[Public]
> -----Original Message-----
> From: Wayne Lin <Wayne.Lin@xxxxxxx>
> Sent: Wednesday, April 24, 2024 4:49 AM
> To: amd-gfx@xxxxxxxxxxxxxxxxxxxxx
> Cc: Wentland, Harry <Harry.Wentland@xxxxxxx>; Li, Sun peng (Leo)
> <Sunpeng.Li@xxxxxxx>; Siqueira, Rodrigo <Rodrigo.Siqueira@xxxxxxx>;
> Pillai, Aurabindo <Aurabindo.Pillai@xxxxxxx>; Li, Roman
> <Roman.Li@xxxxxxx>; Lin, Wayne <Wayne.Lin@xxxxxxx>; Gutierrez,
> Agustin <Agustin.Gutierrez@xxxxxxx>; Chung, ChiaHsuan (Tom)
> <ChiaHsuan.Chung@xxxxxxx>; Wu, Hersen <hersenxs.wu@xxxxxxx>; Zuo,
> Jerry <Jerry.Zuo@xxxxxxx>; Miess, Daniel <Daniel.Miess@xxxxxxx>; Liu,
> Charlene <Charlene.Liu@xxxxxxx>
> Subject: [PATCH 28/46] drm/amd/display: Enable RCO for PHYSYMCLK in
> DCN35
>
> From: Daniel Miess <daniel.miess@xxxxxxx>
>
> [Why & How]
> Enable root clock optimization for PHYSYMCLK and only disable it when it's
> actively being used
>
> Reviewed-by: Charlene Liu <charlene.liu@xxxxxxx>
> Acked-by: Wayne Lin <wayne.lin@xxxxxxx>
> Signed-off-by: Daniel Miess <daniel.miess@xxxxxxx>
> ---
> drivers/gpu/drm/amd/display/dc/dc.h | 1 +
> .../gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c | 45 -------------------
> .../amd/display/dc/hwss/dcn35/dcn35_hwseq.c | 32 +++++++++++++
> .../amd/display/dc/hwss/dcn35/dcn35_hwseq.h | 2 +
> .../amd/display/dc/hwss/dcn35/dcn35_init.c | 1 +
> .../amd/display/dc/hwss/dcn351/dcn351_init.c | 1 +
> .../display/dc/hwss/hw_sequencer_private.h | 4 ++
> 7 files changed, 41 insertions(+), 45 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/display/dc/dc.h
> b/drivers/gpu/drm/amd/display/dc/dc.h
> index 3048d5a0e87d..dd8940c2a4bf 100644
> --- a/drivers/gpu/drm/amd/display/dc/dc.h
> +++ b/drivers/gpu/drm/amd/display/dc/dc.h
> @@ -724,6 +724,7 @@ enum pg_hw_pipe_resources {
> PG_OPTC,
> PG_DPSTREAM,
> PG_HDMISTREAM,
> + PG_PHYSYMCLK,
> PG_HW_PIPE_RESOURCES_NUM_ELEMENT
> };
>
> diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c
> b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c
> index 4b282b7e0996..795320a25fd2 100644
> --- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c
> +++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c
> @@ -461,32 +461,22 @@ static void
> dccg35_set_physymclk_root_clock_gating(
> case 0:
> REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
> PHYASYMCLK_ROOT_GATE_DISABLE, enable ?
> 1 : 0);
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -// PHYA_REFCLK_ROOT_GATE_DISABLE, enable ?
> 1 : 0);
> break;
> case 1:
> REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
> PHYBSYMCLK_ROOT_GATE_DISABLE, enable ?
> 1 : 0);
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -// PHYB_REFCLK_ROOT_GATE_DISABLE, enable ?
> 1 : 0);
> break;
> case 2:
> REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
> PHYCSYMCLK_ROOT_GATE_DISABLE, enable ?
> 1 : 0);
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -// PHYC_REFCLK_ROOT_GATE_DISABLE, enable ?
> 1 : 0);
> break;
> case 3:
> REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
> PHYDSYMCLK_ROOT_GATE_DISABLE, enable ?
> 1 : 0);
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -// PHYD_REFCLK_ROOT_GATE_DISABLE, enable ?
> 1 : 0);
> break;
> case 4:
> REG_UPDATE(DCCG_GATE_DISABLE_CNTL2,
> PHYESYMCLK_ROOT_GATE_DISABLE, enable ?
> 1 : 0);
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -// PHYE_REFCLK_ROOT_GATE_DISABLE, enable ?
> 1 : 0);
> break;
> default:
> BREAK_TO_DEBUGGER();
> @@ -509,16 +499,10 @@ static void dccg35_set_physymclk(
> REG_UPDATE_2(PHYASYMCLK_CLOCK_CNTL,
> PHYASYMCLK_EN, 1,
> PHYASYMCLK_SRC_SEL, clk_src);
> -// if (dccg->ctx->dc-
> >debug.root_clock_optimization.bits.physymclk)
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -//
> PHYA_REFCLK_ROOT_GATE_DISABLE, 0);
> } else {
> REG_UPDATE_2(PHYASYMCLK_CLOCK_CNTL,
> PHYASYMCLK_EN, 0,
> PHYASYMCLK_SRC_SEL, 0);
> -// if (dccg->ctx->dc-
> >debug.root_clock_optimization.bits.physymclk)
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -//
> PHYA_REFCLK_ROOT_GATE_DISABLE, 1);
> }
> break;
> case 1:
> @@ -526,16 +510,10 @@ static void dccg35_set_physymclk(
> REG_UPDATE_2(PHYBSYMCLK_CLOCK_CNTL,
> PHYBSYMCLK_EN, 1,
> PHYBSYMCLK_SRC_SEL, clk_src);
> -// if (dccg->ctx->dc-
> >debug.root_clock_optimization.bits.physymclk)
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -//
> PHYB_REFCLK_ROOT_GATE_DISABLE, 0);
> } else {
> REG_UPDATE_2(PHYBSYMCLK_CLOCK_CNTL,
> PHYBSYMCLK_EN, 0,
> PHYBSYMCLK_SRC_SEL, 0);
> -// if (dccg->ctx->dc-
> >debug.root_clock_optimization.bits.physymclk)
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -//
> PHYB_REFCLK_ROOT_GATE_DISABLE, 1);
> }
> break;
> case 2:
> @@ -543,16 +521,10 @@ static void dccg35_set_physymclk(
> REG_UPDATE_2(PHYCSYMCLK_CLOCK_CNTL,
> PHYCSYMCLK_EN, 1,
> PHYCSYMCLK_SRC_SEL, clk_src);
> -// if (dccg->ctx->dc-
> >debug.root_clock_optimization.bits.physymclk)
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -//
> PHYC_REFCLK_ROOT_GATE_DISABLE, 0);
> } else {
> REG_UPDATE_2(PHYCSYMCLK_CLOCK_CNTL,
> PHYCSYMCLK_EN, 0,
> PHYCSYMCLK_SRC_SEL, 0);
> -// if (dccg->ctx->dc-
> >debug.root_clock_optimization.bits.physymclk)
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -//
> PHYC_REFCLK_ROOT_GATE_DISABLE, 1);
> }
> break;
> case 3:
> @@ -560,16 +532,10 @@ static void dccg35_set_physymclk(
> REG_UPDATE_2(PHYDSYMCLK_CLOCK_CNTL,
> PHYDSYMCLK_EN, 1,
> PHYDSYMCLK_SRC_SEL, clk_src);
> -// if (dccg->ctx->dc-
> >debug.root_clock_optimization.bits.physymclk)
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -//
> PHYD_REFCLK_ROOT_GATE_DISABLE, 0);
> } else {
> REG_UPDATE_2(PHYDSYMCLK_CLOCK_CNTL,
> PHYDSYMCLK_EN, 0,
> PHYDSYMCLK_SRC_SEL, 0);
> -// if (dccg->ctx->dc-
> >debug.root_clock_optimization.bits.physymclk)
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -//
> PHYD_REFCLK_ROOT_GATE_DISABLE, 1);
> }
> break;
> case 4:
> @@ -577,16 +543,10 @@ static void dccg35_set_physymclk(
> REG_UPDATE_2(PHYESYMCLK_CLOCK_CNTL,
> PHYESYMCLK_EN, 1,
> PHYESYMCLK_SRC_SEL, clk_src);
> -// if (dccg->ctx->dc-
> >debug.root_clock_optimization.bits.physymclk)
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -//
> PHYE_REFCLK_ROOT_GATE_DISABLE, 0);
> } else {
> REG_UPDATE_2(PHYESYMCLK_CLOCK_CNTL,
> PHYESYMCLK_EN, 0,
> PHYESYMCLK_SRC_SEL, 0);
> -// if (dccg->ctx->dc-
> >debug.root_clock_optimization.bits.physymclk)
> -// REG_UPDATE(DCCG_GATE_DISABLE_CNTL4,
> -//
> PHYE_REFCLK_ROOT_GATE_DISABLE, 1);
> }
> break;
> default:
> @@ -724,11 +684,6 @@ void dccg35_init(struct dccg *dccg)
> dccg35_set_dpstreamclk_root_clock_gating(dccg,
> otg_inst, false);
> }
>
> - if (dccg->ctx->dc->debug.root_clock_optimization.bits.physymclk)
> - for (otg_inst = 0; otg_inst < 5; otg_inst++)
> - dccg35_set_physymclk_root_clock_gating(dccg,
> otg_inst,
> - false);
> -
> if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp)
> for (otg_inst = 0; otg_inst < 4; otg_inst++)
> dccg35_set_dppclk_root_clock_gating(dccg, otg_inst,
> 0); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
> b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
> index b94a85380d73..dea7e63a49d9 100644
> --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
> +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
> @@ -506,6 +506,17 @@ void dcn35_dpstream_root_clock_control(struct
> dce_hwseq *hws, unsigned int dp_hp
> }
> }
>
> +void dcn35_physymclk_root_clock_control(struct dce_hwseq *hws,
> unsigned
> +int phy_inst, bool clock_on) {
> + if (!hws->ctx->dc->debug.root_clock_optimization.bits.physymclk)
> + return;
> +
> + if (hws->ctx->dc->res_pool->dccg->funcs-
> >set_physymclk_root_clock_gating) {
> + hws->ctx->dc->res_pool->dccg->funcs-
> >set_physymclk_root_clock_gating(
> + hws->ctx->dc->res_pool->dccg, phy_inst, clock_on);
> + }
> +}
> +
> void dcn35_dsc_pg_control(
> struct dce_hwseq *hws,
> unsigned int dsc_inst,
> @@ -1020,6 +1031,13 @@ void dcn35_calc_blocks_to_gate(struct dc *dc,
> struct dc_state *context,
> if (pipe_ctx->stream_res.hpo_dp_stream_enc)
> update_state-
> >pg_pipe_res_update[PG_DPSTREAM][pipe_ctx-
> >stream_res.hpo_dp_stream_enc->inst] = false;
> }
> +
> + for (i = 0; i < dc->link_count; i++) {
> + update_state->pg_pipe_res_update[PG_PHYSYMCLK][i] =
> true;
Please fix the index:
update_state->pg_pipe_res_update[PG_PHYSYMCLK][dc->links[i]->link_enc_hw_inst] = true;
With that fixed, the patch is:
Reviewed-by: Roman Li <roman.li@xxxxxxx>
> + if (dc->links[i]->type != dc_connection_none)
> + update_state-
> >pg_pipe_res_update[PG_PHYSYMCLK][dc->links[i]->link_enc_hw_inst] =
> false;
> + }
> +
> /*domain24 controls all the otg, mpc, opp, as long as one otg is still
> up, avoid enabling OTG PG*/
> for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
> struct timing_generator *tg = dc->res_pool-
> >timing_generators[i];
> @@ -1117,6 +1135,10 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc,
> struct dc_state *context,
> }
> }
>
> + for (i = 0; i < dc->link_count; i++)
> + if (dc->links[i]->type != dc_connection_none)
> +
> +update_state->pg_pipe_res_update[PG_PHYSYMCLK][dc->links[i]-
> >link_enc_h
> +w_inst] = true;
> +
> for (i = 0; i < dc->res_pool->hpo_dp_stream_enc_count; i++) {
> if (context->res_ctx.is_hpo_dp_stream_enc_acquired[i] &&
> dc->res_pool->hpo_dp_stream_enc[i]) { @@ -
> 1267,6 +1289,11 @@ void dcn35_root_clock_control(struct dc *dc,
> dc->hwseq-
> >funcs.dpstream_root_clock_control(dc->hwseq, i, power_on);
> }
>
> + for (i = 0; i < dc->res_pool->dig_link_enc_count; i++)
> + if (update_state-
> >pg_pipe_res_update[PG_PHYSYMCLK][i])
> + if (dc->hwseq-
> >funcs.physymclk_root_clock_control)
> + dc->hwseq-
> >funcs.physymclk_root_clock_control(dc->hwseq, i,
> +power_on);
> +
> }
> for (i = 0; i < dc->res_pool->res_cap->num_dsc; i++) {
> if (update_state->pg_pipe_res_update[PG_DSC][i]) { @@ -
> 1292,6 +1319,11 @@ void dcn35_root_clock_control(struct dc *dc,
> dc->hwseq-
> >funcs.dpstream_root_clock_control(dc->hwseq, i, power_on);
> }
>
> + for (i = 0; i < dc->res_pool->dig_link_enc_count; i++)
> + if (update_state-
> >pg_pipe_res_update[PG_PHYSYMCLK][i])
> + if (dc->hwseq-
> >funcs.physymclk_root_clock_control)
> + dc->hwseq-
> >funcs.physymclk_root_clock_control(dc->hwseq, i,
> +power_on);
> +
> }
> }
>
> diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h
> b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h
> index a731c8880d60..bc05beba5f2c 100644
> --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h
> +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h
> @@ -39,6 +39,8 @@ void dcn35_dpp_root_clock_control(struct dce_hwseq
> *hws, unsigned int dpp_inst,
>
> void dcn35_dpstream_root_clock_control(struct dce_hwseq *hws, unsigned
> int dp_hpo_inst, bool clock_on);
>
> +void dcn35_physymclk_root_clock_control(struct dce_hwseq *hws,
> unsigned
> +int phy_inst, bool clock_on);
> +
> void dcn35_enable_power_gating_plane(struct dce_hwseq *hws, bool
> enable);
>
> void dcn35_set_dmu_fgcg(struct dce_hwseq *hws, bool enable); diff --git
> a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
> b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
> index 0e87f3503265..7f2cbfac9099 100644
> --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
> +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
> @@ -149,6 +149,7 @@ static const struct hwseq_private_funcs
> dcn35_private_funcs = {
> .enable_power_gating_plane = dcn35_enable_power_gating_plane,
> .dpp_root_clock_control = dcn35_dpp_root_clock_control,
> .dpstream_root_clock_control = dcn35_dpstream_root_clock_control,
> + .physymclk_root_clock_control =
> dcn35_physymclk_root_clock_control,
> .program_all_writeback_pipes_in_tree =
> dcn30_program_all_writeback_pipes_in_tree,
> .update_odm = dcn35_update_odm,
> .set_hdr_multiplier = dcn10_set_hdr_multiplier, diff --git
> a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
> b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
> index ff772665d1ae..91484b71b7da 100644
> --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
> +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
> @@ -148,6 +148,7 @@ static const struct hwseq_private_funcs
> dcn351_private_funcs = {
> .enable_power_gating_plane = dcn35_enable_power_gating_plane,
> .dpp_root_clock_control = dcn35_dpp_root_clock_control,
> .dpstream_root_clock_control = dcn35_dpstream_root_clock_control,
> + .physymclk_root_clock_control =
> dcn35_physymclk_root_clock_control,
> .program_all_writeback_pipes_in_tree =
> dcn30_program_all_writeback_pipes_in_tree,
> .update_odm = dcn35_update_odm,
> .set_hdr_multiplier = dcn10_set_hdr_multiplier, diff --git
> a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
> b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
> index 939832372baf..7553d6816d36 100644
> --- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
> +++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer_private.h
> @@ -124,6 +124,10 @@ struct hwseq_private_funcs {
> struct dce_hwseq *hws,
> unsigned int dpp_inst,
> bool clock_on);
> + void (*physymclk_root_clock_control)(
> + struct dce_hwseq *hws,
> + unsigned int phy_inst,
> + bool clock_on);
> void (*dpp_pg_control)(struct dce_hwseq *hws,
> unsigned int dpp_inst,
> bool power_on);
> --
> 2.37.3
