Merge #13724: [contrib] Support ARM and RISC-V symbol check

c516c3a770 [contrib] Support ARM and RISC-V symbol check (Chun Kuan Lee)

Pull request description:

  Solve the TODO in the gitian-descripter

Tree-SHA512: 8115e2958af3dde43d9d9d05f0b1b1b93b1c2aa513e771a3e4e1342a5d78af2b0e40c0bbb7e9a0d15954897317e6f5a0d80996239af3b376d5ddd527f73428ae

contrib/devtools/symbol-check.py

@@ -36,17 +36,18 @@ import os
 #   (glibc)    GLIBC_2_11
 #
 MAX_VERSIONS = {
-'GCC':     (4,4,0),
+'GCC':       (4,4,0),
-'CXXABI':  (1,3,3),
+'CXXABI':    (1,3,3),
-'GLIBCXX': (3,4,13),
+'GLIBCXX':   (3,4,13),
-'GLIBC':   (2,11)
+'GLIBC':     (2,11),
+'LIBATOMIC': (1,0)
 }
 # See here for a description of _IO_stdin_used:
 # https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=634261#109
 
 # Ignore symbols that are exported as part of every executable
 IGNORE_EXPORTS = {
-'_edata', '_end', '_init', '__bss_start', '_fini', '_IO_stdin_used', 'stdin', 'stdout', 'stderr'
+'_edata', '_end', '__end__', '_init', '__bss_start', '__bss_start__', '_bss_end__', '__bss_end__', '_fini', '_IO_stdin_used', 'stdin', 'stdout', 'stderr'
 }
 READELF_CMD = os.getenv('READELF', '/usr/bin/readelf')
 CPPFILT_CMD = os.getenv('CPPFILT', '/usr/bin/c++filt')
@@ -59,8 +60,12 @@ ALLOWED_LIBRARIES = {
 'libanl.so.1', # DNS resolve
 'libm.so.6', # math library
 'librt.so.1', # real-time (clock)
+'libatomic.so.1',
 'ld-linux-x86-64.so.2', # 64-bit dynamic linker
 'ld-linux.so.2', # 32-bit dynamic linker
+'ld-linux-aarch64.so.1', # 64-bit ARM dynamic linker
+'ld-linux-armhf.so.3', # 32-bit ARM dynamic linker
+'ld-linux-riscv64-lp64d.so.1', # 64-bit RISC-V dynamic linker
 # bitcoin-qt only
 'libX11-xcb.so.1', # part of X11
 'libX11.so.6', # part of X11
@@ -69,7 +74,13 @@ ALLOWED_LIBRARIES = {
 'libfreetype.so.6', # font parsing
 'libdl.so.2' # programming interface to dynamic linker
 }
-
+ARCH_MIN_GLIBC_VER = {
+'80386':  (2,1),
+'X86-64': (2,2,5),
+'ARM':    (2,4),
+'AArch64':(2,17),
+'RISC-V': (2,27)
+}
 class CPPFilt(object):
     '''
     Demangle C++ symbol names.
@@ -94,23 +105,25 @@ def read_symbols(executable, imports=True):
     Parse an ELF executable and return a list of (symbol,version) tuples
     for dynamic, imported symbols.
     '''
-    p = subprocess.Popen([READELF_CMD, '--dyn-syms', '-W', executable], stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE, universal_newlines=True)
+    p = subprocess.Popen([READELF_CMD, '--dyn-syms', '-W', '-h', executable], stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE, universal_newlines=True)
     (stdout, stderr) = p.communicate()
     if p.returncode:
         raise IOError('Could not read symbols for %s: %s' % (executable, stderr.strip()))
     syms = []
     for line in stdout.splitlines():
         line = line.split()
+        if 'Machine:' in line:
+            arch = line[-1]
         if len(line)>7 and re.match('[0-9]+:$', line[0]):
             (sym, _, version) = line[7].partition('@')
             is_import = line[6] == 'UND'
             if version.startswith('@'):
                 version = version[1:]
             if is_import == imports:
-                syms.append((sym, version))
+                syms.append((sym, version, arch))
     return syms
 
-def check_version(max_versions, version):
+def check_version(max_versions, version, arch):
     if '_' in version:
         (lib, _, ver) = version.rpartition('_')
     else:
@@ -119,7 +132,7 @@ def check_version(max_versions, version):
     ver = tuple([int(x) for x in ver.split('.')])
     if not lib in max_versions:
         return False
-    return ver <= max_versions[lib]
+    return ver <= max_versions[lib] or lib == 'GLIBC' and ver <= ARCH_MIN_GLIBC_VER[arch]
 
 def read_libraries(filename):
     p = subprocess.Popen([READELF_CMD, '-d', '-W', filename], stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE, universal_newlines=True)
@@ -142,16 +155,17 @@ if __name__ == '__main__':
     retval = 0
     for filename in sys.argv[1:]:
         # Check imported symbols
-        for sym,version in read_symbols(filename, True):
+        for sym,version,arch in read_symbols(filename, True):
-            if version and not check_version(MAX_VERSIONS, version):
+            if version and not check_version(MAX_VERSIONS, version, arch):
                 print('%s: symbol %s from unsupported version %s' % (filename, cppfilt(sym), version))
                 retval = 1
         # Check exported symbols
-        for sym,version in read_symbols(filename, False):
+        if arch != 'RISC-V':
-            if sym in IGNORE_EXPORTS:
+            for sym,version,arch in read_symbols(filename, False):
-                continue
+                if sym in IGNORE_EXPORTS:
-            print('%s: export of symbol %s not allowed' % (filename, cppfilt(sym)))
+                    continue
-            retval = 1
+                print('%s: export of symbol %s not allowed' % (filename, cppfilt(sym)))
+                retval = 1
         # Check dependency libraries
         for library_name in read_libraries(filename):
             if library_name not in ALLOWED_LIBRARIES:

contrib/gitian-descriptors/gitian-linux.yml

@@ -173,18 +173,7 @@ script: |
     CONFIG_SITE=${BASEPREFIX}/${i}/share/config.site ./configure --prefix=/ --disable-ccache --disable-maintainer-mode --disable-dependency-tracking ${CONFIGFLAGS} CFLAGS="${HOST_CFLAGS}" CXXFLAGS="${HOST_CXXFLAGS}" LDFLAGS="${HOST_LDFLAGS}"
     make ${MAKEOPTS}
     make ${MAKEOPTS} -C src check-security
-
+    make ${MAKEOPTS} -C src check-symbols
-    #TODO: This is a quick hack that disables symbol checking for arm.
-    #      Instead, we should investigate why these are popping up.
-    #      For aarch64, we'll need to bump up the min GLIBC version, as the abi
-    #      support wasn't introduced until 2.17.
-    case $i in
-       aarch64-*) : ;;
-       arm-*) : ;;
-       riscv64-*) : ;;
-       *) make ${MAKEOPTS} -C src check-symbols ;;
-    esac
-
     make install DESTDIR=${INSTALLPATH}
     cd installed
     find . -name "lib*.la" -delete