[PATCH 07/10] drm/i915/perf: allowing opening the perf stream without sampling

[Lionel Landwerlin]

We want to allow a user to configure the OA hardware so that
MI_RECORD_PERF_COUNT is functional but without having to deal with the
OA buffer.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin at intel.com>
---
 drivers/gpu/drm/i915/i915_perf.c | 40 ++++++++++++++++++++++++++++++----------
 1 file changed, 30 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 5abc54dff1ad..c1d95101ed81 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -453,6 +453,8 @@ static bool oa_buffer_check_unlocked(struct drm_i915_private *dev_priv)
 	u32 head, hw_tail, aged_tail, aging_tail;
 	u64 now;
 
+	GEM_BUG_ON(!dev_priv->perf.oa.exclusive_stream->sample_flags);
+
 	/* We have to consider the (unlikely) possibility that read() errors
 	 * could result in an OA buffer reset which might reset the head,
 	 * tails[] and aged_tail state.
@@ -1818,6 +1820,7 @@ static int gen8_enable_metric_set(struct drm_i915_private *dev_priv,
 				  const struct i915_perf_stream *stream)
 {
 	struct i915_oa_config *oa_config = stream->oa_config;
+	u32 oa_debug_value = 0;
 	int ret;
 
 	/*
@@ -1844,11 +1847,22 @@ static int gen8_enable_metric_set(struct drm_i915_private *dev_priv,
 	 * RPT_ID field.
 	 */
 	if (IS_GEN9(dev_priv) || IS_GEN10(dev_priv)) {
-		I915_WRITE(GEN8_OA_DEBUG,
-			   _MASKED_BIT_ENABLE(GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
-					      GEN9_OA_DEBUG_INCLUDE_CLK_RATIO));
+		oa_debug_value |=
+			_MASKED_BIT_ENABLE(GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
+					   GEN9_OA_DEBUG_INCLUDE_CLK_RATIO);
 	}
 
+	/*
+	 * If the user didn't require OA reports, instruct the hardware not to
+	 * emit ctx switch reports.
+	 */
+	oa_debug_value |=
+		(stream->sample_flags & SAMPLE_OA_REPORT) ?
+		_MASKED_BIT_ENABLE(GEN9_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS) :
+		_MASKED_BIT_DISABLE(GEN9_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
+
+	I915_WRITE(GEN8_OA_DEBUG, oa_debug_value);
+
 	/*
 	 * Update all contexts prior writing the mux configurations as we need
 	 * to make sure all slices/subslices are ON before writing to NOA
@@ -2033,11 +2047,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		return -EINVAL;
 	}
 
-	if (!(props->sample_flags & SAMPLE_OA_REPORT)) {
-		DRM_DEBUG("Only OA report sampling supported\n");
-		return -EINVAL;
-	}
-
 	if (!dev_priv->perf.oa.ops.enable_metric_set) {
 		DRM_DEBUG("OA unit not supported\n");
 		return -ENODEV;
@@ -2081,8 +2090,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 
 	format_size = dev_priv->perf.oa.oa_formats[props->oa_format].size;
 
-	stream->sample_flags |= SAMPLE_OA_REPORT;
-	stream->sample_size += format_size;
+	if (props->sample_flags & SAMPLE_OA_REPORT) {
+		stream->sample_flags |= SAMPLE_OA_REPORT;
+		stream->sample_size += format_size;
+	}
 
 	dev_priv->perf.oa.oa_buffer.format_size = format_size;
 	if (WARN_ON(dev_priv->perf.oa.oa_buffer.format_size == 0))
@@ -2251,6 +2262,12 @@ static ssize_t i915_perf_read(struct file *file,
 	if (!stream->enabled)
 		return -EIO;
 
+	/* If the user opened the stream only to snapshot counters through
+	 * MI_RECORD_PERF_COUNT, there is nothing to read from the OA buffer.
+	 */
+	if (!stream->sample_flags)
+		return -EIO;
+
 	if (!(file->f_flags & O_NONBLOCK)) {
 		/* There's the small chance of false positives from
 		 * stream->ops->wait_unlocked.
@@ -2332,6 +2349,9 @@ static __poll_t i915_perf_poll_locked(struct drm_i915_private *dev_priv,
 {
 	__poll_t events = 0;
 
+	if (!stream->sample_flags)
+		return events;
+
 	stream->ops->poll_wait(stream, file, wait);
 
 	/* Note: we don't explicitly check whether there's something to read
-- 
2.16.2