Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Here's a set of block fixes for the current 4.8-rc release.  This
  contains:

   - a fix for a secure erase regression, from Adrian.

   - a fix for an mmc use-after-free bug regression, also from Adrian.

   - potential zero pointer deference in bdev freezing, from Andrey.

   - a race fix for blk_set_queue_dying() from Bart.

   - a set of xen blkfront fixes from Bob Liu.

   - three small fixes for bcache, from Eric and Kent.

   - a fix for a potential invalid NVMe state transition, from Gabriel.

   - blk-mq CPU offline fix, preventing us from issuing and completing a
     request on the wrong queue.  From me.

   - revert two previous floppy changes, since they caused a user
     visibile regression.  A better fix is in the works.

   - ensure that we don't send down bios that have more than 256
     elements in them.  Fixes a crash with bcache, for example.  From
     Ming.

   - a fix for deferencing an error pointer with cgroup writeback.
     Fixes a regression.  From Vegard"

* 'for-linus' of git://git.kernel.dk/linux-block:
  mmc: fix use-after-free of struct request
  Revert "floppy: refactor open() flags handling"
  Revert "floppy: fix open(O_ACCMODE) for ioctl-only open"
  fs/block_dev: fix potential NULL ptr deref in freeze_bdev()
  blk-mq: improve warning for running a queue on the wrong CPU
  blk-mq: don't overwrite rq->mq_ctx
  block: make sure a big bio is split into at most 256 bvecs
  nvme: Fix nvme_get/set_features() with a NULL result pointer
  bdev: fix NULL pointer dereference
  xen-blkfront: free resources if xlvbd_alloc_gendisk fails
  xen-blkfront: introduce blkif_set_queue_limits()
  xen-blkfront: fix places not updated after introducing 64KB page granularity
  bcache: pr_err: more meaningful error message when nr_stripes is invalid
  bcache: RESERVE_PRIO is too small by one when prio_buckets() is a power of two.
  bcache: register_bcache(): call blkdev_put() when cache_alloc() fails
  block: Fix race triggered by blk_set_queue_dying()
  block: Fix secure erase
  nvme: Prevent controller state invalid transition

7 files changed, 97 insertions, 68 deletions

diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index b71a9c767009..e3d8e4ced4a2 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3706,22 +3706,21 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	if (UFDCS->rawcmd == 1)
 		UFDCS->rawcmd = 2;
 
-	if (mode & (FMODE_READ|FMODE_WRITE)) {
-		UDRS->last_checked = 0;
-		clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
-		check_disk_change(bdev);
-		if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
-			goto out;
-		if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+	if (!(mode & FMODE_NDELAY)) {
+		if (mode & (FMODE_READ|FMODE_WRITE)) {
+			UDRS->last_checked = 0;
+			clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
+			check_disk_change(bdev);
+			if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
+				goto out;
+			if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+				goto out;
+		}
+		res = -EROFS;
+		if ((mode & FMODE_WRITE) &&
+		    !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
 			goto out;
 	}
-
-	res = -EROFS;
-
-	if ((mode & FMODE_WRITE) &&
-			!test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
-		goto out;
-
 	mutex_unlock(&open_lock);
 	mutex_unlock(&floppy_mutex);
 	return 0;
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index be4fea6a5dd3..88ef6d4729b4 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -189,6 +189,8 @@ struct blkfront_info
 	struct mutex mutex;
 	struct xenbus_device *xbdev;
 	struct gendisk *gd;
+	u16 sector_size;
+	unsigned int physical_sector_size;
 	int vdevice;
 	blkif_vdev_t handle;
 	enum blkif_state connected;
@@ -910,9 +912,45 @@ static struct blk_mq_ops blkfront_mq_ops = {
 	.map_queue = blk_mq_map_queue,
 };
 
+static void blkif_set_queue_limits(struct blkfront_info *info)
+{
+	struct request_queue *rq = info->rq;
+	struct gendisk *gd = info->gd;
+	unsigned int segments = info->max_indirect_segments ? :
+				BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
+
+	if (info->feature_discard) {
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
+		blk_queue_max_discard_sectors(rq, get_capacity(gd));
+		rq->limits.discard_granularity = info->discard_granularity;
+		rq->limits.discard_alignment = info->discard_alignment;
+		if (info->feature_secdiscard)
+			queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
+	}
+
+	/* Hard sector size and max sectors impersonate the equiv. hardware. */
+	blk_queue_logical_block_size(rq, info->sector_size);
+	blk_queue_physical_block_size(rq, info->physical_sector_size);
+	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
+
+	/* Each segment in a request is up to an aligned page in size. */
+	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
+	blk_queue_max_segment_size(rq, PAGE_SIZE);
+
+	/* Ensure a merged request will fit in a single I/O ring slot. */
+	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
+
+	/* Make sure buffer addresses are sector-aligned. */
+	blk_queue_dma_alignment(rq, 511);
+
+	/* Make sure we don't use bounce buffers. */
+	blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
+}
+
 static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
-				unsigned int physical_sector_size,
-				unsigned int segments)
+				unsigned int physical_sector_size)
 {
 	struct request_queue *rq;
 	struct blkfront_info *info = gd->private_data;
@@ -944,36 +982,11 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 	}
 
 	rq->queuedata = info;
-	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
-
-	if (info->feature_discard) {
-		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
-		blk_queue_max_discard_sectors(rq, get_capacity(gd));
-		rq->limits.discard_granularity = info->discard_granularity;
-		rq->limits.discard_alignment = info->discard_alignment;
-		if (info->feature_secdiscard)
-			queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
-	}
-
-	/* Hard sector size and max sectors impersonate the equiv. hardware. */
-	blk_queue_logical_block_size(rq, sector_size);
-	blk_queue_physical_block_size(rq, physical_sector_size);
-	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
-
-	/* Each segment in a request is up to an aligned page in size. */
-	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
-	blk_queue_max_segment_size(rq, PAGE_SIZE);
-
-	/* Ensure a merged request will fit in a single I/O ring slot. */
-	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
-
-	/* Make sure buffer addresses are sector-aligned. */
-	blk_queue_dma_alignment(rq, 511);
-
-	/* Make sure we don't use bounce buffers. */
-	blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
-
-	gd->queue = rq;
+	info->rq = gd->queue = rq;
+	info->gd = gd;
+	info->sector_size = sector_size;
+	info->physical_sector_size = physical_sector_size;
+	blkif_set_queue_limits(info);
 
 	return 0;
 }
@@ -1136,16 +1149,11 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	gd->private_data = info;
 	set_capacity(gd, capacity);
 
-	if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size,
-				 info->max_indirect_segments ? :
-				 BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
+	if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) {
 		del_gendisk(gd);
 		goto release;
 	}
 
-	info->rq = gd->queue;
-	info->gd = gd;
-
 	xlvbd_flush(info);
 
 	if (vdisk_info & VDISK_READONLY)
@@ -1315,7 +1323,7 @@ free_shadow:
 			rinfo->ring_ref[i] = GRANT_INVALID_REF;
 		}
 	}
-	free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * PAGE_SIZE));
+	free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE));
 	rinfo->ring.sring = NULL;
 
 	if (rinfo->irq)
@@ -2007,8 +2015,10 @@ static int blkif_recover(struct blkfront_info *info)
 	struct split_bio *split_bio;
 
 	blkfront_gather_backend_features(info);
+	/* Reset limits changed by blk_mq_update_nr_hw_queues(). */
+	blkif_set_queue_limits(info);
 	segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	blk_queue_max_segments(info->rq, segs);
+	blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG);
 
 	for (r_index = 0; r_index < info->nr_rings; r_index++) {
 		struct blkfront_ring_info *rinfo = &info->rinfo[r_index];
@@ -2432,7 +2442,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
 				 info->xbdev->otherend);
-		return;
+		goto fail;
 	}
 
 	xenbus_switch_state(info->xbdev, XenbusStateConnected);
@@ -2445,6 +2455,11 @@ static void blkfront_connect(struct blkfront_info *info)
 	device_add_disk(&info->xbdev->dev, info->gd);
 
 	info->is_ready = 1;
+	return;
+
+fail:
+	blkif_free(info, 0);
+	return;
 }
 
 /**
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 95a4ca6ce6ff..849ad441cd76 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -760,7 +760,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	if (!d->nr_stripes ||
 	    d->nr_stripes > INT_MAX ||
 	    d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) {
-		pr_err("nr_stripes too large");
+		pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)",
+			(unsigned)d->nr_stripes);
 		return -ENOMEM;
 	}
 
@@ -1820,7 +1821,7 @@ static int cache_alloc(struct cache *ca)
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
 
 	if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
-	    !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
+	    !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
 	    !init_fifo(&ca->free_inc,	free << 2, GFP_KERNEL) ||
@@ -1844,7 +1845,7 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
 				struct block_device *bdev, struct cache *ca)
 {
 	char name[BDEVNAME_SIZE];
-	const char *err = NULL;
+	const char *err = NULL; /* must be set for any error case */
 	int ret = 0;
 
 	memcpy(&ca->sb, sb, sizeof(struct cache_sb));
@@ -1861,8 +1862,13 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
 		ca->discard = CACHE_DISCARD(&ca->sb);
 
 	ret = cache_alloc(ca);
-	if (ret != 0)
+	if (ret != 0) {
+		if (ret == -ENOMEM)
+			err = "cache_alloc(): -ENOMEM";
+		else
+			err = "cache_alloc(): unknown error";
 		goto err;
+	}
 
 	if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) {
 		err = "error calling kobject_add";
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 48a5dd740f3b..2206d4477dbb 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1726,6 +1726,7 @@ static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req)
 			break;
 
 		if (req_op(next) == REQ_OP_DISCARD ||
+		    req_op(next) == REQ_OP_SECURE_ERASE ||
 		    req_op(next) == REQ_OP_FLUSH)
 			break;
 
@@ -2150,6 +2151,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	struct mmc_card *card = md->queue.card;
 	struct mmc_host *host = card->host;
 	unsigned long flags;
+	bool req_is_special = mmc_req_is_special(req);
 
 	if (req && !mq->mqrq_prev->req)
 		/* claim host only for the first request */
@@ -2190,8 +2192,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 	}
 
 out:
-	if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) ||
-	    mmc_req_is_special(req))
+	if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || req_is_special)
 		/*
 		 * Release host when there are no more requests
 		 * and after special request(discard, flush) is done.
diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c
index bf14642a576a..708057261b38 100644
--- a/drivers/mmc/card/queue.c
+++ b/drivers/mmc/card/queue.c
@@ -33,7 +33,8 @@ static int mmc_prep_request(struct request_queue *q, struct request *req)
 	/*
 	 * We only like normal block requests and discards.
 	 */
-	if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) {
+	if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD &&
+	    req_op(req) != REQ_OP_SECURE_ERASE) {
 		blk_dump_rq_flags(req, "MMC bad request");
 		return BLKPREP_KILL;
 	}
@@ -64,6 +65,8 @@ static int mmc_queue_thread(void *d)
 		spin_unlock_irq(q->queue_lock);
 
 		if (req || mq->mqrq_prev->req) {
+			bool req_is_special = mmc_req_is_special(req);
+
 			set_current_state(TASK_RUNNING);
 			mq->issue_fn(mq, req);
 			cond_resched();
@@ -79,7 +82,7 @@ static int mmc_queue_thread(void *d)
 			 * has been finished. Do not assign it to previous
 			 * request.
 			 */
-			if (mmc_req_is_special(req))
+			if (req_is_special)
 				mq->mqrq_cur->req = NULL;
 
 			mq->mqrq_prev->brq.mrq.data = NULL;
diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h
index d62531124d54..fee5e1271465 100644
--- a/drivers/mmc/card/queue.h
+++ b/drivers/mmc/card/queue.h
@@ -4,7 +4,9 @@
 static inline bool mmc_req_is_special(struct request *req)
 {
 	return req &&
-		(req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD);
+		(req_op(req) == REQ_OP_FLUSH ||
+		 req_op(req) == REQ_OP_DISCARD ||
+		 req_op(req) == REQ_OP_SECURE_ERASE);
 }
 
 struct request;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 7ff2e820bbf4..2feacc70bf61 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -81,10 +81,12 @@ EXPORT_SYMBOL_GPL(nvme_cancel_request);
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state)
 {
-	enum nvme_ctrl_state old_state = ctrl->state;
+	enum nvme_ctrl_state old_state;
 	bool changed = false;
 
 	spin_lock_irq(&ctrl->lock);
+
+	old_state = ctrl->state;
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
@@ -140,11 +142,12 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	default:
 		break;
 	}
-	spin_unlock_irq(&ctrl->lock);
 
 	if (changed)
 		ctrl->state = new_state;
 
+	spin_unlock_irq(&ctrl->lock);
+
 	return changed;
 }
 EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
@@ -608,7 +611,7 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
 
 	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
 			NVME_QID_ANY, 0, 0);
-	if (ret >= 0)
+	if (ret >= 0 && result)
 		*result = le32_to_cpu(cqe.result);
 	return ret;
 }
@@ -628,7 +631,7 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
 
 	ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
 			NVME_QID_ANY, 0, 0);
-	if (ret >= 0)
+	if (ret >= 0 && result)
 		*result = le32_to_cpu(cqe.result);
 	return ret;
 }