lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <301c29e0-e520-1235-3ec6-0592b09ddbd1@amd.com>
Date:   Thu, 21 Jul 2022 14:59:21 -0400
From:   Rodrigo Siqueira Jordao <Rodrigo.Siqueira@....com>
To:     Melissa Wen <mwen@...lia.com>, harry.wentland@....com,
        sunpeng.li@....com, alexander.deucher@....com,
        christian.koenig@....com, Xinhui.Pan@....com, airlied@...ux.ie,
        daniel@...ll.ch
Cc:     Guenter Roeck <linux@...ck-us.net>,
        MaĆ­ra Canal <mairacanal@...eup.net>,
        kernel-dev@...lia.com, amd-gfx@...ts.freedesktop.org,
        dri-devel@...ts.freedesktop.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 5/5] drm/amd/display: move FPU code from dcn301 clk mgr to
 DML folder



On 2022-07-20 15:32, Melissa Wen wrote:
> The -mno-gnu-attribute option in dcn301 clk mgr makefile hides a soft vs
> hard fp error for powerpc. After removing this flag, we can see some FPU
> code remains there:
> 
> gcc-11.3.0-nolibc/powerpc64-linux/bin/powerpc64-linux-ld:
> drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.o uses
> hard float,
> drivers/gpu/drm/amd/amdgpu/../display/dc/clk_mgr/dcn301/vg_clk_mgr.o
> uses soft float
> 
> Therefore, remove the -mno-gnu-attribute flag for dcn301/powerpc and
> move FPU-associated code to DML folder.
> 
> Signed-off-by: Melissa Wen <mwen@...lia.com>
> ---
>   .../gpu/drm/amd/display/dc/clk_mgr/Makefile   |  6 --
>   .../display/dc/clk_mgr/dcn301/vg_clk_mgr.c    | 86 ++-----------------
>   .../display/dc/clk_mgr/dcn301/vg_clk_mgr.h    |  3 +
>   .../amd/display/dc/dml/dcn301/dcn301_fpu.c    | 74 ++++++++++++++++
>   4 files changed, 84 insertions(+), 85 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
> index 15b660a951a5..271d8e573181 100644
> --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
> +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
> @@ -123,12 +123,6 @@ AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN30)
>   ###############################################################################
>   CLK_MGR_DCN301 = vg_clk_mgr.o dcn301_smu.o
>   
> -# prevent build errors regarding soft-float vs hard-float FP ABI tags
> -# this code is currently unused on ppc64, as it applies to VanGogh APUs only
> -ifdef CONFIG_PPC64
> -CFLAGS_$(AMDDALPATH)/dc/clk_mgr/dcn301/vg_clk_mgr.o := $(call cc-option,-mno-gnu-attribute)
> -endif
> -
>   AMD_DAL_CLK_MGR_DCN301 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn301/,$(CLK_MGR_DCN301))
>   
>   AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN301)
> diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
> index f310b0d25a07..65f224af03c0 100644
> --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
> +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
> @@ -32,6 +32,10 @@
>   // For dcn20_update_clocks_update_dpp_dto
>   #include "dcn20/dcn20_clk_mgr.h"
>   
> +// For DML FPU code
> +#include "dml/dcn20/dcn20_fpu.h"
> +#include "dml/dcn301/dcn301_fpu.h"
> +
>   #include "vg_clk_mgr.h"
>   #include "dcn301_smu.h"
>   #include "reg_helper.h"
> @@ -526,81 +530,6 @@ static struct clk_bw_params vg_bw_params = {
>   
>   };
>   
> -static struct wm_table ddr4_wm_table = {
> -	.entries = {
> -		{
> -			.wm_inst = WM_A,
> -			.wm_type = WM_TYPE_PSTATE_CHG,
> -			.pstate_latency_us = 11.72,
> -			.sr_exit_time_us = 6.09,
> -			.sr_enter_plus_exit_time_us = 7.14,
> -			.valid = true,
> -		},
> -		{
> -			.wm_inst = WM_B,
> -			.wm_type = WM_TYPE_PSTATE_CHG,
> -			.pstate_latency_us = 11.72,
> -			.sr_exit_time_us = 10.12,
> -			.sr_enter_plus_exit_time_us = 11.48,
> -			.valid = true,
> -		},
> -		{
> -			.wm_inst = WM_C,
> -			.wm_type = WM_TYPE_PSTATE_CHG,
> -			.pstate_latency_us = 11.72,
> -			.sr_exit_time_us = 10.12,
> -			.sr_enter_plus_exit_time_us = 11.48,
> -			.valid = true,
> -		},
> -		{
> -			.wm_inst = WM_D,
> -			.wm_type = WM_TYPE_PSTATE_CHG,
> -			.pstate_latency_us = 11.72,
> -			.sr_exit_time_us = 10.12,
> -			.sr_enter_plus_exit_time_us = 11.48,
> -			.valid = true,
> -		},
> -	}
> -};
> -
> -static struct wm_table lpddr5_wm_table = {
> -	.entries = {
> -		{
> -			.wm_inst = WM_A,
> -			.wm_type = WM_TYPE_PSTATE_CHG,
> -			.pstate_latency_us = 11.65333,
> -			.sr_exit_time_us = 13.5,
> -			.sr_enter_plus_exit_time_us = 16.5,
> -			.valid = true,
> -		},
> -		{
> -			.wm_inst = WM_B,
> -			.wm_type = WM_TYPE_PSTATE_CHG,
> -			.pstate_latency_us = 11.65333,
> -			.sr_exit_time_us = 13.5,
> -			.sr_enter_plus_exit_time_us = 16.5,
> -			.valid = true,
> -		},
> -		{
> -			.wm_inst = WM_C,
> -			.wm_type = WM_TYPE_PSTATE_CHG,
> -			.pstate_latency_us = 11.65333,
> -			.sr_exit_time_us = 13.5,
> -			.sr_enter_plus_exit_time_us = 16.5,
> -			.valid = true,
> -		},
> -		{
> -			.wm_inst = WM_D,
> -			.wm_type = WM_TYPE_PSTATE_CHG,
> -			.pstate_latency_us = 11.65333,
> -			.sr_exit_time_us = 13.5,
> -			.sr_enter_plus_exit_time_us = 16.5,
> -			.valid = true,
> -		},
> -	}
> -};
> -
> -
>   static unsigned int find_dcfclk_for_voltage(const struct vg_dpm_clocks *clock_table,
>   		unsigned int voltage)
>   {
> @@ -670,10 +599,9 @@ static void vg_clk_mgr_helper_populate_bw_params(
>   		/*
>   		 * WM set D will be re-purposed for memory retraining
>   		 */
> -		bw_params->wm_table.entries[WM_D].pstate_latency_us = LPDDR_MEM_RETRAIN_LATENCY;
> -		bw_params->wm_table.entries[WM_D].wm_inst = WM_D;
> -		bw_params->wm_table.entries[WM_D].wm_type = WM_TYPE_RETRAINING;
> -		bw_params->wm_table.entries[WM_D].valid = true;
> +		DC_FP_START();
> +		dcn21_clk_mgr_set_bw_params_wm_table(bw_params);
> +		DC_FP_END();
>   	}
>   
>   }
> diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.h
> index 7255477307f1..75884f572989 100644
> --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.h
> +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.h
> @@ -29,6 +29,9 @@
>   
>   struct watermarks;
>   
> +extern struct wm_table ddr4_wm_table;
> +extern struct wm_table lpddr5_wm_table;
> +
>   struct smu_watermark_set {
>   	struct watermarks *wm_set;
>   	union large_integer mc_address;
> diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
> index e4863f0bf0f6..7ef66e511ec8 100644
> --- a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
> +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
> @@ -214,6 +214,80 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_01_soc = {
>   	.urgent_latency_adjustment_fabric_clock_reference_mhz = 0,
>   };
>   
> +struct wm_table ddr4_wm_table = {
> +	.entries = {
> +		{
> +			.wm_inst = WM_A,
> +			.wm_type = WM_TYPE_PSTATE_CHG,
> +			.pstate_latency_us = 11.72,
> +			.sr_exit_time_us = 6.09,
> +			.sr_enter_plus_exit_time_us = 7.14,
> +			.valid = true,
> +		},
> +		{
> +			.wm_inst = WM_B,
> +			.wm_type = WM_TYPE_PSTATE_CHG,
> +			.pstate_latency_us = 11.72,
> +			.sr_exit_time_us = 10.12,
> +			.sr_enter_plus_exit_time_us = 11.48,
> +			.valid = true,
> +		},
> +		{
> +			.wm_inst = WM_C,
> +			.wm_type = WM_TYPE_PSTATE_CHG,
> +			.pstate_latency_us = 11.72,
> +			.sr_exit_time_us = 10.12,
> +			.sr_enter_plus_exit_time_us = 11.48,
> +			.valid = true,
> +		},
> +		{
> +			.wm_inst = WM_D,
> +			.wm_type = WM_TYPE_PSTATE_CHG,
> +			.pstate_latency_us = 11.72,
> +			.sr_exit_time_us = 10.12,
> +			.sr_enter_plus_exit_time_us = 11.48,
> +			.valid = true,
> +		},
> +	}
> +};
> +
> +struct wm_table lpddr5_wm_table = {
> +	.entries = {
> +		{
> +			.wm_inst = WM_A,
> +			.wm_type = WM_TYPE_PSTATE_CHG,
> +			.pstate_latency_us = 11.65333,
> +			.sr_exit_time_us = 13.5,
> +			.sr_enter_plus_exit_time_us = 16.5,
> +			.valid = true,
> +		},
> +		{
> +			.wm_inst = WM_B,
> +			.wm_type = WM_TYPE_PSTATE_CHG,
> +			.pstate_latency_us = 11.65333,
> +			.sr_exit_time_us = 13.5,
> +			.sr_enter_plus_exit_time_us = 16.5,
> +			.valid = true,
> +		},
> +		{
> +			.wm_inst = WM_C,
> +			.wm_type = WM_TYPE_PSTATE_CHG,
> +			.pstate_latency_us = 11.65333,
> +			.sr_exit_time_us = 13.5,
> +			.sr_enter_plus_exit_time_us = 16.5,
> +			.valid = true,
> +		},
> +		{
> +			.wm_inst = WM_D,
> +			.wm_type = WM_TYPE_PSTATE_CHG,
> +			.pstate_latency_us = 11.65333,
> +			.sr_exit_time_us = 13.5,
> +			.sr_enter_plus_exit_time_us = 16.5,
> +			.valid = true,
> +		},
> +	}
> +};
> +
>   static void calculate_wm_set_for_vlevel(int vlevel,
>   		struct wm_range_table_entry *table_entry,
>   		struct dcn_watermarks *wm_set,

Reviewed-by: Rodrigo Siqueira <Rodrigo.Siqueira@....com>

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ