[compiler-rt][asan] Reland: wcscpy/wcsncpy interceptors and stabilize wchar tests on Darwin/Android #162028
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
llvmbot
added
compiler-rt
compiler-rt:asan
|
@llvm/pr-subscribers-compiler-rt-sanitizer Author: Yixuan Cao (Cao-Wuhui) ChangesSummaryReland: wcscpy/wcsncpy interceptors and stabilize wchar tests on Darwin/Android. Functional reland (runtime + tests). ContextReland of #160493 and #161624; previously reverted by #162021 and #162001 to restore green. Motivation
Runtime (wcscpy/wcsncpy)
Tests (wcscpy/wcsncpy/wcscat/wcsncat)
// CHECK-DAG: Good so far.
// CHECK-DAG: ERROR: AddressSanitizer: stack-buffer-overflow on address [[ADDR:...]] at pc {{...}} bp {{...}} sp {{...}}
// CHECK-DAG: WRITE of size {{[0-9]+}} at [[ADDR]] thread T0
// CHECK-DAG: #<!-- -->0 {{0x[0-9a-f]+}} in <func>Risk
Full diff: https://github.com/llvm/llvm-project/pull/162028.diff 8 Files Affected:
diff --git a/compiler-rt/lib/asan/asan_interceptors.cpp b/compiler-rt/lib/asan/asan_interceptors.cpp
index 7c9a08b9083a2..0f613f0fdc30b 100644
--- a/compiler-rt/lib/asan/asan_interceptors.cpp
+++ b/compiler-rt/lib/asan/asan_interceptors.cpp
@@ -58,13 +58,20 @@ namespace __asan {
static inline uptr MaybeRealStrnlen(const char *s, uptr maxlen) {
#if SANITIZER_INTERCEPT_STRNLEN
- if (REAL(strnlen)) {
+ if (REAL(strnlen))
return REAL(strnlen)(s, maxlen);
- }
-#endif
+# endif
return internal_strnlen(s, maxlen);
}
+static inline uptr MaybeRealWcsnlen(const wchar_t* s, uptr maxlen) {
+# if SANITIZER_INTERCEPT_WCSNLEN
+ if (REAL(wcsnlen))
+ return REAL(wcsnlen)(s, maxlen);
+# endif
+ return internal_wcsnlen(s, maxlen);
+}
+
void SetThreadName(const char *name) {
AsanThread *t = GetCurrentThread();
if (t)
@@ -570,6 +577,20 @@ INTERCEPTOR(char *, strcpy, char *to, const char *from) {
return REAL(strcpy)(to, from);
}
+INTERCEPTOR(wchar_t*, wcscpy, wchar_t* to, const wchar_t* from) {
+ void* ctx;
+ ASAN_INTERCEPTOR_ENTER(ctx, wcscpy);
+ if (!TryAsanInitFromRtl())
+ return REAL(wcscpy)(to, from);
+ if (flags()->replace_str) {
+ uptr size = (internal_wcslen(from) + 1) * sizeof(wchar_t);
+ CHECK_RANGES_OVERLAP("wcscpy", to, size, from, size);
+ ASAN_READ_RANGE(ctx, from, size);
+ ASAN_WRITE_RANGE(ctx, to, size);
+ }
+ return REAL(wcscpy)(to, from);
+}
+
// Windows doesn't always define the strdup identifier,
// and when it does it's a macro defined to either _strdup
// or _strdup_dbg, _strdup_dbg ends up calling _strdup, so
@@ -633,6 +654,20 @@ INTERCEPTOR(char*, strncpy, char *to, const char *from, usize size) {
return REAL(strncpy)(to, from, size);
}
+INTERCEPTOR(wchar_t*, wcsncpy, wchar_t* to, const wchar_t* from, uptr size) {
+ void* ctx;
+ ASAN_INTERCEPTOR_ENTER(ctx, wcsncpy);
+ AsanInitFromRtl();
+ if (flags()->replace_str) {
+ uptr from_size =
+ Min(size, MaybeRealWcsnlen(from, size) + 1) * sizeof(wchar_t);
+ CHECK_RANGES_OVERLAP("wcsncpy", to, from_size, from, from_size);
+ ASAN_READ_RANGE(ctx, from, from_size);
+ ASAN_WRITE_RANGE(ctx, to, size * sizeof(wchar_t));
+ }
+ return REAL(wcsncpy)(to, from, size);
+}
+
template <typename Fn>
static ALWAYS_INLINE auto StrtolImpl(void *ctx, Fn real, const char *nptr,
char **endptr, int base)
@@ -809,6 +844,11 @@ void InitializeAsanInterceptors() {
ASAN_INTERCEPT_FUNC(strncat);
ASAN_INTERCEPT_FUNC(strncpy);
ASAN_INTERCEPT_FUNC(strdup);
+
+ // Intercept wcs* functions.
+ ASAN_INTERCEPT_FUNC(wcscpy);
+ ASAN_INTERCEPT_FUNC(wcsncpy);
+
# if ASAN_INTERCEPT___STRDUP
ASAN_INTERCEPT_FUNC(__strdup);
#endif
diff --git a/compiler-rt/lib/asan/asan_interceptors.h b/compiler-rt/lib/asan/asan_interceptors.h
index 3e2386eaf8092..2d551cfafd1f5 100644
--- a/compiler-rt/lib/asan/asan_interceptors.h
+++ b/compiler-rt/lib/asan/asan_interceptors.h
@@ -129,6 +129,7 @@ DECLARE_REAL(char*, strchr, const char *str, int c)
DECLARE_REAL(SIZE_T, strlen, const char *s)
DECLARE_REAL(char*, strncpy, char *to, const char *from, SIZE_T size)
DECLARE_REAL(SIZE_T, strnlen, const char *s, SIZE_T maxlen)
+DECLARE_REAL(SIZE_T, wcsnlen, const wchar_t* s, SIZE_T maxlen)
DECLARE_REAL(char*, strstr, const char *s1, const char *s2)
# if !SANITIZER_APPLE
diff --git a/compiler-rt/lib/asan/asan_win_static_runtime_thunk.cpp b/compiler-rt/lib/asan/asan_win_static_runtime_thunk.cpp
index 4a69b66574039..46e0e90738f24 100644
--- a/compiler-rt/lib/asan/asan_win_static_runtime_thunk.cpp
+++ b/compiler-rt/lib/asan/asan_win_static_runtime_thunk.cpp
@@ -63,6 +63,10 @@ INTERCEPT_LIBRARY_FUNCTION_ASAN(strpbrk);
INTERCEPT_LIBRARY_FUNCTION_ASAN(strspn);
INTERCEPT_LIBRARY_FUNCTION_ASAN(strstr);
INTERCEPT_LIBRARY_FUNCTION_ASAN(strtok);
+INTERCEPT_LIBRARY_FUNCTION_ASAN(wcscat);
+INTERCEPT_LIBRARY_FUNCTION_ASAN(wcscpy);
+INTERCEPT_LIBRARY_FUNCTION_ASAN(wcsncat);
+INTERCEPT_LIBRARY_FUNCTION_ASAN(wcsncpy);
INTERCEPT_LIBRARY_FUNCTION_ASAN(wcslen);
INTERCEPT_LIBRARY_FUNCTION_ASAN(wcsnlen);
diff --git a/compiler-rt/lib/sanitizer_common/sanitizer_platform_interceptors.h b/compiler-rt/lib/sanitizer_common/sanitizer_platform_interceptors.h
index 29987decdff45..88ecd7e16306a 100644
--- a/compiler-rt/lib/sanitizer_common/sanitizer_platform_interceptors.h
+++ b/compiler-rt/lib/sanitizer_common/sanitizer_platform_interceptors.h
@@ -551,7 +551,7 @@ SANITIZER_WEAK_IMPORT void *aligned_alloc(__sanitizer::usize __alignment,
#define SANITIZER_INTERCEPT_MALLOC_USABLE_SIZE (!SI_MAC && !SI_NETBSD)
#define SANITIZER_INTERCEPT_MCHECK_MPROBE SI_LINUX_NOT_ANDROID
#define SANITIZER_INTERCEPT_WCSLEN 1
-#define SANITIZER_INTERCEPT_WCSCAT SI_POSIX
+#define SANITIZER_INTERCEPT_WCSCAT (SI_POSIX || SI_WINDOWS)
#define SANITIZER_INTERCEPT_WCSDUP SI_POSIX
#define SANITIZER_INTERCEPT_SIGNAL_AND_SIGACTION (!SI_WINDOWS && SI_NOT_FUCHSIA)
#define SANITIZER_INTERCEPT_BSD_SIGNAL SI_ANDROID
diff --git a/compiler-rt/test/asan/TestCases/wcscat.cpp b/compiler-rt/test/asan/TestCases/wcscat.cpp
new file mode 100644
index 0000000000000..833dee9655264
--- /dev/null
+++ b/compiler-rt/test/asan/TestCases/wcscat.cpp
@@ -0,0 +1,26 @@
+// RUN: %clangxx_asan -O0 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O1 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O2 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O3 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+
+#include <stdio.h>
+#include <wchar.h>
+
+int main() {
+ const wchar_t *start = L"X means ";
+ const wchar_t *append = L"dog";
+ wchar_t goodDst[12];
+ wcscpy(goodDst, start);
+ wcscat(goodDst, append);
+
+ wchar_t badDst[9];
+ wcscpy(badDst, start);
+ fprintf(stderr, "Good so far.\n");
+ // CHECK-DAG: Good so far.
+ fflush(stderr);
+ wcscat(badDst, append); // Boom!
+ // CHECK-DAG: ERROR: AddressSanitizer: stack-buffer-overflow on address [[ADDR:0x[0-9a-f]+]] at pc {{0x[0-9a-f]+}} bp {{0x[0-9a-f]+}} sp {{0x[0-9a-f]+}}
+ // CHECK-DAG: WRITE of size {{[0-9]+}} at [[ADDR]] thread T0
+ // CHECK-DAG: #0 {{0x[0-9a-f]+}} in wcscat
+ printf("Should have failed with ASAN error.\n");
+}
\ No newline at end of file
diff --git a/compiler-rt/test/asan/TestCases/wcscpy.cpp b/compiler-rt/test/asan/TestCases/wcscpy.cpp
new file mode 100644
index 0000000000000..c7205e486e3ff
--- /dev/null
+++ b/compiler-rt/test/asan/TestCases/wcscpy.cpp
@@ -0,0 +1,23 @@
+// RUN: %clangxx_asan -O0 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O1 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O2 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O3 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+
+#include <stdio.h>
+#include <wchar.h>
+
+int main() {
+ const wchar_t *src = L"X means dog";
+ wchar_t goodDst[12];
+ wcscpy(goodDst, src);
+
+ wchar_t badDst[7];
+ fprintf(stderr, "Good so far.\n");
+ // CHECK-DAG: Good so far.
+ fflush(stderr);
+ wcscpy(badDst, src); // Boom!
+ // CHECK-DAG: ERROR: AddressSanitizer: stack-buffer-overflow on address [[ADDR:0x[0-9a-f]+]] at pc {{0x[0-9a-f]+}} bp {{0x[0-9a-f]+}} sp {{0x[0-9a-f]+}}
+ // CHECK-DAG: WRITE of size {{[0-9]+}} at [[ADDR]] thread T0
+ // CHECK-DAG: #0 {{0x[0-9a-f]+}} in wcscpy
+ printf("Should have failed with ASAN error.\n");
+}
\ No newline at end of file
diff --git a/compiler-rt/test/asan/TestCases/wcsncat.cpp b/compiler-rt/test/asan/TestCases/wcsncat.cpp
new file mode 100644
index 0000000000000..8fe1e510a26cf
--- /dev/null
+++ b/compiler-rt/test/asan/TestCases/wcsncat.cpp
@@ -0,0 +1,27 @@
+// RUN: %clangxx_asan -O0 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O1 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O2 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O3 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+
+#include <stdio.h>
+#include <wchar.h>
+
+int main() {
+ const wchar_t *start = L"X means ";
+ const wchar_t *append = L"dog";
+ wchar_t goodDst[15];
+ wcscpy(goodDst, start);
+ wcsncat(goodDst, append, 5);
+
+ wchar_t badDst[11];
+ wcscpy(badDst, start);
+ wcsncat(badDst, append, 1);
+ fprintf(stderr, "Good so far.\n");
+ // CHECK-DAG: Good so far.
+ fflush(stderr);
+ wcsncat(badDst, append, 3); // Boom!
+ // CHECK-DAG: ERROR: AddressSanitizer: stack-buffer-overflow on address [[ADDR:0x[0-9a-f]+]] at pc {{0x[0-9a-f]+}} bp {{0x[0-9a-f]+}} sp {{0x[0-9a-f]+}}
+ // CHECK-DAG: WRITE of size {{[0-9]+}} at [[ADDR]] thread T0
+ // CHECK-DAG: #0 {{0x[0-9a-f]+}} in wcsncat
+ printf("Should have failed with ASAN error.\n");
+}
\ No newline at end of file
diff --git a/compiler-rt/test/asan/TestCases/wcsncpy.cpp b/compiler-rt/test/asan/TestCases/wcsncpy.cpp
new file mode 100644
index 0000000000000..7db3351cdb6a6
--- /dev/null
+++ b/compiler-rt/test/asan/TestCases/wcsncpy.cpp
@@ -0,0 +1,24 @@
+// RUN: %clangxx_asan -O0 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O1 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O2 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+// RUN: %clangxx_asan -O3 %s -o %t && not %env_asan_opts=log_to_stderr=1 %run %t 2>&1 | FileCheck %s --check-prefix=CHECK
+
+#include <stdio.h>
+#include <wchar.h>
+
+int main() {
+ const wchar_t *src = L"X means dog";
+ wchar_t goodDst[12];
+ wcsncpy(goodDst, src, 12);
+
+ wchar_t badDst[7];
+ wcsncpy(badDst, src, 7); // This should still work.
+ fprintf(stderr, "Good so far.\n");
+ // CHECK-DAG: Good so far.
+ fflush(stderr);
+ wcsncpy(badDst, src, 15); // Boom!
+ // CHECK-DAG: ERROR: AddressSanitizer: stack-buffer-overflow on address [[ADDR:0x[0-9a-f]+]] at pc {{0x[0-9a-f]+}} bp {{0x[0-9a-f]+}} sp {{0x[0-9a-f]+}}
+ // CHECK-DAG: WRITE of size {{[0-9]+}} at [[ADDR]] thread T0
+ // CHECK-DAG: #0 {{0x[0-9a-f]+}} in wcsncpy
+ printf("Should have failed with ASAN error.\n");
+}
\ No newline at end of file
|
|
Could you please make this pull request a stack of three commits (in one pull request):
It would make this much easier to see what's been fixed. (The commits will be automatically squashed before merging, so it won't negataively affect the LLVM commit history.) |
Cao-Wuhui
force-pushed
the
asan-wchar-reland-all
branch
from
a0def21 to
304e76e
Compare
Thank you for the review and guidance, I’ve split this PR into a stack of 3 commits. Please let me know if any further adjustments would be helpful. I’d be happy to revise. |
|
Thanks! Looks good to me, but prior to merging I'd like to get @wrotki's feedback (perhaps with testing on one of their Darwin buildbots if possible?). |
wrotki
reviewed
Oct 5, 2025
| // CHECK: WRITE of size {{[0-9]+}} at [[ADDR:0x[0-9a-f]+]] thread T0 | ||
| // CHECK: #0 [[ADDR:0x[0-9a-f]+]] in wcscat{{.*}}sanitizer_common_interceptors.inc:{{[0-9]+}} | ||
| printf("Should have failed with ASAN error.\n"); | ||
| } No newline at end of file |
There was a problem hiding this comment.
I think all files you added were missing a newline at last line (Github flags it) .
There was a problem hiding this comment.
I think all files you added were missing a newline at last line (Github flags it) .
Thanks for pointing that out! I'll add the missing newline right away.
Signed-off-by: Yixuan Cao <[email protected]>
wrotki
approved these changes
Oct 6, 2025
There was a problem hiding this comment.
Thanks for fixing newlines.
I could not really run this PR on Darwin bot (we're missing this functionality). But I did a buddy test, i.e. synced the PR to my macOS machine and tested it with check-asan.
This test succeeded - I also verified that changing order of matching doesn't break it, as on my machine 'Good so far.' log comes on top, where on the bot it's the opposite.
So I'm going to call it good. Thanks for contributing.
thurstond
approved these changes
Oct 6, 2025
|
Thanks @wrotki for testing on your macOS machine! |
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/72/builds/15363 Here is the relevant piece of the build log for the reference |
aokblast
pushed a commit
to aokblast/llvm-project
that referenced
this pull request
Oct 6, 2025
… wchar tests on Darwin/Android (llvm#162028) ### Summary Reland: wcscpy/wcsncpy interceptors and stabilize wchar tests on Darwin/Android. Functional reland (runtime + tests). ### Context Reland of llvm#160493 and llvm#161624; previously reverted by llvm#162021 and llvm#162001 to restore green. ### Motivation - Restore wchar interceptors (wcscpy/wcsncpy), broaden ASan coverage, and improve Windows parity with narrow-string checks. - Make tests robust across Darwin/Android to keep bots green. ### Runtime (wcscpy/wcsncpy) - Add overlap checks; mark read/write ranges in bytes. - Use MaybeRealWcsnlen when available to bound reads. - Register Windows static runtime thunk where applicable. ### Tests (wcscpy/wcsncpy/wcscat/wcsncat) - Android: keep `%env_asan_opts=log_to_stderr=1` so the ASan header is on stderr. - Darwin: tolerate reordering by putting all four key lines in one DAG group: ```cpp // CHECK-DAG: Good so far. // CHECK-DAG: ERROR: AddressSanitizer: stack-buffer-overflow on address [[ADDR:...]] at pc {{...}} bp {{...}} sp {{...}} // CHECK-DAG: WRITE of size {{[0-9]+}} at [[ADDR]] thread T0 // CHECK-DAG: #0 {{0x[0-9a-f]+}} in <func> ``` ### Risk - Functional reland (runtime + tests), intended to restore functionality and maintain stability across platforms. --------- Signed-off-by: Yixuan Cao <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Reland: wcscpy/wcsncpy interceptors and stabilize wchar tests on Darwin/Android. Functional reland (runtime + tests).
Context
Reland of #160493 and #161624; previously reverted by #162021 and #162001 to restore green.
Motivation
Runtime (wcscpy/wcsncpy)
Tests (wcscpy/wcsncpy/wcscat/wcsncat)
%env_asan_opts=log_to_stderr=1so the ASan header is on stderr.Risk