summaryrefslogtreecommitdiff
path: root/drivers/nvme
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvme')
-rw-r--r--drivers/nvme/host/core.c170
-rw-r--r--drivers/nvme/host/fabrics.c25
-rw-r--r--drivers/nvme/host/fabrics.h11
-rw-r--r--drivers/nvme/host/lightnvm.c33
-rw-r--r--drivers/nvme/host/nvme.h31
-rw-r--r--drivers/nvme/host/pci.c189
-rw-r--r--drivers/nvme/host/rdma.c27
-rw-r--r--drivers/nvme/host/scsi.c84
-rw-r--r--drivers/nvme/target/admin-cmd.c96
-rw-r--r--drivers/nvme/target/core.c2
-rw-r--r--drivers/nvme/target/discovery.c4
-rw-r--r--drivers/nvme/target/io-cmd.c3
-rw-r--r--drivers/nvme/target/loop.c2
-rw-r--r--drivers/nvme/target/rdma.c2
14 files changed, 382 insertions, 297 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 2feacc70bf61..79e679d12f3b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -156,12 +156,14 @@ static void nvme_free_ns(struct kref *kref)
{
struct nvme_ns *ns = container_of(kref, struct nvme_ns, kref);
- if (ns->type == NVME_NS_LIGHTNVM)
- nvme_nvm_unregister(ns->queue, ns->disk->disk_name);
+ if (ns->ndev)
+ nvme_nvm_unregister(ns);
- spin_lock(&dev_list_lock);
- ns->disk->private_data = NULL;
- spin_unlock(&dev_list_lock);
+ if (ns->disk) {
+ spin_lock(&dev_list_lock);
+ ns->disk->private_data = NULL;
+ spin_unlock(&dev_list_lock);
+ }
put_disk(ns->disk);
ida_simple_remove(&ns->ctrl->ns_ida, ns->instance);
@@ -552,7 +554,7 @@ int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
c.identify.opcode = nvme_admin_identify;
- c.identify.cns = cpu_to_le32(1);
+ c.identify.cns = cpu_to_le32(NVME_ID_CNS_CTRL);
*id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
if (!*id)
@@ -570,7 +572,7 @@ static int nvme_identify_ns_list(struct nvme_ctrl *dev, unsigned nsid, __le32 *n
struct nvme_command c = { };
c.identify.opcode = nvme_admin_identify;
- c.identify.cns = cpu_to_le32(2);
+ c.identify.cns = cpu_to_le32(NVME_ID_CNS_NS_ACTIVE_LIST);
c.identify.nsid = cpu_to_le32(nsid);
return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list, 0x1000);
}
@@ -597,7 +599,7 @@ int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid,
}
int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
- dma_addr_t dma_addr, u32 *result)
+ void *buffer, size_t buflen, u32 *result)
{
struct nvme_command c;
struct nvme_completion cqe;
@@ -606,10 +608,9 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
memset(&c, 0, sizeof(c));
c.features.opcode = nvme_admin_get_features;
c.features.nsid = cpu_to_le32(nsid);
- c.features.dptr.prp1 = cpu_to_le64(dma_addr);
c.features.fid = cpu_to_le32(fid);
- ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
+ ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, buffer, buflen, 0,
NVME_QID_ANY, 0, 0);
if (ret >= 0 && result)
*result = le32_to_cpu(cqe.result);
@@ -617,7 +618,7 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
}
int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
- dma_addr_t dma_addr, u32 *result)
+ void *buffer, size_t buflen, u32 *result)
{
struct nvme_command c;
struct nvme_completion cqe;
@@ -625,12 +626,11 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
memset(&c, 0, sizeof(c));
c.features.opcode = nvme_admin_set_features;
- c.features.dptr.prp1 = cpu_to_le64(dma_addr);
c.features.fid = cpu_to_le32(fid);
c.features.dword11 = cpu_to_le32(dword11);
- ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
- NVME_QID_ANY, 0, 0);
+ ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe,
+ buffer, buflen, 0, NVME_QID_ANY, 0, 0);
if (ret >= 0 && result)
*result = le32_to_cpu(cqe.result);
return ret;
@@ -664,7 +664,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
u32 result;
int status, nr_io_queues;
- status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, 0,
+ status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0,
&result);
if (status < 0)
return status;
@@ -888,42 +888,32 @@ static void nvme_config_discard(struct nvme_ns *ns)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
}
-static int nvme_revalidate_disk(struct gendisk *disk)
+static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
{
- struct nvme_ns *ns = disk->private_data;
- struct nvme_id_ns *id;
- u8 lbaf, pi_type;
- u16 old_ms;
- unsigned short bs;
-
- if (test_bit(NVME_NS_DEAD, &ns->flags)) {
- set_capacity(disk, 0);
- return -ENODEV;
- }
- if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) {
- dev_warn(disk_to_dev(ns->disk), "%s: Identify failure\n",
- __func__);
+ if (nvme_identify_ns(ns->ctrl, ns->ns_id, id)) {
+ dev_warn(ns->ctrl->dev, "%s: Identify failure\n", __func__);
return -ENODEV;
}
- if (id->ncap == 0) {
- kfree(id);
+
+ if ((*id)->ncap == 0) {
+ kfree(*id);
return -ENODEV;
}
- if (nvme_nvm_ns_supported(ns, id) && ns->type != NVME_NS_LIGHTNVM) {
- if (nvme_nvm_register(ns->queue, disk->disk_name)) {
- dev_warn(disk_to_dev(ns->disk),
- "%s: LightNVM init failure\n", __func__);
- kfree(id);
- return -ENODEV;
- }
- ns->type = NVME_NS_LIGHTNVM;
- }
+ if (ns->ctrl->vs >= NVME_VS(1, 1, 0))
+ memcpy(ns->eui, (*id)->eui64, sizeof(ns->eui));
+ if (ns->ctrl->vs >= NVME_VS(1, 2, 0))
+ memcpy(ns->uuid, (*id)->nguid, sizeof(ns->uuid));
+
+ return 0;
+}
- if (ns->ctrl->vs >= NVME_VS(1, 1))
- memcpy(ns->eui, id->eui64, sizeof(ns->eui));
- if (ns->ctrl->vs >= NVME_VS(1, 2))
- memcpy(ns->uuid, id->nguid, sizeof(ns->uuid));
+static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
+{
+ struct nvme_ns *ns = disk->private_data;
+ u8 lbaf, pi_type;
+ u16 old_ms;
+ unsigned short bs;
old_ms = ns->ms;
lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
@@ -962,8 +952,26 @@ static int nvme_revalidate_disk(struct gendisk *disk)
if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
nvme_config_discard(ns);
blk_mq_unfreeze_queue(disk->queue);
+}
+static int nvme_revalidate_disk(struct gendisk *disk)
+{
+ struct nvme_ns *ns = disk->private_data;
+ struct nvme_id_ns *id = NULL;
+ int ret;
+
+ if (test_bit(NVME_NS_DEAD, &ns->flags)) {
+ set_capacity(disk, 0);
+ return -ENODEV;
+ }
+
+ ret = nvme_revalidate_ns(ns, &id);
+ if (ret)
+ return ret;
+
+ __nvme_revalidate_disk(disk, id);
kfree(id);
+
return 0;
}
@@ -1078,6 +1086,8 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled)
int ret;
while ((ret = ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &csts)) == 0) {
+ if (csts == ~0)
+ return -ENODEV;
if ((csts & NVME_CSTS_RDY) == bit)
break;
@@ -1232,7 +1242,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
}
page_shift = NVME_CAP_MPSMIN(cap) + 12;
- if (ctrl->vs >= NVME_VS(1, 1))
+ if (ctrl->vs >= NVME_VS(1, 1, 0))
ctrl->subsystem = NVME_CAP_NSSRC(cap);
ret = nvme_identify_ctrl(ctrl, &id);
@@ -1425,7 +1435,7 @@ static DEVICE_ATTR(rescan_controller, S_IWUSR, NULL, nvme_sysfs_rescan);
static ssize_t wwid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
- struct nvme_ns *ns = dev_to_disk(dev)->private_data;
+ struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
struct nvme_ctrl *ctrl = ns->ctrl;
int serial_len = sizeof(ctrl->serial);
int model_len = sizeof(ctrl->model);
@@ -1449,7 +1459,7 @@ static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL);
static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
- struct nvme_ns *ns = dev_to_disk(dev)->private_data;
+ struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
return sprintf(buf, "%pU\n", ns->uuid);
}
static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL);
@@ -1457,7 +1467,7 @@ static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL);
static ssize_t eui_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
- struct nvme_ns *ns = dev_to_disk(dev)->private_data;
+ struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
return sprintf(buf, "%8phd\n", ns->eui);
}
static DEVICE_ATTR(eui, S_IRUGO, eui_show, NULL);
@@ -1465,7 +1475,7 @@ static DEVICE_ATTR(eui, S_IRUGO, eui_show, NULL);
static ssize_t nsid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
- struct nvme_ns *ns = dev_to_disk(dev)->private_data;
+ struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
return sprintf(buf, "%d\n", ns->ns_id);
}
static DEVICE_ATTR(nsid, S_IRUGO, nsid_show, NULL);
@@ -1482,7 +1492,7 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
struct attribute *a, int n)
{
struct device *dev = container_of(kobj, struct device, kobj);
- struct nvme_ns *ns = dev_to_disk(dev)->private_data;
+ struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
if (a == &dev_attr_uuid.attr) {
if (!memchr_inv(ns->uuid, 0, sizeof(ns->uuid)))
@@ -1642,6 +1652,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
struct nvme_ns *ns;
struct gendisk *disk;
+ struct nvme_id_ns *id;
+ char disk_name[DISK_NAME_LEN];
int node = dev_to_node(ctrl->dev);
ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
@@ -1659,34 +1671,49 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
ns->queue->queuedata = ns;
ns->ctrl = ctrl;
- disk = alloc_disk_node(0, node);
- if (!disk)
- goto out_free_queue;
-
kref_init(&ns->kref);
ns->ns_id = nsid;
- ns->disk = disk;
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);
- disk->fops = &nvme_fops;
- disk->private_data = ns;
- disk->queue = ns->queue;
- disk->flags = GENHD_FL_EXT_DEVT;
- sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, ns->instance);
+ sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->instance);
+
+ if (nvme_revalidate_ns(ns, &id))
+ goto out_free_queue;
+
+ if (nvme_nvm_ns_supported(ns, id)) {
+ if (nvme_nvm_register(ns, disk_name, node,
+ &nvme_ns_attr_group)) {
+ dev_warn(ctrl->dev, "%s: LightNVM init failure\n",
+ __func__);
+ goto out_free_id;
+ }
+ } else {
+ disk = alloc_disk_node(0, node);
+ if (!disk)
+ goto out_free_id;
- if (nvme_revalidate_disk(ns->disk))
- goto out_free_disk;
+ disk->fops = &nvme_fops;
+ disk->private_data = ns;
+ disk->queue = ns->queue;
+ disk->flags = GENHD_FL_EXT_DEVT;
+ memcpy(disk->disk_name, disk_name, DISK_NAME_LEN);
+ ns->disk = disk;
+
+ __nvme_revalidate_disk(disk, id);
+ }
mutex_lock(&ctrl->namespaces_mutex);
list_add_tail(&ns->list, &ctrl->namespaces);
mutex_unlock(&ctrl->namespaces_mutex);
kref_get(&ctrl->kref);
- if (ns->type == NVME_NS_LIGHTNVM)
+
+ kfree(id);
+
+ if (ns->ndev)
return;
device_add_disk(ctrl->device, ns->disk);
@@ -1695,8 +1722,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
pr_warn("%s: failed to create sysfs group for identification\n",
ns->disk->disk_name);
return;
- out_free_disk:
- kfree(disk);
+ out_free_id:
+ kfree(id);
out_free_queue:
blk_cleanup_queue(ns->queue);
out_release_instance:
@@ -1710,7 +1737,7 @@ static void nvme_ns_remove(struct nvme_ns *ns)
if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
return;
- if (ns->disk->flags & GENHD_FL_UP) {
+ if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
if (blk_get_integrity(ns->disk))
blk_integrity_unregister(ns->disk);
sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
@@ -1733,7 +1760,7 @@ static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
ns = nvme_find_get_ns(ctrl, nsid);
if (ns) {
- if (revalidate_disk(ns->disk))
+ if (ns->disk && revalidate_disk(ns->disk))
nvme_ns_remove(ns);
nvme_put_ns(ns);
} else
@@ -1815,7 +1842,7 @@ static void nvme_scan_work(struct work_struct *work)
return;
nn = le32_to_cpu(id->nn);
- if (ctrl->vs >= NVME_VS(1, 1) &&
+ if (ctrl->vs >= NVME_VS(1, 1, 0) &&
!(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
if (!nvme_scan_ns_list(ctrl, nn))
goto done;
@@ -1826,9 +1853,6 @@ static void nvme_scan_work(struct work_struct *work)
list_sort(NULL, &ctrl->namespaces, ns_cmp);
mutex_unlock(&ctrl->namespaces_mutex);
kfree(id);
-
- if (ctrl->ops->post_scan)
- ctrl->ops->post_scan(ctrl);
}
void nvme_queue_scan(struct nvme_ctrl *ctrl)
@@ -2038,7 +2062,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
* Revalidating a dead namespace sets capacity to 0. This will
* end buffered writers dirtying pages that can't be synced.
*/
- if (!test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+ if (ns->disk && !test_and_set_bit(NVME_NS_DEAD, &ns->flags))
revalidate_disk(ns->disk);
blk_set_queue_dying(ns->queue);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 4eff49174466..5a3f008d3480 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -111,8 +111,19 @@ static void nvmf_host_put(struct nvmf_host *host)
*/
int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
{
- return snprintf(buf, size, "traddr=%s,trsvcid=%s\n",
- ctrl->opts->traddr, ctrl->opts->trsvcid);
+ int len = 0;
+
+ if (ctrl->opts->mask & NVMF_OPT_TRADDR)
+ len += snprintf(buf, size, "traddr=%s", ctrl->opts->traddr);
+ if (ctrl->opts->mask & NVMF_OPT_TRSVCID)
+ len += snprintf(buf + len, size - len, "%strsvcid=%s",
+ (len) ? "," : "", ctrl->opts->trsvcid);
+ if (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)
+ len += snprintf(buf + len, size - len, "%shost_traddr=%s",
+ (len) ? "," : "", ctrl->opts->host_traddr);
+ len += snprintf(buf + len, size - len, "\n");
+
+ return len;
}
EXPORT_SYMBOL_GPL(nvmf_get_address);
@@ -519,6 +530,7 @@ static const match_table_t opt_tokens = {
{ NVMF_OPT_RECONNECT_DELAY, "reconnect_delay=%d" },
{ NVMF_OPT_KATO, "keep_alive_tmo=%d" },
{ NVMF_OPT_HOSTNQN, "hostnqn=%s" },
+ { NVMF_OPT_HOST_TRADDR, "host_traddr=%s" },
{ NVMF_OPT_ERR, NULL }
};
@@ -675,6 +687,14 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
}
opts->reconnect_delay = token;
break;
+ case NVMF_OPT_HOST_TRADDR:
+ p = match_strdup(args);
+ if (!p) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ opts->host_traddr = p;
+ break;
default:
pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
p);
@@ -741,6 +761,7 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts)
kfree(opts->traddr);
kfree(opts->trsvcid);
kfree(opts->subsysnqn);
+ kfree(opts->host_traddr);
kfree(opts);
}
EXPORT_SYMBOL_GPL(nvmf_free_options);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 46e460aee52d..924145c979f1 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -52,6 +52,7 @@ enum {
NVMF_OPT_KATO = 1 << 7,
NVMF_OPT_HOSTNQN = 1 << 8,
NVMF_OPT_RECONNECT_DELAY = 1 << 9,
+ NVMF_OPT_HOST_TRADDR = 1 << 10,
};
/**
@@ -64,9 +65,12 @@ enum {
* being added.
* @subsysnqn: Hold the fully qualified NQN subystem name (format defined
* in the NVMe specification, "NVMe Qualified Names").
- * @traddr: network address that will be used by the host to communicate
- * to the added NVMe controller.
- * @trsvcid: network port used for host-controller communication.
+ * @traddr: The transport-specific TRADDR field for a port on the
+ * subsystem which is adding a controller.
+ * @trsvcid: The transport-specific TRSVCID field for a port on the
+ * subsystem which is adding a controller.
+ * @host_traddr: A transport-specific field identifying the NVME host port
+ * to use for the connection to the controller.
* @queue_size: Number of IO queue elements.
* @nr_io_queues: Number of controller IO queues that will be established.
* @reconnect_delay: Time between two consecutive reconnect attempts.
@@ -80,6 +84,7 @@ struct nvmf_ctrl_options {
char *subsysnqn;
char *traddr;
char *trsvcid;
+ char *host_traddr;
size_t queue_size;
unsigned int nr_io_queues;
unsigned int reconnect_delay;
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 63f483daf930..f5e3011e31fc 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -475,7 +475,7 @@ static inline void nvme_nvm_rqtocmd(struct request *rq, struct nvm_rq *rqd,
if (rqd->opcode == NVM_OP_HBWRITE || rqd->opcode == NVM_OP_HBREAD)
c->hb_rw.slba = cpu_to_le64(nvme_block_nr(ns,
- rqd->bio->bi_iter.bi_sector));
+ rqd->bio->bi_iter.bi_sector));
}
static void nvme_nvm_end_io(struct request *rq, int error)
@@ -592,14 +592,37 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = {
.max_phys_sect = 64,
};
-int nvme_nvm_register(struct request_queue *q, char *disk_name)
+int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node,
+ const struct attribute_group *attrs)
{
- return nvm_register(q, disk_name, &nvme_nvm_dev_ops);
+ struct request_queue *q = ns->queue;
+ struct nvm_dev *dev;
+ int ret;
+
+ dev = nvm_alloc_dev(node);
+ if (!dev)
+ return -ENOMEM;
+
+ dev->q = q;
+ memcpy(dev->name, disk_name, DISK_NAME_LEN);
+ dev->ops = &nvme_nvm_dev_ops;
+ dev->parent_dev = ns->ctrl->device;
+ dev->private_data = ns;
+ ns->ndev = dev;
+
+ ret = nvm_register(dev);
+
+ ns->lba_shift = ilog2(dev->sec_size) - 9;
+
+ if (sysfs_create_group(&dev->dev.kobj, attrs))
+ pr_warn("%s: failed to create sysfs group for identification\n",
+ disk_name);
+ return ret;
}
-void nvme_nvm_unregister(struct request_queue *q, char *disk_name)
+void nvme_nvm_unregister(struct nvme_ns *ns)
{
- nvm_unregister(disk_name);
+ nvm_unregister(ns->ndev);
}
/* move to shared place when used in multiple places. */
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ab18b78102bf..d47f5a5d18c7 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -18,6 +18,7 @@
#include <linux/pci.h>
#include <linux/kref.h>
#include <linux/blk-mq.h>
+#include <linux/lightnvm.h>
enum {
/*
@@ -154,6 +155,7 @@ struct nvme_ns {
struct nvme_ctrl *ctrl;
struct request_queue *queue;
struct gendisk *disk;
+ struct nvm_dev *ndev;
struct kref kref;
int instance;
@@ -165,7 +167,6 @@ struct nvme_ns {
u16 ms;
bool ext;
u8 pi_type;
- int type;
unsigned long flags;
#define NVME_NS_REMOVING 0
@@ -184,7 +185,6 @@ struct nvme_ctrl_ops {
int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val);
int (*reset_ctrl)(struct nvme_ctrl *ctrl);
void (*free_ctrl)(struct nvme_ctrl *ctrl);
- void (*post_scan)(struct nvme_ctrl *ctrl);
void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx);
int (*delete_ctrl)(struct nvme_ctrl *ctrl);
const char *(*get_subsysnqn)(struct nvme_ctrl *ctrl);
@@ -292,9 +292,9 @@ int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid,
struct nvme_id_ns **id);
int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log);
int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
- dma_addr_t dma_addr, u32 *result);
+ void *buffer, size_t buflen, u32 *result);
int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
- dma_addr_t dma_addr, u32 *result);
+ void *buffer, size_t buflen, u32 *result);
int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
void nvme_start_keep_alive(struct nvme_ctrl *ctrl);
void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
@@ -307,20 +307,35 @@ int nvme_sg_get_version_num(int __user *ip);
#ifdef CONFIG_NVM
int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id);
-int nvme_nvm_register(struct request_queue *q, char *disk_name);
-void nvme_nvm_unregister(struct request_queue *q, char *disk_name);
+int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node,
+ const struct attribute_group *attrs);
+void nvme_nvm_unregister(struct nvme_ns *ns);
+
+static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
+{
+ if (dev->type->devnode)
+ return dev_to_disk(dev)->private_data;
+
+ return (container_of(dev, struct nvm_dev, dev))->private_data;
+}
#else
-static inline int nvme_nvm_register(struct request_queue *q, char *disk_name)
+static inline int nvme_nvm_register(struct nvme_ns *ns, char *disk_name,
+ int node,
+ const struct attribute_group *attrs)
{
return 0;
}
-static inline void nvme_nvm_unregister(struct request_queue *q, char *disk_name) {};
+static inline void nvme_nvm_unregister(struct nvme_ns *ns) {};
static inline int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *id)
{
return 0;
}
+static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
+{
+ return dev_to_disk(dev)->private_data;
+}
#endif /* CONFIG_NVM */
int __init nvme_core_init(void);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 60f7eab11865..0248d0e21fee 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -16,6 +16,7 @@
#include <linux/bitops.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
+#include <linux/blk-mq-pci.h>
#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/errno.h>
@@ -88,7 +89,6 @@ struct nvme_dev {
unsigned max_qid;
int q_depth;
u32 db_stride;
- struct msix_entry *entry;
void __iomem *bar;
struct work_struct reset_work;
struct work_struct remove_work;
@@ -99,6 +99,7 @@ struct nvme_dev {
dma_addr_t cmb_dma_addr;
u64 cmb_size;
u32 cmbsz;
+ u32 cmbloc;
struct nvme_ctrl ctrl;
struct completion ioq_wait;
};
@@ -201,6 +202,11 @@ static unsigned int nvme_cmd_size(struct nvme_dev *dev)
nvme_iod_alloc_size(dev, NVME_INT_BYTES(dev), NVME_INT_PAGES);
}
+static int nvmeq_irq(struct nvme_queue *nvmeq)
+{
+ return pci_irq_vector(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector);
+}
+
static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
unsigned int hctx_idx)
{
@@ -263,6 +269,13 @@ static int nvme_init_request(void *data, struct request *req,
return 0;
}
+static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
+{
+ struct nvme_dev *dev = set->driver_data;
+
+ return blk_mq_pci_map_queues(set, to_pci_dev(dev->dev));
+}
+
/**
* __nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
* @nvmeq: The queue to use
@@ -503,7 +516,8 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req,
goto out;
ret = BLK_MQ_RQ_QUEUE_BUSY;
- if (!dma_map_sg(dev->dev, iod->sg, iod->nents, dma_dir))
+ if (!dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, dma_dir,
+ DMA_ATTR_NO_WARN))
goto out;
if (!nvme_setup_prps(dev, req, size))
@@ -880,7 +894,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
"I/O %d QID %d timeout, reset controller\n",
req->tag, nvmeq->qid);
nvme_dev_disable(dev, false);
- queue_work(nvme_workq, &dev->reset_work);
+ nvme_reset(dev);
/*
* Mark the request as handled, since the inline shutdown
@@ -960,7 +974,7 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
spin_unlock_irq(&nvmeq->q_lock);
return 1;
}
- vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
+ vector = nvmeq_irq(nvmeq);
nvmeq->dev->online_queues--;
nvmeq->cq_vector = -1;
spin_unlock_irq(&nvmeq->q_lock);
@@ -968,7 +982,6 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
blk_mq_stop_hw_queues(nvmeq->dev->ctrl.admin_q);
- irq_set_affinity_hint(vector, NULL);
free_irq(vector, nvmeq);
return 0;
@@ -1075,15 +1088,14 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
return NULL;
}
-static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
- const char *name)
+static int queue_request_irq(struct nvme_queue *nvmeq)
{
if (use_threaded_interrupts)
- return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector,
- nvme_irq_check, nvme_irq, IRQF_SHARED,
- name, nvmeq);
- return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq,
- IRQF_SHARED, name, nvmeq);
+ return request_threaded_irq(nvmeq_irq(nvmeq), nvme_irq_check,
+ nvme_irq, IRQF_SHARED, nvmeq->irqname, nvmeq);
+ else
+ return request_irq(nvmeq_irq(nvmeq), nvme_irq, IRQF_SHARED,
+ nvmeq->irqname, nvmeq);
}
static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
@@ -1114,7 +1126,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
if (result < 0)
goto release_cq;
- result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+ result = queue_request_irq(nvmeq);
if (result < 0)
goto release_sq;
@@ -1131,7 +1143,6 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
static struct blk_mq_ops nvme_mq_admin_ops = {
.queue_rq = nvme_queue_rq,
.complete = nvme_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_hctx = nvme_admin_init_hctx,
.exit_hctx = nvme_admin_exit_hctx,
.init_request = nvme_admin_init_request,
@@ -1141,9 +1152,9 @@ static struct blk_mq_ops nvme_mq_admin_ops = {
static struct blk_mq_ops nvme_mq_ops = {
.queue_rq = nvme_queue_rq,
.complete = nvme_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_hctx = nvme_init_hctx,
.init_request = nvme_init_request,
+ .map_queues = nvme_pci_map_queues,
.timeout = nvme_timeout,
.poll = nvme_poll,
};
@@ -1204,7 +1215,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
u64 cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
struct nvme_queue *nvmeq;
- dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1) ?
+ dev->subsystem = readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 1, 0) ?
NVME_CAP_NSSRC(cap) : 0;
if (dev->subsystem &&
@@ -1234,7 +1245,7 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
goto free_nvmeq;
nvmeq->cq_vector = 0;
- result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
+ result = queue_request_irq(nvmeq);
if (result) {
nvmeq->cq_vector = -1;
goto free_nvmeq;
@@ -1281,7 +1292,7 @@ static void nvme_watchdog_timer(unsigned long data)
/* Skip controllers under certain specific conditions. */
if (nvme_should_reset(dev, csts)) {
- if (queue_work(nvme_workq, &dev->reset_work))
+ if (!nvme_reset(dev))
dev_warn(dev->dev,
"Failed status: 0x%x, reset controller.\n",
csts);
@@ -1321,28 +1332,37 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
return ret >= 0 ? 0 : ret;
}
+static ssize_t nvme_cmb_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct nvme_dev *ndev = to_nvme_dev(dev_get_drvdata(dev));
+
+ return snprintf(buf, PAGE_SIZE, "cmbloc : x%08x\ncmbsz : x%08x\n",
+ ndev->cmbloc, ndev->cmbsz);
+}
+static DEVICE_ATTR(cmb, S_IRUGO, nvme_cmb_show, NULL);
+
static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
{
u64 szu, size, offset;
- u32 cmbloc;
resource_size_t bar_size;
struct pci_dev *pdev = to_pci_dev(dev->dev);
void __iomem *cmb;
dma_addr_t dma_addr;
- if (!use_cmb_sqes)
- return NULL;
-
dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
if (!(NVME_CMB_SZ(dev->cmbsz)))
return NULL;
+ dev->cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
- cmbloc = readl(dev->bar + NVME_REG_CMBLOC);
+ if (!use_cmb_sqes)
+ return NULL;
szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
size = szu * NVME_CMB_SZ(dev->cmbsz);
- offset = szu * NVME_CMB_OFST(cmbloc);
- bar_size = pci_resource_len(pdev, NVME_CMB_BIR(cmbloc));
+ offset = szu * NVME_CMB_OFST(dev->cmbloc);
+ bar_size = pci_resource_len(pdev, NVME_CMB_BIR(dev->cmbloc));
if (offset > bar_size)
return NULL;
@@ -1355,7 +1375,7 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
if (size > bar_size - offset)
size = bar_size - offset;
- dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(cmbloc)) + offset;
+ dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(dev->cmbloc)) + offset;
cmb = ioremap_wc(dma_addr, size);
if (!cmb)
return NULL;
@@ -1382,7 +1402,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
{
struct nvme_queue *adminq = dev->queues[0];
struct pci_dev *pdev = to_pci_dev(dev->dev);
- int result, i, vecs, nr_io_queues, size;
+ int result, nr_io_queues, size;
nr_io_queues = num_online_cpus();
result = nvme_set_queue_count(&dev->ctrl, &nr_io_queues);
@@ -1417,29 +1437,18 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
}
/* Deregister the admin queue's interrupt */
- free_irq(dev->entry[0].vector, adminq);
+ free_irq(pci_irq_vector(pdev, 0), adminq);
/*
* If we enable msix early due to not intx, disable it again before
* setting up the full range we need.
*/
- if (pdev->msi_enabled)
- pci_disable_msi(pdev);
- else if (pdev->msix_enabled)
- pci_disable_msix(pdev);
-
- for (i = 0; i < nr_io_queues; i++)
- dev->entry[i].entry = i;
- vecs = pci_enable_msix_range(pdev, dev->entry, 1, nr_io_queues);
- if (vecs < 0) {
- vecs = pci_enable_msi_range(pdev, 1, min(nr_io_queues, 32));
- if (vecs < 0) {
- vecs = 1;
- } else {
- for (i = 0; i < vecs; i++)
- dev->entry[i].vector = i + pdev->irq;
- }
- }
+ pci_free_irq_vectors(pdev);
+ nr_io_queues = pci_alloc_irq_vectors(pdev, 1, nr_io_queues,
+ PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY);
+ if (nr_io_queues <= 0)
+ return -EIO;
+ dev->max_qid = nr_io_queues;
/*
* Should investigate if there's a performance win from allocating
@@ -1447,10 +1456,8 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
* path to scale better, even if the receive path is limited by the
* number of interrupts.
*/
- nr_io_queues = vecs;
- dev->max_qid = nr_io_queues;
- result = queue_request_irq(dev, adminq, adminq->irqname);
+ result = queue_request_irq(adminq);
if (result) {
adminq->cq_vector = -1;
goto free_queues;
@@ -1462,23 +1469,6 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
return result;
}
-static void nvme_pci_post_scan(struct nvme_ctrl *ctrl)
-{
- struct nvme_dev *dev = to_nvme_dev(ctrl);
- struct nvme_queue *nvmeq;
- int i;
-
- for (i = 0; i < dev->online_queues; i++) {
- nvmeq = dev->queues[i];
-
- if (!nvmeq->tags || !(*nvmeq->tags))
- continue;
-
- irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
- blk_mq_tags_cpumask(*nvmeq->tags));
- }
-}
-
static void nvme_del_queue_end(struct request *req, int error)
{
struct nvme_queue *nvmeq = req->end_io_data;
@@ -1531,9 +1521,9 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode)
return 0;
}
-static void nvme_disable_io_queues(struct nvme_dev *dev)
+static void nvme_disable_io_queues(struct nvme_dev *dev, int queues)
{
- int pass, queues = dev->online_queues - 1;
+ int pass;
unsigned long timeout;
u8 opcode = nvme_admin_delete_sq;
@@ -1615,15 +1605,9 @@ static int nvme_pci_enable(struct nvme_dev *dev)
* interrupts. Pre-enable a single MSIX or MSI vec for setup. We'll
* adjust this later.
*/
- if (pci_enable_msix(pdev, dev->entry, 1)) {
- pci_enable_msi(pdev);
- dev->entry[0].vector = pdev->irq;
- }
-
- if (!dev->entry[0].vector) {
- result = -ENODEV;
- goto disable;
- }
+ result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
+ if (result < 0)
+ return result;
cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
@@ -1642,9 +1626,25 @@ static int nvme_pci_enable(struct nvme_dev *dev)
dev->q_depth);
}
- if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2))
+ /*
+ * CMBs can currently only exist on >=1.2 PCIe devices. We only
+ * populate sysfs if a CMB is implemented. Note that we add the
+ * CMB attribute to the nvme_ctrl kobj which removes the need to remove
+ * it on exit. Since nvme_dev_attrs_group has no name we can pass
+ * NULL as final argument to sysfs_add_file_to_group.
+ */
+
+ if (readl(dev->bar + NVME_REG_VS) >= NVME_VS(1, 2, 0)) {
dev->cmb = nvme_map_cmb(dev);
+ if (dev->cmbsz) {
+ if (sysfs_add_file_to_group(&dev->ctrl.device->kobj,
+ &dev_attr_cmb.attr, NULL))
+ dev_warn(dev->dev,
+ "failed to add sysfs attribute for CMB\n");
+ }
+ }
+
pci_enable_pcie_error_reporting(pdev);
pci_save_state(pdev);
return 0;
@@ -1665,10 +1665,7 @@ static void nvme_pci_disable(struct nvme_dev *dev)
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
- if (pdev->msi_enabled)
- pci_disable_msi(pdev);
- else if (pdev->msix_enabled)
- pci_disable_msix(pdev);
+ pci_free_irq_vectors(pdev);
if (pci_is_enabled(pdev)) {
pci_disable_pcie_error_reporting(pdev);
@@ -1678,7 +1675,7 @@ static void nvme_pci_disable(struct nvme_dev *dev)
static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
{
- int i;
+ int i, queues;
u32 csts = -1;
del_timer_sync(&dev->watchdog_timer);
@@ -1689,6 +1686,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
csts = readl(dev->bar + NVME_REG_CSTS);
}
+ queues = dev->online_queues - 1;
for (i = dev->queue_count - 1; i > 0; i--)
nvme_suspend_queue(dev->queues[i]);
@@ -1700,7 +1698,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
if (dev->queue_count)
nvme_suspend_queue(dev->queues[0]);
} else {
- nvme_disable_io_queues(dev);
+ nvme_disable_io_queues(dev, queues);
nvme_disable_admin_queue(dev, shutdown);
}
nvme_pci_disable(dev);
@@ -1743,7 +1741,6 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
if (dev->ctrl.admin_q)
blk_put_queue(dev->ctrl.admin_q);
kfree(dev->queues);
- kfree(dev->entry);
kfree(dev);
}
@@ -1848,11 +1845,10 @@ static int nvme_reset(struct nvme_dev *dev)
{
if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q))
return -ENODEV;
-
+ if (work_busy(&dev->reset_work))
+ return -ENODEV;
if (!queue_work(nvme_workq, &dev->reset_work))
return -EBUSY;
-
- flush_work(&dev->reset_work);
return 0;
}
@@ -1876,7 +1872,12 @@ static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
static int nvme_pci_reset_ctrl(struct nvme_ctrl *ctrl)
{
- return nvme_reset(to_nvme_dev(ctrl));
+ struct nvme_dev *dev = to_nvme_dev(ctrl);
+ int ret = nvme_reset(dev);
+
+ if (!ret)
+ flush_work(&dev->reset_work);
+ return ret;
}
static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
@@ -1887,7 +1888,6 @@ static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
.reg_read64 = nvme_pci_reg_read64,
.reset_ctrl = nvme_pci_reset_ctrl,
.free_ctrl = nvme_pci_free_ctrl,
- .post_scan = nvme_pci_post_scan,
.submit_async_event = nvme_pci_submit_async_event,
};
@@ -1920,10 +1920,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
if (!dev)
return -ENOMEM;
- dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev->entry),
- GFP_KERNEL, node);
- if (!dev->entry)
- goto free;
dev->queues = kzalloc_node((num_possible_cpus() + 1) * sizeof(void *),
GFP_KERNEL, node);
if (!dev->queues)
@@ -1964,7 +1960,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
nvme_dev_unmap(dev);
free:
kfree(dev->queues);
- kfree(dev->entry);
kfree(dev);
return result;
}
@@ -1976,7 +1971,7 @@ static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
if (prepare)
nvme_dev_disable(dev, false);
else
- queue_work(nvme_workq, &dev->reset_work);
+ nvme_reset(dev);
}
static void nvme_shutdown(struct pci_dev *pdev)
@@ -2045,7 +2040,7 @@ static int nvme_resume(struct device *dev)
struct pci_dev *pdev = to_pci_dev(dev);
struct nvme_dev *ndev = pci_get_drvdata(pdev);
- queue_work(nvme_workq, &ndev->reset_work);
+ nvme_reset(ndev);
return 0;
}
#endif
@@ -2084,7 +2079,7 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
dev_info(dev->ctrl.device, "restart after slot reset\n");
pci_restore_state(pdev);
- queue_work(nvme_workq, &dev->reset_work);
+ nvme_reset(dev);
return PCI_ERS_RESULT_RECOVERED;
}
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index fbdb2267e460..5a8388177959 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -54,7 +54,6 @@
struct nvme_rdma_device {
struct ib_device *dev;
struct ib_pd *pd;
- struct ib_mr *mr;
struct kref ref;
struct list_head entry;
};
@@ -408,10 +407,7 @@ static void nvme_rdma_free_dev(struct kref *ref)
list_del(&ndev->entry);
mutex_unlock(&device_list_mutex);
- if (!register_always)
- ib_dereg_mr(ndev->mr);
ib_dealloc_pd(ndev->pd);
-
kfree(ndev);
}
@@ -444,24 +440,16 @@ nvme_rdma_find_get_device(struct rdma_cm_id *cm_id)
ndev->dev = cm_id->device;
kref_init(&ndev->ref);
- ndev->pd = ib_alloc_pd(ndev->dev);
+ ndev->pd = ib_alloc_pd(ndev->dev,
+ register_always ? 0 : IB_PD_UNSAFE_GLOBAL_RKEY);
if (IS_ERR(ndev->pd))
goto out_free_dev;
- if (!register_always) {
- ndev->mr = ib_get_dma_mr(ndev->pd,
- IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_REMOTE_READ |
- IB_ACCESS_REMOTE_WRITE);
- if (IS_ERR(ndev->mr))
- goto out_free_pd;
- }
-
if (!(ndev->dev->attrs.device_cap_flags &
IB_DEVICE_MEM_MGT_EXTENSIONS)) {
dev_err(&ndev->dev->dev,
"Memory registrations not supported.\n");
- goto out_free_mr;
+ goto out_free_pd;
}
list_add(&ndev->entry, &device_list);
@@ -469,9 +457,6 @@ out_unlock:
mutex_unlock(&device_list_mutex);
return ndev;
-out_free_mr:
- if (!register_always)
- ib_dereg_mr(ndev->mr);
out_free_pd:
ib_dealloc_pd(ndev->pd);
out_free_dev:
@@ -915,7 +900,7 @@ static int nvme_rdma_map_sg_single(struct nvme_rdma_queue *queue,
sg->addr = cpu_to_le64(sg_dma_address(req->sg_table.sgl));
put_unaligned_le24(sg_dma_len(req->sg_table.sgl), sg->length);
- put_unaligned_le32(queue->device->mr->rkey, sg->key);
+ put_unaligned_le32(queue->device->pd->unsafe_global_rkey, sg->key);
sg->type = NVME_KEY_SGL_FMT_DATA_DESC << 4;
return 0;
}
@@ -1000,7 +985,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
nvme_rdma_queue_idx(queue))
return nvme_rdma_map_sg_inline(queue, req, c);
- if (!register_always)
+ if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY)
return nvme_rdma_map_sg_single(queue, req, c);
}
@@ -1495,7 +1480,6 @@ static void nvme_rdma_complete_rq(struct request *rq)
static struct blk_mq_ops nvme_rdma_mq_ops = {
.queue_rq = nvme_rdma_queue_rq,
.complete = nvme_rdma_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nvme_rdma_init_request,
.exit_request = nvme_rdma_exit_request,
.reinit_request = nvme_rdma_reinit_request,
@@ -1507,7 +1491,6 @@ static struct blk_mq_ops nvme_rdma_mq_ops = {
static struct blk_mq_ops nvme_rdma_admin_mq_ops = {
.queue_rq = nvme_rdma_queue_rq,
.complete = nvme_rdma_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nvme_rdma_init_admin_request,
.exit_request = nvme_rdma_exit_admin_request,
.reinit_request = nvme_rdma_reinit_request,
diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c
index e947e298a737..3eaa4d27801e 100644
--- a/drivers/nvme/host/scsi.c
+++ b/drivers/nvme/host/scsi.c
@@ -72,15 +72,6 @@ static int sg_version_num = 30534; /* 2 digits for each component */
#define ALL_LUNS_RETURNED 0x02
#define ALL_WELL_KNOWN_LUNS_RETURNED 0x01
#define RESTRICTED_LUNS_RETURNED 0x00
-#define NVME_POWER_STATE_START_VALID 0x00
-#define NVME_POWER_STATE_ACTIVE 0x01
-#define NVME_POWER_STATE_IDLE 0x02
-#define NVME_POWER_STATE_STANDBY 0x03
-#define NVME_POWER_STATE_LU_CONTROL 0x07
-#define POWER_STATE_0 0
-#define POWER_STATE_1 1
-#define POWER_STATE_2 2
-#define POWER_STATE_3 3
#define DOWNLOAD_SAVE_ACTIVATE 0x05
#define DOWNLOAD_SAVE_DEFER_ACTIVATE 0x0E
#define ACTIVATE_DEFERRED_MICROCODE 0x0F
@@ -615,7 +606,7 @@ static int nvme_fill_device_id_eui64(struct nvme_ns *ns, struct sg_io_hdr *hdr,
eui = id_ns->eui64;
len = sizeof(id_ns->eui64);
- if (ns->ctrl->vs >= NVME_VS(1, 2)) {
+ if (ns->ctrl->vs >= NVME_VS(1, 2, 0)) {
if (bitmap_empty(eui, len * 8)) {
eui = id_ns->nguid;
len = sizeof(id_ns->nguid);
@@ -688,7 +679,7 @@ static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
{
int res;
- if (ns->ctrl->vs >= NVME_VS(1, 1)) {
+ if (ns->ctrl->vs >= NVME_VS(1, 1, 0)) {
res = nvme_fill_device_id_eui64(ns, hdr, resp, alloc_len);
if (res != -EOPNOTSUPP)
return res;
@@ -915,7 +906,7 @@ static int nvme_trans_log_temperature(struct nvme_ns *ns, struct sg_io_hdr *hdr,
kfree(smart_log);
/* Get Features for Temp Threshold */
- res = nvme_get_features(ns->ctrl, NVME_FEAT_TEMP_THRESH, 0, 0,
+ res = nvme_get_features(ns->ctrl, NVME_FEAT_TEMP_THRESH, 0, NULL, 0,
&feature_resp);
if (res != NVME_SC_SUCCESS)
temp_c_thresh = LOG_TEMP_UNKNOWN;
@@ -1048,7 +1039,7 @@ static int nvme_trans_fill_caching_page(struct nvme_ns *ns,
if (len < MODE_PAGE_CACHING_LEN)
return -EINVAL;
- nvme_sc = nvme_get_features(ns->ctrl, NVME_FEAT_VOLATILE_WC, 0, 0,
+ nvme_sc = nvme_get_features(ns->ctrl, NVME_FEAT_VOLATILE_WC, 0, NULL, 0,
&feature_resp);
res = nvme_trans_status_code(hdr, nvme_sc);
if (res)
@@ -1229,64 +1220,6 @@ static void nvme_trans_fill_read_cap(u8 *response, struct nvme_id_ns *id_ns,
/* Start Stop Unit Helper Functions */
-static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 pc, u8 pcmod, u8 start)
-{
- int res;
- int nvme_sc;
- struct nvme_id_ctrl *id_ctrl;
- int lowest_pow_st; /* max npss = lowest power consumption */
- unsigned ps_desired = 0;
-
- nvme_sc = nvme_identify_ctrl(ns->ctrl, &id_ctrl);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- lowest_pow_st = max(POWER_STATE_0, (int)(id_ctrl->npss - 1));
- kfree(id_ctrl);
-
- switch (pc) {
- case NVME_POWER_STATE_START_VALID:
- /* Action unspecified if POWER CONDITION MODIFIER != 0 */
- if (pcmod == 0 && start == 0x1)
- ps_desired = POWER_STATE_0;
- if (pcmod == 0 && start == 0x0)
- ps_desired = lowest_pow_st;
- break;
- case NVME_POWER_STATE_ACTIVE:
- /* Action unspecified if POWER CONDITION MODIFIER != 0 */
- if (pcmod == 0)
- ps_desired = POWER_STATE_0;
- break;
- case NVME_POWER_STATE_IDLE:
- /* Action unspecified if POWER CONDITION MODIFIER != [0,1,2] */
- if (pcmod == 0x0)
- ps_desired = POWER_STATE_1;
- else if (pcmod == 0x1)
- ps_desired = POWER_STATE_2;
- else if (pcmod == 0x2)
- ps_desired = POWER_STATE_3;
- break;
- case NVME_POWER_STATE_STANDBY:
- /* Action unspecified if POWER CONDITION MODIFIER != [0,1] */
- if (pcmod == 0x0)
- ps_desired = max(POWER_STATE_0, (lowest_pow_st - 2));
- else if (pcmod == 0x1)
- ps_desired = max(POWER_STATE_0, (lowest_pow_st - 1));
- break;
- case NVME_POWER_STATE_LU_CONTROL:
- default:
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
- nvme_sc = nvme_set_features(ns->ctrl, NVME_FEAT_POWER_MGMT, ps_desired, 0,
- NULL);
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
static int nvme_trans_send_activate_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
u8 buffer_id)
{
@@ -1395,7 +1328,7 @@ static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct sg_io_hdr *hdr,
case MODE_PAGE_CACHING:
dword11 = ((mode_page[2] & CACHING_MODE_PAGE_WCE_MASK) ? 1 : 0);
nvme_sc = nvme_set_features(ns->ctrl, NVME_FEAT_VOLATILE_WC,
- dword11, 0, NULL);
+ dword11, NULL, 0, NULL);
res = nvme_trans_status_code(hdr, nvme_sc);
break;
case MODE_PAGE_CONTROL:
@@ -2235,11 +2168,10 @@ static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr,
u8 *cmd)
{
- u8 immed, pcmod, pc, no_flush, start;
+ u8 immed, pcmod, no_flush, start;
immed = cmd[1] & 0x01;
pcmod = cmd[3] & 0x0f;
- pc = (cmd[4] & 0xf0) >> 4;
no_flush = cmd[4] & 0x04;
start = cmd[4] & 0x01;
@@ -2254,8 +2186,8 @@ static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr,
if (res)
return res;
}
- /* Setup the expected power state transition */
- return nvme_trans_power_state(ns, hdr, pc, pcmod, start);
+
+ return 0;
}
}
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 47c564b5a289..6fe4c48a21e4 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -14,6 +14,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <generated/utsrelease.h>
+#include <asm/unaligned.h>
#include "nvmet.h"
u32 nvmet_get_log_page_len(struct nvme_command *cmd)
@@ -29,8 +30,84 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd)
return len;
}
+static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
+ struct nvme_smart_log *slog)
+{
+ u16 status;
+ struct nvmet_ns *ns;
+ u64 host_reads, host_writes, data_units_read, data_units_written;
+
+ status = NVME_SC_SUCCESS;
+ ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->get_log_page.nsid);
+ if (!ns) {
+ status = NVME_SC_INVALID_NS;
+ pr_err("nvmet : Counld not find namespace id : %d\n",
+ le32_to_cpu(req->cmd->get_log_page.nsid));
+ goto out;
+ }
+
+ host_reads = part_stat_read(ns->bdev->bd_part, ios[READ]);
+ data_units_read = part_stat_read(ns->bdev->bd_part, sectors[READ]);
+ host_writes = part_stat_read(ns->bdev->bd_part, ios[WRITE]);
+ data_units_written = part_stat_read(ns->bdev->bd_part, sectors[WRITE]);
+
+ put_unaligned_le64(host_reads, &slog->host_reads[0]);
+ put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
+ put_unaligned_le64(host_writes, &slog->host_writes[0]);
+ put_unaligned_le64(data_units_written, &slog->data_units_written[0]);
+ nvmet_put_namespace(ns);
+out:
+ return status;
+}
+
+static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
+ struct nvme_smart_log *slog)
+{
+ u16 status;
+ u64 host_reads = 0, host_writes = 0;
+ u64 data_units_read = 0, data_units_written = 0;
+ struct nvmet_ns *ns;
+ struct nvmet_ctrl *ctrl;
+
+ status = NVME_SC_SUCCESS;
+ ctrl = req->sq->ctrl;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
+ host_reads += part_stat_read(ns->bdev->bd_part, ios[READ]);
+ data_units_read +=
+ part_stat_read(ns->bdev->bd_part, sectors[READ]);
+ host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]);
+ data_units_written +=
+ part_stat_read(ns->bdev->bd_part, sectors[WRITE]);
+
+ }
+ rcu_read_unlock();
+
+ put_unaligned_le64(host_reads, &slog->host_reads[0]);
+ put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
+ put_unaligned_le64(host_writes, &slog->host_writes[0]);
+ put_unaligned_le64(data_units_written, &slog->data_units_written[0]);
+
+ return status;
+}
+
+static u16 nvmet_get_smart_log(struct nvmet_req *req,
+ struct nvme_smart_log *slog)
+{
+ u16 status;
+
+ WARN_ON(req == NULL || slog == NULL);
+ if (req->cmd->get_log_page.nsid == 0xFFFFFFFF)
+ status = nvmet_get_smart_log_all(req, slog);
+ else
+ status = nvmet_get_smart_log_nsid(req, slog);
+ return status;
+}
+
static void nvmet_execute_get_log_page(struct nvmet_req *req)
{
+ struct nvme_smart_log *smart_log;
size_t data_len = nvmet_get_log_page_len(req->cmd);
void *buf;
u16 status = 0;
@@ -59,6 +136,16 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
* available (e.g. units or commands read/written) those aren't
* persistent over power loss.
*/
+ if (data_len != sizeof(*smart_log)) {
+ status = NVME_SC_INTERNAL;
+ goto err;
+ }
+ smart_log = buf;
+ status = nvmet_get_smart_log(req, smart_log);
+ if (status) {
+ memset(buf, '\0', data_len);
+ goto err;
+ }
break;
case 0x03:
/*
@@ -73,6 +160,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
status = nvmet_copy_to_sgl(req, 0, buf, data_len);
+err:
kfree(buf);
out:
nvmet_req_complete(req, status);
@@ -111,7 +199,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
*/
/* we support multiple ports and multiples hosts: */
- id->mic = (1 << 0) | (1 << 1);
+ id->cmic = (1 << 0) | (1 << 1);
/* no limit on data transfer sizes for now */
id->mdts = 0;
@@ -423,13 +511,13 @@ int nvmet_parse_admin_cmd(struct nvmet_req *req)
case nvme_admin_identify:
req->data_len = 4096;
switch (le32_to_cpu(cmd->identify.cns)) {
- case 0x00:
+ case NVME_ID_CNS_NS:
req->execute = nvmet_execute_identify_ns;
return 0;
- case 0x01:
+ case NVME_ID_CNS_CTRL:
req->execute = nvmet_execute_identify_ctrl;
return 0;
- case 0x02:
+ case NVME_ID_CNS_NS_ACTIVE_LIST:
req->execute = nvmet_execute_identify_nslist;
return 0;
}
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 6559d5afa7bf..b4cacb6f0258 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -882,7 +882,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
if (!subsys)
return NULL;
- subsys->ver = (1 << 16) | (2 << 8) | 1; /* NVMe 1.2.1 */
+ subsys->ver = NVME_VS(1, 2, 1); /* NVMe 1.2.1 */
switch (type) {
case NVME_NQN_NVME:
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 6f65646e89cf..12f39eea569f 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -54,7 +54,7 @@ static void nvmet_format_discovery_entry(struct nvmf_disc_rsp_page_hdr *hdr,
/* we support only dynamic controllers */
e->cntlid = cpu_to_le16(NVME_CNTLID_DYNAMIC);
e->asqsz = cpu_to_le16(NVMF_AQ_DEPTH);
- e->nqntype = type;
+ e->subtype = type;
memcpy(e->trsvcid, port->disc_addr.trsvcid, NVMF_TRSVCID_SIZE);
memcpy(e->traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE);
memcpy(e->tsas.common, port->disc_addr.tsas.common, NVMF_TSAS_SIZE);
@@ -187,7 +187,7 @@ int nvmet_parse_discovery_cmd(struct nvmet_req *req)
case nvme_admin_identify:
req->data_len = 4096;
switch (le32_to_cpu(cmd->identify.cns)) {
- case 0x01:
+ case NVME_ID_CNS_CTRL:
req->execute =
nvmet_execute_identify_disc_ctrl;
return 0;
diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c
index 2cd069b691ae..4a96c2049b7b 100644
--- a/drivers/nvme/target/io-cmd.c
+++ b/drivers/nvme/target/io-cmd.c
@@ -58,6 +58,7 @@ static void nvmet_execute_rw(struct nvmet_req *req)
if (req->cmd->rw.opcode == nvme_cmd_write) {
op = REQ_OP_WRITE;
+ op_flags = WRITE_ODIRECT;
if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
op_flags |= REQ_FUA;
} else {
@@ -205,7 +206,7 @@ int nvmet_parse_io_cmd(struct nvmet_req *req)
return 0;
case nvme_cmd_dsm:
req->execute = nvmet_execute_dsm;
- req->data_len = le32_to_cpu(cmd->dsm.nr) *
+ req->data_len = le32_to_cpu(cmd->dsm.nr + 1) *
sizeof(struct nvme_dsm_range);
return 0;
default:
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 395e60dad835..d5df77d686b2 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -273,7 +273,6 @@ static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
static struct blk_mq_ops nvme_loop_mq_ops = {
.queue_rq = nvme_loop_queue_rq,
.complete = nvme_loop_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nvme_loop_init_request,
.init_hctx = nvme_loop_init_hctx,
.timeout = nvme_loop_timeout,
@@ -282,7 +281,6 @@ static struct blk_mq_ops nvme_loop_mq_ops = {
static struct blk_mq_ops nvme_loop_admin_mq_ops = {
.queue_rq = nvme_loop_queue_rq,
.complete = nvme_loop_complete_rq,
- .map_queue = blk_mq_map_queue,
.init_request = nvme_loop_init_admin_request,
.init_hctx = nvme_loop_init_admin_hctx,
.timeout = nvme_loop_timeout,
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 1cbe6e053b5b..f8d23999e0f2 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -848,7 +848,7 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
ndev->device = cm_id->device;
kref_init(&ndev->ref);
- ndev->pd = ib_alloc_pd(ndev->device);
+ ndev->pd = ib_alloc_pd(ndev->device, 0);
if (IS_ERR(ndev->pd))
goto out_free_dev;
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-31 03:27:35 +0300