gh-65821: Fix ctypes.util.find_library with musl

Lib/ctypes/util.py

@@ -96,8 +96,11 @@ def find_library(name):
     def _is_elf(filename):
         "Return True if the given file is an ELF file"
         elf_header = b'\x7fELF'
-        with open(filename, 'br') as thefile:
-            return thefile.read(4) == elf_header
+        try:
+            with open(filename, 'br') as thefile:
+                return thefile.read(4) == elf_header
+        except OSError:
+            return False
 
     def _findLib_gcc(name):
         # Run GCC's linker with the -t (aka --trace) option and examine the
@@ -324,10 +327,55 @@ def _findLib_ld(name):
                 pass  # result will be None
             return result
 
+        def _findLib_musl(name):
+            # fallback for musl libc, which does not have ldconfig -p
+            # See GH-65821
+
+            from _ctypes import get_interp
+            interp = get_interp()
+            if interp == None:
+                return None
+
+            ldarch = re.sub(r'.*ld-musl-([^.]+)\..*', r'\1', interp)
+            if ldarch == interp:
+                # not musl
+                return None
+
+            from glob import glob
+            if os.path.isabs(name):
+                return name
+            if name.startswith("lib") and name.endswith(".so"):
+                suffixes = [ '.[0-9]*' ]
+                libname = name
+            else:
+                suffixes = ['.so', '.so.[0-9]*', f'.musl-{ldarch}.so.[0-9]*']
+                libname = 'lib'+name
+            # search LD_LIBRARY_PATH list and default musl libc locations
+            paths = os.environ.get('LD_LIBRARY_PATH', '').split(':')
+            try:
+                with open(f'/etc/ld-musl-{ldarch}.path') as f:
+                    paths.extend(re.split(':|\n', f.read()))
+            except OSError:
+                paths.extend(['/lib', '/usr/local/lib', '/usr/lib'])
+
+            for d in paths:
+                f = os.path.join(d, name)
+                if _is_elf(f):
+                    return os.path.basename(f)
+                prefix = os.path.join(d, libname)
+                for suffix in suffixes:
+                    for f in sorted(glob('{0}{1}'.format(prefix, suffix))):
+                        if _is_elf(f):
+                            return os.path.basename(f)
+
         def find_library(name):
             # See issue #9998
-            return _findSoname_ldconfig(name) or \
-                   _get_soname(_findLib_gcc(name)) or _get_soname(_findLib_ld(name))
+            return (
+                _findSoname_ldconfig(name)
+                or _get_soname(_findLib_gcc(name))
+                or _get_soname(_findLib_ld(name))
+                or _findLib_musl(name)
+            )
 
 ################################################################
 # test code
@@ -344,6 +392,7 @@ def test():
         print(find_library("m"))
         print(find_library("c"))
         print(find_library("bz2"))
+        print(find_library("libbz2.so"))
 
         # load
         if sys.platform == "darwin":
@@ -368,8 +417,8 @@ def test():
             print(f"crypto\t:: {find_library('crypto')}")
             print(f"crypto\t:: {cdll.LoadLibrary(find_library('crypto'))}")
         else:
-            print(cdll.LoadLibrary("libm.so"))
-            print(cdll.LoadLibrary("libcrypt.so"))
+            print(cdll.LoadLibrary(find_library("c")))
+            print(cdll.LoadLibrary("libc.so"))
             print(find_library("crypt"))
 
 if __name__ == "__main__":

Lib/test/test_ctypes/test_find.py

@@ -122,6 +122,15 @@ def test_find_library_with_ld(self):
              unittest.mock.patch("ctypes.util._findLib_gcc", lambda *args: None):
             self.assertNotEqual(find_library('c'), None)
 
+    def test_find_library_musl(self):
+        from _ctypes import get_interp
+        interp = get_interp()
+        if interp == None or interp.find("ld-musl-") == -1:
+            self.skipTest('ld-musl not detected')
+
+        with unittest.mock.patch("ctypes.util._findSoname_ldconfig", lambda *args: None), \
+             unittest.mock.patch("ctypes.util._get_soname", lambda *args: None):
+            self.assertNotEqual(find_library('c'), None)
 
 if __name__ == "__main__":
     unittest.main()

Misc/NEWS.d/next/Library/2021-02-10-16-05-03.bpo-21622.sNtCfz.rst

@@ -0,0 +1 @@
+Fix :func:`ctypes.util.find_library` with musl libc.

Modules/_ctypes/callproc.c

@@ -85,6 +85,13 @@
 #include <alloca.h>
 #endif
 
+#ifdef HAVE_ELF_H
+#include <elf.h>
+#endif
+#ifdef HAVE_LINK_H
+#include <link.h>
+#endif
+
 #ifdef _Py_MEMORY_SANITIZER
 #include <sanitizer/msan_interface.h>
 #endif
@@ -1992,7 +1999,52 @@ buffer_info(PyObject *self, PyObject *arg)
     return Py_BuildValue("siN", dict->format, dict->ndim, shape);
 }
 
+#ifndef MS_WIN32
+
+#ifdef HAVE_DL_ITERATE_PHDR
+static int
+interp_cb(struct dl_phdr_info *info, size_t size, void *data)
+{
+    const char **ps = data;
+    const char *base = (const char *)info->dlpi_addr;
+    const ElfW(Phdr) *ph = info->dlpi_phdr;
+    int phn = info->dlpi_phnum;
+
+    for (int i=0; i < phn; i++) {
+        if (ph[i].p_type == PT_INTERP) {
+            *ps = base + ph[i].p_vaddr;
+            return 1;
+        }
+    }
+    return 0;
+}
+
+static PyObject *
+get_interp(PyObject *self, PyObject *arg)
+{
+    const char *s = NULL;
+    if (PySys_Audit("ctypes.get_interp", NULL) < 0) {
+        return NULL;
+    }
 
+    if (dl_iterate_phdr(interp_cb, &s) == 1) {
+        return PyUnicode_FromString(s);
+    }
+
+    return NULL;
+}
+
+#else
+
+static PyObject *
+get_interp(PyObject *self, PyObject *arg)
+{
+    return Py_None;
+}
+
+#endif
+
+#endif
 
 PyMethodDef _ctypes_module_methods[] = {
     {"get_errno", get_errno, METH_NOARGS},
@@ -2015,6 +2067,7 @@ PyMethodDef _ctypes_module_methods[] = {
      "dlopen(name, flag={RTLD_GLOBAL|RTLD_LOCAL}) open a shared library"},
     {"dlclose", py_dl_close, METH_VARARGS, "dlclose a library"},
     {"dlsym", py_dl_sym, METH_VARARGS, "find symbol in shared library"},
+    {"get_interp", get_interp, METH_NOARGS},
 #endif
 #ifdef __APPLE__
      {"_dyld_shared_cache_contains_path", py_dyld_shared_cache_contains_path, METH_VARARGS, "check if path is in the shared cache"},

configure.ac

@@ -2755,8 +2755,8 @@ AC_DEFINE(STDC_HEADERS, 1, [Define to 1 if you have the ANSI C header files.])
 
 # checks for header files
 AC_CHECK_HEADERS([ \
-  alloca.h asm/types.h bluetooth.h conio.h crypt.h direct.h dlfcn.h endian.h errno.h fcntl.h grp.h \
-  ieeefp.h io.h langinfo.h libintl.h libutil.h linux/auxvec.h sys/auxv.h linux/fs.h linux/memfd.h \
+  alloca.h asm/types.h bluetooth.h conio.h crypt.h direct.h dlfcn.h elf.h endian.h errno.h fcntl.h grp.h \
+  ieeefp.h io.h langinfo.h libintl.h libutil.h link.h linux/auxvec.h sys/auxv.h linux/fs.h linux/memfd.h \
   linux/random.h linux/soundcard.h \
   linux/tipc.h linux/wait.h netdb.h net/ethernet.h netinet/in.h netpacket/packet.h poll.h process.h pthread.h pty.h \
   sched.h setjmp.h shadow.h signal.h spawn.h stropts.h sys/audioio.h sys/bsdtty.h sys/devpoll.h \
@@ -4717,7 +4717,7 @@ fi
 # checks for library functions
 AC_CHECK_FUNCS([ \
   accept4 alarm bind_textdomain_codeset chmod chown clock close_range confstr \
-  copy_file_range ctermid dup dup3 execv explicit_bzero explicit_memset \
+  copy_file_range ctermid dl_iterate_phdr dup dup3 execv explicit_bzero explicit_memset \
   faccessat fchmod fchmodat fchown fchownat fdopendir fdwalk fexecve \
   fork fork1 fpathconf fstatat ftime ftruncate futimens futimes futimesat \
   gai_strerror getegid getentropy geteuid getgid getgrgid getgrgid_r \

pyconfig.h.in

@@ -290,6 +290,9 @@
 /* Define to 1 if you have the `dlopen' function. */
 #undef HAVE_DLOPEN
 
+/* Define to 1 if you have the `dl_iterate_phdr' function. */
+#undef HAVE_DL_ITERATE_PHDR
+
 /* Define to 1 if you have the `dup' function. */
 #undef HAVE_DUP
 
@@ -308,6 +311,9 @@
 /* Define to 1 if you have the <editline/readline.h> header file. */
 #undef HAVE_EDITLINE_READLINE_H
 
+/* Define to 1 if you have the <elf.h> header file. */
+#undef HAVE_ELF_H
+
 /* Define to 1 if you have the <endian.h> header file. */
 #undef HAVE_ENDIAN_H
 
@@ -703,6 +709,9 @@
 /* Define to 1 if you have the `linkat' function. */
 #undef HAVE_LINKAT
 
+/* Define to 1 if you have the <link.h> header file. */
+#undef HAVE_LINK_H
+
 /* Define to 1 if you have the <linux/auxvec.h> header file. */
 #undef HAVE_LINUX_AUXVEC_H