Re: [PATCH] hack to debug acpiphp crash

[Woody Suwalski]

Igor Mammedov wrote:
> Woody thanks for testing,
>
> can you try following patch which will try to workaround NULL bus->self if it's
> a really cuplrit and print an extra debug information.
> Add following to kernel command line(make sure that CONFIG_DYNAMIC_DEBUG is enabled):
>
> dyndbg="file drivers/pci/access.c +p; file drivers/pci/hotplug/acpiphp_glue.c +p; file drivers/pci/bus.c +p; file drivers/pci/pci.c +p; file drivers/pci/setup-bus.c +p" ignore_loglevel
>
> What I find odd in you logs is that enable_slot() is called while native PCIe
> should be used. Additional info might help to understand what's going on:
>    1: 'lspci' output
>    2:  DSDT and all SSDT ACPI tables (you can use 'acpidump -b' to get them).
>
> Signed-off-by: Igor Mammedov <imammedo@xxxxxxxxxx>
> ---
>   drivers/pci/hotplug/acpiphp_glue.c | 18 +++++++++++++++++-
>   1 file changed, 17 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
> index 328d1e416014..9ce3fd9d72a9 100644
> --- a/drivers/pci/hotplug/acpiphp_glue.c
> +++ b/drivers/pci/hotplug/acpiphp_glue.c
> @@ -485,7 +485,10 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge)
>   	struct pci_bus *bus = slot->bus;
>   	struct acpiphp_func *func;
>   
> +WARN(1, "enable_slot");
> +pci_info(bus, "enable_slot bus\n");
>   	if (bridge && bus->self && hotplug_is_native(bus->self)) {
> +pr_err("enable_slot: bridge branch\n");
>   		/*
>   		 * If native hotplug is used, it will take care of hotplug
>   		 * slot management and resource allocation for hotplug
> @@ -498,8 +501,10 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge)
>   				acpiphp_native_scan_bridge(dev);
>   		}
>   	} else {
> +		LIST_HEAD(add_list);
>   		int max, pass;
>   
> +pr_err("enable_slot: acpiphp_rescan_slot branch\n");
>   		acpiphp_rescan_slot(slot);
>   		max = acpiphp_max_busnr(bus);
>   		for (pass = 0; pass < 2; pass++) {
> @@ -508,13 +513,23 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge)
>   					continue;
>   
>   				max = pci_scan_bridge(bus, dev, max, pass);
> +pci_info(dev, "enable_slot: pci_scan_bridge: max: %d\n", max);
>   				if (pass && dev->subordinate) {
>   					check_hotplug_bridge(slot, dev);
>   					pcibios_resource_survey_bus(dev->subordinate);
> +                                        if (bus->self)
> +						__pci_bus_size_bridges(dev->subordinate,
> +								       &add_list);
>   				}
>   			}
>   		}
> -		pci_assign_unassigned_bridge_resources(bus->self);
> +                if (bus->self) {
> +pci_info(bus->self, "enable_slot: pci_assign_unassigned_bridge_resources:\n");
> +			pci_assign_unassigned_bridge_resources(bus->self);
> +                } else {
> +pci_info(bus, "enable_slot: __pci_bus_assign_resources:\n");
> +			__pci_bus_assign_resources(bus, &add_list, NULL);
> +		}
>   	}
>   
>   	acpiphp_sanitize_bus(bus);
> @@ -541,6 +556,7 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge)
>   		}
>   		pci_dev_put(dev);
>   	}
> +pr_err("enable_slot: end\n");
>   }
>   
>   /**
Unfortunately the patch above does not seem to prevent the kernel crash.
Here comes the requested diagnostic info: dmesg's before and after, 
choice of lspci's and acpi tables. Hope that will help :-)

Thanks, Woody

Attachment: pcidebug.tar.xz
Description: application/xz