drm/vc4: Expose performance counters to userspace

The V3D engine has various hardware counters which might be interesting
to userspace performance analysis tools.

Expose new ioctls to create/destroy a performance monitor object and
query the counter values of this perfmance monitor.

Note that a perfomance monitor is given an ID that is only valid on the
file descriptor it has been allocated from. A performance monitor can be
attached to a CL submission and the driver will enable HW counters for
this request and update the performance monitor values at the end of the
job.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180112090926.12538-1-boris.brezillon@free-electrons.com

1 files changed, 68 insertions, 0 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 3af22936d9b3..fefa1664a9f5 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -11,6 +11,8 @@
 #include <drm/drm_encoder.h>
 #include <drm/drm_gem_cma_helper.h>
 
+#include "uapi/drm/vc4_drm.h"
+
 /* Don't forget to update vc4_bo.c: bo_type_names[] when adding to
  * this.
  */
@@ -29,6 +31,36 @@ enum vc4_kernel_bo_type {
 	VC4_BO_TYPE_COUNT
 };
 
+/* Performance monitor object. The perform lifetime is controlled by userspace
+ * using perfmon related ioctls. A perfmon can be attached to a submit_cl
+ * request, and when this is the case, HW perf counters will be activated just
+ * before the submit_cl is submitted to the GPU and disabled when the job is
+ * done. This way, only events related to a specific job will be counted.
+ */
+struct vc4_perfmon {
+	/* Tracks the number of users of the perfmon, when this counter reaches
+	 * zero the perfmon is destroyed.
+	 */
+	refcount_t refcnt;
+
+	/* Number of counters activated in this perfmon instance
+	 * (should be less than DRM_VC4_MAX_PERF_COUNTERS).
+	 */
+	u8 ncounters;
+
+	/* Events counted by the HW perf counters. */
+	u8 events[DRM_VC4_MAX_PERF_COUNTERS];
+
+	/* Storage for counter values. Counters are incremented by the HW
+	 * perf counter values every time the perfmon is attached to a GPU job.
+	 * This way, perfmon users don't have to retrieve the results after
+	 * each job if they want to track events covering several submissions.
+	 * Note that counter values can't be reset, but you can fake a reset by
+	 * destroying the perfmon and creating a new one.
+	 */
+	u64 counters[0];
+};
+
 struct vc4_dev {
 	struct drm_device *dev;
 
@@ -121,6 +153,11 @@ struct vc4_dev {
 	wait_queue_head_t job_wait_queue;
 	struct work_struct job_done_work;
 
+	/* Used to track the active perfmon if any. Access to this field is
+	 * protected by job_lock.
+	 */
+	struct vc4_perfmon *active_perfmon;
+
 	/* List of struct vc4_seqno_cb for callbacks to be made from a
 	 * workqueue when the given seqno is passed.
 	 */
@@ -406,6 +443,21 @@ struct vc4_exec_info {
 	void *uniforms_v;
 	uint32_t uniforms_p;
 	uint32_t uniforms_size;
+
+	/* Pointer to a performance monitor object if the user requested it,
+	 * NULL otherwise.
+	 */
+	struct vc4_perfmon *perfmon;
+};
+
+/* Per-open file private data. Any driver-specific resource that has to be
+ * released when the DRM file is closed should be placed here.
+ */
+struct vc4_file {
+	struct {
+		struct idr idr;
+		struct mutex lock;
+	} perfmon;
 };
 
 static inline struct vc4_exec_info *
@@ -646,3 +698,19 @@ bool vc4_check_tex_size(struct vc4_exec_info *exec,
 /* vc4_validate_shader.c */
 struct vc4_validated_shader_info *
 vc4_validate_shader(struct drm_gem_cma_object *shader_obj);
+
+/* vc4_perfmon.c */
+void vc4_perfmon_get(struct vc4_perfmon *perfmon);
+void vc4_perfmon_put(struct vc4_perfmon *perfmon);
+void vc4_perfmon_start(struct vc4_dev *vc4, struct vc4_perfmon *perfmon);
+void vc4_perfmon_stop(struct vc4_dev *vc4, struct vc4_perfmon *perfmon,
+		      bool capture);
+struct vc4_perfmon *vc4_perfmon_find(struct vc4_file *vc4file, int id);
+void vc4_perfmon_open_file(struct vc4_file *vc4file);
+void vc4_perfmon_close_file(struct vc4_file *vc4file);
+int vc4_perfmon_create_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *file_priv);
+int vc4_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+int vc4_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv);