From fd65d1742992361fc2201ecb4e43411e6e417fcb Mon Sep 17 00:00:00 2001 From: Jesse Zhang Date: Thu, 13 Aug 2026 12:28:04 +0800 Subject: [PATCH] drm/amdgpu: force complete the KIQ ring fences on reset Like the MES scheduler ring, the KIQ ring sets no_scheduler = true and uses a polling fence, so it is skipped by the force-completion loop in amdgpu_device_pre_asic_reset(). Its hw fence value lives in wb (GTT) memory and survives a MODE1 reset while fence_drv.sync_seq keeps advancing, so after a reset the first KIQ submission can poll forever on a seq that is never written back. Force complete the KIQ ring fences too so their hw fence is realigned to sync_seq. Cc: stable@vger.kernel.org Reviewed-by: Alex Deucher Suggested-by: Alex Deucher Signed-off-by: Jesse Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index be4c74491554..0b7cdea4b9e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5056,6 +5056,18 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, amdgpu_fence_driver_force_completion(mes_ring, fence); } + /* + * KIQ rings are polling-fence/no_scheduler like MES, so realign their + * fence too (one ring per XCC), otherwise the first post-reset KIQ + * submission polls forever on a stale seq. + */ + for (i = 0; i < AMDGPU_MAX_GC_INSTANCES; i++) { + struct amdgpu_ring *kiq_ring = &adev->gfx.kiq[i].ring; + + if (kiq_ring->fence_drv.initialized && kiq_ring->sched.ready) + amdgpu_fence_driver_force_completion(kiq_ring, fence); + } + amdgpu_fence_driver_isr_toggle(adev, false); r = amdgpu_reset_prepare_hwcontext(adev, reset_context);