From eaefd5abf6b095bfc55eb745bdf7c42cf66790eb Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 14 Sep 2017 10:38:42 -0700 Subject: nvme-fc: add uevent for auto-connect To support auto-connecting to FC-NVME devices upon their dynamic appearance, add a uevent that can kick off connection scripts. uevent is posted against the fc_udev device. patch set tested with the following rule to kick an nvme-cli connect-all for the FC initiator and FC target ports. This is just an example for testing and not intended for real life use. ACTION=="change", SUBSYSTEM=="fc", ENV{FC_EVENT}=="nvmediscovery", \ ENV{NVMEFC_HOST_TRADDR}=="*", ENV{NVMEFC_TRADDR}=="*", \ RUN+="/bin/sh -c '/usr/local/sbin/nvme connect-all --transport=fc --host-traddr=$env{NVMEFC_HOST_TRADDR} --traddr=$env{NVMEFC_TRADDR} >> /tmp/nvme_fc.log'" I will post proposed udev/systemd scripts for possible kernel support. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index af075e998944..f546eecb1f82 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -452,6 +452,36 @@ nvme_fc_unregister_localport(struct nvme_fc_local_port *portptr) } EXPORT_SYMBOL_GPL(nvme_fc_unregister_localport); +/* + * TRADDR strings, per FC-NVME are fixed format: + * "nn-0x<16hexdigits>:pn-0x<16hexdigits>" - 43 characters + * udev event will only differ by prefix of what field is + * being specified: + * "NVMEFC_HOST_TRADDR=" or "NVMEFC_TRADDR=" - 19 max characters + * 19 + 43 + null_fudge = 64 characters + */ +#define FCNVME_TRADDR_LENGTH 64 + +static void +nvme_fc_signal_discovery_scan(struct nvme_fc_lport *lport, + struct nvme_fc_rport *rport) +{ + char hostaddr[FCNVME_TRADDR_LENGTH]; /* NVMEFC_HOST_TRADDR=...*/ + char tgtaddr[FCNVME_TRADDR_LENGTH]; /* NVMEFC_TRADDR=...*/ + char *envp[4] = { "FC_EVENT=nvmediscovery", hostaddr, tgtaddr, NULL }; + + if (!(rport->remoteport.port_role & FC_PORT_ROLE_NVME_DISCOVERY)) + return; + + snprintf(hostaddr, sizeof(hostaddr), + "NVMEFC_HOST_TRADDR=nn-0x%016llx:pn-0x%016llx", + lport->localport.node_name, lport->localport.port_name); + snprintf(tgtaddr, sizeof(tgtaddr), + "NVMEFC_TRADDR=nn-0x%016llx:pn-0x%016llx", + rport->remoteport.node_name, rport->remoteport.port_name); + kobject_uevent_env(&fc_udev_device->kobj, KOBJ_CHANGE, envp); +} + /** * nvme_fc_register_remoteport - transport entry point called by an * LLDD to register the existence of a NVME @@ -516,6 +546,8 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport, list_add_tail(&newrec->endp_list, &lport->endp_list); spin_unlock_irqrestore(&nvme_fc_lock, flags); + nvme_fc_signal_discovery_scan(lport, newrec); + *portptr = &newrec->remoteport; return 0; @@ -634,6 +666,23 @@ nvme_fc_unregister_remoteport(struct nvme_fc_remote_port *portptr) } EXPORT_SYMBOL_GPL(nvme_fc_unregister_remoteport); +/** + * nvme_fc_rescan_remoteport - transport entry point called by an + * LLDD to request a nvme device rescan. + * @remoteport: pointer to the (registered) remote port that is to be + * rescanned. + * + * Returns: N/A + */ +void +nvme_fc_rescan_remoteport(struct nvme_fc_remote_port *remoteport) +{ + struct nvme_fc_rport *rport = remoteport_to_rport(remoteport); + + nvme_fc_signal_discovery_scan(rport->lport, rport); +} +EXPORT_SYMBOL_GPL(nvme_fc_rescan_remoteport); + /* *********************** FC-NVME DMA Handling **************************** */ -- cgit v1.2.3 From 5f5685569ae8fccb0344373d823f2e4c59bb3d8e Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 14 Sep 2017 10:38:41 -0700 Subject: nvme-fc: create fc class and transport device Added a new fc class and a device node for udev events under it. I expect the fc class will eventually be the location where the FC SCSI and FC NVME merge in the future. Therefore names are kept somewhat generic. Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 54 insertions(+), 1 deletion(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index f546eecb1f82..2dc9932e4818 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -213,6 +213,13 @@ static DEFINE_IDA(nvme_fc_ctrl_cnt); +/* + * These items are short-term. They will eventually be moved into + * a generic FC class. See comments in module init. + */ +static struct class *fc_class; +static struct device *fc_udev_device; + /* *********************** FC-NVME Port Management ************************ */ @@ -3046,7 +3053,50 @@ static struct nvmf_transport_ops nvme_fc_transport = { static int __init nvme_fc_init_module(void) { - return nvmf_register_transport(&nvme_fc_transport); + int ret; + + /* + * NOTE: + * It is expected that in the future the kernel will combine + * the FC-isms that are currently under scsi and now being + * added to by NVME into a new standalone FC class. The SCSI + * and NVME protocols and their devices would be under this + * new FC class. + * + * As we need something to post FC-specific udev events to, + * specifically for nvme probe events, start by creating the + * new device class. When the new standalone FC class is + * put in place, this code will move to a more generic + * location for the class. + */ + fc_class = class_create(THIS_MODULE, "fc"); + if (IS_ERR(fc_class)) { + pr_err("couldn't register class fc\n"); + return PTR_ERR(fc_class); + } + + /* + * Create a device for the FC-centric udev events + */ + fc_udev_device = device_create(fc_class, NULL, MKDEV(0, 0), NULL, + "fc_udev_device"); + if (IS_ERR(fc_udev_device)) { + pr_err("couldn't create fc_udev device!\n"); + ret = PTR_ERR(fc_udev_device); + goto out_destroy_class; + } + + ret = nvmf_register_transport(&nvme_fc_transport); + if (ret) + goto out_destroy_device; + + return 0; + +out_destroy_device: + device_destroy(fc_class, MKDEV(0, 0)); +out_destroy_class: + class_destroy(fc_class); + return ret; } static void __exit nvme_fc_exit_module(void) @@ -3059,6 +3109,9 @@ static void __exit nvme_fc_exit_module(void) ida_destroy(&nvme_fc_local_port_cnt); ida_destroy(&nvme_fc_ctrl_cnt); + + device_destroy(fc_class, MKDEV(0, 0)); + class_destroy(fc_class); } module_init(nvme_fc_init_module); -- cgit v1.2.3 From 469d0ef06debe29ec60350b9976a520c4ad5a1e8 Mon Sep 17 00:00:00 2001 From: James Smart Date: Tue, 26 Sep 2017 21:50:45 -0700 Subject: nvme-fc: move remote port get/put/free location move nvme_fc_rport_get/put and rport free to higher in the file to avoid adding prototypes to resolve references in upcoming code additions Signed-off-by: James Smart Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 78 +++++++++++++++++++++++++------------------------- 1 file changed, 39 insertions(+), 39 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 2dc9932e4818..b8e0822127c1 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -489,6 +489,45 @@ nvme_fc_signal_discovery_scan(struct nvme_fc_lport *lport, kobject_uevent_env(&fc_udev_device->kobj, KOBJ_CHANGE, envp); } +static void +nvme_fc_free_rport(struct kref *ref) +{ + struct nvme_fc_rport *rport = + container_of(ref, struct nvme_fc_rport, ref); + struct nvme_fc_lport *lport = + localport_to_lport(rport->remoteport.localport); + unsigned long flags; + + WARN_ON(rport->remoteport.port_state != FC_OBJSTATE_DELETED); + WARN_ON(!list_empty(&rport->ctrl_list)); + + /* remove from lport list */ + spin_lock_irqsave(&nvme_fc_lock, flags); + list_del(&rport->endp_list); + spin_unlock_irqrestore(&nvme_fc_lock, flags); + + /* let the LLDD know we've finished tearing it down */ + lport->ops->remoteport_delete(&rport->remoteport); + + ida_simple_remove(&lport->endp_cnt, rport->remoteport.port_num); + + kfree(rport); + + nvme_fc_lport_put(lport); +} + +static void +nvme_fc_rport_put(struct nvme_fc_rport *rport) +{ + kref_put(&rport->ref, nvme_fc_free_rport); +} + +static int +nvme_fc_rport_get(struct nvme_fc_rport *rport) +{ + return kref_get_unless_zero(&rport->ref); +} + /** * nvme_fc_register_remoteport - transport entry point called by an * LLDD to register the existence of a NVME @@ -568,45 +607,6 @@ out_reghost_failed: } EXPORT_SYMBOL_GPL(nvme_fc_register_remoteport); -static void -nvme_fc_free_rport(struct kref *ref) -{ - struct nvme_fc_rport *rport = - container_of(ref, struct nvme_fc_rport, ref); - struct nvme_fc_lport *lport = - localport_to_lport(rport->remoteport.localport); - unsigned long flags; - - WARN_ON(rport->remoteport.port_state != FC_OBJSTATE_DELETED); - WARN_ON(!list_empty(&rport->ctrl_list)); - - /* remove from lport list */ - spin_lock_irqsave(&nvme_fc_lock, flags); - list_del(&rport->endp_list); - spin_unlock_irqrestore(&nvme_fc_lock, flags); - - /* let the LLDD know we've finished tearing it down */ - lport->ops->remoteport_delete(&rport->remoteport); - - ida_simple_remove(&lport->endp_cnt, rport->remoteport.port_num); - - kfree(rport); - - nvme_fc_lport_put(lport); -} - -static void -nvme_fc_rport_put(struct nvme_fc_rport *rport) -{ - kref_put(&rport->ref, nvme_fc_free_rport); -} - -static int -nvme_fc_rport_get(struct nvme_fc_rport *rport) -{ - return kref_get_unless_zero(&rport->ref); -} - static int nvme_fc_abort_lsops(struct nvme_fc_rport *rport) { -- cgit v1.2.3 From 31b8446079757575e576b0516f0e4c0fcdfbd3dd Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 11 Oct 2017 12:53:07 +0300 Subject: nvme: introduce nvme_reinit_tagset Move blk_mq_reinit_tagset from blk-mq to nvme core as the only user of it. Current transports that use it (rdma, fc) simply implement .reinit_request op. This patch does not change any functionality. Reviewed-by: Jens Axboe Reviewed-by: Max Gurtovoy Reviewed-by: Johannes Thumshirn Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 10 ++++++++++ drivers/nvme/host/fc.c | 3 ++- drivers/nvme/host/nvme.h | 2 ++ drivers/nvme/host/rdma.c | 7 +++---- 4 files changed, 17 insertions(+), 5 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 573cc3b59bfa..c95155696741 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2934,6 +2934,16 @@ void nvme_start_queues(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_start_queues); +int nvme_reinit_tagset(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set) +{ + if (!ctrl->ops->reinit_request) + return 0; + + return blk_mq_tagset_iter(set, set->driver_data, + ctrl->ops->reinit_request); +} +EXPORT_SYMBOL_GPL(nvme_reinit_tagset); + int __init nvme_core_init(void) { int result; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index b8e0822127c1..372a0685b12a 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2393,7 +2393,7 @@ nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl) nvme_fc_init_io_queues(ctrl); - ret = blk_mq_reinit_tagset(&ctrl->tag_set, nvme_fc_reinit_request); + ret = nvme_reinit_tagset(&ctrl->ctrl, ctrl->ctrl.tagset); if (ret) goto out_free_io_queues; @@ -2753,6 +2753,7 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { .submit_async_event = nvme_fc_submit_async_event, .delete_ctrl = nvme_fc_del_nvme_ctrl, .get_address = nvmf_get_address, + .reinit_request = nvme_fc_reinit_request, }; static void diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index df787f39f4c1..cb9d93048f3d 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -237,6 +237,7 @@ struct nvme_ctrl_ops { void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx); int (*delete_ctrl)(struct nvme_ctrl *ctrl); int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size); + int (*reinit_request)(void *data, struct request *rq); }; static inline bool nvme_ctrl_ready(struct nvme_ctrl *ctrl) @@ -311,6 +312,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl); void nvme_wait_freeze(struct nvme_ctrl *ctrl); void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout); void nvme_start_freeze(struct nvme_ctrl *ctrl); +int nvme_reinit_tagset(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set); #define NVME_QID_ANY -1 struct request *nvme_alloc_request(struct request_queue *q, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 92a03ff5fb4d..039f38cb6987 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -774,8 +774,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl, goto out_free_tagset; } } else { - error = blk_mq_reinit_tagset(&ctrl->admin_tag_set, - nvme_rdma_reinit_request); + error = nvme_reinit_tagset(&ctrl->ctrl, ctrl->ctrl.admin_tagset); if (error) goto out_free_queue; } @@ -855,8 +854,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new) goto out_free_tag_set; } } else { - ret = blk_mq_reinit_tagset(&ctrl->tag_set, - nvme_rdma_reinit_request); + ret = nvme_reinit_tagset(&ctrl->ctrl, ctrl->ctrl.tagset); if (ret) goto out_free_io_queues; @@ -1845,6 +1843,7 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { .submit_async_event = nvme_rdma_submit_async_event, .delete_ctrl = nvme_rdma_del_ctrl, .get_address = nvmf_get_address, + .reinit_request = nvme_rdma_reinit_request, }; static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, -- cgit v1.2.3 From 5a22e2bf44fb311e5a6bfec6ed5680199d6e162a Mon Sep 17 00:00:00 2001 From: Israel Rukshin Date: Wed, 18 Oct 2017 12:38:25 +0000 Subject: nvme-fc: Add BLK_MQ_F_NO_SCHED flag to admin tag set Since commit b86dd81 "block: get rid of blk-mq default scheduler choice Kconfig entries", when setting nr_hw_queues to 1 the admin tag set uses mq-deadline scheduler. This flag is useful for admin queues that aren't used for normal IO. Signed-off-by: Israel Rukshin Reviewed-by: Max Gurtovoy Reviewed-by: Sagi Grimberg Reviewed-by: James Smart Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 372a0685b12a..0d0e898912ad 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2853,6 +2853,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ctrl->admin_tag_set.driver_data = ctrl; ctrl->admin_tag_set.nr_hw_queues = 1; ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT; + ctrl->admin_tag_set.flags = BLK_MQ_F_NO_SCHED; ret = blk_mq_alloc_tag_set(&ctrl->admin_tag_set); if (ret) -- cgit v1.2.3 From 0a02e39fd1eb2ceb3dd0dc765cb2de4d09697a14 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 19 Oct 2017 16:11:38 -0700 Subject: nvme-fc: correct io termination handling The io completion handling for i/o's that are failing due to to a transport error or association termination had issues, causing io failures (DNR set so retries didn't kick in) or long stalls. Change the io completion handler for the following items: When an io has been completed due to a transport abort (based on an exchange error) or when marked as aborted as part of an association termination (FCOP_FLAGS_TERMIO), set the NVME completion status to NVME_SC_ABORTED. By default, do not set DNR on the status so that a retry can be attempted after association recreate. In cases where an io is failed (non-successful nvme status including aborted), if the controller is being deleted (blk_queue_dying) or the io was part of the ios used for association creation (ctrl state is NEW or RECONNECTING), then additionally set the DNR bit so the io will not be retried. If the failed io was part of association creation, the failure will tear down the partially completioned association and typically restart a new reconnect attempt (another create association later). Rearranged code flow to remove a largely unneeded local variable. Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 0d0e898912ad..e1a7e5cdfcf4 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1387,7 +1387,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) struct nvme_command *sqe = &op->cmd_iu.sqe; __le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1); union nvme_result result; - bool complete_rq, terminate_assoc = true; + bool terminate_assoc = true; /* * WARNING: @@ -1429,8 +1429,9 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) fc_dma_sync_single_for_cpu(ctrl->lport->dev, op->fcp_req.rspdma, sizeof(op->rsp_iu), DMA_FROM_DEVICE); - if (atomic_read(&op->state) == FCPOP_STATE_ABORTED) - status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1); + if (atomic_read(&op->state) == FCPOP_STATE_ABORTED || + op->flags & FCOP_FLAGS_TERMIO) + status = cpu_to_le16(NVME_SC_ABORT_REQ << 1); else if (freq->status) status = cpu_to_le16(NVME_SC_INTERNAL << 1); @@ -1494,23 +1495,27 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) done: if (op->flags & FCOP_FLAGS_AEN) { nvme_complete_async_event(&queue->ctrl->ctrl, status, &result); - complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op); + __nvme_fc_fcpop_chk_teardowns(ctrl, op); atomic_set(&op->state, FCPOP_STATE_IDLE); op->flags = FCOP_FLAGS_AEN; /* clear other flags */ nvme_fc_ctrl_put(ctrl); goto check_error; } - complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op); - if (!complete_rq) { - if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) { - status = cpu_to_le16(NVME_SC_ABORT_REQ << 1); - if (blk_queue_dying(rq->q)) - status |= cpu_to_le16(NVME_SC_DNR << 1); - } - nvme_end_request(rq, status, result); - } else + /* + * Force failures of commands if we're killing the controller + * or have an error on a command used to create an new association + */ + if (status && + (blk_queue_dying(rq->q) || + ctrl->ctrl.state == NVME_CTRL_NEW || + ctrl->ctrl.state == NVME_CTRL_RECONNECTING)) + status |= cpu_to_le16(NVME_SC_DNR << 1); + + if (__nvme_fc_fcpop_chk_teardowns(ctrl, op)) __nvme_fc_final_op_cleanup(rq); + else + nvme_end_request(rq, status, result); check_error: if (terminate_assoc) -- cgit v1.2.3 From 134aedc9c157d49069e9a98636b0a917678586ee Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 19 Oct 2017 16:11:39 -0700 Subject: nvme-fc: correct io timeout behavior The transport io timeout behavior wasn't quite correct. It ignored that the io error handler is supposed to be synchronous so it possibly allowed the blk request to be restarted while the io associated was still aborting. Timeouts on reserved commands, those used for association create, were never timing out thus they hung out forever. To correct: If an io is times out while a remoteport is not connected, just restart the io timer. The lack of connectivity will simultaneously be resetting the controller, so the reset path will abort and terminate the io. If an io is times out while it was marked for transport abort, just reset the io timer. The abort process is underway and will complete the io. Otherwise, if an io times out, abort the io. If the abort was unsuccessful (unlikely) give up and return not handled. If the abort was successful, as the abort process is underway it will terminate the io, so rather than synchronously waiting, just restart the io timer. Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index e1a7e5cdfcf4..c6c903f1b172 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1903,13 +1903,14 @@ nvme_fc_timeout(struct request *rq, bool reserved) struct nvme_fc_ctrl *ctrl = op->ctrl; int ret; - if (reserved) + if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE || + atomic_read(&op->state) == FCPOP_STATE_ABORTED) return BLK_EH_RESET_TIMER; ret = __nvme_fc_abort_op(ctrl, op); if (ret) - /* io wasn't active to abort consider it done */ - return BLK_EH_HANDLED; + /* io wasn't active to abort */ + return BLK_EH_NOT_HANDLED; /* * we can't individually ABTS an io without affecting the queue, @@ -1920,7 +1921,12 @@ nvme_fc_timeout(struct request *rq, bool reserved) */ nvme_fc_error_recovery(ctrl, "io timeout error"); - return BLK_EH_HANDLED; + /* + * the io abort has been initiated. Have the reset timer + * restarted and the abort completion will complete the io + * shortly. Avoids a synchronous wait while the abort finishes. + */ + return BLK_EH_RESET_TIMER; } static int -- cgit v1.2.3 From d22524a4782a943bb02a9cf6885ac470210aabfc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 18 Oct 2017 13:25:42 +0200 Subject: nvme: switch controller refcounting to use struct device Instead of allocating a separate struct device for the character device handle embedd it into struct nvme_ctrl and use it for the main controller refcounting. This removes double refcounting and gets us an automatic reference for the character device operations. We keep ctrl->device as a pointer for now to avoid chaning printks all over, but in the future we could look into message printing helpers that take a controller structure similar to what other subsystems do. Note the delete_ctrl operation always already has a reference (either through sysfs due this change, or because every open file on the /dev/nvme-fabrics node has a refernece) when it is entered now, so we don't need to do the unless_zero variant there. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke --- drivers/nvme/host/core.c | 43 ++++++++++++++++++++++--------------------- drivers/nvme/host/fc.c | 8 ++------ drivers/nvme/host/nvme.h | 12 +++++++++++- drivers/nvme/host/pci.c | 2 +- drivers/nvme/host/rdma.c | 5 ++--- drivers/nvme/target/loop.c | 2 +- 6 files changed, 39 insertions(+), 33 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 9f8ae15c9fe8..3a97daa163f6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1915,7 +1915,7 @@ static int nvme_dev_open(struct inode *inode, struct file *file) ret = -EWOULDBLOCK; break; } - if (!kref_get_unless_zero(&ctrl->kref)) + if (!kobject_get_unless_zero(&ctrl->device->kobj)) break; file->private_data = ctrl; ret = 0; @@ -2374,7 +2374,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) list_add_tail(&ns->list, &ctrl->namespaces); mutex_unlock(&ctrl->namespaces_mutex); - kref_get(&ctrl->kref); + nvme_get_ctrl(ctrl); kfree(id); @@ -2703,7 +2703,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl); void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) { - device_destroy(nvme_class, MKDEV(nvme_char_major, ctrl->instance)); + device_del(ctrl->device); spin_lock(&dev_list_lock); list_del(&ctrl->node); @@ -2711,23 +2711,17 @@ void nvme_uninit_ctrl(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_uninit_ctrl); -static void nvme_free_ctrl(struct kref *kref) +static void nvme_free_ctrl(struct device *dev) { - struct nvme_ctrl *ctrl = container_of(kref, struct nvme_ctrl, kref); + struct nvme_ctrl *ctrl = + container_of(dev, struct nvme_ctrl, ctrl_device); - put_device(ctrl->device); ida_simple_remove(&nvme_instance_ida, ctrl->instance); ida_destroy(&ctrl->ns_ida); ctrl->ops->free_ctrl(ctrl); } -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 * earliest initialization so that we have the initialized structured around @@ -2742,7 +2736,6 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, spin_lock_init(&ctrl->lock); INIT_LIST_HEAD(&ctrl->namespaces); mutex_init(&ctrl->namespaces_mutex); - kref_init(&ctrl->kref); ctrl->dev = dev; ctrl->ops = ops; ctrl->quirks = quirks; @@ -2755,15 +2748,21 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, goto out; ctrl->instance = ret; - ctrl->device = device_create_with_groups(nvme_class, ctrl->dev, - MKDEV(nvme_char_major, ctrl->instance), - ctrl, nvme_dev_attr_groups, - "nvme%d", ctrl->instance); - if (IS_ERR(ctrl->device)) { - ret = PTR_ERR(ctrl->device); + device_initialize(&ctrl->ctrl_device); + ctrl->device = &ctrl->ctrl_device; + ctrl->device->devt = MKDEV(nvme_char_major, ctrl->instance); + ctrl->device->class = nvme_class; + ctrl->device->parent = ctrl->dev; + ctrl->device->groups = nvme_dev_attr_groups; + ctrl->device->release = nvme_free_ctrl; + dev_set_drvdata(ctrl->device, ctrl); + ret = dev_set_name(ctrl->device, "nvme%d", ctrl->instance); + if (ret) goto out_release_instance; - } - get_device(ctrl->device); + ret = device_add(ctrl->device); + if (ret) + goto out_free_name; + ida_init(&ctrl->ns_ida); spin_lock(&dev_list_lock); @@ -2779,6 +2778,8 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, min(default_ps_max_latency_us, (unsigned long)S32_MAX)); return 0; +out_free_name: + kfree_const(dev->kobj.name); out_release_instance: ida_simple_remove(&nvme_instance_ida, ctrl->instance); out: diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index c6c903f1b172..aa9aec6923bb 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2692,14 +2692,10 @@ nvme_fc_del_nvme_ctrl(struct nvme_ctrl *nctrl) struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); int ret; - if (!kref_get_unless_zero(&ctrl->ctrl.kref)) - return -EBUSY; - + nvme_get_ctrl(&ctrl->ctrl); ret = __nvme_fc_del_ctrl(ctrl); - if (!ret) flush_workqueue(nvme_wq); - nvme_put_ctrl(&ctrl->ctrl); return ret; @@ -2918,7 +2914,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, return ERR_PTR(ret); } - kref_get(&ctrl->ctrl.kref); + nvme_get_ctrl(&ctrl->ctrl); dev_info(ctrl->ctrl.device, "NVME-FC{%d}: new ctrl: NQN \"%s\"\n", diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index cb9d93048f3d..ae60d8342e60 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -127,12 +127,12 @@ struct nvme_ctrl { struct request_queue *admin_q; struct request_queue *connect_q; struct device *dev; - struct kref kref; int instance; struct blk_mq_tag_set *tagset; struct blk_mq_tag_set *admin_tagset; struct list_head namespaces; struct mutex namespaces_mutex; + struct device ctrl_device; struct device *device; /* char device */ struct list_head node; struct ida ns_ida; @@ -279,6 +279,16 @@ static inline void nvme_end_request(struct request *req, __le16 status, blk_mq_complete_request(req); } +static inline void nvme_get_ctrl(struct nvme_ctrl *ctrl) +{ + get_device(ctrl->device); +} + +static inline void nvme_put_ctrl(struct nvme_ctrl *ctrl) +{ + put_device(ctrl->device); +} + void nvme_complete_rq(struct request *req); void nvme_cancel_request(struct request *req, void *data, bool reserved); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 11e6fd9d0ba4..7735571ffc9a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2292,7 +2292,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status) { dev_warn(dev->ctrl.device, "Removing after probe failure status: %d\n", status); - kref_get(&dev->ctrl.kref); + nvme_get_ctrl(&dev->ctrl); nvme_dev_disable(dev, false); if (!schedule_work(&dev->remove_work)) nvme_put_ctrl(&dev->ctrl); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 4552744eff45..62b58f9b7d00 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1793,8 +1793,7 @@ static int nvme_rdma_del_ctrl(struct nvme_ctrl *nctrl) * Keep a reference until all work is flushed since * __nvme_rdma_del_ctrl can free the ctrl mem */ - if (!kref_get_unless_zero(&ctrl->ctrl.kref)) - return -EBUSY; + nvme_get_ctrl(&ctrl->ctrl); ret = __nvme_rdma_del_ctrl(ctrl); if (!ret) flush_work(&ctrl->delete_work); @@ -1955,7 +1954,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n", ctrl->ctrl.opts->subsysnqn, &ctrl->addr); - kref_get(&ctrl->ctrl.kref); + nvme_get_ctrl(&ctrl->ctrl); mutex_lock(&nvme_rdma_ctrl_mutex); list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list); diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index c56354e1e4c6..f83e925fe64a 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -642,7 +642,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, dev_info(ctrl->ctrl.device, "new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn); - kref_get(&ctrl->ctrl.kref); + nvme_get_ctrl(&ctrl->ctrl); changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); WARN_ON_ONCE(!changed); -- cgit v1.2.3 From 56d5f4f108efd4e439d2320738e2b894af0920bb Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 20 Oct 2017 16:17:08 -0700 Subject: nvme-fc: add support for duplicate_connect option Adds support for the duplicate_connect option. When set to true, checks whether there's an existing controller via the same host port and target port for the same host (hostnqn, hostid) to the same subsystem. Fails the connection request if an existing controller. Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index aa9aec6923bb..d12775d12983 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2792,6 +2792,33 @@ static const struct blk_mq_ops nvme_fc_admin_mq_ops = { }; +/* + * Fails a controller request if it matches an existing controller + * (association) with the same tuple: + * + * + * The ports don't need to be compared as they are intrinsically + * already matched by the port pointers supplied. + */ +static bool +nvme_fc_existing_controller(struct nvme_fc_rport *rport, + struct nvmf_ctrl_options *opts) +{ + struct nvme_fc_ctrl *ctrl; + unsigned long flags; + bool found = false; + + spin_lock_irqsave(&rport->lock, flags); + list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) { + found = nvmf_ctlr_matches_baseopts(&ctrl->ctrl, opts); + if (found) + break; + } + spin_unlock_irqrestore(&rport->lock, flags); + + return found; +} + static struct nvme_ctrl * nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, struct nvme_fc_lport *lport, struct nvme_fc_rport *rport) @@ -2806,6 +2833,12 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, goto out_fail; } + if (!opts->duplicate_connect && + nvme_fc_existing_controller(rport, opts)) { + ret = -EALREADY; + goto out_fail; + } + ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); if (!ctrl) { ret = -ENOMEM; -- cgit v1.2.3 From ecad0d2cb8a7997afdc95031ee3328b997aba5c4 Mon Sep 17 00:00:00 2001 From: James Smart Date: Mon, 23 Oct 2017 15:11:36 -0700 Subject: nvme-fc: remove NVME_FC_MAX_SEGMENTS The define is an arbitrary limit to the io size on the initiator, capping the io to 1MB-4KB. Remove the define from the transport. I/O size will solely be limited by the LLDD sg limits. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 6 ++---- include/linux/nvme-fc-driver.h | 2 -- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index d12775d12983..b600c07803cf 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2435,7 +2435,6 @@ static int nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) { struct nvmf_ctrl_options *opts = ctrl->ctrl.opts; - u32 segs; int ret; bool changed; @@ -2486,9 +2485,8 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (ret) goto out_disconnect_admin_queue; - segs = min_t(u32, NVME_FC_MAX_SEGMENTS, - ctrl->lport->ops->max_sgl_segments); - ctrl->ctrl.max_hw_sectors = (segs - 1) << (PAGE_SHIFT - 9); + ctrl->ctrl.max_hw_sectors = + (ctrl->lport->ops->max_sgl_segments - 1) << (PAGE_SHIFT - 9); ret = nvme_init_identify(&ctrl->ctrl); if (ret) diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 4ea03b9a5c8c..2be4db353937 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -102,8 +102,6 @@ enum nvmefc_fcp_datadir { }; -#define NVME_FC_MAX_SEGMENTS 256 - /** * struct nvmefc_fcp_req - Request structure passed from NVME-FC transport * to LLDD in order to perform a NVME FCP IO operation. -- cgit v1.2.3 From 71c691fd06cc2625966620c93ce21bdcce32ed95 Mon Sep 17 00:00:00 2001 From: James Smart Date: Thu, 28 Sep 2017 09:56:31 -0700 Subject: nvme-fc: avoid workqueue flush stalls There's no need to wait for the full nvme_wq, which is now shared, to flush. flush only the delete_work item. Signed-off-by: James Smart Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index b600c07803cf..50cc17e99475 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2693,7 +2693,7 @@ nvme_fc_del_nvme_ctrl(struct nvme_ctrl *nctrl) nvme_get_ctrl(&ctrl->ctrl); ret = __nvme_fc_del_ctrl(ctrl); if (!ret) - flush_workqueue(nvme_wq); + flush_work(&ctrl->delete_work); nvme_put_ctrl(&ctrl->ctrl); return ret; -- cgit v1.2.3 From 29c09648734b94e42802f021658a47361169403b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 29 Oct 2017 10:44:28 +0200 Subject: nvme-fc: merge __nvme_fc_schedule_delete_work into __nvme_fc_del_ctrl No need to have two functions doing the same thing. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: James Smart Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 20 ++++++-------------- 1 file changed, 6 insertions(+), 14 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 50cc17e99475..827e9efbe556 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2663,22 +2663,14 @@ nvme_fc_delete_ctrl_work(struct work_struct *work) nvme_put_ctrl(&ctrl->ctrl); } -static bool -__nvme_fc_schedule_delete_work(struct nvme_fc_ctrl *ctrl) -{ - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) - return true; - - if (!queue_work(nvme_wq, &ctrl->delete_work)) - return true; - - return false; -} - static int __nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl) { - return __nvme_fc_schedule_delete_work(ctrl) ? -EBUSY : 0; + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) + return -EBUSY; + if (!queue_work(nvme_wq, &ctrl->delete_work)) + return -EBUSY; + return 0; } /* @@ -2724,7 +2716,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) "NVME-FC{%d}: Max reconnect attempts (%d) " "reached. Removing controller\n", ctrl->cnum, ctrl->ctrl.nr_reconnects); - WARN_ON(__nvme_fc_schedule_delete_work(ctrl)); + WARN_ON(__nvme_fc_del_ctrl(ctrl)); } } -- cgit v1.2.3 From c5017e85705bfea721732e153305d1988ff965c2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 29 Oct 2017 10:44:29 +0200 Subject: nvme: move controller deletion to common code Move the ->delete_work and the associated helpers to common code instead of duplicating them in every driver. This also adds the missing reference get/put for the loop driver. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: James Smart Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 38 ++++++++++++++++++++++++++++++++++- drivers/nvme/host/fabrics.c | 2 +- drivers/nvme/host/fc.c | 42 +++++---------------------------------- drivers/nvme/host/nvme.h | 5 ++++- drivers/nvme/host/rdma.c | 45 ++++++------------------------------------ drivers/nvme/target/loop.c | 48 +++++++++------------------------------------ 6 files changed, 62 insertions(+), 118 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index df525ab42fcd..d835ac05bbf7 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -97,6 +97,41 @@ static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) return ret; } +static void nvme_delete_ctrl_work(struct work_struct *work) +{ + struct nvme_ctrl *ctrl = + container_of(work, struct nvme_ctrl, delete_work); + + ctrl->ops->delete_ctrl(ctrl); +} + +int nvme_delete_ctrl(struct nvme_ctrl *ctrl) +{ + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING)) + return -EBUSY; + if (!queue_work(nvme_wq, &ctrl->delete_work)) + return -EBUSY; + return 0; +} +EXPORT_SYMBOL_GPL(nvme_delete_ctrl); + +int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl) +{ + int ret = 0; + + /* + * Keep a reference until the work is flushed since ->delete_ctrl + * can free the controller. + */ + nvme_get_ctrl(ctrl); + ret = nvme_delete_ctrl(ctrl); + if (!ret) + flush_work(&ctrl->delete_work); + nvme_put_ctrl(ctrl); + return ret; +} +EXPORT_SYMBOL_GPL(nvme_delete_ctrl_sync); + static blk_status_t nvme_error_status(struct request *req) { switch (nvme_req(req)->status & 0x7ff) { @@ -2122,7 +2157,7 @@ static ssize_t nvme_sysfs_delete(struct device *dev, struct nvme_ctrl *ctrl = dev_get_drvdata(dev); if (device_remove_file_self(dev, attr)) - ctrl->ops->delete_ctrl(ctrl); + nvme_delete_ctrl_sync(ctrl); return count; } static DEVICE_ATTR(delete_controller, S_IWUSR, NULL, nvme_sysfs_delete); @@ -2702,6 +2737,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, INIT_WORK(&ctrl->scan_work, nvme_scan_work); INIT_WORK(&ctrl->async_event_work, nvme_async_event_work); INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work); + INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work); ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL); if (ret < 0) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 4a83137b0268..a4967de5bb25 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -887,7 +887,7 @@ nvmf_create_ctrl(struct device *dev, const char *buf, size_t count) "controller returned incorrect NQN: \"%s\".\n", ctrl->subnqn); up_read(&nvmf_transports_rwsem); - ctrl->ops->delete_ctrl(ctrl); + nvme_delete_ctrl_sync(ctrl); return ERR_PTR(-EINVAL); } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 827e9efbe556..a7bdb17de29d 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -157,7 +157,6 @@ struct nvme_fc_ctrl { struct blk_mq_tag_set admin_tag_set; struct blk_mq_tag_set tag_set; - struct work_struct delete_work; struct delayed_work connect_work; struct kref ref; @@ -223,7 +222,6 @@ static struct device *fc_udev_device; /* *********************** FC-NVME Port Management ************************ */ -static int __nvme_fc_del_ctrl(struct nvme_fc_ctrl *); static void __nvme_fc_delete_hw_queue(struct nvme_fc_ctrl *, struct nvme_fc_queue *, unsigned int); @@ -662,7 +660,7 @@ nvme_fc_unregister_remoteport(struct nvme_fc_remote_port *portptr) /* tear down all associations to the remote port */ list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) - __nvme_fc_del_ctrl(ctrl); + nvme_delete_ctrl(&ctrl->ctrl); spin_unlock_irqrestore(&rport->lock, flags); @@ -2636,10 +2634,9 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) } static void -nvme_fc_delete_ctrl_work(struct work_struct *work) +nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) { - struct nvme_fc_ctrl *ctrl = - container_of(work, struct nvme_fc_ctrl, delete_work); + struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); cancel_work_sync(&ctrl->ctrl.reset_work); cancel_delayed_work_sync(&ctrl->connect_work); @@ -2663,34 +2660,6 @@ nvme_fc_delete_ctrl_work(struct work_struct *work) nvme_put_ctrl(&ctrl->ctrl); } -static int -__nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl) -{ - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) - return -EBUSY; - if (!queue_work(nvme_wq, &ctrl->delete_work)) - return -EBUSY; - return 0; -} - -/* - * Request from nvme core layer to delete the controller - */ -static int -nvme_fc_del_nvme_ctrl(struct nvme_ctrl *nctrl) -{ - struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); - int ret; - - nvme_get_ctrl(&ctrl->ctrl); - ret = __nvme_fc_del_ctrl(ctrl); - if (!ret) - flush_work(&ctrl->delete_work); - nvme_put_ctrl(&ctrl->ctrl); - - return ret; -} - static void nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) { @@ -2716,7 +2685,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) "NVME-FC{%d}: Max reconnect attempts (%d) " "reached. Removing controller\n", ctrl->cnum, ctrl->ctrl.nr_reconnects); - WARN_ON(__nvme_fc_del_ctrl(ctrl)); + WARN_ON(nvme_delete_ctrl(&ctrl->ctrl)); } } @@ -2748,7 +2717,7 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { .reg_write32 = nvmf_reg_write32, .free_ctrl = nvme_fc_nvme_ctrl_freed, .submit_async_event = nvme_fc_submit_async_event, - .delete_ctrl = nvme_fc_del_nvme_ctrl, + .delete_ctrl = nvme_fc_delete_ctrl, .get_address = nvmf_get_address, .reinit_request = nvme_fc_reinit_request, }; @@ -2851,7 +2820,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, get_device(ctrl->dev); kref_init(&ctrl->ref); - INIT_WORK(&ctrl->delete_work, nvme_fc_delete_ctrl_work); INIT_WORK(&ctrl->ctrl.reset_work, nvme_fc_reset_ctrl_work); INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work); spin_lock_init(&ctrl->lock); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 1bb2bc165e54..35d9cee515f1 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -138,6 +138,7 @@ struct nvme_ctrl { struct cdev cdev; struct ida ns_ida; struct work_struct reset_work; + struct work_struct delete_work; struct opal_dev *opal_dev; @@ -236,7 +237,7 @@ struct nvme_ctrl_ops { int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val); void (*free_ctrl)(struct nvme_ctrl *ctrl); void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx); - int (*delete_ctrl)(struct nvme_ctrl *ctrl); + void (*delete_ctrl)(struct nvme_ctrl *ctrl); int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size); int (*reinit_request)(void *data, struct request *rq); }; @@ -339,6 +340,8 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count); void nvme_start_keep_alive(struct nvme_ctrl *ctrl); void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); int nvme_reset_ctrl(struct nvme_ctrl *ctrl); +int nvme_delete_ctrl(struct nvme_ctrl *ctrl); +int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl); #ifdef CONFIG_NVM int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 32b0a9ef26e6..5175b465997d 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -105,7 +105,6 @@ struct nvme_rdma_ctrl { /* other member variables */ struct blk_mq_tag_set tag_set; - struct work_struct delete_work; struct work_struct err_work; struct nvme_rdma_qe async_event_sqe; @@ -913,7 +912,7 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl) ctrl->ctrl.opts->reconnect_delay * HZ); } else { dev_info(ctrl->ctrl.device, "Removing controller...\n"); - queue_work(nvme_wq, &ctrl->delete_work); + queue_work(nvme_wq, &ctrl->ctrl.delete_work); } } @@ -1764,41 +1763,10 @@ static void nvme_rdma_remove_ctrl(struct nvme_rdma_ctrl *ctrl) nvme_put_ctrl(&ctrl->ctrl); } -static void nvme_rdma_del_ctrl_work(struct work_struct *work) +static void nvme_rdma_delete_ctrl(struct nvme_ctrl *ctrl) { - struct nvme_rdma_ctrl *ctrl = container_of(work, - struct nvme_rdma_ctrl, delete_work); - - nvme_stop_ctrl(&ctrl->ctrl); - nvme_rdma_remove_ctrl(ctrl); -} - -static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl) -{ - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) - return -EBUSY; - - if (!queue_work(nvme_wq, &ctrl->delete_work)) - return -EBUSY; - - return 0; -} - -static int nvme_rdma_del_ctrl(struct nvme_ctrl *nctrl) -{ - struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); - int ret = 0; - - /* - * Keep a reference until all work is flushed since - * __nvme_rdma_del_ctrl can free the ctrl mem - */ - nvme_get_ctrl(&ctrl->ctrl); - ret = __nvme_rdma_del_ctrl(ctrl); - if (!ret) - flush_work(&ctrl->delete_work); - nvme_put_ctrl(&ctrl->ctrl); - return ret; + nvme_stop_ctrl(ctrl); + nvme_rdma_remove_ctrl(to_rdma_ctrl(ctrl)); } static void nvme_rdma_reset_ctrl_work(struct work_struct *work) @@ -1846,7 +1814,7 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { .reg_write32 = nvmf_reg_write32, .free_ctrl = nvme_rdma_free_ctrl, .submit_async_event = nvme_rdma_submit_async_event, - .delete_ctrl = nvme_rdma_del_ctrl, + .delete_ctrl = nvme_rdma_delete_ctrl, .get_address = nvmf_get_address, .reinit_request = nvme_rdma_reinit_request, }; @@ -1977,7 +1945,6 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, INIT_DELAYED_WORK(&ctrl->reconnect_work, nvme_rdma_reconnect_ctrl_work); INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work); - INIT_WORK(&ctrl->delete_work, nvme_rdma_del_ctrl_work); INIT_WORK(&ctrl->ctrl.reset_work, nvme_rdma_reset_ctrl_work); ctrl->ctrl.queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */ @@ -2081,7 +2048,7 @@ static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data) dev_info(ctrl->ctrl.device, "Removing ctrl: NQN \"%s\", addr %pISp\n", ctrl->ctrl.opts->subsysnqn, &ctrl->addr); - __nvme_rdma_del_ctrl(ctrl); + nvme_delete_ctrl(&ctrl->ctrl); } mutex_unlock(&nvme_rdma_ctrl_mutex); diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index f83e925fe64a..7f9f3fc3fb2a 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -53,7 +53,6 @@ struct nvme_loop_ctrl { struct nvme_ctrl ctrl; struct nvmet_ctrl *target_ctrl; - struct work_struct delete_work; }; static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl) @@ -439,41 +438,13 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl) nvme_loop_destroy_admin_queue(ctrl); } -static void nvme_loop_del_ctrl_work(struct work_struct *work) +static void nvme_loop_delete_ctrl_host(struct nvme_ctrl *ctrl) { - struct nvme_loop_ctrl *ctrl = container_of(work, - struct nvme_loop_ctrl, delete_work); - - nvme_stop_ctrl(&ctrl->ctrl); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_loop_shutdown_ctrl(ctrl); - nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); -} - -static int __nvme_loop_del_ctrl(struct nvme_loop_ctrl *ctrl) -{ - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) - return -EBUSY; - - if (!queue_work(nvme_wq, &ctrl->delete_work)) - return -EBUSY; - - return 0; -} - -static int nvme_loop_del_ctrl(struct nvme_ctrl *nctrl) -{ - struct nvme_loop_ctrl *ctrl = to_loop_ctrl(nctrl); - int ret; - - ret = __nvme_loop_del_ctrl(ctrl); - if (ret) - return ret; - - flush_work(&ctrl->delete_work); - - return 0; + nvme_stop_ctrl(ctrl); + nvme_remove_namespaces(ctrl); + nvme_loop_shutdown_ctrl(to_loop_ctrl(ctrl)); + nvme_uninit_ctrl(ctrl); + nvme_put_ctrl(ctrl); } static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl) @@ -483,7 +454,7 @@ static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl) mutex_lock(&nvme_loop_ctrl_mutex); list_for_each_entry(ctrl, &nvme_loop_ctrl_list, list) { if (ctrl->ctrl.cntlid == nctrl->cntlid) - __nvme_loop_del_ctrl(ctrl); + nvme_delete_ctrl(&ctrl->ctrl); } mutex_unlock(&nvme_loop_ctrl_mutex); } @@ -539,7 +510,7 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = { .reg_write32 = nvmf_reg_write32, .free_ctrl = nvme_loop_free_ctrl, .submit_async_event = nvme_loop_submit_async_event, - .delete_ctrl = nvme_loop_del_ctrl, + .delete_ctrl = nvme_loop_delete_ctrl_host, }; static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl) @@ -601,7 +572,6 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, ctrl->ctrl.opts = opts; INIT_LIST_HEAD(&ctrl->list); - INIT_WORK(&ctrl->delete_work, nvme_loop_del_ctrl_work); INIT_WORK(&ctrl->ctrl.reset_work, nvme_loop_reset_ctrl_work); ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops, @@ -731,7 +701,7 @@ static void __exit nvme_loop_cleanup_module(void) mutex_lock(&nvme_loop_ctrl_mutex); list_for_each_entry_safe(ctrl, next, &nvme_loop_ctrl_list, list) - __nvme_loop_del_ctrl(ctrl); + nvme_delete_ctrl(&ctrl->ctrl); mutex_unlock(&nvme_loop_ctrl_mutex); flush_workqueue(nvme_wq); -- cgit v1.2.3 From 6cd53d14aaa006b5543f06fbf5e1680ce61c6c6e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 29 Oct 2017 10:44:31 +0200 Subject: nvme: consolidate common code from ->reset_work No change in behavior except that the FC code cancels two work items a little later now. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: James Smart Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 4 ++++ drivers/nvme/host/fc.c | 13 ------------- drivers/nvme/host/rdma.c | 4 ---- drivers/nvme/target/loop.c | 4 ---- 4 files changed, 4 insertions(+), 21 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index d835ac05bbf7..4fa748c9a3f6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -102,7 +102,11 @@ static void nvme_delete_ctrl_work(struct work_struct *work) struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, delete_work); + nvme_stop_ctrl(ctrl); + nvme_remove_namespaces(ctrl); ctrl->ops->delete_ctrl(ctrl); + nvme_uninit_ctrl(ctrl); + nvme_put_ctrl(ctrl); } int nvme_delete_ctrl(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index a7bdb17de29d..e447b532b9ee 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2640,24 +2640,11 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) cancel_work_sync(&ctrl->ctrl.reset_work); cancel_delayed_work_sync(&ctrl->connect_work); - nvme_stop_ctrl(&ctrl->ctrl); - nvme_remove_namespaces(&ctrl->ctrl); /* * kill the association on the link side. this will block * waiting for io to terminate */ nvme_fc_delete_association(ctrl); - - /* - * tear down the controller - * After the last reference on the nvme ctrl is removed, - * the transport nvme_fc_nvme_ctrl_freed() callback will be - * invoked. From there, the transport will tear down it's - * logical queues and association. - */ - nvme_uninit_ctrl(&ctrl->ctrl); - - nvme_put_ctrl(&ctrl->ctrl); } static void diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index a3521b852ea8..ed6e05018a92 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1757,11 +1757,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown) static void nvme_rdma_delete_ctrl(struct nvme_ctrl *ctrl) { - nvme_stop_ctrl(ctrl); - nvme_remove_namespaces(ctrl); nvme_rdma_shutdown_ctrl(to_rdma_ctrl(ctrl), true); - nvme_uninit_ctrl(ctrl); - nvme_put_ctrl(ctrl); } static void nvme_rdma_reset_ctrl_work(struct work_struct *work) diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 7f9f3fc3fb2a..bc95c6ed531a 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -440,11 +440,7 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl) static void nvme_loop_delete_ctrl_host(struct nvme_ctrl *ctrl) { - nvme_stop_ctrl(ctrl); - nvme_remove_namespaces(ctrl); nvme_loop_shutdown_ctrl(to_loop_ctrl(ctrl)); - nvme_uninit_ctrl(ctrl); - nvme_put_ctrl(ctrl); } static void nvme_loop_delete_ctrl(struct nvmet_ctrl *nctrl) -- cgit v1.2.3 From 4054637c9b4fbe9feef0cf6f2516ef00d8053560 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Sun, 29 Oct 2017 14:21:02 +0200 Subject: nvme: flush reset_work before safely continuing with delete operation Prevent racing controller reset and delete flows. reset_work must not ever self-requeue so flushing it suffices. Reported-by: Christoph Hellwig Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 1 + drivers/nvme/host/fc.c | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 4fa748c9a3f6..003314eb6341 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -102,6 +102,7 @@ static void nvme_delete_ctrl_work(struct work_struct *work) struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, delete_work); + flush_work(&ctrl->reset_work); nvme_stop_ctrl(ctrl); nvme_remove_namespaces(ctrl); ctrl->ops->delete_ctrl(ctrl); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index e447b532b9ee..6a025a8d8c32 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2638,7 +2638,6 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) { struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); - cancel_work_sync(&ctrl->ctrl.reset_work); cancel_delayed_work_sync(&ctrl->connect_work); /* * kill the association on the link side. this will block -- cgit v1.2.3 From 44c6ec77e12c387aaba420b30a54b94966f0d9e8 Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 25 Oct 2017 16:43:14 -0700 Subject: nvme-fc: change ctlr state assignments during reset/reconnect Clean up some of the controller state checks and add the RESETTING->RECONNECTING state transition. Specifically: - the movement of the RESETTING state change and schedule of reset_work to core doesn't work wiht nvme_fc_error_recovery setting state to RECONNECTING before attempting to reset. Remove the state change as the reset request does it. - In the rare cases where an error occurs right as we're transitioning to LIVE, defer the controller start actions. - In error handling on teardown of associations while performing initial controller creation - avoid quiesce calls on the admin_q. They are unneeded. - Add the RESETTING->RECONNECTING transition in the reset handler. Signed-off-by: James Smart Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 6a025a8d8c32..e37c69f7921d 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1884,13 +1884,6 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: resetting controller\n", ctrl->cnum); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { - dev_err(ctrl->ctrl.device, - "NVME-FC{%d}: error_recovery: Couldn't change state " - "to RECONNECTING\n", ctrl->cnum); - return; - } - nvme_reset_ctrl(&ctrl->ctrl); } @@ -2528,11 +2521,11 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) } changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - WARN_ON_ONCE(!changed); ctrl->ctrl.nr_reconnects = 0; - nvme_start_ctrl(&ctrl->ctrl); + if (changed) + nvme_start_ctrl(&ctrl->ctrl); return 0; /* Success */ @@ -2600,7 +2593,8 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) * use blk_mq_tagset_busy_itr() and the transport routine to * terminate the exchanges. */ - blk_mq_quiesce_queue(ctrl->ctrl.admin_q); + if (ctrl->ctrl.state != NVME_CTRL_NEW) + blk_mq_quiesce_queue(ctrl->ctrl.admin_q); blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_fc_terminate_exchange, &ctrl->ctrl); @@ -2649,12 +2643,8 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) static void nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) { - /* If we are resetting/deleting then do nothing */ - if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) { - WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW || - ctrl->ctrl.state == NVME_CTRL_LIVE); + if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) return; - } dev_info(ctrl->ctrl.device, "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n", @@ -2683,9 +2673,17 @@ nvme_fc_reset_ctrl_work(struct work_struct *work) int ret; nvme_stop_ctrl(&ctrl->ctrl); + /* will block will waiting for io to terminate */ nvme_fc_delete_association(ctrl); + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) { + dev_err(ctrl->ctrl.device, + "NVME-FC{%d}: error_recovery: Couldn't change state " + "to RECONNECTING\n", ctrl->cnum); + return; + } + ret = nvme_fc_create_association(ctrl); if (ret) nvme_fc_reconnect_or_delete(ctrl, ret); -- cgit v1.2.3 From ac7fe82b6fcf77e757e88005c33b8147c1b7b73f Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 25 Oct 2017 16:43:15 -0700 Subject: nvme-fc: add a dev_loss_tmo field to the remoteport Add a dev_loss_tmo value, paralleling the SCSI FC transport, for device connectivity loss. The transport initializes the value in the nvme_fc_register_remoteport() call. If the value is not set, a default of 60s is set. Add a new routine to the api, nvme_fc_set_remoteport_devloss() routine, which allows the lldd to dynamically update the value on an existing remoteport. Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 31 +++++++++++++++++++++++++++++++ include/linux/nvme-fc-driver.h | 11 +++++++++-- 2 files changed, 40 insertions(+), 2 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index e37c69f7921d..25479d3031fa 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -45,6 +45,8 @@ enum nvme_fc_queue_flags { #define NVMEFC_QUEUE_DELAY 3 /* ms units */ +#define NVME_FC_DEFAULT_DEV_LOSS_TMO 60 /* seconds */ + struct nvme_fc_queue { struct nvme_fc_ctrl *ctrl; struct device *dev; @@ -585,6 +587,11 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport, newrec->remoteport.port_id = pinfo->port_id; newrec->remoteport.port_state = FC_OBJSTATE_ONLINE; newrec->remoteport.port_num = idx; + /* a registration value of dev_loss_tmo=0 results in the default */ + if (pinfo->dev_loss_tmo) + newrec->remoteport.dev_loss_tmo = pinfo->dev_loss_tmo; + else + newrec->remoteport.dev_loss_tmo = NVME_FC_DEFAULT_DEV_LOSS_TMO; spin_lock_irqsave(&nvme_fc_lock, flags); list_add_tail(&newrec->endp_list, &lport->endp_list); @@ -688,6 +695,30 @@ nvme_fc_rescan_remoteport(struct nvme_fc_remote_port *remoteport) } EXPORT_SYMBOL_GPL(nvme_fc_rescan_remoteport); +int +nvme_fc_set_remoteport_devloss(struct nvme_fc_remote_port *portptr, + u32 dev_loss_tmo) +{ + struct nvme_fc_rport *rport = remoteport_to_rport(portptr); + struct nvme_fc_ctrl *ctrl; + unsigned long flags; + + spin_lock_irqsave(&rport->lock, flags); + + if (portptr->port_state != FC_OBJSTATE_ONLINE) { + spin_unlock_irqrestore(&rport->lock, flags); + return -EINVAL; + } + + /* a dev_loss_tmo of 0 (immediate) is allowed to be set */ + rport->remoteport.dev_loss_tmo = dev_loss_tmo; + + spin_unlock_irqrestore(&rport->lock, flags); + + return 0; +} +EXPORT_SYMBOL_GPL(nvme_fc_set_remoteport_devloss); + /* *********************** FC-NVME DMA Handling **************************** */ diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 2be4db353937..496ff759f84c 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -40,6 +40,8 @@ * @node_name: FC WWNN for the port * @port_name: FC WWPN for the port * @port_role: What NVME roles are supported (see FC_PORT_ROLE_xxx) + * @dev_loss_tmo: maximum delay for reconnects to an association on + * this device. Used only on a remoteport. * * Initialization values for dynamic port fields: * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must @@ -50,6 +52,7 @@ struct nvme_fc_port_info { u64 port_name; u32 port_role; u32 port_id; + u32 dev_loss_tmo; }; @@ -200,6 +203,9 @@ enum nvme_fc_obj_state { * The length of the buffer corresponds to the local_priv_sz * value specified in the nvme_fc_port_template supplied by * the LLDD. + * @dev_loss_tmo: maximum delay for reconnects to an association on + * this device. To modify, lldd must call + * nvme_fc_set_remoteport_devloss(). * * Fields with dynamic values. Values may change base on link state. LLDD * may reference fields directly to change them. Initialized by the @@ -257,10 +263,9 @@ struct nvme_fc_remote_port { u32 port_role; u64 node_name; u64 port_name; - struct nvme_fc_local_port *localport; - void *private; + u32 dev_loss_tmo; /* dynamic fields */ u32 port_id; @@ -446,6 +451,8 @@ int nvme_fc_unregister_remoteport(struct nvme_fc_remote_port *remoteport); void nvme_fc_rescan_remoteport(struct nvme_fc_remote_port *remoteport); +int nvme_fc_set_remoteport_devloss(struct nvme_fc_remote_port *remoteport, + u32 dev_loss_tmo); /* -- cgit v1.2.3 From 96e24801056467c6483f68ef71d642fb925c3100 Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 25 Oct 2017 16:43:16 -0700 Subject: nvme-fc: check connectivity before initiating reconnects Check remoteport connectivity before initiating reconnects Signed-off-by: James Smart Reviewed-by: Johannes Thumshirn Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 25479d3031fa..b64cc1002452 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -808,7 +808,6 @@ fc_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, dma_unmap_sg(dev, sg, nents, dir); } - /* *********************** FC-NVME LS Handling **************************** */ static void nvme_fc_ctrl_put(struct nvme_fc_ctrl *); @@ -2462,6 +2461,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) ++ctrl->ctrl.nr_reconnects; + if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE) + return -ENODEV; + /* * Create the admin queue */ @@ -2682,6 +2684,10 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) ctrl->cnum, status); if (nvmf_should_reconnect(&ctrl->ctrl)) { + /* Only schedule the reconnect if the remote port is online */ + if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE) + return; + dev_info(ctrl->ctrl.device, "NVME-FC{%d}: Reconnect attempt in %d seconds.\n", ctrl->cnum, ctrl->ctrl.opts->reconnect_delay); @@ -2715,12 +2721,15 @@ nvme_fc_reset_ctrl_work(struct work_struct *work) return; } - ret = nvme_fc_create_association(ctrl); - if (ret) - nvme_fc_reconnect_or_delete(ctrl, ret); - else - dev_info(ctrl->ctrl.device, - "NVME-FC{%d}: controller reset complete\n", ctrl->cnum); + if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE) { + ret = nvme_fc_create_association(ctrl); + if (ret) + nvme_fc_reconnect_or_delete(ctrl, ret); + else + dev_info(ctrl->ctrl.device, + "NVME-FC{%d}: controller reset complete\n", + ctrl->cnum); + } } static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { -- cgit v1.2.3 From 2b632970da4f288e6dbdc826c34fbf74f40ec94c Mon Sep 17 00:00:00 2001 From: James Smart Date: Wed, 25 Oct 2017 16:43:17 -0700 Subject: nvme-fc: add dev_loss_tmo timeout and remoteport resume support When a remoteport is unregistered (connectivity lost), the following actions are taken: - the remoteport is marked DELETED - the time when dev_loss_tmo would expire is set in the remoteport - all controllers on the remoteport are reset. After a controller resets, it will stall in a RECONNECTING state waiting for one of the following: - the controller will continue to attempt reconnect per max_retries and reconnect_delay. As no remoteport connectivity, the reconnect attempt will immediately fail. If max reconnects has not been reached, a new reconnect_delay timer will be schedule. If the current time plus another reconnect_delay exceeds when dev_loss_tmo expires on the remote port, then the reconnect_delay will be shortend to schedule no later than when dev_loss_tmo expires. If max reconnect attempts are reached (e.g. ctrl_loss_tmo reached) or dev_loss_tmo ix exceeded without connectivity, the controller is deleted. - the remoteport is re-registered prior to dev_loss_tmo expiring. The resume of the remoteport will immediately attempt to reconnect each of its suspended controllers. Signed-off-by: James Smart Reviewed-by: Hannes Reinecke [hch: updated to use nvme_delete_ctrl] Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 278 ++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 239 insertions(+), 39 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index b64cc1002452..113c30be7276 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -138,6 +138,7 @@ struct nvme_fc_rport { struct nvme_fc_lport *lport; spinlock_t lock; struct kref ref; + unsigned long dev_loss_end; } __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ enum nvme_fcctrl_flags { @@ -528,6 +529,102 @@ nvme_fc_rport_get(struct nvme_fc_rport *rport) return kref_get_unless_zero(&rport->ref); } +static void +nvme_fc_resume_controller(struct nvme_fc_ctrl *ctrl) +{ + switch (ctrl->ctrl.state) { + case NVME_CTRL_NEW: + case NVME_CTRL_RECONNECTING: + /* + * As all reconnects were suppressed, schedule a + * connect. + */ + dev_info(ctrl->ctrl.device, + "NVME-FC{%d}: connectivity re-established. " + "Attempting reconnect\n", ctrl->cnum); + + queue_delayed_work(nvme_wq, &ctrl->connect_work, 0); + break; + + case NVME_CTRL_RESETTING: + /* + * Controller is already in the process of terminating the + * association. No need to do anything further. The reconnect + * step will naturally occur after the reset completes. + */ + break; + + default: + /* no action to take - let it delete */ + break; + } +} + +static struct nvme_fc_rport * +nvme_fc_attach_to_suspended_rport(struct nvme_fc_lport *lport, + struct nvme_fc_port_info *pinfo) +{ + struct nvme_fc_rport *rport; + struct nvme_fc_ctrl *ctrl; + unsigned long flags; + + spin_lock_irqsave(&nvme_fc_lock, flags); + + list_for_each_entry(rport, &lport->endp_list, endp_list) { + if (rport->remoteport.node_name != pinfo->node_name || + rport->remoteport.port_name != pinfo->port_name) + continue; + + if (!nvme_fc_rport_get(rport)) { + rport = ERR_PTR(-ENOLCK); + goto out_done; + } + + spin_unlock_irqrestore(&nvme_fc_lock, flags); + + spin_lock_irqsave(&rport->lock, flags); + + /* has it been unregistered */ + if (rport->remoteport.port_state != FC_OBJSTATE_DELETED) { + /* means lldd called us twice */ + spin_unlock_irqrestore(&rport->lock, flags); + nvme_fc_rport_put(rport); + return ERR_PTR(-ESTALE); + } + + rport->remoteport.port_state = FC_OBJSTATE_ONLINE; + rport->dev_loss_end = 0; + + /* + * kick off a reconnect attempt on all associations to the + * remote port. A successful reconnects will resume i/o. + */ + list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) + nvme_fc_resume_controller(ctrl); + + spin_unlock_irqrestore(&rport->lock, flags); + + return rport; + } + + rport = NULL; + +out_done: + spin_unlock_irqrestore(&nvme_fc_lock, flags); + + return rport; +} + +static inline void +__nvme_fc_set_dev_loss_tmo(struct nvme_fc_rport *rport, + struct nvme_fc_port_info *pinfo) +{ + if (pinfo->dev_loss_tmo) + rport->remoteport.dev_loss_tmo = pinfo->dev_loss_tmo; + else + rport->remoteport.dev_loss_tmo = NVME_FC_DEFAULT_DEV_LOSS_TMO; +} + /** * nvme_fc_register_remoteport - transport entry point called by an * LLDD to register the existence of a NVME @@ -554,22 +651,45 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport, unsigned long flags; int ret, idx; + if (!nvme_fc_lport_get(lport)) { + ret = -ESHUTDOWN; + goto out_reghost_failed; + } + + /* + * look to see if there is already a remoteport that is waiting + * for a reconnect (within dev_loss_tmo) with the same WWN's. + * If so, transition to it and reconnect. + */ + newrec = nvme_fc_attach_to_suspended_rport(lport, pinfo); + + /* found an rport, but something about its state is bad */ + if (IS_ERR(newrec)) { + ret = PTR_ERR(newrec); + goto out_lport_put; + + /* found existing rport, which was resumed */ + } else if (newrec) { + nvme_fc_lport_put(lport); + __nvme_fc_set_dev_loss_tmo(newrec, pinfo); + nvme_fc_signal_discovery_scan(lport, newrec); + *portptr = &newrec->remoteport; + return 0; + } + + /* nothing found - allocate a new remoteport struct */ + newrec = kmalloc((sizeof(*newrec) + lport->ops->remote_priv_sz), GFP_KERNEL); if (!newrec) { ret = -ENOMEM; - goto out_reghost_failed; - } - - if (!nvme_fc_lport_get(lport)) { - ret = -ESHUTDOWN; - goto out_kfree_rport; + goto out_lport_put; } idx = ida_simple_get(&lport->endp_cnt, 0, 0, GFP_KERNEL); if (idx < 0) { ret = -ENOSPC; - goto out_lport_put; + goto out_kfree_rport; } INIT_LIST_HEAD(&newrec->endp_list); @@ -587,11 +707,7 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport, newrec->remoteport.port_id = pinfo->port_id; newrec->remoteport.port_state = FC_OBJSTATE_ONLINE; newrec->remoteport.port_num = idx; - /* a registration value of dev_loss_tmo=0 results in the default */ - if (pinfo->dev_loss_tmo) - newrec->remoteport.dev_loss_tmo = pinfo->dev_loss_tmo; - else - newrec->remoteport.dev_loss_tmo = NVME_FC_DEFAULT_DEV_LOSS_TMO; + __nvme_fc_set_dev_loss_tmo(newrec, pinfo); spin_lock_irqsave(&nvme_fc_lock, flags); list_add_tail(&newrec->endp_list, &lport->endp_list); @@ -602,10 +718,10 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport, *portptr = &newrec->remoteport; return 0; -out_lport_put: - nvme_fc_lport_put(lport); out_kfree_rport: kfree(newrec); +out_lport_put: + nvme_fc_lport_put(lport); out_reghost_failed: *portptr = NULL; return ret; @@ -636,6 +752,58 @@ restart: return 0; } +static void +nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl) +{ + dev_info(ctrl->ctrl.device, + "NVME-FC{%d}: controller connectivity lost. Awaiting " + "Reconnect", ctrl->cnum); + + switch (ctrl->ctrl.state) { + case NVME_CTRL_NEW: + case NVME_CTRL_LIVE: + /* + * Schedule a controller reset. The reset will terminate the + * association and schedule the reconnect timer. Reconnects + * will be attempted until either the ctlr_loss_tmo + * (max_retries * connect_delay) expires or the remoteport's + * dev_loss_tmo expires. + */ + if (nvme_reset_ctrl(&ctrl->ctrl)) { + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: Couldn't schedule reset. " + "Deleting controller.\n", + ctrl->cnum); + nvme_delete_ctrl(&ctrl->ctrl); + } + break; + + case NVME_CTRL_RECONNECTING: + /* + * The association has already been terminated and the + * controller is attempting reconnects. No need to do anything + * futher. Reconnects will be attempted until either the + * ctlr_loss_tmo (max_retries * connect_delay) expires or the + * remoteport's dev_loss_tmo expires. + */ + break; + + case NVME_CTRL_RESETTING: + /* + * Controller is already in the process of terminating the + * association. No need to do anything further. The reconnect + * step will kick in naturally after the association is + * terminated. + */ + break; + + case NVME_CTRL_DELETING: + default: + /* no action to take - let it delete */ + break; + } +} + /** * nvme_fc_unregister_remoteport - transport entry point called by an * LLDD to deregister/remove a previously @@ -665,15 +833,31 @@ nvme_fc_unregister_remoteport(struct nvme_fc_remote_port *portptr) } portptr->port_state = FC_OBJSTATE_DELETED; - /* tear down all associations to the remote port */ - list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) - nvme_delete_ctrl(&ctrl->ctrl); + rport->dev_loss_end = jiffies + (portptr->dev_loss_tmo * HZ); + + list_for_each_entry(ctrl, &rport->ctrl_list, ctrl_list) { + /* if dev_loss_tmo==0, dev loss is immediate */ + if (!portptr->dev_loss_tmo) { + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: controller connectivity lost. " + "Deleting controller.\n", + ctrl->cnum); + nvme_delete_ctrl(&ctrl->ctrl); + } else + nvme_fc_ctrl_connectivity_loss(ctrl); + } spin_unlock_irqrestore(&rport->lock, flags); nvme_fc_abort_lsops(rport); + /* + * release the reference, which will allow, if all controllers + * go away, which should only occur after dev_loss_tmo occurs, + * for the rport to be torn down. + */ nvme_fc_rport_put(rport); + return 0; } EXPORT_SYMBOL_GPL(nvme_fc_unregister_remoteport); @@ -700,7 +884,6 @@ nvme_fc_set_remoteport_devloss(struct nvme_fc_remote_port *portptr, u32 dev_loss_tmo) { struct nvme_fc_rport *rport = remoteport_to_rport(portptr); - struct nvme_fc_ctrl *ctrl; unsigned long flags; spin_lock_irqsave(&rport->lock, flags); @@ -2676,28 +2859,43 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) static void nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status) { + struct nvme_fc_rport *rport = ctrl->rport; + struct nvme_fc_remote_port *portptr = &rport->remoteport; + unsigned long recon_delay = ctrl->ctrl.opts->reconnect_delay * HZ; + bool recon = true; + if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) return; - dev_info(ctrl->ctrl.device, - "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n", - ctrl->cnum, status); + if (portptr->port_state == FC_OBJSTATE_ONLINE) + dev_info(ctrl->ctrl.device, + "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n", + ctrl->cnum, status); + else if (time_after_eq(jiffies, rport->dev_loss_end)) + recon = false; - if (nvmf_should_reconnect(&ctrl->ctrl)) { - /* Only schedule the reconnect if the remote port is online */ - if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE) - return; + if (recon && nvmf_should_reconnect(&ctrl->ctrl)) { + if (portptr->port_state == FC_OBJSTATE_ONLINE) + dev_info(ctrl->ctrl.device, + "NVME-FC{%d}: Reconnect attempt in %ld " + "seconds\n", + ctrl->cnum, recon_delay / HZ); + else if (time_after(jiffies + recon_delay, rport->dev_loss_end)) + recon_delay = rport->dev_loss_end - jiffies; - dev_info(ctrl->ctrl.device, - "NVME-FC{%d}: Reconnect attempt in %d seconds.\n", - ctrl->cnum, ctrl->ctrl.opts->reconnect_delay); - queue_delayed_work(nvme_wq, &ctrl->connect_work, - ctrl->ctrl.opts->reconnect_delay * HZ); + queue_delayed_work(nvme_wq, &ctrl->connect_work, recon_delay); } else { - dev_warn(ctrl->ctrl.device, + if (portptr->port_state == FC_OBJSTATE_ONLINE) + dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: Max reconnect attempts (%d) " "reached. Removing controller\n", ctrl->cnum, ctrl->ctrl.nr_reconnects); + else + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: dev_loss_tmo (%d) expired " + "while waiting for remoteport connectivity. " + "Removing controller\n", ctrl->cnum, + portptr->dev_loss_tmo); WARN_ON(nvme_delete_ctrl(&ctrl->ctrl)); } } @@ -2721,15 +2919,17 @@ nvme_fc_reset_ctrl_work(struct work_struct *work) return; } - if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE) { + if (ctrl->rport->remoteport.port_state == FC_OBJSTATE_ONLINE) ret = nvme_fc_create_association(ctrl); - if (ret) - nvme_fc_reconnect_or_delete(ctrl, ret); - else - dev_info(ctrl->ctrl.device, - "NVME-FC{%d}: controller reset complete\n", - ctrl->cnum); - } + else + ret = -ENOTCONN; + + if (ret) + nvme_fc_reconnect_or_delete(ctrl, ret); + else + dev_info(ctrl->ctrl.device, + "NVME-FC{%d}: controller reset complete\n", + ctrl->cnum); } static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = { -- cgit v1.2.3 From c5760f300e25f7d2cea9a9002b1e058a5c18b73f Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 3 Nov 2017 08:13:16 -0700 Subject: nvme-fc: fix localport resume using stale values The localport resume was not updating the lldd ops structure. If the lldd is unloaded and reloaded, the ops pointers will differ. Additionally, as there are device references taken by the localport, ensure that resume only resumes if the device matches as well. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/fc.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 113c30be7276..c49971d1a051 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -268,7 +268,9 @@ nvme_fc_lport_get(struct nvme_fc_lport *lport) static struct nvme_fc_lport * -nvme_fc_attach_to_unreg_lport(struct nvme_fc_port_info *pinfo) +nvme_fc_attach_to_unreg_lport(struct nvme_fc_port_info *pinfo, + struct nvme_fc_port_template *ops, + struct device *dev) { struct nvme_fc_lport *lport; unsigned long flags; @@ -280,6 +282,11 @@ nvme_fc_attach_to_unreg_lport(struct nvme_fc_port_info *pinfo) lport->localport.port_name != pinfo->port_name) continue; + if (lport->dev != dev) { + lport = ERR_PTR(-EXDEV); + goto out_done; + } + if (lport->localport.port_state != FC_OBJSTATE_DELETED) { lport = ERR_PTR(-EEXIST); goto out_done; @@ -296,6 +303,7 @@ nvme_fc_attach_to_unreg_lport(struct nvme_fc_port_info *pinfo) /* resume the lport */ + lport->ops = ops; lport->localport.port_role = pinfo->port_role; lport->localport.port_id = pinfo->port_id; lport->localport.port_state = FC_OBJSTATE_ONLINE; @@ -356,7 +364,7 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, * expired, we can simply re-enable the localport. Remoteports * and controller reconnections should resume naturally. */ - newrec = nvme_fc_attach_to_unreg_lport(pinfo); + newrec = nvme_fc_attach_to_unreg_lport(pinfo, template, dev); /* found an lport, but something about its state is bad */ if (IS_ERR(newrec)) { -- cgit v1.2.3 From 158bfb8888c3f2beab747ab4f7a8197639f03e54 Mon Sep 17 00:00:00 2001 From: James Smart Date: Fri, 3 Nov 2017 08:13:17 -0700 Subject: nvme-fc: decouple ns references from lldd references In the lldd api, a lldd may unregister a remoteport (loss of connectivity or driver unload) or localport (driver unload). The lldd must wait for the remoteport_delete or localport_delete before completing its actions post the unregister. The xxx_deletes currently occur only when the xxxport structure is fully freed after all references are removed. Thus the lldd may be held hostage until an app or in-kernel entity that has a namespace open finally closes so the namespace can be removed, the controller removed, thus the transport objects, thus the lldd. This patch decouples the transport and os-facing objects from the lldd and the remoteport and localport. There is a point in all deletions where the transport will no longer interact with the lldd on behalf of a controller. That point centers around the association established with the target/subsystem. It will access the lldd whenever it attempts to create an association and while the association is active. New associations may only be created if the remoteport is live (thus the localport is live). It will not access the lldd after deleting the association. Therefore, the patch tracks the count of active controllers - those with associations being created or that are active - on a remoteport. It also tracks the number of remoteports that have active controllers, on a a localport. When a remoteport is unregistered, as soon as there are no active controllers, the lldd's remoteport_delete may be called and the lldd may continue. Similarly, when a localport is unregistered, as soon as there are no remoteports with active controllers, the localport_delete callback may be made. This significantly speeds up unregistration with the lldd. The transport objects continue in suspended status with reconnect timers running, and upon expiration, normal ref-counting will occur and the objects will be freed. The transport object may still be held hostage by the application/kernel module, but that is acceptable. With this change, the lldd may be fully unloaded and reloaded, and if registrations occur prior to the timeouts, the nvme controller and namespaces will resume normally as if a link bounce. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/fc.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 78 insertions(+), 6 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index c49971d1a051..da9296a1eb26 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -126,6 +126,7 @@ struct nvme_fc_lport { struct device *dev; /* physical device for dma */ struct nvme_fc_port_template *ops; struct kref ref; + atomic_t act_rport_cnt; } __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ struct nvme_fc_rport { @@ -138,6 +139,7 @@ struct nvme_fc_rport { struct nvme_fc_lport *lport; spinlock_t lock; struct kref ref; + atomic_t act_ctrl_cnt; unsigned long dev_loss_end; } __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ @@ -153,6 +155,7 @@ struct nvme_fc_ctrl { struct nvme_fc_rport *rport; u32 cnum; + bool assoc_active; u64 association_id; struct list_head ctrl_list; /* rport->ctrl_list */ @@ -243,9 +246,6 @@ nvme_fc_free_lport(struct kref *ref) list_del(&lport->port_list); spin_unlock_irqrestore(&nvme_fc_lock, flags); - /* let the LLDD know we've finished tearing it down */ - lport->ops->localport_delete(&lport->localport); - ida_simple_remove(&nvme_fc_local_port_cnt, lport->localport.port_num); ida_destroy(&lport->endp_cnt); @@ -400,6 +400,7 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, INIT_LIST_HEAD(&newrec->port_list); INIT_LIST_HEAD(&newrec->endp_list); kref_init(&newrec->ref); + atomic_set(&newrec->act_rport_cnt, 0); newrec->ops = template; newrec->dev = dev; ida_init(&newrec->endp_cnt); @@ -462,6 +463,9 @@ nvme_fc_unregister_localport(struct nvme_fc_local_port *portptr) spin_unlock_irqrestore(&nvme_fc_lock, flags); + if (atomic_read(&lport->act_rport_cnt) == 0) + lport->ops->localport_delete(&lport->localport); + nvme_fc_lport_put(lport); return 0; @@ -515,9 +519,6 @@ nvme_fc_free_rport(struct kref *ref) list_del(&rport->endp_list); spin_unlock_irqrestore(&nvme_fc_lock, flags); - /* let the LLDD know we've finished tearing it down */ - lport->ops->remoteport_delete(&rport->remoteport); - ida_simple_remove(&lport->endp_cnt, rport->remoteport.port_num); kfree(rport); @@ -704,6 +705,7 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport, INIT_LIST_HEAD(&newrec->ctrl_list); INIT_LIST_HEAD(&newrec->ls_req_list); kref_init(&newrec->ref); + atomic_set(&newrec->act_ctrl_cnt, 0); spin_lock_init(&newrec->lock); newrec->remoteport.localport = &lport->localport; newrec->dev = lport->dev; @@ -859,6 +861,9 @@ nvme_fc_unregister_remoteport(struct nvme_fc_remote_port *portptr) nvme_fc_abort_lsops(rport); + if (atomic_read(&rport->act_ctrl_cnt) == 0) + rport->lport->ops->remoteport_delete(portptr); + /* * release the reference, which will allow, if all controllers * go away, which should only occur after dev_loss_tmo occurs, @@ -2639,6 +2644,61 @@ out_free_io_queues: return ret; } +static void +nvme_fc_rport_active_on_lport(struct nvme_fc_rport *rport) +{ + struct nvme_fc_lport *lport = rport->lport; + + atomic_inc(&lport->act_rport_cnt); +} + +static void +nvme_fc_rport_inactive_on_lport(struct nvme_fc_rport *rport) +{ + struct nvme_fc_lport *lport = rport->lport; + u32 cnt; + + cnt = atomic_dec_return(&lport->act_rport_cnt); + if (cnt == 0 && lport->localport.port_state == FC_OBJSTATE_DELETED) + lport->ops->localport_delete(&lport->localport); +} + +static int +nvme_fc_ctlr_active_on_rport(struct nvme_fc_ctrl *ctrl) +{ + struct nvme_fc_rport *rport = ctrl->rport; + u32 cnt; + + if (ctrl->assoc_active) + return 1; + + ctrl->assoc_active = true; + cnt = atomic_inc_return(&rport->act_ctrl_cnt); + if (cnt == 1) + nvme_fc_rport_active_on_lport(rport); + + return 0; +} + +static int +nvme_fc_ctlr_inactive_on_rport(struct nvme_fc_ctrl *ctrl) +{ + struct nvme_fc_rport *rport = ctrl->rport; + struct nvme_fc_lport *lport = rport->lport; + u32 cnt; + + /* ctrl->assoc_active=false will be set independently */ + + cnt = atomic_dec_return(&rport->act_ctrl_cnt); + if (cnt == 0) { + if (rport->remoteport.port_state == FC_OBJSTATE_DELETED) + lport->ops->remoteport_delete(&rport->remoteport); + nvme_fc_rport_inactive_on_lport(rport); + } + + return 0; +} + /* * This routine restarts the controller on the host side, and * on the link side, recreates the controller association. @@ -2655,6 +2715,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE) return -ENODEV; + if (nvme_fc_ctlr_active_on_rport(ctrl)) + return -ENOTUNIQ; + /* * Create the admin queue */ @@ -2762,6 +2825,8 @@ out_delete_hw_queue: __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0); out_free_queue: nvme_fc_free_queue(&ctrl->queues[0]); + ctrl->assoc_active = false; + nvme_fc_ctlr_inactive_on_rport(ctrl); return ret; } @@ -2777,6 +2842,10 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) { unsigned long flags; + if (!ctrl->assoc_active) + return; + ctrl->assoc_active = false; + spin_lock_irqsave(&ctrl->lock, flags); ctrl->flags |= FCCTRL_TERMIO; ctrl->iocnt = 0; @@ -2849,6 +2918,8 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl) __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0); nvme_fc_free_queue(&ctrl->queues[0]); + + nvme_fc_ctlr_inactive_on_rport(ctrl); } static void @@ -3048,6 +3119,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ctrl->rport = rport; ctrl->dev = lport->dev; ctrl->cnum = idx; + ctrl->assoc_active = false; get_device(ctrl->dev); kref_init(&ctrl->ref); -- cgit v1.2.3 From 38dabe210fbab4e7e8a03670ab3ba42f247ea08f Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 7 Nov 2017 15:13:10 -0700 Subject: nvme: centralize AEN defines All the transports were unnecessarilly duplicating the AEN request accounting. This patch defines everything in one place. Signed-off-by: Keith Busch Reviewed-by: Guan Junxiong Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 2 +- drivers/nvme/host/fc.c | 33 ++++++++++++--------------------- drivers/nvme/host/nvme.h | 1 - drivers/nvme/host/pci.c | 16 +++------------- drivers/nvme/host/rdma.c | 14 +++----------- drivers/nvme/target/loop.c | 14 +++----------- include/linux/nvme.h | 8 ++++++++ 7 files changed, 30 insertions(+), 58 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 6c79b73fe2c3..315087dfcd8d 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2779,7 +2779,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event); void nvme_queue_async_events(struct nvme_ctrl *ctrl) { - ctrl->event_limit = NVME_NR_AERS; + ctrl->event_limit = NVME_NR_AEN_COMMANDS; queue_work(nvme_wq, &ctrl->async_event_work); } EXPORT_SYMBOL_GPL(nvme_queue_async_events); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index da9296a1eb26..f3bfad47a95f 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -30,15 +30,6 @@ /* *************************** Data Structures/Defines ****************** */ -/* - * We handle AEN commands ourselves and don't even let the - * block layer know about them. - */ -#define NVME_FC_NR_AEN_COMMANDS 1 -#define NVME_FC_AQ_BLKMQ_DEPTH \ - (NVME_AQ_DEPTH - NVME_FC_NR_AEN_COMMANDS) -#define AEN_CMDID_BASE (NVME_FC_AQ_BLKMQ_DEPTH + 1) - enum nvme_fc_queue_flags { NVME_FC_Q_CONNECTED = (1 << 0), }; @@ -170,7 +161,7 @@ struct nvme_fc_ctrl { u32 iocnt; wait_queue_head_t ioabort_wait; - struct nvme_fc_fcp_op aen_ops[NVME_FC_NR_AEN_COMMANDS]; + struct nvme_fc_fcp_op aen_ops[NVME_NR_AEN_COMMANDS]; struct nvme_ctrl ctrl; }; @@ -1546,7 +1537,7 @@ nvme_fc_abort_aen_ops(struct nvme_fc_ctrl *ctrl) unsigned long flags; int i, ret; - for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) { + for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) { if (atomic_read(&aen_op->state) != FCPOP_STATE_ACTIVE) continue; @@ -1816,7 +1807,7 @@ nvme_fc_init_aen_ops(struct nvme_fc_ctrl *ctrl) int i, ret; aen_op = ctrl->aen_ops; - for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) { + for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) { private = kzalloc(ctrl->lport->ops->fcprqst_priv_sz, GFP_KERNEL); if (!private) @@ -1826,7 +1817,7 @@ nvme_fc_init_aen_ops(struct nvme_fc_ctrl *ctrl) sqe = &cmdiu->sqe; ret = __nvme_fc_init_request(ctrl, &ctrl->queues[0], aen_op, (struct request *)NULL, - (AEN_CMDID_BASE + i)); + (NVME_AQ_BLK_MQ_DEPTH + i)); if (ret) { kfree(private); return ret; @@ -1839,7 +1830,7 @@ nvme_fc_init_aen_ops(struct nvme_fc_ctrl *ctrl) memset(sqe, 0, sizeof(*sqe)); sqe->common.opcode = nvme_admin_async_event; /* Note: core layer may overwrite the sqe.command_id value */ - sqe->common.command_id = AEN_CMDID_BASE + i; + sqe->common.command_id = NVME_AQ_BLK_MQ_DEPTH + i; } return 0; } @@ -1851,7 +1842,7 @@ nvme_fc_term_aen_ops(struct nvme_fc_ctrl *ctrl) int i; aen_op = ctrl->aen_ops; - for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) { + for (i = 0; i < NVME_NR_AEN_COMMANDS; i++, aen_op++) { if (!aen_op->fcp_req.private) continue; @@ -2402,7 +2393,7 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg, int aer_idx) bool terminating = false; blk_status_t ret; - if (aer_idx > NVME_FC_NR_AEN_COMMANDS) + if (aer_idx > NVME_NR_AEN_COMMANDS) return; spin_lock_irqsave(&ctrl->lock, flags); @@ -2722,16 +2713,16 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) * Create the admin queue */ - nvme_fc_init_queue(ctrl, 0, NVME_FC_AQ_BLKMQ_DEPTH); + nvme_fc_init_queue(ctrl, 0, NVME_AQ_BLK_MQ_DEPTH); ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0, - NVME_FC_AQ_BLKMQ_DEPTH); + NVME_AQ_BLK_MQ_DEPTH); if (ret) goto out_free_queue; ret = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0], - NVME_FC_AQ_BLKMQ_DEPTH, - (NVME_FC_AQ_BLKMQ_DEPTH / 4)); + NVME_AQ_BLK_MQ_DEPTH, + (NVME_AQ_BLK_MQ_DEPTH / 4)); if (ret) goto out_delete_hw_queue; @@ -3145,7 +3136,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set)); ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops; - ctrl->admin_tag_set.queue_depth = NVME_FC_AQ_BLKMQ_DEPTH; + ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; ctrl->admin_tag_set.reserved_tags = 2; /* fabric connect + Keep-Alive */ ctrl->admin_tag_set.numa_node = NUMA_NO_NODE; ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) + diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index f7c21cea9485..a6d750cfa6b2 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -313,7 +313,6 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl); int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len, bool send); -#define NVME_NR_AERS 1 void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, union nvme_result *res); void nvme_queue_async_events(struct nvme_ctrl *ctrl); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 32c413ec818c..c3dfd84feef7 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -35,12 +35,6 @@ #define SQ_SIZE(depth) (depth * sizeof(struct nvme_command)) #define CQ_SIZE(depth) (depth * sizeof(struct nvme_completion)) -/* - * We handle AEN commands ourselves and don't even let the - * block layer know about them. - */ -#define NVME_AQ_BLKMQ_DEPTH (NVME_AQ_DEPTH - NVME_NR_AERS) - #define SGES_PER_PAGE (PAGE_SIZE / sizeof(struct nvme_sgl_desc)) static int use_threaded_interrupts; @@ -956,7 +950,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, * for them but rather special case them here. */ if (unlikely(nvmeq->qid == 0 && - cqe->command_id >= NVME_AQ_BLKMQ_DEPTH)) { + cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) { nvme_complete_async_event(&nvmeq->dev->ctrl, cqe->status, &cqe->result); return; @@ -1057,7 +1051,7 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl, int aer_idx) memset(&c, 0, sizeof(c)); c.common.opcode = nvme_admin_async_event; - c.common.command_id = NVME_AQ_BLKMQ_DEPTH + aer_idx; + c.common.command_id = NVME_AQ_BLK_MQ_DEPTH + aer_idx; spin_lock_irq(&nvmeq->q_lock); __nvme_submit_cmd(nvmeq, &c); @@ -1524,11 +1518,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev) dev->admin_tagset.ops = &nvme_mq_admin_ops; dev->admin_tagset.nr_hw_queues = 1; - /* - * Subtract one to leave an empty queue entry for 'Full Queue' - * condition. See NVM-Express 1.2 specification, section 4.1.2. - */ - dev->admin_tagset.queue_depth = NVME_AQ_BLKMQ_DEPTH - 1; + dev->admin_tagset.queue_depth = NVME_AQ_MQ_TAG_DEPTH; dev->admin_tagset.timeout = ADMIN_TIMEOUT; dev->admin_tagset.numa_node = dev_to_node(dev->dev); dev->admin_tagset.cmd_size = nvme_pci_cmd_size(dev, false); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 32e21ab1ae52..008791bbdfb3 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -41,14 +41,6 @@ #define NVME_RDMA_MAX_INLINE_SEGMENTS 1 -/* - * We handle AEN commands ourselves and don't even let the - * block layer know about them. - */ -#define NVME_RDMA_NR_AEN_COMMANDS 1 -#define NVME_RDMA_AQ_BLKMQ_DEPTH \ - (NVME_AQ_DEPTH - NVME_RDMA_NR_AEN_COMMANDS) - struct nvme_rdma_device { struct ib_device *dev; struct ib_pd *pd; @@ -690,7 +682,7 @@ static struct blk_mq_tag_set *nvme_rdma_alloc_tagset(struct nvme_ctrl *nctrl, set = &ctrl->admin_tag_set; memset(set, 0, sizeof(*set)); set->ops = &nvme_rdma_admin_mq_ops; - set->queue_depth = NVME_RDMA_AQ_BLKMQ_DEPTH; + set->queue_depth = NVME_AQ_MQ_TAG_DEPTH; set->reserved_tags = 2; /* connect + keep-alive */ set->numa_node = NUMA_NO_NODE; set->cmd_size = sizeof(struct nvme_rdma_request) + @@ -1318,7 +1310,7 @@ static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg, int aer_idx) memset(cmd, 0, sizeof(*cmd)); cmd->common.opcode = nvme_admin_async_event; - cmd->common.command_id = NVME_RDMA_AQ_BLKMQ_DEPTH; + cmd->common.command_id = NVME_AQ_BLK_MQ_DEPTH; cmd->common.flags |= NVME_CMD_SGL_METABUF; nvme_rdma_set_sg_null(cmd); @@ -1380,7 +1372,7 @@ static int __nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc, int tag) * for them but rather special case them here. */ if (unlikely(nvme_rdma_queue_idx(queue) == 0 && - cqe->command_id >= NVME_RDMA_AQ_BLKMQ_DEPTH)) + cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); else diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index bc95c6ed531a..7258b796f209 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -23,14 +23,6 @@ #define NVME_LOOP_MAX_SEGMENTS 256 -/* - * We handle AEN commands ourselves and don't even let the - * block layer know about them. - */ -#define NVME_LOOP_NR_AEN_COMMANDS 1 -#define NVME_LOOP_AQ_BLKMQ_DEPTH \ - (NVME_AQ_DEPTH - NVME_LOOP_NR_AEN_COMMANDS) - struct nvme_loop_iod { struct nvme_request nvme_req; struct nvme_command cmd; @@ -112,7 +104,7 @@ static void nvme_loop_queue_response(struct nvmet_req *req) * for them but rather special case them here. */ if (unlikely(nvme_loop_queue_idx(queue) == 0 && - cqe->command_id >= NVME_LOOP_AQ_BLKMQ_DEPTH)) { + cqe->command_id >= NVME_AQ_BLK_MQ_DEPTH)) { nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); } else { @@ -200,7 +192,7 @@ static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx) memset(&iod->cmd, 0, sizeof(iod->cmd)); iod->cmd.common.opcode = nvme_admin_async_event; - iod->cmd.common.command_id = NVME_LOOP_AQ_BLKMQ_DEPTH; + iod->cmd.common.command_id = NVME_AQ_BLK_MQ_DEPTH; iod->cmd.common.flags |= NVME_CMD_SGL_METABUF; if (!nvmet_req_init(&iod->req, &queue->nvme_cq, &queue->nvme_sq, @@ -356,7 +348,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set)); ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops; - ctrl->admin_tag_set.queue_depth = NVME_LOOP_AQ_BLKMQ_DEPTH; + ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH; ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */ ctrl->admin_tag_set.numa_node = NUMA_NO_NODE; ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) + diff --git a/include/linux/nvme.h b/include/linux/nvme.h index fd1d4508a612..89ffa7eed2fd 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -90,6 +90,14 @@ enum { }; #define NVME_AQ_DEPTH 32 +#define NVME_NR_AEN_COMMANDS 1 +#define NVME_AQ_BLK_MQ_DEPTH (NVME_AQ_DEPTH - NVME_NR_AEN_COMMANDS) + +/* + * Subtract one to leave an empty queue entry for 'Full Queue' condition. See + * NVM-Express 1.2 specification, section 4.1.2. + */ +#define NVME_AQ_MQ_TAG_DEPTH (NVME_AQ_BLK_MQ_DEPTH - 1) enum { NVME_REG_CAP = 0x0000, /* Controller Capabilities */ -- cgit v1.2.3 From 08e1507544839b98fc3732aea935e70ed9c209ec Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 7 Nov 2017 15:13:11 -0700 Subject: nvme-fc: remove unused "queue_size" field This was being saved in a structure, but never used anywhere. The queue size is obtained through other means, so there's no reason to duplicate this without a user for it. Reviewed-by: Sagi Grimberg Signed-off-by: Keith Busch Reviewed-by: Guan Junxiong Reviewed-by: James Smart Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/fc.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index f3bfad47a95f..3aa595029192 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -43,7 +43,6 @@ struct nvme_fc_queue { struct device *dev; struct blk_mq_hw_ctx *hctx; void *lldd_handle; - int queue_size; size_t cmnd_capsule_len; u32 qnum; u32 rqcnt; @@ -1886,7 +1885,7 @@ nvme_fc_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data, } static void -nvme_fc_init_queue(struct nvme_fc_ctrl *ctrl, int idx, size_t queue_size) +nvme_fc_init_queue(struct nvme_fc_ctrl *ctrl, int idx) { struct nvme_fc_queue *queue; @@ -1902,8 +1901,6 @@ nvme_fc_init_queue(struct nvme_fc_ctrl *ctrl, int idx, size_t queue_size) else queue->cmnd_capsule_len = sizeof(struct nvme_command); - queue->queue_size = queue_size; - /* * Considered whether we should allocate buffers for all SQEs * and CQEs and dma map them - mapping their respective entries @@ -2027,7 +2024,7 @@ nvme_fc_init_io_queues(struct nvme_fc_ctrl *ctrl) int i; for (i = 1; i < ctrl->ctrl.queue_count; i++) - nvme_fc_init_queue(ctrl, i, ctrl->ctrl.sqsize); + nvme_fc_init_queue(ctrl, i); } static void @@ -2713,7 +2710,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) * Create the admin queue */ - nvme_fc_init_queue(ctrl, 0, NVME_AQ_BLK_MQ_DEPTH); + nvme_fc_init_queue(ctrl, 0); ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0, NVME_AQ_BLK_MQ_DEPTH); -- cgit v1.2.3 From ad22c355b707a8d8d48e282aadc01c0b0604b2e9 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 7 Nov 2017 15:13:12 -0700 Subject: nvme: remove handling of multiple AEN requests The driver can handle tracking only one AEN request, so this patch removes handling for multiple ones. Reviewed-by: Christoph Hellwig Reviewed-by: James Smart Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 28 +++------------------------- drivers/nvme/host/fc.c | 9 +++------ drivers/nvme/host/nvme.h | 3 +-- drivers/nvme/host/pci.c | 4 ++-- drivers/nvme/host/rdma.c | 5 +---- drivers/nvme/target/loop.c | 2 +- 6 files changed, 11 insertions(+), 40 deletions(-) (limited to 'drivers/nvme/host/fc.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 315087dfcd8d..dedbf12847b6 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2670,15 +2670,7 @@ static void nvme_async_event_work(struct work_struct *work) struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, async_event_work); - spin_lock_irq(&ctrl->lock); - while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) { - int aer_idx = --ctrl->event_limit; - - spin_unlock_irq(&ctrl->lock); - ctrl->ops->submit_async_event(ctrl, aer_idx); - spin_lock_irq(&ctrl->lock); - } - spin_unlock_irq(&ctrl->lock); + ctrl->ops->submit_async_event(ctrl); } static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl) @@ -2745,22 +2737,8 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, union nvme_result *res) { u32 result = le32_to_cpu(res->u32); - bool done = true; - switch (le16_to_cpu(status) >> 1) { - case NVME_SC_SUCCESS: - done = false; - /*FALLTHRU*/ - case NVME_SC_ABORT_REQ: - ++ctrl->event_limit; - if (ctrl->state == NVME_CTRL_LIVE) - queue_work(nvme_wq, &ctrl->async_event_work); - break; - default: - break; - } - - if (done) + if (le16_to_cpu(status) >> 1 != NVME_SC_SUCCESS) return; switch (result & 0xff07) { @@ -2774,12 +2752,12 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status, default: dev_warn(ctrl->device, "async event result %08x\n", result); } + queue_work(nvme_wq, &ctrl->async_event_work); } EXPORT_SYMBOL_GPL(nvme_complete_async_event); void nvme_queue_async_events(struct nvme_ctrl *ctrl) { - ctrl->event_limit = NVME_NR_AEN_COMMANDS; queue_work(nvme_wq, &ctrl->async_event_work); } EXPORT_SYMBOL_GPL(nvme_queue_async_events); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 3aa595029192..6eb460b117d6 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2382,7 +2382,7 @@ nvme_fc_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag) } static void -nvme_fc_submit_async_event(struct nvme_ctrl *arg, int aer_idx) +nvme_fc_submit_async_event(struct nvme_ctrl *arg) { struct nvme_fc_ctrl *ctrl = to_fc_ctrl(arg); struct nvme_fc_fcp_op *aen_op; @@ -2390,9 +2390,6 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg, int aer_idx) bool terminating = false; blk_status_t ret; - if (aer_idx > NVME_NR_AEN_COMMANDS) - return; - spin_lock_irqsave(&ctrl->lock, flags); if (ctrl->flags & FCCTRL_TERMIO) terminating = true; @@ -2401,13 +2398,13 @@ nvme_fc_submit_async_event(struct nvme_ctrl *arg, int aer_idx) if (terminating) return; - aen_op = &ctrl->aen_ops[aer_idx]; + aen_op = &ctrl->aen_ops[0]; ret = nvme_fc_start_fcp_op(ctrl, aen_op->queue, aen_op, 0, NVMEFC_FCP_NODATA); if (ret) dev_err(ctrl->ctrl.device, - "failed async event work [%d]\n", aer_idx); + "failed async event work\n"); } static void diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index a6d750cfa6b2..b55c97ecea31 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -162,7 +162,6 @@ struct nvme_ctrl { u16 nssa; u16 nr_streams; atomic_t abort_limit; - u8 event_limit; u8 vwc; u32 vs; u32 sgls; @@ -237,7 +236,7 @@ struct nvme_ctrl_ops { int (*reg_write32)(struct nvme_ctrl *ctrl, u32 off, u32 val); int (*reg_read64)(struct nvme_ctrl *ctrl, u32 off, u64 *val); void (*free_ctrl)(struct nvme_ctrl *ctrl); - void (*submit_async_event)(struct nvme_ctrl *ctrl, int aer_idx); + void (*submit_async_event)(struct nvme_ctrl *ctrl); void (*delete_ctrl)(struct nvme_ctrl *ctrl); int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size); int (*reinit_request)(void *data, struct request *rq); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index c3dfd84feef7..429d56f1a19e 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1043,7 +1043,7 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag) return __nvme_poll(nvmeq, tag); } -static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl, int aer_idx) +static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl) { struct nvme_dev *dev = to_nvme_dev(ctrl); struct nvme_queue *nvmeq = dev->queues[0]; @@ -1051,7 +1051,7 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl, int aer_idx) memset(&c, 0, sizeof(c)); c.common.opcode = nvme_admin_async_event; - c.common.command_id = NVME_AQ_BLK_MQ_DEPTH + aer_idx; + c.common.command_id = NVME_AQ_BLK_MQ_DEPTH; spin_lock_irq(&nvmeq->q_lock); __nvme_submit_cmd(nvmeq, &c); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 008791bbdfb3..c8d854474a5b 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1293,7 +1293,7 @@ static struct blk_mq_tags *nvme_rdma_tagset(struct nvme_rdma_queue *queue) return queue->ctrl->tag_set.tags[queue_idx - 1]; } -static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg, int aer_idx) +static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg) { struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(arg); struct nvme_rdma_queue *queue = &ctrl->queues[0]; @@ -1303,9 +1303,6 @@ static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg, int aer_idx) struct ib_sge sge; int ret; - if (WARN_ON_ONCE(aer_idx != 0)) - return; - ib_dma_sync_single_for_cpu(dev, sqe->dma, sizeof(*cmd), DMA_TO_DEVICE); memset(cmd, 0, sizeof(*cmd)); diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 7258b796f209..f40e70eb4a38 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -184,7 +184,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } -static void nvme_loop_submit_async_event(struct nvme_ctrl *arg, int aer_idx) +static void nvme_loop_submit_async_event(struct nvme_ctrl *arg) { struct nvme_loop_ctrl *ctrl = to_loop_ctrl(arg); struct nvme_loop_queue *queue = &ctrl->queues[0]; -- cgit v1.2.3