summaryrefslogtreecommitdiff
path: root/drivers/nvme
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvme')
-rw-r--r--drivers/nvme/host/core.c226
-rw-r--r--drivers/nvme/host/fabrics.h3
-rw-r--r--drivers/nvme/host/nvme.h7
-rw-r--r--drivers/nvme/host/pci.c103
-rw-r--r--drivers/nvme/host/rdma.c27
-rw-r--r--drivers/nvme/host/tcp.c15
-rw-r--r--drivers/nvme/target/io-cmd-bdev.c16
-rw-r--r--drivers/nvme/target/loop.c4
-rw-r--r--drivers/nvme/target/tcp.c12
9 files changed, 298 insertions, 115 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 108f60b46804..fa7ba09dca77 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -102,10 +102,13 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
*/
if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
return;
- revalidate_disk(ns->disk);
blk_set_queue_dying(ns->queue);
/* Forcibly unquiesce queues to avoid blocking dispatch */
blk_mq_unquiesce_queue(ns->queue);
+ /*
+ * Revalidate after unblocking dispatchers that may be holding bd_butex
+ */
+ revalidate_disk(ns->disk);
}
static void nvme_queue_scan(struct nvme_ctrl *ctrl)
@@ -113,10 +116,26 @@ static void nvme_queue_scan(struct nvme_ctrl *ctrl)
/*
* Only new queue scan work when admin and IO queues are both alive
*/
- if (ctrl->state == NVME_CTRL_LIVE)
+ if (ctrl->state == NVME_CTRL_LIVE && ctrl->tagset)
queue_work(nvme_wq, &ctrl->scan_work);
}
+/*
+ * Use this function to proceed with scheduling reset_work for a controller
+ * that had previously been set to the resetting state. This is intended for
+ * code paths that can't be interrupted by other reset attempts. A hot removal
+ * may prevent this from succeeding.
+ */
+int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
+{
+ if (ctrl->state != NVME_CTRL_RESETTING)
+ return -EBUSY;
+ if (!queue_work(nvme_reset_wq, &ctrl->reset_work))
+ return -EBUSY;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nvme_try_sched_reset);
+
int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
{
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
@@ -134,8 +153,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
ret = nvme_reset_ctrl(ctrl);
if (!ret) {
flush_work(&ctrl->reset_work);
- if (ctrl->state != NVME_CTRL_LIVE &&
- ctrl->state != NVME_CTRL_ADMIN_ONLY)
+ if (ctrl->state != NVME_CTRL_LIVE)
ret = -ENETRESET;
}
@@ -312,15 +330,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
old_state = ctrl->state;
switch (new_state) {
- case NVME_CTRL_ADMIN_ONLY:
- switch (old_state) {
- case NVME_CTRL_CONNECTING:
- changed = true;
- /* FALLTHRU */
- default:
- break;
- }
- break;
case NVME_CTRL_LIVE:
switch (old_state) {
case NVME_CTRL_NEW:
@@ -336,7 +345,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
switch (old_state) {
case NVME_CTRL_NEW:
case NVME_CTRL_LIVE:
- case NVME_CTRL_ADMIN_ONLY:
changed = true;
/* FALLTHRU */
default:
@@ -356,7 +364,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
case NVME_CTRL_DELETING:
switch (old_state) {
case NVME_CTRL_LIVE:
- case NVME_CTRL_ADMIN_ONLY:
case NVME_CTRL_RESETTING:
case NVME_CTRL_CONNECTING:
changed = true;
@@ -378,8 +385,10 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
break;
}
- if (changed)
+ if (changed) {
ctrl->state = new_state;
+ wake_up_all(&ctrl->state_wq);
+ }
spin_unlock_irqrestore(&ctrl->lock, flags);
if (changed && ctrl->state == NVME_CTRL_LIVE)
@@ -388,6 +397,39 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
+/*
+ * Returns true for sink states that can't ever transition back to live.
+ */
+static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
+{
+ switch (ctrl->state) {
+ case NVME_CTRL_NEW:
+ case NVME_CTRL_LIVE:
+ case NVME_CTRL_RESETTING:
+ case NVME_CTRL_CONNECTING:
+ return false;
+ case NVME_CTRL_DELETING:
+ case NVME_CTRL_DEAD:
+ return true;
+ default:
+ WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
+ return true;
+ }
+}
+
+/*
+ * Waits for the controller state to be resetting, or returns false if it is
+ * not possible to ever transition to that state.
+ */
+bool nvme_wait_reset(struct nvme_ctrl *ctrl)
+{
+ wait_event(ctrl->state_wq,
+ nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) ||
+ nvme_state_terminal(ctrl));
+ return ctrl->state == NVME_CTRL_RESETTING;
+}
+EXPORT_SYMBOL_GPL(nvme_wait_reset);
+
static void nvme_free_ns_head(struct kref *ref)
{
struct nvme_ns_head *head =
@@ -847,7 +889,7 @@ out:
static int nvme_submit_user_cmd(struct request_queue *q,
struct nvme_command *cmd, void __user *ubuffer,
unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
- u32 meta_seed, u32 *result, unsigned timeout)
+ u32 meta_seed, u64 *result, unsigned timeout)
{
bool write = nvme_is_write(cmd);
struct nvme_ns *ns = q->queuedata;
@@ -888,7 +930,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
else
ret = nvme_req(req)->status;
if (result)
- *result = le32_to_cpu(nvme_req(req)->result.u32);
+ *result = le64_to_cpu(nvme_req(req)->result.u64);
if (meta && !ret && !write) {
if (copy_to_user(meta_buffer, meta, meta_len))
ret = -EFAULT;
@@ -1303,8 +1345,6 @@ static void nvme_update_formats(struct nvme_ctrl *ctrl)
if (ns->disk && nvme_revalidate_disk(ns->disk))
nvme_set_queue_dying(ns);
up_read(&ctrl->namespaces_rwsem);
-
- nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
}
static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
@@ -1320,6 +1360,7 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
nvme_unfreeze(ctrl);
nvme_mpath_unfreeze(ctrl->subsys);
mutex_unlock(&ctrl->subsys->lock);
+ nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
mutex_unlock(&ctrl->scan_lock);
}
if (effects & NVME_CMD_EFFECTS_CCC)
@@ -1335,6 +1376,54 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
struct nvme_command c;
unsigned timeout = 0;
u32 effects;
+ u64 result;
+ int status;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+ return -EFAULT;
+ if (cmd.flags)
+ return -EINVAL;
+
+ memset(&c, 0, sizeof(c));
+ c.common.opcode = cmd.opcode;
+ c.common.flags = cmd.flags;
+ c.common.nsid = cpu_to_le32(cmd.nsid);
+ c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
+ c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
+ c.common.cdw10 = cpu_to_le32(cmd.cdw10);
+ c.common.cdw11 = cpu_to_le32(cmd.cdw11);
+ c.common.cdw12 = cpu_to_le32(cmd.cdw12);
+ c.common.cdw13 = cpu_to_le32(cmd.cdw13);
+ c.common.cdw14 = cpu_to_le32(cmd.cdw14);
+ c.common.cdw15 = cpu_to_le32(cmd.cdw15);
+
+ if (cmd.timeout_ms)
+ timeout = msecs_to_jiffies(cmd.timeout_ms);
+
+ effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
+ status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
+ (void __user *)(uintptr_t)cmd.addr, cmd.data_len,
+ (void __user *)(uintptr_t)cmd.metadata,
+ cmd.metadata_len, 0, &result, timeout);
+ nvme_passthru_end(ctrl, effects);
+
+ if (status >= 0) {
+ if (put_user(result, &ucmd->result))
+ return -EFAULT;
+ }
+
+ return status;
+}
+
+static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+ struct nvme_passthru_cmd64 __user *ucmd)
+{
+ struct nvme_passthru_cmd64 cmd;
+ struct nvme_command c;
+ unsigned timeout = 0;
+ u32 effects;
int status;
if (!capable(CAP_SYS_ADMIN))
@@ -1405,6 +1494,41 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
srcu_read_unlock(&head->srcu, idx);
}
+static bool is_ctrl_ioctl(unsigned int cmd)
+{
+ if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
+ return true;
+ if (is_sed_ioctl(cmd))
+ return true;
+ return false;
+}
+
+static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
+ void __user *argp,
+ struct nvme_ns_head *head,
+ int srcu_idx)
+{
+ struct nvme_ctrl *ctrl = ns->ctrl;
+ int ret;
+
+ nvme_get_ctrl(ns->ctrl);
+ nvme_put_ns_from_disk(head, srcu_idx);
+
+ switch (cmd) {
+ case NVME_IOCTL_ADMIN_CMD:
+ ret = nvme_user_cmd(ctrl, NULL, argp);
+ break;
+ case NVME_IOCTL_ADMIN64_CMD:
+ ret = nvme_user_cmd64(ctrl, NULL, argp);
+ break;
+ default:
+ ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
+ break;
+ }
+ nvme_put_ctrl(ctrl);
+ return ret;
+}
+
static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
@@ -1422,20 +1546,8 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
* seperately and drop the ns SRCU reference early. This avoids a
* deadlock when deleting namespaces using the passthrough interface.
*/
- if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) {
- struct nvme_ctrl *ctrl = ns->ctrl;
-
- nvme_get_ctrl(ns->ctrl);
- nvme_put_ns_from_disk(head, srcu_idx);
-
- if (cmd == NVME_IOCTL_ADMIN_CMD)
- ret = nvme_user_cmd(ctrl, NULL, argp);
- else
- ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
-
- nvme_put_ctrl(ctrl);
- return ret;
- }
+ if (is_ctrl_ioctl(cmd))
+ return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
switch (cmd) {
case NVME_IOCTL_ID:
@@ -1448,6 +1560,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
case NVME_IOCTL_SUBMIT_IO:
ret = nvme_submit_io(ns, argp);
break;
+ case NVME_IOCTL_IO64_CMD:
+ ret = nvme_user_cmd64(ns->ctrl, ns, argp);
+ break;
default:
if (ns->ndev)
ret = nvme_nvm_ioctl(ns, cmd, arg);
@@ -2289,6 +2404,16 @@ static const struct nvme_core_quirk_entry core_quirks[] = {
.vid = 0x14a4,
.fr = "22301111",
.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
+ },
+ {
+ /*
+ * This Kingston E8FK11.T firmware version has no interrupt
+ * after resume with actions related to suspend to idle
+ * https://bugzilla.kernel.org/show_bug.cgi?id=204887
+ */
+ .vid = 0x2646,
+ .fr = "E8FK11.T",
+ .quirks = NVME_QUIRK_SIMPLE_SUSPEND,
}
};
@@ -2540,8 +2665,9 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
list_add_tail(&subsys->entry, &nvme_subsystems);
}
- if (sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
- dev_name(ctrl->device))) {
+ ret = sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
+ dev_name(ctrl->device));
+ if (ret) {
dev_err(ctrl->device,
"failed to create sysfs link from subsystem.\n");
goto out_put_subsystem;
@@ -2786,7 +2912,6 @@ static int nvme_dev_open(struct inode *inode, struct file *file)
switch (ctrl->state) {
case NVME_CTRL_LIVE:
- case NVME_CTRL_ADMIN_ONLY:
break;
default:
return -EWOULDBLOCK;
@@ -2838,6 +2963,8 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
return nvme_user_cmd(ctrl, NULL, argp);
+ case NVME_IOCTL_ADMIN64_CMD:
+ return nvme_user_cmd64(ctrl, NULL, argp);
case NVME_IOCTL_IO_CMD:
return nvme_dev_user_cmd(ctrl, argp);
case NVME_IOCTL_RESET:
@@ -3045,6 +3172,8 @@ static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
nvme_show_int_function(cntlid);
nvme_show_int_function(numa_node);
+nvme_show_int_function(queue_count);
+nvme_show_int_function(sqsize);
static ssize_t nvme_sysfs_delete(struct device *dev,
struct device_attribute *attr, const char *buf,
@@ -3076,7 +3205,6 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
static const char *const state_name[] = {
[NVME_CTRL_NEW] = "new",
[NVME_CTRL_LIVE] = "live",
- [NVME_CTRL_ADMIN_ONLY] = "only-admin",
[NVME_CTRL_RESETTING] = "resetting",
[NVME_CTRL_CONNECTING] = "connecting",
[NVME_CTRL_DELETING] = "deleting",
@@ -3125,6 +3253,8 @@ static struct attribute *nvme_dev_attrs[] = {
&dev_attr_address.attr,
&dev_attr_state.attr,
&dev_attr_numa_node.attr,
+ &dev_attr_queue_count.attr,
+ &dev_attr_sqsize.attr,
NULL
};
@@ -3585,11 +3715,10 @@ static void nvme_scan_work(struct work_struct *work)
struct nvme_id_ctrl *id;
unsigned nn;
- if (ctrl->state != NVME_CTRL_LIVE)
+ /* No tagset on a live ctrl means IO queues could not created */
+ if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset)
return;
- WARN_ON_ONCE(!ctrl->tagset);
-
if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) {
dev_info(ctrl->device, "rescanning namespaces.\n");
nvme_clear_changed_ns_log(ctrl);
@@ -3750,13 +3879,13 @@ static void nvme_fw_act_work(struct work_struct *work)
if (time_after(jiffies, fw_act_timeout)) {
dev_warn(ctrl->device,
"Fw activation timeout, reset controller\n");
- nvme_reset_ctrl(ctrl);
- break;
+ nvme_try_sched_reset(ctrl);
+ return;
}
msleep(100);
}
- if (ctrl->state != NVME_CTRL_LIVE)
+ if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
return;
nvme_start_queues(ctrl);
@@ -3776,7 +3905,13 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
nvme_queue_scan(ctrl);
break;
case NVME_AER_NOTICE_FW_ACT_STARTING:
- queue_work(nvme_wq, &ctrl->fw_act_work);
+ /*
+ * We are (ab)using the RESETTING state to prevent subsequent
+ * recovery actions from interfering with the controller's
+ * firmware activation.
+ */
+ if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
+ queue_work(nvme_wq, &ctrl->fw_act_work);
break;
#ifdef CONFIG_NVME_MULTIPATH
case NVME_AER_NOTICE_ANA:
@@ -3899,6 +4034,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
INIT_WORK(&ctrl->async_event_work, nvme_async_event_work);
INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
+ init_waitqueue_head(&ctrl->state_wq);
INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 93f08d77c896..a0ec40ab62ee 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -182,8 +182,7 @@ bool nvmf_ip_options_match(struct nvme_ctrl *ctrl,
static inline bool nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
bool queue_live)
{
- if (likely(ctrl->state == NVME_CTRL_LIVE ||
- ctrl->state == NVME_CTRL_ADMIN_ONLY))
+ if (likely(ctrl->state == NVME_CTRL_LIVE))
return true;
return __nvmf_check_ready(ctrl, rq, queue_live);
}
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b5013c101b35..22e8401352c2 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -15,6 +15,7 @@
#include <linux/sed-opal.h>
#include <linux/fault-inject.h>
#include <linux/rcupdate.h>
+#include <linux/wait.h>
#include <trace/events/block.h>
@@ -161,7 +162,6 @@ static inline u16 nvme_req_qid(struct request *req)
enum nvme_ctrl_state {
NVME_CTRL_NEW,
NVME_CTRL_LIVE,
- NVME_CTRL_ADMIN_ONLY, /* Only admin queue live */
NVME_CTRL_RESETTING,
NVME_CTRL_CONNECTING,
NVME_CTRL_DELETING,
@@ -199,6 +199,7 @@ struct nvme_ctrl {
struct cdev cdev;
struct work_struct reset_work;
struct work_struct delete_work;
+ wait_queue_head_t state_wq;
struct nvme_subsystem *subsys;
struct list_head subsys_entry;
@@ -221,6 +222,7 @@ struct nvme_ctrl {
u16 oacs;
u16 nssa;
u16 nr_streams;
+ u16 sqsize;
u32 max_namespaces;
atomic_t abort_limit;
u8 vwc;
@@ -269,7 +271,6 @@ struct nvme_ctrl {
u16 hmmaxd;
/* Fabrics only */
- u16 sqsize;
u32 ioccsz;
u32 iorcsz;
u16 icdoff;
@@ -449,6 +450,7 @@ void nvme_complete_rq(struct request *req);
bool nvme_cancel_request(struct request *req, void *data, bool reserved);
bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
enum nvme_ctrl_state new_state);
+bool nvme_wait_reset(struct nvme_ctrl *ctrl);
int nvme_disable_ctrl(struct nvme_ctrl *ctrl);
int nvme_enable_ctrl(struct nvme_ctrl *ctrl);
int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl);
@@ -499,6 +501,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
int nvme_reset_ctrl(struct nvme_ctrl *ctrl);
int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
+int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c0808f9eb8ab..869f462e6b6e 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -773,7 +773,8 @@ static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev,
struct bio_vec *bv)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
- unsigned int first_prp_len = dev->ctrl.page_size - bv->bv_offset;
+ unsigned int offset = bv->bv_offset & (dev->ctrl.page_size - 1);
+ unsigned int first_prp_len = dev->ctrl.page_size - offset;
iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0);
if (dma_mapping_error(dev->dev, iod->first_dma))
@@ -2263,10 +2264,7 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode)
return true;
}
-/*
- * return error value only when tagset allocation failed
- */
-static int nvme_dev_add(struct nvme_dev *dev)
+static void nvme_dev_add(struct nvme_dev *dev)
{
int ret;
@@ -2296,7 +2294,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
if (ret) {
dev_warn(dev->ctrl.device,
"IO queues tagset allocation failed %d\n", ret);
- return ret;
+ return;
}
dev->ctrl.tagset = &dev->tagset;
} else {
@@ -2307,7 +2305,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
}
nvme_dbbuf_set(dev);
- return 0;
}
static int nvme_pci_enable(struct nvme_dev *dev)
@@ -2467,6 +2464,14 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
mutex_unlock(&dev->shutdown_lock);
}
+static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
+{
+ if (!nvme_wait_reset(&dev->ctrl))
+ return -EBUSY;
+ nvme_dev_disable(dev, shutdown);
+ return 0;
+}
+
static int nvme_setup_prp_pools(struct nvme_dev *dev)
{
dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
@@ -2490,14 +2495,20 @@ static void nvme_release_prp_pools(struct nvme_dev *dev)
dma_pool_destroy(dev->prp_small_pool);
}
+static void nvme_free_tagset(struct nvme_dev *dev)
+{
+ if (dev->tagset.tags)
+ blk_mq_free_tag_set(&dev->tagset);
+ dev->ctrl.tagset = NULL;
+}
+
static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
{
struct nvme_dev *dev = to_nvme_dev(ctrl);
nvme_dbbuf_dma_free(dev);
put_device(dev->dev);
- if (dev->tagset.tags)
- blk_mq_free_tag_set(&dev->tagset);
+ nvme_free_tagset(dev);
if (dev->ctrl.admin_q)
blk_put_queue(dev->ctrl.admin_q);
kfree(dev->queues);
@@ -2508,6 +2519,11 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
static void nvme_remove_dead_ctrl(struct nvme_dev *dev)
{
+ /*
+ * Set state to deleting now to avoid blocking nvme_wait_reset(), which
+ * may be holding this pci_dev's device lock.
+ */
+ nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
nvme_get_ctrl(&dev->ctrl);
nvme_dev_disable(dev, false);
nvme_kill_queues(&dev->ctrl);
@@ -2521,7 +2537,6 @@ static void nvme_reset_work(struct work_struct *work)
container_of(work, struct nvme_dev, ctrl.reset_work);
bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
int result;
- enum nvme_ctrl_state new_state = NVME_CTRL_LIVE;
if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) {
result = -ENODEV;
@@ -2615,13 +2630,11 @@ static void nvme_reset_work(struct work_struct *work)
dev_warn(dev->ctrl.device, "IO queues not created\n");
nvme_kill_queues(&dev->ctrl);
nvme_remove_namespaces(&dev->ctrl);
- new_state = NVME_CTRL_ADMIN_ONLY;
+ nvme_free_tagset(dev);
} else {
nvme_start_queues(&dev->ctrl);
nvme_wait_freeze(&dev->ctrl);
- /* hit this only when allocate tagset fails */
- if (nvme_dev_add(dev))
- new_state = NVME_CTRL_ADMIN_ONLY;
+ nvme_dev_add(dev);
nvme_unfreeze(&dev->ctrl);
}
@@ -2629,9 +2642,9 @@ static void nvme_reset_work(struct work_struct *work)
* If only admin queue live, keep it to do further investigation or
* recovery.
*/
- if (!nvme_change_ctrl_state(&dev->ctrl, new_state)) {
+ if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) {
dev_warn(dev->ctrl.device,
- "failed to mark controller state %d\n", new_state);
+ "failed to mark controller live state\n");
result = -ENODEV;
goto out;
}
@@ -2672,7 +2685,7 @@ static int nvme_pci_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
{
- *val = readq(to_nvme_dev(ctrl)->bar + off);
+ *val = lo_hi_readq(to_nvme_dev(ctrl)->bar + off);
return 0;
}
@@ -2836,19 +2849,28 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
static void nvme_reset_prepare(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
- nvme_dev_disable(dev, false);
+
+ /*
+ * We don't need to check the return value from waiting for the reset
+ * state as pci_dev device lock is held, making it impossible to race
+ * with ->remove().
+ */
+ nvme_disable_prepare_reset(dev, false);
+ nvme_sync_queues(&dev->ctrl);
}
static void nvme_reset_done(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
- nvme_reset_ctrl_sync(&dev->ctrl);
+
+ if (!nvme_try_sched_reset(&dev->ctrl))
+ flush_work(&dev->ctrl.reset_work);
}
static void nvme_shutdown(struct pci_dev *pdev)
{
struct nvme_dev *dev = pci_get_drvdata(pdev);
- nvme_dev_disable(dev, true);
+ nvme_disable_prepare_reset(dev, true);
}
/*
@@ -2901,7 +2923,7 @@ static int nvme_resume(struct device *dev)
if (ndev->last_ps == U32_MAX ||
nvme_set_power_state(ctrl, ndev->last_ps) != 0)
- nvme_reset_ctrl(ctrl);
+ return nvme_try_sched_reset(&ndev->ctrl);
return 0;
}
@@ -2929,43 +2951,42 @@ static int nvme_suspend(struct device *dev)
*/
if (pm_suspend_via_firmware() || !ctrl->npss ||
!pcie_aspm_enabled(pdev) ||
- (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND)) {
- nvme_dev_disable(ndev, true);
- return 0;
- }
+ (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND))
+ return nvme_disable_prepare_reset(ndev, true);
nvme_start_freeze(ctrl);
nvme_wait_freeze(ctrl);
nvme_sync_queues(ctrl);
- if (ctrl->state != NVME_CTRL_LIVE &&
- ctrl->state != NVME_CTRL_ADMIN_ONLY)
+ if (ctrl->state != NVME_CTRL_LIVE)
goto unfreeze;
ret = nvme_get_power_state(ctrl, &ndev->last_ps);
if (ret < 0)
goto unfreeze;
+ /*
+ * A saved state prevents pci pm from generically controlling the
+ * device's power. If we're using protocol specific settings, we don't
+ * want pci interfering.
+ */
+ pci_save_state(pdev);
+
ret = nvme_set_power_state(ctrl, ctrl->npss);
if (ret < 0)
goto unfreeze;
if (ret) {
+ /* discard the saved state */
+ pci_load_saved_state(pdev, NULL);
+
/*
* Clearing npss forces a controller reset on resume. The
* correct value will be resdicovered then.
*/
- nvme_dev_disable(ndev, true);
+ ret = nvme_disable_prepare_reset(ndev, true);
ctrl->npss = 0;
- ret = 0;
- goto unfreeze;
}
- /*
- * A saved state prevents pci pm from generically controlling the
- * device's power. If we're using protocol specific settings, we don't
- * want pci interfering.
- */
- pci_save_state(pdev);
unfreeze:
nvme_unfreeze(ctrl);
return ret;
@@ -2974,9 +2995,7 @@ unfreeze:
static int nvme_simple_suspend(struct device *dev)
{
struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
-
- nvme_dev_disable(ndev, true);
- return 0;
+ return nvme_disable_prepare_reset(ndev, true);
}
static int nvme_simple_resume(struct device *dev)
@@ -2984,8 +3003,7 @@ static int nvme_simple_resume(struct device *dev)
struct pci_dev *pdev = to_pci_dev(dev);
struct nvme_dev *ndev = pci_get_drvdata(pdev);
- nvme_reset_ctrl(&ndev->ctrl);
- return 0;
+ return nvme_try_sched_reset(&ndev->ctrl);
}
static const struct dev_pm_ops nvme_dev_pm_ops = {
@@ -3090,6 +3108,9 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_LIGHTNVM, },
{ PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */
.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+ { PCI_DEVICE(0x1cc1, 0x8201), /* ADATA SX8200PNP 512GB */
+ .driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+ NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index dfa07bb9dfeb..f19a28b4e997 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -427,7 +427,7 @@ static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
static int nvme_rdma_get_max_fr_pages(struct ib_device *ibdev)
{
return min_t(u32, NVME_RDMA_MAX_SEGMENTS,
- ibdev->attrs.max_fast_reg_page_list_len);
+ ibdev->attrs.max_fast_reg_page_list_len - 1);
}
static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
@@ -437,7 +437,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
const int cq_factor = send_wr_factor + 1; /* + RECV */
int comp_vector, idx = nvme_rdma_queue_idx(queue);
enum ib_poll_context poll_ctx;
- int ret;
+ int ret, pages_per_mr;
queue->device = nvme_rdma_find_get_device(queue->cm_id);
if (!queue->device) {
@@ -479,10 +479,16 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
goto out_destroy_qp;
}
+ /*
+ * Currently we don't use SG_GAPS MR's so if the first entry is
+ * misaligned we'll end up using two entries for a single data page,
+ * so one additional entry is required.
+ */
+ pages_per_mr = nvme_rdma_get_max_fr_pages(ibdev) + 1;
ret = ib_mr_pool_init(queue->qp, &queue->qp->rdma_mrs,
queue->queue_size,
IB_MR_TYPE_MEM_REG,
- nvme_rdma_get_max_fr_pages(ibdev), 0);
+ pages_per_mr, 0);
if (ret) {
dev_err(queue->ctrl->ctrl.device,
"failed to initialize MR pool sized %d for QID %d\n",
@@ -614,7 +620,8 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx)
if (!ret) {
set_bit(NVME_RDMA_Q_LIVE, &queue->flags);
} else {
- __nvme_rdma_stop_queue(queue);
+ if (test_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
+ __nvme_rdma_stop_queue(queue);
dev_info(ctrl->ctrl.device,
"failed to connect queue: %d ret=%d\n", idx, ret);
}
@@ -820,8 +827,8 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
if (error)
goto out_stop_queue;
- ctrl->ctrl.max_hw_sectors =
- (ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9);
+ ctrl->ctrl.max_segments = ctrl->max_fr_pages;
+ ctrl->ctrl.max_hw_sectors = ctrl->max_fr_pages << (ilog2(SZ_4K) - 9);
blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
@@ -1694,6 +1701,14 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
rq->tag, nvme_rdma_queue_idx(queue));
+ /*
+ * Restart the timer if a controller reset is already scheduled. Any
+ * timed out commands would be handled before entering the connecting
+ * state.
+ */
+ if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
+ return BLK_EH_RESET_TIMER;
+
if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
/*
* Teardown immediately if controller times out while starting
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 4ffd5957637a..770dbcbc999e 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1042,7 +1042,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
{
struct nvme_tcp_queue *queue =
container_of(w, struct nvme_tcp_queue, io_work);
- unsigned long start = jiffies + msecs_to_jiffies(1);
+ unsigned long deadline = jiffies + msecs_to_jiffies(1);
do {
bool pending = false;
@@ -1067,7 +1067,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
if (!pending)
return;
- } while (time_after(jiffies, start)); /* quota is exhausted */
+ } while (!time_after(jiffies, deadline)); /* quota is exhausted */
queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
}
@@ -1386,7 +1386,9 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
queue->sock->sk->sk_data_ready = nvme_tcp_data_ready;
queue->sock->sk->sk_state_change = nvme_tcp_state_change;
queue->sock->sk->sk_write_space = nvme_tcp_write_space;
+#ifdef CONFIG_NET_RX_BUSY_POLL
queue->sock->sk->sk_ll_usec = 1;
+#endif
write_unlock_bh(&queue->sock->sk->sk_callback_lock);
return 0;
@@ -2044,6 +2046,14 @@ nvme_tcp_timeout(struct request *rq, bool reserved)
struct nvme_tcp_ctrl *ctrl = req->queue->ctrl;
struct nvme_tcp_cmd_pdu *pdu = req->pdu;
+ /*
+ * Restart the timer if a controller reset is already scheduled. Any
+ * timed out commands would be handled before entering the connecting
+ * state.
+ */
+ if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
+ return BLK_EH_RESET_TIMER;
+
dev_warn(ctrl->ctrl.device,
"queue %d: timeout request %#x type %d\n",
nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type);
@@ -2126,6 +2136,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
ret = nvme_tcp_map_data(queue, rq);
if (unlikely(ret)) {
+ nvme_cleanup_cmd(rq);
dev_err(queue->ctrl->ctrl.device,
"Failed to map data (%d)\n", ret);
return ret;
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index de0bff70ebb6..32008d85172b 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -11,10 +11,10 @@
void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
{
const struct queue_limits *ql = &bdev_get_queue(bdev)->limits;
- /* Number of physical blocks per logical block. */
- const u32 ppl = ql->physical_block_size / ql->logical_block_size;
- /* Physical blocks per logical block, 0's based. */
- const __le16 ppl0b = to0based(ppl);
+ /* Number of logical blocks per physical block. */
+ const u32 lpp = ql->physical_block_size / ql->logical_block_size;
+ /* Logical blocks per physical block, 0's based. */
+ const __le16 lpp0b = to0based(lpp);
/*
* For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN,
@@ -25,9 +25,9 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
* field from the identify controller data structure should be used.
*/
id->nsfeat |= 1 << 1;
- id->nawun = ppl0b;
- id->nawupf = ppl0b;
- id->nacwu = ppl0b;
+ id->nawun = lpp0b;
+ id->nawupf = lpp0b;
+ id->nacwu = lpp0b;
/*
* Bit 4 indicates that the fields NPWG, NPWA, NPDG, NPDA, and
@@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
*/
id->nsfeat |= 1 << 4;
/* NPWG = Namespace Preferred Write Granularity. 0's based */
- id->npwg = ppl0b;
+ id->npwg = lpp0b;
/* NPWA = Namespace Preferred Write Alignment. 0's based */
id->npwa = id->npwg;
/* NPDG = Namespace Preferred Deallocate Granularity. 0's based */
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 748a39fca771..11f5aea97d1b 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -157,8 +157,10 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
iod->sg_table.sgl = iod->first_sgl;
if (sg_alloc_table_chained(&iod->sg_table,
blk_rq_nr_phys_segments(req),
- iod->sg_table.sgl, SG_CHUNK_SIZE))
+ iod->sg_table.sgl, SG_CHUNK_SIZE)) {
+ nvme_cleanup_cmd(req);
return BLK_STS_RESOURCE;
+ }
iod->req.sg = iod->sg_table.sgl;
iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl);
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index bf4f03474e89..d535080b781f 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -348,8 +348,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
return 0;
err:
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
return NVME_SC_INTERNAL;
}
@@ -554,8 +553,7 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
if (queue->nvme_sq.sqhd_disabled) {
kfree(cmd->iov);
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
}
return 1;
@@ -586,8 +584,7 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
return -EAGAIN;
kfree(cmd->iov);
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
cmd->queue->snd_cmd = NULL;
nvmet_tcp_put_cmd(cmd);
return 1;
@@ -1310,8 +1307,7 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd)
nvmet_req_uninit(&cmd->req);
nvmet_tcp_unmap_pdu_iovec(cmd);
kfree(cmd->iov);
- if (cmd->req.sg_cnt)
- sgl_free(cmd->req.sg);
+ sgl_free(cmd->req.sg);
}
static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
generated by cgit (git 2.34.1) at 2024-04-28 11:11:54 +0000