Re: [PATCHv4] drm/amdgpu: Update invalid PTE flag setting

[Christian König <ckoenig.leichtzumerken@xxxxxxxxx>]

Am 19.06.23 um 19:38 schrieb Mukul Joshi:
> Update the invalid PTE flag setting with TF enabled.
> This is to ensure, in addition to transitioning the
> retry fault to a no-retry fault, it also causes the
> wavefront to enter the trap handler. With the current
> setting, the fault only transitions to a no-retry fault.
> Additionally, have 2 sets of invalid PTE settings, one for
> TF enabled, the other for TF disabled. The setting with
> TF disabled, doesn't work with TF enabled.
>
> Signed-off-by: Mukul Joshi <mukul.joshi@xxxxxxx>

Acked-by: Christian König <christian.koenig@xxxxxxx>

> ---
> v1->v2:
> - Update handling according to Christian's feedback.
>
> v2->v3:
> - Remove ASIC specific callback (Felix).
>
> v3->v4:
> - Add noretry flag to amdgpu->gmc. This allows to set
>    ASIC specific flags.
>
>   drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h   |  2 ++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c    |  2 +-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h    |  6 +++++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 31 +++++++++++++++++++++++
>   drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c    |  1 +
>   drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c    |  1 +
>   drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c     |  1 +
>   drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c     |  1 +
>   drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c     |  1 +
>   9 files changed, 45 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> index 56d73fade568..fdc25cd559b6 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
> @@ -331,6 +331,8 @@ struct amdgpu_gmc {
>   	u64 VM_CONTEXT_PAGE_TABLE_END_ADDR_LO32[16];
>   	u64 VM_CONTEXT_PAGE_TABLE_END_ADDR_HI32[16];
>   	u64 MC_VM_MX_L1_TLB_CNTL;
> +
> +	u64 noretry_flags;
>   };
>   
>   #define amdgpu_gmc_flush_gpu_tlb(adev, vmid, vmhub, type) ((adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid), (vmhub), (type)))
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> index eff73c428b12..8c7861a4d75d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -2604,7 +2604,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
>   		/* Intentionally setting invalid PTE flag
>   		 * combination to force a no-retry-fault
>   		 */
> -		flags = AMDGPU_PTE_SNOOPED | AMDGPU_PTE_PRT;
> +		flags = AMDGPU_VM_NORETRY_FLAGS;
>   		value = 0;
>   	} else if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
>   		/* Redirect the access to the dummy page */
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
> index 9c85d494f2a2..b81fcb962d8f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
> @@ -84,7 +84,13 @@ struct amdgpu_mem_stats;
>   /* PDE Block Fragment Size for VEGA10 */
>   #define AMDGPU_PDE_BFS(a)	((uint64_t)a << 59)
>   
> +/* Flag combination to set no-retry with TF disabled */
> +#define AMDGPU_VM_NORETRY_FLAGS	(AMDGPU_PTE_EXECUTABLE | AMDGPU_PDE_PTE | \
> +				AMDGPU_PTE_TF)
>   
> +/* Flag combination to set no-retry with TF enabled */
> +#define AMDGPU_VM_NORETRY_FLAGS_TF (AMDGPU_PTE_VALID | AMDGPU_PTE_SYSTEM | \
> +				   AMDGPU_PTE_PRT)
>   /* For GFX9 */
>   #define AMDGPU_PTE_MTYPE_VG10(a)	((uint64_t)(a) << 57)
>   #define AMDGPU_PTE_MTYPE_VG10_MASK	AMDGPU_PTE_MTYPE_VG10(3ULL)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
> index dea1a64be44d..24ddf6a0512a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
> @@ -778,6 +778,27 @@ int amdgpu_vm_pde_update(struct amdgpu_vm_update_params *params,
>   					1, 0, flags);
>   }
>   
> +/**
> + * amdgpu_vm_pte_update_noretry_flags - Update PTE no-retry flags
> + *
> + * @adev - amdgpu_device pointer
> + * @flags: pointer to PTE flags
> + *
> + * Update PTE no-retry flags when TF is enabled.
> + */
> +static void amdgpu_vm_pte_update_noretry_flags(struct amdgpu_device *adev,
> +						uint64_t *flags)
> +{
> +	/*
> +	 * Update no-retry flags with the corresponding TF
> +	 * no-retry combination.
> +	 */
> +	if ((*flags & AMDGPU_VM_NORETRY_FLAGS) == AMDGPU_VM_NORETRY_FLAGS) {
> +		*flags &= ~AMDGPU_VM_NORETRY_FLAGS;
> +		*flags |= adev->gmc.noretry_flags;
> +	}
> +}
> +
>   /*
>    * amdgpu_vm_pte_update_flags - figure out flags for PTE updates
>    *
> @@ -804,6 +825,16 @@ static void amdgpu_vm_pte_update_flags(struct amdgpu_vm_update_params *params,
>   		flags |= AMDGPU_PTE_EXECUTABLE;
>   	}
>   
> +	/*
> +	 * Update no-retry flags to use the no-retry flag combination
> +	 * with TF enabled. The AMDGPU_VM_NORETRY_FLAGS flag combination
> +	 * does not work when TF is enabled. So, replace them with
> +	 * AMDGPU_VM_NORETRY_FLAGS_TF flag combination which works for
> +	 * all cases.
> +	 */
> +	if (level == AMDGPU_VM_PTB)
> +		amdgpu_vm_pte_update_noretry_flags(adev, &flags);
> +
>   	/* APUs mapping system memory may need different MTYPEs on different
>   	 * NUMA nodes. Only do this for contiguous ranges that can be assumed
>   	 * to be on the same NUMA node.
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> index 0c8a47989576..13b89f78d07d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> @@ -751,6 +751,7 @@ static int gmc_v10_0_early_init(void *handle)
>   	adev->gmc.private_aperture_start = 0x1000000000000000ULL;
>   	adev->gmc.private_aperture_end =
>   		adev->gmc.private_aperture_start + (4ULL << 30) - 1;
> +	adev->gmc.noretry_flags = AMDGPU_VM_NORETRY_FLAGS_TF;
>   
>   	return 0;
>   }
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
> index c571f0d95994..c68ecb7dfa39 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
> @@ -651,6 +651,7 @@ static int gmc_v11_0_early_init(void *handle)
>   	adev->gmc.private_aperture_start = 0x1000000000000000ULL;
>   	adev->gmc.private_aperture_end =
>   		adev->gmc.private_aperture_start + (4ULL << 30) - 1;
> +	adev->gmc.noretry_flags = AMDGPU_VM_NORETRY_FLAGS_TF;
>   
>   	return 0;
>   }
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
> index acd2b407860f..027b14603037 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
> @@ -942,6 +942,7 @@ static int gmc_v7_0_early_init(void *handle)
>   		adev->gmc.shared_aperture_end + 1;
>   	adev->gmc.private_aperture_end =
>   		adev->gmc.private_aperture_start + (4ULL << 30) - 1;
> +	adev->gmc.noretry_flags = AMDGPU_VM_NORETRY_FLAGS_TF;
>   
>   	return 0;
>   }
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
> index 85dead2a5702..581ed922dbe3 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
> @@ -1056,6 +1056,7 @@ static int gmc_v8_0_early_init(void *handle)
>   		adev->gmc.shared_aperture_end + 1;
>   	adev->gmc.private_aperture_end =
>   		adev->gmc.private_aperture_start + (4ULL << 30) - 1;
> +	adev->gmc.noretry_flags = AMDGPU_VM_NORETRY_FLAGS_TF;
>   
>   	return 0;
>   }
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> index 67e669e0141c..ebdbc823fae3 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> @@ -1622,6 +1622,7 @@ static int gmc_v9_0_early_init(void *handle)
>   	adev->gmc.private_aperture_start = 0x1000000000000000ULL;
>   	adev->gmc.private_aperture_end =
>   		adev->gmc.private_aperture_start + (4ULL << 30) - 1;
> +	adev->gmc.noretry_flags = AMDGPU_VM_NORETRY_FLAGS_TF;
>   
>   	return 0;
>   }