diff mbox series

[2.0] siggen.py: Improve taskhash reproducibility

Message ID 20250307232720.2170981-1-martin.jansa@gmail.com
State New
Headers show
Series [2.0] siggen.py: Improve taskhash reproducibility | expand

Commit Message

Martin Jansa March 7, 2025, 11:27 p.m. UTC 
From: Paulo Neves <paulo@myneves.com>

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>
Signed-off-by: Martin Jansa <martin.jansa@gmail.com>
---
 lib/bb/siggen.py | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/lib/bb/siggen.py b/lib/bb/siggen.py
index 0a9ce0ede..828729d8b 100644
--- a/lib/bb/siggen.py
+++ b/lib/bb/siggen.py
@@ -331,7 +331,7 @@  class SignatureGeneratorBasic(SignatureGenerator):
         for dep in self.runtaskdeps[tid]:
             data += self.get_unihash(dep)
 
-        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]
@@ -393,7 +393,7 @@  class SignatureGeneratorBasic(SignatureGenerator):
         if runtime and tid in self.taskhash:
             data['runtaskdeps'] = 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:
@@ -720,6 +720,12 @@  class SignatureGeneratorTestMulticonfigDepends(SignatureGeneratorBasicHash):
     name = "TestMulticonfigDepends"
     supports_multiconfig_datacaches = True
 
+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
     fn = d.getVar("BB_FILENAME")