From: Sourab Gupta <sourab.gu...@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.gu...@intel.com>
---
drivers/gpu/drm/i915/i915_drv.h | 2 +-
drivers/gpu/drm/i915/i915_perf.c | 41 ++++++++++++++++++++++------------------
2 files changed, 24 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 40ac362..c005ffa 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2547,7 +2547,7 @@ struct drm_i915_private {
spinlock_t hook_lock;
struct hrtimer poll_check_timer;
- struct i915_perf_stream *exclusive_stream;
+ struct i915_perf_stream *engine_stream[I915_NUM_ENGINES];
wait_queue_head_t poll_wq[I915_NUM_ENGINES];
bool pollin[I915_NUM_ENGINES];
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index d3d934e..5437d08 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1382,7 +1382,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream
*stream,
* switches since it's not-uncommon for periodic samples to
* identify a switch before any 'context switch' report.
*/
- 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 ==
dev_priv->perf.oa.specific_ctx_id) ||
@@ -1391,7 +1391,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream
*stream,
/* While filtering for a single context we avoid
* leaking the IDs of other contexts.
*/
- if (dev_priv->perf.exclusive_stream->ctx &&
+ if (stream->ctx &&
dev_priv->perf.oa.specific_ctx_id != ctx_id) {
report32[2] = INVALID_CTX_ID;
}
@@ -2190,7 +2190,7 @@ static void i915_engine_stream_destroy(struct
i915_perf_stream *stream)
{
struct drm_i915_private *dev_priv = stream->dev_priv;
- if (WARN_ON(stream != dev_priv->perf.exclusive_stream))
+ if (WARN_ON(stream != dev_priv->perf.engine_stream[stream->engine]))
return;
if (stream->using_oa) {
@@ -2208,7 +2208,7 @@ static void i915_engine_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.engine_stream[stream->engine] = NULL;
}
static void gen7_init_oa_buffer(struct drm_i915_private *dev_priv)
@@ -2755,10 +2755,10 @@ 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.engine_stream[RCS]->state !=
I915_PERF_STREAM_DISABLED) {
struct i915_gem_context *ctx =
- dev_priv->perf.exclusive_stream->ctx;
+ dev_priv->perf.engine_stream[RCS]->ctx;
u32 ctx_id = dev_priv->perf.oa.specific_ctx_id;
bool periodic = dev_priv->perf.oa.periodic;
@@ -2931,8 +2931,9 @@ static int i915_engine_stream_init(struct
i915_perf_stream *stream,
* counter reports and marshal to the appropriate client
* we currently only allow exclusive access
*/
- if (dev_priv->perf.exclusive_stream) {
- DRM_DEBUG("I915 perf stream already in use\n");
+ if (dev_priv->perf.engine_stream[props->engine]) {
+ DRM_DEBUG("I915 perf stream : %d already in use\n",
+ props->engine);
return -EBUSY;
}
@@ -3120,7 +3121,7 @@ static int i915_engine_stream_init(struct
i915_perf_stream *stream,
}
stream->ops = &i915_engine_stream_ops;
- dev_priv->perf.exclusive_stream = stream;
+ dev_priv->perf.engine_stream[stream->engine] = stream;
return 0;
@@ -3343,24 +3344,28 @@ 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)) {
dev_priv->perf.pollin[stream->engine] = true;
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
