[Intel-gfx] [PATCH 11/15] drm/i915: Support opening multiple concurrent perf streams

[sourab . gupta]

From: Sourab Gupta 

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 
---
 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 119c82b..e912679 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2204,7 +2204,7 @@ struct drm_i915_private {
 
 
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];
atomic_t pollin[I915_NUM_ENGINES];
 
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index b05c41a..8eb80e8 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1086,7 +1086,7 @@ 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) {
 
@@ -1097,7 +1097,7 @@ 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] = 0x;
 
@@ -1763,7 +1763,7 @@ 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);
@@ -1777,7 +1777,7 @@ 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)
@@ -2220,14 +2220,14 @@ static void gen7_update_oacontrol_locked(struct 
drm_i915_private *dev_priv)
 {
assert_spin_locked(_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;
@@ -2366,15 +2366,6 @@ 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)) {
DRM_ERROR(
@@ -2392,6 +2383,12 @@ 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 

[Intel-gfx] [PATCH 11/15] drm/i915: Support opening multiple concurrent perf streams

[sourab . gupta]

From: Sourab Gupta 

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 
---
 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] = 0x1f;
 
@@ -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(_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]) {
+