diff options
| author | Guchun Chen <guchun.chen@amd.com> | 2023-07-13 10:09:37 +0300 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2023-07-18 18:18:16 +0300 |
| commit | 5003ca63bce63b20c02c8049be46c44135939a64 (patch) | |
| tree | 959ad2912eff7531087a483b15ff3343e5997acf /drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | |
| parent | 50e633081e6d26ca7cae6e2b610032a1df1654ed (diff) | |
| download | linux-5003ca63bce63b20c02c8049be46c44135939a64.tar.xz | |
drm/amdgpu: fix slab-out-of-bounds issue in amdgpu_vm_pt_create
Recent code set xcp_id stored from file private data when opening
device to amdgpu bo for accounting memory usage etc, but not all
VMs are attached to this fpriv structure like the vm cases in
amdgpu_mes_self_test, otherwise, KASAN will complain below out
of bound access. And more importantly, VM code should not touch
fpriv structure, so drop fpriv code handling from amdgpu_vm_pt.
[ 77.292314] BUG: KASAN: slab-out-of-bounds in amdgpu_vm_pt_create+0x17e/0x4b0 [amdgpu]
[ 77.293845] Read of size 4 at addr ffff888102c48a48 by task modprobe/1069
[ 77.294146] Call Trace:
[ 77.294178] <TASK>
[ 77.294208] dump_stack_lvl+0x49/0x63
[ 77.294260] print_report+0x16f/0x4a6
[ 77.294307] ? amdgpu_vm_pt_create+0x17e/0x4b0 [amdgpu]
[ 77.295979] ? kasan_complete_mode_report_info+0x3c/0x200
[ 77.296057] ? amdgpu_vm_pt_create+0x17e/0x4b0 [amdgpu]
[ 77.297556] kasan_report+0xb4/0x130
[ 77.297609] ? amdgpu_vm_pt_create+0x17e/0x4b0 [amdgpu]
[ 77.299202] __asan_load4+0x6f/0x90
[ 77.299272] amdgpu_vm_pt_create+0x17e/0x4b0 [amdgpu]
[ 77.300796] ? amdgpu_init+0x6e/0x1000 [amdgpu]
[ 77.302222] ? amdgpu_vm_pt_clear+0x750/0x750 [amdgpu]
[ 77.303721] ? preempt_count_sub+0x18/0xc0
[ 77.303786] amdgpu_vm_init+0x39e/0x870 [amdgpu]
[ 77.305186] ? amdgpu_vm_wait_idle+0x90/0x90 [amdgpu]
[ 77.306683] ? kasan_set_track+0x25/0x30
[ 77.306737] ? kasan_save_alloc_info+0x1b/0x30
[ 77.306795] ? __kasan_kmalloc+0x87/0xa0
[ 77.306852] amdgpu_mes_self_test+0x169/0x620 [amdgpu]
v2: without specifying xcp partition for PD/PT bo, the xcp id is -1.
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2686
Fixes: 3ebfd221c1a8 ("drm/amdkfd: Store xcp partition id to amdgpu bo")
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 11 |
1 files changed, 6 insertions, 5 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index 70fc5856a5b9..eb52dfe64948 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -498,11 +498,12 @@ exit: * @level: the page table level * @immediate: use a immediate update * @vmbo: pointer to the buffer object pointer + * @xcp_id: GPU partition id */ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, - int level, bool immediate, struct amdgpu_bo_vm **vmbo) + int level, bool immediate, struct amdgpu_bo_vm **vmbo, + int32_t xcp_id) { - struct amdgpu_fpriv *fpriv = container_of(vm, struct amdgpu_fpriv, vm); struct amdgpu_bo_param bp; struct amdgpu_bo *bo; struct dma_resv *resv; @@ -535,7 +536,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, bp.type = ttm_bo_type_kernel; bp.no_wait_gpu = immediate; - bp.xcp_id_plus1 = fpriv->xcp_id == ~0 ? 0 : fpriv->xcp_id + 1; + bp.xcp_id_plus1 = xcp_id + 1; if (vm->root.bo) bp.resv = vm->root.bo->tbo.base.resv; @@ -561,7 +562,7 @@ int amdgpu_vm_pt_create(struct amdgpu_device *adev, struct amdgpu_vm *vm, bp.type = ttm_bo_type_kernel; bp.resv = bo->tbo.base.resv; bp.bo_ptr_size = sizeof(struct amdgpu_bo); - bp.xcp_id_plus1 = fpriv->xcp_id == ~0 ? 0 : fpriv->xcp_id + 1; + bp.xcp_id_plus1 = xcp_id + 1; r = amdgpu_bo_create(adev, &bp, &(*vmbo)->shadow); @@ -606,7 +607,7 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_device *adev, return 0; amdgpu_vm_eviction_unlock(vm); - r = amdgpu_vm_pt_create(adev, vm, cursor->level, immediate, &pt); + r = amdgpu_vm_pt_create(adev, vm, cursor->level, immediate, &pt, 0); amdgpu_vm_eviction_lock(vm); if (r) return r; |