Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.5-2023-06-02:

amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates

amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions

radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero

ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()

UAPI:
- Add new ctx query flag to better handle GPU resets
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
  Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3

amd-drm-next-6.5-2023-06-09:

amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class

amdkfd:
- Add debugger support for gdb

radeon:
- Fix possible UAF

drm:
- Add Colorspace functionality

UAPI:
- Add debugger interface for enabling gdb
  Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
  Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com

4 files changed, 160 insertions, 143 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
index 59836570603a..deb6d162a2d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
@@ -483,7 +483,7 @@ void dcn31_calculate_wm_and_dlg_fp(
 		int pipe_cnt,
 		int vlevel)
 {
-	int i, pipe_idx, active_hubp_count = 0;
+	int i, pipe_idx, total_det = 0, active_hubp_count = 0;
 	double dcfclk = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb];
 
 	dc_assert_fp_enabled();
@@ -563,6 +563,18 @@ void dcn31_calculate_wm_and_dlg_fp(
 			if (context->res_ctx.pipe_ctx[i].stream)
 				context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz = 0;
 	}
+	for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) {
+		if (!context->res_ctx.pipe_ctx[i].stream)
+			continue;
+
+		context->res_ctx.pipe_ctx[i].det_buffer_size_kb =
+				get_det_buffer_size_kbytes(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
+		if (context->res_ctx.pipe_ctx[i].det_buffer_size_kb > 384)
+			context->res_ctx.pipe_ctx[i].det_buffer_size_kb /= 2;
+		total_det += context->res_ctx.pipe_ctx[i].det_buffer_size_kb;
+		pipe_idx++;
+	}
+	context->bw_ctx.bw.dcn.compbuf_size_kb = context->bw_ctx.dml.ip.config_return_buffer_size_in_kbytes - total_det;
 }
 
 void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
@@ -570,6 +582,7 @@ void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 	struct _vcs_dpi_voltage_scaling_st *s = dc->scratch.update_bw_bounding_box.clock_limits;
 	struct clk_limit_table *clk_table = &bw_params->clk_table;
 	unsigned int i, closest_clk_lvl;
+	int max_dispclk_mhz = 0, max_dppclk_mhz = 0;
 	int j;
 
 	dc_assert_fp_enabled();
@@ -577,59 +590,55 @@ void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 	memcpy(s, dcn3_1_soc.clock_limits, sizeof(dcn3_1_soc.clock_limits));
 
 	// Default clock levels are used for diags, which may lead to overclocking.
-	if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
-		int max_dispclk_mhz = 0, max_dppclk_mhz = 0;
+	dcn3_1_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator;
+	dcn3_1_ip.max_num_dpp = dc->res_pool->pipe_count;
+	dcn3_1_soc.num_chans = bw_params->num_channels;
 
-		dcn3_1_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator;
-		dcn3_1_ip.max_num_dpp = dc->res_pool->pipe_count;
-		dcn3_1_soc.num_chans = bw_params->num_channels;
+	ASSERT(clk_table->num_entries);
 
-		ASSERT(clk_table->num_entries);
+	/* Prepass to find max clocks independent of voltage level. */
+	for (i = 0; i < clk_table->num_entries; ++i) {
+		if (clk_table->entries[i].dispclk_mhz > max_dispclk_mhz)
+			max_dispclk_mhz = clk_table->entries[i].dispclk_mhz;
+		if (clk_table->entries[i].dppclk_mhz > max_dppclk_mhz)
+			max_dppclk_mhz = clk_table->entries[i].dppclk_mhz;
+	}
 
-		/* Prepass to find max clocks independent of voltage level. */
-		for (i = 0; i < clk_table->num_entries; ++i) {
-			if (clk_table->entries[i].dispclk_mhz > max_dispclk_mhz)
-				max_dispclk_mhz = clk_table->entries[i].dispclk_mhz;
-			if (clk_table->entries[i].dppclk_mhz > max_dppclk_mhz)
-				max_dppclk_mhz = clk_table->entries[i].dppclk_mhz;
+	for (i = 0; i < clk_table->num_entries; i++) {
+		/* loop backwards*/
+		for (closest_clk_lvl = 0, j = dcn3_1_soc.num_states - 1; j >= 0; j--) {
+			if ((unsigned int) dcn3_1_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) {
+				closest_clk_lvl = j;
+				break;
+			}
 		}
 
-		for (i = 0; i < clk_table->num_entries; i++) {
-			/* loop backwards*/
-			for (closest_clk_lvl = 0, j = dcn3_1_soc.num_states - 1; j >= 0; j--) {
-				if ((unsigned int) dcn3_1_soc.clock_limits[j].dcfclk_mhz <= clk_table->entries[i].dcfclk_mhz) {
-					closest_clk_lvl = j;
-					break;
-				}
-			}
+		s[i].state = i;
 
-			s[i].state = i;
-
-			/* Clocks dependent on voltage level. */
-			s[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
-			s[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
-			s[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
-			s[i].dram_speed_mts = clk_table->entries[i].memclk_mhz *
-				2 * clk_table->entries[i].wck_ratio;
-
-			/* Clocks independent of voltage level. */
-			s[i].dispclk_mhz = max_dispclk_mhz ? max_dispclk_mhz :
-				dcn3_1_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
-
-			s[i].dppclk_mhz = max_dppclk_mhz ? max_dppclk_mhz :
-				dcn3_1_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
-
-			s[i].dram_bw_per_chan_gbps =
-				dcn3_1_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
-			s[i].dscclk_mhz = dcn3_1_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
-			s[i].dtbclk_mhz = dcn3_1_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
-			s[i].phyclk_d18_mhz =
-				dcn3_1_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
-			s[i].phyclk_mhz = dcn3_1_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
-		}
-		if (clk_table->num_entries) {
-			dcn3_1_soc.num_states = clk_table->num_entries;
-		}
+		/* Clocks dependent on voltage level. */
+		s[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
+		s[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
+		s[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
+		s[i].dram_speed_mts = clk_table->entries[i].memclk_mhz *
+			2 * clk_table->entries[i].wck_ratio;
+
+		/* Clocks independent of voltage level. */
+		s[i].dispclk_mhz = max_dispclk_mhz ? max_dispclk_mhz :
+			dcn3_1_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
+
+		s[i].dppclk_mhz = max_dppclk_mhz ? max_dppclk_mhz :
+			dcn3_1_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
+
+		s[i].dram_bw_per_chan_gbps =
+			dcn3_1_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
+		s[i].dscclk_mhz = dcn3_1_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
+		s[i].dtbclk_mhz = dcn3_1_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
+		s[i].phyclk_d18_mhz =
+			dcn3_1_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
+		s[i].phyclk_mhz = dcn3_1_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
+	}
+	if (clk_table->num_entries) {
+		dcn3_1_soc.num_states = clk_table->num_entries;
 	}
 
 	memcpy(dcn3_1_soc.clock_limits, s, sizeof(dcn3_1_soc.clock_limits));
@@ -643,10 +652,7 @@ void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 		dcn3_1_soc.dram_clock_change_latency_us = dc->debug.dram_clock_change_latency_ns / 1000;
 	}
 
-	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
-		dml_init_instance(&dc->dml, &dcn3_1_soc, &dcn3_1_ip, DML_PROJECT_DCN31);
-	else
-		dml_init_instance(&dc->dml, &dcn3_1_soc, &dcn3_1_ip, DML_PROJECT_DCN31_FPGA);
+	dml_init_instance(&dc->dml, &dcn3_1_soc, &dcn3_1_ip, DML_PROJECT_DCN31);
 }
 
 void dcn315_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
@@ -707,10 +713,7 @@ void dcn315_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 		dcn3_15_soc.dram_clock_change_latency_us = dc->debug.dram_clock_change_latency_ns / 1000;
 	}
 
-	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
-		dml_init_instance(&dc->dml, &dcn3_15_soc, &dcn3_15_ip, DML_PROJECT_DCN315);
-	else
-		dml_init_instance(&dc->dml, &dcn3_15_soc, &dcn3_15_ip, DML_PROJECT_DCN31_FPGA);
+	dml_init_instance(&dc->dml, &dcn3_15_soc, &dcn3_15_ip, DML_PROJECT_DCN315);
 }
 
 void dcn316_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
@@ -726,71 +729,68 @@ void dcn316_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 	memcpy(s, dcn3_16_soc.clock_limits, sizeof(dcn3_16_soc.clock_limits));
 
 	// Default clock levels are used for diags, which may lead to overclocking.
-	if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
+	dcn3_16_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator;
+	dcn3_16_ip.max_num_dpp = dc->res_pool->pipe_count;
+	dcn3_16_soc.num_chans = bw_params->num_channels;
 
-		dcn3_16_ip.max_num_otg = dc->res_pool->res_cap->num_timing_generator;
-		dcn3_16_ip.max_num_dpp = dc->res_pool->pipe_count;
-		dcn3_16_soc.num_chans = bw_params->num_channels;
-
-		ASSERT(clk_table->num_entries);
+	ASSERT(clk_table->num_entries);
 
-		/* Prepass to find max clocks independent of voltage level. */
-		for (i = 0; i < clk_table->num_entries; ++i) {
-			if (clk_table->entries[i].dispclk_mhz > max_dispclk_mhz)
-				max_dispclk_mhz = clk_table->entries[i].dispclk_mhz;
-			if (clk_table->entries[i].dppclk_mhz > max_dppclk_mhz)
-				max_dppclk_mhz = clk_table->entries[i].dppclk_mhz;
-		}
+	/* Prepass to find max clocks independent of voltage level. */
+	for (i = 0; i < clk_table->num_entries; ++i) {
+		if (clk_table->entries[i].dispclk_mhz > max_dispclk_mhz)
+			max_dispclk_mhz = clk_table->entries[i].dispclk_mhz;
+		if (clk_table->entries[i].dppclk_mhz > max_dppclk_mhz)
+			max_dppclk_mhz = clk_table->entries[i].dppclk_mhz;
+	}
 
-		for (i = 0; i < clk_table->num_entries; i++) {
-			/* loop backwards*/
-			for (closest_clk_lvl = 0, j = dcn3_16_soc.num_states - 1; j >= 0; j--) {
-				if ((unsigned int) dcn3_16_soc.clock_limits[j].dcfclk_mhz <=
-				    clk_table->entries[i].dcfclk_mhz) {
-					closest_clk_lvl = j;
-					break;
-				}
-			}
-			// Ported from DCN315
-			if (clk_table->num_entries == 1) {
-				/*smu gives one DPM level, let's take the highest one*/
-				closest_clk_lvl = dcn3_16_soc.num_states - 1;
+	for (i = 0; i < clk_table->num_entries; i++) {
+		/* loop backwards*/
+		for (closest_clk_lvl = 0, j = dcn3_16_soc.num_states - 1; j >= 0; j--) {
+			if ((unsigned int) dcn3_16_soc.clock_limits[j].dcfclk_mhz <=
+			    clk_table->entries[i].dcfclk_mhz) {
+				closest_clk_lvl = j;
+				break;
 			}
+		}
+		// Ported from DCN315
+		if (clk_table->num_entries == 1) {
+			/*smu gives one DPM level, let's take the highest one*/
+			closest_clk_lvl = dcn3_16_soc.num_states - 1;
+		}
 
-			s[i].state = i;
+		s[i].state = i;
 
-			/* Clocks dependent on voltage level. */
-			s[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
-			if (clk_table->num_entries == 1 &&
-			    s[i].dcfclk_mhz <
-			    dcn3_16_soc.clock_limits[closest_clk_lvl].dcfclk_mhz) {
-				/*SMU fix not released yet*/
-				s[i].dcfclk_mhz =
-					dcn3_16_soc.clock_limits[closest_clk_lvl].dcfclk_mhz;
-			}
-			s[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
-			s[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
-			s[i].dram_speed_mts = clk_table->entries[i].memclk_mhz *
-				2 * clk_table->entries[i].wck_ratio;
-
-			/* Clocks independent of voltage level. */
-			s[i].dispclk_mhz = max_dispclk_mhz ? max_dispclk_mhz :
-				dcn3_16_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
-
-			s[i].dppclk_mhz = max_dppclk_mhz ? max_dppclk_mhz :
-				dcn3_16_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
-
-			s[i].dram_bw_per_chan_gbps =
-				dcn3_16_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
-			s[i].dscclk_mhz = dcn3_16_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
-			s[i].dtbclk_mhz = dcn3_16_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
-			s[i].phyclk_d18_mhz =
-				dcn3_16_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
-			s[i].phyclk_mhz = dcn3_16_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
-		}
-		if (clk_table->num_entries) {
-			dcn3_16_soc.num_states = clk_table->num_entries;
+		/* Clocks dependent on voltage level. */
+		s[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
+		if (clk_table->num_entries == 1 &&
+		    s[i].dcfclk_mhz <
+		    dcn3_16_soc.clock_limits[closest_clk_lvl].dcfclk_mhz) {
+			/*SMU fix not released yet*/
+			s[i].dcfclk_mhz =
+				dcn3_16_soc.clock_limits[closest_clk_lvl].dcfclk_mhz;
 		}
+		s[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
+		s[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
+		s[i].dram_speed_mts = clk_table->entries[i].memclk_mhz *
+			2 * clk_table->entries[i].wck_ratio;
+
+		/* Clocks independent of voltage level. */
+		s[i].dispclk_mhz = max_dispclk_mhz ? max_dispclk_mhz :
+			dcn3_16_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
+
+		s[i].dppclk_mhz = max_dppclk_mhz ? max_dppclk_mhz :
+			dcn3_16_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
+
+		s[i].dram_bw_per_chan_gbps =
+			dcn3_16_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
+		s[i].dscclk_mhz = dcn3_16_soc.clock_limits[closest_clk_lvl].dscclk_mhz;
+		s[i].dtbclk_mhz = dcn3_16_soc.clock_limits[closest_clk_lvl].dtbclk_mhz;
+		s[i].phyclk_d18_mhz =
+			dcn3_16_soc.clock_limits[closest_clk_lvl].phyclk_d18_mhz;
+		s[i].phyclk_mhz = dcn3_16_soc.clock_limits[closest_clk_lvl].phyclk_mhz;
+	}
+	if (clk_table->num_entries) {
+		dcn3_16_soc.num_states = clk_table->num_entries;
 	}
 
 	memcpy(dcn3_16_soc.clock_limits, s, sizeof(dcn3_16_soc.clock_limits));
@@ -805,13 +805,21 @@ void dcn316_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 		dcn3_16_soc.dram_clock_change_latency_us = dc->debug.dram_clock_change_latency_ns / 1000;
 	}
 
-	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
-		dml_init_instance(&dc->dml, &dcn3_16_soc, &dcn3_16_ip, DML_PROJECT_DCN31);
-	else
-		dml_init_instance(&dc->dml, &dcn3_16_soc, &dcn3_16_ip, DML_PROJECT_DCN31_FPGA);
+	dml_init_instance(&dc->dml, &dcn3_16_soc, &dcn3_16_ip, DML_PROJECT_DCN31);
 }
 
 int dcn_get_max_non_odm_pix_rate_100hz(struct _vcs_dpi_soc_bounding_box_st *soc)
 {
 	return soc->clock_limits[0].dispclk_mhz * 10000.0 / (1.0 + soc->dcn_downspread_percent / 100.0);
 }
+
+int dcn_get_approx_det_segs_required_for_pstate(
+		struct _vcs_dpi_soc_bounding_box_st *soc,
+		int pix_clk_100hz, int bpp, int seg_size_kb)
+{
+	/* Roughly calculate required crb to hide latency. In practice there is slightly
+	 * more buffer available for latency hiding
+	 */
+	return (int)(soc->dram_clock_change_latency_us * pix_clk_100hz * bpp
+					/ 10240000 + seg_size_kb - 1) /	seg_size_kb;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h
index 687d3522cc33..8f9c8faed260 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.h
@@ -47,6 +47,9 @@ void dcn31_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 void dcn315_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params);
 void dcn316_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params);
 int dcn_get_max_non_odm_pix_rate_100hz(struct _vcs_dpi_soc_bounding_box_st *soc);
+int dcn_get_approx_det_segs_required_for_pstate(
+		struct _vcs_dpi_soc_bounding_box_st *soc,
+		int pix_clk_100hz, int bpp, int seg_size_kb);
 
 int dcn31x_populate_dml_pipes_from_context(struct dc *dc,
 					  struct dc_state *context,
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 bd674dc30df3..43016c462251 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
@@ -532,7 +532,8 @@ static void CalculateStutterEfficiency(
 static void CalculateSwathAndDETConfiguration(
 		bool ForceSingleDPP,
 		int NumberOfActivePlanes,
-		unsigned int DETBufferSizeInKByte,
+		bool DETSharedByAllDPP,
+		unsigned int DETBufferSizeInKByte[],
 		double MaximumSwathWidthLuma[],
 		double MaximumSwathWidthChroma[],
 		enum scan_direction_class SourceScan[],
@@ -3118,7 +3119,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 				v->SurfaceWidthC[k],
 				v->SurfaceHeightY[k],
 				v->SurfaceHeightC[k],
-				v->DETBufferSizeInKByte[0] * 1024,
+				v->DETBufferSizeInKByte[k] * 1024,
 				v->BlockHeight256BytesY[k],
 				v->BlockHeight256BytesC[k],
 				v->SurfaceTiling[k],
@@ -3313,7 +3314,8 @@ static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib)
 	CalculateSwathAndDETConfiguration(
 			false,
 			v->NumberOfActivePlanes,
-			v->DETBufferSizeInKByte[0],
+			mode_lib->project == DML_PROJECT_DCN315 && v->DETSizeOverride[0],
+			v->DETBufferSizeInKByte,
 			dummy1,
 			dummy2,
 			v->SourceScan,
@@ -3779,14 +3781,16 @@ static noinline void CalculatePrefetchSchedulePerPlane(
 		&v->VReadyOffsetPix[k]);
 }
 
-static void PatchDETBufferSizeInKByte(unsigned int NumberOfActivePlanes, int NoOfDPPThisState[], unsigned int config_return_buffer_size_in_kbytes, unsigned int *DETBufferSizeInKByte)
+static void PatchDETBufferSizeInKByte(unsigned int NumberOfActivePlanes, int NoOfDPPThisState[], unsigned int config_return_buffer_size_in_kbytes, unsigned int DETBufferSizeInKByte[])
 {
 	int i, total_pipes = 0;
 	for (i = 0; i < NumberOfActivePlanes; i++)
 		total_pipes += NoOfDPPThisState[i];
-	*DETBufferSizeInKByte = ((config_return_buffer_size_in_kbytes - DCN3_15_MIN_COMPBUF_SIZE_KB) / 64 / total_pipes) * 64;
-	if (*DETBufferSizeInKByte > DCN3_15_MAX_DET_SIZE)
-		*DETBufferSizeInKByte = DCN3_15_MAX_DET_SIZE;
+	DETBufferSizeInKByte[0] = ((config_return_buffer_size_in_kbytes - DCN3_15_MIN_COMPBUF_SIZE_KB) / 64 / total_pipes) * 64;
+	if (DETBufferSizeInKByte[0] > DCN3_15_MAX_DET_SIZE)
+		DETBufferSizeInKByte[0] = DCN3_15_MAX_DET_SIZE;
+	for (i = 1; i < NumberOfActivePlanes; i++)
+		DETBufferSizeInKByte[i] = DETBufferSizeInKByte[0];
 }
 
 
@@ -4026,7 +4030,8 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	CalculateSwathAndDETConfiguration(
 			true,
 			v->NumberOfActivePlanes,
-			v->DETBufferSizeInKByte[0],
+			mode_lib->project == DML_PROJECT_DCN315 && v->DETSizeOverride[0],
+			v->DETBufferSizeInKByte,
 			v->MaximumSwathWidthLuma,
 			v->MaximumSwathWidthChroma,
 			v->SourceScan,
@@ -4166,6 +4171,10 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						|| (v->PlaneRequiredDISPCLK > v->MaxDispclkRoundedDownToDFSGranularity)) {
 					v->DISPCLK_DPPCLK_Support[i][j] = false;
 				}
+				if (mode_lib->project == DML_PROJECT_DCN315 && v->DETSizeOverride[k] > DCN3_15_MAX_DET_SIZE && v->NoOfDPP[i][j][k] < 2) {
+					v->MPCCombine[i][j][k] = true;
+					v->NoOfDPP[i][j][k] = 2;
+				}
 			}
 			v->TotalNumberOfActiveDPP[i][j] = 0;
 			v->TotalNumberOfSingleDPPPlanes[i][j] = 0;
@@ -4642,12 +4651,13 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				v->ODMCombineEnableThisState[k] = v->ODMCombineEnablePerState[i][k];
 			}
 
-			if (v->NumberOfActivePlanes > 1 && mode_lib->project == DML_PROJECT_DCN315)
-				PatchDETBufferSizeInKByte(v->NumberOfActivePlanes, v->NoOfDPPThisState, v->ip.config_return_buffer_size_in_kbytes, &v->DETBufferSizeInKByte[0]);
+			if (v->NumberOfActivePlanes > 1 && mode_lib->project == DML_PROJECT_DCN315 && !v->DETSizeOverride[0])
+				PatchDETBufferSizeInKByte(v->NumberOfActivePlanes, v->NoOfDPPThisState, v->ip.config_return_buffer_size_in_kbytes, v->DETBufferSizeInKByte);
 			CalculateSwathAndDETConfiguration(
 					false,
 					v->NumberOfActivePlanes,
-					v->DETBufferSizeInKByte[0],
+					mode_lib->project == DML_PROJECT_DCN315 && v->DETSizeOverride[0],
+					v->DETBufferSizeInKByte,
 					v->MaximumSwathWidthLuma,
 					v->MaximumSwathWidthChroma,
 					v->SourceScan,
@@ -5274,8 +5284,8 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					v->TotImmediateFlipBytes = 0.0;
 					for (k = 0; k < v->NumberOfActivePlanes; k++) {
 						v->TotImmediateFlipBytes = v->TotImmediateFlipBytes
-								+ v->NoOfDPP[i][j][k] * v->PDEAndMetaPTEBytesPerFrame[i][j][k] + v->MetaRowBytes[i][j][k]
-								+ v->DPTEBytesPerRow[i][j][k];
+								+ v->NoOfDPP[i][j][k] * (v->PDEAndMetaPTEBytesPerFrame[i][j][k] + v->MetaRowBytes[i][j][k]
+								+ v->DPTEBytesPerRow[i][j][k]);
 					}
 
 					for (k = 0; k < v->NumberOfActivePlanes; k++) {
@@ -6611,7 +6621,8 @@ static void CalculateStutterEfficiency(
 static void CalculateSwathAndDETConfiguration(
 		bool ForceSingleDPP,
 		int NumberOfActivePlanes,
-		unsigned int DETBufferSizeInKByte,
+		bool DETSharedByAllDPP,
+		unsigned int DETBufferSizeInKByteA[],
 		double MaximumSwathWidthLuma[],
 		double MaximumSwathWidthChroma[],
 		enum scan_direction_class SourceScan[],
@@ -6695,6 +6706,10 @@ static void CalculateSwathAndDETConfiguration(
 
 	*ViewportSizeSupport = true;
 	for (k = 0; k < NumberOfActivePlanes; ++k) {
+		unsigned int DETBufferSizeInKByte = DETBufferSizeInKByteA[k];
+
+		if (DETSharedByAllDPP && DPPPerPlane[k])
+			DETBufferSizeInKByte /= DPPPerPlane[k];
 		if ((SourcePixelFormat[k] == dm_444_64 || SourcePixelFormat[k] == dm_444_32 || SourcePixelFormat[k] == dm_444_16 || SourcePixelFormat[k] == dm_mono_16
 				|| SourcePixelFormat[k] == dm_mono_8 || SourcePixelFormat[k] == dm_rgbe)) {
 			if (SurfaceTiling[k] == dm_sw_linear
@@ -7017,7 +7032,7 @@ static double CalculateUrgentLatency(
 	return ret;
 }
 
-static void UseMinimumDCFCLK(
+static noinline_for_stack void UseMinimumDCFCLK(
 		struct display_mode_lib *mode_lib,
 		int MaxPrefetchMode,
 		int ReorderingBytes)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
index 2244e4fb8c96..4113ce79c4af 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
@@ -987,8 +987,7 @@ static void dml_rq_dlg_get_dlg_params(
 
 	dlg_vblank_start = interlaced ? (vblank_start / 2) : vblank_start;
 	disp_dlg_regs->min_dst_y_next_start = (unsigned int) (((double) dlg_vblank_start) * dml_pow(2, 2));
-	disp_dlg_regs->optimized_min_dst_y_next_start_us = 0;
-	disp_dlg_regs->optimized_min_dst_y_next_start = disp_dlg_regs->min_dst_y_next_start;
+	disp_dlg_regs->min_dst_y_next_start_us = 0;
 	ASSERT(disp_dlg_regs->min_dst_y_next_start < (unsigned int)dml_pow(2, 18));
 
 	dml_print("DML_DLG: %s: min_ttu_vblank (us)         = %3.2f\n", __func__, min_ttu_vblank);
@@ -1433,14 +1432,6 @@ static void dml_rq_dlg_get_dlg_params(
 	dml_print("DML_DLG: %s: disp_dlg_regs->dst_y_per_vm_flip    = 0x%x\n", __func__, disp_dlg_regs->dst_y_per_vm_flip);
 	dml_print("DML_DLG: %s: disp_dlg_regs->dst_y_per_row_flip   = 0x%x\n", __func__, disp_dlg_regs->dst_y_per_row_flip);
 
-	// hack for FPGA
-	if (mode_lib->project == DML_PROJECT_DCN31_FPGA) {
-		if (disp_dlg_regs->vratio_prefetch >= (unsigned int) dml_pow(2, 22)) {
-			disp_dlg_regs->vratio_prefetch = (unsigned int) dml_pow(2, 22) - 1;
-			dml_print("vratio_prefetch exceed the max value, the register field is [21:0]\n");
-		}
-	}
-
 	disp_dlg_regs->refcyc_per_pte_group_vblank_l = (unsigned int) (dst_y_per_row_vblank * (double) htotal * ref_freq_to_pix_freq / (double) dpte_groups_per_row_ub_l);
 	ASSERT(disp_dlg_regs->refcyc_per_pte_group_vblank_l < (unsigned int)dml_pow(2, 13));