[Intel-gfx] [RFC 2/4] drm/i915/perf: Add support for collecting 64 bit timestamps with OA reports

[Sagar Arun Kamble]

From: Sourab Gupta <sourab.gupta at intel.com>

With this patch, for RCS, timestamps and OA reports can be collected
together, and provided to userspace in separate sample fields.
Next patch adds changes to derive timestamp from OA report.

v2: Rebase. Limiting the changes to only OA sample read. Updated sample
flag name.

Signed-off-by: Sourab Gupta <sourab.gupta at intel.com>
Signed-off-by: Sagar Arun Kamble <sagar.a.kamble at intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Sourab Gupta <sourab.gupta at intel.com>
Cc: Matthew Auld <matthew.auld at intel.com>
---
 drivers/gpu/drm/i915/i915_perf.c | 20 +++++++++++++++++++-
 include/uapi/drm/i915_drm.h      |  7 +++++++
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 72ddc34..f7e748c 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -293,6 +293,7 @@
 #define OAREPORT_REASON_CTX_SWITCH     (1<<3)
 #define OAREPORT_REASON_CLK_RATIO      (1<<5)
 
+#define I915_PERF_TS_SAMPLE_SIZE	8
 
 /* For sysctl proc_dointvec_minmax of i915_oa_max_sample_rate
  *
@@ -333,7 +334,8 @@
 	[I915_OA_FORMAT_C4_B8]		    = { 7, 64 },
 };
 
-#define SAMPLE_OA_REPORT      (1<<0)
+#define SAMPLE_OA_REPORT	BIT(0)
+#define SAMPLE_GPU_TS		BIT(1)
 
 /**
  * struct perf_open_properties - for validated properties given to open a stream
@@ -599,6 +601,7 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 	int report_size = dev_priv->perf.oa.oa_buffer.format_size;
 	struct drm_i915_perf_record_header header;
 	u32 sample_flags = stream->sample_flags;
+	u64 gpu_ts = 0;
 
 	header.type = DRM_I915_PERF_RECORD_SAMPLE;
 	header.pad = 0;
@@ -615,6 +618,13 @@ static int append_oa_sample(struct i915_perf_stream *stream,
 	if (sample_flags & SAMPLE_OA_REPORT) {
 		if (copy_to_user(buf, report, report_size))
 			return -EFAULT;
+		buf += report_size;
+	}
+
+	if (sample_flags & SAMPLE_GPU_TS) {
+		/* Timestamp to be populated from OA report */
+		if (copy_to_user(buf, &gpu_ts, I915_PERF_TS_SAMPLE_SIZE))
+			return -EFAULT;
 	}
 
 	(*offset) += header.size;
@@ -2100,6 +2110,11 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	stream->sample_flags |= SAMPLE_OA_REPORT;
 	stream->sample_size += format_size;
 
+	if (props->sample_flags & SAMPLE_GPU_TS) {
+		stream->sample_flags |= SAMPLE_GPU_TS;
+		stream->sample_size += I915_PERF_TS_SAMPLE_SIZE;
+	}
+
 	dev_priv->perf.oa.oa_buffer.format_size = format_size;
 	if (WARN_ON(dev_priv->perf.oa.oa_buffer.format_size == 0))
 		return -EINVAL;
@@ -2815,6 +2830,9 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv,
 		case DRM_I915_PERF_PROP_SAMPLE_OA:
 			props->sample_flags |= SAMPLE_OA_REPORT;
 			break;
+		case DRM_I915_PERF_PROP_SAMPLE_GPU_TS:
+			props->sample_flags |= SAMPLE_GPU_TS;
+			break;
 		case DRM_I915_PERF_PROP_OA_METRICS_SET:
 			if (value == 0) {
 				DRM_DEBUG("Unknown OA metric set ID\n");
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index b579859..0b9249e 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1447,6 +1447,12 @@ enum drm_i915_perf_property_id {
 	DRM_I915_PERF_PROP_SAMPLE_OA,
 
 	/**
+	 * The value of this property set to 1 requests inclusion of GPU
+	 * timestamp in the perf sample data.
+	 */
+	DRM_I915_PERF_PROP_SAMPLE_GPU_TS,
+
+	/**
 	 * The value specifies which set of OA unit metrics should be
 	 * be configured, defining the contents of any OA unit reports.
 	 */
@@ -1532,6 +1538,7 @@ enum drm_i915_perf_record_type {
 	 *     struct drm_i915_perf_record_header header;
 	 *
 	 *     { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA
+	 *     { u64 gpu_timestamp; } && DRM_I915_PERF_PROP_SAMPLE_GPU_TS
 	 * };
 	 */
 	DRM_I915_PERF_RECORD_SAMPLE = 1,
-- 
1.9.1