Auto merge of #143182 - xdoardo:more-addrspace, r=workingjubilee

Allow custom default address spaces and parse `p-` specifications in the datalayout string

Some targets, such as CHERI, use as default an address space different from the "normal" default address space `0` (in the case of CHERI, [200 is used](https://www.cl.cam.ac.uk/techreports/UCAM-CL-TR-877.pdf)). Currently, `rustc` does not allow to specify custom address spaces and does not take into consideration [`p-` specifications in the datalayout string](https://llvm.org/docs/LangRef.html#langref-datalayout).

This patch tries to mitigate these problems by allowing targets to define a custom default address space (while keeping the default value to address space `0`) and adding the code to parse the `p-` specifications in `rustc_abi`. The main changes are that `TargetDataLayout` now uses functions to refer to pointer-related informations, instead of having specific fields for the size and alignment of pointers in the default address space; furthermore, the two `pointer_size` and `pointer_align` fields in `TargetDataLayout` are replaced with an `FxHashMap` that holds info for all the possible address spaces, as parsed by the `p-` specifications.

The potential performance drawbacks of not having ad-hoc fields for the default address space will be tested in this PR's CI run.

r? workingjubilee

4 files changed, 4 insertions, 4 deletions

diff --git a/compiler/rustc_codegen_cranelift/src/abi/mod.rs b/compiler/rustc_codegen_cranelift/src/abi/mod.rs
index 8965e4a944d..7d0731c77bd 100644
--- a/compiler/rustc_codegen_cranelift/src/abi/mod.rs
+++ b/compiler/rustc_codegen_cranelift/src/abi/mod.rs
@@ -786,7 +786,7 @@ pub(crate) fn codegen_drop<'tcx>(
 
 pub(crate) fn lib_call_arg_param(tcx: TyCtxt<'_>, ty: Type, is_signed: bool) -> AbiParam {
     let param = AbiParam::new(ty);
-    if ty.is_int() && u64::from(ty.bits()) < tcx.data_layout.pointer_size.bits() {
+    if ty.is_int() && u64::from(ty.bits()) < tcx.data_layout.pointer_size().bits() {
         match (&*tcx.sess.target.arch, &*tcx.sess.target.vendor) {
             ("x86_64", _) | ("aarch64", "apple") => match (ty, is_signed) {
                 (types::I8 | types::I16, true) => param.sext(),
diff --git a/compiler/rustc_codegen_cranelift/src/abi/pass_mode.rs b/compiler/rustc_codegen_cranelift/src/abi/pass_mode.rs
index cd0afee0cfb..2031842062d 100644
--- a/compiler/rustc_codegen_cranelift/src/abi/pass_mode.rs
+++ b/compiler/rustc_codegen_cranelift/src/abi/pass_mode.rs
@@ -127,7 +127,7 @@ impl<'tcx> ArgAbiExt<'tcx> for ArgAbi<'tcx, Ty<'tcx>> {
             PassMode::Indirect { attrs, meta_attrs: None, on_stack } => {
                 if on_stack {
                     // Abi requires aligning struct size to pointer size
-                    let size = self.layout.size.align_to(tcx.data_layout.pointer_align.abi);
+                    let size = self.layout.size.align_to(tcx.data_layout.pointer_align().abi);
                     let size = u32::try_from(size.bytes()).unwrap();
                     smallvec![apply_attrs_to_abi_param(
                         AbiParam::special(pointer_ty(tcx), ArgumentPurpose::StructArgument(size),),
diff --git a/compiler/rustc_codegen_cranelift/src/common.rs b/compiler/rustc_codegen_cranelift/src/common.rs
index 2f11b2d2dcc..2fbe5c02802 100644
--- a/compiler/rustc_codegen_cranelift/src/common.rs
+++ b/compiler/rustc_codegen_cranelift/src/common.rs
@@ -15,7 +15,7 @@ use crate::debuginfo::FunctionDebugContext;
 use crate::prelude::*;
 
 pub(crate) fn pointer_ty(tcx: TyCtxt<'_>) -> types::Type {
-    match tcx.data_layout.pointer_size.bits() {
+    match tcx.data_layout.pointer_size().bits() {
         16 => types::I16,
         32 => types::I32,
         64 => types::I64,
diff --git a/compiler/rustc_codegen_cranelift/src/constant.rs b/compiler/rustc_codegen_cranelift/src/constant.rs
index ee43eb736e6..ed06423b260 100644
--- a/compiler/rustc_codegen_cranelift/src/constant.rs
+++ b/compiler/rustc_codegen_cranelift/src/constant.rs
@@ -443,7 +443,7 @@ fn define_all_allocs(tcx: TyCtxt<'_>, module: &mut dyn Module, cx: &mut Constant
             let addend = {
                 let endianness = tcx.data_layout.endian;
                 let offset = offset.bytes() as usize;
-                let ptr_size = tcx.data_layout.pointer_size;
+                let ptr_size = tcx.data_layout.pointer_size();
                 let bytes = &alloc.inspect_with_uninit_and_ptr_outside_interpreter(
                     offset..offset + ptr_size.bytes() as usize,
                 );