From e44784b8750016a695361c990024750e037d8f9f Mon Sep 17 00:00:00 2001
From: Andreas Molzer <andreas.molzer@gmx.de>
Date: Sun, 20 Sep 2020 17:22:17 +0200
Subject: [PATCH] Assume slice len is bounded by allocation size

Uses assume to check the length against a constant upper bound. The
inlined result then informs the optimizer of the sound value range.

This was tried with unreachable_unchecked before which introduces a
branch. This has the advantage of not being executed in sound code but
complicates basic blocks. It resulted in ~2% increased compile time in
some worst cases.

Add a codegen test for the assumption, testing the issue from #67186
---
 library/core/src/lib.rs            |  3 ++-
 library/core/src/slice/mod.rs      | 27 +++++++++++++++++++++++++--
 src/test/codegen/len-is-bounded.rs | 24 ++++++++++++++++++++++++
 3 files changed, 51 insertions(+), 3 deletions(-)
 create mode 100644 src/test/codegen/len-is-bounded.rs

diff --git a/library/core/src/lib.rs b/library/core/src/lib.rs
index 22bf2b15d6695..49cec16276260 100644
--- a/library/core/src/lib.rs
+++ b/library/core/src/lib.rs
@@ -80,8 +80,9 @@
 #![feature(constctlz)]
 #![feature(const_panic)]
 #![feature(const_pin)]
-#![feature(const_fn_union)]
 #![feature(const_fn)]
+#![feature(const_fn_union)]
+#![feature(const_assume)]
 #![cfg_attr(not(bootstrap), feature(const_fn_floating_point_arithmetic))]
 #![cfg_attr(not(bootstrap), feature(const_fn_fn_ptr_basics))]
 #![feature(const_generics)]
diff --git a/library/core/src/slice/mod.rs b/library/core/src/slice/mod.rs
index 12dcd6c6ba8d0..d2b64f3ac6ad0 100644
--- a/library/core/src/slice/mod.rs
+++ b/library/core/src/slice/mod.rs
@@ -78,6 +78,17 @@ pub use index::check_range;
 #[lang = "slice"]
 #[cfg(not(test))]
 impl<T> [T] {
+    #[cfg(not(bootstrap))] // Unused in bootstrap
+    /// The maximum, inclusive, length such that the slice is no larger than `isize::MAX` bytes.
+    /// This constant is used in `len` below.
+    const MAX_LEN_BOUND: usize = {
+        if mem::size_of::<T>() == 0 {
+            usize::MAX
+        } else {
+            isize::MAX as usize / mem::size_of::<T>()
+        }
+    };
+
     /// Returns the number of elements in the slice.
     ///
     /// # Examples
@@ -90,11 +101,23 @@ impl<T> [T] {
     #[rustc_const_stable(feature = "const_slice_len", since = "1.32.0")]
     #[inline]
     // SAFETY: const sound because we transmute out the length field as a usize (which it must be)
-    #[allow_internal_unstable(const_fn_union)]
+    #[allow_internal_unstable(const_fn_union, const_assume)]
     pub const fn len(&self) -> usize {
         // SAFETY: this is safe because `&[T]` and `FatPtr<T>` have the same layout.
         // Only `std` can make this guarantee.
-        unsafe { crate::ptr::Repr { rust: self }.raw.len }
+        let raw_len = unsafe { crate::ptr::Repr { rust: self }.raw.len };
+
+        #[cfg(not(bootstrap))] // FIXME: executing assume in const eval not supported in bootstrap
+        // SAFETY: this assume asserts that `raw_len * size_of::<T>() <= isize::MAX`. All
+        // references must point to one allocation with size at most isize::MAX. Note that we the
+        // multiplication could appear to overflow until we have assumed the bound. This overflow
+        // would make additional values appear 'valid' and then `n > 1` the range of permissible
+        // length would no longer be the full or even a single range.
+        unsafe {
+            crate::intrinsics::assume(raw_len <= Self::MAX_LEN_BOUND)
+        };
+
+        raw_len
     }
 
     /// Returns `true` if the slice has a length of 0.
diff --git a/src/test/codegen/len-is-bounded.rs b/src/test/codegen/len-is-bounded.rs
new file mode 100644
index 0000000000000..bb74fc3b2752c
--- /dev/null
+++ b/src/test/codegen/len-is-bounded.rs
@@ -0,0 +1,24 @@
+// min-llvm-version: 11.0
+// compile-flags: -O -C panic=abort
+#![crate_type = "lib"]
+
+#[no_mangle]
+pub fn len_range(a: &[u8], b: &[u8]) -> usize {
+    // CHECK-NOT: panic
+    a.len().checked_add(b.len()).unwrap()
+}
+
+#[no_mangle]
+pub fn len_range_on_non_byte(a: &[u16], b: &[u16]) -> usize {
+    // CHECK-NOT: panic
+    a.len().checked_add(b.len()).unwrap()
+}
+
+pub struct Zst;
+
+#[no_mangle]
+pub fn zst_range(a: &[Zst], b: &[Zst]) -> usize {
+    // Zsts may be arbitrarily large.
+    // CHECK: panic
+    a.len().checked_add(b.len()).unwrap()
+}