Merge remote-tracking branch 'linus/master' into staging/for_v3.8

* linus/master: (1428 commits)
  futex: avoid wake_futex() for a PI futex_q
  watchdog: using u64 in get_sample_period()
  writeback: put unused inodes to LRU after writeback completion
  mm: vmscan: check for fatal signals iff the process was throttled
  Revert "mm: remove __GFP_NO_KSWAPD"
  proc: check vma->vm_file before dereferencing
  UAPI: strip the _UAPI prefix from header guards during header installation
  include/linux/bug.h: fix sparse warning related to BUILD_BUG_ON_INVALID
  Linux 3.7-rc7
  powerpc/eeh: Do not invalidate PE properly
  ALSA: hda - Fix build without CONFIG_PM
  of/address: sparc: Declare of_iomap as an extern function for sparc again
  PM / QoS: fix wrong error-checking condition
  bnx2x: remove redundant warning log
  vxlan: fix command usage in its doc
  8139cp: revert "set ring address before enabling receiver"
  MPI: Fix compilation on MIPS with GCC 4.4 and newer
  MIPS: Fix crash that occurs when function tracing is enabled
  MIPS: Merge overlapping bootmem ranges
  jbd: Fix lock ordering bug in journal_unmap_buffer()
  ...

1 files changed, 78 insertions, 68 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 906ccbd0f7dc..0d5d0ff2c0f7 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -499,7 +499,7 @@ static void raid10_end_write_request(struct bio *bio, int error)
 	 */
 	one_write_done(r10_bio);
 	if (dec_rdev)
-		rdev_dec_pending(conf->mirrors[dev].rdev, conf->mddev);
+		rdev_dec_pending(rdev, conf->mddev);
 }
 
 /*
@@ -1334,18 +1334,21 @@ retry_write:
 			blocked_rdev = rrdev;
 			break;
 		}
+		if (rdev && (test_bit(Faulty, &rdev->flags)
+			     || test_bit(Unmerged, &rdev->flags)))
+			rdev = NULL;
 		if (rrdev && (test_bit(Faulty, &rrdev->flags)
 			      || test_bit(Unmerged, &rrdev->flags)))
 			rrdev = NULL;
 
 		r10_bio->devs[i].bio = NULL;
 		r10_bio->devs[i].repl_bio = NULL;
-		if (!rdev || test_bit(Faulty, &rdev->flags) ||
-		    test_bit(Unmerged, &rdev->flags)) {
+
+		if (!rdev && !rrdev) {
 			set_bit(R10BIO_Degraded, &r10_bio->state);
 			continue;
 		}
-		if (test_bit(WriteErrorSeen, &rdev->flags)) {
+		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
 			sector_t first_bad;
 			sector_t dev_sector = r10_bio->devs[i].addr;
 			int bad_sectors;
@@ -1387,8 +1390,10 @@ retry_write:
 					max_sectors = good_sectors;
 			}
 		}
-		r10_bio->devs[i].bio = bio;
-		atomic_inc(&rdev->nr_pending);
+		if (rdev) {
+			r10_bio->devs[i].bio = bio;
+			atomic_inc(&rdev->nr_pending);
+		}
 		if (rrdev) {
 			r10_bio->devs[i].repl_bio = bio;
 			atomic_inc(&rrdev->nr_pending);
@@ -1444,69 +1449,71 @@ retry_write:
 	for (i = 0; i < conf->copies; i++) {
 		struct bio *mbio;
 		int d = r10_bio->devs[i].devnum;
-		if (!r10_bio->devs[i].bio)
-			continue;
+		if (r10_bio->devs[i].bio) {
+			struct md_rdev *rdev = conf->mirrors[d].rdev;
+			mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+			md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
+				    max_sectors);
+			r10_bio->devs[i].bio = mbio;
+
+			mbio->bi_sector	= (r10_bio->devs[i].addr+
+					   choose_data_offset(r10_bio,
+							      rdev));
+			mbio->bi_bdev = rdev->bdev;
+			mbio->bi_end_io	= raid10_end_write_request;
+			mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+			mbio->bi_private = r10_bio;
 
-		mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
-			    max_sectors);
-		r10_bio->devs[i].bio = mbio;
+			atomic_inc(&r10_bio->remaining);
 
-		mbio->bi_sector	= (r10_bio->devs[i].addr+
-				   choose_data_offset(r10_bio,
-						      conf->mirrors[d].rdev));
-		mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
-		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
-		mbio->bi_private = r10_bio;
+			cb = blk_check_plugged(raid10_unplug, mddev,
+					       sizeof(*plug));
+			if (cb)
+				plug = container_of(cb, struct raid10_plug_cb,
+						    cb);
+			else
+				plug = NULL;
+			spin_lock_irqsave(&conf->device_lock, flags);
+			if (plug) {
+				bio_list_add(&plug->pending, mbio);
+				plug->pending_cnt++;
+			} else {
+				bio_list_add(&conf->pending_bio_list, mbio);
+				conf->pending_count++;
+			}
+			spin_unlock_irqrestore(&conf->device_lock, flags);
+			if (!plug)
+				md_wakeup_thread(mddev->thread);
+		}
 
-		atomic_inc(&r10_bio->remaining);
+		if (r10_bio->devs[i].repl_bio) {
+			struct md_rdev *rdev = conf->mirrors[d].replacement;
+			if (rdev == NULL) {
+				/* Replacement just got moved to main 'rdev' */
+				smp_mb();
+				rdev = conf->mirrors[d].rdev;
+			}
+			mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
+			md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
+				    max_sectors);
+			r10_bio->devs[i].repl_bio = mbio;
+
+			mbio->bi_sector	= (r10_bio->devs[i].addr +
+					   choose_data_offset(
+						   r10_bio, rdev));
+			mbio->bi_bdev = rdev->bdev;
+			mbio->bi_end_io	= raid10_end_write_request;
+			mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+			mbio->bi_private = r10_bio;
 
-		cb = blk_check_plugged(raid10_unplug, mddev, sizeof(*plug));
-		if (cb)
-			plug = container_of(cb, struct raid10_plug_cb, cb);
-		else
-			plug = NULL;
-		spin_lock_irqsave(&conf->device_lock, flags);
-		if (plug) {
-			bio_list_add(&plug->pending, mbio);
-			plug->pending_cnt++;
-		} else {
+			atomic_inc(&r10_bio->remaining);
+			spin_lock_irqsave(&conf->device_lock, flags);
 			bio_list_add(&conf->pending_bio_list, mbio);
 			conf->pending_count++;
+			spin_unlock_irqrestore(&conf->device_lock, flags);
+			if (!mddev_check_plugged(mddev))
+				md_wakeup_thread(mddev->thread);
 		}
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		if (!plug)
-			md_wakeup_thread(mddev->thread);
-
-		if (!r10_bio->devs[i].repl_bio)
-			continue;
-
-		mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
-		md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
-			    max_sectors);
-		r10_bio->devs[i].repl_bio = mbio;
-
-		/* We are actively writing to the original device
-		 * so it cannot disappear, so the replacement cannot
-		 * become NULL here
-		 */
-		mbio->bi_sector	= (r10_bio->devs[i].addr +
-				   choose_data_offset(
-					   r10_bio,
-					   conf->mirrors[d].replacement));
-		mbio->bi_bdev = conf->mirrors[d].replacement->bdev;
-		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
-		mbio->bi_private = r10_bio;
-
-		atomic_inc(&r10_bio->remaining);
-		spin_lock_irqsave(&conf->device_lock, flags);
-		bio_list_add(&conf->pending_bio_list, mbio);
-		conf->pending_count++;
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		if (!mddev_check_plugged(mddev))
-			md_wakeup_thread(mddev->thread);
 	}
 
 	/* Don't remove the bias on 'remaining' (one_write_done) until
@@ -1783,7 +1790,7 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		clear_bit(Unmerged, &rdev->flags);
 	}
 	md_integrity_add_rdev(rdev, mddev);
-	if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
 
 	print_conf(conf);
@@ -3613,11 +3620,14 @@ static int run(struct mddev *mddev)
 			discard_supported = true;
 	}
 
-	if (discard_supported)
-		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
-	else
-		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
-
+	if (mddev->queue) {
+		if (discard_supported)
+			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
+						mddev->queue);
+		else
+			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD,
+						  mddev->queue);
+	}
 	/* need to check that every block has at least one working mirror */
 	if (!enough(conf, -1)) {
 		printk(KERN_ERR "md/raid10:%s: not enough operational mirrors.\n",