public inbox for intel-gfx@lists.freedesktop.org
 help / color / mirror / Atom feed
From: sourab.gupta@intel.com
To: intel-gfx@lists.freedesktop.org
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>,
	Sourab Gupta <sourab.gupta@intel.com>,
	Deepak S <deepak.s@intel.com>
Subject: [PATCH 11/15] drm/i915: Support opening multiple concurrent perf streams
Date: Thu,  2 Jun 2016 10:48:45 +0530	[thread overview]
Message-ID: <1464844729-2774-12-git-send-email-sourab.gupta@intel.com> (raw)
In-Reply-To: <1464844729-2774-1-git-send-email-sourab.gupta@intel.com>

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 | 69 ++++++++++++++++++++++------------------
 2 files changed, 39 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a9a123b..9ccac83 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2161,7 +2161,7 @@ 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 65b4af6..aa3589e 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -944,7 +944,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * an invalid ID. It could be good to annotate these
 		 * reports with a _CTX_SWITCH_AWAY reason later.
 		 */
-		if (!dev_priv->perf.exclusive_stream->ctx ||
+		if (!stream->ctx ||
 		    dev_priv->perf.oa.specific_ctx_id == ctx_id ||
 		    dev_priv->perf.oa.oa_buffer.last_ctx_id == ctx_id) {
 
@@ -955,7 +955,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 			 * the switch-away reports with an invalid
 			 * context id to be recognisable by userspace.
 			 */
-			if (dev_priv->perf.exclusive_stream->ctx &&
+			if (stream->ctx &&
 			    dev_priv->perf.oa.specific_ctx_id != ctx_id)
 				report32[2] = 0x1fffff;
 
@@ -1596,7 +1596,7 @@ 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);
@@ -1610,7 +1610,7 @@ 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 gen7_init_oa_buffer(struct drm_i915_private *dev_priv)
@@ -2012,14 +2012,14 @@ 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->state !=
+	if (dev_priv->perf.ring_stream[RCS]->state !=
 					I915_PERF_STREAM_DISABLED) {
 		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;
@@ -2144,15 +2144,6 @@ 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(
@@ -2170,6 +2161,12 @@ 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;
@@ -2305,6 +2302,13 @@ 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");
@@ -2345,7 +2349,7 @@ static int i915_ring_stream_init(struct i915_perf_stream *stream,
 
 	stream->ops = &i915_oa_stream_ops;
 
-	dev_priv->perf.exclusive_stream = stream;
+	dev_priv->perf.ring_stream[stream->engine] = stream;
 
 	return 0;
 
@@ -2379,8 +2383,8 @@ 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);
@@ -2449,8 +2453,8 @@ 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->state !=
+	if (dev_priv->perf.ring_stream[RCS] &&
+	    dev_priv->perf.ring_stream[RCS]->state !=
 				I915_PERF_STREAM_DISABLED) {
 
 		/* XXX: We don't take a lock here and this may run
@@ -2591,23 +2595,26 @@ 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));
 
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2016-06-02  5:17 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-02  5:18 [PATCH 00/15] Framework to collect command stream gpu metrics using i915 perf sourab.gupta
2016-06-02  5:18 ` [PATCH 01/15] drm/i915: Add ctx getparam ioctl parameter to retrieve ctx unique id sourab.gupta
2016-07-27  9:18   ` Deepak
2016-07-27 10:19     ` Daniel Vetter
2016-07-27 10:50       ` Chris Wilson
2016-07-28  9:37         ` Daniel Vetter
2016-06-02  5:18 ` [PATCH 02/15] drm/i915: Expose OA sample source to userspace sourab.gupta
2016-06-02  5:18 ` [PATCH 03/15] drm/i915: Framework for capturing command stream based OA reports sourab.gupta
2016-06-02  6:00   ` Martin Peres
2016-06-02  6:28     ` sourab gupta
2016-06-02  5:18 ` [PATCH 04/15] drm/i915: flush periodic samples, in case of no pending CS sample requests sourab.gupta
2016-06-02  5:18 ` [PATCH 05/15] drm/i915: Handle the overflow condition for command stream buf sourab.gupta
2016-06-02  5:18 ` [PATCH 06/15] drm/i915: Populate ctx ID for periodic OA reports sourab.gupta
2016-06-02  5:18 ` [PATCH 07/15] drm/i915: Add support for having pid output with OA report sourab.gupta
2016-06-02  5:18 ` [PATCH 08/15] drm/i915: Add support for emitting execbuffer tags through OA counter reports sourab.gupta
2016-06-02  5:18 ` [PATCH 09/15] drm/i915: Extend i915 perf framework for collecting timestamps on all gpu engines sourab.gupta
2016-06-02  5:18 ` [PATCH 10/15] drm/i915: Extract raw GPU timestamps from OA reports to forward in perf samples sourab.gupta
2016-06-02  5:18 ` sourab.gupta [this message]
2016-06-02  5:18 ` [PATCH 12/15] time: Expose current clocksource in use by timekeeping framework sourab.gupta
2016-06-02  5:18 ` [PATCH 13/15] time: export clocks_calc_mult_shift sourab.gupta
2016-06-02  5:18 ` [PATCH 14/15] drm/i915: Mechanism to forward clock monotonic raw time in perf samples sourab.gupta
2016-06-02  5:18 ` [PATCH 15/15] drm/i915: Support for capturing MMIO register values sourab.gupta
2016-06-03 12:08 ` ✗ Ro.CI.BAT: failure for Framework to collect command stream gpu metrics using i915 perf (rev2) Patchwork
  -- strict thread matches above, loose matches on Subject: below --
2016-11-04  9:30 [PATCH 00/15] Framework to collect command stream gpu metrics using i915 perf sourab.gupta
2016-11-04  9:30 ` [PATCH 11/15] drm/i915: Support opening multiple concurrent perf streams sourab.gupta

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1464844729-2774-12-git-send-email-sourab.gupta@intel.com \
    --to=sourab.gupta@intel.com \
    --cc=daniel.vetter@ffwll.ch \
    --cc=deepak.s@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox