From c21377f8366c95440d533edbe47d070f662c62ef Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Thu, 11 Aug 2016 09:35:57 -0600 Subject: nvme: Suspend all queues before deletion When nvme_delete_queue fails in the first pass of the nvme_disable_io_queues() loop, we return early, failing to suspend all of the IO queues. Later, on the nvme_pci_disable path, this causes us to disable MSI without actually having freed all the IRQs, which triggers the BUG_ON in free_msi_irqs(), as show below. This patch refactors nvme_disable_io_queues to suspend all queues before start submitting delete queue commands. This way, we ensure that we have at least returned every IRQ before continuing with the removal path. [ 487.529200] kernel BUG at ../drivers/pci/msi.c:368! cpu 0x46: Vector: 700 (Program Check) at [c0000078c5b83650] pc: c000000000627a50: free_msi_irqs+0x90/0x200 lr: c000000000627a40: free_msi_irqs+0x80/0x200 sp: c0000078c5b838d0 msr: 9000000100029033 current = 0xc0000078c5b40000 paca = 0xc000000002bd7600 softe: 0 irq_happened: 0x01 pid = 1376, comm = kworker/70:1H kernel BUG at ../drivers/pci/msi.c:368! Linux version 4.7.0.mainline+ (root@iod76) (gcc version 5.3.1 20160413 (Ubuntu/IBM 5.3.1-14ubuntu2.1) ) #104 SMP Fri Jul 29 09:20:17 CDT 2016 enter ? for help [c0000078c5b83920] d0000000363b0cd8 nvme_dev_disable+0x208/0x4f0 [nvme] [c0000078c5b83a10] d0000000363b12a4 nvme_timeout+0xe4/0x250 [nvme] [c0000078c5b83ad0] c0000000005690e4 blk_mq_rq_timed_out+0x64/0x110 [c0000078c5b83b40] c00000000056c930 bt_for_each+0x160/0x170 [c0000078c5b83bb0] c00000000056d928 blk_mq_queue_tag_busy_iter+0x78/0x110 [c0000078c5b83c00] c0000000005675d8 blk_mq_timeout_work+0xd8/0x1b0 [c0000078c5b83c50] c0000000000e8cf0 process_one_work+0x1e0/0x590 [c0000078c5b83ce0] c0000000000e9148 worker_thread+0xa8/0x660 [c0000078c5b83d80] c0000000000f2090 kthread+0x110/0x130 [c0000078c5b83e30] c0000000000095f0 ret_from_kernel_thread+0x5c/0x6c Signed-off-by: Gabriel Krisman Bertazi Cc: Brian King Cc: Keith Busch Cc: linux-nvme@lists.infradead.org Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d7c33f9361aa..8dcf5a960951 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1543,15 +1543,10 @@ static void nvme_disable_io_queues(struct nvme_dev *dev) reinit_completion(&dev->ioq_wait); retry: timeout = ADMIN_TIMEOUT; - for (; i > 0; i--) { - struct nvme_queue *nvmeq = dev->queues[i]; - - if (!pass) - nvme_suspend_queue(nvmeq); - if (nvme_delete_queue(nvmeq, opcode)) + for (; i > 0; i--, sent++) + if (nvme_delete_queue(dev->queues[i], opcode)) break; - ++sent; - } + while (sent--) { timeout = wait_for_completion_io_timeout(&dev->ioq_wait, timeout); if (timeout == 0) @@ -1693,11 +1688,12 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_stop_queues(&dev->ctrl); csts = readl(dev->bar + NVME_REG_CSTS); } + + for (i = dev->queue_count - 1; i > 0; i--) + nvme_suspend_queue(dev->queues[i]); + if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) { - for (i = dev->queue_count - 1; i >= 0; i--) { - struct nvme_queue *nvmeq = dev->queues[i]; - nvme_suspend_queue(nvmeq); - } + nvme_suspend_queue(dev->queues[0]); } else { nvme_disable_io_queues(dev); nvme_disable_admin_queue(dev, shutdown); -- cgit v1.2.3 From 82469c59d222f839ded5cd282172258e026f9112 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Tue, 6 Sep 2016 17:39:13 -0300 Subject: nvme: Don't suspend admin queue that wasn't created This fixes a regression in my previous commit c21377f8366c ("nvme: Suspend all queues before deletion"), which provoked an Oops in the removal path when removing a device that became IO incapable very early at probe (i.e. after a failed EEH recovery). Turns out, if the error occurred very early at the probe path, before even configuring the admin queue, we might try to suspend the uninitialized admin queue, accessing bad memory. Fixes: c21377f8366c ("nvme: Suspend all queues before deletion") Signed-off-by: Gabriel Krisman Bertazi Reviewed-by: Jay Freyensee Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 7 ++++++- 1 file changed, 6 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 8dcf5a960951..be84a84a40f7 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1693,7 +1693,12 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_suspend_queue(dev->queues[i]); if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) { - nvme_suspend_queue(dev->queues[0]); + /* A device might become IO incapable very soon during + * probe, before the admin queue is configured. Thus, + * queue_count can be 0 here. + */ + if (dev->queue_count) + nvme_suspend_queue(dev->queues[0]); } else { nvme_disable_io_queues(dev); nvme_disable_admin_queue(dev, shutdown); -- cgit v1.2.3 From 015282c9eb6da05bfad6ff009078f91e06c0c98f Mon Sep 17 00:00:00 2001 From: Wenbo Wang Date: Thu, 8 Sep 2016 12:12:11 -0400 Subject: nvme/quirk: Add a delay before checking device ready for memblaze device Signed-off-by: Wenbo Wang Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/nvme/host/pci.c') diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index be84a84a40f7..60f7eab11865 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2117,6 +2117,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_IDENTIFY_CNS, }, { PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, + { PCI_DEVICE(0x1c5f, 0x0540), /* Memblaze Pblaze4 adapter */ + .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) }, { 0, } -- cgit v1.2.3