This is an automated email from the ASF dual-hosted git repository. xiaoxiang781216 pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/nuttx.git
commit 35176f627711736a0beef7243c95e19cb1ee015b Author: wangmingrong1 <[email protected]> AuthorDate: Mon Nov 2 16:08:35 2026 +0800 tools/gcov: accept little-endian profraw magic in is_profraw_file Root cause: the LLVM raw profile header magic is a uint64_t written by the runtime in native byte order (high byte 0xff, low byte 0x81 with "lprofr"/"lprofR" in the middle). On big-endian targets this lands on disk as \xff..\x81, but on little-endian targets (ARM aarch64, x86_64, sim) it lands as \x81..\xff. The previous magic check only matched the big-endian form, so profraw files dumped on goldfish-arm64-v8a-ap (and every other LE board) were misclassified as text and routed into parse_gcda_data(), which opens them as utf-8 and immediately raises "UnicodeDecodeError: 'utf-8' codec can't decode byte 0x81 in position 0", failing Vela_System_Tools_Gcov_Integration. Fix: accept both the native and byte-swapped 8-byte magic in is_profraw_file(), mirroring LLVM's RawInstrProfReader::hasFormat which compares the on-disk magic against both forms. This unblocks the clang coverage pipeline on every little-endian target without affecting the big-endian path or the gcc / hex-dump / binpack branches. Signed-off-by: wangmingrong1 <[email protected]> --- tools/gcov.py | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/tools/gcov.py b/tools/gcov.py index 01b90d22c85..a13e4fcba0c 100755 --- a/tools/gcov.py +++ b/tools/gcov.py @@ -26,9 +26,17 @@ import struct import subprocess import sys -# LLVM raw profile magic bytes (first 8 bytes of .profraw) -# 64-bit: \xff lprofr \x81 -# 32-bit: \xff lprofR \x81 +# LLVM raw profile magic bytes (first 8 bytes of .profraw). +# +# The magic is a uint64_t written by the runtime in native byte order +# (high byte 0xff, low byte 0x81; "lprofr"/"lprofR" in the middle), so +# big-endian platforms produce \xff..\x81 and little-endian platforms +# (ARM aarch64, x86_64, etc.) produce \x81..\xff. Both forms must be +# accepted, mirroring LLVM's RawInstrProfReader::hasFormat which compares +# the on-disk magic against both the native and byte-swapped values. +# +# 64-bit BE: \xff lprofr \x81 / 64-bit LE: \x81 rforpl \xff +# 32-bit BE: \xff lprofR \x81 / 32-bit LE: \x81 Rforpl \xff PROFRAW_MAGIC_64 = b"\xff\x6c\x70\x72\x6f\x66\x72\x81" PROFRAW_MAGIC_32 = b"\xff\x6c\x70\x72\x6f\x66\x52\x81" @@ -42,11 +50,20 @@ GCOV_BINPACK_PATH_LEN_MAX = 4096 def is_profraw_file(path): - """Check if a file is an LLVM profraw file by magic number.""" + """Check if a file is an LLVM profraw file by magic number. + + Accepts both native and byte-swapped magic so that profraw files + produced on either little- or big-endian targets are recognised. + """ try: with open(path, "rb") as f: magic = f.read(8) - return magic == PROFRAW_MAGIC_64 or magic == PROFRAW_MAGIC_32 + return magic in ( + PROFRAW_MAGIC_64, + PROFRAW_MAGIC_64[::-1], + PROFRAW_MAGIC_32, + PROFRAW_MAGIC_32[::-1], + ) except (IOError, OSError): return False
