summaryrefslogtreecommitdiff
path: root/drivers/nvme/host
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvme/host')
-rw-r--r--drivers/nvme/host/Kconfig2
-rw-r--r--drivers/nvme/host/constants.c2
-rw-r--r--drivers/nvme/host/core.c115
-rw-r--r--drivers/nvme/host/fabrics.c2
-rw-r--r--drivers/nvme/host/fabrics.h6
-rw-r--r--drivers/nvme/host/fc.c4
-rw-r--r--drivers/nvme/host/ioctl.c39
-rw-r--r--drivers/nvme/host/multipath.c14
-rw-r--r--drivers/nvme/host/nvme.h5
-rw-r--r--drivers/nvme/host/pci.c10
-rw-r--r--drivers/nvme/host/pr.c2
-rw-r--r--drivers/nvme/host/rdma.c4
-rw-r--r--drivers/nvme/host/tcp.c24
13 files changed, 125 insertions, 104 deletions
diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig
index 7dca58f0a237..31974c7dd20c 100644
--- a/drivers/nvme/host/Kconfig
+++ b/drivers/nvme/host/Kconfig
@@ -106,7 +106,7 @@ config NVME_TCP_TLS
help
Enables TLS encryption for NVMe TCP using the netlink handshake API.
- The TLS handshake daemon is availble at
+ The TLS handshake daemon is available at
https://github.com/oracle/ktls-utils.
If unsure, say N.
diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 2b9e6cfaf2a8..1a0058be5821 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -145,7 +145,7 @@ static const char * const nvme_statuses[] = {
[NVME_SC_BAD_ATTRIBUTES] = "Conflicting Attributes",
[NVME_SC_INVALID_PI] = "Invalid Protection Information",
[NVME_SC_READ_ONLY] = "Attempted Write to Read Only Range",
- [NVME_SC_ONCS_NOT_SUPPORTED] = "ONCS Not Supported",
+ [NVME_SC_CMD_SIZE_LIM_EXCEEDED ] = "Command Size Limits Exceeded",
[NVME_SC_ZONE_BOUNDARY_ERROR] = "Zoned Boundary Error",
[NVME_SC_ZONE_FULL] = "Zone Is Full",
[NVME_SC_ZONE_READ_ONLY] = "Zone Is Read Only",
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f69a232a000a..895fb163d48e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -290,7 +290,6 @@ static blk_status_t nvme_error_status(u16 status)
case NVME_SC_NS_NOT_READY:
return BLK_STS_TARGET;
case NVME_SC_BAD_ATTRIBUTES:
- case NVME_SC_ONCS_NOT_SUPPORTED:
case NVME_SC_INVALID_OPCODE:
case NVME_SC_INVALID_FIELD:
case NVME_SC_INVALID_NS:
@@ -382,12 +381,12 @@ static void nvme_log_err_passthru(struct request *req)
nr->status & NVME_SC_MASK, /* Status Code */
nr->status & NVME_STATUS_MORE ? "MORE " : "",
nr->status & NVME_STATUS_DNR ? "DNR " : "",
- nr->cmd->common.cdw10,
- nr->cmd->common.cdw11,
- nr->cmd->common.cdw12,
- nr->cmd->common.cdw13,
- nr->cmd->common.cdw14,
- nr->cmd->common.cdw14);
+ le32_to_cpu(nr->cmd->common.cdw10),
+ le32_to_cpu(nr->cmd->common.cdw11),
+ le32_to_cpu(nr->cmd->common.cdw12),
+ le32_to_cpu(nr->cmd->common.cdw13),
+ le32_to_cpu(nr->cmd->common.cdw14),
+ le32_to_cpu(nr->cmd->common.cdw15));
}
enum nvme_disposition {
@@ -765,6 +764,10 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
!test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
return BLK_STS_RESOURCE;
+
+ if (!(rq->rq_flags & RQF_DONTPREP))
+ nvme_clear_nvme_request(rq);
+
return nvme_host_path_error(rq);
}
EXPORT_SYMBOL_GPL(nvme_fail_nonready_command);
@@ -1027,7 +1030,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
if (ns->head->ms) {
/*
- * If formated with metadata, the block layer always provides a
+ * If formatted with metadata, the block layer always provides a
* metadata buffer if CONFIG_BLK_DEV_INTEGRITY is enabled. Else
* we enable the PRACT bit for protection information or set the
* namespace capacity to zero to prevent any I/O.
@@ -2016,21 +2019,41 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl,
}
-static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns,
- struct nvme_id_ns *id, struct queue_limits *lim,
- u32 bs, u32 atomic_bs)
+static u32 nvme_configure_atomic_write(struct nvme_ns *ns,
+ struct nvme_id_ns *id, struct queue_limits *lim, u32 bs)
{
- unsigned int boundary = 0;
+ u32 atomic_bs, boundary = 0;
+
+ /*
+ * We do not support an offset for the atomic boundaries.
+ */
+ if (id->nabo)
+ return bs;
- if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) {
- if (le16_to_cpu(id->nabspf))
+ if ((id->nsfeat & NVME_NS_FEAT_ATOMICS) && id->nawupf) {
+ /*
+ * Use the per-namespace atomic write unit when available.
+ */
+ atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
+ if (id->nabspf)
boundary = (le16_to_cpu(id->nabspf) + 1) * bs;
+ } else {
+ /*
+ * Use the controller wide atomic write unit. This sucks
+ * because the limit is defined in terms of logical blocks while
+ * namespaces can have different formats, and because there is
+ * no clear language in the specification prohibiting different
+ * values for different controllers in the subsystem.
+ */
+ atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
}
+
lim->atomic_write_hw_max = atomic_bs;
lim->atomic_write_hw_boundary = boundary;
lim->atomic_write_hw_unit_min = bs;
lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs);
lim->features |= BLK_FEAT_ATOMIC_WRITES;
+ return atomic_bs;
}
static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl)
@@ -2068,34 +2091,8 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
valid = false;
}
- atomic_bs = phys_bs = bs;
- if (id->nabo == 0) {
- /*
- * Bit 1 indicates whether NAWUPF is defined for this namespace
- * and whether it should be used instead of AWUPF. If NAWUPF ==
- * 0 then AWUPF must be used instead.
- */
- if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
- atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
- else
- atomic_bs = (1 + ns->ctrl->awupf) * bs;
-
- /*
- * Set subsystem atomic bs.
- */
- if (ns->ctrl->subsys->atomic_bs) {
- if (atomic_bs != ns->ctrl->subsys->atomic_bs) {
- dev_err_ratelimited(ns->ctrl->device,
- "%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n",
- ns->disk ? ns->disk->disk_name : "?",
- ns->ctrl->subsys->atomic_bs,
- atomic_bs);
- }
- } else
- ns->ctrl->subsys->atomic_bs = atomic_bs;
-
- nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs);
- }
+ phys_bs = bs;
+ atomic_bs = nvme_configure_atomic_write(ns, id, lim, bs);
if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
/* NPWG = Namespace Preferred Write Granularity */
@@ -2383,16 +2380,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
if (!nvme_update_disk_info(ns, id, &lim))
capacity = 0;
- /*
- * Validate the max atomic write size fits within the subsystem's
- * atomic write capabilities.
- */
- if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) {
- blk_mq_unfreeze_queue(ns->disk->queue, memflags);
- ret = -ENXIO;
- goto out;
- }
-
nvme_config_discard(ns, &lim);
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
ns->head->ids.csi == NVME_CSI_ZNS)
@@ -3216,6 +3203,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
memcpy(subsys->model, id->mn, sizeof(subsys->model));
subsys->vendor_id = le16_to_cpu(id->vid);
subsys->cmic = id->cmic;
+ subsys->awupf = le16_to_cpu(id->awupf);
/* Versions prior to 1.4 don't necessarily report a valid type */
if (id->cntrltype == NVME_CTRL_DISC ||
@@ -3648,7 +3636,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
dev_pm_qos_expose_latency_tolerance(ctrl->device);
else if (!ctrl->apst_enabled && prev_apst_enabled)
dev_pm_qos_hide_latency_tolerance(ctrl->device);
- ctrl->awupf = le16_to_cpu(id->awupf);
out_free:
kfree(id);
return ret;
@@ -4037,6 +4024,10 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
list_add_tail_rcu(&ns->siblings, &head->list);
ns->head = head;
mutex_unlock(&ctrl->subsys->lock);
+
+#ifdef CONFIG_NVME_MULTIPATH
+ cancel_delayed_work(&head->remove_work);
+#endif
return 0;
out_put_ns_head:
@@ -4081,7 +4072,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns)
return;
}
}
- list_add(&ns->list, &ns->ctrl->namespaces);
+ list_add_rcu(&ns->list, &ns->ctrl->namespaces);
}
static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
@@ -4090,6 +4081,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
struct nvme_ns *ns;
struct gendisk *disk;
int node = ctrl->numa_node;
+ bool last_path = false;
ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
if (!ns)
@@ -4182,9 +4174,22 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
out_unlink_ns:
mutex_lock(&ctrl->subsys->lock);
list_del_rcu(&ns->siblings);
- if (list_empty(&ns->head->list))
+ if (list_empty(&ns->head->list)) {
list_del_init(&ns->head->entry);
+ /*
+ * If multipath is not configured, we still create a namespace
+ * head (nshead), but head->disk is not initialized in that
+ * case. As a result, only a single reference to nshead is held
+ * (via kref_init()) when it is created. Therefore, ensure that
+ * we do not release the reference to nshead twice if head->disk
+ * is not present.
+ */
+ if (ns->head->disk)
+ last_path = true;
+ }
mutex_unlock(&ctrl->subsys->lock);
+ if (last_path)
+ nvme_put_ns_head(ns->head);
nvme_put_ns_head(ns->head);
out_cleanup_disk:
put_disk(disk);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 93e9041b9657..2e58a7ce1090 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -582,7 +582,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
* Do not retry when:
*
* - the DNR bit is set and the specification states no further connect
- * attempts with the same set of paramenters should be attempted.
+ * attempts with the same set of parameters should be attempted.
*
* - when the authentication attempt fails, because the key was invalid.
* This error code is set on the host side.
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 9cf5b020adba..1b58ee7d0dce 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -80,7 +80,7 @@ enum {
* @transport: Holds the fabric transport "technology name" (for a lack of
* better description) that will be used by an NVMe controller
* being added.
- * @subsysnqn: Hold the fully qualified NQN subystem name (format defined
+ * @subsysnqn: Hold the fully qualified NQN subsystem name (format defined
* in the NVMe specification, "NVMe Qualified Names").
* @traddr: The transport-specific TRADDR field for a port on the
* subsystem which is adding a controller.
@@ -156,7 +156,7 @@ struct nvmf_ctrl_options {
* @create_ctrl(): function pointer that points to a non-NVMe
* implementation-specific fabric technology
* that would go into starting up that fabric
- * for the purpose of conneciton to an NVMe controller
+ * for the purpose of connection to an NVMe controller
* using that fabric technology.
*
* Notes:
@@ -165,7 +165,7 @@ struct nvmf_ctrl_options {
* 2. create_ctrl() must be defined (even if it does nothing)
* 3. struct nvmf_transport_ops must be statically allocated in the
* modules .bss section so that a pure module_get on @module
- * prevents the memory from beeing freed.
+ * prevents the memory from being freed.
*/
struct nvmf_transport_ops {
struct list_head entry;
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index fdafa3e9e66f..014b387f1e8b 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1955,7 +1955,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
}
/*
- * For the linux implementation, if we have an unsuccesful
+ * For the linux implementation, if we have an unsucceesful
* status, they blk-mq layer can typically be called with the
* non-zero status and the content of the cqe isn't important.
*/
@@ -2479,7 +2479,7 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
* writing the registers for shutdown and polling (call
* nvme_disable_ctrl()). Given a bunch of i/o was potentially
* just aborted and we will wait on those contexts, and given
- * there was no indication of how live the controlelr is on the
+ * there was no indication of how live the controller is on the
* link, don't send more io to create more contexts for the
* shutdown. Let the controller fail via keepalive failure if
* its still present.
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index ca86d3bf7ea4..6b3ac8ae3f34 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -429,21 +429,14 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
/*
- * For iopoll, complete it directly. Note that using the uring_cmd
- * helper for this is safe only because we check blk_rq_is_poll().
- * As that returns false if we're NOT on a polled queue, then it's
- * safe to use the polled completion helper.
- *
- * Otherwise, move the completion to task work.
+ * IOPOLL could potentially complete this request directly, but
+ * if multiple rings are polling on the same queue, then it's possible
+ * for one ring to find completions for another ring. Punting the
+ * completion via task_work will always direct it to the right
+ * location, rather than potentially complete requests for ringA
+ * under iopoll invocations from ringB.
*/
- if (blk_rq_is_poll(req)) {
- if (pdu->bio)
- blk_rq_unmap_user(pdu->bio);
- io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
- } else {
- io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
- }
-
+ io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
return RQ_END_IO_FREE;
}
@@ -493,13 +486,15 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
d.timeout_ms = READ_ONCE(cmd->timeout_ms);
if (d.data_len && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
- /* fixedbufs is only for non-vectored io */
- if (vec)
- return -EINVAL;
+ int ddir = nvme_is_write(&c) ? WRITE : READ;
- ret = io_uring_cmd_import_fixed(d.addr, d.data_len,
- nvme_is_write(&c) ? WRITE : READ, &iter, ioucmd,
- issue_flags);
+ if (vec)
+ ret = io_uring_cmd_import_fixed_vec(ioucmd,
+ u64_to_user_ptr(d.addr), d.data_len,
+ ddir, &iter, issue_flags);
+ else
+ ret = io_uring_cmd_import_fixed(d.addr, d.data_len,
+ ddir, &iter, ioucmd, issue_flags);
if (ret < 0)
return ret;
@@ -521,7 +516,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
if (d.data_len) {
ret = nvme_map_user_request(req, d.addr, d.data_len,
nvme_to_user_ptr(d.metadata), d.metadata_len,
- map_iter, vec);
+ map_iter, vec ? NVME_IOCTL_VEC : 0);
if (ret)
goto out_free_req;
}
@@ -727,7 +722,7 @@ int nvme_ns_head_ioctl(struct block_device *bdev, blk_mode_t mode,
/*
* Handle ioctls that apply to the controller instead of the namespace
- * seperately and drop the ns SRCU reference early. This avoids a
+ * separately and drop the ns SRCU reference early. This avoids a
* deadlock when deleting namespaces using the passthrough interface.
*/
if (is_ctrl_ioctl(cmd))
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 878ea8b1a0ac..3da980dc60d9 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -690,8 +690,8 @@ static void nvme_remove_head(struct nvme_ns_head *head)
nvme_cdev_del(&head->cdev, &head->cdev_device);
synchronize_srcu(&head->srcu);
del_gendisk(head->disk);
- nvme_put_ns_head(head);
}
+ nvme_put_ns_head(head);
}
static void nvme_remove_head_work(struct work_struct *work)
@@ -760,7 +760,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
* controller's scan_work context. If a path error occurs here, the IO
* will wait until a path becomes available or all paths are torn down,
* but that action also occurs within scan_work, so it would deadlock.
- * Defer the partion scan to a different context that does not block
+ * Defer the partition scan to a different context that does not block
* scan_work.
*/
set_bit(GD_SUPPRESS_PART_SCAN, &head->disk->state);
@@ -998,7 +998,7 @@ void nvme_mpath_update(struct nvme_ctrl *ctrl)
static void nvme_anatt_timeout(struct timer_list *t)
{
- struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);
+ struct nvme_ctrl *ctrl = timer_container_of(ctrl, t, anatt_timer);
dev_info(ctrl->device, "ANATT timeout, resetting controller.\n");
nvme_reset_ctrl(ctrl);
@@ -1200,7 +1200,8 @@ void nvme_mpath_add_sysfs_link(struct nvme_ns_head *head)
*/
srcu_idx = srcu_read_lock(&head->srcu);
- list_for_each_entry_rcu(ns, &head->list, siblings) {
+ list_for_each_entry_srcu(ns, &head->list, siblings,
+ srcu_read_lock_held(&head->srcu)) {
/*
* Ensure that ns path disk node is already added otherwise we
* may get invalid kobj name for target
@@ -1291,6 +1292,9 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
{
bool remove = false;
+ if (!head->disk)
+ return;
+
mutex_lock(&head->subsys->lock);
/*
* We are called when all paths have been removed, and at that point
@@ -1311,7 +1315,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
*/
if (!try_module_get(THIS_MODULE))
goto out;
- queue_delayed_work(nvme_wq, &head->remove_work,
+ mod_delayed_work(nvme_wq, &head->remove_work,
head->delayed_removal_secs * HZ);
} else {
list_del_init(&head->entry);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ad0c1f834f09..7df2ea21851f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -410,7 +410,6 @@ struct nvme_ctrl {
enum nvme_ctrl_type cntrltype;
enum nvme_dctype dctype;
- u16 awupf; /* 0's based value. */
};
static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
@@ -443,11 +442,11 @@ struct nvme_subsystem {
u8 cmic;
enum nvme_subsys_type subtype;
u16 vendor_id;
+ u16 awupf; /* 0's based value. */
struct ida ns_ida;
#ifdef CONFIG_NVME_MULTIPATH
enum nvme_iopolicy iopolicy;
#endif
- u32 atomic_bs;
};
/*
@@ -523,7 +522,7 @@ static inline bool nvme_ns_head_multipath(struct nvme_ns_head *head)
enum nvme_ns_features {
NVME_NS_EXT_LBAS = 1 << 0, /* support extended LBA format */
NVME_NS_METADATA_SUPPORTED = 1 << 1, /* support getting generated md */
- NVME_NS_DEAC = 1 << 2, /* DEAC bit in Write Zeores supported */
+ NVME_NS_DEAC = 1 << 2, /* DEAC bit in Write Zeroes supported */
};
struct nvme_ns {
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index e0bfe04a2bc2..320aaa41ec39 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2101,8 +2101,6 @@ static void nvme_map_cmb(struct nvme_dev *dev)
if ((dev->cmbsz & (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) ==
(NVME_CMBSZ_WDS | NVME_CMBSZ_RDS))
pci_p2pmem_publish(pdev, true);
-
- nvme_update_attrs(dev);
}
static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
@@ -3010,12 +3008,14 @@ static void nvme_reset_work(struct work_struct *work)
if (result < 0)
goto out;
+ nvme_update_attrs(dev);
+
result = nvme_setup_io_queues(dev);
if (result)
goto out;
/*
- * Freeze and update the number of I/O queues as thos might have
+ * Freeze and update the number of I/O queues as those might have
* changed. If there are no I/O queues left after this reset, keep the
* controller around but remove all namespaces.
*/
@@ -3186,7 +3186,7 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
/*
* Exclude some Kingston NV1 and A2000 devices from
* NVME_QUIRK_SIMPLE_SUSPEND. Do a full suspend to save a
- * lot fo energy with s2idle sleep on some TUXEDO platforms.
+ * lot of energy with s2idle sleep on some TUXEDO platforms.
*/
if (dmi_match(DMI_BOARD_NAME, "NS5X_NS7XAU") ||
dmi_match(DMI_BOARD_NAME, "NS5x_7xAU") ||
@@ -3343,6 +3343,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (result < 0)
goto out_disable;
+ nvme_update_attrs(dev);
+
result = nvme_setup_io_queues(dev);
if (result)
goto out_disable;
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index cf2d2c5039dd..ca6a74607b13 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -82,8 +82,6 @@ static int nvme_status_to_pr_err(int status)
return PR_STS_SUCCESS;
case NVME_SC_RESERVATION_CONFLICT:
return PR_STS_RESERVATION_CONFLICT;
- case NVME_SC_ONCS_NOT_SUPPORTED:
- return -EOPNOTSUPP;
case NVME_SC_BAD_ATTRIBUTES:
case NVME_SC_INVALID_OPCODE:
case NVME_SC_INVALID_FIELD:
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index b5a0295b5bf4..9bd3646568d0 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -221,7 +221,7 @@ static struct nvme_rdma_qe *nvme_rdma_alloc_ring(struct ib_device *ibdev,
/*
* Bind the CQEs (post recv buffers) DMA mapping to the RDMA queue
- * lifetime. It's safe, since any chage in the underlying RDMA device
+ * lifetime. It's safe, since any change in the underlying RDMA device
* will issue error recovery and queue re-creation.
*/
for (i = 0; i < ib_queue_size; i++) {
@@ -800,7 +800,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
/*
* Bind the async event SQE DMA mapping to the admin queue lifetime.
- * It's safe, since any chage in the underlying RDMA device will issue
+ * It's safe, since any change in the underlying RDMA device will issue
* error recovery and queue re-creation.
*/
error = nvme_rdma_alloc_qe(ctrl->device->dev, &ctrl->async_event_sqe,
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index f6379aa33d77..d924008c3949 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -452,7 +452,8 @@ nvme_tcp_fetch_request(struct nvme_tcp_queue *queue)
return NULL;
}
- list_del(&req->entry);
+ list_del_init(&req->entry);
+ init_llist_node(&req->lentry);
return req;
}
@@ -565,6 +566,8 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set,
req->queue = queue;
nvme_req(rq)->ctrl = &ctrl->ctrl;
nvme_req(rq)->cmd = &pdu->cmd;
+ init_llist_node(&req->lentry);
+ INIT_LIST_HEAD(&req->entry);
return 0;
}
@@ -769,6 +772,14 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
return -EPROTO;
}
+ if (llist_on_list(&req->lentry) ||
+ !list_empty(&req->entry)) {
+ dev_err(queue->ctrl->ctrl.device,
+ "req %d unexpected r2t while processing request\n",
+ rq->tag);
+ return -EPROTO;
+ }
+
req->pdu_len = 0;
req->h2cdata_left = r2t_length;
req->h2cdata_offset = r2t_offset;
@@ -1355,7 +1366,7 @@ static int nvme_tcp_try_recv(struct nvme_tcp_queue *queue)
queue->nr_cqe = 0;
consumed = sock->ops->read_sock(sk, &rd_desc, nvme_tcp_recv_skb);
release_sock(sk);
- return consumed;
+ return consumed == -EAGAIN ? 0 : consumed;
}
static void nvme_tcp_io_work(struct work_struct *w)
@@ -1383,6 +1394,11 @@ static void nvme_tcp_io_work(struct work_struct *w)
else if (unlikely(result < 0))
return;
+ /* did we get some space after spending time in recv? */
+ if (nvme_tcp_queue_has_pending(queue) &&
+ sk_stream_is_writeable(queue->sock->sk))
+ pending = true;
+
if (!pending || !queue->rd_enabled)
return;
@@ -2350,7 +2366,7 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new)
nvme_tcp_teardown_admin_queue(ctrl, false);
ret = nvme_tcp_configure_admin_queue(ctrl, false);
if (ret)
- return ret;
+ goto destroy_admin;
}
if (ctrl->icdoff) {
@@ -2594,6 +2610,8 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg)
ctrl->async_req.offset = 0;
ctrl->async_req.curr_bio = NULL;
ctrl->async_req.data_len = 0;
+ init_llist_node(&ctrl->async_req.lentry);
+ INIT_LIST_HEAD(&ctrl->async_req.entry);
nvme_tcp_queue_request(&ctrl->async_req, true);
}
generated by cgit (git 2.34.1) at 2025-07-24 17:14:19 +0000