[libc][bug] Fix out of bound write in memcpy wi software prefetching

This bug showed up when running fuzzers newly added fuzzers llvm#90591.

Author: gchatelet

libc/src/string/memory_utils/x86_64/inline_memcpy.h

@@ -107,7 +107,13 @@ inline_memcpy_x86_sse2_ge64_sw_prefetching(Ptr __restrict dst,
       offset += K_THREE_CACHELINES;
     }
   }
-  return builtin::Memcpy<32>::loop_and_tail_offset(dst, src, count, offset);
+  // We don't use 'loop_and_tail_offset' because it assumes at least one
+  // iteration of the loop.
+  while (offset + 32 <= count) {
+    builtin::Memcpy<32>::block_offset(dst, src, offset);
+    offset += 32;
+  }
+  return builtin::Memcpy<32>::tail(dst, src, count);
 }
 
 [[maybe_unused]] LIBC_INLINE void
@@ -140,6 +146,12 @@ inline_memcpy_x86_avx_ge64_sw_prefetching(Ptr __restrict dst,
     offset += K_THREE_CACHELINES;
   }
   return builtin::Memcpy<64>::loop_and_tail_offset(dst, src, count, offset);
+  // We don't use 'loop_and_tail_offset' because it assumes at least one
+  // iteration of the loop.
+  while (offset + 64 <= count) {
+    builtin::Memcpy<64>::block_offset(dst, src, offset);
+    offset += 64;
+  }
 }
 
 [[maybe_unused]] LIBC_INLINE void