MES userqueues bypass amdgpu_vm_flush(), so a reservation granted to a userqueue never got its VMID's page table programmed. Add amdgpu_vm_spm_update(), called from amdgpu_vm_validate(), to bind the fixed SPM VMID's page-table-base to the reserving VM's root PD when that VM holds the reservation; it is a no-op for every other VM. amdgpu_vmid_free_reserved() unbinds it directly to a dummy address under the same lock that clears the reservation, so stray SPM accesses fault instead of racing a new reservation's binding.
Signed-off-by: Sunil Khatri <[email protected]> --- drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 6 ++++ drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 37 +++++++++++++++++++++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 1 + 3 files changed, 44 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index 992f7cb3a3102..0ad94b09c6b46 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -581,6 +581,12 @@ void amdgpu_vmid_free_reserved(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (vm->reserved_vmid[vmhub]) { vm->reserved_vmid[vmhub] = NULL; id_mgr->reserved_vmid = false; + + if (adev->vm_manager.spm_vmid && adev->gfxhub.funcs) { + adev->gfxhub.funcs->setup_vm_pt_regs(adev, adev->vm_manager.spm_vmid, 0); + amdgpu_gmc_flush_gpu_tlb(adev, adev->vm_manager.spm_vmid, + AMDGPU_GFXHUB(0), TLB_FLUSH_LEGACY); + } } mutex_unlock(&id_mgr->lock); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index de992405ed718..3967dadb8d425 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -568,6 +568,41 @@ uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm) return result; } +/** + * amdgpu_vm_spm_update - bind the SPM VMID's page table base to @vm + * + * @adev: amdgpu device pointer + * @vm: vm to check against the SPM reservation + * + * The SPM VMID is fixed (adev->vm_manager.spm_vmid), so its page-table-base + * register must track whichever VM currently holds the reservation instead + * of being set per-job like a normal VMID. Bind it to @vm's real root PD + * address if @vm holds the reservation; otherwise do nothing, since @vm is + * not the one that could legitimately change the current binding. + */ +void amdgpu_vm_spm_update(struct amdgpu_device *adev, struct amdgpu_vm *vm) +{ + struct amdgpu_kq_vmid_mgr *id_mgr = + &adev->vm_manager.id_mgr[AMDGPU_GFXHUB(0)]; + uint64_t pd_addr; + + if (!adev->vm_manager.spm_vmid || !adev->gfxhub.funcs) + return; + + mutex_lock(&id_mgr->lock); + if (vm->reserved_vmid[AMDGPU_GFXHUB(0)] != + &id_mgr->ids[adev->vm_manager.spm_vmid] || !vm->root.bo) { + mutex_unlock(&id_mgr->lock); + return; + } + + pd_addr = amdgpu_gmc_pd_addr(vm->root.bo); + adev->gfxhub.funcs->setup_vm_pt_regs(adev, adev->vm_manager.spm_vmid, pd_addr); + amdgpu_gmc_flush_gpu_tlb(adev, adev->vm_manager.spm_vmid, AMDGPU_GFXHUB(0), + TLB_FLUSH_LEGACY); + mutex_unlock(&id_mgr->lock); +} + /** * amdgpu_vm_validate - validate evicted BOs tracked in the VM * @@ -630,6 +665,8 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, amdgpu_vm_bo_needs_update(bo_base); } + amdgpu_vm_spm_update(adev, vm); + if (!ticket) return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index b8aa45db1d844..2a2a2ccbaa2cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -443,6 +443,7 @@ int amdgpu_vm_lock_individual(struct amdgpu_vm *vm, struct drm_exec *exec, unsigned int num_fences); bool amdgpu_vm_ready(struct amdgpu_vm *vm); uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm); +void amdgpu_vm_spm_update(struct amdgpu_device *adev, struct amdgpu_vm *vm); int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket, int (*callback)(void *p, struct amdgpu_bo *bo), -- 2.34.1
