Merge tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block/storage for 4.21.

  Larger than usual, it was a busy round with lots of goodies queued up.
  Most notable is the removal of the old IO stack, which has been a long
  time coming. No new features for a while, everything coming in this
  week has all been fixes for things that were previously merged.

  This contains:

   - Use atomic counters instead of semaphores for mtip32xx (Arnd)

   - Cleanup of the mtip32xx request setup (Christoph)

   - Fix for circular locking dependency in loop (Jan, Tetsuo)

   - bcache (Coly, Guoju, Shenghui)
      * Optimizations for writeback caching
      * Various fixes and improvements

   - nvme (Chaitanya, Christoph, Sagi, Jay, me, Keith)
      * host and target support for NVMe over TCP
      * Error log page support
      * Support for separate read/write/poll queues
      * Much improved polling
      * discard OOM fallback
      * Tracepoint improvements

   - lightnvm (Hans, Hua, Igor, Matias, Javier)
      * Igor added packed metadata to pblk. Now drives without metadata
        per LBA can be used as well.
      * Fix from Geert on uninitialized value on chunk metadata reads.
      * Fixes from Hans and Javier to pblk recovery and write path.
      * Fix from Hua Su to fix a race condition in the pblk recovery
        code.
      * Scan optimization added to pblk recovery from Zhoujie.
      * Small geometry cleanup from me.

   - Conversion of the last few drivers that used the legacy path to
     blk-mq (me)

   - Removal of legacy IO path in SCSI (me, Christoph)

   - Removal of legacy IO stack and schedulers (me)

   - Support for much better polling, now without interrupts at all.
     blk-mq adds support for multiple queue maps, which enables us to
     have a map per type. This in turn enables nvme to have separate
     completion queues for polling, which can then be interrupt-less.
     Also means we're ready for async polled IO, which is hopefully
     coming in the next release.

   - Killing of (now) unused block exports (Christoph)

   - Unification of the blk-rq-qos and blk-wbt wait handling (Josef)

   - Support for zoned testing with null_blk (Masato)

   - sx8 conversion to per-host tag sets (Christoph)

   - IO priority improvements (Damien)

   - mq-deadline zoned fix (Damien)

   - Ref count blkcg series (Dennis)

   - Lots of blk-mq improvements and speedups (me)

   - sbitmap scalability improvements (me)

   - Make core inflight IO accounting per-cpu (Mikulas)

   - Export timeout setting in sysfs (Weiping)

   - Cleanup the direct issue path (Jianchao)

   - Export blk-wbt internals in block debugfs for easier debugging
     (Ming)

   - Lots of other fixes and improvements"

* tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block: (364 commits)
  kyber: use sbitmap add_wait_queue/list_del wait helpers
  sbitmap: add helpers for add/del wait queue handling
  block: save irq state in blkg_lookup_create()
  dm: don't reuse bio for flushes
  nvme-pci: trace SQ status on completions
  nvme-rdma: implement polling queue map
  nvme-fabrics: allow user to pass in nr_poll_queues
  nvme-fabrics: allow nvmf_connect_io_queue to poll
  nvme-core: optionally poll sync commands
  block: make request_to_qc_t public
  nvme-tcp: fix spelling mistake "attepmpt" -> "attempt"
  nvme-tcp: fix endianess annotations
  nvmet-tcp: fix endianess annotations
  nvme-pci: refactor nvme_poll_irqdisable to make sparse happy
  nvme-pci: only set nr_maps to 2 if poll queues are supported
  nvmet: use a macro for default error location
  nvmet: fix comparison of a u16 with -1
  blk-mq: enable IO poll if .nr_queues of type poll > 0
  blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()
  blk-mq: skip zero-queue maps in blk_mq_map_swqueue
  ...

1 files changed, 108 insertions, 68 deletions

diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 8ac93fcbaa2e..f0c56649775f 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -489,31 +489,21 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 }
 
 struct wbt_wait_data {
-	struct wait_queue_entry wq;
-	struct task_struct *task;
 	struct rq_wb *rwb;
-	struct rq_wait *rqw;
+	enum wbt_flags wb_acct;
 	unsigned long rw;
-	bool got_token;
 };
 
-static int wbt_wake_function(struct wait_queue_entry *curr, unsigned int mode,
-			     int wake_flags, void *key)
+static bool wbt_inflight_cb(struct rq_wait *rqw, void *private_data)
 {
-	struct wbt_wait_data *data = container_of(curr, struct wbt_wait_data,
-							wq);
-
-	/*
-	 * If we fail to get a budget, return -1 to interrupt the wake up
-	 * loop in __wake_up_common.
-	 */
-	if (!rq_wait_inc_below(data->rqw, get_limit(data->rwb, data->rw)))
-		return -1;
+	struct wbt_wait_data *data = private_data;
+	return rq_wait_inc_below(rqw, get_limit(data->rwb, data->rw));
+}
 
-	data->got_token = true;
-	list_del_init(&curr->entry);
-	wake_up_process(data->task);
-	return 1;
+static void wbt_cleanup_cb(struct rq_wait *rqw, void *private_data)
+{
+	struct wbt_wait_data *data = private_data;
+	wbt_rqw_done(data->rwb, rqw, data->wb_acct);
 }
 
 /*
@@ -521,57 +511,16 @@ static int wbt_wake_function(struct wait_queue_entry *curr, unsigned int mode,
  * the timer to kick off queuing again.
  */
 static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
-		       unsigned long rw, spinlock_t *lock)
-	__releases(lock)
-	__acquires(lock)
+		       unsigned long rw)
 {
 	struct rq_wait *rqw = get_rq_wait(rwb, wb_acct);
 	struct wbt_wait_data data = {
-		.wq = {
-			.func	= wbt_wake_function,
-			.entry	= LIST_HEAD_INIT(data.wq.entry),
-		},
-		.task = current,
 		.rwb = rwb,
-		.rqw = rqw,
+		.wb_acct = wb_acct,
 		.rw = rw,
 	};
-	bool has_sleeper;
-
-	has_sleeper = wq_has_sleeper(&rqw->wait);
-	if (!has_sleeper && rq_wait_inc_below(rqw, get_limit(rwb, rw)))
-		return;
 
-	prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE);
-	do {
-		if (data.got_token)
-			break;
-
-		if (!has_sleeper &&
-		    rq_wait_inc_below(rqw, get_limit(rwb, rw))) {
-			finish_wait(&rqw->wait, &data.wq);
-
-			/*
-			 * We raced with wbt_wake_function() getting a token,
-			 * which means we now have two. Put our local token
-			 * and wake anyone else potentially waiting for one.
-			 */
-			if (data.got_token)
-				wbt_rqw_done(rwb, rqw, wb_acct);
-			break;
-		}
-
-		if (lock) {
-			spin_unlock_irq(lock);
-			io_schedule();
-			spin_lock_irq(lock);
-		} else
-			io_schedule();
-
-		has_sleeper = false;
-	} while (1);
-
-	finish_wait(&rqw->wait, &data.wq);
+	rq_qos_wait(rqw, &data, wbt_inflight_cb, wbt_cleanup_cb);
 }
 
 static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
@@ -624,7 +573,7 @@ static void wbt_cleanup(struct rq_qos *rqos, struct bio *bio)
  * in an irq held spinlock, if it holds one when calling this function.
  * If we do sleep, we'll release and re-grab it.
  */
-static void wbt_wait(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock)
+static void wbt_wait(struct rq_qos *rqos, struct bio *bio)
 {
 	struct rq_wb *rwb = RQWB(rqos);
 	enum wbt_flags flags;
@@ -636,7 +585,7 @@ static void wbt_wait(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock)
 		return;
 	}
 
-	__wbt_wait(rwb, flags, bio->bi_opf, lock);
+	__wbt_wait(rwb, flags, bio->bi_opf);
 
 	if (!blk_stat_is_active(rwb->cb))
 		rwb_arm_timer(rwb);
@@ -709,8 +658,7 @@ void wbt_enable_default(struct request_queue *q)
 	if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
 		return;
 
-	if ((q->mq_ops && IS_ENABLED(CONFIG_BLK_WBT_MQ)) ||
-	    (q->request_fn && IS_ENABLED(CONFIG_BLK_WBT_SQ)))
+	if (queue_is_mq(q) && IS_ENABLED(CONFIG_BLK_WBT_MQ))
 		wbt_init(q);
 }
 EXPORT_SYMBOL_GPL(wbt_enable_default);
@@ -760,11 +708,100 @@ void wbt_disable_default(struct request_queue *q)
 	if (!rqos)
 		return;
 	rwb = RQWB(rqos);
-	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
+	if (rwb->enable_state == WBT_STATE_ON_DEFAULT) {
+		blk_stat_deactivate(rwb->cb);
 		rwb->wb_normal = 0;
+	}
 }
 EXPORT_SYMBOL_GPL(wbt_disable_default);
 
+#ifdef CONFIG_BLK_DEBUG_FS
+static int wbt_curr_win_nsec_show(void *data, struct seq_file *m)
+{
+	struct rq_qos *rqos = data;
+	struct rq_wb *rwb = RQWB(rqos);
+
+	seq_printf(m, "%llu\n", rwb->cur_win_nsec);
+	return 0;
+}
+
+static int wbt_enabled_show(void *data, struct seq_file *m)
+{
+	struct rq_qos *rqos = data;
+	struct rq_wb *rwb = RQWB(rqos);
+
+	seq_printf(m, "%d\n", rwb->enable_state);
+	return 0;
+}
+
+static int wbt_id_show(void *data, struct seq_file *m)
+{
+	struct rq_qos *rqos = data;
+
+	seq_printf(m, "%u\n", rqos->id);
+	return 0;
+}
+
+static int wbt_inflight_show(void *data, struct seq_file *m)
+{
+	struct rq_qos *rqos = data;
+	struct rq_wb *rwb = RQWB(rqos);
+	int i;
+
+	for (i = 0; i < WBT_NUM_RWQ; i++)
+		seq_printf(m, "%d: inflight %d\n", i,
+			   atomic_read(&rwb->rq_wait[i].inflight));
+	return 0;
+}
+
+static int wbt_min_lat_nsec_show(void *data, struct seq_file *m)
+{
+	struct rq_qos *rqos = data;
+	struct rq_wb *rwb = RQWB(rqos);
+
+	seq_printf(m, "%lu\n", rwb->min_lat_nsec);
+	return 0;
+}
+
+static int wbt_unknown_cnt_show(void *data, struct seq_file *m)
+{
+	struct rq_qos *rqos = data;
+	struct rq_wb *rwb = RQWB(rqos);
+
+	seq_printf(m, "%u\n", rwb->unknown_cnt);
+	return 0;
+}
+
+static int wbt_normal_show(void *data, struct seq_file *m)
+{
+	struct rq_qos *rqos = data;
+	struct rq_wb *rwb = RQWB(rqos);
+
+	seq_printf(m, "%u\n", rwb->wb_normal);
+	return 0;
+}
+
+static int wbt_background_show(void *data, struct seq_file *m)
+{
+	struct rq_qos *rqos = data;
+	struct rq_wb *rwb = RQWB(rqos);
+
+	seq_printf(m, "%u\n", rwb->wb_background);
+	return 0;
+}
+
+static const struct blk_mq_debugfs_attr wbt_debugfs_attrs[] = {
+	{"curr_win_nsec", 0400, wbt_curr_win_nsec_show},
+	{"enabled", 0400, wbt_enabled_show},
+	{"id", 0400, wbt_id_show},
+	{"inflight", 0400, wbt_inflight_show},
+	{"min_lat_nsec", 0400, wbt_min_lat_nsec_show},
+	{"unknown_cnt", 0400, wbt_unknown_cnt_show},
+	{"wb_normal", 0400, wbt_normal_show},
+	{"wb_background", 0400, wbt_background_show},
+	{},
+};
+#endif
 
 static struct rq_qos_ops wbt_rqos_ops = {
 	.throttle = wbt_wait,
@@ -774,6 +811,9 @@ static struct rq_qos_ops wbt_rqos_ops = {
 	.done = wbt_done,
 	.cleanup = wbt_cleanup,
 	.exit = wbt_exit,
+#ifdef CONFIG_BLK_DEBUG_FS
+	.debugfs_attrs = wbt_debugfs_attrs,
+#endif
 };
 
 int wbt_init(struct request_queue *q)