When amdgpu_vm_update_range hits a failure at amdgpu_vm_ptes_update, it
will skip calling update_funcs commit, which might lead to a memory
leak.
Prepare the commit function to be called in such error paths, where job
might be NULL or empty.
This allows the following commits to prevent the job leak below in the
presence of such failures.
[ 2877.877264] kmemleak: unreferenced object 0xffff89b1f3cf0800 (size 1024):
[ 2877.877273] kmemleak: comm "vm_always_valid", pid 3027, jiffies 4295714403
[ 2877.877275] kmemleak: hex dump (first 32 bytes):
[ 2877.877277] kmemleak: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
................
[ 2877.877279] kmemleak: 00 03 da 52 b1 89 ff ff 38 25 5f cb b1 89 ff ff
...R....8%_.....
[ 2877.877280] kmemleak: backtrace (crc d52b9041):
[ 2877.877282] kmemleak: __kmalloc_noprof+0x4b3/0x770
[ 2877.877288] kmemleak: amdgpu_job_alloc+0x69/0x280 [amdgpu]
[ 2877.877668] kmemleak: amdgpu_job_alloc_with_ib+0x55/0xf0 [amdgpu]
[ 2877.878023] kmemleak: amdgpu_vm_sdma_prepare+0x4b/0xa0 [amdgpu]
[ 2877.878350] kmemleak: amdgpu_vm_update_range+0x24f/0x940 [amdgpu]
[ 2877.878668] kmemleak: amdgpu_vm_clear_freed+0x13b/0x290 [amdgpu]
[ 2877.878983] kmemleak: amdgpu_gem_object_close+0x1ac/0x270 [amdgpu]
[ 2877.879300] kmemleak: drm_gem_object_release_handle+0x35/0xd0
[ 2877.879305] kmemleak: idr_for_each+0x70/0xe0
[ 2877.879310] kmemleak: drm_gem_release+0x23/0x30
[ 2877.879311] kmemleak: drm_file_free+0x217/0x2a0
[ 2877.879314] kmemleak: drm_release+0x61/0xe0
[ 2877.879317] kmemleak: amdgpu_drm_release+0x62/0xd0 [amdgpu]
[ 2877.879630] kmemleak: __fput+0xfb/0x2d0
[ 2877.879634] kmemleak: __x64_sys_close+0x3d/0x80
[ 2877.879637] kmemleak: do_syscall_64+0x12d/0x6c0
Fixes: 81417bea8755 ("drm/amdgpu: explicitly sync VM update to PDs/PTs")
Fixes: c3546695830e ("drm/amdgpu: use the new VM backend for PTEs")
Signed-off-by: Thadeu Lima de Souza Cascardo <[email protected]>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
index 50cc0779c340..975e26a48cd3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
@@ -90,6 +90,7 @@ static int amdgpu_vm_sdma_prepare(struct
amdgpu_vm_update_params *p,
if (r) {
p->num_dw_left = 0;
amdgpu_job_free(p->job);
+ p->job = NULL;
}
return r;
}
@@ -106,14 +107,24 @@ static int amdgpu_vm_sdma_prepare(struct
amdgpu_vm_update_params *p,
static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
struct dma_fence **fence)
{
- struct amdgpu_ib *ib = p->job->ibs;
+ struct amdgpu_ib *ib;
struct amdgpu_ring *ring;
struct dma_fence *f;
+ if (!p->job)
+ return 0;
+
+ ib = p->job->ibs;
+
+ if (ib->length_dw == 0) {
+ amdgpu_job_free(p->job);
+ p->job = NULL;
+ return 0;
+ }
+
ring = container_of(p->vm->delayed.rq->sched, struct amdgpu_ring,
sched);
- WARN_ON(ib->length_dw == 0);
amdgpu_ring_pad_ib(ring, ib);
if (p->needs_flush)
--
2.47.3
