On Mon, 4 Dec 2023 18:33:00 +0100
Boris Brezillon <boris.brezillon@xxxxxxxxxxxxx> wrote:
> +/**
> + * panthor_vm_active() - Flag a VM as active
> + * @VM: VM to flag as active.
> + *
> + * Assigns an address space to a VM so it can be used by the GPU/MCU.
> + *
> + * Return: 0 on success, a negative error code otherwise.
> + */
> +int panthor_vm_active(struct panthor_vm *vm)
> +{
> + struct panthor_device *ptdev = vm->ptdev;
> + struct io_pgtable_cfg *cfg = &io_pgtable_ops_to_pgtable(vm->pgtbl_ops)->cfg;
> + int ret = 0, as, cookie;
> + u64 transtab, transcfg;
> +
> + if (!drm_dev_enter(&ptdev->base, &cookie))
> + return -ENODEV;
> +
> + mutex_lock(&ptdev->mmu->as.slots_lock);
> +
> + as = vm->as.id;
> + if (as >= 0) {
> + /* Unhandled pagefault on this AS, the MMU was disabled. We need to
> + * re-enable the MMU after clearing+unmasking the AS interrupts.
> + */
> + if (ptdev->mmu->as.faulty_mask & panthor_mmu_as_fault_mask(ptdev, as))
> + goto out_enable_as;
> +
When the context was idle and we make it active, we never remove the VM
from the LRU list, which might cause this AS to be re-assigned to
someone else while the GPU is still using the AS. I'll fix that along
the active_cnt issue I mentioned in my previous reply.
> + goto out_unlock;
> + }
> +
> + /* Check for a free AS */
> + if (vm->for_mcu) {
> + drm_WARN_ON(&ptdev->base, ptdev->mmu->as.alloc_mask & BIT(0));
> + as = 0;
> + } else {
> + as = ffz(ptdev->mmu->as.alloc_mask | BIT(0));
> + }
> +
> + if (!(BIT(as) & ptdev->gpu_info.as_present)) {
> + struct panthor_vm *lru_vm;
> +
> + lru_vm = list_first_entry_or_null(&ptdev->mmu->as.lru_list,
> + struct panthor_vm,
> + as.lru_node);
> + if (drm_WARN_ON(&ptdev->base, !lru_vm)) {
> + ret = -EBUSY;
> + goto out_unlock;
> + }
> +
> + list_del_init(&lru_vm->as.lru_node);
> + as = lru_vm->as.id;
> +
> + lru_vm->as.id = -1;
> + } else {
> + set_bit(as, &ptdev->mmu->as.alloc_mask);
> + }
> +
> + /* Assign the free or reclaimed AS to the FD */
> + vm->as.id = as;
> + ptdev->mmu->as.slots[as].vm = vm;
> +
> +out_enable_as:
> + transtab = cfg->arm_lpae_s1_cfg.ttbr;
> + transcfg = AS_TRANSCFG_PTW_MEMATTR_WB |
> + AS_TRANSCFG_PTW_RA |
> + AS_TRANSCFG_ADRMODE_AARCH64_4K;
> + if (ptdev->coherent)
> + transcfg |= AS_TRANSCFG_PTW_SH_OS;
> +
> + /* If the VM is re-activated, we clear the fault. */
> + vm->unhandled_fault = false;
> +
> + /* Unhandled pagefault on this AS, clear the fault and re-enable interrupts
> + * before enabling the AS.
> + */
> + if (ptdev->mmu->as.faulty_mask & panthor_mmu_as_fault_mask(ptdev, as)) {
> + gpu_write(ptdev, MMU_INT_CLEAR, panthor_mmu_as_fault_mask(ptdev, as));
> + ptdev->mmu->as.faulty_mask &= ~panthor_mmu_as_fault_mask(ptdev, as);
> + gpu_write(ptdev, MMU_INT_MASK, ~ptdev->mmu->as.faulty_mask);
> + }
> +
> + ret = panthor_mmu_as_enable(vm->ptdev, vm->as.id, transtab, transcfg, vm->memattr);
> +
> +out_unlock:
> + mutex_unlock(&ptdev->mmu->as.slots_lock);
> + drm_dev_exit(cookie);
> + return ret;
> +}
