summaryrefslogtreecommitdiff
path: root/drivers/nvme/host
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvme/host')
-rw-r--r--drivers/nvme/host/core.c390
-rw-r--r--drivers/nvme/host/fabrics.c7
-rw-r--r--drivers/nvme/host/fabrics.h2
-rw-r--r--drivers/nvme/host/fc.c17
-rw-r--r--drivers/nvme/host/lightnvm.c315
-rw-r--r--drivers/nvme/host/nvme.h29
-rw-r--r--drivers/nvme/host/pci.c77
-rw-r--r--drivers/nvme/host/rdma.c86
-rw-r--r--drivers/nvme/host/scsi.c7
9 files changed, 776 insertions, 154 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 8a3c3e32a704..9b3b57fef446 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -26,6 +26,7 @@
#include <linux/ptrace.h>
#include <linux/nvme_ioctl.h>
#include <linux/t10-pi.h>
+#include <linux/pm_qos.h>
#include <scsi/sg.h>
#include <asm/unaligned.h>
@@ -56,6 +57,11 @@ EXPORT_SYMBOL_GPL(nvme_max_retries);
static int nvme_char_major;
module_param(nvme_char_major, int, 0);
+static unsigned long default_ps_max_latency_us = 25000;
+module_param(default_ps_max_latency_us, ulong, 0644);
+MODULE_PARM_DESC(default_ps_max_latency_us,
+ "max power saving latency for new devices; use PM QOS to change per device");
+
static LIST_HEAD(nvme_ctrl_list);
static DEFINE_SPINLOCK(dev_list_lock);
@@ -208,18 +214,18 @@ EXPORT_SYMBOL_GPL(nvme_requeue_req);
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, unsigned int flags, int qid)
{
+ unsigned op = nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
struct request *req;
if (qid == NVME_QID_ANY) {
- req = blk_mq_alloc_request(q, nvme_is_write(cmd), flags);
+ req = blk_mq_alloc_request(q, op, flags);
} else {
- req = blk_mq_alloc_request_hctx(q, nvme_is_write(cmd), flags,
+ req = blk_mq_alloc_request_hctx(q, op, flags,
qid ? qid - 1 : 0);
}
if (IS_ERR(req))
return req;
- req->cmd_type = REQ_TYPE_DRV_PRIV;
req->cmd_flags |= REQ_FAILFAST_DRIVER;
nvme_req(req)->cmd = cmd;
@@ -238,26 +244,38 @@ static inline void nvme_setup_flush(struct nvme_ns *ns,
static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmnd)
{
+ unsigned short segments = blk_rq_nr_discard_segments(req), n = 0;
struct nvme_dsm_range *range;
- unsigned int nr_bytes = blk_rq_bytes(req);
+ struct bio *bio;
- range = kmalloc(sizeof(*range), GFP_ATOMIC);
+ range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC);
if (!range)
return BLK_MQ_RQ_QUEUE_BUSY;
- range->cattr = cpu_to_le32(0);
- range->nlb = cpu_to_le32(nr_bytes >> ns->lba_shift);
- range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+ __rq_for_each_bio(bio, req) {
+ u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector);
+ u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
+
+ range[n].cattr = cpu_to_le32(0);
+ range[n].nlb = cpu_to_le32(nlb);
+ range[n].slba = cpu_to_le64(slba);
+ n++;
+ }
+
+ if (WARN_ON_ONCE(n != segments)) {
+ kfree(range);
+ return BLK_MQ_RQ_QUEUE_ERROR;
+ }
memset(cmnd, 0, sizeof(*cmnd));
cmnd->dsm.opcode = nvme_cmd_dsm;
cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
- cmnd->dsm.nr = 0;
+ cmnd->dsm.nr = segments - 1;
cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
req->special_vec.bv_page = virt_to_page(range);
req->special_vec.bv_offset = offset_in_page(range);
- req->special_vec.bv_len = sizeof(*range);
+ req->special_vec.bv_len = sizeof(*range) * segments;
req->rq_flags |= RQF_SPECIAL_PAYLOAD;
return BLK_MQ_RQ_QUEUE_OK;
@@ -309,17 +327,27 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
{
int ret = BLK_MQ_RQ_QUEUE_OK;
- if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+ switch (req_op(req)) {
+ case REQ_OP_DRV_IN:
+ case REQ_OP_DRV_OUT:
memcpy(cmd, nvme_req(req)->cmd, sizeof(*cmd));
- else if (req_op(req) == REQ_OP_FLUSH)
+ break;
+ case REQ_OP_FLUSH:
nvme_setup_flush(ns, cmd);
- else if (req_op(req) == REQ_OP_DISCARD)
+ break;
+ case REQ_OP_DISCARD:
ret = nvme_setup_discard(ns, req, cmd);
- else
+ break;
+ case REQ_OP_READ:
+ case REQ_OP_WRITE:
nvme_setup_rw(ns, req, cmd);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ return BLK_MQ_RQ_QUEUE_ERROR;
+ }
cmd->common.command_id = req->tag;
-
return ret;
}
EXPORT_SYMBOL_GPL(nvme_setup_cmd);
@@ -538,7 +566,7 @@ 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(NVME_ID_CNS_CTRL);
+ c.identify.cns = NVME_ID_CNS_CTRL;
*id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
if (!*id)
@@ -556,7 +584,7 @@ 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(NVME_ID_CNS_NS_ACTIVE_LIST);
+ c.identify.cns = 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);
}
@@ -568,8 +596,9 @@ int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid,
int error;
/* gcc-4.4.4 (at least) has issues with initializers and anon unions */
- c.identify.opcode = nvme_admin_identify,
- c.identify.nsid = cpu_to_le32(nsid),
+ c.identify.opcode = nvme_admin_identify;
+ c.identify.nsid = cpu_to_le32(nsid);
+ c.identify.cns = NVME_ID_CNS_NS;
*id = kmalloc(sizeof(struct nvme_id_ns), GFP_KERNEL);
if (!*id)
@@ -784,6 +813,13 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
return nvme_sg_io(ns, (void __user *)arg);
#endif
default:
+#ifdef CONFIG_NVM
+ if (ns->ndev)
+ return nvme_nvm_ioctl(ns, cmd, arg);
+#endif
+ if (is_sed_ioctl(cmd))
+ return sed_ioctl(ns->ctrl->opal_dev, cmd,
+ (void __user *) arg);
return -ENOTTY;
}
}
@@ -861,6 +897,9 @@ static void nvme_config_discard(struct nvme_ns *ns)
struct nvme_ctrl *ctrl = ns->ctrl;
u32 logical_block_size = queue_logical_block_size(ns->queue);
+ BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
+ NVME_DSM_MAX_RANGES);
+
if (ctrl->quirks & NVME_QUIRK_DISCARD_ZEROES)
ns->queue->limits.discard_zeroes_data = 1;
else
@@ -869,6 +908,7 @@ static void nvme_config_discard(struct nvme_ns *ns)
ns->queue->limits.discard_alignment = logical_block_size;
ns->queue->limits.discard_granularity = logical_block_size;
blk_queue_max_discard_sectors(ns->queue, UINT_MAX);
+ blk_queue_max_discard_segments(ns->queue, NVME_DSM_MAX_RANGES);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
}
@@ -1051,6 +1091,28 @@ static const struct pr_ops nvme_pr_ops = {
.pr_clear = nvme_pr_clear,
};
+#ifdef CONFIG_BLK_SED_OPAL
+int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
+ bool send)
+{
+ struct nvme_ctrl *ctrl = data;
+ struct nvme_command cmd;
+
+ memset(&cmd, 0, sizeof(cmd));
+ if (send)
+ cmd.common.opcode = nvme_admin_security_send;
+ else
+ cmd.common.opcode = nvme_admin_security_recv;
+ cmd.common.nsid = 0;
+ cmd.common.cdw10[0] = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
+ cmd.common.cdw10[1] = cpu_to_le32(len);
+
+ return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
+ ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0);
+}
+EXPORT_SYMBOL_GPL(nvme_sec_submit);
+#endif /* CONFIG_BLK_SED_OPAL */
+
static const struct block_device_operations nvme_fops = {
.owner = THIS_MODULE,
.ioctl = nvme_ioctl,
@@ -1196,6 +1258,176 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
blk_queue_write_cache(q, vwc, vwc);
}
+static void nvme_configure_apst(struct nvme_ctrl *ctrl)
+{
+ /*
+ * APST (Autonomous Power State Transition) lets us program a
+ * table of power state transitions that the controller will
+ * perform automatically. We configure it with a simple
+ * heuristic: we are willing to spend at most 2% of the time
+ * transitioning between power states. Therefore, when running
+ * in any given state, we will enter the next lower-power
+ * non-operational state after waiting 100 * (enlat + exlat)
+ * microseconds, as long as that state's total latency is under
+ * the requested maximum latency.
+ *
+ * We will not autonomously enter any non-operational state for
+ * which the total latency exceeds ps_max_latency_us. Users
+ * can set ps_max_latency_us to zero to turn off APST.
+ */
+
+ unsigned apste;
+ struct nvme_feat_auto_pst *table;
+ int ret;
+
+ /*
+ * If APST isn't supported or if we haven't been initialized yet,
+ * then don't do anything.
+ */
+ if (!ctrl->apsta)
+ return;
+
+ if (ctrl->npss > 31) {
+ dev_warn(ctrl->device, "NPSS is invalid; not using APST\n");
+ return;
+ }
+
+ table = kzalloc(sizeof(*table), GFP_KERNEL);
+ if (!table)
+ return;
+
+ if (ctrl->ps_max_latency_us == 0) {
+ /* Turn off APST. */
+ apste = 0;
+ } else {
+ __le64 target = cpu_to_le64(0);
+ int state;
+
+ /*
+ * Walk through all states from lowest- to highest-power.
+ * According to the spec, lower-numbered states use more
+ * power. NPSS, despite the name, is the index of the
+ * lowest-power state, not the number of states.
+ */
+ for (state = (int)ctrl->npss; state >= 0; state--) {
+ u64 total_latency_us, transition_ms;
+
+ if (target)
+ table->entries[state] = target;
+
+ /*
+ * Is this state a useful non-operational state for
+ * higher-power states to autonomously transition to?
+ */
+ if (!(ctrl->psd[state].flags &
+ NVME_PS_FLAGS_NON_OP_STATE))
+ continue;
+
+ total_latency_us =
+ (u64)le32_to_cpu(ctrl->psd[state].entry_lat) +
+ + le32_to_cpu(ctrl->psd[state].exit_lat);
+ if (total_latency_us > ctrl->ps_max_latency_us)
+ continue;
+
+ /*
+ * This state is good. Use it as the APST idle
+ * target for higher power states.
+ */
+ transition_ms = total_latency_us + 19;
+ do_div(transition_ms, 20);
+ if (transition_ms > (1 << 24) - 1)
+ transition_ms = (1 << 24) - 1;
+
+ target = cpu_to_le64((state << 3) |
+ (transition_ms << 8));
+ }
+
+ apste = 1;
+ }
+
+ ret = nvme_set_features(ctrl, NVME_FEAT_AUTO_PST, apste,
+ table, sizeof(*table), NULL);
+ if (ret)
+ dev_err(ctrl->device, "failed to set APST feature (%d)\n", ret);
+
+ kfree(table);
+}
+
+static void nvme_set_latency_tolerance(struct device *dev, s32 val)
+{
+ struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+ u64 latency;
+
+ switch (val) {
+ case PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT:
+ case PM_QOS_LATENCY_ANY:
+ latency = U64_MAX;
+ break;
+
+ default:
+ latency = val;
+ }
+
+ if (ctrl->ps_max_latency_us != latency) {
+ ctrl->ps_max_latency_us = latency;
+ nvme_configure_apst(ctrl);
+ }
+}
+
+struct nvme_core_quirk_entry {
+ /*
+ * NVMe model and firmware strings are padded with spaces. For
+ * simplicity, strings in the quirk table are padded with NULLs
+ * instead.
+ */
+ u16 vid;
+ const char *mn;
+ const char *fr;
+ unsigned long quirks;
+};
+
+static const struct nvme_core_quirk_entry core_quirks[] = {
+ /*
+ * Seen on a Samsung "SM951 NVMe SAMSUNG 256GB": using APST causes
+ * the controller to go out to lunch. It dies when the watchdog
+ * timer reads CSTS and gets 0xffffffff.
+ */
+ {
+ .vid = 0x144d,
+ .fr = "BXW75D0Q",
+ .quirks = NVME_QUIRK_NO_APST,
+ },
+};
+
+/* match is null-terminated but idstr is space-padded. */
+static bool string_matches(const char *idstr, const char *match, size_t len)
+{
+ size_t matchlen;
+
+ if (!match)
+ return true;
+
+ matchlen = strlen(match);
+ WARN_ON_ONCE(matchlen > len);
+
+ if (memcmp(idstr, match, matchlen))
+ return false;
+
+ for (; matchlen < len; matchlen++)
+ if (idstr[matchlen] != ' ')
+ return false;
+
+ return true;
+}
+
+static bool quirk_matches(const struct nvme_id_ctrl *id,
+ const struct nvme_core_quirk_entry *q)
+{
+ return q->vid == le16_to_cpu(id->vid) &&
+ string_matches(id->mn, q->mn, sizeof(id->mn)) &&
+ string_matches(id->fr, q->fr, sizeof(id->fr));
+}
+
/*
* Initialize the cached copies of the Identify data and various controller
* register in our nvme_ctrl structure. This should be called as soon as
@@ -1207,6 +1439,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
u64 cap;
int ret, page_shift;
u32 max_hw_sectors;
+ u8 prev_apsta;
ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs);
if (ret) {
@@ -1230,6 +1463,25 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
return -EIO;
}
+ if (!ctrl->identified) {
+ /*
+ * Check for quirks. Quirk can depend on firmware version,
+ * so, in principle, the set of quirks present can change
+ * across a reset. As a possible future enhancement, we
+ * could re-scan for quirks every time we reinitialize
+ * the device, but we'd have to make sure that the driver
+ * behaves intelligently if the quirks change.
+ */
+
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(core_quirks); i++) {
+ if (quirk_matches(id, &core_quirks[i]))
+ ctrl->quirks |= core_quirks[i].quirks;
+ }
+ }
+
+ ctrl->oacs = le16_to_cpu(id->oacs);
ctrl->vid = le16_to_cpu(id->vid);
ctrl->oncs = le16_to_cpup(&id->oncs);
atomic_set(&ctrl->abort_limit, id->acl + 1);
@@ -1249,6 +1501,11 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
ctrl->sgls = le32_to_cpu(id->sgls);
ctrl->kas = le16_to_cpu(id->kas);
+ ctrl->npss = id->npss;
+ prev_apsta = ctrl->apsta;
+ ctrl->apsta = (ctrl->quirks & NVME_QUIRK_NO_APST) ? 0 : id->apsta;
+ memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd));
+
if (ctrl->ops->is_fabrics) {
ctrl->icdoff = le16_to_cpu(id->icdoff);
ctrl->ioccsz = le32_to_cpu(id->ioccsz);
@@ -1272,6 +1529,16 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
}
kfree(id);
+
+ if (ctrl->apsta && !prev_apsta)
+ dev_pm_qos_expose_latency_tolerance(ctrl->device);
+ else if (!ctrl->apsta && prev_apsta)
+ dev_pm_qos_hide_latency_tolerance(ctrl->device);
+
+ nvme_configure_apst(ctrl);
+
+ ctrl->identified = true;
+
return ret;
}
EXPORT_SYMBOL_GPL(nvme_init_identify);
@@ -1521,6 +1788,29 @@ static ssize_t nvme_sysfs_show_transport(struct device *dev,
}
static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL);
+static ssize_t nvme_sysfs_show_state(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+ static const char *const state_name[] = {
+ [NVME_CTRL_NEW] = "new",
+ [NVME_CTRL_LIVE] = "live",
+ [NVME_CTRL_RESETTING] = "resetting",
+ [NVME_CTRL_RECONNECTING]= "reconnecting",
+ [NVME_CTRL_DELETING] = "deleting",
+ [NVME_CTRL_DEAD] = "dead",
+ };
+
+ if ((unsigned)ctrl->state < ARRAY_SIZE(state_name) &&
+ state_name[ctrl->state])
+ return sprintf(buf, "%s\n", state_name[ctrl->state]);
+
+ return sprintf(buf, "unknown state\n");
+}
+
+static DEVICE_ATTR(state, S_IRUGO, nvme_sysfs_show_state, NULL);
+
static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev,
struct device_attribute *attr,
char *buf)
@@ -1553,6 +1843,7 @@ static struct attribute *nvme_dev_attrs[] = {
&dev_attr_transport.attr,
&dev_attr_subsysnqn.attr,
&dev_attr_address.attr,
+ &dev_attr_state.attr,
NULL
};
@@ -2009,6 +2300,14 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
list_add_tail(&ctrl->node, &nvme_ctrl_list);
spin_unlock(&dev_list_lock);
+ /*
+ * Initialize latency tolerance controls. The sysfs files won't
+ * be visible to userspace unless the device actually supports APST.
+ */
+ ctrl->device->power.set_latency_tolerance = nvme_set_latency_tolerance;
+ dev_pm_qos_update_user_latency_tolerance(ctrl->device,
+ min(default_ps_max_latency_us, (unsigned long)S32_MAX));
+
return 0;
out_release_instance:
nvme_release_instance(ctrl);
@@ -2034,9 +2333,9 @@ 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 (ns->disk && !test_and_set_bit(NVME_NS_DEAD, &ns->flags))
- revalidate_disk(ns->disk);
-
+ if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+ continue;
+ revalidate_disk(ns->disk);
blk_set_queue_dying(ns->queue);
blk_mq_abort_requeue_list(ns->queue);
blk_mq_start_stopped_hw_queues(ns->queue, true);
@@ -2045,6 +2344,53 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
}
EXPORT_SYMBOL_GPL(nvme_kill_queues);
+void nvme_unfreeze(struct nvme_ctrl *ctrl)
+{
+ struct nvme_ns *ns;
+
+ mutex_lock(&ctrl->namespaces_mutex);
+ list_for_each_entry(ns, &ctrl->namespaces, list)
+ blk_mq_unfreeze_queue(ns->queue);
+ mutex_unlock(&ctrl->namespaces_mutex);
+}
+EXPORT_SYMBOL_GPL(nvme_unfreeze);
+
+void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
+{
+ struct nvme_ns *ns;
+
+ mutex_lock(&ctrl->namespaces_mutex);
+ list_for_each_entry(ns, &ctrl->namespaces, list) {
+ timeout = blk_mq_freeze_queue_wait_timeout(ns->queue, timeout);
+ if (timeout <= 0)
+ break;
+ }
+ mutex_unlock(&ctrl->namespaces_mutex);
+}
+EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
+
+void nvme_wait_freeze(struct nvme_ctrl *ctrl)
+{
+ struct nvme_ns *ns;
+
+ mutex_lock(&ctrl->namespaces_mutex);
+ list_for_each_entry(ns, &ctrl->namespaces, list)
+ blk_mq_freeze_queue_wait(ns->queue);
+ mutex_unlock(&ctrl->namespaces_mutex);
+}
+EXPORT_SYMBOL_GPL(nvme_wait_freeze);
+
+void nvme_start_freeze(struct nvme_ctrl *ctrl)
+{
+ struct nvme_ns *ns;
+
+ mutex_lock(&ctrl->namespaces_mutex);
+ list_for_each_entry(ns, &ctrl->namespaces, list)
+ blk_mq_freeze_queue_start(ns->queue);
+ mutex_unlock(&ctrl->namespaces_mutex);
+}
+EXPORT_SYMBOL_GPL(nvme_start_freeze);
+
void nvme_stop_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 916d13608059..5b7386f69f4d 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -480,11 +480,16 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
* being implemented to the common NVMe fabrics library. Part of
* the overall init sequence of starting up a fabrics driver.
*/
-void nvmf_register_transport(struct nvmf_transport_ops *ops)
+int nvmf_register_transport(struct nvmf_transport_ops *ops)
{
+ if (!ops->create_ctrl)
+ return -EINVAL;
+
mutex_lock(&nvmf_transports_mutex);
list_add_tail(&ops->entry, &nvmf_transports);
mutex_unlock(&nvmf_transports_mutex);
+
+ return 0;
}
EXPORT_SYMBOL_GPL(nvmf_register_transport);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 924145c979f1..156018182ce4 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -128,7 +128,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl);
int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid);
-void nvmf_register_transport(struct nvmf_transport_ops *ops);
+int nvmf_register_transport(struct nvmf_transport_ops *ops);
void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
void nvmf_free_options(struct nvmf_ctrl_options *opts);
const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index e65041c640cb..9690beb15e69 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1937,7 +1937,7 @@ nvme_fc_complete_rq(struct request *rq)
return;
}
- if (rq->cmd_type == REQ_TYPE_DRV_PRIV)
+ if (blk_rq_is_passthrough(rq))
error = rq->errors;
else
error = nvme_error_status(rq->errors);
@@ -2353,18 +2353,6 @@ __nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
/* sanity checks */
- /* FC-NVME supports 64-byte SQE only */
- if (ctrl->ctrl.ioccsz != 4) {
- dev_err(ctrl->ctrl.device, "ioccsz %d is not supported!\n",
- ctrl->ctrl.ioccsz);
- goto out_remove_admin_queue;
- }
- /* FC-NVME supports 16-byte CQE only */
- if (ctrl->ctrl.iorcsz != 1) {
- dev_err(ctrl->ctrl.device, "iorcsz %d is not supported!\n",
- ctrl->ctrl.iorcsz);
- goto out_remove_admin_queue;
- }
/* FC-NVME does not have other data in the capsule */
if (ctrl->ctrl.icdoff) {
dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
@@ -2562,8 +2550,7 @@ static int __init nvme_fc_init_module(void)
if (!nvme_fc_wq)
return -ENOMEM;
- nvmf_register_transport(&nvme_fc_transport);
- return 0;
+ return nvmf_register_transport(&nvme_fc_transport);
}
static void __exit nvme_fc_exit_module(void)
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 588d4a34c083..21cac8523bd8 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -26,6 +26,8 @@
#include <linux/bitops.h>
#include <linux/lightnvm.h>
#include <linux/vmalloc.h>
+#include <linux/sched/sysctl.h>
+#include <uapi/linux/lightnvm.h>
enum nvme_nvm_admin_opcode {
nvme_nvm_admin_identity = 0xe2,
@@ -248,50 +250,48 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
{
struct nvme_nvm_id_group *src;
struct nvm_id_group *dst;
- int i, end;
-
- end = min_t(u32, 4, nvm_id->cgrps);
-
- for (i = 0; i < end; i++) {
- src = &nvme_nvm_id->groups[i];
- dst = &nvm_id->groups[i];
-
- dst->mtype = src->mtype;
- dst->fmtype = src->fmtype;
- dst->num_ch = src->num_ch;
- dst->num_lun = src->num_lun;
- dst->num_pln = src->num_pln;
-
- dst->num_pg = le16_to_cpu(src->num_pg);
- dst->num_blk = le16_to_cpu(src->num_blk);
- dst->fpg_sz = le16_to_cpu(src->fpg_sz);
- dst->csecs = le16_to_cpu(src->csecs);
- dst->sos = le16_to_cpu(src->sos);
-
- dst->trdt = le32_to_cpu(src->trdt);
- dst->trdm = le32_to_cpu(src->trdm);
- dst->tprt = le32_to_cpu(src->tprt);
- dst->tprm = le32_to_cpu(src->tprm);
- dst->tbet = le32_to_cpu(src->tbet);
- dst->tbem = le32_to_cpu(src->tbem);
- dst->mpos = le32_to_cpu(src->mpos);
- dst->mccap = le32_to_cpu(src->mccap);
-
- dst->cpar = le16_to_cpu(src->cpar);
-
- if (dst->fmtype == NVM_ID_FMTYPE_MLC) {
- memcpy(dst->lptbl.id, src->lptbl.id, 8);
- dst->lptbl.mlc.num_pairs =
- le16_to_cpu(src->lptbl.mlc.num_pairs);
-
- if (dst->lptbl.mlc.num_pairs > NVME_NVM_LP_MLC_PAIRS) {
- pr_err("nvm: number of MLC pairs not supported\n");
- return -EINVAL;
- }
- memcpy(dst->lptbl.mlc.pairs, src->lptbl.mlc.pairs,
- dst->lptbl.mlc.num_pairs);
+ if (nvme_nvm_id->cgrps != 1)
+ return -EINVAL;
+
+ src = &nvme_nvm_id->groups[0];
+ dst = &nvm_id->grp;
+
+ dst->mtype = src->mtype;
+ dst->fmtype = src->fmtype;
+ dst->num_ch = src->num_ch;
+ dst->num_lun = src->num_lun;
+ dst->num_pln = src->num_pln;
+
+ dst->num_pg = le16_to_cpu(src->num_pg);
+ dst->num_blk = le16_to_cpu(src->num_blk);
+ dst->fpg_sz = le16_to_cpu(src->fpg_sz);
+ dst->csecs = le16_to_cpu(src->csecs);
+ dst->sos = le16_to_cpu(src->sos);
+
+ dst->trdt = le32_to_cpu(src->trdt);
+ dst->trdm = le32_to_cpu(src->trdm);
+ dst->tprt = le32_to_cpu(src->tprt);
+ dst->tprm = le32_to_cpu(src->tprm);
+ dst->tbet = le32_to_cpu(src->tbet);
+ dst->tbem = le32_to_cpu(src->tbem);
+ dst->mpos = le32_to_cpu(src->mpos);
+ dst->mccap = le32_to_cpu(src->mccap);
+
+ dst->cpar = le16_to_cpu(src->cpar);
+
+ if (dst->fmtype == NVM_ID_FMTYPE_MLC) {
+ memcpy(dst->lptbl.id, src->lptbl.id, 8);
+ dst->lptbl.mlc.num_pairs =
+ le16_to_cpu(src->lptbl.mlc.num_pairs);
+
+ if (dst->lptbl.mlc.num_pairs > NVME_NVM_LP_MLC_PAIRS) {
+ pr_err("nvm: number of MLC pairs not supported\n");
+ return -EINVAL;
}
+
+ memcpy(dst->lptbl.mlc.pairs, src->lptbl.mlc.pairs,
+ dst->lptbl.mlc.num_pairs);
}
return 0;
@@ -321,7 +321,6 @@ static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id)
nvm_id->ver_id = nvme_nvm_id->ver_id;
nvm_id->vmnt = nvme_nvm_id->vmnt;
- nvm_id->cgrps = nvme_nvm_id->cgrps;
nvm_id->cap = le32_to_cpu(nvme_nvm_id->cap);
nvm_id->dom = le32_to_cpu(nvme_nvm_id->dom);
memcpy(&nvm_id->ppaf, &nvme_nvm_id->ppaf,
@@ -372,7 +371,7 @@ static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb,
}
/* Transform physical address to target address space */
- nvmdev->mt->part_to_tgt(nvmdev, entries, cmd_nlb);
+ nvm_part_to_tgt(nvmdev, entries, cmd_nlb);
if (update_l2p(cmd_slba, cmd_nlb, entries, priv)) {
ret = -EINTR;
@@ -485,7 +484,8 @@ static void nvme_nvm_end_io(struct request *rq, int error)
struct nvm_rq *rqd = rq->end_io_data;
rqd->ppa_status = nvme_req(rq)->result.u64;
- nvm_end_io(rqd, error);
+ rqd->error = error;
+ nvm_end_io(rqd);
kfree(nvme_req(rq)->cmd);
blk_mq_free_request(rq);
@@ -586,6 +586,224 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = {
.max_phys_sect = 64,
};
+static void nvme_nvm_end_user_vio(struct request *rq, int error)
+{
+ struct completion *waiting = rq->end_io_data;
+
+ complete(waiting);
+}
+
+static int nvme_nvm_submit_user_cmd(struct request_queue *q,
+ struct nvme_ns *ns,
+ struct nvme_nvm_command *vcmd,
+ void __user *ubuf, unsigned int bufflen,
+ void __user *meta_buf, unsigned int meta_len,
+ void __user *ppa_buf, unsigned int ppa_len,
+ u32 *result, u64 *status, unsigned int timeout)
+{
+ bool write = nvme_is_write((struct nvme_command *)vcmd);
+ struct nvm_dev *dev = ns->ndev;
+ struct gendisk *disk = ns->disk;
+ struct request *rq;
+ struct bio *bio = NULL;
+ __le64 *ppa_list = NULL;
+ dma_addr_t ppa_dma;
+ __le64 *metadata = NULL;
+ dma_addr_t metadata_dma;
+ DECLARE_COMPLETION_ONSTACK(wait);
+ int ret;
+
+ rq = nvme_alloc_request(q, (struct nvme_command *)vcmd, 0,
+ NVME_QID_ANY);
+ if (IS_ERR(rq)) {
+ ret = -ENOMEM;
+ goto err_cmd;
+ }
+
+ rq->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+
+ rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
+ rq->end_io_data = &wait;
+
+ if (ppa_buf && ppa_len) {
+ ppa_list = dma_pool_alloc(dev->dma_pool, GFP_KERNEL, &ppa_dma);
+ if (!ppa_list) {
+ ret = -ENOMEM;
+ goto err_rq;
+ }
+ if (copy_from_user(ppa_list, (void __user *)ppa_buf,
+ sizeof(u64) * (ppa_len + 1))) {
+ ret = -EFAULT;
+ goto err_ppa;
+ }
+ vcmd->ph_rw.spba = cpu_to_le64(ppa_dma);
+ } else {
+ vcmd->ph_rw.spba = cpu_to_le64((uintptr_t)ppa_buf);
+ }
+
+ if (ubuf && bufflen) {
+ ret = blk_rq_map_user(q, rq, NULL, ubuf, bufflen, GFP_KERNEL);
+ if (ret)
+ goto err_ppa;
+ bio = rq->bio;
+
+ if (meta_buf && meta_len) {
+ metadata = dma_pool_alloc(dev->dma_pool, GFP_KERNEL,
+ &metadata_dma);
+ if (!metadata) {
+ ret = -ENOMEM;
+ goto err_map;
+ }
+
+ if (write) {
+ if (copy_from_user(metadata,
+ (void __user *)meta_buf,
+ meta_len)) {
+ ret = -EFAULT;
+ goto err_meta;
+ }
+ }
+ vcmd->ph_rw.metadata = cpu_to_le64(metadata_dma);
+ }
+
+ if (!disk)
+ goto submit;
+
+ bio->bi_bdev = bdget_disk(disk, 0);
+ if (!bio->bi_bdev) {
+ ret = -ENODEV;
+ goto err_meta;
+ }
+ }
+
+submit:
+ blk_execute_rq_nowait(q, NULL, rq, 0, nvme_nvm_end_user_vio);
+
+ wait_for_completion_io(&wait);
+
+ ret = nvme_error_status(rq->errors);
+ if (result)
+ *result = rq->errors & 0x7ff;
+ if (status)
+ *status = le64_to_cpu(nvme_req(rq)->result.u64);
+
+ if (metadata && !ret && !write) {
+ if (copy_to_user(meta_buf, (void *)metadata, meta_len))
+ ret = -EFAULT;
+ }
+err_meta:
+ if (meta_buf && meta_len)
+ dma_pool_free(dev->dma_pool, metadata, metadata_dma);
+err_map:
+ if (bio) {
+ if (disk && bio->bi_bdev)
+ bdput(bio->bi_bdev);
+ blk_rq_unmap_user(bio);
+ }
+err_ppa:
+ if (ppa_buf && ppa_len)
+ dma_pool_free(dev->dma_pool, ppa_list, ppa_dma);
+err_rq:
+ blk_mq_free_request(rq);
+err_cmd:
+ return ret;
+}
+
+static int nvme_nvm_submit_vio(struct nvme_ns *ns,
+ struct nvm_user_vio __user *uvio)
+{
+ struct nvm_user_vio vio;
+ struct nvme_nvm_command c;
+ unsigned int length;
+ int ret;
+
+ if (copy_from_user(&vio, uvio, sizeof(vio)))
+ return -EFAULT;
+ if (vio.flags)
+ return -EINVAL;
+
+ memset(&c, 0, sizeof(c));
+ c.ph_rw.opcode = vio.opcode;
+ c.ph_rw.nsid = cpu_to_le32(ns->ns_id);
+ c.ph_rw.control = cpu_to_le16(vio.control);
+ c.ph_rw.length = cpu_to_le16(vio.nppas);
+
+ length = (vio.nppas + 1) << ns->lba_shift;
+
+ ret = nvme_nvm_submit_user_cmd(ns->queue, ns, &c,
+ (void __user *)(uintptr_t)vio.addr, length,
+ (void __user *)(uintptr_t)vio.metadata,
+ vio.metadata_len,
+ (void __user *)(uintptr_t)vio.ppa_list, vio.nppas,
+ &vio.result, &vio.status, 0);
+
+ if (ret && copy_to_user(uvio, &vio, sizeof(vio)))
+ return -EFAULT;
+
+ return ret;
+}
+
+static int nvme_nvm_user_vcmd(struct nvme_ns *ns, int admin,
+ struct nvm_passthru_vio __user *uvcmd)
+{
+ struct nvm_passthru_vio vcmd;
+ struct nvme_nvm_command c;
+ struct request_queue *q;
+ unsigned int timeout = 0;
+ int ret;
+
+ if (copy_from_user(&vcmd, uvcmd, sizeof(vcmd)))
+ return -EFAULT;
+ if ((vcmd.opcode != 0xF2) && (!capable(CAP_SYS_ADMIN)))
+ return -EACCES;
+ if (vcmd.flags)
+ return -EINVAL;
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = vcmd.opcode;
+ c.common.nsid = cpu_to_le32(ns->ns_id);
+ c.common.cdw2[0] = cpu_to_le32(vcmd.cdw2);
+ c.common.cdw2[1] = cpu_to_le32(vcmd.cdw3);
+ /* cdw11-12 */
+ c.ph_rw.length = cpu_to_le16(vcmd.nppas);
+ c.ph_rw.control = cpu_to_le32(vcmd.control);
+ c.common.cdw10[3] = cpu_to_le32(vcmd.cdw13);
+ c.common.cdw10[4] = cpu_to_le32(vcmd.cdw14);
+ c.common.cdw10[5] = cpu_to_le32(vcmd.cdw15);
+
+ if (vcmd.timeout_ms)
+ timeout = msecs_to_jiffies(vcmd.timeout_ms);
+
+ q = admin ? ns->ctrl->admin_q : ns->queue;
+
+ ret = nvme_nvm_submit_user_cmd(q, ns,
+ (struct nvme_nvm_command *)&c,
+ (void __user *)(uintptr_t)vcmd.addr, vcmd.data_len,
+ (void __user *)(uintptr_t)vcmd.metadata,
+ vcmd.metadata_len,
+ (void __user *)(uintptr_t)vcmd.ppa_list, vcmd.nppas,
+ &vcmd.result, &vcmd.status, timeout);
+
+ if (ret && copy_to_user(uvcmd, &vcmd, sizeof(vcmd)))
+ return -EFAULT;
+
+ return ret;
+}
+
+int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case NVME_NVM_IOCTL_ADMIN_VIO:
+ return nvme_nvm_user_vcmd(ns, 1, (void __user *)arg);
+ case NVME_NVM_IOCTL_IO_VIO:
+ return nvme_nvm_user_vcmd(ns, 0, (void __user *)arg);
+ case NVME_NVM_IOCTL_SUBMIT_VIO:
+ return nvme_nvm_submit_vio(ns, (void __user *)arg);
+ default:
+ return -ENOTTY;
+ }
+}
+
int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node)
{
struct request_queue *q = ns->queue;
@@ -622,7 +840,7 @@ static ssize_t nvm_dev_attr_show(struct device *dev,
return 0;
id = &ndev->identity;
- grp = &id->groups[0];
+ grp = &id->grp;
attr = &dattr->attr;
if (strcmp(attr->name, "version") == 0) {
@@ -633,10 +851,9 @@ static ssize_t nvm_dev_attr_show(struct device *dev,
return scnprintf(page, PAGE_SIZE, "%u\n", id->cap);
} else if (strcmp(attr->name, "device_mode") == 0) {
return scnprintf(page, PAGE_SIZE, "%u\n", id->dom);
+ /* kept for compatibility */
} else if (strcmp(attr->name, "media_manager") == 0) {
- if (!ndev->mt)
- return scnprintf(page, PAGE_SIZE, "%s\n", "none");
- return scnprintf(page, PAGE_SIZE, "%s\n", ndev->mt->name);
+ return scnprintf(page, PAGE_SIZE, "%s\n", "gennvm");
} else if (strcmp(attr->name, "ppa_format") == 0) {
return scnprintf(page, PAGE_SIZE,
"0x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x\n",
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index aead6d08ed2c..2aa20e3e5675 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -19,6 +19,7 @@
#include <linux/kref.h>
#include <linux/blk-mq.h>
#include <linux/lightnvm.h>
+#include <linux/sed-opal.h>
enum {
/*
@@ -77,6 +78,11 @@ enum nvme_quirks {
* readiness, which is done by reading the NVME_CSTS_RDY bit.
*/
NVME_QUIRK_DELAY_BEFORE_CHK_RDY = (1 << 3),
+
+ /*
+ * APST should not be used.
+ */
+ NVME_QUIRK_NO_APST = (1 << 4),
};
/*
@@ -111,6 +117,7 @@ enum nvme_ctrl_state {
struct nvme_ctrl {
enum nvme_ctrl_state state;
+ bool identified;
spinlock_t lock;
const struct nvme_ctrl_ops *ops;
struct request_queue *admin_q;
@@ -125,6 +132,8 @@ struct nvme_ctrl {
struct list_head node;
struct ida ns_ida;
+ struct opal_dev *opal_dev;
+
char name[12];
char serial[20];
char model[40];
@@ -137,19 +146,26 @@ struct nvme_ctrl {
u32 max_hw_sectors;
u16 oncs;
u16 vid;
+ u16 oacs;
atomic_t abort_limit;
u8 event_limit;
u8 vwc;
u32 vs;
u32 sgls;
u16 kas;
+ u8 npss;
+ u8 apsta;
unsigned int kato;
bool subsystem;
unsigned long quirks;
+ struct nvme_id_power_state psd[32];
struct work_struct scan_work;
struct work_struct async_event_work;
struct delayed_work ka_work;
+ /* Power saving configuration */
+ u64 ps_max_latency_us;
+
/* Fabrics only */
u16 sqsize;
u32 ioccsz;
@@ -267,6 +283,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl);
void nvme_queue_scan(struct nvme_ctrl *ctrl);
void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
+int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
+ bool send);
+
#define NVME_NR_AERS 1
void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
union nvme_result *res);
@@ -275,6 +294,10 @@ void nvme_queue_async_events(struct nvme_ctrl *ctrl);
void nvme_stop_queues(struct nvme_ctrl *ctrl);
void nvme_start_queues(struct nvme_ctrl *ctrl);
void nvme_kill_queues(struct nvme_ctrl *ctrl);
+void nvme_unfreeze(struct nvme_ctrl *ctrl);
+void nvme_wait_freeze(struct nvme_ctrl *ctrl);
+void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
+void nvme_start_freeze(struct nvme_ctrl *ctrl);
#define NVME_QID_ANY -1
struct request *nvme_alloc_request(struct request_queue *q,
@@ -318,6 +341,7 @@ int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
void nvme_nvm_unregister(struct nvme_ns *ns);
int nvme_nvm_register_sysfs(struct nvme_ns *ns);
void nvme_nvm_unregister_sysfs(struct nvme_ns *ns);
+int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, unsigned long arg);
#else
static inline int nvme_nvm_register(struct nvme_ns *ns, char *disk_name,
int node)
@@ -335,6 +359,11 @@ static inline int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *i
{
return 0;
}
+static inline int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd,
+ unsigned long arg)
+{
+ return -ENOTTY;
+}
#endif /* CONFIG_NVM */
static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 3faefabf339c..26a5fd05fe88 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -43,6 +43,7 @@
#include <linux/types.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <asm/unaligned.h>
+#include <linux/sed-opal.h>
#include "nvme.h"
@@ -588,7 +589,7 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
*/
if (ns && ns->ms && !blk_integrity_rq(req)) {
if (!(ns->pi_type && ns->ms == 8) &&
- req->cmd_type != REQ_TYPE_DRV_PRIV) {
+ !blk_rq_is_passthrough(req)) {
blk_mq_end_request(req, -EFAULT);
return BLK_MQ_RQ_QUEUE_OK;
}
@@ -612,10 +613,7 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
spin_lock_irq(&nvmeq->q_lock);
if (unlikely(nvmeq->cq_vector < 0)) {
- if (ns && !test_bit(NVME_NS_DEAD, &ns->flags))
- ret = BLK_MQ_RQ_QUEUE_BUSY;
- else
- ret = BLK_MQ_RQ_QUEUE_ERROR;
+ ret = BLK_MQ_RQ_QUEUE_ERROR;
spin_unlock_irq(&nvmeq->q_lock);
goto out_cleanup_iod;
}
@@ -645,7 +643,7 @@ static void nvme_complete_rq(struct request *req)
return;
}
- if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+ if (blk_rq_is_passthrough(req))
error = req->errors;
else
error = nvme_error_status(req->errors);
@@ -895,12 +893,11 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
return BLK_EH_HANDLED;
}
- iod->aborted = 1;
-
if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
atomic_inc(&dev->ctrl.abort_limit);
return BLK_EH_RESET_TIMER;
}
+ iod->aborted = 1;
memset(&cmd, 0, sizeof(cmd));
cmd.abort.opcode = nvme_admin_abort_cmd;
@@ -1041,9 +1038,10 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
}
static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
- int depth)
+ int depth, int node)
{
- struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq), GFP_KERNEL);
+ struct nvme_queue *nvmeq = kzalloc_node(sizeof(*nvmeq), GFP_KERNEL,
+ node);
if (!nvmeq)
return NULL;
@@ -1178,6 +1176,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
dev->admin_tagset.timeout = ADMIN_TIMEOUT;
dev->admin_tagset.numa_node = dev_to_node(dev->dev);
dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
+ dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
dev->admin_tagset.driver_data = dev;
if (blk_mq_alloc_tag_set(&dev->admin_tagset))
@@ -1219,7 +1218,8 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
nvmeq = dev->queues[0];
if (!nvmeq) {
- nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
+ nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH,
+ dev_to_node(dev->dev));
if (!nvmeq)
return -ENOMEM;
}
@@ -1311,7 +1311,9 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
int ret = 0;
for (i = dev->queue_count; i <= dev->max_qid; i++) {
- if (!nvme_alloc_queue(dev, i, dev->q_depth)) {
+ /* vector == qid - 1, match nvme_create_queue */
+ if (!nvme_alloc_queue(dev, i, dev->q_depth,
+ pci_irq_get_node(to_pci_dev(dev->dev), i - 1))) {
ret = -ENOMEM;
break;
}
@@ -1673,21 +1675,34 @@ static void nvme_pci_disable(struct nvme_dev *dev)
static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
{
int i, queues;
- u32 csts = -1;
+ bool dead = true;
+ struct pci_dev *pdev = to_pci_dev(dev->dev);
del_timer_sync(&dev->watchdog_timer);
mutex_lock(&dev->shutdown_lock);
- if (pci_is_enabled(to_pci_dev(dev->dev))) {
- nvme_stop_queues(&dev->ctrl);
- csts = readl(dev->bar + NVME_REG_CSTS);
+ if (pci_is_enabled(pdev)) {
+ u32 csts = readl(dev->bar + NVME_REG_CSTS);
+
+ if (dev->ctrl.state == NVME_CTRL_LIVE)
+ nvme_start_freeze(&dev->ctrl);
+ dead = !!((csts & NVME_CSTS_CFS) || !(csts & NVME_CSTS_RDY) ||
+ pdev->error_state != pci_channel_io_normal);
}
+ /*
+ * Give the controller a chance to complete all entered requests if
+ * doing a safe shutdown.
+ */
+ if (!dead && shutdown)
+ nvme_wait_freeze_timeout(&dev->ctrl, NVME_IO_TIMEOUT);
+ nvme_stop_queues(&dev->ctrl);
+
queues = dev->online_queues - 1;
for (i = dev->queue_count - 1; i > 0; i--)
nvme_suspend_queue(dev->queues[i]);
- if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
+ if (dead) {
/* A device might become IO incapable very soon during
* probe, before the admin queue is configured. Thus,
* queue_count can be 0 here.
@@ -1702,6 +1717,14 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl);
blk_mq_tagset_busy_iter(&dev->admin_tagset, nvme_cancel_request, &dev->ctrl);
+
+ /*
+ * The driver will not be starting up queues again if shutting down so
+ * must flush all entered requests to their failed completion to avoid
+ * deadlocking blk-mq hot-cpu notifier.
+ */
+ if (shutdown)
+ nvme_start_queues(&dev->ctrl);
mutex_unlock(&dev->shutdown_lock);
}
@@ -1738,6 +1761,7 @@ 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);
+ free_opal_dev(dev->ctrl.opal_dev);
kfree(dev);
}
@@ -1754,6 +1778,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
static void nvme_reset_work(struct work_struct *work)
{
struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work);
+ bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
int result = -ENODEV;
if (WARN_ON(dev->ctrl.state == NVME_CTRL_RESETTING))
@@ -1786,6 +1811,17 @@ static void nvme_reset_work(struct work_struct *work)
if (result)
goto out;
+ if (dev->ctrl.oacs & NVME_CTRL_OACS_SEC_SUPP) {
+ if (!dev->ctrl.opal_dev)
+ dev->ctrl.opal_dev =
+ init_opal_dev(&dev->ctrl, &nvme_sec_submit);
+ else if (was_suspend)
+ opal_unlock_from_suspend(dev->ctrl.opal_dev);
+ } else {
+ free_opal_dev(dev->ctrl.opal_dev);
+ dev->ctrl.opal_dev = NULL;
+ }
+
result = nvme_setup_io_queues(dev);
if (result)
goto out;
@@ -1811,7 +1847,9 @@ static void nvme_reset_work(struct work_struct *work)
nvme_remove_namespaces(&dev->ctrl);
} else {
nvme_start_queues(&dev->ctrl);
+ nvme_wait_freeze(&dev->ctrl);
nvme_dev_add(dev);
+ nvme_unfreeze(&dev->ctrl);
}
if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) {
@@ -1990,8 +2028,10 @@ static void nvme_remove(struct pci_dev *pdev)
pci_set_drvdata(pdev, NULL);
- if (!pci_device_is_present(pdev))
+ if (!pci_device_is_present(pdev)) {
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD);
+ nvme_dev_disable(dev, false);
+ }
flush_work(&dev->reset_work);
nvme_uninit_ctrl(&dev->ctrl);
@@ -2110,6 +2150,7 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
+ { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
{ 0, }
};
MODULE_DEVICE_TABLE(pci, nvme_id_table);
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 557f29b1f1bb..47a479f26e5d 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -42,28 +42,6 @@
#define NVME_RDMA_MAX_INLINE_SEGMENTS 1
-static const char *const nvme_rdma_cm_status_strs[] = {
- [NVME_RDMA_CM_INVALID_LEN] = "invalid length",
- [NVME_RDMA_CM_INVALID_RECFMT] = "invalid record format",
- [NVME_RDMA_CM_INVALID_QID] = "invalid queue ID",
- [NVME_RDMA_CM_INVALID_HSQSIZE] = "invalid host SQ size",
- [NVME_RDMA_CM_INVALID_HRQSIZE] = "invalid host RQ size",
- [NVME_RDMA_CM_NO_RSC] = "resource not found",
- [NVME_RDMA_CM_INVALID_IRD] = "invalid IRD",
- [NVME_RDMA_CM_INVALID_ORD] = "Invalid ORD",
-};
-
-static const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status)
-{
- size_t index = status;
-
- if (index < ARRAY_SIZE(nvme_rdma_cm_status_strs) &&
- nvme_rdma_cm_status_strs[index])
- return nvme_rdma_cm_status_strs[index];
- else
- return "unrecognized reason";
-};
-
/*
* We handle AEN commands ourselves and don't even let the
* block layer know about them.
@@ -155,6 +133,10 @@ struct nvme_rdma_ctrl {
struct sockaddr addr;
struct sockaddr_in addr_in;
};
+ union {
+ struct sockaddr src_addr;
+ struct sockaddr_in src_addr_in;
+ };
struct nvme_ctrl ctrl;
};
@@ -361,8 +343,6 @@ static int __nvme_rdma_init_request(struct nvme_rdma_ctrl *ctrl,
struct ib_device *ibdev = dev->dev;
int ret;
- BUG_ON(queue_idx >= ctrl->queue_count);
-
ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
DMA_TO_DEVICE);
if (ret)
@@ -567,6 +547,7 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
int idx, size_t queue_size)
{
struct nvme_rdma_queue *queue;
+ struct sockaddr *src_addr = NULL;
int ret;
queue = &ctrl->queues[idx];
@@ -589,7 +570,10 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
}
queue->cm_error = -ETIMEDOUT;
- ret = rdma_resolve_addr(queue->cm_id, NULL, &ctrl->addr,
+ if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR)
+ src_addr = &ctrl->src_addr;
+
+ ret = rdma_resolve_addr(queue->cm_id, src_addr, &ctrl->addr,
NVME_RDMA_CONNECT_TIMEOUT_MS);
if (ret) {
dev_info(ctrl->ctrl.device,
@@ -666,8 +650,22 @@ out_free_queues:
static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl)
{
+ struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+ unsigned int nr_io_queues;
int i, ret;
+ nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
+ ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
+ if (ret)
+ return ret;
+
+ ctrl->queue_count = nr_io_queues + 1;
+ if (ctrl->queue_count < 2)
+ return 0;
+
+ dev_info(ctrl->ctrl.device,
+ "creating %d I/O queues.\n", nr_io_queues);
+
for (i = 1; i < ctrl->queue_count; i++) {
ret = nvme_rdma_init_queue(ctrl, i,
ctrl->ctrl.opts->queue_size);
@@ -1065,7 +1063,7 @@ static int nvme_rdma_post_send(struct nvme_rdma_queue *queue,
* sequencer is not allocated in our driver's tagset and it's
* triggered to be freed by blk_cleanup_queue(). So we need to
* always mark it as signaled to ensure that the "wr_cqe", which is
- * embeded in request's payload, is not freed when __ib_process_cq()
+ * embedded in request's payload, is not freed when __ib_process_cq()
* calls wr_cqe->done().
*/
if ((++queue->sig_count % 32) == 0 || flush)
@@ -1265,7 +1263,7 @@ static int nvme_rdma_addr_resolved(struct nvme_rdma_queue *queue)
dev = nvme_rdma_find_get_device(queue->cm_id);
if (!dev) {
- dev_err(queue->cm_id->device->dma_device,
+ dev_err(queue->cm_id->device->dev.parent,
"no client data found!\n");
return -ECONNREFUSED;
}
@@ -1423,7 +1421,7 @@ static inline bool nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue,
if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) {
struct nvme_command *cmd = nvme_req(rq)->cmd;
- if (rq->cmd_type != REQ_TYPE_DRV_PRIV ||
+ if (!blk_rq_is_passthrough(rq) ||
cmd->common.opcode != nvme_fabrics_command ||
cmd->fabrics.fctype != nvme_fabrics_type_connect)
return false;
@@ -1471,7 +1469,7 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
ib_dma_sync_single_for_device(dev, sqe->dma,
sizeof(struct nvme_command), DMA_TO_DEVICE);
- if (rq->cmd_type == REQ_TYPE_FS && req_op(rq) == REQ_OP_FLUSH)
+ if (req_op(rq) == REQ_OP_FLUSH)
flush = true;
ret = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
req->mr->need_inval ? &req->reg_wr.wr : NULL, flush);
@@ -1522,7 +1520,7 @@ static void nvme_rdma_complete_rq(struct request *rq)
return;
}
- if (rq->cmd_type == REQ_TYPE_DRV_PRIV)
+ if (blk_rq_is_passthrough(rq))
error = rq->errors;
else
error = nvme_error_status(rq->errors);
@@ -1805,20 +1803,8 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
static int nvme_rdma_create_io_queues(struct nvme_rdma_ctrl *ctrl)
{
- struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
int ret;
- ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
- if (ret)
- return ret;
-
- ctrl->queue_count = opts->nr_io_queues + 1;
- if (ctrl->queue_count < 2)
- return 0;
-
- dev_info(ctrl->ctrl.device,
- "creating %d I/O queues.\n", opts->nr_io_queues);
-
ret = nvme_rdma_init_io_queues(ctrl);
if (ret)
return ret;
@@ -1905,6 +1891,16 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
goto out_free_ctrl;
}
+ if (opts->mask & NVMF_OPT_HOST_TRADDR) {
+ ret = nvme_rdma_parse_ipaddr(&ctrl->src_addr_in,
+ opts->host_traddr);
+ if (ret) {
+ pr_err("malformed src IP address passed: %s\n",
+ opts->host_traddr);
+ goto out_free_ctrl;
+ }
+ }
+
if (opts->mask & NVMF_OPT_TRSVCID) {
u16 port;
@@ -2016,7 +2012,8 @@ out_free_ctrl:
static struct nvmf_transport_ops nvme_rdma_transport = {
.name = "rdma",
.required_opts = NVMF_OPT_TRADDR,
- .allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY,
+ .allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
+ NVMF_OPT_HOST_TRADDR,
.create_ctrl = nvme_rdma_create_ctrl,
};
@@ -2063,8 +2060,7 @@ static int __init nvme_rdma_init_module(void)
return ret;
}
- nvmf_register_transport(&nvme_rdma_transport);
- return 0;
+ return nvmf_register_transport(&nvme_rdma_transport);
}
static void __exit nvme_rdma_cleanup_module(void)
diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c
index a5c09e703bd8..f49ae2758bb7 100644
--- a/drivers/nvme/host/scsi.c
+++ b/drivers/nvme/host/scsi.c
@@ -43,6 +43,7 @@
#include <asm/unaligned.h>
#include <scsi/sg.h>
#include <scsi/scsi.h>
+#include <scsi/scsi_request.h>
#include "nvme.h"
@@ -2347,12 +2348,14 @@ static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr *hdr)
{
- u8 cmd[BLK_MAX_CDB];
+ u8 cmd[16];
int retcode;
unsigned int opcode;
if (hdr->cmdp == NULL)
return -EMSGSIZE;
+ if (hdr->cmd_len > sizeof(cmd))
+ return -EINVAL;
if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len))
return -EFAULT;
@@ -2451,8 +2454,6 @@ int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr)
return -EFAULT;
if (hdr.interface_id != 'S')
return -EINVAL;
- if (hdr.cmd_len > BLK_MAX_CDB)
- return -EINVAL;
/*
* A positive return code means a NVMe status, which has been
generated by cgit v1.2.3 (git 2.39.0) at 2025-03-02 16:17:51 +0300