diff options
Diffstat (limited to 'drivers/nvme/host/core.c')
-rw-r--r-- | drivers/nvme/host/core.c | 277 |
1 files changed, 212 insertions, 65 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 3cd921e6121e..643f457131c2 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -33,6 +33,20 @@ #define NVME_MINORS (1U << MINORBITS) +unsigned char admin_timeout = 60; +module_param(admin_timeout, byte, 0644); +MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin commands"); +EXPORT_SYMBOL_GPL(admin_timeout); + +unsigned char nvme_io_timeout = 30; +module_param_named(io_timeout, nvme_io_timeout, byte, 0644); +MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O"); +EXPORT_SYMBOL_GPL(nvme_io_timeout); + +unsigned char shutdown_timeout = 5; +module_param(shutdown_timeout, byte, 0644); +MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown"); + static int nvme_major; module_param(nvme_major, int, 0); @@ -40,7 +54,7 @@ static int nvme_char_major; module_param(nvme_char_major, int, 0); static LIST_HEAD(nvme_ctrl_list); -DEFINE_SPINLOCK(dev_list_lock); +static DEFINE_SPINLOCK(dev_list_lock); static struct class *nvme_class; @@ -55,8 +69,9 @@ static void nvme_free_ns(struct kref *kref) ns->disk->private_data = NULL; spin_unlock(&dev_list_lock); - nvme_put_ctrl(ns->ctrl); put_disk(ns->disk); + ida_simple_remove(&ns->ctrl->ns_ida, ns->instance); + nvme_put_ctrl(ns->ctrl); kfree(ns); } @@ -71,11 +86,21 @@ static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk) spin_lock(&dev_list_lock); ns = disk->private_data; - if (ns && !kref_get_unless_zero(&ns->kref)) - ns = NULL; + if (ns) { + if (!kref_get_unless_zero(&ns->kref)) + goto fail; + if (!try_module_get(ns->ctrl->ops->module)) + goto fail_put_ns; + } spin_unlock(&dev_list_lock); return ns; + +fail_put_ns: + kref_put(&ns->kref, nvme_free_ns); +fail: + spin_unlock(&dev_list_lock); + return NULL; } void nvme_requeue_req(struct request *req) @@ -88,6 +113,7 @@ void nvme_requeue_req(struct request *req) blk_mq_kick_requeue_list(req->q); spin_unlock_irqrestore(req->q->queue_lock, flags); } +EXPORT_SYMBOL_GPL(nvme_requeue_req); struct request *nvme_alloc_request(struct request_queue *q, struct nvme_command *cmd, unsigned int flags) @@ -107,17 +133,18 @@ struct request *nvme_alloc_request(struct request_queue *q, req->cmd = (unsigned char *)cmd; req->cmd_len = sizeof(struct nvme_command); - req->special = (void *)0; return req; } +EXPORT_SYMBOL_GPL(nvme_alloc_request); /* * Returns 0 on success. If the result is negative, it's a Linux error code; * if the result is positive, it's an NVM Express status code */ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, - void *buffer, unsigned bufflen, u32 *result, unsigned timeout) + struct nvme_completion *cqe, void *buffer, unsigned bufflen, + unsigned timeout) { struct request *req; int ret; @@ -127,6 +154,7 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, return PTR_ERR(req); req->timeout = timeout ? timeout : ADMIN_TIMEOUT; + req->special = cqe; if (buffer && bufflen) { ret = blk_rq_map_kern(q, req, buffer, bufflen, GFP_KERNEL); @@ -135,8 +163,6 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, } blk_execute_rq(req->q, NULL, req, 0); - if (result) - *result = (u32)(uintptr_t)req->special; ret = req->errors; out: blk_mq_free_request(req); @@ -146,8 +172,9 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, void *buffer, unsigned bufflen) { - return __nvme_submit_sync_cmd(q, cmd, buffer, bufflen, NULL, 0); + return __nvme_submit_sync_cmd(q, cmd, NULL, buffer, bufflen, 0); } +EXPORT_SYMBOL_GPL(nvme_submit_sync_cmd); int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, void __user *ubuffer, unsigned bufflen, @@ -155,6 +182,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, u32 *result, unsigned timeout) { bool write = cmd->common.opcode & 1; + struct nvme_completion cqe; struct nvme_ns *ns = q->queuedata; struct gendisk *disk = ns ? ns->disk : NULL; struct request *req; @@ -167,6 +195,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, return PTR_ERR(req); req->timeout = timeout ? timeout : ADMIN_TIMEOUT; + req->special = &cqe; if (ubuffer && bufflen) { ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, @@ -183,7 +212,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, goto out_unmap; } - if (meta_buffer) { + if (meta_buffer && meta_len) { struct bio_integrity_payload *bip; meta = kmalloc(meta_len, GFP_KERNEL); @@ -221,7 +250,7 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd, blk_execute_rq(req->q, disk, req, 0); ret = req->errors; if (result) - *result = (u32)(uintptr_t)req->special; + *result = le32_to_cpu(cqe.result); if (meta && !ret && !write) { if (copy_to_user(meta_buffer, meta, meta_len)) ret = -EFAULT; @@ -302,6 +331,8 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, dma_addr_t dma_addr, u32 *result) { struct nvme_command c; + struct nvme_completion cqe; + int ret; memset(&c, 0, sizeof(c)); c.features.opcode = nvme_admin_get_features; @@ -309,13 +340,18 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, c.features.prp1 = cpu_to_le64(dma_addr); c.features.fid = cpu_to_le32(fid); - return __nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0, result, 0); + ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0); + if (ret >= 0) + *result = le32_to_cpu(cqe.result); + return ret; } int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, dma_addr_t dma_addr, u32 *result) { struct nvme_command c; + struct nvme_completion cqe; + int ret; memset(&c, 0, sizeof(c)); c.features.opcode = nvme_admin_set_features; @@ -323,7 +359,10 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, c.features.fid = cpu_to_le32(fid); c.features.dword11 = cpu_to_le32(dword11); - return __nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0, result, 0); + ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0); + if (ret >= 0) + *result = le32_to_cpu(cqe.result); + return ret; } int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log) @@ -363,6 +402,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) *count = min(*count, nr_io_queues); return 0; } +EXPORT_SYMBOL_GPL(nvme_set_queue_count); static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) { @@ -373,6 +413,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) if (copy_from_user(&io, uio, sizeof(io))) return -EFAULT; + if (io.flags) + return -EINVAL; switch (io.opcode) { case nvme_cmd_write: @@ -424,6 +466,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return -EACCES; if (copy_from_user(&cmd, ucmd, sizeof(cmd))) return -EFAULT; + if (cmd.flags) + return -EINVAL; memset(&c, 0, sizeof(c)); c.common.opcode = cmd.opcode; @@ -499,7 +543,10 @@ static int nvme_open(struct block_device *bdev, fmode_t mode) static void nvme_release(struct gendisk *disk, fmode_t mode) { - nvme_put_ns(disk->private_data); + struct nvme_ns *ns = disk->private_data; + + module_put(ns->ctrl->ops->module); + nvme_put_ns(ns); } static int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo) @@ -540,8 +587,14 @@ static void nvme_init_integrity(struct nvme_ns *ns) static void nvme_config_discard(struct nvme_ns *ns) { + struct nvme_ctrl *ctrl = ns->ctrl; u32 logical_block_size = queue_logical_block_size(ns->queue); - ns->queue->limits.discard_zeroes_data = 0; + + if (ctrl->quirks & NVME_QUIRK_DISCARD_ZEROES) + ns->queue->limits.discard_zeroes_data = 1; + else + ns->queue->limits.discard_zeroes_data = 0; + ns->queue->limits.discard_alignment = logical_block_size; ns->queue->limits.discard_granularity = logical_block_size; blk_queue_max_discard_sectors(ns->queue, 0xffffffff); @@ -556,9 +609,13 @@ static int nvme_revalidate_disk(struct gendisk *disk) u16 old_ms; unsigned short bs; + if (test_bit(NVME_NS_DEAD, &ns->flags)) { + set_capacity(disk, 0); + return -ENODEV; + } if (nvme_identify_ns(ns->ctrl, ns->ns_id, &id)) { - dev_warn(ns->ctrl->dev, "%s: Identify failure nvme%dn%d\n", - __func__, ns->ctrl->instance, ns->ns_id); + dev_warn(disk_to_dev(ns->disk), "%s: Identify failure\n", + __func__); return -ENODEV; } if (id->ncap == 0) { @@ -568,7 +625,7 @@ static int nvme_revalidate_disk(struct gendisk *disk) if (nvme_nvm_ns_supported(ns, id) && ns->type != NVME_NS_LIGHTNVM) { if (nvme_nvm_register(ns->queue, disk->disk_name)) { - dev_warn(ns->ctrl->dev, + dev_warn(disk_to_dev(ns->disk), "%s: LightNVM init failure\n", __func__); kfree(id); return -ENODEV; @@ -741,7 +798,7 @@ static int nvme_wait_ready(struct nvme_ctrl *ctrl, u64 cap, bool enabled) if (fatal_signal_pending(current)) return -EINTR; if (time_after(jiffies, timeout)) { - dev_err(ctrl->dev, + dev_err(ctrl->device, "Device not ready; aborting %s\n", enabled ? "initialisation" : "reset"); return -ENODEV; @@ -769,6 +826,7 @@ int nvme_disable_ctrl(struct nvme_ctrl *ctrl, u64 cap) return ret; return nvme_wait_ready(ctrl, cap, false); } +EXPORT_SYMBOL_GPL(nvme_disable_ctrl); int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap) { @@ -781,7 +839,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap) int ret; if (page_shift < dev_page_min) { - dev_err(ctrl->dev, + dev_err(ctrl->device, "Minimum device page size %u too large for host (%u)\n", 1 << dev_page_min, 1 << page_shift); return -ENODEV; @@ -800,6 +858,7 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl, u64 cap) return ret; return nvme_wait_ready(ctrl, cap, true); } +EXPORT_SYMBOL_GPL(nvme_enable_ctrl); int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl) { @@ -822,7 +881,7 @@ int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl) if (fatal_signal_pending(current)) return -EINTR; if (time_after(jiffies, timeout)) { - dev_err(ctrl->dev, + dev_err(ctrl->device, "Device shutdown incomplete; abort shutdown\n"); return -ENODEV; } @@ -830,6 +889,24 @@ int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl) return ret; } +EXPORT_SYMBOL_GPL(nvme_shutdown_ctrl); + +static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, + struct request_queue *q) +{ + if (ctrl->max_hw_sectors) { + u32 max_segments = + (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1; + + blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors); + blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX)); + } + if (ctrl->stripe_size) + blk_queue_chunk_sectors(q, ctrl->stripe_size >> 9); + if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) + blk_queue_flush(q, REQ_FLUSH | REQ_FUA); + blk_queue_virt_boundary(q, ctrl->page_size - 1); +} /* * Initialize the cached copies of the Identify data and various controller @@ -844,13 +921,13 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ret = ctrl->ops->reg_read32(ctrl, NVME_REG_VS, &ctrl->vs); if (ret) { - dev_err(ctrl->dev, "Reading VS failed (%d)\n", ret); + dev_err(ctrl->device, "Reading VS failed (%d)\n", ret); return ret; } ret = ctrl->ops->reg_read64(ctrl, NVME_REG_CAP, &cap); if (ret) { - dev_err(ctrl->dev, "Reading CAP failed (%d)\n", ret); + dev_err(ctrl->device, "Reading CAP failed (%d)\n", ret); return ret; } page_shift = NVME_CAP_MPSMIN(cap) + 12; @@ -860,13 +937,15 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ret = nvme_identify_ctrl(ctrl, &id); if (ret) { - dev_err(ctrl->dev, "Identify Controller failed (%d)\n", ret); + dev_err(ctrl->device, "Identify Controller failed (%d)\n", ret); return -EIO; } + ctrl->vid = le16_to_cpu(id->vid); ctrl->oncs = le16_to_cpup(&id->oncs); atomic_set(&ctrl->abort_limit, id->acl + 1); ctrl->vwc = id->vwc; + ctrl->cntlid = le16_to_cpup(&id->cntlid); memcpy(ctrl->serial, id->sn, sizeof(id->sn)); memcpy(ctrl->model, id->mn, sizeof(id->mn)); memcpy(ctrl->firmware_rev, id->fr, sizeof(id->fr)); @@ -888,9 +967,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) } } + nvme_set_queue_limits(ctrl, ctrl->admin_q); + kfree(id); return 0; } +EXPORT_SYMBOL_GPL(nvme_init_identify); static int nvme_dev_open(struct inode *inode, struct file *file) { @@ -937,13 +1019,13 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp) ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list); if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) { - dev_warn(ctrl->dev, + dev_warn(ctrl->device, "NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n"); ret = -EINVAL; goto out_unlock; } - dev_warn(ctrl->dev, + dev_warn(ctrl->device, "using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n"); kref_get(&ns->kref); mutex_unlock(&ctrl->namespaces_mutex); @@ -969,7 +1051,7 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd, case NVME_IOCTL_IO_CMD: return nvme_dev_user_cmd(ctrl, argp); case NVME_IOCTL_RESET: - dev_warn(ctrl->dev, "resetting controller\n"); + dev_warn(ctrl->device, "resetting controller\n"); return ctrl->ops->reset_ctrl(ctrl); case NVME_IOCTL_SUBSYS_RESET: return nvme_reset_subsystem(ctrl); @@ -1000,6 +1082,30 @@ static ssize_t nvme_sysfs_reset(struct device *dev, } static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset); +static ssize_t wwid_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct nvme_ns *ns = dev_to_disk(dev)->private_data; + struct nvme_ctrl *ctrl = ns->ctrl; + int serial_len = sizeof(ctrl->serial); + int model_len = sizeof(ctrl->model); + + if (memchr_inv(ns->uuid, 0, sizeof(ns->uuid))) + return sprintf(buf, "eui.%16phN\n", ns->uuid); + + if (memchr_inv(ns->eui, 0, sizeof(ns->eui))) + return sprintf(buf, "eui.%8phN\n", ns->eui); + + while (ctrl->serial[serial_len - 1] == ' ') + serial_len--; + while (ctrl->model[model_len - 1] == ' ') + model_len--; + + return sprintf(buf, "nvme.%04x-%*phN-%*phN-%08x\n", ctrl->vid, + serial_len, ctrl->serial, model_len, ctrl->model, ns->ns_id); +} +static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL); + static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -1025,6 +1131,7 @@ static ssize_t nsid_show(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR(nsid, S_IRUGO, nsid_show, NULL); static struct attribute *nvme_ns_attrs[] = { + &dev_attr_wwid.attr, &dev_attr_uuid.attr, &dev_attr_eui.attr, &dev_attr_nsid.attr, @@ -1053,7 +1160,7 @@ static const struct attribute_group nvme_ns_attr_group = { .is_visible = nvme_attrs_are_visible, }; -#define nvme_show_function(field) \ +#define nvme_show_str_function(field) \ static ssize_t field##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ @@ -1062,15 +1169,26 @@ static ssize_t field##_show(struct device *dev, \ } \ static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); -nvme_show_function(model); -nvme_show_function(serial); -nvme_show_function(firmware_rev); +#define nvme_show_int_function(field) \ +static ssize_t field##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ +{ \ + struct nvme_ctrl *ctrl = dev_get_drvdata(dev); \ + return sprintf(buf, "%d\n", ctrl->field); \ +} \ +static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL); + +nvme_show_str_function(model); +nvme_show_str_function(serial); +nvme_show_str_function(firmware_rev); +nvme_show_int_function(cntlid); static struct attribute *nvme_dev_attrs[] = { &dev_attr_reset_controller.attr, &dev_attr_model.attr, &dev_attr_serial.attr, &dev_attr_firmware_rev.attr, + &dev_attr_cntlid.attr, NULL }; @@ -1118,9 +1236,13 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (!ns) return; + ns->instance = ida_simple_get(&ctrl->ns_ida, 1, 0, GFP_KERNEL); + if (ns->instance < 0) + goto out_free_ns; + ns->queue = blk_mq_init_queue(ctrl->tagset); if (IS_ERR(ns->queue)) - goto out_free_ns; + goto out_release_instance; queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue); ns->queue->queuedata = ns; ns->ctrl = ctrl; @@ -1134,17 +1256,9 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) ns->disk = disk; ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */ + blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift); - if (ctrl->max_hw_sectors) { - blk_queue_max_hw_sectors(ns->queue, ctrl->max_hw_sectors); - blk_queue_max_segments(ns->queue, - (ctrl->max_hw_sectors / (ctrl->page_size >> 9)) + 1); - } - if (ctrl->stripe_size) - blk_queue_chunk_sectors(ns->queue, ctrl->stripe_size >> 9); - if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) - blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA); - blk_queue_virt_boundary(ns->queue, ctrl->page_size - 1); + nvme_set_queue_limits(ctrl, ns->queue); disk->major = nvme_major; disk->first_minor = 0; @@ -1153,7 +1267,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) disk->queue = ns->queue; disk->driverfs_dev = ctrl->device; disk->flags = GENHD_FL_EXT_DEVT; - sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, nsid); + sprintf(disk->disk_name, "nvme%dn%d", ctrl->instance, ns->instance); if (nvme_revalidate_disk(ns->disk)) goto out_free_disk; @@ -1173,40 +1287,29 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) kfree(disk); out_free_queue: blk_cleanup_queue(ns->queue); + out_release_instance: + ida_simple_remove(&ctrl->ns_ida, ns->instance); out_free_ns: kfree(ns); } static void nvme_ns_remove(struct nvme_ns *ns) { - bool kill = nvme_io_incapable(ns->ctrl) && - !blk_queue_dying(ns->queue); - - lockdep_assert_held(&ns->ctrl->namespaces_mutex); - - if (kill) { - blk_set_queue_dying(ns->queue); + if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags)) + return; - /* - * The controller was shutdown first if we got here through - * device removal. The shutdown may requeue outstanding - * requests. These need to be aborted immediately so - * del_gendisk doesn't block indefinitely for their completion. - */ - blk_mq_abort_requeue_list(ns->queue); - } if (ns->disk->flags & GENHD_FL_UP) { if (blk_get_integrity(ns->disk)) blk_integrity_unregister(ns->disk); sysfs_remove_group(&disk_to_dev(ns->disk)->kobj, &nvme_ns_attr_group); del_gendisk(ns->disk); - } - if (kill || !blk_queue_dying(ns->queue)) { blk_mq_abort_requeue_list(ns->queue); blk_cleanup_queue(ns->queue); } + mutex_lock(&ns->ctrl->namespaces_mutex); list_del_init(&ns->list); + mutex_unlock(&ns->ctrl->namespaces_mutex); nvme_put_ns(ns); } @@ -1295,16 +1398,16 @@ void nvme_scan_namespaces(struct nvme_ctrl *ctrl) mutex_unlock(&ctrl->namespaces_mutex); kfree(id); } +EXPORT_SYMBOL_GPL(nvme_scan_namespaces); void nvme_remove_namespaces(struct nvme_ctrl *ctrl) { struct nvme_ns *ns, *next; - mutex_lock(&ctrl->namespaces_mutex); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) nvme_ns_remove(ns); - mutex_unlock(&ctrl->namespaces_mutex); } +EXPORT_SYMBOL_GPL(nvme_remove_namespaces); static DEFINE_IDA(nvme_instance_ida); @@ -1336,13 +1439,14 @@ static void nvme_release_instance(struct nvme_ctrl *ctrl) } void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) - { +{ device_destroy(nvme_class, MKDEV(nvme_char_major, ctrl->instance)); spin_lock(&dev_list_lock); list_del(&ctrl->node); spin_unlock(&dev_list_lock); } +EXPORT_SYMBOL_GPL(nvme_uninit_ctrl); static void nvme_free_ctrl(struct kref *kref) { @@ -1350,6 +1454,7 @@ static void nvme_free_ctrl(struct kref *kref) put_device(ctrl->device); nvme_release_instance(ctrl); + ida_destroy(&ctrl->ns_ida); ctrl->ops->free_ctrl(ctrl); } @@ -1358,6 +1463,7 @@ void nvme_put_ctrl(struct nvme_ctrl *ctrl) { kref_put(&ctrl->kref, nvme_free_ctrl); } +EXPORT_SYMBOL_GPL(nvme_put_ctrl); /* * Initialize a NVMe controller structures. This needs to be called during @@ -1382,14 +1488,14 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->device = device_create_with_groups(nvme_class, ctrl->dev, MKDEV(nvme_char_major, ctrl->instance), - dev, nvme_dev_attr_groups, + ctrl, nvme_dev_attr_groups, "nvme%d", ctrl->instance); if (IS_ERR(ctrl->device)) { ret = PTR_ERR(ctrl->device); goto out_release_instance; } get_device(ctrl->device); - dev_set_drvdata(ctrl->device, ctrl); + ida_init(&ctrl->ns_ida); spin_lock(&dev_list_lock); list_add_tail(&ctrl->node, &nvme_ctrl_list); @@ -1401,6 +1507,40 @@ out_release_instance: out: return ret; } +EXPORT_SYMBOL_GPL(nvme_init_ctrl); + +/** + * nvme_kill_queues(): Ends all namespace queues + * @ctrl: the dead controller that needs to end + * + * Call this function when the driver determines it is unable to get the + * controller in a state capable of servicing IO. + */ +void nvme_kill_queues(struct nvme_ctrl *ctrl) +{ + struct nvme_ns *ns; + + mutex_lock(&ctrl->namespaces_mutex); + list_for_each_entry(ns, &ctrl->namespaces, list) { + if (!kref_get_unless_zero(&ns->kref)) + continue; + + /* + * Revalidating a dead namespace sets capacity to 0. This will + * end buffered writers dirtying pages that can't be synced. + */ + if (!test_and_set_bit(NVME_NS_DEAD, &ns->flags)) + revalidate_disk(ns->disk); + + blk_set_queue_dying(ns->queue); + blk_mq_abort_requeue_list(ns->queue); + blk_mq_start_stopped_hw_queues(ns->queue, true); + + nvme_put_ns(ns); + } + mutex_unlock(&ctrl->namespaces_mutex); +} +EXPORT_SYMBOL_GPL(nvme_kill_queues); void nvme_stop_queues(struct nvme_ctrl *ctrl) { @@ -1417,6 +1557,7 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl) } mutex_unlock(&ctrl->namespaces_mutex); } +EXPORT_SYMBOL_GPL(nvme_stop_queues); void nvme_start_queues(struct nvme_ctrl *ctrl) { @@ -1430,6 +1571,7 @@ void nvme_start_queues(struct nvme_ctrl *ctrl) } mutex_unlock(&ctrl->namespaces_mutex); } +EXPORT_SYMBOL_GPL(nvme_start_queues); int __init nvme_core_init(void) { @@ -1469,3 +1611,8 @@ void nvme_core_exit(void) class_destroy(nvme_class); __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme"); } + +MODULE_LICENSE("GPL"); +MODULE_VERSION("1.0"); +module_init(nvme_core_init); +module_exit(nvme_core_exit); |