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

Pull more block layer updates from Jens Axboe:
"A followup pull request, with some parts that either needed a bit more
testing before going in, merge sync, or just later arriving fixes.
This contains:

- Timer related updates from Kees. These were purposefully delayed
since I didn't want to pull in a later v4.14-rc tag to my block
tree.

- ide-cd prep sense buffer fix from Bart. Also delayed, as not to
clash with the late fix we put into 4.14-rc.

- Small BFQ updates series from Luca and Paolo.

- Single nvmet fix from James, fixing a non-functional case there.

- Bio fast clone fix from Michael, which made bcache return the wrong
data for some cases.

- Legacy IO path regression hang fix from Ming"

* 'for-linus' of git://git.kernel.dk/linux-block:
bio: ensure __bio_clone_fast copies bi_partno
nvmet_fc: fix better length checking
block: wake up all tasks blocked in get_request()
block, bfq: move debug blkio stats behind CONFIG_DEBUG_BLK_CGROUP
block, bfq: update blkio stats outside the scheduler lock
block, bfq: add missing invocations of bfqg_stats_update_io_add/remove
doc, block, bfq: update max IOPS sustainable with BFQ
ide: Make ide_cdrom_prep_fs() initialize the sense buffer pointer
md: Convert timers to use timer_setup()
block: swim3: Convert timers to use timer_setup()
block/aoe: Convert timers to use timer_setup()
amifloppy: Convert timers to use timer_setup()
block/floppy: Convert callback to pass timer_list

Documentation/block/bfq-iosched.txt

···
 details on how to configure BFQ for the desired tradeoff between
 latency and throughput, or on how to maximize throughput.
 
-On average CPUs, the current version of BFQ can handle devices
-performing at most ~30K IOPS; at most ~50 KIOPS on faster CPUs. As a
-reference, 30-50 KIOPS correspond to very high bandwidths with
-sequential I/O (e.g., 8-12 GB/s if I/O requests are 256 KB large), and
-to 120-200 MB/s with 4KB random I/O. BFQ is currently being tested on
-multi-queue devices too.
+BFQ has a non-null overhead, which limits the maximum IOPS that a CPU
+can process for a device scheduled with BFQ. To give an idea of the
+limits on slow or average CPUs, here are, first, the limits of BFQ for
+three different CPUs, on, respectively, an average laptop, an old
+desktop, and a cheap embedded system, in case full hierarchical
+support is enabled (i.e., CONFIG_BFQ_GROUP_IOSCHED is set), but
+CONFIG_DEBUG_BLK_CGROUP is not set (Section 4-2):
+- Intel i7-4850HQ: 400 KIOPS
+- AMD A8-3850: 250 KIOPS
+- ARM CortexTM-A53 Octa-core: 80 KIOPS
+
+If CONFIG_DEBUG_BLK_CGROUP is set (and of course full hierarchical
+support is enabled), then the sustainable throughput with BFQ
+decreases, because all blkio.bfq* statistics are created and updated
+(Section 4-2). For BFQ, this leads to the following maximum
+sustainable throughputs, on the same systems as above:
+- Intel i7-4850HQ: 310 KIOPS
+- AMD A8-3850: 200 KIOPS
+- ARM CortexTM-A53 Octa-core: 56 KIOPS
+
+BFQ works for multi-queue devices too.
 
 The table of contents follow. Impatients can just jump to Section 3.
 
···
 BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group
 parameter to set the weight of a group with BFQ is blkio.bfq.weight
 or io.bfq.weight.
+
+As for cgroups-v1 (blkio controller), the exact set of stat files
+created, and kept up-to-date by bfq, depends on whether
+CONFIG_DEBUG_BLK_CGROUP is set. If it is set, then bfq creates all
+the stat files documented in
+Documentation/cgroup-v1/blkio-controller.txt. If, instead,
+CONFIG_DEBUG_BLK_CGROUP is not set, then bfq creates only the files
+blkio.bfq.io_service_bytes
+blkio.bfq.io_service_bytes_recursive
+blkio.bfq.io_serviced
+blkio.bfq.io_serviced_recursive
+
+The value of CONFIG_DEBUG_BLK_CGROUP greatly influences the maximum
+throughput sustainable with bfq, because updating the blkio.bfq.*
+stats is rather costly, especially for some of the stats enabled by
+CONFIG_DEBUG_BLK_CGROUP.
 
 Parameters to set
 -----------------

block/bfq-cgroup.c

···
 
 #include "bfq-iosched.h"
 
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 
 /* bfqg stats flags */
 enum bfqg_stats_flags {
···
 	bfqg_stats_update_group_wait_time(stats);
 }
 
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.queued, op, 1);
+	bfqg_stats_end_empty_time(&bfqg->stats);
+	if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
+		bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
+}
+
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.queued, op, -1);
+}
+
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.merged, op, 1);
+}
+
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+				  uint64_t io_start_time, unsigned int op)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+	unsigned long long now = sched_clock();
+
+	if (time_after64(now, io_start_time))
+		blkg_rwstat_add(&stats->service_time, op,
+				now - io_start_time);
+	if (time_after64(io_start_time, start_time))
+		blkg_rwstat_add(&stats->wait_time, op,
+				io_start_time - start_time);
+}
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      unsigned int op) { }
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+				  uint64_t io_start_time, unsigned int op) { }
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
+
+#endif /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
 /*
  * blk-cgroup policy-related handlers
  * The following functions help in converting between blk-cgroup
···
 	blkg_put(bfqg_to_blkg(bfqg));
 }
 
-void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
-			      unsigned int op)
-{
-	blkg_rwstat_add(&bfqg->stats.queued, op, 1);
-	bfqg_stats_end_empty_time(&bfqg->stats);
-	if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
-		bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
-}
-
-void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
-{
-	blkg_rwstat_add(&bfqg->stats.queued, op, -1);
-}
-
-void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
-{
-	blkg_rwstat_add(&bfqg->stats.merged, op, 1);
-}
-
-void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
-				  uint64_t io_start_time, unsigned int op)
-{
-	struct bfqg_stats *stats = &bfqg->stats;
-	unsigned long long now = sched_clock();
-
-	if (time_after64(now, io_start_time))
-		blkg_rwstat_add(&stats->service_time, op,
-				now - io_start_time);
-	if (time_after64(io_start_time, start_time))
-		blkg_rwstat_add(&stats->wait_time, op,
-				io_start_time - start_time);
-}
-
 /* @stats = 0 */
 static void bfqg_stats_reset(struct bfqg_stats *stats)
 {
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* queued stats shouldn't be cleared */
 	blkg_rwstat_reset(&stats->merged);
 	blkg_rwstat_reset(&stats->service_time);
···
 	blkg_stat_reset(&stats->group_wait_time);
 	blkg_stat_reset(&stats->idle_time);
 	blkg_stat_reset(&stats->empty_time);
+#endif
 }
 
 /* @to += @from */
···
 	if (!to || !from)
 		return;
 
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* queued stats shouldn't be cleared */
 	blkg_rwstat_add_aux(&to->merged, &from->merged);
 	blkg_rwstat_add_aux(&to->service_time, &from->service_time);
···
 	blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
 	blkg_stat_add_aux(&to->idle_time, &from->idle_time);
 	blkg_stat_add_aux(&to->empty_time, &from->empty_time);
+#endif
 }
 
 /*
···
 
 static void bfqg_stats_exit(struct bfqg_stats *stats)
 {
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	blkg_rwstat_exit(&stats->merged);
 	blkg_rwstat_exit(&stats->service_time);
 	blkg_rwstat_exit(&stats->wait_time);
···
 	blkg_stat_exit(&stats->group_wait_time);
 	blkg_stat_exit(&stats->idle_time);
 	blkg_stat_exit(&stats->empty_time);
+#endif
 }
 
 static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
 {
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	if (blkg_rwstat_init(&stats->merged, gfp) ||
 	    blkg_rwstat_init(&stats->service_time, gfp) ||
 	    blkg_rwstat_init(&stats->wait_time, gfp) ||
···
 		bfqg_stats_exit(stats);
 		return -ENOMEM;
 	}
+#endif
 
 	return 0;
 }
···
 	return bfq_io_set_weight_legacy(of_css(of), NULL, weight);
 }
 
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 static int bfqg_print_stat(struct seq_file *sf, void *v)
 {
 	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
···
 			  0, false);
 	return 0;
 }
+#endif /* CONFIG_DEBUG_BLK_CGROUP */
 
 struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 {
···
 
 	/* statistics, covers only the tasks in the bfqg */
 	{
-		.name = "bfq.time",
-		.private = offsetof(struct bfq_group, stats.time),
-		.seq_show = bfqg_print_stat,
-	},
-	{
-		.name = "bfq.sectors",
-		.seq_show = bfqg_print_stat_sectors,
-	},
-	{
 		.name = "bfq.io_service_bytes",
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_bytes,
···
 		.name = "bfq.io_serviced",
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_ios,
+	},
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	{
+		.name = "bfq.time",
+		.private = offsetof(struct bfq_group, stats.time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = "bfq.sectors",
+		.seq_show = bfqg_print_stat_sectors,
 	},
 	{
 		.name = "bfq.io_service_time",
···
 		.private = offsetof(struct bfq_group, stats.queued),
 		.seq_show = bfqg_print_rwstat,
 	},
+#endif /* CONFIG_DEBUG_BLK_CGROUP */
 
 	/* the same statictics which cover the bfqg and its descendants */
-	{
-		.name = "bfq.time_recursive",
-		.private = offsetof(struct bfq_group, stats.time),
-		.seq_show = bfqg_print_stat_recursive,
-	},
-	{
-		.name = "bfq.sectors_recursive",
-		.seq_show = bfqg_print_stat_sectors_recursive,
-	},
 	{
 		.name = "bfq.io_service_bytes_recursive",
 		.private = (unsigned long)&blkcg_policy_bfq,
···
 		.name = "bfq.io_serviced_recursive",
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_ios_recursive,
+	},
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	{
+		.name = "bfq.time_recursive",
+		.private = offsetof(struct bfq_group, stats.time),
+		.seq_show = bfqg_print_stat_recursive,
+	},
+	{
+		.name = "bfq.sectors_recursive",
+		.seq_show = bfqg_print_stat_sectors_recursive,
 	},
 	{
 		.name = "bfq.io_service_time_recursive",
···
 		.private = offsetof(struct bfq_group, stats.dequeue),
 		.seq_show = bfqg_print_stat,
 	},
+#endif	/* CONFIG_DEBUG_BLK_CGROUP */
 	{ }	/* terminate */
 };
 
···
 };
 
 #else	/* CONFIG_BFQ_GROUP_IOSCHED */
-
-void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
-			      unsigned int op) { }
-void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
-void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
-void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
-				  uint64_t io_start_time, unsigned int op) { }
-void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
-void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
-void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
-void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
-void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
 
 void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		   struct bfq_group *bfqg) {}

block/bfq-iosched.c

···
 			bfqq->ttime.last_end_request +
 			bfqd->bfq_slice_idle * 3;
 
-	bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags);
 
 	/*
 	 * bfqq deserves to be weight-raised if:
···
 	if (rq->cmd_flags & REQ_META)
 		bfqq->meta_pending--;
 
-	bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
 }
 
 static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
···
 		bfqq->next_rq = rq;
 
 	bfq_remove_request(q, next);
+	bfqg_stats_update_io_remove(bfqq_group(bfqq), next->cmd_flags);
 
 	spin_unlock_irq(&bfqq->bfqd->lock);
 end:
···
 				       struct bfq_queue *bfqq)
 {
 	if (bfqq) {
-		bfqg_stats_update_avg_queue_size(bfqq_group(bfqq));
 		bfq_clear_bfqq_fifo_expire(bfqq);
 
 		bfqd->budgets_assigned = (bfqd->budgets_assigned * 7 + 256) / 8;
···
 				 */
 				bfq_clear_bfqq_wait_request(bfqq);
 				hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
-				bfqg_stats_update_idle_time(bfqq_group(bfqq));
 			}
 			goto keep_queue;
 		}
···
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 	struct request *rq;
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+	struct bfq_queue *in_serv_queue, *bfqq;
+	bool waiting_rq, idle_timer_disabled;
+#endif
 
 	spin_lock_irq(&bfqd->lock);
 
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+	in_serv_queue = bfqd->in_service_queue;
+	waiting_rq = in_serv_queue && bfq_bfqq_wait_request(in_serv_queue);
+
 	rq = __bfq_dispatch_request(hctx);
+
+	idle_timer_disabled =
+		waiting_rq && !bfq_bfqq_wait_request(in_serv_queue);
+
+#else
+	rq = __bfq_dispatch_request(hctx);
+#endif
 	spin_unlock_irq(&bfqd->lock);
+
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+	bfqq = rq ? RQ_BFQQ(rq) : NULL;
+	if (!idle_timer_disabled && !bfqq)
+		return rq;
+
+	/*
+	 * rq and bfqq are guaranteed to exist until this function
+	 * ends, for the following reasons. First, rq can be
+	 * dispatched to the device, and then can be completed and
+	 * freed, only after this function ends. Second, rq cannot be
+	 * merged (and thus freed because of a merge) any longer,
+	 * because it has already started. Thus rq cannot be freed
+	 * before this function ends, and, since rq has a reference to
+	 * bfqq, the same guarantee holds for bfqq too.
+	 *
+	 * In addition, the following queue lock guarantees that
+	 * bfqq_group(bfqq) exists as well.
+	 */
+	spin_lock_irq(hctx->queue->queue_lock);
+	if (idle_timer_disabled)
+		/*
+		 * Since the idle timer has been disabled,
+		 * in_serv_queue contained some request when
+		 * __bfq_dispatch_request was invoked above, which
+		 * implies that rq was picked exactly from
+		 * in_serv_queue. Thus in_serv_queue == bfqq, and is
+		 * therefore guaranteed to exist because of the above
+		 * arguments.
+		 */
+		bfqg_stats_update_idle_time(bfqq_group(in_serv_queue));
+	if (bfqq) {
+		struct bfq_group *bfqg = bfqq_group(bfqq);
+
+		bfqg_stats_update_avg_queue_size(bfqg);
+		bfqg_stats_set_start_empty_time(bfqg);
+		bfqg_stats_update_io_remove(bfqg, rq->cmd_flags);
+	}
+	spin_unlock_irq(hctx->queue->queue_lock);
+#endif
 
 	return rq;
 }
···
 		 */
 		bfq_clear_bfqq_wait_request(bfqq);
 		hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
-		bfqg_stats_update_idle_time(bfqq_group(bfqq));
 
 		/*
 		 * The queue is not empty, because a new request just
···
 	}
 }
 
-static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
+/* returns true if it causes the idle timer to be disabled */
+static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
 {
 	struct bfq_queue *bfqq = RQ_BFQQ(rq),
 		*new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
+	bool waiting, idle_timer_disabled = false;
 
 	if (new_bfqq) {
 		if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
···
 		bfqq = new_bfqq;
 	}
 
+	waiting = bfqq && bfq_bfqq_wait_request(bfqq);
 	bfq_add_request(rq);
+	idle_timer_disabled = waiting && !bfq_bfqq_wait_request(bfqq);
 
 	rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &bfqq->fifo);
 
 	bfq_rq_enqueued(bfqd, bfqq, rq);
+
+	return idle_timer_disabled;
 }
 
 static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
···
 {
 	struct request_queue *q = hctx->queue;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	bool idle_timer_disabled = false;
+	unsigned int cmd_flags;
+#endif
 
 	spin_lock_irq(&bfqd->lock);
 	if (blk_mq_sched_try_insert_merge(q, rq)) {
···
 		else
 			list_add_tail(&rq->queuelist, &bfqd->dispatch);
 	} else {
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+		idle_timer_disabled = __bfq_insert_request(bfqd, rq);
+		/*
+		 * Update bfqq, because, if a queue merge has occurred
+		 * in __bfq_insert_request, then rq has been
+		 * redirected into a new queue.
+		 */
+		bfqq = RQ_BFQQ(rq);
+#else
 		__bfq_insert_request(bfqd, rq);
+#endif
 
 		if (rq_mergeable(rq)) {
 			elv_rqhash_add(q, rq);
···
 		}
 	}
 
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+	/*
+	 * Cache cmd_flags before releasing scheduler lock, because rq
+	 * may disappear afterwards (for example, because of a request
+	 * merge).
+	 */
+	cmd_flags = rq->cmd_flags;
+#endif
 	spin_unlock_irq(&bfqd->lock);
+
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
+	if (!bfqq)
+		return;
+	/*
+	 * bfqq still exists, because it can disappear only after
+	 * either it is merged with another queue, or the process it
+	 * is associated with exits. But both actions must be taken by
+	 * the same process currently executing this flow of
+	 * instruction.
+	 *
+	 * In addition, the following queue lock guarantees that
+	 * bfqq_group(bfqq) exists as well.
+	 */
+	spin_lock_irq(q->queue_lock);
+	bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, cmd_flags);
+	if (idle_timer_disabled)
+		bfqg_stats_update_idle_time(bfqq_group(bfqq));
+	spin_unlock_irq(q->queue_lock);
+#endif
 }
 
 static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
···
 		 * lock is held.
 		 */
 
-		if (!RB_EMPTY_NODE(&rq->rb_node))
+		if (!RB_EMPTY_NODE(&rq->rb_node)) {
 			bfq_remove_request(rq->q, rq);
+			bfqg_stats_update_io_remove(bfqq_group(bfqq),
+						    rq->cmd_flags);
+		}
 		bfq_put_rq_priv_body(bfqq);
 	}
 

block/bfq-iosched.h

···
 };
 
 struct bfqg_stats {
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) && defined(CONFIG_DEBUG_BLK_CGROUP)
 	/* number of ios merged */
 	struct blkg_rwstat		merged;
 	/* total time spent on device in ns, may not be accurate w/ queueing */
···
 	uint64_t			start_idle_time;
 	uint64_t			start_empty_time;
 	uint16_t			flags;
-#endif	/* CONFIG_BFQ_GROUP_IOSCHED */
+#endif	/* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
 };
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED

block/bfq-wf2q.c

···
 		st->vtime += bfq_delta(served, st->wsum);
 		bfq_forget_idle(st);
 	}
-	bfqg_stats_set_start_empty_time(bfqq_group(bfqq));
 	bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs", served);
 }
 

block/bio.c

···
 	 * so we don't set nor calculate new physical/hw segment counts here
 	 */
 	bio->bi_disk = bio_src->bi_disk;
+	bio->bi_partno = bio_src->bi_partno;
 	bio_set_flag(bio, BIO_CLONED);
 	bio->bi_opf = bio_src->bi_opf;
 	bio->bi_write_hint = bio_src->bi_write_hint;

block/blk-core.c

···
 		spin_lock_irq(q->queue_lock);
 		blk_queue_for_each_rl(rl, q) {
 			if (rl->rq_pool) {
-				wake_up(&rl->wait[BLK_RW_SYNC]);
-				wake_up(&rl->wait[BLK_RW_ASYNC]);
+				wake_up_all(&rl->wait[BLK_RW_SYNC]);
+				wake_up_all(&rl->wait[BLK_RW_ASYNC]);
 			}
 		}
 		spin_unlock_irq(q->queue_lock);

drivers/block/amiflop.c

···
 
 static struct timer_list flush_track_timer[FD_MAX_UNITS];
 static struct timer_list post_write_timer;
+static unsigned long post_write_timer_drive;
 static struct timer_list motor_on_timer;
 static struct timer_list motor_off_timer[FD_MAX_UNITS];
 static int on_attempts;
···
 
 }
 
-static void motor_on_callback(unsigned long ignored)
+static void motor_on_callback(struct timer_list *unused)
 {
 	if (!(ciaa.pra & DSKRDY) || --on_attempts == 0) {
 		complete_all(&motor_on_completion);
···
 		on_attempts = -1;
 #if 0
 		printk (KERN_ERR "motor_on failed, turning motor off\n");
-		fd_motor_off (nr);
+		fd_motor_off (motor_off_timer + nr);
 		return 0;
 #else
 		printk (KERN_WARNING "DSKRDY not set after 1.5 seconds - assuming drive is spinning notwithstanding\n");
···
 	return 1;
 }
 
-static void fd_motor_off(unsigned long drive)
+static void fd_motor_off(struct timer_list *timer)
 {
-	long calledfromint;
-#ifdef MODULE
-	long decusecount;
+	unsigned long drive = ((unsigned long)timer -
+			       (unsigned long)&motor_off_timer[0]) /
+					sizeof(motor_off_timer[0]);
 
-	decusecount = drive & 0x40000000;
-#endif
-	calledfromint = drive & 0x80000000;
 	drive&=3;
-	if (calledfromint && !try_fdc(drive)) {
+	if (!try_fdc(drive)) {
 		/* We would be blocked in an interrupt, so try again later */
-		motor_off_timer[drive].expires = jiffies + 1;
-		add_timer(motor_off_timer + drive);
+		timer->expires = jiffies + 1;
+		add_timer(timer);
 		return;
 	}
 	unit[drive].motor = 0;
···
 	int drive;
 
 	drive = nr & 3;
-	/* called this way it is always from interrupt */
-	motor_off_timer[drive].data = nr | 0x80000000;
 	mod_timer(motor_off_timer + drive, jiffies + 3*HZ);
 }
 
···
 			break;
 		if (--n == 0) {
 			printk (KERN_ERR "fd%d: calibrate failed, turning motor off\n", drive);
-			fd_motor_off (drive);
+			fd_motor_off (motor_off_timer + drive);
 			unit[drive].track = -1;
 			rel_fdc();
 			return 0;
···
 	if (block_flag == 2) { /* writing */
 		writepending = 2;
 		post_write_timer.expires = jiffies + 1; /* at least 2 ms */
-		post_write_timer.data = selected;
+		post_write_timer_drive = selected;
 		add_timer(&post_write_timer);
 	}
 	else {                /* reading */
···
 	rel_fdc(); /* corresponds to get_fdc() in raw_write */
 }
 
+static void post_write_callback(struct timer_list *timer)
+{
+	post_write(post_write_timer_drive);
+}
 
 /*
  * The following functions are to convert the block contents into raw data
···
 /* FIXME: this assumes the drive is still spinning -
  * which is only true if we complete writing a track within three seconds
  */
-static void flush_track_callback(unsigned long nr)
+static void flush_track_callback(struct timer_list *timer)
 {
+	unsigned long nr = ((unsigned long)timer -
+			       (unsigned long)&flush_track_timer[0]) /
+					sizeof(flush_track_timer[0]);
+
 	nr&=3;
 	writefromint = 1;
 	if (!try_fdc(nr)) {
···
 		fd_ref[drive] = 0;
 	}
 #ifdef MODULE
-/* the mod_use counter is handled this way */
-	floppy_off (drive | 0x40000000);
+	floppy_off (drive);
 #endif
 	mutex_unlock(&amiflop_mutex);
 }
···
 				floppy_find, NULL, NULL);
 
 	/* initialize variables */
-	init_timer(&motor_on_timer);
+	timer_setup(&motor_on_timer, motor_on_callback, 0);
 	motor_on_timer.expires = 0;
-	motor_on_timer.data = 0;
-	motor_on_timer.function = motor_on_callback;
 	for (i = 0; i < FD_MAX_UNITS; i++) {
-		init_timer(&motor_off_timer[i]);
+		timer_setup(&motor_off_timer[i], fd_motor_off, 0);
 		motor_off_timer[i].expires = 0;
-		motor_off_timer[i].data = i|0x80000000;
-		motor_off_timer[i].function = fd_motor_off;
-		init_timer(&flush_track_timer[i]);
+		timer_setup(&flush_track_timer[i], flush_track_callback, 0);
 		flush_track_timer[i].expires = 0;
-		flush_track_timer[i].data = i;
-		flush_track_timer[i].function = flush_track_callback;
 
 		unit[i].track = -1;
 	}
 
-	init_timer(&post_write_timer);
+	timer_setup(&post_write_timer, post_write_callback, 0);
 	post_write_timer.expires = 0;
-	post_write_timer.data = 0;
-	post_write_timer.function = post_write;
   
 	for (i = 0; i < 128; i++)
 		mfmdecode[i]=255;

drivers/block/aoe/aoecmd.c

···
 }
 
 static void
-rexmit_timer(ulong vp)
+rexmit_timer(struct timer_list *timer)
 {
 	struct aoedev *d;
 	struct aoetgt *t;
···
 	int utgts;	/* number of aoetgt descriptors (not slots) */
 	int since;
 
-	d = (struct aoedev *) vp;
+	d = from_timer(d, timer, timer);
 
 	spin_lock_irqsave(&d->lock, flags);
 
···
 
 	d->rttavg = RTTAVG_INIT;
 	d->rttdev = RTTDEV_INIT;
-	d->timer.function = rexmit_timer;
+	d->timer.function = (TIMER_FUNC_TYPE)rexmit_timer;
 
 	skb = skb_clone(skb, GFP_ATOMIC);
 	if (skb) {

drivers/block/aoe/aoedev.c

···
 #include <linux/string.h>
 #include "aoe.h"
 
-static void dummy_timer(ulong);
 static void freetgt(struct aoedev *d, struct aoetgt *t);
 static void skbpoolfree(struct aoedev *d);
 
···
 }
 
 static void
-dummy_timer(ulong vp)
+dummy_timer(struct timer_list *t)
 {
 	struct aoedev *d;
 
-	d = (struct aoedev *)vp;
+	d = from_timer(d, t, timer);
 	if (d->flags & DEVFL_TKILL)
 		return;
 	d->timer.expires = jiffies + HZ;
···
 	INIT_WORK(&d->work, aoecmd_sleepwork);
 	spin_lock_init(&d->lock);
 	skb_queue_head_init(&d->skbpool);
-	init_timer(&d->timer);
-	d->timer.data = (ulong) d;
-	d->timer.function = dummy_timer;
+	timer_setup(&d->timer, dummy_timer, 0);
 	d->timer.expires = jiffies + HZ;
 	add_timer(&d->timer);
 	d->bufpool = NULL;	/* defer to aoeblk_gdalloc */

drivers/block/floppy.c

···
 }
 
 /* switches the motor off after a given timeout */
-static void motor_off_callback(unsigned long nr)
+static void motor_off_callback(struct timer_list *t)
 {
+	unsigned long nr = t - motor_off_timer;
 	unsigned char mask = ~(0x10 << UNIT(nr));
+
+	if (WARN_ON_ONCE(nr >= N_DRIVE))
+		return;
 
 	set_dor(FDC(nr), mask, 0);
 }
···
 		else
 			raw_cmd->flags &= ~FD_RAW_DISK_CHANGE;
 		if (raw_cmd->flags & FD_RAW_NO_MOTOR_AFTER)
-			motor_off_callback(current_drive);
+			motor_off_callback(&motor_off_timer[current_drive]);
 
 		if (raw_cmd->next &&
 		    (!(raw_cmd->flags & FD_RAW_FAILURE) ||
···
 		disks[drive]->fops = &floppy_fops;
 		sprintf(disks[drive]->disk_name, "fd%d", drive);
 
-		setup_timer(&motor_off_timer[drive], motor_off_callback, drive);
+		timer_setup(&motor_off_timer[drive], motor_off_callback, 0);
 	}
 
 	err = register_blkdev(FLOPPY_MAJOR, "fd");

drivers/block/swim3.c

···
 static void seek_track(struct floppy_state *fs, int n);
 static void init_dma(struct dbdma_cmd *cp, int cmd, void *buf, int count);
 static void act(struct floppy_state *fs);
-static void scan_timeout(unsigned long data);
-static void seek_timeout(unsigned long data);
-static void settle_timeout(unsigned long data);
-static void xfer_timeout(unsigned long data);
+static void scan_timeout(struct timer_list *t);
+static void seek_timeout(struct timer_list *t);
+static void settle_timeout(struct timer_list *t);
+static void xfer_timeout(struct timer_list *t);
 static irqreturn_t swim3_interrupt(int irq, void *dev_id);
 /*static void fd_dma_interrupt(int irq, void *dev_id);*/
 static int grab_drive(struct floppy_state *fs, enum swim_state state,
···
 }
 
 static void set_timeout(struct floppy_state *fs, int nticks,
-			void (*proc)(unsigned long))
+			void (*proc)(struct timer_list *t))
 {
 	if (fs->timeout_pending)
 		del_timer(&fs->timeout);
 	fs->timeout.expires = jiffies + nticks;
-	fs->timeout.function = proc;
-	fs->timeout.data = (unsigned long) fs;
+	fs->timeout.function = (TIMER_FUNC_TYPE)proc;
 	add_timer(&fs->timeout);
 	fs->timeout_pending = 1;
 }
···
 	}
 }
 
-static void scan_timeout(unsigned long data)
+static void scan_timeout(struct timer_list *t)
 {
-	struct floppy_state *fs = (struct floppy_state *) data;
+	struct floppy_state *fs = from_timer(fs, t, timeout);
 	struct swim3 __iomem *sw = fs->swim3;
 	unsigned long flags;
 
···
 	spin_unlock_irqrestore(&swim3_lock, flags);
 }
 
-static void seek_timeout(unsigned long data)
+static void seek_timeout(struct timer_list *t)
 {
-	struct floppy_state *fs = (struct floppy_state *) data;
+	struct floppy_state *fs = from_timer(fs, t, timeout);
 	struct swim3 __iomem *sw = fs->swim3;
 	unsigned long flags;
 
···
 	spin_unlock_irqrestore(&swim3_lock, flags);
 }
 
-static void settle_timeout(unsigned long data)
+static void settle_timeout(struct timer_list *t)
 {
-	struct floppy_state *fs = (struct floppy_state *) data;
+	struct floppy_state *fs = from_timer(fs, t, timeout);
 	struct swim3 __iomem *sw = fs->swim3;
 	unsigned long flags;
 
···
 	spin_unlock_irqrestore(&swim3_lock, flags);
 }
 
-static void xfer_timeout(unsigned long data)
+static void xfer_timeout(struct timer_list *t)
 {
-	struct floppy_state *fs = (struct floppy_state *) data;
+	struct floppy_state *fs = from_timer(fs, t, timeout);
 	struct swim3 __iomem *sw = fs->swim3;
 	struct dbdma_regs __iomem *dr = fs->dma;
 	unsigned long flags;
···
 		return -EBUSY;
 	}
 
-	init_timer(&fs->timeout);
+	timer_setup(&fs->timeout, NULL, 0);
 
 	swim3_info("SWIM3 floppy controller %s\n",
 		mdev->media_bay ? "in media bay" : "");

drivers/ide/ide-cd.c

···
 	unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9);
 	struct scsi_request *req = scsi_req(rq);
 
-	scsi_req_init(req);
-	memset(req->cmd, 0, BLK_MAX_CDB);
+	q->initialize_rq_fn(rq);
 
 	if (rq_data_dir(rq) == READ)
 		req->cmd[0] = GPCMD_READ_10;

drivers/md/bcache/stats.c

···
 	}
 }
 
-static void scale_accounting(unsigned long data)
+static void scale_accounting(struct timer_list *t)
 {
-	struct cache_accounting *acc = (struct cache_accounting *) data;
+	struct cache_accounting *acc = from_timer(acc, t, timer);
 
 #define move_stat(name) do {						\
 	unsigned t = atomic_xchg(&acc->collector.name, 0);		\
···
 	kobject_init(&acc->day.kobj,		&bch_stats_ktype);
 
 	closure_init(&acc->cl, parent);
-	init_timer(&acc->timer);
+	timer_setup(&acc->timer, scale_accounting, 0);
 	acc->timer.expires	= jiffies + accounting_delay;
-	acc->timer.data		= (unsigned long) acc;
-	acc->timer.function	= scale_accounting;
 	add_timer(&acc->timer);
 }

drivers/md/dm-delay.c

···
 
 static DEFINE_MUTEX(delayed_bios_lock);
 
-static void handle_delayed_timer(unsigned long data)
+static void handle_delayed_timer(struct timer_list *t)
 {
-	struct delay_c *dc = (struct delay_c *)data;
+	struct delay_c *dc = from_timer(dc, t, delay_timer);
 
 	queue_work(dc->kdelayd_wq, &dc->flush_expired_bios);
 }
···
 		goto bad_queue;
 	}
 
-	setup_timer(&dc->delay_timer, handle_delayed_timer, (unsigned long)dc);
+	timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
 
 	INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
 	INIT_LIST_HEAD(&dc->delayed_bios);

drivers/md/dm-integrity.c

···
 	__remove_wait_queue(&ic->endio_wait, &wait);
 }
 
-static void autocommit_fn(unsigned long data)
+static void autocommit_fn(struct timer_list *t)
 {
-	struct dm_integrity_c *ic = (struct dm_integrity_c *)data;
+	struct dm_integrity_c *ic = from_timer(ic, t, autocommit_timer);
 
 	if (likely(!dm_integrity_failed(ic)))
 		queue_work(ic->commit_wq, &ic->commit_work);
···
 
 	ic->autocommit_jiffies = msecs_to_jiffies(sync_msec);
 	ic->autocommit_msec = sync_msec;
-	setup_timer(&ic->autocommit_timer, autocommit_fn, (unsigned long)ic);
+	timer_setup(&ic->autocommit_timer, autocommit_fn, 0);
 
 	ic->io = dm_io_client_create();
 	if (IS_ERR(ic->io)) {

drivers/md/dm-raid1.c

···
 	queue_work(ms->kmirrord_wq, &ms->kmirrord_work);
 }
 
-static void delayed_wake_fn(unsigned long data)
+static void delayed_wake_fn(struct timer_list *t)
 {
-	struct mirror_set *ms = (struct mirror_set *) data;
+	struct mirror_set *ms = from_timer(ms, t, timer);
 
 	clear_bit(0, &ms->timer_pending);
 	wakeup_mirrord(ms);
···
 		return;
 
 	ms->timer.expires = jiffies + HZ / 5;
-	ms->timer.data = (unsigned long) ms;
-	ms->timer.function = delayed_wake_fn;
 	add_timer(&ms->timer);
 }
 
···
 		goto err_free_context;
 	}
 	INIT_WORK(&ms->kmirrord_work, do_mirror);
-	init_timer(&ms->timer);
+	timer_setup(&ms->timer, delayed_wake_fn, 0);
 	ms->timer_pending = 0;
 	INIT_WORK(&ms->trigger_event, trigger_event);
 

drivers/md/md.c

···
 		bioset_free(sync_bs);
 }
 
-static void md_safemode_timeout(unsigned long data);
+static void md_safemode_timeout(struct timer_list *t);
 
 void mddev_init(struct mddev *mddev)
 {
···
 	mutex_init(&mddev->bitmap_info.mutex);
 	INIT_LIST_HEAD(&mddev->disks);
 	INIT_LIST_HEAD(&mddev->all_mddevs);
-	setup_timer(&mddev->safemode_timer, md_safemode_timeout,
-		    (unsigned long) mddev);
+	timer_setup(&mddev->safemode_timer, md_safemode_timeout, 0);
 	atomic_set(&mddev->active, 1);
 	atomic_set(&mddev->openers, 0);
 	atomic_set(&mddev->active_io, 0);
···
 	return -EINVAL;
 }
 
-static void md_safemode_timeout(unsigned long data)
+static void md_safemode_timeout(struct timer_list *t)
 {
-	struct mddev *mddev = (struct mddev *) data;
+	struct mddev *mddev = from_timer(mddev, t, safemode_timer);
 
 	mddev->safemode = 1;
 	if (mddev->external)

drivers/nvme/target/fc.c

···
 			struct nvmet_fc_fcp_iod *fod)
 {
 	struct nvme_fc_cmd_iu *cmdiu = &fod->cmdiubuf;
+	u32 xfrlen = be32_to_cpu(cmdiu->data_len);
 	int ret;
 
 	/*
···
 
 	fod->fcpreq->done = nvmet_fc_xmt_fcp_op_done;
 
-	fod->req.transfer_len = be32_to_cpu(cmdiu->data_len);
 	if (cmdiu->flags & FCNVME_CMD_FLAGS_WRITE) {
 		fod->io_dir = NVMET_FCP_WRITE;
 		if (!nvme_is_write(&cmdiu->sqe))
···
 			goto transport_error;
 	} else {
 		fod->io_dir = NVMET_FCP_NODATA;
-		if (fod->req.transfer_len)
+		if (xfrlen)
 			goto transport_error;
 	}
 
···
 		/* nvmet layer has already called op done to send rsp. */
 		return;
 	}
+
+	fod->req.transfer_len = xfrlen;
 
 	/* keep a running counter of tail position */
 	atomic_inc(&fod->queue->sqtail);