From 9f57f7b47d4c9559ae85666eeaf9ffd150096574 Mon Sep 17 00:00:00 2001 From: Jay Cornwall Date: Wed, 26 Apr 2017 14:51:57 -0500 Subject: [PATCH] drm/amdgpu: Send no-retry XNACK for all fault types MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit A subset of VM fault types currently send retry XNACK to the client. This causes a storm of interrupts from the VM to the host. Until the storm is throttled by other means send no-retry XNACK for all fault types instead. No change in behavior to the client which will stall indefinitely with the current configuration in any case. Improves system stability under GC or MMHUB faults. Signed-off-by: Jay Cornwall Reviewed-by: Felix Kuehling Reviewed-by: John Bridgman Acked-by: Alex Deucher Acked-by: Christian König Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 3 +++ drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 3 +++ 2 files changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c index 3ff786cfc947..008ad3dc4afd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c @@ -206,6 +206,9 @@ static void gfxhub_v1_0_setup_vmid_config(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_BLOCK_SIZE, adev->vm_manager.block_size - 9); + /* Send no-retry XNACK on fault to suppress VM fault storm. */ + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0); WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_CNTL, i, tmp); WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, i*2, 0); WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_HI32, i*2, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index 0780e830b76b..96f1628541bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -222,6 +222,9 @@ static void mmhub_v1_0_setup_vmid_config(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_BLOCK_SIZE, adev->vm_manager.block_size - 9); + /* Send no-retry XNACK on fault to suppress VM fault storm. */ + tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, + RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0); WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_CNTL, i, tmp); WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, i*2, 0); WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_HI32, i*2, 0); -- 2.20.1