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

Pull block layer fixes from Jens Axboe:
 "A round of fixes/updates for the current series.

  This looks a little bigger than it is, but that's mainly because we
  pushed the lightnvm enabled null_blk change out of the merge window so
  it could be updated a bit.  The rest of the volume is also mostly
  lightnvm.  In particular:

   - Lightnvm.  Various fixes, additions, updates from Matias and
     Javier, as well as from Wenwei Tao.

   - NVMe:
        - Fix for potential arithmetic overflow from Keith.
        - Also from Keith, ensure that we reap pending completions from
          a completion queue before deleting it.  Fixes kernel crashes
          when resetting a device with IO pending.
        - Various little lightnvm related tweaks from Matias.

   - Fixup flushes to go through the IO scheduler, for the cases where a
     flush is not required.  Fixes a case in CFQ where we would be
     idling and not see this request, hence not break the idling.  From
     Jan Kara.

   - Use list_{first,prev,next} in elevator.c for cleaner code.  From
     Gelian Tang.

   - Fix for a warning trigger on btrfs and raid on single queue blk-mq
     devices, where we would flush plug callbacks with preemption
     disabled.  From me.

   - A mac partition validation fix from Kees Cook.

   - Two merge fixes from Ming, marked stable.  A third part is adding a
     new warning so we'll notice this quicker in the future, if we screw
     up the accounting.

   - Cleanup of thread name/creation in mtip32xx from Rasmus Villemoes"

* 'for-linus' of git://git.kernel.dk/linux-block: (32 commits)
  blk-merge: warn if figured out segment number is bigger than nr_phys_segments
  blk-merge: fix blk_bio_segment_split
  block: fix segment split
  blk-mq: fix calling unplug callbacks with preempt disabled
  mac: validate mac_partition is within sector
  mtip32xx: use formatting capability of kthread_create_on_node
  NVMe: reap completion entries when deleting queue
  lightnvm: add free and bad lun info to show luns
  lightnvm: keep track of block counts
  nvme: lightnvm: use admin queues for admin cmds
  lightnvm: missing free on init error
  lightnvm: wrong return value and redundant free
  null_blk: do not del gendisk with lightnvm
  null_blk: use device addressing mode
  null_blk: use ppa_cache pool
  NVMe: Fix possible arithmetic overflow for max segments
  blk-flush: Queue through IO scheduler when flush not required
  null_blk: register as a LightNVM device
  elevator: use list_{first,prev,next}_entry
  lightnvm: cleanup queue before target removal
  ...

Author: torvalds

Documentation/block/null_blk.txt

@@ -70,3 +70,6 @@ use_per_node_hctx=[0/1]: Default: 0
      parameter.
   1: The multi-queue block layer is instantiated with a hardware dispatch
      queue for each CPU node in the system.
+
+use_lightnvm=[0/1]: Default: 0
+  Register device with LightNVM. Requires blk-mq to be used.

MAINTAINERS

@@ -6366,6 +6366,7 @@ F:	arch/*/include/asm/pmem.h
 LIGHTNVM PLATFORM SUPPORT
 M:	Matias Bjorling <mb@lightnvm.io>
 W:	http://github/OpenChannelSSD
+L:	linux-block@vger.kernel.org
 S:	Maintained
 F:	drivers/lightnvm/
 F:	include/linux/lightnvm.h

block/blk-flush.c

@@ -422,7 +422,7 @@ void blk_insert_flush(struct request *rq)
 		if (q->mq_ops) {
 			blk_mq_insert_request(rq, false, false, true);
 		} else
-			list_add_tail(&rq->queuelist, &q->queue_head);
+			q->elevator->type->ops.elevator_add_req_fn(q, rq);
 		return;
 	}
 

block/blk-merge.c

@@ -76,6 +76,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
 	unsigned seg_size = 0, nsegs = 0, sectors = 0;
+	unsigned front_seg_size = bio->bi_seg_front_size;
+	bool do_split = true;
+	struct bio *new = NULL;
 
 	bio_for_each_segment(bv, bio, iter) {
 		if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q))
@@ -98,7 +101,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 
 			seg_size += bv.bv_len;
 			bvprv = bv;
-			bvprvp = &bv;
+			bvprvp = &bvprv;
 			sectors += bv.bv_len >> 9;
 			continue;
 		}
@@ -108,16 +111,29 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 
 		nsegs++;
 		bvprv = bv;
-		bvprvp = &bv;
+		bvprvp = &bvprv;
 		seg_size = bv.bv_len;
 		sectors += bv.bv_len >> 9;
+
+		if (nsegs == 1 && seg_size > front_seg_size)
+			front_seg_size = seg_size;
 	}
 
-	*segs = nsegs;
-	return NULL;
+	do_split = false;
 split:
 	*segs = nsegs;
-	return bio_split(bio, sectors, GFP_NOIO, bs);
+
+	if (do_split) {
+		new = bio_split(bio, sectors, GFP_NOIO, bs);
+		if (new)
+			bio = new;
+	}
+
+	bio->bi_seg_front_size = front_seg_size;
+	if (seg_size > bio->bi_seg_back_size)
+		bio->bi_seg_back_size = seg_size;
+
+	return do_split ? new : NULL;
 }
 
 void blk_queue_split(struct request_queue *q, struct bio **bio,
@@ -412,6 +428,12 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	if (sg)
 		sg_mark_end(sg);
 
+	/*
+	 * Something must have been wrong if the figured number of
+	 * segment is bigger than number of req's physical segments
+	 */
+	WARN_ON(nsegs > rq->nr_phys_segments);
+
 	return nsegs;
 }
 EXPORT_SYMBOL(blk_rq_map_sg);

block/blk-mq.c

@@ -1291,15 +1291,16 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_bio_to_request(rq, bio);
 
 		/*
-		 * we do limited pluging. If bio can be merged, do merge.
+		 * We do limited pluging. If the bio can be merged, do that.
 		 * Otherwise the existing request in the plug list will be
 		 * issued. So the plug list will have one request at most
 		 */
 		if (plug) {
 			/*
 			 * The plug list might get flushed before this. If that
-			 * happens, same_queue_rq is invalid and plug list is empty
-			 **/
+			 * happens, same_queue_rq is invalid and plug list is
+			 * empty
+			 */
 			if (same_queue_rq && !list_empty(&plug->mq_list)) {
 				old_rq = same_queue_rq;
 				list_del_init(&old_rq->queuelist);
@@ -1380,12 +1381,15 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_bio_to_request(rq, bio);
 		if (!request_count)
 			trace_block_plug(q);
-		else if (request_count >= BLK_MAX_REQUEST_COUNT) {
+
+		blk_mq_put_ctx(data.ctx);
+
+		if (request_count >= BLK_MAX_REQUEST_COUNT) {
 			blk_flush_plug_list(plug, false);
 			trace_block_plug(q);
 		}
+
 		list_add_tail(&rq->queuelist, &plug->mq_list);
-		blk_mq_put_ctx(data.ctx);
 		return cookie;
 	}
 

block/noop-iosched.c

@@ -21,10 +21,10 @@ static void noop_merged_requests(struct request_queue *q, struct request *rq,
 static int noop_dispatch(struct request_queue *q, int force)
 {
 	struct noop_data *nd = q->elevator->elevator_data;
+	struct request *rq;
 
-	if (!list_empty(&nd->queue)) {
-		struct request *rq;
-		rq = list_entry(nd->queue.next, struct request, queuelist);
+	rq = list_first_entry_or_null(&nd->queue, struct request, queuelist);
+	if (rq) {
 		list_del_init(&rq->queuelist);
 		elv_dispatch_sort(q, rq);
 		return 1;
@@ -46,7 +46,7 @@ noop_former_request(struct request_queue *q, struct request *rq)
 
 	if (rq->queuelist.prev == &nd->queue)
 		return NULL;
-	return list_entry(rq->queuelist.prev, struct request, queuelist);
+	return list_prev_entry(rq, queuelist);
 }
 
 static struct request *
@@ -56,7 +56,7 @@ noop_latter_request(struct request_queue *q, struct request *rq)
 
 	if (rq->queuelist.next == &nd->queue)
 		return NULL;
-	return list_entry(rq->queuelist.next, struct request, queuelist);
+	return list_next_entry(rq, queuelist);
 }
 
 static int noop_init_queue(struct request_queue *q, struct elevator_type *e)

block/partitions/mac.c

@@ -32,7 +32,7 @@ int mac_partition(struct parsed_partitions *state)
 	Sector sect;
 	unsigned char *data;
 	int slot, blocks_in_map;
-	unsigned secsize;
+	unsigned secsize, datasize, partoffset;
 #ifdef CONFIG_PPC_PMAC
 	int found_root = 0;
 	int found_root_goodness = 0;
@@ -50,10 +50,14 @@ int mac_partition(struct parsed_partitions *state)
 	}
 	secsize = be16_to_cpu(md->block_size);
 	put_dev_sector(sect);
-	data = read_part_sector(state, secsize/512, &sect);
+	datasize = round_down(secsize, 512);
+	data = read_part_sector(state, datasize / 512, &sect);
 	if (!data)
 		return -1;
-	part = (struct mac_partition *) (data + secsize%512);
+	partoffset = secsize % 512;
+	if (partoffset + sizeof(*part) > datasize)
+		return -1;
+	part = (struct mac_partition *) (data + partoffset);
 	if (be16_to_cpu(part->signature) != MAC_PARTITION_MAGIC) {
 		put_dev_sector(sect);
 		return 0;		/* not a MacOS disk */

drivers/Makefile

@@ -63,14 +63,14 @@ obj-$(CONFIG_FB_I810)           += video/fbdev/i810/
 obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
 
 obj-$(CONFIG_PARPORT)		+= parport/
+obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= macintosh/
 obj-$(CONFIG_IDE)		+= ide/
 obj-$(CONFIG_SCSI)		+= scsi/
-obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= nvme/
 obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/

drivers/block/mtip32xx/mtip32xx.c

@@ -3810,7 +3810,6 @@ static int mtip_block_initialize(struct driver_data *dd)
 	sector_t capacity;
 	unsigned int index = 0;
 	struct kobject *kobj;
-	unsigned char thd_name[16];
 
 	if (dd->disk)
 		goto skip_create_disk; /* hw init done, before rebuild */
@@ -3958,10 +3957,9 @@ static int mtip_block_initialize(struct driver_data *dd)
 	}
 
 start_service_thread:
-	sprintf(thd_name, "mtip_svc_thd_%02d", index);
 	dd->mtip_svc_handler = kthread_create_on_node(mtip_service_thread,
-						dd, dd->numa_node, "%s",
-						thd_name);
+						dd, dd->numa_node,
+						"mtip_svc_thd_%02d", index);
 
 	if (IS_ERR(dd->mtip_svc_handler)) {
 		dev_err(&dd->pdev->dev, "service thread failed to start\n");