[scudo] CRC32 optimizations

Summary:
This change optimizes several aspects of the checksum used for chunk headers.

First, there is no point in checking the weak symbol `computeHardwareCRC32`
everytime, it will either be there or not when we start, so check it once
during initialization and set the checksum type accordingly.

Then, the loading of `HashAlgorithm` for SSE versions (and ARM equivalent) was
not optimized out, while not necessary. So I reshuffled that part of the code,
which duplicates a tiny bit of code, but ends up in a much cleaner assembly
(and faster as we avoid an extraneous load and some calls).

The following code is the checksum at the end of `scudoMalloc` for x86_64 with
full SSE 4.2, before:
```
mov     rax, 0FFFFFFFFFFFFFFh
shl     r10, 38h
mov     edi, dword ptr cs:_ZN7__scudoL6CookieE ; __scudo::Cookie
and     r14, rax
lea     rsi, [r13-10h]
movzx   eax, cs:_ZN7__scudoL13HashAlgorithmE ; __scudo::HashAlgorithm
or      r14, r10
mov     rbx, r14
xor     bx, bx
call    _ZN7__scudo20computeHardwareCRC32Ejm ; __scudo::computeHardwareCRC32(uint,ulong)
mov     rsi, rbx
mov     edi, eax
call    _ZN7__scudo20computeHardwareCRC32Ejm ; __scudo::computeHardwareCRC32(uint,ulong)
mov     r14w, ax
mov     rax, r13
mov     [r13-10h], r14
```
After:
```
mov     rax, cs:_ZN7__scudoL6CookieE ; __scudo::Cookie
lea     rcx, [rbx-10h]
mov     rdx, 0FFFFFFFFFFFFFFh
and     r14, rdx
shl     r9, 38h
or      r14, r9
crc32   eax, rcx
mov     rdx, r14
xor     dx, dx
mov     eax, eax
crc32   eax, rdx
mov     r14w, ax
mov     rax, rbx
mov     [rbx-10h], r14
```

Reviewers: dvyukov, alekseyshl, kcc

Reviewed By: alekseyshl

Subscribers: aemerson, rengolin, llvm-commits

Differential Revision: https://reviews.llvm.org/D32971

git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@302538 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 1 insertions, 18 deletions

diff --git a/lib/scudo/scudo_crc32.cpp b/lib/scudo/scudo_crc32.cpp
index 56be22f4e..a267dc4e3 100644
--- a/lib/scudo/scudo_crc32.cpp
+++ b/lib/scudo/scudo_crc32.cpp
@@ -12,24 +12,7 @@
 ///
 //===----------------------------------------------------------------------===//
 
-#include "sanitizer_common/sanitizer_internal_defs.h"
-
-// Hardware CRC32 is supported at compilation via the following:
-// - for i386 & x86_64: -msse4.2
-// - for ARM & AArch64: -march=armv8-a+crc or -mcrc
-// An additional check must be performed at runtime as well to make sure the
-// emitted instructions are valid on the target host.
-
-#if defined(__SSE4_2__) || defined(__ARM_FEATURE_CRC32)
-# ifdef __SSE4_2__
-#  include <smmintrin.h>
-#  define CRC32_INTRINSIC FIRST_32_SECOND_64(_mm_crc32_u32, _mm_crc32_u64)
-# endif
-# ifdef __ARM_FEATURE_CRC32
-#  include <arm_acle.h>
-#  define CRC32_INTRINSIC FIRST_32_SECOND_64(__crc32cw, __crc32cd)
-# endif
-#endif  // defined(__SSE4_2__) || defined(__ARM_FEATURE_CRC32)
+#include "scudo_crc32.h"
 
 namespace __scudo {