Auto merge of #116270 - cjgillot:gvn-aggregate, r=oli-obk,RalfJung

See through aggregates in GVN

This PR is extracted from https://github.com/rust-lang/rust/pull/111344

The first 2 commit are cleanups to avoid repeated work. I propose to stop removing useless assignments as part of this pass, and let a later `SimplifyLocals` do it. This makes tests easier to read (among others).

The next 3 commits add a constant folding mechanism to the GVN pass, presented in https://github.com/rust-lang/rust/pull/116012. ~This pass is designed to only use global allocations, to avoid any risk of accidental modification of the stored state.~

The following commits implement opportunistic simplifications, in particular:
- projections of aggregates: `MyStruct { x: a }.x` gets replaced by `a`, works with enums too;
- projections of arrays: `[a, b][0]` becomes `a`;
- projections of repeat expressions: `[a; N][x]` becomes `a`;
- transform arrays of equal operands into a repeat rvalue.

Fixes https://github.com/rust-lang/miri/issues/3090

r? `@oli-obk`

7 files changed, 58 insertions, 9 deletions

diff --git a/compiler/rustc_const_eval/src/interpret/discriminant.rs b/compiler/rustc_const_eval/src/interpret/discriminant.rs
index 8dab45d65ee..fd173670374 100644
--- a/compiler/rustc_const_eval/src/interpret/discriminant.rs
+++ b/compiler/rustc_const_eval/src/interpret/discriminant.rs
@@ -1,7 +1,8 @@
 //! Functions for reading and writing discriminants of multi-variant layouts (enums and coroutines).
 
-use rustc_middle::ty::layout::{LayoutOf, PrimitiveExt, TyAndLayout};
-use rustc_middle::{mir, ty};
+use rustc_middle::mir;
+use rustc_middle::ty::layout::{LayoutOf, PrimitiveExt};
+use rustc_middle::ty::{self, Ty};
 use rustc_target::abi::{self, TagEncoding};
 use rustc_target::abi::{VariantIdx, Variants};
 
@@ -244,11 +245,11 @@ impl<'mir, 'tcx: 'mir, M: Machine<'mir, 'tcx>> InterpCx<'mir, 'tcx, M> {
 
     pub fn discriminant_for_variant(
         &self,
-        layout: TyAndLayout<'tcx>,
+        ty: Ty<'tcx>,
         variant: VariantIdx,
     ) -> InterpResult<'tcx, ImmTy<'tcx, M::Provenance>> {
-        let discr_layout = self.layout_of(layout.ty.discriminant_ty(*self.tcx))?;
-        let discr_value = match layout.ty.discriminant_for_variant(*self.tcx, variant) {
+        let discr_layout = self.layout_of(ty.discriminant_ty(*self.tcx))?;
+        let discr_value = match ty.discriminant_for_variant(*self.tcx, variant) {
             Some(discr) => {
                 // This type actually has discriminants.
                 assert_eq!(discr.ty, discr_layout.ty);
diff --git a/compiler/rustc_const_eval/src/interpret/intern.rs b/compiler/rustc_const_eval/src/interpret/intern.rs
index fd89e34204f..3d90e95c09c 100644
--- a/compiler/rustc_const_eval/src/interpret/intern.rs
+++ b/compiler/rustc_const_eval/src/interpret/intern.rs
@@ -450,6 +450,42 @@ pub fn intern_const_alloc_recursive<
     Ok(())
 }
 
+/// Intern `ret`. This function assumes that `ret` references no other allocation.
+#[instrument(level = "debug", skip(ecx))]
+pub fn intern_const_alloc_for_constprop<
+    'mir,
+    'tcx: 'mir,
+    T,
+    M: CompileTimeMachine<'mir, 'tcx, T>,
+>(
+    ecx: &mut InterpCx<'mir, 'tcx, M>,
+    alloc_id: AllocId,
+) -> InterpResult<'tcx, ()> {
+    // Move allocation to `tcx`.
+    let Some((_, mut alloc)) = ecx.memory.alloc_map.remove(&alloc_id) else {
+        // Pointer not found in local memory map. It is either a pointer to the global
+        // map, or dangling.
+        if ecx.tcx.try_get_global_alloc(alloc_id).is_none() {
+            throw_ub!(DeadLocal)
+        }
+        // The constant is already in global memory. Do nothing.
+        return Ok(());
+    };
+
+    alloc.mutability = Mutability::Not;
+
+    // We are not doing recursive interning, so we don't currently support provenance.
+    // (If this assertion ever triggers, we should just implement a
+    // proper recursive interning loop.)
+    assert!(alloc.provenance().ptrs().is_empty());
+
+    // Link the alloc id to the actual allocation
+    let alloc = ecx.tcx.mk_const_alloc(alloc);
+    ecx.tcx.set_alloc_id_memory(alloc_id, alloc);
+
+    Ok(())
+}
+
 impl<'mir, 'tcx: 'mir, M: super::intern::CompileTimeMachine<'mir, 'tcx, !>>
     InterpCx<'mir, 'tcx, M>
 {
diff --git a/compiler/rustc_const_eval/src/interpret/intrinsics.rs b/compiler/rustc_const_eval/src/interpret/intrinsics.rs
index c97207a61ac..c48857fcf3c 100644
--- a/compiler/rustc_const_eval/src/interpret/intrinsics.rs
+++ b/compiler/rustc_const_eval/src/interpret/intrinsics.rs
@@ -218,7 +218,7 @@ impl<'mir, 'tcx: 'mir, M: Machine<'mir, 'tcx>> InterpCx<'mir, 'tcx, M> {
             sym::discriminant_value => {
                 let place = self.deref_pointer(&args[0])?;
                 let variant = self.read_discriminant(&place)?;
-                let discr = self.discriminant_for_variant(place.layout, variant)?;
+                let discr = self.discriminant_for_variant(place.layout.ty, variant)?;
                 self.write_immediate(*discr, dest)?;
             }
             sym::exact_div => {
diff --git a/compiler/rustc_const_eval/src/interpret/memory.rs b/compiler/rustc_const_eval/src/interpret/memory.rs
index d7c7e279849..16905e93bf1 100644
--- a/compiler/rustc_const_eval/src/interpret/memory.rs
+++ b/compiler/rustc_const_eval/src/interpret/memory.rs
@@ -1011,7 +1011,7 @@ impl<'tcx, 'a, Prov: Provenance, Extra, Bytes: AllocBytes> AllocRef<'a, 'tcx, Pr
     }
 
     /// Returns whether the allocation has provenance anywhere in the range of the `AllocRef`.
-    pub(crate) fn has_provenance(&self) -> bool {
+    pub fn has_provenance(&self) -> bool {
         !self.alloc.provenance().range_empty(self.range, &self.tcx)
     }
 }
diff --git a/compiler/rustc_const_eval/src/interpret/mod.rs b/compiler/rustc_const_eval/src/interpret/mod.rs
index 13664456987..7d286d103ad 100644
--- a/compiler/rustc_const_eval/src/interpret/mod.rs
+++ b/compiler/rustc_const_eval/src/interpret/mod.rs
@@ -21,7 +21,9 @@ mod visitor;
 pub use rustc_middle::mir::interpret::*; // have all the `interpret` symbols in one place: here
 
 pub use self::eval_context::{Frame, FrameInfo, InterpCx, StackPopCleanup};
-pub use self::intern::{intern_const_alloc_recursive, InternKind};
+pub use self::intern::{
+    intern_const_alloc_for_constprop, intern_const_alloc_recursive, InternKind,
+};
 pub use self::machine::{compile_time_machine, AllocMap, Machine, MayLeak, StackPopJump};
 pub use self::memory::{AllocKind, AllocRef, AllocRefMut, FnVal, Memory, MemoryKind};
 pub use self::operand::{ImmTy, Immediate, OpTy, Readable};
diff --git a/compiler/rustc_const_eval/src/interpret/operand.rs b/compiler/rustc_const_eval/src/interpret/operand.rs
index 6716888290d..255dd1eba97 100644
--- a/compiler/rustc_const_eval/src/interpret/operand.rs
+++ b/compiler/rustc_const_eval/src/interpret/operand.rs
@@ -169,6 +169,16 @@ impl<'tcx, Prov: Provenance> ImmTy<'tcx, Prov> {
         ImmTy { imm: val.into(), layout }
     }
 
+    #[inline]
+    pub fn from_scalar_pair(a: Scalar<Prov>, b: Scalar<Prov>, layout: TyAndLayout<'tcx>) -> Self {
+        debug_assert!(
+            matches!(layout.abi, Abi::ScalarPair(..)),
+            "`ImmTy::from_scalar_pair` on non-scalar-pair layout"
+        );
+        let imm = Immediate::ScalarPair(a, b);
+        ImmTy { imm, layout }
+    }
+
     #[inline(always)]
     pub fn from_immediate(imm: Immediate<Prov>, layout: TyAndLayout<'tcx>) -> Self {
         debug_assert!(
diff --git a/compiler/rustc_const_eval/src/interpret/step.rs b/compiler/rustc_const_eval/src/interpret/step.rs
index 79cbda545f1..8c34d05042b 100644
--- a/compiler/rustc_const_eval/src/interpret/step.rs
+++ b/compiler/rustc_const_eval/src/interpret/step.rs
@@ -297,7 +297,7 @@ impl<'mir, 'tcx: 'mir, M: Machine<'mir, 'tcx>> InterpCx<'mir, 'tcx, M> {
             Discriminant(place) => {
                 let op = self.eval_place_to_op(place, None)?;
                 let variant = self.read_discriminant(&op)?;
-                let discr = self.discriminant_for_variant(op.layout, variant)?;
+                let discr = self.discriminant_for_variant(op.layout.ty, variant)?;
                 self.write_immediate(*discr, &dest)?;
             }
         }