static int handle_tprot(struct kvm_vcpu *vcpu) { u64 address1, address2; struct vm_area_struct *vma; unsigned long user_address; vcpu->stat.instruction_tprot++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); kvm_s390_get_base_disp_sse(vcpu, &address1, &address2); /* we only handle the Linux memory detection case: * access key == 0 * guest DAT == off * everything else goes to userspace. */ if (address2 & 0xf0) return -EOPNOTSUPP; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) return -EOPNOTSUPP; down_read(¤t->mm->mmap_sem); user_address = __gmap_translate(address1, vcpu->arch.gmap); if (IS_ERR_VALUE(user_address)) goto out_inject; vma = find_vma(current->mm, user_address); if (!vma) goto out_inject; vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); if (!(vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_READ)) vcpu->arch.sie_block->gpsw.mask |= (1ul << 44); if (!(vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_READ)) vcpu->arch.sie_block->gpsw.mask |= (2ul << 44); up_read(¤t->mm->mmap_sem); return 0; out_inject: up_read(¤t->mm->mmap_sem); return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); }
/* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate * routines. * * interruption code (int_code): * 04 Protection -> Write-Protection (suprression) * 10 Segment translation -> Not present (nullification) * 11 Page translation -> Not present (nullification) * 3b Region third trans. -> Not present (nullification) */ static inline int do_exception(struct pt_regs *regs, int access) { struct gmap *gmap; struct task_struct *tsk; struct mm_struct *mm; struct vm_area_struct *vma; enum fault_type type; unsigned long trans_exc_code; unsigned long address; unsigned int flags; int fault; tsk = current; /* * The instruction that caused the program check has * been nullified. Don't signal single step via SIGTRAP. */ clear_pt_regs_flag(regs, PIF_PER_TRAP); if (notify_page_fault(regs)) return 0; mm = tsk->mm; trans_exc_code = regs->int_parm_long; /* * Verify that the fault happened in user space, that * we are not in an interrupt and that there is a * user context. */ fault = VM_FAULT_BADCONTEXT; type = get_fault_type(regs); switch (type) { case KERNEL_FAULT: goto out; case VDSO_FAULT: fault = VM_FAULT_BADMAP; goto out; case USER_FAULT: case GMAP_FAULT: if (faulthandler_disabled() || !mm) goto out; break; } address = trans_exc_code & __FAIL_ADDR_MASK; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (user_mode(regs)) flags |= FAULT_FLAG_USER; if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400) flags |= FAULT_FLAG_WRITE; down_read(&mm->mmap_sem); gmap = NULL; if (IS_ENABLED(CONFIG_PGSTE) && type == GMAP_FAULT) { gmap = (struct gmap *) S390_lowcore.gmap; current->thread.gmap_addr = address; current->thread.gmap_write_flag = !!(flags & FAULT_FLAG_WRITE); current->thread.gmap_int_code = regs->int_code & 0xffff; address = __gmap_translate(gmap, address); if (address == -EFAULT) { fault = VM_FAULT_BADMAP; goto out_up; } if (gmap->pfault_enabled) flags |= FAULT_FLAG_RETRY_NOWAIT; } retry: fault = VM_FAULT_BADMAP; vma = find_vma(mm, address); if (!vma) goto out_up; if (unlikely(vma->vm_start > address)) { if (!(vma->vm_flags & VM_GROWSDOWN)) goto out_up; if (expand_stack(vma, address)) goto out_up; } /* * Ok, we have a good vm_area for this memory access, so * we can handle it.. */ fault = VM_FAULT_BADACCESS; if (unlikely(!(vma->vm_flags & access))) goto out_up; if (is_vm_hugetlb_page(vma)) address &= HPAGE_MASK; /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo * the fault. */ fault = handle_mm_fault(vma, address, flags); /* No reason to continue if interrupted by SIGKILL. */ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { fault = VM_FAULT_SIGNAL; goto out; } if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; /* * Major/minor page fault accounting is only done on the * initial attempt. If we go through a retry, it is extremely * likely that the page will be found in page cache at that point. */ if (flags & FAULT_FLAG_ALLOW_RETRY) { if (fault & VM_FAULT_MAJOR) { tsk->maj_flt++; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); } else { tsk->min_flt++; perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } if (fault & VM_FAULT_RETRY) { if (IS_ENABLED(CONFIG_PGSTE) && gmap && (flags & FAULT_FLAG_RETRY_NOWAIT)) { /* FAULT_FLAG_RETRY_NOWAIT has been set, * mmap_sem has not been released */ current->thread.gmap_pfault = 1; fault = VM_FAULT_PFAULT; goto out_up; } /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk * of starvation. */ flags &= ~(FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT); flags |= FAULT_FLAG_TRIED; down_read(&mm->mmap_sem); goto retry; } } if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, address); if (address == -EFAULT) { fault = VM_FAULT_BADMAP; goto out_up; } if (address == -ENOMEM) { fault = VM_FAULT_OOM; goto out_up; } } fault = 0; out_up: up_read(&mm->mmap_sem); out: return fault; }