From: Keith Busch <[email protected]>
To: <[email protected]>, <[email protected]>,
<[email protected]>
Cc: <[email protected]>, <[email protected]>,
<[email protected]>, <[email protected]>, <[email protected]>,
Keith Busch <[email protected]>, Hannes Reinecke <[email protected]>,
Nitesh Shetty <[email protected]>
Subject: [PATCHv2 10/11] nvme: register fdp parameters with the block layer
Date: Mon, 3 Feb 2025 10:41:28 -0800 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
From: Keith Busch <[email protected]>
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.
Reviewed-by: Hannes Reinecke <[email protected]>
Reviewed-by: Nitesh Shetty <[email protected]>
Signed-off-by: Keith Busch <[email protected]>
---
drivers/nvme/host/core.c | 144 +++++++++++++++++++++++++++++++++++++++
drivers/nvme/host/nvme.h | 2 +
2 files changed, 146 insertions(+)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 324b31ba270a6..c8bc58b8ee3aa 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;
@@ -2156,6 +2160,132 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns,
return ret;
}
+static int nvme_query_fdp_granularity(struct nvme_ctrl *ctrl,
+ 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);
+ void *log, *end;
+ int i, n, ret;
+
+ ret = nvme_get_log_lsi(ctrl, 0, NVME_LOG_FDP_CONFIGS, 0,
+ NVME_CSI_NVM, &hdr, size, 0, info->endgid);
+ if (ret) {
+ dev_warn(ctrl->device,
+ "FDP configs log header status:0x%x endgid:%d\n", ret,
+ info->endgid);
+ return ret;
+ }
+
+ size = le32_to_cpu(hdr.sze);
+ if (size > PAGE_SIZE * MAX_ORDER_NR_PAGES) {
+ dev_warn(ctrl->device, "FDP config size too large:%zu\n",
+ size);
+ return 0;
+ }
+
+ h = kvmalloc(size, GFP_KERNEL);
+ if (!h)
+ return -ENOMEM;
+
+ ret = nvme_get_log_lsi(ctrl, 0, NVME_LOG_FDP_CONFIGS, 0,
+ NVME_CSI_NVM, h, size, 0, info->endgid);
+ if (ret) {
+ dev_warn(ctrl->device,
+ "FDP configs log status:0x%x endgid:%d\n", ret,
+ info->endgid);
+ goto out;
+ }
+
+ n = le16_to_cpu(h->numfdpc) + 1;
+ if (fdp_idx > n) {
+ dev_warn(ctrl->device, "FDP index:%d out of range:%d\n",
+ fdp_idx, n);
+ /* Proceed without registering FDP streams */
+ ret = 0;
+ goto out;
+ }
+
+ log = h + 1;
+ desc = log;
+ end = log + size - sizeof(*h);
+ for (i = 0; i < fdp_idx; i++) {
+ log += le16_to_cpu(desc->dsze);
+ desc = log;
+ if (log >= end) {
+ dev_warn(ctrl->device,
+ "FDP invalid config descriptor list\n");
+ ret = 0;
+ goto out;
+ }
+ }
+
+ if (le32_to_cpu(desc->nrg) > 1) {
+ dev_warn(ctrl->device, "FDP NRG > 1 not supported\n");
+ ret = 0;
+ goto out;
+ }
+
+ info->runs = le64_to_cpu(desc->runs);
+out:
+ kvfree(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_ctrl *ctrl = ns->ctrl;
+ struct nvme_fdp_ruh_status *ruhs;
+ struct nvme_fdp_config fdp;
+ struct nvme_command c = {};
+ size_t size;
+ int ret;
+
+ /*
+ * The FDP configuration is static for the lifetime of the namespace,
+ * so return immediately if we've already registered this namespace's
+ * streams.
+ */
+ if (head->nr_plids)
+ return 0;
+
+ ret = nvme_get_features(ctrl, NVME_FEAT_FDP, info->endgid, NULL, 0,
+ &fdp);
+ if (ret) {
+ dev_warn(ctrl->device, "FDP get feature status:0x%x\n", ret);
+ return ret;
+ }
+
+ if (!(fdp.flags & FDPCFG_FDPE))
+ return 0;
+
+ ret = nvme_query_fdp_granularity(ctrl, info, fdp.fdpcidx);
+ if (!info->runs)
+ return ret;
+
+ size = struct_size(ruhs, ruhsd, S8_MAX - 1);
+ ruhs = kzalloc(size, GFP_KERNEL);
+ if (!ruhs)
+ return -ENOMEM;
+
+ 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) {
+ dev_warn(ctrl->device, "FDP io-mgmt status:0x%x\n", ret);
+ goto free;
+ }
+
+ head->nr_plids = le16_to_cpu(ruhs->nruhsd);
+free:
+ kfree(ruhs);
+ return ret;
+}
+
static int nvme_update_ns_info_block(struct nvme_ns *ns,
struct nvme_ns_info *info)
{
@@ -2194,6 +2324,12 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
lim = queue_limits_start_update(ns->disk->queue);
+ if (ns->ctrl->ctratt & NVME_CTRL_ATTR_FDPS) {
+ ret = nvme_query_fdp_info(ns, info);
+ 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);
@@ -2225,6 +2361,12 @@ 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 = max(info->runs, U32_MAX);
+ else
+ lim.write_stream_granularity = 0;
+
ret = queue_limits_commit_update(ns->disk->queue, &lim);
if (ret) {
blk_mq_unfreeze_queue(ns->disk->queue);
@@ -2327,6 +2469,8 @@ 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 9c94c1085869b..b63164cf6b274 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -496,6 +496,8 @@ 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
next prev parent reply other threads:[~2025-02-03 18:53 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-03 18:41 [PATCHv2 00/11] block write streams with nvme fdp Keith Busch
2025-02-03 18:41 ` [PATCHv2 01/11] fs: add a write stream field to the kiocb Keith Busch
2025-02-03 18:41 ` [PATCHv2 02/11] block: add a bi_write_stream field Keith Busch
2025-02-03 18:41 ` [PATCHv2 03/11] block: introduce max_write_streams queue limit Keith Busch
2025-02-03 18:41 ` [PATCHv2 04/11] block: introduce a write_stream_granularity " Keith Busch
2025-02-03 18:41 ` [PATCHv2 05/11] block: expose write streams for block device nodes Keith Busch
2025-02-03 18:41 ` [PATCHv2 06/11] io_uring: enable per-io write streams Keith Busch
2025-02-04 6:00 ` Christoph Hellwig
2025-02-03 18:41 ` [PATCHv2 07/11] nvme: add a nvme_get_log_lsi helper Keith Busch
2025-02-03 18:41 ` [PATCHv2 08/11] nvme: pass a void pointer to nvme_get/set_features for the result Keith Busch
2025-02-03 18:41 ` [PATCHv2 09/11] nvme: add FDP definitions Keith Busch
2025-02-03 18:41 ` Keith Busch [this message]
2025-02-04 6:01 ` [PATCHv2 10/11] nvme: register fdp parameters with the block layer Christoph Hellwig
2025-02-03 18:41 ` [PATCHv2 11/11] nvme: use fdp streams if write stream is provided Keith Busch
2025-02-04 6:01 ` Christoph Hellwig
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox