Merge branch 'for-4.16/block' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block IO related changes for the
  4.16 kernel. Nothing major in this pull request, but a good amount of
  improvements and fixes all over the map. This contains:

   - BFQ improvements, fixes, and cleanups from Angelo, Chiara, and
     Paolo.

   - Support for SMR zones for deadline and mq-deadline from Damien and
     Christoph.

   - Set of fixes for bcache by way of Michael Lyle, including fixes
     from himself, Kent, Rui, Tang, and Coly.

   - Series from Matias for lightnvm with fixes from Hans Holmberg,
     Javier, and Matias. Mostly centered around pblk, and the removing
     rrpc 1.2 in preparation for supporting 2.0.

   - A couple of NVMe pull requests from Christoph. Nothing major in
     here, just fixes and cleanups, and support for command tracing from
     Johannes.

   - Support for blk-throttle for tracking reads and writes separately.
     From Joseph Qi. A few cleanups/fixes also for blk-throttle from
     Weiping.

   - Series from Mike Snitzer that enables dm to register its queue more
     logically, something that's alwways been problematic on dm since
     it's a stacked device.

   - Series from Ming cleaning up some of the bio accessor use, in
     preparation for supporting multipage bvecs.

   - Various fixes from Ming closing up holes around queue mapping and
     quiescing.

   - BSD partition fix from Richard Narron, fixing a problem where we
     can't mount newer (10/11) FreeBSD partitions.

   - Series from Tejun reworking blk-mq timeout handling. The previous
     scheme relied on atomic bits, but it had races where we would think
     a request had timed out if it to reused at the wrong time.

   - null_blk now supports faking timeouts, to enable us to better
     exercise and test that functionality separately. From me.

   - Kill the separate atomic poll bit in the request struct. After
     this, we don't use the atomic bits on blk-mq anymore at all. From
     me.

   - sgl_alloc/free helpers from Bart.

   - Heavily contended tag case scalability improvement from me.

   - Various little fixes and cleanups from Arnd, Bart, Corentin,
     Douglas, Eryu, Goldwyn, and myself"

* 'for-4.16/block' of git://git.kernel.dk/linux-block: (186 commits)
  block: remove smart1,2.h
  nvme: add tracepoint for nvme_complete_rq
  nvme: add tracepoint for nvme_setup_cmd
  nvme-pci: introduce RECONNECTING state to mark initializing procedure
  nvme-rdma: remove redundant boolean for inline_data
  nvme: don't free uuid pointer before printing it
  nvme-pci: Suspend queues after deleting them
  bsg: use pr_debug instead of hand crafted macros
  blk-mq-debugfs: don't allow write on attributes with seq_operations set
  nvme-pci: Fix queue double allocations
  block: Set BIO_TRACE_COMPLETION on new bio during split
  blk-throttle: use queue_is_rq_based
  block: Remove kblockd_schedule_delayed_work{,_on}()
  blk-mq: Avoid that blk_mq_delay_run_hw_queue() introduces unintended delays
  blk-mq: Rename blk_mq_request_direct_issue() into blk_mq_request_issue_directly()
  lib/scatterlist: Fix chaining support in sgl_alloc_order()
  blk-throttle: track read and write request individually
  block: add bdev_read_only() checks to common helpers
  block: fail op_is_write() requests to read-only partitions
  blk-throttle: export io_serviced_recursive, io_service_bytes_recursive
  ...

1 files changed, 90 insertions, 56 deletions

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index d19f416d6101..c5a131673733 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -216,9 +216,9 @@ struct throtl_data
 
 	unsigned int scale;
 
-	struct latency_bucket tmp_buckets[LATENCY_BUCKET_SIZE];
-	struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
-	struct latency_bucket __percpu *latency_buckets;
+	struct latency_bucket tmp_buckets[2][LATENCY_BUCKET_SIZE];
+	struct avg_latency_bucket avg_buckets[2][LATENCY_BUCKET_SIZE];
+	struct latency_bucket __percpu *latency_buckets[2];
 	unsigned long last_calculate_time;
 	unsigned long filtered_latency;
 
@@ -1511,10 +1511,20 @@ static struct cftype throtl_legacy_files[] = {
 		.seq_show = blkg_print_stat_bytes,
 	},
 	{
+		.name = "throttle.io_service_bytes_recursive",
+		.private = (unsigned long)&blkcg_policy_throtl,
+		.seq_show = blkg_print_stat_bytes_recursive,
+	},
+	{
 		.name = "throttle.io_serviced",
 		.private = (unsigned long)&blkcg_policy_throtl,
 		.seq_show = blkg_print_stat_ios,
 	},
+	{
+		.name = "throttle.io_serviced_recursive",
+		.private = (unsigned long)&blkcg_policy_throtl,
+		.seq_show = blkg_print_stat_ios_recursive,
+	},
 	{ }	/* terminate */
 };
 
@@ -2040,10 +2050,10 @@ static void blk_throtl_update_idletime(struct throtl_grp *tg)
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 static void throtl_update_latency_buckets(struct throtl_data *td)
 {
-	struct avg_latency_bucket avg_latency[LATENCY_BUCKET_SIZE];
-	int i, cpu;
-	unsigned long last_latency = 0;
-	unsigned long latency;
+	struct avg_latency_bucket avg_latency[2][LATENCY_BUCKET_SIZE];
+	int i, cpu, rw;
+	unsigned long last_latency[2] = { 0 };
+	unsigned long latency[2];
 
 	if (!blk_queue_nonrot(td->queue))
 		return;
@@ -2052,56 +2062,67 @@ static void throtl_update_latency_buckets(struct throtl_data *td)
 	td->last_calculate_time = jiffies;
 
 	memset(avg_latency, 0, sizeof(avg_latency));
-	for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
-		struct latency_bucket *tmp = &td->tmp_buckets[i];
-
-		for_each_possible_cpu(cpu) {
-			struct latency_bucket *bucket;
-
-			/* this isn't race free, but ok in practice */
-			bucket = per_cpu_ptr(td->latency_buckets, cpu);
-			tmp->total_latency += bucket[i].total_latency;
-			tmp->samples += bucket[i].samples;
-			bucket[i].total_latency = 0;
-			bucket[i].samples = 0;
-		}
+	for (rw = READ; rw <= WRITE; rw++) {
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+			struct latency_bucket *tmp = &td->tmp_buckets[rw][i];
+
+			for_each_possible_cpu(cpu) {
+				struct latency_bucket *bucket;
+
+				/* this isn't race free, but ok in practice */
+				bucket = per_cpu_ptr(td->latency_buckets[rw],
+					cpu);
+				tmp->total_latency += bucket[i].total_latency;
+				tmp->samples += bucket[i].samples;
+				bucket[i].total_latency = 0;
+				bucket[i].samples = 0;
+			}
 
-		if (tmp->samples >= 32) {
-			int samples = tmp->samples;
+			if (tmp->samples >= 32) {
+				int samples = tmp->samples;
 
-			latency = tmp->total_latency;
+				latency[rw] = tmp->total_latency;
 
-			tmp->total_latency = 0;
-			tmp->samples = 0;
-			latency /= samples;
-			if (latency == 0)
-				continue;
-			avg_latency[i].latency = latency;
+				tmp->total_latency = 0;
+				tmp->samples = 0;
+				latency[rw] /= samples;
+				if (latency[rw] == 0)
+					continue;
+				avg_latency[rw][i].latency = latency[rw];
+			}
 		}
 	}
 
-	for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
-		if (!avg_latency[i].latency) {
-			if (td->avg_buckets[i].latency < last_latency)
-				td->avg_buckets[i].latency = last_latency;
-			continue;
-		}
+	for (rw = READ; rw <= WRITE; rw++) {
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+			if (!avg_latency[rw][i].latency) {
+				if (td->avg_buckets[rw][i].latency < last_latency[rw])
+					td->avg_buckets[rw][i].latency =
+						last_latency[rw];
+				continue;
+			}
 
-		if (!td->avg_buckets[i].valid)
-			latency = avg_latency[i].latency;
-		else
-			latency = (td->avg_buckets[i].latency * 7 +
-				avg_latency[i].latency) >> 3;
+			if (!td->avg_buckets[rw][i].valid)
+				latency[rw] = avg_latency[rw][i].latency;
+			else
+				latency[rw] = (td->avg_buckets[rw][i].latency * 7 +
+					avg_latency[rw][i].latency) >> 3;
 
-		td->avg_buckets[i].latency = max(latency, last_latency);
-		td->avg_buckets[i].valid = true;
-		last_latency = td->avg_buckets[i].latency;
+			td->avg_buckets[rw][i].latency = max(latency[rw],
+				last_latency[rw]);
+			td->avg_buckets[rw][i].valid = true;
+			last_latency[rw] = td->avg_buckets[rw][i].latency;
+		}
 	}
 
 	for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
 		throtl_log(&td->service_queue,
-			"Latency bucket %d: latency=%ld, valid=%d", i,
-			td->avg_buckets[i].latency, td->avg_buckets[i].valid);
+			"Latency bucket %d: read latency=%ld, read valid=%d, "
+			"write latency=%ld, write valid=%d", i,
+			td->avg_buckets[READ][i].latency,
+			td->avg_buckets[READ][i].valid,
+			td->avg_buckets[WRITE][i].latency,
+			td->avg_buckets[WRITE][i].valid);
 }
 #else
 static inline void throtl_update_latency_buckets(struct throtl_data *td)
@@ -2242,16 +2263,17 @@ static void throtl_track_latency(struct throtl_data *td, sector_t size,
 	struct latency_bucket *latency;
 	int index;
 
-	if (!td || td->limit_index != LIMIT_LOW || op != REQ_OP_READ ||
+	if (!td || td->limit_index != LIMIT_LOW ||
+	    !(op == REQ_OP_READ || op == REQ_OP_WRITE) ||
 	    !blk_queue_nonrot(td->queue))
 		return;
 
 	index = request_bucket_index(size);
 
-	latency = get_cpu_ptr(td->latency_buckets);
+	latency = get_cpu_ptr(td->latency_buckets[op]);
 	latency[index].total_latency += time;
 	latency[index].samples++;
-	put_cpu_ptr(td->latency_buckets);
+	put_cpu_ptr(td->latency_buckets[op]);
 }
 
 void blk_throtl_stat_add(struct request *rq, u64 time_ns)
@@ -2270,6 +2292,7 @@ void blk_throtl_bio_endio(struct bio *bio)
 	unsigned long finish_time;
 	unsigned long start_time;
 	unsigned long lat;
+	int rw = bio_data_dir(bio);
 
 	tg = bio->bi_cg_private;
 	if (!tg)
@@ -2298,7 +2321,7 @@ void blk_throtl_bio_endio(struct bio *bio)
 
 		bucket = request_bucket_index(
 			blk_stat_size(&bio->bi_issue_stat));
-		threshold = tg->td->avg_buckets[bucket].latency +
+		threshold = tg->td->avg_buckets[rw][bucket].latency +
 			tg->latency_target;
 		if (lat > threshold)
 			tg->bad_bio_cnt++;
@@ -2391,9 +2414,16 @@ int blk_throtl_init(struct request_queue *q)
 	td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
 	if (!td)
 		return -ENOMEM;
-	td->latency_buckets = __alloc_percpu(sizeof(struct latency_bucket) *
+	td->latency_buckets[READ] = __alloc_percpu(sizeof(struct latency_bucket) *
 		LATENCY_BUCKET_SIZE, __alignof__(u64));
-	if (!td->latency_buckets) {
+	if (!td->latency_buckets[READ]) {
+		kfree(td);
+		return -ENOMEM;
+	}
+	td->latency_buckets[WRITE] = __alloc_percpu(sizeof(struct latency_bucket) *
+		LATENCY_BUCKET_SIZE, __alignof__(u64));
+	if (!td->latency_buckets[WRITE]) {
+		free_percpu(td->latency_buckets[READ]);
 		kfree(td);
 		return -ENOMEM;
 	}
@@ -2412,7 +2442,8 @@ int blk_throtl_init(struct request_queue *q)
 	/* activate policy */
 	ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
 	if (ret) {
-		free_percpu(td->latency_buckets);
+		free_percpu(td->latency_buckets[READ]);
+		free_percpu(td->latency_buckets[WRITE]);
 		kfree(td);
 	}
 	return ret;
@@ -2423,7 +2454,8 @@ void blk_throtl_exit(struct request_queue *q)
 	BUG_ON(!q->td);
 	throtl_shutdown_wq(q);
 	blkcg_deactivate_policy(q, &blkcg_policy_throtl);
-	free_percpu(q->td->latency_buckets);
+	free_percpu(q->td->latency_buckets[READ]);
+	free_percpu(q->td->latency_buckets[WRITE]);
 	kfree(q->td);
 }
 
@@ -2441,15 +2473,17 @@ void blk_throtl_register_queue(struct request_queue *q)
 	} else {
 		td->throtl_slice = DFL_THROTL_SLICE_HD;
 		td->filtered_latency = LATENCY_FILTERED_HD;
-		for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
-			td->avg_buckets[i].latency = DFL_HD_BASELINE_LATENCY;
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+			td->avg_buckets[READ][i].latency = DFL_HD_BASELINE_LATENCY;
+			td->avg_buckets[WRITE][i].latency = DFL_HD_BASELINE_LATENCY;
+		}
 	}
 #ifndef CONFIG_BLK_DEV_THROTTLING_LOW
 	/* if no low limit, use previous default */
 	td->throtl_slice = DFL_THROTL_SLICE_HD;
 #endif
 
-	td->track_bio_latency = !q->mq_ops && !q->request_fn;
+	td->track_bio_latency = !queue_is_rq_based(q);
 	if (!td->track_bio_latency)
 		blk_stat_enable_accounting(q);
 }