1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-22 20:43:44 +02:00
llvm-mirror/lib/Transforms/IPO/FunctionAttrs.cpp

1839 lines
58 KiB
C++
Raw Normal View History

//===- FunctionAttrs.cpp - Pass which marks functions attributes ----------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements a simple interprocedural pass which walks the
// call-graph, looking for functions which do not access or only read
// non-local memory, and marking them readnone/readonly. It does the
// same with function arguments independently, marking them readonly/
// readnone/nocapture. Finally, well-known library call declarations
// are marked with all attributes that are consistent with the
// function's standard definition. This pass is implemented as a
// bottom-up traversal of the call-graph.
//
//===----------------------------------------------------------------------===//
#include "llvm/Transforms/IPO.h"
#include "llvm/ADT/SCCIterator.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AliasAnalysis.h"
[PM/AA] Rebuild LLVM's alias analysis infrastructure in a way compatible with the new pass manager, and no longer relying on analysis groups. This builds essentially a ground-up new AA infrastructure stack for LLVM. The core ideas are the same that are used throughout the new pass manager: type erased polymorphism and direct composition. The design is as follows: - FunctionAAResults is a type-erasing alias analysis results aggregation interface to walk a single query across a range of results from different alias analyses. Currently this is function-specific as we always assume that aliasing queries are *within* a function. - AAResultBase is a CRTP utility providing stub implementations of various parts of the alias analysis result concept, notably in several cases in terms of other more general parts of the interface. This can be used to implement only a narrow part of the interface rather than the entire interface. This isn't really ideal, this logic should be hoisted into FunctionAAResults as currently it will cause a significant amount of redundant work, but it faithfully models the behavior of the prior infrastructure. - All the alias analysis passes are ported to be wrapper passes for the legacy PM and new-style analysis passes for the new PM with a shared result object. In some cases (most notably CFL), this is an extremely naive approach that we should revisit when we can specialize for the new pass manager. - BasicAA has been restructured to reflect that it is much more fundamentally a function analysis because it uses dominator trees and loop info that need to be constructed for each function. All of the references to getting alias analysis results have been updated to use the new aggregation interface. All the preservation and other pass management code has been updated accordingly. The way the FunctionAAResultsWrapperPass works is to detect the available alias analyses when run, and add them to the results object. This means that we should be able to continue to respect when various passes are added to the pipeline, for example adding CFL or adding TBAA passes should just cause their results to be available and to get folded into this. The exception to this rule is BasicAA which really needs to be a function pass due to using dominator trees and loop info. As a consequence, the FunctionAAResultsWrapperPass directly depends on BasicAA and always includes it in the aggregation. This has significant implications for preserving analyses. Generally, most passes shouldn't bother preserving FunctionAAResultsWrapperPass because rebuilding the results just updates the set of known AA passes. The exception to this rule are LoopPass instances which need to preserve all the function analyses that the loop pass manager will end up needing. This means preserving both BasicAAWrapperPass and the aggregating FunctionAAResultsWrapperPass. Now, when preserving an alias analysis, you do so by directly preserving that analysis. This is only necessary for non-immutable-pass-provided alias analyses though, and there are only three of interest: BasicAA, GlobalsAA (formerly GlobalsModRef), and SCEVAA. Usually BasicAA is preserved when needed because it (like DominatorTree and LoopInfo) is marked as a CFG-only pass. I've expanded GlobalsAA into the preserved set everywhere we previously were preserving all of AliasAnalysis, and I've added SCEVAA in the intersection of that with where we preserve SCEV itself. One significant challenge to all of this is that the CGSCC passes were actually using the alias analysis implementations by taking advantage of a pretty amazing set of loop holes in the old pass manager's analysis management code which allowed analysis groups to slide through in many cases. Moving away from analysis groups makes this problem much more obvious. To fix it, I've leveraged the flexibility the design of the new PM components provides to just directly construct the relevant alias analyses for the relevant functions in the IPO passes that need them. This is a bit hacky, but should go away with the new pass manager, and is already in many ways cleaner than the prior state. Another significant challenge is that various facilities of the old alias analysis infrastructure just don't fit any more. The most significant of these is the alias analysis 'counter' pass. That pass relied on the ability to snoop on AA queries at different points in the analysis group chain. Instead, I'm planning to build printing functionality directly into the aggregation layer. I've not included that in this patch merely to keep it smaller. Note that all of this needs a nearly complete rewrite of the AA documentation. I'm planning to do that, but I'd like to make sure the new design settles, and to flesh out a bit more of what it looks like in the new pass manager first. Differential Revision: http://reviews.llvm.org/D12080 llvm-svn: 247167
2015-09-09 19:55:00 +02:00
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/BasicAliasAnalysis.h"
#include "llvm/Analysis/CallGraph.h"
#include "llvm/Analysis/CallGraphSCCPass.h"
#include "llvm/Analysis/CaptureTracking.h"
[PM/AA] Rebuild LLVM's alias analysis infrastructure in a way compatible with the new pass manager, and no longer relying on analysis groups. This builds essentially a ground-up new AA infrastructure stack for LLVM. The core ideas are the same that are used throughout the new pass manager: type erased polymorphism and direct composition. The design is as follows: - FunctionAAResults is a type-erasing alias analysis results aggregation interface to walk a single query across a range of results from different alias analyses. Currently this is function-specific as we always assume that aliasing queries are *within* a function. - AAResultBase is a CRTP utility providing stub implementations of various parts of the alias analysis result concept, notably in several cases in terms of other more general parts of the interface. This can be used to implement only a narrow part of the interface rather than the entire interface. This isn't really ideal, this logic should be hoisted into FunctionAAResults as currently it will cause a significant amount of redundant work, but it faithfully models the behavior of the prior infrastructure. - All the alias analysis passes are ported to be wrapper passes for the legacy PM and new-style analysis passes for the new PM with a shared result object. In some cases (most notably CFL), this is an extremely naive approach that we should revisit when we can specialize for the new pass manager. - BasicAA has been restructured to reflect that it is much more fundamentally a function analysis because it uses dominator trees and loop info that need to be constructed for each function. All of the references to getting alias analysis results have been updated to use the new aggregation interface. All the preservation and other pass management code has been updated accordingly. The way the FunctionAAResultsWrapperPass works is to detect the available alias analyses when run, and add them to the results object. This means that we should be able to continue to respect when various passes are added to the pipeline, for example adding CFL or adding TBAA passes should just cause their results to be available and to get folded into this. The exception to this rule is BasicAA which really needs to be a function pass due to using dominator trees and loop info. As a consequence, the FunctionAAResultsWrapperPass directly depends on BasicAA and always includes it in the aggregation. This has significant implications for preserving analyses. Generally, most passes shouldn't bother preserving FunctionAAResultsWrapperPass because rebuilding the results just updates the set of known AA passes. The exception to this rule are LoopPass instances which need to preserve all the function analyses that the loop pass manager will end up needing. This means preserving both BasicAAWrapperPass and the aggregating FunctionAAResultsWrapperPass. Now, when preserving an alias analysis, you do so by directly preserving that analysis. This is only necessary for non-immutable-pass-provided alias analyses though, and there are only three of interest: BasicAA, GlobalsAA (formerly GlobalsModRef), and SCEVAA. Usually BasicAA is preserved when needed because it (like DominatorTree and LoopInfo) is marked as a CFG-only pass. I've expanded GlobalsAA into the preserved set everywhere we previously were preserving all of AliasAnalysis, and I've added SCEVAA in the intersection of that with where we preserve SCEV itself. One significant challenge to all of this is that the CGSCC passes were actually using the alias analysis implementations by taking advantage of a pretty amazing set of loop holes in the old pass manager's analysis management code which allowed analysis groups to slide through in many cases. Moving away from analysis groups makes this problem much more obvious. To fix it, I've leveraged the flexibility the design of the new PM components provides to just directly construct the relevant alias analyses for the relevant functions in the IPO passes that need them. This is a bit hacky, but should go away with the new pass manager, and is already in many ways cleaner than the prior state. Another significant challenge is that various facilities of the old alias analysis infrastructure just don't fit any more. The most significant of these is the alias analysis 'counter' pass. That pass relied on the ability to snoop on AA queries at different points in the analysis group chain. Instead, I'm planning to build printing functionality directly into the aggregation layer. I've not included that in this patch merely to keep it smaller. Note that all of this needs a nearly complete rewrite of the AA documentation. I'm planning to do that, but I'd like to make sure the new design settles, and to flesh out a bit more of what it looks like in the new pass manager first. Differential Revision: http://reviews.llvm.org/D12080 llvm-svn: 247167
2015-09-09 19:55:00 +02:00
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
using namespace llvm;
#define DEBUG_TYPE "functionattrs"
STATISTIC(NumReadNone, "Number of functions marked readnone");
STATISTIC(NumReadOnly, "Number of functions marked readonly");
STATISTIC(NumNoCapture, "Number of arguments marked nocapture");
STATISTIC(NumReadNoneArg, "Number of arguments marked readnone");
STATISTIC(NumReadOnlyArg, "Number of arguments marked readonly");
STATISTIC(NumNoAlias, "Number of function returns marked noalias");
STATISTIC(NumNonNullReturn, "Number of function returns marked nonnull");
STATISTIC(NumAnnotated, "Number of attributes added to library functions");
namespace {
struct FunctionAttrs : public CallGraphSCCPass {
static char ID; // Pass identification, replacement for typeid
FunctionAttrs() : CallGraphSCCPass(ID) {
initializeFunctionAttrsPass(*PassRegistry::getPassRegistry());
}
bool runOnSCC(CallGraphSCC &SCC) override;
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesCFG();
AU.addRequired<AssumptionCacheTracker>();
AU.addRequired<TargetLibraryInfoWrapperPass>();
CallGraphSCCPass::getAnalysisUsage(AU);
}
private:
TargetLibraryInfo *TLI;
bool AddReadAttrs(const CallGraphSCC &SCC);
bool AddArgumentAttrs(const CallGraphSCC &SCC);
bool AddNoAliasAttrs(const CallGraphSCC &SCC);
bool AddNonNullAttrs(const CallGraphSCC &SCC);
bool annotateLibraryCalls(const CallGraphSCC &SCC);
};
}
char FunctionAttrs::ID = 0;
INITIALIZE_PASS_BEGIN(FunctionAttrs, "functionattrs",
"Deduce function attributes", false, false)
[PM/AA] Rebuild LLVM's alias analysis infrastructure in a way compatible with the new pass manager, and no longer relying on analysis groups. This builds essentially a ground-up new AA infrastructure stack for LLVM. The core ideas are the same that are used throughout the new pass manager: type erased polymorphism and direct composition. The design is as follows: - FunctionAAResults is a type-erasing alias analysis results aggregation interface to walk a single query across a range of results from different alias analyses. Currently this is function-specific as we always assume that aliasing queries are *within* a function. - AAResultBase is a CRTP utility providing stub implementations of various parts of the alias analysis result concept, notably in several cases in terms of other more general parts of the interface. This can be used to implement only a narrow part of the interface rather than the entire interface. This isn't really ideal, this logic should be hoisted into FunctionAAResults as currently it will cause a significant amount of redundant work, but it faithfully models the behavior of the prior infrastructure. - All the alias analysis passes are ported to be wrapper passes for the legacy PM and new-style analysis passes for the new PM with a shared result object. In some cases (most notably CFL), this is an extremely naive approach that we should revisit when we can specialize for the new pass manager. - BasicAA has been restructured to reflect that it is much more fundamentally a function analysis because it uses dominator trees and loop info that need to be constructed for each function. All of the references to getting alias analysis results have been updated to use the new aggregation interface. All the preservation and other pass management code has been updated accordingly. The way the FunctionAAResultsWrapperPass works is to detect the available alias analyses when run, and add them to the results object. This means that we should be able to continue to respect when various passes are added to the pipeline, for example adding CFL or adding TBAA passes should just cause their results to be available and to get folded into this. The exception to this rule is BasicAA which really needs to be a function pass due to using dominator trees and loop info. As a consequence, the FunctionAAResultsWrapperPass directly depends on BasicAA and always includes it in the aggregation. This has significant implications for preserving analyses. Generally, most passes shouldn't bother preserving FunctionAAResultsWrapperPass because rebuilding the results just updates the set of known AA passes. The exception to this rule are LoopPass instances which need to preserve all the function analyses that the loop pass manager will end up needing. This means preserving both BasicAAWrapperPass and the aggregating FunctionAAResultsWrapperPass. Now, when preserving an alias analysis, you do so by directly preserving that analysis. This is only necessary for non-immutable-pass-provided alias analyses though, and there are only three of interest: BasicAA, GlobalsAA (formerly GlobalsModRef), and SCEVAA. Usually BasicAA is preserved when needed because it (like DominatorTree and LoopInfo) is marked as a CFG-only pass. I've expanded GlobalsAA into the preserved set everywhere we previously were preserving all of AliasAnalysis, and I've added SCEVAA in the intersection of that with where we preserve SCEV itself. One significant challenge to all of this is that the CGSCC passes were actually using the alias analysis implementations by taking advantage of a pretty amazing set of loop holes in the old pass manager's analysis management code which allowed analysis groups to slide through in many cases. Moving away from analysis groups makes this problem much more obvious. To fix it, I've leveraged the flexibility the design of the new PM components provides to just directly construct the relevant alias analyses for the relevant functions in the IPO passes that need them. This is a bit hacky, but should go away with the new pass manager, and is already in many ways cleaner than the prior state. Another significant challenge is that various facilities of the old alias analysis infrastructure just don't fit any more. The most significant of these is the alias analysis 'counter' pass. That pass relied on the ability to snoop on AA queries at different points in the analysis group chain. Instead, I'm planning to build printing functionality directly into the aggregation layer. I've not included that in this patch merely to keep it smaller. Note that all of this needs a nearly complete rewrite of the AA documentation. I'm planning to do that, but I'd like to make sure the new design settles, and to flesh out a bit more of what it looks like in the new pass manager first. Differential Revision: http://reviews.llvm.org/D12080 llvm-svn: 247167
2015-09-09 19:55:00 +02:00
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(CallGraphWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_END(FunctionAttrs, "functionattrs",
"Deduce function attributes", false, false)
Pass *llvm::createFunctionAttrsPass() { return new FunctionAttrs(); }
namespace {
/// The three kinds of memory access relevant to 'readonly' and
/// 'readnone' attributes.
enum MemoryAccessKind {
MAK_ReadNone = 0,
MAK_ReadOnly = 1,
MAK_MayWrite = 2
};
}
static MemoryAccessKind
checkFunctionMemoryAccess(Function &F, AAResults &AAR,
const SmallPtrSetImpl<Function *> &SCCNodes) {
FunctionModRefBehavior MRB = AAR.getModRefBehavior(&F);
if (MRB == FMRB_DoesNotAccessMemory)
// Already perfect!
return MAK_ReadNone;
// Definitions with weak linkage may be overridden at linktime with
// something that writes memory, so treat them like declarations.
if (F.isDeclaration() || F.mayBeOverridden()) {
if (AliasAnalysis::onlyReadsMemory(MRB))
return MAK_ReadOnly;
// Conservatively assume it writes to memory.
return MAK_MayWrite;
}
// Scan the function body for instructions that may read or write memory.
bool ReadsMemory = false;
for (inst_iterator II = inst_begin(F), E = inst_end(F); II != E; ++II) {
Instruction *I = &*II;
// Some instructions can be ignored even if they read or write memory.
// Detect these now, skipping to the next instruction if one is found.
CallSite CS(cast<Value>(I));
if (CS) {
// Ignore calls to functions in the same SCC.
if (CS.getCalledFunction() && SCCNodes.count(CS.getCalledFunction()))
continue;
FunctionModRefBehavior MRB = AAR.getModRefBehavior(CS);
// If the call doesn't access arbitrary memory, we may be able to
// figure out something.
if (AliasAnalysis::onlyAccessesArgPointees(MRB)) {
// If the call does access argument pointees, check each argument.
if (AliasAnalysis::doesAccessArgPointees(MRB))
// Check whether all pointer arguments point to local memory, and
// ignore calls that only access local memory.
for (CallSite::arg_iterator CI = CS.arg_begin(), CE = CS.arg_end();
CI != CE; ++CI) {
Value *Arg = *CI;
if (Arg->getType()->isPointerTy()) {
AAMDNodes AAInfo;
I->getAAMetadata(AAInfo);
MemoryLocation Loc(Arg, MemoryLocation::UnknownSize, AAInfo);
if (!AAR.pointsToConstantMemory(Loc, /*OrLocal=*/true)) {
if (MRB & MRI_Mod)
// Writes non-local memory. Give up.
return MAK_MayWrite;
if (MRB & MRI_Ref)
// Ok, it reads non-local memory.
ReadsMemory = true;
}
}
}
continue;
}
// The call could access any memory. If that includes writes, give up.
if (MRB & MRI_Mod)
return MAK_MayWrite;
// If it reads, note it.
if (MRB & MRI_Ref)
ReadsMemory = true;
continue;
} else if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
// Ignore non-volatile loads from local memory. (Atomic is okay here.)
if (!LI->isVolatile()) {
MemoryLocation Loc = MemoryLocation::get(LI);
if (AAR.pointsToConstantMemory(Loc, /*OrLocal=*/true))
continue;
}
} else if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
// Ignore non-volatile stores to local memory. (Atomic is okay here.)
if (!SI->isVolatile()) {
MemoryLocation Loc = MemoryLocation::get(SI);
if (AAR.pointsToConstantMemory(Loc, /*OrLocal=*/true))
continue;
}
} else if (VAArgInst *VI = dyn_cast<VAArgInst>(I)) {
// Ignore vaargs on local memory.
MemoryLocation Loc = MemoryLocation::get(VI);
if (AAR.pointsToConstantMemory(Loc, /*OrLocal=*/true))
continue;
}
// Any remaining instructions need to be taken seriously! Check if they
// read or write memory.
if (I->mayWriteToMemory())
// Writes memory. Just give up.
return MAK_MayWrite;
// If this instruction may read memory, remember that.
ReadsMemory |= I->mayReadFromMemory();
}
return ReadsMemory ? MAK_ReadOnly : MAK_ReadNone;
}
/// Deduce readonly/readnone attributes for the SCC.
bool FunctionAttrs::AddReadAttrs(const CallGraphSCC &SCC) {
SmallPtrSet<Function *, 8> SCCNodes;
// Fill SCCNodes with the elements of the SCC. Used for quickly
// looking up whether a given CallGraphNode is in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I)
SCCNodes.insert((*I)->getFunction());
2008-09-29 15:35:31 +02:00
// Check if any of the functions in the SCC read or write memory. If they
// write memory then they can't be marked readnone or readonly.
bool ReadsMemory = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F || F->hasFnAttribute(Attribute::OptimizeNone))
// External node or node we don't want to optimize - assume it may write
// memory and give up.
return false;
[PM/AA] Rebuild LLVM's alias analysis infrastructure in a way compatible with the new pass manager, and no longer relying on analysis groups. This builds essentially a ground-up new AA infrastructure stack for LLVM. The core ideas are the same that are used throughout the new pass manager: type erased polymorphism and direct composition. The design is as follows: - FunctionAAResults is a type-erasing alias analysis results aggregation interface to walk a single query across a range of results from different alias analyses. Currently this is function-specific as we always assume that aliasing queries are *within* a function. - AAResultBase is a CRTP utility providing stub implementations of various parts of the alias analysis result concept, notably in several cases in terms of other more general parts of the interface. This can be used to implement only a narrow part of the interface rather than the entire interface. This isn't really ideal, this logic should be hoisted into FunctionAAResults as currently it will cause a significant amount of redundant work, but it faithfully models the behavior of the prior infrastructure. - All the alias analysis passes are ported to be wrapper passes for the legacy PM and new-style analysis passes for the new PM with a shared result object. In some cases (most notably CFL), this is an extremely naive approach that we should revisit when we can specialize for the new pass manager. - BasicAA has been restructured to reflect that it is much more fundamentally a function analysis because it uses dominator trees and loop info that need to be constructed for each function. All of the references to getting alias analysis results have been updated to use the new aggregation interface. All the preservation and other pass management code has been updated accordingly. The way the FunctionAAResultsWrapperPass works is to detect the available alias analyses when run, and add them to the results object. This means that we should be able to continue to respect when various passes are added to the pipeline, for example adding CFL or adding TBAA passes should just cause their results to be available and to get folded into this. The exception to this rule is BasicAA which really needs to be a function pass due to using dominator trees and loop info. As a consequence, the FunctionAAResultsWrapperPass directly depends on BasicAA and always includes it in the aggregation. This has significant implications for preserving analyses. Generally, most passes shouldn't bother preserving FunctionAAResultsWrapperPass because rebuilding the results just updates the set of known AA passes. The exception to this rule are LoopPass instances which need to preserve all the function analyses that the loop pass manager will end up needing. This means preserving both BasicAAWrapperPass and the aggregating FunctionAAResultsWrapperPass. Now, when preserving an alias analysis, you do so by directly preserving that analysis. This is only necessary for non-immutable-pass-provided alias analyses though, and there are only three of interest: BasicAA, GlobalsAA (formerly GlobalsModRef), and SCEVAA. Usually BasicAA is preserved when needed because it (like DominatorTree and LoopInfo) is marked as a CFG-only pass. I've expanded GlobalsAA into the preserved set everywhere we previously were preserving all of AliasAnalysis, and I've added SCEVAA in the intersection of that with where we preserve SCEV itself. One significant challenge to all of this is that the CGSCC passes were actually using the alias analysis implementations by taking advantage of a pretty amazing set of loop holes in the old pass manager's analysis management code which allowed analysis groups to slide through in many cases. Moving away from analysis groups makes this problem much more obvious. To fix it, I've leveraged the flexibility the design of the new PM components provides to just directly construct the relevant alias analyses for the relevant functions in the IPO passes that need them. This is a bit hacky, but should go away with the new pass manager, and is already in many ways cleaner than the prior state. Another significant challenge is that various facilities of the old alias analysis infrastructure just don't fit any more. The most significant of these is the alias analysis 'counter' pass. That pass relied on the ability to snoop on AA queries at different points in the analysis group chain. Instead, I'm planning to build printing functionality directly into the aggregation layer. I've not included that in this patch merely to keep it smaller. Note that all of this needs a nearly complete rewrite of the AA documentation. I'm planning to do that, but I'd like to make sure the new design settles, and to flesh out a bit more of what it looks like in the new pass manager first. Differential Revision: http://reviews.llvm.org/D12080 llvm-svn: 247167
2015-09-09 19:55:00 +02:00
// We need to manually construct BasicAA directly in order to disable its
// use of other function analyses.
BasicAAResult BAR(createLegacyPMBasicAAResult(*this, *F));
// Construct our own AA results for this function. We do this manually to
// work around the limitations of the legacy pass manager.
AAResults AAR(createLegacyPMAAResults(*this, *F, BAR));
switch (checkFunctionMemoryAccess(*F, AAR, SCCNodes)) {
case MAK_MayWrite:
return false;
case MAK_ReadOnly:
ReadsMemory = true;
break;
case MAK_ReadNone:
// Nothing to do!
break;
}
}
// Success! Functions in this SCC do not access memory, or only read memory.
// Give them the appropriate attribute.
bool MadeChange = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F->doesNotAccessMemory())
// Already perfect!
continue;
if (F->onlyReadsMemory() && ReadsMemory)
// No change.
continue;
MadeChange = true;
// Clear out any existing attributes.
AttrBuilder B;
B.addAttribute(Attribute::ReadOnly).addAttribute(Attribute::ReadNone);
F->removeAttributes(
AttributeSet::FunctionIndex,
AttributeSet::get(F->getContext(), AttributeSet::FunctionIndex, B));
// Add in the new attribute.
F->addAttribute(AttributeSet::FunctionIndex,
ReadsMemory ? Attribute::ReadOnly : Attribute::ReadNone);
if (ReadsMemory)
++NumReadOnly;
else
++NumReadNone;
}
return MadeChange;
}
namespace {
/// For a given pointer Argument, this retains a list of Arguments of functions
/// in the same SCC that the pointer data flows into. We use this to build an
/// SCC of the arguments.
struct ArgumentGraphNode {
Argument *Definition;
SmallVector<ArgumentGraphNode *, 4> Uses;
};
class ArgumentGraph {
// We store pointers to ArgumentGraphNode objects, so it's important that
// that they not move around upon insert.
typedef std::map<Argument *, ArgumentGraphNode> ArgumentMapTy;
ArgumentMapTy ArgumentMap;
// There is no root node for the argument graph, in fact:
// void f(int *x, int *y) { if (...) f(x, y); }
// is an example where the graph is disconnected. The SCCIterator requires a
// single entry point, so we maintain a fake ("synthetic") root node that
// uses every node. Because the graph is directed and nothing points into
// the root, it will not participate in any SCCs (except for its own).
ArgumentGraphNode SyntheticRoot;
public:
ArgumentGraph() { SyntheticRoot.Definition = nullptr; }
typedef SmallVectorImpl<ArgumentGraphNode *>::iterator iterator;
iterator begin() { return SyntheticRoot.Uses.begin(); }
iterator end() { return SyntheticRoot.Uses.end(); }
ArgumentGraphNode *getEntryNode() { return &SyntheticRoot; }
ArgumentGraphNode *operator[](Argument *A) {
ArgumentGraphNode &Node = ArgumentMap[A];
Node.Definition = A;
SyntheticRoot.Uses.push_back(&Node);
return &Node;
}
};
/// This tracker checks whether callees are in the SCC, and if so it does not
/// consider that a capture, instead adding it to the "Uses" list and
/// continuing with the analysis.
struct ArgumentUsesTracker : public CaptureTracker {
ArgumentUsesTracker(const SmallPtrSet<Function *, 8> &SCCNodes)
: Captured(false), SCCNodes(SCCNodes) {}
void tooManyUses() override { Captured = true; }
bool captured(const Use *U) override {
CallSite CS(U->getUser());
if (!CS.getInstruction()) {
Captured = true;
return true;
}
Function *F = CS.getCalledFunction();
if (!F || !SCCNodes.count(F)) {
Captured = true;
return true;
}
bool Found = false;
Function::arg_iterator AI = F->arg_begin(), AE = F->arg_end();
for (CallSite::arg_iterator PI = CS.arg_begin(), PE = CS.arg_end();
PI != PE; ++PI, ++AI) {
if (AI == AE) {
assert(F->isVarArg() && "More params than args in non-varargs call");
Captured = true;
return true;
}
if (PI == U) {
Uses.push_back(AI);
Found = true;
break;
}
}
assert(Found && "Capturing call-site captured nothing?");
(void)Found;
return false;
}
bool Captured; // True only if certainly captured (used outside our SCC).
SmallVector<Argument *, 4> Uses; // Uses within our SCC.
const SmallPtrSet<Function *, 8> &SCCNodes;
};
}
namespace llvm {
template <> struct GraphTraits<ArgumentGraphNode *> {
typedef ArgumentGraphNode NodeType;
typedef SmallVectorImpl<ArgumentGraphNode *>::iterator ChildIteratorType;
static inline NodeType *getEntryNode(NodeType *A) { return A; }
static inline ChildIteratorType child_begin(NodeType *N) {
return N->Uses.begin();
}
static inline ChildIteratorType child_end(NodeType *N) {
return N->Uses.end();
}
};
template <>
struct GraphTraits<ArgumentGraph *> : public GraphTraits<ArgumentGraphNode *> {
static NodeType *getEntryNode(ArgumentGraph *AG) {
return AG->getEntryNode();
}
static ChildIteratorType nodes_begin(ArgumentGraph *AG) {
return AG->begin();
}
static ChildIteratorType nodes_end(ArgumentGraph *AG) { return AG->end(); }
};
}
/// Returns Attribute::None, Attribute::ReadOnly or Attribute::ReadNone.
static Attribute::AttrKind
determinePointerReadAttrs(Argument *A,
const SmallPtrSet<Argument *, 8> &SCCNodes) {
SmallVector<Use *, 32> Worklist;
SmallSet<Use *, 32> Visited;
// inalloca arguments are always clobbered by the call.
if (A->hasInAllocaAttr())
return Attribute::None;
bool IsRead = false;
// We don't need to track IsWritten. If A is written to, return immediately.
[C++11] Add range based accessors for the Use-Def chain of a Value. This requires a number of steps. 1) Move value_use_iterator into the Value class as an implementation detail 2) Change it to actually be a *Use* iterator rather than a *User* iterator. 3) Add an adaptor which is a User iterator that always looks through the Use to the User. 4) Wrap these in Value::use_iterator and Value::user_iterator typedefs. 5) Add the range adaptors as Value::uses() and Value::users(). 6) Update *all* of the callers to correctly distinguish between whether they wanted a use_iterator (and to explicitly dig out the User when needed), or a user_iterator which makes the Use itself totally opaque. Because #6 requires churning essentially everything that walked the Use-Def chains, I went ahead and added all of the range adaptors and switched them to range-based loops where appropriate. Also because the renaming requires at least churning every line of code, it didn't make any sense to split these up into multiple commits -- all of which would touch all of the same lies of code. The result is still not quite optimal. The Value::use_iterator is a nice regular iterator, but Value::user_iterator is an iterator over User*s rather than over the User objects themselves. As a consequence, it fits a bit awkwardly into the range-based world and it has the weird extra-dereferencing 'operator->' that so many of our iterators have. I think this could be fixed by providing something which transforms a range of T&s into a range of T*s, but that *can* be separated into another patch, and it isn't yet 100% clear whether this is the right move. However, this change gets us most of the benefit and cleans up a substantial amount of code around Use and User. =] llvm-svn: 203364
2014-03-09 04:16:01 +01:00
for (Use &U : A->uses()) {
Visited.insert(&U);
Worklist.push_back(&U);
}
while (!Worklist.empty()) {
Use *U = Worklist.pop_back_val();
Instruction *I = cast<Instruction>(U->getUser());
Value *V = U->get();
switch (I->getOpcode()) {
case Instruction::BitCast:
case Instruction::GetElementPtr:
case Instruction::PHI:
case Instruction::Select:
case Instruction::AddrSpaceCast:
// The original value is not read/written via this if the new value isn't.
[C++11] Add range based accessors for the Use-Def chain of a Value. This requires a number of steps. 1) Move value_use_iterator into the Value class as an implementation detail 2) Change it to actually be a *Use* iterator rather than a *User* iterator. 3) Add an adaptor which is a User iterator that always looks through the Use to the User. 4) Wrap these in Value::use_iterator and Value::user_iterator typedefs. 5) Add the range adaptors as Value::uses() and Value::users(). 6) Update *all* of the callers to correctly distinguish between whether they wanted a use_iterator (and to explicitly dig out the User when needed), or a user_iterator which makes the Use itself totally opaque. Because #6 requires churning essentially everything that walked the Use-Def chains, I went ahead and added all of the range adaptors and switched them to range-based loops where appropriate. Also because the renaming requires at least churning every line of code, it didn't make any sense to split these up into multiple commits -- all of which would touch all of the same lies of code. The result is still not quite optimal. The Value::use_iterator is a nice regular iterator, but Value::user_iterator is an iterator over User*s rather than over the User objects themselves. As a consequence, it fits a bit awkwardly into the range-based world and it has the weird extra-dereferencing 'operator->' that so many of our iterators have. I think this could be fixed by providing something which transforms a range of T&s into a range of T*s, but that *can* be separated into another patch, and it isn't yet 100% clear whether this is the right move. However, this change gets us most of the benefit and cleans up a substantial amount of code around Use and User. =] llvm-svn: 203364
2014-03-09 04:16:01 +01:00
for (Use &UU : I->uses())
if (Visited.insert(&UU).second)
[C++11] Add range based accessors for the Use-Def chain of a Value. This requires a number of steps. 1) Move value_use_iterator into the Value class as an implementation detail 2) Change it to actually be a *Use* iterator rather than a *User* iterator. 3) Add an adaptor which is a User iterator that always looks through the Use to the User. 4) Wrap these in Value::use_iterator and Value::user_iterator typedefs. 5) Add the range adaptors as Value::uses() and Value::users(). 6) Update *all* of the callers to correctly distinguish between whether they wanted a use_iterator (and to explicitly dig out the User when needed), or a user_iterator which makes the Use itself totally opaque. Because #6 requires churning essentially everything that walked the Use-Def chains, I went ahead and added all of the range adaptors and switched them to range-based loops where appropriate. Also because the renaming requires at least churning every line of code, it didn't make any sense to split these up into multiple commits -- all of which would touch all of the same lies of code. The result is still not quite optimal. The Value::use_iterator is a nice regular iterator, but Value::user_iterator is an iterator over User*s rather than over the User objects themselves. As a consequence, it fits a bit awkwardly into the range-based world and it has the weird extra-dereferencing 'operator->' that so many of our iterators have. I think this could be fixed by providing something which transforms a range of T&s into a range of T*s, but that *can* be separated into another patch, and it isn't yet 100% clear whether this is the right move. However, this change gets us most of the benefit and cleans up a substantial amount of code around Use and User. =] llvm-svn: 203364
2014-03-09 04:16:01 +01:00
Worklist.push_back(&UU);
break;
case Instruction::Call:
case Instruction::Invoke: {
bool Captures = true;
if (I->getType()->isVoidTy())
Captures = false;
auto AddUsersToWorklistIfCapturing = [&] {
if (Captures)
for (Use &UU : I->uses())
if (Visited.insert(&UU).second)
Worklist.push_back(&UU);
};
CallSite CS(I);
if (CS.doesNotAccessMemory()) {
AddUsersToWorklistIfCapturing();
continue;
}
Function *F = CS.getCalledFunction();
if (!F) {
if (CS.onlyReadsMemory()) {
IsRead = true;
AddUsersToWorklistIfCapturing();
continue;
}
return Attribute::None;
}
Function::arg_iterator AI = F->arg_begin(), AE = F->arg_end();
CallSite::arg_iterator B = CS.arg_begin(), E = CS.arg_end();
for (CallSite::arg_iterator A = B; A != E; ++A, ++AI) {
if (A->get() == V) {
if (AI == AE) {
assert(F->isVarArg() &&
"More params than args in non-varargs call.");
return Attribute::None;
}
Captures &= !CS.doesNotCapture(A - B);
if (SCCNodes.count(AI))
continue;
if (!CS.onlyReadsMemory() && !CS.onlyReadsMemory(A - B))
return Attribute::None;
if (!CS.doesNotAccessMemory(A - B))
IsRead = true;
}
}
AddUsersToWorklistIfCapturing();
break;
}
case Instruction::Load:
IsRead = true;
break;
case Instruction::ICmp:
case Instruction::Ret:
break;
default:
return Attribute::None;
}
}
return IsRead ? Attribute::ReadOnly : Attribute::ReadNone;
}
/// Deduce nocapture attributes for the SCC.
bool FunctionAttrs::AddArgumentAttrs(const CallGraphSCC &SCC) {
bool Changed = false;
SmallPtrSet<Function *, 8> SCCNodes;
// Fill SCCNodes with the elements of the SCC. Used for quickly
// looking up whether a given CallGraphNode is in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F && !F->isDeclaration() && !F->mayBeOverridden() &&
!F->hasFnAttribute(Attribute::OptimizeNone))
SCCNodes.insert(F);
}
ArgumentGraph AG;
AttrBuilder B;
B.addAttribute(Attribute::NoCapture);
// Check each function in turn, determining which pointer arguments are not
// captured.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F || F->hasFnAttribute(Attribute::OptimizeNone))
// External node or function we're trying not to optimize - only a problem
// for arguments that we pass to it.
continue;
// Definitions with weak linkage may be overridden at linktime with
// something that captures pointers, so treat them like declarations.
if (F->isDeclaration() || F->mayBeOverridden())
continue;
// Functions that are readonly (or readnone) and nounwind and don't return
// a value can't capture arguments. Don't analyze them.
if (F->onlyReadsMemory() && F->doesNotThrow() &&
F->getReturnType()->isVoidTy()) {
for (Function::arg_iterator A = F->arg_begin(), E = F->arg_end(); A != E;
++A) {
if (A->getType()->isPointerTy() && !A->hasNoCaptureAttr()) {
A->addAttr(AttributeSet::get(F->getContext(), A->getArgNo() + 1, B));
++NumNoCapture;
Changed = true;
}
}
continue;
}
for (Function::arg_iterator A = F->arg_begin(), E = F->arg_end(); A != E;
++A) {
if (!A->getType()->isPointerTy())
continue;
bool HasNonLocalUses = false;
if (!A->hasNoCaptureAttr()) {
ArgumentUsesTracker Tracker(SCCNodes);
PointerMayBeCaptured(A, &Tracker);
if (!Tracker.Captured) {
if (Tracker.Uses.empty()) {
// If it's trivially not captured, mark it nocapture now.
A->addAttr(
AttributeSet::get(F->getContext(), A->getArgNo() + 1, B));
++NumNoCapture;
Changed = true;
} else {
// If it's not trivially captured and not trivially not captured,
// then it must be calling into another function in our SCC. Save
// its particulars for Argument-SCC analysis later.
ArgumentGraphNode *Node = AG[A];
for (SmallVectorImpl<Argument *>::iterator
UI = Tracker.Uses.begin(),
UE = Tracker.Uses.end();
UI != UE; ++UI) {
Node->Uses.push_back(AG[*UI]);
if (*UI != A)
HasNonLocalUses = true;
}
}
}
// Otherwise, it's captured. Don't bother doing SCC analysis on it.
}
if (!HasNonLocalUses && !A->onlyReadsMemory()) {
// Can we determine that it's readonly/readnone without doing an SCC?
// Note that we don't allow any calls at all here, or else our result
// will be dependent on the iteration order through the functions in the
// SCC.
SmallPtrSet<Argument *, 8> Self;
Self.insert(A);
Attribute::AttrKind R = determinePointerReadAttrs(A, Self);
if (R != Attribute::None) {
AttrBuilder B;
B.addAttribute(R);
A->addAttr(AttributeSet::get(A->getContext(), A->getArgNo() + 1, B));
Changed = true;
R == Attribute::ReadOnly ? ++NumReadOnlyArg : ++NumReadNoneArg;
}
}
}
}
// The graph we've collected is partial because we stopped scanning for
// argument uses once we solved the argument trivially. These partial nodes
// show up as ArgumentGraphNode objects with an empty Uses list, and for
// these nodes the final decision about whether they capture has already been
// made. If the definition doesn't have a 'nocapture' attribute by now, it
// captures.
for (scc_iterator<ArgumentGraph *> I = scc_begin(&AG); !I.isAtEnd(); ++I) {
const std::vector<ArgumentGraphNode *> &ArgumentSCC = *I;
if (ArgumentSCC.size() == 1) {
if (!ArgumentSCC[0]->Definition)
continue; // synthetic root node
// eg. "void f(int* x) { if (...) f(x); }"
if (ArgumentSCC[0]->Uses.size() == 1 &&
ArgumentSCC[0]->Uses[0] == ArgumentSCC[0]) {
Argument *A = ArgumentSCC[0]->Definition;
A->addAttr(AttributeSet::get(A->getContext(), A->getArgNo() + 1, B));
++NumNoCapture;
Changed = true;
}
continue;
}
bool SCCCaptured = false;
for (auto I = ArgumentSCC.begin(), E = ArgumentSCC.end();
I != E && !SCCCaptured; ++I) {
ArgumentGraphNode *Node = *I;
if (Node->Uses.empty()) {
if (!Node->Definition->hasNoCaptureAttr())
SCCCaptured = true;
}
}
if (SCCCaptured)
continue;
SmallPtrSet<Argument *, 8> ArgumentSCCNodes;
// Fill ArgumentSCCNodes with the elements of the ArgumentSCC. Used for
// quickly looking up whether a given Argument is in this ArgumentSCC.
for (auto I = ArgumentSCC.begin(), E = ArgumentSCC.end(); I != E; ++I) {
ArgumentSCCNodes.insert((*I)->Definition);
}
for (auto I = ArgumentSCC.begin(), E = ArgumentSCC.end();
I != E && !SCCCaptured; ++I) {
ArgumentGraphNode *N = *I;
for (SmallVectorImpl<ArgumentGraphNode *>::iterator UI = N->Uses.begin(),
UE = N->Uses.end();
UI != UE; ++UI) {
Argument *A = (*UI)->Definition;
if (A->hasNoCaptureAttr() || ArgumentSCCNodes.count(A))
continue;
SCCCaptured = true;
break;
}
}
if (SCCCaptured)
continue;
for (unsigned i = 0, e = ArgumentSCC.size(); i != e; ++i) {
Argument *A = ArgumentSCC[i]->Definition;
A->addAttr(AttributeSet::get(A->getContext(), A->getArgNo() + 1, B));
++NumNoCapture;
Changed = true;
}
// We also want to compute readonly/readnone. With a small number of false
// negatives, we can assume that any pointer which is captured isn't going
// to be provably readonly or readnone, since by definition we can't
// analyze all uses of a captured pointer.
//
// The false negatives happen when the pointer is captured by a function
// that promises readonly/readnone behaviour on the pointer, then the
// pointer's lifetime ends before anything that writes to arbitrary memory.
// Also, a readonly/readnone pointer may be returned, but returning a
// pointer is capturing it.
Attribute::AttrKind ReadAttr = Attribute::ReadNone;
for (unsigned i = 0, e = ArgumentSCC.size(); i != e; ++i) {
Argument *A = ArgumentSCC[i]->Definition;
Attribute::AttrKind K = determinePointerReadAttrs(A, ArgumentSCCNodes);
if (K == Attribute::ReadNone)
continue;
if (K == Attribute::ReadOnly) {
ReadAttr = Attribute::ReadOnly;
continue;
}
ReadAttr = K;
break;
}
if (ReadAttr != Attribute::None) {
AttrBuilder B, R;
B.addAttribute(ReadAttr);
R.addAttribute(Attribute::ReadOnly).addAttribute(Attribute::ReadNone);
for (unsigned i = 0, e = ArgumentSCC.size(); i != e; ++i) {
Argument *A = ArgumentSCC[i]->Definition;
// Clear out existing readonly/readnone attributes
A->removeAttr(AttributeSet::get(A->getContext(), A->getArgNo() + 1, R));
A->addAttr(AttributeSet::get(A->getContext(), A->getArgNo() + 1, B));
ReadAttr == Attribute::ReadOnly ? ++NumReadOnlyArg : ++NumReadNoneArg;
Changed = true;
}
}
}
return Changed;
}
/// Tests whether a function is "malloc-like".
///
/// A function is "malloc-like" if it returns either null or a pointer that
/// doesn't alias any other pointer visible to the caller.
static bool isFunctionMallocLike(Function *F,
SmallPtrSet<Function *, 8> &SCCNodes) {
SmallSetVector<Value *, 8> FlowsToReturn;
for (Function::iterator I = F->begin(), E = F->end(); I != E; ++I)
if (ReturnInst *Ret = dyn_cast<ReturnInst>(I->getTerminator()))
FlowsToReturn.insert(Ret->getReturnValue());
for (unsigned i = 0; i != FlowsToReturn.size(); ++i) {
Value *RetVal = FlowsToReturn[i];
if (Constant *C = dyn_cast<Constant>(RetVal)) {
if (!C->isNullValue() && !isa<UndefValue>(C))
return false;
continue;
}
if (isa<Argument>(RetVal))
return false;
if (Instruction *RVI = dyn_cast<Instruction>(RetVal))
switch (RVI->getOpcode()) {
// Extend the analysis by looking upwards.
case Instruction::BitCast:
case Instruction::GetElementPtr:
case Instruction::AddrSpaceCast:
FlowsToReturn.insert(RVI->getOperand(0));
continue;
case Instruction::Select: {
SelectInst *SI = cast<SelectInst>(RVI);
FlowsToReturn.insert(SI->getTrueValue());
FlowsToReturn.insert(SI->getFalseValue());
continue;
}
case Instruction::PHI: {
PHINode *PN = cast<PHINode>(RVI);
for (Value *IncValue : PN->incoming_values())
FlowsToReturn.insert(IncValue);
continue;
}
// Check whether the pointer came from an allocation.
case Instruction::Alloca:
break;
case Instruction::Call:
case Instruction::Invoke: {
CallSite CS(RVI);
if (CS.paramHasAttr(0, Attribute::NoAlias))
break;
if (CS.getCalledFunction() && SCCNodes.count(CS.getCalledFunction()))
break;
} // fall-through
default:
return false; // Did not come from an allocation.
}
if (PointerMayBeCaptured(RetVal, false, /*StoreCaptures=*/false))
return false;
}
return true;
}
/// Deduce noalias attributes for the SCC.
bool FunctionAttrs::AddNoAliasAttrs(const CallGraphSCC &SCC) {
SmallPtrSet<Function *, 8> SCCNodes;
// Fill SCCNodes with the elements of the SCC. Used for quickly
// looking up whether a given CallGraphNode is in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I)
SCCNodes.insert((*I)->getFunction());
// Check each function in turn, determining which functions return noalias
// pointers.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F || F->hasFnAttribute(Attribute::OptimizeNone))
// External node or node we don't want to optimize - skip it;
return false;
// Already noalias.
if (F->doesNotAlias(0))
continue;
// Definitions with weak linkage may be overridden at linktime, so
// treat them like declarations.
if (F->isDeclaration() || F->mayBeOverridden())
return false;
// We annotate noalias return values, which are only applicable to
// pointer types.
if (!F->getReturnType()->isPointerTy())
continue;
if (!isFunctionMallocLike(F, SCCNodes))
return false;
}
bool MadeChange = false;
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F->doesNotAlias(0) || !F->getReturnType()->isPointerTy())
continue;
F->setDoesNotAlias(0);
++NumNoAlias;
MadeChange = true;
}
return MadeChange;
}
/// Tests whether this function is known to not return null.
///
/// Requires that the function returns a pointer.
///
/// Returns true if it believes the function will not return a null, and sets
/// \p Speculative based on whether the returned conclusion is a speculative
/// conclusion due to SCC calls.
static bool isReturnNonNull(Function *F, SmallPtrSet<Function *, 8> &SCCNodes,
const TargetLibraryInfo &TLI, bool &Speculative) {
assert(F->getReturnType()->isPointerTy() &&
"nonnull only meaningful on pointer types");
Speculative = false;
SmallSetVector<Value *, 8> FlowsToReturn;
for (BasicBlock &BB : *F)
if (auto *Ret = dyn_cast<ReturnInst>(BB.getTerminator()))
FlowsToReturn.insert(Ret->getReturnValue());
for (unsigned i = 0; i != FlowsToReturn.size(); ++i) {
Value *RetVal = FlowsToReturn[i];
// If this value is locally known to be non-null, we're good
if (isKnownNonNull(RetVal, &TLI))
continue;
// Otherwise, we need to look upwards since we can't make any local
// conclusions.
Instruction *RVI = dyn_cast<Instruction>(RetVal);
if (!RVI)
return false;
switch (RVI->getOpcode()) {
// Extend the analysis by looking upwards.
case Instruction::BitCast:
case Instruction::GetElementPtr:
case Instruction::AddrSpaceCast:
FlowsToReturn.insert(RVI->getOperand(0));
continue;
case Instruction::Select: {
SelectInst *SI = cast<SelectInst>(RVI);
FlowsToReturn.insert(SI->getTrueValue());
FlowsToReturn.insert(SI->getFalseValue());
continue;
}
case Instruction::PHI: {
PHINode *PN = cast<PHINode>(RVI);
for (int i = 0, e = PN->getNumIncomingValues(); i != e; ++i)
FlowsToReturn.insert(PN->getIncomingValue(i));
continue;
}
case Instruction::Call:
case Instruction::Invoke: {
CallSite CS(RVI);
Function *Callee = CS.getCalledFunction();
// A call to a node within the SCC is assumed to return null until
// proven otherwise
if (Callee && SCCNodes.count(Callee)) {
Speculative = true;
continue;
}
return false;
}
default:
return false; // Unknown source, may be null
};
llvm_unreachable("should have either continued or returned");
}
return true;
}
/// Deduce nonnull attributes for the SCC.
bool FunctionAttrs::AddNonNullAttrs(const CallGraphSCC &SCC) {
SmallPtrSet<Function *, 8> SCCNodes;
// Fill SCCNodes with the elements of the SCC. Used for quickly
// looking up whether a given CallGraphNode is in this SCC.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I)
SCCNodes.insert((*I)->getFunction());
// Speculative that all functions in the SCC return only nonnull
// pointers. We may refute this as we analyze functions.
bool SCCReturnsNonNull = true;
bool MadeChange = false;
// Check each function in turn, determining which functions return nonnull
// pointers.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (!F || F->hasFnAttribute(Attribute::OptimizeNone))
// External node or node we don't want to optimize - skip it;
return false;
// Already nonnull.
if (F->getAttributes().hasAttribute(AttributeSet::ReturnIndex,
Attribute::NonNull))
continue;
// Definitions with weak linkage may be overridden at linktime, so
// treat them like declarations.
if (F->isDeclaration() || F->mayBeOverridden())
return false;
// We annotate nonnull return values, which are only applicable to
// pointer types.
if (!F->getReturnType()->isPointerTy())
continue;
bool Speculative = false;
if (isReturnNonNull(F, SCCNodes, *TLI, Speculative)) {
if (!Speculative) {
// Mark the function eagerly since we may discover a function
// which prevents us from speculating about the entire SCC
DEBUG(dbgs() << "Eagerly marking " << F->getName() << " as nonnull\n");
F->addAttribute(AttributeSet::ReturnIndex, Attribute::NonNull);
++NumNonNullReturn;
MadeChange = true;
}
continue;
}
// At least one function returns something which could be null, can't
// speculate any more.
SCCReturnsNonNull = false;
}
if (SCCReturnsNonNull) {
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F->getAttributes().hasAttribute(AttributeSet::ReturnIndex,
Attribute::NonNull) ||
!F->getReturnType()->isPointerTy())
continue;
DEBUG(dbgs() << "SCC marking " << F->getName() << " as nonnull\n");
F->addAttribute(AttributeSet::ReturnIndex, Attribute::NonNull);
++NumNonNullReturn;
MadeChange = true;
}
}
return MadeChange;
}
static void setDoesNotAccessMemory(Function &F) {
if (!F.doesNotAccessMemory()) {
F.setDoesNotAccessMemory();
++NumAnnotated;
}
}
static void setOnlyReadsMemory(Function &F) {
if (!F.onlyReadsMemory()) {
F.setOnlyReadsMemory();
++NumAnnotated;
}
}
static void setDoesNotThrow(Function &F) {
if (!F.doesNotThrow()) {
F.setDoesNotThrow();
++NumAnnotated;
}
}
static void setDoesNotCapture(Function &F, unsigned n) {
if (!F.doesNotCapture(n)) {
F.setDoesNotCapture(n);
++NumAnnotated;
}
}
static void setOnlyReadsMemory(Function &F, unsigned n) {
if (!F.onlyReadsMemory(n)) {
F.setOnlyReadsMemory(n);
++NumAnnotated;
}
}
static void setDoesNotAlias(Function &F, unsigned n) {
if (!F.doesNotAlias(n)) {
F.setDoesNotAlias(n);
++NumAnnotated;
}
}
/// Analyze the name and prototype of the given function and set any applicable
/// attributes.
///
/// Returns true if any attributes were set and false otherwise.
static bool inferPrototypeAttributes(Function &F, const TargetLibraryInfo &TLI) {
if (F.hasFnAttribute(Attribute::OptimizeNone))
return false;
FunctionType *FTy = F.getFunctionType();
LibFunc::Func TheLibFunc;
if (!(TLI.getLibFunc(F.getName(), TheLibFunc) && TLI.has(TheLibFunc)))
return false;
switch (TheLibFunc) {
case LibFunc::strlen:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setOnlyReadsMemory(F);
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::strchr:
case LibFunc::strrchr:
if (FTy->getNumParams() != 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isIntegerTy())
return false;
setOnlyReadsMemory(F);
setDoesNotThrow(F);
break;
case LibFunc::strtol:
case LibFunc::strtod:
case LibFunc::strtof:
case LibFunc::strtoul:
case LibFunc::strtoll:
case LibFunc::strtold:
case LibFunc::strtoull:
if (FTy->getNumParams() < 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::strcpy:
case LibFunc::stpcpy:
case LibFunc::strcat:
case LibFunc::strncat:
case LibFunc::strncpy:
case LibFunc::stpncpy:
if (FTy->getNumParams() < 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::strxfrm:
if (FTy->getNumParams() != 3 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::strcmp: // 0,1
case LibFunc::strspn: // 0,1
case LibFunc::strncmp: // 0,1
case LibFunc::strcspn: // 0,1
case LibFunc::strcoll: // 0,1
case LibFunc::strcasecmp: // 0,1
case LibFunc::strncasecmp: //
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setOnlyReadsMemory(F);
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
break;
case LibFunc::strstr:
case LibFunc::strpbrk:
if (FTy->getNumParams() != 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setOnlyReadsMemory(F);
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
break;
case LibFunc::strtok:
case LibFunc::strtok_r:
if (FTy->getNumParams() < 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::scanf:
if (FTy->getNumParams() < 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::setbuf:
case LibFunc::setvbuf:
if (FTy->getNumParams() < 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::strdup:
case LibFunc::strndup:
if (FTy->getNumParams() < 1 || !FTy->getReturnType()->isPointerTy() ||
!FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::stat:
case LibFunc::statvfs:
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::sscanf:
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::sprintf:
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::snprintf:
if (FTy->getNumParams() != 3 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(2)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 3);
setOnlyReadsMemory(F, 3);
break;
case LibFunc::setitimer:
if (FTy->getNumParams() != 3 || !FTy->getParamType(1)->isPointerTy() ||
!FTy->getParamType(2)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
setDoesNotCapture(F, 3);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::system:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
// May throw; "system" is a valid pthread cancellation point.
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::malloc:
if (FTy->getNumParams() != 1 || !FTy->getReturnType()->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
break;
case LibFunc::memcmp:
if (FTy->getNumParams() != 3 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setOnlyReadsMemory(F);
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
break;
case LibFunc::memchr:
case LibFunc::memrchr:
if (FTy->getNumParams() != 3)
return false;
setOnlyReadsMemory(F);
setDoesNotThrow(F);
break;
case LibFunc::modf:
case LibFunc::modff:
case LibFunc::modfl:
if (FTy->getNumParams() < 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
break;
case LibFunc::memcpy:
case LibFunc::memccpy:
case LibFunc::memmove:
if (FTy->getNumParams() < 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::memalign:
if (!FTy->getReturnType()->isPointerTy())
return false;
setDoesNotAlias(F, 0);
break;
case LibFunc::mkdir:
if (FTy->getNumParams() == 0 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::mktime:
if (FTy->getNumParams() == 0 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::realloc:
if (FTy->getNumParams() != 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getReturnType()->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
setDoesNotCapture(F, 1);
break;
case LibFunc::read:
if (FTy->getNumParams() != 3 || !FTy->getParamType(1)->isPointerTy())
return false;
// May throw; "read" is a valid pthread cancellation point.
setDoesNotCapture(F, 2);
break;
case LibFunc::rewind:
if (FTy->getNumParams() < 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::rmdir:
case LibFunc::remove:
case LibFunc::realpath:
if (FTy->getNumParams() < 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::rename:
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::readlink:
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::write:
if (FTy->getNumParams() != 3 || !FTy->getParamType(1)->isPointerTy())
return false;
// May throw; "write" is a valid pthread cancellation point.
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::bcopy:
if (FTy->getNumParams() != 3 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::bcmp:
if (FTy->getNumParams() != 3 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setOnlyReadsMemory(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
break;
case LibFunc::bzero:
if (FTy->getNumParams() != 2 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::calloc:
if (FTy->getNumParams() != 2 || !FTy->getReturnType()->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
break;
case LibFunc::chmod:
case LibFunc::chown:
if (FTy->getNumParams() == 0 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::ctermid:
case LibFunc::clearerr:
case LibFunc::closedir:
if (FTy->getNumParams() == 0 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::atoi:
case LibFunc::atol:
case LibFunc::atof:
case LibFunc::atoll:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setOnlyReadsMemory(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::access:
if (FTy->getNumParams() != 2 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::fopen:
if (FTy->getNumParams() != 2 || !FTy->getReturnType()->isPointerTy() ||
!FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::fdopen:
if (FTy->getNumParams() != 2 || !FTy->getReturnType()->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::feof:
case LibFunc::free:
case LibFunc::fseek:
case LibFunc::ftell:
case LibFunc::fgetc:
case LibFunc::fseeko:
case LibFunc::ftello:
case LibFunc::fileno:
case LibFunc::fflush:
case LibFunc::fclose:
case LibFunc::fsetpos:
case LibFunc::flockfile:
case LibFunc::funlockfile:
case LibFunc::ftrylockfile:
if (FTy->getNumParams() == 0 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::ferror:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F);
break;
case LibFunc::fputc:
case LibFunc::fstat:
case LibFunc::frexp:
case LibFunc::frexpf:
case LibFunc::frexpl:
case LibFunc::fstatvfs:
if (FTy->getNumParams() != 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
break;
case LibFunc::fgets:
if (FTy->getNumParams() != 3 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(2)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 3);
break;
case LibFunc::fread:
if (FTy->getNumParams() != 4 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(3)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 4);
break;
case LibFunc::fwrite:
if (FTy->getNumParams() != 4 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(3)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 4);
break;
case LibFunc::fputs:
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::fscanf:
case LibFunc::fprintf:
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::fgetpos:
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
break;
case LibFunc::getc:
case LibFunc::getlogin_r:
case LibFunc::getc_unlocked:
if (FTy->getNumParams() == 0 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::getenv:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setOnlyReadsMemory(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::gets:
case LibFunc::getchar:
setDoesNotThrow(F);
break;
case LibFunc::getitimer:
if (FTy->getNumParams() != 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
break;
case LibFunc::getpwnam:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::ungetc:
if (FTy->getNumParams() != 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
break;
case LibFunc::uname:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::unlink:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::unsetenv:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::utime:
case LibFunc::utimes:
if (FTy->getNumParams() != 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::putc:
if (FTy->getNumParams() != 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
break;
case LibFunc::puts:
case LibFunc::printf:
case LibFunc::perror:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::pread:
if (FTy->getNumParams() != 4 || !FTy->getParamType(1)->isPointerTy())
return false;
// May throw; "pread" is a valid pthread cancellation point.
setDoesNotCapture(F, 2);
break;
case LibFunc::pwrite:
if (FTy->getNumParams() != 4 || !FTy->getParamType(1)->isPointerTy())
return false;
// May throw; "pwrite" is a valid pthread cancellation point.
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::putchar:
setDoesNotThrow(F);
break;
case LibFunc::popen:
if (FTy->getNumParams() != 2 || !FTy->getReturnType()->isPointerTy() ||
!FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::pclose:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::vscanf:
if (FTy->getNumParams() != 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::vsscanf:
if (FTy->getNumParams() != 3 || !FTy->getParamType(1)->isPointerTy() ||
!FTy->getParamType(2)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::vfscanf:
if (FTy->getNumParams() != 3 || !FTy->getParamType(1)->isPointerTy() ||
!FTy->getParamType(2)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::valloc:
if (!FTy->getReturnType()->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
break;
case LibFunc::vprintf:
if (FTy->getNumParams() != 2 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::vfprintf:
case LibFunc::vsprintf:
if (FTy->getNumParams() != 3 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::vsnprintf:
if (FTy->getNumParams() != 4 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(2)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 3);
setOnlyReadsMemory(F, 3);
break;
case LibFunc::open:
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy())
return false;
// May throw; "open" is a valid pthread cancellation point.
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::opendir:
if (FTy->getNumParams() != 1 || !FTy->getReturnType()->isPointerTy() ||
!FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::tmpfile:
if (!FTy->getReturnType()->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
break;
case LibFunc::times:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::htonl:
case LibFunc::htons:
case LibFunc::ntohl:
case LibFunc::ntohs:
setDoesNotThrow(F);
setDoesNotAccessMemory(F);
break;
case LibFunc::lstat:
if (FTy->getNumParams() != 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::lchown:
if (FTy->getNumParams() != 3 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::qsort:
if (FTy->getNumParams() != 4 || !FTy->getParamType(3)->isPointerTy())
return false;
// May throw; places call through function pointer.
setDoesNotCapture(F, 4);
break;
case LibFunc::dunder_strdup:
case LibFunc::dunder_strndup:
if (FTy->getNumParams() < 1 || !FTy->getReturnType()->isPointerTy() ||
!FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::dunder_strtok_r:
if (FTy->getNumParams() != 3 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::under_IO_getc:
if (FTy->getNumParams() != 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::under_IO_putc:
if (FTy->getNumParams() != 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
break;
case LibFunc::dunder_isoc99_scanf:
if (FTy->getNumParams() < 1 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::stat64:
case LibFunc::lstat64:
case LibFunc::statvfs64:
if (FTy->getNumParams() < 1 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::dunder_isoc99_sscanf:
if (FTy->getNumParams() < 1 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::fopen64:
if (FTy->getNumParams() != 2 || !FTy->getReturnType()->isPointerTy() ||
!FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
setOnlyReadsMemory(F, 1);
setOnlyReadsMemory(F, 2);
break;
case LibFunc::fseeko64:
case LibFunc::ftello64:
if (FTy->getNumParams() == 0 || !FTy->getParamType(0)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
break;
case LibFunc::tmpfile64:
if (!FTy->getReturnType()->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotAlias(F, 0);
break;
case LibFunc::fstat64:
case LibFunc::fstatvfs64:
if (FTy->getNumParams() != 2 || !FTy->getParamType(1)->isPointerTy())
return false;
setDoesNotThrow(F);
setDoesNotCapture(F, 2);
break;
case LibFunc::open64:
if (FTy->getNumParams() < 2 || !FTy->getParamType(0)->isPointerTy())
return false;
// May throw; "open" is a valid pthread cancellation point.
setDoesNotCapture(F, 1);
setOnlyReadsMemory(F, 1);
break;
case LibFunc::gettimeofday:
if (FTy->getNumParams() != 2 || !FTy->getParamType(0)->isPointerTy() ||
!FTy->getParamType(1)->isPointerTy())
return false;
// Currently some platforms have the restrict keyword on the arguments to
// gettimeofday. To be conservative, do not add noalias to gettimeofday's
// arguments.
setDoesNotThrow(F);
setDoesNotCapture(F, 1);
setDoesNotCapture(F, 2);
break;
default:
// Didn't mark any attributes.
return false;
}
return true;
}
/// Adds attributes to well-known standard library call declarations.
bool FunctionAttrs::annotateLibraryCalls(const CallGraphSCC &SCC) {
bool MadeChange = false;
// Check each function in turn annotating well-known library function
// declarations with attributes.
for (CallGraphSCC::iterator I = SCC.begin(), E = SCC.end(); I != E; ++I) {
Function *F = (*I)->getFunction();
if (F && F->isDeclaration())
MadeChange |= inferPrototypeAttributes(*F, *TLI);
}
return MadeChange;
}
bool FunctionAttrs::runOnSCC(CallGraphSCC &SCC) {
TLI = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
bool Changed = annotateLibraryCalls(SCC);
Changed |= AddReadAttrs(SCC);
Changed |= AddArgumentAttrs(SCC);
Changed |= AddNoAliasAttrs(SCC);
Changed |= AddNonNullAttrs(SCC);
return Changed;
}