[igt-dev] [PATCH i-g-t v1 1/4] lib/drmtest: add multi-GPU helpers for filtered devices

[Zbigniew Kempczyński]

On Thu, Nov 02, 2023 at 01:10:36PM +0100, Kamil Konieczny wrote:
> Created multiGPU helpers for filtering GPU cards.  When no
> filters used with --device or IGT_DEVICE, this will add new
> filters for discrete GPUs, otherwise will count them using user
> supplied ones.
>   Opening filtered card will allow to re-open already exiting
> one, if user gives something like:
> 
> IGT_DEVICE=pci:vendor=intel,device=discrete,card=0\;pci:vendor=intel,device=discrete,card=0
> 
> Signed-off-by: Kamil Konieczny <kamil.konieczny at linux.intel.com>
> ---
>  lib/drmtest.c | 102 ++++++++++++++++++++++++++++++++++++++++++++++++++
>  lib/drmtest.h |   3 ++
>  2 files changed, 105 insertions(+)
> 
> diff --git a/lib/drmtest.c b/lib/drmtest.c
> index e1da66c87..4425d4ca9 100644
> --- a/lib/drmtest.c
> +++ b/lib/drmtest.c
> @@ -777,6 +777,108 @@ int drm_reopen_driver(int fd)
>  	return fd;
>  }
>  
> +/**
> + * drm_get_filtered_gpu_count:
> + * @chipset: flag for one chipset to search, eg. #DRIVER_INTEL
> + *
> + * Get number of GPUs for given chipset. If used --device option or IGT_DEVICE
> + * environment variable, perform countig based on supplied filters.

s/countig/counting/

> + *
> + * Returns:
> + * Number of GPUs for given chipset or filters.
> + */
> +int drm_get_filtered_gpu_count(int chipset)
> +{
> +	struct igt_device_card card;
> +	int gpu_count;
> +	bool found;
> +	char v[16];
> +
> +	if (chipset == DRIVER_VGEM || chipset == DRIVER_ANY) {
> +		igt_debug("No multi-gpu for chipset %d\n", chipset);
> +		return 0;
> +	}
> +
> +	gpu_count = igt_device_filter_count();
> +	if (!gpu_count) {
> +		char gpu_filter[256];
> +
> +		if (chipset == DRIVER_INTEL || chipset == DRIVER_XE)
> +			strncpy(v, "Intel", sizeof(v) - 1);
> +		else
> +			strncpy(v, chipset_to_str(chipset), sizeof(v) - 1);
> +		igt_assert(snprintf(gpu_filter, sizeof(gpu_filter),
> +				    "pci:vendor=%s,device=discrete,card=all",

I think this is risky assumption. I mean discrete is not defined for
AMD and I see no reason why we limit this to discrete only.

IGT_DEVICE=pci:vendor=Intel,card=all ./xe_create --r multigpu-create-massive-size --debug

works for me when filters are passed explicitly. I think I would
use vendor + card skipping device when no filter is passed.


> +				    v) < sizeof(gpu_filter));
> +
> +		igt_device_filter_add(gpu_filter);
> +		gpu_count = igt_device_filter_count();

This is what might be confusing according to function name as it
adds (allocates) filter for !gpu_count case. And why it is on
drmtest.c and not on igt_device_scan.c?

--
Zbigniew

> +	} else {
> +		int count = 0;
> +
> +		for (int i = 0; i < gpu_count; i++) {
> +			const char *filter;
> +
> +			filter = igt_device_filter_get(i);
> +			found = igt_device_card_match(filter, &card);
> +			if (found && strlen(card.card)) {
> +				igt_debug("Found GPU%d card %s\n", i, card.card);
> +				++count;
> +			}
> +		}
> +
> +		if (count < gpu_count) {
> +			igt_debug("Counted GPUs %d lower than number of filters %d\n", count, gpu_count);
> +			gpu_count = count;
> +		}
> +	}
> +
> +	igt_debug("Found %d GPUs for chipset: %d\n", gpu_count, chipset);
> +
> +	return gpu_count;
> +}
> +
> +/**
> + * drm_open_filtered_card:
> + * @idx: index for GPU to open
> + *
> + * Open N-th GPU from filtered list
> + *
> + * Returns:
> + * Opened device or -1 if error.
> + */
> +int drm_open_filtered_card(int idx)
> +{
> +	struct igt_device_card card;
> +	const char *filter;
> +	bool found;
> +	int fd = -1;
> +
> +	if (idx < 0 || idx >= igt_device_filter_count()) {
> +		igt_debug("Invalid filter index %d\n", idx);
> +		return -1;
> +	}
> +
> +	filter = igt_device_filter_get(idx);
> +	found = igt_device_card_match(filter, &card);
> +
> +	if (found && strlen(card.card)) {
> +		fd = open(card.card, O_RDWR);
> +		igt_debug("Opened fd: %d filter idx: %d card: %s\n", fd, idx, card.card);
> +	} else {
> +		igt_debug("%s for GPU%d with filter: %s\n", found ? "Empty card name" : "Card not found", idx, filter);
> +	}
> +
> +	if (fd >= 0) {
> +		log_opened_device_path(card.card);
> +		/* Cache xe_device struct. */
> +		if (is_xe_device(fd))
> +			xe_device_get(fd);
> +	}
> +
> +	return fd;
> +}
> +
>  void igt_require_amdgpu(int fd)
>  {
>  	igt_require(is_amdgpu_device(fd));
> diff --git a/lib/drmtest.h b/lib/drmtest.h
> index 97ab6e759..992ada194 100644
> --- a/lib/drmtest.h
> +++ b/lib/drmtest.h
> @@ -109,6 +109,9 @@ int drm_close_driver(int fd);
>  
>  int drm_reopen_driver(int fd);
>  
> +int drm_get_filtered_gpu_count(int chipset);
> +int drm_open_filtered_card(int idx);
> +
>  void igt_require_amdgpu(int fd);
>  void igt_require_intel(int fd);
>  void igt_require_i915(int fd);
> -- 
> 2.42.0
>