[PATCH] amdgpu: Avoid sleeping during FPU critical sections

[PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Jeremy Cline]

dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
calls which can sleep, but kernel_fpu_begin() disables preemption and
sleeping in this context is invalid.

The only places the FPU appears to be required is in the
init_soc_bounding_box() function and when calculating the
{min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
avoid sleeping while using the FPU.

Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
Cc: Timothy Pearson <tpearson@raptorengineering.com>
Signed-off-by: Jeremy Cline <jcline@redhat.com>
---
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index e04ecf0fc0db..a4fa5bf016c1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
 	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
 		int i;
 
+		DC_FP_START();
 		dcn2_0_nv12_soc.sr_exit_time_us =
 				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
 		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
@@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
 			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
 					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
 		}
+		DC_FP_END();
 	}
 
 	if (pool->base.pp_smu) {
@@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
 	enum dml_project dml_project_version =
 			get_dml_project_version(ctx->asic_id.hw_internal_rev);
 
-	DC_FP_START();
-
 	ctx->dc_bios->regs = &bios_regs;
 	pool->base.funcs = &dcn20_res_pool_funcs;
 
@@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
 				ranges.reader_wm_sets[i].wm_inst = i;
 				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
 				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+				DC_FP_START();
 				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
 				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
+				DC_FP_END();
 
 				ranges.num_reader_wm_sets = i + 1;
 			}
@@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
 		pool->base.oem_device = NULL;
 	}
 
-	DC_FP_END();
 	return true;
 
 create_fail:
 
-	DC_FP_END();
 	dcn20_resource_destruct(pool);
 
 	return false;
-- 
2.28.0

[PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Jeremy Cline]

dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
calls which can sleep, but kernel_fpu_begin() disables preemption and
sleeping in this context is invalid.

The only places the FPU appears to be required is in the
init_soc_bounding_box() function and when calculating the
{min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
avoid sleeping while using the FPU.

Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
Cc: Timothy Pearson <tpearson@raptorengineering.com>
Signed-off-by: Jeremy Cline <jcline@redhat.com>
---
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index e04ecf0fc0db..a4fa5bf016c1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
 	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
 		int i;
 
+		DC_FP_START();
 		dcn2_0_nv12_soc.sr_exit_time_us =
 				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
 		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
@@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
 			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
 					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
 		}
+		DC_FP_END();
 	}
 
 	if (pool->base.pp_smu) {
@@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
 	enum dml_project dml_project_version =
 			get_dml_project_version(ctx->asic_id.hw_internal_rev);
 
-	DC_FP_START();
-
 	ctx->dc_bios->regs = &bios_regs;
 	pool->base.funcs = &dcn20_res_pool_funcs;
 
@@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
 				ranges.reader_wm_sets[i].wm_inst = i;
 				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
 				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+				DC_FP_START();
 				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
 				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
+				DC_FP_END();
 
 				ranges.num_reader_wm_sets = i + 1;
 			}
@@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
 		pool->base.oem_device = NULL;
 	}
 
-	DC_FP_END();
 	return true;
 
 create_fail:
 
-	DC_FP_END();
 	dcn20_resource_destruct(pool);
 
 	return false;
-- 
2.28.0

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Jeremy Cline]

dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
calls which can sleep, but kernel_fpu_begin() disables preemption and
sleeping in this context is invalid.

The only places the FPU appears to be required is in the
init_soc_bounding_box() function and when calculating the
{min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
avoid sleeping while using the FPU.

Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
Cc: Timothy Pearson <tpearson@raptorengineering.com>
Signed-off-by: Jeremy Cline <jcline@redhat.com>
---
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index e04ecf0fc0db..a4fa5bf016c1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
 	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
 		int i;
 
+		DC_FP_START();
 		dcn2_0_nv12_soc.sr_exit_time_us =
 				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
 		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
@@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
 			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
 					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
 		}
+		DC_FP_END();
 	}
 
 	if (pool->base.pp_smu) {
@@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
 	enum dml_project dml_project_version =
 			get_dml_project_version(ctx->asic_id.hw_internal_rev);
 
-	DC_FP_START();
-
 	ctx->dc_bios->regs = &bios_regs;
 	pool->base.funcs = &dcn20_res_pool_funcs;
 
@@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
 				ranges.reader_wm_sets[i].wm_inst = i;
 				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
 				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+				DC_FP_START();
 				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
 				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
+				DC_FP_END();
 
 				ranges.num_reader_wm_sets = i + 1;
 			}
@@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
 		pool->base.oem_device = NULL;
 	}
 
-	DC_FP_END();
 	return true;
 
 create_fail:
 
-	DC_FP_END();
 	dcn20_resource_destruct(pool);
 
 	return false;
-- 
2.28.0

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Christian König]

Am 08.01.21 um 22:58 schrieb Jeremy Cline:
> dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
> calls which can sleep, but kernel_fpu_begin() disables preemption and
> sleeping in this context is invalid.
>
> The only places the FPU appears to be required is in the
> init_soc_bounding_box() function and when calculating the
> {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
> avoid sleeping while using the FPU.
>
> Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
> Cc: Timothy Pearson <tpearson@raptorengineering.com>
> Signed-off-by: Jeremy Cline <jcline@redhat.com>

Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a 
kzalloc(GFP_ATOMIC) for now.

We have tons of problems with this DC_FP_START()/DC_FP_END() annotations 
and are even in the process of moving them out of the file because the 
compiles tend to clutter FP registers even outside of the annotated 
ranges on some architectures.

Regards,
Christian.

> ---
>   drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
>   1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> index e04ecf0fc0db..a4fa5bf016c1 100644
> --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>   	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
>   		int i;
>   
> +		DC_FP_START();
>   		dcn2_0_nv12_soc.sr_exit_time_us =
>   				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
>   		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
> @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>   			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
>   					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
>   		}
> +		DC_FP_END();
>   	}
>   
>   	if (pool->base.pp_smu) {
> @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
>   	enum dml_project dml_project_version =
>   			get_dml_project_version(ctx->asic_id.hw_internal_rev);
>   
> -	DC_FP_START();
> -
>   	ctx->dc_bios->regs = &bios_regs;
>   	pool->base.funcs = &dcn20_res_pool_funcs;
>   
> @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
>   				ranges.reader_wm_sets[i].wm_inst = i;
>   				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
>   				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
> +				DC_FP_START();
>   				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
>   				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
> +				DC_FP_END();
>   
>   				ranges.num_reader_wm_sets = i + 1;
>   			}
> @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
>   		pool->base.oem_device = NULL;
>   	}
>   
> -	DC_FP_END();
>   	return true;
>   
>   create_fail:
>   
> -	DC_FP_END();
>   	dcn20_resource_destruct(pool);
>   
>   	return false;

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Christian König]

Am 08.01.21 um 22:58 schrieb Jeremy Cline:
> dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
> calls which can sleep, but kernel_fpu_begin() disables preemption and
> sleeping in this context is invalid.
>
> The only places the FPU appears to be required is in the
> init_soc_bounding_box() function and when calculating the
> {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
> avoid sleeping while using the FPU.
>
> Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
> Cc: Timothy Pearson <tpearson@raptorengineering.com>
> Signed-off-by: Jeremy Cline <jcline@redhat.com>

Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a 
kzalloc(GFP_ATOMIC) for now.

We have tons of problems with this DC_FP_START()/DC_FP_END() annotations 
and are even in the process of moving them out of the file because the 
compiles tend to clutter FP registers even outside of the annotated 
ranges on some architectures.

Regards,
Christian.

> ---
>   drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
>   1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> index e04ecf0fc0db..a4fa5bf016c1 100644
> --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>   	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
>   		int i;
>   
> +		DC_FP_START();
>   		dcn2_0_nv12_soc.sr_exit_time_us =
>   				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
>   		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
> @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>   			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
>   					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
>   		}
> +		DC_FP_END();
>   	}
>   
>   	if (pool->base.pp_smu) {
> @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
>   	enum dml_project dml_project_version =
>   			get_dml_project_version(ctx->asic_id.hw_internal_rev);
>   
> -	DC_FP_START();
> -
>   	ctx->dc_bios->regs = &bios_regs;
>   	pool->base.funcs = &dcn20_res_pool_funcs;
>   
> @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
>   				ranges.reader_wm_sets[i].wm_inst = i;
>   				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
>   				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
> +				DC_FP_START();
>   				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
>   				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
> +				DC_FP_END();
>   
>   				ranges.num_reader_wm_sets = i + 1;
>   			}
> @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
>   		pool->base.oem_device = NULL;
>   	}
>   
> -	DC_FP_END();
>   	return true;
>   
>   create_fail:
>   
> -	DC_FP_END();
>   	dcn20_resource_destruct(pool);
>   
>   	return false;

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Christian König]

Am 08.01.21 um 22:58 schrieb Jeremy Cline:
> dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
> calls which can sleep, but kernel_fpu_begin() disables preemption and
> sleeping in this context is invalid.
>
> The only places the FPU appears to be required is in the
> init_soc_bounding_box() function and when calculating the
> {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
> avoid sleeping while using the FPU.
>
> Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
> Cc: Timothy Pearson <tpearson@raptorengineering.com>
> Signed-off-by: Jeremy Cline <jcline@redhat.com>

Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a 
kzalloc(GFP_ATOMIC) for now.

We have tons of problems with this DC_FP_START()/DC_FP_END() annotations 
and are even in the process of moving them out of the file because the 
compiles tend to clutter FP registers even outside of the annotated 
ranges on some architectures.

Regards,
Christian.

> ---
>   drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
>   1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> index e04ecf0fc0db..a4fa5bf016c1 100644
> --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>   	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
>   		int i;
>   
> +		DC_FP_START();
>   		dcn2_0_nv12_soc.sr_exit_time_us =
>   				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
>   		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
> @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>   			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
>   					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
>   		}
> +		DC_FP_END();
>   	}
>   
>   	if (pool->base.pp_smu) {
> @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
>   	enum dml_project dml_project_version =
>   			get_dml_project_version(ctx->asic_id.hw_internal_rev);
>   
> -	DC_FP_START();
> -
>   	ctx->dc_bios->regs = &bios_regs;
>   	pool->base.funcs = &dcn20_res_pool_funcs;
>   
> @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
>   				ranges.reader_wm_sets[i].wm_inst = i;
>   				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
>   				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
> +				DC_FP_START();
>   				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
>   				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
> +				DC_FP_END();
>   
>   				ranges.num_reader_wm_sets = i + 1;
>   			}
> @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
>   		pool->base.oem_device = NULL;
>   	}
>   
> -	DC_FP_END();
>   	return true;
>   
>   create_fail:
>   
> -	DC_FP_END();
>   	dcn20_resource_destruct(pool);
>   
>   	return false;

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Jeremy Cline]

Hi,

On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
> > dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
> > calls which can sleep, but kernel_fpu_begin() disables preemption and
> > sleeping in this context is invalid.
> > 
> > The only places the FPU appears to be required is in the
> > init_soc_bounding_box() function and when calculating the
> > {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
> > avoid sleeping while using the FPU.
> > 
> > Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
> > Cc: Timothy Pearson <tpearson@raptorengineering.com>
> > Signed-off-by: Jeremy Cline <jcline@redhat.com>
> 
> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
> kzalloc(GFP_ATOMIC) for now.
> 
> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
> are even in the process of moving them out of the file because the compiles
> tend to clutter FP registers even outside of the annotated ranges on some
> architectures.
> 

Thanks for the review. Is it acceptable to move the DC_FP_END()
annotation up to the last usage? Keeping it where it is is probably
do-able, but covers things like calls to resource_construct() which
makes use of struct resource_create_funcs. I'm guessing only a sub-set
of the implementations are called via this function, but having an
interface which can't sleep sometimes doesn't sound appealing.

Happy to do it, but before I go down that road I just wanted to make
sure that's what you had in mind.

Thanks,
Jeremy

> > ---
> >   drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
> >   1 file changed, 4 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > index e04ecf0fc0db..a4fa5bf016c1 100644
> > --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
> >   		int i;
> > +		DC_FP_START();
> >   		dcn2_0_nv12_soc.sr_exit_time_us =
> >   				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
> >   		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
> > @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
> >   					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
> >   		}
> > +		DC_FP_END();
> >   	}
> >   	if (pool->base.pp_smu) {
> > @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
> >   	enum dml_project dml_project_version =
> >   			get_dml_project_version(ctx->asic_id.hw_internal_rev);
> > -	DC_FP_START();
> > -
> >   	ctx->dc_bios->regs = &bios_regs;
> >   	pool->base.funcs = &dcn20_res_pool_funcs;
> > @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
> >   				ranges.reader_wm_sets[i].wm_inst = i;
> >   				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
> >   				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
> > +				DC_FP_START();
> >   				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
> >   				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
> > +				DC_FP_END();
> >   				ranges.num_reader_wm_sets = i + 1;
> >   			}
> > @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
> >   		pool->base.oem_device = NULL;
> >   	}
> > -	DC_FP_END();
> >   	return true;
> >   create_fail:
> > -	DC_FP_END();
> >   	dcn20_resource_destruct(pool);
> >   	return false;
> 

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Jeremy Cline]

Hi,

On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
> > dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
> > calls which can sleep, but kernel_fpu_begin() disables preemption and
> > sleeping in this context is invalid.
> > 
> > The only places the FPU appears to be required is in the
> > init_soc_bounding_box() function and when calculating the
> > {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
> > avoid sleeping while using the FPU.
> > 
> > Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
> > Cc: Timothy Pearson <tpearson@raptorengineering.com>
> > Signed-off-by: Jeremy Cline <jcline@redhat.com>
> 
> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
> kzalloc(GFP_ATOMIC) for now.
> 
> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
> are even in the process of moving them out of the file because the compiles
> tend to clutter FP registers even outside of the annotated ranges on some
> architectures.
> 

Thanks for the review. Is it acceptable to move the DC_FP_END()
annotation up to the last usage? Keeping it where it is is probably
do-able, but covers things like calls to resource_construct() which
makes use of struct resource_create_funcs. I'm guessing only a sub-set
of the implementations are called via this function, but having an
interface which can't sleep sometimes doesn't sound appealing.

Happy to do it, but before I go down that road I just wanted to make
sure that's what you had in mind.

Thanks,
Jeremy

> > ---
> >   drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
> >   1 file changed, 4 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > index e04ecf0fc0db..a4fa5bf016c1 100644
> > --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
> >   		int i;
> > +		DC_FP_START();
> >   		dcn2_0_nv12_soc.sr_exit_time_us =
> >   				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
> >   		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
> > @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
> >   					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
> >   		}
> > +		DC_FP_END();
> >   	}
> >   	if (pool->base.pp_smu) {
> > @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
> >   	enum dml_project dml_project_version =
> >   			get_dml_project_version(ctx->asic_id.hw_internal_rev);
> > -	DC_FP_START();
> > -
> >   	ctx->dc_bios->regs = &bios_regs;
> >   	pool->base.funcs = &dcn20_res_pool_funcs;
> > @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
> >   				ranges.reader_wm_sets[i].wm_inst = i;
> >   				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
> >   				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
> > +				DC_FP_START();
> >   				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
> >   				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
> > +				DC_FP_END();
> >   				ranges.num_reader_wm_sets = i + 1;
> >   			}
> > @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
> >   		pool->base.oem_device = NULL;
> >   	}
> > -	DC_FP_END();
> >   	return true;
> >   create_fail:
> > -	DC_FP_END();
> >   	dcn20_resource_destruct(pool);
> >   	return false;
> 

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Jeremy Cline]

Hi,

On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
> > dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
> > calls which can sleep, but kernel_fpu_begin() disables preemption and
> > sleeping in this context is invalid.
> > 
> > The only places the FPU appears to be required is in the
> > init_soc_bounding_box() function and when calculating the
> > {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
> > avoid sleeping while using the FPU.
> > 
> > Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
> > Cc: Timothy Pearson <tpearson@raptorengineering.com>
> > Signed-off-by: Jeremy Cline <jcline@redhat.com>
> 
> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
> kzalloc(GFP_ATOMIC) for now.
> 
> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
> are even in the process of moving them out of the file because the compiles
> tend to clutter FP registers even outside of the annotated ranges on some
> architectures.
> 

Thanks for the review. Is it acceptable to move the DC_FP_END()
annotation up to the last usage? Keeping it where it is is probably
do-able, but covers things like calls to resource_construct() which
makes use of struct resource_create_funcs. I'm guessing only a sub-set
of the implementations are called via this function, but having an
interface which can't sleep sometimes doesn't sound appealing.

Happy to do it, but before I go down that road I just wanted to make
sure that's what you had in mind.

Thanks,
Jeremy

> > ---
> >   drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
> >   1 file changed, 4 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > index e04ecf0fc0db..a4fa5bf016c1 100644
> > --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
> >   		int i;
> > +		DC_FP_START();
> >   		dcn2_0_nv12_soc.sr_exit_time_us =
> >   				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
> >   		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
> > @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
> >   					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
> >   		}
> > +		DC_FP_END();
> >   	}
> >   	if (pool->base.pp_smu) {
> > @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
> >   	enum dml_project dml_project_version =
> >   			get_dml_project_version(ctx->asic_id.hw_internal_rev);
> > -	DC_FP_START();
> > -
> >   	ctx->dc_bios->regs = &bios_regs;
> >   	pool->base.funcs = &dcn20_res_pool_funcs;
> > @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
> >   				ranges.reader_wm_sets[i].wm_inst = i;
> >   				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
> >   				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
> > +				DC_FP_START();
> >   				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
> >   				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
> > +				DC_FP_END();
> >   				ranges.num_reader_wm_sets = i + 1;
> >   			}
> > @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
> >   		pool->base.oem_device = NULL;
> >   	}
> > -	DC_FP_END();
> >   	return true;
> >   create_fail:
> > -	DC_FP_END();
> >   	dcn20_resource_destruct(pool);
> >   	return false;
> 

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Daniel Vetter]

On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
> > dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
> > calls which can sleep, but kernel_fpu_begin() disables preemption and
> > sleeping in this context is invalid.
> > 
> > The only places the FPU appears to be required is in the
> > init_soc_bounding_box() function and when calculating the
> > {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
> > avoid sleeping while using the FPU.
> > 
> > Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
> > Cc: Timothy Pearson <tpearson@raptorengineering.com>
> > Signed-off-by: Jeremy Cline <jcline@redhat.com>
> 
> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
> kzalloc(GFP_ATOMIC) for now.
> 
> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
> are even in the process of moving them out of the file because the compiles
> tend to clutter FP registers even outside of the annotated ranges on some
> architectures.

Out of curiosity, what's the plan? Soft-fp implementation for DC so you
can keep the algorithms all unchanged, or redoing them as some fixed point
with careful review and retesting everything? Something else?
-Daniel

> 
> Regards,
> Christian.
> 
> > ---
> >   drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
> >   1 file changed, 4 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > index e04ecf0fc0db..a4fa5bf016c1 100644
> > --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
> >   		int i;
> > +		DC_FP_START();
> >   		dcn2_0_nv12_soc.sr_exit_time_us =
> >   				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
> >   		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
> > @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
> >   					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
> >   		}
> > +		DC_FP_END();
> >   	}
> >   	if (pool->base.pp_smu) {
> > @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
> >   	enum dml_project dml_project_version =
> >   			get_dml_project_version(ctx->asic_id.hw_internal_rev);
> > -	DC_FP_START();
> > -
> >   	ctx->dc_bios->regs = &bios_regs;
> >   	pool->base.funcs = &dcn20_res_pool_funcs;
> > @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
> >   				ranges.reader_wm_sets[i].wm_inst = i;
> >   				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
> >   				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
> > +				DC_FP_START();
> >   				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
> >   				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
> > +				DC_FP_END();
> >   				ranges.num_reader_wm_sets = i + 1;
> >   			}
> > @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
> >   		pool->base.oem_device = NULL;
> >   	}
> > -	DC_FP_END();
> >   	return true;
> >   create_fail:
> > -	DC_FP_END();
> >   	dcn20_resource_destruct(pool);
> >   	return false;
> 

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Daniel Vetter]

On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
> > dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
> > calls which can sleep, but kernel_fpu_begin() disables preemption and
> > sleeping in this context is invalid.
> > 
> > The only places the FPU appears to be required is in the
> > init_soc_bounding_box() function and when calculating the
> > {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
> > avoid sleeping while using the FPU.
> > 
> > Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
> > Cc: Timothy Pearson <tpearson@raptorengineering.com>
> > Signed-off-by: Jeremy Cline <jcline@redhat.com>
> 
> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
> kzalloc(GFP_ATOMIC) for now.
> 
> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
> are even in the process of moving them out of the file because the compiles
> tend to clutter FP registers even outside of the annotated ranges on some
> architectures.

Out of curiosity, what's the plan? Soft-fp implementation for DC so you
can keep the algorithms all unchanged, or redoing them as some fixed point
with careful review and retesting everything? Something else?
-Daniel

> 
> Regards,
> Christian.
> 
> > ---
> >   drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
> >   1 file changed, 4 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > index e04ecf0fc0db..a4fa5bf016c1 100644
> > --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
> >   		int i;
> > +		DC_FP_START();
> >   		dcn2_0_nv12_soc.sr_exit_time_us =
> >   				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
> >   		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
> > @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
> >   					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
> >   		}
> > +		DC_FP_END();
> >   	}
> >   	if (pool->base.pp_smu) {
> > @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
> >   	enum dml_project dml_project_version =
> >   			get_dml_project_version(ctx->asic_id.hw_internal_rev);
> > -	DC_FP_START();
> > -
> >   	ctx->dc_bios->regs = &bios_regs;
> >   	pool->base.funcs = &dcn20_res_pool_funcs;
> > @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
> >   				ranges.reader_wm_sets[i].wm_inst = i;
> >   				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
> >   				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
> > +				DC_FP_START();
> >   				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
> >   				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
> > +				DC_FP_END();
> >   				ranges.num_reader_wm_sets = i + 1;
> >   			}
> > @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
> >   		pool->base.oem_device = NULL;
> >   	}
> > -	DC_FP_END();
> >   	return true;
> >   create_fail:
> > -	DC_FP_END();
> >   	dcn20_resource_destruct(pool);
> >   	return false;
> 

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Daniel Vetter]

On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
> > dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
> > calls which can sleep, but kernel_fpu_begin() disables preemption and
> > sleeping in this context is invalid.
> > 
> > The only places the FPU appears to be required is in the
> > init_soc_bounding_box() function and when calculating the
> > {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
> > avoid sleeping while using the FPU.
> > 
> > Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
> > Cc: Timothy Pearson <tpearson@raptorengineering.com>
> > Signed-off-by: Jeremy Cline <jcline@redhat.com>
> 
> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
> kzalloc(GFP_ATOMIC) for now.
> 
> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
> are even in the process of moving them out of the file because the compiles
> tend to clutter FP registers even outside of the annotated ranges on some
> architectures.

Out of curiosity, what's the plan? Soft-fp implementation for DC so you
can keep the algorithms all unchanged, or redoing them as some fixed point
with careful review and retesting everything? Something else?
-Daniel

> 
> Regards,
> Christian.
> 
> > ---
> >   drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
> >   1 file changed, 4 insertions(+), 4 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > index e04ecf0fc0db..a4fa5bf016c1 100644
> > --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
> > @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
> >   		int i;
> > +		DC_FP_START();
> >   		dcn2_0_nv12_soc.sr_exit_time_us =
> >   				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
> >   		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
> > @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
> >   			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
> >   					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
> >   		}
> > +		DC_FP_END();
> >   	}
> >   	if (pool->base.pp_smu) {
> > @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
> >   	enum dml_project dml_project_version =
> >   			get_dml_project_version(ctx->asic_id.hw_internal_rev);
> > -	DC_FP_START();
> > -
> >   	ctx->dc_bios->regs = &bios_regs;
> >   	pool->base.funcs = &dcn20_res_pool_funcs;
> > @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
> >   				ranges.reader_wm_sets[i].wm_inst = i;
> >   				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
> >   				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
> > +				DC_FP_START();
> >   				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
> >   				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
> > +				DC_FP_END();
> >   				ranges.num_reader_wm_sets = i + 1;
> >   			}
> > @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
> >   		pool->base.oem_device = NULL;
> >   	}
> > -	DC_FP_END();
> >   	return true;
> >   create_fail:
> > -	DC_FP_END();
> >   	dcn20_resource_destruct(pool);
> >   	return false;
> 

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Christian König]

Am 11.01.21 um 17:32 schrieb Daniel Vetter:
> On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
>> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
>>> dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
>>> calls which can sleep, but kernel_fpu_begin() disables preemption and
>>> sleeping in this context is invalid.
>>>
>>> The only places the FPU appears to be required is in the
>>> init_soc_bounding_box() function and when calculating the
>>> {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
>>> avoid sleeping while using the FPU.
>>>
>>> Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
>>> Cc: Timothy Pearson <tpearson@raptorengineering.com>
>>> Signed-off-by: Jeremy Cline <jcline@redhat.com>
>> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
>> kzalloc(GFP_ATOMIC) for now.
>>
>> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
>> are even in the process of moving them out of the file because the compiles
>> tend to clutter FP registers even outside of the annotated ranges on some
>> architectures.
> Out of curiosity, what's the plan? Soft-fp implementation for DC so you
> can keep the algorithms all unchanged, or redoing them as some fixed point
> with careful review and retesting everything? Something else?

My last status is that we want to move all FP related functions into a 
separate C file.

Then compile only that file with FP enabled and all callers of those 
functions must protected the function calls with FP enable/disable.

That's the only way we can guarantee that no FP state is corrupted.

Regards,
Christian.

> -Daniel
>
>> Regards,
>> Christian.
>>
>>> ---
>>>    drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
>>>    1 file changed, 4 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> index e04ecf0fc0db..a4fa5bf016c1 100644
>>> --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
>>>    		int i;
>>> +		DC_FP_START();
>>>    		dcn2_0_nv12_soc.sr_exit_time_us =
>>>    				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
>>>    		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
>>> @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
>>>    					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
>>>    		}
>>> +		DC_FP_END();
>>>    	}
>>>    	if (pool->base.pp_smu) {
>>> @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
>>>    	enum dml_project dml_project_version =
>>>    			get_dml_project_version(ctx->asic_id.hw_internal_rev);
>>> -	DC_FP_START();
>>> -
>>>    	ctx->dc_bios->regs = &bios_regs;
>>>    	pool->base.funcs = &dcn20_res_pool_funcs;
>>> @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
>>>    				ranges.reader_wm_sets[i].wm_inst = i;
>>>    				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
>>>    				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
>>> +				DC_FP_START();
>>>    				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
>>>    				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
>>> +				DC_FP_END();
>>>    				ranges.num_reader_wm_sets = i + 1;
>>>    			}
>>> @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
>>>    		pool->base.oem_device = NULL;
>>>    	}
>>> -	DC_FP_END();
>>>    	return true;
>>>    create_fail:
>>> -	DC_FP_END();
>>>    	dcn20_resource_destruct(pool);
>>>    	return false;

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Christian König]

Am 11.01.21 um 17:32 schrieb Daniel Vetter:
> On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
>> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
>>> dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
>>> calls which can sleep, but kernel_fpu_begin() disables preemption and
>>> sleeping in this context is invalid.
>>>
>>> The only places the FPU appears to be required is in the
>>> init_soc_bounding_box() function and when calculating the
>>> {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
>>> avoid sleeping while using the FPU.
>>>
>>> Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
>>> Cc: Timothy Pearson <tpearson@raptorengineering.com>
>>> Signed-off-by: Jeremy Cline <jcline@redhat.com>
>> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
>> kzalloc(GFP_ATOMIC) for now.
>>
>> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
>> are even in the process of moving them out of the file because the compiles
>> tend to clutter FP registers even outside of the annotated ranges on some
>> architectures.
> Out of curiosity, what's the plan? Soft-fp implementation for DC so you
> can keep the algorithms all unchanged, or redoing them as some fixed point
> with careful review and retesting everything? Something else?

My last status is that we want to move all FP related functions into a 
separate C file.

Then compile only that file with FP enabled and all callers of those 
functions must protected the function calls with FP enable/disable.

That's the only way we can guarantee that no FP state is corrupted.

Regards,
Christian.

> -Daniel
>
>> Regards,
>> Christian.
>>
>>> ---
>>>    drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
>>>    1 file changed, 4 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> index e04ecf0fc0db..a4fa5bf016c1 100644
>>> --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
>>>    		int i;
>>> +		DC_FP_START();
>>>    		dcn2_0_nv12_soc.sr_exit_time_us =
>>>    				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
>>>    		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
>>> @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
>>>    					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
>>>    		}
>>> +		DC_FP_END();
>>>    	}
>>>    	if (pool->base.pp_smu) {
>>> @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
>>>    	enum dml_project dml_project_version =
>>>    			get_dml_project_version(ctx->asic_id.hw_internal_rev);
>>> -	DC_FP_START();
>>> -
>>>    	ctx->dc_bios->regs = &bios_regs;
>>>    	pool->base.funcs = &dcn20_res_pool_funcs;
>>> @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
>>>    				ranges.reader_wm_sets[i].wm_inst = i;
>>>    				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
>>>    				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
>>> +				DC_FP_START();
>>>    				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
>>>    				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
>>> +				DC_FP_END();
>>>    				ranges.num_reader_wm_sets = i + 1;
>>>    			}
>>> @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
>>>    		pool->base.oem_device = NULL;
>>>    	}
>>> -	DC_FP_END();
>>>    	return true;
>>>    create_fail:
>>> -	DC_FP_END();
>>>    	dcn20_resource_destruct(pool);
>>>    	return false;

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Christian König]

Am 11.01.21 um 17:32 schrieb Daniel Vetter:
> On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
>> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
>>> dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
>>> calls which can sleep, but kernel_fpu_begin() disables preemption and
>>> sleeping in this context is invalid.
>>>
>>> The only places the FPU appears to be required is in the
>>> init_soc_bounding_box() function and when calculating the
>>> {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
>>> avoid sleeping while using the FPU.
>>>
>>> Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
>>> Cc: Timothy Pearson <tpearson@raptorengineering.com>
>>> Signed-off-by: Jeremy Cline <jcline@redhat.com>
>> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
>> kzalloc(GFP_ATOMIC) for now.
>>
>> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
>> are even in the process of moving them out of the file because the compiles
>> tend to clutter FP registers even outside of the annotated ranges on some
>> architectures.
> Out of curiosity, what's the plan? Soft-fp implementation for DC so you
> can keep the algorithms all unchanged, or redoing them as some fixed point
> with careful review and retesting everything? Something else?

My last status is that we want to move all FP related functions into a 
separate C file.

Then compile only that file with FP enabled and all callers of those 
functions must protected the function calls with FP enable/disable.

That's the only way we can guarantee that no FP state is corrupted.

Regards,
Christian.

> -Daniel
>
>> Regards,
>> Christian.
>>
>>> ---
>>>    drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
>>>    1 file changed, 4 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> index e04ecf0fc0db..a4fa5bf016c1 100644
>>> --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
>>>    		int i;
>>> +		DC_FP_START();
>>>    		dcn2_0_nv12_soc.sr_exit_time_us =
>>>    				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
>>>    		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
>>> @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
>>>    					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
>>>    		}
>>> +		DC_FP_END();
>>>    	}
>>>    	if (pool->base.pp_smu) {
>>> @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
>>>    	enum dml_project dml_project_version =
>>>    			get_dml_project_version(ctx->asic_id.hw_internal_rev);
>>> -	DC_FP_START();
>>> -
>>>    	ctx->dc_bios->regs = &bios_regs;
>>>    	pool->base.funcs = &dcn20_res_pool_funcs;
>>> @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
>>>    				ranges.reader_wm_sets[i].wm_inst = i;
>>>    				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
>>>    				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
>>> +				DC_FP_START();
>>>    				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
>>>    				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
>>> +				DC_FP_END();
>>>    				ranges.num_reader_wm_sets = i + 1;
>>>    			}
>>> @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
>>>    		pool->base.oem_device = NULL;
>>>    	}
>>> -	DC_FP_END();
>>>    	return true;
>>>    create_fail:
>>> -	DC_FP_END();
>>>    	dcn20_resource_destruct(pool);
>>>    	return false;

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Christian König]

Am 11.01.21 um 16:39 schrieb Jeremy Cline:
> Hi,
>
> On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
>> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
>>> dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
>>> calls which can sleep, but kernel_fpu_begin() disables preemption and
>>> sleeping in this context is invalid.
>>>
>>> The only places the FPU appears to be required is in the
>>> init_soc_bounding_box() function and when calculating the
>>> {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
>>> avoid sleeping while using the FPU.
>>>
>>> Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
>>> Cc: Timothy Pearson <tpearson@raptorengineering.com>
>>> Signed-off-by: Jeremy Cline <jcline@redhat.com>
>> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
>> kzalloc(GFP_ATOMIC) for now.
>>
>> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
>> are even in the process of moving them out of the file because the compiles
>> tend to clutter FP registers even outside of the annotated ranges on some
>> architectures.
>>
> Thanks for the review. Is it acceptable to move the DC_FP_END()
> annotation up to the last usage? Keeping it where it is is probably
> do-able, but covers things like calls to resource_construct() which
> makes use of struct resource_create_funcs. I'm guessing only a sub-set
> of the implementations are called via this function, but having an
> interface which can't sleep sometimes doesn't sound appealing.
>
> Happy to do it, but before I go down that road I just wanted to make
> sure that's what you had in mind.

I can't fully judge that either. Harry and the rest of our DC team needs 
to decide that.

Thanks,
Christian.

>
> Thanks,
> Jeremy
>
>>> ---
>>>    drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
>>>    1 file changed, 4 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> index e04ecf0fc0db..a4fa5bf016c1 100644
>>> --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
>>>    		int i;
>>> +		DC_FP_START();
>>>    		dcn2_0_nv12_soc.sr_exit_time_us =
>>>    				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
>>>    		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
>>> @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
>>>    					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
>>>    		}
>>> +		DC_FP_END();
>>>    	}
>>>    	if (pool->base.pp_smu) {
>>> @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
>>>    	enum dml_project dml_project_version =
>>>    			get_dml_project_version(ctx->asic_id.hw_internal_rev);
>>> -	DC_FP_START();
>>> -
>>>    	ctx->dc_bios->regs = &bios_regs;
>>>    	pool->base.funcs = &dcn20_res_pool_funcs;
>>> @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
>>>    				ranges.reader_wm_sets[i].wm_inst = i;
>>>    				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
>>>    				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
>>> +				DC_FP_START();
>>>    				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
>>>    				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
>>> +				DC_FP_END();
>>>    				ranges.num_reader_wm_sets = i + 1;
>>>    			}
>>> @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
>>>    		pool->base.oem_device = NULL;
>>>    	}
>>> -	DC_FP_END();
>>>    	return true;
>>>    create_fail:
>>> -	DC_FP_END();
>>>    	dcn20_resource_destruct(pool);
>>>    	return false;

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Christian König]

Am 11.01.21 um 16:39 schrieb Jeremy Cline:
> Hi,
>
> On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
>> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
>>> dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
>>> calls which can sleep, but kernel_fpu_begin() disables preemption and
>>> sleeping in this context is invalid.
>>>
>>> The only places the FPU appears to be required is in the
>>> init_soc_bounding_box() function and when calculating the
>>> {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
>>> avoid sleeping while using the FPU.
>>>
>>> Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
>>> Cc: Timothy Pearson <tpearson@raptorengineering.com>
>>> Signed-off-by: Jeremy Cline <jcline@redhat.com>
>> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
>> kzalloc(GFP_ATOMIC) for now.
>>
>> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
>> are even in the process of moving them out of the file because the compiles
>> tend to clutter FP registers even outside of the annotated ranges on some
>> architectures.
>>
> Thanks for the review. Is it acceptable to move the DC_FP_END()
> annotation up to the last usage? Keeping it where it is is probably
> do-able, but covers things like calls to resource_construct() which
> makes use of struct resource_create_funcs. I'm guessing only a sub-set
> of the implementations are called via this function, but having an
> interface which can't sleep sometimes doesn't sound appealing.
>
> Happy to do it, but before I go down that road I just wanted to make
> sure that's what you had in mind.

I can't fully judge that either. Harry and the rest of our DC team needs 
to decide that.

Thanks,
Christian.

>
> Thanks,
> Jeremy
>
>>> ---
>>>    drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
>>>    1 file changed, 4 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> index e04ecf0fc0db..a4fa5bf016c1 100644
>>> --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
>>>    		int i;
>>> +		DC_FP_START();
>>>    		dcn2_0_nv12_soc.sr_exit_time_us =
>>>    				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
>>>    		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
>>> @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
>>>    					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
>>>    		}
>>> +		DC_FP_END();
>>>    	}
>>>    	if (pool->base.pp_smu) {
>>> @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
>>>    	enum dml_project dml_project_version =
>>>    			get_dml_project_version(ctx->asic_id.hw_internal_rev);
>>> -	DC_FP_START();
>>> -
>>>    	ctx->dc_bios->regs = &bios_regs;
>>>    	pool->base.funcs = &dcn20_res_pool_funcs;
>>> @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
>>>    				ranges.reader_wm_sets[i].wm_inst = i;
>>>    				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
>>>    				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
>>> +				DC_FP_START();
>>>    				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
>>>    				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
>>> +				DC_FP_END();
>>>    				ranges.num_reader_wm_sets = i + 1;
>>>    			}
>>> @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
>>>    		pool->base.oem_device = NULL;
>>>    	}
>>> -	DC_FP_END();
>>>    	return true;
>>>    create_fail:
>>> -	DC_FP_END();
>>>    	dcn20_resource_destruct(pool);
>>>    	return false;

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH] amdgpu: Avoid sleeping during FPU critical sections

[Christian König]

Am 11.01.21 um 16:39 schrieb Jeremy Cline:
> Hi,
>
> On Mon, Jan 11, 2021 at 09:53:56AM +0100, Christian König wrote:
>> Am 08.01.21 um 22:58 schrieb Jeremy Cline:
>>> dcn20_resource_construct() includes a number of kzalloc(GFP_KERNEL)
>>> calls which can sleep, but kernel_fpu_begin() disables preemption and
>>> sleeping in this context is invalid.
>>>
>>> The only places the FPU appears to be required is in the
>>> init_soc_bounding_box() function and when calculating the
>>> {min,max}_fill_clk_mhz. Narrow the scope to just these two parts to
>>> avoid sleeping while using the FPU.
>>>
>>> Fixes: 7a8a3430be15 ("amdgpu: Wrap FPU dependent functions in dc20")
>>> Cc: Timothy Pearson <tpearson@raptorengineering.com>
>>> Signed-off-by: Jeremy Cline <jcline@redhat.com>
>> Good catch, but I would rather replace the kzalloc(GFP_KERNEL) with a
>> kzalloc(GFP_ATOMIC) for now.
>>
>> We have tons of problems with this DC_FP_START()/DC_FP_END() annotations and
>> are even in the process of moving them out of the file because the compiles
>> tend to clutter FP registers even outside of the annotated ranges on some
>> architectures.
>>
> Thanks for the review. Is it acceptable to move the DC_FP_END()
> annotation up to the last usage? Keeping it where it is is probably
> do-able, but covers things like calls to resource_construct() which
> makes use of struct resource_create_funcs. I'm guessing only a sub-set
> of the implementations are called via this function, but having an
> interface which can't sleep sometimes doesn't sound appealing.
>
> Happy to do it, but before I go down that road I just wanted to make
> sure that's what you had in mind.

I can't fully judge that either. Harry and the rest of our DC team needs 
to decide that.

Thanks,
Christian.

>
> Thanks,
> Jeremy
>
>>> ---
>>>    drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c | 8 ++++----
>>>    1 file changed, 4 insertions(+), 4 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> index e04ecf0fc0db..a4fa5bf016c1 100644
>>> --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
>>> @@ -3622,6 +3622,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
>>>    		int i;
>>> +		DC_FP_START();
>>>    		dcn2_0_nv12_soc.sr_exit_time_us =
>>>    				fixed16_to_double_to_cpu(bb->sr_exit_time_us);
>>>    		dcn2_0_nv12_soc.sr_enter_plus_exit_time_us =
>>> @@ -3721,6 +3722,7 @@ static bool init_soc_bounding_box(struct dc *dc,
>>>    			dcn2_0_nv12_soc.clock_limits[i].dram_speed_mts =
>>>    					fixed16_to_double_to_cpu(bb->clock_limits[i].dram_speed_mts);
>>>    		}
>>> +		DC_FP_END();
>>>    	}
>>>    	if (pool->base.pp_smu) {
>>> @@ -3777,8 +3779,6 @@ static bool dcn20_resource_construct(
>>>    	enum dml_project dml_project_version =
>>>    			get_dml_project_version(ctx->asic_id.hw_internal_rev);
>>> -	DC_FP_START();
>>> -
>>>    	ctx->dc_bios->regs = &bios_regs;
>>>    	pool->base.funcs = &dcn20_res_pool_funcs;
>>> @@ -3959,8 +3959,10 @@ static bool dcn20_resource_construct(
>>>    				ranges.reader_wm_sets[i].wm_inst = i;
>>>    				ranges.reader_wm_sets[i].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
>>>    				ranges.reader_wm_sets[i].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
>>> +				DC_FP_START();
>>>    				ranges.reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
>>>    				ranges.reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
>>> +				DC_FP_END();
>>>    				ranges.num_reader_wm_sets = i + 1;
>>>    			}
>>> @@ -4125,12 +4127,10 @@ static bool dcn20_resource_construct(
>>>    		pool->base.oem_device = NULL;
>>>    	}
>>> -	DC_FP_END();
>>>    	return true;
>>>    create_fail:
>>> -	DC_FP_END();
>>>    	dcn20_resource_destruct(pool);
>>>    	return false;

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx