[libc-commits] [libc] [libc] Fix stale char_ptr for find_first_character_wide read (PR #166594)

[via libc-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-libc

Author: None (Sterling-Augustine)

<details>
<summary>Changes</summary>

On exit from the loop, char_ptr had not been updated to match block_ptr, resulting in erroneous results. Moving all updates out of the loop fixes that.

---
Full diff: https://github.com/llvm/llvm-project/pull/166594.diff


2 Files Affected:

- (modified) libc/src/string/string_utils.h (+5-5) 
- (modified) libc/test/src/string/memchr_test.cpp (+5) 


``````````diff
diff --git a/libc/src/string/string_utils.h b/libc/src/string/string_utils.h
index 7feef56fb3676..c9a720bef98a0 100644
--- a/libc/src/string/string_utils.h
+++ b/libc/src/string/string_utils.h
@@ -136,11 +136,11 @@ find_first_character_wide_read(const unsigned char *src, unsigned char ch,
   const Word ch_mask = repeat_byte<Word>(ch);
 
   // Step 2: read blocks
-  for (const Word *block_ptr = reinterpret_cast<const Word *>(char_ptr);
-       !has_zeroes<Word>((*block_ptr) ^ ch_mask) && cur < n;
-       ++block_ptr, cur += sizeof(Word)) {
-    char_ptr = reinterpret_cast<const unsigned char *>(block_ptr);
-  }
+  const Word *block_ptr = reinterpret_cast<const Word *>(char_ptr);
+  for (; !has_zeroes<Word>((*block_ptr) ^ ch_mask) && cur < n;
+       ++block_ptr, cur += sizeof(Word))
+    ;
+  char_ptr = reinterpret_cast<const unsigned char *>(block_ptr);
 
   // Step 3: find the match in the block
   for (; *char_ptr != ch && cur < n; ++char_ptr, ++cur) {
diff --git a/libc/test/src/string/memchr_test.cpp b/libc/test/src/string/memchr_test.cpp
index ede841118fe03..1db5ecaed40cd 100644
--- a/libc/test/src/string/memchr_test.cpp
+++ b/libc/test/src/string/memchr_test.cpp
@@ -21,6 +21,11 @@ const char *call_memchr(const void *src, int c, size_t size) {
   return reinterpret_cast<const char *>(LIBC_NAMESPACE::memchr(src, c, size));
 }
 
+TEST(LlvmLibcMemChrTest, FromProtoC) {
+  const char *src = "protobuf_cpp_version$\n";
+  ASSERT_STREQ(call_memchr(src, '$', 22), "$\n");
+}
+
 TEST(LlvmLibcMemChrTest, FindsCharacterAfterNullTerminator) {
   // memchr should continue searching after a null terminator.
   const size_t size = 5;

``````````

</details>


https://github.com/llvm/llvm-project/pull/166594