[scudo] Separate hardware CRC32 routines

Summary:
As raised in D28304, enabling SSE 4.2 for the whole Scudo tree leads to the
emission of SSE 4.2 instructions everywhere, while the runtime checks only
applied to the CRC32 computing function.

This patch separates the CRC32 function taking advantage of the hardware into
its own file, and only enabled -msse4.2 for that file, if detected to be
supported by the compiler.

Another consequence of removing SSE4.2 globally is realizing that memcpy were
not being optimized, which turned out to be due to the -fno-builtin in
SANITIZER_COMMON_CFLAGS. So we now explicitely enable builtins for Scudo.

The resulting assembly looks good, with some CALLs are introduced instead of
the CRC32 code being inlined.

Reviewers: kcc, mgorny, alekseyshl

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D28417

llvm-svn: 291570

1 files changed, 3 insertions, 30 deletions

diff --git a/compiler-rt/lib/scudo/scudo_allocator.cpp b/compiler-rt/lib/scudo/scudo_allocator.cpp
index 96cfbdbc1af..d1121b0e7a7 100644
--- a/compiler-rt/lib/scudo/scudo_allocator.cpp
+++ b/compiler-rt/lib/scudo/scudo_allocator.cpp
@@ -15,6 +15,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "scudo_allocator.h"
+#include "scudo_crc32.h"
 #include "scudo_utils.h"
 
 #include "sanitizer_common/sanitizer_allocator_interface.h"
@@ -25,22 +26,6 @@
 
 #include <cstring>
 
-// Hardware CRC32 is supported at compilation via the following:
-// - for i386 & x86_64: -msse4.2
-// - for ARM & AArch64: -march=armv8-a+crc
-// 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 HW_CRC32 FIRST_32_SECOND_64(_mm_crc32_u32, _mm_crc32_u64)
-# endif
-# ifdef __ARM_FEATURE_CRC32
-#  include <arm_acle.h>
-#  define HW_CRC32 FIRST_32_SECOND_64(__crc32cw, __crc32cd)
-# endif
-#endif
-
 namespace __scudo {
 
 #if SANITIZER_CAN_USE_ALLOCATOR64
@@ -84,10 +69,6 @@ static thread_local Xorshift128Plus Prng;
 // Global static cookie, initialized at start-up.
 static uptr Cookie;
 
-enum : u8 {
-  CRC32Software = 0,
-  CRC32Hardware = 1,
-};
 // We default to software CRC32 if the alternatives are not supported, either
 // at compilation or at runtime.
 static atomic_uint8_t HashAlgorithm = { CRC32Software };
@@ -97,17 +78,9 @@ static atomic_uint8_t HashAlgorithm = { CRC32Software };
 // the checksumming function if available.
 INLINE u32 hashUptrs(uptr Pointer, uptr *Array, uptr ArraySize, u8 HashType) {
   u32 Crc;
-#if defined(__SSE4_2__) || defined(__ARM_FEATURE_CRC32)
-  if (HashType == CRC32Hardware) {
-    Crc = HW_CRC32(Cookie, Pointer);
-    for (uptr i = 0; i < ArraySize; i++)
-      Crc = HW_CRC32(Crc, Array[i]);
-    return Crc;
-  }
-#endif
-  Crc = computeCRC32(Cookie, Pointer);
+  Crc = computeCRC32(Cookie, Pointer, HashType);
   for (uptr i = 0; i < ArraySize; i++)
-    Crc = computeCRC32(Crc, Array[i]);
+    Crc = computeCRC32(Crc, Array[i], HashType);
   return Crc;
 }