aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
diff options
context:
space:
mode:
authorChristian König <[email protected]>2021-06-01 17:47:50 +0000
committerChristian König <[email protected]>2021-06-08 09:47:51 +0000
commitf91142c62161aecb6570d1d0a01aefcb6130b12b (patch)
tree2357efae00423f561935a120cdb3988af240250b /drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
parentdrm/bridge: ti-sn65dsi83: Add TI SN65DSI83 and SN65DSI84 driver (diff)
downloadkernel-f91142c62161aecb6570d1d0a01aefcb6130b12b.tar.gz
kernel-f91142c62161aecb6570d1d0a01aefcb6130b12b.zip
drm/ttm: nuke VM_MIXEDMAP on BO mappings v3
We discussed if that is really the right approach for quite a while now, but digging deeper into a bug report on arm turned out that this is actually horrible broken right now. The reason for this is that vmf_insert_mixed_prot() always tries to grab a reference to the underlaying page on architectures without ARCH_HAS_PTE_SPECIAL and as far as I can see also enabled GUP. So nuke using VM_MIXEDMAP here and use VM_PFNMAP instead. Also make sure to reject mappings without VM_SHARED. v2: reject COW mappings, merge function with only caller v3: adjust comment as suggested by Thomas Signed-off-by: Christian König <[email protected]> Bugs: https://gitlab.freedesktop.org/drm/amd/-/issues/1606#note_936174 Link: https://patchwork.freedesktop.org/patch/msgid/[email protected] Reviewed-by: Thomas Hellström <[email protected]>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c')
0 files changed, 0 insertions, 0 deletions