hohn/codeql
1
0
Fork 0
mirror of https://github.com/github/codeql.git synced 2026-04-30 19:26:02 +02:00
Code Issues Packages Projects Releases Wiki Activity

Python: Fix performance problem in PoorMansFunctionResolution

Browse Source 
Before these changes:

[2021-11-22 12:02:50] (8s) Tuple counts for PoorMansFunctionResolution::getSimpleMethodReferenceWithinClass#ff/2@cbddf257 after 8.6s:
                      387565   ~0%     {3} r1 = JOIN Attributes::AttrRead#class#f WITH Attributes::AttrRef::accesses_dispred#bff ON FIRST 1 OUTPUT Rhs.2, Lhs.0 'result', Rhs.1
                      6548632  ~0%     {3} r2 = JOIN r1 WITH Function::Function::getName_dispred#ff_10#join_rhs ON FIRST 1 OUTPUT Rhs.1 'func', Lhs.1 'result', Lhs.2
                      5640480  ~0%     {4} r3 = JOIN r2 WITH Class::Class::getAMethod_dispred#ff_10#join_rhs ON FIRST 1 OUTPUT Rhs.1, Lhs.1 'result', Lhs.2, Lhs.0 'func'
                      55660458 ~0%     {5} r4 = JOIN r3 WITH Class::Class::getAMethod_dispred#ff ON FIRST 1 OUTPUT Rhs.1, 0, Lhs.1 'result', Lhs.2, Lhs.3 'func'
                      55621412 ~0%     {4} r5 = JOIN r4 WITH AstGenerated::Function_::getArg_dispred#fff ON FIRST 2 OUTPUT Rhs.2, Lhs.2 'result', Lhs.3, Lhs.4 'func'
                      54467144 ~0%     {4} r6 = JOIN r5 WITH DataFlowPublic::ParameterNode::getParameter_dispred#fb_10#join_rhs ON FIRST 1 OUTPUT Lhs.2, Rhs.1, Lhs.1 'result', Lhs.3 'func'
                      20928    ~0%     {2} r7 = JOIN r6 WITH LocalSources::Cached::hasLocalSource#ff ON FIRST 2 OUTPUT Lhs.3 'func', Lhs.2 'result'
                                       return r7

With these changes:

[2021-11-22 11:54:25] (415s) Tuple counts for PoorMansFunctionResolution::getSimpleMethodReferenceWithinClass_helper#fff/3@14db70a8 after 75ms:
                      388306 ~0%     {2} r1 = JOIN Attributes::AttrRead#class#f WITH Attributes::AttrRef::getObject_dispred#bf ON FIRST 1 OUTPUT Rhs.1, Lhs.0 'read'
                      379420 ~4%     {2} r2 = JOIN r1 WITH LocalSources::Cached::hasLocalSource#ff ON FIRST 1 OUTPUT Rhs.1, Lhs.1 'read'
                      175082 ~0%     {2} r3 = JOIN r2 WITH DataFlowPublic::ParameterNode#class#fff ON FIRST 1 OUTPUT Rhs.2, Lhs.1 'read'
                      175082 ~2%     {3} r4 = JOIN r3 WITH Essa::ParameterDefinition::getParameter_dispred#ff ON FIRST 1 OUTPUT 0, Rhs.1, Lhs.1 'read'
                      166798 ~0%     {2} r5 = JOIN r4 WITH AstGenerated::Function_::getArg_dispred#fff_120#join_rhs ON FIRST 2 OUTPUT Rhs.2 'func', Lhs.2 'read'
                      162096 ~0%     {3} r6 = JOIN r5 WITH Class::Class::getAMethod_dispred#ff_10#join_rhs ON FIRST 1 OUTPUT Lhs.0 'func', Rhs.1 'cls', Lhs.1 'read'
                                     return r6

[2021-11-22 11:54:25] (415s) Tuple counts for PoorMansFunctionResolution::getSimpleMethodReferenceWithinClass_helper2#ffff/4@2b60f0s9 after 63ms:
                      162046 ~0%     {3} r1 = SCAN PoorMansFunctionResolution::getSimpleMethodReferenceWithinClass_helper#fff OUTPUT In.2 'read', In.0 'func', In.1 'cls'
                      162046 ~0%     {3} r2 = JOIN r1 WITH Attributes::AttrRead#class#f ON FIRST 1 OUTPUT Lhs.1 'func', Lhs.2 'cls', Lhs.0 'read'
                      162046 ~1%     {3} r3 = JOIN r2 WITH py_Functions ON FIRST 1 OUTPUT Lhs.1 'cls', Lhs.2 'read', Lhs.0 'func'
                      162046 ~0%     {3} r4 = JOIN r3 WITH py_Classes ON FIRST 1 OUTPUT Lhs.1 'read', Lhs.2 'func', Lhs.0 'cls'
                      161935 ~5%     {4} r5 = JOIN r4 WITH Attributes::AttrRef::getAttributeName_dispred#bf ON FIRST 1 OUTPUT Rhs.1, Lhs.0 'read', Lhs.1 'func', Lhs.2 'cls'
                      688526 ~1%     {4} r6 = JOIN r5 WITH Function::Function::getName_dispred#ff_10#join_rhs ON FIRST 1 OUTPUT Lhs.2 'func', Lhs.3 'cls', Lhs.1 'read', Rhs.1 'readFunction'
                                     return r6

[2021-11-22 11:54:25] (415s) Tuple counts for PoorMansFunctionResolution::getSimpleMethodReferenceWithinClass#ff/2@f73ae6dq after 58ms:
                      688526 ~0%     {4} r1 = SCAN PoorMansFunctionResolution::getSimpleMethodReferenceWithinClass_helper2#ffff OUTPUT In.1, In.0, In.3 'func', In.2 'result'
                      688526 ~0%     {3} r2 = JOIN r1 WITH Class::Class::getAMethod_dispred#ff ON FIRST 2 OUTPUT Rhs.0, Lhs.2 'func', Lhs.3 'result'
                      20913  ~0%     {2} r3 = JOIN r2 WITH Class::Class::getAMethod_dispred#ff ON FIRST 2 OUTPUT Lhs.1 'func', Lhs.2 'result'
                                     return r3

We need the `pragma[only_bind_into]` in getSimpleMethodReferenceWithinClass_helper2, otherwise the tuple counts would look like, which is needlessly big.

[2021-11-22 17:14:34] (2s) Tuple counts for PoorMansFunctionResolution::getSimpleMethodReferenceWithinClass_helper2#ffff/4@5f0505h7 after 711ms:
                      13570510 ~3%     {2} r1 = JOIN Function::Function::getName_dispred#ff_10#join_rhs WITH Attributes::AttrRef::getAttributeName_dispred#ff_10#join_rhs ON FIRST 1 OUTPUT Rhs.1 'read', Lhs.1 'readFunction'
                      688526   ~1%     {4} r2 = JOIN r1 WITH PoorMansFunctionResolution::getSimpleMethodReferenceWithinClass_helper#fff_201#join_rhs ON FIRST 1 OUTPUT Rhs.1 'func', Rhs.2 'cls', Lhs.0 'read', Lhs.1 'readFunction'
                                       return r2
This commit is contained in:
Rasmus Wriedt Larsen
2021-11-22 17:22:39 +01:00
parent f09f1c4c50
commit eaed870b31
1 changed files with 34 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
python/ql/lib/semmle/python/frameworks/internal/PoorMansFunctionResolution.qll
View File

@@ -62,19 +62,49 @@ private DataFlow::TypeTrackingNode poorMansFunctionTracker(DataFlow::TypeTracker
exists(DataFlow::TypeTracker t2 | result = poorMansFunctionTracker(t2, func).track(t2, t))
}
/** Helper predicate to avoid bad join order. */
pragma[noinline]
private predicate getSimpleMethodReferenceWithinClass_helper(
Function func, Class cls, DataFlow::AttrRead read
) {
DataFlow::parameterNode(func.getArg(0)).flowsTo(read.getObject()) and
cls.getAMethod() = func
}
/**
* Helper predicate to avoid bad join order, which looked like:
*
* (8s) Tuple counts for PoorMansFunctionResolution::getSimpleMethodReferenceWithinClass#ff/2@cbddf257 after 8.6s:
* 387565 ~0% {3} r1 = JOIN Attributes::AttrRead#class#f WITH Attributes::AttrRef::accesses_dispred#bff ON FIRST 1 OUTPUT Rhs.2, Lhs.0 'result', Rhs.1
* 6548632 ~0% {3} r2 = JOIN r1 WITH Function::Function::getName_dispred#ff_10#join_rhs ON FIRST 1 OUTPUT Rhs.1 'func', Lhs.1 'result', Lhs.2
* 5640480 ~0% {4} r3 = JOIN r2 WITH Class::Class::getAMethod_dispred#ff_10#join_rhs ON FIRST 1 OUTPUT Rhs.1, Lhs.1 'result', Lhs.2, Lhs.0 'func'
* 55660458 ~0% {5} r4 = JOIN r3 WITH Class::Class::getAMethod_dispred#ff ON FIRST 1 OUTPUT Rhs.1, 0, Lhs.1 'result', Lhs.2, Lhs.3 'func'
* 55621412 ~0% {4} r5 = JOIN r4 WITH AstGenerated::Function_::getArg_dispred#fff ON FIRST 2 OUTPUT Rhs.2, Lhs.2 'result', Lhs.3, Lhs.4 'func'
* 54467144 ~0% {4} r6 = JOIN r5 WITH DataFlowPublic::ParameterNode::getParameter_dispred#fb_10#join_rhs ON FIRST 1 OUTPUT Lhs.2, Rhs.1, Lhs.1 'result', Lhs.3 'func'
* 20928 ~0% {2} r7 = JOIN r6 WITH LocalSources::Cached::hasLocalSource#ff ON FIRST 2 OUTPUT Lhs.3 'func', Lhs.2 'result'
* return r7
*/
pragma[noinline]
private predicate getSimpleMethodReferenceWithinClass_helper2(
Function func, Class cls, DataFlow::AttrRead read, Function readFunction
) {
getSimpleMethodReferenceWithinClass_helper(pragma[only_bind_into](func),
pragma[only_bind_into](cls), pragma[only_bind_into](read)) and
read.getAttributeName() = readFunction.getName()
}
/**
* Gets a reference to `func`. `func` must be defined inside a class, and the reference
* will be inside a different method of the same class.
*/
private DataFlow::Node getSimpleMethodReferenceWithinClass(Function func) {
// TODO: Should take MRO into account
exists(Class cls, Function otherFunc, DataFlow::Node selfRefOtherFunc |
exists(Class cls, Function otherFunc |
cls.getAMethod() = func and
cls.getAMethod() = otherFunc
|
selfRefOtherFunc.getALocalSource().(DataFlow::ParameterNode).getParameter() =
otherFunc.getArg(0) and
result.(DataFlow::AttrRead).accesses(selfRefOtherFunc, func.getName())
getSimpleMethodReferenceWithinClass_helper2(pragma[only_bind_into](otherFunc),
pragma[only_bind_into](cls), pragma[only_bind_into](result), pragma[only_bind_into](func))
)
}