3 files changed, 63 insertions, 20 deletions

diff --git a/bitbake/lib/bb/fetch2/__init__.py b/bitbake/lib/bb/fetch2/__init__.py
index dc99914cd9..3e6555bd67 100644
--- a/bitbake/lib/bb/fetch2/__init__.py
+++ b/bitbake/lib/bb/fetch2/__init__.py
@@ -562,6 +562,9 @@ def verify_checksum(ud, d, precomputed={}):
 
         checksum_expected = getattr(ud, "%s_expected" % checksum_id)
 
+        if checksum_expected == '':
+            checksum_expected = None
+
         return {
             "id": checksum_id,
             "name": checksum_name,
@@ -612,7 +615,7 @@ def verify_checksum(ud, d, precomputed={}):
 
     for ci in checksum_infos:
         if ci["expected"] and ci["expected"] != ci["data"]:
-            messages.append("File: '%s' has %s checksum %s when %s was " \
+            messages.append("File: '%s' has %s checksum '%s' when '%s' was " \
                             "expected" % (ud.localpath, ci["id"], ci["data"], ci["expected"]))
             bad_checksum = ci["data"]
 
diff --git a/bitbake/lib/bb/fetch2/git.py b/bitbake/lib/bb/fetch2/git.py
index 8740e9c05f..cad1ae8207 100644
--- a/bitbake/lib/bb/fetch2/git.py
+++ b/bitbake/lib/bb/fetch2/git.py
@@ -44,7 +44,8 @@ Supported SRC_URI options are:
 
 - nobranch
    Don't check the SHA validation for branch. set this option for the recipe
-   referring to commit which is valid in tag instead of branch.
+   referring to commit which is valid in any namespace (branch, tag, ...)
+   instead of branch.
    The default is "0", set nobranch=1 if needed.
 
 - usehead
@@ -63,10 +64,12 @@ import errno
 import fnmatch
 import os
 import re
+import shlex
 import subprocess
 import tempfile
 import bb
 import bb.progress
+from contextlib import contextmanager
 from   bb.fetch2 import FetchMethod
 from   bb.fetch2 import runfetchcmd
 from   bb.fetch2 import logger
@@ -140,6 +143,10 @@ class Git(FetchMethod):
             ud.proto = 'file'
         else:
             ud.proto = "git"
+        if ud.host == "github.com" and ud.proto == "git":
+            # github stopped supporting git protocol
+            # https://github.blog/2021-09-01-improving-git-protocol-security-github/#no-more-unauthenticated-git
+            ud.proto = "https"
 
         if not ud.proto in ('git', 'file', 'ssh', 'http', 'https', 'rsync'):
             raise bb.fetch2.ParameterError("Invalid protocol type", ud.url)
@@ -219,7 +226,12 @@ class Git(FetchMethod):
             ud.shallow = False
 
         if ud.usehead:
-            ud.unresolvedrev['default'] = 'HEAD'
+            # When usehead is set let's associate 'HEAD' with the unresolved
+            # rev of this repository. This will get resolved into a revision
+            # later. If an actual revision happens to have also been provided
+            # then this setting will be overridden.
+            for name in ud.names:
+                ud.unresolvedrev[name] = 'HEAD'
 
         ud.basecmd = d.getVar("FETCHCMD_git") or "git -c core.fsyncobjectfiles=0"
 
@@ -342,7 +354,7 @@ class Git(FetchMethod):
             # We do this since git will use a "-l" option automatically for local urls where possible
             if repourl.startswith("file://"):
                 repourl = repourl[7:]
-            clone_cmd = "LANG=C %s clone --bare --mirror \"%s\" %s --progress" % (ud.basecmd, repourl, ud.clonedir)
+            clone_cmd = "LANG=C %s clone --bare --mirror %s %s --progress" % (ud.basecmd, shlex.quote(repourl), ud.clonedir)
             if ud.proto.lower() != 'file':
                 bb.fetch2.check_network_access(d, clone_cmd, ud.url)
             progresshandler = GitProgressHandler(d)
@@ -354,8 +366,12 @@ class Git(FetchMethod):
             if "origin" in output:
               runfetchcmd("%s remote rm origin" % ud.basecmd, d, workdir=ud.clonedir)
 
-            runfetchcmd("%s remote add --mirror=fetch origin \"%s\"" % (ud.basecmd, repourl), d, workdir=ud.clonedir)
-            fetch_cmd = "LANG=C %s fetch -f --progress \"%s\" refs/*:refs/*" % (ud.basecmd, repourl)
+            runfetchcmd("%s remote add --mirror=fetch origin %s" % (ud.basecmd, shlex.quote(repourl)), d, workdir=ud.clonedir)
+
+            if ud.nobranch:
+                fetch_cmd = "LANG=C %s fetch -f --progress %s refs/*:refs/*" % (ud.basecmd, shlex.quote(repourl))
+            else:
+                fetch_cmd = "LANG=C %s fetch -f --progress %s refs/heads/*:refs/heads/* refs/tags/*:refs/tags/*" % (ud.basecmd, shlex.quote(repourl))
             if ud.proto.lower() != 'file':
                 bb.fetch2.check_network_access(d, fetch_cmd, ud.url)
             progresshandler = GitProgressHandler(d)
@@ -388,7 +404,7 @@ class Git(FetchMethod):
             tmpdir = tempfile.mkdtemp(dir=d.getVar('DL_DIR'))
             try:
                 # Do the checkout. This implicitly involves a Git LFS fetch.
-                self.unpack(ud, tmpdir, d)
+                Git.unpack(self, ud, tmpdir, d)
 
                 # Scoop up a copy of any stuff that Git LFS downloaded. Merge them into
                 # the bare clonedir.
@@ -408,6 +424,20 @@ class Git(FetchMethod):
                 bb.utils.remove(tmpdir, recurse=True)
 
     def build_mirror_data(self, ud, d):
+
+        # Create as a temp file and move atomically into position to avoid races
+        @contextmanager
+        def create_atomic(filename):
+            fd, tfile = tempfile.mkstemp(dir=os.path.dirname(filename))
+            try:
+                yield tfile
+                umask = os.umask(0o666)
+                os.umask(umask)
+                os.chmod(tfile, (0o666 & ~umask))
+                os.rename(tfile, filename)
+            finally:
+                os.close(fd)
+
         if ud.shallow and ud.write_shallow_tarballs:
             if not os.path.exists(ud.fullshallow):
                 if os.path.islink(ud.fullshallow):
@@ -418,7 +448,8 @@ class Git(FetchMethod):
                     self.clone_shallow_local(ud, shallowclone, d)
 
                     logger.info("Creating tarball of git repository")
-                    runfetchcmd("tar -czf %s ." % ud.fullshallow, d, workdir=shallowclone)
+                    with create_atomic(ud.fullshallow) as tfile:
+                        runfetchcmd("tar -czf %s ." % tfile, d, workdir=shallowclone)
                     runfetchcmd("touch %s.done" % ud.fullshallow, d)
                 finally:
                     bb.utils.remove(tempdir, recurse=True)
@@ -427,7 +458,8 @@ class Git(FetchMethod):
                 os.unlink(ud.fullmirror)
 
             logger.info("Creating tarball of git repository")
-            runfetchcmd("tar -czf %s ." % ud.fullmirror, d, workdir=ud.clonedir)
+            with create_atomic(ud.fullmirror) as tfile:
+                runfetchcmd("tar -czf %s ." % tfile, d, workdir=ud.clonedir)
             runfetchcmd("touch %s.done" % ud.fullmirror, d)
 
     def clone_shallow_local(self, ud, dest, d):
@@ -533,7 +565,7 @@ class Git(FetchMethod):
             raise bb.fetch2.UnpackError("No up to date source found: " + "; ".join(source_error), ud.url)
 
         repourl = self._get_repo_url(ud)
-        runfetchcmd("%s remote set-url origin \"%s\"" % (ud.basecmd, repourl), d, workdir=destdir)
+        runfetchcmd("%s remote set-url origin %s" % (ud.basecmd, shlex.quote(repourl)), d, workdir=destdir)
 
         if self._contains_lfs(ud, d, destdir):
             if need_lfs and not self._find_git_lfs(d):
@@ -661,8 +693,8 @@ class Git(FetchMethod):
         d.setVar('_BB_GIT_IN_LSREMOTE', '1')
         try:
             repourl = self._get_repo_url(ud)
-            cmd = "%s ls-remote \"%s\" %s" % \
-                (ud.basecmd, repourl, search)
+            cmd = "%s ls-remote %s %s" % \
+                (ud.basecmd, shlex.quote(repourl), search)
             if ud.proto.lower() != 'file':
                 bb.fetch2.check_network_access(d, cmd, repourl)
             output = runfetchcmd(cmd, d, True)
diff --git a/bitbake/lib/bb/fetch2/wget.py b/bitbake/lib/bb/fetch2/wget.py
index f7d1de26b7..368c644337 100644
--- a/bitbake/lib/bb/fetch2/wget.py
+++ b/bitbake/lib/bb/fetch2/wget.py
@@ -52,6 +52,12 @@ class WgetProgressHandler(bb.progress.LineFilterProgressHandler):
 
 
 class Wget(FetchMethod):
+
+    # CDNs like CloudFlare may do a 'browser integrity test' which can fail
+    # with the standard wget/urllib User-Agent, so pretend to be a modern
+    # browser.
+    user_agent = "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:84.0) Gecko/20100101 Firefox/84.0"
+
     """Class to fetch urls via 'wget'"""
     def supports(self, ud, d):
         """
@@ -91,10 +97,9 @@ class Wget(FetchMethod):
 
         fetchcmd = self.basecmd
 
-        if 'downloadfilename' in ud.parm:
-            localpath = os.path.join(d.getVar("DL_DIR"), ud.localfile)
-            bb.utils.mkdirhier(os.path.dirname(localpath))
-            fetchcmd += " -O %s" % shlex.quote(localpath)
+        localpath = os.path.join(d.getVar("DL_DIR"), ud.localfile) + ".tmp"
+        bb.utils.mkdirhier(os.path.dirname(localpath))
+        fetchcmd += " -O %s" % shlex.quote(localpath)
 
         if ud.user and ud.pswd:
             fetchcmd += " --user=%s --password=%s --auth-no-challenge" % (ud.user, ud.pswd)
@@ -108,6 +113,10 @@ class Wget(FetchMethod):
 
         self._runwget(ud, d, fetchcmd, False)
 
+        # Remove the ".tmp" and move the file into position atomically
+        # Our lock prevents multiple writers but mirroring code may grab incomplete files
+        os.rename(localpath, localpath[:-4])
+
         # Sanity check since wget can pretend it succeed when it didn't
         # Also, this used to happen if sourceforge sent us to the mirror page
         if not os.path.exists(ud.localpath):
@@ -300,7 +309,7 @@ class Wget(FetchMethod):
             # Some servers (FusionForge, as used on Alioth) require that the
             # optional Accept header is set.
             r.add_header("Accept", "*/*")
-            r.add_header("User-Agent", "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.2.12) Gecko/20101027 Ubuntu/9.10 (karmic) Firefox/3.6.12")
+            r.add_header("User-Agent", self.user_agent)
             def add_basic_auth(login_str, request):
                 '''Adds Basic auth to http request, pass in login:password as string'''
                 import base64
@@ -319,7 +328,7 @@ class Wget(FetchMethod):
             except (TypeError, ImportError, IOError, netrc.NetrcParseError):
                 pass
 
-            with opener.open(r) as response:
+            with opener.open(r, timeout=30) as response:
                 pass
         except urllib.error.URLError as e:
             if try_again:
@@ -404,9 +413,8 @@ class Wget(FetchMethod):
         """
         f = tempfile.NamedTemporaryFile()
         with tempfile.TemporaryDirectory(prefix="wget-index-") as workdir, tempfile.NamedTemporaryFile(dir=workdir, prefix="wget-listing-") as f:
-            agent = "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.2.12) Gecko/20101027 Ubuntu/9.10 (karmic) Firefox/3.6.12"
             fetchcmd = self.basecmd
-            fetchcmd += " -O " + f.name + " --user-agent='" + agent + "' '" + uri + "'"
+            fetchcmd += " -O " + f.name + " --user-agent='" + self.user_agent + "' '" + uri + "'"
             try:
                 self._runwget(ud, d, fetchcmd, True, workdir=workdir)
                 fetchresult = f.read()