Am 04.06.21 um 09:53 schrieb Chen Li:
I met a gpu addr bug recently and the kernel log
tells me the pc is memcpy/memset and link register is
radeon_uvd_resume.

As we know, in some architectures, optimized memcpy/memset
may not work well on device memory. Trival memcpy_toio/memset_io
can fix this problem.

BTW, amdgpu has already done it in:
commit ba0b2275a678 ("drm/amdgpu: use memcpy_to/fromio for UVD fw upload"),
that's why it has no this issue on the same gpu and platform.

Signed-off-by: Chen Li <che...@uniontech.com>
---
  drivers/gpu/drm/radeon/radeon_uvd.c | 6 ++++--
  1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c 
b/drivers/gpu/drm/radeon/radeon_uvd.c
index 85a1f2c31749..55abf9a9623b 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -288,7 +288,9 @@ int radeon_uvd_resume(struct radeon_device *rdev)
        if (rdev->uvd.vcpu_bo == NULL)
                return -EINVAL;
- memcpy(rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size);
+       memcpy_toio((void __iomem *)rdev->uvd.cpu_addr,
+                               rdev->uvd_fw->data,
+                               rdev->uvd_fw->size);

The coding style still looks wrong here, e.g. it is indented to far to the right and data/size can be on one line.

Apart from that the patch is Reviewed-by: Christian König <christian.koe...@amd.com>

Regards,
Christian.

size = radeon_bo_size(rdev->uvd.vcpu_bo);
        size -= rdev->uvd_fw->size;
@@ -296,7 +298,7 @@ int radeon_uvd_resume(struct radeon_device *rdev)
        ptr = rdev->uvd.cpu_addr;
        ptr += rdev->uvd_fw->size;
- memset(ptr, 0, size);
+       memset_io((void __iomem *)ptr, 0, size);
return 0;
  }

Reply via email to