[Support] Optimize SHA1 implementation

* Add inline to the helper functions because gcc-9 won't inline all of
  them without the hint. I've avoided `__attribute__((always_inline))`
  because gcc and clang will inline without it, and improves
  compatibility.
* Replace the byte-by-byte copy in update() with endian::readbe32()
  since perf reports that 1/2 of the time is spent copying into the
  buffer before this patch.

When lld uses --build-id=sha1 it spends 30-45% of CPU in SHA1 depending on the binary (not wall-time since it is parallel). This patch speeds up SHA1 by a factor of 2 on clang-8 and 3 on gcc-6. This leads to a >10% improvement in overall linking time.

lld-speed-test benchmarks run on an Intel i9-9900k with Turbo disabled on CPU 0 compiled with clang-9. Stats recorded with `perf stat -r 5`. All inputs are using `--build-id=sha1`.

| Input | Before (seconds) | After (seconds) |
| --- | --- | --- |
| chrome | 2.14 | 1.82 (-15%) |
| chrome-icf | 2.56 | 2.29 (-10%) |
| clang | 0.65 | 0.53 (-18%) |
| clang-fsds | 0.69 | 0.58 (-16%) |
| clang-gdb-index | 21.71 | 19.3 (-11%) |
| gold | 0.42 | 0.34 (-19%) |
| gold-fsds | 0.431 | 0.355 (-17%) |
| linux-kernel | 0.625 | 0.575 (-8%) |
| llvm-as | 0.045 | 0.039 (-14%) |
| llvm-as-fsds | 0.035 | 0.039 (-11%) |
| mozilla | 11.3 | 9.8  (-13%) |
| mozilla-gc | 11.84 | 10.36 (-12%) |
| mozilla-O0 | 8.2 | 5.84 (-28%) |
| scylla | 5.59 | 4.52 (-19%) |

Reviewed By: ruiu, MaskRay

Differential Revision: https://reviews.llvm.org/D69295

lib/Support/SHA1.cpp

@@ -16,6 +16,7 @@
 
 #include "llvm/Support/SHA1.h"
 #include "llvm/ADT/ArrayRef.h"
+#include "llvm/Support/Endian.h"
 #include "llvm/Support/Host.h"
 using namespace llvm;
 
@@ -26,45 +27,45 @@ using namespace llvm;
 #define SHA_BIG_ENDIAN
 #endif
 
-static uint32_t rol(uint32_t Number, int Bits) {
+static inline uint32_t rol(uint32_t Number, int Bits) {
   return (Number << Bits) | (Number >> (32 - Bits));
 }
 
-static uint32_t blk0(uint32_t *Buf, int I) { return Buf[I]; }
+static inline uint32_t blk0(uint32_t *Buf, int I) { return Buf[I]; }
 
-static uint32_t blk(uint32_t *Buf, int I) {
+static inline uint32_t blk(uint32_t *Buf, int I) {
   Buf[I & 15] = rol(Buf[(I + 13) & 15] ^ Buf[(I + 8) & 15] ^ Buf[(I + 2) & 15] ^
                         Buf[I & 15],
                     1);
   return Buf[I & 15];
 }
 
-static void r0(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D, uint32_t &E,
-               int I, uint32_t *Buf) {
+static inline void r0(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D,
+                      uint32_t &E, int I, uint32_t *Buf) {
   E += ((B & (C ^ D)) ^ D) + blk0(Buf, I) + 0x5A827999 + rol(A, 5);
   B = rol(B, 30);
 }
 
-static void r1(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D, uint32_t &E,
-               int I, uint32_t *Buf) {
+static inline void r1(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D,
+                      uint32_t &E, int I, uint32_t *Buf) {
   E += ((B & (C ^ D)) ^ D) + blk(Buf, I) + 0x5A827999 + rol(A, 5);
   B = rol(B, 30);
 }
 
-static void r2(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D, uint32_t &E,
-               int I, uint32_t *Buf) {
+static inline void r2(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D,
+                      uint32_t &E, int I, uint32_t *Buf) {
   E += (B ^ C ^ D) + blk(Buf, I) + 0x6ED9EBA1 + rol(A, 5);
   B = rol(B, 30);
 }
 
-static void r3(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D, uint32_t &E,
-               int I, uint32_t *Buf) {
+static inline void r3(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D,
+                      uint32_t &E, int I, uint32_t *Buf) {
   E += (((B | C) & D) | (B & C)) + blk(Buf, I) + 0x8F1BBCDC + rol(A, 5);
   B = rol(B, 30);
 }
 
-static void r4(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D, uint32_t &E,
-               int I, uint32_t *Buf) {
+static inline void r4(uint32_t &A, uint32_t &B, uint32_t &C, uint32_t &D,
+                      uint32_t &E, int I, uint32_t *Buf) {
   E += (B ^ C ^ D) + blk(Buf, I) + 0xCA62C1D6 + rol(A, 5);
   B = rol(B, 30);
 }
@@ -210,8 +211,31 @@ void SHA1::writebyte(uint8_t Data) {
 }
 
 void SHA1::update(ArrayRef<uint8_t> Data) {
-  for (auto &C : Data)
-    writebyte(C);
+  InternalState.ByteCount += Data.size();
+
+  // Finish the current block.
+  if (InternalState.BufferOffset > 0) {
+    const size_t Remainder = std::min<size_t>(
+        Data.size(), BLOCK_LENGTH - InternalState.BufferOffset);
+    for (size_t I = 0; I < Remainder; ++I)
+      addUncounted(Data[I]);
+    Data = Data.drop_front(Remainder);
+  }
+
+  // Fast buffer filling for large inputs.
+  while (Data.size() >= BLOCK_LENGTH) {
+    assert(InternalState.BufferOffset == 0);
+    assert(BLOCK_LENGTH % 4 == 0);
+    constexpr size_t BLOCK_LENGTH_32 = BLOCK_LENGTH / 4;
+    for (size_t I = 0; I < BLOCK_LENGTH_32; ++I)
+      InternalState.Buffer.L[I] = support::endian::read32be(&Data[I * 4]);
+    hashBlock();
+    Data = Data.drop_front(BLOCK_LENGTH);
+  }
+
+  // Finish the remainder.
+  for (uint8_t C : Data)
+    addUncounted(C);
 }
 
 void SHA1::pad() {

unittests/Support/raw_sha1_ostream_test.cpp

@@ -43,6 +43,22 @@ TEST(sha1_hash_test, Basic) {
   ASSERT_EQ("2EF7BDE608CE5404E97D5F042F95F89F1C232871", Hash);
 }
 
+TEST(sha1_hash_test, Update) {
+  SHA1 sha1;
+  std::string Input = "123456789012345678901234567890";
+  ASSERT_EQ(Input.size(), 30UL);
+  // 3 short updates.
+  sha1.update(Input);
+  sha1.update(Input);
+  sha1.update(Input);
+  // Long update that gets into the optimized loop with prefix/suffix.
+  sha1.update(Input + Input + Input + Input);
+  // 18 bytes buffered now.
+
+  std::string Hash = toHex(sha1.final());
+  ASSERT_EQ("3E4A614101AD84985AB0FE54DC12A6D71551E5AE", Hash);
+}
+
 // Check that getting the intermediate hash in the middle of the stream does
 // not invalidate the final result.
 TEST(raw_sha1_ostreamTest, Intermediate) {