drm/amd/display: move FPU code from dcn10 to dml/dcn10 folder

FPU operations in dcn10 was already moved to dml folder via calcs code.
However, dcn1_0_ip and dcn_1_0_soc with FPU componentd remains on dcn10.
Following previous changes to isolate FPU, this patch creates dcn10_fpu
files to isolate FPU-specific code and moves those structs to it.
Signed-off-by: Melissa Wen <mwen@igalia.com>
Acked-by: Alan Liu <HaoPing.Liu@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c

@@ -70,68 +70,6 @@
 #include "dce/dce_aux.h"
 #include "dce/dce_i2c.h"
 
-const struct _vcs_dpi_ip_params_st dcn1_0_ip = {
-	.rob_buffer_size_kbytes = 64,
-	.det_buffer_size_kbytes = 164,
-	.dpte_buffer_size_in_pte_reqs_luma = 42,
-	.dpp_output_buffer_pixels = 2560,
-	.opp_output_buffer_lines = 1,
-	.pixel_chunk_size_kbytes = 8,
-	.pte_enable = 1,
-	.pte_chunk_size_kbytes = 2,
-	.meta_chunk_size_kbytes = 2,
-	.writeback_chunk_size_kbytes = 2,
-	.line_buffer_size_bits = 589824,
-	.max_line_buffer_lines = 12,
-	.IsLineBufferBppFixed = 0,
-	.LineBufferFixedBpp = -1,
-	.writeback_luma_buffer_size_kbytes = 12,
-	.writeback_chroma_buffer_size_kbytes = 8,
-	.max_num_dpp = 4,
-	.max_num_wb = 2,
-	.max_dchub_pscl_bw_pix_per_clk = 4,
-	.max_pscl_lb_bw_pix_per_clk = 2,
-	.max_lb_vscl_bw_pix_per_clk = 4,
-	.max_vscl_hscl_bw_pix_per_clk = 4,
-	.max_hscl_ratio = 4,
-	.max_vscl_ratio = 4,
-	.hscl_mults = 4,
-	.vscl_mults = 4,
-	.max_hscl_taps = 8,
-	.max_vscl_taps = 8,
-	.dispclk_ramp_margin_percent = 1,
-	.underscan_factor = 1.10,
-	.min_vblank_lines = 14,
-	.dppclk_delay_subtotal = 90,
-	.dispclk_delay_subtotal = 42,
-	.dcfclk_cstate_latency = 10,
-	.max_inter_dcn_tile_repeaters = 8,
-	.can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0,
-	.bug_forcing_LC_req_same_size_fixed = 0,
-};
-
-const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = {
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
-	.urgent_latency_us = 4.0,
-	.writeback_latency_us = 12.0,
-	.ideal_dram_bw_after_urgent_percent = 80.0,
-	.max_request_size_bytes = 256,
-	.downspread_percent = 0.5,
-	.dram_page_open_time_ns = 50.0,
-	.dram_rw_turnaround_time_ns = 17.5,
-	.dram_return_buffer_per_channel_bytes = 8192,
-	.round_trip_ping_latency_dcfclk_cycles = 128,
-	.urgent_out_of_order_return_per_channel_bytes = 256,
-	.channel_interleave_bytes = 256,
-	.num_banks = 8,
-	.num_chans = 2,
-	.vmm_page_size_bytes = 4096,
-	.dram_clock_change_latency_us = 17.0,
-	.writeback_dram_clock_change_latency_us = 23.0,
-	.return_bus_width_bytes = 64,
-};
-
 #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL
 	#define mmDP0_DP_DPHY_INTERNAL_CTRL		0x210f
 	#define mmDP0_DP_DPHY_INTERNAL_CTRL_BASE_IDX	2

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.h

@@ -27,6 +27,7 @@
 #define __DC_RESOURCE_DCN10_H__
 
 #include "core_types.h"
+#include "dml/dcn10/dcn10_fpu.h"
 
 #define TO_DCN10_RES_POOL(pool)\
 	container_of(pool, struct dcn10_resource_pool, base)
@@ -35,6 +36,9 @@ struct dc;
 struct resource_pool;
 struct _vcs_dpi_display_pipe_params_st;
 
+extern struct _vcs_dpi_ip_params_st dcn1_0_ip;
+extern struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc;
+
 struct dcn10_resource_pool {
 	struct resource_pool base;
 };

drivers/gpu/drm/amd/display/dc/dml/Makefile

@@ -58,6 +58,7 @@ CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 
 ifdef CONFIG_DRM_AMD_DC_DCN
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
+CFLAGS_$(AMDDALPATH)/dc/dml/dcn10/dcn10_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/dcn20_fpu.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
@@ -106,6 +107,7 @@ DML = calcs/dce_calcs.o calcs/custom_float.o calcs/bw_fixed.o
 
 ifdef CONFIG_DRM_AMD_DC_DCN
 DML += display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o
+DML += dcn10/dcn10_fpu.o
 DML += dcn20/dcn20_fpu.o
 DML += display_mode_vba.o dcn20/display_rq_dlg_calc_20.o dcn20/display_mode_vba_20.o
 DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o

drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.c

+// SPDX-License-Identifier: MIT
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dcn10/dcn10_resource.h"
+
+#include "dcn10_fpu.h"
+
+/**
+ * DOC: DCN10 FPU manipulation Overview
+ *
+ * The DCN architecture relies on FPU operations, which require special
+ * compilation flags and the use of kernel_fpu_begin/end functions; ideally, we
+ * want to avoid spreading FPU access across multiple files. With this idea in
+ * mind, this file aims to centralize DCN10 functions that require FPU access
+ * in a single place. Code in this file follows the following code pattern:
+ *
+ * 1. Functions that use FPU operations should be isolated in static functions.
+ * 2. The FPU functions should have the noinline attribute to ensure anything
+ *    that deals with FP register is contained within this call.
+ * 3. All function that needs to be accessed outside this file requires a
+ *    public interface that not uses any FPU reference.
+ * 4. Developers **must not** use DC_FP_START/END in this file, but they need
+ *    to ensure that the caller invokes it before access any function available
+ *    in this file. For this reason, public functions in this file must invoke
+ *    dc_assert_fp_enabled();
+ *
+ * Let's expand a little bit more the idea in the code pattern. To fully
+ * isolate FPU operations in a single place, we must avoid situations where
+ * compilers spill FP values to registers due to FP enable in a specific C
+ * file. Note that even if we isolate all FPU functions in a single file and
+ * call its interface from other files, the compiler might enable the use of
+ * FPU before we call DC_FP_START. Nevertheless, it is the programmer's
+ * responsibility to invoke DC_FP_START/END in the correct place. To highlight
+ * situations where developers forgot to use the FP protection before calling
+ * the DC FPU interface functions, we introduce a helper that checks if the
+ * function is invoked under FP protection. If not, it will trigger a kernel
+ * warning.
+ */
+
+struct _vcs_dpi_ip_params_st dcn1_0_ip = {
+	.rob_buffer_size_kbytes = 64,
+	.det_buffer_size_kbytes = 164,
+	.dpte_buffer_size_in_pte_reqs_luma = 42,
+	.dpp_output_buffer_pixels = 2560,
+	.opp_output_buffer_lines = 1,
+	.pixel_chunk_size_kbytes = 8,
+	.pte_enable = 1,
+	.pte_chunk_size_kbytes = 2,
+	.meta_chunk_size_kbytes = 2,
+	.writeback_chunk_size_kbytes = 2,
+	.line_buffer_size_bits = 589824,
+	.max_line_buffer_lines = 12,
+	.IsLineBufferBppFixed = 0,
+	.LineBufferFixedBpp = -1,
+	.writeback_luma_buffer_size_kbytes = 12,
+	.writeback_chroma_buffer_size_kbytes = 8,
+	.max_num_dpp = 4,
+	.max_num_wb = 2,
+	.max_dchub_pscl_bw_pix_per_clk = 4,
+	.max_pscl_lb_bw_pix_per_clk = 2,
+	.max_lb_vscl_bw_pix_per_clk = 4,
+	.max_vscl_hscl_bw_pix_per_clk = 4,
+	.max_hscl_ratio = 4,
+	.max_vscl_ratio = 4,
+	.hscl_mults = 4,
+	.vscl_mults = 4,
+	.max_hscl_taps = 8,
+	.max_vscl_taps = 8,
+	.dispclk_ramp_margin_percent = 1,
+	.underscan_factor = 1.10,
+	.min_vblank_lines = 14,
+	.dppclk_delay_subtotal = 90,
+	.dispclk_delay_subtotal = 42,
+	.dcfclk_cstate_latency = 10,
+	.max_inter_dcn_tile_repeaters = 8,
+	.can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0,
+	.bug_forcing_LC_req_same_size_fixed = 0,
+};
+
+struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = {
+	.sr_exit_time_us = 9.0,
+	.sr_enter_plus_exit_time_us = 11.0,
+	.urgent_latency_us = 4.0,
+	.writeback_latency_us = 12.0,
+	.ideal_dram_bw_after_urgent_percent = 80.0,
+	.max_request_size_bytes = 256,
+	.downspread_percent = 0.5,
+	.dram_page_open_time_ns = 50.0,
+	.dram_rw_turnaround_time_ns = 17.5,
+	.dram_return_buffer_per_channel_bytes = 8192,
+	.round_trip_ping_latency_dcfclk_cycles = 128,
+	.urgent_out_of_order_return_per_channel_bytes = 256,
+	.channel_interleave_bytes = 256,
+	.num_banks = 8,
+	.num_chans = 2,
+	.vmm_page_size_bytes = 4096,
+	.dram_clock_change_latency_us = 17.0,
+	.writeback_dram_clock_change_latency_us = 23.0,
+	.return_bus_width_bytes = 64,
+};

drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.h

+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2021 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DCN10_FPU_H__
+#define __DCN10_FPU_H__
+
+#endif /* __DCN20_FPU_H__ */