diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-02-21 11:06:54 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-02-21 11:06:54 -0800 |
commit | 9820b4dca0f9c6b7ab8b4307286cdace171b724d (patch) | |
tree | 9feef543deb60557f301ceeed8f7c56ed3efedad /drivers/nvme | |
parent | 582cd91f69de8e44857cb610ebca661dac8656b7 (diff) | |
parent | f4b64ae6745177642cd9610cfd7df0041e7fca58 (diff) |
Merge tag 'for-5.12/drivers-2021-02-17' of git://git.kernel.dk/linux-block
Pull block driver updates from Jens Axboe:
- Remove the skd driver. It's been EOL for a long time (Damien)
- NVMe pull requests
- fix multipath handling of ->queue_rq errors (Chao Leng)
- nvmet cleanups (Chaitanya Kulkarni)
- add a quirk for buggy Amazon controller (Filippo Sironi)
- avoid devm allocations in nvme-hwmon that don't interact well
with fabrics (Hannes Reinecke)
- sysfs cleanups (Jiapeng Chong)
- fix nr_zones for multipath (Keith Busch)
- nvme-tcp crash fix for no-data commands (Sagi Grimberg)
- nvmet-tcp fixes (Sagi Grimberg)
- add a missing __rcu annotation (Christoph)
- failed reconnect fixes (Chao Leng)
- various tracing improvements (Michal Krakowiak, Johannes
Thumshirn)
- switch the nvmet-fc assoc_list to use RCU protection (Leonid
Ravich)
- resync the status codes with the latest spec (Max Gurtovoy)
- minor nvme-tcp improvements (Sagi Grimberg)
- various cleanups (Rikard Falkeborn, Minwoo Im, Chaitanya
Kulkarni, Israel Rukshin)
- Floppy O_NDELAY fix (Denis)
- MD pull request
- raid5 chunk_sectors fix (Guoqing)
- Use lore links (Kees)
- Use DEFINE_SHOW_ATTRIBUTE for nbd (Liao)
- loop lock scaling (Pavel)
- mtip32xx PCI fixes (Bjorn)
- bcache fixes (Kai, Dongdong)
- Misc fixes (Tian, Yang, Guoqing, Joe, Andy)
* tag 'for-5.12/drivers-2021-02-17' of git://git.kernel.dk/linux-block: (64 commits)
lightnvm: pblk: Replace guid_copy() with export_guid()/import_guid()
lightnvm: fix unnecessary NULL check warnings
nvme-tcp: fix crash triggered with a dataless request submission
block: Replace lkml.org links with lore
nbd: Convert to DEFINE_SHOW_ATTRIBUTE
nvme: add 48-bit DMA address quirk for Amazon NVMe controllers
nvme-hwmon: rework to avoid devm allocation
nvmet: remove else at the end of the function
nvmet: add nvmet_req_subsys() helper
nvmet: use min of device_path and disk len
nvmet: use invalid cmd opcode helper
nvmet: use invalid cmd opcode helper
nvmet: add helper to report invalid opcode
nvmet: remove extra variable in id-ns handler
nvmet: make nvmet_find_namespace() req based
nvmet: return uniform error for invalid ns
nvmet: set status to 0 in case for invalid nsid
nvmet-fc: add a missing __rcu annotation to nvmet_fc_tgt_assoc.queues
nvme-multipath: set nr_zones for zoned namespaces
nvmet-tcp: fix potential race of tcp socket closing accept_work
...
Diffstat (limited to 'drivers/nvme')
-rw-r--r-- | drivers/nvme/host/core.c | 63 | ||||
-rw-r--r-- | drivers/nvme/host/fabrics.c | 6 | ||||
-rw-r--r-- | drivers/nvme/host/fc.c | 2 | ||||
-rw-r--r-- | drivers/nvme/host/hwmon.c | 31 | ||||
-rw-r--r-- | drivers/nvme/host/multipath.c | 4 | ||||
-rw-r--r-- | drivers/nvme/host/nvme.h | 17 | ||||
-rw-r--r-- | drivers/nvme/host/pci.c | 17 | ||||
-rw-r--r-- | drivers/nvme/host/rdma.c | 34 | ||||
-rw-r--r-- | drivers/nvme/host/tcp.c | 55 | ||||
-rw-r--r-- | drivers/nvme/host/trace.c | 53 | ||||
-rw-r--r-- | drivers/nvme/target/admin-cmd.c | 114 | ||||
-rw-r--r-- | drivers/nvme/target/configfs.c | 6 | ||||
-rw-r--r-- | drivers/nvme/target/core.c | 37 | ||||
-rw-r--r-- | drivers/nvme/target/fc.c | 83 | ||||
-rw-r--r-- | drivers/nvme/target/fcloop.c | 2 | ||||
-rw-r--r-- | drivers/nvme/target/io-cmd-bdev.c | 13 | ||||
-rw-r--r-- | drivers/nvme/target/io-cmd-file.c | 5 | ||||
-rw-r--r-- | drivers/nvme/target/nvmet.h | 20 | ||||
-rw-r--r-- | drivers/nvme/target/passthru.c | 6 | ||||
-rw-r--r-- | drivers/nvme/target/tcp.c | 59 | ||||
-rw-r--r-- | drivers/nvme/target/trace.h | 9 |
21 files changed, 401 insertions, 235 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 89cacff897a8..e68a8c4ac5a6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -279,14 +279,13 @@ static blk_status_t nvme_error_status(u16 status) static void nvme_retry_req(struct request *req) { - struct nvme_ns *ns = req->q->queuedata; unsigned long delay = 0; u16 crd; /* The mask and shift result must be <= 3 */ crd = (nvme_req(req)->status & NVME_SC_CRD) >> 11; - if (ns && crd) - delay = ns->ctrl->crdt[crd - 1] * 100; + if (crd) + delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100; nvme_req(req)->retries++; blk_mq_requeue_request(req, false); @@ -356,6 +355,21 @@ void nvme_complete_rq(struct request *req) } EXPORT_SYMBOL_GPL(nvme_complete_rq); +/* + * Called to unwind from ->queue_rq on a failed command submission so that the + * multipathing code gets called to potentially failover to another path. + * The caller needs to unwind all transport specific resource allocations and + * must return propagate the return value. + */ +blk_status_t nvme_host_path_error(struct request *req) +{ + nvme_req(req)->status = NVME_SC_HOST_PATH_ERROR; + blk_mq_set_request_complete(req); + nvme_complete_rq(req); + return BLK_STS_OK; +} +EXPORT_SYMBOL_GPL(nvme_host_path_error); + bool nvme_cancel_request(struct request *req, void *data, bool reserved) { dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device, @@ -371,6 +385,26 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved) } EXPORT_SYMBOL_GPL(nvme_cancel_request); +void nvme_cancel_tagset(struct nvme_ctrl *ctrl) +{ + if (ctrl->tagset) { + blk_mq_tagset_busy_iter(ctrl->tagset, + nvme_cancel_request, ctrl); + blk_mq_tagset_wait_completed_request(ctrl->tagset); + } +} +EXPORT_SYMBOL_GPL(nvme_cancel_tagset); + +void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl) +{ + if (ctrl->admin_tagset) { + blk_mq_tagset_busy_iter(ctrl->admin_tagset, + nvme_cancel_request, ctrl); + blk_mq_tagset_wait_completed_request(ctrl->admin_tagset); + } +} +EXPORT_SYMBOL_GPL(nvme_cancel_admin_tagset); + bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state) { @@ -842,11 +876,11 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, void nvme_cleanup_cmd(struct request *req) { if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { - struct nvme_ns *ns = req->rq_disk->private_data; + struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; struct page *page = req->special_vec.bv_page; - if (page == ns->ctrl->discard_page) - clear_bit_unlock(0, &ns->ctrl->discard_page_busy); + if (page == ctrl->discard_page) + clear_bit_unlock(0, &ctrl->discard_page_busy); else kfree(page_address(page) + req->special_vec.bv_offset); } @@ -2831,7 +2865,7 @@ static ssize_t nvme_subsys_show_nqn(struct device *dev, struct nvme_subsystem *subsys = container_of(dev, struct nvme_subsystem, dev); - return snprintf(buf, PAGE_SIZE, "%s\n", subsys->subnqn); + return sysfs_emit(buf, "%s\n", subsys->subnqn); } static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn); @@ -2861,7 +2895,7 @@ static struct attribute *nvme_subsys_attrs[] = { NULL, }; -static struct attribute_group nvme_subsys_attrs_group = { +static const struct attribute_group nvme_subsys_attrs_group = { .attrs = nvme_subsys_attrs, }; @@ -3524,7 +3558,7 @@ static ssize_t nvme_sysfs_show_transport(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->ops->name); + return sysfs_emit(buf, "%s\n", ctrl->ops->name); } static DEVICE_ATTR(transport, S_IRUGO, nvme_sysfs_show_transport, NULL); @@ -3558,7 +3592,7 @@ static ssize_t nvme_sysfs_show_subsysnqn(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->subsys->subnqn); + return sysfs_emit(buf, "%s\n", ctrl->subsys->subnqn); } static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL); @@ -3568,7 +3602,7 @@ static ssize_t nvme_sysfs_show_hostnqn(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->opts->host->nqn); + return sysfs_emit(buf, "%s\n", ctrl->opts->host->nqn); } static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL); @@ -3578,7 +3612,7 @@ static ssize_t nvme_sysfs_show_hostid(struct device *dev, { struct nvme_ctrl *ctrl = dev_get_drvdata(dev); - return snprintf(buf, PAGE_SIZE, "%pU\n", &ctrl->opts->host->id); + return sysfs_emit(buf, "%pU\n", &ctrl->opts->host->id); } static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL); @@ -3696,7 +3730,7 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj, return a->mode; } -static struct attribute_group nvme_dev_attrs_group = { +static const struct attribute_group nvme_dev_attrs_group = { .attrs = nvme_dev_attrs, .is_visible = nvme_dev_attrs_are_visible, }; @@ -4439,6 +4473,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl); void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) { + nvme_hwmon_exit(ctrl); nvme_fault_inject_fini(&ctrl->fault_inject); dev_pm_qos_hide_latency_tolerance(ctrl->device); cdev_device_del(&ctrl->cdev, ctrl->device); @@ -4451,7 +4486,7 @@ static void nvme_free_cels(struct nvme_ctrl *ctrl) struct nvme_effects_log *cel; unsigned long i; - xa_for_each (&ctrl->cels, i, cel) { + xa_for_each(&ctrl->cels, i, cel) { xa_erase(&ctrl->cels, i); kfree(cel); } diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 72ac00173500..5dfd806fc2d2 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -552,11 +552,7 @@ blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) && !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) return BLK_STS_RESOURCE; - - nvme_req(rq)->status = NVME_SC_HOST_PATH_ERROR; - blk_mq_start_request(rq); - nvme_complete_rq(rq); - return BLK_STS_OK; + return nvme_host_path_error(rq); } EXPORT_SYMBOL_GPL(nvmf_fail_nonready_command); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 5f36cfa8136c..20dadd86e981 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3789,7 +3789,7 @@ static struct attribute *nvme_fc_attrs[] = { NULL }; -static struct attribute_group nvme_fc_attr_group = { +static const struct attribute_group nvme_fc_attr_group = { .attrs = nvme_fc_attrs, }; diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 552dbc04567b..8f9e96986780 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -223,12 +223,12 @@ static const struct hwmon_chip_info nvme_hwmon_chip_info = { int nvme_hwmon_init(struct nvme_ctrl *ctrl) { - struct device *dev = ctrl->dev; + struct device *dev = ctrl->device; struct nvme_hwmon_data *data; struct device *hwmon; int err; - data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return 0; @@ -237,19 +237,30 @@ int nvme_hwmon_init(struct nvme_ctrl *ctrl) err = nvme_hwmon_get_smart_log(data); if (err) { - dev_warn(ctrl->device, - "Failed to read smart log (error %d)\n", err); - devm_kfree(dev, data); + dev_warn(dev, "Failed to read smart log (error %d)\n", err); + kfree(data); return err; } - hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data, - &nvme_hwmon_chip_info, - NULL); + hwmon = hwmon_device_register_with_info(dev, "nvme", + data, &nvme_hwmon_chip_info, + NULL); if (IS_ERR(hwmon)) { dev_warn(dev, "Failed to instantiate hwmon device\n"); - devm_kfree(dev, data); + kfree(data); } - + ctrl->hwmon_device = hwmon; return 0; } + +void nvme_hwmon_exit(struct nvme_ctrl *ctrl) +{ + if (ctrl->hwmon_device) { + struct nvme_hwmon_data *data = + dev_get_drvdata(ctrl->hwmon_device); + + hwmon_device_unregister(ctrl->hwmon_device); + ctrl->hwmon_device = NULL; + kfree(data); + } +} diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 1427c9555cef..a1d476e1ac02 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -677,6 +677,10 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id) if (blk_queue_stable_writes(ns->queue) && ns->head->disk) blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, ns->head->disk->queue); +#ifdef CONFIG_BLK_DEV_ZONED + if (blk_queue_is_zoned(ns->queue) && ns->head->disk) + ns->head->disk->queue->nr_zones = ns->queue->nr_zones; +#endif } void nvme_mpath_remove_disk(struct nvme_ns_head *head) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 88a6b97247f5..07b34175c6ce 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -144,6 +144,12 @@ enum nvme_quirks { * NVMe 1.3 compliance. */ NVME_QUIRK_NO_NS_DESC_LIST = (1 << 15), + + /* + * The controller does not properly handle DMA addresses over + * 48 bits. + */ + NVME_QUIRK_DMA_ADDRESS_BITS_48 = (1 << 16), }; /* @@ -246,6 +252,9 @@ struct nvme_ctrl { struct rw_semaphore namespaces_rwsem; struct device ctrl_device; struct device *device; /* char device */ +#ifdef CONFIG_NVME_HWMON + struct device *hwmon_device; +#endif struct cdev cdev; struct work_struct reset_work; struct work_struct delete_work; @@ -575,7 +584,10 @@ static inline bool nvme_is_aen_req(u16 qid, __u16 command_id) } void nvme_complete_rq(struct request *req); +blk_status_t nvme_host_path_error(struct request *req); bool nvme_cancel_request(struct request *req, void *data, bool reserved); +void nvme_cancel_tagset(struct nvme_ctrl *ctrl); +void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state); bool nvme_wait_reset(struct nvme_ctrl *ctrl); @@ -809,11 +821,16 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) #ifdef CONFIG_NVME_HWMON int nvme_hwmon_init(struct nvme_ctrl *ctrl); +void nvme_hwmon_exit(struct nvme_ctrl *ctrl); #else static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl) { return 0; } + +static inline void nvme_hwmon_exit(struct nvme_ctrl *ctrl) +{ +} #endif u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 808ab5186928..7b6632c00ffd 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2362,13 +2362,16 @@ static int nvme_pci_enable(struct nvme_dev *dev) { int result = -ENOMEM; struct pci_dev *pdev = to_pci_dev(dev->dev); + int dma_address_bits = 64; if (pci_enable_device_mem(pdev)) return result; pci_set_master(pdev); - if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64))) + if (dev->ctrl.quirks & NVME_QUIRK_DMA_ADDRESS_BITS_48) + dma_address_bits = 48; + if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(dma_address_bits))) goto disable; if (readl(dev->bar + NVME_REG_CSTS) == -1) { @@ -3263,6 +3266,18 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x2646, 0x2263), /* KINGSTON A2000 NVMe SSD */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS, }, + { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061), + .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, + { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065), + .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, + { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x8061), + .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, + { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd00), + .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, + { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd01), + .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, + { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd02), + .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001), .driver_data = NVME_QUIRK_SINGLE_VECTOR }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) }, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index f5ef3edeb2fd..53ac4d7442ba 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -919,12 +919,16 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, error = nvme_init_identify(&ctrl->ctrl); if (error) - goto out_stop_queue; + goto out_quiesce_queue; return 0; +out_quiesce_queue: + blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + blk_sync_queue(ctrl->ctrl.admin_q); out_stop_queue: nvme_rdma_stop_queue(&ctrl->queues[0]); + nvme_cancel_admin_tagset(&ctrl->ctrl); out_cleanup_queue: if (new) blk_cleanup_queue(ctrl->ctrl.admin_q); @@ -1001,8 +1005,10 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) out_wait_freeze_timed_out: nvme_stop_queues(&ctrl->ctrl); + nvme_sync_io_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); out_cleanup_connect_q: + nvme_cancel_tagset(&ctrl->ctrl); if (new) blk_cleanup_queue(ctrl->ctrl.connect_q); out_free_tag_set: @@ -1019,11 +1025,7 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl, blk_mq_quiesce_queue(ctrl->ctrl.admin_q); blk_sync_queue(ctrl->ctrl.admin_q); nvme_rdma_stop_queue(&ctrl->queues[0]); - if (ctrl->ctrl.admin_tagset) { - blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset, - nvme_cancel_request, &ctrl->ctrl); - blk_mq_tagset_wait_completed_request(ctrl->ctrl.admin_tagset); - } + nvme_cancel_admin_tagset(&ctrl->ctrl); if (remove) blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); nvme_rdma_destroy_admin_queue(ctrl, remove); @@ -1037,11 +1039,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, nvme_stop_queues(&ctrl->ctrl); nvme_sync_io_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); - if (ctrl->ctrl.tagset) { - blk_mq_tagset_busy_iter(ctrl->ctrl.tagset, - nvme_cancel_request, &ctrl->ctrl); - blk_mq_tagset_wait_completed_request(ctrl->ctrl.tagset); - } + nvme_cancel_tagset(&ctrl->ctrl); if (remove) nvme_start_queues(&ctrl->ctrl); nvme_rdma_destroy_io_queues(ctrl, remove); @@ -1144,10 +1142,18 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) return 0; destroy_io: - if (ctrl->ctrl.queue_count > 1) + if (ctrl->ctrl.queue_count > 1) { + nvme_stop_queues(&ctrl->ctrl); + nvme_sync_io_queues(&ctrl->ctrl); + nvme_rdma_stop_io_queues(ctrl); + nvme_cancel_tagset(&ctrl->ctrl); nvme_rdma_destroy_io_queues(ctrl, new); + } destroy_admin: + blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + blk_sync_queue(ctrl->ctrl.admin_q); nvme_rdma_stop_queue(&ctrl->queues[0]); + nvme_cancel_admin_tagset(&ctrl->ctrl); nvme_rdma_destroy_admin_queue(ctrl, new); return ret; } @@ -2092,7 +2098,9 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, err_unmap: nvme_rdma_unmap_data(queue, rq); err: - if (err == -ENOMEM || err == -EAGAIN) + if (err == -EIO) + ret = nvme_host_path_error(rq); + else if (err == -ENOMEM || err == -EAGAIN) ret = BLK_STS_RESOURCE; else ret = BLK_STS_IOERR; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 881d28eb15e9..69f59d2c5799 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -206,11 +206,6 @@ static inline size_t nvme_tcp_req_cur_length(struct nvme_tcp_request *req) req->pdu_len - req->pdu_sent); } -static inline size_t nvme_tcp_req_offset(struct nvme_tcp_request *req) -{ - return req->iter.iov_offset; -} - static inline size_t nvme_tcp_pdu_data_left(struct nvme_tcp_request *req) { return rq_data_dir(blk_mq_rq_from_pdu(req)) == WRITE ? @@ -229,24 +224,29 @@ static void nvme_tcp_init_iter(struct nvme_tcp_request *req, struct request *rq = blk_mq_rq_from_pdu(req); struct bio_vec *vec; unsigned int size; - int nsegs; + int nr_bvec; size_t offset; if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) { vec = &rq->special_vec; - nsegs = 1; + nr_bvec = 1; size = blk_rq_payload_bytes(rq); offset = 0; } else { struct bio *bio = req->curr_bio; + struct bvec_iter bi; + struct bio_vec bv; vec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); - nsegs = bio_segments(bio); + nr_bvec = 0; + bio_for_each_bvec(bv, bio, bi) { + nr_bvec++; + } size = bio->bi_iter.bi_size; offset = bio->bi_iter.bi_bvec_done; } - iov_iter_bvec(&req->iter, dir, vec, nsegs, size); + iov_iter_bvec(&req->iter, dir, vec, nr_bvec, size); req->iter.iov_offset = offset; } @@ -983,7 +983,6 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req) req->state = NVME_TCP_SEND_DATA; if (queue->data_digest) crypto_ahash_init(queue->snd_hash); - nvme_tcp_init_iter(req, WRITE); } else { nvme_tcp_done_send_req(queue); } @@ -1016,8 +1015,6 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req) req->state = NVME_TCP_SEND_DATA; if (queue->data_digest) crypto_ahash_init(queue->snd_hash); - if (!req->data_sent) - nvme_tcp_init_iter(req, WRITE); return 1; } req->offset += ret; @@ -1815,8 +1812,10 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) out_wait_freeze_timed_out: nvme_stop_queues(ctrl); + nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); out_cleanup_connect_q: + nvme_cancel_tagset(ctrl); if (new) blk_cleanup_queue(ctrl->connect_q); out_free_tag_set: @@ -1878,12 +1877,16 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new) error = nvme_init_identify(ctrl); if (error) - goto out_stop_queue; + goto out_quiesce_queue; return 0; +out_quiesce_queue: + blk_mq_quiesce_queue(ctrl->admin_q); + blk_sync_queue(ctrl->admin_q); out_stop_queue: nvme_tcp_stop_queue(ctrl, 0); + nvme_cancel_admin_tagset(ctrl); out_cleanup_queue: if (new) blk_cleanup_queue(ctrl->admin_q); @@ -1904,11 +1907,7 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl, blk_mq_quiesce_queue(ctrl->admin_q); blk_sync_queue(ctrl->admin_q); nvme_tcp_stop_queue(ctrl, 0); - if (ctrl->admin_tagset) { - blk_mq_tagset_busy_iter(ctrl->admin_tagset, - nvme_cancel_request, ctrl); - blk_mq_tagset_wait_completed_request(ctrl->admin_tagset); - } + nvme_cancel_admin_tagset(ctrl); if (remove) blk_mq_unquiesce_queue(ctrl->admin_q); nvme_tcp_destroy_admin_queue(ctrl, remove); @@ -1924,11 +1923,7 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, nvme_stop_queues(ctrl); nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); - if (ctrl->tagset) { - blk_mq_tagset_busy_iter(ctrl->tagset, - nvme_cancel_request, ctrl); - blk_mq_tagset_wait_completed_request(ctrl->tagset); - } + nvme_cancel_tagset(ctrl); if (remove) nvme_start_queues(ctrl); nvme_tcp_destroy_io_queues(ctrl, remove); @@ -2003,10 +1998,18 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new) return 0; destroy_io: - if (ctrl->queue_count > 1) + if (ctrl->queue_count > 1) { + nvme_stop_queues(ctrl); + nvme_sync_io_queues(ctrl); + nvme_tcp_stop_io_queues(ctrl); + nvme_cancel_tagset(ctrl); nvme_tcp_destroy_io_queues(ctrl, new); + } destroy_admin: + blk_mq_quiesce_queue(ctrl->admin_q); + blk_sync_queue(ctrl->admin_q); nvme_tcp_stop_queue(ctrl, 0); + nvme_cancel_admin_tagset(ctrl); nvme_tcp_destroy_admin_queue(ctrl, new); return ret; } @@ -2268,12 +2271,12 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns, req->data_len = blk_rq_nr_phys_segments(rq) ? blk_rq_payload_bytes(rq) : 0; req->curr_bio = rq->bio; + if (req->curr_bio && req->data_len) + nvme_tcp_init_iter(req, rq_data_dir(rq)); if (rq_data_dir(rq) == WRITE && req->data_len <= nvme_tcp_inline_data_size(queue)) req->pdu_len = req->data_len; - else if (req->curr_bio) - nvme_tcp_init_iter(req, READ); pdu->hdr.type = nvme_tcp_cmd; pdu->hdr.flags = 0; diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c index 5c3cb6928f3c..6543015b6121 100644 --- a/drivers/nvme/host/trace.c +++ b/drivers/nvme/host/trace.c @@ -102,6 +102,23 @@ static const char *nvme_trace_get_lba_status(struct trace_seq *p, return ret; } +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; + u8 mset = (cdw10[0] >> 4) & 0x1; + u8 pi = (cdw10[0] >> 5) & 0x7; + u8 pil = cdw10[1] & 0x1; + u8 ses = (cdw10[1] >> 1) & 0x7; + + trace_seq_printf(p, "lbaf=%u, mset=%u, pi=%u, pil=%u, ses=%u", + lbaf, mset, pi, pil, ses); + + trace_seq_putc(p, 0); + + return ret; +} + static const char *nvme_trace_read_write(struct trace_seq *p, u8 *cdw10) { const char *ret = trace_seq_buffer_ptr(p); @@ -131,6 +148,35 @@ static const char *nvme_trace_dsm(struct trace_seq *p, u8 *cdw10) return ret; } +static const char *nvme_trace_zone_mgmt_send(struct trace_seq *p, u8 *cdw10) +{ + const char *ret = trace_seq_buffer_ptr(p); + u64 slba = get_unaligned_le64(cdw10); + u8 zsa = cdw10[12]; + u8 all = cdw10[13]; + + trace_seq_printf(p, "slba=%llu, zsa=%u, all=%u", slba, zsa, all); + trace_seq_putc(p, 0); + + return ret; +} + +static const char *nvme_trace_zone_mgmt_recv(struct trace_seq *p, u8 *cdw10) +{ + 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]; + u8 pr = cdw10[14]; + + trace_seq_printf(p, "slba=%llu, numd=%u, zra=%u, zrasf=%u, pr=%u", + slba, numd, zra, zrasf, pr); + trace_seq_putc(p, 0); + + return ret; +} + static const char *nvme_trace_common(struct trace_seq *p, u8 *cdw10) { const char *ret = trace_seq_buffer_ptr(p); @@ -159,6 +205,8 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, return nvme_trace_admin_get_features(p, cdw10); case nvme_admin_get_lba_status: return nvme_trace_get_lba_status(p, cdw10); + case nvme_admin_format_nvm: + return nvme_trace_admin_format_nvm(p, cdw10); default: return nvme_trace_common(p, cdw10); } @@ -171,9 +219,14 @@ const char *nvme_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 nvme_trace_read_write(p, cdw10); case nvme_cmd_dsm: return nvme_trace_dsm(p, cdw10); + case nvme_cmd_zone_mgmt_send: + return nvme_trace_zone_mgmt_send(p, cdw10); + case nvme_cmd_zone_mgmt_recv: + return nvme_trace_zone_mgmt_recv(p, cdw10); default: return nvme_trace_common(p, cdw10); } diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index dc1ea468b182..bc6a774f2124 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -74,34 +74,28 @@ static void nvmet_execute_get_log_page_error(struct nvmet_req *req) static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req, struct nvme_smart_log *slog) { - struct nvmet_ns *ns; u64 host_reads, host_writes, data_units_read, data_units_written; + u16 status; - ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->get_log_page.nsid); - if (!ns) { - pr_err("Could not find namespace id : %d\n", - le32_to_cpu(req->cmd->get_log_page.nsid)); - req->error_loc = offsetof(struct nvme_rw_command, nsid); - return NVME_SC_INVALID_NS; - } + status = nvmet_req_find_ns(req); + if (status) + return status; /* we don't have the right data for file backed ns */ - if (!ns->bdev) - goto out; + if (!req->ns->bdev) + return NVME_SC_SUCCESS; - host_reads = part_stat_read(ns->bdev, ios[READ]); + host_reads = part_stat_read(req->ns->bdev, ios[READ]); data_units_read = - DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[READ]), 1000); - host_writes = part_stat_read(ns->bdev, ios[WRITE]); + DIV_ROUND_UP(part_stat_read(req->ns->bdev, sectors[READ]), 1000); + host_writes = part_stat_read(req->ns->bdev, ios[WRITE]); data_units_written = - DIV_ROUND_UP(part_stat_read(ns->bdev, sectors[WRITE]), 1000); + DIV_ROUND_UP(part_stat_read(req->ns->bdev, sectors[WRITE]), 1000); put_unaligned_le64(host_reads, &slog->host_reads[0]); put_unaligned_le64(data_units_read, &slog->data_units_read[0]); put_unaligned_le64(host_writes, &slog->host_writes[0]); put_unaligned_le64(data_units_written, &slog->data_units_written[0]); -out: - nvmet_put_namespace(ns); return NVME_SC_SUCCESS; } @@ -468,10 +462,8 @@ out: static void nvmet_execute_identify_ns(struct nvmet_req *req) { - struct nvmet_ctrl *ctrl = req->sq->ctrl; - struct nvmet_ns *ns; struct nvme_id_ns *id; - u16 status = 0; + u16 status; if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) { req->error_loc = offsetof(struct nvme_identify, nsid); @@ -486,20 +478,21 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) } /* return an all zeroed buffer if we can't find an active namespace */ - ns = nvmet_find_namespace(ctrl, req->cmd->identify.nsid); - if (!ns) { - status = NVME_SC_INVALID_NS; + status = nvmet_req_find_ns(req); + if (status) { + status = 0; goto done; } - nvmet_ns_revalidate(ns); + nvmet_ns_revalidate(req->ns); /* * nuse = ncap = nsze isn't always true, but we have no way to find * that out from the underlying device. */ - id->ncap = id->nsze = cpu_to_le64(ns->size >> ns->blksize_shift); - switch (req->port->ana_state[ns->anagrpid]) { + id->ncap = id->nsze = + cpu_to_le64(req->ns->size >> req->ns->blksize_shift); + switch (req->port->ana_state[req->ns->anagrpid]) { case NVME_ANA_INACCESSIBLE: case NVME_ANA_PERSISTENT_LOSS: break; @@ -508,8 +501,8 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) break; } - if (ns->bdev) - nvmet_bdev_set_limits(ns->bdev, id); + if (req->ns->bdev) + nvmet_bdev_set_limits(req->ns->bdev, id); /* * We just provide a single LBA format that matches what the @@ -523,25 +516,24 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) * controllers, but also with any other user of the block device. */ id->nmic = (1 << 0); - id->anagrpid = cpu_to_le32(ns->anagrpid); + id->anagrpid = cpu_to_le32(req->ns->anagrpid); - memcpy(&id->nguid, &ns->nguid, sizeof(id->nguid)); + memcpy(&id->nguid, &req->ns->nguid, sizeof(id->nguid)); - id->lbaf[0].ds = ns->blksize_shift; + id->lbaf[0].ds = req->ns->blksize_shift; - if (ctrl->pi_support && nvmet_ns_has_pi(ns)) { + if (req->sq->ctrl->pi_support && nvmet_ns_has_pi(req->ns)) { id->dpc = NVME_NS_DPC_PI_FIRST | NVME_NS_DPC_PI_LAST | NVME_NS_DPC_PI_TYPE1 | NVME_NS_DPC_PI_TYPE2 | NVME_NS_DPC_PI_TYPE3; id->mc = NVME_MC_EXTENDED_LBA; - id->dps = ns->pi_type; + id->dps = req->ns->pi_type; id->flbas = NVME_NS_FLBAS_META_EXT; - id->lbaf[0].ms = cpu_to_le16(ns->metadata_size); + id->lbaf[0].ms = cpu_to_le16(req->ns->metadata_size); } - if (ns->readonly) + if (req->ns->readonly) id->nsattr |= (1 << 0); - nvmet_put_namespace(ns); done: if (!status) status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); @@ -607,37 +599,32 @@ static u16 nvmet_copy_ns_identifier(struct nvmet_req *req, u8 type, u8 len, static void nvmet_execute_identify_desclist(struct nvmet_req *req) { - struct nvmet_ns *ns; - u16 status = 0; off_t off = 0; + u16 status; - ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->identify.nsid); - if (!ns) { - req->error_loc = offsetof(struct nvme_identify, nsid); - status = NVME_SC_INVALID_NS | NVME_SC_DNR; + status = nvmet_req_find_ns(req); + if (status) goto out; - } - if (memchr_inv(&ns->uuid, 0, sizeof(ns->uuid))) { + if (memchr_inv(&req->ns->uuid, 0, sizeof(req->ns->uuid))) { status = nvmet_copy_ns_identifier(req, NVME_NIDT_UUID, NVME_NIDT_UUID_LEN, - &ns->uuid, &off); + &req->ns->uuid, &off); if (status) - goto out_put_ns; + goto out; } - if (memchr_inv(ns->nguid, 0, sizeof(ns->nguid))) { + if (memchr_inv(req->ns->nguid, 0, sizeof(req->ns->nguid))) { status = nvmet_copy_ns_identifier(req, NVME_NIDT_NGUID, NVME_NIDT_NGUID_LEN, - &ns->nguid, &off); + &req->ns->nguid, &off); if (status) - goto out_put_ns; + goto out; } if (sg_zero_buffer(req->sg, req->sg_cnt, NVME_IDENTIFY_DATA_SIZE - off, off) != NVME_IDENTIFY_DATA_SIZE - off) status = NVME_SC_INTERNAL | NVME_SC_DNR; -out_put_ns: - nvmet_put_namespace(ns); + out: nvmet_req_complete(req, status); } @@ -696,14 +683,12 @@ static u16 nvmet_write_protect_flush_sync(struct nvmet_req *req) static u16 nvmet_set_feat_write_protect(struct nvmet_req *req) { u32 write_protect = le32_to_cpu(req->cmd->common.cdw11); - struct nvmet_subsys *subsys = req->sq->ctrl->subsys; - u16 status = NVME_SC_FEATURE_NOT_CHANGEABLE; + struct nvmet_subsys *subsys = nvmet_req_subsys(req); + u16 status; - req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->rw.nsid); - if (unlikely(!req->ns)) { - req->error_loc = offsetof(struct nvme_common_command, nsid); + status = nvmet_req_find_ns(req); + if (status) return status; - } mutex_lock(&subsys->lock); switch (write_protect) { @@ -757,7 +742,7 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask) void nvmet_execute_set_features(struct nvmet_req *req) { - struct nvmet_subsys *subsys = req->sq->ctrl->subsys; + struct nvmet_subsys *subsys = nvmet_req_subsys(req); u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11); u16 status = 0; @@ -801,14 +786,13 @@ void nvmet_execute_set_features(struct nvmet_req *req) static u16 nvmet_get_feat_write_protect(struct nvmet_req *req) { - struct nvmet_subsys *subsys = req->sq->ctrl->subsys; + struct nvmet_subsys *subsys = nvmet_req_subsys(req); u32 result; - req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->common.nsid); - if (!req->ns) { - req->error_loc = offsetof(struct nvme_common_command, nsid); - return NVME_SC_INVALID_NS | NVME_SC_DNR; - } + result = nvmet_req_find_ns(req); + if (result) + return result; + mutex_lock(&subsys->lock); if (req->ns->readonly == true) result = NVME_NS_WRITE_PROTECT; @@ -832,7 +816,7 @@ void nvmet_get_feat_async_event(struct nvmet_req *req) void nvmet_execute_get_features(struct nvmet_req *req) { - struct nvmet_subsys *subsys = req->sq->ctrl->subsys; + struct nvmet_subsys *subsys = nvmet_req_subsys(req); u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10); u16 status = 0; @@ -939,7 +923,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) if (nvme_is_fabrics(cmd)) return nvmet_parse_fabrics_cmd(req); - if (req->sq->ctrl->subsys->type == NVME_NQN_DISC) + if (nvmet_req_subsys(req)->type == NVME_NQN_DISC) return nvmet_parse_discovery_cmd(req); ret = nvmet_check_ctrl_status(req, cmd); diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index c61ffd767062..635a7cb45d0b 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -45,7 +45,7 @@ static bool nvmet_is_port_enabled(struct nvmet_port *p, const char *caller) { if (p->enabled) pr_err("Disable port '%u' before changing attribute in %s\n", - le16_to_cpu(p->disc_addr.portid), caller); + le16_to_cpu(p->disc_addr.portid), caller); return p->enabled; } @@ -266,10 +266,8 @@ static ssize_t nvmet_param_pi_enable_store(struct config_item *item, if (strtobool(page, &val)) return -EINVAL; - if (port->enabled) { - pr_err("Disable port before setting pi_enable value.\n"); + if (nvmet_is_port_enabled(port, __func__)) return -EACCES; - } port->pi_enable = val; return count; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 8ce4d59cc9e7..67bbf0e3b507 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -82,6 +82,15 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno) return status; } +u16 nvmet_report_invalid_opcode(struct nvmet_req *req) +{ + pr_debug("unhandled cmd %d on qid %d\n", req->cmd->common.opcode, + req->sq->qid); + + req->error_loc = offsetof(struct nvme_common_command, opcode); + return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; +} + static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port, const char *subsysnqn); @@ -417,15 +426,18 @@ void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl) cancel_delayed_work_sync(&ctrl->ka_work); } -struct nvmet_ns *nvmet_find_namespace(struct nvmet_ctrl *ctrl, __le32 nsid) +u16 nvmet_req_find_ns(struct nvmet_req *req) { - struct nvmet_ns *ns; + u32 nsid = le32_to_cpu(req->cmd->common.nsid); - ns = xa_load(&ctrl->subsys->namespaces, le32_to_cpu(nsid)); - if (ns) - percpu_ref_get(&ns->ref); + req->ns = xa_load(&nvmet_req_subsys(req)->namespaces, nsid); + if (unlikely(!req->ns)) { + req->error_loc = offsetof(struct nvme_common_command, nsid); + return NVME_SC_INVALID_NS | NVME_SC_DNR; + } - return ns; + percpu_ref_get(&req->ns->ref); + return NVME_SC_SUCCESS; } static void nvmet_destroy_namespace(struct percpu_ref *ref) @@ -862,11 +874,10 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req) if (nvmet_req_passthru_ctrl(req)) return nvmet_parse_passthru_io_cmd(req); - req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid); - if (unlikely(!req->ns)) { - req->error_loc = offsetof(struct nvme_common_command, nsid); - return NVME_SC_INVALID_NS | NVME_SC_DNR; - } + ret = nvmet_req_find_ns(req); + if (unlikely(ret)) + return ret; + ret = nvmet_check_ana_state(req->port, req->ns); if (unlikely(ret)) { req->error_loc = offsetof(struct nvme_common_command, nsid); @@ -880,8 +891,8 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req) if (req->ns->file) return nvmet_file_parse_io_cmd(req); - else - return nvmet_bdev_parse_io_cmd(req); + + return nvmet_bdev_parse_io_cmd(req); } bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index cd4e73aa9807..d375745fc4ed 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -145,6 +145,7 @@ struct nvmet_fc_tgt_queue { struct list_head avail_defer_list; struct workqueue_struct *work_q; struct kref ref; + struct rcu_head rcu; struct nvmet_fc_fcp_iod fod[]; /* array of fcp_iods */ } __aligned(sizeof(unsigned long long)); @@ -164,9 +165,10 @@ struct nvmet_fc_tgt_assoc { struct nvmet_fc_hostport *hostport; struct nvmet_fc_ls_iod *rcv_disconn; struct list_head a_list; - struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1]; + struct nvmet_fc_tgt_queue __rcu *queues[NVMET_NR_QUEUES + 1]; struct kref ref; struct work_struct del_work; + struct rcu_head rcu; }; @@ -790,7 +792,6 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, u16 qid, u16 sqsize) { struct nvmet_fc_tgt_queue *queue; - unsigned long flags; int ret; if (qid > NVMET_NR_QUEUES) @@ -829,9 +830,7 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, goto out_fail_iodlist; WARN_ON(assoc->queues[qid]); - spin_lock_irqsave(&assoc->tgtport->lock, flags); - assoc->queues[qid] = queue; - spin_unlock_irqrestore(&assoc->tgtport->lock, flags); + rcu_assign_pointer(assoc->queues[qid], queue); return queue; @@ -851,11 +850,8 @@ nvmet_fc_tgt_queue_free(struct kref *ref) { struct nvmet_fc_tgt_queue *queue = container_of(ref, struct nvmet_fc_tgt_queue, ref); - unsigned long flags; - spin_lock_irqsave(&queue->assoc->tgtport->lock, flags); - queue->assoc->queues[queue->qid] = NULL; - spin_unlock_irqrestore(&queue->assoc->tgtport->lock, flags); + rcu_assign_pointer(queue->assoc->queues[queue->qid], NULL); nvmet_fc_destroy_fcp_iodlist(queue->assoc->tgtport, queue); @@ -863,7 +859,7 @@ nvmet_fc_tgt_queue_free(struct kref *ref) destroy_workqueue(queue->work_q); - kfree(queue); + kfree_rcu(queue, rcu); } static void @@ -965,24 +961,23 @@ nvmet_fc_find_target_queue(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_tgt_queue *queue; u64 association_id = nvmet_fc_getassociationid(connection_id); u16 qid = nvmet_fc_getqueueid(connection_id); - unsigned long flags; if (qid > NVMET_NR_QUEUES) return NULL; - spin_lock_irqsave(&tgtport->lock, flags); - list_for_each_entry(assoc, &tgtport->assoc_list, a_list) { + rcu_read_lock(); + list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { if (association_id == assoc->association_id) { - queue = assoc->queues[qid]; + queue = rcu_dereference(assoc->queues[qid]); if (queue && (!atomic_read(&queue->connected) || !nvmet_fc_tgt_q_get(queue))) queue = NULL; - spin_unlock_irqrestore(&tgtport->lock, flags); + rcu_read_unlock(); return queue; } } - spin_unlock_irqrestore(&tgtport->lock, flags); + rcu_read_unlock(); return NULL; } @@ -1137,7 +1132,7 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle) } if (!needrandom) { assoc->association_id = ran; - list_add_tail(&assoc->a_list, &tgtport->assoc_list); + list_add_tail_rcu(&assoc->a_list, &tgtport->assoc_list); } spin_unlock_irqrestore(&tgtport->lock, flags); } @@ -1167,7 +1162,7 @@ nvmet_fc_target_assoc_free(struct kref *ref) nvmet_fc_free_hostport(assoc->hostport); spin_lock_irqsave(&tgtport->lock, flags); - list_del(&assoc->a_list); + list_del_rcu(&assoc->a_list); oldls = assoc->rcv_disconn; spin_unlock_irqrestore(&tgtport->lock, flags); /* if pending Rcv Disconnect Association LS, send rsp now */ @@ -1177,7 +1172,7 @@ nvmet_fc_target_assoc_free(struct kref *ref) dev_info(tgtport->dev, "{%d:%d} Association freed\n", tgtport->fc_target_port.port_num, assoc->a_id); - kfree(assoc); + kfree_rcu(assoc, rcu); nvmet_fc_tgtport_put(tgtport); } @@ -1198,7 +1193,6 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) { struct nvmet_fc_tgtport *tgtport = assoc->tgtport; struct nvmet_fc_tgt_queue *queue; - unsigned long flags; int i, terminating; terminating = atomic_xchg(&assoc->terminating, 1); @@ -1207,19 +1201,23 @@ nvmet_fc_delete_target_assoc(struct nvmet_fc_tgt_assoc *assoc) if (terminating) return; - spin_lock_irqsave(&tgtport->lock, flags); + for (i = NVMET_NR_QUEUES; i >= 0; i--) { - queue = assoc->queues[i]; - if (queue) { - if (!nvmet_fc_tgt_q_get(queue)) - continue; - spin_unlock_irqrestore(&tgtport->lock, flags); - nvmet_fc_delete_target_queue(queue); - nvmet_fc_tgt_q_put(queue); - spin_lock_irqsave(&tgtport->lock, flags); + rcu_read_lock(); + queue = rcu_dereference(assoc->queues[i]); + if (!queue) { + rcu_read_unlock(); + continue; + } + + if (!nvmet_fc_tgt_q_get(queue)) { + rcu_read_unlock(); + continue; } + rcu_read_unlock(); + nvmet_fc_delete_target_queue(queue); + nvmet_fc_tgt_q_put(queue); } - spin_unlock_irqrestore(&tgtport->lock, flags); dev_info(tgtport->dev, "{%d:%d} Association deleted\n", @@ -1234,10 +1232,9 @@ nvmet_fc_find_target_assoc(struct nvmet_fc_tgtport *tgtport, { struct nvmet_fc_tgt_assoc *assoc; struct nvmet_fc_tgt_assoc *ret = NULL; - unsigned long flags; - spin_lock_irqsave(&tgtport->lock, flags); - list_for_each_entry(assoc, &tgtport->assoc_list, a_list) { + rcu_read_lock(); + list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { if (association_id == assoc->association_id) { ret = assoc; if (!nvmet_fc_tgt_a_get(assoc)) @@ -1245,7 +1242,7 @@ nvmet_fc_find_target_assoc(struct nvmet_fc_tgtport *tgtport, break; } } - spin_unlock_irqrestore(&tgtport->lock, flags); + rcu_read_unlock(); return ret; } @@ -1473,19 +1470,17 @@ nvmet_fc_tgtport_get(struct nvmet_fc_tgtport *tgtport) static void __nvmet_fc_free_assocs(struct nvmet_fc_tgtport *tgtport) { - struct nvmet_fc_tgt_assoc *assoc, *next; - unsigned long flags; + struct nvmet_fc_tgt_assoc *assoc; - spin_lock_irqsave(&tgtport->lock, flags); - list_for_each_entry_safe(assoc, next, - &tgtport->assoc_list, a_list) { + rcu_read_lock(); + list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { if (!nvmet_fc_tgt_a_get(assoc)) continue; if (!schedule_work(&assoc->del_work)) /* already deleting - release local reference */ nvmet_fc_tgt_a_put(assoc); } - spin_unlock_irqrestore(&tgtport->lock, flags); + rcu_read_unlock(); } /** @@ -1568,16 +1563,16 @@ nvmet_fc_delete_ctrl(struct nvmet_ctrl *ctrl) continue; spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags); - spin_lock_irqsave(&tgtport->lock, flags); - list_for_each_entry(assoc, &tgtport->assoc_list, a_list) { - queue = assoc->queues[0]; + rcu_read_lock(); + list_for_each_entry_rcu(assoc, &tgtport->assoc_list, a_list) { + queue = rcu_dereference(assoc->queues[0]); if (queue && queue->nvme_sq.ctrl == ctrl) { if (nvmet_fc_tgt_a_get(assoc)) found_ctrl = true; break; } } - spin_unlock_irqrestore(&tgtport->lock, flags); + rcu_read_unlock(); nvmet_fc_tgtport_put(tgtport); diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 68213f0a052b..54606f1872b4 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -1545,7 +1545,7 @@ static struct attribute *fcloop_dev_attrs[] = { NULL }; -static struct attribute_group fclopp_dev_attrs_group = { +static const struct attribute_group fclopp_dev_attrs_group = { .attrs = fcloop_dev_attrs, }; diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index bf6e0ac9ad28..3d9a5d3ed9cd 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -256,8 +256,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) if (is_pci_p2pdma_page(sg_page(req->sg))) op |= REQ_NOMERGE; - sector = le64_to_cpu(req->cmd->rw.slba); - sector <<= (req->ns->blksize_shift - 9); + sector = nvmet_lba_to_sect(req->ns, req->cmd->rw.slba); if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) { bio = &req->b.inline_bio; @@ -345,7 +344,7 @@ static u16 nvmet_bdev_discard_range(struct nvmet_req *req, int ret; ret = __blkdev_issue_discard(ns->bdev, - le64_to_cpu(range->slba) << (ns->blksize_shift - 9), + nvmet_lba_to_sect(ns, range->slba), le32_to_cpu(range->nlb) << (ns->blksize_shift - 9), GFP_KERNEL, 0, bio); if (ret && ret != -EOPNOTSUPP) { @@ -414,8 +413,7 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req) if (!nvmet_check_transfer_len(req, 0)) return; - sector = le64_to_cpu(write_zeroes->slba) << - (req->ns->blksize_shift - 9); + sector = nvmet_lba_to_sect(req->ns, write_zeroes->slba); nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) << (req->ns->blksize_shift - 9)); @@ -451,9 +449,6 @@ u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req) req->execute = nvmet_bdev_execute_write_zeroes; return 0; default: - pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode, - req->sq->qid); - req->error_loc = offsetof(struct nvme_common_command, opcode); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return nvmet_report_invalid_opcode(req); } } diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 0abbefd9925e..715d4376c997 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -400,9 +400,6 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req) req->execute = nvmet_file_execute_write_zeroes; return 0; default: - pr_err("unhandled cmd for file ns %d on qid %d\n", - cmd->common.opcode, req->sq->qid); - req->error_loc = offsetof(struct nvme_common_command, opcode); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return nvmet_report_invalid_opcode(req); } } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 592763732065..cdfa537b1c0a 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -443,7 +443,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, void nvmet_subsys_put(struct nvmet_subsys *subsys); void nvmet_subsys_del_ctrls(struct nvmet_subsys *subsys); -struct nvmet_ns *nvmet_find_namespace(struct nvmet_ctrl *ctrl, __le32 nsid); +u16 nvmet_req_find_ns(struct nvmet_req *req); void nvmet_put_namespace(struct nvmet_ns *ns); int nvmet_ns_enable(struct nvmet_ns *ns); void nvmet_ns_disable(struct nvmet_ns *ns); @@ -551,6 +551,11 @@ static inline u32 nvmet_dsm_len(struct nvmet_req *req) sizeof(struct nvme_dsm_range); } +static inline struct nvmet_subsys *nvmet_req_subsys(struct nvmet_req *req) +{ + return req->sq->ctrl->subsys; +} + #ifdef CONFIG_NVME_TARGET_PASSTHRU void nvmet_passthru_subsys_free(struct nvmet_subsys *subsys); int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys); @@ -585,10 +590,11 @@ static inline struct nvme_ctrl *nvmet_passthru_ctrl(struct nvmet_subsys *subsys) static inline struct nvme_ctrl * nvmet_req_passthru_ctrl(struct nvmet_req *req) { - return nvmet_passthru_ctrl(req->sq->ctrl->subsys); + return nvmet_passthru_ctrl(nvmet_req_subsys(req)); } u16 errno_to_nvme_status(struct nvmet_req *req, int errno); +u16 nvmet_report_invalid_opcode(struct nvmet_req *req); /* Convert a 32-bit number to a 16-bit 0's based number */ static inline __le16 to0based(u32 a) @@ -603,4 +609,14 @@ static inline bool nvmet_ns_has_pi(struct nvmet_ns *ns) return ns->pi_type && ns->metadata_size == sizeof(struct t10_pi_tuple); } +static inline __le64 nvmet_sect_to_lba(struct nvmet_ns *ns, sector_t sect) +{ + return cpu_to_le64(sect >> (ns->blksize_shift - SECTOR_SHIFT)); +} + +static inline sector_t nvmet_lba_to_sect(struct nvmet_ns *ns, __le64 lba) +{ + return le64_to_cpu(lba) << (ns->blksize_shift - SECTOR_SHIFT); +} + #endif /* _NVMET_H */ diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index cbc88acdd233..f50c7b2bf21c 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -239,9 +239,9 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req) } q = ns->queue; - timeout = req->sq->ctrl->subsys->io_timeout; + timeout = nvmet_req_subsys(req)->io_timeout; } else { - timeout = req->sq->ctrl->subsys->admin_timeout; + timeout = nvmet_req_subsys(req)->admin_timeout; } rq = nvme_alloc_request(q, req->cmd, 0); @@ -494,7 +494,7 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req) return nvmet_setup_passthru_command(req); default: /* Reject commands not in the allowlist above */ - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return nvmet_report_invalid_opcode(req); } } diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index aacf06f0b431..8b0485ada315 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -379,7 +379,7 @@ err: return NVME_SC_INTERNAL; } -static void nvmet_tcp_ddgst(struct ahash_request *hash, +static void nvmet_tcp_send_ddgst(struct ahash_request *hash, struct nvmet_tcp_cmd *cmd) { ahash_request_set_crypt(hash, cmd->req.sg, @@ -387,6 +387,23 @@ static void nvmet_tcp_ddgst(struct ahash_request *hash, crypto_ahash_digest(hash); } +static void nvmet_tcp_recv_ddgst(struct ahash_request *hash, + struct nvmet_tcp_cmd *cmd) +{ + struct scatterlist sg; + struct kvec *iov; + int i; + + crypto_ahash_init(hash); + for (i = 0, iov = cmd->iov; i < cmd->nr_mapped; i++, iov++) { + sg_init_one(&sg, iov->iov_base, iov->iov_len); + ahash_request_set_crypt(hash, &sg, NULL, iov->iov_len); + crypto_ahash_update(hash); + } + ahash_request_set_crypt(hash, NULL, (void *)&cmd->exp_ddgst, 0); + crypto_ahash_final(hash); +} + static void nvmet_setup_c2h_data_pdu(struct nvmet_tcp_cmd *cmd) { struct nvme_tcp_data_pdu *pdu = cmd->data_pdu; @@ -411,7 +428,7 @@ static void nvmet_setup_c2h_data_pdu(struct nvmet_tcp_cmd *cmd) if (queue->data_digest) { pdu->hdr.flags |= NVME_TCP_F_DDGST; - nvmet_tcp_ddgst(queue->snd_hash, cmd); + nvmet_tcp_send_ddgst(queue->snd_hash, cmd); } if (cmd->queue->hdr_digest) { @@ -1060,7 +1077,7 @@ static void nvmet_tcp_prep_recv_ddgst(struct nvmet_tcp_cmd *cmd) { struct nvmet_tcp_queue *queue = cmd->queue; - nvmet_tcp_ddgst(queue->rcv_hash, cmd); + nvmet_tcp_recv_ddgst(queue->rcv_hash, cmd); queue->offset = 0; queue->left = NVME_TCP_DIGEST_LENGTH; queue->rcv_state = NVMET_TCP_RECV_DDGST; @@ -1081,14 +1098,14 @@ static int nvmet_tcp_try_recv_data(struct nvmet_tcp_queue *queue) cmd->rbytes_done += ret; } + if (queue->data_digest) { + nvmet_tcp_prep_recv_ddgst(cmd); + return 0; + } nvmet_tcp_unmap_pdu_iovec(cmd); if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) && cmd->rbytes_done == cmd->req.transfer_len) { - if (queue->data_digest) { - nvmet_tcp_prep_recv_ddgst(cmd); - return 0; - } cmd->req.execute(&cmd->req); } @@ -1468,17 +1485,27 @@ static int nvmet_tcp_set_queue_sock(struct nvmet_tcp_queue *queue) if (inet->rcv_tos > 0) ip_sock_set_tos(sock->sk, inet->rcv_tos); + ret = 0; write_lock_bh(&sock->sk->sk_callback_lock); - sock->sk->sk_user_data = queue; - queue->data_ready = sock->sk->sk_data_ready; - sock->sk->sk_data_ready = nvmet_tcp_data_ready; - queue->state_change = sock->sk->sk_state_change; - sock->sk->sk_state_change = nvmet_tcp_state_change; - queue->write_space = sock->sk->sk_write_space; - sock->sk->sk_write_space = nvmet_tcp_write_space; + if (sock->sk->sk_state != TCP_ESTABLISHED) { + /* + * If the socket is already closing, don't even start + * consuming it + */ + ret = -ENOTCONN; + } else { + sock->sk->sk_user_data = queue; + queue->data_ready = sock->sk->sk_data_ready; + sock->sk->sk_data_ready = nvmet_tcp_data_ready; + queue->state_change = sock->sk->sk_state_change; + sock->sk->sk_state_change = nvmet_tcp_state_change; + queue->write_space = sock->sk->sk_write_space; + sock->sk->sk_write_space = nvmet_tcp_write_space; + queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work); + } write_unlock_bh(&sock->sk->sk_callback_lock); - return 0; + return ret; } static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port, @@ -1526,8 +1553,6 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port, if (ret) goto out_destroy_sq; - queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work); - return 0; out_destroy_sq: mutex_lock(&nvmet_tcp_queue_mutex); diff --git a/drivers/nvme/target/trace.h b/drivers/nvme/target/trace.h index c14e3249a14d..6109b3806b12 100644 --- a/drivers/nvme/target/trace.h +++ b/drivers/nvme/target/trace.h @@ -48,10 +48,13 @@ static inline struct nvmet_ctrl *nvmet_req_to_ctrl(struct nvmet_req *req) static inline void __assign_req_name(char *name, struct nvmet_req *req) { - if (req->ns) - strncpy(name, req->ns->device_path, DISK_NAME_LEN); - else + if (!req->ns) { memset(name, 0, DISK_NAME_LEN); + return; + } + + strncpy(name, req->ns->device_path, + min_t(size_t, DISK_NAME_LEN, strlen(req->ns->device_path))); } #endif |