Auto merge of #127638 - adwinwhite:cache_string, r=oli-obk

Add cache for `allocate_str`

Best effort cache for string allocation in const eval.

Fixes [rust-lang/miri#3470](https://github.com/rust-lang/miri/issues/3470).

4 files changed, 28 insertions, 10 deletions

diff --git a/compiler/rustc_const_eval/src/interpret/place.rs b/compiler/rustc_const_eval/src/interpret/place.rs
index baaee67e787..33c25b746cc 100644
--- a/compiler/rustc_const_eval/src/interpret/place.rs
+++ b/compiler/rustc_const_eval/src/interpret/place.rs
@@ -995,13 +995,25 @@ where
     }
 
     /// Returns a wide MPlace of type `str` to a new 1-aligned allocation.
+    /// Immutable strings are deduplicated and stored in global memory.
     pub fn allocate_str(
         &mut self,
         str: &str,
         kind: MemoryKind<M::MemoryKind>,
         mutbl: Mutability,
     ) -> InterpResult<'tcx, MPlaceTy<'tcx, M::Provenance>> {
-        let ptr = self.allocate_bytes_ptr(str.as_bytes(), Align::ONE, kind, mutbl)?;
+        let tcx = self.tcx.tcx;
+
+        // Use cache for immutable strings.
+        let ptr = if mutbl.is_not() {
+            // Use dedup'd allocation function.
+            let id = tcx.allocate_bytes_dedup(str.as_bytes());
+
+            // Turn untagged "global" pointers (obtained via `tcx`) into the machine pointer to the allocation.
+            M::adjust_alloc_root_pointer(&self, Pointer::from(id), Some(kind))?
+        } else {
+            self.allocate_bytes_ptr(str.as_bytes(), Align::ONE, kind, mutbl)?
+        };
         let meta = Scalar::from_target_usize(u64::try_from(str.len()).unwrap(), self);
         let layout = self.layout_of(self.tcx.types.str_).unwrap();
         Ok(self.ptr_with_meta_to_mplace(ptr.into(), MemPlaceMeta::Meta(meta), layout))
diff --git a/compiler/rustc_middle/src/mir/interpret/mod.rs b/compiler/rustc_middle/src/mir/interpret/mod.rs
index 4e95e600b5a..bdd1eb11a38 100644
--- a/compiler/rustc_middle/src/mir/interpret/mod.rs
+++ b/compiler/rustc_middle/src/mir/interpret/mod.rs
@@ -393,7 +393,6 @@ pub(crate) struct AllocMap<'tcx> {
     alloc_map: FxHashMap<AllocId, GlobalAlloc<'tcx>>,
 
     /// Used to ensure that statics and functions only get one associated `AllocId`.
-    /// Should never contain a `GlobalAlloc::Memory`!
     //
     // FIXME: Should we just have two separate dedup maps for statics and functions each?
     dedup: FxHashMap<GlobalAlloc<'tcx>, AllocId>,
@@ -433,13 +432,13 @@ impl<'tcx> TyCtxt<'tcx> {
     }
 
     /// Reserves a new ID *if* this allocation has not been dedup-reserved before.
-    /// Should only be used for "symbolic" allocations (function pointers, vtables, statics), we
-    /// don't want to dedup IDs for "real" memory!
+    /// Should not be used for mutable memory.
     fn reserve_and_set_dedup(self, alloc: GlobalAlloc<'tcx>) -> AllocId {
         let mut alloc_map = self.alloc_map.lock();
-        match alloc {
-            GlobalAlloc::Function { .. } | GlobalAlloc::Static(..) | GlobalAlloc::VTable(..) => {}
-            GlobalAlloc::Memory(..) => bug!("Trying to dedup-reserve memory with real data!"),
+        if let GlobalAlloc::Memory(mem) = alloc {
+            if mem.inner().mutability.is_mut() {
+                bug!("trying to dedup-reserve mutable memory");
+            }
         }
         if let Some(&alloc_id) = alloc_map.dedup.get(&alloc) {
             return alloc_id;
@@ -451,6 +450,12 @@ impl<'tcx> TyCtxt<'tcx> {
         id
     }
 
+    /// Generates an `AllocId` for a memory allocation. If the exact same memory has been
+    /// allocated before, this will return the same `AllocId`.
+    pub fn reserve_and_set_memory_dedup(self, mem: ConstAllocation<'tcx>) -> AllocId {
+        self.reserve_and_set_dedup(GlobalAlloc::Memory(mem))
+    }
+
     /// Generates an `AllocId` for a static or return a cached one in case this function has been
     /// called on the same static before.
     pub fn reserve_and_set_static_alloc(self, static_id: DefId) -> AllocId {
diff --git a/compiler/rustc_middle/src/ty/context.rs b/compiler/rustc_middle/src/ty/context.rs
index 9e24ea485b2..25070e6b042 100644
--- a/compiler/rustc_middle/src/ty/context.rs
+++ b/compiler/rustc_middle/src/ty/context.rs
@@ -1442,11 +1442,12 @@ impl<'tcx> TyCtxt<'tcx> {
     }
 
     /// Allocates a read-only byte or string literal for `mir::interpret`.
-    pub fn allocate_bytes(self, bytes: &[u8]) -> interpret::AllocId {
+    /// Returns the same `AllocId` if called again with the same bytes.
+    pub fn allocate_bytes_dedup(self, bytes: &[u8]) -> interpret::AllocId {
         // Create an allocation that just contains these bytes.
         let alloc = interpret::Allocation::from_bytes_byte_aligned_immutable(bytes);
         let alloc = self.mk_const_alloc(alloc);
-        self.reserve_and_set_memory_alloc(alloc)
+        self.reserve_and_set_memory_dedup(alloc)
     }
 
     /// Returns a range of the start/end indices specified with the
diff --git a/compiler/rustc_mir_build/src/build/expr/as_constant.rs b/compiler/rustc_mir_build/src/build/expr/as_constant.rs
index 3b69058d3cb..be62a3d3736 100644
--- a/compiler/rustc_mir_build/src/build/expr/as_constant.rs
+++ b/compiler/rustc_mir_build/src/build/expr/as_constant.rs
@@ -140,7 +140,7 @@ fn lit_to_mir_constant<'tcx>(
             ConstValue::Slice { data: allocation, meta: allocation.inner().size().bytes() }
         }
         (ast::LitKind::ByteStr(data, _), ty::Ref(_, inner_ty, _)) if inner_ty.is_array() => {
-            let id = tcx.allocate_bytes(data);
+            let id = tcx.allocate_bytes_dedup(data);
             ConstValue::Scalar(Scalar::from_pointer(id.into(), &tcx))
         }
         (ast::LitKind::CStr(data, _), ty::Ref(_, inner_ty, _)) if matches!(inner_ty.kind(), ty::Adt(def, _) if tcx.is_lang_item(def.did(), LangItem::CStr)) =>