siggen.py: Improve taskhash reproducibility

file checksums are part of the data checksummed
to generate the task hash. The list of file checksums
was not ordered.

In this commit we make sure the task hash checksum takes
a list of checksum data that is ordered by unique file name
thus guaranteeing reproducibility.

Signed-off-by: Paulo Neves <paulo@myneves.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

1 files changed, 8 insertions, 2 deletions

diff --git a/lib/bb/siggen.py b/lib/bb/siggen.py
index 879c136e1..b023b79ec 100644
--- a/lib/bb/siggen.py
+++ b/lib/bb/siggen.py
@@ -361,7 +361,7 @@ class SignatureGeneratorBasic(SignatureGenerator):
         for dep in sorted(self.runtaskdeps[tid]):
             data += self.get_unihash(dep[1])
 
-        for (f, cs) in self.file_checksum_values[tid]:
+        for (f, cs) in sorted(self.file_checksum_values[tid], key=clean_checksum_file_path):
             if cs:
                 if "/./" in f:
                     data += "./" + f.split("/./")[1]
@@ -426,7 +426,7 @@ class SignatureGeneratorBasic(SignatureGenerator):
         if runtime and tid in self.taskhash:
             data['runtaskdeps'] = [dep[0] for dep in sorted(self.runtaskdeps[tid])]
             data['file_checksum_values'] = []
-            for f,cs in self.file_checksum_values[tid]:
+            for f,cs in sorted(self.file_checksum_values[tid], key=clean_checksum_file_path):
                 if "/./" in f:
                     data['file_checksum_values'].append(("./" + f.split("/./")[1], cs))
                 else:
@@ -745,6 +745,12 @@ class SignatureGeneratorTestEquivHash(SignatureGeneratorUniHashMixIn, SignatureG
         self.server = data.getVar('BB_HASHSERVE')
         self.method = "sstate_output_hash"
 
+def clean_checksum_file_path(file_checksum_tuple):
+    f, cs = file_checksum_tuple
+    if "/./" in f:
+        return "./" + f.split("/./")[1]
+    return f
+
 def dump_this_task(outfile, d):
     import bb.parse
     mcfn = d.getVar("BB_FILENAME")