[PATCH AUTOSEL 6.4 10/31] drm/amd/display: Add stream overhead in BW calculations for 128b/132b

[PATCH AUTOSEL 6.4 10/31] drm/amd/display: Add stream overhead in BW calculations for 128b/132b

[Sasha Levin]

From: George Shen <george.shen@amd.com>

[ Upstream commit 974764180838516f80a13257da67a1ec6afb87d4 ]

[Why]
Current BW calculations do not account for the additional padding added
for uncompressed pixel-to-symbol packing.

This results in X.Y being too low for 128b/132b SST streams in certain
scenarios. If X.Y is too low, end user can observe image corruption.

[How]
Add function to calculate stream overhead to timing BW calculation for
128b/132b SST cases.

Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Acked-by: Alan Liu <haoping.liu@amd.com>
Signed-off-by: George Shen <george.shen@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/dc.h         |  2 +
 drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c | 42 +++++++++++++++++++++
 2 files changed, 44 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 9279990e43694..508fd6ab58e80 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1375,6 +1375,8 @@ struct dc_plane_state *dc_get_surface_for_mpcc(struct dc *dc,
 
 uint32_t dc_get_opp_for_plane(struct dc *dc, struct dc_plane_state *plane);
 
+void dc_set_disable_128b_132b_stream_overhead(bool disable);
+
 /* The function returns minimum bandwidth required to drive a given timing
  * return - minimum required timing bandwidth in kbps.
  */
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index 2bdc47615543c..9a0c9f9353b41 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -40,6 +40,8 @@ static bool dsc_policy_enable_dsc_when_not_needed;
 
 static bool dsc_policy_disable_dsc_stream_overhead;
 
+static bool disable_128b_132b_stream_overhead;
+
 #ifndef MAX
 #define MAX(X, Y) ((X) > (Y) ? (X) : (Y))
 #endif
@@ -47,6 +49,41 @@ static bool dsc_policy_disable_dsc_stream_overhead;
 #define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
 #endif
 
+/* Need to account for padding due to pixel-to-symbol packing
+ * for uncompressed 128b/132b streams.
+ */
+static uint32_t apply_128b_132b_stream_overhead(
+	const struct dc_crtc_timing *timing, const uint32_t kbps)
+{
+	uint32_t total_kbps = kbps;
+
+	if (disable_128b_132b_stream_overhead)
+		return kbps;
+
+	if (!timing->flags.DSC) {
+		struct fixed31_32 bpp;
+		struct fixed31_32 overhead_factor;
+
+		bpp = dc_fixpt_from_int(kbps);
+		bpp = dc_fixpt_div_int(bpp, timing->pix_clk_100hz / 10);
+
+		/* Symbols_per_HActive = HActive * bpp / (4 lanes * 32-bit symbol size)
+		 * Overhead_factor = ceil(Symbols_per_HActive) / Symbols_per_HActive
+		 */
+		overhead_factor = dc_fixpt_from_int(timing->h_addressable);
+		overhead_factor = dc_fixpt_mul(overhead_factor, bpp);
+		overhead_factor = dc_fixpt_div_int(overhead_factor, 128);
+		overhead_factor = dc_fixpt_div(
+			dc_fixpt_from_int(dc_fixpt_ceil(overhead_factor)),
+			overhead_factor);
+
+		total_kbps = dc_fixpt_ceil(
+			dc_fixpt_mul_int(overhead_factor, total_kbps));
+	}
+
+	return total_kbps;
+}
+
 uint32_t dc_bandwidth_in_kbps_from_timing(
 	const struct dc_crtc_timing *timing)
 {
@@ -1160,6 +1197,11 @@ void dc_dsc_policy_set_disable_dsc_stream_overhead(bool disable)
 	dsc_policy_disable_dsc_stream_overhead = disable;
 }
 
+void dc_set_disable_128b_132b_stream_overhead(bool disable)
+{
+	disable_128b_132b_stream_overhead = disable;
+}
+
 void dc_dsc_get_default_config_option(const struct dc *dc, struct dc_dsc_config_options *options)
 {
 	options->dsc_min_slice_height_override = dc->debug.dsc_min_slice_height_override;
-- 
2.40.1

[PATCH AUTOSEL 6.4 12/31] drm/amd/display: Read down-spread percentage from lut to adjust dprefclk.

[Sasha Levin]

From: Martin Tsai <martin.tsai@amd.com>

[ Upstream commit 6917b0b711713b9d84d7e0844e9aa613997a51b2 ]

[Why]
Panels show corruption with high refresh rate timings when
ss is enabled.

[How]
Read down-spread percentage from lut to adjust dprefclk.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Martin Tsai <martin.tsai@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../dc/clk_mgr/dcn314/dcn314_clk_mgr.c        | 33 +++++++++++++++++--
 .../dc/clk_mgr/dcn314/dcn314_clk_mgr.h        |  7 ++++
 2 files changed, 38 insertions(+), 2 deletions(-)

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 5cb44f838bde5..db1b15796e307 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
@@ -87,6 +87,14 @@ static const struct IP_BASE CLK_BASE = { { { { 0x00016C00, 0x02401800, 0, 0, 0,
 #define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK	0x0000F000L
 #define CLK1_CLK_PLL_REQ__FbMult_frac_MASK	0xFFFF0000L
 
+#define regCLK1_CLK2_BYPASS_CNTL			0x029c
+#define regCLK1_CLK2_BYPASS_CNTL_BASE_IDX	0
+
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL__SHIFT	0x0
+#define CLK1_CLK2_BYPASS_CNTL__LK2_BYPASS_DIV__SHIFT	0x10
+#define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL_MASK		0x00000007L
+#define CLK1_CLK2_BYPASS_CNTL__LK2_BYPASS_DIV_MASK		0x000F0000L
+
 #define REG(reg_name) \
 	(CLK_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
 
@@ -440,6 +448,11 @@ static DpmClocks314_t dummy_clocks;
 
 static struct dcn314_watermarks dummy_wms = { 0 };
 
+static struct dcn314_ss_info_table ss_info_table = {
+	.ss_divider = 1000,
+	.ss_percentage = {0, 0, 375, 375, 375}
+};
+
 static void dcn314_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn314_watermarks *table)
 {
 	int i, num_valid_sets;
@@ -719,6 +732,20 @@ static struct clk_mgr_funcs dcn314_funcs = {
 };
 extern struct clk_mgr_funcs dcn3_fpga_funcs;
 
+static void dcn314_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr)
+{
+	uint32_t clock_source;
+
+	REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source);
+
+	clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source];
+
+	if (clk_mgr->dprefclk_ss_percentage != 0) {
+		clk_mgr->ss_on_dprefclk = true;
+		clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider;
+	}
+}
+
 void dcn314_clk_mgr_construct(
 		struct dc_context *ctx,
 		struct clk_mgr_dcn314 *clk_mgr,
@@ -791,9 +818,11 @@ void dcn314_clk_mgr_construct(
 
 	clk_mgr->base.base.dprefclk_khz = 600000;
 	clk_mgr->base.base.clks.ref_dtbclk_khz = 600000;
-	dce_clock_read_ss_info(&clk_mgr->base);
+
+	dcn314_read_ss_info_from_lut(&clk_mgr->base);
 	/*if bios enabled SS, driver needs to adjust dtb clock, only enable with correct bios*/
-	//clk_mgr->base.dccg->ref_dtbclk_khz = dce_adjust_dp_ref_freq_for_ss(clk_mgr_internal, clk_mgr->base.base.dprefclk_khz);
+	clk_mgr->base.base.dprefclk_khz =
+		dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz);
 
 	clk_mgr->base.base.bw_params = &dcn314_bw_params;
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
index 171f84340eb2f..e0670dafe2600 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
@@ -28,6 +28,8 @@
 #define __DCN314_CLK_MGR_H__
 #include "clk_mgr_internal.h"
 
+#define NUM_CLOCK_SOURCES   5
+
 struct dcn314_watermarks;
 
 struct dcn314_smu_watermark_set {
@@ -40,6 +42,11 @@ struct clk_mgr_dcn314 {
 	struct dcn314_smu_watermark_set smu_wm_set;
 };
 
+struct dcn314_ss_info_table {
+	uint32_t ss_divider;
+	uint32_t ss_percentage[NUM_CLOCK_SOURCES];
+};
+
 bool dcn314_are_clock_states_equal(struct dc_clocks *a,
 		struct dc_clocks *b);
 
-- 
2.40.1

[PATCH AUTOSEL 6.4 13/31] drm/amd/display: Fix underflow issue on 175hz timing

[Sasha Levin]

From: Leo Ma <hanghong.ma@amd.com>

[ Upstream commit 735688eb905db529efea0c78466fccc1461c3fde ]

[Why]
Screen underflows happen on 175hz timing for 3 plane overlay case.

[How]
Based on dst y prefetch value clamp to equ or oto for bandwidth
calculation.

Reviewed-by: Dillon Varone <dillon.varone@amd.com>
Acked-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Leo Ma <hanghong.ma@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../amd/display/dc/dml/dcn32/display_mode_vba_util_32.c    | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
index 61cc4904ade41..4c645854b263b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
@@ -3463,6 +3463,7 @@ bool dml32_CalculatePrefetchSchedule(
 	double TimeForFetchingMetaPTE = 0;
 	double TimeForFetchingRowInVBlank = 0;
 	double LinesToRequestPrefetchPixelData = 0;
+	double LinesForPrefetchBandwidth = 0;
 	unsigned int HostVMDynamicLevelsTrips;
 	double  trip_to_mem;
 	double  Tvm_trips;
@@ -3892,11 +3893,15 @@ bool dml32_CalculatePrefetchSchedule(
 			TimeForFetchingMetaPTE = Tvm_oto;
 			TimeForFetchingRowInVBlank = Tr0_oto;
 			*PrefetchBandwidth = prefetch_bw_oto;
+			/* Clamp to oto for bandwidth calculation */
+			LinesForPrefetchBandwidth = dst_y_prefetch_oto;
 		} else {
 			*DestinationLinesForPrefetch = dst_y_prefetch_equ;
 			TimeForFetchingMetaPTE = Tvm_equ;
 			TimeForFetchingRowInVBlank = Tr0_equ;
 			*PrefetchBandwidth = prefetch_bw_equ;
+			/* Clamp to equ for bandwidth calculation */
+			LinesForPrefetchBandwidth = dst_y_prefetch_equ;
 		}
 
 		*DestinationLinesToRequestVMInVBlank = dml_ceil(4.0 * TimeForFetchingMetaPTE / LineTime, 1.0) / 4.0;
@@ -3904,7 +3909,7 @@ bool dml32_CalculatePrefetchSchedule(
 		*DestinationLinesToRequestRowInVBlank =
 				dml_ceil(4.0 * TimeForFetchingRowInVBlank / LineTime, 1.0) / 4.0;
 
-		LinesToRequestPrefetchPixelData = *DestinationLinesForPrefetch -
+		LinesToRequestPrefetchPixelData = LinesForPrefetchBandwidth -
 				*DestinationLinesToRequestVMInVBlank - 2 * *DestinationLinesToRequestRowInVBlank;
 
 #ifdef __DML_VBA_DEBUG__
-- 
2.40.1

[PATCH AUTOSEL 6.4 18/31] drm/amd/display: Use DTBCLK as refclk instead of DPREFCLK

[Sasha Levin]

From: Austin Zheng <austin.zheng@amd.com>

[ Upstream commit 4a30cc2bd281fa176a68b5305cd3695d636152ad ]

[Why]
Flash of corruption observed when UCLK switching after transitioning
from DTBCLK to DPREFCLK on subVP(DP) + subVP(HDMI) config
Scenario where DPREFCLK is required instead of DTBCLK is not expected

[How]
Always set the DTBCLK source as DTBCLK0

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Austin Zheng <austin.zheng@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
index ffbb739d85b69..8496ff4a25e35 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
@@ -290,7 +290,8 @@ static void dccg32_set_dpstreamclk(
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
 
 	/* set the dtbclk_p source */
-	dccg32_set_dtbclk_p_src(dccg, src, otg_inst);
+	/* always program refclk as DTBCLK. No use-case expected to require DPREFCLK as refclk */
+	dccg32_set_dtbclk_p_src(dccg, DTBCLK0, otg_inst);
 
 	/* enabled to select one of the DTBCLKs for pipe */
 	switch (dp_hpo_inst) {
-- 
2.40.1

[PATCH AUTOSEL 6.4 19/31] drm/amd/display: Blocking invalid 420 modes on HDMI TMDS for DCN31

[Sasha Levin]

From: Leo Chen <sancchen@amd.com>

[ Upstream commit 026a71babf48efb6b9884a3a66fa31aec9e1ea54 ]

[Why & How]
HDMI TMDS does not have ODM support. Filtering 420 modes that
exceed the 4096 FMT limitation on DCN31 will resolve
intermittent corruptions issues.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Leo Chen <sancchen@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c    | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
index a0f44eef7763f..316335be71d0d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
@@ -4135,7 +4135,9 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				if (v->OutputFormat[k] == dm_420 && v->HActive[k] > DCN31_MAX_FMT_420_BUFFER_WIDTH
 						&& v->ODMCombineEnablePerState[i][k] != dm_odm_combine_mode_4to1) {
-					if (v->HActive[k] / 2 > DCN31_MAX_FMT_420_BUFFER_WIDTH) {
+					if (v->Output[k] == dm_hdmi) {
+						FMTBufferExceeded = true;
+					} else if (v->HActive[k] / 2 > DCN31_MAX_FMT_420_BUFFER_WIDTH) {
 						v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_4to1;
 						v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine4To1;
 
-- 
2.40.1

[PATCH AUTOSEL 6.4 20/31] drm/amd/display: Blocking invalid 420 modes on HDMI TMDS for DCN314

[Sasha Levin]

From: Leo Chen <sancchen@amd.com>

[ Upstream commit 4c6107a653ccf361cb1b6ba35d558a1a5e6e57ac ]

[Why & How]
HDMI TMDS does not have ODM support. Filtering 420 modes that
exceed the 4096 FMT limitation on DCN314 will resolve
intermittent corruptions issues.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Leo Chen <sancchen@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c  | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

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 7eb2173b7691e..168dca6e8fcd1 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
@@ -4227,7 +4227,9 @@ void dml314_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_
 				}
 				if (v->OutputFormat[k] == dm_420 && v->HActive[k] > DCN314_MAX_FMT_420_BUFFER_WIDTH
 						&& v->ODMCombineEnablePerState[i][k] != dm_odm_combine_mode_4to1) {
-					if (v->HActive[k] / 2 > DCN314_MAX_FMT_420_BUFFER_WIDTH) {
+					if (v->Output[k] == dm_hdmi) {
+						FMTBufferExceeded = true;
+					} else if (v->HActive[k] / 2 > DCN314_MAX_FMT_420_BUFFER_WIDTH) {
 						v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_4to1;
 						v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine4To1;
 
-- 
2.40.1