@@ -189,6 +189,7 @@ extern uint amdgpu_force_long_training;
extern int amdgpu_lbpw;
extern int amdgpu_compute_multipipe;
extern int amdgpu_gpu_recovery;
+extern bool amdgpu_soft_recovery;
extern int amdgpu_emu_mode;
extern uint amdgpu_smu_memory_pool_size;
extern int amdgpu_smu_pptable_id;
@@ -163,6 +163,7 @@ uint amdgpu_force_long_training;
int amdgpu_lbpw = -1;
int amdgpu_compute_multipipe = -1;
int amdgpu_gpu_recovery = -1; /* auto */
+bool amdgpu_soft_recovery = true;
int amdgpu_emu_mode;
uint amdgpu_smu_memory_pool_size;
int amdgpu_smu_pptable_id = -1;
@@ -540,6 +541,14 @@ module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444);
MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto)");
module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444);
+/**
+ * DOC: gpu_soft_recovery (bool)
+ * Set true to allow the driver to try soft recoveries if a job get stuck. Set
+ * to false to always force a GPU reset during recovery.
+ */
+MODULE_PARM_DESC(gpu_soft_recovery, "Enable GPU soft recovery mechanism (default: true)");
+module_param_named(gpu_soft_recovery, amdgpu_soft_recovery, bool, 0644);
+
/**
* DOC: emu_mode (int)
* Set value 1 to enable emulation mode. This is only needed when running on an emulator. The default is 0 (disabled).
@@ -434,8 +434,12 @@ bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid,
struct dma_fence *fence)
{
unsigned long flags;
+ ktime_t deadline;
- ktime_t deadline = ktime_add_us(ktime_get(), 10000);
+ if (!amdgpu_soft_recovery)
+ return false;
+
+ deadline = ktime_add_us(ktime_get(), 10000);
if (amdgpu_sriov_vf(ring->adev) || !ring->funcs->soft_recovery || !fence)
return false;
Create a module parameter to disable soft recoveries on amdgpu, making every recovery go through the device reset path. This option makes easier to force device resets for testing and debugging purposes. Signed-off-by: André Almeida <andrealmeid@igalia.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 9 +++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 6 +++++- 3 files changed, 15 insertions(+), 1 deletion(-)