Merge remote-tracking branch 'kernelorg/linux-3.0.y' into 3_0_64

Conflicts:
	arch/arm/Kconfig
	arch/arm/include/asm/hwcap.h
	arch/arm/kernel/smp.c
	arch/arm/plat-samsung/adc.c
	drivers/gpu/drm/i915/i915_reg.h
	drivers/gpu/drm/i915/intel_drv.h
	drivers/mmc/core/sd.c
	drivers/net/tun.c
	drivers/net/usb/usbnet.c
	drivers/regulator/max8997.c
	drivers/usb/core/hub.c
	drivers/usb/host/xhci.h
	drivers/usb/serial/qcserial.c
	fs/jbd2/transaction.c
	include/linux/migrate.h
	kernel/sys.c
	kernel/time/timekeeping.c
	lib/genalloc.c
	mm/memory-failure.c
	mm/memory_hotplug.c
	mm/mempolicy.c
	mm/page_alloc.c
	mm/vmalloc.c
	mm/vmscan.c
	mm/vmstat.c
	scripts/Kbuild.include

Change-Id: I91e2d85c07320c7ccfc04cf98a448e89bed6ade6

7 files changed, 79 insertions, 27 deletions

diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 4cacdad..bd3b294 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1524,6 +1524,14 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl **param)
 	if (copy_from_user(dmi, user, tmp.data_size))
 		goto bad;
 
+	/*
+	 * Abort if something changed the ioctl data while it was being copied.
+	 */
+	if (dmi->data_size != tmp.data_size) {
+		DMERR("rejecting ioctl: data size modified while processing parameters");
+		goto bad;
+	}
+
 	/* Wipe the user buffer so we do not return it to userspace */
 	if (secure_data && clear_user(user, tmp.data_size))
 		goto bad;
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 9bfd057..42ef54f 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1210,7 +1210,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 	 * We need to dec pending if this was a write.
 	 */
 	if (rw == WRITE) {
-		if (!(bio->bi_rw & REQ_FLUSH))
+		if (!(bio->bi_rw & (REQ_FLUSH | REQ_DISCARD)))
 			dm_rh_dec(ms->rh, map_context->ll);
 		return error;
 	}
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
index 7771ed2..69732e0 100644
--- a/drivers/md/dm-region-hash.c
+++ b/drivers/md/dm-region-hash.c
@@ -404,6 +404,9 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio)
 		return;
 	}
 
+	if (bio->bi_rw & REQ_DISCARD)
+		return;
+
 	/* We must inform the log that the sync count has changed. */
 	log->type->set_region_sync(log, region, 0);
 
@@ -524,7 +527,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios)
 	struct bio *bio;
 
 	for (bio = bios->head; bio; bio = bio->bi_next) {
-		if (bio->bi_rw & REQ_FLUSH)
+		if (bio->bi_rw & (REQ_FLUSH | REQ_DISCARD))
 			continue;
 		rh_inc(rh, dm_rh_bio_to_region(rh, bio));
 	}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 41abc6d..9f472d5 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -745,8 +745,14 @@ static void rq_completed(struct mapped_device *md, int rw, int run_queue)
 	if (!md_in_flight(md))
 		wake_up(&md->wait);
 
+	/*
+	 * Run this off this callpath, as drivers could invoke end_io while
+	 * inside their request_fn (and holding the queue lock). Calling
+	 * back into ->request_fn() could deadlock attempting to grab the
+	 * queue lock again.
+	 */
 	if (run_queue)
-		blk_run_queue(md->queue);
+		blk_run_queue_async(md->queue);
 
 	/*
 	 * dm_put() must be at the end of this function. See the comment above
@@ -856,10 +862,14 @@ static void dm_done(struct request *clone, int error, bool mapped)
 {
 	int r = error;
 	struct dm_rq_target_io *tio = clone->end_io_data;
-	dm_request_endio_fn rq_end_io = tio->ti->type->rq_end_io;
+	dm_request_endio_fn rq_end_io = NULL;
 
-	if (mapped && rq_end_io)
-		r = rq_end_io(tio->ti, clone, error, &tio->info);
+	if (tio->ti) {
+		rq_end_io = tio->ti->type->rq_end_io;
+
+		if (mapped && rq_end_io)
+			r = rq_end_io(tio->ti, clone, error, &tio->info);
+	}
 
 	if (r <= 0)
 		/* The target wants to complete the I/O */
@@ -1562,15 +1572,6 @@ static int map_request(struct dm_target *ti, struct request *clone,
 	int r, requeued = 0;
 	struct dm_rq_target_io *tio = clone->end_io_data;
 
-	/*
-	 * Hold the md reference here for the in-flight I/O.
-	 * We can't rely on the reference count by device opener,
-	 * because the device may be closed during the request completion
-	 * when all bios are completed.
-	 * See the comment in rq_completed() too.
-	 */
-	dm_get(md);
-
 	tio->ti = ti;
 	r = ti->type->map_rq(ti, clone, &tio->info);
 	switch (r) {
@@ -1602,6 +1603,26 @@ static int map_request(struct dm_target *ti, struct request *clone,
 	return requeued;
 }
 
+static struct request *dm_start_request(struct mapped_device *md, struct request *orig)
+{
+	struct request *clone;
+
+	blk_start_request(orig);
+	clone = orig->special;
+	atomic_inc(&md->pending[rq_data_dir(clone)]);
+
+	/*
+	 * Hold the md reference here for the in-flight I/O.
+	 * We can't rely on the reference count by device opener,
+	 * because the device may be closed during the request completion
+	 * when all bios are completed.
+	 * See the comment in rq_completed() too.
+	 */
+	dm_get(md);
+
+	return clone;
+}
+
 /*
  * q->request_fn for request-based dm.
  * Called with the queue lock held.
@@ -1631,14 +1652,21 @@ static void dm_request_fn(struct request_queue *q)
 			pos = blk_rq_pos(rq);
 
 		ti = dm_table_find_target(map, pos);
-		BUG_ON(!dm_target_is_valid(ti));
+		if (!dm_target_is_valid(ti)) {
+			/*
+			 * Must perform setup, that dm_done() requires,
+			 * before calling dm_kill_unmapped_request
+			 */
+			DMERR_LIMIT("request attempted access beyond the end of device");
+			clone = dm_start_request(md, rq);
+			dm_kill_unmapped_request(clone, -EIO);
+			continue;
+		}
 
 		if (ti->type->busy && ti->type->busy(ti))
 			goto delay_and_out;
 
-		blk_start_request(rq);
-		clone = rq->special;
-		atomic_inc(&md->pending[rq_data_dir(clone)]);
+		clone = dm_start_request(md, rq);
 
 		spin_unlock(q->queue_lock);
 		if (map_request(ti, clone, md))
@@ -1658,8 +1686,6 @@ delay_and_out:
 	blk_delay_queue(q, HZ / 10);
 out:
 	dm_table_put(map);
-
-	return;
 }
 
 int dm_underlying_device_busy(struct request_queue *q)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index bc83428..98262e5 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -348,6 +348,8 @@ void mddev_suspend(mddev_t *mddev)
 	synchronize_rcu();
 	wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
 	mddev->pers->quiesce(mddev, 1);
+
+	del_timer_sync(&mddev->safemode_timer);
 }
 EXPORT_SYMBOL_GPL(mddev_suspend);
 
@@ -407,7 +409,7 @@ static void submit_flushes(struct work_struct *ws)
 			atomic_inc(&rdev->nr_pending);
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();
-			bi = bio_alloc_mddev(GFP_KERNEL, 0, mddev);
+			bi = bio_alloc_mddev(GFP_NOIO, 0, mddev);
 			bi->bi_end_io = md_end_flush;
 			bi->bi_private = rdev;
 			bi->bi_bdev = rdev->bdev;
@@ -1094,8 +1096,11 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
 			ret = 0;
 	}
 	rdev->sectors = rdev->sb_start;
-	/* Limit to 4TB as metadata cannot record more than that */
-	if (rdev->sectors >= (2ULL << 32))
+	/* Limit to 4TB as metadata cannot record more than that.
+	 * (not needed for Linear and RAID0 as metadata doesn't
+	 * record this size)
+	 */
+	if (rdev->sectors >= (2ULL << 32) && sb->level >= 1)
 		rdev->sectors = (2ULL << 32) - 2;
 
 	if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1)
@@ -1377,7 +1382,7 @@ super_90_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
 	/* Limit to 4TB as metadata cannot record more than that.
 	 * 4TB == 2^32 KB, or 2*2^32 sectors.
 	 */
-	if (num_sectors >= (2ULL << 32))
+	if (num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1)
 		num_sectors = (2ULL << 32) - 2;
 	md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size,
 		       rdev->sb_page);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 0d6c42f..b65a7c5 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1858,6 +1858,12 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr,
 			/* want to reconstruct this device */
 			rb2 = r10_bio;
 			sect = raid10_find_virt(conf, sector_nr, i);
+			if (sect >= mddev->resync_max_sectors) {
+				/* last stripe is not complete - don't
+				 * try to recover this sector.
+				 */
+				continue;
+			}
 			/* Unless we are doing a full sync, we only need
 			 * to recover the block if it is set in the bitmap
 			 */
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 1f6c68d..cff955a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -199,12 +199,14 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
 		BUG_ON(!list_empty(&sh->lru));
 		BUG_ON(atomic_read(&conf->active_stripes)==0);
 		if (test_bit(STRIPE_HANDLE, &sh->state)) {
-			if (test_bit(STRIPE_DELAYED, &sh->state))
+			if (test_bit(STRIPE_DELAYED, &sh->state) &&
+			    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
 				list_add_tail(&sh->lru, &conf->delayed_list);
 			else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
 				   sh->bm_seq - conf->seq_write > 0)
 				list_add_tail(&sh->lru, &conf->bitmap_list);
 			else {
+				clear_bit(STRIPE_DELAYED, &sh->state);
 				clear_bit(STRIPE_BIT_DELAY, &sh->state);
 				list_add_tail(&sh->lru, &conf->handle_list);
 			}
@@ -3846,7 +3848,6 @@ static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio)
 		raid_bio->bi_next = (void*)rdev;
 		align_bi->bi_bdev =  rdev->bdev;
 		align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
-		align_bi->bi_sector += rdev->data_offset;
 
 		if (!bio_fits_rdev(align_bi)) {
 			/* too big in some way */
@@ -3855,6 +3856,9 @@ static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio)
 			return 0;
 		}
 
+		/* No reshape active, so we can trust rdev->data_offset */
+		align_bi->bi_sector += rdev->data_offset;
+
 		spin_lock_irq(&conf->device_lock);
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    conf->quiesce == 0,