Merge tag 'for-5.6/block-2020-01-27' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "This may be the most quiet round we've had in years. I'm not
  complaining. Really not a lot to detail here, outside of spelling and
  documentation improvements/fixes, we have:

   - Allow t10-pi to be modular (Herbert)

   - Remove dead code in bfq (Alex)

   - Mark zone management requests with REQ_SYNC (Chaitanya)

   - BFQ division improvement (Wen)

   - Small series improving plugging (Pavel)"

* tag 'for-5.6/block-2020-01-27' of git://git.kernel.dk/linux-block:
  partitions/ldm: fix spelling mistake "to" -> "too"
  block, bfq: improve arithmetic division in bfq_delta()
  block/bfq: remove unused bfq_class_rt which never used
  block: mark zone-mgmt bios with REQ_SYNC
  blk-mq: Document functions for sending request
  block: Allow t10-pi to be modular
  blk-mq: optimise blk_mq_flush_plug_list()
  list: introduce list_for_each_continue()
  blk-mq: optimise rq sort function

block/Kconfig

@@ -66,7 +66,6 @@ config BLK_DEV_BSGLIB
 
 config BLK_DEV_INTEGRITY
 	bool "Block layer data integrity support"
-	select CRC_T10DIF if BLK_DEV_INTEGRITY
 	---help---
 	Some storage devices allow extra information to be
 	stored/retrieved to help protect the data.  The block layer
@@ -77,6 +76,11 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
+config BLK_DEV_INTEGRITY_T10
+	tristate
+	depends on BLK_DEV_INTEGRITY
+	select CRC_T10DIF
+
 config BLK_DEV_ZONED
 	bool "Zoned block device support"
 	select MQ_IOSCHED_DEADLINE

block/Makefile

@@ -27,7 +27,8 @@ obj-$(CONFIG_IOSCHED_BFQ)	+= bfq.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
-obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
+obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o
+obj-$(CONFIG_BLK_DEV_INTEGRITY_T10)	+= t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
 obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
 obj-$(CONFIG_BLK_MQ_RDMA)	+= blk-mq-rdma.o

block/bfq-iosched.c

@@ -427,7 +427,6 @@ void bfq_schedule_dispatch(struct bfq_data *bfqd)
 }
 
 #define bfq_class_idle(bfqq)	((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
-#define bfq_class_rt(bfqq)	((bfqq)->ioprio_class == IOPRIO_CLASS_RT)
 
 #define bfq_sample_valid(samples)	((samples) > 80)
 

block/bfq-wf2q.c

@@ -277,10 +277,7 @@ struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
  */
 static u64 bfq_delta(unsigned long service, unsigned long weight)
 {
-	u64 d = (u64)service << WFQ_SERVICE_SHIFT;
-
-	do_div(d, weight);
-	return d;
+	return div64_ul((u64)service << WFQ_SERVICE_SHIFT, weight);
 }
 
 /**

block/blk-mq.c

@@ -641,6 +641,14 @@ bool blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
+/**
+ * blk_mq_start_request - Start processing a request
+ * @rq: Pointer to request to be started
+ *
+ * Function used by device drivers to notify the block layer that a request
+ * is going to be processed now, so blk layer can do proper initializations
+ * such as starting the timeout timer.
+ */
 void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -1327,6 +1335,12 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 	return (queued + errors) != 0;
 }
 
+/**
+ * __blk_mq_run_hw_queue - Run a hardware queue.
+ * @hctx: Pointer to the hardware queue to run.
+ *
+ * Send pending requests to the hardware.
+ */
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	int srcu_idx;
@@ -1424,6 +1438,15 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 	return next_cpu;
 }
 
+/**
+ * __blk_mq_delay_run_hw_queue - Run (or schedule to run) a hardware queue.
+ * @hctx: Pointer to the hardware queue to run.
+ * @async: If we want to run the queue asynchronously.
+ * @msecs: Microseconds of delay to wait before running the queue.
+ *
+ * If !@async, try to run the queue now. Else, run the queue asynchronously and
+ * with a delay of @msecs.
+ */
 static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
 					unsigned long msecs)
 {
@@ -1445,12 +1468,28 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
 				    msecs_to_jiffies(msecs));
 }
 
+/**
+ * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously.
+ * @hctx: Pointer to the hardware queue to run.
+ * @msecs: Microseconds of delay to wait before running the queue.
+ *
+ * Run a hardware queue asynchronously with a delay of @msecs.
+ */
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 {
 	__blk_mq_delay_run_hw_queue(hctx, true, msecs);
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
 
+/**
+ * blk_mq_run_hw_queue - Start to run a hardware queue.
+ * @hctx: Pointer to the hardware queue to run.
+ * @async: If we want to run the queue asynchronously.
+ *
+ * Check if the request queue is not in a quiesced state and if there are
+ * pending requests to be sent. If this is true, run the queue to send requests
+ * to hardware.
+ */
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
 	int srcu_idx;
@@ -1474,6 +1513,11 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
+/**
+ * blk_mq_run_hw_queue - Run all hardware queues in a request queue.
+ * @q: Pointer to the request queue to run.
+ * @async: If we want to run the queue asynchronously.
+ */
 void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 {
 	struct blk_mq_hw_ctx *hctx;
@@ -1625,7 +1669,11 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
-/*
+/**
+ * blk_mq_request_bypass_insert - Insert a request at dispatch list.
+ * @rq: Pointer to request to be inserted.
+ * @run_queue: If we should run the hardware queue after inserting the request.
+ *
  * Should only be used carefully, when the caller knows we want to
  * bypass a potential IO scheduler on the target device.
  */
@@ -1668,28 +1716,20 @@ static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b)
 	struct request *rqa = container_of(a, struct request, queuelist);
 	struct request *rqb = container_of(b, struct request, queuelist);
 
-	if (rqa->mq_ctx < rqb->mq_ctx)
-		return -1;
-	else if (rqa->mq_ctx > rqb->mq_ctx)
-		return 1;
-	else if (rqa->mq_hctx < rqb->mq_hctx)
-		return -1;
-	else if (rqa->mq_hctx > rqb->mq_hctx)
-		return 1;
+	if (rqa->mq_ctx != rqb->mq_ctx)
+		return rqa->mq_ctx > rqb->mq_ctx;
+	if (rqa->mq_hctx != rqb->mq_hctx)
+		return rqa->mq_hctx > rqb->mq_hctx;
 
 	return blk_rq_pos(rqa) > blk_rq_pos(rqb);
 }
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 {
-	struct blk_mq_hw_ctx *this_hctx;
-	struct blk_mq_ctx *this_ctx;
-	struct request_queue *this_q;
-	struct request *rq;
 	LIST_HEAD(list);
-	LIST_HEAD(rq_list);
-	unsigned int depth;
 
+	if (list_empty(&plug->mq_list))
+		return;
 	list_splice_init(&plug->mq_list, &list);
 
 	if (plug->rq_count > 2 && plug->multiple_queues)
@@ -1697,42 +1737,27 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 
 	plug->rq_count = 0;
 
-	this_q = NULL;
-	this_hctx = NULL;
-	this_ctx = NULL;
-	depth = 0;
-
-	while (!list_empty(&list)) {
-		rq = list_entry_rq(list.next);
-		list_del_init(&rq->queuelist);
-		BUG_ON(!rq->q);
-		if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx) {
-			if (this_hctx) {
-				trace_block_unplug(this_q, depth, !from_schedule);
-				blk_mq_sched_insert_requests(this_hctx, this_ctx,
-								&rq_list,
-								from_schedule);
-			}
-
-			this_q = rq->q;
-			this_ctx = rq->mq_ctx;
-			this_hctx = rq->mq_hctx;
-			depth = 0;
+	do {
+		struct list_head rq_list;
+		struct request *rq, *head_rq = list_entry_rq(list.next);
+		struct list_head *pos = &head_rq->queuelist; /* skip first */
+		struct blk_mq_hw_ctx *this_hctx = head_rq->mq_hctx;
+		struct blk_mq_ctx *this_ctx = head_rq->mq_ctx;
+		unsigned int depth = 1;
+
+		list_for_each_continue(pos, &list) {
+			rq = list_entry_rq(pos);
+			BUG_ON(!rq->q);
+			if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx)
+				break;
+			depth++;
 		}
 
-		depth++;
-		list_add_tail(&rq->queuelist, &rq_list);
-	}
-
-	/*
-	 * If 'this_hctx' is set, we know we have entries to complete
-	 * on 'rq_list'. Do those.
-	 */
-	if (this_hctx) {
-		trace_block_unplug(this_q, depth, !from_schedule);
+		list_cut_before(&rq_list, &list, pos);
+		trace_block_unplug(head_rq->q, depth, !from_schedule);
 		blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list,
 						from_schedule);
-	}
+	} while(!list_empty(&list));
 }
 
 static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
@@ -1828,6 +1853,17 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
+/**
+ * blk_mq_try_issue_directly - Try to send a request directly to device driver.
+ * @hctx: Pointer of the associated hardware queue.
+ * @rq: Pointer to request to be sent.
+ * @cookie: Request queue cookie.
+ *
+ * If the device has enough resources to accept a new request now, send the
+ * request directly to device driver. Else, insert at hctx->dispatch queue, so
+ * we can try send it another time in the future. Requests inserted at this
+ * queue have higher priority.
+ */
 static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		struct request *rq, blk_qc_t *cookie)
 {
@@ -1905,6 +1941,22 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
 	}
 }
 
+/**
+ * blk_mq_make_request - Create and send a request to block device.
+ * @q: Request queue pointer.
+ * @bio: Bio pointer.
+ *
+ * Builds up a request structure from @q and @bio and send to the device. The
+ * request may not be queued directly to hardware if:
+ * * This request can be merged with another one
+ * * We want to place request at plug queue for possible future merging
+ * * There is an IO scheduler active at this queue
+ *
+ * It will not queue the request if there is an error with the bio, or at the
+ * request creation.
+ *
+ * Returns: Request queue cookie.
+ */
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
@@ -1950,7 +2002,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	plug = blk_mq_plug(q, bio);
 	if (unlikely(is_flush_fua)) {
-		/* bypass scheduler for flush rq */
+		/* Bypass scheduler for flush requests */
 		blk_insert_flush(rq);
 		blk_mq_run_hw_queue(data.hctx, true);
 	} else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs ||
@@ -1978,6 +2030,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 		blk_add_rq_to_plug(plug, rq);
 	} else if (q->elevator) {
+		/* Insert the request at the IO scheduler queue */
 		blk_mq_sched_insert_request(rq, false, true, true);
 	} else if (plug && !blk_queue_nomerges(q)) {
 		/*
@@ -2004,8 +2057,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		}
 	} else if ((q->nr_hw_queues > 1 && is_sync) ||
 			!data.hctx->dispatch_busy) {
+		/*
+		 * There is no scheduler and we can try to send directly
+		 * to the hardware.
+		 */
 		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
 	} else {
+		/* Default case. */
 		blk_mq_sched_insert_request(rq, false, true, true);
 	}
 

block/blk-zoned.c

@@ -198,7 +198,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 			break;
 		}
 
-		bio->bi_opf = op;
+		bio->bi_opf = op | REQ_SYNC;
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 

block/partitions/ldm.c

@@ -1233,7 +1233,7 @@ static bool ldm_frag_add (const u8 *data, int size, struct list_head *frags)
 	BUG_ON (!data || !frags);
 
 	if (size < 2 * VBLK_SIZE_HEAD) {
-		ldm_error("Value of size is to small.");
+		ldm_error("Value of size is too small.");
 		return false;
 	}
 

block/t10-pi.c

@@ -7,6 +7,7 @@
 #include <linux/t10-pi.h>
 #include <linux/blkdev.h>
 #include <linux/crc-t10dif.h>
+#include <linux/module.h>
 #include <net/checksum.h>
 
 typedef __be16 (csum_fn) (void *, unsigned int);
@@ -280,3 +281,5 @@ const struct blk_integrity_profile t10_pi_type3_ip = {
 	.complete_fn		= t10_pi_type3_complete,
 };
 EXPORT_SYMBOL(t10_pi_type3_ip);
+
+MODULE_LICENSE("GPL");

drivers/nvme/host/Kconfig

 # SPDX-License-Identifier: GPL-2.0-only
 config NVME_CORE
 	tristate
+	select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY
 
 config BLK_DEV_NVME
 	tristate "NVM Express block device"

drivers/scsi/Kconfig

@@ -68,6 +68,7 @@ comment "SCSI support type (disk, tape, CD-ROM)"
 config BLK_DEV_SD
 	tristate "SCSI disk support"
 	depends on SCSI
+	select BLK_DEV_INTEGRITY_T10 if BLK_DEV_INTEGRITY
 	---help---
 	  If you want to use SCSI hard disks, Fibre Channel disks,
 	  Serial ATA (SATA) or Parallel ATA (PATA) hard disks,

include/linux/list.h

@@ -538,6 +538,16 @@ static inline void list_splice_tail_init(struct list_head *list,
 #define list_for_each(pos, head) \
 	for (pos = (head)->next; pos != (head); pos = pos->next)
 
+/**
+ * list_for_each_continue - continue iteration over a list
+ * @pos:	the &struct list_head to use as a loop cursor.
+ * @head:	the head for your list.
+ *
+ * Continue to iterate over a list, continuing after the current position.
+ */
+#define list_for_each_continue(pos, head) \
+	for (pos = pos->next; pos != (head); pos = pos->next)
+
 /**
  * list_for_each_prev	-	iterate over a list backwards
  * @pos:	the &struct list_head to use as a loop cursor.