[Intel-gfx] [PATCH 10/12] drm/i915: Extract raw GPU timestamps from OA reports to forward in perf samples

[Sagar Arun Kamble]

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

The OA reports contain the least significant 32 bits of the gpu timestamp.
This patch enables retrieval of the timestamp field from OA reports, to
forward as 64 bit raw gpu timestamps in the perf samples.

Signed-off-by: Sourab Gupta <sourab.gupta at intel.com>
Signed-off-by: Sagar Arun Kamble <sagar.a.kamble at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h  |  1 +
 drivers/gpu/drm/i915/i915_perf.c | 48 ++++++++++++++++++++++++++++++----------
 drivers/gpu/drm/i915/i915_reg.h  |  4 ++++
 3 files changed, 41 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0763280..c7823ff 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2656,6 +2656,7 @@ struct drm_i915_private {
 			u32 ctx_flexeu0_offset;
 			u32 n_pending_periodic_samples;
 			u32 pending_periodic_ts;
+			u64 last_gpu_ts;
 
 			/**
 			 * The RPT_ID/reason field for Gen8+ includes a bit
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2c7ab98..24d0823 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1084,6 +1084,26 @@ static int append_perf_sample(struct i915_perf_stream *stream,
 }
 
 /**
+ * get_gpu_ts_from_oa_report - Retrieve absolute gpu timestamp from OA report
+ *
+ * Note: We are assuming that we're updating last_gpu_ts frequently enough so
+ * that it's never possible to see multiple overflows before we compare
+ * sample_ts to last_gpu_ts. Since this is significantly large duration
+ * (~6min for 80ns ts base), we can safely assume so.
+ */
+static u64 get_gpu_ts_from_oa_report(struct drm_i915_private *dev_priv,
+					const u8 *report)
+{
+	u32 sample_ts = *(u32 *)(report + 4);
+	u32 delta;
+
+	delta = sample_ts - (u32)dev_priv->perf.oa.last_gpu_ts;
+	dev_priv->perf.oa.last_gpu_ts += delta;
+
+	return dev_priv->perf.oa.last_gpu_ts;
+}
+
+/**
  * append_oa_buffer_sample - Copies single periodic OA report into userspace
  * read() buffer.
  * @stream: An i915-perf stream opened for OA metrics
@@ -1115,11 +1135,8 @@ static int append_oa_buffer_sample(struct i915_perf_stream *stream,
 	if (sample_flags & SAMPLE_TAG)
 		data.tag = stream->last_tag;
 
-	/* TODO: Derive timestamp from OA report,
-	 * after scaling with the ts base
-	 */
 	if (sample_flags & SAMPLE_TS)
-		data.ts = 0;
+		data.ts = get_gpu_ts_from_oa_report(dev_priv, report);
 
 	if (sample_flags & SAMPLE_OA_REPORT)
 		data.report = report;
@@ -1693,6 +1710,7 @@ static int append_cs_buffer_sample(struct i915_perf_stream *stream,
 	struct drm_i915_private *dev_priv = stream->dev_priv;
 	struct i915_perf_sample_data data = { 0 };
 	u32 sample_flags = stream->sample_flags;
+	u64 gpu_ts = 0;
 	int ret = 0;
 
 	if (sample_flags & SAMPLE_OA_REPORT) {
@@ -1709,6 +1727,9 @@ static int append_cs_buffer_sample(struct i915_perf_stream *stream,
 						 sample_ts, U32_MAX);
 		if (ret)
 			return ret;
+
+		if (sample_flags & SAMPLE_TS)
+			gpu_ts = get_gpu_ts_from_oa_report(dev_priv, report);
 	}
 
 	if (sample_flags & SAMPLE_OA_SOURCE)
@@ -1730,16 +1751,13 @@ static int append_cs_buffer_sample(struct i915_perf_stream *stream,
 	}
 
 	if (sample_flags & SAMPLE_TS) {
-		/* For RCS, if OA samples are also being collected, derive the
-		 * timestamp from OA report, after scaling with the TS base.
+		/* If OA sampling is enabled, derive the ts from OA report.
 		 * Else, forward the timestamp collected via command stream.
 		 */
-		/* TODO: derive the timestamp from OA report */
-		if (sample_flags & SAMPLE_OA_REPORT)
-			data.ts = 0;
-		else
-			data.ts = *(u64 *) (stream->cs_buffer.vaddr +
+		if (!(sample_flags & SAMPLE_OA_REPORT))
+			gpu_ts = *(u64 *) (stream->cs_buffer.vaddr +
 					   node->ts_offset);
+		data.ts = gpu_ts;
 	}
 
 	return append_perf_sample(stream, buf, count, offset, &data);
@@ -2827,9 +2845,15 @@ static void i915_perf_stream_enable(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *dev_priv = stream->dev_priv;
 
-	if (stream->sample_flags & SAMPLE_OA_REPORT)
+	if (stream->sample_flags & SAMPLE_OA_REPORT) {
 		dev_priv->perf.oa.ops.oa_enable(dev_priv);
 
+		if (stream->sample_flags & SAMPLE_TS)
+			dev_priv->perf.oa.last_gpu_ts =
+				I915_READ64_2x32(GT_TIMESTAMP_COUNT,
+					GT_TIMESTAMP_COUNT_UDW);
+	}
+
 	if (stream->cs_mode || dev_priv->perf.oa.periodic)
 		hrtimer_start(&dev_priv->perf.poll_check_timer,
 			      ns_to_ktime(POLL_PERIOD),
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index ecd5794..05be687 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -617,6 +617,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define PS_DEPTH_COUNT                  _MMIO(0x2350)
 #define PS_DEPTH_COUNT_UDW		_MMIO(0x2350 + 4)
 
+/* Timestamp count register */
+#define GT_TIMESTAMP_COUNT		_MMIO(0x2358)
+#define GT_TIMESTAMP_COUNT_UDW		_MMIO(0x2358 + 4)
+
 /* There are the 4 64-bit counter registers, one for each stream output */
 #define GEN7_SO_NUM_PRIMS_WRITTEN(n)		_MMIO(0x5200 + (n) * 8)
 #define GEN7_SO_NUM_PRIMS_WRITTEN_UDW(n)	_MMIO(0x5200 + (n) * 8 + 4)
-- 
1.9.1