rust/src/librustc_codegen_llvm/common.rs

400 lines
13 KiB
Rust
Raw Normal View History

// Copyright 2012-2014 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
#![allow(non_camel_case_types, non_snake_case)]
2018-05-08 08:10:16 -05:00
//! Code that is useful in various codegen modules.
use llvm::{self, True, False, Bool, BasicBlock, OperandBundleDef};
use abi;
use consts;
use type_::Type;
use type_of::LayoutLlvmExt;
use value::Value;
use rustc_codegen_ssa::traits::*;
use rustc::ty::layout::{HasDataLayout, LayoutOf, self, TyLayout, Size};
use rustc::mir::interpret::{Scalar, AllocType, Allocation};
use consts::const_alloc_to_llvm;
use rustc_codegen_ssa::mir::place::PlaceRef;
use libc::{c_uint, c_char};
2016-02-23 13:57:22 -06:00
use syntax::symbol::LocalInternedString;
use syntax::ast::Mutability;
pub use context::CodegenCx;
2013-06-12 21:02:33 -05:00
/*
* A note on nomenclature of linking: "extern", "foreign", and "upcall".
*
* An "extern" is an LLVM symbol we wind up emitting an undefined external
* reference to. This means "we don't have the thing in this compilation unit,
* please make sure you link it in at runtime". This could be a reference to
* C code found in a C library, or rust code found in a rust crate.
*
* Most "externs" are implicitly declared (automatically) as a result of a
* user declaring an extern _module_ dependency; this causes the rust driver
* to locate an extern crate, scan its compilation metadata, and emit extern
* declarations for any symbols used by the declaring crate.
*
* A "foreign" is an extern that references C (or other non-rust ABI) code.
* There is no metadata to scan for extern references so in these cases either
* a header-digester like bindgen, or manual function prototypes, have to
* serve as declarators. So these are usually given explicitly as prototype
* declarations, in rust code, with ABI attributes on them noting which ABI to
* link via.
*
* An "upcall" is a foreign call generated by the compiler (not corresponding
* to any user-written call in the code) into the runtime library, to perform
* some helper task such as bringing a task to life, allocating memory, etc.
*
*/
trans: Reimplement unwinding on MSVC This commit transitions the compiler to using the new exception handling instructions in LLVM for implementing unwinding for MSVC. This affects both 32 and 64-bit MSVC as they're both now using SEH-based strategies. In terms of standard library support, lots more details about how SEH unwinding is implemented can be found in the commits. In terms of trans, this change necessitated a few modifications: * Branches were added to detect when the old landingpad instruction is used or the new cleanuppad instruction is used to `trans::cleanup`. * The return value from `cleanuppad` is not stored in an `alloca` (because it cannot be). * Each block in trans now has an `Option<LandingPad>` instead of `is_lpad: bool` for indicating whether it's in a landing pad or not. The new exception handling intrinsics require that on MSVC each `call` inside of a landing pad is annotated with which landing pad that it's in. This change to the basic block means that whenever a `call` or `invoke` instruction is generated we know whether to annotate it as part of a cleanuppad or not. * Lots of modifications were made to the instruction builders to construct the new instructions as well as pass the tagging information for the call/invoke instructions. * The translation of the `try` intrinsics for MSVC has been overhauled to use the new `catchpad` instruction. The filter function is now also a rustc-generated function instead of a purely libstd-defined function. The libstd definition still exists, it just has a stable ABI across architectures and leaves some of the really weird implementation details to the compiler (e.g. the `localescape` and `localrecover` intrinsics).
2015-10-23 20:18:44 -05:00
/// A structure representing an active landing pad for the duration of a basic
/// block.
///
/// Each `Block` may contain an instance of this, indicating whether the block
/// is part of a landing pad or not. This is used to make decision about whether
/// to emit `invoke` instructions (e.g. in a landing pad we don't continue to
/// use `invoke`) and also about various function call metadata.
///
/// For GNU exceptions (`landingpad` + `resume` instructions) this structure is
/// just a bunch of `None` instances (not too interesting), but for MSVC
/// exceptions (`cleanuppad` + `cleanupret` instructions) this contains data.
/// When inside of a landing pad, each function call in LLVM IR needs to be
/// annotated with which landing pad it's a part of. This is accomplished via
/// the `OperandBundleDef` value created for MSVC landing pads.
pub struct Funclet<'ll> {
cleanuppad: &'ll Value,
operand: OperandBundleDef<'ll>,
trans: Reimplement unwinding on MSVC This commit transitions the compiler to using the new exception handling instructions in LLVM for implementing unwinding for MSVC. This affects both 32 and 64-bit MSVC as they're both now using SEH-based strategies. In terms of standard library support, lots more details about how SEH unwinding is implemented can be found in the commits. In terms of trans, this change necessitated a few modifications: * Branches were added to detect when the old landingpad instruction is used or the new cleanuppad instruction is used to `trans::cleanup`. * The return value from `cleanuppad` is not stored in an `alloca` (because it cannot be). * Each block in trans now has an `Option<LandingPad>` instead of `is_lpad: bool` for indicating whether it's in a landing pad or not. The new exception handling intrinsics require that on MSVC each `call` inside of a landing pad is annotated with which landing pad that it's in. This change to the basic block means that whenever a `call` or `invoke` instruction is generated we know whether to annotate it as part of a cleanuppad or not. * Lots of modifications were made to the instruction builders to construct the new instructions as well as pass the tagging information for the call/invoke instructions. * The translation of the `try` intrinsics for MSVC has been overhauled to use the new `catchpad` instruction. The filter function is now also a rustc-generated function instead of a purely libstd-defined function. The libstd definition still exists, it just has a stable ABI across architectures and leaves some of the really weird implementation details to the compiler (e.g. the `localescape` and `localrecover` intrinsics).
2015-10-23 20:18:44 -05:00
}
impl Funclet<'ll> {
pub fn new(cleanuppad: &'ll Value) -> Self {
Funclet {
cleanuppad,
operand: OperandBundleDef::new("funclet", &[cleanuppad]),
}
trans: Reimplement unwinding on MSVC This commit transitions the compiler to using the new exception handling instructions in LLVM for implementing unwinding for MSVC. This affects both 32 and 64-bit MSVC as they're both now using SEH-based strategies. In terms of standard library support, lots more details about how SEH unwinding is implemented can be found in the commits. In terms of trans, this change necessitated a few modifications: * Branches were added to detect when the old landingpad instruction is used or the new cleanuppad instruction is used to `trans::cleanup`. * The return value from `cleanuppad` is not stored in an `alloca` (because it cannot be). * Each block in trans now has an `Option<LandingPad>` instead of `is_lpad: bool` for indicating whether it's in a landing pad or not. The new exception handling intrinsics require that on MSVC each `call` inside of a landing pad is annotated with which landing pad that it's in. This change to the basic block means that whenever a `call` or `invoke` instruction is generated we know whether to annotate it as part of a cleanuppad or not. * Lots of modifications were made to the instruction builders to construct the new instructions as well as pass the tagging information for the call/invoke instructions. * The translation of the `try` intrinsics for MSVC has been overhauled to use the new `catchpad` instruction. The filter function is now also a rustc-generated function instead of a purely libstd-defined function. The libstd definition still exists, it just has a stable ABI across architectures and leaves some of the really weird implementation details to the compiler (e.g. the `localescape` and `localrecover` intrinsics).
2015-10-23 20:18:44 -05:00
}
pub fn cleanuppad(&self) -> &'ll Value {
self.cleanuppad
trans: Reimplement unwinding on MSVC This commit transitions the compiler to using the new exception handling instructions in LLVM for implementing unwinding for MSVC. This affects both 32 and 64-bit MSVC as they're both now using SEH-based strategies. In terms of standard library support, lots more details about how SEH unwinding is implemented can be found in the commits. In terms of trans, this change necessitated a few modifications: * Branches were added to detect when the old landingpad instruction is used or the new cleanuppad instruction is used to `trans::cleanup`. * The return value from `cleanuppad` is not stored in an `alloca` (because it cannot be). * Each block in trans now has an `Option<LandingPad>` instead of `is_lpad: bool` for indicating whether it's in a landing pad or not. The new exception handling intrinsics require that on MSVC each `call` inside of a landing pad is annotated with which landing pad that it's in. This change to the basic block means that whenever a `call` or `invoke` instruction is generated we know whether to annotate it as part of a cleanuppad or not. * Lots of modifications were made to the instruction builders to construct the new instructions as well as pass the tagging information for the call/invoke instructions. * The translation of the `try` intrinsics for MSVC has been overhauled to use the new `catchpad` instruction. The filter function is now also a rustc-generated function instead of a purely libstd-defined function. The libstd definition still exists, it just has a stable ABI across architectures and leaves some of the really weird implementation details to the compiler (e.g. the `localescape` and `localrecover` intrinsics).
2015-10-23 20:18:44 -05:00
}
pub fn bundle(&self) -> &OperandBundleDef<'ll> {
&self.operand
}
trans: Reimplement unwinding on MSVC This commit transitions the compiler to using the new exception handling instructions in LLVM for implementing unwinding for MSVC. This affects both 32 and 64-bit MSVC as they're both now using SEH-based strategies. In terms of standard library support, lots more details about how SEH unwinding is implemented can be found in the commits. In terms of trans, this change necessitated a few modifications: * Branches were added to detect when the old landingpad instruction is used or the new cleanuppad instruction is used to `trans::cleanup`. * The return value from `cleanuppad` is not stored in an `alloca` (because it cannot be). * Each block in trans now has an `Option<LandingPad>` instead of `is_lpad: bool` for indicating whether it's in a landing pad or not. The new exception handling intrinsics require that on MSVC each `call` inside of a landing pad is annotated with which landing pad that it's in. This change to the basic block means that whenever a `call` or `invoke` instruction is generated we know whether to annotate it as part of a cleanuppad or not. * Lots of modifications were made to the instruction builders to construct the new instructions as well as pass the tagging information for the call/invoke instructions. * The translation of the `try` intrinsics for MSVC has been overhauled to use the new `catchpad` instruction. The filter function is now also a rustc-generated function instead of a purely libstd-defined function. The libstd definition still exists, it just has a stable ABI across architectures and leaves some of the really weird implementation details to the compiler (e.g. the `localescape` and `localrecover` intrinsics).
2015-10-23 20:18:44 -05:00
}
2018-09-13 07:58:19 -05:00
impl BackendTypes for CodegenCx<'ll, 'tcx> {
2018-08-28 10:03:46 -05:00
type Value = &'ll Value;
type BasicBlock = &'ll BasicBlock;
type Type = &'ll Type;
type Funclet = Funclet<'ll>;
type DIScope = &'ll llvm::debuginfo::DIScope;
}
2018-09-13 07:58:19 -05:00
impl ConstMethods<'tcx> for CodegenCx<'ll, 'tcx> {
fn const_null(&self, t: &'ll Type) -> &'ll Value {
2018-08-28 10:03:46 -05:00
unsafe {
llvm::LLVMConstNull(t)
}
}
fn const_undef(&self, t: &'ll Type) -> &'ll Value {
2018-08-28 10:03:46 -05:00
unsafe {
llvm::LLVMGetUndef(t)
}
}
fn const_int(&self, t: &'ll Type, i: i64) -> &'ll Value {
2018-08-28 10:03:46 -05:00
unsafe {
llvm::LLVMConstInt(t, i as u64, True)
}
}
fn const_uint(&self, t: &'ll Type, i: u64) -> &'ll Value {
2018-08-28 10:03:46 -05:00
unsafe {
llvm::LLVMConstInt(t, i, False)
}
}
fn const_uint_big(&self, t: &'ll Type, u: u128) -> &'ll Value {
2018-08-28 10:03:46 -05:00
unsafe {
let words = [u as u64, (u >> 64) as u64];
llvm::LLVMConstIntOfArbitraryPrecision(t, 2, words.as_ptr())
}
}
fn const_bool(&self, val: bool) -> &'ll Value {
2018-11-07 04:08:41 -06:00
self.const_uint(self.type_i1(), val as u64)
}
fn const_i32(&self, i: i32) -> &'ll Value {
2018-11-07 04:08:41 -06:00
self.const_int(self.type_i32(), i as i64)
2018-08-28 10:03:46 -05:00
}
fn const_u32(&self, i: u32) -> &'ll Value {
2018-11-07 04:08:41 -06:00
self.const_uint(self.type_i32(), i as u64)
2018-08-28 10:03:46 -05:00
}
fn const_u64(&self, i: u64) -> &'ll Value {
2018-11-07 04:08:41 -06:00
self.const_uint(self.type_i64(), i)
2018-08-28 10:03:46 -05:00
}
fn const_usize(&self, i: u64) -> &'ll Value {
2018-08-28 10:03:46 -05:00
let bit_size = self.data_layout().pointer_size.bits();
if bit_size < 64 {
// make sure it doesn't overflow
assert!(i < (1<<bit_size));
}
2018-11-07 04:08:41 -06:00
self.const_uint(self.isize_ty, i)
}
fn const_u8(&self, i: u8) -> &'ll Value {
2018-11-07 04:08:41 -06:00
self.const_uint(self.type_i8(), i as u64)
2018-08-28 10:03:46 -05:00
}
fn const_cstr(
2018-08-28 10:03:46 -05:00
&self,
s: LocalInternedString,
null_terminated: bool,
) -> &'ll Value {
unsafe {
2018-11-07 04:08:41 -06:00
if let Some(&llval) = self.const_cstr_cache.borrow().get(&s) {
2018-08-28 10:03:46 -05:00
return llval;
}
2018-11-07 04:08:41 -06:00
let sc = llvm::LLVMConstStringInContext(self.llcx,
2018-08-28 10:03:46 -05:00
s.as_ptr() as *const c_char,
s.len() as c_uint,
!null_terminated as Bool);
2018-11-07 04:08:41 -06:00
let sym = self.generate_local_symbol_name("str");
let g = self.define_global(&sym[..], self.val_ty(sc)).unwrap_or_else(||{
2018-08-28 10:03:46 -05:00
bug!("symbol `{}` is already defined", sym);
});
llvm::LLVMSetInitializer(g, sc);
llvm::LLVMSetGlobalConstant(g, True);
llvm::LLVMRustSetLinkage(g, llvm::Linkage::InternalLinkage);
2018-11-07 04:08:41 -06:00
self.const_cstr_cache.borrow_mut().insert(s, g);
2018-08-28 10:03:46 -05:00
g
}
}
fn const_str_slice(&self, s: LocalInternedString) -> &'ll Value {
2018-08-28 10:03:46 -05:00
let len = s.len();
2018-11-07 04:08:41 -06:00
let cs = consts::ptrcast(self.const_cstr(s, false),
2018-09-13 07:58:19 -05:00
self.type_ptr_to(self.layout_of(self.tcx.mk_str()).llvm_type(self)));
2018-11-07 04:08:41 -06:00
self.const_fat_ptr(cs, self.const_usize(len as u64))
}
2011-08-04 12:46:10 -05:00
fn const_fat_ptr(
2018-08-28 10:03:46 -05:00
&self,
ptr: &'ll Value,
meta: &'ll Value
) -> &'ll Value {
assert_eq!(abi::FAT_PTR_ADDR, 0);
assert_eq!(abi::FAT_PTR_EXTRA, 1);
2018-11-07 04:08:41 -06:00
self.const_struct(&[ptr, meta], false)
}
fn const_struct(
2018-08-28 10:03:46 -05:00
&self,
elts: &[&'ll Value],
packed: bool
) -> &'ll Value {
2018-11-07 04:08:41 -06:00
struct_in_context(self.llcx, elts, packed)
}
fn const_array(&self, ty: &'ll Type, elts: &[&'ll Value]) -> &'ll Value {
2018-08-28 10:03:46 -05:00
unsafe {
return llvm::LLVMConstArray(ty, elts.as_ptr(), elts.len() as c_uint);
}
}
fn const_vector(&self, elts: &[&'ll Value]) -> &'ll Value {
2018-08-28 10:03:46 -05:00
unsafe {
return llvm::LLVMConstVector(elts.as_ptr(), elts.len() as c_uint);
}
}
fn const_bytes(&self, bytes: &[u8]) -> &'ll Value {
2018-11-07 04:08:41 -06:00
bytes_in_context(self.llcx, bytes)
}
fn const_get_elt(&self, v: &'ll Value, idx: u64) -> &'ll Value {
2018-08-28 10:03:46 -05:00
unsafe {
assert_eq!(idx as c_uint as u64, idx);
let us = &[idx as c_uint];
let r = llvm::LLVMConstExtractValue(v, us.as_ptr(), us.len() as c_uint);
debug!("const_get_elt(v={:?}, idx={}, r={:?})",
v, idx, r);
r
}
}
fn const_get_real(&self, v: &'ll Value) -> Option<(f64, bool)> {
2018-08-28 10:03:46 -05:00
unsafe {
if self.is_const_real(v) {
2018-08-28 10:03:46 -05:00
let mut loses_info: llvm::Bool = ::std::mem::uninitialized();
let r = llvm::LLVMConstRealGetDouble(v, &mut loses_info);
let loses_info = if loses_info == 1 { true } else { false };
Some((r, loses_info))
} else {
None
}
}
}
fn const_to_uint(&self, v: &'ll Value) -> u64 {
2018-08-28 10:03:46 -05:00
unsafe {
llvm::LLVMConstIntGetZExtValue(v)
}
2018-03-15 10:36:02 -05:00
}
fn is_const_integral(&self, v: &'ll Value) -> bool {
2018-08-28 10:03:46 -05:00
unsafe {
llvm::LLVMIsAConstantInt(v).is_some()
}
}
2018-03-15 10:36:02 -05:00
fn is_const_real(&self, v: &'ll Value) -> bool {
2018-08-28 10:03:46 -05:00
unsafe {
llvm::LLVMIsAConstantFP(v).is_some()
}
}
fn const_to_opt_u128(&self, v: &'ll Value, sign_ext: bool) -> Option<u128> {
2018-08-28 10:03:46 -05:00
unsafe {
if self.is_const_integral(v) {
2018-08-28 10:03:46 -05:00
let (mut lo, mut hi) = (0u64, 0u64);
let success = llvm::LLVMRustConstInt128Get(v, sign_ext,
&mut hi, &mut lo);
if success {
Some(hi_lo_to_u128(lo, hi))
} else {
None
}
} else {
None
}
}
}
fn scalar_to_backend(
&self,
cv: Scalar,
layout: &layout::Scalar,
llty: &'ll Type,
) -> &'ll Value {
let bitsize = if layout.is_bool() { 1 } else { layout.value.size(self).bits() };
match cv {
Scalar::Bits { size: 0, .. } => {
assert_eq!(0, layout.value.size(self).bytes());
self.const_undef(self.type_ix(0))
},
Scalar::Bits { bits, size } => {
assert_eq!(size as u64, layout.value.size(self).bytes());
let llval = self.const_uint_big(self.type_ix(bitsize), bits);
if layout.value == layout::Pointer {
unsafe { llvm::LLVMConstIntToPtr(llval, llty) }
} else {
self.static_bitcast(llval, llty)
}
},
Scalar::Ptr(ptr) => {
let alloc_type = self.tcx.alloc_map.lock().get(ptr.alloc_id);
let base_addr = match alloc_type {
Some(AllocType::Memory(alloc)) => {
let init = const_alloc_to_llvm(self, alloc);
if alloc.mutability == Mutability::Mutable {
self.static_addr_of_mut(init, alloc.align, None)
} else {
self.static_addr_of(init, alloc.align, None)
}
}
Some(AllocType::Function(fn_instance)) => {
self.get_fn(fn_instance)
}
Some(AllocType::Static(def_id)) => {
assert!(self.tcx.is_static(def_id).is_some());
self.get_static(def_id)
}
None => bug!("missing allocation {:?}", ptr.alloc_id),
};
let llval = unsafe { llvm::LLVMConstInBoundsGEP(
self.static_bitcast(base_addr, self.type_i8p()),
&self.const_usize(ptr.offset.bytes()),
1,
) };
if layout.value != layout::Pointer {
unsafe { llvm::LLVMConstPtrToInt(llval, llty) }
} else {
self.static_bitcast(llval, llty)
}
}
}
}
fn from_const_alloc(
&self,
layout: TyLayout<'tcx>,
alloc: &Allocation,
offset: Size,
) -> PlaceRef<'tcx, &'ll Value> {
let init = const_alloc_to_llvm(self, alloc);
let base_addr = self.static_addr_of(init, layout.align.abi, None);
let llval = unsafe { llvm::LLVMConstInBoundsGEP(
self.static_bitcast(base_addr, self.type_i8p()),
&self.const_usize(offset.bytes()),
1,
)};
let llval = self.static_bitcast(llval, self.type_ptr_to(layout.llvm_type(self)));
PlaceRef::new_sized(llval, layout, alloc.align)
}
}
pub fn val_ty(v: &'ll Value) -> &'ll Type {
unsafe {
llvm::LLVMTypeOf(v)
}
}
pub fn bytes_in_context(llcx: &'ll llvm::Context, bytes: &[u8]) -> &'ll Value {
unsafe {
let ptr = bytes.as_ptr() as *const c_char;
return llvm::LLVMConstStringInContext(llcx, ptr, bytes.len() as c_uint, True);
}
}
pub fn struct_in_context(
llcx: &'a llvm::Context,
elts: &[&'a Value],
packed: bool,
) -> &'a Value {
unsafe {
llvm::LLVMConstStructInContext(llcx,
elts.as_ptr(), elts.len() as c_uint,
packed as Bool)
}
}
2018-08-28 10:03:46 -05:00
#[inline]
fn hi_lo_to_u128(lo: u64, hi: u64) -> u128 {
((hi as u128) << 64) | (lo as u128)
}