Am 12.03.25 um 14:09 schrieb Chris Bainbridge:
> Fix an oops in ttm_bo_delayed_delete which results from dererencing a
> dangling pointer:
>
> Oops: general protection fault, probably for non-canonical address
> 0x6b6b6b6b6b6b6b7b: [#1] PREEMPT SMP
> CPU: 4 UID: 0 PID: 1082 Comm: kworker/u65:
Hi Thomas,
kernel test robot noticed the following build errors:
[auto build test ERROR on next-20250311]
[also build test ERROR on v6.14-rc6]
[cannot apply to drm-exynos/exynos-drm-next rockchip/for-next tegra/for-next
drm-xe/drm-xe-next linus/master v6.14-rc6 v6.14-rc5 v6.14-rc4]
[If your patc
Hi Thomas,
kernel test robot noticed the following build errors:
[auto build test ERROR on next-20250311]
[also build test ERROR on v6.14-rc6]
[cannot apply to drm-exynos/exynos-drm-next rockchip/for-next tegra/for-next
drm-xe/drm-xe-next linus/master v6.14-rc6 v6.14-rc5 v6.14-rc4]
[If your patc
Userspace needs this information to set up zcull correctly.
Signed-off-by: Mel Henning
---
.../drm/nouveau/include/nvkm/core/device.h| 6 ++
.../sdk/nvidia/inc/ctrl/ctrl2080/ctrl2080gr.h | 69 +++
drivers/gpu/drm/nouveau/nouveau_abi16.c | 15
drivers/gpu/drm/nouve
These patches add kernel-side support for using the zcull hardware in nvidia
gpus. Zcull aims to improve memory bandwidth by using an early approximate
depth test, similar to hierarchical Z on an AMD card. These patches add two
new ioctls on nouveau devices, which are currently only supported when
We add this ioctl to set up the zcull context switch buffer so userspace
can manage it. This also includes support for unbinding the buffer,
which helps simplify device teardown on the userspace side.
Signed-off-by: Mel Henning
---
drivers/gpu/drm/nouveau/include/nvif/if0020.h | 6 +++
.../gpu/
