enum AMDGPU_DEBUG_MASK {
AMDGPU_DEBUG_VM = BIT(0),
AMDGPU_DEBUG_LARGEBAR = BIT(1),
+ AMDGPU_DEBUG_DISABLE_GPU_SOFT_RECOVERY = BIT(2),
};
unsigned int amdgpu_vram_limit = UINT_MAX;
* - 0x2: Enable simulating large-bar capability on non-large bar system. This
* limits the VRAM size reported to ROCm applications to the visible
* size, usually 256MB.
+ * - 0x4: Disable GPU soft recovery, always do a full reset
*/
MODULE_PARM_DESC(debug_mask, "debug options for amdgpu, disabled by default");
module_param_named(debug_mask, amdgpu_debug_mask, uint, 0444);
pr_info("debug: enabled simulating large-bar capability on non-large bar system\n");
adev->debug_largebar = true;
}
+
+ if (amdgpu_debug_mask & AMDGPU_DEBUG_DISABLE_GPU_SOFT_RECOVERY) {
+ pr_info("debug: soft reset for GPU recovery disabled\n");
+ adev->debug_disable_soft_recovery = true;
+ }
}
static int amdgpu_pci_probe(struct pci_dev *pdev,
struct dma_fence *fence)
{
unsigned long flags;
+ ktime_t deadline;
- ktime_t deadline = ktime_add_us(ktime_get(), 10000);
+ if (unlikely(ring->adev->debug_disable_soft_recovery))
+ return false;
+
+ deadline = ktime_add_us(ktime_get(), 10000);
if (amdgpu_sriov_vf(ring->adev) || !ring->funcs->soft_recovery || !fence)
return false;