Ensure ptr::read gets all the same LLVM load metadata that dereferencing does

compiler/rustc_hir_analysis/src/check/intrinsic.rs

@@ -363,6 +363,8 @@ pub fn check_intrinsic_type(tcx: TyCtxt<'_>, it: &hir::ForeignItem<'_>) {
             sym::likely => (0, vec![tcx.types.bool], tcx.types.bool),
             sym::unlikely => (0, vec![tcx.types.bool], tcx.types.bool),
 
+            sym::read_via_copy => (1, vec![tcx.mk_imm_ptr(param(0))], param(0)),
+
             sym::discriminant_value => {
                 let assoc_items = tcx.associated_item_def_ids(
                     tcx.require_lang_item(hir::LangItem::DiscriminantKind, None),

compiler/rustc_lint_defs/src/builtin.rs

@@ -1026,12 +1026,13 @@ declare_lint! {
     /// ### Example
     ///
     /// ```rust,compile_fail
-    /// #![feature(const_ptr_read)]
+    /// #![feature(const_mut_refs)]
     /// const FOO: () = unsafe {
     ///     let x = &[0_u8; 4];
     ///     let y = x.as_ptr().cast::<u32>();
-    ///     y.read(); // the address of a `u8` array is unknown and thus we don't know if
-    ///     // it is aligned enough for reading a `u32`.
+    ///     let mut z = 123;
+    ///     y.copy_to_nonoverlapping(&mut z, 1); // the address of a `u8` array is unknown
+    ///     // and thus we don't know if it is aligned enough for copying a `u32`.
     /// };
     /// ```
     ///

compiler/rustc_mir_transform/src/lower_intrinsics.rs

@@ -149,6 +149,30 @@ impl<'tcx> MirPass<'tcx> for LowerIntrinsics {
                             terminator.kind = TerminatorKind::Goto { target };
                         }
                     }
+                    sym::read_via_copy => {
+                        let Ok([arg]) = <[_; 1]>::try_from(std::mem::take(args)) else {
+                            span_bug!(terminator.source_info.span, "Wrong number of arguments");
+                        };
+                        let derefed_place =
+                            if let Some(place) = arg.place() && let Some(local) = place.as_local() {
+                                tcx.mk_place_deref(local.into())
+                            } else {
+                                span_bug!(terminator.source_info.span, "Only passing a local is supported");
+                            };
+                        block.statements.push(Statement {
+                            source_info: terminator.source_info,
+                            kind: StatementKind::Assign(Box::new((
+                                *destination,
+                                Rvalue::Use(Operand::Copy(derefed_place)),
+                            ))),
+                        });
+                        if let Some(target) = *target {
+                            terminator.kind = TerminatorKind::Goto { target };
+                        } else {
+                            // Reading something uninhabited means this is unreachable.
+                            terminator.kind = TerminatorKind::Unreachable;
+                        }
+                    }
                     sym::discriminant_value => {
                         if let (Some(target), Some(arg)) = (*target, args[0].place()) {
                             let arg = tcx.mk_place_deref(arg);

compiler/rustc_span/src/symbol.rs

@@ -1153,6 +1153,7 @@ symbols! {
         read_enum_variant_arg,
         read_struct,
         read_struct_field,
+        read_via_copy,
         readonly,
         realloc,
         reason,

library/core/src/intrinsics.rs

@@ -2020,6 +2020,20 @@ extern "rust-intrinsic" {
     #[rustc_safe_intrinsic]
     pub fn saturating_sub<T: Copy>(a: T, b: T) -> T;
 
+    /// This is a *typed* read, `copy *p` in MIR.
+    ///
+    /// The stabilized form of this intrinsic is [`crate::ptr::read`], so
+    /// that can be implemented without needing to do an *untyped* copy
+    /// via [`copy_nonoverlapping`], and thus can get proper metadata.
+    ///
+    /// This intrinsic can *only* be called with a copy or move of a local.
+    /// (It allows neither constants nor projections.)
+    ///
+    /// To avoid introducing any `noalias` requirements, it just takes a pointer.
+    #[cfg(not(bootstrap))]
+    #[rustc_const_unstable(feature = "const_ptr_read", issue = "80377")]
+    pub fn read_via_copy<T>(p: *const T) -> T;
+
     /// Returns the value of the discriminant for the variant in 'v';
     /// if `T` has no discriminant, returns `0`.
     ///

library/core/src/ptr/mod.rs

@@ -1137,25 +1137,33 @@ pub const unsafe fn replace<T>(dst: *mut T, mut src: T) -> T {
 pub const unsafe fn read<T>(src: *const T) -> T {
     // We are calling the intrinsics directly to avoid function calls in the generated code
     // as `intrinsics::copy_nonoverlapping` is a wrapper function.
+    #[cfg(bootstrap)]
     extern "rust-intrinsic" {
         #[rustc_const_stable(feature = "const_intrinsic_copy", since = "1.63.0")]
         fn copy_nonoverlapping<T>(src: *const T, dst: *mut T, count: usize);
     }
 
-    let mut tmp = MaybeUninit::<T>::uninit();
     // SAFETY: the caller must guarantee that `src` is valid for reads.
     // `src` cannot overlap `tmp` because `tmp` was just allocated on
     // the stack as a separate allocated object.
-    //
-    // Also, since we just wrote a valid value into `tmp`, it is guaranteed
-    // to be properly initialized.
     unsafe {
         assert_unsafe_precondition!(
             "ptr::read requires that the pointer argument is aligned and non-null",
             [T](src: *const T) => is_aligned_and_not_null(src)
         );
-        copy_nonoverlapping(src, tmp.as_mut_ptr(), 1);
-        tmp.assume_init()
+
+        #[cfg(bootstrap)]
+        {
+            let mut tmp = MaybeUninit::<T>::uninit();
+            copy_nonoverlapping(src, tmp.as_mut_ptr(), 1);
+            tmp.assume_init()
+        }
+        #[cfg(not(bootstrap))]
+        {
+            // This uses a dedicated intrinsic, not `copy_nonoverlapping`,
+            // so that it gets a *typed* copy, not an *untyped* one.
+            crate::intrinsics::read_via_copy(src)
+        }
     }
 }
 

tests/codegen/mem-replace-direct-memcpy.rs

@@ -12,13 +12,44 @@ pub fn replace_byte(dst: &mut u8, src: u8) -> u8 {
     std::mem::replace(dst, src)
 }
 
+#[repr(C, align(8))]
+pub struct Big([u64; 7]);
+pub fn replace_big(dst: &mut Big, src: Big) -> Big {
+    // Before the `read_via_copy` intrinsic, this emitted six `memcpy`s.
+    std::mem::replace(dst, src)
+}
+
 // NOTE(eddyb) the `CHECK-NOT`s ensure that the only calls of `@llvm.memcpy` in
-// the entire output, are the two direct calls we want, from `ptr::replace`.
+// the entire output, are the direct calls we want, from `ptr::replace`.
 
 // CHECK-NOT: call void @llvm.memcpy
-// CHECK: ; core::mem::replace
-// CHECK-NOT: call void @llvm.memcpy
-// CHECK: call void @llvm.memcpy.{{.+}}({{i8\*|ptr}} align 1 %{{.*}}, {{i8\*|ptr}} align 1 %{{.*}}, i{{.*}} 1, i1 false)
+
+// For a large type, we expect exactly three `memcpy`s
+// CHECK-LABEL: define internal void @{{.+}}mem{{.+}}replace{{.+}}sret(%Big)
+    // CHECK-NOT: alloca
+    // CHECK: alloca %Big
+    // CHECK-NOT: alloca
+    // CHECK-NOT: call void @llvm.memcpy
+    // CHECK: call void @llvm.memcpy.{{.+}}({{i8\*|ptr}} align 8 %{{.*}}, {{i8\*|ptr}} align 8 %{{.*}}, i{{.*}} 56, i1 false)
+    // CHECK-NOT: call void @llvm.memcpy
+    // CHECK: call void @llvm.memcpy.{{.+}}({{i8\*|ptr}} align 8 %{{.*}}, {{i8\*|ptr}} align 8 %{{.*}}, i{{.*}} 56, i1 false)
+    // CHECK-NOT: call void @llvm.memcpy
+    // CHECK: call void @llvm.memcpy.{{.+}}({{i8\*|ptr}} align 8 %{{.*}}, {{i8\*|ptr}} align 8 %{{.*}}, i{{.*}} 56, i1 false)
+    // CHECK-NOT: call void @llvm.memcpy
+
 // CHECK-NOT: call void @llvm.memcpy
-// CHECK: call void @llvm.memcpy.{{.+}}({{i8\*|ptr}} align 1 %{{.*}}, {{i8\*|ptr}} align 1 %{{.*}}, i{{.*}} 1, i1 false)
+
+// For a small type, we expect one each of `load`/`store`/`memcpy` instead
+// CHECK-LABEL: define internal noundef i8 @{{.+}}mem{{.+}}replace
+    // CHECK-NOT: alloca
+    // CHECK: alloca i8
+    // CHECK-NOT: alloca
+    // CHECK-NOT: call void @llvm.memcpy
+    // CHECK: load i8
+    // CHECK-NOT: call void @llvm.memcpy
+    // CHECK: store i8
+    // CHECK-NOT: call void @llvm.memcpy
+    // CHECK: call void @llvm.memcpy.{{.+}}({{i8\*|ptr}} align 1 %{{.*}}, {{i8\*|ptr}} align 1 %{{.*}}, i{{.*}} 1, i1 false)
+    // CHECK-NOT: call void @llvm.memcpy
+
 // CHECK-NOT: call void @llvm.memcpy

tests/codegen/read-noundef-metadata.rs

@@ -0,0 +1,51 @@
+// compile-flags: -O -Z merge-functions=disabled
+// no-system-llvm
+// ignore-debug (the extra assertions get in the way)
+
+#![crate_type = "lib"]
+
+// Ensure that various forms of reading pointers correctly annotate the `load`s
+// with `!noundef` metadata to enable extra optimization.  The functions return
+// `MaybeUninit` to keep it from being inferred from the function type.
+
+use std::mem::MaybeUninit;
+
+// CHECK-LABEL: define i8 @copy_byte(
+#[no_mangle]
+pub unsafe fn copy_byte(p: *const u8) -> MaybeUninit<u8> {
+    // CHECK-NOT: load
+    // CHECK: load i8, ptr %p, align 1
+    // CHECK-SAME: !noundef !
+    // CHECK-NOT: load
+    MaybeUninit::new(*p)
+}
+
+// CHECK-LABEL: define i8 @read_byte(
+#[no_mangle]
+pub unsafe fn read_byte(p: *const u8) -> MaybeUninit<u8> {
+    // CHECK-NOT: load
+    // CHECK: load i8, ptr %p, align 1
+    // CHECK-SAME: !noundef !
+    // CHECK-NOT: load
+    MaybeUninit::new(p.read())
+}
+
+// CHECK-LABEL: define i8 @read_byte_maybe_uninit(
+#[no_mangle]
+pub unsafe fn read_byte_maybe_uninit(p: *const MaybeUninit<u8>) -> MaybeUninit<u8> {
+    // CHECK-NOT: load
+    // CHECK: load i8, ptr %p, align 1
+    // CHECK-NOT: noundef
+    // CHECK-NOT: load
+    p.read()
+}
+
+// CHECK-LABEL: define i8 @read_byte_assume_init(
+#[no_mangle]
+pub unsafe fn read_byte_assume_init(p: &MaybeUninit<u8>) -> MaybeUninit<u8> {
+    // CHECK-NOT: load
+    // CHECK: load i8, ptr %p, align 1
+    // CHECK-SAME: !noundef !
+    // CHECK-NOT: load
+    MaybeUninit::new(p.assume_init_read())
+}

tests/mir-opt/lower_intrinsics.read_via_copy_primitive.LowerIntrinsics.diff

@@ -0,0 +1,27 @@
+- // MIR for `read_via_copy_primitive` before LowerIntrinsics
++ // MIR for `read_via_copy_primitive` after LowerIntrinsics
+
+  fn read_via_copy_primitive(_1: &i32) -> i32 {
+      debug r => _1;                       // in scope 0 at $DIR/lower_intrinsics.rs:+0:32: +0:33
+      let mut _0: i32;                     // return place in scope 0 at $DIR/lower_intrinsics.rs:+0:44: +0:47
+      let mut _2: *const i32;              // in scope 0 at $DIR/lower_intrinsics.rs:+1:46: +1:47
+      scope 1 {
+      }
+
+      bb0: {
+          StorageLive(_2);                 // scope 1 at $DIR/lower_intrinsics.rs:+1:46: +1:47
+          _2 = &raw const (*_1);           // scope 1 at $DIR/lower_intrinsics.rs:+1:46: +1:47
+-         _0 = read_via_copy::<i32>(move _2) -> bb1; // scope 1 at $DIR/lower_intrinsics.rs:+1:14: +1:48
+-                                          // mir::Constant
+-                                          // + span: $DIR/lower_intrinsics.rs:85:14: 85:45
+-                                          // + literal: Const { ty: unsafe extern "rust-intrinsic" fn(*const i32) -> i32 {read_via_copy::<i32>}, val: Value(<ZST>) }
++         _0 = (*_2);                      // scope 1 at $DIR/lower_intrinsics.rs:+1:14: +1:48
++         goto -> bb1;                     // scope 1 at $DIR/lower_intrinsics.rs:+1:14: +1:48
+      }
+
+      bb1: {
+          StorageDead(_2);                 // scope 1 at $DIR/lower_intrinsics.rs:+1:47: +1:48
+          return;                          // scope 0 at $DIR/lower_intrinsics.rs:+2:2: +2:2
+      }
+  }
+

tests/mir-opt/lower_intrinsics.read_via_copy_uninhabited.LowerIntrinsics.diff

@@ -0,0 +1,22 @@
+- // MIR for `read_via_copy_uninhabited` before LowerIntrinsics
++ // MIR for `read_via_copy_uninhabited` after LowerIntrinsics
+
+  fn read_via_copy_uninhabited(_1: &Never) -> Never {
+      debug r => _1;                       // in scope 0 at $DIR/lower_intrinsics.rs:+0:34: +0:35
+      let mut _0: Never;                   // return place in scope 0 at $DIR/lower_intrinsics.rs:+0:48: +0:53
+      let mut _2: *const Never;            // in scope 0 at $DIR/lower_intrinsics.rs:+1:46: +1:47
+      scope 1 {
+      }
+
+      bb0: {
+          StorageLive(_2);                 // scope 1 at $DIR/lower_intrinsics.rs:+1:46: +1:47
+          _2 = &raw const (*_1);           // scope 1 at $DIR/lower_intrinsics.rs:+1:46: +1:47
+-         _0 = read_via_copy::<Never>(move _2); // scope 1 at $DIR/lower_intrinsics.rs:+1:14: +1:48
+-                                          // mir::Constant
+-                                          // + span: $DIR/lower_intrinsics.rs:90:14: 90:45
+-                                          // + literal: Const { ty: unsafe extern "rust-intrinsic" fn(*const Never) -> Never {read_via_copy::<Never>}, val: Value(<ZST>) }
++         _0 = (*_2);                      // scope 1 at $DIR/lower_intrinsics.rs:+1:14: +1:48
++         unreachable;                     // scope 1 at $DIR/lower_intrinsics.rs:+1:14: +1:48
+      }
+  }
+

tests/mir-opt/lower_intrinsics.rs

@@ -79,3 +79,15 @@ pub fn with_overflow(a: i32, b: i32) {
     let _y = core::intrinsics::sub_with_overflow(a, b);
     let _z = core::intrinsics::mul_with_overflow(a, b);
 }
+
+// EMIT_MIR lower_intrinsics.read_via_copy_primitive.LowerIntrinsics.diff
+pub fn read_via_copy_primitive(r: &i32) -> i32 {
+    unsafe { core::intrinsics::read_via_copy(r) }
+}
+
+// EMIT_MIR lower_intrinsics.read_via_copy_uninhabited.LowerIntrinsics.diff
+pub fn read_via_copy_uninhabited(r: &Never) -> Never {
+    unsafe { core::intrinsics::read_via_copy(r) }
+}
+
+pub enum Never {}

tests/ui/const-ptr/out_of_bounds_read.stderr

@@ -1,7 +1,7 @@
 error[E0080]: evaluation of constant value failed
   --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL
    |
-   = note: memory access failed: alloc5 has size 4, so pointer to 4 bytes starting at offset 4 is out-of-bounds
+   = note: dereferencing pointer failed: alloc5 has size 4, so pointer to 4 bytes starting at offset 4 is out-of-bounds
    |
 note: inside `std::ptr::read::<u32>`
   --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL
@@ -14,7 +14,7 @@ LL |     const _READ: u32 = unsafe { ptr::read(PAST_END_PTR) };
 error[E0080]: evaluation of constant value failed
   --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL
    |
-   = note: memory access failed: alloc5 has size 4, so pointer to 4 bytes starting at offset 4 is out-of-bounds
+   = note: dereferencing pointer failed: alloc5 has size 4, so pointer to 4 bytes starting at offset 4 is out-of-bounds
    |
 note: inside `std::ptr::read::<u32>`
   --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL
@@ -29,7 +29,7 @@ LL |     const _CONST_READ: u32 = unsafe { PAST_END_PTR.read() };
 error[E0080]: evaluation of constant value failed
   --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL
    |
-   = note: memory access failed: alloc5 has size 4, so pointer to 4 bytes starting at offset 4 is out-of-bounds
+   = note: dereferencing pointer failed: alloc5 has size 4, so pointer to 4 bytes starting at offset 4 is out-of-bounds
    |
 note: inside `std::ptr::read::<u32>`
   --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL

tests/ui/consts/const-eval/ub-ref-ptr.stderr

@@ -148,11 +148,11 @@ LL | const DATA_FN_PTR: fn() = unsafe { mem::transmute(&13) };
                HEX_DUMP
            }
 
-error: accessing memory with alignment 1, but alignment 4 is required
+error[E0080]: evaluation of constant value failed
   --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL
    |
-   = warning: this was previously accepted by the compiler but is being phased out; it will become a hard error in a future release!
-   = note: for more information, see issue #68585 <https://github.com/rust-lang/rust/issues/104616>
+   = note: accessing memory with alignment 1, but alignment 4 is required
+   |
 note: inside `std::ptr::read::<u32>`
   --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL
 note: inside `ptr::const_ptr::<impl *const u32>::read`
@@ -162,25 +162,7 @@ note: inside `UNALIGNED_READ`
    |
 LL |     ptr.read();
    |     ^^^^^^^^^^
-   = note: `#[deny(invalid_alignment)]` on by default
 
 error: aborting due to 15 previous errors
 
 For more information about this error, try `rustc --explain E0080`.
-Future incompatibility report: Future breakage diagnostic:
-error: accessing memory with alignment 1, but alignment 4 is required
-  --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL
-   |
-   = warning: this was previously accepted by the compiler but is being phased out; it will become a hard error in a future release!
-   = note: for more information, see issue #68585 <https://github.com/rust-lang/rust/issues/104616>
-note: inside `std::ptr::read::<u32>`
-  --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL
-note: inside `ptr::const_ptr::<impl *const u32>::read`
-  --> $SRC_DIR/core/src/ptr/const_ptr.rs:LL:COL
-note: inside `UNALIGNED_READ`
-  --> $DIR/ub-ref-ptr.rs:67:5
-   |
-LL |     ptr.read();
-   |     ^^^^^^^^^^
-   = note: `#[deny(invalid_alignment)]` on by default
-

tests/ui/consts/issue-miri-1910.stderr

@@ -1,7 +1,7 @@
 error[E0080]: evaluation of constant value failed
   --> $SRC_DIR/core/src/ptr/mod.rs:LL:COL
    |
-   = note: unable to copy parts of a pointer from memory at ALLOC
+   = note: unable to turn pointer into raw bytes
    |
    = help: this code performed an operation that depends on the underlying bytes representing a pointer
    = help: the absolute address of a pointer is not known at compile-time, so such operations are not supported