From 9aa7dd1e6afc0f8c944c63458fba0ea19ae2c392 Mon Sep 17 00:00:00 2001
From: Josh Stone <jistone@redhat.com>
Date: Fri, 8 Jan 2021 13:02:23 -0800
Subject: [PATCH] Specialize Box clones to try to avoid locals

For generic `T: Clone`, we can allocate an uninitialized box beforehand,
which gives the optimizer a chance to create the clone directly in the
heap. For `T: Copy`, we can go further and do a simple memory copy,
regardless of optimization level.
---
 library/alloc/src/boxed.rs | 30 ++++++++++++++++++++++++++++--
 1 file changed, 28 insertions(+), 2 deletions(-)

diff --git a/library/alloc/src/boxed.rs b/library/alloc/src/boxed.rs
index 33b812ec59f..7a9cf1948ea 100644
--- a/library/alloc/src/boxed.rs
+++ b/library/alloc/src/boxed.rs
@@ -1014,10 +1014,14 @@ impl<T: Clone, A: Allocator + Clone> Clone for Box<T, A> {
     /// // But they are unique objects
     /// assert_ne!(&*x as *const i32, &*y as *const i32);
     /// ```
-    #[rustfmt::skip]
     #[inline]
     fn clone(&self) -> Self {
-        Self::new_in((**self).clone(), self.1.clone())
+        // Pre-allocate memory to allow writing the cloned value directly.
+        let mut boxed = Self::new_uninit_in(self.1.clone());
+        unsafe {
+            (**self).write_clone_into_raw(boxed.as_mut_ptr());
+            boxed.assume_init()
+        }
     }
 
     /// Copies `source`'s contents into `self` without creating a new allocation.
@@ -1043,6 +1047,28 @@ fn clone_from(&mut self, source: &Self) {
     }
 }
 
+/// Specialize clones into pre-allocated, uninitialized memory.
+pub(crate) trait WriteCloneIntoRaw: Sized {
+    unsafe fn write_clone_into_raw(&self, target: *mut Self);
+}
+
+impl<T: Clone> WriteCloneIntoRaw for T {
+    #[inline]
+    default unsafe fn write_clone_into_raw(&self, target: *mut Self) {
+        // Having allocated *first* may allow the optimizer to create
+        // the cloned value in-place, skipping the local and move.
+        unsafe { target.write(self.clone()) };
+    }
+}
+
+impl<T: Copy> WriteCloneIntoRaw for T {
+    #[inline]
+    unsafe fn write_clone_into_raw(&self, target: *mut Self) {
+        // We can always copy in-place, without ever involving a local value.
+        unsafe { target.copy_from_nonoverlapping(self, 1) };
+    }
+}
+
 #[stable(feature = "box_slice_clone", since = "1.3.0")]
 impl Clone for Box<str> {
     fn clone(&self) -> Self {