15 files changed, 374 insertions, 63 deletions

diff --git a/meta/lib/oe/__init__.py b/meta/lib/oe/__init__.py
index dd094a874a..73de774266 100644
--- a/meta/lib/oe/__init__.py
+++ b/meta/lib/oe/__init__.py
@@ -12,4 +12,4 @@ __path__ = extend_path(__path__, __name__)
 BBIMPORTS = ["qa", "data", "path", "utils", "types", "package", "packagedata", \
              "packagegroup", "sstatesig", "lsb", "cachedpath", "license", "qemu", \
              "reproducible", "rust", "buildcfg", "go", "spdx30_tasks", "spdx_common", \
-             "cve_check"]
+             "cve_check", "tune"]
diff --git a/meta/lib/oe/bootfiles.py b/meta/lib/oe/bootfiles.py
index 155fe742db..7ee148c4e2 100644
--- a/meta/lib/oe/bootfiles.py
+++ b/meta/lib/oe/bootfiles.py
@@ -10,7 +10,7 @@
 # Returns a list of tuples with (original filepath relative to
 # deploy_dir, desired filepath renaming)
 #
-# Heavily inspired of bootimg-partition.py
+# Heavily inspired of bootimg_partition.py
 #
 def get_boot_files(deploy_dir, boot_files):
     import re
diff --git a/meta/lib/oe/go.py b/meta/lib/oe/go.py
index dfd957d157..4559dc63b2 100644
--- a/meta/lib/oe/go.py
+++ b/meta/lib/oe/go.py
@@ -7,6 +7,10 @@
 import re
 
 def map_arch(a):
+    """
+    Map our architecture names to Go's GOARCH names.
+    See https://github.com/golang/go/blob/master/src/internal/syslist/syslist.go for the complete list.
+    """
     if re.match('i.86', a):
         return '386'
     elif a == 'x86_64':
@@ -31,4 +35,4 @@ def map_arch(a):
         return 'riscv64'
     elif a == 'loongarch64':
         return 'loong64'
-    return ''
+    raise KeyError(f"Cannot map architecture {a}")
diff --git a/meta/lib/oe/license.py b/meta/lib/oe/license.py
index 6f882c3812..6e55fa1e7f 100644
--- a/meta/lib/oe/license.py
+++ b/meta/lib/oe/license.py
@@ -462,3 +462,18 @@ def skip_incompatible_package_licenses(d, pkgs):
             skipped_pkgs[pkg] = incompatible_lic
 
     return skipped_pkgs
+
+def tidy_licenses(value):
+    """
+    Flat, split and sort licenses.
+    """
+    from oe.license import flattened_licenses
+
+    def _choose(a, b):
+        str_a, str_b  = sorted((" & ".join(a), " & ".join(b)), key=str.casefold)
+        return ["(%s | %s)" % (str_a, str_b)]
+
+    if not isinstance(value, str):
+        value = " & ".join(value)
+
+    return sorted(list(set(flattened_licenses(value, _choose))), key=str.casefold)
diff --git a/meta/lib/oe/license_finder.py b/meta/lib/oe/license_finder.py
new file mode 100644
index 0000000000..16f5d7c94c
--- /dev/null
+++ b/meta/lib/oe/license_finder.py
@@ -0,0 +1,179 @@
+#
+# Copyright OpenEmbedded Contributors
+#
+# SPDX-License-Identifier: GPL-2.0-only
+#
+
+import fnmatch
+import hashlib
+import logging
+import os
+import re
+
+import bb
+import bb.utils
+
+logger = logging.getLogger("BitBake.OE.LicenseFinder")
+
+def _load_hash_csv(d):
+    """
+    Load a mapping of (checksum: license name) from all files/license-hashes.csv
+    files that can be found in the available layers.
+    """
+    import csv
+    md5sums = {}
+
+    # Read license md5sums from csv file
+    for path in d.getVar('BBPATH').split(':'):
+        csv_path = os.path.join(path, 'files', 'license-hashes.csv')
+        if os.path.isfile(csv_path):
+            with open(csv_path, newline='') as csv_file:
+                reader = csv.DictReader(csv_file, delimiter=',', fieldnames=['md5sum', 'license'])
+                for row in reader:
+                    md5sums[row['md5sum']] = row['license']
+
+    return md5sums
+
+
+def _crunch_known_licenses(d):
+    """
+    Calculate the MD5 checksums for the original and "crunched" versions of all
+    known licenses.
+    """
+    md5sums = {}
+
+    lic_dirs = [d.getVar('COMMON_LICENSE_DIR')] + (d.getVar('LICENSE_PATH') or "").split()
+    for lic_dir in lic_dirs:
+        for fn in os.listdir(lic_dir):
+            path = os.path.join(lic_dir, fn)
+            # Hash the exact contents
+            md5value = bb.utils.md5_file(path)
+            md5sums[md5value] = fn
+            # Also hash a "crunched" version
+            md5value = _crunch_license(path)
+            md5sums[md5value] = fn
+
+    return md5sums
+
+
+def _crunch_license(licfile):
+    '''
+    Remove non-material text from a license file and then calculate its
+    md5sum. This works well for licenses that contain a copyright statement,
+    but is also a useful way to handle people's insistence upon reformatting
+    the license text slightly (with no material difference to the text of the
+    license).
+    '''
+
+    import oe.utils
+
+    # Note: these are carefully constructed!
+    license_title_re = re.compile(r'^#*\(? *(This is )?([Tt]he )?.{0,15} ?[Ll]icen[sc]e( \(.{1,10}\))?\)?[:\.]? ?#*$')
+    license_statement_re = re.compile(r'^((This (project|software)|.{1,10}) is( free software)? (released|licen[sc]ed)|(Released|Licen[cs]ed)) under the .{1,10} [Ll]icen[sc]e:?$')
+    copyright_re = re.compile(r'^ *[#\*]* *(Modified work |MIT LICENSED )?Copyright ?(\([cC]\))? .*$')
+    disclaimer_re = re.compile(r'^ *\*? ?All [Rr]ights [Rr]eserved\.$')
+    email_re = re.compile(r'^.*<[\w\.-]*@[\w\.\-]*>$')
+    header_re = re.compile(r'^(\/\**!?)? ?[\-=\*]* ?(\*\/)?$')
+    tag_re = re.compile(r'^ *@?\(?([Ll]icense|MIT)\)?$')
+    url_re = re.compile(r'^ *[#\*]* *https?:\/\/[\w\.\/\-]+$')
+
+    lictext = []
+    with open(licfile, 'r', errors='surrogateescape') as f:
+        for line in f:
+            # Drop opening statements
+            if copyright_re.match(line):
+                continue
+            elif disclaimer_re.match(line):
+                continue
+            elif email_re.match(line):
+                continue
+            elif header_re.match(line):
+                continue
+            elif tag_re.match(line):
+                continue
+            elif url_re.match(line):
+                continue
+            elif license_title_re.match(line):
+                continue
+            elif license_statement_re.match(line):
+                continue
+            # Strip comment symbols
+            line = line.replace('*', '') \
+                       .replace('#', '')
+            # Unify spelling
+            line = line.replace('sub-license', 'sublicense')
+            # Squash spaces
+            line = oe.utils.squashspaces(line.strip())
+            # Replace smart quotes, double quotes and backticks with single quotes
+            line = line.replace(u"\u2018", "'").replace(u"\u2019", "'").replace(u"\u201c","'").replace(u"\u201d", "'").replace('"', '\'').replace('`', '\'')
+            # Unify brackets
+            line = line.replace("{", "[").replace("}", "]")
+            if line:
+                lictext.append(line)
+
+    m = hashlib.md5()
+    try:
+        m.update(' '.join(lictext).encode('utf-8'))
+        md5val = m.hexdigest()
+    except UnicodeEncodeError:
+        md5val = None
+    return md5val
+
+
+def find_license_files(srctree, first_only=False):
+    """
+    Search srctree for files that look like they could be licenses.
+    If first_only is True, only return the first file found.
+    """
+    licspecs = ['*LICEN[CS]E*', 'COPYING*', '*[Ll]icense*', 'LEGAL*', '[Ll]egal*', '*GPL*', 'README.lic*', 'COPYRIGHT*', '[Cc]opyright*', 'e[dp]l-v10']
+    skip_extensions = (".html", ".js", ".json", ".svg", ".ts", ".go", ".sh")
+    licfiles = []
+    for root, dirs, files in os.walk(srctree):
+        # Sort files so that LICENSE is before LICENSE.subcomponent, which is
+        # meaningful if first_only is set.
+        for fn in sorted(files):
+            if fn.endswith(skip_extensions):
+                continue
+            for spec in licspecs:
+                if fnmatch.fnmatch(fn, spec):
+                    fullpath = os.path.join(root, fn)
+                    if not fullpath in licfiles:
+                        licfiles.append(fullpath)
+                        if first_only:
+                            return licfiles
+
+    return licfiles
+
+
+def match_licenses(licfiles, srctree, d, extra_hashes={}):
+    md5sums = {}
+    md5sums.update(_load_hash_csv(d))
+    md5sums.update(_crunch_known_licenses(d))
+    md5sums.update(extra_hashes)
+
+    licenses = []
+    for licfile in sorted(licfiles):
+        resolved_licfile = d.expand(licfile)
+        md5value = bb.utils.md5_file(resolved_licfile)
+        license = md5sums.get(md5value, None)
+        if not license:
+            crunched_md5 = _crunch_license(resolved_licfile)
+            license = md5sums.get(crunched_md5, None)
+            if not license:
+                license = 'Unknown'
+                logger.info("Please add the following line for '%s' to a 'license-hashes.csv' " \
+                    "and replace `Unknown` with the license:\n" \
+                    "%s,Unknown" % (os.path.relpath(licfile, srctree + "/.."), md5value))
+
+        licenses.append((license, os.path.relpath(licfile, srctree), md5value))
+
+    return licenses
+
+
+def find_licenses(srctree, d, first_only=False, extra_hashes={}):
+    licfiles = find_license_files(srctree, first_only)
+    licenses = match_licenses(licfiles, srctree, d, extra_hashes)
+
+    # FIXME should we grab at least one source file with a license header and add that too?
+
+    return licenses
diff --git a/meta/lib/oe/package.py b/meta/lib/oe/package.py
index 60392cbced..ce69151e5d 100644
--- a/meta/lib/oe/package.py
+++ b/meta/lib/oe/package.py
@@ -16,6 +16,7 @@ import mmap
 import subprocess
 import shutil
 
+import bb.parse
 import oe.cachedpath
 
 def runstrip(file, elftype, strip, extra_strip_sections=''):
@@ -1049,6 +1050,7 @@ def copydebugsources(debugsrcdir, sources, d):
             if os.path.exists(p) and not os.listdir(p):
                 os.rmdir(p)
 
+@bb.parse.vardepsexclude("BB_NUMBER_THREADS")
 def save_debugsources_info(debugsrcdir, sources_raw, d):
     import json
     import bb.compress.zstd
@@ -1081,6 +1083,7 @@ def save_debugsources_info(debugsrcdir, sources_raw, d):
         with bb.compress.zstd.open(debugsources_file, "wt", encoding="utf-8", num_threads=num_threads) as f:
             json.dump(sources_dict, f, sort_keys=True)
 
+@bb.parse.vardepsexclude("BB_NUMBER_THREADS")
 def read_debugsources_info(d):
     import json
     import bb.compress.zstd
diff --git a/meta/lib/oe/packagedata.py b/meta/lib/oe/packagedata.py
index 2d1d6ddeb7..b6a10a930a 100644
--- a/meta/lib/oe/packagedata.py
+++ b/meta/lib/oe/packagedata.py
@@ -7,6 +7,7 @@
 import codecs
 import os
 import json
+import bb.parse
 import bb.compress.zstd
 import oe.path
 
@@ -64,6 +65,7 @@ def read_subpkgdata_dict(pkg, d):
         ret[newvar] = subd[var]
     return ret
 
+@bb.parse.vardepsexclude("BB_NUMBER_THREADS")
 def read_subpkgdata_extended(pkg, d):
     import json
     import bb.compress.zstd
@@ -182,6 +184,7 @@ def runtime_mapping_rename(varname, pkg, d):
 
     #bb.note("%s after: %s" % (varname, d.getVar(varname)))
 
+@bb.parse.vardepsexclude("BB_NUMBER_THREADS")
 def emit_pkgdata(pkgfiles, d):
     def process_postinst_on_target(pkg, mlprefix):
         pkgval = d.getVar('PKG:%s' % pkg)
diff --git a/meta/lib/oe/path.py b/meta/lib/oe/path.py
index 5d21cdcbdf..a1efe97d88 100644
--- a/meta/lib/oe/path.py
+++ b/meta/lib/oe/path.py
@@ -10,6 +10,8 @@ import shutil
 import subprocess
 import os.path
 
+import bb.parse
+
 def join(*paths):
     """Like os.path.join but doesn't treat absolute RHS specially"""
     return os.path.normpath("/".join(paths))
@@ -77,6 +79,7 @@ def replace_absolute_symlinks(basedir, d):
             os.remove(path)
             os.symlink(base, path)
 
+@bb.parse.vardepsexclude("TOPDIR")
 def format_display(path, metadata):
     """ Prepare a path for display to the user. """
     rel = relative(metadata.getVar("TOPDIR"), path)
diff --git a/meta/lib/oe/reproducible.py b/meta/lib/oe/reproducible.py
index cdb38d5aa4..0270024a83 100644
--- a/meta/lib/oe/reproducible.py
+++ b/meta/lib/oe/reproducible.py
@@ -75,10 +75,11 @@ def get_source_date_epoch_from_known_files(d, sourcedir):
     return source_date_epoch
 
 def find_git_folder(d, sourcedir):
-    # First guess: UNPACKDIR/git
+    # First guess: UNPACKDIR/BB_GIT_DEFAULT_DESTSUFFIX
     # This is the default git fetcher unpack path
     unpackdir = d.getVar('UNPACKDIR')
-    gitpath = os.path.join(unpackdir, "git/.git")
+    default_destsuffix = d.getVar('BB_GIT_DEFAULT_DESTSUFFIX')
+    gitpath = os.path.join(unpackdir, default_destsuffix, ".git")
     if os.path.isdir(gitpath):
         return gitpath
 
diff --git a/meta/lib/oe/rust.py b/meta/lib/oe/rust.py
index 185553eeeb..1dc9cf150d 100644
--- a/meta/lib/oe/rust.py
+++ b/meta/lib/oe/rust.py
@@ -8,6 +8,4 @@
 def arch_to_rust_arch(arch):
     if arch == "ppc64le":
         return "powerpc64le"
-    if arch in ('riscv32', 'riscv64'):
-        return arch + 'gc'
     return arch
diff --git a/meta/lib/oe/spdx30_tasks.py b/meta/lib/oe/spdx30_tasks.py
index 61d7ba45e3..c352dab152 100644
--- a/meta/lib/oe/spdx30_tasks.py
+++ b/meta/lib/oe/spdx30_tasks.py
@@ -156,6 +156,11 @@ def add_package_files(
         bb.note(f"Skip {topdir}")
         return spdx_files
 
+    check_compiled_sources = d.getVar("SPDX_INCLUDE_COMPILED_SOURCES") == "1"
+    if check_compiled_sources:
+        compiled_sources, types = oe.spdx_common.get_compiled_sources(d)
+        bb.debug(1, f"Total compiled files: {len(compiled_sources)}")
+
     for subdir, dirs, files in os.walk(topdir, onerror=walk_error):
         dirs[:] = [d for d in dirs if d not in ignore_dirs]
         if subdir == str(topdir):
@@ -171,6 +176,11 @@ def add_package_files(
             filename = str(filepath.relative_to(topdir))
             file_purposes = get_purposes(filepath)
 
+            # Check if file is compiled
+            if check_compiled_sources:
+                if not oe.spdx_common.is_compiled_source(filename, compiled_sources, types):
+                    continue
+
             spdx_file = objset.new_file(
                 get_spdxid(file_counter),
                 filename,
@@ -542,7 +552,7 @@ def create_spdx(d):
     )
     build_objset.new_relationship(
         source_files,
-        oe.spdx30.RelationshipType.hasConcludedLicense,
+        oe.spdx30.RelationshipType.hasDeclaredLicense,
         [oe.sbom30.get_element_link_id(recipe_spdx_license)],
     )
 
@@ -714,24 +724,23 @@ def create_spdx(d):
                             impact_statement=description,
                         )
 
-                        if detail in (
-                            "ignored",
-                            "cpe-incorrect",
-                            "disputed",
-                            "upstream-wontfix",
-                        ):
-                            # VEX doesn't have justifications for this
-                            pass
-                        elif detail in (
-                            "not-applicable-config",
-                            "not-applicable-platform",
-                        ):
-                            for v in spdx_vex:
-                                v.security_justificationType = (
-                                    oe.spdx30.security_VexJustificationType.vulnerableCodeNotPresent
+                        vex_just_type = d.getVarFlag(
+                            "CVE_CHECK_VEX_JUSTIFICATION", detail
+                        )
+                        if vex_just_type:
+                            if (
+                                vex_just_type
+                                not in oe.spdx30.security_VexJustificationType.NAMED_INDIVIDUALS
+                            ):
+                                bb.fatal(
+                                    f"Unknown vex justification '{vex_just_type}', detail '{detail}', for ignored {cve}"
                                 )
-                        else:
-                            bb.fatal(f"Unknown detail '{detail}' for ignored {cve}")
+
+                            for v in spdx_vex:
+                                v.security_justificationType = oe.spdx30.security_VexJustificationType.NAMED_INDIVIDUALS[
+                                    vex_just_type
+                                ]
+
                     elif status == "Unknown":
                         bb.note(f"Skipping {cve} with status 'Unknown'")
                     else:
diff --git a/meta/lib/oe/spdx_common.py b/meta/lib/oe/spdx_common.py
index 4caefc7673..c2dec65563 100644
--- a/meta/lib/oe/spdx_common.py
+++ b/meta/lib/oe/spdx_common.py
@@ -242,3 +242,44 @@ def fetch_data_to_uri(fd, name):
         uri = uri + "@" + fd.revision
 
     return uri
+
+def is_compiled_source (filename, compiled_sources, types):
+    """
+    Check if the file is a compiled file
+    """
+    import os
+    # If we don't have compiled source, we assume all are compiled.
+    if not compiled_sources:
+        return True
+
+    # We return always true if the file type is not in the list of compiled files.
+    # Some files in the source directory are not compiled, for example, Makefiles,
+    # but also python .py file. We need to include them in the SPDX.
+    basename = os.path.basename(filename)
+    ext = basename.partition(".")[2]
+    if ext not in types:
+        return True
+    # Check that the file is in the list
+    return filename in compiled_sources
+
+def get_compiled_sources(d):
+    """
+    Get list of compiled sources from debug information and normalize the paths
+    """
+    import itertools
+    source_info = oe.package.read_debugsources_info(d)
+    if not source_info:
+        bb.debug(1, "Do not have debugsources.list. Skipping")
+        return [], []
+
+    # Sources are not split now in SPDX, so we aggregate them
+    sources = set(itertools.chain.from_iterable(source_info.values()))
+    # Check extensions of files
+    types = set()
+    for src in sources:
+        basename = os.path.basename(src)
+        ext = basename.partition(".")[2]
+        if ext not in types and ext:
+            types.add(ext)
+    bb.debug(1, f"Num of sources: {len(sources)} and types: {len(types)} {str(types)}")
+    return sources, types
diff --git a/meta/lib/oe/sstatesig.py b/meta/lib/oe/sstatesig.py
index 826549948e..ef687f5d41 100644
--- a/meta/lib/oe/sstatesig.py
+++ b/meta/lib/oe/sstatesig.py
@@ -3,6 +3,7 @@
 #
 # SPDX-License-Identifier: GPL-2.0-only
 #
+import bb.parse
 import bb.siggen
 import bb.runqueue
 import oe
@@ -493,6 +494,7 @@ def sstate_get_manifest_filename(task, d):
         d2.setVar("SSTATE_MANMACH", extrainf)
     return (d2.expand("${SSTATE_MANFILEPREFIX}.%s" % task), d2)
 
+@bb.parse.vardepsexclude("BBEXTENDCURR", "BBEXTENDVARIANT", "OVERRIDES", "PACKAGE_EXTRA_ARCHS")
 def find_sstate_manifest(taskdata, taskdata2, taskname, d, multilibcache):
     d2 = d
     variant = ''
diff --git a/meta/lib/oe/tune.py b/meta/lib/oe/tune.py
new file mode 100644
index 0000000000..7fda19430d
--- /dev/null
+++ b/meta/lib/oe/tune.py
@@ -0,0 +1,81 @@
+#
+# Copyright OpenEmbedded Contributors
+#
+# SPDX-License-Identifier: GPL-2.0-only
+#
+
+# riscv_isa_to_tune(isa)
+#
+# Automatically translate a RISC-V ISA string to TUNE_FEATURES
+#
+# Abbreviations, such as rv32g -> rv32imaffd_zicsr_zifencei are supported.
+#
+# Profiles, such as rva22u64, are NOT supported, you must use ISA strings.
+#
+def riscv_isa_to_tune(isa):
+    _isa = isa.lower()
+
+    feature = []
+    iter = 0
+
+    # rv or riscv
+    if _isa[iter:].startswith('rv'):
+        feature.append('rv')
+        iter = iter + 2
+    elif _isa[iter:].startswith('riscv'):
+        feature.append('rv')
+        iter = iter + 5
+    else:
+        # Not a risc-v ISA!
+        return _isa
+
+    while (_isa[iter:]):
+        # Skip _ and whitespace
+        if _isa[iter] == '_' or _isa[iter].isspace():
+            iter = iter + 1
+            continue
+
+        # Length, just capture numbers here
+        if _isa[iter].isdigit():
+            iter_end = iter
+            while iter_end < len(_isa) and _isa[iter_end].isdigit():
+                iter_end = iter_end + 1
+
+            feature.append(_isa[iter:iter_end])
+            iter = iter_end
+            continue
+
+        # Typically i, e or g is next, followed by extensions.
+        # Extensions are single character, except for Z, Ss, Sh, Sm, Sv, and X
+
+        # If the extension starts with 'Z', 'S' or 'X' use the name until the next _, whitespace or end
+        if _isa[iter] in ['z', 's', 'x']:
+            ext_type = _isa[iter]
+            iter_end = iter + 1
+
+            # Multicharacter extension, these are supposed to have a _ before the next multicharacter extension
+            # See 37.4 and 37.5:
+            # 37.4: Underscores "_" may be used to separate ISA extensions...
+            # 37.5: All multi-letter extensions ... must be separated from other multi-letter extensions by an underscore...
+            # Some extensions permit only alphabetic characters, while others allow alphanumeric chartacters
+            while iter_end < len(_isa) and _isa[iter_end] != "_" and not _isa[iter_end].isspace():
+                iter_end = iter_end + 1
+
+            feature.append(_isa[iter:iter_end])
+            iter = iter_end
+            continue
+
+        # 'g' is special, it's an abbreviation for imafd_zicsr_zifencei
+        # When expanding the abbreviation, any additional letters must appear before the _z* extensions
+        if _isa[iter] == 'g':
+            _isa = 'imafd' + _isa[iter+1:] + '_zicsr_zifencei'
+            iter = 0
+            continue
+
+        feature.append(_isa[iter])
+        iter = iter + 1
+        continue
+
+    # Eliminate duplicates, but preserve the order
+    feature = list(dict.fromkeys(feature))
+    return ' '.join(feature)
diff --git a/meta/lib/oe/utils.py b/meta/lib/oe/utils.py
index d272dd2b8d..779c5e593f 100644
--- a/meta/lib/oe/utils.py
+++ b/meta/lib/oe/utils.py
@@ -9,6 +9,8 @@ import multiprocessing
 import traceback
 import errno
 
+import bb.parse
+
 def read_file(filename):
     try:
         f = open( filename, "r" )
@@ -265,6 +267,7 @@ def execute_pre_post_process(d, cmds):
         bb.note("Executing %s ..." % cmd)
         bb.build.exec_func(cmd, d)
 
+@bb.parse.vardepsexclude("BB_NUMBER_THREADS")
 def get_bb_number_threads(d):
     return int(d.getVar("BB_NUMBER_THREADS") or os.cpu_count() or 1)
 
@@ -412,62 +415,31 @@ def format_pkg_list(pkg_dict, ret_format=None, pkgdata_dir=None):
     return output_str
 
 
-# Helper function to get the host compiler version
-# Do not assume the compiler is gcc
-def get_host_compiler_version(d, taskcontextonly=False):
+# Helper function to get the host gcc version
+def get_host_gcc_version(d, taskcontextonly=False):
     import re, subprocess
 
     if taskcontextonly and d.getVar('BB_WORKERCONTEXT') != '1':
         return
 
-    compiler = d.getVar("BUILD_CC")
-    # Get rid of ccache since it is not present when parsing.
-    if compiler.startswith('ccache '):
-        compiler = compiler[7:]
     try:
         env = os.environ.copy()
         # datastore PATH does not contain session PATH as set by environment-setup-...
         # this breaks the install-buildtools use-case
         # env["PATH"] = d.getVar("PATH")
-        output = subprocess.check_output("%s --version" % compiler, \
-                    shell=True, env=env, stderr=subprocess.STDOUT).decode("utf-8")
-    except subprocess.CalledProcessError as e:
-        bb.fatal("Error running %s --version: %s" % (compiler, e.output.decode("utf-8")))
-
-    match = re.match(r".* (\d+\.\d+)\.\d+.*", output.split('\n')[0])
-    if not match:
-        bb.fatal("Can't get compiler version from %s --version output" % compiler)
-
-    version = match.group(1)
-    return compiler, version
-
-
-def host_gcc_version(d, taskcontextonly=False):
-    import re, subprocess
-
-    if taskcontextonly and d.getVar('BB_WORKERCONTEXT') != '1':
-        return
-
-    compiler = d.getVar("BUILD_CC")
-    # Get rid of ccache since it is not present when parsing.
-    if compiler.startswith('ccache '):
-        compiler = compiler[7:]
-    try:
-        env = os.environ.copy()
-        env["PATH"] = d.getVar("PATH")
-        output = subprocess.check_output("%s --version" % compiler, \
+        output = subprocess.check_output("gcc --version", \
                     shell=True, env=env, stderr=subprocess.STDOUT).decode("utf-8")
     except subprocess.CalledProcessError as e:
-        bb.fatal("Error running %s --version: %s" % (compiler, e.output.decode("utf-8")))
+        bb.fatal("Error running gcc --version: %s" % (e.output.decode("utf-8")))
 
     match = re.match(r".* (\d+\.\d+)\.\d+.*", output.split('\n')[0])
     if not match:
-        bb.fatal("Can't get compiler version from %s --version output" % compiler)
+        bb.fatal("Can't get compiler version from gcc --version output")
 
     version = match.group(1)
-    return "-%s" % version if version in ("4.8", "4.9") else ""
-
+    return version
 
+@bb.parse.vardepsexclude("DEFAULTTUNE_MULTILIB_ORIGINAL", "OVERRIDES")
 def get_multilib_datastore(variant, d):
     localdata = bb.data.createCopy(d)
     if variant: