[PATCH 09/11] media: hantro: Add v4l2_hw run/done traces

[Detlev Casanova <detlev.casanova@collabora.com>]

Add the trace calls as well as retrieving the number of clock cycles for
the rockchip_vpu core.

Signed-off-by: Detlev Casanova <detlev.casanova@collabora.com>
---
 drivers/media/platform/verisilicon/hantro.h            |  1 +
 drivers/media/platform/verisilicon/hantro_drv.c        | 10 ++++++++++
 .../media/platform/verisilicon/rockchip_vpu981_regs.h  |  1 +
 drivers/media/platform/verisilicon/rockchip_vpu_hw.c   |  4 ++++
 4 files changed, 16 insertions(+)

diff --git a/drivers/media/platform/verisilicon/hantro.h b/drivers/media/platform/verisilicon/hantro.h
index 0353de154a1e..d5cddc783688 100644
--- a/drivers/media/platform/verisilicon/hantro.h
+++ b/drivers/media/platform/verisilicon/hantro.h
@@ -253,6 +253,7 @@ struct hantro_ctx {
 
 	u32 sequence_cap;
 	u32 sequence_out;
+	u32 hw_cycles;
 
 	const struct hantro_fmt *vpu_src_fmt;
 	struct v4l2_pix_format_mplane src_fmt;
diff --git a/drivers/media/platform/verisilicon/hantro_drv.c b/drivers/media/platform/verisilicon/hantro_drv.c
index 94f58f4e4a4e..8dd26ca32459 100644
--- a/drivers/media/platform/verisilicon/hantro_drv.c
+++ b/drivers/media/platform/verisilicon/hantro_drv.c
@@ -25,6 +25,8 @@
 #include <media/videobuf2-core.h>
 #include <media/videobuf2-vmalloc.h>
 
+#include <trace/events/v4l2.h>
+
 #include "hantro_v4l2.h"
 #include "hantro.h"
 #include "hantro_hw.h"
@@ -103,6 +105,9 @@ void hantro_irq_done(struct hantro_dev *vpu,
 	struct hantro_ctx *ctx =
 		v4l2_m2m_get_curr_priv(vpu->m2m_dev);
 
+	if (ctx)
+		trace_v4l2_hw_done(ctx->fh.tgid, ctx->fh.fd, ctx->hw_cycles);
+
 	/*
 	 * If cancel_delayed_work returns false
 	 * the timeout expired. The watchdog is running,
@@ -125,6 +130,9 @@ void hantro_watchdog(struct work_struct *work)
 	ctx = v4l2_m2m_get_curr_priv(vpu->m2m_dev);
 	if (ctx) {
 		vpu_err("frame processing timed out!\n");
+
+		trace_v4l2_hw_done(ctx->fh.tgid, ctx->fh.fd, ctx->hw_cycles);
+
 		if (ctx->codec_ops->reset)
 			ctx->codec_ops->reset(ctx);
 		hantro_job_finish(vpu, ctx, VB2_BUF_STATE_ERROR);
@@ -189,6 +197,8 @@ static void device_run(void *priv)
 	if (ctx->codec_ops->run(ctx))
 		goto err_cancel_job;
 
+	trace_v4l2_hw_run(ctx->fh.tgid, ctx->fh.fd);
+
 	return;
 
 err_cancel_job:
diff --git a/drivers/media/platform/verisilicon/rockchip_vpu981_regs.h b/drivers/media/platform/verisilicon/rockchip_vpu981_regs.h
index e4008da64f19..96b85470208b 100644
--- a/drivers/media/platform/verisilicon/rockchip_vpu981_regs.h
+++ b/drivers/media/platform/verisilicon/rockchip_vpu981_regs.h
@@ -451,6 +451,7 @@
 #define av1_pp0_dup_ver			AV1_DEC_REG(394, 16, 0xff)
 #define av1_pp0_dup_hor			AV1_DEC_REG(394, 24, 0xff)
 
+#define AV1_CYCLE_COUNT			(AV1_SWREG(63))
 #define AV1_TILE_OUT_LU			(AV1_SWREG(65))
 #define AV1_REFERENCE_Y(i)		(AV1_SWREG(67) + ((i) * 0x8))
 #define AV1_SEGMENTATION		(AV1_SWREG(81))
diff --git a/drivers/media/platform/verisilicon/rockchip_vpu_hw.c b/drivers/media/platform/verisilicon/rockchip_vpu_hw.c
index 02673be9878e..f959151b6645 100644
--- a/drivers/media/platform/verisilicon/rockchip_vpu_hw.c
+++ b/drivers/media/platform/verisilicon/rockchip_vpu_hw.c
@@ -424,6 +424,8 @@ static irqreturn_t rk3588_vpu981_irq(int irq, void *dev_id)
 {
 	struct hantro_dev *vpu = dev_id;
 	enum vb2_buffer_state state;
+	struct hantro_ctx *ctx =
+		v4l2_m2m_get_curr_priv(vpu->m2m_dev);
 	u32 status;
 
 	status = vdpu_read(vpu, AV1_REG_INTERRUPT);
@@ -433,6 +435,8 @@ static irqreturn_t rk3588_vpu981_irq(int irq, void *dev_id)
 	vdpu_write(vpu, 0, AV1_REG_INTERRUPT);
 	vdpu_write(vpu, AV1_REG_CONFIG_DEC_CLK_GATE_E, AV1_REG_CONFIG);
 
+	ctx->hw_cycles = vdpu_read(vpu, AV1_CYCLE_COUNT);
+
 	hantro_irq_done(vpu, state);
 
 	return IRQ_HANDLED;
-- 
2.53.0