// run - Calculate the top down data structure graphs for each function in the
// program.
//
bool TDDataStructures::runOnModule(Module &M) {
init(useEQBU ? &getAnalysis<EquivBUDataStructures>()
: &getAnalysis<BUDataStructures>(),
true, true, true, false);
for (Module::iterator F = M.begin(); F != M.end(); ++F) {
if (!(F->isDeclaration())){
DSGraph *G = getOrCreateGraph(F);
G->getAuxFunctionCalls().clear();
}
}
// Figure out which functions must not mark their arguments complete because
// they are accessible outside this compilation unit. Currently, these
// arguments are functions which are reachable by incomplete or external
// nodes in the globals graph.
const DSScalarMap &GGSM = GlobalsGraph->getScalarMap();
DenseSet<DSNode*> Visited;
for (DSScalarMap::global_iterator I=GGSM.global_begin(), E=GGSM.global_end();
I != E; ++I) {
DSNode *N = GGSM.find(*I)->second.getNode();
if (N->isIncompleteNode() || N->isExternalNode())
markReachableFunctionsExternallyAccessible(N, Visited);
}
// Loop over unresolved call nodes. Any functions passed into (but not
// returned!) from unresolvable call nodes may be invoked outside of the
// current module.
for (DSGraph::afc_iterator I = GlobalsGraph->afc_begin(),
E = GlobalsGraph->afc_end(); I != E; ++I)
for (unsigned arg = 0, e = I->getNumPtrArgs(); arg != e; ++arg)
markReachableFunctionsExternallyAccessible(I->getPtrArg(arg).getNode(),
Visited);
Visited.clear();
// Clear Aux of Globals Graph to be refilled in later by post-TD unresolved
// functions
GlobalsGraph->getAuxFunctionCalls().clear();
// Functions without internal linkage are definitely externally callable!
for (Module::iterator I = M.begin(), E = M.end(); I != E; ++I)
if (!I->isDeclaration() && !I->hasInternalLinkage() && !I->hasPrivateLinkage())
ExternallyCallable.insert(I);
// Debug code to print the functions that are externally callable
#if 0
for (Module::iterator I = M.begin(), E = M.end(); I != E; ++I)
if (ExternallyCallable.count(I)) {
errs() << "ExternallyCallable: " << I->getNameStr() << "\n";
}
#endif
// We want to traverse the call graph in reverse post-order. To do this, we
// calculate a post-order traversal, then reverse it.
DenseSet<DSGraph*> VisitedGraph;
std::vector<DSGraph*> PostOrder;
{TIME_REGION(XXX, "td:Compute postorder");
// Calculate top-down from main...
if (Function *F = M.getFunction("main"))
ComputePostOrder(*F, VisitedGraph, PostOrder);
// Next calculate the graphs for each unreachable function...
for (Module::iterator I = M.begin(), E = M.end(); I != E; ++I)
if (!I->isDeclaration())
ComputePostOrder(*I, VisitedGraph, PostOrder);
VisitedGraph.clear(); // Release memory!
}
{TIME_REGION(XXX, "td:Inline stuff");
// Visit each of the graphs in reverse post-order now!
while (!PostOrder.empty()) {
InlineCallersIntoGraph(PostOrder.back());
PostOrder.pop_back();
}
}
// Free the IndCallMap.
while (!IndCallMap.empty()) {
delete IndCallMap.begin()->second;
IndCallMap.erase(IndCallMap.begin());
}
formGlobalECs();
ExternallyCallable.clear();
GlobalsGraph->removeTriviallyDeadNodes();
GlobalsGraph->computeExternalFlags(DSGraph::DontMarkFormalsExternal);
GlobalsGraph->computeIntPtrFlags();
// Make sure each graph has updated external information about globals
// in the globals graph.
VisitedGraph.clear();
for (Module::iterator F = M.begin(); F != M.end(); ++F) {
if (!(F->isDeclaration())){
DSGraph *Graph = getOrCreateGraph(F);
if (!VisitedGraph.insert(Graph).second) continue;
cloneGlobalsInto(Graph, DSGraph::DontCloneCallNodes |
DSGraph::DontCloneAuxCallNodes);
Graph->computeExternalFlags(DSGraph::DontMarkFormalsExternal);
Graph->computeIntPtrFlags();
// Clean up uninteresting nodes
Graph->removeDeadNodes(0);
}
}
// CBU contains the correct call graph.
// Restore it, so that subsequent passes and clients can get it.
restoreCorrectCallGraph();
return false;
}
static void printCollection(const Collection &C, llvm::raw_ostream &O,
const Module *M, const std::string &Prefix) {
if (M == 0) {
O << "Null Module pointer, cannot continue!\n";
return;
}
unsigned TotalNumNodes = 0, TotalCallNodes = 0;
for (Module::const_iterator I = M->begin(), E = M->end(); I != E; ++I)
if (C.hasDSGraph(*I)) {
DSGraph* Gr = C.getDSGraph((const Function&)*I);
unsigned NumCalls = Gr->shouldUseAuxCalls() ?
Gr->getAuxFunctionCalls().size() : Gr->getFunctionCalls().size();
bool IsDuplicateGraph = false;
//if no only print options, print everything
bool doPrint = OnlyPrint.begin() == OnlyPrint.end();
//otherwise check the name
if (!doPrint)
doPrint = OnlyPrint.end() !=
std::find(OnlyPrint.begin(), OnlyPrint.end(), I->getName().str());
if (doPrint) {
const Function *SCCFn = Gr->retnodes_begin()->first;
if (&*I == SCCFn) {
Gr->writeGraphToFile(O, Prefix+I->getName().str());
} else {
IsDuplicateGraph = true; // Don't double count node/call nodes.
O << "Didn't write '" << Prefix+I->getName().str()
<< ".dot' - Graph already emitted to '" << Prefix+SCCFn->getName().str()
<< "\n";
}
} else {
const Function *SCCFn = Gr->retnodes_begin()->first;
if (&*I == SCCFn) {
//O << "Skipped Writing '" << Prefix+I->getName().str() << ".dot'... ["
// << Gr->getGraphSize() << "+" << NumCalls << "]\n";
} else {
IsDuplicateGraph = true; // Don't double count node/call nodes.
}
}
if (!IsDuplicateGraph) {
unsigned GraphSize = Gr->getGraphSize();
if (MaxGraphSize < GraphSize) MaxGraphSize = GraphSize;
TotalNumNodes += Gr->getGraphSize();
TotalCallNodes += NumCalls;
for (DSGraph::node_iterator NI = Gr->node_begin(), E = Gr->node_end();
NI != E; ++NI)
if (NI->isNodeCompletelyFolded())
++NumFoldedNodes;
}
}
DSGraph* GG = C.getGlobalsGraph();
TotalNumNodes += GG->getGraphSize();
TotalCallNodes += GG->getFunctionCalls().size();
GG->writeGraphToFile(O, Prefix + "GlobalsGraph");
O << "\nGraphs contain [" << TotalNumNodes << "+" << TotalCallNodes
<< "] nodes total\n";
}
//
// Method: calculateGraphs()
//
// Description:
// Perform recursive bottom-up inlining of DSGraphs from callee to caller.
//
// Inputs:
// F - The function which should have its callees' DSGraphs merged into its
// own DSGraph.
// Stack - The stack used for Tarjan's SCC-finding algorithm.
// NextID - The nextID value used for Tarjan's SCC-finding algorithm.
// ValMap - The map used for Tarjan's SCC-finding algorithm.
//
// Return value:
//
unsigned
BUDataStructures::calculateGraphs (const Function *F,
TarjanStack & Stack,
unsigned & NextID,
TarjanMap & ValMap) {
assert(!ValMap.count(F) && "Shouldn't revisit functions!");
unsigned Min = NextID++, MyID = Min;
ValMap[F] = Min;
Stack.push_back(F);
//
// FIXME: This test should be generalized to be any function that we have
// already processed in the case when there isn't a main() or there are
// unreachable functions!
//
if (F->isDeclaration()) { // sprintf, fprintf, sscanf, etc...
// No callees!
Stack.pop_back();
ValMap[F] = ~0;
return Min;
}
//
// Get the DSGraph of the current function. Make one if one doesn't exist.
//
DSGraph* Graph = getOrCreateGraph(F);
//
// Find all callee functions. Use the DSGraph for this (do not use the call
// graph (DSCallgraph) as we're still in the process of constructing it).
//
FuncSet CalleeFunctions;
getAllAuxCallees(Graph, CalleeFunctions);
//
// Iterate through each call target (these are the edges out of the current
// node (i.e., the current function) in Tarjan graph parlance). Find the
// minimum assigned ID.
//
for (FuncSet::iterator I = CalleeFunctions.begin(), E = CalleeFunctions.end();
I != E; ++I) {
const Function *Callee = *I;
unsigned M;
//
// If we have not visited this callee before, visit it now (this is the
// post-order component of the Bottom-Up algorithm). Otherwise, look up
// the assigned ID value from the Tarjan Value Map.
//
TarjanMap::iterator It = ValMap.find(Callee);
if (It == ValMap.end()) // No, visit it now.
M = calculateGraphs(Callee, Stack, NextID, ValMap);
else // Yes, get it's number.
M = It->second;
//
// If we've found a function with a smaller ID than this funtion, record
// that ID as the minimum ID.
//
if (M < Min) Min = M;
}
assert(ValMap[F] == MyID && "SCC construction assumption wrong!");
//
// If the minimum ID found is not this function's ID, then this function is
// part of a larger SCC.
//
if (Min != MyID)
return Min;
//
// If this is a new SCC, process it now.
//
if (Stack.back() == F) { // Special case the single "SCC" case here.
DEBUG(errs() << "Visiting single node SCC #: " << MyID << " fn: "
<< F->getName() << "\n");
Stack.pop_back();
DEBUG(errs() << " [BU] Calculating graph for: " << F->getName()<< "\n");
DSGraph* G = getOrCreateGraph(F);
calculateGraph(G);
DEBUG(errs() << " [BU] Done inlining: " << F->getName() << " ["
<< G->getGraphSize() << "+" << G->getAuxFunctionCalls().size()
<< "]\n");
if (MaxSCC < 1) MaxSCC = 1;
//
// Should we revisit the graph? Only do it if there are now new resolvable
// callees.
FuncSet NewCallees;
getAllAuxCallees(G, NewCallees);
if (!NewCallees.empty()) {
if (hasNewCallees(NewCallees, CalleeFunctions)) {
DEBUG(errs() << "Recalculating " << F->getName() << " due to new knowledge\n");
ValMap.erase(F);
++NumRecalculations;
return calculateGraphs(F, Stack, NextID, ValMap);
}
++NumRecalculationsSkipped;
}
ValMap[F] = ~0U;
return MyID;
} else {
unsigned SCCSize = 1;
const Function *NF = Stack.back();
if(NF != F)
ValMap[NF] = ~0U;
DSGraph* SCCGraph = getDSGraph(*NF);
//
// First thing first: collapse all of the DSGraphs into a single graph for
// the entire SCC. Splice all of the graphs into one and discard all of
// the old graphs.
//
while (NF != F) {
Stack.pop_back();
NF = Stack.back();
if(NF != F)
ValMap[NF] = ~0U;
DSGraph* NFG = getDSGraph(*NF);
if (NFG != SCCGraph) {
// Update the Function -> DSG map.
for (DSGraph::retnodes_iterator I = NFG->retnodes_begin(),
E = NFG->retnodes_end(); I != E; ++I)
setDSGraph(*I->first, SCCGraph);
SCCGraph->spliceFrom(NFG);
delete NFG;
++SCCSize;
}
}
Stack.pop_back();
DEBUG(errs() << "Calculating graph for SCC #: " << MyID << " of size: "
<< SCCSize << "\n");
// Compute the Max SCC Size.
if (MaxSCC < SCCSize)
MaxSCC = SCCSize;
// Clean up the graph before we start inlining a bunch again...
SCCGraph->removeDeadNodes(DSGraph::KeepUnreachableGlobals);
// Now that we have one big happy family, resolve all of the call sites in
// the graph...
calculateGraph(SCCGraph);
DEBUG(errs() << " [BU] Done inlining SCC [" << SCCGraph->getGraphSize()
<< "+" << SCCGraph->getAuxFunctionCalls().size() << "]\n"
<< "DONE with SCC #: " << MyID << "\n");
FuncSet NewCallees;
getAllAuxCallees(SCCGraph, NewCallees);
if (!NewCallees.empty()) {
if (hasNewCallees(NewCallees, CalleeFunctions)) {
DEBUG(errs() << "Recalculating SCC Graph " << F->getName() << " due to new knowledge\n");
ValMap.erase(F);
++NumRecalculations;
return calculateGraphs(F, Stack, NextID, ValMap);
}
++NumRecalculationsSkipped;
}
ValMap[F] = ~0U;
return MyID;
}
}
unsigned BUDataStructures::calculateGraphs(const Function *F,
std::vector<const Function*> &Stack,
unsigned &NextID,
hash_map<const Function*, unsigned> &ValMap) {
assert(!ValMap.count(F) && "Shouldn't revisit functions!");
unsigned Min = NextID++, MyID = Min;
ValMap[F] = Min;
Stack.push_back(F);
// FIXME! This test should be generalized to be any function that we have
// already processed, in the case when there isn't a main or there are
// unreachable functions!
if (F->isDeclaration()) { // sprintf, fprintf, sscanf, etc...
// No callees!
Stack.pop_back();
ValMap[F] = ~0;
return Min;
}
DSGraph* Graph = getOrFetchDSGraph(F);
// Find all callee functions.
std::vector<const Function*> CalleeFunctions;
GetAllAuxCallees(Graph, CalleeFunctions);
std::sort(CalleeFunctions.begin(), CalleeFunctions.end());
std::vector<const Function*>::iterator uid = std::unique(CalleeFunctions.begin(), CalleeFunctions.end());
CalleeFunctions.resize(uid - CalleeFunctions.begin());
// The edges out of the current node are the call site targets...
for (unsigned i = 0, e = CalleeFunctions.size(); i != e; ++i) {
const Function *Callee = CalleeFunctions[i];
unsigned M;
// Have we visited the destination function yet?
hash_map<const Function*, unsigned>::iterator It = ValMap.find(Callee);
if (It == ValMap.end()) // No, visit it now.
M = calculateGraphs(Callee, Stack, NextID, ValMap);
else // Yes, get it's number.
M = It->second;
if (M < Min) Min = M;
}
assert(ValMap[F] == MyID && "SCC construction assumption wrong!");
if (Min != MyID)
return Min; // This is part of a larger SCC!
// If this is a new SCC, process it now.
if (Stack.back() == F) { // Special case the single "SCC" case here.
DEBUG(errs() << "Visiting single node SCC #: " << MyID << " fn: "
<< F->getName() << "\n");
Stack.pop_back();
DEBUG(errs() << " [BU] Calculating graph for: " << F->getName()<< "\n");
calculateGraph(Graph);
DEBUG(errs() << " [BU] Done inlining: " << F->getName() << " ["
<< Graph->getGraphSize() << "+" << Graph->getAuxFunctionCalls().size()
<< "]\n");
if (MaxSCC < 1) MaxSCC = 1;
// Should we revisit the graph? Only do it if there are now new resolvable
// callees or new callees
GetAllAuxCallees(Graph, CalleeFunctions);
if (CalleeFunctions.size()) {
DEBUG(errs() << "Recalculating " << F->getName() << " due to new knowledge\n");
ValMap.erase(F);
return calculateGraphs(F, Stack, NextID, ValMap);
} else {
ValMap[F] = ~0U;
return MyID;
}
} else {
// SCCFunctions - Keep track of the functions in the current SCC
//
std::vector<DSGraph*> SCCGraphs;
unsigned SCCSize = 1;
const Function *NF = Stack.back();
ValMap[NF] = ~0U;
DSGraph* SCCGraph = getDSGraph(NF);
// First thing first, collapse all of the DSGraphs into a single graph for
// the entire SCC. Splice all of the graphs into one and discard all of the
// old graphs.
//
while (NF != F) {
Stack.pop_back();
NF = Stack.back();
ValMap[NF] = ~0U;
DSGraph* NFG = getDSGraph(NF);
if (NFG != SCCGraph) {
// Update the Function -> DSG map.
for (DSGraph::retnodes_iterator I = NFG->retnodes_begin(),
E = NFG->retnodes_end(); I != E; ++I)
setDSGraph(I->first, SCCGraph);
SCCGraph->spliceFrom(NFG);
delete NFG;
++SCCSize;
}
}
Stack.pop_back();
DEBUG(errs() << "Calculating graph for SCC #: " << MyID << " of size: "
<< SCCSize << "\n");
// Compute the Max SCC Size.
if (MaxSCC < SCCSize)
MaxSCC = SCCSize;
// Clean up the graph before we start inlining a bunch again...
SCCGraph->removeDeadNodes(DSGraph::KeepUnreachableGlobals);
// Now that we have one big happy family, resolve all of the call sites in
// the graph...
calculateGraph(SCCGraph);
DEBUG(errs() << " [BU] Done inlining SCC [" << SCCGraph->getGraphSize()
<< "+" << SCCGraph->getAuxFunctionCalls().size() << "]\n"
<< "DONE with SCC #: " << MyID << "\n");
// We never have to revisit "SCC" processed functions...
return MyID;
}
return MyID; // == Min
}