yocto-compat-layer: test signature differences when setting MACHINE

Selecting a machine is only allowed to affect the signature of tasks
that are specific to that machine. In other words, when MACHINE=A and
MACHINE=B share a recipe foo and the output of foo, then both machine
configurations must build foo in exactly the same way. Otherwise it is
not possible to use both machines in the same distribution.

This criteria can only be tested by testing different machines in combination,
i.e. one main layer, potentially several additional BSP layers and an explicit
choice of machines:
yocto-compat-layer --additional-layers .../meta-intel --machines intel-corei7-64 imx6slevk -- .../meta-freescale

To simplify the analysis and limit the amount of output, mismatches
are sorted by task order such that tasks that run first are also
reported first. Following tasks for the same recipe and set of
machines then get pruned, because they are likely to be different
because of the underlying task (same approach as in
test_signatures). The difference here is that we get information about
all machines. The task order in the base configuration serves as
heuristic for sorting that merged list.

The test has already found issues in go-cross (depended on
tune-specific libgcc) and gdb-cross (had a tune-specific path
unnecessarily), so it is also useful to uncover issues that are not
caused by the BSP layer itself.

Signed-off-by: Patrick Ohly <patrick.ohly@intel.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

3 files changed, 161 insertions, 3 deletions

diff --git a/scripts/lib/compatlayer/__init__.py b/scripts/lib/compatlayer/__init__.py
index 6130b8548c..0d6f4e9c3b 100644
--- a/scripts/lib/compatlayer/__init__.py
+++ b/scripts/lib/compatlayer/__init__.py
@@ -215,7 +215,7 @@ def check_command(error_msg, cmd):
         raise RuntimeError(msg)
     return output
 
-def get_signatures(builddir, failsafe=False):
+def get_signatures(builddir, failsafe=False, machine=None):
     import re
 
     # some recipes needs to be excluded like meta-world-pkgdata
@@ -226,7 +226,10 @@ def get_signatures(builddir, failsafe=False):
     sigs = {}
     tune2tasks = {}
 
-    cmd = 'bitbake '
+    cmd = ''
+    if machine:
+        cmd += 'MACHINE=%s ' % machine
+    cmd += 'bitbake '
     if failsafe:
         cmd += '-k '
     cmd += '-S none world'
diff --git a/scripts/lib/compatlayer/cases/bsp.py b/scripts/lib/compatlayer/cases/bsp.py
index 5d9bf93e4a..90256750af 100644
--- a/scripts/lib/compatlayer/cases/bsp.py
+++ b/scripts/lib/compatlayer/cases/bsp.py
@@ -3,7 +3,7 @@
 
 import unittest
 
-from compatlayer import LayerType
+from compatlayer import LayerType, get_signatures, check_command, get_depgraph
 from compatlayer.case import OECompatLayerTestCase
 
 class BSPCompatLayer(OECompatLayerTestCase):
@@ -24,3 +24,155 @@ class BSPCompatLayer(OECompatLayerTestCase):
         self.assertEqual(self.td['bbvars']['MACHINE'], machine,
                 msg="Layer %s modified machine %s -> %s" % \
                     (self.tc.layer['name'], self.td['bbvars']['MACHINE'], machine))
+
+    def test_machine_signatures(self):
+        '''
+        Selecting a machine may only affect the signature of tasks that are specific
+        to that machine. In other words, when MACHINE=A and MACHINE=B share a recipe
+        foo and the output of foo, then both machine configurations must build foo
+        in exactly the same way. Otherwise it is not possible to use both machines
+        in the same distribution.
+
+        This criteria can only be tested by testing different machines in combination,
+        i.e. one main layer, potentially several additional BSP layers and an explicit
+        choice of machines:
+        yocto-compat-layer --additional-layers .../meta-intel --machines intel-corei7-64 imx6slevk -- .../meta-freescale
+        '''
+
+        if not self.td['machines']:
+            self.skipTest('No machines set with --machines.')
+
+        # Collect signatures for all machines that we are testing
+        # and merge that into a hash:
+        # tune -> task -> signature -> list of machines with that combination
+        #
+        # It is an error if any tune/task pair has more than one signature,
+        # because that implies that the machines that caused those different
+        # signatures do not agree on how to execute the task.
+        tunes = {}
+        # Preserve ordering of machines as chosen by the user.
+        for machine in self.td['machines']:
+            curr_sigs, tune2tasks = get_signatures(self.td['builddir'], failsafe=True, machine=machine)
+            # Invert the tune -> [tasks] mapping.
+            tasks2tune = {}
+            for tune, tasks in tune2tasks.items():
+                for task in tasks:
+                    tasks2tune[task] = tune
+            for task, sighash in curr_sigs.items():
+                tunes.setdefault(tasks2tune[task], {}).setdefault(task, {}).setdefault(sighash, []).append(machine)
+
+        msg = []
+        pruned = 0
+        last_line_key = None
+        # do_fetch, do_unpack, ..., do_build
+        taskname_list = []
+        if tunes:
+            # The output below is most useful when we start with tasks that are at
+            # the bottom of the dependency chain, i.e. those that run first. If
+            # those tasks differ, the rest also does.
+            #
+            # To get an ordering of tasks, we do a topological sort of the entire
+            # depgraph for the base configuration, then on-the-fly flatten that list by stripping
+            # out the recipe names and removing duplicates. The base configuration
+            # is not necessarily representative, but should be close enough. Tasks
+            # that were not encountered get a default priority.
+            depgraph = get_depgraph()
+            depends = depgraph['tdepends']
+            WHITE = 1
+            GRAY = 2
+            BLACK = 3
+            color = {}
+            found = set()
+            def visit(task):
+                color[task] = GRAY
+                for dep in depends.get(task, ()):
+                    if color.setdefault(dep, WHITE) == WHITE:
+                        visit(dep)
+                color[task] = BLACK
+                pn, taskname = task.rsplit('.', 1)
+                if taskname not in found:
+                    taskname_list.append(taskname)
+                    found.add(taskname)
+            for task in depends.keys():
+                if color.setdefault(task, WHITE) == WHITE:
+                    visit(task)
+
+        taskname_order = dict([(task, index) for index, task in enumerate(taskname_list) ])
+        def task_key(task):
+            pn, taskname = task.rsplit(':', 1)
+            return (pn, taskname_order.get(taskname, len(taskname_list)), taskname)
+
+        for tune in sorted(tunes.keys()):
+            tasks = tunes[tune]
+            # As for test_signatures it would be nicer to sort tasks
+            # by dependencies here, but that is harder because we have
+            # to report on tasks from different machines, which might
+            # have different dependencies. We resort to pruning the
+            # output by reporting only one task per recipe if the set
+            # of machines matches.
+            #
+            # "bitbake-diffsigs -t -s" is intelligent enough to print
+            # diffs recursively, so often it does not matter that much
+            # if we don't pick the underlying difference
+            # here. However, sometimes recursion fails
+            # (https://bugzilla.yoctoproject.org/show_bug.cgi?id=6428).
+            #
+            # To mitigate that a bit, we use a hard-coded ordering of
+            # tasks that represents how they normally run and prefer
+            # to print the ones that run first.
+            for task in sorted(tasks.keys(), key=task_key):
+                signatures = tasks[task]
+                # do_build can be ignored: it is know to have
+                # different signatures in some cases, for example in
+                # the allarch ca-certificates due to RDEPENDS=openssl.
+                # That particular dependency is whitelisted via
+                # SIGGEN_EXCLUDE_SAFE_RECIPE_DEPS, but still shows up
+                # in the sstate signature hash because filtering it
+                # out would be hard and running do_build multiple
+                # times doesn't really matter.
+                if len(signatures.keys()) > 1 and \
+                   not task.endswith(':do_build'):
+                    # Error!
+                    #
+                    # Sort signatures by machines, because the hex values don't mean anything.
+                    # => all-arch adwaita-icon-theme:do_build: 1234... (beaglebone, qemux86) != abcdf... (qemux86-64)
+                    #
+                    # Skip the line if it is covered already by the predecessor (same pn, same sets of machines).
+                    pn, taskname = task.rsplit(':', 1)
+                    next_line_key = (pn, sorted(signatures.values()))
+                    if next_line_key != last_line_key:
+                        line = '   %s %s: ' % (tune, task)
+                        line += ' != '.join(['%s (%s)' % (signature, ', '.join([m for m in signatures[signature]])) for
+                                             signature in sorted(signatures.keys(), key=lambda s: signatures[s])])
+                        last_line_key = next_line_key
+                        msg.append(line)
+                        # Randomly pick two mismatched signatures and remember how to invoke
+                        # bitbake-diffsigs for them.
+                        iterator = iter(signatures.items())
+                        a = next(iterator)
+                        b = next(iterator)
+                        diffsig_machines = '(%s) != (%s)' % (', '.join(a[1]), ', '.join(b[1]))
+                        diffsig_params = '-t %s %s -s %s %s' % (pn, taskname, a[0], b[0])
+                    else:
+                        pruned += 1
+
+        if msg:
+            msg.insert(0, 'The machines have conflicting signatures for some shared tasks:')
+            if pruned > 0:
+                msg.append('')
+                msg.append('%d tasks where not listed because some other task of the recipe already differed.' % pruned)
+                msg.append('It is likely that differences from different recipes also have the same root cause.')
+            msg.append('')
+            # Explain how to investigate...
+            msg.append('To investigate, run bitbake-diffsigs -t recipename taskname -s fromsig tosig.')
+            cmd = 'bitbake-diffsigs %s' % diffsig_params
+            msg.append('Example: %s in the last line' % diffsig_machines)
+            msg.append('Command: %s' % cmd)
+            # ... and actually do it automatically for that example, but without aborting
+            # when that fails.
+            try:
+                output = check_command('Comparing signatures failed.', cmd).decode('utf-8')
+            except RuntimeError as ex:
+                output = str(ex)
+            msg.extend(['   ' + line for line in output.splitlines()])
+            self.fail('\n'.join(msg))
diff --git a/scripts/yocto-compat-layer.py b/scripts/yocto-compat-layer.py
index daf3a6a32a..0d5700b538 100755
--- a/scripts/yocto-compat-layer.py
+++ b/scripts/yocto-compat-layer.py
@@ -49,6 +49,8 @@ def main():
             help='File to output log (optional)', action='store')
     parser.add_argument('--dependency', nargs="+",
             help='Layers to process for dependencies', action='store')
+    parser.add_argument('--machines', nargs="+",
+            help='List of MACHINEs to be used during testing', action='store')
     parser.add_argument('--additional-layers', nargs="+",
             help='List of additional layers to add during testing', action='store')
     parser.add_argument('-n', '--no-auto', help='Disable auto layer discovery',
@@ -162,6 +164,7 @@ def main():
         logger.info('Getting initial signatures ...')
         td['builddir'] = builddir
         td['sigs'], td['tunetasks'] = get_signatures(td['builddir'])
+        td['machines'] = args.machines
 
         if not add_layer(bblayersconf, layer, dep_layers, logger):
             logger.info('Skipping %s ???.' % layer['name'])