[PATCHv14 00/11] block write streams with nvme fdp

[PATCHv14 00/11] block write streams with nvme fdp

[Keith Busch]

From: Keith Busch <kbusch@kernel.org>

Previous discussion:

https://lore.kernel.org/linux-nvme/20241210194722.1905732-1-kbusch@meta.com/T/#u

Changes from v13:

  Fixed up printing size_t format (kernel test robot)

  Use %d for endgid (John)

  Removed bdev write stream granularity helper (no user in this series)
  (John)

  Clamp variable size FDP config log page size to max order (Hannes)

  Ensure the log descriptor sizes make sense (Hannes)

  Comment typos (Nitesh)

  Commit log description fix for where to find the write stream
  parameters (Nitesh).

Christoph Hellwig (7):
  fs: add a write stream field to the kiocb
  block: add a bi_write_stream field
  block: introduce a write_stream_granularity queue limit
  block: expose write streams for block device nodes
  nvme: add a nvme_get_log_lsi helper
  nvme: pass a void pointer to nvme_get/set_features for the result
  nvme: add FDP definitions

Keith Busch (4):
  block: introduce max_write_streams queue limit
  io_uring: enable per-io write streams
  nvme: register fdp parameters with the block layer
  nvme: use fdp streams if write stream is provided

 Documentation/ABI/stable/sysfs-block |  15 +++
 block/bio.c                          |   2 +
 block/blk-crypto-fallback.c          |   1 +
 block/blk-merge.c                    |   4 +
 block/blk-sysfs.c                    |   6 +
 block/bounce.c                       |   1 +
 block/fops.c                         |  23 ++++
 drivers/nvme/host/core.c             | 192 ++++++++++++++++++++++++++-
 drivers/nvme/host/nvme.h             |   7 +-
 include/linux/blk_types.h            |   1 +
 include/linux/blkdev.h               |  10 ++
 include/linux/fs.h                   |   1 +
 include/linux/nvme.h                 |  77 +++++++++++
 include/uapi/linux/io_uring.h        |   4 +
 io_uring/io_uring.c                  |   2 +
 io_uring/rw.c                        |   1 +
 16 files changed, 341 insertions(+), 6 deletions(-)

-- 
2.43.5

[PATCHv14 10/11] nvme: register fdp parameters with the block layer

[Keith Busch]

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 | 145 +++++++++++++++++++++++++++++++++++++++
 drivers/nvme/host/nvme.h |   2 +
 2 files changed, 147 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index c2a3585a3fa59..2392373415fd6 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -23,6 +23,7 @@
 #include <linux/pm_qos.h>
 #include <linux/ratelimit.h>
 #include <linux/unaligned.h>
+#include <linux/vmalloc.h>
 
 #include "nvme.h"
 #include "fabrics.h"
@@ -38,6 +39,8 @@ 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 +1616,7 @@ 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 +1657,7 @@ 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 +2152,132 @@ 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 = vmalloc(size);
+	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)
 {
@@ -2183,6 +2314,12 @@ 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 < 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 +2353,12 @@ 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);
@@ -2318,6 +2461,8 @@ 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..4b412cd8001f1 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -491,6 +491,8 @@ 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

Re: [PATCHv14 10/11] nvme: register fdp parameters with the block layer

[Hannes Reinecke]

On 12/11/24 19:35, Keith Busch wrote:
> 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 | 145 +++++++++++++++++++++++++++++++++++++++
>   drivers/nvme/host/nvme.h |   2 +
>   2 files changed, 147 insertions(+)
> 
Reviewed-by: Hannes Reinecke <hare@suse.de>

Cheers,

Hannes
-- 
Dr. Hannes Reinecke                  Kernel Storage Architect
hare@suse.de                                +49 911 74053 688
SUSE Software Solutions GmbH, Frankenstr. 146, 90461 Nürnberg
HRB 36809 (AG Nürnberg), GF: I. Totev, A. McDonald, W. Knoblich

Re: [PATCHv14 10/11] nvme: register fdp parameters with the block layer

[Nitesh Shetty]

[-- Attachment #1: Type: text/plain, Size: 375 bytes --]

On 11/12/24 10:35AM, Keith Busch wrote:
>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>
>---

Reviewed-by: Nitesh Shetty <nj.shetty@samsung.com>

[-- Attachment #2: Type: text/plain, Size: 0 bytes --]

Re: [PATCHv14 10/11] nvme: register fdp parameters with the block layer

[Christoph Hellwig]

On Wed, Dec 11, 2024 at 10:35:13AM -0800, Keith Busch wrote:
> +	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 = vmalloc(size);
> +	if (!h)
> +		return -ENOMEM;

Isn't an unconditional vmalloc here for something that usually should
have less than a handful of descriptors a little aggressive?  I'd use
kvmalloc here to get the best of both worlds, and the free path seems
to already use kvfree anyway.

Otherwise the incremental changes vs the previous version for the entire
series look good to me.

Re: [PATCHv14 00/11] block write streams with nvme fdp

[Kanchan Joshi]

For
> 16 files changed, 341 insertions(+), 6 deletions(-)

Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>