[14/16] drm/i915: Support opening multiple concurrent perf streams

Submitted by sourab.gupta@intel.com on April 22, 2016, 11:34 a.m.

Details

Message ID 1461324845-25755-15-git-send-email-sourab.gupta@intel.com
State New
Headers show
Series "Framework to collect command stream gpu metrics using i915 perf" ( rev: 1 ) in Intel GFX

Not browsing as part of any series.

Commit Message

sourab.gupta@intel.com April 22, 2016, 11:34 a.m.
From: Sourab Gupta <sourab.gupta@intel.com>

This patch adds support for opening multiple concurrent perf streams for
different gpu engines, while having the restriction to open only a single
stream open for a particular gpu engine.
This enables userspace client to open multiple streams, one per engine,
at any time to capture sample data for multiple gpu engines.

Signed-off-by: Sourab Gupta <sourab.gupta@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h  |  2 +-
 drivers/gpu/drm/i915/i915_perf.c | 65 ++++++++++++++++++++++------------------
 2 files changed, 37 insertions(+), 30 deletions(-)

Patch hide | download patch | download mbox

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2ac07fb..0923a17 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2141,7 +2141,7 @@  struct drm_i915_private {
 		spinlock_t hook_lock;
 
 		struct hrtimer poll_check_timer;
-		struct i915_perf_stream *exclusive_stream;
+		struct i915_perf_stream *ring_stream[I915_NUM_ENGINES];
 		wait_queue_head_t poll_wq[I915_NUM_ENGINES];
 
 		struct {
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2bf9cf0..abb9d04 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1545,7 +1545,7 @@  static void i915_ring_stream_destroy(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *dev_priv = stream->dev_priv;
 
-	BUG_ON(stream != dev_priv->perf.exclusive_stream);
+	BUG_ON(stream != dev_priv->perf.ring_stream[stream->engine]);
 
 	if (stream->using_oa) {
 		dev_priv->perf.oa.ops.disable_metric_set(dev_priv);
@@ -1559,7 +1559,7 @@  static void i915_ring_stream_destroy(struct i915_perf_stream *stream)
 	if (stream->cs_mode)
 		free_command_stream_buf(dev_priv, stream->engine);
 
-	dev_priv->perf.exclusive_stream = NULL;
+	dev_priv->perf.ring_stream[stream->engine] = NULL;
 }
 
 static void *vmap_oa_buffer(struct drm_i915_gem_object *obj)
@@ -1983,13 +1983,13 @@  static void gen7_update_oacontrol_locked(struct drm_i915_private *dev_priv)
 {
 	assert_spin_locked(&dev_priv->perf.hook_lock);
 
-	if (dev_priv->perf.exclusive_stream->enabled) {
+	if (dev_priv->perf.ring_stream[RCS]->enabled) {
 		unsigned long ctx_id = 0;
 
-		if (dev_priv->perf.exclusive_stream->ctx)
+		if (dev_priv->perf.ring_stream[RCS]->ctx)
 			ctx_id = dev_priv->perf.oa.specific_ctx_id;
 
-		if (dev_priv->perf.exclusive_stream->ctx == NULL || ctx_id) {
+		if (dev_priv->perf.ring_stream[RCS]->ctx == NULL || ctx_id) {
 			bool periodic = dev_priv->perf.oa.periodic;
 			u32 period_exponent = dev_priv->perf.oa.period_exponent;
 			u32 report_format = dev_priv->perf.oa.oa_buffer.format;
@@ -2105,15 +2105,6 @@  static int i915_ring_stream_init(struct i915_perf_stream *stream,
 							SAMPLE_TS);
 	int ret;
 
-	/* To avoid the complexity of having to accurately filter
-	 * counter reports and marshal to the appropriate client
-	 * we currently only allow exclusive access
-	 */
-	if (dev_priv->perf.exclusive_stream) {
-		DRM_ERROR("Stream already in use\n");
-		return -EBUSY;
-	}
-
 	if ((props->sample_flags & SAMPLE_CTX_ID) && !props->cs_mode) {
 		if (IS_HASWELL(dev_priv->dev)) {
 			DRM_ERROR(
@@ -2131,6 +2122,12 @@  static int i915_ring_stream_init(struct i915_perf_stream *stream,
 	if (require_oa_unit) {
 		int format_size;
 
+		/* Only allow exclusive access per stream */
+		if (dev_priv->perf.ring_stream[RCS]) {
+			DRM_ERROR("Stream:0 already in use\n");
+			return -EBUSY;
+		}
+
 		if (!dev_priv->perf.oa.ops.init_oa_buffer) {
 			DRM_ERROR("OA unit not supported\n");
 			return -ENODEV;
@@ -2260,6 +2257,13 @@  static int i915_ring_stream_init(struct i915_perf_stream *stream,
 	}
 
 	if (props->cs_mode) {
+		/* Only allow exclusive access per stream */
+		if (dev_priv->perf.ring_stream[props->engine]) {
+			DRM_ERROR("Stream:%d already in use\n", props->engine);
+			ret = -EBUSY;
+			goto cs_error;
+		}
+
 		if (!cs_sample_data) {
 			DRM_ERROR(
 				"Ring given without requesting any CS data to sample");
@@ -2311,7 +2315,7 @@  static int i915_ring_stream_init(struct i915_perf_stream *stream,
 	 */
 	dev_priv->perf.oa.gen7_latched_oastatus1 = 0;
 
-	dev_priv->perf.exclusive_stream = stream;
+	dev_priv->perf.ring_stream[stream->engine] = stream;
 
 	return 0;
 
@@ -2345,8 +2349,8 @@  static void i915_oa_context_pin_notify_locked(struct drm_i915_private *dev_priv,
 	    dev_priv->perf.oa.ops.update_hw_ctx_id_locked == NULL)
 		return;
 
-	if (dev_priv->perf.exclusive_stream &&
-	    dev_priv->perf.exclusive_stream->ctx == context) {
+	if (dev_priv->perf.ring_stream[RCS] &&
+	    dev_priv->perf.ring_stream[RCS]->ctx == context) {
 		struct drm_i915_gem_object *obj =
 			context->legacy_hw_ctx.rcs_state;
 		u32 ctx_id = i915_gem_obj_ggtt_offset(obj);
@@ -2415,8 +2419,8 @@  void i915_oa_legacy_ctx_switch_notify(struct drm_i915_gem_request *req)
 	if (dev_priv->perf.oa.ops.legacy_ctx_switch_unlocked == NULL)
 		return;
 
-	if (dev_priv->perf.exclusive_stream &&
-	    dev_priv->perf.exclusive_stream->enabled) {
+	if (dev_priv->perf.ring_stream[RCS] &&
+	    dev_priv->perf.ring_stream[RCS]->enabled) {
 
 		/* XXX: We don't take a lock here and this may run
 		 * async with respect to stream methods. Notably we
@@ -2560,23 +2564,26 @@  static ssize_t i915_perf_read(struct file *file,
 	return ret;
 }
 
-static enum hrtimer_restart poll_check_timer_cb(struct hrtimer *hrtimer)
+static void wake_up_perf_streams(void *data, async_cookie_t cookie)
 {
+	struct drm_i915_private *dev_priv = data;
 	struct i915_perf_stream *stream;
 
-	struct drm_i915_private *dev_priv =
-		container_of(hrtimer, typeof(*dev_priv),
-			     perf.poll_check_timer);
-
-	/* No need to protect the streams list here, since the hrtimer is
-	 * disabled before the stream is removed from list, and currently a
-	 * single exclusive_stream is supported.
-	 * XXX: revisit this when multiple concurrent streams are supported.
-	 */
+	mutex_lock(&dev_priv->perf.streams_lock);
 	list_for_each_entry(stream, &dev_priv->perf.streams, link) {
 		if (stream_have_data__unlocked(stream))
 			wake_up(&dev_priv->perf.poll_wq[stream->engine]);
 	}
+	mutex_unlock(&dev_priv->perf.streams_lock);
+}
+
+static enum hrtimer_restart poll_check_timer_cb(struct hrtimer *hrtimer)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(hrtimer, typeof(*dev_priv),
+			     perf.poll_check_timer);
+
+	async_schedule(wake_up_perf_streams, dev_priv);
 
 	hrtimer_forward_now(hrtimer, ns_to_ktime(POLL_PERIOD));