a one page request is never in
+			 * violation.
 			 */
-			if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-			    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
-				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+			if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+				blk_queue_max_segments(mddev->queue, 1);
+				blk_queue_segment_boundary(mddev->queue,
+							   PAGE_CACHE_SIZE - 1);
+			}
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
@@ -1218,7 +1210,7 @@ abort:
 
 static void end_sync_read(struct bio *bio, int error)
 {
-	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+	r1bio_t *r1_bio = bio->bi_private;
 	int i;
 
 	for (i=r1_bio->mddev->raid_disks; i--; )
@@ -1241,7 +1233,7 @@ static void end_sync_read(struct bio *bio, int error)
 static void end_sync_write(struct bio *bio, int error)
 {
 	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+	r1bio_t *r1_bio = bio->bi_private;
 	mddev_t *mddev = r1_bio->mddev;
 	conf_t *conf = mddev->private;
 	int i;
@@ -1448,9 +1440,10 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
 				char b[BDEVNAME_SIZE];
 				/* Cannot read from anywhere, array is toast */
 				md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev);
-				printk(KERN_ALERT "raid1: %s: unrecoverable I/O read error"
+				printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O read error"
 				       " for block %llu\n",
-				       bdevname(bio->bi_bdev,b),
+				       mdname(mddev),
+				       bdevname(bio->bi_bdev, b),
 				       (unsigned long long)r1_bio->sector);
 				md_done_sync(mddev, r1_bio->sectors, 0);
 				put_buf(r1_bio);
@@ -1572,7 +1565,7 @@ static void fix_read_error(conf_t *conf, int read_disk,
 				else {
 					atomic_add(s, &rdev->corrected_errors);
 					printk(KERN_INFO
-					       "raid1:%s: read error corrected "
+					       "md/raid1:%s: read error corrected "
 					       "(%d sectors at %llu on %s)\n",
 					       mdname(mddev), s,
 					       (unsigned long long)(sect +
@@ -1618,42 +1611,6 @@ static void raid1d(mddev_t *mddev)
 		if (test_bit(R1BIO_IsSync, &r1_bio->state)) {
 			sync_request_write(mddev, r1_bio);
 			unplug = 1;
-		} else if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
-			/* some requests in the r1bio were BIO_RW_BARRIER
-			 * requests which failed with -EOPNOTSUPP.  Hohumm..
-			 * Better resubmit without the barrier.
-			 * We know which devices to resubmit for, because
-			 * all others have had their bios[] entry cleared.
-			 * We already have a nr_pending reference on these rdevs.
-			 */
-			int i;
-			const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
-			clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
-			clear_bit(R1BIO_Barrier, &r1_bio->state);
-			for (i=0; i < conf->raid_disks; i++)
-				if (r1_bio->bios[i])
-					atomic_inc(&r1_bio->remaining);
-			for (i=0; i < conf->raid_disks; i++)
-				if (r1_bio->bios[i]) {
-					struct bio_vec *bvec;
-					int j;
-
-					bio = bio_clone(r1_bio->master_bio, GFP_NOIO);
-					/* copy pages from the failed bio, as
-					 * this might be a write-behind device */
-					__bio_for_each_segment(bvec, bio, j, 0)
-						bvec->bv_page = bio_iovec_idx(r1_bio->bios[i], j)->bv_page;
-					bio_put(r1_bio->bios[i]);
-					bio->bi_sector = r1_bio->sector +
-						conf->mirrors[i].rdev->data_offset;
-					bio->bi_bdev = conf->mirrors[i].rdev->bdev;
-					bio->bi_end_io = raid1_end_write_request;
-					bio->bi_rw = WRITE |
-						(do_sync << BIO_RW_SYNCIO);
-					bio->bi_private = r1_bio;
-					r1_bio->bios[i] = bio;
-					generic_make_request(bio);
-				}
 		} else {
 			int disk;
 
@@ -1677,13 +1634,14 @@ static void raid1d(mddev_t *mddev)
 
 			bio = r1_bio->bios[r1_bio->read_disk];
 			if ((disk=read_balance(conf, r1_bio)) == -1) {
-				printk(KERN_ALERT "raid1: %s: unrecoverable I/O"
+				printk(KERN_ALERT "md/raid1:%s: %s: unrecoverable I/O"
 				       " read error for block %llu\n",
+				       mdname(mddev),
 				       bdevname(bio->bi_bdev,b),
 				       (unsigned long long)r1_bio->sector);
 				raid_end_bio_io(r1_bio);
 			} else {
-				const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
+				const unsigned long do_sync = r1_bio->master_bio->bi_rw & REQ_SYNC;
 				r1_bio->bios[r1_bio->read_disk] =
 					mddev->ro ? IO_BLOCKED : NULL;
 				r1_bio->read_disk = disk;
@@ -1692,14 +1650,15 @@ static void raid1d(mddev_t *mddev)
 				r1_bio->bios[r1_bio->read_disk] = bio;
 				rdev = conf->mirrors[disk].rdev;
 				if (printk_ratelimit())
-					printk(KERN_ERR "raid1: %s: redirecting sector %llu to"
-					       " another mirror\n",
-					       bdevname(rdev->bdev,b),
-					       (unsigned long long)r1_bio->sector);
+					printk(KERN_ERR "md/raid1:%s: redirecting sector %llu to"
+					       " other mirror: %s\n",
+					       mdname(mddev),
+					       (unsigned long long)r1_bio->sector,
+					       bdevname(rdev->bdev,b));
 				bio->bi_sector = r1_bio->sector + rdev->data_offset;
 				bio->bi_bdev = rdev->bdev;
 				bio->bi_end_io = raid1_end_read_request;
-				bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
+				bio->bi_rw = READ | do_sync;
 				bio->bi_private = r1_bio;
 				unplug = 1;
 				generic_make_request(bio);
@@ -1750,13 +1709,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 	int still_degraded = 0;
 
 	if (!conf->r1buf_pool)
-	{
-/*
-		printk("sync start - bitmap %p\n", mddev->bitmap);
-*/
 		if (init_resync(conf))
 			return 0;
-	}
 
 	max_sector = mddev->dev_sectors;
 	if (sector_nr >= max_sector) {
@@ -1827,7 +1781,9 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 
 		/* take from bio_init */
 		bio->bi_next = NULL;
+		bio->bi_flags &= ~(BIO_POOL_MASK-1);
 		bio->bi_flags |= 1 << BIO_UPTODATE;
+		bio->bi_comp_cpu = -1;
 		bio->bi_rw = READ;
 		bio->bi_vcnt = 0;
 		bio->bi_idx = 0;
@@ -1900,7 +1856,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 			    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
 				break;
 			BUG_ON(sync_blocks < (PAGE_SIZE>>9));
-			if (len > (sync_blocks<<9))
+			if ((len >> 9) > sync_blocks)
 				len = sync_blocks<<9;
 		}
 
@@ -2037,7 +1993,7 @@ static conf_t *setup_conf(mddev_t *mddev)
 
 	err = -EIO;
 	if (conf->last_used < 0) {
-		printk(KERN_ERR "raid1: no operational mirrors for %s\n",
+		printk(KERN_ERR "md/raid1:%s: no operational mirrors\n",
 		       mdname(mddev));
 		goto abort;
 	}
@@ -2045,7 +2001,7 @@ static conf_t *setup_conf(mddev_t *mddev)
 	conf->thread = md_register_thread(raid1d, mddev, NULL);
 	if (!conf->thread) {
 		printk(KERN_ERR
-		       "raid1: couldn't allocate thread for %s\n",
+		       "md/raid1:%s: couldn't allocate thread\n",
 		       mdname(mddev));
 		goto abort;
 	}
@@ -2071,12 +2027,12 @@ static int run(mddev_t *mddev)
 	mdk_rdev_t *rdev;
 
 	if (mddev->level != 1) {
-		printk("raid1: %s: raid level not set to mirroring (%d)\n",
+		printk(KERN_ERR "md/raid1:%s: raid level not set to mirroring (%d)\n",
 		       mdname(mddev), mddev->level);
 		return -EIO;
 	}
 	if (mddev->reshape_position != MaxSector) {
-		printk("raid1: %s: reshape_position set but not supported\n",
+		printk(KERN_ERR "md/raid1:%s: reshape_position set but not supported\n",
 		       mdname(mddev));
 		return -EIO;
 	}
@@ -2098,12 +2054,14 @@ static int run(mddev_t *mddev)
 		disk_stack_limits(mddev->gendisk, rdev->bdev,
 				  rdev->data_offset << 9);
 		/* as we don't honour merge_bvec_fn, we must never risk
-		 * violating it, so limit ->max_sector to one PAGE, as
-		 * a one page request is never in violation.
+		 * violating it, so limit ->max_segments to 1 lying within
+		 * a single page, as a one page request is never in violation.
 		 */
-		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
-			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+		if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+			blk_queue_max_segments(mddev->queue, 1);
+			blk_queue_segment_boundary(mddev->queue,
+						   PAGE_CACHE_SIZE - 1);
+		}
 	}
 
 	mddev->degraded = 0;
@@ -2117,11 +2075,11 @@ static int run(mddev_t *mddev)
 		mddev->recovery_cp = MaxSector;
 
 	if (mddev->recovery_cp != MaxSector)
-		printk(KERN_NOTICE "raid1: %s is not clean"
+		printk(KERN_NOTICE "md/raid1:%s: not clean"
 		       " -- starting background reconstruction\n",
 		       mdname(mddev));
 	printk(KERN_INFO 
-		"raid1: raid set %s active with %d out of %d mirrors\n",
+		"md/raid1:%s: active with %d out of %d mirrors\n",
 		mdname(mddev), mddev->raid_disks - mddev->degraded, 
 		mddev->raid_disks);
 
@@ -2145,15 +2103,14 @@ static int stop(mddev_t *mddev)
 {
 	conf_t *conf = mddev->private;
 	struct bitmap *bitmap = mddev->bitmap;
-	int behind_wait = 0;
 
 	/* wait for behind writes to complete */
-	while (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
-		behind_wait++;
-		printk(KERN_INFO "raid1: behind writes in progress on device %s, waiting to stop (%d)\n", mdname(mddev), behind_wait);
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		schedule_timeout(HZ); /* wait a second */
+	if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
+		printk(KERN_INFO "md/raid1:%s: behind writes in progress - waiting to stop.\n",
+		       mdname(mddev));
 		/* need to kick something here to make sure I/O goes? */
+		wait_event(bitmap->behind_wait,
+			   atomic_read(&bitmap->behind_writes) == 0);
 	}
 
 	raise_barrier(conf);
@@ -2184,7 +2141,6 @@ static int raid1_resize(mddev_t *mddev, sector_t sectors)
 	if (mddev->array_sectors > raid1_size(mddev, sectors, 0))
 		return -EINVAL;
 	set_capacity(mddev->gendisk, mddev->array_sectors);
-	mddev->changed = 1;
 	revalidate_disk(mddev->gendisk);
 	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp == MaxSector) {
@@ -2279,9 +2235,9 @@ static int raid1_reshape(mddev_t *mddev)
 			if (sysfs_create_link(&mddev->kobj,
 					      &rdev->kobj, nm))
 				printk(KERN_WARNING
-				       "md/raid1: cannot register "
-				       "%s for %s\n",
-				       nm, mdname(mddev));
+				       "md/raid1:%s: cannot register "
+				       "%s\n",
+				       mdname(mddev), nm);
 		}
 		if (rdev)
 			newmirrors[d2++].rdev = rdev;