[PATCHv12 11/12] nvme: register fdp parameters with the block layer

[Keith Busch <kbusch@meta.com>]

From: Keith Busch <kbusch@kernel.org>

Register the device data placement limits if supported. This is just
registering the limits with the block layer. Nothing beyond reporting
these attributes is happening in this patch.

Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 112 +++++++++++++++++++++++++++++++++++++++
 drivers/nvme/host/nvme.h |   4 ++
 2 files changed, 116 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c2a3585a3fa59..5f802e243736a 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -38,6 +38,8 @@ struct nvme_ns_info {
 	u32 nsid;
 	__le32 anagrpid;
 	u8 pi_offset;
+	u16 endgid;
+	u64 runs;
 	bool is_shared;
 	bool is_readonly;
 	bool is_ready;
@@ -1613,6 +1615,7 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 	info->is_shared = id->nmic & NVME_NS_NMIC_SHARED;
 	info->is_readonly = id->nsattr & NVME_NS_ATTR_RO;
 	info->is_ready = true;
+	info->endgid = le16_to_cpu(id->endgid);
 	if (ctrl->quirks & NVME_QUIRK_BOGUS_NID) {
 		dev_info(ctrl->device,
 			 "Ignoring bogus Namespace Identifiers\n");
@@ -1653,6 +1656,7 @@ static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl,
 		info->is_ready = id->nstat & NVME_NSTAT_NRDY;
 		info->is_rotational = id->nsfeat & NVME_NS_ROTATIONAL;
 		info->no_vwc = id->nsfeat & NVME_NS_VWC_NOT_PRESENT;
+		info->endgid = le16_to_cpu(id->endgid);
 	}
 	kfree(id);
 	return ret;
@@ -2147,6 +2151,97 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns,
 	return ret;
 }
 
+static int nvme_check_fdp(struct nvme_ns *ns, struct nvme_ns_info *info,
+			  u8 fdp_idx)
+{
+	struct nvme_fdp_config_log hdr, *h;
+	struct nvme_fdp_config_desc *desc;
+	size_t size = sizeof(hdr);
+	int i, n, ret;
+	void *log;
+
+	info->runs = 0;
+	ret = nvme_get_log_lsi(ns->ctrl, 0, NVME_LOG_FDP_CONFIGS, 0, NVME_CSI_NVM,
+			   (void *)&hdr, size, 0, info->endgid);
+	if (ret)
+		return ret;
+
+	size = le32_to_cpu(hdr.sze);
+	h = kzalloc(size, GFP_KERNEL);
+	if (!h)
+		return 0;
+
+	ret = nvme_get_log_lsi(ns->ctrl, 0, NVME_LOG_FDP_CONFIGS, 0, NVME_CSI_NVM,
+			   h, size, 0, info->endgid);
+	if (ret)
+		goto out;
+
+	n = le16_to_cpu(h->numfdpc) + 1;
+	if (fdp_idx > n)
+		goto out;
+
+	log = h + 1;
+	do {
+		desc = log;
+		log += le16_to_cpu(desc->dsze);
+	} while (i++ < fdp_idx);
+
+	info->runs = le64_to_cpu(desc->runs);
+out:
+	kfree(h);
+	return ret;
+}
+
+static int nvme_query_fdp_info(struct nvme_ns *ns, struct nvme_ns_info *info)
+{
+	struct nvme_ns_head *head = ns->head;
+	struct nvme_fdp_ruh_status *ruhs;
+	struct nvme_fdp_config fdp;
+	struct nvme_command c = {};
+	int size, ret;
+
+	ret = nvme_get_features(ns->ctrl, NVME_FEAT_FDP, info->endgid, NULL, 0,
+				&fdp);
+	if (ret)
+		goto err;
+
+	if (!(fdp.flags & FDPCFG_FDPE))
+		goto err;
+
+	ret = nvme_check_fdp(ns, info, fdp.fdpcidx);
+	if (ret || !info->runs)
+		goto err;
+
+	size = struct_size(ruhs, ruhsd, NVME_MAX_PLIDS);
+	ruhs = kzalloc(size, GFP_KERNEL);
+	if (!ruhs) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	c.imr.opcode = nvme_cmd_io_mgmt_recv;
+	c.imr.nsid = cpu_to_le32(head->ns_id);
+	c.imr.mo = NVME_IO_MGMT_RECV_MO_RUHS;
+	c.imr.numd = cpu_to_le32(nvme_bytes_to_numd(size));
+	ret = nvme_submit_sync_cmd(ns->queue, &c, ruhs, size);
+	if (ret)
+		goto free;
+
+	head->nr_plids = le16_to_cpu(ruhs->nruhsd);
+	if (!head->nr_plids)
+		goto free;
+
+	kfree(ruhs);
+	return 0;
+
+free:
+	kfree(ruhs);
+err:
+	head->nr_plids = 0;
+	info->runs = 0;
+	return ret;
+}
+
 static int nvme_update_ns_info_block(struct nvme_ns *ns,
 		struct nvme_ns_info *info)
 {
@@ -2183,6 +2278,15 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 			goto out;
 	}
 
+	if (ns->ctrl->ctratt & NVME_CTRL_ATTR_FDPS) {
+		ret = nvme_query_fdp_info(ns, info);
+		if (ret)
+			dev_warn(ns->ctrl->device,
+				"FDP failure status:0x%x\n", ret);
+		if (ret < 0)
+			goto out;
+	}
+
 	blk_mq_freeze_queue(ns->disk->queue);
 	ns->head->lba_shift = id->lbaf[lbaf].ds;
 	ns->head->nuse = le64_to_cpu(id->nuse);
@@ -2216,6 +2320,12 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if (!nvme_init_integrity(ns->head, &lim, info))
 		capacity = 0;
 
+	lim.max_write_streams = ns->head->nr_plids;
+	if (lim.max_write_streams)
+		lim.write_stream_granularity = info->runs;
+	else
+		lim.write_stream_granularity = 0;
+
 	ret = queue_limits_commit_update(ns->disk->queue, &lim);
 	if (ret) {
 		blk_mq_unfreeze_queue(ns->disk->queue);
@@ -2318,6 +2428,8 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 			ns->head->disk->flags |= GENHD_FL_HIDDEN;
 		else
 			nvme_init_integrity(ns->head, &lim, info);
+		lim.max_write_streams = ns_lim->max_write_streams;
+		lim.write_stream_granularity = ns_lim->write_stream_granularity;
 		ret = queue_limits_commit_update(ns->head->disk->queue, &lim);
 
 		set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index c1995d89ffdb8..914cc93e91f6d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -454,6 +454,8 @@ struct nvme_ns_ids {
 	u8	csi;
 };
 
+#define NVME_MAX_PLIDS   (S8_MAX - 1)
+
 /*
  * Anchor structure for namespaces.  There is one for each namespace in a
  * NVMe subsystem that any of our controllers can see, and the namespace
@@ -491,6 +493,8 @@ struct nvme_ns_head {
 	struct device		cdev_device;
 
 	struct gendisk		*disk;
+
+	u16			nr_plids;
 #ifdef CONFIG_NVME_MULTIPATH
 	struct bio_list		requeue_list;
 	spinlock_t		requeue_lock;
-- 
2.43.5