Re: [PATCH] tests/core_hotunplug: add *-with-load subtests exercising GPU workload during hotplug

[Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>]

Hi Nitin,

On Mon, 2026-05-18 at 13:57 +0530, Nitin Gote wrote:
> The six fd-holding hot* subtests keep a DRM fd open across unbind/unplug
> but leave the GPU idle, so the kernel hotplug path is never exercised
> against an active VM, exec queue and BOs.
> 
> Add six new dedicated *-with-load subtests that run a GPU spinner across
> the unbind/unplug sequence so the device is removed while a workload is
> actively using it.
> 
> The workload helpers are driver-agnostic: igt_spin_new() dispatches
> transparently for both Xe and i915. New subtests are gated on
> workload_available(), which covers DRIVER_XE and DRIVER_INTEL, and
> returns false (SKIP) on any other driver.

While that's a good idea to skip early, I'd still pass the chipset argument
to workload_start/end() and process it with a case or if block that calls
vendor specific workload functions.  That way we invite other vendors to
contribute to this test instead of creating their own implementations.

Thanks,
Janusz

> 
> igt_spin_free() is avoided in workload_stop() since the device may be
> gone by then — igt_spin_end() writes the stop condition via a userspace
> mmap and lets the DRM fd close reclaim kernel-side resources.
> 
> Validated on BMG and DG2 with a KASAN-enabled kernel:
> all six new subtests pass with no KASAN reports.
> 
> Cc: Matthew Auld <matthew.auld@intel.com>
> Cc: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
> Cc: Kamil Konieczny <kamil.konieczny@linux.intel.com>
> Assisted-by: Copilot:claude-opus-4.7
> Signed-off-by: Nitin Gote <nitin.r.gote@intel.com>
> ---
> Hi Janusz/Kamil,
> I have introduced new subtests as per review comments in
> https://patchwork.freedesktop.org/series/166056/ 
> instead of modifying existing ones to avoid changing their scope.
> Also used driver-agnostic helper names throughout.
> 
> Thanks,
> Nitin
> 
> 
>  tests/core_hotunplug.c | 285 +++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 285 insertions(+)
> 
> diff --git a/tests/core_hotunplug.c b/tests/core_hotunplug.c
> index 7c9dae1bf..85a96294e 100644
> --- a/tests/core_hotunplug.c
> +++ b/tests/core_hotunplug.c
> @@ -80,6 +80,34 @@
>   * SUBTEST: unplug-rescan
>   * Description: Check if a device believed to be closed can be cleanly
>   *		unplugged, then restored
> + *
> + * SUBTEST: hotunbind-rebind-with-load
> + * Description: Check if the driver can be cleanly unbound from an open device
> + *		with a background GPU workload in flight, then released and
> + *		rebound
> + *
> + * SUBTEST: hotunplug-rescan-with-load
> + * Description: Check if an open device with a background GPU workload in
> + *		flight can be cleanly unplugged, then released and restored
> + *
> + * SUBTEST: hotrebind-with-load
> + * Description: Check if the driver can be cleanly rebound to a device with a
> + *		still open hot unbound driver instance while a background GPU
> + *		workload is in flight
> + *
> + * SUBTEST: hotreplug-with-load
> + * Description: Check if a hot unplugged and still open device can be cleanly
> + *		restored while a background GPU workload is in flight
> + *
> + * SUBTEST: hotrebind-lateclose-with-load
> + * Description: Check if a hot unbound driver instance still open after hot
> + *		rebind with a background GPU workload in flight can be cleanly
> + *		released
> + *
> + * SUBTEST: hotreplug-lateclose-with-load
> + * Description: Check if an instance of a still open while hot replugged
> + *		device with a background GPU workload in flight can be cleanly
> + *		released
>   */
>  
>  IGT_TEST_DESCRIPTION("Examine behavior of a driver on device hot unplug");
> @@ -565,6 +593,47 @@ static void set_filter_from_device(int fd)
>  	igt_assert_eq(igt_device_filter_add(filter), 1);
>  }
>  
> +/* GPU workload helpers */
> +
> +struct gpu_workload {
> +	igt_spin_t *spin;
> +	uint64_t ahnd;
> +};
> +
> +static bool workload_available(int chipset)
> +{
> +	return chipset == DRIVER_XE || chipset == DRIVER_INTEL;
> +}
> +
> +static void workload_start(struct hotunplug *priv, int fd,
> +			   struct gpu_workload *w)
> +{
> +	local_debug("%s\n", "starting GPU spinner");
> +	priv->failure = "GPU workload start failure!";
> +	w->ahnd = intel_allocator_open(fd, 0, INTEL_ALLOCATOR_RELOC);
> +	w->spin = igt_spin_new(fd, .ahnd = w->ahnd);
> +	priv->failure = NULL;
> +}
> +
> +static void workload_stop(struct gpu_workload *w)
> +{
> +	if (!w->spin)
> +		return;
> +
> +	/*
> +	 * The device may be gone (unbind/unplug), so avoid igt_spin_free():
> +	 * on Xe it would wait forever on a syncobj that never signals; on i915
> +	 * it would touch the dead fd via gem_munmap()/gem_close(). Instead, end
> +	 * the spinner via a userspace mmap write and let the DRM fd close
> +	 * reclaim the kernel-side resources.
> +	 */
> +	local_debug("%s\n", "stopping GPU spinner");
> +	igt_spin_end(w->spin);
> +	put_ahnd(w->ahnd);
> +	w->spin = NULL;
> +	w->ahnd = 0;
> +}
> +
>  /* Subtests */
>  
>  static void unbind_rebind(struct hotunplug *priv)
> @@ -679,6 +748,150 @@ static void hotreplug_lateclose(struct hotunplug *priv)
>  	igt_assert_f(healthcheck(priv, false), "%s\n", priv->failure);
>  }
>  
> +static void hotunbind_rebind_with_load(struct hotunplug *priv)
> +{
> +	struct gpu_workload w = { 0 };
> +
> +	pre_check(priv);
> +
> +	igt_require_f(workload_available(priv->chipset),
> +		      "No GPU workload support for this driver\n");
> +
> +	priv->fd.drm = local_drm_open_driver(false, "", " for hot unbind");
> +
> +	workload_start(priv, priv->fd.drm, &w);
> +
> +	driver_unbind(priv, "hot ", 0);
> +
> +	workload_stop(&w);
> +
> +	priv->fd.drm = close_device(priv->fd.drm, "late ", "unbound ");
> +	igt_assert_eq(priv->fd.drm, -1);
> +
> +	driver_bind(priv, 0);
> +
> +	igt_assert_f(healthcheck(priv, false), "%s\n", priv->failure);
> +}
> +
> +static void hotunplug_rescan_with_load(struct hotunplug *priv)
> +{
> +	struct gpu_workload w = { 0 };
> +
> +	pre_check(priv);
> +
> +	igt_require_f(workload_available(priv->chipset),
> +		      "No GPU workload support for this driver\n");
> +
> +	priv->fd.drm = local_drm_open_driver(false, "", " for hot unplug");
> +
> +	workload_start(priv, priv->fd.drm, &w);
> +
> +	device_unplug(priv, "hot ", 0);
> +
> +	workload_stop(&w);
> +
> +	priv->fd.drm = close_device(priv->fd.drm, "late ", "removed ");
> +	igt_assert_eq(priv->fd.drm, -1);
> +
> +	bus_rescan(priv, 0);
> +
> +	igt_assert_f(healthcheck(priv, false), "%s\n", priv->failure);
> +}
> +
> +static void hotrebind_with_load(struct hotunplug *priv)
> +{
> +	struct gpu_workload w = { 0 };
> +
> +	pre_check(priv);
> +
> +	igt_require_f(workload_available(priv->chipset),
> +		      "No GPU workload support for this driver\n");
> +
> +	priv->fd.drm = local_drm_open_driver(false, "", " for hot rebind");
> +
> +	workload_start(priv, priv->fd.drm, &w);
> +
> +	driver_unbind(priv, "hot ", 60);
> +
> +	driver_bind(priv, 0);
> +
> +	workload_stop(&w);
> +
> +	igt_assert_f(healthcheck(priv, false), "%s\n", priv->failure);
> +}
> +
> +static void hotreplug_with_load(struct hotunplug *priv)
> +{
> +	struct gpu_workload w = { 0 };
> +
> +	pre_check(priv);
> +
> +	igt_require_f(workload_available(priv->chipset),
> +		      "No GPU workload support for this driver\n");
> +
> +	priv->fd.drm = local_drm_open_driver(false, "", " for hot replug");
> +
> +	workload_start(priv, priv->fd.drm, &w);
> +
> +	device_unplug(priv, "hot ", 60);
> +
> +	bus_rescan(priv, 0);
> +
> +	workload_stop(&w);
> +
> +	igt_assert_f(healthcheck(priv, false), "%s\n", priv->failure);
> +}
> +
> +static void hotrebind_lateclose_with_load(struct hotunplug *priv)
> +{
> +	struct gpu_workload w = { 0 };
> +
> +	pre_check(priv);
> +
> +	igt_require_f(workload_available(priv->chipset),
> +		      "No GPU workload support for this driver\n");
> +
> +	priv->fd.drm = local_drm_open_driver(false, "", " for hot rebind");
> +
> +	workload_start(priv, priv->fd.drm, &w);
> +
> +	driver_unbind(priv, "hot ", 60);
> +
> +	driver_bind(priv, 0);
> +
> +	workload_stop(&w);
> +
> +	priv->fd.drm = close_device(priv->fd.drm, "late ", "unbound ");
> +	igt_assert_eq(priv->fd.drm, -1);
> +
> +	igt_assert_f(healthcheck(priv, false), "%s\n", priv->failure);
> +}
> +
> +static void hotreplug_lateclose_with_load(struct hotunplug *priv)
> +{
> +	struct gpu_workload w = { 0 };
> +
> +	pre_check(priv);
> +
> +	igt_require_f(workload_available(priv->chipset),
> +		      "No GPU workload support for this driver\n");
> +
> +	priv->fd.drm = local_drm_open_driver(false, "", " for hot replug");
> +
> +	workload_start(priv, priv->fd.drm, &w);
> +
> +	device_unplug(priv, "hot ", 60);
> +
> +	bus_rescan(priv, 0);
> +
> +	workload_stop(&w);
> +
> +	priv->fd.drm = close_device(priv->fd.drm, "late ", "removed ");
> +	igt_assert_eq(priv->fd.drm, -1);
> +
> +	igt_assert_f(healthcheck(priv, false), "%s\n", priv->failure);
> +}
> +
>  /* Main */
>  
>  int igt_main()
> @@ -817,6 +1030,78 @@ int igt_main()
>  			recover(&priv);
>  	}
>  
> +	igt_fixture()
> +		post_healthcheck(&priv);
> +
> +	igt_subtest_group() {
> +		igt_describe("Check if the driver can be cleanly unbound from an open device with a background GPU workload in flight, then released and rebound");
> +		igt_subtest("hotunbind-rebind-with-load")
> +			hotunbind_rebind_with_load(&priv);
> +
> +		igt_fixture()
> +			recover(&priv);
> +	}
> +
> +	igt_fixture()
> +		post_healthcheck(&priv);
> +
> +	igt_subtest_group() {
> +		igt_describe("Check if an open device with a background GPU workload in flight can be cleanly unplugged, then released and restored");
> +		igt_subtest("hotunplug-rescan-with-load")
> +			hotunplug_rescan_with_load(&priv);
> +
> +		igt_fixture()
> +			recover(&priv);
> +	}
> +
> +	igt_fixture()
> +		post_healthcheck(&priv);
> +
> +	igt_subtest_group() {
> +		igt_describe("Check if the driver can be cleanly rebound to a device with a still open hot unbound driver instance while a background GPU workload is in flight");
> +		igt_subtest("hotrebind-with-load")
> +			hotrebind_with_load(&priv);
> +
> +		igt_fixture()
> +			recover(&priv);
> +	}
> +
> +	igt_fixture()
> +		post_healthcheck(&priv);
> +
> +	igt_subtest_group() {
> +		igt_describe("Check if a hot unplugged and still open device can be cleanly restored while a background GPU workload is in flight");
> +		igt_subtest("hotreplug-with-load")
> +			hotreplug_with_load(&priv);
> +
> +		igt_fixture()
> +			recover(&priv);
> +	}
> +
> +	igt_fixture()
> +		post_healthcheck(&priv);
> +
> +	igt_subtest_group() {
> +		igt_describe("Check if a hot unbound driver instance still open after hot rebind with a background GPU workload in flight can be cleanly released");
> +		igt_subtest("hotrebind-lateclose-with-load")
> +			hotrebind_lateclose_with_load(&priv);
> +
> +		igt_fixture()
> +			recover(&priv);
> +	}
> +
> +	igt_fixture()
> +		post_healthcheck(&priv);
> +
> +	igt_subtest_group() {
> +		igt_describe("Check if an instance of a still open while hot replugged device with a background GPU workload in flight can be cleanly released");
> +		igt_subtest("hotreplug-lateclose-with-load")
> +			hotreplug_lateclose_with_load(&priv);
> +
> +		igt_fixture()
> +			recover(&priv);
> +	}
> +
>  	igt_fixture() {
>  		post_healthcheck(&priv);
>