drm/amdgpu: rework how we handle TLB fences

Add a new VM flag to indicate whether or not we need
a TLB fence.  Userqs (KFD or KGD) require a TLB fence.
A TLB fence is not strictly required for kernel queues,
but it shouldn't hurt.  That said, enabling this
unconditionally should be fine, but it seems to tickle
some issues in KIQ/MES.  Only enable them for KFD,
or when KGD userq queues are enabled (currently via module
parameter).

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4798
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4749
Fixes: f3854e04b708 ("drm/amdgpu: attach tlb fence to the PTs update")
Cc: Christian König <christian.koenig@amd.com>
Cc: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Prike Liang <Prike.Liang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 69c5fbd2b93b5ced77c6e79afe83371bca84c788)
Cc: stable@vger.kernel.org

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index f2beb980e3c3af0841fe412df3740aaea8776f2f..c60cbce356cfefa9eddf4dcdf40709e2d493c078 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1069,7 +1069,10 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params,
        }
 
        /* Prepare a TLB flush fence to be attached to PTs */
-       if (!params->unlocked) {
+       /* The check for need_tlb_fence should be dropped once we
+        * sort out the issues with KIQ/MES TLB invalidation timeouts.
+        */
+       if (!params->unlocked && vm->need_tlb_fence) {
                amdgpu_vm_tlb_fence_create(params->adev, vm, fence);
 
                /* Makes sure no PD/PT is freed before the flush */
@@ -2602,6 +2605,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
        ttm_lru_bulk_move_init(&vm->lru_bulk_move);
 
        vm->is_compute_context = false;
+       vm->need_tlb_fence = amdgpu_userq_enabled(&adev->ddev);
 
        vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &
                                    AMDGPU_VM_USE_CPU_FOR_GFX);
@@ -2739,6 +2743,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
        dma_fence_put(vm->last_update);
        vm->last_update = dma_fence_get_stub();
        vm->is_compute_context = true;
+       vm->need_tlb_fence = true;
 
 unreserve_bo:
        amdgpu_bo_unreserve(vm->root.bo);

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 806d62ed61efff7be545ac3419e2657aa27704fe..bb276c0ad06dd667e50b46f3d97779361b1791d9 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -441,6 +441,8 @@ struct amdgpu_vm {
        struct ttm_lru_bulk_move lru_bulk_move;
        /* Flag to indicate if VM is used for compute */
        bool                    is_compute_context;
+       /* Flag to indicate if VM needs a TLB fence (KFD or KGD) */
+       bool                    need_tlb_fence;
 
        /* Memory partition number, -1 means any partition */
        int8_t                  mem_id;