[PATCH V2 1/3] nvmet: support reservation feature
Sagi Grimberg
sagi at grimberg.me
Mon Jan 15 01:26:45 PST 2024
On 1/14/24 11:23, Guixin Liu wrote:
> This patch implements the reservation feature, includes:
> 1. reservation register(register, unregister and replace).
> 2. reservation acquire(acquire, preempt, preempt and abort).
> 3. reservation release(release and clear).
> 4. reservation report.
>
> And also make reservation configurable, one can set ns to support
> reservation before enable ns. The default of resv_enable is false.
>
> Signed-off-by: Guixin Liu <kanie at linux.alibaba.com>
> ---
> drivers/nvme/target/Makefile | 2 +-
> drivers/nvme/target/admin-cmd.c | 14 +-
> drivers/nvme/target/configfs.c | 27 +
> drivers/nvme/target/core.c | 49 +-
> drivers/nvme/target/nvmet.h | 33 ++
> drivers/nvme/target/pr.c | 887 ++++++++++++++++++++++++++++++++
> include/linux/nvme.h | 48 ++
> 7 files changed, 1053 insertions(+), 7 deletions(-)
> create mode 100644 drivers/nvme/target/pr.c
>
> diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile
> index c66820102493..f9bfc904a5b3 100644
> --- a/drivers/nvme/target/Makefile
> +++ b/drivers/nvme/target/Makefile
> @@ -10,7 +10,7 @@ obj-$(CONFIG_NVME_TARGET_FCLOOP) += nvme-fcloop.o
> obj-$(CONFIG_NVME_TARGET_TCP) += nvmet-tcp.o
>
> nvmet-y += core.o configfs.o admin-cmd.o fabrics-cmd.o \
> - discovery.o io-cmd-file.o io-cmd-bdev.o
> + discovery.o io-cmd-file.o io-cmd-bdev.o pr.o
> nvmet-$(CONFIG_NVME_TARGET_PASSTHRU) += passthru.o
> nvmet-$(CONFIG_BLK_DEV_ZONED) += zns.o
> nvmet-$(CONFIG_NVME_TARGET_AUTH) += fabrics-cmd-auth.o auth.o
> diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
> index 39cb570f833d..791bc7e740c0 100644
> --- a/drivers/nvme/target/admin-cmd.c
> +++ b/drivers/nvme/target/admin-cmd.c
> @@ -176,6 +176,10 @@ static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log)
> log->iocs[nvme_cmd_read] =
> log->iocs[nvme_cmd_flush] =
> log->iocs[nvme_cmd_dsm] =
> + log->iocs[nvme_cmd_resv_acquire] =
> + log->iocs[nvme_cmd_resv_register] =
> + log->iocs[nvme_cmd_resv_release] =
> + log->iocs[nvme_cmd_resv_report] =
> cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
> log->iocs[nvme_cmd_write] =
> log->iocs[nvme_cmd_write_zeroes] =
> @@ -340,6 +344,8 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
> return nvmet_execute_get_log_cmd_effects_ns(req);
> case NVME_LOG_ANA:
> return nvmet_execute_get_log_page_ana(req);
> + case NVME_LOG_RESERVATION:
> + return nvmet_execute_get_log_page_resv(req);
> }
> pr_debug("unhandled lid %d on qid %d\n",
> req->cmd->get_log_page.lid, req->sq->qid);
> @@ -550,7 +556,13 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
> */
> id->nmic = NVME_NS_NMIC_SHARED;
> id->anagrpid = cpu_to_le32(req->ns->anagrpid);
> -
> + id->rescap = NVME_PR_SUPPORT_WRITE_EXCLUSIVE |
> + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS |
> + NVME_PR_SUPPORT_WRITE_EXCLUSIVE_REG_ONLY |
> + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_REG_ONLY |
> + NVME_PR_SUPPORT_WRITE_EXCLUSIVE_ALL_REGS |
> + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_ALL_REGS |
> + NVME_PR_SUPPORT_IEKEY_VER_1_3_DEF;
> memcpy(&id->nguid, &req->ns->nguid, sizeof(id->nguid));
>
> id->lbaf[0].ds = req->ns->blksize_shift;
> diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
> index d937fe05129e..1ac4802ec818 100644
> --- a/drivers/nvme/target/configfs.c
> +++ b/drivers/nvme/target/configfs.c
> @@ -714,6 +714,32 @@ static ssize_t nvmet_ns_revalidate_size_store(struct config_item *item,
>
> CONFIGFS_ATTR_WO(nvmet_ns_, revalidate_size);
>
> +static ssize_t nvmet_ns_resv_enable_show(struct config_item *item, char *page)
> +{
> + return sprintf(page, "%d\n", to_nvmet_ns(item)->pr.enable);
> +}
> +
> +static ssize_t nvmet_ns_resv_enable_store(struct config_item *item,
> + const char *page, size_t count)
> +{
> + struct nvmet_ns *ns = to_nvmet_ns(item);
> + bool val;
> +
> + if (kstrtobool(page, &val))
> + return -EINVAL;
> +
> + mutex_lock(&ns->subsys->lock);
> + if (ns->enabled) {
> + pr_err("the ns:%d is already enabled.\n", ns->nsid);
> + mutex_unlock(&ns->subsys->lock);
> + return -EINVAL;
> + }
> + ns->pr.enable = val;
> + mutex_unlock(&ns->subsys->lock);
> + return count;
> +}
> +CONFIGFS_ATTR(nvmet_ns_, resv_enable);
> +
> static struct configfs_attribute *nvmet_ns_attrs[] = {
> &nvmet_ns_attr_device_path,
> &nvmet_ns_attr_device_nguid,
> @@ -722,6 +748,7 @@ static struct configfs_attribute *nvmet_ns_attrs[] = {
> &nvmet_ns_attr_enable,
> &nvmet_ns_attr_buffered_io,
> &nvmet_ns_attr_revalidate_size,
> + &nvmet_ns_attr_resv_enable,
> #ifdef CONFIG_PCI_P2PDMA
> &nvmet_ns_attr_p2pmem,
> #endif
> diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
> index 3935165048e7..a5019881d60b 100644
> --- a/drivers/nvme/target/core.c
> +++ b/drivers/nvme/target/core.c
> @@ -591,6 +591,8 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
> if (ns->nsid > subsys->max_nsid)
> subsys->max_nsid = ns->nsid;
>
> + nvmet_pr_init_ns(ns);
> +
> ret = xa_insert(&subsys->namespaces, ns->nsid, ns, GFP_KERNEL);
> if (ret)
> goto out_restore_subsys_maxnsid;
> @@ -651,6 +653,7 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
>
> subsys->nr_namespaces--;
> nvmet_ns_changed(subsys, ns->nsid);
> + nvmet_pr_exit_ns(ns);
> nvmet_ns_dev_disable(ns);
> out_unlock:
> mutex_unlock(&subsys->lock);
> @@ -904,18 +907,34 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
> return ret;
> }
>
> + if (req->ns->pr.enable) {
> + ret = nvmet_parse_pr_cmd(req);
> + if (!ret)
> + return ret;
> + }
> +
> switch (req->ns->csi) {
> case NVME_CSI_NVM:
> if (req->ns->file)
> - return nvmet_file_parse_io_cmd(req);
> - return nvmet_bdev_parse_io_cmd(req);
> + ret = nvmet_file_parse_io_cmd(req);
> + else
> + ret = nvmet_bdev_parse_io_cmd(req);
> + break;
> case NVME_CSI_ZNS:
> if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
> - return nvmet_bdev_zns_parse_io_cmd(req);
> - return NVME_SC_INVALID_IO_CMD_SET;
> + ret = nvmet_bdev_zns_parse_io_cmd(req);
> + else
> + ret = NVME_SC_INVALID_IO_CMD_SET;
> + break;
> default:
> - return NVME_SC_INVALID_IO_CMD_SET;
> + ret = NVME_SC_INVALID_IO_CMD_SET;
> }
> + if (ret)
> + return ret;
> +
> + if (req->ns->pr.enable)
> + ret = nvmet_pr_check_cmd_access(req);
> + return ret;
> }
>
> bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
> @@ -1231,6 +1250,21 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
> nvmet_passthrough_override_cap(ctrl);
> }
>
> +bool nvmet_is_host_still_connected(uuid_t *hostid, struct nvmet_subsys *subsys)
> +{
> + struct nvmet_ctrl *ctrl;
> +
> + mutex_lock(&subsys->lock);
> + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
> + if (uuid_equal(hostid, &ctrl->hostid)) {
> + mutex_unlock(&subsys->lock);
> + return true;
> + }
> + }
> + mutex_unlock(&subsys->lock);
> + return false;
> +}
> +
> struct nvmet_ctrl *nvmet_ctrl_find_get(const char *subsysnqn,
> const char *hostnqn, u16 cntlid,
> struct nvmet_req *req)
> @@ -1450,6 +1484,10 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
> ctrl->err_counter = 0;
> spin_lock_init(&ctrl->error_lock);
>
> + ctrl->resv_log_counter = 0;
> + mutex_init(&ctrl->resv_log_lock);
> + INIT_LIST_HEAD(&ctrl->resv_log_list);
> +
> nvmet_start_keep_alive_timer(ctrl);
>
> mutex_lock(&subsys->lock);
> @@ -1488,6 +1526,7 @@ static void nvmet_ctrl_free(struct kref *ref)
> cancel_work_sync(&ctrl->fatal_err_work);
>
> nvmet_destroy_auth(ctrl);
> + nvmet_ctrl_destroy_pr(ctrl);
>
> ida_free(&cntlid_ida, ctrl->cntlid);
>
> diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
> index 6c8acebe1a1a..4ba4958768ac 100644
> --- a/drivers/nvme/target/nvmet.h
> +++ b/drivers/nvme/target/nvmet.h
> @@ -56,6 +56,22 @@
> #define IPO_IATTR_CONNECT_SQE(x) \
> (cpu_to_le32(offsetof(struct nvmf_connect_command, x)))
>
> +struct nvmet_pr_registrant {
> + bool is_holder;
> + u64 rkey;
> + uuid_t hostid;
> + struct list_head entry;
> +};
> +
> +struct nvmet_pr {
> + bool enable;
> + enum nvme_pr_type rtype;
> + u32 generation;
> + struct nvmet_pr_registrant *holder;
> + rwlock_t pr_lock;
> + struct list_head registrant_list;
> +};
> +
> struct nvmet_ns {
> struct percpu_ref ref;
> struct bdev_handle *bdev_handle;
> @@ -85,6 +101,7 @@ struct nvmet_ns {
> int pi_type;
> int metadata_size;
> u8 csi;
> + struct nvmet_pr pr;
> };
>
> static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item)
> @@ -190,6 +207,11 @@ static inline bool nvmet_port_secure_channel_required(struct nvmet_port *port)
> return nvmet_port_disc_addr_treq_secure_channel(port) == NVMF_TREQ_REQUIRED;
> }
>
> +struct nvmet_pr_log_entry {
> + struct nvme_pr_log log;
> + struct list_head entry;
> +};
> +
> struct nvmet_ctrl {
> struct nvmet_subsys *subsys;
> struct nvmet_sq **sqs;
> @@ -243,6 +265,9 @@ struct nvmet_ctrl {
> u8 *dh_key;
> size_t dh_keysize;
> #endif
> + struct mutex resv_log_lock;
> + u64 resv_log_counter;
> + struct list_head resv_log_list;
> };
>
> struct nvmet_subsys {
> @@ -750,4 +775,12 @@ static inline bool nvmet_has_auth(struct nvmet_ctrl *ctrl)
> static inline const char *nvmet_dhchap_dhgroup_name(u8 dhgid) { return NULL; }
> #endif
>
> +void nvmet_pr_init_ns(struct nvmet_ns *ns);
> +u16 nvmet_parse_pr_cmd(struct nvmet_req *req);
> +u16 nvmet_pr_check_cmd_access(struct nvmet_req *req);
> +void nvmet_ctrl_destroy_pr(struct nvmet_ctrl *ctrl);
> +void nvmet_pr_exit_ns(struct nvmet_ns *ns);
> +bool nvmet_is_host_still_connected(uuid_t *hostid, struct nvmet_subsys *subsys);
> +void nvmet_execute_get_log_page_resv(struct nvmet_req *req);
> +
> #endif /* _NVMET_H */
> diff --git a/drivers/nvme/target/pr.c b/drivers/nvme/target/pr.c
> new file mode 100644
> index 000000000000..900a3f7a0808
> --- /dev/null
> +++ b/drivers/nvme/target/pr.c
> @@ -0,0 +1,887 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * NVMe over Fabrics Persist Reservation.
> + * Copyright (c) 2024 Guixin Liu, Alibaba Group.
> + * All rights reserved.
> + */
> +#include "nvmet.h"
> +#include <linux/slab.h>
> +#include <asm/unaligned.h>
> +
> +struct nvmet_pr_register_data {
> + __le64 crkey;
> + __le64 nrkey;
> +};
> +
> +struct nvmet_pr_acquire_data {
> + __le64 crkey;
> + __le64 prkey;
> +};
> +
> +struct nvmet_pr_release_data {
> + __le64 crkey;
> +};
> +
> +static inline struct nvmet_ns *nvmet_pr_to_ns(struct nvmet_pr *pr)
> +{
> + return container_of(pr, struct nvmet_ns, pr);
> +}
> +
> +static inline void nvmet_pr_clean_holder(struct nvmet_pr *pr)
> +{
> + pr->holder = NULL;
> + pr->rtype = 0;
> +}
> +
> +static u16 nvmet_pr_validate_and_set_rtype(struct nvmet_pr *pr, u8 rtype)
> +{
> + if (rtype < NVME_PR_WRITE_EXCLUSIVE ||
> + rtype > NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS)
> + return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
> +
> + pr->rtype = rtype;
> + return NVME_SC_SUCCESS;
> +}
> +
> +static u16 nvmet_pr_set_rtype_and_holder(struct nvmet_pr *pr, u8 rtype,
> + struct nvmet_pr_registrant *reg)
> +{
> + u16 status;
> +
> + status = nvmet_pr_validate_and_set_rtype(pr, rtype);
> + if (!status)
> + pr->holder = reg;
> + return status;
> +}
> +
> +static inline void nvmet_pr_inc_generation(struct nvmet_pr *pr)
> +{
> + pr->generation++;
> +}
Useless wrapper. Shouldn't this be atomic_inc btw?
> +
> +static struct nvmet_pr_registrant *nvmet_pr_find_registrant_by_hostid(
> + struct nvmet_pr *pr,
> + uuid_t *hostid)
> +{
> + struct nvmet_pr_registrant *reg;
> +
> + list_for_each_entry(reg, &pr->registrant_list, entry) {
> + if (uuid_equal(®->hostid, hostid))
> + return reg;
> + }
> + return NULL;
> +}
> +
> +static u16 nvmet_pr_register(struct nvmet_req *req,
> + struct nvmet_pr_register_data *d)
> +{
> + u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + struct nvmet_ctrl *ctrl = req->sq->ctrl;
> + struct nvmet_pr *pr = &req->ns->pr;
> + struct nvmet_pr_registrant *reg;
> +
> + read_lock(&pr->pr_lock);
> + list_for_each_entry(reg, &pr->registrant_list, entry) {
> + if (uuid_equal(®->hostid, &ctrl->hostid)) {
> + if (reg->rkey == le64_to_cpu(d->nrkey))
> + status = NVME_SC_SUCCESS;
> + read_unlock(&pr->pr_lock);
> + goto out;
> + }
> + }
> + read_unlock(&pr->pr_lock);
Move to a wrapper?
> +
> + reg = kmalloc(sizeof(*reg), GFP_KERNEL);
> + if (!reg) {
> + status = NVME_SC_INTERNAL;
> + goto out;
> + }
> +
> + memset(reg, 0, sizeof(*reg));
> + INIT_LIST_HEAD(®->entry);
> + reg->rkey = le64_to_cpu(d->nrkey);
> + uuid_copy(®->hostid, &ctrl->hostid);
> + reg->is_holder = false;
> +
> + write_lock(&pr->pr_lock);
> + list_add_tail(®->entry, &pr->registrant_list);
> + write_unlock(&pr->pr_lock);
> + status = NVME_SC_SUCCESS;
> +out:
> + return status;
> +}
> +
> +void nvmet_execute_get_log_page_resv(struct nvmet_req *req)
> +{
> + struct nvmet_ctrl *ctrl = req->sq->ctrl;
> + struct nvmet_pr_log_entry *log_entry;
> + u16 status = NVME_SC_SUCCESS;
> + struct nvme_pr_log *log;
> +
> + mutex_lock(&ctrl->resv_log_lock);
> + log_entry = list_first_entry_or_null(&ctrl->resv_log_list,
> + struct nvmet_pr_log_entry, entry);
> + if (!log_entry)
> + goto out;
> +
> + list_del(&log_entry->entry);
> + log = &log_entry->log;
> + log->nr_avl_pages = min(list_count_nodes(&ctrl->resv_log_list), 255);
nr_pages
> + status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
> + kfree(log_entry);
> +out:
> + mutex_unlock(&ctrl->resv_log_lock);
> + nvmet_req_complete(req, status);
> +}
> +
> +static void nvmet_pr_add_resv_log(struct nvmet_ctrl *ctrl, u8 log_type, u32 nsid)
> +{
> + struct nvmet_pr_log_entry *log_entry;
> + struct nvme_pr_log *log;
> +
> + mutex_lock(&ctrl->resv_log_lock);
> + ctrl->resv_log_counter++;
> + if (ctrl->resv_log_counter == U64_MAX)
> + ctrl->resv_log_counter = 1;
> + log_entry = kmalloc(sizeof(*log_entry), GFP_KERNEL);
> + if (!log_entry) {
> + pr_warn("a reservation log lost, cntlid:%d, log_type:%d, nsid:%d\n",
> + ctrl->cntlid, log_type, nsid);
> + log_entry = list_last_entry(&ctrl->resv_log_list,
> + struct nvmet_pr_log_entry, entry);
> + if (log_entry)
> + log_entry->log.count =
> + cpu_to_le64(le64_to_cpu(log_entry->log.count) + 1);
> + goto unlock;
> + }
> +
> + log = &log_entry->log;
> + log->count = cpu_to_le64(ctrl->resv_log_counter);
> + log->type = log_type;
> + log->nsid = cpu_to_le32(nsid);
> +
> + list_add_tail(&log_entry->entry, &ctrl->resv_log_list);
What prevents this list from exploding?
I think you should mimic the ctrl error log slots.
> +unlock:
> + mutex_unlock(&ctrl->resv_log_lock);
> +}
> +
> +static void nvmet_pr_send_resv_released(struct nvmet_pr *pr, uuid_t *hostid)
> +{
> + struct nvmet_ns *ns = nvmet_pr_to_ns(pr);
> + struct nvmet_subsys *subsys = ns->subsys;
> + struct nvmet_ctrl *ctrl;
> +
> + mutex_lock(&subsys->lock);
> + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
> + if (!uuid_equal(&ctrl->hostid, hostid) &&
> + nvmet_pr_find_registrant_by_hostid(pr, &ctrl->hostid)) {
> + nvmet_pr_add_resv_log(ctrl,
> + NVME_PR_LOG_RESERVATION_RELEASED,
> + ns->nsid);
> + nvmet_add_async_event(ctrl, NVME_AER_CSS,
> + NVME_AEN_RESV_LOG_PAGE_AVALIABLE,
> + NVME_LOG_RESERVATION);
> + }
> + }
> + mutex_unlock(&subsys->lock);
> +}
> +
> +static void nvmet_pr_send_event_by_hostid(struct nvmet_pr *pr, uuid_t *hostid,
> + u8 log_type)
> +{
> + struct nvmet_ns *ns = nvmet_pr_to_ns(pr);
> + struct nvmet_subsys *subsys = ns->subsys;
> + struct nvmet_ctrl *ctrl;
> +
> + mutex_lock(&subsys->lock);
> + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
> + if (uuid_equal(hostid, &ctrl->hostid)) {
> + nvmet_pr_add_resv_log(ctrl, log_type, ns->nsid);
> + nvmet_add_async_event(ctrl, NVME_AER_CSS,
> + NVME_AEN_RESV_LOG_PAGE_AVALIABLE,
> + NVME_LOG_RESERVATION);
> + }
> + }
> + mutex_unlock(&subsys->lock);
> +}
> +
> +static void nvmet_pr_send_resv_preempted(struct nvmet_pr *pr, uuid_t *hostid)
> +{
> + nvmet_pr_send_event_by_hostid(pr, hostid,
> + NVME_PR_LOG_RESERVATOPM_PREEMPTED);
> +}
> +
> +static void nvmet_pr_send_registration_preempted(struct nvmet_pr *pr,
> + uuid_t *hostid)
> +{
> + nvmet_pr_send_event_by_hostid(pr, hostid,
> + NVME_PR_LOG_REGISTRATION_PREEMPTED);
> +}
> +
> +static void __nvmet_pr_unregister_one(struct nvmet_pr *pr,
> + struct nvmet_pr_registrant *reg)
> +{
> + u8 original_rtype = pr->rtype;
> +
> + list_del(®->entry);
> +
> + if (pr->holder != reg)
> + goto free_reg;
> +
> + if (original_rtype == NVME_PR_WRITE_EXCLUSIVE_ALL_REGS ||
> + original_rtype == NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS) {
> + pr->holder = list_first_entry_or_null(&pr->registrant_list,
> + struct nvmet_pr_registrant, entry);
> + if (!pr->holder)
> + pr->rtype = 0;
> + goto free_reg;
> + }
> +
> + nvmet_pr_clean_holder(pr);
> +
> + if (original_rtype == NVME_PR_WRITE_EXCLUSIVE_REG_ONLY ||
> + original_rtype == NVME_PR_WRITE_EXCLUSIVE_REG_ONLY)
> + nvmet_pr_send_resv_released(pr, ®->hostid);
> +
> +free_reg:
> + kfree(reg);
> +}
> +
> +static u16 nvmet_pr_unregister(struct nvmet_req *req,
> + struct nvmet_pr_register_data *d,
> + bool ignore_key)
> +{
> + u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + struct nvmet_ctrl *ctrl = req->sq->ctrl;
> + struct nvmet_pr *pr = &req->ns->pr;
> + struct nvmet_pr_registrant *reg;
> + struct nvmet_pr_registrant *tmp;
> +
> + write_lock(&pr->pr_lock);
> + list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) {
> + if (uuid_equal(®->hostid, &ctrl->hostid)) {
> + if (ignore_key || reg->rkey == le64_to_cpu(d->crkey)) {
> + status = NVME_SC_SUCCESS;
> + __nvmet_pr_unregister_one(pr, reg);
> + }
> + break;
> + }
> + }
> + write_unlock(&pr->pr_lock);
> +
> + return status;
> +}
> +
> +static u16 nvmet_pr_replace(struct nvmet_req *req,
> + struct nvmet_pr_register_data *d,
> + bool ignore_key)
> +{
> + u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + struct nvmet_ctrl *ctrl = req->sq->ctrl;
> + struct nvmet_pr *pr = &req->ns->pr;
> + struct nvmet_pr_registrant *reg;
> +
> + write_lock(&pr->pr_lock);
> + list_for_each_entry(reg, &pr->registrant_list, entry) {
> + if (uuid_equal(®->hostid, &ctrl->hostid)) {
> + if (ignore_key || reg->rkey == le64_to_cpu(d->crkey)) {
> + reg->rkey = le64_to_cpu(d->nrkey);
> + status = NVME_SC_SUCCESS;
> + }
> + break;
> + }
> + }
> + write_unlock(&pr->pr_lock);
> + return status;
> +}
> +
> +static void nvmet_execute_pr_register(struct nvmet_req *req)
> +{
> + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
> + bool ignore_key = (bool)((cdw10 >> 3) & 1); /* Ignore existing key, bit 03 */
> + struct nvmet_pr_register_data *d;
> + u8 reg_act = cdw10 & 0x07; /* Reservation Register Action, bit 02:00 */
> + u16 status;
> +
> + d = kmalloc(sizeof(*d), GFP_KERNEL);
> + if (!d) {
> + status = NVME_SC_INTERNAL;
> + goto out;
> + }
> +
> + status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
> + if (status)
> + goto free_data;
> +
> + switch (reg_act) {
> + case NVME_PR_REGISTER_ACT_REG:
> + status = nvmet_pr_register(req, d);
> + break;
> + case NVME_PR_REGISTER_ACT_UNREG:
> + status = nvmet_pr_unregister(req, d, ignore_key);
> + break;
> + case NVME_PR_REGISTER_ACT_REPLACE:
> + status = nvmet_pr_replace(req, d, ignore_key);
> + break;
> + default:
> + req->error_loc = offsetof(struct nvme_common_command,
> + cdw10);
> + status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
> + break;
> + }
> +free_data:
> + kfree(d);
> +out:
> + if (!status)
> + nvmet_pr_inc_generation(&req->ns->pr);
> + nvmet_req_complete(req, status);
> +}
> +
> +static u16 nvmet_pr_acquire(struct nvmet_req *req,
> + struct nvmet_pr_registrant *reg,
> + u8 rtype)
> +{
> + struct nvmet_pr *pr = &req->ns->pr;
> +
> + if (pr->holder && reg != pr->holder)
> + return NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + if (pr->holder && reg == pr->holder) {
> + if (pr->rtype == rtype)
> + return 0;
NVME_SC_SUCCESS
> + return NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + }
> +
> + return nvmet_pr_set_rtype_and_holder(pr, rtype, reg);
> +}
> +
> +static u16 nvmet_pr_unreg_by_prkey(struct nvmet_pr *pr, u64 prkey,
> + uuid_t *send_hostid)
> +{
> + u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + struct nvmet_pr_registrant *reg;
> + struct nvmet_pr_registrant *tmp;
> +
> + list_for_each_entry_safe(reg, tmp,
> + &pr->registrant_list, entry) {
> + if (reg->rkey == prkey) {
> + status = NVME_SC_SUCCESS;
> + if (!uuid_equal(®->hostid, send_hostid))
> + nvmet_pr_send_registration_preempted(pr,
> + ®->hostid);
> + __nvmet_pr_unregister_one(pr, reg);
> + }
> + }
> + return status;
> +}
> +
> +static u16 nvmet_pr_unreg_by_prkey_except_hostid(struct nvmet_pr *pr, u64 prkey,
> + uuid_t *send_hostid)
> +{
> + u16 status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + struct nvmet_pr_registrant *reg;
> + struct nvmet_pr_registrant *tmp;
> +
> + list_for_each_entry_safe(reg, tmp,
> + &pr->registrant_list, entry) {
> + if (reg->rkey == prkey &&
> + !uuid_equal(®->hostid, send_hostid)) {
> + status = NVME_SC_SUCCESS;
> + nvmet_pr_send_registration_preempted(pr, ®->hostid);
> + __nvmet_pr_unregister_one(pr, reg);
> + }
> + }
> + return status;
> +}
> +
> +static void nvmet_pr_unreg_except_hostid(struct nvmet_pr *pr,
> + uuid_t *send_hostid)
> +{
> + struct nvmet_pr_registrant *reg;
> + struct nvmet_pr_registrant *tmp;
> +
> + list_for_each_entry_safe(reg, tmp,
> + &pr->registrant_list, entry) {
> + if (!uuid_equal(®->hostid, send_hostid)) {
> + nvmet_pr_send_registration_preempted(pr, ®->hostid);
> + __nvmet_pr_unregister_one(pr, reg);
> + }
> + }
> +}
> +
> +static u16 nvmet_pr_create_new_resv(struct nvmet_pr *pr, u8 rtype,
> + struct nvmet_pr_registrant *reg)
> +{
> + u16 status;
> +
> + status = nvmet_pr_set_rtype_and_holder(pr, rtype, reg);
> + if (!status)
> + nvmet_pr_send_resv_released(pr, ®->hostid);
> + return status;
> +}
> +
> +static u16 nvmet_pr_preempt(struct nvmet_req *req,
> + struct nvmet_pr_registrant *reg,
> + u8 rtype,
> + struct nvmet_pr_acquire_data *d)
> +{
> + struct nvmet_ctrl *ctrl = req->sq->ctrl;
> + struct nvmet_pr *pr = &req->ns->pr;
> + u16 status;
> +
> + if (!pr->holder)
> + return nvmet_pr_unreg_by_prkey(pr, le64_to_cpu(d->prkey),
> + &ctrl->hostid);
> +
> + if (pr->rtype == NVME_PR_WRITE_EXCLUSIVE_ALL_REGS ||
> + pr->rtype == NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS) {
> + if (!le64_to_cpu(d->prkey)) {
> + nvmet_pr_unreg_except_hostid(pr, &ctrl->hostid);
> + return nvmet_pr_create_new_resv(pr, rtype, reg);
> + }
> + return nvmet_pr_unreg_by_prkey(pr, le64_to_cpu(d->prkey),
> + &ctrl->hostid);
> + }
> +
> + if (pr->holder == reg)
> + return nvmet_pr_validate_and_set_rtype(pr, rtype);
> +
> + if (le64_to_cpu(d->prkey) == pr->holder->rkey) {
> + status = nvmet_pr_unreg_by_prkey_except_hostid(pr,
> + le64_to_cpu(d->prkey),
> + &ctrl->hostid);
> + if (status)
> + return status;
> + return nvmet_pr_create_new_resv(pr, rtype, reg);
> + }
> +
> + if (le64_to_cpu(d->prkey))
> + return nvmet_pr_unreg_by_prkey(pr, le64_to_cpu(d->prkey),
> + &ctrl->hostid);
> + return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
> +}
> +
> +static u16 __nvmet_execute_pr_acquire(struct nvmet_req *req,
> + struct nvmet_pr_registrant *reg,
> + u8 acquire_act,
> + u8 rtype,
> + struct nvmet_pr_acquire_data *d)
> +{
> + u16 status;
> +
> + switch (acquire_act) {
> + case NVME_PR_ACQUIRE_ACT_ACQUIRE:
> + status = nvmet_pr_acquire(req, reg, rtype);
> + goto out;
> + case NVME_PR_ACQUIRE_ACT_PREEMPT:
> + status = nvmet_pr_preempt(req, reg, rtype, d);
> + goto inc_gen;
> + case NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT:
> + status = nvmet_pr_preempt(req, reg, rtype, d);
> + goto inc_gen;
> + default:
> + req->error_loc = offsetof(struct nvme_common_command,
> + cdw10);
> + status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
> + goto out;
> + }
> +inc_gen:
> + if (!status)
> + nvmet_pr_inc_generation(&req->ns->pr);
> +out:
> + return status;
> +}
> +
> +static void nvmet_execute_pr_acquire(struct nvmet_req *req)
> +{
> + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
> + bool ignore_key = (bool)((cdw10 >> 3) & 1); /* Ignore existing key, bit 03 */
> + u8 rtype = (u8)((cdw10 >> 8) & 0xff); /* Reservation type, bit 15:08 */
> + u8 acquire_act = cdw10 & 0x07; /* Reservation acquire action, bit 02:00 */
> + struct nvmet_ctrl *ctrl = req->sq->ctrl;
> + struct nvmet_pr_acquire_data *d = NULL;
> + struct nvmet_pr *pr = &req->ns->pr;
> + struct nvmet_pr_registrant *reg;
> + u16 status = NVME_SC_SUCCESS;
> +
> + if (ignore_key) {
> + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
> + goto out;
> + }
> +
> + d = kmalloc(sizeof(*d), GFP_KERNEL);
> + if (!d) {
> + status = NVME_SC_INTERNAL;
> + goto out;
> + }
> +
> + status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
> + if (status)
> + goto free_data;
> +
> + status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + write_lock(&pr->pr_lock);
> + list_for_each_entry(reg, &pr->registrant_list, entry) {
> + if (uuid_equal(®->hostid, &ctrl->hostid) &&
> + reg->rkey == le64_to_cpu(d->crkey)) {
> + status = __nvmet_execute_pr_acquire(req, reg,
> + acquire_act,
> + rtype, d);
> + break;
> + }
> + }
> + write_unlock(&pr->pr_lock);
> +
> +free_data:
> + kfree(d);
> +out:
> + nvmet_req_complete(req, status);
> +}
> +
> +static u16 nvmet_pr_release(struct nvmet_req *req,
> + struct nvmet_pr_registrant *reg,
> + u8 rtype)
> +{
> + struct nvmet_pr *pr = &req->ns->pr;
> + u8 original_rtype = pr->rtype;
> +
> + if (reg != pr->holder || !pr->holder)
> + return 0;
> + if (pr->rtype != rtype)
> + return NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> +
> + nvmet_pr_clean_holder(pr);
> +
> + if (original_rtype != NVME_PR_WRITE_EXCLUSIVE &&
> + original_rtype != NVME_PR_EXCLUSIVE_ACCESS)
> + nvmet_pr_send_resv_released(pr, ®->hostid);
> +
> + return 0;
> +}
> +
> +static void nvmet_pr_clear(struct nvmet_req *req)
> +{
> + struct nvmet_pr *pr = &req->ns->pr;
> + struct nvmet_pr_registrant *reg;
> + struct nvmet_pr_registrant *tmp;
> +
> + list_for_each_entry_safe(reg, tmp, &pr->registrant_list, entry) {
> + list_del(®->entry);
> + if (!uuid_equal(&req->sq->ctrl->hostid, ®->hostid))
> + nvmet_pr_send_resv_preempted(pr, ®->hostid);
> + kfree(reg);
> + }
> + nvmet_pr_clean_holder(pr);
> +
> + nvmet_pr_inc_generation(&req->ns->pr);
> +}
> +
> +static u16 __nvmet_execute_pr_release(struct nvmet_req *req,
> + struct nvmet_pr_registrant *reg,
> + u8 release_act, u8 rtype)
> +{
> + switch (release_act) {
> + case NVME_PR_RELEASE_ACT_RELEASE:
> + return nvmet_pr_release(req, reg, rtype);
> + case NVME_PR_RELEASE_ACT_CLEAR:
> + nvmet_pr_clear(req);
> + return 0;
> + default:
> + req->error_loc = offsetof(struct nvme_common_command,
> + cdw10);
> + return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
> + }
> +}
> +
> +static void nvmet_execute_pr_release(struct nvmet_req *req)
> +{
> + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
> + bool ignore_key = (bool)((cdw10 >> 3) & 1); /* Ignore existing key, bit 03 */
> + u8 rtype = (u8)((cdw10 >> 8) & 0xff); /* Reservation type, bit 15:08 */
> + u8 release_act = cdw10 & 0x07; /* Reservation release action, bit 02:00 */
> + struct nvmet_ctrl *ctrl = req->sq->ctrl;
> + struct nvmet_pr *pr = &req->ns->pr;
> + struct nvmet_pr_release_data *d;
> + struct nvmet_pr_registrant *reg;
> + struct nvmet_pr_registrant *tmp;
> + u16 status;
> +
> + if (ignore_key) {
> + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
> + goto out;
> + }
> +
> + d = kmalloc(sizeof(*d), GFP_KERNEL);
> + if (!d) {
> + status = NVME_SC_INTERNAL;
> + goto out;
> + }
> +
> + status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
> + if (status)
> + goto free_data;
> +
> + status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + write_lock(&pr->pr_lock);
> + list_for_each_entry_safe(reg, tmp,
> + &pr->registrant_list, entry) {
> + if (uuid_equal(®->hostid, &ctrl->hostid) &&
> + reg->rkey == le64_to_cpu(d->crkey)) {
> + status = __nvmet_execute_pr_release(req, reg,
> + release_act, rtype);
> + break;
> + }
> + }
> + write_unlock(&pr->pr_lock);
> +free_data:
> + kfree(d);
> +out:
> + nvmet_req_complete(req, status);
> +}
> +
> +static void nvmet_execute_pr_report(struct nvmet_req *req)
> +{
> + u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11);
> + u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
> + u32 num_bytes = 4 * (cdw10 + 1); /* cdw10 is number of dwords */
> + u8 eds = cdw11 & 1; /* Extended data structure, bit 00 */
> + struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
> + struct nvme_registered_ctrl_ext *ctrl_data;
> + struct nvme_reservation_status_ext *data;
> + struct nvmet_pr *pr = &req->ns->pr;
> + struct nvmet_pr_registrant *reg;
> + struct nvmet_ctrl *ctrl;
> + u16 num_ctrls = 0;
> + u16 status;
> +
> + /* nvmet hostid(uuid_t) is 128 bit. */
> + if (!eds) {
> + req->error_loc = offsetof(struct nvme_common_command,
> + cdw11);
> + status = NVME_SC_HOST_ID_INCONSIST | NVME_SC_DNR;
> + goto out;
> + }
> +
> + if (num_bytes < sizeof(struct nvme_reservation_status_ext)) {
> + req->error_loc = offsetof(struct nvme_common_command,
> + cdw10);
> + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
> + goto out;
> + }
> +
> + mutex_lock(&subsys->lock);
> + read_lock(&pr->pr_lock);
> + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
> + if (nvmet_pr_find_registrant_by_hostid(pr, &ctrl->hostid))
> + num_ctrls++;
> + }
> +
> + num_bytes = min(num_bytes,
> + sizeof(struct nvme_reservation_status_ext) +
> + sizeof(struct nvme_registered_ctrl_ext) * num_ctrls);
> +
> + data = kmalloc(num_bytes, GFP_KERNEL);
> + if (!data) {
> + status = NVME_SC_INTERNAL;
> + goto out_unlock;
> + }
> + memset(data, 0, num_bytes);
> + data->gen = cpu_to_le32(pr->generation);
> + data->rtype = pr->rtype;
> + put_unaligned_le16(num_ctrls, data->regctl);
> + data->ptpls = 0;
> + ctrl_data = data->regctl_eds;
> +
> + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
> + if ((void *)ctrl_data >= (void *)(data + num_bytes))
> + break;
> + reg = nvmet_pr_find_registrant_by_hostid(pr, &ctrl->hostid);
> + if (!reg)
> + continue;
> + ctrl_data->cntlid = cpu_to_le16(ctrl->cntlid);
> + if (pr->rtype == NVME_PR_WRITE_EXCLUSIVE_ALL_REGS ||
> + pr->rtype == NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS)
> + ctrl_data->rcsts = 1;
> + if (pr->holder &&
> + uuid_equal(&ctrl->hostid, &pr->holder->hostid))
> + ctrl_data->rcsts = 1;
> + uuid_copy((uuid_t *)&ctrl_data->hostid, &ctrl->hostid);
> + ctrl_data->rkey = cpu_to_le64(reg->rkey);
> + ctrl_data++;
> + }
> + status = nvmet_copy_to_sgl(req, 0, data, num_bytes);
> +out_unlock:
> + read_unlock(&pr->pr_lock);
> + mutex_unlock(&subsys->lock);
> +out:
> + nvmet_req_complete(req, status);
> +}
> +
> +u16 nvmet_parse_pr_cmd(struct nvmet_req *req)
> +{
> + struct nvme_command *cmd = req->cmd;
> +
> + switch (cmd->common.opcode) {
> + case nvme_cmd_resv_register:
> + req->execute = nvmet_execute_pr_register;
> + break;
> + case nvme_cmd_resv_acquire:
> + req->execute = nvmet_execute_pr_acquire;
> + break;
> + case nvme_cmd_resv_release:
> + req->execute = nvmet_execute_pr_release;
> + break;
> + case nvme_cmd_resv_report:
> + req->execute = nvmet_execute_pr_report;
> + break;
> + default:
> + return 1;
> + }
> + return 0;
> +}
> +
> +static bool nvmet_is_req_write_cmd_group(struct nvmet_req *req)
> +{
> + u8 opcode = req->cmd->common.opcode;
> +
> + if (req->sq->qid) {
> + switch (opcode) {
> + case nvme_cmd_flush:
> + case nvme_cmd_write:
> + case nvme_cmd_write_zeroes:
> + case nvme_cmd_dsm:
> + case nvme_cmd_zone_append:
> + case nvme_cmd_zone_mgmt_send:
> + return true;
> + default:
> + return false;
> + }
> + }
> + return false;
> +}
> +
> +static bool nvmet_is_req_read_cmd_group(struct nvmet_req *req)
> +{
> + u8 opcode = req->cmd->common.opcode;
> +
> + if (req->sq->qid) {
> + switch (opcode) {
> + case nvme_cmd_read:
> + case nvme_cmd_zone_mgmt_recv:
> + return true;
> + default:
> + return false;
> + }
> + }
> + return false;
> +}
> +
> +u16 nvmet_pr_check_cmd_access(struct nvmet_req *req)
> +{
> + struct nvmet_ctrl *ctrl = req->sq->ctrl;
> + struct nvmet_ns *ns = req->ns;
> + struct nvmet_pr *pr = &ns->pr;
> + u16 status = NVME_SC_SUCCESS;
> +
> + read_lock(&pr->pr_lock);
> + if (!pr->holder)
> + goto unlock;
> + if (uuid_equal(&ctrl->hostid, &pr->holder->hostid))
> + goto unlock;
> +
> + /*
> + * The Reservation command group is checked in executing,
> + * allow it here.
> + */
> + switch ((u8)pr->rtype) {
> + case NVME_PR_WRITE_EXCLUSIVE:
> + if (nvmet_is_req_write_cmd_group(req))
> + status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + break;
> + case NVME_PR_EXCLUSIVE_ACCESS:
> + if (nvmet_is_req_read_cmd_group(req) ||
> + nvmet_is_req_write_cmd_group(req))
> + status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + break;
> + case NVME_PR_WRITE_EXCLUSIVE_REG_ONLY:
> + case NVME_PR_WRITE_EXCLUSIVE_ALL_REGS:
> + if ((nvmet_is_req_write_cmd_group(req)) &&
> + !nvmet_pr_find_registrant_by_hostid(pr, &ctrl->hostid))
> + status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + break;
> + case NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY:
> + case NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS:
> + if ((nvmet_is_req_read_cmd_group(req) ||
> + nvmet_is_req_write_cmd_group(req)) &&
> + !nvmet_pr_find_registrant_by_hostid(pr, &ctrl->hostid))
> + status = NVME_SC_RESERVATION_CONFLICT | NVME_SC_DNR;
> + break;
> + default:
> + pr_warn("the reservation type is set wrong, type:%d\n",
> + pr->rtype);
> + break;
> + }
What about impacted admin commands? I'm assuming none of them is
supported by nvmet?
What about the passthru ctrl? Chaitanya, how does this play with
the passthru controller?
> +
> +unlock:
> + read_unlock(&pr->pr_lock);
> + if (status)
> + req->error_loc = offsetof(struct nvme_common_command, opcode);
> + return status;
> +}
> +
> +void nvmet_ctrl_destroy_pr(struct nvmet_ctrl *ctrl)
> +{
> + struct nvmet_pr_log_entry *tmp_log_entry;
> + struct nvmet_pr_log_entry *log_entry;
> + struct nvmet_pr_registrant *reg;
> + struct nvmet_pr_registrant *tmp;
> + struct nvmet_ns *ns;
> + unsigned long idx;
> +
> + mutex_lock(&ctrl->resv_log_lock);
> + list_for_each_entry_safe(log_entry, tmp_log_entry,
> + &ctrl->resv_log_list, entry) {
> + list_del(&log_entry->entry);
> + kfree(log_entry);
> + }
> + mutex_unlock(&ctrl->resv_log_lock);
> +
> + mutex_destroy(&ctrl->resv_log_lock);
> +
> + if (nvmet_is_host_still_connected(&ctrl->hostid, ctrl->subsys))
> + return;
> +
> + xa_for_each(&ctrl->subsys->namespaces, idx, ns) {
> + write_lock(&ns->pr.pr_lock);
> + list_for_each_entry_safe(reg, tmp,
> + &ns->pr.registrant_list, entry) {
> + if (uuid_equal(®->hostid, &ctrl->hostid)) {
> + __nvmet_pr_unregister_one(&ns->pr, reg);
> + break;
> + }
> + }
> + write_unlock(&ns->pr.pr_lock);
> + }
> +}
> +
> +void nvmet_pr_exit_ns(struct nvmet_ns *ns)
> +{
> + struct nvmet_pr_registrant *tmp_reg;
> + struct nvmet_pr_registrant *tmp;
> + struct nvmet_pr *pr = &ns->pr;
> +
> + write_lock(&pr->pr_lock);
> + list_for_each_entry_safe(tmp_reg, tmp, &pr->registrant_list, entry) {
> + list_del(&tmp_reg->entry);
> + kfree(tmp_reg);
> + }
> + write_unlock(&pr->pr_lock);
> +}
> +
> +void nvmet_pr_init_ns(struct nvmet_ns *ns)
> +{
> + ns->pr.holder = NULL;
> + ns->pr.generation = 0;
> + ns->pr.rtype = 0;
> + rwlock_init(&ns->pr.pr_lock);
> + INIT_LIST_HEAD(&ns->pr.registrant_list);
> +}
> diff --git a/include/linux/nvme.h b/include/linux/nvme.h
> index 44325c068b6a..bb5f56ebae50 100644
> --- a/include/linux/nvme.h
> +++ b/include/linux/nvme.h
> @@ -746,6 +746,26 @@ enum {
> NVME_AEN_CFG_DISC_CHANGE = 1 << NVME_AEN_BIT_DISC_CHANGE,
> };
>
> +enum {
> + NVME_AEN_RESV_LOG_PAGE_AVALIABLE = 0x00,
> +};
> +
> +enum {
> + NVME_PR_LOG_EMPTY_LOG_PAGE = 0x00,
> + NVME_PR_LOG_REGISTRATION_PREEMPTED = 0x01,
> + NVME_PR_LOG_RESERVATION_RELEASED = 0x02,
> + NVME_PR_LOG_RESERVATOPM_PREEMPTED = 0x03,
> +};
> +
> +struct nvme_pr_log {
> + __le64 count;
> + __u8 type;
> + __u8 nr_avl_pages;
> + __u8 rsvd1[2];
> + __le32 nsid;
> + __u8 rsvd2[48];
> +};
> +
> struct nvme_lba_range_type {
> __u8 type;
> __u8 attributes;
> @@ -766,6 +786,17 @@ enum {
> NVME_LBART_ATTRIB_HIDE = 1 << 1,
> };
>
> +enum nvme_pr_capabilities {
> + NVME_PR_SUPPORT_PTPL = 1,
> + NVME_PR_SUPPORT_WRITE_EXCLUSIVE = 1 << 1,
> + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS = 1 << 2,
> + NVME_PR_SUPPORT_WRITE_EXCLUSIVE_REG_ONLY = 1 << 3,
> + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_REG_ONLY = 1 << 4,
> + NVME_PR_SUPPORT_WRITE_EXCLUSIVE_ALL_REGS = 1 << 5,
> + NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_ALL_REGS = 1 << 6,
> + NVME_PR_SUPPORT_IEKEY_VER_1_3_DEF = 1 << 7,
> +};
> +
> enum nvme_pr_type {
> NVME_PR_WRITE_EXCLUSIVE = 1,
> NVME_PR_EXCLUSIVE_ACCESS = 2,
> @@ -775,6 +806,23 @@ enum nvme_pr_type {
> NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS = 6,
> };
>
> +enum nvme_pr_register_action {
> + NVME_PR_REGISTER_ACT_REG = 0,
> + NVME_PR_REGISTER_ACT_UNREG = 1,
> + NVME_PR_REGISTER_ACT_REPLACE = 1 << 1,
> +};
> +
> +enum nvme_pr_acquire_action {
> + NVME_PR_ACQUIRE_ACT_ACQUIRE = 0,
> + NVME_PR_ACQUIRE_ACT_PREEMPT = 1,
> + NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT = 1 << 1,
> +};
> +
> +enum nvme_pr_release_action {
> + NVME_PR_RELEASE_ACT_RELEASE = 0,
> + NVME_PR_RELEASE_ACT_CLEAR = 1,
> +};
> +
> enum nvme_eds {
> NVME_EXTENDED_DATA_STRUCT = 0x1,
> };
More information about the Linux-nvme
mailing list