From 203926da2bff8e172200a2f11c758987af112d4a Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Mon, 18 Apr 2022 15:02:37 +0000 Subject: [PATCH] PCI/AER: Clear MULTI_ERR_COR/UNCOR_RCV bits When a Root Port or Root Complex Event Collector receives an error Message e.g., ERR_COR, it sets PCI_ERR_ROOT_COR_RCV in the Root Error Status register and logs the Requester ID in the Error Source Identification register. If it receives a second ERR_COR Message before software clears PCI_ERR_ROOT_COR_RCV, hardware sets PCI_ERR_ROOT_MULTI_COR_RCV and the Requester ID is lost. In the following scenario, PCI_ERR_ROOT_MULTI_COR_RCV was never cleared: - hardware receives ERR_COR message - hardware sets PCI_ERR_ROOT_COR_RCV - aer_irq() entered - aer_irq(): status = pci_read_config_dword(PCI_ERR_ROOT_STATUS) - aer_irq(): now status == PCI_ERR_ROOT_COR_RCV - hardware receives second ERR_COR message - hardware sets PCI_ERR_ROOT_MULTI_COR_RCV - aer_irq(): pci_write_config_dword(PCI_ERR_ROOT_STATUS, status) - PCI_ERR_ROOT_COR_RCV is cleared; PCI_ERR_ROOT_MULTI_COR_RCV is set - aer_irq() entered again - aer_irq(): status = pci_read_config_dword(PCI_ERR_ROOT_STATUS) - aer_irq(): now status == PCI_ERR_ROOT_MULTI_COR_RCV - aer_irq() exits because PCI_ERR_ROOT_COR_RCV not set - PCI_ERR_ROOT_MULTI_COR_RCV is still set The same problem occurred with ERR_NONFATAL/ERR_FATAL Messages and PCI_ERR_ROOT_UNCOR_RCV and PCI_ERR_ROOT_MULTI_UNCOR_RCV. Fix the problem by queueing an AER event and clearing the Root Error Status bits when any of these bits are set: PCI_ERR_ROOT_COR_RCV PCI_ERR_ROOT_UNCOR_RCV PCI_ERR_ROOT_MULTI_COR_RCV PCI_ERR_ROOT_MULTI_UNCOR_RCV See the bugzilla link for details from Eric about how to reproduce this problem. [bhelgaas: commit log, move repro details to bugzilla] Fixes: e167bfcaa4cd ("PCI: aerdrv: remove magical ROOT_ERR_STATUS_MASKS") Link: https://bugzilla.kernel.org/show_bug.cgi?id=215992 Link: https://lore.kernel.org/r/20220418150237.1021519-1-sathyanarayanan.kuppuswamy@linux.intel.com Reported-by: Eric Badger Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Bjorn Helgaas Reviewed-by: Ashok Raj --- drivers/pci/pcie/aer.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 9fa1f97e5b27..7952e5efd6cf 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -101,6 +101,11 @@ struct aer_stats { #define ERR_COR_ID(d) (d & 0xffff) #define ERR_UNCOR_ID(d) (d >> 16) +#define AER_ERR_STATUS_MASK (PCI_ERR_ROOT_UNCOR_RCV | \ + PCI_ERR_ROOT_COR_RCV | \ + PCI_ERR_ROOT_MULTI_COR_RCV | \ + PCI_ERR_ROOT_MULTI_UNCOR_RCV) + static int pcie_aer_disable; static pci_ers_result_t aer_root_reset(struct pci_dev *dev); @@ -1196,7 +1201,7 @@ static irqreturn_t aer_irq(int irq, void *context) struct aer_err_source e_src = {}; pci_read_config_dword(rp, aer + PCI_ERR_ROOT_STATUS, &e_src.status); - if (!(e_src.status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV))) + if (!(e_src.status & AER_ERR_STATUS_MASK)) return IRQ_NONE; pci_read_config_dword(rp, aer + PCI_ERR_ROOT_ERR_SRC, &e_src.id);