[igt-dev] [PATCH i-g-t] lib/igt_device_scan: Rescan pci properties if PCI_SLOT_NAME wasn't found

[Petri Latvala]

On Wed, Aug 10, 2022 at 10:19:49AM +0200, Zbigniew Kempczyński wrote:
> References: https://gitlab.freedesktop.org/drm/intel/-/issues/6543
> 
> Due to lack of reproduction path of the above issue more data about
> missing PCI_SLOT_NAME property is required.
> 
> What is extremely weird when PCI_SLOT_NAME is missing udev returns some
> properties, like:
> 
> [properties]
> DEVPATH                         : /devices/pci0000:00/0000:00:02.0
> DRIVER                          : i915
> PCI_CLASS                       : 30000
> PCI_ID                          : 8086:191E
> SUBSYSTEM                       : pci
> 
> To narrow the problematic code when PCI_SLOT_NAME is missing lets dump
> kernel uevent file and retry scanning properties from udev. Retry path
> allows to detect if udev returns same list of properties.
> 
> Above doesn't fix the issue. It is providing additional information about
> devices and their properties provided from udev, especially when missing
> PCI_SLOT_NAME will strike again. It also contains warning which might
> detect situation where two scanning of properties will provide different
> results.
> 
> Signed-off-by: Zbigniew Kempczyński <zbigniew.kempczynski at intel.com>
> Cc: Petri Latvala <petri.latvala at intel.com>
> ---
>  lib/igt_device_scan.c | 48 +++++++++++++++++++++++++++++++++++++------
>  1 file changed, 42 insertions(+), 6 deletions(-)
> 
> diff --git a/lib/igt_device_scan.c b/lib/igt_device_scan.c
> index d6fae0650c..c2ecfcd3d4 100644
> --- a/lib/igt_device_scan.c
> +++ b/lib/igt_device_scan.c
> @@ -568,28 +568,54 @@ static void dump_props_and_attrs(const struct igt_device *dev)
>  	printf("\n");
>  }
>  
> +static void dump_uevent_file(struct igt_device *dev)
> +{
> +	char filename[FILENAME_MAX];
> +	const char *devpath = get_prop(dev, "DEVPATH");
> +	char *line = NULL;
> +	FILE *in;
> +	size_t n;
> +
> +	igt_assert_f(devpath, "DEVPATH property doesn't exist\n");
> +	snprintf(filename, FILENAME_MAX, "/sys%s/uevent", devpath);
> +
> +	in = fopen(filename, "r");
> +	igt_assert(in);
> +
> +	printf("[uevent: %s]\n", filename);
> +	while (getline(&line, &n, in) >= 0)
> +		printf("%s", line);

Bleh, I was going to ask you to use igt_info instead so we get the log
buffer out in the correct order, but the file already has a lot of
printfs for lsgpu's sake. Let's consider that a cleanup TODO for
later...

Reviewed-by: Petri Latvala <petri.latvala at intel.com>

> +
> +	free(line);
> +	fclose(in);
> +}
> +
>  /*
>   * Get PCI_SLOT_NAME property, it should be in format of
>   * xxxx:yy:zz.z
>   */
> -static void set_pci_slot_name(struct igt_device *dev)
> +static bool set_pci_slot_name(struct igt_device *dev)
>  {
>  	const char *pci_slot_name = get_prop(dev, "PCI_SLOT_NAME");
>  	int len;
>  
>  	if (!pci_slot_name) {
>  		dump_props_and_attrs(dev);
> -		igt_assert_f(pci_slot_name, "PCI_SLOT_NAME property == NULL\n");
> +		igt_warn("PCI_SLOT_NAME property == NULL\n");
> +		dump_uevent_file(dev);
> +		return false;
>  	}
>  
>  	len = strlen(pci_slot_name);
>  	if (len != PCI_SLOT_NAME_SIZE) {
>  		dump_props_and_attrs(dev);
> -		igt_assert_f(len != PCI_SLOT_NAME_SIZE,
> -			     "PCI_SLOT_NAME length != %d [%s]\n", len, pci_slot_name);
> +		igt_warn("PCI_SLOT_NAME length != %d [%s]\n", len, pci_slot_name);
> +		dump_uevent_file(dev);
> +		return false;
>  	}
>  
>  	dev->pci_slot_name = strdup(pci_slot_name);
> +	return true;
>  }
>  
>  /*
> @@ -649,7 +675,16 @@ static struct igt_device *igt_device_new_from_udev(struct udev_device *dev)
>  		uint16_t vendor, device;
>  
>  		set_vendor_device(idev);
> -		set_pci_slot_name(idev);
> +
> +		/*
> +		 * Very rare we observe there's no PCI_SLOT_NAME property.
> +		 * We depend on it so retry acquiring properties from udev.
> +		 */
> +		if (!set_pci_slot_name(idev)) {
> +			g_hash_table_remove_all(idev->props_ht);
> +			get_props(dev, idev);
> +			igt_assert(set_pci_slot_name(idev));
> +		}
>  		get_pci_vendor_device(idev, &vendor, &device);
>  		idev->codename = __pci_codename(vendor, device);
>  		idev->dev_type = __pci_devtype(vendor, device, idev->pci_slot_name);
> @@ -1270,7 +1305,8 @@ igt_devs_print_detail(struct igt_list_head *view,
>  			_print_key_value("codename", dev->codename);
>  		}
>  
> -		dump_props_and_attrs(dev);
> +		if (is_pci_subsystem(dev))
> +			dump_props_and_attrs(dev);
>  	}
>  }
>  
> -- 
> 2.34.1
>