From 750afb08ca71310fcf0c4e2cb1565c63b8235b60 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 4 Jan 2019 09:23:09 +0100 Subject: cross-tree: phase out dma_zalloc_coherent() We already need to zero out memory for dma_alloc_coherent(), as such using dma_zalloc_coherent() is superflous. Phase it out. This change was generated with the following Coccinelle SmPL patch: @ replace_dma_zalloc_coherent @ expression dev, size, data, handle, flags; @@ -dma_zalloc_coherent(dev, size, handle, flags) +dma_alloc_coherent(dev, size, handle, flags) Suggested-by: Christoph Hellwig Signed-off-by: Luis Chamberlain [hch: re-ran the script on the latest tree] Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 5a0bf6a24d50..e8d0942c9c92 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1485,8 +1485,8 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth) if (dev->ctrl.queue_count > qid) return 0; - nvmeq->cqes = dma_zalloc_coherent(dev->dev, CQ_SIZE(depth), - &nvmeq->cq_dma_addr, GFP_KERNEL); + nvmeq->cqes = dma_alloc_coherent(dev->dev, CQ_SIZE(depth), + &nvmeq->cq_dma_addr, GFP_KERNEL); if (!nvmeq->cqes) goto free_nvmeq; @@ -1915,8 +1915,8 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred, if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries) max_entries = dev->ctrl.hmmaxd; - descs = dma_zalloc_coherent(dev->dev, max_entries * sizeof(*descs), - &descs_dma, GFP_KERNEL); + descs = dma_alloc_coherent(dev->dev, max_entries * sizeof(*descs), + &descs_dma, GFP_KERNEL); if (!descs) goto out; -- cgit v1.2.3 From c61e678f30da733a1b7fdd5983d0770de2e6009c Mon Sep 17 00:00:00 2001 From: Jianchao Wang Date: Mon, 24 Dec 2018 11:15:53 +0800 Subject: nvme-pci: fix the wrong setting of nr_maps We only set the nr_maps to 3 if poll queues are supported. Signed-off-by: Jianchao Wang Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 5a0bf6a24d50..cc65fa8a537b 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2294,7 +2294,6 @@ static int nvme_dev_add(struct nvme_dev *dev) dev->tagset.nr_maps = 2; /* default + read */ if (dev->io_queues[HCTX_TYPE_POLL]) dev->tagset.nr_maps++; - dev->tagset.nr_maps = HCTX_MAX_TYPES; dev->tagset.timeout = NVME_IO_TIMEOUT; dev->tagset.numa_node = dev_to_node(dev->dev); dev->tagset.queue_depth = -- cgit v1.2.3 From cc667f6d5de023ee131e96bb88e5cddca23272bd Mon Sep 17 00:00:00 2001 From: Liviu Dudau Date: Sat, 29 Dec 2018 17:23:43 +0000 Subject: nvme-pci: use the same attributes when freeing host_mem_desc_bufs. When using HMB the PCIe host driver allocates host_mem_desc_bufs using dma_alloc_attrs() but frees them using dma_free_coherent(). Use the correct dma_free_attrs() function to free the buffers. Signed-off-by: Liviu Dudau Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index cc65fa8a537b..efe46f518022 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1885,8 +1885,9 @@ static void nvme_free_host_mem(struct nvme_dev *dev) struct nvme_host_mem_buf_desc *desc = &dev->host_mem_descs[i]; size_t size = le32_to_cpu(desc->size) * dev->ctrl.page_size; - dma_free_coherent(dev->dev, size, dev->host_mem_desc_bufs[i], - le64_to_cpu(desc->addr)); + dma_free_attrs(dev->dev, size, dev->host_mem_desc_bufs[i], + le64_to_cpu(desc->addr), + DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN); } kfree(dev->host_mem_desc_bufs); @@ -1952,8 +1953,9 @@ out_free_bufs: while (--i >= 0) { size_t size = le32_to_cpu(descs[i].size) * dev->ctrl.page_size; - dma_free_coherent(dev->dev, size, bufs[i], - le64_to_cpu(descs[i].addr)); + dma_free_attrs(dev->dev, size, bufs[i], + le64_to_cpu(descs[i].addr), + DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN); } kfree(bufs); -- cgit v1.2.3 From 8fae268b40f5191227ae7050a99cb2cf1b914ddd Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 4 Jan 2019 15:04:33 -0700 Subject: nvme-pci: rerun irq setup on IO queue init errors If the driver is unable to create a subset of IO queues for any reason, the read/write and polled queue sets will not match the actual allocated hardware contexts. This leaves gaps in the CPU affinity mappings and causes the following kernel panic after blk_mq_map_queue_type() returns a NULL hctx. BUG: unable to handle kernel NULL pointer dereference at 0000000000000198 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP CPU: 64 PID: 1171 Comm: kworker/u259:1 Not tainted 4.20.0+ #241 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014 Workqueue: nvme-wq nvme_scan_work [nvme_core] RIP: 0010:blk_mq_init_allocated_queue+0x2d9/0x440 RSP: 0018:ffffb1bf0abc3cd0 EFLAGS: 00010286 RAX: 000000000000001f RBX: ffff8ea744cf0718 RCX: 0000000000000000 RDX: 0000000000000002 RSI: 000000000000007c RDI: ffffffff9109a820 RBP: ffff8ea7565f7008 R08: 000000000000001f R09: 000000000000003f R10: ffffb1bf0abc3c00 R11: 0000000000000000 R12: 000000000001d008 R13: ffff8ea7565f7008 R14: 000000000000003f R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff8ea757200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000198 CR3: 0000000013058000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: blk_mq_init_queue+0x35/0x60 nvme_validate_ns+0xc6/0x7c0 [nvme_core] ? nvme_identify_ctrl.isra.56+0x7e/0xc0 [nvme_core] nvme_scan_work+0xc8/0x340 [nvme_core] ? __wake_up_common+0x6d/0x120 ? try_to_wake_up+0x55/0x410 process_one_work+0x1e9/0x3d0 worker_thread+0x2d/0x3d0 ? process_one_work+0x3d0/0x3d0 kthread+0x111/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x1f/0x30 Modules linked in: nvme nvme_core serio_raw CR2: 0000000000000198 Fix by re-running the interrupt vector setup from scratch using a reduced count that may be successful until the created queues matches the irq affinity plus polling queue sets. Signed-off-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Ming Lei Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 50 +++++++++++++++++++++++++++++++++++-------------- 1 file changed, 36 insertions(+), 14 deletions(-) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index efe46f518022..f891eb57f263 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -95,6 +95,7 @@ struct nvme_dev; struct nvme_queue; static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown); +static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode); /* * Represents an NVM Express device. Each nvme_dev is a PCI function. @@ -1420,6 +1421,14 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq) return 0; } +static void nvme_suspend_io_queues(struct nvme_dev *dev) +{ + int i; + + for (i = dev->ctrl.queue_count - 1; i > 0; i--) + nvme_suspend_queue(&dev->queues[i]); +} + static void nvme_disable_admin_queue(struct nvme_dev *dev, bool shutdown) { struct nvme_queue *nvmeq = &dev->queues[0]; @@ -2134,6 +2143,12 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) return result; } +static void nvme_disable_io_queues(struct nvme_dev *dev) +{ + if (__nvme_disable_io_queues(dev, nvme_admin_delete_sq)) + __nvme_disable_io_queues(dev, nvme_admin_delete_cq); +} + static int nvme_setup_io_queues(struct nvme_dev *dev) { struct nvme_queue *adminq = &dev->queues[0]; @@ -2170,6 +2185,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) } while (1); adminq->q_db = dev->dbs; + retry: /* Deregister the admin queue's interrupt */ pci_free_irq(pdev, 0, adminq); @@ -2187,25 +2203,34 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) result = max(result - 1, 1); dev->max_qid = result + dev->io_queues[HCTX_TYPE_POLL]; - dev_info(dev->ctrl.device, "%d/%d/%d default/read/poll queues\n", - dev->io_queues[HCTX_TYPE_DEFAULT], - dev->io_queues[HCTX_TYPE_READ], - dev->io_queues[HCTX_TYPE_POLL]); - /* * Should investigate if there's a performance win from allocating * more queues than interrupt vectors; it might allow the submission * path to scale better, even if the receive path is limited by the * number of interrupts. */ - result = queue_request_irq(adminq); if (result) { adminq->cq_vector = -1; return result; } set_bit(NVMEQ_ENABLED, &adminq->flags); - return nvme_create_io_queues(dev); + + result = nvme_create_io_queues(dev); + if (result || dev->online_queues < 2) + return result; + + if (dev->online_queues - 1 < dev->max_qid) { + nr_io_queues = dev->online_queues - 1; + nvme_disable_io_queues(dev); + nvme_suspend_io_queues(dev); + goto retry; + } + dev_info(dev->ctrl.device, "%d/%d/%d default/read/poll queues\n", + dev->io_queues[HCTX_TYPE_DEFAULT], + dev->io_queues[HCTX_TYPE_READ], + dev->io_queues[HCTX_TYPE_POLL]); + return 0; } static void nvme_del_queue_end(struct request *req, blk_status_t error) @@ -2250,7 +2275,7 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode) return 0; } -static bool nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode) +static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode) { int nr_queues = dev->online_queues - 1, sent = 0; unsigned long timeout; @@ -2411,7 +2436,6 @@ static void nvme_pci_disable(struct nvme_dev *dev) static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) { - int i; bool dead = true; struct pci_dev *pdev = to_pci_dev(dev->dev); @@ -2438,13 +2462,11 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_stop_queues(&dev->ctrl); if (!dead && dev->ctrl.queue_count > 0) { - if (nvme_disable_io_queues(dev, nvme_admin_delete_sq)) - nvme_disable_io_queues(dev, nvme_admin_delete_cq); + nvme_disable_io_queues(dev); nvme_disable_admin_queue(dev, shutdown); } - for (i = dev->ctrl.queue_count - 1; i >= 0; i--) - nvme_suspend_queue(&dev->queues[i]); - + nvme_suspend_io_queues(dev); + nvme_suspend_queue(&dev->queues[0]); nvme_pci_disable(dev); blk_mq_tagset_busy_iter(&dev->tagset, nvme_cancel_request, &dev->ctrl); -- cgit v1.2.3 From dcca1662727220d18fa351097ddff33f95f516c5 Mon Sep 17 00:00:00 2001 From: Hongbo Yao Date: Mon, 7 Jan 2019 10:22:07 +0800 Subject: nvme-pci: fix out of bounds access in nvme_cqe_pending There is an out of bounds array access in nvme_cqe_peding(). When enable irq_thread for nvme interrupt, there is racing between the nvmeq->cq_head updating and reading. nvmeq->cq_head is updated in nvme_update_cq_head(), if nvmeq->cq_head equals nvmeq->q_depth and before its value set to zero, nvme_cqe_pending() uses its value as an array index, the index will be out of bounds. Signed-off-by: Hongbo Yao [hch: slight coding style update] Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index f891eb57f263..3f53a2c3042d 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1020,9 +1020,11 @@ static void nvme_complete_cqes(struct nvme_queue *nvmeq, u16 start, u16 end) static inline void nvme_update_cq_head(struct nvme_queue *nvmeq) { - if (++nvmeq->cq_head == nvmeq->q_depth) { + if (nvmeq->cq_head == nvmeq->q_depth - 1) { nvmeq->cq_head = 0; nvmeq->cq_phase = !nvmeq->cq_phase; + } else { + nvmeq->cq_head++; } } -- cgit v1.2.3 From 6299358d198a0635da2dd3c4b3ec37789e811e44 Mon Sep 17 00:00:00 2001 From: James Dingwall Date: Tue, 8 Jan 2019 10:20:51 -0700 Subject: nvme: introduce NVME_QUIRK_IGNORE_DEV_SUBNQN If a device provides an NQN it is expected to be globally unique. Unfortunately some firmware revisions for Intel 760p/Pro 7600p devices did not satisfy this requirement. In these circumstances if a system has >1 affected device then only one device is enabled. If this quirk is enabled then the device supplied subnqn is ignored and we fallback to generating one as if the field was empty. In this case we also suppress the version check so we don't print a warning when the quirk is enabled. Reviewed-by: Keith Busch Signed-off-by: James Dingwall Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 16 +++++++++------- drivers/nvme/host/nvme.h | 5 +++++ drivers/nvme/host/pci.c | 2 ++ 3 files changed, 16 insertions(+), 7 deletions(-) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f81fde164d37..8485be6bb895 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2173,14 +2173,16 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct size_t nqnlen; int off; - nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE); - if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) { - strlcpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE); - return; - } + if(!(ctrl->quirks & NVME_QUIRK_IGNORE_DEV_SUBNQN)) { + nqnlen = strnlen(id->subnqn, NVMF_NQN_SIZE); + if (nqnlen > 0 && nqnlen < NVMF_NQN_SIZE) { + strlcpy(subsys->subnqn, id->subnqn, NVMF_NQN_SIZE); + return; + } - if (ctrl->vs >= NVME_VS(1, 2, 1)) - dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n"); + if (ctrl->vs >= NVME_VS(1, 2, 1)) + dev_warn(ctrl->device, "missing or invalid SUBNQN field.\n"); + } /* Generate a "fake" NQN per Figure 254 in NVMe 1.3 + ECN 001 */ off = snprintf(subsys->subnqn, NVMF_NQN_SIZE, diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 2b36ac922596..ab961bdeea89 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -90,6 +90,11 @@ enum nvme_quirks { * Set MEDIUM priority on SQ creation */ NVME_QUIRK_MEDIUM_PRIO_SQ = (1 << 7), + + /* + * Ignore device provided subnqn. + */ + NVME_QUIRK_IGNORE_DEV_SUBNQN = (1 << 8), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 3f53a2c3042d..fc9d17c317b8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2971,6 +2971,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_MEDIUM_PRIO_SQ }, + { PCI_VDEVICE(INTEL, 0xf1a6), /* Intel 760p/Pro 7600p */ + .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_IDENTIFY_CNS, }, { PCI_DEVICE(0x1bb1, 0x0100), /* Seagate Nytro Flash Storage */ -- cgit v1.2.3 From c45b1fa2433c65e44bdf48f513cb37289f3116b9 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 3 Jan 2019 09:34:39 +0800 Subject: nvme-pci: fix nvme_setup_irqs() When -ENOSPC is returned from pci_alloc_irq_vectors_affinity(), we still try to allocate multiple irq vectors again, so irq queues covers the admin queue actually. But we don't consider that, then number of the allocated irq vector may be same with sum of io_queues[HCTX_TYPE_DEFAULT] and io_queues[HCTX_TYPE_READ], this way is obviously wrong, and finally breaks nvme_pci_map_queues(), and warning from pci_irq_get_affinity() is triggered. IRQ queues should cover admin queues, this patch makes this point explicitely in nvme_calc_io_queues(). We got severl boot failure internal report on aarch64, so please consider to fix it in v4.20. Fixes: 6451fe73fa0f ("nvme: fix irq vs io_queue calculations") Signed-off-by: Ming Lei Reviewed-by: Keith Busch Tested-by: fin4478 Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index fc9d17c317b8..89f9dd72135a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2041,14 +2041,18 @@ static int nvme_setup_host_mem(struct nvme_dev *dev) return ret; } +/* irq_queues covers admin queue */ static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues) { unsigned int this_w_queues = write_queues; + WARN_ON(!irq_queues); + /* - * Setup read/write queue split + * Setup read/write queue split, assign admin queue one independent + * irq vector if irq_queues is > 1. */ - if (irq_queues == 1) { + if (irq_queues <= 2) { dev->io_queues[HCTX_TYPE_DEFAULT] = 1; dev->io_queues[HCTX_TYPE_READ] = 0; return; @@ -2056,21 +2060,21 @@ static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues) /* * If 'write_queues' is set, ensure it leaves room for at least - * one read queue + * one read queue and one admin queue */ if (this_w_queues >= irq_queues) - this_w_queues = irq_queues - 1; + this_w_queues = irq_queues - 2; /* * If 'write_queues' is set to zero, reads and writes will share * a queue set. */ if (!this_w_queues) { - dev->io_queues[HCTX_TYPE_DEFAULT] = irq_queues; + dev->io_queues[HCTX_TYPE_DEFAULT] = irq_queues - 1; dev->io_queues[HCTX_TYPE_READ] = 0; } else { dev->io_queues[HCTX_TYPE_DEFAULT] = this_w_queues; - dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues; + dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues - 1; } } @@ -2095,7 +2099,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) this_p_queues = nr_io_queues - 1; irq_queues = 1; } else { - irq_queues = nr_io_queues - this_p_queues; + irq_queues = nr_io_queues - this_p_queues + 1; } dev->io_queues[HCTX_TYPE_POLL] = this_p_queues; @@ -2115,8 +2119,9 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) * If we got a failure and we're down to asking for just * 1 + 1 queues, just ask for a single vector. We'll share * that between the single IO queue and the admin queue. + * Otherwise, we assign one independent vector to admin queue. */ - if (result >= 0 && irq_queues > 1) + if (irq_queues > 1) irq_queues = irq_sets[0] + irq_sets[1] + 1; result = pci_alloc_irq_vectors_affinity(pdev, irq_queues, -- cgit v1.2.3 From 5c959d73dba6495ec01d04c206ee679d61ccb2b0 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 23 Jan 2019 18:46:11 -0700 Subject: nvme-pci: fix rapid add remove sequence A surprise removal may fail to tear down request queues if it is racing with the initial asynchronous probe. If that happens, the remove path won't see the queue resources to tear down, and the controller reset path may create a new request queue on a removed device, but will not be able to make forward progress, deadlocking the pci removal. Protect setting up non-blocking resources from a shutdown by holding the same mutex, and transition to the CONNECTING state after these resources are initialized so the probe path may see the dead controller state before dispatching new IO. Link: https://bugzilla.kernel.org/show_bug.cgi?id=202081 Reported-by: Alex Gagniuc Signed-off-by: Keith Busch Tested-by: Alex Gagniuc Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9bc585415d9b..022ea1ee63f8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2557,16 +2557,7 @@ static void nvme_reset_work(struct work_struct *work) if (dev->ctrl.ctrl_config & NVME_CC_ENABLE) nvme_dev_disable(dev, false); - /* - * Introduce CONNECTING state from nvme-fc/rdma transports to mark the - * initializing procedure here. - */ - if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { - dev_warn(dev->ctrl.device, - "failed to mark controller CONNECTING\n"); - goto out; - } - + mutex_lock(&dev->shutdown_lock); result = nvme_pci_enable(dev); if (result) goto out; @@ -2585,6 +2576,17 @@ static void nvme_reset_work(struct work_struct *work) */ dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1; dev->ctrl.max_segments = NVME_MAX_SEGS; + mutex_unlock(&dev->shutdown_lock); + + /* + * Introduce CONNECTING state from nvme-fc/rdma transports to mark the + * initializing procedure here. + */ + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { + dev_warn(dev->ctrl.device, + "failed to mark controller CONNECTING\n"); + goto out; + } result = nvme_init_identify(&dev->ctrl); if (result) -- cgit v1.2.3 From 4726bcf30fad37cc555cd9dcd6c73f2b2668c879 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 11 Feb 2019 09:23:50 -0700 Subject: nvme-pci: add missing unlock for reset error The reset work holds a mutex to prevent races with removal modifying the same resources, but was unlocking only on success. Unlock on failure too. Fixes: 5c959d73dba64 ("nvme-pci: fix rapid add remove sequence") Signed-off-by: Keith Busch Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 022ea1ee63f8..7fee665ec45e 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2560,15 +2560,15 @@ static void nvme_reset_work(struct work_struct *work) mutex_lock(&dev->shutdown_lock); result = nvme_pci_enable(dev); if (result) - goto out; + goto out_unlock; result = nvme_pci_configure_admin_queue(dev); if (result) - goto out; + goto out_unlock; result = nvme_alloc_admin_tags(dev); if (result) - goto out; + goto out_unlock; /* * Limit the max command size to prevent iod->sg allocations going @@ -2651,6 +2651,8 @@ static void nvme_reset_work(struct work_struct *work) nvme_start_ctrl(&dev->ctrl); return; + out_unlock: + mutex_unlock(&dev->shutdown_lock); out: nvme_remove_dead_ctrl(dev, result); } -- cgit v1.2.3