commit 53b54ad074de1896f8b021615f65b27f557ce874 upstream.
pci_bridge_wait_for_secondary_bus() is called after a Secondary Bus Reset, but not after a DPC-induced Hot Reset.
As a result, the delays prescribed by PCIe r6.0 sec 6.6.1 are not observed and devices on the secondary bus may be accessed before they're ready.
One affected device is Intel's Ponte Vecchio HPC GPU. It comprises a PCIe switch whose upstream port is not immediately ready after reset. Because its config space is restored too early, it remains in D0uninitialized, its subordinate devices remain inaccessible and DPC recovery fails with messages such as:
i915 0000:8c:00.0: can't change power state from D3cold to D0 (config space inaccessible) intel_vsec 0000:8e:00.1: can't change power state from D3cold to D0 (config space inaccessible) pcieport 0000:89:02.0: AER: device recovery failed
Fix it.
Link: https://lore.kernel.org/r/9f5ff00e1593d8d9a4b452398b98aa14d23fca11.167376951... Tested-by: Ravi Kishore Koppuravuri ravi.kishore.koppuravuri@intel.com Signed-off-by: Lukas Wunner lukas@wunner.de Signed-off-by: Bjorn Helgaas bhelgaas@google.com Reviewed-by: Mika Westerberg mika.westerberg@linux.intel.com Cc: stable@vger.kernel.org --- drivers/pci/pci.c | 3 --- drivers/pci/pci.h | 6 ++++++ drivers/pci/pcie/dpc.c | 4 ++-- 3 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index a5bf37b7e9dc..649df298869c 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -163,9 +163,6 @@ static int __init pcie_port_pm_setup(char *str) } __setup("pcie_port_pm=", pcie_port_pm_setup);
-/* Time to wait after a reset for device to become responsive */ -#define PCIE_RESET_READY_POLL_MS 60000 - /** * pci_bus_max_busnr - returns maximum PCI bus number of given bus' children * @bus: pointer to PCI bus structure to search diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index ffad77b0e93a..72280e9b23b2 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -69,6 +69,12 @@ struct pci_cap_saved_state *pci_find_saved_ext_cap(struct pci_dev *dev, * Reset (PCIe r6.0 sec 5.8). */ #define PCI_RESET_WAIT 1000 /* msec */ +/* + * Devices may extend the 1 sec period through Request Retry Status completions + * (PCIe r6.0 sec 2.3.1). The spec does not provide an upper limit, but 60 sec + * ought to be enough for any device to become responsive. + */ +#define PCIE_RESET_READY_POLL_MS 60000 /* msec */
/** * struct pci_platform_pm_ops - Firmware PM callbacks diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index c556e7beafe3..f21d64ae4ffc 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -170,8 +170,8 @@ pci_ers_result_t dpc_reset_link(struct pci_dev *pdev) pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS, PCI_EXP_DPC_STATUS_TRIGGER);
- if (!pcie_wait_for_link(pdev, true)) { - pci_info(pdev, "Data Link Layer Link Active not set in 1000 msec\n"); + if (pci_bridge_wait_for_secondary_bus(pdev, "DPC", + PCIE_RESET_READY_POLL_MS)) { clear_bit(PCI_DPC_RECOVERED, &pdev->priv_flags); ret = PCI_ERS_RESULT_DISCONNECT; } else {