Igt-dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
To: igt-dev@lists.freedesktop.org
Cc: Lionel G Landwerlin <lionel.g.landwerlin@linux.intel.com>
Subject: [igt-dev] [PATCH 06/30] i915/perf: Add class:instance support to OA tests
Date: Tue, 14 Feb 2023 12:59:43 -0800	[thread overview]
Message-ID: <20230214210007.2026033-7-umesh.nerlige.ramappa@intel.com> (raw)
In-Reply-To: <20230214210007.2026033-1-umesh.nerlige.ramappa@intel.com>

Add test to verify class:instance interface to perf OA.

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
---
 include/drm-uapi/i915_drm.h | 20 +++++++++++++++
 tests/i915/perf.c           | 49 +++++++++++++++++++++++++++++++++++++
 2 files changed, 69 insertions(+)

diff --git a/include/drm-uapi/i915_drm.h b/include/drm-uapi/i915_drm.h
index b71acfba..5fab3066 100644
--- a/include/drm-uapi/i915_drm.h
+++ b/include/drm-uapi/i915_drm.h
@@ -2627,6 +2627,26 @@ enum drm_i915_perf_property_id {
 	 */
 	DRM_I915_PERF_PROP_POLL_OA_PERIOD,
 
+	/**
+	 * In platforms with multiple OA buffers, the engine class instance must
+	 * be passed to open a stream to a OA unit corresponding to the engine.
+	 * Multiple engines may be mapped to the same OA unit.
+	 *
+	 * In addition to the class:instance, if a gem context is also passed, then
+	 * 1) the report headers of OA reports from other engines are squashed.
+	 * 2) OAR is enabled for the class:instance
+	 *
+	 * This property is available in perf revision 6.
+	 */
+	DRM_I915_PERF_PROP_OA_ENGINE_CLASS,
+
+	/**
+	 * This parameter specifies the engine instance.
+	 *
+	 * This property is available in perf revision 6.
+	 */
+	DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE,
+
 	DRM_I915_PERF_PROP_MAX /* non-ABI */
 };
 
diff --git a/tests/i915/perf.c b/tests/i915/perf.c
index 77bda442..13cfe895 100644
--- a/tests/i915/perf.c
+++ b/tests/i915/perf.c
@@ -1188,6 +1188,47 @@ test_invalid_open_flags(void)
 	do_ioctl_err(drm_fd, DRM_IOCTL_I915_PERF_OPEN, &param, EINVAL);
 }
 
+static void
+test_invalid_class_instance(void)
+{
+	uint64_t properties[] = {
+		DRM_I915_PERF_PROP_SAMPLE_OA, true,
+		DRM_I915_PERF_PROP_OA_METRICS_SET, test_set->perf_oa_metrics_set,
+		DRM_I915_PERF_PROP_OA_FORMAT, test_set->perf_oa_format,
+		DRM_I915_PERF_PROP_OA_EXPONENT, oa_exp_1_millisec,
+		DRM_I915_PERF_PROP_OA_ENGINE_CLASS, 0,
+		DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE, 0,
+	};
+	struct drm_i915_perf_open_param param = {
+		.flags = I915_PERF_FLAG_FD_CLOEXEC,
+		.num_properties = ARRAY_SIZE(properties) / 2,
+		.properties_ptr = to_user_pointer(properties),
+	};
+
+#define OA_E_CLASS 9
+#define OA_E_INSTANCE 11
+
+	properties[OA_E_CLASS] = I915_ENGINE_CLASS_COPY;
+	do_ioctl_err(drm_fd, DRM_IOCTL_I915_PERF_OPEN, &param, EINVAL);
+
+	properties[OA_E_CLASS] = 10;
+	do_ioctl_err(drm_fd, DRM_IOCTL_I915_PERF_OPEN, &param, EINVAL);
+
+	properties[OA_E_CLASS] = I915_ENGINE_CLASS_RENDER;
+
+	properties[OA_E_INSTANCE] = 100;
+	do_ioctl_err(drm_fd, DRM_IOCTL_I915_PERF_OPEN, &param, EINVAL);
+
+	properties[OA_E_INSTANCE] = 248;
+	do_ioctl_err(drm_fd, DRM_IOCTL_I915_PERF_OPEN, &param, EINVAL);
+
+	properties[OA_E_CLASS] = default_e2.class;
+	properties[OA_E_INSTANCE] = default_e2.instance;
+
+	stream_fd = __perf_open(drm_fd, &param, false);
+	__perf_close(stream_fd);
+}
+
 static void
 test_invalid_oa_metric_set_id(void)
 {
@@ -5305,6 +5346,14 @@ igt_main
 		}
 	}
 
+	igt_subtest_group {
+		igt_fixture igt_require(i915_perf_revision(drm_fd) >= 6);
+
+		igt_describe("Verify invalid class instance");
+		igt_subtest("gen12-invalid-class-instance")
+			test_invalid_class_instance();
+	}
+
 	igt_subtest("rc6-disable")
 		test_rc6_disable();
 
-- 
2.36.1

  parent reply	other threads:[~2023-02-14 21:00 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-14 20:59 [igt-dev] [PATCH 00/30] Enable OAM support in IGT and GPUvis Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 01/30] i915/perf: Add support for 64-bit OA formats Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 02/30] i915/perf: Define a default engine for OA Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 03/30] i915/perf: Use default engine for sseu tests Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 04/30] i915/perf: Ensure rcs0 is present for gen12-mi-rpc Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 05/30] i915/perf: Use ARRAY_SIZE for buffer-fill test Umesh Nerlige Ramappa
2023-02-14 20:59 ` Umesh Nerlige Ramappa [this message]
2023-02-14 20:59 ` [igt-dev] [PATCH 07/30] i915/perf: Enable tests to run on specific engines Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 08/30] i915/perf: Treat ticks as 64 bit Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 09/30] i915/perf: Treat timestamp as 64 bit value Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 10/30] i915/perf: Add OAM format type Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 11/30] i915/perf: Use a helper for OA format Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 12/30] i915/perf: Add support for oa perf groups Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 13/30] i915/perf: Test concurrent access to OA in different groups Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 14/30] i915/perf: Add OAM support Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 15/30] lib/perf: Make chipsets aware of oa formats Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 16/30] i915/perf: Choose OAM format for media metrics Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 17/30] lib/perf" Set missing metric unit for some counters Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 18/30] lib/perf: Add MTL to supprted HW in oa guid registry Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 19/30] lib/perf: Add support for OAM format in codegen Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 20/30] lib/perf: Update MTL GT2 metrics for OAM Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 21/30] lib/perf: Update MTL GT3 " Umesh Nerlige Ramappa
2023-02-14 20:59 ` [igt-dev] [PATCH 22/30] i915/perf: Add support for engine specific metrics Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 23/30] i915/perf: Run non-zero-reason on media engines as well Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 24/30] i915/perf: Make sanity check failures descriptive Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 25/30] lib/perf: Enable multi-tile support for perf library Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 26/30] lib/perf: Update MTL OA timestamp and EU thread config Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 27/30] lib/perf: Add support for MPEC format Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 28/30] lib/perf: Adjust the GPU timestamp for new OA formats Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 29/30] tools/perf: Choose the right card Umesh Nerlige Ramappa
2023-02-14 21:00 ` [igt-dev] [PATCH 30/30] lib/perf: Apply shift to raw timestamp as well Umesh Nerlige Ramappa
2023-02-14 21:18 ` [igt-dev] ✗ GitLab.Pipeline: warning for Enable OAM support in IGT and GPUvis Patchwork
2023-02-14 21:47 ` [igt-dev] ✓ Fi.CI.BAT: success " Patchwork
2023-02-15  0:48 ` [igt-dev] [PATCH 00/30] " Umesh Nerlige Ramappa
2023-02-15  7:22 ` [igt-dev] ✗ Fi.CI.IGT: failure for " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230214210007.2026033-7-umesh.nerlige.ramappa@intel.com \
    --to=umesh.nerlige.ramappa@intel.com \
    --cc=igt-dev@lists.freedesktop.org \
    --cc=lionel.g.landwerlin@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox