Merge tag 'for-5.7/block-2020-03-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Online capacity resizing (Balbir)

 - Number of hardware queue change fixes (Bart)

 - null_blk fault injection addition (Bart)

 - Cleanup of queue allocation, unifying the node/no-node API
   (Christoph)

 - Cleanup of genhd, moving code to where it makes sense (Christoph)

 - Cleanup of the partition handling code (Christoph)

 - disk stat fixes/improvements (Konstantin)

 - BFQ improvements (Paolo)

 - Various fixes and improvements

* tag 'for-5.7/block-2020-03-29' of git://git.kernel.dk/linux-block: (72 commits)
  block: return NULL in blk_alloc_queue() on error
  block: move bio_map_* to blk-map.c
  Revert "blkdev: check for valid request queue before issuing flush"
  block: simplify queue allocation
  bcache: pass the make_request methods to blk_queue_make_request
  null_blk: use blk_mq_init_queue_data
  block: add a blk_mq_init_queue_data helper
  block: move the ->devnode callback to struct block_device_operations
  block: move the part_stat* helpers from genhd.h to a new header
  block: move block layer internals out of include/linux/genhd.h
  block: move guard_bio_eod to bio.c
  block: unexport get_gendisk
  block: unexport disk_map_sector_rcu
  block: unexport disk_get_part
  block: mark part_in_flight and part_in_flight_rw static
  block: mark block_depr static
  block: factor out requeue handling from dispatch code
  block/diskstats: replace time_in_queue with sum of request times
  block/diskstats: accumulate all per-cpu counters in one pass
  block/diskstats: more accurate approximation of io_ticks for slow disks
  ...

Documentation/admin-guide/iostats.rst

@@ -100,7 +100,7 @@ Field 10 -- # of milliseconds spent doing I/Os (unsigned int)
 
     Since 5.0 this field counts jiffies when at least one request was
     started or completed. If request runs more than 2 jiffies then some
-    I/O time will not be accounted unless there are other requests.
+    I/O time might be not accounted in case of concurrent requests.
 
 Field 11 -- weighted # of milliseconds spent doing I/Os (unsigned int)
     This field is incremented at each I/O start, I/O completion, I/O
@@ -143,6 +143,9 @@ are summed (possibly overflowing the unsigned long variable they are
 summed to) and the result given to the user.  There is no convenient
 user interface for accessing the per-CPU counters themselves.
 
+Since 4.19 request times are measured with nanoseconds precision and
+truncated to milliseconds before showing in this interface.
+
 Disks vs Partitions
 -------------------
 

Documentation/block/capability.rst

@@ -2,17 +2,9 @@
 Generic Block Device Capability
 ===============================
 
-This file documents the sysfs file block/<disk>/capability
+This file documents the sysfs file ``block/<disk>/capability``.
 
-capability is a hex word indicating which capabilities a specific disk
-supports.  For more information on bits not listed here, see
-include/linux/genhd.h
+``capability`` is a bitfield, printed in hexadecimal, indicating which
+capabilities a specific block device supports:
 
-GENHD_FL_MEDIA_CHANGE_NOTIFY
-----------------------------
-
-Value: 4
-
-When this bit is set, the disk supports Asynchronous Notification
-of media change events.  These events will be broadcast to user
-space via kernel uevent.
+.. kernel-doc:: include/linux/genhd.h

Documentation/scsi/scsi_mid_low_api.txt

@@ -299,7 +299,6 @@ Summary:
    scsi_host_alloc - return a new scsi_host instance whose refcount==1
    scsi_host_get - increments Scsi_Host instance's refcount
    scsi_host_put - decrements Scsi_Host instance's refcount (free if 0)
-   scsi_partsize - parse partition table into cylinders, heads + sectors
    scsi_register - create and register a scsi host adapter instance.
    scsi_remove_device - detach and remove a SCSI device
    scsi_remove_host - detach and remove all SCSI devices owned by host
@@ -472,26 +471,6 @@ void scsi_host_get(struct Scsi_Host *shost)
 void scsi_host_put(struct Scsi_Host *shost)
 
 
-/**
- * scsi_partsize - parse partition table into cylinders, heads + sectors
- * @buf: pointer to partition table
- * @capacity: size of (total) disk in 512 byte sectors
- * @cyls: outputs number of cylinders calculated via this pointer
- * @hds: outputs number of heads calculated via this pointer
- * @secs: outputs number of sectors calculated via this pointer
- *
- *      Returns 0 on success, -1 on failure
- *
- *      Might block: no
- *
- *      Notes: Caller owns memory returned (free with kfree() )
- *
- *      Defined in: drivers/scsi/scsicam.c
- **/
-int scsi_partsize(unsigned char *buf, unsigned long capacity,
-                  unsigned int *cyls, unsigned int *hds, unsigned int *secs)
-
-
 /**
  * scsi_register - create and register a scsi host adapter instance.
  * @sht:        pointer to scsi host template

arch/m68k/emu/nfblock.c

@@ -118,12 +118,11 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
 	dev->bsize = bsize;
 	dev->bshift = ffs(bsize) - 10;
 
-	dev->queue = blk_alloc_queue(GFP_KERNEL);
+	dev->queue = blk_alloc_queue(nfhd_make_request, NUMA_NO_NODE);
 	if (dev->queue == NULL)
 		goto free_dev;
 
 	dev->queue->queuedata = dev;
-	blk_queue_make_request(dev->queue, nfhd_make_request);
 	blk_queue_logical_block_size(dev->queue, bsize);
 
 	dev->disk = alloc_disk(16);

arch/xtensa/platforms/iss/simdisk.c

@@ -267,13 +267,12 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
 	spin_lock_init(&dev->lock);
 	dev->users = 0;
 
-	dev->queue = blk_alloc_queue(GFP_KERNEL);
+	dev->queue = blk_alloc_queue(simdisk_make_request, NUMA_NO_NODE);
 	if (dev->queue == NULL) {
 		pr_err("blk_alloc_queue failed\n");
 		goto out_alloc_queue;
 	}
 
-	blk_queue_make_request(dev->queue, simdisk_make_request);
 	dev->queue->queuedata = dev;
 
 	dev->gd = alloc_disk(SIMDISK_MINORS);

block/Makefile

@@ -8,8 +8,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
-			genhd.o partition-generic.o ioprio.o \
-			badblocks.o partitions/ blk-rq-qos.o
+			genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o
 
 obj-$(CONFIG_BOUNCE)		+= bounce.o
 obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o

block/bfq-cgroup.c

@@ -642,6 +642,12 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 {
 	struct bfq_entity *entity = &bfqq->entity;
 
+	/*
+	 * Get extra reference to prevent bfqq from being freed in
+	 * next possible expire or deactivate.
+	 */
+	bfqq->ref++;
+
 	/* If bfqq is empty, then bfq_bfqq_expire also invokes
 	 * bfq_del_bfqq_busy, thereby removing bfqq and its entity
 	 * from data structures related to current group. Otherwise we
@@ -652,12 +658,6 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
 				false, BFQQE_PREEMPTED);
 
-	/*
-	 * get extra reference to prevent bfqq from being freed in
-	 * next possible deactivate
-	 */
-	bfqq->ref++;
-
 	if (bfq_bfqq_busy(bfqq))
 		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
 	else if (entity->on_st_or_in_serv)
@@ -677,7 +677,7 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 
 	if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
 		bfq_schedule_dispatch(bfqd);
-	/* release extra ref taken above */
+	/* release extra ref taken above, bfqq may happen to be freed now */
 	bfq_put_queue(bfqq);
 }
 
@@ -714,10 +714,7 @@ static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
 
 		if (entity->sched_data != &bfqg->sched_data) {
 			bic_set_bfqq(bic, NULL, 0);
-			bfq_log_bfqq(bfqd, async_bfqq,
-				     "bic_change_group: %p %d",
-				     async_bfqq, async_bfqq->ref);
-			bfq_put_queue(async_bfqq);
+			bfq_release_process_ref(bfqd, async_bfqq);
 		}
 	}
 
@@ -818,39 +815,53 @@ static void bfq_flush_idle_tree(struct bfq_service_tree *st)
 /**
  * bfq_reparent_leaf_entity - move leaf entity to the root_group.
  * @bfqd: the device data structure with the root group.
- * @entity: the entity to move.
+ * @entity: the entity to move, if entity is a leaf; or the parent entity
+ *	    of an active leaf entity to move, if entity is not a leaf.
  */
 static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
-				     struct bfq_entity *entity)
+				     struct bfq_entity *entity,
+				     int ioprio_class)
 {
-	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct bfq_queue *bfqq;
+	struct bfq_entity *child_entity = entity;
 
+	while (child_entity->my_sched_data) { /* leaf not reached yet */
+		struct bfq_sched_data *child_sd = child_entity->my_sched_data;
+		struct bfq_service_tree *child_st = child_sd->service_tree +
+			ioprio_class;
+		struct rb_root *child_active = &child_st->active;
+
+		child_entity = bfq_entity_of(rb_first(child_active));
+
+		if (!child_entity)
+			child_entity = child_sd->in_service_entity;
+	}
+
+	bfqq = bfq_entity_to_bfqq(child_entity);
 	bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
 }
 
 /**
- * bfq_reparent_active_entities - move to the root group all active
- *                                entities.
+ * bfq_reparent_active_queues - move to the root group all active queues.
  * @bfqd: the device data structure with the root group.
  * @bfqg: the group to move from.
- * @st: the service tree with the entities.
+ * @st: the service tree to start the search from.
  */
-static void bfq_reparent_active_entities(struct bfq_data *bfqd,
-					 struct bfq_group *bfqg,
-					 struct bfq_service_tree *st)
+static void bfq_reparent_active_queues(struct bfq_data *bfqd,
+				       struct bfq_group *bfqg,
+				       struct bfq_service_tree *st,
+				       int ioprio_class)
 {
 	struct rb_root *active = &st->active;
-	struct bfq_entity *entity = NULL;
-
-	if (!RB_EMPTY_ROOT(&st->active))
-		entity = bfq_entity_of(rb_first(active));
+	struct bfq_entity *entity;
 
-	for (; entity ; entity = bfq_entity_of(rb_first(active)))
-		bfq_reparent_leaf_entity(bfqd, entity);
+	while ((entity = bfq_entity_of(rb_first(active))))
+		bfq_reparent_leaf_entity(bfqd, entity, ioprio_class);
 
 	if (bfqg->sched_data.in_service_entity)
 		bfq_reparent_leaf_entity(bfqd,
-			bfqg->sched_data.in_service_entity);
+					 bfqg->sched_data.in_service_entity,
+					 ioprio_class);
 }
 
 /**
@@ -882,13 +893,6 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
 		st = bfqg->sched_data.service_tree + i;
 
-		/*
-		 * The idle tree may still contain bfq_queues belonging
-		 * to exited task because they never migrated to a different
-		 * cgroup from the one being destroyed now.
-		 */
-		bfq_flush_idle_tree(st);
-
 		/*
 		 * It may happen that some queues are still active
 		 * (busy) upon group destruction (if the corresponding
@@ -901,7 +905,20 @@ static void bfq_pd_offline(struct blkg_policy_data *pd)
 		 * There is no need to put the sync queues, as the
 		 * scheduler has taken no reference.
 		 */
-		bfq_reparent_active_entities(bfqd, bfqg, st);
+		bfq_reparent_active_queues(bfqd, bfqg, st, i);
+
+		/*
+		 * The idle tree may still contain bfq_queues
+		 * belonging to exited task because they never
+		 * migrated to a different cgroup from the one being
+		 * destroyed now. In addition, even
+		 * bfq_reparent_active_queues() may happen to add some
+		 * entities to the idle tree. It happens if, in some
+		 * of the calls to bfq_bfqq_move() performed by
+		 * bfq_reparent_active_queues(), the queue to move is
+		 * empty and gets expired.
+		 */
+		bfq_flush_idle_tree(st);
 	}
 
 	__bfq_deactivate_entity(entity, false);

block/bfq-iosched.c

@@ -2716,8 +2716,6 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
 	}
 }
 
-
-static
 void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	/*
@@ -6215,20 +6213,28 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
 	return bfqq;
 }
 
-static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
+static void
+bfq_idle_slice_timer_body(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
-	struct bfq_data *bfqd = bfqq->bfqd;
 	enum bfqq_expiration reason;
 	unsigned long flags;
 
 	spin_lock_irqsave(&bfqd->lock, flags);
-	bfq_clear_bfqq_wait_request(bfqq);
 
+	/*
+	 * Considering that bfqq may be in race, we should firstly check
+	 * whether bfqq is in service before doing something on it. If
+	 * the bfqq in race is not in service, it has already been expired
+	 * through __bfq_bfqq_expire func and its wait_request flags has
+	 * been cleared in __bfq_bfqd_reset_in_service func.
+	 */
 	if (bfqq != bfqd->in_service_queue) {
 		spin_unlock_irqrestore(&bfqd->lock, flags);
 		return;
 	}
 
+	bfq_clear_bfqq_wait_request(bfqq);
+
 	if (bfq_bfqq_budget_timeout(bfqq))
 		/*
 		 * Also here the queue can be safely expired
@@ -6273,7 +6279,7 @@ static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
 	 * early.
 	 */
 	if (bfqq)
-		bfq_idle_slice_timer_body(bfqq);
+		bfq_idle_slice_timer_body(bfqd, bfqq);
 
 	return HRTIMER_NORESTART;
 }

block/bfq-iosched.h

@@ -955,6 +955,7 @@ void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		     bool compensate, enum bfqq_expiration reason);
 void bfq_put_queue(struct bfq_queue *bfqq);
 void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 void bfq_schedule_dispatch(struct bfq_data *bfqd);
 void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);