public inbox for io-uring@vger.kernel.org
 help / color / mirror / Atom feed
From: Caleb Sander Mateos <csander@purestorage.com>
To: Kanchan Joshi <joshi.k@samsung.com>
Cc: axboe@kernel.dk, kbusch@kernel.org, hch@lst.de,
	asml.silence@gmail.com,  io-uring@vger.kernel.org,
	linux-block@vger.kernel.org,  linux-fsdevel@vger.kernel.org,
	linux-nvme@lists.infradead.org,  Hannes Reinecke <hare@suse.de>,
	Nitesh Shetty <nj.shetty@samsung.com>
Subject: Re: [PATCH v16 10/11] nvme: register fdp parameters with the block layer
Date: Tue, 6 May 2025 09:13:33 -0700	[thread overview]
Message-ID: <CADUfDZqqqQVHqMpVaMWre1=GZfu42_SOQ5W9m0vhSZYyp1BBUA@mail.gmail.com> (raw)
In-Reply-To: <20250506121732.8211-11-joshi.k@samsung.com>

On Tue, May 6, 2025 at 5:31 AM Kanchan Joshi <joshi.k@samsung.com> 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.
>
> Reviewed-by: Hannes Reinecke <hare@suse.de>
> Reviewed-by: Nitesh Shetty <nj.shetty@samsung.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> Signed-off-by: Keith Busch <kbusch@kernel.org>
> Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
> ---
>  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 dd71b4c2b7b7..f25e03ff03df 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;
> @@ -1611,6 +1613,7 @@ 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");
> @@ -1651,6 +1654,7 @@ 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;
> @@ -2155,6 +2159,132 @@ 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)
>  {
> @@ -2192,6 +2322,12 @@ 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;
> +       }
> +
>         lim = queue_limits_start_update(ns->disk->queue);
>
>         memflags = blk_mq_freeze_queue(ns->disk->queue);
> @@ -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);

What is the purpose of this max(..., U32_MAX)? Should it be min() instead?

Best,
Caleb

> +       else
> +               lim.write_stream_granularity = 0;
> +
>         ret = queue_limits_commit_update(ns->disk->queue, &lim);
>         if (ret) {
>                 blk_mq_unfreeze_queue(ns->disk->queue, memflags);
> @@ -2328,6 +2470,8 @@ 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 aedb734283b8..3e14daa4ed3e 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;
> --
> 2.25.1
>
>

  reply	other threads:[~2025-05-06 16:13 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20250506122633epcas5p21d2c989313f38dea82162fff7b9856e7@epcas5p2.samsung.com>
2025-05-06 12:17 ` [PATCH v16 00/11] Block write streams with nvme fdp Kanchan Joshi
     [not found]   ` <CGME20250506122635epcas5p145565666b3bfedf8da08075dd928d2ac@epcas5p1.samsung.com>
2025-05-06 12:17     ` [PATCH v16 01/11] fs: add a write stream field to the kiocb Kanchan Joshi
     [not found]   ` <CGME20250506122637epcas5p4a4e84171a1c6fa4ce0f01b6783fa2385@epcas5p4.samsung.com>
2025-05-06 12:17     ` [PATCH v16 02/11] block: add a bi_write_stream field Kanchan Joshi
     [not found]   ` <CGME20250506122638epcas5p364107da78e115a57f1fa91436265edeb@epcas5p3.samsung.com>
2025-05-06 12:17     ` [PATCH v16 03/11] block: introduce max_write_streams queue limit Kanchan Joshi
     [not found]   ` <CGME20250506122640epcas5p43b5abe6562ad64ee1d7254b1215906d4@epcas5p4.samsung.com>
2025-05-06 12:17     ` [PATCH v16 04/11] block: introduce a write_stream_granularity " Kanchan Joshi
     [not found]   ` <CGME20250506122642epcas5p267fef037060e55d1e9c0055b0dfd692e@epcas5p2.samsung.com>
2025-05-06 12:17     ` [PATCH v16 05/11] block: expose write streams for block device nodes Kanchan Joshi
     [not found]   ` <CGME20250506122644epcas5p2b2bf2c66172dbaf3127f6621062efb24@epcas5p2.samsung.com>
2025-05-06 12:17     ` [PATCH v16 06/11] io_uring: enable per-io write streams Kanchan Joshi
     [not found]   ` <CGME20250506122646epcas5p3bd2a00493c94d1032c31ec64aaa1bbb0@epcas5p3.samsung.com>
2025-05-06 12:17     ` [PATCH v16 07/11] nvme: add a nvme_get_log_lsi helper Kanchan Joshi
     [not found]   ` <CGME20250506122647epcas5p41ed9efc231e2300a1547f6081db73842@epcas5p4.samsung.com>
2025-05-06 12:17     ` [PATCH v16 08/11] nvme: pass a void pointer to nvme_get/set_features for the result Kanchan Joshi
     [not found]   ` <CGME20250506122649epcas5p1294652bcfc93f08dd12e6ba8a497c55b@epcas5p1.samsung.com>
2025-05-06 12:17     ` [PATCH v16 09/11] nvme: add FDP definitions Kanchan Joshi
     [not found]   ` <CGME20250506122651epcas5p4100fd5435ce6e6686318265b414c1176@epcas5p4.samsung.com>
2025-05-06 12:17     ` [PATCH v16 10/11] nvme: register fdp parameters with the block layer Kanchan Joshi
2025-05-06 16:13       ` Caleb Sander Mateos [this message]
2025-05-06 16:26         ` Keith Busch
2025-05-06 18:14           ` Kanchan Joshi
2025-05-06 19:03             ` Keith Busch
     [not found]   ` <CGME20250506122653epcas5p1824d4af64d0b599fde2de831d8ebf732@epcas5p1.samsung.com>
2025-05-06 12:17     ` [PATCH v16 11/11] nvme: use fdp streams if write stream is provided Kanchan Joshi
2025-05-06 16:14       ` Caleb Sander Mateos
2025-05-06 16:28         ` Keith Busch
2025-05-06 13:48   ` [PATCH v16 00/11] Block write streams with nvme fdp Jens Axboe

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 \
    --in-reply-to='CADUfDZqqqQVHqMpVaMWre1=GZfu42_SOQ5W9m0vhSZYyp1BBUA@mail.gmail.com' \
    --to=csander@purestorage.com \
    --cc=asml.silence@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=io-uring@vger.kernel.org \
    --cc=joshi.k@samsung.com \
    --cc=kbusch@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=nj.shetty@samsung.com \
    /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