nvme: add support for streams and directives

This adds support for Directives in NVMe, particular for the Streams
directive. Support for Directives is a new feature in NVMe 1.3. It
allows a user to pass in information about where to store the data, so
that it the device can do so most effiently. If an application is
managing and writing data with different life times, mixing differently
retentioned data onto the same locations on flash can cause write
amplification to grow. This, in turn, will reduce performance and life
time of the device.

Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 151 insertions, 4 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index aee37b73231d..5c50f53e32f3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -65,6 +65,10 @@ static bool force_apst;
 module_param(force_apst, bool, 0644);
 MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off");
 
+static bool streams;
+module_param(streams, bool, 0644);
+MODULE_PARM_DESC(streams, "turn on support for Streams write directives");
+
 struct workqueue_struct *nvme_wq;
 EXPORT_SYMBOL_GPL(nvme_wq);
 
@@ -297,6 +301,105 @@ struct request *nvme_alloc_request(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(nvme_alloc_request);
 
+static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
+{
+	struct nvme_command c;
+
+	memset(&c, 0, sizeof(c));
+
+	c.directive.opcode = nvme_admin_directive_send;
+	c.directive.nsid = cpu_to_le32(0xffffffff);
+	c.directive.doper = NVME_DIR_SND_ID_OP_ENABLE;
+	c.directive.dtype = NVME_DIR_IDENTIFY;
+	c.directive.tdtype = NVME_DIR_STREAMS;
+	c.directive.endir = enable ? NVME_DIR_ENDIR : 0;
+
+	return nvme_submit_sync_cmd(ctrl->admin_q, &c, NULL, 0);
+}
+
+static int nvme_disable_streams(struct nvme_ctrl *ctrl)
+{
+	return nvme_toggle_streams(ctrl, false);
+}
+
+static int nvme_enable_streams(struct nvme_ctrl *ctrl)
+{
+	return nvme_toggle_streams(ctrl, true);
+}
+
+static int nvme_get_stream_params(struct nvme_ctrl *ctrl,
+				  struct streams_directive_params *s, u32 nsid)
+{
+	struct nvme_command c;
+
+	memset(&c, 0, sizeof(c));
+	memset(s, 0, sizeof(*s));
+
+	c.directive.opcode = nvme_admin_directive_recv;
+	c.directive.nsid = cpu_to_le32(nsid);
+	c.directive.numd = sizeof(*s);
+	c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM;
+	c.directive.dtype = NVME_DIR_STREAMS;
+
+	return nvme_submit_sync_cmd(ctrl->admin_q, &c, s, sizeof(*s));
+}
+
+static int nvme_configure_directives(struct nvme_ctrl *ctrl)
+{
+	struct streams_directive_params s;
+	int ret;
+
+	if (!(ctrl->oacs & NVME_CTRL_OACS_DIRECTIVES))
+		return 0;
+	if (!streams)
+		return 0;
+
+	ret = nvme_enable_streams(ctrl);
+	if (ret)
+		return ret;
+
+	ret = nvme_get_stream_params(ctrl, &s, 0xffffffff);
+	if (ret)
+		return ret;
+
+	ctrl->nssa = le16_to_cpu(s.nssa);
+	if (ctrl->nssa < BLK_MAX_WRITE_HINTS - 1) {
+		dev_info(ctrl->device, "too few streams (%u) available\n",
+					ctrl->nssa);
+		nvme_disable_streams(ctrl);
+		return 0;
+	}
+
+	ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
+	dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams);
+	return 0;
+}
+
+/*
+ * Check if 'req' has a write hint associated with it. If it does, assign
+ * a valid namespace stream to the write.
+ */
+static void nvme_assign_write_stream(struct nvme_ctrl *ctrl,
+				     struct request *req, u16 *control,
+				     u32 *dsmgmt)
+{
+	enum rw_hint streamid = req->write_hint;
+
+	if (streamid == WRITE_LIFE_NOT_SET || streamid == WRITE_LIFE_NONE)
+		streamid = 0;
+	else {
+		streamid--;
+		if (WARN_ON_ONCE(streamid > ctrl->nr_streams))
+			return;
+
+		*control |= NVME_RW_DTYPE_STREAMS;
+		*dsmgmt |= streamid << 16;
+	}
+
+	if (streamid < ARRAY_SIZE(req->q->write_hints))
+		req->q->write_hints[streamid] += blk_rq_bytes(req) >> 9;
+}
+
 static inline void nvme_setup_flush(struct nvme_ns *ns,
 		struct nvme_command *cmnd)
 {
@@ -348,6 +451,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		struct request *req, struct nvme_command *cmnd)
 {
+	struct nvme_ctrl *ctrl = ns->ctrl;
 	u16 control = 0;
 	u32 dsmgmt = 0;
 
@@ -375,6 +479,9 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
 	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
 
+	if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams)
+		nvme_assign_write_stream(ctrl, req, &control, &dsmgmt);
+
 	if (ns->ms) {
 		switch (ns->pi_type) {
 		case NVME_NS_DPS_PI_TYPE3:
@@ -1094,8 +1201,15 @@ static void nvme_config_discard(struct nvme_ns *ns)
 	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
 			NVME_DSM_MAX_RANGES);
 
-	ns->queue->limits.discard_alignment = logical_block_size;
-	ns->queue->limits.discard_granularity = logical_block_size;
+	if (ctrl->nr_streams && ns->sws && ns->sgs) {
+		unsigned int sz = logical_block_size * ns->sws * ns->sgs;
+
+		ns->queue->limits.discard_alignment = sz;
+		ns->queue->limits.discard_granularity = sz;
+	} else {
+		ns->queue->limits.discard_alignment = logical_block_size;
+		ns->queue->limits.discard_granularity = logical_block_size;
+	}
 	blk_queue_max_discard_sectors(ns->queue, UINT_MAX);
 	blk_queue_max_discard_segments(ns->queue, NVME_DSM_MAX_RANGES);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
@@ -1135,6 +1249,7 @@ static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
 static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 {
 	struct nvme_ns *ns = disk->private_data;
+	struct nvme_ctrl *ctrl = ns->ctrl;
 	u16 bs;
 
 	/*
@@ -1149,7 +1264,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 
 	blk_mq_freeze_queue(disk->queue);
 
-	if (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
+	if (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
 		nvme_prep_integrity(disk, id, bs);
 	blk_queue_logical_block_size(ns->queue, bs);
 	if (ns->noiob)
@@ -1161,7 +1276,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	else
 		set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
 
-	if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
+	if (ctrl->oncs & NVME_CTRL_ONCS_DSM)
 		nvme_config_discard(ns);
 	blk_mq_unfreeze_queue(disk->queue);
 }
@@ -1766,6 +1881,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		dev_pm_qos_hide_latency_tolerance(ctrl->device);
 
 	nvme_configure_apst(ctrl);
+	nvme_configure_directives(ctrl);
 
 	ctrl->identified = true;
 
@@ -2158,6 +2274,32 @@ static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 	return ret;
 }
 
+static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns)
+{
+	struct streams_directive_params s;
+	int ret;
+
+	if (!ctrl->nr_streams)
+		return 0;
+
+	ret = nvme_get_stream_params(ctrl, &s, ns->ns_id);
+	if (ret)
+		return ret;
+
+	ns->sws = le32_to_cpu(s.sws);
+	ns->sgs = le16_to_cpu(s.sgs);
+
+	if (ns->sws) {
+		unsigned int bs = 1 << ns->lba_shift;
+
+		blk_queue_io_min(ns->queue, bs * ns->sws);
+		if (ns->sgs)
+			blk_queue_io_opt(ns->queue, bs * ns->sws * ns->sgs);
+	}
+
+	return 0;
+}
+
 static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 {
 	struct nvme_ns *ns;
@@ -2187,6 +2329,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
 	nvme_set_queue_limits(ctrl, ns->queue);
+	nvme_setup_streams_ns(ctrl, ns);
 
 	sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->instance);
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ec8c7363934d..f616835afc4c 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -147,6 +147,8 @@ struct nvme_ctrl {
 	u16 oncs;
 	u16 vid;
 	u16 oacs;
+	u16 nssa;
+	u16 nr_streams;
 	atomic_t abort_limit;
 	u8 event_limit;
 	u8 vwc;
@@ -199,6 +201,8 @@ struct nvme_ns {
 	unsigned ns_id;
 	int lba_shift;
 	u16 ms;
+	u16 sgs;
+	u32 sws;
 	bool ext;
 	u8 pi_type;
 	unsigned long flags;