Auto merge of #130541 - workingjubilee:rollup-26jmumi, r=workingjubilee

Rollup of 3 pull requests

Successful merges:

 - #129755 (test: cross-edition metavar fragment specifiers)
 - #130511 (Support `char::encode_utf8` in const scenarios.)
 - #130531 (Check params for unsafety in THIR)

r? `@ghost`
`@rustbot` modify labels: rollup

Author: bors

compiler/rustc_mir_build/src/check_unsafety.rs

@@ -218,6 +218,13 @@ impl<'tcx> UnsafetyVisitor<'_, 'tcx> {
                 warnings: self.warnings,
                 suggest_unsafe_block: self.suggest_unsafe_block,
             };
+            // params in THIR may be unsafe, e.g. a union pattern.
+            for param in &inner_thir.params {
+                if let Some(param_pat) = param.pat.as_deref() {
+                    inner_visitor.visit_pat(param_pat);
+                }
+            }
+            // Visit the body.
             inner_visitor.visit_expr(&inner_thir[expr]);
             // Unsafe blocks can be used in the inner body, make sure to take it into account
             self.safety_context = inner_visitor.safety_context;
@@ -1032,6 +1039,13 @@ pub(crate) fn check_unsafety(tcx: TyCtxt<'_>, def: LocalDefId) {
         warnings: &mut warnings,
         suggest_unsafe_block: true,
     };
+    // params in THIR may be unsafe, e.g. a union pattern.
+    for param in &thir.params {
+        if let Some(param_pat) = param.pat.as_deref() {
+            visitor.visit_pat(param_pat);
+        }
+    }
+    // Visit the body.
     visitor.visit_expr(&thir[expr]);
 
     warnings.sort_by_key(|w| w.block_span);

library/core/src/char/methods.rs

@@ -672,8 +672,9 @@ impl char {
     /// 'ß'.encode_utf8(&mut b);
     /// ```
     #[stable(feature = "unicode_encode_char", since = "1.15.0")]
+    #[rustc_const_unstable(feature = "const_char_encode_utf8", issue = "130512")]
     #[inline]
-    pub fn encode_utf8(self, dst: &mut [u8]) -> &mut str {
+    pub const fn encode_utf8(self, dst: &mut [u8]) -> &mut str {
         // SAFETY: `char` is not a surrogate, so this is valid UTF-8.
         unsafe { from_utf8_unchecked_mut(encode_utf8_raw(self as u32, dst)) }
     }
@@ -1735,14 +1736,11 @@ impl EscapeDebugExtArgs {
 
 #[inline]
 const fn len_utf8(code: u32) -> usize {
-    if code < MAX_ONE_B {
-        1
-    } else if code < MAX_TWO_B {
-        2
-    } else if code < MAX_THREE_B {
-        3
-    } else {
-        4
+    match code {
+        ..MAX_ONE_B => 1,
+        ..MAX_TWO_B => 2,
+        ..MAX_THREE_B => 3,
+        _ => 4,
     }
 }
 
@@ -1760,11 +1758,12 @@ const fn len_utf8(code: u32) -> usize {
 /// Panics if the buffer is not large enough.
 /// A buffer of length four is large enough to encode any `char`.
 #[unstable(feature = "char_internals", reason = "exposed only for libstd", issue = "none")]
+#[rustc_const_unstable(feature = "const_char_encode_utf8", issue = "130512")]
 #[doc(hidden)]
 #[inline]
-pub fn encode_utf8_raw(code: u32, dst: &mut [u8]) -> &mut [u8] {
+pub const fn encode_utf8_raw(code: u32, dst: &mut [u8]) -> &mut [u8] {
     let len = len_utf8(code);
-    match (len, &mut dst[..]) {
+    match (len, &mut *dst) {
         (1, [a, ..]) => {
             *a = code as u8;
         }
@@ -1783,14 +1782,11 @@ pub fn encode_utf8_raw(code: u32, dst: &mut [u8]) -> &mut [u8] {
             *c = (code >> 6 & 0x3F) as u8 | TAG_CONT;
             *d = (code & 0x3F) as u8 | TAG_CONT;
         }
-        _ => panic!(
-            "encode_utf8: need {} bytes to encode U+{:X}, but the buffer has {}",
-            len,
-            code,
-            dst.len(),
-        ),
+        // Note that we cannot format in constant expressions.
+        _ => panic!("encode_utf8: buffer does not have enough bytes to encode code point"),
     };
-    &mut dst[..len]
+    // SAFETY: `<&mut [u8]>::as_mut_ptr` is guaranteed to return a valid pointer and `len` has been tested to be within bounds.
+    unsafe { slice::from_raw_parts_mut(dst.as_mut_ptr(), len) }
 }
 
 /// Encodes a raw u32 value as UTF-16 into the provided `u16` buffer,

library/core/src/lib.rs

@@ -119,6 +119,7 @@
 #![feature(const_bigint_helper_methods)]
 #![feature(const_black_box)]
 #![feature(const_cell_into_inner)]
+#![feature(const_char_encode_utf8)]
 #![feature(const_eval_select)]
 #![feature(const_exact_div)]
 #![feature(const_float_classify)]

tests/ui/macros/auxiliary/metavar_2018.rs

@@ -0,0 +1,14 @@
+//@ edition: 2018
+#[macro_export]
+macro_rules! make_matcher {
+    ($name:ident, $fragment_type:ident, $d:tt) => {
+        #[macro_export]
+        macro_rules! $name {
+            ($d _:$fragment_type) => { true };
+            (const { 0 }) => { false };
+            (A | B) => { false };
+        }
+    };
+}
+make_matcher!(is_expr_from_2018, expr, $);
+make_matcher!(is_pat_from_2018, pat, $);

tests/ui/macros/metavar_cross_edition_recursive_macros.rs

@@ -0,0 +1,38 @@
+//@ compile-flags: --edition=2024 -Z unstable-options
+//@ aux-build: metavar_2018.rs
+//@ known-bug: #130484
+//@ run-pass
+
+// This test captures the behavior of macro-generating-macros with fragment
+// specifiers across edition boundaries.
+
+#![feature(expr_fragment_specifier_2024)]
+#![feature(macro_metavar_expr)]
+#![allow(incomplete_features)]
+
+extern crate metavar_2018;
+
+use metavar_2018::{is_expr_from_2018, is_pat_from_2018, make_matcher};
+
+make_matcher!(is_expr_from_2024, expr, $);
+make_matcher!(is_pat_from_2024, pat, $);
+
+fn main() {
+    // Check expr
+    let from_2018 = is_expr_from_2018!(const { 0 });
+    dbg!(from_2018);
+    let from_2024 = is_expr_from_2024!(const { 0 });
+    dbg!(from_2024);
+
+    assert!(!from_2018);
+    assert!(!from_2024); // from_2024 will be true once #130484 is fixed
+
+    // Check pat
+    let from_2018 = is_pat_from_2018!(A | B);
+    dbg!(from_2018);
+    let from_2024 = is_pat_from_2024!(A | B);
+    dbg!(from_2024);
+
+    assert!(!from_2018);
+    assert!(!from_2024); // from_2024 will be true once #130484 is fixed
+}

tests/ui/unsafe/union-pat-in-param.rs

@@ -0,0 +1,19 @@
+union U {
+    a: &'static i32,
+    b: usize,
+}
+
+fn fun(U { a }: U) {
+    //~^ ERROR access to union field is unsafe
+    dbg!(*a);
+}
+
+fn main() {
+    fun(U { b: 0 });
+
+    let closure = |U { a }| {
+        //~^ ERROR access to union field is unsafe
+        dbg!(*a);
+    };
+    closure(U { b: 0 });
+}

tests/ui/unsafe/union-pat-in-param.stderr

@@ -0,0 +1,19 @@
+error[E0133]: access to union field is unsafe and requires unsafe function or block
+  --> $DIR/union-pat-in-param.rs:6:12
+   |
+LL | fn fun(U { a }: U) {
+   |            ^ access to union field
+   |
+   = note: the field may not be properly initialized: using uninitialized data will cause undefined behavior
+
+error[E0133]: access to union field is unsafe and requires unsafe function or block
+  --> $DIR/union-pat-in-param.rs:14:24
+   |
+LL |     let closure = |U { a }| {
+   |                        ^ access to union field
+   |
+   = note: the field may not be properly initialized: using uninitialized data will cause undefined behavior
+
+error: aborting due to 2 previous errors
+
+For more information about this error, try `rustc --explain E0133`.