[llvm] 8bdbebb - [ELF] Fix SysV hash function.

[Nathan Sidwell via llvm-commits]

Author: Nathan Sidwell
Date: 2023-04-14T17:14:25-04:00
New Revision: 8bdbebbecdd5d0f70fa0722659b67adee930c58c

URL: https://github.com/llvm/llvm-project/commit/8bdbebbecdd5d0f70fa0722659b67adee930c58c
DIFF: https://github.com/llvm/llvm-project/commit/8bdbebbecdd5d0f70fa0722659b67adee930c58c.diff

LOG: [ELF] Fix SysV hash function.

(a) Treat name as unsigned chars.

(b) Refactor for better optimization of main loop.

Differential Revision: https://reviews.llvm.org/D147890

Added: 
    

Modified: 
    llvm/include/llvm/Object/ELF.h
    llvm/unittests/Object/ELFTest.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/include/llvm/Object/ELF.h b/llvm/include/llvm/Object/ELF.h
index 0db0ebb5c7c32..9c5146f014958 100644
--- a/llvm/include/llvm/Object/ELF.h
+++ b/llvm/include/llvm/Object/ELF.h
@@ -1237,15 +1237,12 @@ Expected<StringRef> ELFFile<ELFT>::getSectionName(const Elf_Shdr &Section,
 /// Name of the API remains consistent as specified in the libelf
 /// REF : http://www.sco.com/developers/gabi/latest/ch5.dynamic.html#hash
 inline unsigned hashSysV(StringRef SymbolName) {
-  unsigned h = 0, g;
-  for (char C : SymbolName) {
-    h = (h << 4) + C;
-    g = h & 0xf0000000L;
-    if (g != 0)
-      h ^= g >> 24;
-    h &= ~g;
+  uint32_t H = 0;
+  for (uint8_t C : SymbolName) {
+    H = (H << 4) + C;
+    H ^= (H >> 24) & 0xf0;
   }
-  return h;
+  return H & 0x0fffffff;
 }
 
 /// This function returns the hash value for a symbol in the .dynsym section

diff  --git a/llvm/unittests/Object/ELFTest.cpp b/llvm/unittests/Object/ELFTest.cpp
index 9cf8feb0e2c52..24f65841c5f22 100644
--- a/llvm/unittests/Object/ELFTest.cpp
+++ b/llvm/unittests/Object/ELFTest.cpp
@@ -271,3 +271,26 @@ TEST(ELFTest, DataRegionTest) {
   EXPECT_THAT_ERROR(Region[3].takeError(), FailedWithMessage(ErrMsg2));
   EXPECT_THAT_ERROR(Region[4].takeError(), FailedWithMessage(ErrMsg2));
 }
+
+// Test the sysV and the gnu hash functions, particularly with UTF-8 unicode.
+// Use names long enough for the hash's recycling of the high bits to kick in.
+// Explicitly encode the UTF-8 to avoid encoding transliterations.
+TEST(ELFTest, Hash) {
+  EXPECT_EQ(hashSysV("FooBarBazToto"), 0x5ec3e8fU);
+  EXPECT_EQ(hashGnu("FooBarBazToto"), 0x5478be61U);
+
+  // boom💥pants
+  EXPECT_EQ(hashSysV("boom\xf0\x9f\x92\xa5pants"), 0x5a0cf53U);
+  EXPECT_EQ(hashGnu("boom\xf0\x9f\x92\xa5pants"), 0xf5dda2deU);
+
+  // woot!🧙 💑 🌈
+  EXPECT_EQ(hashSysV("woot!\xf0\x9f\xa7\x99 \xf0\x9f\x92\x91 "
+                     "\xf0\x9f\x8c\x88"), 0x3522e38U);
+  EXPECT_EQ(hashGnu("woot!\xf0\x9f\xa7\x99 \xf0\x9f\x92\x91 "
+                    "\xf0\x9f\x8c\x88"), 0xf7603f3U);
+
+  // This string hashes to 0x100000000 in the originally formulated function,
+  // when long is 64 bits -- but that was never the intent. The code was
+  // presuming 32-bit long. Thus make sure that extra bit doesn't appear. 
+  EXPECT_EQ(hashSysV("ZZZZZW9p"), 0U);
+}