bitbake: ast/data/codeparser: Add dependencies from python module functions

Moving code into python modules is a very effective way to reduce parsing
time and overhead in recipes. The downside has always been that any
dependency information on which variables those functions access is lost
and the hashes can therefore become less reliable.

This patch adds parsing of the imported module functions and that dependency
information is them injected back into the hash dependency information.

Intermodule function references are resolved to the full function
call names in our module namespace to ensure interfunction dependencies
are correctly handled too.

(Bitbake rev: 605c478ce14cdc3c02d6ef6d57146a76d436a83c)

(Bitbake rev: 91441e157e495b02db44e19e836afad366ee8924)

Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

bitbake/lib/bb/codeparser.py

@@ -27,6 +27,7 @@ import ast
 import sys
 import codegen
 import logging
+import inspect
 import bb.pysh as pysh
 import bb.utils, bb.data
 import hashlib
@@ -58,10 +59,33 @@ def check_indent(codestr):
 
     return codestr
 
+modulecode_deps = {}
+
+def add_module_functions(fn, functions, namespace):
+    fstat = os.stat(fn)
+    fixedhash = fn + ":" + str(fstat.st_size) +  ":" + str(fstat.st_mtime)
+    for f in functions:
+        name = "%s.%s" % (namespace, f)
+        parser = PythonParser(name, logger)
+        try:
+            parser.parse_python(None, filename=fn, lineno=1, fixedhash=fixedhash+f)
+            #bb.warn("Cached %s" % f)
+        except KeyError:
+            lines, lineno = inspect.getsourcelines(functions[f])
+            src = "".join(lines)
+            parser.parse_python(src, filename=fn, lineno=lineno, fixedhash=fixedhash+f)
+            #bb.warn("Not cached %s" % f)
+        execs = parser.execs.copy()
+        # Expand internal module exec references
+        for e in parser.execs:
+            if e in functions:
+                execs.remove(e)
+                execs.add(namespace + "." + e)
+        modulecode_deps[name] = [parser.references.copy(), execs, parser.var_execs.copy(), parser.contains.copy()]
+        #bb.warn("%s: %s\nRefs:%s Execs: %s %s %s" % (name, src, parser.references, parser.execs, parser.var_execs, parser.contains))
+
 # A custom getstate/setstate using tuples is actually worth 15% cachesize by
 # avoiding duplication of the attribute names!
-
-
 class SetCache(object):
     def __init__(self):
         self.setcache = {}
@@ -289,11 +313,17 @@ class PythonParser():
         self.unhandled_message = "in call of %s, argument '%s' is not a string literal"
         self.unhandled_message = "while parsing %s, %s" % (name, self.unhandled_message)
 
-    def parse_python(self, node, lineno=0, filename="<string>"):
+    # For the python module code it is expensive to have the function text so it is
-        if not node or not node.strip():
+    # uses a different fixedhash to cache against. We can take the hit on obtaining the
+    # text if it isn't in the cache.
+    def parse_python(self, node, lineno=0, filename="<string>", fixedhash=None):
+        if not fixedhash and (not node or not node.strip()):
             return
 
-        h = bbhash(str(node))
+        if fixedhash:
+            h = fixedhash
+        else:
+            h = bbhash(str(node))
 
         if h in codeparsercache.pythoncache:
             self.references = set(codeparsercache.pythoncache[h].refs)
@@ -311,6 +341,9 @@ class PythonParser():
                 self.contains[i] = set(codeparsercache.pythoncacheextras[h].contains[i])
             return
 
+        if fixedhash and not node:
+            raise KeyError
+
         # Need to parse so take the hit on the real log buffer
         self.log = BufferedLogger('BitBake.Data.PythonParser', logging.DEBUG, self._log)
 

bitbake/lib/bb/data.py

@@ -261,7 +261,7 @@ def emit_func_python(func, o=sys.__stdout__, d = init()):
                newdeps |= set((d.getVarFlag(dep, "vardeps") or "").split())
         newdeps -= seen
 
-def build_dependencies(key, keys, shelldeps, varflagsexcl, ignored_vars, d):
+def build_dependencies(key, keys, mod_funcs, shelldeps, varflagsexcl, ignored_vars, d):
     def handle_contains(value, contains, exclusions, d):
         newvalue = []
         if value:
@@ -289,6 +289,12 @@ def build_dependencies(key, keys, shelldeps, varflagsexcl, ignored_vars, d):
 
     deps = set()
     try:
+        if key in mod_funcs:
+            exclusions = set()
+            moddep = bb.codeparser.modulecode_deps[key]
+            value = handle_contains("", moddep[3], exclusions, d)
+            return frozenset((moddep[0] | keys & moddep[1]) - ignored_vars), value
+
         if key[-1] == ']':
             vf = key[:-1].split('[')
             if vf[1] == "vardepvalueexclude":
@@ -367,7 +373,8 @@ def build_dependencies(key, keys, shelldeps, varflagsexcl, ignored_vars, d):
 
 def generate_dependencies(d, ignored_vars):
 
-    keys = set(key for key in d if not key.startswith("__"))
+    mod_funcs = set(bb.codeparser.modulecode_deps.keys())
+    keys = set(key for key in d if not key.startswith("__")) | mod_funcs
     shelldeps = set(key for key in d.getVar("__exportlist", False) if d.getVarFlag(key, "export", False) and not d.getVarFlag(key, "unexport", False))
     varflagsexcl = d.getVar('BB_SIGNATURE_EXCLUDE_FLAGS')
 
@@ -376,7 +383,7 @@ def generate_dependencies(d, ignored_vars):
 
     tasklist = d.getVar('__BBTASKS', False) or []
     for task in tasklist:
-        deps[task], values[task] = build_dependencies(task, keys, shelldeps, varflagsexcl, ignored_vars, d)
+        deps[task], values[task] = build_dependencies(task, keys, mod_funcs, shelldeps, varflagsexcl, ignored_vars, d)
         newdeps = deps[task]
         seen = set()
         while newdeps:
@@ -385,7 +392,7 @@ def generate_dependencies(d, ignored_vars):
             newdeps = set()
             for dep in nextdeps:
                 if dep not in deps:
-                    deps[dep], values[dep] = build_dependencies(dep, keys, shelldeps, varflagsexcl, ignored_vars, d)
+                    deps[dep], values[dep] = build_dependencies(dep, keys, mod_funcs, shelldeps, varflagsexcl, ignored_vars, d)
                 newdeps |=  deps[dep]
             newdeps -= seen
         #print "For %s: %s" % (task, str(deps[task]))

bitbake/lib/bb/parse/ast.py

@@ -290,6 +290,18 @@ class PyLibNode(AstNode):
             toimport = getattr(bb.utils._context[self.namespace], "BBIMPORTS", [])
             for i in toimport:
                 bb.utils._context[self.namespace] = __import__(self.namespace + "." + i)
+                mod = getattr(bb.utils._context[self.namespace], i)
+                fn = getattr(mod, "__file__")
+                funcs = {}
+                for f in dir(mod):
+                    if f.startswith("_"):
+                        continue
+                    fcall = getattr(mod, f)
+                    if not callable(fcall):
+                        continue
+                    funcs[f] = fcall
+                bb.codeparser.add_module_functions(fn, funcs, "%s.%s" % (self.namespace, i))
+
         except AttributeError as e:
             bb.error("Error importing OE modules: %s" % str(e))
 

bitbake/lib/bb/tests/codeparser.py

@@ -318,7 +318,7 @@ d.getVar(a(), False)
             "filename": "example.bb",
         })
 
-        deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), self.d)
+        deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d)
 
         self.assertEqual(deps, set(["somevar", "bar", "something", "inexpand", "test", "test2", "a"]))
 
@@ -365,7 +365,7 @@ esac
         self.d.setVarFlags("FOO", {"func": True})
         self.setEmptyVars(execs)
 
-        deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), self.d)
+        deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d)
 
         self.assertEqual(deps, set(["somevar", "inverted"] + execs))
 
@@ -375,7 +375,7 @@ esac
         self.d.setVar("FOO", "foo=oe_libinstall; eval $foo")
         self.d.setVarFlag("FOO", "vardeps", "oe_libinstall")
 
-        deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), self.d)
+        deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d)
 
         self.assertEqual(deps, set(["oe_libinstall"]))
 
@@ -384,7 +384,7 @@ esac
         self.d.setVar("FOO", "foo=oe_libinstall; eval $foo")
         self.d.setVarFlag("FOO", "vardeps", "${@'oe_libinstall'}")
 
-        deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), self.d)
+        deps, values = bb.data.build_dependencies("FOO", set(self.d.keys()), set(), set(), set(), set(), self.d)
 
         self.assertEqual(deps, set(["oe_libinstall"]))
 
@@ -399,7 +399,7 @@ esac
         # Check dependencies
         self.d.setVar('ANOTHERVAR', expr)
         self.d.setVar('TESTVAR', 'anothervalue testval testval2')
-        deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), self.d)
+        deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), set(), self.d)
         self.assertEqual(sorted(values.splitlines()),
                          sorted([expr,
                           'TESTVAR{anothervalue} = Set',
@@ -418,14 +418,14 @@ esac
         self.d.setVar('ANOTHERVAR', varval)
         self.d.setVar('TESTVAR', 'anothervalue testval testval2')
         self.d.setVar('TESTVAR2', 'testval3')
-        deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(["TESTVAR"]), self.d)
+        deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), set(["TESTVAR"]), self.d)
         self.assertEqual(sorted(values.splitlines()), sorted([varval]))
         self.assertEqual(deps, set(["TESTVAR2"]))
         self.assertEqual(self.d.getVar('ANOTHERVAR').split(), ['testval3', 'anothervalue'])
 
         # Check the vardepsexclude flag is handled by contains functionality
         self.d.setVarFlag('ANOTHERVAR', 'vardepsexclude', 'TESTVAR')
-        deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), self.d)
+        deps, values = bb.data.build_dependencies("ANOTHERVAR", set(self.d.keys()), set(), set(), set(), set(), self.d)
         self.assertEqual(sorted(values.splitlines()), sorted([varval]))
         self.assertEqual(deps, set(["TESTVAR2"]))
         self.assertEqual(self.d.getVar('ANOTHERVAR').split(), ['testval3', 'anothervalue'])