[PATCH 01/21] drm/amd/display: Reverted DSC programming sequence change

[PATCH 01/21] drm/amd/display: Reverted DSC programming sequence change

[Pavle Kotarac]

From: Iswara Nagulendran <Iswara.Nagulendran@amd.com>

[HOW&WHY]
Revert a previous commit by moving DSC programming
back to before link enablement.

Reviewed-by: Jayendran Ramani <Jayendran.Ramani@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Iswara Nagulendran <Iswara.Nagulendran@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c       | 13 +++++++++++++
 .../drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 13 -------------
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 38fa63d43ad9..db45a6fdffca 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -4303,6 +4303,19 @@ void core_link_enable_stream(
 		if (pipe_ctx->stream->dpms_off)
 			return;
 
+		/* Have to setup DSC before DIG FE and BE are connected (which happens before the
+		 * link training). This is to make sure the bandwidth sent to DIG BE won't be
+		 * bigger than what the link and/or DIG BE can handle. VBID[6]/CompressedStream_flag
+		 * will be automatically set at a later time when the video is enabled
+		 * (DP_VID_STREAM_EN = 1).
+		 */
+		if (pipe_ctx->stream->timing.flags.DSC) {
+			if (dc_is_dp_signal(pipe_ctx->stream->signal) ||
+				dc_is_virtual_signal(pipe_ctx->stream->signal))
+			dp_set_dsc_enable(pipe_ctx, true);
+
+		}
+
 		status = enable_link(state, pipe_ctx);
 
 		if (status != DC_OK) {
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index fe346e96c2d1..801206aed63a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1577,19 +1577,6 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 	if (dc_is_dp_signal(pipe_ctx->stream->signal))
 		dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_CONNECT_DIG_FE_OTG);
 
-	/* Have to setup DSC before DIG FE and BE are connected (which happens before the
-	 * link training). This is to make sure the bandwidth sent to DIG BE won't be
-	 * bigger than what the link and/or DIG BE can handle. VBID[6]/CompressedStream_flag
-	 * will be automatically set at a later time when the video is enabled
-	 * (DP_VID_STREAM_EN = 1).
-	 */
-	if (pipe_ctx->stream->timing.flags.DSC) {
-		if (dc_is_dp_signal(pipe_ctx->stream->signal) ||
-			dc_is_virtual_signal(pipe_ctx->stream->signal))
-			dp_set_dsc_enable(pipe_ctx, true);
-
-	}
-
 	if (!stream->dpms_off) {
 		if (dc->hwss.update_phy_state)
 			dc->hwss.update_phy_state(context, pipe_ctx, TX_ON_SYMCLK_ON);
-- 
2.34.1

[PATCH 02/21] drm/amd/display: Assign link type before check dsc workaround.

[Pavle Kotarac]

From: "Xu, Jinze" <JinZe.Xu@amd.com>

[Why]
link type is not assigned before check dpia_mst_dsc_always_on conditions.

Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: JinZe.Xu <JinZe.Xu@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index db45a6fdffca..d860d60a4c20 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -832,8 +832,9 @@ static bool discover_dp_mst_topology(struct dc_link *link, enum dc_detect_reason
 	LINK_INFO("link=%d, mst branch is now Connected\n",
 		  link->link_index);
 
-	apply_dpia_mst_dsc_always_on_wa(link);
 	link->type = dc_connection_mst_branch;
+	apply_dpia_mst_dsc_always_on_wa(link);
+
 	dm_helpers_dp_update_branch_info(link->ctx, link);
 	if (dm_helpers_dp_mst_start_top_mgr(link->ctx,
 			link, (reason == DETECT_REASON_BOOT || reason == DETECT_REASON_RESUMEFROMS3S4))) {
-- 
2.34.1

[PATCH 03/21] drm/amd/display: SW cursor fallback for SubVP

[Pavle Kotarac]

From: "Lee, Alvin" <Alvin.Lee2@amd.com>

[Description]
Leverage SW cursor fall back for SubVP
when the cursor is too big. We want to
take advantage of being able to fallback
to SW cursor when possible because it's
not worth it to disable MCLK switching
because the cursor is slightly too big.

Reviewed-by: Aurabindo Pillai <Aurabindo.Pillai@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Alvin Lee <Alvin.Lee2@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_stream.c         | 5 +++++
 drivers/gpu/drm/amd/display/dc/dc.h                     | 1 +
 drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c   | 1 +
 drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c | 1 +
 4 files changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 6752ca44e6e0..0c85ab5933b4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -328,6 +328,11 @@ bool dc_stream_set_cursor_attributes(
 	}
 
 	dc = stream->ctx->dc;
+
+	if (dc->debug.allow_sw_cursor_fallback && attributes->height * attributes->width * 4 > 16384)
+		if (stream->mall_stream_config.type == SUBVP_MAIN)
+			return false;
+
 	stream->cursor_attributes = *attributes;
 
 	dc_z10_restore(dc);
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 75dbc665f435..c48403d49f2e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -830,6 +830,7 @@ struct dc_debug_options {
 	bool disable_fixed_vs_aux_timeout_wa;
 	bool force_disable_subvp;
 	bool force_subvp_mclk_switch;
+	bool allow_sw_cursor_fallback;
 	bool force_usr_allow;
 	/* uses value at boot and disables switch */
 	bool disable_dtb_ref_clk_switch;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index 5a21cf041732..5953083b76a7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -747,6 +747,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.exit_idle_opt_for_cursor_updates = true,
 	.enable_single_display_2to1_odm_policy = true,
 	.enable_dp_dig_pixel_rate_div_policy = 1,
+	.allow_sw_cursor_fallback = false,
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
index 8a89c28add0d..64c225ee3a46 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
@@ -750,6 +750,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.exit_idle_opt_for_cursor_updates = true,
 	.enable_single_display_2to1_odm_policy = true,
 	.enable_dp_dig_pixel_rate_div_policy = 1,
+	.allow_sw_cursor_fallback = false,
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
-- 
2.34.1

[PATCH 04/21] drm/amd/display: Fixing DIG FIFO Error

[Pavle Kotarac]

From: Leo Chen <sancchen@amd.com>

[Why & How]
DIG_FIFO_READ_START_LEVEL should only be set to default value (7) by software.
Removed all instances of resetting the register to 0

Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Leo Chen <sancchen@amd.com>
---
 .../gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c  | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
index e3351ddc566c..06d8638db696 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c
@@ -67,8 +67,7 @@ static void enc314_disable_fifo(struct stream_encoder *enc)
 {
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
-	REG_UPDATE_2(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0,
-		     DIG_FIFO_READ_START_LEVEL, 0);
+	REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0);
 }
 
 static void enc314_dp_set_odm_combine(
-- 
2.34.1

[PATCH 05/21] drm/amd/display: Fix divide by zero in DML

[Pavle Kotarac]

From: Aric Cyr <aric.cyr@amd.com>

[why]
Incorrectly using MicroTileWidth instead of MacroTileWidth for
calculations.

[how]
Remove all unused references to MicroTile and change them to MacroTile.

Reviewed-by: Alvin Lee <Alvin.Lee2@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
---
 .../dc/dml/dcn32/display_mode_vba_32.c        | 24 +++++++++----------
 .../drm/amd/display/dc/dml/display_mode_vba.h | 10 ++++----
 2 files changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
index d8014bfbc3fe..cd6bf67035d4 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
@@ -1806,10 +1806,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				&mode_lib->vba.Read256BlockHeightC[k],
 				&mode_lib->vba.Read256BlockWidthY[k],
 				&mode_lib->vba.Read256BlockWidthC[k],
-				&mode_lib->vba.MicroTileHeightY[k],
-				&mode_lib->vba.MicroTileHeightC[k],
-				&mode_lib->vba.MicroTileWidthY[k],
-				&mode_lib->vba.MicroTileWidthC[k]);
+				&mode_lib->vba.MacroTileHeightY[k],
+				&mode_lib->vba.MacroTileHeightC[k],
+				&mode_lib->vba.MacroTileWidthY[k],
+				&mode_lib->vba.MacroTileWidthC[k]);
 	}
 
 	/*Bandwidth Support Check*/
@@ -2661,10 +2661,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			mode_lib->vba.Read256BlockWidthC,
 			mode_lib->vba.Read256BlockHeightY,
 			mode_lib->vba.Read256BlockHeightC,
-			mode_lib->vba.MicroTileWidthY,
-			mode_lib->vba.MicroTileWidthC,
-			mode_lib->vba.MicroTileHeightY,
-			mode_lib->vba.MicroTileHeightC,
+			mode_lib->vba.MacroTileWidthY,
+			mode_lib->vba.MacroTileWidthC,
+			mode_lib->vba.MacroTileHeightY,
+			mode_lib->vba.MacroTileHeightC,
 
 			/* Output */
 			mode_lib->vba.SurfaceSizeInMALL,
@@ -2711,10 +2711,10 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeight256BytesY = mode_lib->vba.Read256BlockHeightY[k];
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidth256BytesC = mode_lib->vba.Read256BlockWidthC[k];
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeight256BytesC = mode_lib->vba.Read256BlockHeightC[k];
-				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthY = mode_lib->vba.MicroTileWidthY[k];
-				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightY = mode_lib->vba.MicroTileHeightY[k];
-				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthC = mode_lib->vba.MicroTileWidthC[k];
-				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightC = mode_lib->vba.MicroTileHeightC[k];
+				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthY = mode_lib->vba.MacroTileWidthY[k];
+				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightY = mode_lib->vba.MacroTileHeightY[k];
+				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockWidthC = mode_lib->vba.MacroTileWidthC[k];
+				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].BlockHeightC = mode_lib->vba.MacroTileHeightC[k];
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].InterlaceEnable = mode_lib->vba.Interlace[k];
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].HTotal = mode_lib->vba.HTotal[k];
 				v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.SurfParameters[k].DCCEnable = mode_lib->vba.DCCEnable[k];
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
index da8acf59ccac..630f3395e90a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
@@ -652,10 +652,10 @@ struct vba_vars_st {
 
 	unsigned int OutputTypeAndRatePerState[DC__VOLTAGE_STATES][DC__NUM_DPP__MAX];
 	double RequiredDISPCLKPerSurface[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX];
-	unsigned int MicroTileHeightY[DC__NUM_DPP__MAX];
-	unsigned int MicroTileHeightC[DC__NUM_DPP__MAX];
-	unsigned int MicroTileWidthY[DC__NUM_DPP__MAX];
-	unsigned int MicroTileWidthC[DC__NUM_DPP__MAX];
+	unsigned int MacroTileHeightY[DC__NUM_DPP__MAX];
+	unsigned int MacroTileHeightC[DC__NUM_DPP__MAX];
+	unsigned int MacroTileWidthY[DC__NUM_DPP__MAX];
+	unsigned int MacroTileWidthC[DC__NUM_DPP__MAX];
 	bool ImmediateFlipRequiredFinal;
 	bool DCCProgrammingAssumesScanDirectionUnknownFinal;
 	bool EnoughWritebackUnits;
@@ -801,8 +801,6 @@ struct vba_vars_st {
 	double PSCL_FACTOR[DC__NUM_DPP__MAX];
 	double PSCL_FACTOR_CHROMA[DC__NUM_DPP__MAX];
 	double MaximumVStartup[DC__VOLTAGE_STATES][2][DC__NUM_DPP__MAX];
-	unsigned int MacroTileWidthY[DC__NUM_DPP__MAX];
-	unsigned int MacroTileWidthC[DC__NUM_DPP__MAX];
 	double AlignedDCCMetaPitch[DC__NUM_DPP__MAX];
 	double AlignedYPitch[DC__NUM_DPP__MAX];
 	double AlignedCPitch[DC__NUM_DPP__MAX];
-- 
2.34.1

[PATCH 06/21] drm/amd/display: Fix compilation errors on DCN314

[Pavle Kotarac]

From: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>

We have some compilation errors in some DML files from DCN314 that we
never noticed because we were not compiling some of the DML files. This
commit fixes those syntax errors before we enable the compilation.

Cc: Roman Li <roman.li@amd.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
---
 .../drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c
index 503d9ede0ac1..9fe4dc32fbe0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c
@@ -61,7 +61,7 @@
 // fudge factor for min dcfclk calclation
 #define __DML_MIN_DCFCLK_FACTOR__   1.15
 
-struct {
+typedef struct {
 	double DPPCLK;
 	double DISPCLK;
 	double PixelClock;
@@ -1599,7 +1599,7 @@ static void CalculateDCCConfiguration(
 	int segment_order_vert_contiguous_luma;
 	int segment_order_vert_contiguous_chroma;
 
-	enum {
+	typedef enum {
 		REQ_256Bytes, REQ_128BytesNonContiguous, REQ_128BytesContiguous, REQ_NA
 	} RequestType;
 	RequestType RequestLuma;
@@ -7159,12 +7159,13 @@ static double CalculateExtraLatencyBytes(
 			HostVMDynamicLevels = dml_max(0, (int) HostVMMaxNonCachedPageTableLevels - 1);
 		else
 			HostVMDynamicLevels = dml_max(0, (int) HostVMMaxNonCachedPageTableLevels - 2);
-	else
+	} else {
 		HostVMDynamicLevels = 0;
+	}
 
 	ret = ReorderingBytes + (TotalNumberOfActiveDPP * PixelChunkSizeInKByte + TotalNumberOfDCCActiveDPP * MetaChunkSize) * 1024.0;
 
-	if (GPUVMEnable == true)
+	if (GPUVMEnable == true) {
 		for (k = 0; k < NumberOfActivePlanes; ++k)
 			ret = ret + NumberOfDPP[k] * dpte_group_bytes[k] * (1 + 8 * HostVMDynamicLevels) * HostVMInefficiencyFactor;
 	}
-- 
2.34.1

[PATCH 07/21] drm/amd/display: Enable dlg and vba compilation for dcn314

[Pavle Kotarac]

From: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>

We were not using the VBA and DLG files for DCN314, but the next
sequence of changes for DCN314 will require those files. This commit
adds the necessary files to the Makefile.

Cc: Roman Li <roman.li@amd.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/Makefile | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 86a3b5bfd699..cb81ed2fbd53 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -70,6 +70,8 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(fram
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) $(frame_warn_flag)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_mode_vba_314.o := $(dml_ccflags) $(frame_warn_flag)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_rq_dlg_calc_314.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/dcn314_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/dcn30_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/dcn32_fpu.o := $(dml_ccflags)
@@ -123,6 +125,7 @@ DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o
 DML += dcn21/display_rq_dlg_calc_21.o dcn21/display_mode_vba_21.o
 DML += dcn30/dcn30_fpu.o dcn30/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o
 DML += dcn31/display_mode_vba_31.o dcn31/display_rq_dlg_calc_31.o
+DML += dcn314/display_mode_vba_314.o dcn314/display_rq_dlg_calc_314.o
 DML += dcn32/display_mode_vba_32.o dcn32/display_rq_dlg_calc_32.o dcn32/display_mode_vba_util_32.o
 DML += dcn31/dcn31_fpu.o
 DML += dcn32/dcn32_fpu.o
-- 
2.34.1

[PATCH 08/21] drm/amd/display: Hook up DCN314 specific dml implementation

[Pavle Kotarac]

From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>

[Why & How]
Add support for the DML314 functions and hook up DCN314 to use them.

This has some necessary additions for calculating Max VSTARTUP for
future features, but there's also some changes that we have to make
for pixel format/swizzle support.

That will come in a following patch to make this transition easier to
bisect.

Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
---
 .../gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c   |  2 +-
 .../gpu/drm/amd/display/dc/dml/display_mode_lib.c    | 12 ++++++++++++
 .../gpu/drm/amd/display/dc/dml/display_mode_lib.h    |  1 +
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
index 34a5d0f87b5f..fc5529fa51b3 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -262,7 +262,7 @@ void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p
 	}
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
-		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31);
+		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN314);
 	else
 		dml_init_instance(&dc->dml, &dcn3_14_soc, &dcn3_14_ip, DML_PROJECT_DCN31_FPGA);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
index 5d27ff0ebb5f..f5400eda07a5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
@@ -35,6 +35,8 @@
 #include "dcn30/display_rq_dlg_calc_30.h"
 #include "dcn31/display_mode_vba_31.h"
 #include "dcn31/display_rq_dlg_calc_31.h"
+#include "dcn314/display_mode_vba_314.h"
+#include "dcn314/display_rq_dlg_calc_314.h"
 #include "dcn32/display_mode_vba_32.h"
 #include "dcn32/display_rq_dlg_calc_32.h"
 #include "dml_logger.h"
@@ -74,6 +76,13 @@ const struct dml_funcs dml31_funcs = {
 	.rq_dlg_get_rq_reg = dml31_rq_dlg_get_rq_reg
 };
 
+const struct dml_funcs dml314_funcs = {
+	.validate = dml314_ModeSupportAndSystemConfigurationFull,
+	.recalculate = dml314_recalculate,
+	.rq_dlg_get_dlg_reg = dml314_rq_dlg_get_dlg_reg,
+	.rq_dlg_get_rq_reg = dml314_rq_dlg_get_rq_reg
+};
+
 const struct dml_funcs dml32_funcs = {
 	.validate = dml32_ModeSupportAndSystemConfigurationFull,
     .recalculate = dml32_recalculate,
@@ -107,6 +116,9 @@ void dml_init_instance(struct display_mode_lib *lib,
 	case DML_PROJECT_DCN31_FPGA:
 		lib->funcs = dml31_funcs;
 		break;
+	case DML_PROJECT_DCN314:
+		lib->funcs = dml314_funcs;
+		break;
 	case DML_PROJECT_DCN32:
 		lib->funcs = dml32_funcs;
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
index 2bdd6ed22611..b1878a1440e2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
@@ -41,6 +41,7 @@ enum dml_project {
 	DML_PROJECT_DCN30,
 	DML_PROJECT_DCN31,
 	DML_PROJECT_DCN31_FPGA,
+	DML_PROJECT_DCN314,
 	DML_PROJECT_DCN32,
 };
 
-- 
2.34.1

[PATCH 09/21] drm/amd/display: Relax swizzle checks for video non-RGB formats on DCN314

[Pavle Kotarac]

From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>

[Why]
HW can support the display swizzle modes for video, and those are
preferable over standard or linear for decode use.

[How]
Remove the check for DCN314.

Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
---
 .../gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c  | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c
index 9fe4dc32fbe0..2829f179f982 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c
@@ -4071,9 +4071,7 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 
 	v->SourceFormatPixelAndScanSupport = true;
 	for (k = 0; k < v->NumberOfActivePlanes; k++) {
-		if ((v->SurfaceTiling[k] == dm_sw_linear && (!(v->SourceScan[k] != dm_vert) || v->DCCEnable[k] == true))
-				|| ((v->SurfaceTiling[k] == dm_sw_64kb_d || v->SurfaceTiling[k] == dm_sw_64kb_d_t
-						|| v->SurfaceTiling[k] == dm_sw_64kb_d_x) && !(v->SourcePixelFormat[k] == dm_444_64))) {
+		if (v->SurfaceTiling[k] == dm_sw_linear && (!(v->SourceScan[k] != dm_vert) || v->DCCEnable[k] == true)) {
 			v->SourceFormatPixelAndScanSupport = false;
 		}
 	}
-- 
2.34.1

[PATCH 10/21] drm/amd/display: Correct dram channel width for dcn314

[Pavle Kotarac]

From: Duncan Ma <duncan.ma@amd.com>

[Why]
The interpretation of the number of memory channels
differ by memory type, and this affects channel width
for the DML input.

[How]
Set dram channel width according to memory type for
dcn314.

Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Duncan Ma <duncan.ma@amd.com>
---
 drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c | 2 ++
 drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c         | 3 +++
 drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h                | 1 +
 3 files changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index 171c38fac6a3..cd86aa912e3c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -677,6 +677,8 @@ static void dcn314_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *cl
 	}
 	ASSERT(bw_params->clk_table.entries[i-1].dcfclk_mhz);
 	bw_params->vram_type = bios_info->memory_type;
+
+	bw_params->dram_channel_width_bytes = bios_info->memory_type == 0x22 ? 8 : 4;
 	bw_params->num_channels = bios_info->ma_channel_number ? bios_info->ma_channel_number : 4;
 
 	for (i = 0; i < WM_SET_COUNT; i++) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
index fc5529fa51b3..4bb3b31ea7e0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -194,6 +194,9 @@ void dcn314_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p
 		dcn3_14_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator;
 		dcn3_14_ip.max_num_dpp = dc->res_pool->pipe_count;
 
+		if (bw_params->dram_channel_width_bytes > 0)
+			dcn3_14_soc.dram_channel_width_bytes = bw_params->dram_channel_width_bytes;
+
 		if (bw_params->num_channels > 0)
 			dcn3_14_soc.num_chans = bw_params->num_channels;
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index 5d2b028e5dad..d9f1b0a4fbd4 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -214,6 +214,7 @@ struct dummy_pstate_entry {
 struct clk_bw_params {
 	unsigned int vram_type;
 	unsigned int num_channels;
+	unsigned int dram_channel_width_bytes;
  	unsigned int dispclk_vco_khz;
 	unsigned int dc_mode_softmax_memclk;
 	struct clk_limit_table clk_table;
-- 
2.34.1

[PATCH 11/21] drm/amd/display: Round cursor width up for MALL allocation

[Pavle Kotarac]

From: Taimur Hassan <Syed.Hassan@amd.com>

[Why & How]
When calculating cursor size for MALL allocation, the cursor width should
be the actual width rounded up to 64 alignment. Additionally, the bit
depth should vary depending on color format.

Reviewed-by: Alvin Lee <Alvin.Lee2@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
---
 .../gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c | 24 ++++++++++++++++++-
 .../drm/amd/display/dc/dcn32/dcn32_hwseq.c    | 24 ++++++++++++++++++-
 2 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
index 6ec1c52535b9..2038cbda33f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
@@ -103,6 +103,11 @@ void hubp32_cursor_set_attributes(
 	enum cursor_lines_per_chunk lpc = hubp2_get_lines_per_chunk(
 			attr->width, attr->color_format);
 
+	//Round cursor width up to next multiple of 64
+	uint32_t cursor_width = ((attr->width + 63) / 64) * 64;
+	uint32_t cursor_height = attr->height;
+	uint32_t cursor_size = cursor_width * cursor_height;
+
 	hubp->curs_attr = *attr;
 
 	REG_UPDATE(CURSOR_SURFACE_ADDRESS_HIGH,
@@ -126,7 +131,24 @@ void hubp32_cursor_set_attributes(
 			 /* used to shift the cursor chunk request deadline */
 			CURSOR0_CHUNK_HDL_ADJUST, 3);
 
-	if (attr->width * attr->height * 4 > 16384)
+	switch (attr->color_format) {
+	case CURSOR_MODE_MONO:
+		cursor_size /= 2;
+		break;
+	case CURSOR_MODE_COLOR_1BIT_AND:
+	case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA:
+	case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA:
+		cursor_size *= 4;
+		break;
+
+	case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED:
+	case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED:
+	default:
+		cursor_size *= 8;
+		break;
+	}
+
+	if (cursor_size > 16384)
 		REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, true);
 	else
 		REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, false);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
index 769171ab8ef6..dbf2d7cc96c5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -741,7 +741,29 @@ void dcn32_update_mall_sel(struct dc *dc, struct dc_state *context)
 		struct hubp *hubp = pipe->plane_res.hubp;
 
 		if (pipe->stream && pipe->plane_state && hubp && hubp->funcs->hubp_update_mall_sel) {
-			if (hubp->curs_attr.width * hubp->curs_attr.height * 4 > 16384)
+			//Round cursor width up to next multiple of 64
+			int cursor_width = ((hubp->curs_attr.width + 63) / 64) * 64;
+			int cursor_height = hubp->curs_attr.height;
+			int cursor_size = cursor_width * cursor_height;
+
+			switch (hubp->curs_attr.color_format) {
+			case CURSOR_MODE_MONO:
+				cursor_size /= 2;
+				break;
+			case CURSOR_MODE_COLOR_1BIT_AND:
+			case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA:
+			case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA:
+				cursor_size *= 4;
+				break;
+
+			case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED:
+			case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED:
+			default:
+				cursor_size *= 8;
+				break;
+			}
+
+			if (cursor_size > 16384)
 				cache_cursor = true;
 
 			if (pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) {
-- 
2.34.1

[PATCH 12/21] drm/amd/display: Update viewport position for phantom pipes

[Pavle Kotarac]

From: "Lee, Alvin" <Alvin.Lee2@amd.com>

[Description]
In some cases the viewport position of the
main pipes can change without triggering a full update.
In this case the subvp phantom viewports must be updated accordingly.

Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Alvin Lee <Alvin.Lee2@amd.com>
---
 .../drm/amd/display/dc/dcn20/dcn20_hwseq.c    |  7 ++--
 .../drm/amd/display/dc/dcn32/dcn32_hwseq.c    | 32 +++++++++++++++++++
 .../drm/amd/display/dc/dcn32/dcn32_hwseq.h    |  4 +++
 .../gpu/drm/amd/display/dc/dcn32/dcn32_init.c |  1 +
 .../gpu/drm/amd/display/dc/inc/hw_sequencer.h |  5 +++
 5 files changed, 47 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 6271caca4d9a..6f8c344e321d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1898,8 +1898,11 @@ void dcn20_post_unlock_program_front_end(
 			 * can underflow due to HUBP_VTG_SEL programming if done in the regular front end
 			 * programming sequence).
 			 */
-			if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM)
-					dcn20_program_pipe(dc, pipe, context);
+			if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) {
+				if (dc->hwss.update_phantom_vp_position)
+					dc->hwss.update_phantom_vp_position(dc, context, pipe);
+				dcn20_program_pipe(dc, pipe, context);
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
index dbf2d7cc96c5..449459ca5a72 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -1301,3 +1301,35 @@ void dcn32_update_phy_state(struct dc_state *state, struct pipe_ctx *pipe_ctx,
 	} else
 		BREAK_TO_DEBUGGER();
 }
+
+/* For SubVP the main pipe can have a viewport position change
+ * without a full update. In this case we must also update the
+ * viewport positions for the phantom pipe accordingly.
+ */
+void dcn32_update_phantom_vp_position(struct dc *dc,
+		struct dc_state *context,
+		struct pipe_ctx *phantom_pipe)
+{
+	uint8_t i;
+	struct dc_plane_state *phantom_plane = phantom_pipe->plane_state;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_MAIN &&
+				pipe->stream->mall_stream_config.paired_stream == phantom_pipe->stream) {
+			if (pipe->plane_state && pipe->plane_state->update_flags.bits.position_change) {
+
+				phantom_plane->src_rect.x = pipe->plane_state->src_rect.x;
+				phantom_plane->src_rect.y = pipe->plane_state->src_rect.y;
+				phantom_plane->clip_rect.x = pipe->plane_state->clip_rect.x;
+				phantom_plane->dst_rect.x = pipe->plane_state->dst_rect.x;
+				phantom_plane->dst_rect.y = pipe->plane_state->dst_rect.y;
+
+				phantom_pipe->plane_state->update_flags.bits.position_change = 1;
+				resource_build_scaling_params(phantom_pipe);
+				return;
+			}
+		}
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h
index 221e31144d50..150d541f35b4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h
@@ -87,4 +87,8 @@ bool dcn32_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx);
 void dcn32_update_phy_state(struct dc_state *state, struct pipe_ctx *pipe_ctx,
 		enum phy_state target_state);
 
+void dcn32_update_phantom_vp_position(struct dc *dc,
+		struct dc_state *context,
+		struct pipe_ctx *phantom_pipe);
+
 #endif /* __DC_HWSS_DCN32_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
index 28d220218133..c554929471af 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
@@ -105,6 +105,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.subvp_pipe_control_lock = dcn32_subvp_pipe_control_lock,
 	.update_visual_confirm_color = dcn20_update_visual_confirm_color,
 	.update_phy_state = dcn32_update_phy_state,
+	.update_phantom_vp_position = dcn32_update_phantom_vp_position,
 };
 
 static const struct hwseq_private_funcs dcn32_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index 52b4350c9cd8..d7a7b2790143 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -247,6 +247,11 @@ struct hw_sequencer_funcs {
 
 	void (*update_phy_state)(struct dc_state *state, struct pipe_ctx *pipe_ctx, enum phy_state target_state);
 
+
+	void (*update_phantom_vp_position)(struct dc *dc,
+			struct dc_state *context,
+			struct pipe_ctx *phantom_pipe);
+
 	void (*commit_subvp_config)(struct dc *dc, struct dc_state *context);
 	void (*subvp_pipe_control_lock)(struct dc *dc,
 			struct dc_state *context,
-- 
2.34.1

[PATCH 13/21] drm/amd/display: Added debug option for forcing subvp num ways

[Pavle Kotarac]

From: "Lee, Alvin" <Alvin.Lee2@amd.com>

[Description]
Regkey option for forcing num ways for
subvp for debug purposes

Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Alvin Lee <Alvin.Lee2@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h                   |  1 +
 .../drm/amd/display/dc/dcn32/dcn32_resource_helpers.c | 11 ++++++++---
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index c48403d49f2e..e8e8e031b9d7 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -831,6 +831,7 @@ struct dc_debug_options {
 	bool force_disable_subvp;
 	bool force_subvp_mclk_switch;
 	bool allow_sw_cursor_fallback;
+	unsigned int force_subvp_num_ways;
 	bool force_usr_allow;
 	/* uses value at boot and disables switch */
 	bool disable_dtb_ref_clk_switch;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
index 13cd1f2e50ca..7c37575d69c7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -54,13 +54,14 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat
 	uint32_t num_mblks = 0;
 	uint32_t cache_lines_per_plane = 0;
 	uint32_t i = 0, j = 0;
-	uint32_t mblk_width = 0;
-	uint32_t mblk_height = 0;
+	uint16_t mblk_width = 0;
+	uint16_t mblk_height = 0;
 	uint32_t full_vp_width_blk_aligned = 0;
 	uint32_t full_vp_height_blk_aligned = 0;
 	uint32_t mall_alloc_width_blk_aligned = 0;
 	uint32_t mall_alloc_height_blk_aligned = 0;
-	uint32_t full_vp_height = 0;
+	uint16_t full_vp_height = 0;
+	bool subvp_in_use = false;
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
@@ -70,6 +71,7 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat
 				pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) {
 			struct pipe_ctx *main_pipe = NULL;
 
+			subvp_in_use = true;
 			/* Get full viewport height from main pipe (required for MBLK calculation) */
 			for (j = 0; j < dc->res_pool->pipe_count; j++) {
 				main_pipe = &context->res_ctx.pipe_ctx[j];
@@ -129,6 +131,9 @@ uint32_t dcn32_helper_calculate_num_ways_for_subvp(struct dc *dc, struct dc_stat
 	if (cache_lines_used % lines_per_way > 0)
 		num_ways++;
 
+	if (subvp_in_use && dc->debug.force_subvp_num_ways > 0)
+		num_ways = dc->debug.force_subvp_num_ways;
+
 	return num_ways;
 }
 
-- 
2.34.1

[PATCH 14/21] drm/amd/display: add workaround for subvp cursor corruption for DCN32/321

[Pavle Kotarac]

From: Aurabindo Pillai <aurabindo.pillai@amd.com>

[Why&How]
Kernel does not have a means to tell the userspace to use software
cursor. Due to lack of this functionality, reducing the max cursor size
is the only way to ensure that power savings of Subview port feature is
utilized for asics that support it. The workaround could be removed after
cursor caching is fixed while a subviewport config is active.

Reviewed-by: Alvin Lee <Alvin.Lee2@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c   | 3 ++-
 drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index 5953083b76a7..0b94a783d285 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -2116,7 +2116,8 @@ static bool dcn32_resource_construct(
 	dc->caps.max_downscale_ratio = 600;
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.i2c_speed_in_khz_hdcp = 100; /*1.4 w/a applied by default*/
-	dc->caps.max_cursor_size = 256;
+	/* TODO: Bring max_cursor_size back to 256 after subvp cursor corruption is fixed*/
+	dc->caps.max_cursor_size = 64;
 	dc->caps.min_horizontal_blanking_period = 80;
 	dc->caps.dmdata_alloc_size = 2048;
 	dc->caps.mall_size_per_mem_channel = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
index 64c225ee3a46..b602fdbbaf10 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
@@ -1721,7 +1721,8 @@ static bool dcn321_resource_construct(
 	dc->caps.max_downscale_ratio = 600;
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.i2c_speed_in_khz_hdcp = 100; /*1.4 w/a applied by default*/
-	dc->caps.max_cursor_size = 256;
+	/* TODO: Bring max cursor size back to 256 after subvp cursor corruption is fixed*/
+	dc->caps.max_cursor_size = 64;
 	dc->caps.min_horizontal_blanking_period = 80;
 	dc->caps.dmdata_alloc_size = 2048;
 	dc->caps.mall_size_per_mem_channel = 0;
-- 
2.34.1

[PATCH 15/21] drm/amd/display: Limit user regamma to a valid value

[Pavle Kotarac]

From: Yao Wang1 <Yao.Wang1@amd.com>

[Why]
For HDR mode, we get total 512 tf_point and after
switching to SDR mode we actually get 400 tf_point
and the rest of points(401~512) still use dirty
value from HDR mode. We should limit the rest of
the points to max value.

[How]
Limit the value when coordinates_x.x > 1, just like
what we do in translate_from_linear_space for other
re-gamma build paths.

Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Yao Wang1 <Yao.Wang1@amd.com>
---
 drivers/gpu/drm/amd/display/modules/color/color_gamma.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index 859ffd8725c5..04f7656906ca 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -1600,6 +1600,7 @@ static void interpolate_user_regamma(uint32_t hw_points_num,
 	struct fixed31_32 lut2;
 	struct fixed31_32 delta_lut;
 	struct fixed31_32 delta_index;
+	const struct fixed31_32 one = dc_fixpt_from_int(1);
 
 	i = 0;
 	/* fixed_pt library has problems handling too small values */
@@ -1628,6 +1629,9 @@ static void interpolate_user_regamma(uint32_t hw_points_num,
 			} else
 				hw_x = coordinates_x[i].x;
 
+			if (dc_fixpt_le(one, hw_x))
+				hw_x = one;
+
 			norm_x = dc_fixpt_mul(norm_factor, hw_x);
 			index = dc_fixpt_floor(norm_x);
 			if (index < 0 || index > 255)
-- 
2.34.1

[PATCH 16/21] drm/amd/display: Adding log for spread_spectrum_info

[Pavle Kotarac]

From: "Chen, Leo" <SanChuan.Chen@amd.com>

[Why & How]
Enable logging for spread_spectrum_percentage in spread_spectrum_info
to facilitate debugging for audio compliance issues

Co-authored-by: Leo Chen <sancchen@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Leo Chen <sancchen@amd.com>
---
 .../drm/amd/display/dc/bios/bios_parser2.c    | 20 +++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index ead4da11a992..85ed0afb74a9 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -849,6 +849,8 @@ static enum bp_result get_ss_info_v4_1(
 				disp_cntl_tbl->dvi_ss_rate_10hz * 10;
 		if (disp_cntl_tbl->dvi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
 			ss_info->type.CENTER_MODE = true;
+
+		DC_LOG_BIOS("AS_SIGNAL_TYPE_DVI: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_HDMI:
 		ss_info->spread_spectrum_percentage =
@@ -857,6 +859,8 @@ static enum bp_result get_ss_info_v4_1(
 				disp_cntl_tbl->hdmi_ss_rate_10hz * 10;
 		if (disp_cntl_tbl->hdmi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
 			ss_info->type.CENTER_MODE = true;
+
+		DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	/* TODO LVDS not support anymore? */
 	case AS_SIGNAL_TYPE_DISPLAY_PORT:
@@ -866,6 +870,8 @@ static enum bp_result get_ss_info_v4_1(
 				disp_cntl_tbl->dp_ss_rate_10hz * 10;
 		if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
 			ss_info->type.CENTER_MODE = true;
+
+		DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_GPU_PLL:
 		/* atom_firmware: DAL only get data from dce_info table.
@@ -886,6 +892,8 @@ static enum bp_result get_ss_info_v4_1(
 				smu_info->gpuclk_ss_rate_10hz * 10;
 		if (smu_info->waflclk_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
 			ss_info->type.CENTER_MODE = true;
+
+		DC_LOG_BIOS("AS_SIGNAL_TYPE_XGMI: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	default:
 		result = BP_RESULT_UNSUPPORTED;
@@ -935,6 +943,8 @@ static enum bp_result get_ss_info_v4_2(
 				disp_cntl_tbl->dvi_ss_rate_10hz * 10;
 		if (disp_cntl_tbl->dvi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
 			ss_info->type.CENTER_MODE = true;
+
+		DC_LOG_BIOS("AS_SIGNAL_TYPE_DVI: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_HDMI:
 		ss_info->spread_spectrum_percentage =
@@ -943,6 +953,8 @@ static enum bp_result get_ss_info_v4_2(
 				disp_cntl_tbl->hdmi_ss_rate_10hz * 10;
 		if (disp_cntl_tbl->hdmi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
 			ss_info->type.CENTER_MODE = true;
+
+		DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	/* TODO LVDS not support anymore? */
 	case AS_SIGNAL_TYPE_DISPLAY_PORT:
@@ -952,6 +964,8 @@ static enum bp_result get_ss_info_v4_2(
 				smu_info->gpuclk_ss_rate_10hz * 10;
 		if (smu_info->gpuclk_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
 			ss_info->type.CENTER_MODE = true;
+
+		DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_GPU_PLL:
 		/* atom_firmware: DAL only get data from dce_info table.
@@ -1000,6 +1014,8 @@ static enum bp_result get_ss_info_v4_5(
 				disp_cntl_tbl->dvi_ss_rate_10hz * 10;
 		if (disp_cntl_tbl->dvi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
 			ss_info->type.CENTER_MODE = true;
+
+		DC_LOG_BIOS("AS_SIGNAL_TYPE_DVI: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_HDMI:
 		ss_info->spread_spectrum_percentage =
@@ -1008,6 +1024,8 @@ static enum bp_result get_ss_info_v4_5(
 				disp_cntl_tbl->hdmi_ss_rate_10hz * 10;
 		if (disp_cntl_tbl->hdmi_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
 			ss_info->type.CENTER_MODE = true;
+
+		DC_LOG_BIOS("AS_SIGNAL_TYPE_HDMI: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_DISPLAY_PORT:
 		ss_info->spread_spectrum_percentage =
@@ -1016,6 +1034,8 @@ static enum bp_result get_ss_info_v4_5(
 				disp_cntl_tbl->dp_ss_rate_10hz * 10;
 		if (disp_cntl_tbl->dp_ss_mode & ATOM_SS_CENTRE_SPREAD_MODE)
 			ss_info->type.CENTER_MODE = true;
+
+		DC_LOG_BIOS("AS_SIGNAL_TYPE_DISPLAY_PORT: %d\n", ss_info->spread_spectrum_percentage);
 		break;
 	case AS_SIGNAL_TYPE_GPU_PLL:
 		/* atom_smu_info_v4_0 does not have fields for SS for SMU Display PLL anymore.
-- 
2.34.1

[PATCH 17/21] drm/amd/display: Don't adjust VRR unnecessarily

[Pavle Kotarac]

From: "Cyr, Aric" <Aric.Cyr@amd.com>

[why]
Do not need to spend time reprogramming DRR if there were no updates to
the parameters.

[how]
Compare the current stream state to the requested one to determine if an
update is required.

In amdgpu_dm the timing_changed flag is set but never used so can remove it.
Similarly, the stream update for VRR is done after dc_commit and should
not update its adjust field until after the update is completed.  The
adjust field is managed by dc_stream_adjust_vmin_vmax and should not be
manually updated in amdgpu_dm.

Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 10 ----------
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h |  1 -
 drivers/gpu/drm/amd/display/dc/core/dc.c          |  3 +++
 3 files changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index dbe76b85552e..7a9f7c7da7d6 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7385,11 +7385,6 @@ static void update_freesync_state_on_stream(
 		&vrr_infopacket,
 		pack_sdp_v1_3);
 
-	new_crtc_state->freesync_timing_changed |=
-		(memcmp(&acrtc->dm_irq_params.vrr_params.adjust,
-			&vrr_params.adjust,
-			sizeof(vrr_params.adjust)) != 0);
-
 	new_crtc_state->freesync_vrr_info_changed |=
 		(memcmp(&new_crtc_state->vrr_infopacket,
 			&vrr_infopacket,
@@ -7398,7 +7393,6 @@ static void update_freesync_state_on_stream(
 	acrtc->dm_irq_params.vrr_params = vrr_params;
 	new_crtc_state->vrr_infopacket = vrr_infopacket;
 
-	new_stream->adjust = acrtc->dm_irq_params.vrr_params.adjust;
 	new_stream->vrr_infopacket = vrr_infopacket;
 
 	if (new_crtc_state->freesync_vrr_info_changed)
@@ -7461,10 +7455,6 @@ static void update_stream_irq_parameters(
 				      new_stream,
 				      &config, &vrr_params);
 
-	new_crtc_state->freesync_timing_changed |=
-		(memcmp(&acrtc->dm_irq_params.vrr_params.adjust,
-			&vrr_params.adjust, sizeof(vrr_params.adjust)) != 0);
-
 	new_crtc_state->freesync_config = config;
 	/* Copy state for access from DM IRQ handler */
 	acrtc->dm_irq_params.freesync_config = config;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index b44faaad9b0b..b5ce15c43bcc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -681,7 +681,6 @@ struct dm_crtc_state {
 
 	int crc_skip_count;
 
-	bool freesync_timing_changed;
 	bool freesync_vrr_info_changed;
 
 	bool dsc_force_changed;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 9860bf38c547..7481801c6d7c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -401,6 +401,9 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 {
 	int i;
 
+	if (memcmp(adjust, &stream->adjust, sizeof(struct dc_crtc_timing_adjust)) == 0)
+		return true;
+
 	stream->adjust.v_total_max = adjust->v_total_max;
 	stream->adjust.v_total_mid = adjust->v_total_mid;
 	stream->adjust.v_total_mid_frame_num = adjust->v_total_mid_frame_num;
-- 
2.34.1

[PATCH 18/21] drm/amd/display: Avoid force minimal transaction in case of surface_count equal to 0.

[Pavle Kotarac]

From: JeromeHong <jerome.hong@amd.com>

[why]
Call commit_minimal_transition_state wrongly in case of surface_count equal to 0.

[how]
Add a condition to filter case of surface_count equal to 0.

Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: JeromeHong <jerome.hong@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 7481801c6d7c..253dc4e35ba4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3625,11 +3625,13 @@ bool dc_update_planes_and_stream(struct dc *dc,
 			dc->current_state->stream_count > 0 &&
 			dc->debug.pipe_split_policy != MPC_SPLIT_AVOID) {
 		/* determine if minimal transition is required */
-		if (cur_stream_status->plane_count > surface_count) {
-			force_minimal_pipe_splitting = true;
-		} else if (cur_stream_status->plane_count < surface_count) {
-			force_minimal_pipe_splitting = true;
-			is_plane_addition = true;
+		if (surface_count > 0) {
+			if (cur_stream_status->plane_count > surface_count) {
+				force_minimal_pipe_splitting = true;
+			} else if (cur_stream_status->plane_count < surface_count) {
+				force_minimal_pipe_splitting = true;
+				is_plane_addition = true;
+			}
 		}
 	}
 
-- 
2.34.1

[PATCH 19/21] drm/amd/display: Refactor SubVP calculation to remove FPU

[Pavle Kotarac]

From: Alvin Lee <alvin.lee2@amd.com>

Refactor calculation to remove floating point operations from dmub_srv.
To ensure that 32-bit compilation works well, we use the div64 family of
macros to do integer division for SubVP-related timing parameters.

Cc: Maíra Canal <mairacanal@riseup.net>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Isabella Basso <isabbasso@riseup.net>
Cc: Magali Lemes <magalilemes00@gmail.com>
Reviewed-by: Samson Tam <Samson.Tam@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Alvin Lee <alvin.lee2@amd.com>
Co-developed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Co-developed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c | 89 ++++++++++----------
 1 file changed, 44 insertions(+), 45 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index 7b765efe0825..080704d4e540 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -450,44 +450,42 @@ static void populate_subvp_cmd_drr_info(struct dc *dc,
 	struct dc_crtc_timing *main_timing = &subvp_pipe->stream->timing;
 	struct dc_crtc_timing *phantom_timing = &subvp_pipe->stream->mall_stream_config.paired_stream->timing;
 	struct dc_crtc_timing *drr_timing = &vblank_pipe->stream->timing;
-	int16_t drr_frame_us = 0;
-	int16_t min_drr_supported_us = 0;
-	int16_t max_drr_supported_us = 0;
-	int16_t max_drr_vblank_us = 0;
-	int16_t max_drr_mallregion_us = 0;
-	int16_t mall_region_us = 0;
-	int16_t prefetch_us = 0;
-	int16_t subvp_active_us = 0;
-	int16_t drr_active_us = 0;
-	int16_t min_vtotal_supported = 0;
-	int16_t max_vtotal_supported = 0;
+	uint16_t drr_frame_us = 0;
+	uint16_t min_drr_supported_us = 0;
+	uint16_t max_drr_supported_us = 0;
+	uint16_t max_drr_vblank_us = 0;
+	uint16_t max_drr_mallregion_us = 0;
+	uint16_t mall_region_us = 0;
+	uint16_t prefetch_us = 0;
+	uint16_t subvp_active_us = 0;
+	uint16_t drr_active_us = 0;
+	uint16_t min_vtotal_supported = 0;
+	uint16_t max_vtotal_supported = 0;
 
 	pipe_data->pipe_config.vblank_data.drr_info.drr_in_use = true;
 	pipe_data->pipe_config.vblank_data.drr_info.use_ramping = false; // for now don't use ramping
 	pipe_data->pipe_config.vblank_data.drr_info.drr_window_size_ms = 4; // hardcode 4ms DRR window for now
 
-	drr_frame_us = div64_s64(drr_timing->v_total * drr_timing->h_total,
-				 (int64_t)(drr_timing->pix_clk_100hz * 100) * 1000000);
+	drr_frame_us = div64_u64(((uint64_t)drr_timing->v_total * drr_timing->h_total * 1000000),
+			(((uint64_t)drr_timing->pix_clk_100hz * 100)));
 	// P-State allow width and FW delays already included phantom_timing->v_addressable
-	mall_region_us = div64_s64(phantom_timing->v_addressable * phantom_timing->h_total,
-				   (int64_t)(phantom_timing->pix_clk_100hz * 100) * 1000000);
+	mall_region_us = div64_u64(((uint64_t)phantom_timing->v_addressable * phantom_timing->h_total * 1000000),
+			(((uint64_t)phantom_timing->pix_clk_100hz * 100)));
 	min_drr_supported_us = drr_frame_us + mall_region_us + SUBVP_DRR_MARGIN_US;
-	min_vtotal_supported = div64_s64(drr_timing->pix_clk_100hz * 100 *
-					 (div64_s64((int64_t)min_drr_supported_us, 1000000)),
-					 (int64_t)drr_timing->h_total);
-
-	prefetch_us = div64_s64((phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total,
-				(int64_t)(phantom_timing->pix_clk_100hz * 100) * 1000000 +
-				dc->caps.subvp_prefetch_end_to_mall_start_us);
-	subvp_active_us = div64_s64(main_timing->v_addressable * main_timing->h_total,
-				    (int64_t)(main_timing->pix_clk_100hz * 100) * 1000000);
-	drr_active_us = div64_s64(drr_timing->v_addressable * drr_timing->h_total,
-				  (int64_t)(drr_timing->pix_clk_100hz * 100) * 1000000);
-	max_drr_vblank_us = div64_s64((int64_t)(subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us;
+	min_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * min_drr_supported_us),
+			(((uint64_t)drr_timing->h_total * 1000000)));
+
+	prefetch_us = ((uint64_t)(phantom_timing->v_total - phantom_timing->v_front_porch) * phantom_timing->h_total * 1000000)
+			/ (((uint64_t)phantom_timing->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us);
+	subvp_active_us = div64_u64(((uint64_t)main_timing->v_addressable * main_timing->h_total * 1000000),
+			(((uint64_t)main_timing->pix_clk_100hz * 100)));
+	drr_active_us = div64_u64(((uint64_t)drr_timing->v_addressable * drr_timing->h_total * 1000000),
+			(((uint64_t)drr_timing->pix_clk_100hz * 100)));
+	max_drr_vblank_us = div64_u64((subvp_active_us - prefetch_us - drr_active_us), 2) + drr_active_us;
 	max_drr_mallregion_us = subvp_active_us - prefetch_us - mall_region_us;
 	max_drr_supported_us = max_drr_vblank_us > max_drr_mallregion_us ? max_drr_vblank_us : max_drr_mallregion_us;
-	max_vtotal_supported = div64_s64(drr_timing->pix_clk_100hz * 100 * (div64_s64((int64_t)max_drr_supported_us, 1000000)),
-					 (int64_t)drr_timing->h_total);
+	max_vtotal_supported = div64_u64(((uint64_t)drr_timing->pix_clk_100hz * 100 * max_drr_supported_us),
+			(((uint64_t)drr_timing->h_total * 1000000)));
 
 	pipe_data->pipe_config.vblank_data.drr_info.min_vtotal_supported = min_vtotal_supported;
 	pipe_data->pipe_config.vblank_data.drr_info.max_vtotal_supported = max_vtotal_supported;
@@ -581,10 +579,12 @@ static void update_subvp_prefetch_end_to_mall_start(struct dc *dc,
 	struct dc_crtc_timing *phantom_timing1 = &subvp_pipes[1]->stream->mall_stream_config.paired_stream->timing;
 	struct dmub_cmd_fw_assisted_mclk_switch_pipe_data_v2 *pipe_data = NULL;
 
-	subvp0_prefetch_us = div64_s64((phantom_timing0->v_total - phantom_timing0->v_front_porch) * phantom_timing0->h_total,
-				       (int64_t)(phantom_timing0->pix_clk_100hz * 100) * 1000000 + dc->caps.subvp_prefetch_end_to_mall_start_us);
-	subvp1_prefetch_us = div64_s64((phantom_timing1->v_total - phantom_timing1->v_front_porch) * phantom_timing1->h_total,
-				       (int64_t)(phantom_timing1->pix_clk_100hz * 100) * 1000000 + dc->caps.subvp_prefetch_end_to_mall_start_us);
+	subvp0_prefetch_us = div64_u64(((uint64_t)(phantom_timing0->v_total - phantom_timing0->v_front_porch) *
+			(uint64_t)phantom_timing0->h_total * 1000000),
+			(((uint64_t)phantom_timing0->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us));
+	subvp1_prefetch_us = div64_u64(((uint64_t)(phantom_timing1->v_total - phantom_timing1->v_front_porch) *
+			(uint64_t)phantom_timing1->h_total * 1000000),
+			(((uint64_t)phantom_timing1->pix_clk_100hz * 100) + dc->caps.subvp_prefetch_end_to_mall_start_us));
 
 	// Whichever SubVP PIPE has the smaller prefetch (including the prefetch end to mall start time)
 	// should increase it's prefetch time to match the other
@@ -592,16 +592,17 @@ static void update_subvp_prefetch_end_to_mall_start(struct dc *dc,
 		pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[1];
 		prefetch_delta_us = subvp0_prefetch_us - subvp1_prefetch_us;
 		pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines =
-			div64_s64(((div64_s64((int64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us), 1000000)) *
-				   (phantom_timing1->pix_clk_100hz * 100) + phantom_timing1->h_total - 1),
-				  (int64_t)phantom_timing1->h_total);
+				div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) *
+					((uint64_t)phantom_timing1->pix_clk_100hz * 100) + ((uint64_t)phantom_timing1->h_total * 1000000 - 1)),
+					((uint64_t)phantom_timing1->h_total * 1000000));
+
 	} else if (subvp1_prefetch_us >  subvp0_prefetch_us) {
 		pipe_data = &cmd->fw_assisted_mclk_switch_v2.config_data.pipe_data[0];
 		prefetch_delta_us = subvp1_prefetch_us - subvp0_prefetch_us;
 		pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines =
-			div64_s64(((div64_s64((int64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us), 1000000)) *
-				   (phantom_timing0->pix_clk_100hz * 100) + phantom_timing0->h_total - 1),
-				  (int64_t)phantom_timing0->h_total);
+				div64_u64(((uint64_t)(dc->caps.subvp_prefetch_end_to_mall_start_us + prefetch_delta_us) *
+					((uint64_t)phantom_timing0->pix_clk_100hz * 100) + ((uint64_t)phantom_timing0->h_total * 1000000 - 1)),
+					((uint64_t)phantom_timing0->h_total * 1000000));
 	}
 }
 
@@ -668,13 +669,11 @@ static void populate_subvp_cmd_pipe_info(struct dc *dc,
 
 	// Round up
 	pipe_data->pipe_config.subvp_data.prefetch_to_mall_start_lines =
-		div64_s64(((div64_s64((int64_t)dc->caps.subvp_prefetch_end_to_mall_start_us, 1000000)) *
-			   (phantom_timing->pix_clk_100hz * 100) + phantom_timing->h_total - 1),
-			  (int64_t)phantom_timing->h_total);
+			div64_u64(((uint64_t)dc->caps.subvp_prefetch_end_to_mall_start_us * ((uint64_t)phantom_timing->pix_clk_100hz * 100) +
+					((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000));
 	pipe_data->pipe_config.subvp_data.processing_delay_lines =
-		div64_s64(((div64_s64((int64_t)dc->caps.subvp_fw_processing_delay_us, 1000000)) *
-			   (phantom_timing->pix_clk_100hz * 100) + phantom_timing->h_total - 1),
-			  (int64_t)phantom_timing->h_total);
+			div64_u64(((uint64_t)(dc->caps.subvp_fw_processing_delay_us) * ((uint64_t)phantom_timing->pix_clk_100hz * 100) +
+					((uint64_t)phantom_timing->h_total * 1000000 - 1)), ((uint64_t)phantom_timing->h_total * 1000000));
 	// Find phantom pipe index based on phantom stream
 	for (j = 0; j < dc->res_pool->pipe_count; j++) {
 		struct pipe_ctx *phantom_pipe = &context->res_ctx.pipe_ctx[j];
-- 
2.34.1

[PATCH 20/21] drm/amd/display: Fix register definitions for DCN32/321

[Pavle Kotarac]

From: Aurabindo Pillai <aurabindo.pillai@amd.com>

[Why & How]
Fix the instatiation sequence for MPC registers and add a few other
missing register definitions that were ommited erroneously when copying
them over to enable runtime initialization of reigster offsets for
DCN32/321

Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
---
 .../drm/amd/display/dc/dcn32/dcn32_resource.c |  27 +--
 .../drm/amd/display/dc/dcn32/dcn32_resource.h | 216 ++++++++++++------
 .../amd/display/dc/dcn321/dcn321_resource.c   |  24 +-
 3 files changed, 166 insertions(+), 101 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index 0b94a783d285..11f1435b8c07 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -468,22 +468,17 @@ static const struct dcn20_dsc_mask dsc_mask = {
 };
 
 static struct dcn30_mpc_registers mpc_regs;
-#define dcn_mpc_regs_init()\
-		( \
-		MPC_REG_LIST_DCN3_0_RI(0),\
-		MPC_REG_LIST_DCN3_0_RI(1),\
-		MPC_REG_LIST_DCN3_0_RI(2),\
-		MPC_REG_LIST_DCN3_0_RI(3),\
-		MPC_OUT_MUX_REG_LIST_DCN3_0_RI(0),\
-		MPC_OUT_MUX_REG_LIST_DCN3_0_RI(1),\
-		MPC_OUT_MUX_REG_LIST_DCN3_0_RI(2),\
-		MPC_OUT_MUX_REG_LIST_DCN3_0_RI(3),\
-		MPC_MCM_REG_LIST_DCN32_RI(0),\
-		MPC_MCM_REG_LIST_DCN32_RI(1),\
-		MPC_MCM_REG_LIST_DCN32_RI(2),\
-		MPC_MCM_REG_LIST_DCN32_RI(3),\
-		MPC_DWB_MUX_REG_LIST_DCN3_0_RI(0)\
-		)
+
+#define dcn_mpc_regs_init() \
+	MPC_REG_LIST_DCN3_2_RI(0),\
+	MPC_REG_LIST_DCN3_2_RI(1),\
+	MPC_REG_LIST_DCN3_2_RI(2),\
+	MPC_REG_LIST_DCN3_2_RI(3),\
+	MPC_OUT_MUX_REG_LIST_DCN3_0_RI(0),\
+	MPC_OUT_MUX_REG_LIST_DCN3_0_RI(1),\
+	MPC_OUT_MUX_REG_LIST_DCN3_0_RI(2),\
+	MPC_OUT_MUX_REG_LIST_DCN3_0_RI(3),\
+	MPC_DWB_MUX_REG_LIST_DCN3_0_RI(0)
 
 static const struct dcn30_mpc_shift mpc_shift = {
 	MPC_COMMON_MASK_SH_LIST_DCN32(__SHIFT)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h
index d1e85622dd3b..95f3517724d1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.h
@@ -225,7 +225,8 @@ void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_par
       SRI_ARR(DP_MSA_TIMING_PARAM4, DP, id),                                   \
       SRI_ARR(DP_MSE_RATE_CNTL, DP, id), SRI_ARR(DP_MSE_RATE_UPDATE, DP, id),  \
       SRI_ARR(DP_PIXEL_FORMAT, DP, id), SRI_ARR(DP_SEC_CNTL, DP, id),          \
-      SRI_ARR(DP_SEC_CNTL2, DP, id), SRI_ARR(DP_SEC_CNTL6, DP, id),            \
+      SRI_ARR(DP_SEC_CNTL1, DP, id), SRI_ARR(DP_SEC_CNTL2, DP, id),            \
+      SRI_ARR(DP_SEC_CNTL5, DP, id), SRI_ARR(DP_SEC_CNTL6, DP, id),            \
       SRI_ARR(DP_STEER_FIFO, DP, id), SRI_ARR(DP_VID_M, DP, id),               \
       SRI_ARR(DP_VID_N, DP, id), SRI_ARR(DP_VID_STREAM_CNTL, DP, id),          \
       SRI_ARR(DP_VID_TIMING, DP, id), SRI_ARR(DP_SEC_AUD_N, DP, id),           \
@@ -738,75 +739,6 @@ void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_par
 #define MPC_DWB_MUX_REG_LIST_DCN3_0_RI(inst)                                   \
   SRII_DWB(DWB_MUX, MUX, MPC_DWB, inst)
 
-#define MPC_MCM_REG_LIST_DCN32_RI(inst)                                        \
-  ( \
-  SRII(MPCC_MCM_SHAPER_CONTROL, MPCC_MCM, inst),                               \
-      SRII(MPCC_MCM_SHAPER_OFFSET_R, MPCC_MCM, inst),                          \
-      SRII(MPCC_MCM_SHAPER_OFFSET_G, MPCC_MCM, inst),                          \
-      SRII(MPCC_MCM_SHAPER_OFFSET_B, MPCC_MCM, inst),                          \
-      SRII(MPCC_MCM_SHAPER_SCALE_R, MPCC_MCM, inst),                           \
-      SRII(MPCC_MCM_SHAPER_SCALE_G_B, MPCC_MCM, inst),                         \
-      SRII(MPCC_MCM_SHAPER_LUT_INDEX, MPCC_MCM, inst),                         \
-      SRII(MPCC_MCM_SHAPER_LUT_DATA, MPCC_MCM, inst),                          \
-      SRII(MPCC_MCM_SHAPER_LUT_WRITE_EN_MASK, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_B, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_G, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_R, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_B, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_G, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_R, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_0_1, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_2_3, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_4_5, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_6_7, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_8_9, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_10_11, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_12_13, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_14_15, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_16_17, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_18_19, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_20_21, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_22_23, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_24_25, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_26_27, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_28_29, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_30_31, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMA_REGION_32_33, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_B, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_G, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_R, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_B, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_G, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_R, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_0_1, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_2_3, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_4_5, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_6_7, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_8_9, MPCC_MCM, inst),                   \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_10_11, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_12_13, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_14_15, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_16_17, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_18_19, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_20_21, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_22_23, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_24_25, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_26_27, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_28_29, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_30_31, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_SHAPER_RAMB_REGION_32_33, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_3DLUT_MODE, MPCC_MCM, inst),                               \
-      SRII(MPCC_MCM_3DLUT_INDEX, MPCC_MCM, inst),                              \
-      SRII(MPCC_MCM_3DLUT_DATA, MPCC_MCM, inst),                               \
-      SRII(MPCC_MCM_3DLUT_DATA_30BIT, MPCC_MCM, inst),                         \
-      SRII(MPCC_MCM_3DLUT_READ_WRITE_CONTROL, MPCC_MCM, inst),                 \
-      SRII(MPCC_MCM_3DLUT_OUT_NORM_FACTOR, MPCC_MCM, inst),                    \
-      SRII(MPCC_MCM_3DLUT_OUT_OFFSET_R, MPCC_MCM, inst),                       \
-      SRII(MPCC_MCM_3DLUT_OUT_OFFSET_G, MPCC_MCM, inst),                       \
-      SRII(MPCC_MCM_3DLUT_OUT_OFFSET_B, MPCC_MCM, inst),                       \
-      SRII(MPCC_MCM_MEM_PWR_CTRL, MPCC_MCM, inst)                              \
-  )
-
 #define MPC_OUT_MUX_COMMON_REG_LIST_DCN1_0_RI(inst)                            \
   ( \
   SRII(MUX, MPC_OUT, inst), VUPDATE_SRII(CUR, VUPDATE_LOCK_SET, inst)          \
@@ -890,6 +822,149 @@ void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_par
       SRII(MPCC_OGAM_LUT_CONTROL, MPCC_OGAM, inst)                             \
   )
 
+#define MPC_REG_LIST_DCN3_2_RI(inst) \
+	MPC_REG_LIST_DCN3_0_RI(inst),\
+	SRII(MPCC_MOVABLE_CM_LOCATION_CONTROL, MPCC, inst),\
+	SRII(MPCC_MCM_SHAPER_CONTROL, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_OFFSET_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_OFFSET_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_OFFSET_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_SCALE_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_SCALE_G_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_LUT_INDEX, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_LUT_DATA, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_LUT_WRITE_EN_MASK, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_START_CNTL_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_END_CNTL_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_0_1, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_2_3, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_4_5, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_6_7, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_8_9, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_10_11, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_12_13, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_14_15, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_16_17, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_18_19, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_20_21, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_22_23, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_24_25, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_26_27, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_28_29, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_30_31, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMA_REGION_32_33, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_START_CNTL_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_END_CNTL_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_0_1, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_2_3, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_4_5, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_6_7, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_8_9, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_10_11, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_12_13, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_14_15, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_16_17, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_18_19, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_20_21, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_22_23, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_24_25, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_26_27, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_28_29, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_30_31, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_SHAPER_RAMB_REGION_32_33, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_3DLUT_MODE, MPCC_MCM, inst), /*TODO: may need to add other 3DLUT regs*/\
+	SRII(MPCC_MCM_3DLUT_INDEX, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_3DLUT_DATA, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_3DLUT_DATA_30BIT, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_3DLUT_READ_WRITE_CONTROL, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_3DLUT_OUT_NORM_FACTOR, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_3DLUT_OUT_OFFSET_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_3DLUT_OUT_OFFSET_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_3DLUT_OUT_OFFSET_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_CONTROL, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_LUT_INDEX, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_LUT_DATA, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_LUT_CONTROL, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_START_CNTL_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_START_CNTL_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_START_CNTL_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_START_SLOPE_CNTL_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_START_SLOPE_CNTL_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_START_SLOPE_CNTL_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_START_BASE_CNTL_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_START_BASE_CNTL_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_START_BASE_CNTL_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL1_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL2_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL1_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL2_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL1_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_END_CNTL2_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_OFFSET_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_OFFSET_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_OFFSET_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_0_1, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_2_3, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_4_5, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_6_7, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_8_9, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_10_11, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_12_13, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_14_15, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_16_17, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_18_19, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_20_21, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_22_23, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_24_25, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_26_27, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_28_29, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_30_31, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMA_REGION_32_33, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_START_CNTL_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_START_CNTL_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_START_CNTL_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_START_SLOPE_CNTL_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_START_SLOPE_CNTL_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_START_SLOPE_CNTL_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_START_BASE_CNTL_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_START_BASE_CNTL_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_START_BASE_CNTL_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL1_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL2_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL1_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL2_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL1_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_END_CNTL2_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_OFFSET_B, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_OFFSET_G, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_OFFSET_R, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_0_1, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_2_3, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_4_5, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_6_7, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_8_9, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_10_11, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_12_13, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_14_15, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_16_17, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_18_19, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_20_21, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_22_23, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_24_25, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_26_27, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_28_29, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_30_31, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_1DLUT_RAMB_REGION_32_33, MPCC_MCM, inst),\
+	SRII(MPCC_MCM_MEM_PWR_CTRL, MPCC_MCM, inst)
+
 /* OPTC */
 
 #define OPTC_COMMON_REG_LIST_DCN3_2_RI(inst)                                   \
@@ -1124,6 +1199,7 @@ void dcn32_determine_det_override(struct dc_state *context, display_e2e_pipe_par
       SR(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_D), SR(DCHUBBUB_DET0_CTRL),    \
       SR(DCHUBBUB_DET1_CTRL), SR(DCHUBBUB_DET2_CTRL), SR(DCHUBBUB_DET3_CTRL),  \
       SR(DCHUBBUB_COMPBUF_CTRL), SR(COMPBUF_RESERVED_SPACE),                   \
+      SR(DCHUBBUB_DEBUG_CTRL_0),                                               \
       SR(DCHUBBUB_ARB_USR_RETRAINING_CNTL),                                    \
       SR(DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_A),                             \
       SR(DCHUBBUB_ARB_USR_RETRAINING_WATERMARK_B),                             \
diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
index b602fdbbaf10..1bbc0bdf5dc3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
@@ -473,21 +473,15 @@ static const struct dcn20_dsc_mask dsc_mask = {
 
 static struct dcn30_mpc_registers mpc_regs;
 #define dcn_mpc_regs_init()\
-		( \
-		MPC_REG_LIST_DCN3_0_RI(0),\
-		MPC_REG_LIST_DCN3_0_RI(1),\
-		MPC_REG_LIST_DCN3_0_RI(2),\
-		MPC_REG_LIST_DCN3_0_RI(3),\
-		MPC_OUT_MUX_REG_LIST_DCN3_0_RI(0),\
-		MPC_OUT_MUX_REG_LIST_DCN3_0_RI(1),\
-		MPC_OUT_MUX_REG_LIST_DCN3_0_RI(2),\
-		MPC_OUT_MUX_REG_LIST_DCN3_0_RI(3),\
-		MPC_MCM_REG_LIST_DCN32_RI(0),\
-		MPC_MCM_REG_LIST_DCN32_RI(1),\
-		MPC_MCM_REG_LIST_DCN32_RI(2),\
-		MPC_MCM_REG_LIST_DCN32_RI(3),\
-		MPC_DWB_MUX_REG_LIST_DCN3_0_RI(0)\
-		)
+	MPC_REG_LIST_DCN3_2_RI(0),\
+	MPC_REG_LIST_DCN3_2_RI(1),\
+	MPC_REG_LIST_DCN3_2_RI(2),\
+	MPC_REG_LIST_DCN3_2_RI(3),\
+	MPC_OUT_MUX_REG_LIST_DCN3_0_RI(0),\
+	MPC_OUT_MUX_REG_LIST_DCN3_0_RI(1),\
+	MPC_OUT_MUX_REG_LIST_DCN3_0_RI(2),\
+	MPC_OUT_MUX_REG_LIST_DCN3_0_RI(3),\
+	MPC_DWB_MUX_REG_LIST_DCN3_0_RI(0)
 
 static const struct dcn30_mpc_shift mpc_shift = {
 	MPC_COMMON_MASK_SH_LIST_DCN32(__SHIFT)
-- 
2.34.1

[PATCH 21/21] drm/amd/display: 3.2.202

[Pavle Kotarac]

From: Aric Cyr <aric.cyr@amd.com>

This version brings along following fixes:
*Fixed register definitions for DCN32/321
*Adding log for spread_spectrum_info
*Reverted DSC programming sequence change
*Correct I2C register offset *Updated DCN30 header files, viewport position for phantom pipes
*Enable dlg and vba compilation for dcn314

Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
Signed-off-by: Aric Cyr <aric.cyr@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index e8e8e031b9d7..53b13beff0b2 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -47,7 +47,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.201"
+#define DC_VER "3.2.202"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
-- 
2.34.1

RE: [PATCH 07/21] drm/amd/display: Enable dlg and vba compilation for dcn314

[Li, Roman]

[Public]

Reviewed-by: Roman Li <Roman.Li@amd.com>

> -----Original Message-----
> From: Kotarac, Pavle <Pavle.Kotarac@amd.com>
> Sent: Wednesday, September 7, 2022 2:12 PM
> To: amd-gfx@lists.freedesktop.org
> Cc: Wentland, Harry <Harry.Wentland@amd.com>; Li, Sun peng (Leo)
> <Sunpeng.Li@amd.com>; Lakha, Bhawanpreet
> <Bhawanpreet.Lakha@amd.com>; Siqueira, Rodrigo
> <Rodrigo.Siqueira@amd.com>; Pillai, Aurabindo
> <Aurabindo.Pillai@amd.com>; Zhuo, Qingqing (Lillian)
> <Qingqing.Zhuo@amd.com>; Li, Roman <Roman.Li@amd.com>; Lin, Wayne
> <Wayne.Lin@amd.com>; Wang, Chao-kai (Stylon)
> <Stylon.Wang@amd.com>; Chiu, Solomon <Solomon.Chiu@amd.com>;
> Kotarac, Pavle <Pavle.Kotarac@amd.com>; Gutierrez, Agustin
> <Agustin.Gutierrez@amd.com>
> Subject: [PATCH 07/21] drm/amd/display: Enable dlg and vba compilation for
> dcn314
>
> From: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
>
> We were not using the VBA and DLG files for DCN314, but the next sequence
> of changes for DCN314 will require those files. This commit adds the
> necessary files to the Makefile.
>
> Cc: Roman Li <roman.li@amd.com>
> Signed-off-by: Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
> ---
>  drivers/gpu/drm/amd/display/dc/dml/Makefile | 3 +++
>  1 file changed, 3 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile
> b/drivers/gpu/drm/amd/display/dc/dml/Makefile
> index 86a3b5bfd699..cb81ed2fbd53 100644
> --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
> +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
> @@ -70,6 +70,8 @@
> CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o :=
> $(dml_ccflags) $(fram
> CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o :=
> $(dml_ccflags)
> CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o :=
> $(dml_ccflags) $(frame_warn_flag)
> CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o :=
> $(dml_ccflags)
> +CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_mode_vba_314.o :=
> +$(dml_ccflags) $(frame_warn_flag)
> +CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/display_rq_dlg_calc_314.o :=
> +$(dml_ccflags)
>  CFLAGS_$(AMDDALPATH)/dc/dml/dcn314/dcn314_fpu.o := $(dml_ccflags)
> CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/dcn30_fpu.o := $(dml_ccflags)
> CFLAGS_$(AMDDALPATH)/dc/dml/dcn32/dcn32_fpu.o := $(dml_ccflags) @@
> -123,6 +125,7 @@ DML += dcn20/display_rq_dlg_calc_20v2.o
> dcn20/display_mode_vba_20v2.o  DML += dcn21/display_rq_dlg_calc_21.o
> dcn21/display_mode_vba_21.o  DML += dcn30/dcn30_fpu.o
> dcn30/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o  DML +=
> dcn31/display_mode_vba_31.o dcn31/display_rq_dlg_calc_31.o
> +DML += dcn314/display_mode_vba_314.o
> dcn314/display_rq_dlg_calc_314.o
>  DML += dcn32/display_mode_vba_32.o dcn32/display_rq_dlg_calc_32.o
> dcn32/display_mode_vba_util_32.o  DML += dcn31/dcn31_fpu.o  DML +=
> dcn32/dcn32_fpu.o
> --
> 2.34.1

Re: [PATCH 11/21] drm/amd/display: Round cursor width up for MALL allocation

[Christian König]

Am 07.09.22 um 20:11 schrieb Pavle Kotarac:
> From: Taimur Hassan <Syed.Hassan@amd.com>
>
> [Why & How]
> When calculating cursor size for MALL allocation, the cursor width should
> be the actual width rounded up to 64 alignment. Additionally, the bit
> depth should vary depending on color format.
>
> Reviewed-by: Alvin Lee <Alvin.Lee2@amd.com>
> Acked-by: Pavle Kotarac <Pavle.Kotarac@amd.com>
> Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
> ---
>   .../gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c | 24 ++++++++++++++++++-
>   .../drm/amd/display/dc/dcn32/dcn32_hwseq.c    | 24 ++++++++++++++++++-
>   2 files changed, 46 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
> index 6ec1c52535b9..2038cbda33f7 100644
> --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
> +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
> @@ -103,6 +103,11 @@ void hubp32_cursor_set_attributes(
>   	enum cursor_lines_per_chunk lpc = hubp2_get_lines_per_chunk(
>   			attr->width, attr->color_format);
>   
> +	//Round cursor width up to next multiple of 64

Please no // style comments in kernel code.

Regards,
Christian.

> +	uint32_t cursor_width = ((attr->width + 63) / 64) * 64;
> +	uint32_t cursor_height = attr->height;
> +	uint32_t cursor_size = cursor_width * cursor_height;
> +
>   	hubp->curs_attr = *attr;
>   
>   	REG_UPDATE(CURSOR_SURFACE_ADDRESS_HIGH,
> @@ -126,7 +131,24 @@ void hubp32_cursor_set_attributes(
>   			 /* used to shift the cursor chunk request deadline */
>   			CURSOR0_CHUNK_HDL_ADJUST, 3);
>   
> -	if (attr->width * attr->height * 4 > 16384)
> +	switch (attr->color_format) {
> +	case CURSOR_MODE_MONO:
> +		cursor_size /= 2;
> +		break;
> +	case CURSOR_MODE_COLOR_1BIT_AND:
> +	case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA:
> +	case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA:
> +		cursor_size *= 4;
> +		break;
> +
> +	case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED:
> +	case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED:
> +	default:
> +		cursor_size *= 8;
> +		break;
> +	}
> +
> +	if (cursor_size > 16384)
>   		REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, true);
>   	else
>   		REG_UPDATE(DCHUBP_MALL_CONFIG, USE_MALL_FOR_CURSOR, false);
> diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
> index 769171ab8ef6..dbf2d7cc96c5 100644
> --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
> +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
> @@ -741,7 +741,29 @@ void dcn32_update_mall_sel(struct dc *dc, struct dc_state *context)
>   		struct hubp *hubp = pipe->plane_res.hubp;
>   
>   		if (pipe->stream && pipe->plane_state && hubp && hubp->funcs->hubp_update_mall_sel) {
> -			if (hubp->curs_attr.width * hubp->curs_attr.height * 4 > 16384)
> +			//Round cursor width up to next multiple of 64
> +			int cursor_width = ((hubp->curs_attr.width + 63) / 64) * 64;
> +			int cursor_height = hubp->curs_attr.height;
> +			int cursor_size = cursor_width * cursor_height;
> +
> +			switch (hubp->curs_attr.color_format) {
> +			case CURSOR_MODE_MONO:
> +				cursor_size /= 2;
> +				break;
> +			case CURSOR_MODE_COLOR_1BIT_AND:
> +			case CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA:
> +			case CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA:
> +				cursor_size *= 4;
> +				break;
> +
> +			case CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED:
> +			case CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED:
> +			default:
> +				cursor_size *= 8;
> +				break;
> +			}
> +
> +			if (cursor_size > 16384)
>   				cache_cursor = true;
>   
>   			if (pipe->stream->mall_stream_config.type == SUBVP_PHANTOM) {