Hi Ao,
First of all, thanks a lot for this patch.
On 10/20/22 20:31, Ao Zhong wrote:
Move remaining FPU code to dml folder
in preparation for enabling aarch64 support.
I guess you found some of the issues here after you tried enabling the
arm64 compilation, right? If so, could you expand the commit message to
describe it better?
Signed-off-by: Ao Zhong <hacc1...@gmail.com>
---
.../drm/amd/display/dc/dcn10/dcn10_resource.c | 44 +------------------
.../drm/amd/display/dc/dcn32/dcn32_resource.c | 5 ++-
.../drm/amd/display/dc/dml/dcn10/dcn10_fpu.c | 40 +++++++++++++++++
.../drm/amd/display/dc/dml/dcn10/dcn10_fpu.h | 3 ++
.../drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 8 ++++
.../drm/amd/display/dc/dml/dcn32/dcn32_fpu.h | 3 ++
Could you split this commit in two parts?
One for DCN10 and another one for DCN32.
6 files changed, 59 insertions(+), 44 deletions(-)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 56d30baf12df..6bfac8088ab0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1295,47 +1295,6 @@ static uint32_t read_pipe_fuses(struct dc_context *ctx)
return value;
}
-/*
- * Some architectures don't support soft-float (e.g. aarch64), on those
- * this function has to be called with hardfloat enabled, make sure not
- * to inline it so whatever fp stuff is done stays inside
- */
-static noinline void dcn10_resource_construct_fp(
- struct dc *dc)
-{
- if (dc->ctx->dce_version == DCN_VERSION_1_01) {
- struct dcn_soc_bounding_box *dcn_soc = dc->dcn_soc;
- struct dcn_ip_params *dcn_ip = dc->dcn_ip;
- struct display_mode_lib *dml = &dc->dml;
-
- dml->ip.max_num_dpp = 3;
- /* TODO how to handle 23.84? */
- dcn_soc->dram_clock_change_latency = 23;
- dcn_ip->max_num_dpp = 3;
- }
- if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
- dc->dcn_soc->urgent_latency = 3;
- dc->debug.disable_dmcu = true;
- dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 41.60f;
- }
-
-
- dc->dcn_soc->number_of_channels = dc->ctx->asic_id.vram_width /
ddr4_dram_width;
- ASSERT(dc->dcn_soc->number_of_channels < 3);
- if (dc->dcn_soc->number_of_channels == 0)/*old sbios bug*/
- dc->dcn_soc->number_of_channels = 2;
-
- if (dc->dcn_soc->number_of_channels == 1) {
- dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 19.2f;
- dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = 17.066f;
- dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = 14.933f;
- dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 12.8f;
- if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
- dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 20.80f;
- }
- }
-}
-
static bool verify_clock_values(struct dm_pp_clock_levels_with_voltage *clks)
{
int i;
@@ -1510,8 +1469,9 @@ static bool dcn10_resource_construct(
memcpy(dc->dcn_ip, &dcn10_ip_defaults, sizeof(dcn10_ip_defaults));
memcpy(dc->dcn_soc, &dcn10_soc_defaults, sizeof(dcn10_soc_defaults));
- /* Other architectures we build for build this with soft-float */
+ DC_FP_START();
dcn10_resource_construct_fp(dc);
+ DC_FP_END();
if (!dc->config.is_vmin_only_asic)
if (ASICREV_IS_RAVEN2(dc->ctx->asic_id.hw_internal_rev))
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 a88dd7b3d1c1..287b7fa9bf41 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -1918,8 +1918,9 @@ int dcn32_populate_dml_pipes_from_context(
timing = &pipe->stream->timing;
pipes[pipe_cnt].pipe.src.gpuvm = true;
- pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0;
- pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_chroma = 0;
+ DC_FP_START();
+ dcn32_zero_pipe_dcc_fraction(pipes, pipe_cnt);
+ DC_FP_END();
pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
pipes[pipe_cnt].pipe.src.gpuvm_min_page_size_kbytes = 256; //
according to spreadsheet
pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.c
b/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.c
index 99644d896222..0495cecaf1df 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.c
@@ -27,6 +27,8 @@
#include "dcn10/dcn10_resource.h"
#include "dcn10_fpu.h"
+#include "resource.h"
+#include "amdgpu_dm/dc_fpu.h"
/**
* DOC: DCN10 FPU manipulation Overview
@@ -121,3 +123,41 @@ struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = {
.writeback_dram_clock_change_latency_us = 23.0,
.return_bus_width_bytes = 64,
};
+
+void dcn10_resource_construct_fp(
+ struct dc *dc)
Since this is a small function signature, could you add the dc parameter
in the same line as the function name? Same idea for the header file.
+{
+ dc_assert_fp_enabled();
+
Drop the extra space in the above line.
Thanks
Siqueira
+ if (dc->ctx->dce_version == DCN_VERSION_1_01) {
+ struct dcn_soc_bounding_box *dcn_soc = dc->dcn_soc;
+ struct dcn_ip_params *dcn_ip = dc->dcn_ip;
+ struct display_mode_lib *dml = &dc->dml;
+
+ dml->ip.max_num_dpp = 3;
+ /* TODO how to handle 23.84? */
+ dcn_soc->dram_clock_change_latency = 23;
+ dcn_ip->max_num_dpp = 3;
+ }
+ if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
+ dc->dcn_soc->urgent_latency = 3;
+ dc->debug.disable_dmcu = true;
+ dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 41.60f;
+ }
+
+
+ dc->dcn_soc->number_of_channels = dc->ctx->asic_id.vram_width /
ddr4_dram_width;
+ ASSERT(dc->dcn_soc->number_of_channels < 3);
+ if (dc->dcn_soc->number_of_channels == 0)/*old sbios bug*/
+ dc->dcn_soc->number_of_channels = 2;
+
+ if (dc->dcn_soc->number_of_channels == 1) {
+ dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 19.2f;
+ dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 = 17.066f;
+ dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 = 14.933f;
+ dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 12.8f;
+ if (ASICREV_IS_RV1_F0(dc->ctx->asic_id.hw_internal_rev)) {
+ dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 = 20.80f;
+ }
+ }
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.h
b/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.h
index e74ed4b4ce5b..dcbfb73b0afd 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn10/dcn10_fpu.h
@@ -27,4 +27,7 @@
#ifndef __DCN10_FPU_H__
#define __DCN10_FPU_H__
+void dcn10_resource_construct_fp(
+ struct dc *dc);
+
#endif /* __DCN20_FPU_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 819de0f11012..58772fce6437 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -2521,3 +2521,11 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc,
struct clk_bw_params *bw_pa
}
}
+void dcn32_zero_pipe_dcc_fraction(display_e2e_pipe_params_st *pipes,
+ int pipe_cnt)
+{
+ dc_assert_fp_enabled();
+
+ pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0;
+ pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_chroma = 0;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
index 3a3dc2ce4c73..ab010e7e840b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
@@ -73,4 +73,7 @@ int
dcn32_find_dummy_latency_index_for_fw_based_mclk_switch(struct dc *dc,
void dcn32_patch_dpm_table(struct clk_bw_params *bw_params);
+void dcn32_zero_pipe_dcc_fraction(display_e2e_pipe_params_st *pipes,
+ int pipe_cnt);
+
#endif
