From e427d29e3c9800c43fabbadd023fb0f75a59767e Mon Sep 17 00:00:00 2001
From: Folkert de Vries <folkert@folkertdev.nl>
Date: Thu, 26 Feb 2026 13:00:21 +0100
Subject: [PATCH] aarch64: fix UB in non-power-of-two reads and writes

(cherry picked from commit 2fa37e7b3498a9cb46004fae5fd9d6d40835ad28)
---
 .../stdarch/crates/core_arch/src/macros.rs    | 20 +++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/library/stdarch/crates/core_arch/src/macros.rs b/library/stdarch/crates/core_arch/src/macros.rs
index 9f6922efeeb7..54d4668e52fe 100644
--- a/library/stdarch/crates/core_arch/src/macros.rs
+++ b/library/stdarch/crates/core_arch/src/macros.rs
@@ -226,12 +226,12 @@ macro_rules! deinterleaving_load {
     ($elem:ty, $lanes:literal, 2, $ptr:expr) => {{
         use $crate::core_arch::macros::deinterleave_mask;
         use $crate::core_arch::simd::Simd;
-        use $crate::{mem::transmute, ptr};
+        use $crate::mem::transmute;
 
         type V = Simd<$elem, $lanes>;
         type W = Simd<$elem, { $lanes * 2 }>;
 
-        let w: W = ptr::read_unaligned($ptr as *const W);
+        let w: W = $crate::ptr::read_unaligned($ptr as *const W);
 
         let v0: V = simd_shuffle!(w, w, deinterleave_mask::<$lanes, 2, 0>());
         let v1: V = simd_shuffle!(w, w, deinterleave_mask::<$lanes, 2, 1>());
@@ -242,12 +242,20 @@ macro_rules! deinterleaving_load {
     ($elem:ty, $lanes:literal, 3, $ptr:expr) => {{
         use $crate::core_arch::macros::deinterleave_mask;
         use $crate::core_arch::simd::Simd;
-        use $crate::{mem::transmute, ptr};
+        use $crate::mem::{MaybeUninit, transmute};
 
         type V = Simd<$elem, $lanes>;
         type W = Simd<$elem, { $lanes * 3 }>;
 
-        let w: W = ptr::read_unaligned($ptr as *const W);
+        // NOTE: repr(simd) adds padding to make the total size a power of two.
+        // Hence reading W from ptr might read out of bounds.
+        let mut mem = MaybeUninit::<W>::uninit();
+        $crate::ptr::copy_nonoverlapping(
+            $ptr.cast::<$elem>(),
+            mem.as_mut_ptr().cast::<$elem>(),
+            $lanes * 3,
+        );
+        let w = mem.assume_init();
 
         let v0: V = simd_shuffle!(w, w, deinterleave_mask::<$lanes, 3, 0>());
         let v1: V = simd_shuffle!(w, w, deinterleave_mask::<$lanes, 3, 1>());
@@ -259,12 +267,12 @@ macro_rules! deinterleaving_load {
     ($elem:ty, $lanes:literal, 4, $ptr:expr) => {{
         use $crate::core_arch::macros::deinterleave_mask;
         use $crate::core_arch::simd::Simd;
-        use $crate::{mem::transmute, ptr};
+        use $crate::mem::transmute;
 
         type V = Simd<$elem, $lanes>;
         type W = Simd<$elem, { $lanes * 4 }>;
 
-        let w: W = ptr::read_unaligned($ptr as *const W);
+        let w: W = $crate::ptr::read_unaligned($ptr as *const W);
 
         let v0: V = simd_shuffle!(w, w, deinterleave_mask::<$lanes, 4, 0>());
         let v1: V = simd_shuffle!(w, w, deinterleave_mask::<$lanes, 4, 1>());