From: Chia-I Wu olvaffe@gmail.com
[ Upstream commit 9da050b0d9e04439d225a2ec3044af70cdfb3933 ]
kgd_mem pointers returned by kfd_process_device_translate_handle are only guaranteed to be valid while p->mutex is held. As soon as the mutex is unlocked, another thread can free the BO.
Signed-off-by: Chia-I Wu olvaffe@gmail.com Signed-off-by: Felix Kuehling Felix.Kuehling@amd.com Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index f79b8e964140e..e191d38f3da62 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1298,14 +1298,14 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, args->n_success = i+1; }
- mutex_unlock(&p->mutex); - err = amdgpu_amdkfd_gpuvm_sync_memory(dev->adev, (struct kgd_mem *) mem, true); if (err) { pr_debug("Sync memory failed, wait interrupted by user signal\n"); goto sync_memory_failed; }
+ mutex_unlock(&p->mutex); + /* Flush TLBs after waiting for the page table updates to complete */ for (i = 0; i < args->n_devices; i++) { peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); @@ -1321,9 +1321,9 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, bind_process_to_device_failed: get_mem_obj_from_handle_failed: map_memory_to_gpu_failed: +sync_memory_failed: mutex_unlock(&p->mutex); copy_from_user_failed: -sync_memory_failed: kfree(devices_arr);
return err; @@ -1337,6 +1337,7 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, void *mem; long err = 0; uint32_t *devices_arr = NULL, i; + bool flush_tlb;
if (!args->n_devices) { pr_debug("Device IDs array empty\n"); @@ -1389,16 +1390,19 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, } args->n_success = i+1; } - mutex_unlock(&p->mutex);
- if (kfd_flush_tlb_after_unmap(pdd->dev)) { + flush_tlb = kfd_flush_tlb_after_unmap(pdd->dev); + if (flush_tlb) { err = amdgpu_amdkfd_gpuvm_sync_memory(pdd->dev->adev, (struct kgd_mem *) mem, true); if (err) { pr_debug("Sync memory failed, wait interrupted by user signal\n"); goto sync_memory_failed; } + } + mutex_unlock(&p->mutex);
+ if (flush_tlb) { /* Flush TLBs after waiting for the page table updates to complete */ for (i = 0; i < args->n_devices; i++) { peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); @@ -1414,9 +1418,9 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, bind_process_to_device_failed: get_mem_obj_from_handle_failed: unmap_memory_from_gpu_failed: +sync_memory_failed: mutex_unlock(&p->mutex); copy_from_user_failed: -sync_memory_failed: kfree(devices_arr); return err; }