From: Sourab Gupta <sourab.gupta@xxxxxxxxx>
This patch introduces flags and adds support for having pid output with
the OA reports generated through the RCS commands.
When the stream is opened with pid sample type, the pid information is also
captured through the command stream samples and forwarded along with the
OA reports.
v2: Changed payload field pid to u64 to keep all sample data aligned at 8
bytes. (Lionel)
Signed-off-by: Sourab Gupta <sourab.gupta@xxxxxxxxx>
Signed-off-by: Sagar Arun Kamble <sagar.a.kamble@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_drv.h | 7 ++++++
drivers/gpu/drm/i915/i915_perf.c | 48 +++++++++++++++++++++++++++++++++++++++-
include/uapi/drm/i915_drm.h | 7 ++++++
3 files changed, 61 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 6c011f3..b56ea20 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2079,6 +2079,7 @@ struct i915_perf_stream {
bool pollin;
u32 last_ctx_id;
+ u32 last_pid;
};
/**
@@ -2189,6 +2190,12 @@ struct i915_perf_cs_sample {
* @ctx_id: Context ID associated with this perf sample
*/
u32 ctx_id;
+
+ /**
+ * @pid: PID of the process in context of which the workload was
+ * submitted, pertaining to this perf sample
+ */
+ u32 pid;
};
struct intel_cdclk_state {
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 1f5ebdb..5ac1a41 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -293,6 +293,7 @@
struct i915_perf_sample_data {
u64 source;
u64 ctx_id;
+ u64 pid;
const u8 *report;
};
@@ -348,6 +349,7 @@ struct i915_perf_sample_data {
#define SAMPLE_OA_REPORT (1<<0)
#define SAMPLE_OA_SOURCE (1<<1)
#define SAMPLE_CTX_ID (1<<2)
+#define SAMPLE_PID (1<<3)
/**
* struct perf_open_properties - for validated properties given to open a stream
@@ -608,6 +610,7 @@ static void i915_perf_stream_emit_sample_capture(
sample->request = i915_gem_request_get(request);
sample->ctx_id = request->ctx->hw_id;
+ sample->pid = current->pid;
insert_perf_sample(stream, sample);
@@ -924,6 +927,12 @@ static int append_perf_sample(struct i915_perf_stream *stream,
buf += 8;
}
+ if (sample_flags & SAMPLE_PID) {
+ if (copy_to_user(buf, &data->pid, 8))
+ return -EFAULT;
+ buf += 8;
+ }
+
if (sample_flags & SAMPLE_OA_REPORT) {
if (copy_to_user(buf, data->report, report_size))
return -EFAULT;
@@ -961,6 +970,9 @@ static int append_oa_buffer_sample(struct i915_perf_stream *stream,
data.ctx_id = dev_priv->perf.oa.ops.get_ctx_id(stream, report);
}
+ if (sample_flags & SAMPLE_PID)
+ data.pid = stream->last_pid;
+
if (sample_flags & SAMPLE_OA_REPORT)
data.report = report;
@@ -1558,6 +1570,11 @@ static int append_cs_buffer_sample(struct i915_perf_stream *stream,
stream->last_ctx_id = data.ctx_id;
}
+ if (sample_flags & SAMPLE_PID) {
+ data.pid = node->pid;
+ stream->last_pid = node->pid;
+ }
+
return append_perf_sample(stream, buf, count, offset, &data);
}
@@ -2719,6 +2736,7 @@ static int i915_perf_stream_init(struct i915_perf_stream *stream,
struct drm_i915_private *dev_priv = stream->dev_priv;
bool require_oa_unit = props->sample_flags & (SAMPLE_OA_REPORT |
SAMPLE_OA_SOURCE);
+ bool require_cs_mode = props->sample_flags & SAMPLE_PID;
bool cs_sample_data = props->sample_flags & SAMPLE_OA_REPORT;
struct i915_perf_stream *curr_stream;
struct intel_engine_cs *engine = NULL;
@@ -2866,6 +2884,20 @@ static int i915_perf_stream_init(struct i915_perf_stream *stream,
if (props->sample_flags & SAMPLE_CTX_ID) {
stream->sample_flags |= SAMPLE_CTX_ID;
stream->sample_size += 8;
+
+ /*
+ * NB: it's meaningful to request SAMPLE_CTX_ID with just CS
+ * mode or periodic OA mode sampling but we don't allow
+ * SAMPLE_CTX_ID without either mode
+ */
+ if (!require_oa_unit)
+ require_cs_mode = true;
+ }
+
+ if (require_cs_mode && !props->cs_mode) {
+ DRM_ERROR("PID sampling requires a ring to be specified");
+ ret = -EINVAL;
+ goto err_enable;
}
if (props->cs_mode) {
@@ -2875,12 +2907,23 @@ static int i915_perf_stream_init(struct i915_perf_stream *stream,
goto err_enable;
}
- if (!(props->sample_flags & SAMPLE_CTX_ID)) {
+ /*
+ * The only time we should allow enabling CS mode if it's not
+ * strictly required, is if SAMPLE_CTX_ID has been requested
+ * as it's usable with periodic OA or CS sampling.
+ */
+ if (!require_cs_mode &&
+ !(props->sample_flags & SAMPLE_CTX_ID)) {
DRM_ERROR("Stream engine given without requesting any CS specific property\n");
ret = -EINVAL;
goto err_enable;
}
+ if (props->sample_flags & SAMPLE_PID) {
+ stream->sample_flags |= SAMPLE_PID;
+ stream->sample_size += 8;
+ }
+
engine = dev_priv->engine[props->engine];
idx = srcu_read_lock(&engine->perf_srcu);
@@ -3595,6 +3638,9 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv,
case DRM_I915_PERF_PROP_SAMPLE_CTX_ID:
props->sample_flags |= SAMPLE_CTX_ID;
break;
+ case DRM_I915_PERF_PROP_SAMPLE_PID:
+ props->sample_flags |= SAMPLE_PID;
+ 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 768b1a5..34d8e41 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1408,6 +1408,12 @@ enum drm_i915_perf_property_id {
*/
DRM_I915_PERF_PROP_SAMPLE_CTX_ID,
+ /**
+ * The value of this property set to 1 requests inclusion of pid in the
+ * perf sample data.
+ */
+ DRM_I915_PERF_PROP_SAMPLE_PID,
+
DRM_I915_PERF_PROP_MAX /* non-ABI */
};
@@ -1475,6 +1481,7 @@ 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
* { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA
* };
*/
--
1.9.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
