summaryrefslogtreecommitdiffstats
path: root/drivers/nvme
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvme')
-rw-r--r--drivers/nvme/host/apple.c36
-rw-r--r--drivers/nvme/host/auth.c6
-rw-r--r--drivers/nvme/host/core.c616
-rw-r--r--drivers/nvme/host/fabrics.c79
-rw-r--r--drivers/nvme/host/fabrics.h2
-rw-r--r--drivers/nvme/host/fc.c8
-rw-r--r--drivers/nvme/host/ioctl.c43
-rw-r--r--drivers/nvme/host/multipath.c43
-rw-r--r--drivers/nvme/host/nvme.h31
-rw-r--r--drivers/nvme/host/pci.c21
-rw-r--r--drivers/nvme/host/pr.c5
-rw-r--r--drivers/nvme/host/rdma.c37
-rw-r--r--drivers/nvme/host/sysfs.c3
-rw-r--r--drivers/nvme/host/tcp.c58
-rw-r--r--drivers/nvme/host/trace.c105
-rw-r--r--drivers/nvme/host/zns.c41
-rw-r--r--drivers/nvme/target/admin-cmd.c2
-rw-r--r--drivers/nvme/target/auth.c38
-rw-r--r--drivers/nvme/target/configfs.c146
-rw-r--r--drivers/nvme/target/core.c38
-rw-r--r--drivers/nvme/target/discovery.c2
-rw-r--r--drivers/nvme/target/fabrics-cmd-auth.c52
-rw-r--r--drivers/nvme/target/fabrics-cmd.c22
-rw-r--r--drivers/nvme/target/fc.c19
-rw-r--r--drivers/nvme/target/fcloop.c17
-rw-r--r--drivers/nvme/target/io-cmd-bdev.c16
-rw-r--r--drivers/nvme/target/nvmet.h16
-rw-r--r--drivers/nvme/target/passthru.c8
-rw-r--r--drivers/nvme/target/rdma.c50
-rw-r--r--drivers/nvme/target/tcp.c5
-rw-r--r--drivers/nvme/target/trace.c98
-rw-r--r--drivers/nvme/target/zns.c15
32 files changed, 1084 insertions, 594 deletions
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index c727cd1f26..25ecc1a005 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -1388,7 +1388,7 @@ static void devm_apple_nvme_mempool_destroy(void *data)
mempool_destroy(data);
}
-static int apple_nvme_probe(struct platform_device *pdev)
+static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
struct apple_nvme *anv;
@@ -1396,7 +1396,7 @@ static int apple_nvme_probe(struct platform_device *pdev)
anv = devm_kzalloc(dev, sizeof(*anv), GFP_KERNEL);
if (!anv)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
anv->dev = get_device(dev);
anv->adminq.is_adminq = true;
@@ -1516,10 +1516,26 @@ static int apple_nvme_probe(struct platform_device *pdev)
goto put_dev;
}
- anv->ctrl.admin_q = blk_mq_init_queue(&anv->admin_tagset);
+ return anv;
+put_dev:
+ put_device(anv->dev);
+ return ERR_PTR(ret);
+}
+
+static int apple_nvme_probe(struct platform_device *pdev)
+{
+ struct apple_nvme *anv;
+ int ret;
+
+ anv = apple_nvme_alloc(pdev);
+ if (IS_ERR(anv))
+ return PTR_ERR(anv);
+
+ anv->ctrl.admin_q = blk_mq_alloc_queue(&anv->admin_tagset, NULL, NULL);
if (IS_ERR(anv->ctrl.admin_q)) {
ret = -ENOMEM;
- goto put_dev;
+ anv->ctrl.admin_q = NULL;
+ goto out_uninit_ctrl;
}
nvme_reset_ctrl(&anv->ctrl);
@@ -1527,12 +1543,13 @@ static int apple_nvme_probe(struct platform_device *pdev)
return 0;
-put_dev:
- put_device(anv->dev);
+out_uninit_ctrl:
+ nvme_uninit_ctrl(&anv->ctrl);
+ nvme_put_ctrl(&anv->ctrl);
return ret;
}
-static int apple_nvme_remove(struct platform_device *pdev)
+static void apple_nvme_remove(struct platform_device *pdev)
{
struct apple_nvme *anv = platform_get_drvdata(pdev);
@@ -1547,8 +1564,6 @@ static int apple_nvme_remove(struct platform_device *pdev)
apple_rtkit_shutdown(anv->rtk);
apple_nvme_detach_genpd(anv);
-
- return 0;
}
static void apple_nvme_shutdown(struct platform_device *pdev)
@@ -1598,10 +1613,11 @@ static struct platform_driver apple_nvme_driver = {
.pm = pm_sleep_ptr(&apple_nvme_pm_ops),
},
.probe = apple_nvme_probe,
- .remove = apple_nvme_remove,
+ .remove_new = apple_nvme_remove,
.shutdown = apple_nvme_shutdown,
};
module_platform_driver(apple_nvme_driver);
MODULE_AUTHOR("Sven Peter <sven@svenpeter.dev>");
+MODULE_DESCRIPTION("Apple ANS NVM Express device driver");
MODULE_LICENSE("GPL");
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index a264b3ae07..371e14f0a2 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -730,7 +730,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE);
if (ret) {
chap->status = ret;
- chap->error = -ECONNREFUSED;
+ chap->error = -EKEYREJECTED;
return;
}
@@ -797,7 +797,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1);
if (ret) {
chap->status = ret;
- chap->error = -ECONNREFUSED;
+ chap->error = -EKEYREJECTED;
return;
}
@@ -818,7 +818,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
ret = nvme_auth_process_dhchap_success1(ctrl, chap);
if (ret) {
/* Controller authentication failed */
- chap->error = -ECONNREFUSED;
+ chap->error = -EKEYREJECTED;
goto fail2;
}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 3cc79817e4..782090ce0b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -114,12 +114,21 @@ static DEFINE_MUTEX(nvme_subsystems_lock);
static DEFINE_IDA(nvme_instance_ida);
static dev_t nvme_ctrl_base_chr_devt;
-static struct class *nvme_class;
-static struct class *nvme_subsys_class;
+static int nvme_class_uevent(const struct device *dev, struct kobj_uevent_env *env);
+static const struct class nvme_class = {
+ .name = "nvme",
+ .dev_uevent = nvme_class_uevent,
+};
+
+static const struct class nvme_subsys_class = {
+ .name = "nvme-subsystem",
+};
static DEFINE_IDA(nvme_ns_chr_minor_ida);
static dev_t nvme_ns_chr_devt;
-static struct class *nvme_ns_chr_class;
+static const struct class nvme_ns_chr_class = {
+ .name = "nvme-generic",
+};
static void nvme_put_subsystem(struct nvme_subsystem *subsys);
static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
@@ -374,14 +383,14 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
if (likely(nvme_req(req)->status == 0))
return COMPLETE;
- if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED)
- return AUTHENTICATE;
-
if (blk_noretry_request(req) ||
(nvme_req(req)->status & NVME_SC_DNR) ||
nvme_req(req)->retries >= nvme_max_retries)
return COMPLETE;
+ if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED)
+ return AUTHENTICATE;
+
if (req->cmd_flags & REQ_NVME_MPATH) {
if (nvme_is_path_error(nvme_req(req)->status) ||
blk_queue_dying(req->q))
@@ -405,7 +414,15 @@ static inline void nvme_end_req_zoned(struct request *req)
}
}
-static inline void nvme_end_req(struct request *req)
+static inline void __nvme_end_req(struct request *req)
+{
+ nvme_end_req_zoned(req);
+ nvme_trace_bio_complete(req);
+ if (req->cmd_flags & REQ_NVME_MPATH)
+ nvme_mpath_end_request(req);
+}
+
+void nvme_end_req(struct request *req)
{
blk_status_t status = nvme_error_status(nvme_req(req)->status);
@@ -415,10 +432,7 @@ static inline void nvme_end_req(struct request *req)
else
nvme_log_error(req);
}
- nvme_end_req_zoned(req);
- nvme_trace_bio_complete(req);
- if (req->cmd_flags & REQ_NVME_MPATH)
- nvme_mpath_end_request(req);
+ __nvme_end_req(req);
blk_mq_end_request(req, status);
}
@@ -467,7 +481,7 @@ void nvme_complete_batch_req(struct request *req)
{
trace_nvme_complete_rq(req);
nvme_cleanup_cmd(req);
- nvme_end_req_zoned(req);
+ __nvme_end_req(req);
}
EXPORT_SYMBOL_GPL(nvme_complete_batch_req);
@@ -664,7 +678,7 @@ static void nvme_free_ns(struct kref *kref)
kfree(ns);
}
-static inline bool nvme_get_ns(struct nvme_ns *ns)
+bool nvme_get_ns(struct nvme_ns *ns)
{
return kref_get_unless_zero(&ns->kref);
}
@@ -984,6 +998,7 @@ void nvme_cleanup_cmd(struct request *req)
clear_bit_unlock(0, &ctrl->discard_page_busy);
else
kfree(bvec_virt(&req->special_vec));
+ req->rq_flags &= ~RQF_SPECIAL_PAYLOAD;
}
}
EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
@@ -1377,8 +1392,10 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
sizeof(struct nvme_id_ctrl));
- if (error)
+ if (error) {
kfree(*id);
+ *id = NULL;
+ }
return error;
}
@@ -1507,6 +1524,7 @@ int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid,
if (error) {
dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error);
kfree(*id);
+ *id = NULL;
}
return error;
}
@@ -1706,12 +1724,23 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo)
return 0;
}
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_init_integrity(struct gendisk *disk,
- struct nvme_ns_head *head, u32 max_integrity_segments)
+static bool nvme_init_integrity(struct gendisk *disk, struct nvme_ns_head *head)
{
struct blk_integrity integrity = { };
+ blk_integrity_unregister(disk);
+
+ if (!head->ms)
+ return true;
+
+ /*
+ * PI can always be supported as we can ask the controller to simply
+ * insert/strip it, which is not possible for other kinds of metadata.
+ */
+ if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) ||
+ !(head->features & NVME_NS_METADATA_SUPPORTED))
+ return nvme_ns_has_pi(head);
+
switch (head->pi_type) {
case NVME_NS_DPS_PI_TYPE3:
switch (head->guard_type) {
@@ -1754,53 +1783,29 @@ static void nvme_init_integrity(struct gendisk *disk,
}
integrity.tuple_size = head->ms;
+ integrity.pi_offset = head->pi_offset;
blk_integrity_register(disk, &integrity);
- blk_queue_max_integrity_segments(disk->queue, max_integrity_segments);
-}
-#else
-static void nvme_init_integrity(struct gendisk *disk,
- struct nvme_ns_head *head, u32 max_integrity_segments)
-{
+ return true;
}
-#endif /* CONFIG_BLK_DEV_INTEGRITY */
-static void nvme_config_discard(struct nvme_ctrl *ctrl, struct gendisk *disk,
- struct nvme_ns_head *head)
+static void nvme_config_discard(struct nvme_ns *ns, struct queue_limits *lim)
{
- struct request_queue *queue = disk->queue;
- u32 max_discard_sectors;
-
- if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(head, UINT_MAX)) {
- max_discard_sectors = nvme_lba_to_sect(head, ctrl->dmrsl);
- } else if (ctrl->oncs & NVME_CTRL_ONCS_DSM) {
- max_discard_sectors = UINT_MAX;
- } else {
- blk_queue_max_discard_sectors(queue, 0);
- return;
- }
+ struct nvme_ctrl *ctrl = ns->ctrl;
- BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
- NVME_DSM_MAX_RANGES);
+ if (ctrl->dmrsl && ctrl->dmrsl <= nvme_sect_to_lba(ns->head, UINT_MAX))
+ lim->max_hw_discard_sectors =
+ nvme_lba_to_sect(ns->head, ctrl->dmrsl);
+ else if (ctrl->oncs & NVME_CTRL_ONCS_DSM)
+ lim->max_hw_discard_sectors = UINT_MAX;
+ else
+ lim->max_hw_discard_sectors = 0;
- /*
- * If discard is already enabled, don't reset queue limits.
- *
- * This works around the fact that the block layer can't cope well with
- * updating the hardware limits when overridden through sysfs. This is
- * harmless because discard limits in NVMe are purely advisory.
- */
- if (queue->limits.max_discard_sectors)
- return;
+ lim->discard_granularity = lim->logical_block_size;
- blk_queue_max_discard_sectors(queue, max_discard_sectors);
if (ctrl->dmrl)
- blk_queue_max_discard_segments(queue, ctrl->dmrl);
+ lim->max_discard_segments = ctrl->dmrl;
else
- blk_queue_max_discard_segments(queue, NVME_DSM_MAX_RANGES);
- queue->limits.discard_granularity = queue_logical_block_size(queue);
-
- if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
- blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
+ lim->max_discard_segments = NVME_DSM_MAX_RANGES;
}
static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
@@ -1811,42 +1816,38 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
a->csi == b->csi;
}
-static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head,
- struct nvme_id_ns *id)
+static int nvme_identify_ns_nvm(struct nvme_ctrl *ctrl, unsigned int nsid,
+ struct nvme_id_ns_nvm **nvmp)
{
- bool first = id->dps & NVME_NS_DPS_PI_FIRST;
- unsigned lbaf = nvme_lbaf_index(id->flbas);
- struct nvme_command c = { };
+ struct nvme_command c = {
+ .identify.opcode = nvme_admin_identify,
+ .identify.nsid = cpu_to_le32(nsid),
+ .identify.cns = NVME_ID_CNS_CS_NS,
+ .identify.csi = NVME_CSI_NVM,
+ };
struct nvme_id_ns_nvm *nvm;
- int ret = 0;
- u32 elbaf;
-
- head->pi_size = 0;
- head->ms = le16_to_cpu(id->lbaf[lbaf].ms);
- if (!(ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
- head->pi_size = sizeof(struct t10_pi_tuple);
- head->guard_type = NVME_NVM_NS_16B_GUARD;
- goto set_pi;
- }
+ int ret;
nvm = kzalloc(sizeof(*nvm), GFP_KERNEL);
if (!nvm)
return -ENOMEM;
- c.identify.opcode = nvme_admin_identify;
- c.identify.nsid = cpu_to_le32(head->ns_id);
- c.identify.cns = NVME_ID_CNS_CS_NS;
- c.identify.csi = NVME_CSI_NVM;
-
ret = nvme_submit_sync_cmd(ctrl->admin_q, &c, nvm, sizeof(*nvm));
if (ret)
- goto free_data;
+ kfree(nvm);
+ else
+ *nvmp = nvm;
+ return ret;
+}
- elbaf = le32_to_cpu(nvm->elbaf[lbaf]);
+static void nvme_configure_pi_elbas(struct nvme_ns_head *head,
+ struct nvme_id_ns *id, struct nvme_id_ns_nvm *nvm)
+{
+ u32 elbaf = le32_to_cpu(nvm->elbaf[nvme_lbaf_index(id->flbas)]);
/* no support for storage tag formats right now */
if (nvme_elbaf_sts(elbaf))
- goto free_data;
+ return;
head->guard_type = nvme_elbaf_guard_type(elbaf);
switch (head->guard_type) {
@@ -1859,30 +1860,31 @@ static int nvme_init_ms(struct nvme_ctrl *ctrl, struct nvme_ns_head *head,
default:
break;
}
-
-free_data:
- kfree(nvm);
-set_pi:
- if (head->pi_size && (first || head->ms == head->pi_size))
- head->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
- else
- head->pi_type = 0;
-
- return ret;
}
-static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
- struct nvme_ns_head *head, struct nvme_id_ns *id)
+static void nvme_configure_metadata(struct nvme_ctrl *ctrl,
+ struct nvme_ns_head *head, struct nvme_id_ns *id,
+ struct nvme_id_ns_nvm *nvm)
{
- int ret;
-
- ret = nvme_init_ms(ctrl, head, id);
- if (ret)
- return ret;
-
head->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+ head->pi_type = 0;
+ head->pi_size = 0;
+ head->pi_offset = 0;
+ head->ms = le16_to_cpu(id->lbaf[nvme_lbaf_index(id->flbas)].ms);
if (!head->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
- return 0;
+ return;
+
+ if (nvm && (ctrl->ctratt & NVME_CTRL_ATTR_ELBAS)) {
+ nvme_configure_pi_elbas(head, id, nvm);
+ } else {
+ head->pi_size = sizeof(struct t10_pi_tuple);
+ head->guard_type = NVME_NVM_NS_16B_GUARD;
+ }
+
+ if (head->pi_size && head->ms >= head->pi_size)
+ head->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
+ if (!(id->dps & NVME_NS_DPS_PI_FIRST))
+ head->pi_offset = head->ms - head->pi_size;
if (ctrl->ops->flags & NVME_F_FABRICS) {
/*
@@ -1891,7 +1893,7 @@ static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
* remap the separate metadata buffer from the block layer.
*/
if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
- return 0;
+ return;
head->features |= NVME_NS_EXT_LBAS;
@@ -1918,33 +1920,32 @@ static int nvme_configure_metadata(struct nvme_ctrl *ctrl,
else
head->features |= NVME_NS_METADATA_SUPPORTED;
}
- return 0;
}
-static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
- struct request_queue *q)
+static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl)
{
- bool vwc = ctrl->vwc & NVME_CTRL_VWC_PRESENT;
-
- if (ctrl->max_hw_sectors) {
- u32 max_segments =
- (ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> 9)) + 1;
+ return ctrl->max_hw_sectors / (NVME_CTRL_PAGE_SIZE >> SECTOR_SHIFT) + 1;
+}
- max_segments = min_not_zero(max_segments, ctrl->max_segments);
- blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors);
- blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX));
- }
- blk_queue_virt_boundary(q, NVME_CTRL_PAGE_SIZE - 1);
- blk_queue_dma_alignment(q, 3);
- blk_queue_write_cache(q, vwc, vwc);
+static void nvme_set_ctrl_limits(struct nvme_ctrl *ctrl,
+ struct queue_limits *lim)
+{
+ lim->max_hw_sectors = ctrl->max_hw_sectors;
+ lim->max_segments = min_t(u32, USHRT_MAX,
+ min_not_zero(nvme_max_drv_segments(ctrl), ctrl->max_segments));
+ lim->max_integrity_segments = ctrl->max_integrity_segments;
+ lim->virt_boundary_mask = NVME_CTRL_PAGE_SIZE - 1;
+ lim->max_segment_size = UINT_MAX;
+ lim->dma_alignment = 3;
}
-static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
- struct nvme_ns_head *head, struct nvme_id_ns *id)
+static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
+ struct queue_limits *lim)
{
- sector_t capacity = nvme_lba_to_sect(head, le64_to_cpu(id->nsze));
+ struct nvme_ns_head *head = ns->head;
u32 bs = 1U << head->lba_shift;
u32 atomic_bs, phys_bs, io_opt = 0;
+ bool valid = true;
/*
* The block layer can't support LBA sizes larger than the page size
@@ -1952,12 +1953,10 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
* allow block I/O.
*/
if (head->lba_shift > PAGE_SHIFT || head->lba_shift < SECTOR_SHIFT) {
- capacity = 0;
bs = (1 << 9);
+ valid = false;
}
- blk_integrity_unregister(disk);
-
atomic_bs = phys_bs = bs;
if (id->nabo == 0) {
/*
@@ -1968,7 +1967,7 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
else
- atomic_bs = (1 + ctrl->subsys->awupf) * bs;
+ atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
}
if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
@@ -1978,36 +1977,20 @@ static void nvme_update_disk_info(struct nvme_ctrl *ctrl, struct gendisk *disk,
io_opt = bs * (1 + le16_to_cpu(id->nows));
}
- blk_queue_logical_block_size(disk->queue, bs);
/*
* Linux filesystems assume writing a single physical block is
* an atomic operation. Hence limit the physical block size to the
* value of the Atomic Write Unit Power Fail parameter.
*/
- blk_queue_physical_block_size(disk->queue, min(phys_bs, atomic_bs));
- blk_queue_io_min(disk->queue, phys_bs);
- blk_queue_io_opt(disk->queue, io_opt);
-
- /*
- * Register a metadata profile for PI, or the plain non-integrity NVMe
- * metadata masquerading as Type 0 if supported, otherwise reject block
- * I/O to namespaces with metadata except when the namespace supports
- * PI, as it can strip/insert in that case.
- */
- if (head->ms) {
- if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
- (head->features & NVME_NS_METADATA_SUPPORTED))
- nvme_init_integrity(disk, head,
- ctrl->max_integrity_segments);
- else if (!nvme_ns_has_pi(head))
- capacity = 0;
- }
-
- set_capacity_and_notify(disk, capacity);
-
- nvme_config_discard(ctrl, disk, head);
- blk_queue_max_write_zeroes_sectors(disk->queue,
- ctrl->max_zeroes_sectors);
+ lim->logical_block_size = bs;
+ lim->physical_block_size = min(phys_bs, atomic_bs);
+ lim->io_min = phys_bs;
+ lim->io_opt = io_opt;
+ if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
+ lim->max_write_zeroes_sectors = UINT_MAX;
+ else
+ lim->max_write_zeroes_sectors = ns->ctrl->max_zeroes_sectors;
+ return valid;
}
static bool nvme_ns_is_readonly(struct nvme_ns *ns, struct nvme_ns_info *info)
@@ -2021,7 +2004,8 @@ static inline bool nvme_first_scan(struct gendisk *disk)
return !disk_live(disk);
}
-static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
+static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id,
+ struct queue_limits *lim)
{
struct nvme_ctrl *ctrl = ns->ctrl;
u32 iob;
@@ -2049,38 +2033,37 @@ static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
return;
}
- blk_queue_chunk_sectors(ns->queue, iob);
+ lim->chunk_sectors = iob;
}
static int nvme_update_ns_info_generic(struct nvme_ns *ns,
struct nvme_ns_info *info)
{
+ struct queue_limits lim;
+ int ret;
+
blk_mq_freeze_queue(ns->disk->queue);
- nvme_set_queue_limits(ns->ctrl, ns->queue);
+ lim = queue_limits_start_update(ns->disk->queue);
+ nvme_set_ctrl_limits(ns->ctrl, &lim);
+ ret = queue_limits_commit_update(ns->disk->queue, &lim);
set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
blk_mq_unfreeze_queue(ns->disk->queue);
- if (nvme_ns_head_multipath(ns->head)) {
- blk_mq_freeze_queue(ns->head->disk->queue);
- set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
- nvme_mpath_revalidate_paths(ns);
- blk_stack_limits(&ns->head->disk->queue->limits,
- &ns->queue->limits, 0);
- ns->head->disk->flags |= GENHD_FL_HIDDEN;
- blk_mq_unfreeze_queue(ns->head->disk->queue);
- }
-
/* Hide the block-interface for these devices */
- ns->disk->flags |= GENHD_FL_HIDDEN;
- set_bit(NVME_NS_READY, &ns->flags);
-
- return 0;
+ if (!ret)
+ ret = -ENODEV;
+ return ret;
}
static int nvme_update_ns_info_block(struct nvme_ns *ns,
struct nvme_ns_info *info)
{
+ bool vwc = ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT;
+ struct queue_limits lim;
+ struct nvme_id_ns_nvm *nvm = NULL;
+ struct nvme_zone_info zi = {};
struct nvme_id_ns *id;
+ sector_t capacity;
unsigned lbaf;
int ret;
@@ -2091,31 +2074,55 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
if (id->ncap == 0) {
/* namespace not allocated or attached */
info->is_removed = true;
- ret = -ENODEV;
- goto error;
+ ret = -ENXIO;
+ goto out;
+ }
+ lbaf = nvme_lbaf_index(id->flbas);
+
+ if (ns->ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) {
+ ret = nvme_identify_ns_nvm(ns->ctrl, info->nsid, &nvm);
+ if (ret < 0)
+ goto out;
+ }
+
+ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+ ns->head->ids.csi == NVME_CSI_ZNS) {
+ ret = nvme_query_zone_info(ns, lbaf, &zi);
+ if (ret < 0)
+ goto out;
}
blk_mq_freeze_queue(ns->disk->queue);
- lbaf = nvme_lbaf_index(id->flbas);
ns->head->lba_shift = id->lbaf[lbaf].ds;
ns->head->nuse = le64_to_cpu(id->nuse);
- nvme_set_queue_limits(ns->ctrl, ns->queue);
+ capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze));
- ret = nvme_configure_metadata(ns->ctrl, ns->head, id);
- if (ret < 0) {
+ lim = queue_limits_start_update(ns->disk->queue);
+ nvme_set_ctrl_limits(ns->ctrl, &lim);
+ nvme_configure_metadata(ns->ctrl, ns->head, id, nvm);
+ nvme_set_chunk_sectors(ns, id, &lim);
+ if (!nvme_update_disk_info(ns, id, &lim))
+ capacity = 0;
+ nvme_config_discard(ns, &lim);
+ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+ ns->head->ids.csi == NVME_CSI_ZNS)
+ nvme_update_zone_info(ns, &lim, &zi);
+ ret = queue_limits_commit_update(ns->disk->queue, &lim);
+ if (ret) {
blk_mq_unfreeze_queue(ns->disk->queue);
goto out;
}
- nvme_set_chunk_sectors(ns, id);
- nvme_update_disk_info(ns->ctrl, ns->disk, ns->head, id);
- if (ns->head->ids.csi == NVME_CSI_ZNS) {
- ret = nvme_update_zone_info(ns, lbaf);
- if (ret) {
- blk_mq_unfreeze_queue(ns->disk->queue);
- goto out;
- }
- }
+ /*
+ * Register a metadata profile for PI, or the plain non-integrity NVMe
+ * metadata masquerading as Type 0 if supported, otherwise reject block
+ * I/O to namespaces with metadata except when the namespace supports
+ * PI, as it can strip/insert in that case.
+ */
+ if (!nvme_init_integrity(ns->disk, ns->head))
+ capacity = 0;
+
+ set_capacity_and_notify(ns->disk, capacity);
/*
* Only set the DEAC bit if the device guarantees that reads from
@@ -2126,62 +2133,101 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
if ((id->dlfeat & 0x7) == 0x1 && (id->dlfeat & (1 << 3)))
ns->head->features |= NVME_NS_DEAC;
set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info));
+ blk_queue_write_cache(ns->disk->queue, vwc, vwc);
set_bit(NVME_NS_READY, &ns->flags);
blk_mq_unfreeze_queue(ns->disk->queue);
if (blk_queue_is_zoned(ns->queue)) {
- ret = nvme_revalidate_zones(ns);
+ ret = blk_revalidate_disk_zones(ns->disk);
if (ret && !nvme_first_scan(ns->disk))
goto out;
}
- if (nvme_ns_head_multipath(ns->head)) {
- blk_mq_freeze_queue(ns->head->disk->queue);
- nvme_update_disk_info(ns->ctrl, ns->head->disk, ns->head, id);
- set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
- nvme_mpath_revalidate_paths(ns);
- blk_stack_limits(&ns->head->disk->queue->limits,
- &ns->queue->limits, 0);
- disk_update_readahead(ns->head->disk);
- blk_mq_unfreeze_queue(ns->head->disk->queue);
- }
-
ret = 0;
out:
- /*
- * If probing fails due an unsupported feature, hide the block device,
- * but still allow other access.
- */
- if (ret == -ENODEV) {
- ns->disk->flags |= GENHD_FL_HIDDEN;
- set_bit(NVME_NS_READY, &ns->flags);
- ret = 0;
- }
-
-error:
+ kfree(nvm);
kfree(id);
return ret;
}
static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
{
+ bool unsupported = false;
+ int ret;
+
switch (info->ids.csi) {
case NVME_CSI_ZNS:
if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
dev_info(ns->ctrl->device,
"block device for nsid %u not supported without CONFIG_BLK_DEV_ZONED\n",
info->nsid);
- return nvme_update_ns_info_generic(ns, info);
+ ret = nvme_update_ns_info_generic(ns, info);
+ break;
}
- return nvme_update_ns_info_block(ns, info);
+ ret = nvme_update_ns_info_block(ns, info);
+ break;
case NVME_CSI_NVM:
- return nvme_update_ns_info_block(ns, info);
+ ret = nvme_update_ns_info_block(ns, info);
+ break;
default:
dev_info(ns->ctrl->device,
"block device for nsid %u not supported (csi %u)\n",
info->nsid, info->ids.csi);
- return nvme_update_ns_info_generic(ns, info);
+ ret = nvme_update_ns_info_generic(ns, info);
+ break;
+ }
+
+ /*
+ * If probing fails due an unsupported feature, hide the block device,
+ * but still allow other access.
+ */
+ if (ret == -ENODEV) {
+ ns->disk->flags |= GENHD_FL_HIDDEN;
+ set_bit(NVME_NS_READY, &ns->flags);
+ unsupported = true;
+ ret = 0;
+ }
+
+ if (!ret && nvme_ns_head_multipath(ns->head)) {
+ struct queue_limits *ns_lim = &ns->disk->queue->limits;
+ struct queue_limits lim;
+
+ blk_mq_freeze_queue(ns->head->disk->queue);
+ if (unsupported)
+ ns->head->disk->flags |= GENHD_FL_HIDDEN;
+ else
+ nvme_init_integrity(ns->head->disk, ns->head);
+ set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
+ set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
+ nvme_mpath_revalidate_paths(ns);
+
+ /*
+ * queue_limits mixes values that are the hardware limitations
+ * for bio splitting with what is the device configuration.
+ *
+ * For NVMe the device configuration can change after e.g. a
+ * Format command, and we really want to pick up the new format
+ * value here. But we must still stack the queue limits to the
+ * least common denominator for multipathing to split the bios
+ * properly.
+ *
+ * To work around this, we explicitly set the device
+ * configuration to those that we just queried, but only stack
+ * the splitting limits in to make sure we still obey possibly
+ * lower limitations of other controllers.
+ */
+ lim = queue_limits_start_update(ns->head->disk->queue);
+ lim.logical_block_size = ns_lim->logical_block_size;
+ lim.physical_block_size = ns_lim->physical_block_size;
+ lim.io_min = ns_lim->io_min;
+ lim.io_opt = ns_lim->io_opt;
+ queue_limits_stack_bdev(&lim, ns->disk->part0, 0,
+ ns->head->disk->disk_name);
+ ret = queue_limits_commit_update(ns->head->disk->queue, &lim);
+ blk_mq_unfreeze_queue(ns->head->disk->queue);
}
+
+ return ret;
}
#ifdef CONFIG_BLK_SED_OPAL
@@ -2856,7 +2902,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
subsys->awupf = le16_to_cpu(id->awupf);
nvme_mpath_default_iopolicy(subsys);
- subsys->dev.class = nvme_subsys_class;
+ subsys->dev.class = &nvme_subsys_class;
subsys->dev.release = nvme_release_subsystem;
subsys->dev.groups = nvme_subsys_attrs_groups;
dev_set_name(&subsys->dev, "nvme-subsys%d", ctrl->instance);
@@ -3096,11 +3142,17 @@ static int nvme_check_ctrl_fabric_info(struct nvme_ctrl *ctrl, struct nvme_id_ct
return -EINVAL;
}
+ if (!ctrl->maxcmd) {
+ dev_err(ctrl->device, "Maximum outstanding commands is 0\n");
+ return -EINVAL;
+ }
+
return 0;
}
static int nvme_init_identify(struct nvme_ctrl *ctrl)
{
+ struct queue_limits lim;
struct nvme_id_ctrl *id;
u32 max_hw_sectors;
bool prev_apst_enabled;
@@ -3167,7 +3219,12 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
ctrl->max_hw_sectors =
min_not_zero(ctrl->max_hw_sectors, max_hw_sectors);
- nvme_set_queue_limits(ctrl, ctrl->admin_q);
+ lim = queue_limits_start_update(ctrl->admin_q);
+ nvme_set_ctrl_limits(ctrl, &lim);
+ ret = queue_limits_commit_update(ctrl->admin_q, &lim);
+ if (ret)
+ goto out_free;
+
ctrl->sgls = le32_to_cpu(id->sgls);
ctrl->kas = le16_to_cpu(id->kas);
ctrl->max_namespaces = le32_to_cpu(id->mnan);
@@ -3185,7 +3242,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
if (ctrl->shutdown_timeout != shutdown_timeout)
dev_info(ctrl->device,
- "Shutdown timeout set to %u seconds\n",
+ "D3 entry latency set to %u seconds\n",
ctrl->shutdown_timeout);
} else
ctrl->shutdown_timeout = shutdown_timeout;
@@ -3399,7 +3456,7 @@ int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
if (minor < 0)
return minor;
cdev_device->devt = MKDEV(MAJOR(nvme_ns_chr_devt), minor);
- cdev_device->class = nvme_ns_chr_class;
+ cdev_device->class = &nvme_ns_chr_class;
cdev_device->release = nvme_cdev_rel;
device_initialize(cdev_device);
cdev_init(cdev, fops);
@@ -3628,9 +3685,10 @@ out_unlock:
struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
struct nvme_ns *ns, *ret = NULL;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
if (ns->head->ns_id == nsid) {
if (!nvme_get_ns(ns))
continue;
@@ -3640,7 +3698,7 @@ struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
if (ns->head->ns_id > nsid)
break;
}
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
return ret;
}
EXPORT_SYMBOL_NS_GPL(nvme_find_get_ns, NVME_TARGET_PASSTHRU);
@@ -3654,7 +3712,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns)
list_for_each_entry_reverse(tmp, &ns->ctrl->namespaces, list) {
if (tmp->head->ns_id < ns->head->ns_id) {
- list_add(&ns->list, &tmp->list);
+ list_add_rcu(&ns->list, &tmp->list);
return;
}
}
@@ -3671,7 +3729,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
if (!ns)
return;
- disk = blk_mq_alloc_disk(ctrl->tagset, ns);
+ disk = blk_mq_alloc_disk(ctrl->tagset, NULL, ns);
if (IS_ERR(disk))
goto out_free_ns;
disk->fops = &nvme_bdev_ops;
@@ -3720,17 +3778,18 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
if (nvme_update_ns_info(ns, info))
goto out_unlink_ns;
- down_write(&ctrl->namespaces_rwsem);
+ mutex_lock(&ctrl->namespaces_lock);
/*
* Ensure that no namespaces are added to the ctrl list after the queues
* are frozen, thereby avoiding a deadlock between scan and reset.
*/
if (test_bit(NVME_CTRL_FROZEN, &ctrl->flags)) {
- up_write(&ctrl->namespaces_rwsem);
+ mutex_unlock(&ctrl->namespaces_lock);
goto out_unlink_ns;
}
nvme_ns_add_to_ctrl_list(ns);
- up_write(&ctrl->namespaces_rwsem);
+ mutex_unlock(&ctrl->namespaces_lock);
+ synchronize_srcu(&ctrl->srcu);
nvme_get_ctrl(ctrl);
if (device_add_disk(ctrl->device, ns->disk, nvme_ns_attr_groups))
@@ -3753,9 +3812,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
out_cleanup_ns_from_list:
nvme_put_ctrl(ctrl);
- down_write(&ctrl->namespaces_rwsem);
- list_del_init(&ns->list);
- up_write(&ctrl->namespaces_rwsem);
+ mutex_lock(&ctrl->namespaces_lock);
+ list_del_rcu(&ns->list);
+ mutex_unlock(&ctrl->namespaces_lock);
+ synchronize_srcu(&ctrl->srcu);
out_unlink_ns:
mutex_lock(&ctrl->subsys->lock);
list_del_rcu(&ns->siblings);
@@ -3805,9 +3865,10 @@ static void nvme_ns_remove(struct nvme_ns *ns)
nvme_cdev_del(&ns->cdev, &ns->cdev_device);
del_gendisk(ns->disk);
- down_write(&ns->ctrl->namespaces_rwsem);
- list_del_init(&ns->list);
- up_write(&ns->ctrl->namespaces_rwsem);
+ mutex_lock(&ns->ctrl->namespaces_lock);
+ list_del_rcu(&ns->list);
+ mutex_unlock(&ns->ctrl->namespaces_lock);
+ synchronize_srcu(&ns->ctrl->srcu);
if (last_path)
nvme_mpath_shutdown_disk(ns->head);
@@ -3897,16 +3958,18 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
struct nvme_ns *ns, *next;
LIST_HEAD(rm_list);
- down_write(&ctrl->namespaces_rwsem);
+ mutex_lock(&ctrl->namespaces_lock);
list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
- if (ns->head->ns_id > nsid)
- list_move_tail(&ns->list, &rm_list);
+ if (ns->head->ns_id > nsid) {
+ list_del_rcu(&ns->list);
+ synchronize_srcu(&ctrl->srcu);
+ list_add_tail_rcu(&ns->list, &rm_list);
+ }
}
- up_write(&ctrl->namespaces_rwsem);
+ mutex_unlock(&ctrl->namespaces_lock);
list_for_each_entry_safe(ns, next, &rm_list, list)
nvme_ns_remove(ns);
-
}
static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
@@ -4076,9 +4139,10 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
/* this is a no-op when called from the controller reset handler */
nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);
- down_write(&ctrl->namespaces_rwsem);
- list_splice_init(&ctrl->namespaces, &ns_list);
- up_write(&ctrl->namespaces_rwsem);
+ mutex_lock(&ctrl->namespaces_lock);
+ list_splice_init_rcu(&ctrl->namespaces, &ns_list, synchronize_rcu);
+ mutex_unlock(&ctrl->namespaces_lock);
+ synchronize_srcu(&ctrl->srcu);
list_for_each_entry_safe(ns, next, &ns_list, list)
nvme_ns_remove(ns);
@@ -4332,6 +4396,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
const struct blk_mq_ops *ops, unsigned int cmd_size)
{
+ struct queue_limits lim = {};
int ret;
memset(set, 0, sizeof(*set));
@@ -4352,14 +4417,14 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
if (ret)
return ret;
- ctrl->admin_q = blk_mq_init_queue(set);
+ ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL);
if (IS_ERR(ctrl->admin_q)) {
ret = PTR_ERR(ctrl->admin_q);
goto out_free_tagset;
}
if (ctrl->ops->flags & NVME_F_FABRICS) {
- ctrl->fabrics_q = blk_mq_init_queue(set);
+ ctrl->fabrics_q = blk_mq_alloc_queue(set, NULL, NULL);
if (IS_ERR(ctrl->fabrics_q)) {
ret = PTR_ERR(ctrl->fabrics_q);
goto out_cleanup_admin_q;
@@ -4424,7 +4489,7 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
return ret;
if (ctrl->ops->flags & NVME_F_FABRICS) {
- ctrl->connect_q = blk_mq_init_queue(set);
+ ctrl->connect_q = blk_mq_alloc_queue(set, NULL, NULL);
if (IS_ERR(ctrl->connect_q)) {
ret = PTR_ERR(ctrl->connect_q);
goto out_free_tag_set;
@@ -4525,6 +4590,7 @@ static void nvme_free_ctrl(struct device *dev)
key_put(ctrl->tls_key);
nvme_free_cels(ctrl);
nvme_mpath_uninit(ctrl);
+ cleanup_srcu_struct(&ctrl->srcu);
nvme_auth_stop(ctrl);
nvme_auth_free(ctrl);
__free_page(ctrl->discard_page);
@@ -4557,10 +4623,15 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
ctrl->passthru_err_log_enabled = false;
clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
spin_lock_init(&ctrl->lock);
+ mutex_init(&ctrl->namespaces_lock);
+
+ ret = init_srcu_struct(&ctrl->srcu);
+ if (ret)
+ return ret;
+
mutex_init(&ctrl->scan_lock);
INIT_LIST_HEAD(&ctrl->namespaces);
xa_init(&ctrl->cels);
- init_rwsem(&ctrl->namespaces_rwsem);
ctrl->dev = dev;
ctrl->ops = ops;
ctrl->quirks = quirks;
@@ -4594,7 +4665,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
ctrl->device = &ctrl->ctrl_device;
ctrl->device->devt = MKDEV(MAJOR(nvme_ctrl_base_chr_devt),
ctrl->instance);
- ctrl->device->class = nvme_class;
+ ctrl->device->class = &nvme_class;
ctrl->device->parent = ctrl->dev;
if (ops->dev_attr_groups)
ctrl->device->groups = ops->dev_attr_groups;
@@ -4640,6 +4711,7 @@ out_release_instance:
out:
if (ctrl->discard_page)
__free_page(ctrl->discard_page);
+ cleanup_srcu_struct(&ctrl->srcu);
return ret;
}
EXPORT_SYMBOL_GPL(nvme_init_ctrl);
@@ -4648,22 +4720,24 @@ EXPORT_SYMBOL_GPL(nvme_init_ctrl);
void nvme_mark_namespaces_dead(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
blk_mark_disk_dead(ns->disk);
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
EXPORT_SYMBOL_GPL(nvme_mark_namespaces_dead);
void nvme_unfreeze(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
blk_mq_unfreeze_queue(ns->queue);
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
clear_bit(NVME_CTRL_FROZEN, &ctrl->flags);
}
EXPORT_SYMBOL_GPL(nvme_unfreeze);
@@ -4671,14 +4745,15 @@ EXPORT_SYMBOL_GPL(nvme_unfreeze);
int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
timeout = blk_mq_freeze_queue_wait_timeout(ns->queue, timeout);
if (timeout <= 0)
break;
}
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
return timeout;
}
EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
@@ -4686,23 +4761,25 @@ EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
void nvme_wait_freeze(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
blk_mq_freeze_queue_wait(ns->queue);
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
EXPORT_SYMBOL_GPL(nvme_wait_freeze);
void nvme_start_freeze(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
set_bit(NVME_CTRL_FROZEN, &ctrl->flags);
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
blk_freeze_queue_start(ns->queue);
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
EXPORT_SYMBOL_GPL(nvme_start_freeze);
@@ -4745,11 +4822,12 @@ EXPORT_SYMBOL_GPL(nvme_unquiesce_admin_queue);
void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
blk_sync_queue(ns->queue);
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
EXPORT_SYMBOL_GPL(nvme_sync_io_queues);
@@ -4827,42 +4905,36 @@ static int __init nvme_core_init(void)
if (result < 0)
goto destroy_delete_wq;
- nvme_class = class_create("nvme");
- if (IS_ERR(nvme_class)) {
- result = PTR_ERR(nvme_class);
+ result = class_register(&nvme_class);
+ if (result)
goto unregister_chrdev;
- }
- nvme_class->dev_uevent = nvme_class_uevent;
- nvme_subsys_class = class_create("nvme-subsystem");
- if (IS_ERR(nvme_subsys_class)) {
- result = PTR_ERR(nvme_subsys_class);
+ result = class_register(&nvme_subsys_class);
+ if (result)
goto destroy_class;
- }
result = alloc_chrdev_region(&nvme_ns_chr_devt, 0, NVME_MINORS,
"nvme-generic");
if (result < 0)
goto destroy_subsys_class;
- nvme_ns_chr_class = class_create("nvme-generic");
- if (IS_ERR(nvme_ns_chr_class)) {
- result = PTR_ERR(nvme_ns_chr_class);
+ result = class_register(&nvme_ns_chr_class);
+ if (result)
goto unregister_generic_ns;
- }
+
result = nvme_init_auth();
if (result)
goto destroy_ns_chr;
return 0;
destroy_ns_chr:
- class_destroy(nvme_ns_chr_class);
+ class_unregister(&nvme_ns_chr_class);
unregister_generic_ns:
unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
destroy_subsys_class:
- class_destroy(nvme_subsys_class);
+ class_unregister(&nvme_subsys_class);
destroy_class:
- class_destroy(nvme_class);
+ class_unregister(&nvme_class);
unregister_chrdev:
unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
destroy_delete_wq:
@@ -4878,9 +4950,9 @@ out:
static void __exit nvme_core_exit(void)
{
nvme_exit_auth();
- class_destroy(nvme_ns_chr_class);
- class_destroy(nvme_subsys_class);
- class_destroy(nvme_class);
+ class_unregister(&nvme_ns_chr_class);
+ class_unregister(&nvme_subsys_class);
+ class_unregister(&nvme_class);
unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
destroy_workqueue(nvme_delete_wq);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 495c171dae..ceb9c0ed31 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -180,7 +180,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
cmd.prop_get.offset = cpu_to_le32(off);
ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
- NVME_QID_ANY, 0);
+ NVME_QID_ANY, NVME_SUBMIT_RESERVED);
if (ret >= 0)
*val = le64_to_cpu(res.u64);
@@ -226,7 +226,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
cmd.prop_get.offset = cpu_to_le32(off);
ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
- NVME_QID_ANY, 0);
+ NVME_QID_ANY, NVME_SUBMIT_RESERVED);
if (ret >= 0)
*val = le64_to_cpu(res.u64);
@@ -271,7 +271,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
cmd.prop_set.value = cpu_to_le64(val);
ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0,
- NVME_QID_ANY, 0);
+ NVME_QID_ANY, NVME_SUBMIT_RESERVED);
if (unlikely(ret))
dev_err(ctrl->device,
"Property Set error: %d, offset %#x\n",
@@ -428,12 +428,6 @@ static void nvmf_connect_cmd_prep(struct nvme_ctrl *ctrl, u16 qid,
* fabrics-protocol connection of the NVMe Admin queue between the
* host system device and the allocated NVMe controller on the
* target system via a NVMe Fabrics "Connect" command.
- *
- * Return:
- * 0: success
- * > 0: NVMe error status code
- * < 0: Linux errno error code
- *
*/
int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
{
@@ -467,7 +461,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
if (result & NVME_CONNECT_AUTHREQ_ASCR) {
dev_warn(ctrl->device,
"qid 0: secure concatenation is not supported\n");
- ret = NVME_SC_AUTH_REQUIRED;
+ ret = -EOPNOTSUPP;
goto out_free_data;
}
/* Authentication required */
@@ -475,14 +469,14 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
if (ret) {
dev_warn(ctrl->device,
"qid 0: authentication setup failed\n");
- ret = NVME_SC_AUTH_REQUIRED;
goto out_free_data;
}
ret = nvme_auth_wait(ctrl, 0);
- if (ret)
+ if (ret) {
dev_warn(ctrl->device,
- "qid 0: authentication failed\n");
- else
+ "qid 0: authentication failed, error %d\n",
+ ret);
+ } else
dev_info(ctrl->device,
"qid 0: authenticated\n");
}
@@ -542,7 +536,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
if (result & NVME_CONNECT_AUTHREQ_ASCR) {
dev_warn(ctrl->device,
"qid 0: secure concatenation is not supported\n");
- ret = NVME_SC_AUTH_REQUIRED;
+ ret = -EOPNOTSUPP;
goto out_free_data;
}
/* Authentication required */
@@ -550,12 +544,13 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
if (ret) {
dev_warn(ctrl->device,
"qid %d: authentication setup failed\n", qid);
- ret = NVME_SC_AUTH_REQUIRED;
- } else {
- ret = nvme_auth_wait(ctrl, qid);
- if (ret)
- dev_warn(ctrl->device,
- "qid %u: authentication failed\n", qid);
+ goto out_free_data;
+ }
+ ret = nvme_auth_wait(ctrl, qid);
+ if (ret) {
+ dev_warn(ctrl->device,
+ "qid %u: authentication failed, error %d\n",
+ qid, ret);
}
}
out_free_data:
@@ -564,8 +559,26 @@ out_free_data:
}
EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
-bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
+/*
+ * Evaluate the status information returned by the transport in order to decided
+ * if a reconnect attempt should be scheduled.
+ *
+ * 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.
+ *
+ * - when the authentication attempt fails, because the key was invalid.
+ * This error code is set on the host side.
+ */
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status)
{
+ if (status > 0 && (status & NVME_SC_DNR))
+ return false;
+
+ if (status == -EKEYREJECTED)
+ return false;
+
if (ctrl->opts->max_reconnects == -1 ||
ctrl->nr_reconnects < ctrl->opts->max_reconnects)
return true;
@@ -638,7 +651,7 @@ static struct key *nvmf_parse_key(int key_id)
}
key = key_lookup(key_id);
- if (!IS_ERR(key))
+ if (IS_ERR(key))
pr_err("key id %08x not found\n", key_id);
else
pr_debug("Using key id %08x\n", key_id);
@@ -1319,7 +1332,10 @@ out_free_opts:
return ERR_PTR(ret);
}
-static struct class *nvmf_class;
+static const struct class nvmf_class = {
+ .name = "nvme-fabrics",
+};
+
static struct device *nvmf_device;
static DEFINE_MUTEX(nvmf_dev_mutex);
@@ -1439,15 +1455,14 @@ static int __init nvmf_init(void)
if (!nvmf_default_host)
return -ENOMEM;
- nvmf_class = class_create("nvme-fabrics");
- if (IS_ERR(nvmf_class)) {
+ ret = class_register(&nvmf_class);
+ if (ret) {
pr_err("couldn't register class nvme-fabrics\n");
- ret = PTR_ERR(nvmf_class);
goto out_free_host;
}
nvmf_device =
- device_create(nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
+ device_create(&nvmf_class, NULL, MKDEV(0, 0), NULL, "ctl");
if (IS_ERR(nvmf_device)) {
pr_err("couldn't create nvme-fabrics device!\n");
ret = PTR_ERR(nvmf_device);
@@ -1463,9 +1478,9 @@ static int __init nvmf_init(void)
return 0;
out_destroy_device:
- device_destroy(nvmf_class, MKDEV(0, 0));
+ device_destroy(&nvmf_class, MKDEV(0, 0));
out_destroy_class:
- class_destroy(nvmf_class);
+ class_unregister(&nvmf_class);
out_free_host:
nvmf_host_put(nvmf_default_host);
return ret;
@@ -1474,8 +1489,8 @@ out_free_host:
static void __exit nvmf_exit(void)
{
misc_deregister(&nvmf_misc);
- device_destroy(nvmf_class, MKDEV(0, 0));
- class_destroy(nvmf_class);
+ device_destroy(&nvmf_class, MKDEV(0, 0));
+ class_unregister(&nvmf_class);
nvmf_host_put(nvmf_default_host);
BUILD_BUG_ON(sizeof(struct nvmf_common_command) != 64);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 37c974c38d..602135910a 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -223,7 +223,7 @@ 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);
int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
-bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status);
bool nvmf_ip_options_match(struct nvme_ctrl *ctrl,
struct nvmf_ctrl_options *opts);
void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues,
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 68a5d97165..f0b0813327 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2428,7 +2428,7 @@ nvme_fc_ctrl_get(struct nvme_fc_ctrl *ctrl)
* controller. Called after last nvme_put_ctrl() call
*/
static void
-nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl)
+nvme_fc_free_ctrl(struct nvme_ctrl *nctrl)
{
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
@@ -3310,12 +3310,10 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
ctrl->cnum, status);
- if (status > 0 && (status & NVME_SC_DNR))
- recon = false;
} else if (time_after_eq(jiffies, rport->dev_loss_end))
recon = false;
- if (recon && nvmf_should_reconnect(&ctrl->ctrl)) {
+ if (recon && nvmf_should_reconnect(&ctrl->ctrl, status)) {
if (portptr->port_state == FC_OBJSTATE_ONLINE)
dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: Reconnect attempt in %ld "
@@ -3384,7 +3382,7 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
.reg_read32 = nvmf_reg_read32,
.reg_read64 = nvmf_reg_read64,
.reg_write32 = nvmf_reg_write32,
- .free_ctrl = nvme_fc_nvme_ctrl_freed,
+ .free_ctrl = nvme_fc_free_ctrl,
.submit_async_event = nvme_fc_submit_async_event,
.delete_ctrl = nvme_fc_delete_ctrl,
.get_address = nvmf_get_address,
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 3dfd5ae99a..8b69427a44 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -111,6 +111,13 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
return req;
}
+static void nvme_unmap_bio(struct bio *bio)
+{
+ if (bio_integrity(bio))
+ bio_integrity_unmap_free_user(bio);
+ blk_rq_unmap_user(bio);
+}
+
static int nvme_map_user_request(struct request *req, u64 ubuffer,
unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags)
@@ -157,7 +164,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
out_unmap:
if (bio)
- blk_rq_unmap_user(bio);
+ nvme_unmap_bio(bio);
out:
blk_mq_free_request(req);
return ret;
@@ -195,7 +202,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
if (result)
*result = le64_to_cpu(nvme_req(req)->result.u64);
if (bio)
- blk_rq_unmap_user(bio);
+ nvme_unmap_bio(bio);
blk_mq_free_request(req);
if (effects)
@@ -406,7 +413,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
if (pdu->bio)
- blk_rq_unmap_user(pdu->bio);
+ nvme_unmap_bio(pdu->bio);
io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags);
}
@@ -423,13 +430,20 @@ 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.
+ * 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.
*/
- if (blk_rq_is_poll(req))
- nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
- else
+ if (blk_rq_is_poll(req)) {
+ if (pdu->bio)
+ nvme_unmap_bio(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);
+ }
return RQ_END_IO_FREE;
}
@@ -782,15 +796,15 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
bool open_for_write)
{
struct nvme_ns *ns;
- int ret;
+ int ret, srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
if (list_empty(&ctrl->namespaces)) {
ret = -ENOTTY;
goto out_unlock;
}
- ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list);
+ ns = list_first_or_null_rcu(&ctrl->namespaces, struct nvme_ns, list);
if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) {
dev_warn(ctrl->device,
"NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n");
@@ -800,15 +814,18 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
dev_warn(ctrl->device,
"using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n");
- kref_get(&ns->kref);
- up_read(&ctrl->namespaces_rwsem);
+ if (!nvme_get_ns(ns)) {
+ ret = -ENXIO;
+ goto out_unlock;
+ }
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
ret = nvme_user_cmd(ctrl, ns, argp, 0, open_for_write);
nvme_put_ns(ns);
return ret;
out_unlock:
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
return ret;
}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 75386d3e0f..d8b6b4648e 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -118,7 +118,8 @@ void nvme_failover_req(struct request *req)
blk_steal_bios(&ns->head->requeue_list, req);
spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
- blk_mq_end_request(req, 0);
+ nvme_req(req)->status = 0;
+ nvme_end_req(req);
kblockd_schedule_work(&ns->head->requeue_work);
}
@@ -150,16 +151,17 @@ void nvme_mpath_end_request(struct request *rq)
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
if (!ns->head->disk)
continue;
kblockd_schedule_work(&ns->head->requeue_work);
if (nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
disk_uevent(ns->head->disk, KOBJ_CHANGE);
}
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
static const char *nvme_ana_state_names[] = {
@@ -193,13 +195,14 @@ out:
void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
+ int srcu_idx;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
nvme_mpath_clear_current_path(ns);
kblockd_schedule_work(&ns->head->requeue_work);
}
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
}
void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
@@ -517,6 +520,7 @@ static void nvme_requeue_work(struct work_struct *work)
int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
{
+ struct queue_limits lim;
bool vwc = false;
mutex_init(&head->lock);
@@ -533,9 +537,14 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
!nvme_is_unique_nsid(ctrl, head) || !multipath)
return 0;
- head->disk = blk_alloc_disk(ctrl->numa_node);
- if (!head->disk)
- return -ENOMEM;
+ blk_set_stacking_limits(&lim);
+ lim.dma_alignment = 3;
+ if (head->ids.csi != NVME_CSI_ZNS)
+ lim.max_zone_append_sectors = 0;
+
+ head->disk = blk_alloc_disk(&lim, ctrl->numa_node);
+ if (IS_ERR(head->disk))
+ return PTR_ERR(head->disk);
head->disk->fops = &nvme_ns_head_ops;
head->disk->private_data = head;
sprintf(head->disk->disk_name, "nvme%dn%d",
@@ -554,11 +563,6 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
ctrl->tagset->map[HCTX_TYPE_POLL].nr_queues)
blk_queue_flag_set(QUEUE_FLAG_POLL, head->disk->queue);
- /* set to a default value of 512 until the disk is validated */
- blk_queue_logical_block_size(head->disk->queue, 512);
- blk_set_stacking_limits(&head->disk->queue->limits);
- blk_queue_dma_alignment(head->disk->queue, 3);
-
/* we need to propagate up the VMC settings */
if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
vwc = true;
@@ -594,7 +598,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
int node, srcu_idx;
srcu_idx = srcu_read_lock(&head->srcu);
- for_each_node(node)
+ for_each_online_node(node)
__nvme_find_path(head, node);
srcu_read_unlock(&head->srcu, srcu_idx);
}
@@ -679,6 +683,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
unsigned *nr_change_groups = data;
struct nvme_ns *ns;
+ int srcu_idx;
dev_dbg(ctrl->device, "ANA group %d: %s.\n",
le32_to_cpu(desc->grpid),
@@ -690,8 +695,8 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
if (!nr_nsids)
return 0;
- down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list) {
+ srcu_idx = srcu_read_lock(&ctrl->srcu);
+ list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
unsigned nsid;
again:
nsid = le32_to_cpu(desc->nsids[n]);
@@ -704,7 +709,7 @@ again:
if (ns->head->ns_id > nsid)
goto again;
}
- up_read(&ctrl->namespaces_rwsem);
+ srcu_read_unlock(&ctrl->srcu, srcu_idx);
return 0;
}
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 2a7bf57428..68b400f9c4 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -282,7 +282,8 @@ struct nvme_ctrl {
struct blk_mq_tag_set *tagset;
struct blk_mq_tag_set *admin_tagset;
struct list_head namespaces;
- struct rw_semaphore namespaces_rwsem;
+ struct mutex namespaces_lock;
+ struct srcu_struct srcu;
struct device ctrl_device;
struct device *device; /* char device */
#ifdef CONFIG_NVME_HWMON
@@ -469,9 +470,8 @@ struct nvme_ns_head {
u16 ms;
u16 pi_size;
u8 pi_type;
+ u8 pi_offset;
u8 guard_type;
- u16 sgs;
- u32 sws;
#ifdef CONFIG_BLK_DEV_ZONED
u64 zsze;
#endif
@@ -502,7 +502,7 @@ 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, /* DEAC bit in Write Zeores supported */
+ NVME_NS_DEAC = 1 << 2, /* DEAC bit in Write Zeores supported */
};
struct nvme_ns {
@@ -766,6 +766,7 @@ static inline bool nvme_state_terminal(struct nvme_ctrl *ctrl)
}
}
+void nvme_end_req(struct request *req);
void nvme_complete_rq(struct request *req);
void nvme_complete_batch_req(struct request *req);
@@ -1061,11 +1062,19 @@ static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
}
#endif /* CONFIG_NVME_MULTIPATH */
-int nvme_revalidate_zones(struct nvme_ns *ns);
+struct nvme_zone_info {
+ u64 zone_size;
+ unsigned int max_open_zones;
+ unsigned int max_active_zones;
+};
+
int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
+int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf,
+ struct nvme_zone_info *zi);
+void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
+ struct nvme_zone_info *zi);
#ifdef CONFIG_BLK_DEV_ZONED
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf);
blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmnd,
enum nvme_zone_mgmt_action action);
@@ -1076,13 +1085,6 @@ static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
{
return BLK_STS_NOTSUPP;
}
-
-static inline int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
-{
- dev_warn(ns->ctrl->device,
- "Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
- return -EPROTONOSUPPORT;
-}
#endif
static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
@@ -1146,7 +1148,7 @@ static inline int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid)
}
static inline int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid)
{
- return NVME_SC_AUTH_REQUIRED;
+ return -EPROTONOSUPPORT;
}
static inline void nvme_auth_free(struct nvme_ctrl *ctrl) {};
#endif
@@ -1159,6 +1161,7 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects,
struct nvme_command *cmd, int status);
struct nvme_ctrl *nvme_ctrl_from_file(struct file *file);
struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
+bool nvme_get_ns(struct nvme_ns *ns);
void nvme_put_ns(struct nvme_ns *ns);
static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 710043086d..a823330567 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -778,7 +778,8 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
struct bio_vec bv = req_bvec(req);
if (!is_pci_p2pdma_page(bv.bv_page)) {
- if (bv.bv_offset + bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
+ if ((bv.bv_offset & (NVME_CTRL_PAGE_SIZE - 1)) +
+ bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
return nvme_setup_prp_simple(dev, req,
&cmnd->rw, &bv);
@@ -825,9 +826,9 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
struct nvme_command *cmnd)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+ struct bio_vec bv = rq_integrity_vec(req);
- iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req),
- rq_dma_dir(req), 0);
+ iod->meta_dma = dma_map_bvec(dev->dev, &bv, rq_dma_dir(req), 0);
if (dma_mapping_error(dev->dev, iod->meta_dma))
return BLK_STS_IOERR;
cmnd->rw.metadata = cpu_to_le64(iod->meta_dma);
@@ -862,7 +863,8 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
nvme_start_request(req);
return BLK_STS_OK;
out_unmap_data:
- nvme_unmap_data(dev, req);
+ if (blk_rq_nr_phys_segments(req))
+ nvme_unmap_data(dev, req);
out_free_cmd:
nvme_cleanup_cmd(req);
return ret;
@@ -966,7 +968,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req)
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
dma_unmap_page(dev->dev, iod->meta_dma,
- rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
+ rq_integrity_vec(req).bv_len, rq_dma_dir(req));
}
if (blk_rq_nr_phys_segments(req))
@@ -1273,7 +1275,7 @@ static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
dev_warn(dev->ctrl.device,
"Does your device have a faulty power saving mode enabled?\n");
dev_warn(dev->ctrl.device,
- "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off\" and report a bug\n");
+ "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off pcie_port_pm=off\" and report a bug\n");
}
static enum blk_eh_timer_return nvme_timeout(struct request *req)
@@ -2931,6 +2933,13 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND;
}
+ /*
+ * NVMe SSD drops off the PCIe bus after system idle
+ * for 10 hours on a Lenovo N60z board.
+ */
+ if (dmi_match(DMI_BOARD_NAME, "LXKT-ZXEG-N6"))
+ return NVME_QUIRK_NO_APST;
+
return 0;
}
diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index fc3eed00f9..8fa1ffcdae 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -77,7 +77,7 @@ static int nvme_sc_to_pr_err(int nvme_sc)
if (nvme_is_path_error(nvme_sc))
return PR_STS_PATH_FAILED;
- switch (nvme_sc) {
+ switch (nvme_sc & 0x7ff) {
case NVME_SC_SUCCESS:
return PR_STS_SUCCESS;
case NVME_SC_RESERVATION_CONFLICT:
@@ -97,8 +97,7 @@ static int nvme_sc_to_pr_err(int nvme_sc)
static int nvme_send_pr_command(struct block_device *bdev,
struct nvme_command *c, void *data, unsigned int data_len)
{
- if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
- nvme_disk_is_ns_head(bdev->bd_disk))
+ if (nvme_disk_is_ns_head(bdev->bd_disk))
return nvme_send_ns_head_pr_command(bdev, c, data, data_len);
return nvme_send_ns_pr_command(bdev->bd_disk->private_data, c, data,
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 20fdd40b18..51a62b0c64 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -982,7 +982,8 @@ free_ctrl:
kfree(ctrl);
}
-static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
+static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl,
+ int status)
{
enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
@@ -992,7 +993,7 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
return;
}
- if (nvmf_should_reconnect(&ctrl->ctrl)) {
+ if (nvmf_should_reconnect(&ctrl->ctrl, status)) {
dev_info(ctrl->ctrl.device, "Reconnecting in %d seconds...\n",
ctrl->ctrl.opts->reconnect_delay);
queue_delayed_work(nvme_wq, &ctrl->reconnect_work,
@@ -1006,6 +1007,7 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
{
int ret;
bool changed;
+ u16 max_queue_size;
ret = nvme_rdma_configure_admin_queue(ctrl, new);
if (ret)
@@ -1030,11 +1032,16 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
}
- if (ctrl->ctrl.sqsize + 1 > NVME_RDMA_MAX_QUEUE_SIZE) {
+ if (ctrl->ctrl.max_integrity_segments)
+ max_queue_size = NVME_RDMA_MAX_METADATA_QUEUE_SIZE;
+ else
+ max_queue_size = NVME_RDMA_MAX_QUEUE_SIZE;
+
+ if (ctrl->ctrl.sqsize + 1 > max_queue_size) {
dev_warn(ctrl->ctrl.device,
- "ctrl sqsize %u > max queue size %u, clamping down\n",
- ctrl->ctrl.sqsize + 1, NVME_RDMA_MAX_QUEUE_SIZE);
- ctrl->ctrl.sqsize = NVME_RDMA_MAX_QUEUE_SIZE - 1;
+ "ctrl sqsize %u > max queue size %u, clamping down\n",
+ ctrl->ctrl.sqsize + 1, max_queue_size);
+ ctrl->ctrl.sqsize = max_queue_size - 1;
}
if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
@@ -1098,10 +1105,12 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
{
struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
struct nvme_rdma_ctrl, reconnect_work);
+ int ret;
++ctrl->ctrl.nr_reconnects;
- if (nvme_rdma_setup_ctrl(ctrl, false))
+ ret = nvme_rdma_setup_ctrl(ctrl, false);
+ if (ret)
goto requeue;
dev_info(ctrl->ctrl.device, "Successfully reconnected (%d attempts)\n",
@@ -1112,9 +1121,9 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
return;
requeue:
- dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
- ctrl->ctrl.nr_reconnects);
- nvme_rdma_reconnect_or_remove(ctrl);
+ dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d/%d\n",
+ ctrl->ctrl.nr_reconnects, ctrl->ctrl.opts->max_reconnects);
+ nvme_rdma_reconnect_or_remove(ctrl, ret);
}
static void nvme_rdma_error_recovery_work(struct work_struct *work)
@@ -1139,7 +1148,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
return;
}
- nvme_rdma_reconnect_or_remove(ctrl);
+ nvme_rdma_reconnect_or_remove(ctrl, 0);
}
static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
@@ -2163,6 +2172,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
{
struct nvme_rdma_ctrl *ctrl =
container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work);
+ int ret;
nvme_stop_ctrl(&ctrl->ctrl);
nvme_rdma_shutdown_ctrl(ctrl, false);
@@ -2173,14 +2183,15 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
return;
}
- if (nvme_rdma_setup_ctrl(ctrl, false))
+ ret = nvme_rdma_setup_ctrl(ctrl, false);
+ if (ret)
goto out_fail;
return;
out_fail:
++ctrl->ctrl.nr_reconnects;
- nvme_rdma_reconnect_or_remove(ctrl);
+ nvme_rdma_reconnect_or_remove(ctrl, ret);
}
static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index 09fcaa519e..3c55f7edd1 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -236,8 +236,7 @@ static ssize_t nuse_show(struct device *dev, struct device_attribute *attr,
struct block_device *bdev = disk->part0;
int ret;
- if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
- bdev->bd_disk->fops == &nvme_ns_head_ops)
+ if (nvme_disk_is_ns_head(bdev->bd_disk))
ret = ns_head_update_nuse(head);
else
ret = ns_update_nuse(bdev->bd_disk->private_data);
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 6eeb96578d..8b5e4327fe 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -37,6 +37,14 @@ module_param(so_priority, int, 0644);
MODULE_PARM_DESC(so_priority, "nvme tcp socket optimize priority");
/*
+ * Use the unbound workqueue for nvme_tcp_wq, then we can set the cpu affinity
+ * from sysfs.
+ */
+static bool wq_unbound;
+module_param(wq_unbound, bool, 0644);
+MODULE_PARM_DESC(wq_unbound, "Use unbound workqueue for nvme-tcp IO context (default false)");
+
+/*
* TLS handshake timeout
*/
static int tls_handshake_timeout = 10;
@@ -1350,7 +1358,6 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl)
static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
{
- struct page *page;
struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
struct nvme_tcp_queue *queue = &ctrl->queues[qid];
unsigned int noreclaim_flag;
@@ -1361,11 +1368,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
if (queue->hdr_digest || queue->data_digest)
nvme_tcp_free_crypto(queue);
- if (queue->pf_cache.va) {
- page = virt_to_head_page(queue->pf_cache.va);
- __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
- queue->pf_cache.va = NULL;
- }
+ page_frag_cache_drain(&queue->pf_cache);
noreclaim_flag = memalloc_noreclaim_save();
/* ->sock will be released by fput() */
@@ -1557,7 +1560,10 @@ static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue)
else if (nvme_tcp_poll_queue(queue))
n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] -
ctrl->io_queues[HCTX_TYPE_READ] - 1;
- queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
+ if (wq_unbound)
+ queue->io_cpu = WORK_CPU_UNBOUND;
+ else
+ queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
}
static void nvme_tcp_tls_done(void *data, int status, key_serial_t pskid)
@@ -2155,7 +2161,8 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
nvme_tcp_destroy_io_queues(ctrl, remove);
}
-static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
+static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl,
+ int status)
{
enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
@@ -2165,13 +2172,14 @@ static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
return;
}
- if (nvmf_should_reconnect(ctrl)) {
+ if (nvmf_should_reconnect(ctrl, status)) {
dev_info(ctrl->device, "Reconnecting in %d seconds...\n",
ctrl->opts->reconnect_delay);
queue_delayed_work(nvme_wq, &to_tcp_ctrl(ctrl)->connect_work,
ctrl->opts->reconnect_delay * HZ);
} else {
- dev_info(ctrl->device, "Removing controller...\n");
+ dev_info(ctrl->device, "Removing controller (%d)...\n",
+ status);
nvme_delete_ctrl(ctrl);
}
}
@@ -2252,23 +2260,25 @@ static void nvme_tcp_reconnect_ctrl_work(struct work_struct *work)
struct nvme_tcp_ctrl *tcp_ctrl = container_of(to_delayed_work(work),
struct nvme_tcp_ctrl, connect_work);
struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl;
+ int ret;
++ctrl->nr_reconnects;
- if (nvme_tcp_setup_ctrl(ctrl, false))
+ ret = nvme_tcp_setup_ctrl(ctrl, false);
+ if (ret)
goto requeue;
- dev_info(ctrl->device, "Successfully reconnected (%d attempt)\n",
- ctrl->nr_reconnects);
+ dev_info(ctrl->device, "Successfully reconnected (attempt %d/%d)\n",
+ ctrl->nr_reconnects, ctrl->opts->max_reconnects);
ctrl->nr_reconnects = 0;
return;
requeue:
- dev_info(ctrl->device, "Failed reconnect attempt %d\n",
- ctrl->nr_reconnects);
- nvme_tcp_reconnect_or_remove(ctrl);
+ dev_info(ctrl->device, "Failed reconnect attempt %d/%d\n",
+ ctrl->nr_reconnects, ctrl->opts->max_reconnects);
+ nvme_tcp_reconnect_or_remove(ctrl, ret);
}
static void nvme_tcp_error_recovery_work(struct work_struct *work)
@@ -2295,7 +2305,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
return;
}
- nvme_tcp_reconnect_or_remove(ctrl);
+ nvme_tcp_reconnect_or_remove(ctrl, 0);
}
static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
@@ -2315,6 +2325,7 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl =
container_of(work, struct nvme_ctrl, reset_work);
+ int ret;
nvme_stop_ctrl(ctrl);
nvme_tcp_teardown_ctrl(ctrl, false);
@@ -2328,14 +2339,15 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
return;
}
- if (nvme_tcp_setup_ctrl(ctrl, false))
+ ret = nvme_tcp_setup_ctrl(ctrl, false);
+ if (ret)
goto out_fail;
return;
out_fail:
++ctrl->nr_reconnects;
- nvme_tcp_reconnect_or_remove(ctrl);
+ nvme_tcp_reconnect_or_remove(ctrl, ret);
}
static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl)
@@ -2796,6 +2808,8 @@ static struct nvmf_transport_ops nvme_tcp_transport = {
static int __init nvme_tcp_init_module(void)
{
+ unsigned int wq_flags = WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_SYSFS;
+
BUILD_BUG_ON(sizeof(struct nvme_tcp_hdr) != 8);
BUILD_BUG_ON(sizeof(struct nvme_tcp_cmd_pdu) != 72);
BUILD_BUG_ON(sizeof(struct nvme_tcp_data_pdu) != 24);
@@ -2805,8 +2819,10 @@ static int __init nvme_tcp_init_module(void)
BUILD_BUG_ON(sizeof(struct nvme_tcp_icresp_pdu) != 128);
BUILD_BUG_ON(sizeof(struct nvme_tcp_term_pdu) != 24);
- nvme_tcp_wq = alloc_workqueue("nvme_tcp_wq",
- WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+ if (wq_unbound)
+ wq_flags |= WQ_UNBOUND;
+
+ nvme_tcp_wq = alloc_workqueue("nvme_tcp_wq", wq_flags, 0);
if (!nvme_tcp_wq)
return -ENOMEM;
diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c
index 1c36fcedea..0288315f00 100644
--- a/drivers/nvme/host/trace.c
+++ b/drivers/nvme/host/trace.c
@@ -119,7 +119,10 @@ static const char *nvme_trace_get_lba_status(struct trace_seq *p,
static const char *nvme_trace_admin_format_nvm(struct trace_seq *p, u8 *cdw10)
{
const char *ret = trace_seq_buffer_ptr(p);
- u8 lbaf = cdw10[0] & 0xF;
+ /*
+ * lbafu(bit 13:12) is already in the upper 4 bits, lbafl: bit 03:00.
+ */
+ u8 lbaf = (cdw10[1] & 0x30) | (cdw10[0] & 0xF);
u8 mset = (cdw10[0] >> 4) & 0x1;
u8 pi = (cdw10[0] >> 5) & 0x7;
u8 pil = cdw10[1] & 0x1;
@@ -164,12 +167,27 @@ static const char *nvme_trace_dsm(struct trace_seq *p, u8 *cdw10)
static const char *nvme_trace_zone_mgmt_send(struct trace_seq *p, u8 *cdw10)
{
+ static const char * const zsa_strs[] = {
+ [0x01] = "close zone",
+ [0x02] = "finish zone",
+ [0x03] = "open zone",
+ [0x04] = "reset zone",
+ [0x05] = "offline zone",
+ [0x10] = "set zone descriptor extension"
+ };
const char *ret = trace_seq_buffer_ptr(p);
u64 slba = get_unaligned_le64(cdw10);
+ const char *zsa_str;
u8 zsa = cdw10[12];
u8 all = cdw10[13];
- trace_seq_printf(p, "slba=%llu, zsa=%u, all=%u", slba, zsa, all);
+ if (zsa < ARRAY_SIZE(zsa_strs) && zsa_strs[zsa])
+ zsa_str = zsa_strs[zsa];
+ else
+ zsa_str = "reserved";
+
+ trace_seq_printf(p, "slba=%llu, zsa=%u:%s, all=%u",
+ slba, zsa, zsa_str, all);
trace_seq_putc(p, 0);
return ret;
@@ -177,15 +195,86 @@ static const char *nvme_trace_zone_mgmt_send(struct trace_seq *p, u8 *cdw10)
static const char *nvme_trace_zone_mgmt_recv(struct trace_seq *p, u8 *cdw10)
{
+ static const char * const zrasf_strs[] = {
+ [0x00] = "list all zones",
+ [0x01] = "list the zones in the ZSE: Empty state",
+ [0x02] = "list the zones in the ZSIO: Implicitly Opened state",
+ [0x03] = "list the zones in the ZSEO: Explicitly Opened state",
+ [0x04] = "list the zones in the ZSC: Closed state",
+ [0x05] = "list the zones in the ZSF: Full state",
+ [0x06] = "list the zones in the ZSRO: Read Only state",
+ [0x07] = "list the zones in the ZSO: Offline state",
+ [0x09] = "list the zones that have the zone attribute"
+ };
const char *ret = trace_seq_buffer_ptr(p);
u64 slba = get_unaligned_le64(cdw10);
u32 numd = get_unaligned_le32(cdw10 + 8);
u8 zra = cdw10[12];
u8 zrasf = cdw10[13];
+ const char *zrasf_str;
u8 pr = cdw10[14];
- trace_seq_printf(p, "slba=%llu, numd=%u, zra=%u, zrasf=%u, pr=%u",
- slba, numd, zra, zrasf, pr);
+ if (zrasf < ARRAY_SIZE(zrasf_strs) && zrasf_strs[zrasf])
+ zrasf_str = zrasf_strs[zrasf];
+ else
+ zrasf_str = "reserved";
+
+ trace_seq_printf(p, "slba=%llu, numd=%u, zra=%u, zrasf=%u:%s, pr=%u",
+ slba, numd, zra, zrasf, zrasf_str, pr);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvme_trace_resv_reg(struct trace_seq *p, u8 *cdw10)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 rrega = cdw10[0] & 0x7;
+ u8 iekey = (cdw10[0] >> 3) & 0x1;
+ u8 ptpl = (cdw10[3] >> 6) & 0x3;
+
+ trace_seq_printf(p, "rrega=%u, iekey=%u, ptpl=%u",
+ rrega, iekey, ptpl);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvme_trace_resv_acq(struct trace_seq *p, u8 *cdw10)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 racqa = cdw10[0] & 0x7;
+ u8 iekey = (cdw10[0] >> 3) & 0x1;
+ u8 rtype = cdw10[1];
+
+ trace_seq_printf(p, "racqa=%u, iekey=%u, rtype=%u",
+ racqa, iekey, rtype);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvme_trace_resv_rel(struct trace_seq *p, u8 *cdw10)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 rrela = cdw10[0] & 0x7;
+ u8 iekey = (cdw10[0] >> 3) & 0x1;
+ u8 rtype = cdw10[1];
+
+ trace_seq_printf(p, "rrela=%u, iekey=%u, rtype=%u",
+ rrela, iekey, rtype);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvme_trace_resv_report(struct trace_seq *p, u8 *cdw10)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u32 numd = get_unaligned_le32(cdw10);
+ u8 eds = cdw10[4] & 0x1;
+
+ trace_seq_printf(p, "numd=%u, eds=%u", numd, eds);
trace_seq_putc(p, 0);
return ret;
@@ -243,6 +332,14 @@ const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p,
return nvme_trace_zone_mgmt_send(p, cdw10);
case nvme_cmd_zone_mgmt_recv:
return nvme_trace_zone_mgmt_recv(p, cdw10);
+ case nvme_cmd_resv_register:
+ return nvme_trace_resv_reg(p, cdw10);
+ case nvme_cmd_resv_acquire:
+ return nvme_trace_resv_acq(p, cdw10);
+ case nvme_cmd_resv_release:
+ return nvme_trace_resv_rel(p, cdw10);
+ case nvme_cmd_resv_report:
+ return nvme_trace_resv_report(p, cdw10);
default:
return nvme_trace_common(p, cdw10);
}
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 499bbb0eee..77aa0f440a 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -7,16 +7,6 @@
#include <linux/vmalloc.h>
#include "nvme.h"
-int nvme_revalidate_zones(struct nvme_ns *ns)
-{
- struct request_queue *q = ns->queue;
-
- blk_queue_chunk_sectors(q, ns->head->zsze);
- blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
-
- return blk_revalidate_disk_zones(ns->disk, NULL);
-}
-
static int nvme_set_max_append(struct nvme_ctrl *ctrl)
{
struct nvme_command c = { };
@@ -45,10 +35,10 @@ static int nvme_set_max_append(struct nvme_ctrl *ctrl)
return 0;
}
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
+int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf,
+ struct nvme_zone_info *zi)
{
struct nvme_effects_log *log = ns->head->effects;
- struct request_queue *q = ns->queue;
struct nvme_command c = { };
struct nvme_id_ns_zns *id;
int status;
@@ -99,25 +89,34 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
goto free_data;
}
- ns->head->zsze =
- nvme_lba_to_sect(ns->head, le64_to_cpu(id->lbafe[lbaf].zsze));
- if (!is_power_of_2(ns->head->zsze)) {
+ zi->zone_size = le64_to_cpu(id->lbafe[lbaf].zsze);
+ if (!is_power_of_2(zi->zone_size)) {
dev_warn(ns->ctrl->device,
- "invalid zone size:%llu for namespace:%u\n",
- ns->head->zsze, ns->head->ns_id);
+ "invalid zone size: %llu for namespace: %u\n",
+ zi->zone_size, ns->head->ns_id);
status = -ENODEV;
goto free_data;
}
+ zi->max_open_zones = le32_to_cpu(id->mor) + 1;
+ zi->max_active_zones = le32_to_cpu(id->mar) + 1;
- disk_set_zoned(ns->disk);
- blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
- disk_set_max_open_zones(ns->disk, le32_to_cpu(id->mor) + 1);
- disk_set_max_active_zones(ns->disk, le32_to_cpu(id->mar) + 1);
free_data:
kfree(id);
return status;
}
+void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
+ struct nvme_zone_info *zi)
+{
+ lim->zoned = 1;
+ lim->max_open_zones = zi->max_open_zones;
+ lim->max_active_zones = zi->max_active_zones;
+ lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
+ lim->chunk_sectors = ns->head->zsze =
+ nvme_lba_to_sect(ns->head, zi->zone_size);
+ blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue);
+}
+
static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
unsigned int nr_zones, size_t *buflen)
{
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 39cb570f83..f5b7054a4a 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -428,7 +428,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
id->cqes = (0x4 << 4) | 0x4;
/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
- id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+ id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES);
id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c
index fb518b00f7..8bc3f431c7 100644
--- a/drivers/nvme/target/auth.c
+++ b/drivers/nvme/target/auth.c
@@ -44,6 +44,7 @@ int nvmet_auth_set_key(struct nvmet_host *host, const char *secret,
dhchap_secret = kstrdup(secret, GFP_KERNEL);
if (!dhchap_secret)
return -ENOMEM;
+ down_write(&nvmet_config_sem);
if (set_ctrl) {
kfree(host->dhchap_ctrl_secret);
host->dhchap_ctrl_secret = strim(dhchap_secret);
@@ -53,6 +54,7 @@ int nvmet_auth_set_key(struct nvmet_host *host, const char *secret,
host->dhchap_secret = strim(dhchap_secret);
host->dhchap_key_hash = key_hash;
}
+ up_write(&nvmet_config_sem);
return 0;
}
@@ -124,12 +126,11 @@ int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id)
return ret;
}
-int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
+u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl)
{
int ret = 0;
struct nvmet_host_link *p;
struct nvmet_host *host = NULL;
- const char *hash_name;
down_read(&nvmet_config_sem);
if (nvmet_is_disc_subsys(ctrl->subsys))
@@ -147,13 +148,16 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
}
if (!host) {
pr_debug("host %s not found\n", ctrl->hostnqn);
- ret = -EPERM;
+ ret = NVME_AUTH_DHCHAP_FAILURE_FAILED;
goto out_unlock;
}
ret = nvmet_setup_dhgroup(ctrl, host->dhchap_dhgroup_id);
- if (ret < 0)
+ if (ret < 0) {
pr_warn("Failed to setup DH group");
+ ret = NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE;
+ goto out_unlock;
+ }
if (!host->dhchap_secret) {
pr_debug("No authentication provided\n");
@@ -164,12 +168,6 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
pr_debug("Re-use existing hash ID %d\n",
ctrl->shash_id);
} else {
- hash_name = nvme_auth_hmac_name(host->dhchap_hash_id);
- if (!hash_name) {
- pr_warn("Hash ID %d invalid\n", host->dhchap_hash_id);
- ret = -EINVAL;
- goto out_unlock;
- }
ctrl->shash_id = host->dhchap_hash_id;
}
@@ -178,7 +176,7 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
ctrl->host_key = nvme_auth_extract_key(host->dhchap_secret + 10,
host->dhchap_key_hash);
if (IS_ERR(ctrl->host_key)) {
- ret = PTR_ERR(ctrl->host_key);
+ ret = NVME_AUTH_DHCHAP_FAILURE_NOT_USABLE;
ctrl->host_key = NULL;
goto out_free_hash;
}
@@ -196,7 +194,7 @@ int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
ctrl->ctrl_key = nvme_auth_extract_key(host->dhchap_ctrl_secret + 10,
host->dhchap_ctrl_key_hash);
if (IS_ERR(ctrl->ctrl_key)) {
- ret = PTR_ERR(ctrl->ctrl_key);
+ ret = NVME_AUTH_DHCHAP_FAILURE_NOT_USABLE;
ctrl->ctrl_key = NULL;
goto out_free_hash;
}
@@ -316,7 +314,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
req->sq->dhchap_c1,
challenge, shash_len);
if (ret)
- goto out_free_response;
+ goto out_free_challenge;
}
pr_debug("ctrl %d qid %d host response seq %u transaction %d\n",
@@ -327,7 +325,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
GFP_KERNEL);
if (!shash) {
ret = -ENOMEM;
- goto out_free_response;
+ goto out_free_challenge;
}
shash->tfm = shash_tfm;
ret = crypto_shash_init(shash);
@@ -363,9 +361,10 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
goto out;
ret = crypto_shash_final(shash, response);
out:
+ kfree(shash);
+out_free_challenge:
if (challenge != req->sq->dhchap_c1)
kfree(challenge);
- kfree(shash);
out_free_response:
nvme_auth_free_key(transformed_key);
out_free_tfm:
@@ -429,14 +428,14 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response,
req->sq->dhchap_c2,
challenge, shash_len);
if (ret)
- goto out_free_response;
+ goto out_free_challenge;
}
shash = kzalloc(sizeof(*shash) + crypto_shash_descsize(shash_tfm),
GFP_KERNEL);
if (!shash) {
ret = -ENOMEM;
- goto out_free_response;
+ goto out_free_challenge;
}
shash->tfm = shash_tfm;
@@ -473,14 +472,15 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response,
goto out;
ret = crypto_shash_final(shash, response);
out:
+ kfree(shash);
+out_free_challenge:
if (challenge != req->sq->dhchap_c2)
kfree(challenge);
- kfree(shash);
out_free_response:
nvme_auth_free_key(transformed_key);
out_free_tfm:
crypto_free_shash(shash_tfm);
- return 0;
+ return ret;
}
int nvmet_auth_ctrl_exponential(struct nvmet_req *req,
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 3ef6bc6556..685e89b35d 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -273,6 +273,32 @@ static ssize_t nvmet_param_inline_data_size_store(struct config_item *item,
CONFIGFS_ATTR(nvmet_, param_inline_data_size);
+static ssize_t nvmet_param_max_queue_size_show(struct config_item *item,
+ char *page)
+{
+ struct nvmet_port *port = to_nvmet_port(item);
+
+ return snprintf(page, PAGE_SIZE, "%d\n", port->max_queue_size);
+}
+
+static ssize_t nvmet_param_max_queue_size_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct nvmet_port *port = to_nvmet_port(item);
+ int ret;
+
+ if (nvmet_is_port_enabled(port, __func__))
+ return -EACCES;
+ ret = kstrtoint(page, 0, &port->max_queue_size);
+ if (ret) {
+ pr_err("Invalid value '%s' for max_queue_size\n", page);
+ return -EINVAL;
+ }
+ return count;
+}
+
+CONFIGFS_ATTR(nvmet_, param_max_queue_size);
+
#ifdef CONFIG_BLK_DEV_INTEGRITY
static ssize_t nvmet_param_pi_enable_show(struct config_item *item,
char *page)
@@ -384,7 +410,29 @@ static ssize_t nvmet_addr_tsas_show(struct config_item *item,
return sprintf(page, "%s\n", nvmet_addr_tsas_rdma[i].name);
}
}
- return sprintf(page, "reserved\n");
+ return sprintf(page, "\n");
+}
+
+static u8 nvmet_addr_tsas_rdma_store(const char *page)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_rdma); i++) {
+ if (sysfs_streq(page, nvmet_addr_tsas_rdma[i].name))
+ return nvmet_addr_tsas_rdma[i].type;
+ }
+ return NVMF_RDMA_QPTYPE_INVALID;
+}
+
+static u8 nvmet_addr_tsas_tcp_store(const char *page)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_tcp); i++) {
+ if (sysfs_streq(page, nvmet_addr_tsas_tcp[i].name))
+ return nvmet_addr_tsas_tcp[i].type;
+ }
+ return NVMF_TCP_SECTYPE_INVALID;
}
static ssize_t nvmet_addr_tsas_store(struct config_item *item,
@@ -392,20 +440,19 @@ static ssize_t nvmet_addr_tsas_store(struct config_item *item,
{
struct nvmet_port *port = to_nvmet_port(item);
u8 treq = nvmet_port_disc_addr_treq_mask(port);
- u8 sectype;
- int i;
+ u8 sectype, qptype;
if (nvmet_is_port_enabled(port, __func__))
return -EACCES;
- if (port->disc_addr.trtype != NVMF_TRTYPE_TCP)
- return -EINVAL;
-
- for (i = 0; i < ARRAY_SIZE(nvmet_addr_tsas_tcp); i++) {
- if (sysfs_streq(page, nvmet_addr_tsas_tcp[i].name)) {
- sectype = nvmet_addr_tsas_tcp[i].type;
+ if (port->disc_addr.trtype == NVMF_TRTYPE_RDMA) {
+ qptype = nvmet_addr_tsas_rdma_store(page);
+ if (qptype == port->disc_addr.tsas.rdma.qptype)
+ return count;
+ } else if (port->disc_addr.trtype == NVMF_TRTYPE_TCP) {
+ sectype = nvmet_addr_tsas_tcp_store(page);
+ if (sectype != NVMF_TCP_SECTYPE_INVALID)
goto found;
- }
}
pr_err("Invalid value '%s' for tsas\n", page);
@@ -650,10 +697,18 @@ static ssize_t nvmet_ns_enable_store(struct config_item *item,
if (kstrtobool(page, &enable))
return -EINVAL;
+ /*
+ * take a global nvmet_config_sem because the disable routine has a
+ * window where it releases the subsys-lock, giving a chance to
+ * a parallel enable to concurrently execute causing the disable to
+ * have a misaccounting of the ns percpu_ref.
+ */
+ down_write(&nvmet_config_sem);
if (enable)
ret = nvmet_ns_enable(ns);
else
nvmet_ns_disable(ns);
+ up_write(&nvmet_config_sem);
return ret ? ret : count;
}
@@ -1599,6 +1654,11 @@ static struct config_group *nvmet_subsys_make(struct config_group *group,
return ERR_PTR(-EINVAL);
}
+ if (sysfs_streq(name, nvmet_disc_subsys->subsysnqn)) {
+ pr_err("can't create subsystem using unique discovery NQN\n");
+ return ERR_PTR(-EINVAL);
+ }
+
subsys = nvmet_subsys_alloc(name, NVME_NQN_NVME);
if (IS_ERR(subsys))
return ERR_CAST(subsys);
@@ -1871,6 +1931,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
&nvmet_attr_addr_trtype,
&nvmet_attr_addr_tsas,
&nvmet_attr_param_inline_data_size,
+ &nvmet_attr_param_max_queue_size,
#ifdef CONFIG_BLK_DEV_INTEGRITY
&nvmet_attr_param_pi_enable,
#endif
@@ -1929,6 +1990,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
INIT_LIST_HEAD(&port->subsystems);
INIT_LIST_HEAD(&port->referrals);
port->inline_data_size = -1; /* < 0 == let the transport choose */
+ port->max_queue_size = -1; /* < 0 == let the transport choose */
port->disc_addr.portid = cpu_to_le16(portid);
port->disc_addr.adrfam = NVMF_ADDR_FAMILY_MAX;
@@ -1974,11 +2036,17 @@ static struct config_group nvmet_ports_group;
static ssize_t nvmet_host_dhchap_key_show(struct config_item *item,
char *page)
{
- u8 *dhchap_secret = to_host(item)->dhchap_secret;
+ u8 *dhchap_secret;
+ ssize_t ret;
+ down_read(&nvmet_config_sem);
+ dhchap_secret = to_host(item)->dhchap_secret;
if (!dhchap_secret)
- return sprintf(page, "\n");
- return sprintf(page, "%s\n", dhchap_secret);
+ ret = sprintf(page, "\n");
+ else
+ ret = sprintf(page, "%s\n", dhchap_secret);
+ up_read(&nvmet_config_sem);
+ return ret;
}
static ssize_t nvmet_host_dhchap_key_store(struct config_item *item,
@@ -2002,10 +2070,16 @@ static ssize_t nvmet_host_dhchap_ctrl_key_show(struct config_item *item,
char *page)
{
u8 *dhchap_secret = to_host(item)->dhchap_ctrl_secret;
+ ssize_t ret;
+ down_read(&nvmet_config_sem);
+ dhchap_secret = to_host(item)->dhchap_ctrl_secret;
if (!dhchap_secret)
- return sprintf(page, "\n");
- return sprintf(page, "%s\n", dhchap_secret);
+ ret = sprintf(page, "\n");
+ else
+ ret = sprintf(page, "%s\n", dhchap_secret);
+ up_read(&nvmet_config_sem);
+ return ret;
}
static ssize_t nvmet_host_dhchap_ctrl_key_store(struct config_item *item,
@@ -2143,7 +2217,49 @@ static const struct config_item_type nvmet_hosts_type = {
static struct config_group nvmet_hosts_group;
+static ssize_t nvmet_root_discovery_nqn_show(struct config_item *item,
+ char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%s\n", nvmet_disc_subsys->subsysnqn);
+}
+
+static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct list_head *entry;
+ size_t len;
+
+ len = strcspn(page, "\n");
+ if (!len || len > NVMF_NQN_FIELD_LEN - 1)
+ return -EINVAL;
+
+ down_write(&nvmet_config_sem);
+ list_for_each(entry, &nvmet_subsystems_group.cg_children) {
+ struct config_item *item =
+ container_of(entry, struct config_item, ci_entry);
+
+ if (!strncmp(config_item_name(item), page, len)) {
+ pr_err("duplicate NQN %s\n", config_item_name(item));
+ up_write(&nvmet_config_sem);
+ return -EINVAL;
+ }
+ }
+ memset(nvmet_disc_subsys->subsysnqn, 0, NVMF_NQN_FIELD_LEN);
+ memcpy(nvmet_disc_subsys->subsysnqn, page, len);
+ up_write(&nvmet_config_sem);
+
+ return len;
+}
+
+CONFIGFS_ATTR(nvmet_root_, discovery_nqn);
+
+static struct configfs_attribute *nvmet_root_attrs[] = {
+ &nvmet_root_attr_discovery_nqn,
+ NULL,
+};
+
static const struct config_item_type nvmet_root_type = {
+ .ct_attrs = nvmet_root_attrs,
.ct_owner = THIS_MODULE,
};
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 7a6b3d37cc..4ff460ba28 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -358,6 +358,18 @@ int nvmet_enable_port(struct nvmet_port *port)
if (port->inline_data_size < 0)
port->inline_data_size = 0;
+ /*
+ * If the transport didn't set the max_queue_size properly, then clamp
+ * it to the target limits. Also set default values in case the
+ * transport didn't set it at all.
+ */
+ if (port->max_queue_size < 0)
+ port->max_queue_size = NVMET_MAX_QUEUE_SIZE;
+ else
+ port->max_queue_size = clamp_t(int, port->max_queue_size,
+ NVMET_MIN_QUEUE_SIZE,
+ NVMET_MAX_QUEUE_SIZE);
+
port->enabled = true;
port->tr_ops = ops;
return 0;
@@ -806,6 +818,15 @@ void nvmet_sq_destroy(struct nvmet_sq *sq)
percpu_ref_exit(&sq->ref);
nvmet_auth_sq_free(sq);
+ /*
+ * we must reference the ctrl again after waiting for inflight IO
+ * to complete. Because admin connect may have sneaked in after we
+ * store sq->ctrl locally, but before we killed the percpu_ref. the
+ * admin connect allocates and assigns sq->ctrl, which now needs a
+ * final ref put, as this ctrl is going away.
+ */
+ ctrl = sq->ctrl;
+
if (ctrl) {
/*
* The teardown flow may take some time, and the host may not
@@ -936,6 +957,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
req->metadata_sg_cnt = 0;
req->transfer_len = 0;
req->metadata_len = 0;
+ req->cqe->result.u64 = 0;
req->cqe->status = 0;
req->cqe->sq_head = 0;
req->ns = NULL;
@@ -1226,9 +1248,10 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
ctrl->cap |= (15ULL << 24);
/* maximum queue entries supported: */
if (ctrl->ops->get_max_queue_size)
- ctrl->cap |= ctrl->ops->get_max_queue_size(ctrl) - 1;
+ ctrl->cap |= min_t(u16, ctrl->ops->get_max_queue_size(ctrl),
+ ctrl->port->max_queue_size) - 1;
else
- ctrl->cap |= NVMET_QUEUE_SIZE - 1;
+ ctrl->cap |= ctrl->port->max_queue_size - 1;
if (nvmet_is_passthru_subsys(ctrl->subsys))
nvmet_passthrough_override_cap(ctrl);
@@ -1414,6 +1437,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
kref_init(&ctrl->ref);
ctrl->subsys = subsys;
+ ctrl->pi_support = ctrl->port->pi_enable && ctrl->subsys->pi_support;
nvmet_init_cap(ctrl);
WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL);
@@ -1530,6 +1554,13 @@ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
}
down_read(&nvmet_config_sem);
+ if (!strncmp(nvmet_disc_subsys->subsysnqn, subsysnqn,
+ NVMF_NQN_SIZE)) {
+ if (kref_get_unless_zero(&nvmet_disc_subsys->ref)) {
+ up_read(&nvmet_config_sem);
+ return nvmet_disc_subsys;
+ }
+ }
list_for_each_entry(p, &port->subsystems, entry) {
if (!strncmp(p->subsys->subsysnqn, subsysnqn,
NVMF_NQN_SIZE)) {
@@ -1665,7 +1696,8 @@ static int __init nvmet_init(void)
if (!buffered_io_wq)
goto out_free_zbd_work_queue;
- nvmet_wq = alloc_workqueue("nvmet-wq", WQ_MEM_RECLAIM, 0);
+ nvmet_wq = alloc_workqueue("nvmet-wq",
+ WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
if (!nvmet_wq)
goto out_free_buffered_work_queue;
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 68e82ccc0e..ce54da8c6b 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -282,7 +282,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
id->lpa = (1 << 2);
/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
- id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+ id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
id->sgls = cpu_to_le32(1 << 0); /* we always support SGLs */
if (ctrl->ops->flags & NVMF_KEYED_SGLS)
diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c
index eb7785be0c..cb34d644ed 100644
--- a/drivers/nvme/target/fabrics-cmd-auth.c
+++ b/drivers/nvme/target/fabrics-cmd-auth.c
@@ -31,7 +31,7 @@ void nvmet_auth_sq_init(struct nvmet_sq *sq)
sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE;
}
-static u16 nvmet_auth_negotiate(struct nvmet_req *req, void *d)
+static u8 nvmet_auth_negotiate(struct nvmet_req *req, void *d)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvmf_auth_dhchap_negotiate_data *data = d;
@@ -109,7 +109,7 @@ static u16 nvmet_auth_negotiate(struct nvmet_req *req, void *d)
return 0;
}
-static u16 nvmet_auth_reply(struct nvmet_req *req, void *d)
+static u8 nvmet_auth_reply(struct nvmet_req *req, void *d)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvmf_auth_dhchap_reply_data *data = d;
@@ -172,7 +172,7 @@ static u16 nvmet_auth_reply(struct nvmet_req *req, void *d)
return 0;
}
-static u16 nvmet_auth_failure2(void *d)
+static u8 nvmet_auth_failure2(void *d)
{
struct nvmf_auth_dhchap_failure_data *data = d;
@@ -186,6 +186,7 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
void *d;
u32 tl;
u16 status = 0;
+ u8 dhchap_status;
if (req->cmd->auth_send.secp != NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER) {
status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
@@ -237,30 +238,32 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
if (data->auth_type == NVME_AUTH_COMMON_MESSAGES) {
if (data->auth_id == NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE) {
/* Restart negotiation */
- pr_debug("%s: ctrl %d qid %d reset negotiation\n", __func__,
- ctrl->cntlid, req->sq->qid);
+ pr_debug("%s: ctrl %d qid %d reset negotiation\n",
+ __func__, ctrl->cntlid, req->sq->qid);
if (!req->sq->qid) {
- if (nvmet_setup_auth(ctrl) < 0) {
- status = NVME_SC_INTERNAL;
- pr_err("ctrl %d qid 0 failed to setup"
- "re-authentication",
+ dhchap_status = nvmet_setup_auth(ctrl);
+ if (dhchap_status) {
+ pr_err("ctrl %d qid 0 failed to setup re-authentication\n",
ctrl->cntlid);
- goto done_failure1;
+ req->sq->dhchap_status = dhchap_status;
+ req->sq->dhchap_step =
+ NVME_AUTH_DHCHAP_MESSAGE_FAILURE1;
+ goto done_kfree;
}
}
- req->sq->dhchap_step = NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE;
+ req->sq->dhchap_step =
+ NVME_AUTH_DHCHAP_MESSAGE_NEGOTIATE;
} else if (data->auth_id != req->sq->dhchap_step)
goto done_failure1;
/* Validate negotiation parameters */
- status = nvmet_auth_negotiate(req, d);
- if (status == 0)
+ dhchap_status = nvmet_auth_negotiate(req, d);
+ if (dhchap_status == 0)
req->sq->dhchap_step =
NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE;
else {
req->sq->dhchap_step =
NVME_AUTH_DHCHAP_MESSAGE_FAILURE1;
- req->sq->dhchap_status = status;
- status = 0;
+ req->sq->dhchap_status = dhchap_status;
}
goto done_kfree;
}
@@ -284,15 +287,14 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
switch (data->auth_id) {
case NVME_AUTH_DHCHAP_MESSAGE_REPLY:
- status = nvmet_auth_reply(req, d);
- if (status == 0)
+ dhchap_status = nvmet_auth_reply(req, d);
+ if (dhchap_status == 0)
req->sq->dhchap_step =
NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1;
else {
req->sq->dhchap_step =
NVME_AUTH_DHCHAP_MESSAGE_FAILURE1;
- req->sq->dhchap_status = status;
- status = 0;
+ req->sq->dhchap_status = dhchap_status;
}
goto done_kfree;
case NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2:
@@ -301,13 +303,12 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
__func__, ctrl->cntlid, req->sq->qid);
goto done_kfree;
case NVME_AUTH_DHCHAP_MESSAGE_FAILURE2:
- status = nvmet_auth_failure2(d);
- if (status) {
+ dhchap_status = nvmet_auth_failure2(d);
+ if (dhchap_status) {
pr_warn("ctrl %d qid %d: authentication failed (%d)\n",
- ctrl->cntlid, req->sq->qid, status);
- req->sq->dhchap_status = status;
+ ctrl->cntlid, req->sq->qid, dhchap_status);
+ req->sq->dhchap_status = dhchap_status;
req->sq->authenticated = false;
- status = 0;
}
goto done_kfree;
default:
@@ -332,7 +333,6 @@ done:
pr_debug("%s: ctrl %d qid %d nvme status %x error loc %d\n",
__func__, ctrl->cntlid, req->sq->qid,
status, req->error_loc);
- req->cqe->result.u64 = 0;
if (req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2 &&
req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) {
unsigned long auth_expire_secs = ctrl->kato ? ctrl->kato : 120;
@@ -515,8 +515,6 @@ void nvmet_execute_auth_receive(struct nvmet_req *req)
status = nvmet_copy_to_sgl(req, 0, d, al);
kfree(d);
done:
- req->cqe->result.u64 = 0;
-
if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2)
nvmet_auth_sq_free(req->sq);
else if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) {
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 9964ffe347..69d77d34be 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -157,7 +157,8 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
}
- if (sqsize > mqes) {
+ /* for fabrics, this value applies to only the I/O Submission Queues */
+ if (qid && sqsize > mqes) {
pr_warn("sqsize %u is larger than MQES supported %u cntlid %d\n",
sqsize, mqes, ctrl->cntlid);
req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
@@ -210,7 +211,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
struct nvmf_connect_data *d;
struct nvmet_ctrl *ctrl = NULL;
u16 status;
- int ret;
+ u8 dhchap_status;
if (!nvmet_check_transfer_len(req, sizeof(struct nvmf_connect_data)))
return;
@@ -225,9 +226,6 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
if (status)
goto out;
- /* zero out initial completion result, assign values as needed */
- req->cqe->result.u32 = 0;
-
if (c->recfmt != 0) {
pr_warn("invalid connect version (%d).\n",
le16_to_cpu(c->recfmt));
@@ -251,15 +249,14 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
if (status)
goto out;
- ctrl->pi_support = ctrl->port->pi_enable && ctrl->subsys->pi_support;
-
uuid_copy(&ctrl->hostid, &d->hostid);
- ret = nvmet_setup_auth(ctrl);
- if (ret < 0) {
- pr_err("Failed to setup authentication, error %d\n", ret);
+ dhchap_status = nvmet_setup_auth(ctrl);
+ if (dhchap_status) {
+ pr_err("Failed to setup authentication, dhchap status %u\n",
+ dhchap_status);
nvmet_ctrl_put(ctrl);
- if (ret == -EPERM)
+ if (dhchap_status == NVME_AUTH_DHCHAP_FAILURE_FAILED)
status = (NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR);
else
status = NVME_SC_INTERNAL;
@@ -305,9 +302,6 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
if (status)
goto out;
- /* zero out initial completion result, assign values as needed */
- req->cqe->result.u32 = 0;
-
if (c->recfmt != 0) {
pr_warn("invalid connect version (%d).\n",
le16_to_cpu(c->recfmt));
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index fd229f310c..381b439473 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -148,7 +148,7 @@ struct nvmet_fc_tgt_queue {
struct workqueue_struct *work_q;
struct kref ref;
/* array of fcp_iods */
- struct nvmet_fc_fcp_iod fod[] __counted_by(sqsize);
+ struct nvmet_fc_fcp_iod fod[] /* __counted_by(sqsize) */;
} __aligned(sizeof(unsigned long long));
struct nvmet_fc_hostport {
@@ -1115,16 +1115,21 @@ nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
}
static bool
-nvmet_fc_assoc_exits(struct nvmet_fc_tgtport *tgtport, u64 association_id)
+nvmet_fc_assoc_exists(struct nvmet_fc_tgtport *tgtport, u64 association_id)
{
struct nvmet_fc_tgt_assoc *a;
+ bool found = false;
+ rcu_read_lock();
list_for_each_entry_rcu(a, &tgtport->assoc_list, a_list) {
- if (association_id == a->association_id)
- return true;
+ if (association_id == a->association_id) {
+ found = true;
+ break;
+ }
}
+ rcu_read_unlock();
- return false;
+ return found;
}
static struct nvmet_fc_tgt_assoc *
@@ -1164,13 +1169,11 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
ran = ran << BYTES_FOR_QID_SHIFT;
spin_lock_irqsave(&tgtport->lock, flags);
- rcu_read_lock();
- if (!nvmet_fc_assoc_exits(tgtport, ran)) {
+ if (!nvmet_fc_assoc_exists(tgtport, ran)) {
assoc->association_id = ran;
list_add_tail_rcu(&assoc->a_list, &tgtport->assoc_list);
done = true;
}
- rcu_read_unlock();
spin_unlock_irqrestore(&tgtport->lock, flags);
} while (!done);
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 1471af250e..913cd2ec7a 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -1556,7 +1556,9 @@ static const struct attribute_group *fcloop_dev_attr_groups[] = {
NULL,
};
-static struct class *fcloop_class;
+static const struct class fcloop_class = {
+ .name = "fcloop",
+};
static struct device *fcloop_device;
@@ -1564,15 +1566,14 @@ static int __init fcloop_init(void)
{
int ret;
- fcloop_class = class_create("fcloop");
- if (IS_ERR(fcloop_class)) {
+ ret = class_register(&fcloop_class);
+ if (ret) {
pr_err("couldn't register class fcloop\n");
- ret = PTR_ERR(fcloop_class);
return ret;
}
fcloop_device = device_create_with_groups(
- fcloop_class, NULL, MKDEV(0, 0), NULL,
+ &fcloop_class, NULL, MKDEV(0, 0), NULL,
fcloop_dev_attr_groups, "ctl");
if (IS_ERR(fcloop_device)) {
pr_err("couldn't create ctl device!\n");
@@ -1585,7 +1586,7 @@ static int __init fcloop_init(void)
return 0;
out_destroy_class:
- class_destroy(fcloop_class);
+ class_unregister(&fcloop_class);
return ret;
}
@@ -1643,8 +1644,8 @@ static void __exit fcloop_exit(void)
put_device(fcloop_device);
- device_destroy(fcloop_class, MKDEV(0, 0));
- class_destroy(fcloop_class);
+ device_destroy(&fcloop_class, MKDEV(0, 0));
+ class_unregister(&fcloop_class);
}
module_init(fcloop_init);
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index f11400a908..6426aac263 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -50,10 +50,10 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
{
- if (ns->bdev_handle) {
- bdev_release(ns->bdev_handle);
+ if (ns->bdev_file) {
+ fput(ns->bdev_file);
ns->bdev = NULL;
- ns->bdev_handle = NULL;
+ ns->bdev_file = NULL;
}
}
@@ -85,18 +85,18 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns)
if (ns->buffered_io)
return -ENOTBLK;
- ns->bdev_handle = bdev_open_by_path(ns->device_path,
+ ns->bdev_file = bdev_file_open_by_path(ns->device_path,
BLK_OPEN_READ | BLK_OPEN_WRITE, NULL, NULL);
- if (IS_ERR(ns->bdev_handle)) {
- ret = PTR_ERR(ns->bdev_handle);
+ if (IS_ERR(ns->bdev_file)) {
+ ret = PTR_ERR(ns->bdev_file);
if (ret != -ENOTBLK) {
pr_err("failed to open block device %s: (%d)\n",
ns->device_path, ret);
}
- ns->bdev_handle = NULL;
+ ns->bdev_file = NULL;
return ret;
}
- ns->bdev = ns->bdev_handle->bdev;
+ ns->bdev = file_bdev(ns->bdev_file);
ns->size = bdev_nr_bytes(ns->bdev);
ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 477416abf8..2f22b07eab 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -58,7 +58,7 @@
struct nvmet_ns {
struct percpu_ref ref;
- struct bdev_handle *bdev_handle;
+ struct file *bdev_file;
struct block_device *bdev;
struct file *file;
bool readonly;
@@ -113,8 +113,8 @@ struct nvmet_sq {
bool authenticated;
struct delayed_work auth_expired_work;
u16 dhchap_tid;
- u16 dhchap_status;
- int dhchap_step;
+ u8 dhchap_status;
+ u8 dhchap_step;
u8 *dhchap_c1;
u8 *dhchap_c2;
u32 dhchap_s1;
@@ -163,6 +163,7 @@ struct nvmet_port {
void *priv;
bool enabled;
int inline_data_size;
+ int max_queue_size;
const struct nvmet_fabrics_ops *tr_ops;
bool pi_enable;
};
@@ -544,9 +545,10 @@ void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
u8 event_info, u8 log_page);
bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid);
-#define NVMET_QUEUE_SIZE 1024
+#define NVMET_MIN_QUEUE_SIZE 16
+#define NVMET_MAX_QUEUE_SIZE 1024
#define NVMET_NR_QUEUES 128
-#define NVMET_MAX_CMD NVMET_QUEUE_SIZE
+#define NVMET_MAX_CMD(ctrl) (NVME_CAP_MQES(ctrl->cap) + 1)
/*
* Nice round number that makes a list of nsids fit into a page.
@@ -712,7 +714,7 @@ void nvmet_execute_auth_receive(struct nvmet_req *req);
int nvmet_auth_set_key(struct nvmet_host *host, const char *secret,
bool set_ctrl);
int nvmet_auth_set_host_hash(struct nvmet_host *host, const char *hash);
-int nvmet_setup_auth(struct nvmet_ctrl *ctrl);
+u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl);
void nvmet_auth_sq_init(struct nvmet_sq *sq);
void nvmet_destroy_auth(struct nvmet_ctrl *ctrl);
void nvmet_auth_sq_free(struct nvmet_sq *sq);
@@ -731,7 +733,7 @@ int nvmet_auth_ctrl_exponential(struct nvmet_req *req,
int nvmet_auth_ctrl_sesskey(struct nvmet_req *req,
u8 *buf, int buf_size);
#else
-static inline int nvmet_setup_auth(struct nvmet_ctrl *ctrl)
+static inline u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl)
{
return 0;
}
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index f2d963e1fe..f003782d4e 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -132,7 +132,7 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
id->sqes = min_t(__u8, ((0x6 << 4) | 0x6), id->sqes);
id->cqes = min_t(__u8, ((0x4 << 4) | 0x4), id->cqes);
- id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
+ id->maxcmd = cpu_to_le16(NVMET_MAX_CMD(ctrl));
/* don't support fuse commands */
id->fuses = 0;
@@ -226,13 +226,13 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w)
req->cmd->common.opcode == nvme_admin_identify) {
switch (req->cmd->identify.cns) {
case NVME_ID_CNS_CTRL:
- nvmet_passthru_override_id_ctrl(req);
+ status = nvmet_passthru_override_id_ctrl(req);
break;
case NVME_ID_CNS_NS:
- nvmet_passthru_override_id_ns(req);
+ status = nvmet_passthru_override_id_ns(req);
break;
case NVME_ID_CNS_NS_DESC_LIST:
- nvmet_passthru_override_id_descs(req);
+ status = nvmet_passthru_override_id_descs(req);
break;
}
} else if (status < 0)
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 3a0f2c170f..689bb5d3cf 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -53,7 +53,6 @@ struct nvmet_rdma_cmd {
enum {
NVMET_RDMA_REQ_INLINE_DATA = (1 << 0),
- NVMET_RDMA_REQ_INVALIDATE_RKEY = (1 << 1),
};
struct nvmet_rdma_rsp {
@@ -475,12 +474,8 @@ nvmet_rdma_alloc_rsps(struct nvmet_rdma_queue *queue)
return 0;
out_free:
- while (--i >= 0) {
- struct nvmet_rdma_rsp *rsp = &queue->rsps[i];
-
- list_del(&rsp->free_list);
- nvmet_rdma_free_rsp(ndev, rsp);
- }
+ while (--i >= 0)
+ nvmet_rdma_free_rsp(ndev, &queue->rsps[i]);
kfree(queue->rsps);
out:
return ret;
@@ -491,12 +486,8 @@ static void nvmet_rdma_free_rsps(struct nvmet_rdma_queue *queue)
struct nvmet_rdma_device *ndev = queue->dev;
int i, nr_rsps = queue->recv_queue_size * 2;
- for (i = 0; i < nr_rsps; i++) {
- struct nvmet_rdma_rsp *rsp = &queue->rsps[i];
-
- list_del(&rsp->free_list);
- nvmet_rdma_free_rsp(ndev, rsp);
- }
+ for (i = 0; i < nr_rsps; i++)
+ nvmet_rdma_free_rsp(ndev, &queue->rsps[i]);
kfree(queue->rsps);
}
@@ -722,7 +713,7 @@ static void nvmet_rdma_queue_response(struct nvmet_req *req)
struct rdma_cm_id *cm_id = rsp->queue->cm_id;
struct ib_send_wr *first_wr;
- if (rsp->flags & NVMET_RDMA_REQ_INVALIDATE_RKEY) {
+ if (rsp->invalidate_rkey) {
rsp->send_wr.opcode = IB_WR_SEND_WITH_INV;
rsp->send_wr.ex.invalidate_rkey = rsp->invalidate_rkey;
} else {
@@ -905,10 +896,8 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp,
goto error_out;
rsp->n_rdma += ret;
- if (invalidate) {
+ if (invalidate)
rsp->invalidate_rkey = key;
- rsp->flags |= NVMET_RDMA_REQ_INVALIDATE_RKEY;
- }
return 0;
@@ -1047,6 +1036,7 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
rsp->req.cmd = cmd->nvme_cmd;
rsp->req.port = queue->port;
rsp->n_rdma = 0;
+ rsp->invalidate_rkey = 0;
if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) {
unsigned long flags;
@@ -1816,18 +1806,14 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
static void nvmet_rdma_delete_ctrl(struct nvmet_ctrl *ctrl)
{
- struct nvmet_rdma_queue *queue;
+ struct nvmet_rdma_queue *queue, *n;
-restart:
mutex_lock(&nvmet_rdma_queue_mutex);
- list_for_each_entry(queue, &nvmet_rdma_queue_list, queue_list) {
- if (queue->nvme_sq.ctrl == ctrl) {
- list_del_init(&queue->queue_list);
- mutex_unlock(&nvmet_rdma_queue_mutex);
-
- __nvmet_rdma_queue_disconnect(queue);
- goto restart;
- }
+ list_for_each_entry_safe(queue, n, &nvmet_rdma_queue_list, queue_list) {
+ if (queue->nvme_sq.ctrl != ctrl)
+ continue;
+ list_del_init(&queue->queue_list);
+ __nvmet_rdma_queue_disconnect(queue);
}
mutex_unlock(&nvmet_rdma_queue_mutex);
}
@@ -1956,6 +1942,14 @@ static int nvmet_rdma_add_port(struct nvmet_port *nport)
nport->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE;
}
+ if (nport->max_queue_size < 0) {
+ nport->max_queue_size = NVME_RDMA_DEFAULT_QUEUE_SIZE;
+ } else if (nport->max_queue_size > NVME_RDMA_MAX_QUEUE_SIZE) {
+ pr_warn("max_queue_size %u is too large, reducing to %u\n",
+ nport->max_queue_size, NVME_RDMA_MAX_QUEUE_SIZE);
+ nport->max_queue_size = NVME_RDMA_MAX_QUEUE_SIZE;
+ }
+
ret = inet_pton_with_scope(&init_net, af, nport->disc_addr.traddr,
nport->disc_addr.trsvcid, &port->addr);
if (ret) {
@@ -2015,6 +2009,8 @@ static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
static u16 nvmet_rdma_get_max_queue_size(const struct nvmet_ctrl *ctrl)
{
+ if (ctrl->pi_support)
+ return NVME_RDMA_MAX_METADATA_QUEUE_SIZE;
return NVME_RDMA_MAX_QUEUE_SIZE;
}
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 8d4531a160..380f22ee3e 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -899,6 +899,7 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue)
pr_err("bad nvme-tcp pdu length (%d)\n",
le32_to_cpu(icreq->hdr.plen));
nvmet_tcp_fatal_error(queue);
+ return -EPROTO;
}
if (icreq->pfv != NVME_TCP_PFV_1_0) {
@@ -1588,7 +1589,6 @@ static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue)
static void nvmet_tcp_release_queue_work(struct work_struct *w)
{
- struct page *page;
struct nvmet_tcp_queue *queue =
container_of(w, struct nvmet_tcp_queue, release_work);
@@ -1612,8 +1612,7 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
if (queue->hdr_digest || queue->data_digest)
nvmet_tcp_free_crypto(queue);
ida_free(&nvmet_tcp_queue_ida, queue->idx);
- page = virt_to_head_page(queue->pf_cache.va);
- __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
+ page_frag_cache_drain(&queue->pf_cache);
kfree(queue);
}
diff --git a/drivers/nvme/target/trace.c b/drivers/nvme/target/trace.c
index 6ee1f3db81..8d1806a828 100644
--- a/drivers/nvme/target/trace.c
+++ b/drivers/nvme/target/trace.c
@@ -119,6 +119,67 @@ const char *nvmet_trace_parse_admin_cmd(struct trace_seq *p,
}
}
+static const char *nvmet_trace_zone_mgmt_send(struct trace_seq *p, u8 *cdw10)
+{
+ static const char * const zsa_strs[] = {
+ [0x01] = "close zone",
+ [0x02] = "finish zone",
+ [0x03] = "open zone",
+ [0x04] = "reset zone",
+ [0x05] = "offline zone",
+ [0x10] = "set zone descriptor extension"
+ };
+ const char *ret = trace_seq_buffer_ptr(p);
+ u64 slba = get_unaligned_le64(cdw10);
+ const char *zsa_str;
+ u8 zsa = cdw10[12];
+ u8 all = cdw10[13];
+
+ if (zsa < ARRAY_SIZE(zsa_strs) && zsa_strs[zsa])
+ zsa_str = zsa_strs[zsa];
+ else
+ zsa_str = "reserved";
+
+ trace_seq_printf(p, "slba=%llu, zsa=%u:%s, all=%u",
+ slba, zsa, zsa_str, all);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
+static const char *nvmet_trace_zone_mgmt_recv(struct trace_seq *p, u8 *cdw10)
+{
+ static const char * const zrasf_strs[] = {
+ [0x00] = "list all zones",
+ [0x01] = "list the zones in the ZSE: Empty state",
+ [0x02] = "list the zones in the ZSIO: Implicitly Opened state",
+ [0x03] = "list the zones in the ZSEO: Explicitly Opened state",
+ [0x04] = "list the zones in the ZSC: Closed state",
+ [0x05] = "list the zones in the ZSF: Full state",
+ [0x06] = "list the zones in the ZSRO: Read Only state",
+ [0x07] = "list the zones in the ZSO: Offline state",
+ [0x09] = "list the zones that have the zone attribute"
+ };
+ const char *ret = trace_seq_buffer_ptr(p);
+ u64 slba = get_unaligned_le64(cdw10);
+ u32 numd = get_unaligned_le32(&cdw10[8]);
+ u8 zra = cdw10[12];
+ u8 zrasf = cdw10[13];
+ const char *zrasf_str;
+ u8 pr = cdw10[14];
+
+ if (zrasf < ARRAY_SIZE(zrasf_strs) && zrasf_strs[zrasf])
+ zrasf_str = zrasf_strs[zrasf];
+ else
+ zrasf_str = "reserved";
+
+ trace_seq_printf(p, "slba=%llu, numd=%u, zra=%u, zrasf=%u:%s, pr=%u",
+ slba, numd, zra, zrasf, zrasf_str, pr);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
+
const char *nvmet_trace_parse_nvm_cmd(struct trace_seq *p,
u8 opcode, u8 *cdw10)
{
@@ -126,9 +187,14 @@ const char *nvmet_trace_parse_nvm_cmd(struct trace_seq *p,
case nvme_cmd_read:
case nvme_cmd_write:
case nvme_cmd_write_zeroes:
+ case nvme_cmd_zone_append:
return nvmet_trace_read_write(p, cdw10);
case nvme_cmd_dsm:
return nvmet_trace_dsm(p, cdw10);
+ case nvme_cmd_zone_mgmt_send:
+ return nvmet_trace_zone_mgmt_send(p, cdw10);
+ case nvme_cmd_zone_mgmt_recv:
+ return nvmet_trace_zone_mgmt_recv(p, cdw10);
default:
return nvmet_trace_common(p, cdw10);
}
@@ -176,6 +242,34 @@ static const char *nvmet_trace_fabrics_property_get(struct trace_seq *p,
return ret;
}
+static const char *nvmet_trace_fabrics_auth_send(struct trace_seq *p, u8 *spc)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 spsp0 = spc[1];
+ u8 spsp1 = spc[2];
+ u8 secp = spc[3];
+ u32 tl = get_unaligned_le32(spc + 4);
+
+ trace_seq_printf(p, "spsp0=%02x, spsp1=%02x, secp=%02x, tl=%u",
+ spsp0, spsp1, secp, tl);
+ trace_seq_putc(p, 0);
+ return ret;
+}
+
+static const char *nvmet_trace_fabrics_auth_receive(struct trace_seq *p, u8 *spc)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+ u8 spsp0 = spc[1];
+ u8 spsp1 = spc[2];
+ u8 secp = spc[3];
+ u32 al = get_unaligned_le32(spc + 4);
+
+ trace_seq_printf(p, "spsp0=%02x, spsp1=%02x, secp=%02x, al=%u",
+ spsp0, spsp1, secp, al);
+ trace_seq_putc(p, 0);
+ return ret;
+}
+
static const char *nvmet_trace_fabrics_common(struct trace_seq *p, u8 *spc)
{
const char *ret = trace_seq_buffer_ptr(p);
@@ -195,6 +289,10 @@ const char *nvmet_trace_parse_fabrics_cmd(struct trace_seq *p,
return nvmet_trace_fabrics_connect(p, spc);
case nvme_fabrics_type_property_get:
return nvmet_trace_fabrics_property_get(p, spc);
+ case nvme_fabrics_type_auth_send:
+ return nvmet_trace_fabrics_auth_send(p, spc);
+ case nvme_fabrics_type_auth_receive:
+ return nvmet_trace_fabrics_auth_receive(p, spc);
default:
return nvmet_trace_fabrics_common(p, spc);
}
diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
index 5b5c1e4817..0021d06041 100644
--- a/drivers/nvme/target/zns.c
+++ b/drivers/nvme/target/zns.c
@@ -52,14 +52,10 @@ bool nvmet_bdev_zns_enable(struct nvmet_ns *ns)
if (get_capacity(bd_disk) & (bdev_zone_sectors(ns->bdev) - 1))
return false;
/*
- * ZNS does not define a conventional zone type. If the underlying
- * device has a bitmap set indicating the existence of conventional
- * zones, reject the device. Otherwise, use report zones to detect if
- * the device has conventional zones.
+ * ZNS does not define a conventional zone type. Use report zones
+ * to detect if the device has conventional zones and reject it if
+ * it does.
*/
- if (ns->bdev->bd_disk->conv_zones_bitmap)
- return false;
-
ret = blkdev_report_zones(ns->bdev, 0, bdev_nr_zones(ns->bdev),
validate_conv_zones_cb, NULL);
if (ret < 0)
@@ -456,8 +452,7 @@ static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req)
switch (zsa_req_op(req->cmd->zms.zsa)) {
case REQ_OP_ZONE_RESET:
ret = blkdev_zone_mgmt(req->ns->bdev, REQ_OP_ZONE_RESET, 0,
- get_capacity(req->ns->bdev->bd_disk),
- GFP_KERNEL);
+ get_capacity(req->ns->bdev->bd_disk));
if (ret < 0)
return blkdev_zone_mgmt_errno_to_nvme_status(ret);
break;
@@ -508,7 +503,7 @@ static void nvmet_bdev_zmgmt_send_work(struct work_struct *w)
goto out;
}
- ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors, GFP_KERNEL);
+ ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors);
if (ret < 0)
status = blkdev_zone_mgmt_errno_to_nvme_status(ret);