Re: [PATCH i-g-t v4 7/7] tests/dmem_cgroups: add test for dmem.current

["Thomas Hellström" <thomas.hellstrom@linux.intel.com>]

On Fri, 2026-07-17 at 09:04 -0300, Thadeu Lima de Souza Cascardo wrote:
> Based on the work of Thomas Hellström to test dmem.max eviction, add
> a
> test for dmem.current usage after allocations and setting dmem.max.
> 
> Create a dmem cgroup, allocate close to capacity (or at most 4GiB),
> check current usage is within a small slack of the expected
> allocation.
> Then, set max to a small value and check allocations and current
> usage
> are limited to the max set.  Set max to less than a single BO size,
> then
> check no allocations are allowed and current usage is also within the
> slack. After each allocation, release memory and check current usage
> has gone down.
> 
> Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>

In what situations do you see the need for a slack? I've seen it only
when max is set close to 0. For higher max limit, the slack usage may
potentially mask bugs. Is there a way the slack can be activated only
when it's needed?

Thanks,
Thomas



> ---
>  tests/cgroup_dmem.c | 251
> +++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 246 insertions(+), 5 deletions(-)
> 
> diff --git a/tests/cgroup_dmem.c b/tests/cgroup_dmem.c
> index 442c965f9bbf..fa4694b45035 100644
> --- a/tests/cgroup_dmem.c
> +++ b/tests/cgroup_dmem.c
> @@ -1,6 +1,8 @@
>  // SPDX-License-Identifier: MIT
>  /*
>   * Copyright © 2025 Intel Corporation
> + * Copyright © 2026 Intel Corporation
> + * Copyright 2026 Valve Corporation
>   */
>  
>  /**
> @@ -17,10 +19,214 @@
>   * Test category: uapi
>   */
>  
> +#include <errno.h>
>  #include <inttypes.h>
> +#include <signal.h>
> +#include <stdatomic.h>
> +#include <stdint.h>
> +#include <stdlib.h>
> +#include <string.h>
> +#include <unistd.h>
>  
> +#include "drmtest.h"
>  #include "igt.h"
> +#include "igt_aux.h"
>  #include "igt_cgroup.h"
> +#include "igt_dmem_driver.h"
> +
> +#define BO_SIZE			SZ_64M
> +#define MAX_LIMIT		((uint64_t)4 * SZ_1G)
> +#define USAGE_SLACK		SZ_4M		/* tolerance above
> the set max */
> +#define USAGE_POLL_MS		10
> +#define USAGE_DROP_TIMEOUT_MS	1000
> +
> +/**
> + * SUBTEST: simple
> + * DESCRIPTION:
> + *  Creates a cgroup, moves the process into it, enumerates all dmem
> regions,
> + *  prints their capacity, system-wide current usage, per-cgroup
> current usage
> + *  and configured limits, then destroys the cgroup.
> + */
> +
> +/**
> + * SUBTEST: current
> + * DESCRIPTION:
> + *  Create a dmem cgroup, allocate close to capacity (or at most
> 4GiB),
> + *  check current usage is within a small slack of the expected
> allocation.
> + *  Then, set max to a small value and check allocations and current
> usage
> + *  are limited to the max set.
> + *  Set max to less than a single BO size, then check no allocations
> are allowed
> + *  and current usage is also within the slack.
> + *  After each allocation, release memory and check current usage
> has gone
> + *  down.
> + * REQUIREMENTS: xe or amdgpu device with at least one VRAM region
> + */
> +
> +static uint64_t wait_for_usage_drop(struct igt_cgroup *cg, const
> char *region,
> +				    uint64_t limit)
> +{
> +	uint64_t current;
> +	unsigned int elapsed = 0;
> +
> +	do {
> +		igt_cgroup_dmem_get_current(cg, region, &current);
> +		if (current <= limit)
> +			return current;
> +		usleep(USAGE_POLL_MS * 1000);
> +		elapsed += USAGE_POLL_MS;
> +	} while (elapsed < USAGE_DROP_TIMEOUT_MS);
> +
> +	return current;
> +}
> +
> +static int allocate_vram(const struct igt_dmem_driver *drv, void
> *ctx, int fd, int max_bo, size_t len)
> +{
> +	int n_bo, err = 0;
> +	for (n_bo = 0; n_bo < max_bo; n_bo++) {
> +		err = drv->allocate_vram(ctx, n_bo, len);
> +		if (err)
> +			break;
> +	}
> +	/* These are expected failures we can ignore. */
> +	if (err == -ENOMEM || err == -ENOSPC)
> +		err = 0;
> +	return err ?: n_bo;
> +}
> +
> +static void free_vram(const struct igt_dmem_driver *drv, void *ctx,
> int max_bo)
> +{
> +	int i;
> +	for (i = 0; i < max_bo; i++)
> +		drv->free_vram(ctx, i);
> +}
> +
> +static void test_current(int fd, char *cg_region, unsigned int
> flags, const struct igt_dmem_driver *drv)
> +{
> +	struct igt_cgroup *cg;
> +	void *ctx;
> +	uint64_t current, capacity, cg_max;
> +	int n_bo = 0, max_bo;
> +	int err;
> +
> +	igt_cgroup_dmem_get_capacity(cg_region, &capacity);
> +	igt_require_f(capacity >= 4 * BO_SIZE,
> +		      "VRAM capacity (%"PRIu64" MiB) too small to
> test\n",
> +		      capacity / SZ_1M);
> +
> +	/*
> +	 * Use up to 4 GiB, or the full capacity if the device has
> less.
> +	 * Leave one BO_SIZE worth of headroom so the device isn't
> completely
> +	 * exhausted before the cgroup limit is hit.
> +	 */
> +	cg_max = min(MAX_LIMIT, capacity - BO_SIZE - USAGE_SLACK);
> +	cg_max = ALIGN_DOWN(cg_max, BO_SIZE);
> +
> +	/* Create cgroup and move into it */
> +	cg = igt_cgroup_new("igt_cgroups_test");
> +	igt_cgroup_move_current(cg);
> +
> +	max_bo = cg_max / BO_SIZE;
> +
> +	err = drv->init(&ctx, fd, max_bo);
> +	igt_assert_f(!err, "Failed to initialize driver");
> +
> +	n_bo = allocate_vram(drv, ctx, fd, max_bo, BO_SIZE);
> +	igt_assert_f(n_bo > 0, "failed to allocate VRAM\n");
> +
> +	igt_cgroup_dmem_get_current(cg, cg_region, &current);
> +	igt_debug("After fill: cgroup current = %"PRIu64" MiB, "
> +		  "max = %"PRIu64" MiB\n",
> +		  current / SZ_1M, cg_max / SZ_1M);
> +	igt_assert_f(current < cg_max + USAGE_SLACK && current >
> cg_max - USAGE_SLACK,
> +		     "current usage (%"PRIu64" MiB) is not within
> margin of allocation (%"PRIu64" MiB)\n",
> +		     current / SZ_1M, cg_max / SZ_1M);
> +
> +	free_vram(drv, ctx, n_bo);
> +	wait_for_usage_drop(cg, cg_region, USAGE_SLACK);
> +
> +	igt_cgroup_dmem_get_current(cg, cg_region, &current);
> +	igt_debug("After free: cgroup current = %"PRIu64" MiB, "
> +		  "max = %"PRIu64" MiB\n",
> +		  current / SZ_1M, cg_max / SZ_1M);
> +	igt_assert_f(current < USAGE_SLACK,
> +		     "current usage (%"PRIu64" MiB) is not within
> margin (%d MiB)\n",
> +		     current / SZ_1M, USAGE_SLACK / SZ_1M);
> +
> +	/* Allow for a slack as there might be some extra pages
> allocated. */
> +	igt_cgroup_dmem_set_max(cg, cg_region, 2 * BO_SIZE +
> USAGE_SLACK, false);
> +
> +	n_bo = allocate_vram(drv, ctx, fd, max_bo, BO_SIZE);
> +	igt_assert_f(n_bo > 0, "failed to allocate VRAM\n");
> +
> +	igt_cgroup_dmem_get_current(cg, cg_region, &current);
> +	igt_debug("After fill: cgroup current = %"PRIu64" MiB, "
> +		  "max = %"PRIu64" MiB\n",
> +		  current / SZ_1M, cg_max / SZ_1M);
> +	igt_assert_f(current < 2 * BO_SIZE + USAGE_SLACK && current
> > 2 * BO_SIZE - USAGE_SLACK,
> +		     "current usage (%"PRIu64" MiB) is not within
> margin of allocation (%"PRIu64" MiB)\n",
> +		     current / SZ_1M, cg_max / SZ_1M);
> +
> +	free_vram(drv, ctx, n_bo);
> +	wait_for_usage_drop(cg, cg_region, USAGE_SLACK);
> +
> +	igt_cgroup_dmem_get_current(cg, cg_region, &current);
> +	igt_debug("After free: cgroup current = %"PRIu64" MiB, "
> +		  "max = %"PRIu64" MiB\n",
> +		  current / SZ_1M, cg_max / SZ_1M);
> +	igt_assert_f(current < USAGE_SLACK,
> +		     "current usage (%"PRIu64" MiB) is not within
> margin (%d MiB)\n",
> +		     current / SZ_1M, USAGE_SLACK / SZ_1M);
> +
> +	igt_cgroup_dmem_set_max(cg, cg_region, USAGE_SLACK, false);
> +
> +	n_bo = allocate_vram(drv, ctx, fd, max_bo, BO_SIZE);
> +
> +	/*
> +	 * amdgpu may succeed the allocation, by falling back to
> GTT, so no assertion here.
> +	 * Verify by reading current usage.
> +	 */
> +
> +	igt_cgroup_dmem_get_current(cg, cg_region, &current);
> +	igt_debug("After fill: cgroup current = %"PRIu64" MiB, "
> +		  "max = %"PRIu64" MiB\n",
> +		  current / SZ_1M, cg_max / SZ_1M);
> +	igt_assert_f(current < USAGE_SLACK,
> +		     "current usage (%"PRIu64" MiB) is not within
> margin\n",
> +		     current / SZ_1M);
> +
> +	if (n_bo > 0)
> +		free_vram(drv, ctx, n_bo);
> +	wait_for_usage_drop(cg, cg_region, USAGE_SLACK);
> +
> +	igt_cgroup_dmem_get_current(cg, cg_region, &current);
> +	igt_debug("After free: cgroup current = %"PRIu64" MiB, "
> +		  "max = %"PRIu64" MiB\n",
> +		  current / SZ_1M, cg_max / SZ_1M);
> +	igt_assert_f(current < USAGE_SLACK,
> +		     "current usage (%"PRIu64" MiB) is not within
> margin (%d MiB)\n",
> +		     current / SZ_1M, USAGE_SLACK / SZ_1M);
> +
> +	drv->deinit(ctx);
> +	igt_cgroup_free(cg);
> +}
> +
> +static const struct {
> +	const char *name;
> +	void (*test_fn)(int fd, char *cg_region, unsigned int flags,
> const struct igt_dmem_driver *drv);
> +	unsigned int flags;
> +} subtests[] = {
> +	{ "current", test_current, 0 },
> +	{ }
> +};
> +
> +static const struct {
> +	int driver_flag;
> +	const struct igt_dmem_driver *driver;
> +} drivers[] = {
> +	{ DRIVER_XE, &xe_dmem_driver },
> +	{ DRIVER_AMDGPU, &amdgpu_dmem_driver },
> +	{ },
> +};
>  
>  IGT_TEST_DESCRIPTION("Exercises the cgroup v2 dmem controller
> interface.");
>  
> @@ -32,7 +238,7 @@ static void fmt_bytes(uint64_t v, char *buf,
> size_t len)
>  		snprintf(buf, len, "%" PRIu64, v);
>  }
>  
> -int igt_simple_main()
> +static void simple_cgroup(void)
>  {
>  	struct igt_cgroup *cg;
>  	const char *region;
> @@ -42,10 +248,6 @@ int igt_simple_main()
>  	char min_s[32], low_s[32], max_s[32];
>  	int i;
>  
> -	igt_require_f(igt_cgroup_dmem_available(),
> -		      "No dmem regions found; is cgroup v2 with the
> "
> -		      "dmem controller available?\n");
> -
>  	cg = igt_cgroup_new("igt-cgroup-dmem-test");
>  	igt_assert_f(cg, "Failed to create cgroup\n");
>  
> @@ -90,3 +292,42 @@ int igt_simple_main()
>  	igt_cgroup_dmem_regions_free(regions);
>  	igt_cgroup_free(cg);
>  }
> +
> +int igt_main()
> +{
> +	igt_fixture() {
> +		igt_require_f(getuid() == 0, "Test requires
> root\n");
> +		/* Check dmem cgroup controller is available before
> doing anything else */
> +		igt_require_f(igt_cgroup_dmem_available(),
> +			      "dmem cgroup controller not available
> (no cgroup v2 or no registered regions)\n");
> +
> +	}
> +
> +	igt_subtest("simple")
> +		simple_cgroup();
> +
> +	for (int d = 0; drivers[d].driver; d++) {
> +		igt_subtest_group() {
> +			int fd = -1;
> +			char *cg_region;
> +			igt_fixture() {
> +				fd =
> drm_open_driver(drivers[d].driver_flag);
> +				igt_require_f(fd >= 0,
> +					"No %s device found,
> skipping\n",
> +					drivers[d].driver->name);
> +				cg_region = drivers[d].driver-
> >get_region_name(fd);
> +				igt_require_f(cg_region, "Region not
> tracked by dmem cgroup controller\n");
> +			}
> +
> +			for (int i = 0; subtests[i].name; i++)
> +				igt_subtest_f("%s-%s",
> drivers[d].driver->name, subtests[i].name)
> +					subtests[i].test_fn(fd,
> cg_region, subtests[i].flags, drivers[d].driver);
> +
> +			igt_fixture() {
> +				if (fd >= 0)
> +					drm_close_driver(fd);
> +				free(cg_region);
> +			}
> +		}
> +	}
> +}