[compiler-rt] [scudo] Add support for LoongArch hardware CRC32 checksumming (PR #83113)

[WÁNG Xuěruì via llvm-commits]

https://github.com/xen0n updated https://github.com/llvm/llvm-project/pull/83113

>From 83646b79038bbbcda4ad21f4474c504eecb31e40 Mon Sep 17 00:00:00 2001
From: WANG Xuerui <git at xen0n.name>
Date: Tue, 27 Feb 2024 16:20:46 +0800
Subject: [PATCH] [scudo] Add support for LoongArch hardware CRC32 checksumming

One has to probe for platform capability prior to use with HWCAP,
according to LoongArch documentation.
---
 compiler-rt/lib/scudo/standalone/checksum.cpp | 11 +++++++++++
 compiler-rt/lib/scudo/standalone/checksum.h   |  4 ++++
 compiler-rt/lib/scudo/standalone/crc32_hw.cpp |  7 +++++++
 3 files changed, 22 insertions(+)

diff --git a/compiler-rt/lib/scudo/standalone/checksum.cpp b/compiler-rt/lib/scudo/standalone/checksum.cpp
index 2c277391a2ec16..a3dfccdd5bba32 100644
--- a/compiler-rt/lib/scudo/standalone/checksum.cpp
+++ b/compiler-rt/lib/scudo/standalone/checksum.cpp
@@ -19,6 +19,8 @@
 #else
 #include <sys/auxv.h>
 #endif
+#elif defined(__loongarch__)
+#include <sys/auxv.h>
 #endif
 
 namespace scudo {
@@ -75,6 +77,15 @@ bool hasHardwareCRC32() {
   return !!(getauxval(AT_HWCAP) & HWCAP_CRC32);
 #endif // SCUDO_FUCHSIA
 }
+#elif defined(__loongarch__)
+// Query HWCAP for platform capability, according to *Software Development and
+// Build Convention for LoongArch Architectures* v0.1, Section 9.1.
+//
+// Link:
+// https://github.com/loongson/la-softdev-convention/blob/v0.1/la-softdev-convention.adoc#kernel-development
+bool hasHardwareCRC32() {
+  return !!(getauxval(AT_HWCAP) & HWCAP_LOONGARCH_CRC32);
+}
 #else
 // No hardware CRC32 implemented in Scudo for other architectures.
 bool hasHardwareCRC32() { return false; }
diff --git a/compiler-rt/lib/scudo/standalone/checksum.h b/compiler-rt/lib/scudo/standalone/checksum.h
index f8eda81fd91288..32ca372b097f68 100644
--- a/compiler-rt/lib/scudo/standalone/checksum.h
+++ b/compiler-rt/lib/scudo/standalone/checksum.h
@@ -30,6 +30,10 @@
 #include <arm_acle.h>
 #define CRC32_INTRINSIC FIRST_32_SECOND_64(__crc32cw, __crc32cd)
 #endif
+#ifdef __loongarch__
+#include <larchintrin.h>
+#define CRC32_INTRINSIC FIRST_32_SECOND_64(__crcc_w_w_w, __crcc_w_d_w)
+#endif
 
 namespace scudo {
 
diff --git a/compiler-rt/lib/scudo/standalone/crc32_hw.cpp b/compiler-rt/lib/scudo/standalone/crc32_hw.cpp
index 73f2ae000c63d6..c582b14d601bb3 100644
--- a/compiler-rt/lib/scudo/standalone/crc32_hw.cpp
+++ b/compiler-rt/lib/scudo/standalone/crc32_hw.cpp
@@ -17,4 +17,11 @@ u32 computeHardwareCRC32(u32 Crc, uptr Data) {
 #endif // defined(__CRC32__) || defined(__SSE4_2__) ||
        // defined(__ARM_FEATURE_CRC32)
 
+#if defined(__loongarch__)
+u32 computeHardwareCRC32(u32 Crc, uptr Data) {
+  // The LoongArch CRC intrinsics have the two input arguments swapped.
+  return static_cast<u32>(CRC32_INTRINSIC(Data, Crc));
+}
+#endif // defined(__loongarch__)
+
 } // namespace scudo