From 4641a8e6e145f595059e695f0f8dbbe608134086 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Mon, 6 Jun 2022 09:53:17 -0700 Subject: [PATCH] nvme-pci: add trouble shooting steps for timeouts Many users have encountered IO timeouts with a CSTS value of 0xffffffff, which indicates a failure to read the register. While there are various potential causes for this observation, faulty NVMe APST has been the culprit quite frequently. Add the recommended troubleshooting steps in the error output when this condition occurs. Signed-off-by: Keith Busch Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 96579d4..be053d9 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1334,6 +1334,14 @@ static void nvme_warn_reset(struct nvme_dev *dev, u32 csts) dev_warn(dev->ctrl.device, "controller is down; will reset: CSTS=0x%x, PCI_STATUS read failed (%d)\n", csts, result); + + if (csts != ~0) + return; + + dev_warn(dev->ctrl.device, + "Does your device have a faulty power saving mode enabled?\n"); + dev_warn(dev->ctrl.device, + "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off\" and report a bug\n"); } static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) -- 2.7.4