1
Fork 0

Auto merge of #87123 - RalfJung:miri-provenance-overhaul, r=oli-obk

CTFE/Miri engine Pointer type overhaul

This fixes the long-standing problem that we are using `Scalar` as a type to represent pointers that might be integer values (since they point to a ZST). The main problem is that with int-to-ptr casts, there are multiple ways to represent the same pointer as a `Scalar` and it is unclear if "normalization" (i.e., the cast) already happened or not. This leads to ugly methods like `force_mplace_ptr` and `force_op_ptr`.
Another problem this solves is that in Miri, it would make a lot more sense to have the `Pointer::offset` field represent the full absolute address (instead of being relative to the `AllocId`). This means we can do ptr-to-int casts without access to any machine state, and it means that the overflow checks on pointer arithmetic are (finally!) accurate.

To solve this, the `Pointer` type is made entirely parametric over the provenance, so that we can use `Pointer<AllocId>` inside `Scalar` but use `Pointer<Option<AllocId>>` when accessing memory (where `None` represents the case that we could not figure out an `AllocId`; in that case the `offset` is an absolute address). Moreover, the `Provenance` trait determines if a pointer with a given provenance can be cast to an integer by simply dropping the provenance.

I hope this can be read commit-by-commit, but the first commit does the bulk of the work. It introduces some FIXMEs that are resolved later.
Fixes https://github.com/rust-lang/miri/issues/841
Miri PR: https://github.com/rust-lang/miri/pull/1851
r? `@oli-obk`
This commit is contained in:
bors 2021-07-17 15:26:27 +00:00
commit c78ebb7bdc
106 changed files with 1317 additions and 1407 deletions

View file

@ -243,8 +243,9 @@ impl ConstMethods<'tcx> for CodegenCx<'ll, 'tcx> {
self.const_bitcast(llval, llty)
}
}
Scalar::Ptr(ptr) => {
let (base_addr, base_addr_space) = match self.tcx.global_alloc(ptr.alloc_id) {
Scalar::Ptr(ptr, _size) => {
let (alloc_id, offset) = ptr.into_parts();
let (base_addr, base_addr_space) = match self.tcx.global_alloc(alloc_id) {
GlobalAlloc::Memory(alloc) => {
let init = const_alloc_to_llvm(self, alloc);
let value = match alloc.mutability {
@ -252,7 +253,7 @@ impl ConstMethods<'tcx> for CodegenCx<'ll, 'tcx> {
_ => self.static_addr_of(init, alloc.align, None),
};
if !self.sess().fewer_names() {
llvm::set_value_name(value, format!("{:?}", ptr.alloc_id).as_bytes());
llvm::set_value_name(value, format!("{:?}", alloc_id).as_bytes());
}
(value, AddressSpace::DATA)
}
@ -269,7 +270,7 @@ impl ConstMethods<'tcx> for CodegenCx<'ll, 'tcx> {
let llval = unsafe {
llvm::LLVMConstInBoundsGEP(
self.const_bitcast(base_addr, self.type_i8p_ext(base_addr_space)),
&self.const_usize(ptr.offset.bytes()),
&self.const_usize(offset.bytes()),
1,
)
};

View file

@ -11,7 +11,7 @@ use rustc_codegen_ssa::traits::*;
use rustc_hir::def_id::DefId;
use rustc_middle::middle::codegen_fn_attrs::{CodegenFnAttrFlags, CodegenFnAttrs};
use rustc_middle::mir::interpret::{
read_target_uint, Allocation, ErrorHandled, GlobalAlloc, Pointer,
read_target_uint, Allocation, ErrorHandled, GlobalAlloc, Pointer, Scalar as InterpScalar,
};
use rustc_middle::mir::mono::MonoItem;
use rustc_middle::ty::{self, Instance, Ty};
@ -25,7 +25,7 @@ pub fn const_alloc_to_llvm(cx: &CodegenCx<'ll, '_>, alloc: &Allocation) -> &'ll
let pointer_size = dl.pointer_size.bytes() as usize;
let mut next_offset = 0;
for &(offset, ((), alloc_id)) in alloc.relocations().iter() {
for &(offset, alloc_id) in alloc.relocations().iter() {
let offset = offset.bytes();
assert_eq!(offset as usize as u64, offset);
let offset = offset as usize;
@ -55,7 +55,10 @@ pub fn const_alloc_to_llvm(cx: &CodegenCx<'ll, '_>, alloc: &Allocation) -> &'ll
};
llvals.push(cx.scalar_to_backend(
Pointer::new(alloc_id, Size::from_bytes(ptr_offset)).into(),
InterpScalar::from_pointer(
Pointer::new(alloc_id, Size::from_bytes(ptr_offset)),
&cx.tcx,
),
&Scalar { value: Primitive::Pointer, valid_range: 0..=!0 },
cx.type_i8p_ext(address_space),
));