From d6a2b9535d1e52bea269c138614c4801469d10e1 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 26 Nov 2018 16:39:47 -0700 Subject: nvme: Free ctrl device name on init failure Free the kobject name that was allocated for the controller device on failure rather than its parent. Fixes: d22524a4782a9 ("nvme: switch controller refcounting to use struct device") Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/nvme/host/core.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 559d567693b8..5afda6fe5ae9 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3585,7 +3585,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, return 0; out_free_name: - kfree_const(dev->kobj.name); + kfree_const(ctrl->device->kobj.name); out_release_instance: ida_simple_remove(&nvme_instance_ida, ctrl->instance); out: -- cgit v1.2.3 From 751a0cc0cd3a0d51e6aaf6fd3b8bd31f4ecfaf3e Mon Sep 17 00:00:00 2001 From: Igor Konopko Date: Fri, 23 Nov 2018 16:58:10 +0100 Subject: nvme-pci: fix surprise removal When a PCIe NVMe device is not present, nvme_dev_remove_admin() calls blk_cleanup_queue() on the admin queue, which frees the hctx for that queue. Moments later, on the same path nvme_kill_queues() calls blk_mq_unquiesce_queue() on admin queue and tries to access hctx of it, which leads to following OOPS: Oops: 0000 [#1] SMP PTI RIP: 0010:sbitmap_any_bit_set+0xb/0x40 Call Trace: blk_mq_run_hw_queue+0xd5/0x150 blk_mq_run_hw_queues+0x3a/0x50 nvme_kill_queues+0x26/0x50 nvme_remove_namespaces+0xb2/0xc0 nvme_remove+0x60/0x140 pci_device_remove+0x3b/0xb0 Fixes: cb4bfda62afa2 ("nvme-pci: fix hot removal during error handling") Signed-off-by: Igor Konopko Reviewed-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/nvme/host/core.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 5afda6fe5ae9..bb39b91253c2 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3607,7 +3607,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) down_read(&ctrl->namespaces_rwsem); /* Forcibly unquiesce queues to avoid blocking dispatch */ - if (ctrl->admin_q) + if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q)) blk_mq_unquiesce_queue(ctrl->admin_q); list_for_each_entry(ns, &ctrl->namespaces, list) -- cgit v1.2.3 From f6c8e432cb0479255322c5d0335b9f1699a0270c Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 21 Nov 2018 15:17:37 -0800 Subject: nvme: flush namespace scanning work just before removing namespaces nvme_stop_ctrl can be called also for reset flow and there is no need to flush the scan_work as namespaces are not being removed. This can cause deadlock in rdma, fc and loop drivers since nvme_stop_ctrl barriers before controller teardown (and specifically I/O cancellation of the scan_work itself) takes place, but the scan_work will be blocked anyways so there is no need to flush it. Instead, move scan_work flush to nvme_remove_namespaces() where it really needs to flush. Reported-by: Ming Lei Signed-off-by: Sagi Grimberg Reviewed-by: Keith Busch Reviewed by: James Smart Tested-by: Ewan D. Milne Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/nvme/host/core.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index bb39b91253c2..3cf1b773158e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3314,6 +3314,9 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) struct nvme_ns *ns, *next; LIST_HEAD(ns_list); + /* prevent racing with ns scanning */ + flush_work(&ctrl->scan_work); + /* * The dead states indicates the controller was not gracefully * disconnected. In that case, we won't be able to flush any data while @@ -3476,7 +3479,6 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl) nvme_mpath_stop(ctrl); nvme_stop_keep_alive(ctrl); flush_work(&ctrl->async_event_work); - flush_work(&ctrl->scan_work); cancel_work_sync(&ctrl->fw_act_work); if (ctrl->ops->stop_ctrl) ctrl->ops->stop_ctrl(ctrl); -- cgit v1.2.3