From 8f453c51cfae92fded6e232985f6943c51b7829c Mon Sep 17 00:00:00 2001 From: YiPeng Chai Date: Fri, 6 Jan 2023 20:16:53 +0800 Subject: [PATCH] drm/amdgpu: Adjust ras support check condition for special asic [Why]: Amdgpu ras uses amdgpu_ras_is_supported to check whether the ras block supports the ras function. amdgpu_ras_is_supported uses .ras_enabled to determine whether the ras function of the block is enabled. But for special asic with mem ecc enabled but sram ecc not enabled, some ras blocks support poison mode but their ras function is not enabled on .ras_enabled, these ras blocks will run abnormally. [How]: If the ras block is not supported on .ras_enabled but the asic supports poison mode and the ras block has ras configuration, it can be considered that the ras block supports ras function. Signed-off-by: YiPeng Chai Reviewed-by: Tao Zhou Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 3f1e987bdf83..6e543558386d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -3022,11 +3022,26 @@ int amdgpu_ras_set_context(struct amdgpu_device *adev, struct amdgpu_ras *ras_co int amdgpu_ras_is_supported(struct amdgpu_device *adev, unsigned int block) { + int ret = 0; struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); if (block >= AMDGPU_RAS_BLOCK_COUNT) return 0; - return ras && (adev->ras_enabled & (1 << block)); + + ret = ras && (adev->ras_enabled & (1 << block)); + + /* For the special asic with mem ecc enabled but sram ecc + * not enabled, even if the ras block is not supported on + * .ras_enabled, if the asic supports poison mode and the + * ras block has ras configuration, it can be considered + * that the ras block supports ras function. + */ + if (!ret && + amdgpu_ras_is_poison_mode_supported(adev) && + amdgpu_ras_get_ras_block(adev, block, 0)) + ret = 1; + + return ret; } int amdgpu_ras_reset_gpu(struct amdgpu_device *adev) -- 2.11.0