diff mbox

[09/14] drm/i915: Add support for emitting execbuffer tags through OA counter reports

Message ID 1504778774-18117-10-git-send-email-sagar.a.kamble@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

sagar.a.kamble@intel.com Sept. 7, 2017, 10:06 a.m. UTC
From: Sourab Gupta <sourab.gupta@intel.com>

This patch enables userspace to specify tags (per workload), provided via
execbuffer ioctl, which could be added to OA reports, to help associate
reports with the corresponding workloads.

There may be multiple stages within a single context, from a userspace
perspective. An ability is needed to individually associate the OA reports
with their corresponding workloads(execbuffers), which may not be possible
solely with ctx_id or pid information. This patch enables such a mechanism.

In this patch, upper 32 bits of rsvd1 field, which were previously unused
are now being used to pass in the tag.

v2: Updated i915_execbuffer2_get_tag to get the tag properly. (Sagar)
Changed tag size to 64 bit to ensure all sample fields are aligned at 8
bytes. (Lionel)
Updated last_tag for stream based on the id of perf sample as the
periodic OA reports after the request gets completed should not be
associated with any tag.

v3: Updated last_tag to INVALID_TAG during stream_init. Added definition
of i915_execbuffer2_set_tag.

Testcase: igt/intel_perf_dapc/perf-tag
Signed-off-by: Sourab Gupta <sourab.gupta@intel.com>
Signed-off-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h            | 18 +++++++++--
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 11 ++++---
 drivers/gpu/drm/i915/i915_gem_request.h    |  1 +
 drivers/gpu/drm/i915/i915_perf.c           | 50 +++++++++++++++++++++++++++---
 include/uapi/drm/i915_drm.h                | 15 +++++++++
 5 files changed, 84 insertions(+), 11 deletions(-)
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c1102fe..5c38cf5 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2043,7 +2043,8 @@  struct i915_perf_stream_ops {
 	 */
 	void (*emit_sample_capture)(struct i915_perf_stream *stream,
 				    struct drm_i915_gem_request *request,
-				    bool preallocate);
+				    bool preallocate,
+				    u32 tag);
 
 	/*
 	 * @patch_sample_capture: Patch the offsets in commands to capture perf
@@ -2130,6 +2131,7 @@  struct i915_perf_stream {
 
 	u32 last_ctx_id;
 	u64 last_pid;
+	u32 last_tag;
 };
 
 /**
@@ -2268,6 +2270,17 @@  struct i915_perf_cs_sample {
 	 * submitted, pertaining to this perf sample
 	 */
 	u64 pid;
+
+	/**
+	 * @tag: Tag associated with workload, for which the perf sample is
+	 * being collected.
+	 *
+	 * Userspace can specify tags (provided via execbuffer ioctl), which
+	 * can be associated with the perf samples, and be used to functionally
+	 * distinguish different workload stages, and associate samples with
+	 * these different stages.
+	 */
+	u32 tag;
 };
 
 struct intel_cdclk_state {
@@ -3985,7 +3998,8 @@  int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 extern void i915_perf_register(struct drm_i915_private *dev_priv);
 extern void i915_perf_unregister(struct drm_i915_private *dev_priv);
 void i915_perf_emit_sample_capture(struct drm_i915_gem_request *req,
-				   bool preallocate);
+				   bool preallocate,
+				   u32 tag);
 void i915_perf_patch_request(struct drm_i915_gem_request *request);
 void i915_perf_streams_mark_idle(struct drm_i915_private *dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index d54bfed..acd36a3 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -245,6 +245,7 @@  struct i915_execbuffer {
 	 */
 	int lut_size;
 	struct hlist_head *buckets; /** ht for relocation handles */
+	uint32_t tag;
 };
 
 #define exec_entry(EB, VMA) (&(EB)->exec[(VMA)->exec_flags - (EB)->flags])
@@ -1115,7 +1116,7 @@  static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	if (err)
 		goto err_request;
 
-	i915_perf_emit_sample_capture(rq, true);
+	i915_perf_emit_sample_capture(rq, true, eb->tag);
 
 	err = eb->engine->emit_bb_start(rq,
 					batch->node.start, PAGE_SIZE,
@@ -1123,7 +1124,7 @@  static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	if (err)
 		goto err_request;
 
-	i915_perf_emit_sample_capture(rq, false);
+	i915_perf_emit_sample_capture(rq, false, eb->tag);
 
 	GEM_BUG_ON(!reservation_object_test_signaled_rcu(batch->resv, true));
 	i915_vma_move_to_active(batch, rq, 0);
@@ -1974,7 +1975,7 @@  static int eb_submit(struct i915_execbuffer *eb)
 			return err;
 	}
 
-	i915_perf_emit_sample_capture(eb->request, true);
+	i915_perf_emit_sample_capture(eb->request, true, eb->tag);
 
 	err = eb->engine->emit_bb_start(eb->request,
 					eb->batch->node.start +
@@ -1984,7 +1985,7 @@  static int eb_submit(struct i915_execbuffer *eb)
 	if (err)
 		return err;
 
-	i915_perf_emit_sample_capture(eb->request, false);
+	i915_perf_emit_sample_capture(eb->request, false, eb->tag);
 
 	return 0;
 }
@@ -2232,6 +2233,8 @@  static int eb_submit(struct i915_execbuffer *eb)
 	if (!eb.engine)
 		return -EINVAL;
 
+	eb.tag	= i915_execbuffer2_get_tag(*args);
+
 	if (args->flags & I915_EXEC_RESOURCE_STREAMER) {
 		if (!HAS_RESOURCE_STREAMER(eb.i915)) {
 			DRM_DEBUG("RS is only allowed for Haswell, Gen8 and above\n");
diff --git a/drivers/gpu/drm/i915/i915_gem_request.h b/drivers/gpu/drm/i915/i915_gem_request.h
index c839e34..a2535c6 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.h
+++ b/drivers/gpu/drm/i915/i915_gem_request.h
@@ -199,6 +199,7 @@  struct drm_i915_gem_request {
 	u32 *pre_oa_offset;
 	u32 *post_oa_offset;
 	u64 pid;
+	u32 tag;
 };
 
 extern const struct dma_fence_ops i915_fence_ops;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index ecfcffa..b44d76e 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -283,6 +283,7 @@ 
 
 #define INVALID_CTX_ID 0xffffffff
 #define INVALID_PID    0xffffffff
+#define INVALID_TAG    0xffffffff
 
 /* On Gen8+ automatically triggered OA reports include a 'reason' field... */
 #define OAREPORT_REASON_MASK           0x3f
@@ -296,6 +297,7 @@  struct i915_perf_sample_data {
 	u64 source;
 	u64 ctx_id;
 	u64 pid;
+	u64 tag;
 	const u8 *report;
 };
 
@@ -352,6 +354,7 @@  struct i915_perf_sample_data {
 #define SAMPLE_OA_SOURCE      (1<<1)
 #define SAMPLE_CTX_ID	      (1<<2)
 #define SAMPLE_PID	      (1<<3)
+#define SAMPLE_TAG	      (1<<4)
 
 /**
  * struct perf_open_properties - for validated properties given to open a stream
@@ -500,11 +503,14 @@  static int i915_emit_oa_report_capture(struct drm_i915_gem_request *request,
  * @stream: Stream to which this request corresponds.
  * @request: request in whose context the metrics are being collected.
  * @preallocate: allocate space in ring for related sample.
+ * @tag: userspace provided tag to be associated with the perf sample
  */
 static void i915_perf_stream_emit_sample_capture(
 					struct i915_perf_stream *stream,
 					struct drm_i915_gem_request *request,
-					bool preallocate)
+					bool preallocate,
+					u32 tag)
+
 {
 	struct reservation_object *resv = stream->cs_buffer.vma->resv;
 	int ret;
@@ -518,6 +524,9 @@  static void i915_perf_stream_emit_sample_capture(
 	if (stream->sample_flags & SAMPLE_PID)
 		request->pid = current->pid;
 
+	if (stream->sample_flags & SAMPLE_TAG)
+		request->tag = tag;
+
 	reservation_object_lock(resv, NULL);
 	if (reservation_object_reserve_shared(resv) == 0)
 		reservation_object_add_shared_fence(resv, &request->fence);
@@ -532,12 +541,14 @@  static void i915_perf_stream_emit_sample_capture(
  * the command stream of a GPU engine.
  * @request: request in whose context the metrics are being collected.
  * @preallocate: allocate space in ring for related sample.
+ * @tag: userspace provided tag to be associated with the perf sample
  *
  * The function provides a hook through which the commands to capture perf
  * metrics, are inserted into the command stream of a GPU engine.
  */
 void i915_perf_emit_sample_capture(struct drm_i915_gem_request *request,
-				   bool preallocate)
+				   bool preallocate,
+				   u32 tag)
 {
 	struct drm_i915_private *dev_priv = request->i915;
 	struct i915_perf_stream *stream;
@@ -551,7 +562,8 @@  void i915_perf_emit_sample_capture(struct drm_i915_gem_request *request,
 				  &dev_priv->perf.oa.srcu);
 	if (stream && stream->enabled && stream->cs_mode)
 		stream->ops->emit_sample_capture(stream, request,
-						 preallocate);
+						 preallocate, tag);
+
 	srcu_read_unlock(&dev_priv->perf.oa.srcu, idx);
 }
 
@@ -633,6 +645,7 @@  static void i915_perf_stream_patch_request(struct i915_perf_stream *stream,
 		sample->id = sample_id;
 		sample->ctx_id = request->ctx->hw_id;
 		sample->pid = request->pid;
+		sample->tag = request->tag;
 		if (stream->sample_flags &
 		    (SAMPLE_OA_REPORT | SAMPLE_OA_SOURCE))
 			i915_perf_stream_patch_sample_oa(stream, request,
@@ -956,6 +969,12 @@  static int append_perf_sample(struct i915_perf_stream *stream,
 		buf += 8;
 	}
 
+	if (sample_flags & SAMPLE_TAG) {
+		if (copy_to_user(buf, &data->tag, 8))
+			return -EFAULT;
+		buf += 8;
+	}
+
 	if (sample_flags & SAMPLE_OA_REPORT) {
 		if (copy_to_user(buf, data->report, report_size))
 			return -EFAULT;
@@ -996,6 +1015,9 @@  static int append_oa_buffer_sample(struct i915_perf_stream *stream,
 	if (sample_flags & SAMPLE_PID)
 		data.pid = stream->last_pid;
 
+	if (sample_flags & SAMPLE_TAG)
+		data.tag = stream->last_tag;
+
 	if (sample_flags & SAMPLE_OA_REPORT)
 		data.report = report;
 
@@ -1612,6 +1634,14 @@  static int append_cs_buffer_sample(struct i915_perf_stream *stream,
 			stream->last_pid = INVALID_PID;
 	}
 
+	if (sample_flags & SAMPLE_TAG) {
+		data.tag = node->tag;
+		if (node->id == PRE_REQUEST_SAMPLE_ID)
+			stream->last_tag = node->tag;
+		else
+			stream->last_tag = INVALID_TAG;
+	}
+
 	return append_perf_sample(stream, buf, count, offset, &data);
 }
 
@@ -2844,7 +2874,8 @@  static int i915_perf_stream_init(struct i915_perf_stream *stream,
 	bool require_oa_unit = props->sample_flags & (SAMPLE_OA_REPORT |
 						      SAMPLE_OA_SOURCE);
 	bool cs_sample_data = props->sample_flags & SAMPLE_OA_REPORT;
-	bool require_cs_mode = props->sample_flags & SAMPLE_PID;
+	bool require_cs_mode = props->sample_flags & (SAMPLE_PID |
+						      SAMPLE_TAG);
 	struct i915_perf_stream *curr_stream;
 	struct intel_engine_cs *engine = NULL;
 	int ret;
@@ -3006,7 +3037,7 @@  static int i915_perf_stream_init(struct i915_perf_stream *stream,
 	}
 
 	if (require_cs_mode && !props->cs_mode) {
-		DRM_ERROR("PID sampling requires a ring to be specified");
+		DRM_ERROR("PID/TAG sampling requires a ring to be specified");
 		ret = -EINVAL;
 		goto err_enable;
 	}
@@ -3039,6 +3070,12 @@  static int i915_perf_stream_init(struct i915_perf_stream *stream,
 			stream->last_pid = INVALID_PID;
 		}
 
+		if (props->sample_flags & SAMPLE_TAG) {
+			stream->sample_flags |= SAMPLE_TAG;
+			stream->sample_size += 8;
+			stream->last_tag = INVALID_TAG;
+		}
+
 		idx = srcu_read_lock(&dev_priv->perf.oa.srcu);
 		curr_stream = srcu_dereference(
 					dev_priv->perf.oa.exclusive_stream,
@@ -3762,6 +3799,9 @@  static int read_properties_unlocked(struct drm_i915_private *dev_priv,
 		case DRM_I915_PERF_PROP_SAMPLE_PID:
 			props->sample_flags |= SAMPLE_PID;
 			break;
+		case DRM_I915_PERF_PROP_SAMPLE_TAG:
+			props->sample_flags |= SAMPLE_TAG;
+			break;
 		case DRM_I915_PERF_PROP_MAX:
 			MISSING_CASE(id);
 			return -EINVAL;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index f96ecfd..71c102e 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -966,6 +966,14 @@  struct drm_i915_gem_execbuffer2 {
 #define i915_execbuffer2_get_context_id(eb2) \
 	((eb2).rsvd1 & I915_EXEC_CONTEXT_ID_MASK)
 
+/* upper 32 bits of rsvd1 field contain tag */
+#define I915_EXEC_TAG_MASK		(0xffffffff00000000UL)
+#define i915_execbuffer2_set_tag(eb2, tag) \
+	(eb2).rsvd1 = ((eb2).rsvd1 & ~I915_EXEC_TAG_MASK) |\
+		      ((tag << 32) & I915_EXEC_TAG_MASK)
+#define i915_execbuffer2_get_tag(eb2) \
+	(((eb2).rsvd1 & I915_EXEC_TAG_MASK) >> 32)
+
 struct drm_i915_gem_pin {
 	/** Handle of the buffer to be pinned. */
 	__u32 handle;
@@ -1445,6 +1453,12 @@  enum drm_i915_perf_property_id {
 	 */
 	DRM_I915_PERF_PROP_SAMPLE_PID,
 
+	/**
+	 * The value of this property set to 1 requests inclusion of tag in the
+	 * perf sample data.
+	 */
+	DRM_I915_PERF_PROP_SAMPLE_TAG,
+
 	DRM_I915_PERF_PROP_MAX /* non-ABI */
 };
 
@@ -1513,6 +1527,7 @@  enum drm_i915_perf_record_type {
 	 *     { u64 source; } && DRM_I915_PERF_PROP_SAMPLE_OA_SOURCE
 	 *     { u64 ctx_id; } && DRM_I915_PERF_PROP_SAMPLE_CTX_ID
 	 *     { u64 pid; } && DRM_I915_PERF_PROP_SAMPLE_PID
+	 *     { u64 tag; } && DRM_I915_PERF_PROP_SAMPLE_TAG
 	 *     { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA
 	 * };
 	 */