Merge branch 'for-4.13/block' of git://git.kernel.dk/linux-block

Pull core block/IO updates from Jens Axboe:
 "This is the main pull request for the block layer for 4.13. Not a huge
  round in terms of features, but there's a lot of churn related to some
  core cleanups.

  Note this depends on the UUID tree pull request, that Christoph
  already sent out.

  This pull request contains:

   - A series from Christoph, unifying the error/stats codes in the
     block layer. We now use blk_status_t everywhere, instead of using
     different schemes for different places.

   - Also from Christoph, some cleanups around request allocation and IO
     scheduler interactions in blk-mq.

   - And yet another series from Christoph, cleaning up how we handle
     and do bounce buffering in the block layer.

   - A blk-mq debugfs series from Bart, further improving on the support
     we have for exporting internal information to aid debugging IO
     hangs or stalls.

   - Also from Bart, a series that cleans up the request initialization
     differences across types of devices.

   - A series from Goldwyn Rodrigues, allowing the block layer to return
     failure if we will block and the user asked for non-blocking.

   - Patch from Hannes for supporting setting loop devices block size to
     that of the underlying device.

   - Two series of patches from Javier, fixing various issues with
     lightnvm, particular around pblk.

   - A series from me, adding support for write hints. This comes with
     NVMe support as well, so applications can help guide data placement
     on flash to improve performance, latencies, and write
     amplification.

   - A series from Ming, improving and hardening blk-mq support for
     stopping/starting and quiescing hardware queues.

   - Two pull requests for NVMe updates. Nothing major on the feature
     side, but lots of cleanups and bug fixes. From the usual crew.

   - A series from Neil Brown, greatly improving the bio rescue set
     support. Most notably, this kills the bio rescue work queues, if we
     don't really need them.

   - Lots of other little bug fixes that are all over the place"

* 'for-4.13/block' of git://git.kernel.dk/linux-block: (217 commits)
  lightnvm: pblk: set line bitmap check under debug
  lightnvm: pblk: verify that cache read is still valid
  lightnvm: pblk: add initialization check
  lightnvm: pblk: remove target using async. I/Os
  lightnvm: pblk: use vmalloc for GC data buffer
  lightnvm: pblk: use right metadata buffer for recovery
  lightnvm: pblk: schedule if data is not ready
  lightnvm: pblk: remove unused return variable
  lightnvm: pblk: fix double-free on pblk init
  lightnvm: pblk: fix bad le64 assignations
  nvme: Makefile: remove dead build rule
  blk-mq: map all HWQ also in hyperthreaded system
  nvmet-rdma: register ib_client to not deadlock in device removal
  nvme_fc: fix error recovery on link down.
  nvmet_fc: fix crashes on bad opcodes
  nvme_fc: Fix crash when nvme controller connection fails.
  nvme_fc: replace ioabort msleep loop with completion
  nvme_fc: fix double calls to nvme_cleanup_cmd()
  nvme-fabrics: verify that a controller returns the correct NQN
  nvme: simplify nvme_dev_attrs_are_visible
  ...

1 files changed, 100 insertions, 1 deletions

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 803aed4d7221..9ebc2945f991 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -114,10 +114,12 @@ static ssize_t queue_state_write(void *data, const char __user *buf,
 		blk_mq_run_hw_queues(q, true);
 	} else if (strcmp(op, "start") == 0) {
 		blk_mq_start_stopped_hw_queues(q, true);
+	} else if (strcmp(op, "kick") == 0) {
+		blk_mq_kick_requeue_list(q);
 	} else {
 		pr_err("%s: unsupported operation '%s'\n", __func__, op);
 inval:
-		pr_err("%s: use either 'run' or 'start'\n", __func__);
+		pr_err("%s: use 'run', 'start' or 'kick'\n", __func__);
 		return -EINVAL;
 	}
 	return count;
@@ -133,6 +135,29 @@ static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
 	}
 }
 
+static int queue_write_hint_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	int i;
+
+	for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
+		seq_printf(m, "hint%d: %llu\n", i, q->write_hints[i]);
+
+	return 0;
+}
+
+static ssize_t queue_write_hint_store(void *data, const char __user *buf,
+				      size_t count, loff_t *ppos)
+{
+	struct request_queue *q = data;
+	int i;
+
+	for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
+		q->write_hints[i] = 0;
+
+	return count;
+}
+
 static int queue_poll_stat_show(void *data, struct seq_file *m)
 {
 	struct request_queue *q = data;
@@ -267,6 +292,14 @@ static const char *const rqf_name[] = {
 };
 #undef RQF_NAME
 
+#define RQAF_NAME(name) [REQ_ATOM_##name] = #name
+static const char *const rqaf_name[] = {
+	RQAF_NAME(COMPLETE),
+	RQAF_NAME(STARTED),
+	RQAF_NAME(POLL_SLEPT),
+};
+#undef RQAF_NAME
+
 int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 {
 	const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
@@ -283,6 +316,8 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 	seq_puts(m, ", .rq_flags=");
 	blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
 		       ARRAY_SIZE(rqf_name));
+	seq_puts(m, ", .atomic_flags=");
+	blk_flags_show(m, rq->atomic_flags, rqaf_name, ARRAY_SIZE(rqaf_name));
 	seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
 		   rq->internal_tag);
 	if (mq_ops->show_rq)
@@ -298,6 +333,37 @@ int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
 }
 EXPORT_SYMBOL_GPL(blk_mq_debugfs_rq_show);
 
+static void *queue_requeue_list_start(struct seq_file *m, loff_t *pos)
+	__acquires(&q->requeue_lock)
+{
+	struct request_queue *q = m->private;
+
+	spin_lock_irq(&q->requeue_lock);
+	return seq_list_start(&q->requeue_list, *pos);
+}
+
+static void *queue_requeue_list_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct request_queue *q = m->private;
+
+	return seq_list_next(v, &q->requeue_list, pos);
+}
+
+static void queue_requeue_list_stop(struct seq_file *m, void *v)
+	__releases(&q->requeue_lock)
+{
+	struct request_queue *q = m->private;
+
+	spin_unlock_irq(&q->requeue_lock);
+}
+
+static const struct seq_operations queue_requeue_list_seq_ops = {
+	.start	= queue_requeue_list_start,
+	.next	= queue_requeue_list_next,
+	.stop	= queue_requeue_list_stop,
+	.show	= blk_mq_debugfs_rq_show,
+};
+
 static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
 	__acquires(&hctx->lock)
 {
@@ -329,6 +395,36 @@ static const struct seq_operations hctx_dispatch_seq_ops = {
 	.show	= blk_mq_debugfs_rq_show,
 };
 
+struct show_busy_params {
+	struct seq_file		*m;
+	struct blk_mq_hw_ctx	*hctx;
+};
+
+/*
+ * Note: the state of a request may change while this function is in progress,
+ * e.g. due to a concurrent blk_mq_finish_request() call.
+ */
+static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved)
+{
+	const struct show_busy_params *params = data;
+
+	if (blk_mq_map_queue(rq->q, rq->mq_ctx->cpu) == params->hctx &&
+	    test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+		__blk_mq_debugfs_rq_show(params->m,
+					 list_entry_rq(&rq->queuelist));
+}
+
+static int hctx_busy_show(void *data, struct seq_file *m)
+{
+	struct blk_mq_hw_ctx *hctx = data;
+	struct show_busy_params params = { .m = m, .hctx = hctx };
+
+	blk_mq_tagset_busy_iter(hctx->queue->tag_set, hctx_show_busy_rq,
+				&params);
+
+	return 0;
+}
+
 static int hctx_ctx_map_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
@@ -655,7 +751,9 @@ const struct file_operations blk_mq_debugfs_fops = {
 
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
 	{"poll_stat", 0400, queue_poll_stat_show},
+	{"requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops},
 	{"state", 0600, queue_state_show, queue_state_write},
+	{"write_hints", 0600, queue_write_hint_show, queue_write_hint_store},
 	{},
 };
 
@@ -663,6 +761,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"state", 0400, hctx_state_show},
 	{"flags", 0400, hctx_flags_show},
 	{"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops},
+	{"busy", 0400, hctx_busy_show},
 	{"ctx_map", 0400, hctx_ctx_map_show},
 	{"tags", 0400, hctx_tags_show},
 	{"tags_bitmap", 0400, hctx_tags_bitmap_show},