[igt-dev] [PATCH i-g-t v2 2/2] test/xe_pm: Add vram_d3cold_threshold subtest

[Rodrigo Vivi]

On Fri, Aug 11, 2023 at 04:40:26PM +0530, Anshuman Gupta wrote:
> Adding a vram_d3cold_threshold subtest, which creates a Xe bo and
> set the vram_d3cold_threshold according to vram used and bo size.
> Test setups the d3cold and expect card to be limited to d3hot.
> 
> v2:
> - Add subtest doc.
> v3:
> - skip the test on igfx. [Riana]
> - Test doc enhancement. [Riana]
> - Create the bo before vram query. [Riana]
> - Use xe_bo_map insead of xe_bo_mmap_offset and mmap. [Riana]
> - Close the bo handle. [Riana]
> v3:
> - Restore the vram_d3cold_threshold value. [Badal]
> - Don't fail the test if there is no vram_d3cold_threshold.
> - Test d3cold after closing the xe BO.
> v4:
> - When d3cold is not allowed, don't use out_of_d3() as device will
>   be runtime suspended.
> - Set vram_d3cold_threshold to vram_used + Xe BO size such that
>   it can enter to d3cold after freeing up the Xe BO.
> - Use forcewake handle to wake the device.
> 
> Signed-off-by: Anshuman Gupta <anshuman.gupta at intel.com>
> ---
>  tests/xe/xe_pm.c | 128 +++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 128 insertions(+)
> 
> diff --git a/tests/xe/xe_pm.c b/tests/xe/xe_pm.c
> index 23b8246ed..480382f9e 100644
> --- a/tests/xe/xe_pm.c
> +++ b/tests/xe/xe_pm.c
> @@ -19,6 +19,7 @@
>  #include "igt.h"
>  #include "lib/igt_device.h"
>  #include "lib/igt_pm.h"
> +#include "lib/igt_sysfs.h"
>  #include "lib/igt_syncobj.h"
>  #include "lib/intel_reg.h"
>  
> @@ -30,12 +31,16 @@
>  #define NO_SUSPEND -1
>  #define NO_RPM -1
>  
> +#define SIZE (4096 * 1024)
> +
>  typedef struct {
>  	int fd_xe;
>  	struct pci_device *pci_xe;
>  	struct pci_device *pci_root;
>  } device_t;
>  
> +uint64_t orig_threshold;
> +
>  /* runtime_usage is only available if kernel build CONFIG_PM_ADVANCED_DEBUG */
>  static bool runtime_usage_available(struct pci_device *pci)
>  {
> @@ -76,6 +81,49 @@ static void set_d3cold_allowed(struct pci_device *pci,
>  	close(fd);
>  }
>  
> +static uint64_t get_vram_d3cold_threshold(int sysfs)
> +{
> +	uint64_t threshold;
> +	char path[64];
> +	int ret;
> +
> +	sprintf(path, "device/vram_d3cold_threshold");
> +	igt_require_f(!faccessat(sysfs, path, R_OK, 0), "vram_d3cold_threshold is not present\n");
> +
> +	ret = igt_sysfs_scanf(sysfs, path, "%lu", &threshold);
> +	igt_assert(ret > 0);
> +
> +	return threshold;
> +}
> +
> +static void set_vram_d3cold_threshold(int sysfs, uint64_t threshold)
> +{
> +	char path[64];
> +	int ret;
> +
> +	sprintf(path, "device/vram_d3cold_threshold");
> +
> +	if (!faccessat(sysfs, path, R_OK | W_OK, 0))
> +		ret = igt_sysfs_printf(sysfs, path, "%lu", threshold);
> +	else
> +		igt_warn("vram_d3cold_threshold is not present\n");
> +
> +	igt_assert(ret > 0);
> +}
> +
> +static void vram_d3cold_threshold_restore(int sig)
> +{
> +	int fd, sysfs_fd;
> +
> +	fd = drm_open_driver(DRIVER_XE);
> +	sysfs_fd = igt_sysfs_open(fd);
> +
> +	set_vram_d3cold_threshold(sysfs_fd, orig_threshold);
> +
> +	close(sysfs_fd);
> +	close(fd);
> +}
> +
>  static bool setup_d3(device_t device, enum igt_acpi_d_state state)
>  {
>  	switch (state) {
> @@ -341,11 +389,82 @@ NULL));
>  		igt_assert(in_d3(device, d_state));
>  }
>  
> +/**
> + * SUBTEST: vram-d3cold-threshold
> + * Description:
> + *	Validate whether card is limited to d3hot while vram used
> + *	is greater than vram_d3cold_threshold.
> + * Run type: FULL
> + */
> +static void test_vram_d3cold_threshold(device_t device, int sysfs_fd)
> +{
> +	struct drm_xe_query_mem_usage *mem_usage;
> +	struct drm_xe_device_query query = {
> +		.extensions = 0,
> +		.query = DRM_XE_DEVICE_QUERY_MEM_USAGE,
> +		.size = 0,
> +		.data = 0,
> +	};
> +	uint64_t vram_used_mb = 0, vram_total_mb = 0, threshold;
> +	uint32_t bo, flags;
> +	int handle, i;
> +	bool active;
> +	void *map;
> +
> +	igt_require(xe_has_vram(device.fd_xe));
> +
> +	flags = vram_memory(device.fd_xe, 0);
> +	igt_require_f(flags, "Device doesn't support vram memory region\n");
> +
> +	igt_assert_eq(igt_ioctl(device.fd_xe, DRM_IOCTL_XE_DEVICE_QUERY, &query), 0);
> +	igt_assert_neq(query.size, 0);
> +
> +	mem_usage = malloc(query.size);
> +	igt_assert(mem_usage);
> +
> +	query.data = to_user_pointer(mem_usage);
> +	igt_assert_eq(igt_ioctl(device.fd_xe, DRM_IOCTL_XE_DEVICE_QUERY, &query), 0);
> +
> +	for (i = 0; i < mem_usage->num_regions; i++) {
> +		if (mem_usage->regions[i].mem_class == XE_MEM_REGION_CLASS_VRAM) {
> +			vram_used_mb +=  (mem_usage->regions[i].used / (1024 * 1024));
> +			vram_total_mb += (mem_usage->regions[i].total_size / (1024 * 1024));
> +		}
> +	}
> +
> +	threshold = vram_used_mb + (SIZE / 1024 /1024);
> +	igt_require(threshold < vram_total_mb);
> +
> +	bo = xe_bo_create_flags(device.fd_xe, 0, SIZE, flags);
> +	map = xe_bo_map(device.fd_xe, bo, SIZE);
> +	memset(map, 0, SIZE);
> +	munmap(map, SIZE);
> +	set_vram_d3cold_threshold(sysfs_fd, threshold);
> +
> +	/* Setup D3Cold but card should be in D3hot */
> +	igt_assert(setup_d3(device, IGT_ACPI_D3Cold));
> +	sleep(1);
> +	igt_assert(in_d3(device, IGT_ACPI_D3Hot));
> +	igt_assert(igt_pm_get_acpi_real_d_state(device.pci_root) == IGT_ACPI_D0);
> +	gem_close(device.fd_xe, bo);
> +
> +	/* open and close fw handle to wake the device */

hmmm I would expect that we should wake the device with mem_access when cleaning
up the stuff...
Maybe I'm wrong, but I'm in the process of moving the mem_access to xe_pm,
documenting it and taking care of other suspicious cases like xe_exec without VM.

https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/551 assigned for myself.

But anyway, while I don't get to that, let's move with this patch as is.
Maybe adding an "XXX" along with the comment line above? up to you.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi at intel.com>

> +	handle = igt_debugfs_open(device.fd_xe, "forcewake_all", O_RDONLY);
> +	igt_assert(handle >= 0);
> +	active = igt_get_runtime_pm_status() == IGT_RUNTIME_PM_STATUS_ACTIVE;
> +	close(handle);
> +	igt_assert(active);
> +
> +	/* Test D3Cold again after freeing up the Xe BO */
> +	igt_assert(in_d3(device, IGT_ACPI_D3Cold));
> +}
> +
>  igt_main
>  {
>  	struct drm_xe_engine_class_instance *hwe;
>  	device_t device;
>  	char d3cold_allowed[2];
> +	int sysfs_fd;
>  	const struct s_state {
>  		const char *name;
>  		enum igt_suspend_state state;
> @@ -378,6 +497,7 @@ igt_main
>  
>  		get_d3cold_allowed(device.pci_xe, d3cold_allowed);
>  		igt_assert(igt_setup_runtime_pm(device.fd_xe));
> +		sysfs_fd = igt_sysfs_open(device.fd_xe);
>  	}
>  
>  	for (const struct s_state *s = s_states; s->name; s++) {
> @@ -437,7 +557,15 @@ igt_main
>  		}
>  	}
>  
> +	igt_describe("Validate whether card is limited to d3hot, if vram used > vram threshold");
> +	igt_subtest("vram-d3cold-threshold") {
> +		orig_threshold = get_vram_d3cold_threshold(sysfs_fd);
> +		igt_install_exit_handler(vram_d3cold_threshold_restore);
> +		test_vram_d3cold_threshold(device, sysfs_fd);
> +	}
> +
>  	igt_fixture {
> +		close(sysfs_fd);
>  		set_d3cold_allowed(device.pci_xe, d3cold_allowed);
>  		igt_restore_runtime_pm();
>  		xe_device_put(device.fd_xe);
> -- 
> 2.25.1
>