From: Christoph Hellwig <hch@lst.de>
Date: Thu, 9 Nov 2017 13:50:43 +0100
Subject: nvme: track shared namespaces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Patch-mainline: v4.15-rc1
Git-commit: ed754e5deeb17f4e675c84e4b6c640cc7344e498
References: FATE#323952, FATE#322506
Introduce a new struct nvme_ns_head that holds information about an actual
namespace, unlike struct nvme_ns, which only holds the per-controller
namespace information. For private namespaces there is a 1:1 relation of
the two, but for shared namespaces this lets us discover all the paths to
it. For now only the identifiers are moved to the new structure, but most
of the information in struct nvme_ns should eventually move over.
To allow lockless path lookup the list of nvme_ns structures per
nvme_ns_head is protected by SRCU, which requires freeing the nvme_ns
structure through call_srcu.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
drivers/nvme/host/core.c | 220 +++++++++++++++++++++++++++++++++++--------
drivers/nvme/host/lightnvm.c | 14 +-
drivers/nvme/host/nvme.h | 26 ++++-
3 files changed, 210 insertions(+), 50 deletions(-)
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -291,6 +291,22 @@ bool nvme_change_ctrl_state(struct nvme_
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
+static void nvme_free_ns_head(struct kref *ref)
+{
+ struct nvme_ns_head *head =
+ container_of(ref, struct nvme_ns_head, ref);
+
+ ida_simple_remove(&head->subsys->ns_ida, head->instance);
+ list_del_init(&head->entry);
+ cleanup_srcu_struct(&head->srcu);
+ kfree(head);
+}
+
+static void nvme_put_ns_head(struct nvme_ns_head *head)
+{
+ kref_put(&head->ref, nvme_free_ns_head);
+}
+
static void nvme_free_ns(struct kref *kref)
{
struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);
@@ -299,7 +315,7 @@ static void nvme_free_ns(struct kref *kr
nvme_nvm_unregister(ns);
put_disk(ns->disk);
- ida_simple_remove(&ns->ctrl->ns_ida, ns->instance);
+ nvme_put_ns_head(ns->head);
nvme_put_ctrl(ns->ctrl);
kfree(ns);
}
@@ -435,7 +451,7 @@ static inline void nvme_setup_flush(stru
{
memset(cmnd, 0, sizeof(*cmnd));
cmnd->common.opcode = nvme_cmd_flush;
- cmnd->common.nsid = cpu_to_le32(ns->ns_id);
+ cmnd->common.nsid = cpu_to_le32(ns->head->ns_id);
}
static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
@@ -466,7 +482,7 @@ static blk_status_t nvme_setup_discard(s
memset(cmnd, 0, sizeof(*cmnd));
cmnd->dsm.opcode = nvme_cmd_dsm;
- cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
+ cmnd->dsm.nsid = cpu_to_le32(ns->head->ns_id);
cmnd->dsm.nr = cpu_to_le32(segments - 1);
cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
@@ -495,7 +511,7 @@ static inline blk_status_t nvme_setup_rw
memset(cmnd, 0, sizeof(*cmnd));
cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
- cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
+ cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
@@ -987,7 +1003,7 @@ static int nvme_submit_io(struct nvme_ns
memset(&c, 0, sizeof(c));
c.rw.opcode = io.opcode;
c.rw.flags = io.flags;
- c.rw.nsid = cpu_to_le32(ns->ns_id);
+ c.rw.nsid = cpu_to_le32(ns->head->ns_id);
c.rw.slba = cpu_to_le64(io.slba);
c.rw.length = cpu_to_le16(io.nblocks);
c.rw.control = cpu_to_le16(io.control);
@@ -1130,7 +1146,7 @@ static int nvme_ioctl(struct block_devic
switch (cmd) {
case NVME_IOCTL_ID:
force_successful_syscall_return();
- return ns->ns_id;
+ return ns->head->ns_id;
case NVME_IOCTL_ADMIN_CMD:
return nvme_user_cmd(ns->ctrl, NULL, (void __user *)arg);
case NVME_IOCTL_IO_CMD:
@@ -1251,6 +1267,13 @@ static void nvme_report_ns_ids(struct nv
}
}
+static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
+{
+ return !uuid_is_null(&ids->uuid) ||
+ memchr_inv(ids->nguid, 0, sizeof(ids->nguid)) ||
+ memchr_inv(ids->eui64, 0, sizeof(ids->eui64));
+}
+
static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
{
return uuid_equal(&a->uuid, &b->uuid) &&
@@ -1321,7 +1344,7 @@ static int nvme_revalidate_disk(struct g
return -ENODEV;
}
- id = nvme_identify_ns(ctrl, ns->ns_id);
+ id = nvme_identify_ns(ctrl, ns->head->ns_id);
if (!id)
return -ENODEV;
@@ -1331,10 +1354,10 @@ static int nvme_revalidate_disk(struct g
}
__nvme_revalidate_disk(disk, id);
- nvme_report_ns_ids(ctrl, ns->ns_id, id, &ids);
- if (!nvme_ns_ids_equal(&ns->ids, &ids)) {
+ nvme_report_ns_ids(ctrl, ns->head->ns_id, id, &ids);
+ if (!nvme_ns_ids_equal(&ns->head->ids, &ids)) {
dev_err(ctrl->device,
- "identifiers changed for nsid %d\n", ns->ns_id);
+ "identifiers changed for nsid %d\n", ns->head->ns_id);
ret = -ENODEV;
}
@@ -1375,7 +1398,7 @@ static int nvme_pr_command(struct block_
memset(&c, 0, sizeof(c));
c.common.opcode = op;
- c.common.nsid = cpu_to_le32(ns->ns_id);
+ c.common.nsid = cpu_to_le32(ns->head->ns_id);
c.common.cdw10[0] = cpu_to_le32(cdw10);
return nvme_submit_sync_cmd(ns->queue, &c, data, 16);
@@ -1862,6 +1885,7 @@ static void nvme_destroy_subsystem(struc
list_del(&subsys->entry);
mutex_unlock(&nvme_subsystems_lock);
+ ida_destroy(&subsys->ns_ida);
device_del(&subsys->dev);
put_device(&subsys->dev);
}
@@ -1905,6 +1929,7 @@ static int nvme_init_subsystem(struct nv
mutex_init(&subsys->lock);
kref_init(&subsys->ref);
INIT_LIST_HEAD(&subsys->ctrls);
+ INIT_LIST_HEAD(&subsys->nsheads);
nvme_init_subnqn(subsys, ctrl, id);
memcpy(subsys->serial, id->sn, sizeof(subsys->serial));
memcpy(subsys->model, id->mn, sizeof(subsys->model));
@@ -1942,6 +1967,7 @@ static int nvme_init_subsystem(struct nv
"failed to register subsystem device.\n");
goto out_unlock;
}
+ ida_init(&subsys->ns_ida);
list_add_tail(&subsys->entry, &nvme_subsystems);
}
@@ -2273,7 +2299,7 @@ static ssize_t wwid_show(struct device *
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
- struct nvme_ns_ids *ids = &ns->ids;
+ struct nvme_ns_ids *ids = &ns->head->ids;
struct nvme_subsystem *subsys = ns->ctrl->subsys;
int serial_len = sizeof(subsys->serial);
int model_len = sizeof(subsys->model);
@@ -2296,7 +2322,7 @@ static ssize_t wwid_show(struct device *
return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", subsys->vendor_id,
serial_len, subsys->serial, model_len, subsys->model,
- ns->ns_id);
+ ns->head->ns_id);
}
static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL);
@@ -2304,7 +2330,7 @@ static ssize_t nguid_show(struct device
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
- return sprintf(buf, "%pU\n", ns->ids.nguid);
+ return sprintf(buf, "%pU\n", ns->head->ids.nguid);
}
static DEVICE_ATTR(nguid, S_IRUGO, nguid_show, NULL);
@@ -2312,7 +2338,7 @@ static ssize_t uuid_show(struct device *
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
- struct nvme_ns_ids *ids = &ns->ids;
+ struct nvme_ns_ids *ids = &ns->head->ids;
/* For backward compatibility expose the NGUID to userspace if
* we have no UUID set
@@ -2330,7 +2356,7 @@ static ssize_t eui_show(struct device *d
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
- return sprintf(buf, "%8ph\n", ns->ids.eui64);
+ return sprintf(buf, "%8ph\n", ns->head->ids.eui64);
}
static DEVICE_ATTR(eui, S_IRUGO, eui_show, NULL);
@@ -2338,7 +2364,7 @@ static ssize_t nsid_show(struct device *
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
- return sprintf(buf, "%d\n", ns->ns_id);
+ return sprintf(buf, "%d\n", ns->head->ns_id);
}
static DEVICE_ATTR(nsid, S_IRUGO, nsid_show, NULL);
@@ -2356,7 +2382,7 @@ static umode_t nvme_ns_attrs_are_visible
{
struct device *dev = container_of(kobj, struct device, kobj);
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
- struct nvme_ns_ids *ids = &ns->ids;
+ struct nvme_ns_ids *ids = &ns->head->ids;
if (a == &dev_attr_uuid.attr) {
if (uuid_is_null(&ids->uuid) ||
@@ -2508,12 +2534,124 @@ static const struct attribute_group *nvm
NULL,
};
+static struct nvme_ns_head *__nvme_find_ns_head(struct nvme_subsystem *subsys,
+ unsigned nsid)
+{
+ struct nvme_ns_head *h;
+
+ lockdep_assert_held(&subsys->lock);
+
+ list_for_each_entry(h, &subsys->nsheads, entry) {
+ if (h->ns_id == nsid && kref_get_unless_zero(&h->ref))
+ return h;
+ }
+
+ return NULL;
+}
+
+static int __nvme_check_ids(struct nvme_subsystem *subsys,
+ struct nvme_ns_head *new)
+{
+ struct nvme_ns_head *h;
+
+ lockdep_assert_held(&subsys->lock);
+
+ list_for_each_entry(h, &subsys->nsheads, entry) {
+ if (nvme_ns_ids_valid(&new->ids) &&
+ nvme_ns_ids_equal(&new->ids, &h->ids))
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
+ unsigned nsid, struct nvme_id_ns *id)
+{
+ struct nvme_ns_head *head;
+ int ret = -ENOMEM;
+
+ head = kzalloc(sizeof(*head), GFP_KERNEL);
+ if (!head)
+ goto out;
+ ret = ida_simple_get(&ctrl->subsys->ns_ida, 1, 0, GFP_KERNEL);
+ if (ret < 0)
+ goto out_free_head;
+ head->instance = ret;
+ INIT_LIST_HEAD(&head->list);
+ init_srcu_struct(&head->srcu);
+ head->subsys = ctrl->subsys;
+ head->ns_id = nsid;
+ kref_init(&head->ref);
+
+ nvme_report_ns_ids(ctrl, nsid, id, &head->ids);
+
+ ret = __nvme_check_ids(ctrl->subsys, head);
+ if (ret) {
+ dev_err(ctrl->device,
+ "duplicate IDs for nsid %d\n", nsid);
+ goto out_cleanup_srcu;
+ }
+
+ list_add_tail(&head->entry, &ctrl->subsys->nsheads);
+ return head;
+out_cleanup_srcu:
+ cleanup_srcu_struct(&head->srcu);
+ ida_simple_remove(&ctrl->subsys->ns_ida, head->instance);
+out_free_head:
+ kfree(head);
+out:
+ return ERR_PTR(ret);
+}
+
+static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
+ struct nvme_id_ns *id, bool *new)
+{
+ struct nvme_ctrl *ctrl = ns->ctrl;
+ bool is_shared = id->nmic & (1 << 0);
+ struct nvme_ns_head *head = NULL;
+ int ret = 0;
+
+ mutex_lock(&ctrl->subsys->lock);
+ if (is_shared)
+ head = __nvme_find_ns_head(ctrl->subsys, nsid);
+ if (!head) {
+ head = nvme_alloc_ns_head(ctrl, nsid, id);
+ if (IS_ERR(head)) {
+ ret = PTR_ERR(head);
+ goto out_unlock;
+ }
+
+ *new = true;
+ } else {
+ struct nvme_ns_ids ids;
+
+ nvme_report_ns_ids(ctrl, nsid, id, &ids);
+ if (!nvme_ns_ids_equal(&head->ids, &ids)) {
+ dev_err(ctrl->device,
+ "IDs don't match for shared namespace %d\n",
+ nsid);
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
+ *new = false;
+ }
+
+ list_add_tail(&ns->siblings, &head->list);
+ ns->head = head;
+
+out_unlock:
+ mutex_unlock(&ctrl->subsys->lock);
+ return ret;
+}
+
static int ns_cmp(void *priv, struct list_head *a, struct list_head *b)
{
struct nvme_ns *nsa = container_of(a, struct nvme_ns, list);
struct nvme_ns *nsb = container_of(b, struct nvme_ns, list);
- return nsa->ns_id - nsb->ns_id;
+ return nsa->head->ns_id - nsb->head->ns_id;
}
static struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
@@ -2522,13 +2660,13 @@ static struct nvme_ns *nvme_find_get_ns(
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list) {
- if (ns->ns_id == nsid) {
+ if (ns->head->ns_id == nsid) {
if (!kref_get_unless_zero(&ns->kref))
continue;
ret = ns;
break;
}
- if (ns->ns_id > nsid)
+ if (ns->head->ns_id > nsid)
break;
}
mutex_unlock(&ctrl->namespaces_mutex);
@@ -2543,7 +2681,7 @@ static int nvme_setup_streams_ns(struct
if (!ctrl->nr_streams)
return 0;
- ret = nvme_get_stream_params(ctrl, &s, ns->ns_id);
+ ret = nvme_get_stream_params(ctrl, &s, ns->head->ns_id);
if (ret)
return ret;
@@ -2568,32 +2706,26 @@ static void nvme_alloc_ns(struct nvme_ct
struct nvme_id_ns *id;
char disk_name[DISK_NAME_LEN];
int node = dev_to_node(ctrl->dev);
+ bool new = true;
ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
if (!ns)
return;
- ns->instance = ida_simple_get(&ctrl->ns_ida, 1, 0, GFP_KERNEL);
- if (ns->instance < 0)
- goto out_free_ns;
-
ns->queue = blk_mq_init_queue(ctrl->tagset);
if (IS_ERR(ns->queue))
- goto out_release_instance;
+ goto out_free_ns;
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
ns->queue->queuedata = ns;
ns->ctrl = ctrl;
kref_init(&ns->kref);
- ns->ns_id = nsid;
ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */
blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
nvme_set_queue_limits(ctrl, ns->queue);
nvme_setup_streams_ns(ctrl, ns);
- sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->instance);
-
id = nvme_identify_ns(ctrl, nsid);
if (!id)
goto out_free_queue;
@@ -2601,18 +2733,21 @@ static void nvme_alloc_ns(struct nvme_ct
if (id->ncap == 0)
goto out_free_id;
- nvme_report_ns_ids(ctrl, ns->ns_id, id, &ns->ids);
+ if (nvme_init_ns_head(ns, nsid, id, &new))
+ goto out_free_id;
+
+ sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) {
if (nvme_nvm_register(ns, disk_name, node)) {
dev_warn(ctrl->device, "LightNVM init failure\n");
- goto out_free_id;
+ goto out_unlink_ns;
}
}
disk = alloc_disk_node(0, node);
if (!disk)
- goto out_free_id;
+ goto out_unlink_ns;
disk->fops = &nvme_fops;
disk->private_data = ns;
@@ -2640,18 +2775,22 @@ static void nvme_alloc_ns(struct nvme_ct
pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
ns->disk->disk_name);
return;
+ out_unlink_ns:
+ mutex_lock(&ctrl->subsys->lock);
+ list_del_rcu(&ns->siblings);
+ mutex_unlock(&ctrl->subsys->lock);
out_free_id:
kfree(id);
out_free_queue:
blk_cleanup_queue(ns->queue);
- out_release_instance:
- ida_simple_remove(&ctrl->ns_ida, ns->instance);
out_free_ns:
kfree(ns);
}
static void nvme_ns_remove(struct nvme_ns *ns)
{
+ struct nvme_ns_head *head = ns->head;
+
if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
return;
@@ -2666,10 +2805,16 @@ static void nvme_ns_remove(struct nvme_n
blk_cleanup_queue(ns->queue);
}
+ mutex_lock(&ns->ctrl->subsys->lock);
+ if (head)
+ list_del_rcu(&ns->siblings);
+ mutex_unlock(&ns->ctrl->subsys->lock);
+
mutex_lock(&ns->ctrl->namespaces_mutex);
list_del_init(&ns->list);
mutex_unlock(&ns->ctrl->namespaces_mutex);
+ synchronize_srcu(&head->srcu);
nvme_put_ns(ns);
}
@@ -2692,7 +2837,7 @@ static void nvme_remove_invalid_namespac
struct nvme_ns *ns, *next;
list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
- if (ns->ns_id > nsid)
+ if (ns->head->ns_id > nsid)
nvme_ns_remove(ns);
}
}
@@ -2962,7 +3107,6 @@ static void nvme_free_ctrl(struct device
struct nvme_subsystem *subsys = ctrl->subsys;
ida_simple_remove(&nvme_instance_ida, ctrl->instance);
- ida_destroy(&ctrl->ns_ida);
kfree(ctrl->effects);
if (subsys) {
@@ -3023,8 +3167,6 @@ int nvme_init_ctrl(struct nvme_ctrl *ctr
if (ret)
goto out_free_name;
- ida_init(&ctrl->ns_ida);
-
/*
* Initialize latency tolerance controls. The sysfs files won't
* be visible to userspace unless the device actually supports APST.
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -305,7 +305,7 @@ static int nvme_nvm_identity(struct nvm_
int ret;
c.identity.opcode = nvme_nvm_admin_identity;
- c.identity.nsid = cpu_to_le32(ns->ns_id);
+ c.identity.nsid = cpu_to_le32(ns->head->ns_id);
c.identity.chnl_off = 0;
nvme_nvm_id = kmalloc(sizeof(struct nvme_nvm_id), GFP_KERNEL);
@@ -344,7 +344,7 @@ static int nvme_nvm_get_l2p_tbl(struct n
int ret = 0;
c.l2p.opcode = nvme_nvm_admin_get_l2p_tbl;
- c.l2p.nsid = cpu_to_le32(ns->ns_id);
+ c.l2p.nsid = cpu_to_le32(ns->head->ns_id);
entries = kmalloc(len, GFP_KERNEL);
if (!entries)
return -ENOMEM;
@@ -402,7 +402,7 @@ static int nvme_nvm_get_bb_tbl(struct nv
int ret = 0;
c.get_bb.opcode = nvme_nvm_admin_get_bb_tbl;
- c.get_bb.nsid = cpu_to_le32(ns->ns_id);
+ c.get_bb.nsid = cpu_to_le32(ns->head->ns_id);
c.get_bb.spba = cpu_to_le64(ppa.ppa);
bb_tbl = kzalloc(tblsz, GFP_KERNEL);
@@ -452,7 +452,7 @@ static int nvme_nvm_set_bb_tbl(struct nv
int ret = 0;
c.set_bb.opcode = nvme_nvm_admin_set_bb_tbl;
- c.set_bb.nsid = cpu_to_le32(ns->ns_id);
+ c.set_bb.nsid = cpu_to_le32(ns->head->ns_id);
c.set_bb.spba = cpu_to_le64(ppas->ppa);
c.set_bb.nlb = cpu_to_le16(nr_ppas - 1);
c.set_bb.value = type;
@@ -469,7 +469,7 @@ static inline void nvme_nvm_rqtocmd(stru
struct nvme_nvm_command *c)
{
c->ph_rw.opcode = rqd->opcode;
- c->ph_rw.nsid = cpu_to_le32(ns->ns_id);
+ c->ph_rw.nsid = cpu_to_le32(ns->head->ns_id);
c->ph_rw.spba = cpu_to_le64(rqd->ppa_addr.ppa);
c->ph_rw.metadata = cpu_to_le64(rqd->dma_meta_list);
c->ph_rw.control = cpu_to_le16(rqd->flags);
@@ -691,7 +691,7 @@ static int nvme_nvm_submit_vio(struct nv
memset(&c, 0, sizeof(c));
c.ph_rw.opcode = vio.opcode;
- c.ph_rw.nsid = cpu_to_le32(ns->ns_id);
+ c.ph_rw.nsid = cpu_to_le32(ns->head->ns_id);
c.ph_rw.control = cpu_to_le16(vio.control);
c.ph_rw.length = cpu_to_le16(vio.nppas);
@@ -728,7 +728,7 @@ static int nvme_nvm_user_vcmd(struct nvm
memset(&c, 0, sizeof(c));
c.common.opcode = vcmd.opcode;
- c.common.nsid = cpu_to_le32(ns->ns_id);
+ c.common.nsid = cpu_to_le32(ns->head->ns_id);
c.common.cdw2[0] = cpu_to_le32(vcmd.cdw2);
c.common.cdw2[1] = cpu_to_le32(vcmd.cdw3);
/* cdw11-12 */
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -136,7 +136,6 @@ struct nvme_ctrl {
struct device ctrl_device;
struct device *device; /* char device */
struct cdev cdev;
- struct ida ns_ida;
struct work_struct reset_work;
struct work_struct delete_work;
@@ -209,12 +208,14 @@ struct nvme_subsystem {
struct list_head entry;
struct mutex lock;
struct list_head ctrls;
+ struct list_head nsheads;
char subnqn[NVMF_NQN_SIZE];
char serial[20];
char model[40];
char firmware_rev[8];
u8 cmic;
u16 vendor_id;
+ struct ida ns_ida;
};
/*
@@ -226,18 +227,35 @@ struct nvme_ns_ids {
uuid_t uuid;
};
+/*
+ * Anchor structure for namespaces. There is one for each namespace in a
+ * NVMe subsystem that any of our controllers can see, and the namespace
+ * structure for each controller is chained of it. For private namespaces
+ * there is a 1:1 relation to our namespace structures, that is ->list
+ * only ever has a single entry for private namespaces.
+ */
+struct nvme_ns_head {
+ struct list_head list;
+ struct srcu_struct srcu;
+ struct nvme_subsystem *subsys;
+ unsigned ns_id;
+ struct nvme_ns_ids ids;
+ struct list_head entry;
+ struct kref ref;
+ int instance;
+};
+
struct nvme_ns {
struct list_head list;
struct nvme_ctrl *ctrl;
struct request_queue *queue;
struct gendisk *disk;
+ struct list_head siblings;
struct nvm_dev *ndev;
struct kref kref;
- int instance;
+ struct nvme_ns_head *head;
- unsigned ns_id;
- struct nvme_ns_ids ids;
int lba_shift;
u16 ms;
u16 sgs;