On Tue, May 6, 2025 at 5:31 AM Kanchan Joshi <joshi.k@xxxxxxxxxxx> wrote:
>
> From: Keith Busch <kbusch@xxxxxxxxxx>
>
> 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@xxxxxxx>
> Reviewed-by: Nitesh Shetty <nj.shetty@xxxxxxxxxxx>
> Reviewed-by: Christoph Hellwig <hch@xxxxxx>
> Signed-off-by: Keith Busch <kbusch@xxxxxxxxxx>
> Signed-off-by: Kanchan Joshi <joshi.k@xxxxxxxxxxx>
> ---
> 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
>
>
