On macOS, the system regex engine leaks an internal buffer when
regexec() encounters an invalid multibyte sequence in a UTF-8 locale.
The line-by-line path can call regexec_buf() for each pattern on every
line, so "git grep" can leak repeatedly on a file containing invalid
UTF-8. The total leak grows with the number of calls, and the per-call
allocation grows with the pattern's automaton. In one case, grepping a
repository containing PDFs exhausted memory and caused the machine to
restart.
ce025ae4f61e (grep: disable lookahead on error, 2024-10-20) made "git
grep" fall back to line-by-line matching when regexec() reports an error
on invalid UTF-8. That fallback cannot prevent this leak: the allocation
has already leaked when regexec() returns REG_ILLSEQ.
Avoid the leaking path by providing a Darwin-specific regexec_buf().
Walk the input with mbrtowc(), split it at bytes that cannot form a
complete multibyte character, and search each valid segment separately.
This preserves matches in valid text on either side of an invalid byte.
Search each segment with REG_STARTEND so match offsets remain relative to
the original buffer. Set REG_NOTBOL and REG_NOTEOL for internal segment
boundaries so "^" and "$" do not match there. Keep the flags clear at
the true beginning and end of the buffer.
Use the normal regexec_buf() path in single-byte locales, where no byte
can form an invalid multibyte sequence. Use the bundled regex
implementation unchanged when NO_REGEX is enabled.
Declare the Darwin override in compat/darwin.h and map regexec_buf() to
darwin_regexec_buf(). This follows the platform override pattern used
by the other compatibility headers and leaves the common inline
implementation as the default.
There is no reliable way to detect a future macOS version in which the
system regex implementation has been fixed. Even after a fix, Git will
need the workaround while it supports affected macOS releases, so treat
it as an indefinite compatibility workaround.
Add tests for matches before, after, and between invalid bytes, including
an offset check after an invalid byte. Also check incomplete trailing
input and anchors at true and internal line boundaries.
Signed-off-by: Chungmin Lee <chungmin@chungminlee.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
COMPAT_CFLAGS += -DUSE_ENHANCED_BASIC_REGULAR_EXPRESSIONS
COMPAT_OBJS += compat/regcomp_enhanced.o
endif
+ifdef DARWIN_REGEXEC
+ COMPAT_OBJS += compat/darwin/regexec.o
+ BASIC_CFLAGS += -DDARWIN_REGEXEC
+endif
endif
ifdef NATIVE_CRLF
BASIC_CFLAGS += -DNATIVE_CRLF
--- /dev/null
+#ifndef COMPAT_DARWIN_H
+#define COMPAT_DARWIN_H
+
+int darwin_regexec_buf(const regex_t *preg, const char *buf, size_t size,
+ size_t nmatch, regmatch_t pmatch[], int eflags);
+#define regexec_buf darwin_regexec_buf
+
+#endif
--- /dev/null
+#include "git-compat-util.h"
+
+#include <wchar.h>
+
+/*
+ * Darwin's TRE regex engine leaks an internal buffer when it encounters an
+ * invalid multibyte sequence. Since the leak has already happened when
+ * regexec() reports REG_ILLSEQ, keep invalid bytes out of regexec() by
+ * searching each valid segment separately.
+ */
+
+/*
+ * Search buf[start, end), where size is the full size of buf. REG_STARTEND
+ * keeps match offsets relative to buf. Do not let an internal segment create
+ * a false beginning or end of line.
+ */
+static int regexec_segment(const regex_t *preg, const char *buf,
+ size_t size, size_t start, size_t end,
+ size_t nmatch, regmatch_t pmatch[], int eflags)
+{
+ eflags |= REG_STARTEND;
+ if (start > 0)
+ eflags |= REG_NOTBOL;
+ if (end < size)
+ eflags |= REG_NOTEOL;
+ pmatch[0].rm_so = start;
+ pmatch[0].rm_eo = end;
+ return regexec(preg, buf, nmatch, pmatch, eflags);
+}
+
+int darwin_regexec_buf(const regex_t *preg, const char *buf, size_t size,
+ size_t nmatch, regmatch_t pmatch[], int eflags)
+{
+ size_t seg_start = 0, i = 0;
+ mbstate_t mbs;
+
+ assert(nmatch > 0 && pmatch);
+
+ /*
+ * A single-byte locale cannot contain an invalid multibyte sequence,
+ * so use regexec() directly.
+ */
+ if (MB_CUR_MAX == 1) {
+ pmatch[0].rm_so = 0;
+ pmatch[0].rm_eo = size;
+ return regexec(preg, buf, nmatch, pmatch, eflags | REG_STARTEND);
+ }
+
+ memset(&mbs, 0, sizeof(mbs));
+ while (i < size) {
+ unsigned char c = (unsigned char)buf[i];
+ size_t n;
+
+ if (c < 0x80) {
+ i++;
+ continue;
+ }
+
+ n = mbrtowc(NULL, buf + i, size - i, &mbs);
+ if (!n)
+ n = 1;
+ if (n != (size_t)-1 && n != (size_t)-2) {
+ i += n;
+ continue;
+ }
+
+ /*
+ * -1 denotes an encoding error; -2 denotes an incomplete
+ * trailing sequence. In either case, buf[i] cannot begin a
+ * complete valid character within this buffer. Search an
+ * empty initial segment to preserve zero-width matches at the
+ * true beginning.
+ */
+ if (i > seg_start || i == 0) {
+ int ret = regexec_segment(preg, buf, size, seg_start, i,
+ nmatch, pmatch, eflags);
+ if (ret != REG_NOMATCH)
+ return ret;
+ }
+ i++;
+ seg_start = i;
+ memset(&mbs, 0, sizeof(mbs));
+ }
+
+ /*
+ * Search the final segment even when it is empty, so an empty buffer
+ * or a buffer ending in invalid bytes still has its true end.
+ */
+ return regexec_segment(preg, buf, size, seg_start, size,
+ nmatch, pmatch, eflags);
+}
HAVE_DEV_TTY = YesPlease
COMPAT_OBJS += compat/precompose_utf8.o
BASIC_CFLAGS += -DPRECOMPOSE_UNICODE
+ DARWIN_REGEXEC = YesPlease
BASIC_CFLAGS += -DPROTECT_HFS_DEFAULT=1
HAVE_BSD_SYSCTL = YesPlease
FREAD_READS_DIRECTORIES = UnfortunatelyYes
include_directories(${CMAKE_SOURCE_DIR}/compat/regex)
list(APPEND compat_SOURCES compat/regex/regex.c )
add_compile_definitions(NO_REGEX NO_MBSUPPORT GAWK)
+elseif(APPLE)
+ list(APPEND compat_SOURCES compat/darwin/regexec.c)
+ add_compile_definitions(DARWIN_REGEXEC)
endif()
#include "compat/win32/path-utils.h"
#include "compat/msvc.h"
#endif
+#ifdef DARWIN_REGEXEC
+#include "compat/darwin.h"
+#endif
/* used on Mac OS X */
#ifdef PRECOMPOSE_UNICODE
#error "Git requires REG_STARTEND support. Compile with NO_REGEX=NeedsStartEnd"
#endif
+#ifndef regexec_buf
static inline int regexec_buf(const regex_t *preg, const char *buf, size_t size,
size_t nmatch, regmatch_t pmatch[], int eflags)
{
pmatch[0].rm_eo = size;
return regexec(preg, buf, nmatch, pmatch, eflags | REG_STARTEND);
}
+#endif
#ifdef USE_ENHANCED_BASIC_REGULAR_EXPRESSIONS
int git_regcomp(regex_t *preg, const char *pattern, int cflags);
libgit_c_args += '-DUSE_ENHANCED_BASIC_REGULAR_EXPRESSIONS'
compat_sources += 'compat/regcomp_enhanced.c'
endif
+
+ if host_machine.system() == 'darwin'
+ libgit_c_args += '-DDARWIN_REGEXEC'
+ compat_sources += 'compat/darwin/regexec.c'
+ endif
elif not get_option('regex').enabled()
libgit_c_args += [
'-DNO_REGEX',
function dummy() {}
EOF
printf "\200\nASCII\n" >invalid-utf8 &&
+ printf "before\346world\n" >invalid-utf8-embedded &&
+ printf "a\346b\347c\n" >invalid-utf8-multi &&
+ printf "\346world\n" >invalid-utf8-leading &&
+ printf "before\346\n" >invalid-utf8-trailing &&
if test_have_prereq FUNNYNAMES
then
echo unusual >"\"unusual\" pathname" &&
LC_ALL=en_US.UTF-8 test_expect_code 1 git grep ".." reverse-question-mark
'
+test_expect_success MACOS,MB_REGEX 'grep matches valid text on both sides of invalid UTF-8' '
+ LC_ALL=en_US.UTF-8 git grep -h "befo[r]e" invalid-utf8-embedded >actual &&
+ test_cmp invalid-utf8-embedded actual &&
+ LC_ALL=en_US.UTF-8 git grep -h "worl[d]" invalid-utf8-embedded >actual &&
+ test_cmp invalid-utf8-embedded actual &&
+ LC_ALL=en_US.UTF-8 git grep -h -o "worl[d]" invalid-utf8-embedded >actual &&
+ echo world >expected &&
+ test_cmp expected actual
+'
+
+test_expect_success MACOS,MB_REGEX 'grep matches a run between two invalid sequences' '
+ LC_ALL=en_US.UTF-8 git grep -h "[b]" invalid-utf8-multi >actual &&
+ test_cmp invalid-utf8-multi actual
+'
+
+test_expect_success MB_REGEX 'grep does not anchor ^ or $ inside an invalid-byte line' '
+ test_expect_code 1 env LC_ALL=en_US.UTF-8 \
+ git grep -h "^world" invalid-utf8-embedded &&
+ test_expect_code 1 env LC_ALL=en_US.UTF-8 \
+ git grep -h "before\$" invalid-utf8-embedded
+'
+
+test_expect_success MACOS,MB_REGEX 'grep anchors ^ and $ at true line ends past invalid UTF-8' '
+ LC_ALL=en_US.UTF-8 git grep -h "^before" invalid-utf8-embedded >actual &&
+ test_cmp invalid-utf8-embedded actual &&
+ LC_ALL=en_US.UTF-8 git grep -h "world\$" invalid-utf8-embedded >actual &&
+ test_cmp invalid-utf8-embedded actual &&
+ LC_ALL=en_US.UTF-8 git grep -h "^" invalid-utf8-leading >actual &&
+ test_cmp invalid-utf8-leading actual &&
+ LC_ALL=en_US.UTF-8 git grep -h "\$" invalid-utf8-trailing >actual &&
+ test_cmp invalid-utf8-trailing actual
+'
+
cat >expected <<EOF
file
EOF