drm/v3d: Expose performance counters to userspace

The V3D engine has several hardware performance counters that can of
interest for userspace performance analysis tools.

This exposes new ioctls to create and destroy performance monitor
objects, as well as to query the counter values.

Each created performance monitor object has an ID that can be attached
to CL/CSD submissions, so the driver enables the requested counters when
the job is submitted, and updates the performance monitor values when
the job is done.

It is up to the user to ensure all the jobs have been finished before
getting the performance monitor values. It is also up to the user to
properly synchronize BCL jobs when submitting jobs with different
performance monitors attached.

Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: Emma Anholt <emma@anholt.net>
To: dri-devel@lists.freedesktop.org
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Acked-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210608111541.461991-1-jasuarez@igalia.com

1 files changed, 136 insertions, 0 deletions

diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h
index 1ce746e228d9..4104f22fb3d3 100644
--- a/include/uapi/drm/v3d_drm.h
+++ b/include/uapi/drm/v3d_drm.h
@@ -38,6 +38,9 @@ extern "C" {
 #define DRM_V3D_GET_BO_OFFSET                     0x05
 #define DRM_V3D_SUBMIT_TFU                        0x06
 #define DRM_V3D_SUBMIT_CSD                        0x07
+#define DRM_V3D_PERFMON_CREATE                    0x08
+#define DRM_V3D_PERFMON_DESTROY                   0x09
+#define DRM_V3D_PERFMON_GET_VALUES                0x0a
 
 #define DRM_IOCTL_V3D_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CL, struct drm_v3d_submit_cl)
 #define DRM_IOCTL_V3D_WAIT_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_WAIT_BO, struct drm_v3d_wait_bo)
@@ -47,6 +50,12 @@ extern "C" {
 #define DRM_IOCTL_V3D_GET_BO_OFFSET       DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_BO_OFFSET, struct drm_v3d_get_bo_offset)
 #define DRM_IOCTL_V3D_SUBMIT_TFU          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_TFU, struct drm_v3d_submit_tfu)
 #define DRM_IOCTL_V3D_SUBMIT_CSD          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CSD, struct drm_v3d_submit_csd)
+#define DRM_IOCTL_V3D_PERFMON_CREATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_CREATE, \
+						   struct drm_v3d_perfmon_create)
+#define DRM_IOCTL_V3D_PERFMON_DESTROY     DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_DESTROY, \
+						   struct drm_v3d_perfmon_destroy)
+#define DRM_IOCTL_V3D_PERFMON_GET_VALUES  DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_GET_VALUES, \
+						   struct drm_v3d_perfmon_get_values)
 
 #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE             0x01
 
@@ -127,6 +136,11 @@ struct drm_v3d_submit_cl {
 	__u32 bo_handle_count;
 
 	__u32 flags;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmon_id;
+
+	__u32 pad;
 };
 
 /**
@@ -195,6 +209,7 @@ enum drm_v3d_param {
 	DRM_V3D_PARAM_SUPPORTS_TFU,
 	DRM_V3D_PARAM_SUPPORTS_CSD,
 	DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH,
+	DRM_V3D_PARAM_SUPPORTS_PERFMON,
 };
 
 struct drm_v3d_get_param {
@@ -258,6 +273,127 @@ struct drm_v3d_submit_csd {
 	__u32 in_sync;
 	/* Sync object to signal when the CSD job is done. */
 	__u32 out_sync;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmon_id;
+};
+
+enum {
+	V3D_PERFCNT_FEP_VALID_PRIMTS_NO_PIXELS,
+	V3D_PERFCNT_FEP_VALID_PRIMS,
+	V3D_PERFCNT_FEP_EZ_NFCLIP_QUADS,
+	V3D_PERFCNT_FEP_VALID_QUADS,
+	V3D_PERFCNT_TLB_QUADS_STENCIL_FAIL,
+	V3D_PERFCNT_TLB_QUADS_STENCILZ_FAIL,
+	V3D_PERFCNT_TLB_QUADS_STENCILZ_PASS,
+	V3D_PERFCNT_TLB_QUADS_ZERO_COV,
+	V3D_PERFCNT_TLB_QUADS_NONZERO_COV,
+	V3D_PERFCNT_TLB_QUADS_WRITTEN,
+	V3D_PERFCNT_PTB_PRIM_VIEWPOINT_DISCARD,
+	V3D_PERFCNT_PTB_PRIM_CLIP,
+	V3D_PERFCNT_PTB_PRIM_REV,
+	V3D_PERFCNT_QPU_IDLE_CYCLES,
+	V3D_PERFCNT_QPU_ACTIVE_CYCLES_VERTEX_COORD_USER,
+	V3D_PERFCNT_QPU_ACTIVE_CYCLES_FRAG,
+	V3D_PERFCNT_QPU_CYCLES_VALID_INSTR,
+	V3D_PERFCNT_QPU_CYCLES_TMU_STALL,
+	V3D_PERFCNT_QPU_CYCLES_SCOREBOARD_STALL,
+	V3D_PERFCNT_QPU_CYCLES_VARYINGS_STALL,
+	V3D_PERFCNT_QPU_IC_HIT,
+	V3D_PERFCNT_QPU_IC_MISS,
+	V3D_PERFCNT_QPU_UC_HIT,
+	V3D_PERFCNT_QPU_UC_MISS,
+	V3D_PERFCNT_TMU_TCACHE_ACCESS,
+	V3D_PERFCNT_TMU_TCACHE_MISS,
+	V3D_PERFCNT_VPM_VDW_STALL,
+	V3D_PERFCNT_VPM_VCD_STALL,
+	V3D_PERFCNT_BIN_ACTIVE,
+	V3D_PERFCNT_RDR_ACTIVE,
+	V3D_PERFCNT_L2T_HITS,
+	V3D_PERFCNT_L2T_MISSES,
+	V3D_PERFCNT_CYCLE_COUNT,
+	V3D_PERFCNT_QPU_CYCLES_STALLED_VERTEX_COORD_USER,
+	V3D_PERFCNT_QPU_CYCLES_STALLED_FRAGMENT,
+	V3D_PERFCNT_PTB_PRIMS_BINNED,
+	V3D_PERFCNT_AXI_WRITES_WATCH_0,
+	V3D_PERFCNT_AXI_READS_WATCH_0,
+	V3D_PERFCNT_AXI_WRITE_STALLS_WATCH_0,
+	V3D_PERFCNT_AXI_READ_STALLS_WATCH_0,
+	V3D_PERFCNT_AXI_WRITE_BYTES_WATCH_0,
+	V3D_PERFCNT_AXI_READ_BYTES_WATCH_0,
+	V3D_PERFCNT_AXI_WRITES_WATCH_1,
+	V3D_PERFCNT_AXI_READS_WATCH_1,
+	V3D_PERFCNT_AXI_WRITE_STALLS_WATCH_1,
+	V3D_PERFCNT_AXI_READ_STALLS_WATCH_1,
+	V3D_PERFCNT_AXI_WRITE_BYTES_WATCH_1,
+	V3D_PERFCNT_AXI_READ_BYTES_WATCH_1,
+	V3D_PERFCNT_TLB_PARTIAL_QUADS,
+	V3D_PERFCNT_TMU_CONFIG_ACCESSES,
+	V3D_PERFCNT_L2T_NO_ID_STALL,
+	V3D_PERFCNT_L2T_COM_QUE_STALL,
+	V3D_PERFCNT_L2T_TMU_WRITES,
+	V3D_PERFCNT_TMU_ACTIVE_CYCLES,
+	V3D_PERFCNT_TMU_STALLED_CYCLES,
+	V3D_PERFCNT_CLE_ACTIVE,
+	V3D_PERFCNT_L2T_TMU_READS,
+	V3D_PERFCNT_L2T_CLE_READS,
+	V3D_PERFCNT_L2T_VCD_READS,
+	V3D_PERFCNT_L2T_TMUCFG_READS,
+	V3D_PERFCNT_L2T_SLC0_READS,
+	V3D_PERFCNT_L2T_SLC1_READS,
+	V3D_PERFCNT_L2T_SLC2_READS,
+	V3D_PERFCNT_L2T_TMU_W_MISSES,
+	V3D_PERFCNT_L2T_TMU_R_MISSES,
+	V3D_PERFCNT_L2T_CLE_MISSES,
+	V3D_PERFCNT_L2T_VCD_MISSES,
+	V3D_PERFCNT_L2T_TMUCFG_MISSES,
+	V3D_PERFCNT_L2T_SLC0_MISSES,
+	V3D_PERFCNT_L2T_SLC1_MISSES,
+	V3D_PERFCNT_L2T_SLC2_MISSES,
+	V3D_PERFCNT_CORE_MEM_WRITES,
+	V3D_PERFCNT_L2T_MEM_WRITES,
+	V3D_PERFCNT_PTB_MEM_WRITES,
+	V3D_PERFCNT_TLB_MEM_WRITES,
+	V3D_PERFCNT_CORE_MEM_READS,
+	V3D_PERFCNT_L2T_MEM_READS,
+	V3D_PERFCNT_PTB_MEM_READS,
+	V3D_PERFCNT_PSE_MEM_READS,
+	V3D_PERFCNT_TLB_MEM_READS,
+	V3D_PERFCNT_GMP_MEM_READS,
+	V3D_PERFCNT_PTB_W_MEM_WORDS,
+	V3D_PERFCNT_TLB_W_MEM_WORDS,
+	V3D_PERFCNT_PSE_R_MEM_WORDS,
+	V3D_PERFCNT_TLB_R_MEM_WORDS,
+	V3D_PERFCNT_TMU_MRU_HITS,
+	V3D_PERFCNT_COMPUTE_ACTIVE,
+	V3D_PERFCNT_NUM,
+};
+
+#define DRM_V3D_MAX_PERF_COUNTERS                 32
+
+struct drm_v3d_perfmon_create {
+	__u32 id;
+	__u32 ncounters;
+	__u8 counters[DRM_V3D_MAX_PERF_COUNTERS];
+};
+
+struct drm_v3d_perfmon_destroy {
+	__u32 id;
+};
+
+/*
+ * Returns the values of the performance counters tracked by this
+ * perfmon (as an array of ncounters u64 values).
+ *
+ * No implicit synchronization is performed, so the user has to
+ * guarantee that any jobs using this perfmon have already been
+ * completed  (probably by blocking on the seqno returned by the
+ * last exec that used the perfmon).
+ */
+struct drm_v3d_perfmon_get_values {
+	__u32 id;
+	__u32 pad;
+	__u64 values_ptr;
 };
 
 #if defined(__cplusplus)