drm/amdgpu/gfx: fix cleaner shader IB buffer overflow

The cleaner shader sysfs path allocates a 16-dword (64 byte) IB but
incorrectly fills (align_mask + 1) dwords. On GFX rings align_mask is
0xff, so the loop wrote 256 dwords into a 64-byte buffer, causing a
kernel page fault.

The IB only needs to be a minimal NOP shell to schedule the job; the
cleaner shader itself is emitted on the ring via emit_cleaner_shader().
Fill 16 dwords to match the allocation.

v2: Use ib_size_dw variable (Lijo)

Fixes: d361ad5d2f ("drm/amdgpu: Add sysfs interface for running cleaner shader")
Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Asad Kamal
2026-06-05 23:44:08 +08:00
committed by Alex Deucher
parent fe29192e1c
commit bf21af331e

View File

@@ -1689,12 +1689,13 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
struct drm_gpu_scheduler *sched = &ring->sched;
struct drm_sched_entity entity;
unsigned int ib_size_dw = 16;
static atomic_t counter;
struct dma_fence *f;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
void *owner;
int i, r;
int r;
/* Initialize the scheduler entity */
r = drm_sched_entity_init(&entity, DRM_SCHED_PRIORITY_NORMAL,
@@ -1712,7 +1713,7 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring)
owner = (void *)(unsigned long)atomic_inc_return(&counter);
r = amdgpu_job_alloc_with_ib(ring->adev, &entity, owner,
64, 0, &job,
ib_size_dw * sizeof(uint32_t), 0, &job,
AMDGPU_KERNEL_JOB_ID_CLEANER_SHADER);
if (r)
goto err;
@@ -1722,9 +1723,8 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring)
job->run_cleaner_shader = true;
ib = &job->ibs[0];
for (i = 0; i <= ring->funcs->align_mask; ++i)
ib->ptr[i] = ring->funcs->nop;
ib->length_dw = ring->funcs->align_mask + 1;
memset32(ib->ptr, ring->funcs->nop, ib_size_dw);
ib->length_dw = ib_size_dw;
f = amdgpu_job_submit(job);