[PATCH v4 00/11] drm/msm/dpu: cleanup dpu_core_perf module

[PATCH v4 00/11] drm/msm/dpu: cleanup dpu_core_perf module

[Dmitry Baryshkov]

Apply several cleanups to the DPU's core_perf module.

Changes since v3:
- Dropped avg_bw type change (Abhinav)
- Removed core_perf from the commit cubject (Abhinav)

Changes since v2:
- Dropped perf tuning patches for now (Abhinav)
- Restored kms variable assignment in dpu_core_perf_crtc_release_bw
  (LKP)
- Fixed description for the last patch (Abhinav)

Changes since v1:
- Reworked overrides for the perf parameters instead of completely
  dropping them. Abhinav described why these overrides are useful.
- Moved max clock rate determination to dpu_kms.c

Dmitry Baryshkov (11):
  drm/msm/dpu: drop enum dpu_core_perf_data_bus_id
  drm/msm/dpu: core_perf: extract bandwidth aggregation function
  drm/msm/dpu: core_perf: bail earlier if there are no ICC paths
  drm/msm/dpu: drop separate dpu_core_perf_tune overrides
  drm/msm/dpu: rework indentation in dpu_core_perf
  drm/msm/dpu: drop the dpu_core_perf_crtc_update()'s stop_req param
  drm/msm/dpu: use dpu_perf_cfg in DPU core_perf code
  drm/msm/dpu: remove unused fields from struct dpu_core_perf
  drm/msm/dpu: remove extra clk_round_rate() call
  drm/msm/dpu: move max clock decision to dpu_kms.
  drm/msm/dpu: drop dpu_core_perf_destroy()

 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 187 +++++++-----------
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h |  48 +----
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c      |   6 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c       |  14 +-
 4 files changed, 96 insertions(+), 159 deletions(-)

-- 
2.39.2

[PATCH v4 01/11] drm/msm/dpu: drop enum dpu_core_perf_data_bus_id

[Dmitry Baryshkov]

Drop the leftover of bus-client -> interconnect conversion, the enum
dpu_core_perf_data_bus_id.

Fixes: cb88482e2570 ("drm/msm/dpu: clean up references of DPU custom bus scaling")
Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
index e3795995e145..29bb8ee2bc26 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -14,19 +14,6 @@
 
 #define	DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE	412500000
 
-/**
- * enum dpu_core_perf_data_bus_id - data bus identifier
- * @DPU_CORE_PERF_DATA_BUS_ID_MNOC: DPU/MNOC data bus
- * @DPU_CORE_PERF_DATA_BUS_ID_LLCC: MNOC/LLCC data bus
- * @DPU_CORE_PERF_DATA_BUS_ID_EBI: LLCC/EBI data bus
- */
-enum dpu_core_perf_data_bus_id {
-	DPU_CORE_PERF_DATA_BUS_ID_MNOC,
-	DPU_CORE_PERF_DATA_BUS_ID_LLCC,
-	DPU_CORE_PERF_DATA_BUS_ID_EBI,
-	DPU_CORE_PERF_DATA_BUS_ID_MAX,
-};
-
 /**
  * struct dpu_core_perf_params - definition of performance parameters
  * @max_per_pipe_ib: maximum instantaneous bandwidth request
-- 
2.39.2

[PATCH v4 02/11] drm/msm/dpu: core_perf: extract bandwidth aggregation function

[Dmitry Baryshkov]

In preparation to refactoring the dpu_core_perf debugfs interface,
extract the bandwidth aggregation function from
_dpu_core_perf_crtc_update_bus().

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 39 +++++++++++--------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 1d9d83d7b99e..333dcfe57800 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -206,33 +206,38 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
 	return 0;
 }
 
-static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
-		struct drm_crtc *crtc)
+static void dpu_core_perf_aggregate(struct drm_device *ddev,
+				    enum dpu_crtc_client_type curr_client_type,
+				    struct dpu_core_perf_params *perf)
 {
-	struct dpu_core_perf_params perf = { 0 };
-	enum dpu_crtc_client_type curr_client_type
-					= dpu_crtc_get_client_type(crtc);
-	struct drm_crtc *tmp_crtc;
 	struct dpu_crtc_state *dpu_cstate;
-	int i, ret = 0;
-	u64 avg_bw;
+	struct drm_crtc *tmp_crtc;
 
-	drm_for_each_crtc(tmp_crtc, crtc->dev) {
+	drm_for_each_crtc(tmp_crtc, ddev) {
 		if (tmp_crtc->enabled &&
-			curr_client_type ==
-				dpu_crtc_get_client_type(tmp_crtc)) {
+		    curr_client_type == dpu_crtc_get_client_type(tmp_crtc)) {
 			dpu_cstate = to_dpu_crtc_state(tmp_crtc->state);
 
-			perf.max_per_pipe_ib = max(perf.max_per_pipe_ib,
-					dpu_cstate->new_perf.max_per_pipe_ib);
+			perf->max_per_pipe_ib = max(perf->max_per_pipe_ib,
+						    dpu_cstate->new_perf.max_per_pipe_ib);
 
-			perf.bw_ctl += dpu_cstate->new_perf.bw_ctl;
+			perf->bw_ctl += dpu_cstate->new_perf.bw_ctl;
 
-			DRM_DEBUG_ATOMIC("crtc=%d bw=%llu paths:%d\n",
-				  tmp_crtc->base.id,
-				  dpu_cstate->new_perf.bw_ctl, kms->num_paths);
+			DRM_DEBUG_ATOMIC("crtc=%d bw=%llu\n",
+					 tmp_crtc->base.id,
+					 dpu_cstate->new_perf.bw_ctl);
 		}
 	}
+}
+
+static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
+		struct drm_crtc *crtc)
+{
+	struct dpu_core_perf_params perf = { 0 };
+	int i, ret = 0;
+	u64 avg_bw;
+
+	dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf);
 
 	if (!kms->num_paths)
 		return 0;
-- 
2.39.2

Re: [PATCH v4 02/11] drm/msm/dpu: core_perf: extract bandwidth aggregation function

[Abhinav Kumar]

On 7/12/2023 3:11 PM, Dmitry Baryshkov wrote:
> In preparation to refactoring the dpu_core_perf debugfs interface,
> extract the bandwidth aggregation function from
> _dpu_core_perf_crtc_update_bus().
> 
> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
> ---

Drop the core_perf tag from the subject line.

The debugfs refactor was dropped from this series if thats what you are 
referring to here.

So even this and the next patch dont serve any purpose in this series 
and should be dropped, Unless you have some reason of keeping them here.

>   drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 39 +++++++++++--------
>   1 file changed, 22 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
> index 1d9d83d7b99e..333dcfe57800 100644
> --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
> +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
> @@ -206,33 +206,38 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
>   	return 0;
>   }
>   
> -static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
> -		struct drm_crtc *crtc)
> +static void dpu_core_perf_aggregate(struct drm_device *ddev,
> +				    enum dpu_crtc_client_type curr_client_type,
> +				    struct dpu_core_perf_params *perf)
>   {
> -	struct dpu_core_perf_params perf = { 0 };
> -	enum dpu_crtc_client_type curr_client_type
> -					= dpu_crtc_get_client_type(crtc);
> -	struct drm_crtc *tmp_crtc;
>   	struct dpu_crtc_state *dpu_cstate;
> -	int i, ret = 0;
> -	u64 avg_bw;
> +	struct drm_crtc *tmp_crtc;
>   
> -	drm_for_each_crtc(tmp_crtc, crtc->dev) {
> +	drm_for_each_crtc(tmp_crtc, ddev) {
>   		if (tmp_crtc->enabled &&
> -			curr_client_type ==
> -				dpu_crtc_get_client_type(tmp_crtc)) {
> +		    curr_client_type == dpu_crtc_get_client_type(tmp_crtc)) {
>   			dpu_cstate = to_dpu_crtc_state(tmp_crtc->state);
>   
> -			perf.max_per_pipe_ib = max(perf.max_per_pipe_ib,
> -					dpu_cstate->new_perf.max_per_pipe_ib);
> +			perf->max_per_pipe_ib = max(perf->max_per_pipe_ib,
> +						    dpu_cstate->new_perf.max_per_pipe_ib);
>   
> -			perf.bw_ctl += dpu_cstate->new_perf.bw_ctl;
> +			perf->bw_ctl += dpu_cstate->new_perf.bw_ctl;
>   
> -			DRM_DEBUG_ATOMIC("crtc=%d bw=%llu paths:%d\n",
> -				  tmp_crtc->base.id,
> -				  dpu_cstate->new_perf.bw_ctl, kms->num_paths);
> +			DRM_DEBUG_ATOMIC("crtc=%d bw=%llu\n",
> +					 tmp_crtc->base.id,
> +					 dpu_cstate->new_perf.bw_ctl);
>   		}
>   	}
> +}
> +
> +static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
> +		struct drm_crtc *crtc)
> +{
> +	struct dpu_core_perf_params perf = { 0 };
> +	int i, ret = 0;
> +	u64 avg_bw;
> +
> +	dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf);
>   
>   	if (!kms->num_paths)
>   		return 0;

Re: [PATCH v4 02/11] drm/msm/dpu: core_perf: extract bandwidth aggregation function

[Dmitry Baryshkov]

On Mon, 17 Jul 2023 at 21:45, Abhinav Kumar <quic_abhinavk@quicinc.com> wrote:
>
>
>
> On 7/12/2023 3:11 PM, Dmitry Baryshkov wrote:
> > In preparation to refactoring the dpu_core_perf debugfs interface,
> > extract the bandwidth aggregation function from
> > _dpu_core_perf_crtc_update_bus().
> >
> > Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
> > ---
>
> Drop the core_perf tag from the subject line.

Ack.

>
> The debugfs refactor was dropped from this series if thats what you are
> referring to here.
>
> So even this and the next patch dont serve any purpose in this series
> and should be dropped, Unless you have some reason of keeping them here.

The next patch serves its purpose: it prevents recalculating bandwidth
if there are no ICC paths (useless math).

This patch separates actual math and control paths. It was required
for debugfs, but it serves its own purpose too. I'll reflect that in
the commit message.

>
> >   drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 39 +++++++++++--------
> >   1 file changed, 22 insertions(+), 17 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
> > index 1d9d83d7b99e..333dcfe57800 100644
> > --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
> > +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
> > @@ -206,33 +206,38 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
> >       return 0;
> >   }
> >
> > -static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
> > -             struct drm_crtc *crtc)
> > +static void dpu_core_perf_aggregate(struct drm_device *ddev,
> > +                                 enum dpu_crtc_client_type curr_client_type,
> > +                                 struct dpu_core_perf_params *perf)
> >   {
> > -     struct dpu_core_perf_params perf = { 0 };
> > -     enum dpu_crtc_client_type curr_client_type
> > -                                     = dpu_crtc_get_client_type(crtc);
> > -     struct drm_crtc *tmp_crtc;
> >       struct dpu_crtc_state *dpu_cstate;
> > -     int i, ret = 0;
> > -     u64 avg_bw;
> > +     struct drm_crtc *tmp_crtc;
> >
> > -     drm_for_each_crtc(tmp_crtc, crtc->dev) {
> > +     drm_for_each_crtc(tmp_crtc, ddev) {
> >               if (tmp_crtc->enabled &&
> > -                     curr_client_type ==
> > -                             dpu_crtc_get_client_type(tmp_crtc)) {
> > +                 curr_client_type == dpu_crtc_get_client_type(tmp_crtc)) {
> >                       dpu_cstate = to_dpu_crtc_state(tmp_crtc->state);
> >
> > -                     perf.max_per_pipe_ib = max(perf.max_per_pipe_ib,
> > -                                     dpu_cstate->new_perf.max_per_pipe_ib);
> > +                     perf->max_per_pipe_ib = max(perf->max_per_pipe_ib,
> > +                                                 dpu_cstate->new_perf.max_per_pipe_ib);
> >
> > -                     perf.bw_ctl += dpu_cstate->new_perf.bw_ctl;
> > +                     perf->bw_ctl += dpu_cstate->new_perf.bw_ctl;
> >
> > -                     DRM_DEBUG_ATOMIC("crtc=%d bw=%llu paths:%d\n",
> > -                               tmp_crtc->base.id,
> > -                               dpu_cstate->new_perf.bw_ctl, kms->num_paths);
> > +                     DRM_DEBUG_ATOMIC("crtc=%d bw=%llu\n",
> > +                                      tmp_crtc->base.id,
> > +                                      dpu_cstate->new_perf.bw_ctl);
> >               }
> >       }
> > +}
> > +
> > +static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
> > +             struct drm_crtc *crtc)
> > +{
> > +     struct dpu_core_perf_params perf = { 0 };
> > +     int i, ret = 0;
> > +     u64 avg_bw;
> > +
> > +     dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf);
> >
> >       if (!kms->num_paths)
> >               return 0;



-- 
With best wishes
Dmitry

[PATCH v4 03/11] drm/msm/dpu: core_perf: bail earlier if there are no ICC paths

[Dmitry Baryshkov]

Skip bandwidth aggregation and return early if there are no interconnect
paths defined for the DPU device.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 333dcfe57800..05d340aa18c5 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -237,11 +237,11 @@ static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
 	int i, ret = 0;
 	u64 avg_bw;
 
-	dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf);
-
 	if (!kms->num_paths)
 		return 0;
 
+	dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf);
+
 	avg_bw = perf.bw_ctl;
 	do_div(avg_bw, (kms->num_paths * 1000)); /*Bps_to_icc*/
 
-- 
2.39.2

[PATCH v4 04/11] drm/msm/dpu: drop separate dpu_core_perf_tune overrides

[Dmitry Baryshkov]

The values in struct dpu_core_perf_tune are fixed per the core perf
mode. Drop the 'tune' values and substitute them with known values when
performing perf management.

Note: min_bus_vote was not used at all, so it is just silently dropped.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 27 ++++++++-----------
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h |  4 ---
 2 files changed, 11 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 05d340aa18c5..f9f44cfcfbf2 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -291,10 +291,16 @@ void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
 
 static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms)
 {
-	u64 clk_rate = kms->perf.perf_tune.min_core_clk;
+	u64 clk_rate;
 	struct drm_crtc *crtc;
 	struct dpu_crtc_state *dpu_cstate;
 
+	if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED)
+		return kms->perf.fix_core_clk_rate;
+
+	if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM)
+		return kms->perf.max_core_clk_rate;
+
 	drm_for_each_crtc(crtc, kms->dev) {
 		if (crtc->enabled) {
 			dpu_cstate = to_dpu_crtc_state(crtc->state);
@@ -305,11 +311,6 @@ static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms)
 		}
 	}
 
-	if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED)
-		clk_rate = kms->perf.fix_core_clk_rate;
-
-	DRM_DEBUG_ATOMIC("clk:%llu\n", clk_rate);
-
 	return clk_rate;
 }
 
@@ -397,6 +398,8 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	if (update_clk) {
 		clk_rate = _dpu_core_perf_get_core_clk_rate(kms);
 
+		DRM_DEBUG_ATOMIC("clk:%llu\n", clk_rate);
+
 		trace_dpu_core_perf_update_clk(kms->dev, stop_req, clk_rate);
 
 		clk_rate = min(clk_rate, kms->perf.max_core_clk_rate);
@@ -418,7 +421,6 @@ static ssize_t _dpu_core_perf_mode_write(struct file *file,
 		    const char __user *user_buf, size_t count, loff_t *ppos)
 {
 	struct dpu_core_perf *perf = file->private_data;
-	const struct dpu_perf_cfg *cfg = perf->catalog->perf;
 	u32 perf_mode = 0;
 	int ret;
 
@@ -433,14 +435,9 @@ static ssize_t _dpu_core_perf_mode_write(struct file *file,
 		DRM_INFO("fix performance mode\n");
 	} else if (perf_mode == DPU_PERF_MODE_MINIMUM) {
 		/* run the driver with max clk and BW vote */
-		perf->perf_tune.min_core_clk = perf->max_core_clk_rate;
-		perf->perf_tune.min_bus_vote =
-				(u64) cfg->max_bw_high * 1000;
 		DRM_INFO("minimum performance mode\n");
 	} else if (perf_mode == DPU_PERF_MODE_NORMAL) {
 		/* reset the perf tune params to 0 */
-		perf->perf_tune.min_core_clk = 0;
-		perf->perf_tune.min_bus_vote = 0;
 		DRM_INFO("normal performance mode\n");
 	}
 	perf->perf_tune.mode = perf_mode;
@@ -456,10 +453,8 @@ static ssize_t _dpu_core_perf_mode_read(struct file *file,
 	char buf[128];
 
 	len = scnprintf(buf, sizeof(buf),
-			"mode %d min_mdp_clk %llu min_bus_vote %llu\n",
-			perf->perf_tune.mode,
-			perf->perf_tune.min_core_clk,
-			perf->perf_tune.min_bus_vote);
+			"mode %d\n",
+			perf->perf_tune.mode);
 
 	return simple_read_from_buffer(buff, count, ppos, buf, len);
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
index 29bb8ee2bc26..c965dfbc3007 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -29,13 +29,9 @@ struct dpu_core_perf_params {
 /**
  * struct dpu_core_perf_tune - definition of performance tuning control
  * @mode: performance mode
- * @min_core_clk: minimum core clock
- * @min_bus_vote: minimum bus vote
  */
 struct dpu_core_perf_tune {
 	u32 mode;
-	u64 min_core_clk;
-	u64 min_bus_vote;
 };
 
 /**
-- 
2.39.2

Re: [PATCH v4 04/11] drm/msm/dpu: drop separate dpu_core_perf_tune overrides

[Abhinav Kumar]

On 7/12/2023 3:11 PM, Dmitry Baryshkov wrote:
> The values in struct dpu_core_perf_tune are fixed per the core perf
> mode. Drop the 'tune' values and substitute them with known values when
> performing perf management.
> 
> Note: min_bus_vote was not used at all, so it is just silently dropped.
> 
> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
> ---
>   drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 27 ++++++++-----------
>   drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h |  4 ---
>   2 files changed, 11 insertions(+), 20 deletions(-)
> 

Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>

[PATCH v4 05/11] drm/msm/dpu: rework indentation in dpu_core_perf

[Dmitry Baryshkov]

dpu_core_perf.c contains several multi-line conditions which are hard to
comprehent because of the indentation. Rework the identation of these
conditions to make it easier to understand them.

Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Acked-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index f9f44cfcfbf2..841e1fc0c6a7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -173,8 +173,8 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
 
 	drm_for_each_crtc(tmp_crtc, crtc->dev) {
 		if (tmp_crtc->enabled &&
-		    (dpu_crtc_get_client_type(tmp_crtc) ==
-				curr_client_type) && (tmp_crtc != crtc)) {
+		    dpu_crtc_get_client_type(tmp_crtc) == curr_client_type &&
+		    tmp_crtc != crtc) {
 			struct dpu_crtc_state *tmp_cstate =
 				to_dpu_crtc_state(tmp_crtc->state);
 
@@ -365,10 +365,8 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 			update_bus = true;
 		}
 
-		if ((params_changed &&
-			(new->core_clk_rate > old->core_clk_rate)) ||
-			(!params_changed &&
-			(new->core_clk_rate < old->core_clk_rate))) {
+		if ((params_changed && new->core_clk_rate > old->core_clk_rate) ||
+		    (!params_changed && new->core_clk_rate < old->core_clk_rate)) {
 			old->core_clk_rate = new->core_clk_rate;
 			update_clk = true;
 		}
-- 
2.39.2

[PATCH v4 06/11] drm/msm/dpu: drop the dpu_core_perf_crtc_update()'s stop_req param

[Dmitry Baryshkov]

The stop_req is true only in the dpu_crtc_disable() case, when
crtc->enable has already been set to false. This renders the stop_req
argument useless. Remove it completely.

Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 12 ++++++------
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h |  3 +--
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c      |  6 +++---
 3 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 841e1fc0c6a7..3b3c2659297d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -315,7 +315,7 @@ static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms)
 }
 
 int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
-		int params_changed, bool stop_req)
+			      int params_changed)
 {
 	struct dpu_core_perf_params *new, *old;
 	bool update_bus = false, update_clk = false;
@@ -339,13 +339,13 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	dpu_crtc = to_dpu_crtc(crtc);
 	dpu_cstate = to_dpu_crtc_state(crtc->state);
 
-	DRM_DEBUG_ATOMIC("crtc:%d stop_req:%d core_clk:%llu\n",
-			crtc->base.id, stop_req, kms->perf.core_clk_rate);
+	DRM_DEBUG_ATOMIC("crtc:%d enabled:%d core_clk:%llu\n",
+			crtc->base.id, crtc->enabled, kms->perf.core_clk_rate);
 
 	old = &dpu_crtc->cur_perf;
 	new = &dpu_cstate->new_perf;
 
-	if (crtc->enabled && !stop_req) {
+	if (crtc->enabled) {
 		/*
 		 * cases for bus bandwidth update.
 		 * 1. new bandwidth vote - "ab or ib vote" is higher
@@ -378,7 +378,7 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	}
 
 	trace_dpu_perf_crtc_update(crtc->base.id, new->bw_ctl,
-		new->core_clk_rate, stop_req, update_bus, update_clk);
+		new->core_clk_rate, !crtc->enabled, update_bus, update_clk);
 
 	if (update_bus) {
 		ret = _dpu_core_perf_crtc_update_bus(kms, crtc);
@@ -398,7 +398,7 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 
 		DRM_DEBUG_ATOMIC("clk:%llu\n", clk_rate);
 
-		trace_dpu_core_perf_update_clk(kms->dev, stop_req, clk_rate);
+		trace_dpu_core_perf_update_clk(kms->dev, !crtc->enabled, clk_rate);
 
 		clk_rate = min(clk_rate, kms->perf.max_core_clk_rate);
 		ret = dev_pm_opp_set_rate(&kms->pdev->dev, clk_rate);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
index c965dfbc3007..c0097b67f9dd 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -75,11 +75,10 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
  * dpu_core_perf_crtc_update - update performance of the given crtc
  * @crtc: Pointer to crtc
  * @params_changed: true if crtc parameters are modified
- * @stop_req: true if this is a stop request
  * return: zero if success, or error code otherwise
  */
 int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
-		int params_changed, bool stop_req);
+			      int params_changed);
 
 /**
  * dpu_core_perf_crtc_release_bw - release bandwidth of the given crtc
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index 1edf2b6b0a26..8ce7586e2ddf 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -718,7 +718,7 @@ static void dpu_crtc_frame_event_cb(void *data, u32 event)
 void dpu_crtc_complete_commit(struct drm_crtc *crtc)
 {
 	trace_dpu_crtc_complete_commit(DRMID(crtc));
-	dpu_core_perf_crtc_update(crtc, 0, false);
+	dpu_core_perf_crtc_update(crtc, 0);
 	_dpu_crtc_complete_flip(crtc);
 }
 
@@ -884,7 +884,7 @@ static void dpu_crtc_atomic_flush(struct drm_crtc *crtc,
 		return;
 
 	/* update performance setting before crtc kickoff */
-	dpu_core_perf_crtc_update(crtc, 1, false);
+	dpu_core_perf_crtc_update(crtc, 1);
 
 	/*
 	 * Final plane updates: Give each plane a chance to complete all
@@ -1100,7 +1100,7 @@ static void dpu_crtc_disable(struct drm_crtc *crtc,
 		atomic_set(&dpu_crtc->frame_pending, 0);
 	}
 
-	dpu_core_perf_crtc_update(crtc, 0, true);
+	dpu_core_perf_crtc_update(crtc, 0);
 
 	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
 		dpu_encoder_register_frame_event_callback(encoder, NULL, NULL);
-- 
2.39.2

[PATCH v4 07/11] drm/msm/dpu: use dpu_perf_cfg in DPU core_perf code

[Dmitry Baryshkov]

Simplify dpu_core_perf code by using only dpu_perf_cfg instead of using
full-featured catalog data.

Acked-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 73 ++++++++-----------
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h |  8 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c       |  2 +-
 3 files changed, 35 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 3b3c2659297d..27a0312bd140 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -33,11 +33,11 @@ enum dpu_perf_mode {
 
 /**
  * _dpu_core_perf_calc_bw() - to calculate BW per crtc
- * @kms:  pointer to the dpu_kms
+ * @perf_cfg: performance configuration
  * @crtc: pointer to a crtc
  * Return: returns aggregated BW for all planes in crtc.
  */
-static u64 _dpu_core_perf_calc_bw(struct dpu_kms *kms,
+static u64 _dpu_core_perf_calc_bw(const struct dpu_perf_cfg *perf_cfg,
 		struct drm_crtc *crtc)
 {
 	struct drm_plane *plane;
@@ -53,7 +53,7 @@ static u64 _dpu_core_perf_calc_bw(struct dpu_kms *kms,
 		crtc_plane_bw += pstate->plane_fetch_bw;
 	}
 
-	bw_factor = kms->catalog->perf->bw_inefficiency_factor;
+	bw_factor = perf_cfg->bw_inefficiency_factor;
 	if (bw_factor) {
 		crtc_plane_bw *= bw_factor;
 		do_div(crtc_plane_bw, 100);
@@ -64,12 +64,12 @@ static u64 _dpu_core_perf_calc_bw(struct dpu_kms *kms,
 
 /**
  * _dpu_core_perf_calc_clk() - to calculate clock per crtc
- * @kms:  pointer to the dpu_kms
+ * @perf_cfg: performance configuration
  * @crtc: pointer to a crtc
  * @state: pointer to a crtc state
  * Return: returns max clk for all planes in crtc.
  */
-static u64 _dpu_core_perf_calc_clk(struct dpu_kms *kms,
+static u64 _dpu_core_perf_calc_clk(const struct dpu_perf_cfg *perf_cfg,
 		struct drm_crtc *crtc, struct drm_crtc_state *state)
 {
 	struct drm_plane *plane;
@@ -90,7 +90,7 @@ static u64 _dpu_core_perf_calc_clk(struct dpu_kms *kms,
 		crtc_clk = max(pstate->plane_clk, crtc_clk);
 	}
 
-	clk_factor = kms->catalog->perf->clk_inefficiency_factor;
+	clk_factor = perf_cfg->clk_inefficiency_factor;
 	if (clk_factor) {
 		crtc_clk *= clk_factor;
 		do_div(crtc_clk, 100);
@@ -106,30 +106,32 @@ static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
 	return to_dpu_kms(priv->kms);
 }
 
-static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms,
-		struct drm_crtc *crtc,
-		struct drm_crtc_state *state,
-		struct dpu_core_perf_params *perf)
+static void _dpu_core_perf_calc_crtc(const struct dpu_core_perf *core_perf,
+				     struct drm_crtc *crtc,
+				     struct drm_crtc_state *state,
+				     struct dpu_core_perf_params *perf)
 {
-	if (!kms || !kms->catalog || !crtc || !state || !perf) {
+	const struct dpu_perf_cfg *perf_cfg = core_perf->perf_cfg;
+
+	if (!perf_cfg || !crtc || !state || !perf) {
 		DPU_ERROR("invalid parameters\n");
 		return;
 	}
 
 	memset(perf, 0, sizeof(struct dpu_core_perf_params));
 
-	if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) {
+	if (core_perf->perf_tune.mode == DPU_PERF_MODE_MINIMUM) {
 		perf->bw_ctl = 0;
 		perf->max_per_pipe_ib = 0;
 		perf->core_clk_rate = 0;
-	} else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) {
-		perf->bw_ctl = kms->perf.fix_core_ab_vote;
-		perf->max_per_pipe_ib = kms->perf.fix_core_ib_vote;
-		perf->core_clk_rate = kms->perf.fix_core_clk_rate;
+	} else if (core_perf->perf_tune.mode == DPU_PERF_MODE_FIXED) {
+		perf->bw_ctl = core_perf->fix_core_ab_vote;
+		perf->max_per_pipe_ib = core_perf->fix_core_ib_vote;
+		perf->core_clk_rate = core_perf->fix_core_clk_rate;
 	} else {
-		perf->bw_ctl = _dpu_core_perf_calc_bw(kms, crtc);
-		perf->max_per_pipe_ib = kms->catalog->perf->min_dram_ib;
-		perf->core_clk_rate = _dpu_core_perf_calc_clk(kms, crtc, state);
+		perf->bw_ctl = _dpu_core_perf_calc_bw(perf_cfg, crtc);
+		perf->max_per_pipe_ib = perf_cfg->min_dram_ib;
+		perf->core_clk_rate = _dpu_core_perf_calc_clk(perf_cfg, crtc, state);
 	}
 
 	DRM_DEBUG_ATOMIC(
@@ -154,10 +156,6 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms->catalog) {
-		DPU_ERROR("invalid parameters\n");
-		return 0;
-	}
 
 	/* we only need bandwidth check on real-time clients (interfaces) */
 	if (dpu_crtc_get_client_type(crtc) == NRT_CLIENT)
@@ -166,7 +164,7 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
 	dpu_cstate = to_dpu_crtc_state(state);
 
 	/* obtain new values */
-	_dpu_core_perf_calc_crtc(kms, crtc, state, &dpu_cstate->new_perf);
+	_dpu_core_perf_calc_crtc(&kms->perf, crtc, state, &dpu_cstate->new_perf);
 
 	bw_sum_of_intfs = dpu_cstate->new_perf.bw_ctl;
 	curr_client_type = dpu_crtc_get_client_type(crtc);
@@ -189,7 +187,7 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
 		bw = DIV_ROUND_UP_ULL(bw_sum_of_intfs, 1000);
 		DRM_DEBUG_ATOMIC("calculated bandwidth=%uk\n", bw);
 
-		threshold = kms->catalog->perf->max_bw_high;
+		threshold = kms->perf.perf_cfg->max_bw_high;
 
 		DRM_DEBUG_ATOMIC("final threshold bw limit = %d\n", threshold);
 
@@ -270,11 +268,6 @@ void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms->catalog) {
-		DPU_ERROR("invalid kms\n");
-		return;
-	}
-
 	dpu_crtc = to_dpu_crtc(crtc);
 
 	if (atomic_dec_return(&kms->bandwidth_ref) > 0)
@@ -331,10 +324,6 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms->catalog) {
-		DPU_ERROR("invalid kms\n");
-		return -EINVAL;
-	}
 
 	dpu_crtc = to_dpu_crtc(crtc);
 	dpu_cstate = to_dpu_crtc_state(crtc->state);
@@ -466,7 +455,6 @@ static const struct file_operations dpu_core_perf_mode_fops = {
 int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent)
 {
 	struct dpu_core_perf *perf = &dpu_kms->perf;
-	const struct dpu_mdss_cfg *catalog = perf->catalog;
 	struct dentry *entry;
 
 	entry = debugfs_create_dir("core_perf", parent);
@@ -478,15 +466,15 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent)
 	debugfs_create_u32("enable_bw_release", 0600, entry,
 			(u32 *)&perf->enable_bw_release);
 	debugfs_create_u32("threshold_low", 0600, entry,
-			(u32 *)&catalog->perf->max_bw_low);
+			(u32 *)&perf->perf_cfg->max_bw_low);
 	debugfs_create_u32("threshold_high", 0600, entry,
-			(u32 *)&catalog->perf->max_bw_high);
+			(u32 *)&perf->perf_cfg->max_bw_high);
 	debugfs_create_u32("min_core_ib", 0600, entry,
-			(u32 *)&catalog->perf->min_core_ib);
+			(u32 *)&perf->perf_cfg->min_core_ib);
 	debugfs_create_u32("min_llcc_ib", 0600, entry,
-			(u32 *)&catalog->perf->min_llcc_ib);
+			(u32 *)&perf->perf_cfg->min_llcc_ib);
 	debugfs_create_u32("min_dram_ib", 0600, entry,
-			(u32 *)&catalog->perf->min_dram_ib);
+			(u32 *)&perf->perf_cfg->min_dram_ib);
 	debugfs_create_file("perf_mode", 0600, entry,
 			(u32 *)perf, &dpu_core_perf_mode_fops);
 	debugfs_create_u64("fix_core_clk_rate", 0600, entry,
@@ -509,17 +497,16 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf)
 
 	perf->max_core_clk_rate = 0;
 	perf->core_clk = NULL;
-	perf->catalog = NULL;
 	perf->dev = NULL;
 }
 
 int dpu_core_perf_init(struct dpu_core_perf *perf,
 		struct drm_device *dev,
-		const struct dpu_mdss_cfg *catalog,
+		const struct dpu_perf_cfg *perf_cfg,
 		struct clk *core_clk)
 {
 	perf->dev = dev;
-	perf->catalog = catalog;
+	perf->perf_cfg = perf_cfg;
 	perf->core_clk = core_clk;
 
 	perf->max_core_clk_rate = clk_get_rate(core_clk);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
index c0097b67f9dd..f4b84e67138c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -38,7 +38,7 @@ struct dpu_core_perf_tune {
  * struct dpu_core_perf - definition of core performance context
  * @dev: Pointer to drm device
  * @debugfs_root: top level debug folder
- * @catalog: Pointer to catalog configuration
+ * @perf_cfg: Platform-specific performance configuration
  * @core_clk: Pointer to the core clock
  * @core_clk_rate: current core clock rate
  * @max_core_clk_rate: maximum allowable core clock rate
@@ -51,7 +51,7 @@ struct dpu_core_perf_tune {
 struct dpu_core_perf {
 	struct drm_device *dev;
 	struct dentry *debugfs_root;
-	const struct dpu_mdss_cfg *catalog;
+	const struct dpu_perf_cfg *perf_cfg;
 	struct clk *core_clk;
 	u64 core_clk_rate;
 	u64 max_core_clk_rate;
@@ -96,12 +96,12 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf);
  * dpu_core_perf_init - initialize the given core performance context
  * @perf: Pointer to core performance context
  * @dev: Pointer to drm device
- * @catalog: Pointer to catalog
+ * @perf_cfg: Pointer to platform performance configuration
  * @core_clk: pointer to core clock
  */
 int dpu_core_perf_init(struct dpu_core_perf *perf,
 		struct drm_device *dev,
-		const struct dpu_mdss_cfg *catalog,
+		const struct dpu_perf_cfg *perf_cfg,
 		struct clk *core_clk);
 
 struct dpu_kms;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index c1d06e19b237..074c032cd24e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -1156,7 +1156,7 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 		dpu_kms->hw_vbif[vbif->id] = hw;
 	}
 
-	rc = dpu_core_perf_init(&dpu_kms->perf, dev, dpu_kms->catalog,
+	rc = dpu_core_perf_init(&dpu_kms->perf, dev, dpu_kms->catalog->perf,
 			msm_clk_bulk_get_clock(dpu_kms->clocks, dpu_kms->num_clocks, "core"));
 	if (rc) {
 		DPU_ERROR("failed to init perf %d\n", rc);
-- 
2.39.2

Re: [PATCH v4 07/11] drm/msm/dpu: use dpu_perf_cfg in DPU core_perf code

[Abhinav Kumar]

On 7/12/2023 3:11 PM, Dmitry Baryshkov wrote:
> Simplify dpu_core_perf code by using only dpu_perf_cfg instead of using
> full-featured catalog data.
> 
> Acked-by: Konrad Dybcio <konrad.dybcio@linaro.org>
> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
> ---
>   drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 73 ++++++++-----------
>   drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h |  8 +-
>   drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c       |  2 +-
>   3 files changed, 35 insertions(+), 48 deletions(-)
> 

With dpu_core_rev as a separate struct, if we do need the dpu hw version 
in this module, we can just pass that instead. Hence,

Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>

[PATCH v4 08/11] drm/msm/dpu: remove unused fields from struct dpu_core_perf

[Dmitry Baryshkov]

Remove dpu_core_perf::dev and dpu_core_perf::debugfs_root fields, they
are not used by the code.

Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 3 ---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h | 6 ------
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c       | 2 +-
 3 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 27a0312bd140..d8c88ce5190d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -497,15 +497,12 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf)
 
 	perf->max_core_clk_rate = 0;
 	perf->core_clk = NULL;
-	perf->dev = NULL;
 }
 
 int dpu_core_perf_init(struct dpu_core_perf *perf,
-		struct drm_device *dev,
 		const struct dpu_perf_cfg *perf_cfg,
 		struct clk *core_clk)
 {
-	perf->dev = dev;
 	perf->perf_cfg = perf_cfg;
 	perf->core_clk = core_clk;
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
index f4b84e67138c..e718d523ff30 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -36,8 +36,6 @@ struct dpu_core_perf_tune {
 
 /**
  * struct dpu_core_perf - definition of core performance context
- * @dev: Pointer to drm device
- * @debugfs_root: top level debug folder
  * @perf_cfg: Platform-specific performance configuration
  * @core_clk: Pointer to the core clock
  * @core_clk_rate: current core clock rate
@@ -49,8 +47,6 @@ struct dpu_core_perf_tune {
  * @fix_core_ab_vote: fixed core ab vote in bps used in mode 2
  */
 struct dpu_core_perf {
-	struct drm_device *dev;
-	struct dentry *debugfs_root;
 	const struct dpu_perf_cfg *perf_cfg;
 	struct clk *core_clk;
 	u64 core_clk_rate;
@@ -95,12 +91,10 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf);
 /**
  * dpu_core_perf_init - initialize the given core performance context
  * @perf: Pointer to core performance context
- * @dev: Pointer to drm device
  * @perf_cfg: Pointer to platform performance configuration
  * @core_clk: pointer to core clock
  */
 int dpu_core_perf_init(struct dpu_core_perf *perf,
-		struct drm_device *dev,
 		const struct dpu_perf_cfg *perf_cfg,
 		struct clk *core_clk);
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 074c032cd24e..80e08302680c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -1156,7 +1156,7 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 		dpu_kms->hw_vbif[vbif->id] = hw;
 	}
 
-	rc = dpu_core_perf_init(&dpu_kms->perf, dev, dpu_kms->catalog->perf,
+	rc = dpu_core_perf_init(&dpu_kms->perf, dpu_kms->catalog->perf,
 			msm_clk_bulk_get_clock(dpu_kms->clocks, dpu_kms->num_clocks, "core"));
 	if (rc) {
 		DPU_ERROR("failed to init perf %d\n", rc);
-- 
2.39.2

[PATCH v4 09/11] drm/msm/dpu: remove extra clk_round_rate() call

[Dmitry Baryshkov]

The dev_pm_opp_set_rate() already contains a call for clk_round_rate for
the passed value. Stop calling it manually from
_dpu_core_perf_get_core_clk_rate(). It is slightly incorrect to call it
this way, as we should round the final calculated clock rate rather than
rounding all the intermediate values.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index d8c88ce5190d..896e87b13dbe 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -299,8 +299,6 @@ static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms)
 			dpu_cstate = to_dpu_crtc_state(crtc->state);
 			clk_rate = max(dpu_cstate->new_perf.core_clk_rate,
 							clk_rate);
-			clk_rate = clk_round_rate(kms->perf.core_clk,
-					clk_rate);
 		}
 	}
 
-- 
2.39.2

Re: [PATCH v4 09/11] drm/msm/dpu: remove extra clk_round_rate() call

[Abhinav Kumar]

On 7/12/2023 3:11 PM, Dmitry Baryshkov wrote:
> The dev_pm_opp_set_rate() already contains a call for clk_round_rate for
> the passed value. Stop calling it manually from
> _dpu_core_perf_get_core_clk_rate(). It is slightly incorrect to call it
> this way, as we should round the final calculated clock rate rather than
> rounding all the intermediate values.
> 
> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
> ---

Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>

[PATCH v4 10/11] drm/msm/dpu: move max clock decision to dpu_kms.

[Dmitry Baryshkov]

dpu_core_perf should not make decisions on the maximum possible core
clock rate. Pass the value from dpu_kms_hw_init().

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 11 ++---------
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h |  8 ++------
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c       | 13 +++++++++++--
 3 files changed, 15 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 896e87b13dbe..16a4d6c67f4d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -494,21 +494,14 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf)
 	}
 
 	perf->max_core_clk_rate = 0;
-	perf->core_clk = NULL;
 }
 
 int dpu_core_perf_init(struct dpu_core_perf *perf,
 		const struct dpu_perf_cfg *perf_cfg,
-		struct clk *core_clk)
+		unsigned long max_core_clk_rate)
 {
 	perf->perf_cfg = perf_cfg;
-	perf->core_clk = core_clk;
-
-	perf->max_core_clk_rate = clk_get_rate(core_clk);
-	if (!perf->max_core_clk_rate) {
-		DPU_DEBUG("optional max core clk rate, use default\n");
-		perf->max_core_clk_rate = DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE;
-	}
+	perf->max_core_clk_rate = max_core_clk_rate;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
index e718d523ff30..8cc55752db5e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -12,8 +12,6 @@
 
 #include "dpu_hw_catalog.h"
 
-#define	DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE	412500000
-
 /**
  * struct dpu_core_perf_params - definition of performance parameters
  * @max_per_pipe_ib: maximum instantaneous bandwidth request
@@ -37,7 +35,6 @@ struct dpu_core_perf_tune {
 /**
  * struct dpu_core_perf - definition of core performance context
  * @perf_cfg: Platform-specific performance configuration
- * @core_clk: Pointer to the core clock
  * @core_clk_rate: current core clock rate
  * @max_core_clk_rate: maximum allowable core clock rate
  * @perf_tune: debug control for performance tuning
@@ -48,7 +45,6 @@ struct dpu_core_perf_tune {
  */
 struct dpu_core_perf {
 	const struct dpu_perf_cfg *perf_cfg;
-	struct clk *core_clk;
 	u64 core_clk_rate;
 	u64 max_core_clk_rate;
 	struct dpu_core_perf_tune perf_tune;
@@ -92,11 +88,11 @@ void dpu_core_perf_destroy(struct dpu_core_perf *perf);
  * dpu_core_perf_init - initialize the given core performance context
  * @perf: Pointer to core performance context
  * @perf_cfg: Pointer to platform performance configuration
- * @core_clk: pointer to core clock
+ * @max_core_clk_rate: Maximum core clock rate
  */
 int dpu_core_perf_init(struct dpu_core_perf *perf,
 		const struct dpu_perf_cfg *perf_cfg,
-		struct clk *core_clk);
+		unsigned long max_core_clk_rate);
 
 struct dpu_kms;
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 80e08302680c..5bfea4868e43 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -1051,11 +1051,14 @@ unsigned long dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name)
 	return clk_get_rate(clk);
 }
 
+#define	DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE	412500000
+
 static int dpu_kms_hw_init(struct msm_kms *kms)
 {
 	struct dpu_kms *dpu_kms;
 	struct drm_device *dev;
 	int i, rc = -EINVAL;
+	unsigned long max_core_clk_rate;
 	u32 core_rev;
 
 	if (!kms) {
@@ -1156,8 +1159,14 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 		dpu_kms->hw_vbif[vbif->id] = hw;
 	}
 
-	rc = dpu_core_perf_init(&dpu_kms->perf, dpu_kms->catalog->perf,
-			msm_clk_bulk_get_clock(dpu_kms->clocks, dpu_kms->num_clocks, "core"));
+	/* TODO: use the same max_freq as in dpu_kms_hw_init */
+	max_core_clk_rate = dpu_kms_get_clk_rate(dpu_kms, "core");
+	if (!max_core_clk_rate) {
+		DPU_DEBUG("max core clk rate not determined, using default\n");
+		max_core_clk_rate = DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE;
+	}
+
+	rc = dpu_core_perf_init(&dpu_kms->perf, dpu_kms->catalog->perf, max_core_clk_rate);
 	if (rc) {
 		DPU_ERROR("failed to init perf %d\n", rc);
 		goto perf_err;
-- 
2.39.2

Re: [PATCH v4 10/11] drm/msm/dpu: move max clock decision to dpu_kms.

[Abhinav Kumar]

On 7/12/2023 3:11 PM, Dmitry Baryshkov wrote:
> dpu_core_perf should not make decisions on the maximum possible core
> clock rate. Pass the value from dpu_kms_hw_init().
> 
> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>

Also mention that with this, you are dropping the now unused core_clk 
handle in the dpu_core_perf.

With that,

Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>

[PATCH v4 11/11] drm/msm/dpu: drop dpu_core_perf_destroy()

[Dmitry Baryshkov]

This function does nothing, just clears one struct field. Drop it now.

Acked-by: Konrad Dybcio <konrad.dybcio@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 10 ----------
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h |  6 ------
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c       |  1 -
 3 files changed, 17 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 16a4d6c67f4d..31813a322afd 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -486,16 +486,6 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent)
 }
 #endif
 
-void dpu_core_perf_destroy(struct dpu_core_perf *perf)
-{
-	if (!perf) {
-		DPU_ERROR("invalid parameters\n");
-		return;
-	}
-
-	perf->max_core_clk_rate = 0;
-}
-
 int dpu_core_perf_init(struct dpu_core_perf *perf,
 		const struct dpu_perf_cfg *perf_cfg,
 		unsigned long max_core_clk_rate)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
index 8cc55752db5e..4186977390bd 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -78,12 +78,6 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
  */
 void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc);
 
-/**
- * dpu_core_perf_destroy - destroy the given core performance context
- * @perf: Pointer to core performance context
- */
-void dpu_core_perf_destroy(struct dpu_core_perf *perf);
-
 /**
  * dpu_core_perf_init - initialize the given core performance context
  * @perf: Pointer to core performance context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 5bfea4868e43..76ba86d3e436 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -1212,7 +1212,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 	return 0;
 
 drm_obj_init_err:
-	dpu_core_perf_destroy(&dpu_kms->perf);
 hw_intr_init_err:
 perf_err:
 power_error:
-- 
2.39.2

Re: [PATCH v4 11/11] drm/msm/dpu: drop dpu_core_perf_destroy()

[Abhinav Kumar]

On 7/12/2023 3:11 PM, Dmitry Baryshkov wrote:
> This function does nothing, just clears one struct field. Drop it now.
> 
> Acked-by: Konrad Dybcio <konrad.dybcio@linaro.org>
> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
> ---
>   drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c | 10 ----------
>   drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h |  6 ------
>   drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c       |  1 -
>   3 files changed, 17 deletions(-)
> 

Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>