llvm-6502/lib/Analysis/CaptureTracking.cpp

184 lines
6.8 KiB
C++
Raw Normal View History

//===--- CaptureTracking.cpp - Determine whether a pointer is captured ----===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains routines that help determine which pointers are captured.
// A pointer value is captured if the function makes a copy of any part of the
// pointer that outlives the call. Not being captured means, more or less, that
// the pointer is only dereferenced and not stored in a global. Returning part
// of the pointer as the function return value may or may not count as capturing
// the pointer, depending on the context.
//
//===----------------------------------------------------------------------===//
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/CaptureTracking.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Instructions.h"
using namespace llvm;
CaptureTracker::~CaptureTracker() {}
bool CaptureTracker::shouldExplore(const Use *U) { return true; }
namespace {
struct SimpleCaptureTracker : public CaptureTracker {
explicit SimpleCaptureTracker(bool ReturnCaptures)
: ReturnCaptures(ReturnCaptures), Captured(false) {}
void tooManyUses() override { Captured = true; }
bool captured(const Use *U) override {
if (isa<ReturnInst>(U->getUser()) && !ReturnCaptures)
return false;
Captured = true;
return true;
}
bool ReturnCaptures;
bool Captured;
};
}
/// PointerMayBeCaptured - Return true if this pointer value may be captured
/// by the enclosing function (which is required to exist). This routine can
/// be expensive, so consider caching the results. The boolean ReturnCaptures
/// specifies whether returning the value (or part of it) from the function
/// counts as capturing it or not. The boolean StoreCaptures specified whether
/// storing the value (or part of it) into memory anywhere automatically
/// counts as capturing it or not.
bool llvm::PointerMayBeCaptured(const Value *V,
bool ReturnCaptures, bool StoreCaptures) {
assert(!isa<GlobalValue>(V) &&
"It doesn't make sense to ask whether a global is captured.");
// TODO: If StoreCaptures is not true, we could do Fancy analysis
// to determine whether this store is not actually an escape point.
// In that case, BasicAliasAnalysis should be updated as well to
// take advantage of this.
(void)StoreCaptures;
SimpleCaptureTracker SCT(ReturnCaptures);
PointerMayBeCaptured(V, &SCT);
return SCT.Captured;
}
/// TODO: Write a new FunctionPass AliasAnalysis so that it can keep
/// a cache. Then we can move the code from BasicAliasAnalysis into
/// that path, and remove this threshold.
static int const Threshold = 20;
void llvm::PointerMayBeCaptured(const Value *V, CaptureTracker *Tracker) {
assert(V->getType()->isPointerTy() && "Capture is for pointers only!");
SmallVector<const Use *, Threshold> Worklist;
SmallSet<const Use *, Threshold> Visited;
int Count = 0;
[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. =] git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@203364 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-09 03:16:01 +00:00
for (const Use &U : V->uses()) {
// If there are lots of uses, conservatively say that the value
// is captured to avoid taking too much compile time.
if (Count++ >= Threshold)
return Tracker->tooManyUses();
[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. =] git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@203364 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-09 03:16:01 +00:00
if (!Tracker->shouldExplore(&U)) continue;
Visited.insert(&U);
Worklist.push_back(&U);
}
while (!Worklist.empty()) {
const Use *U = Worklist.pop_back_val();
Instruction *I = cast<Instruction>(U->getUser());
V = U->get();
switch (I->getOpcode()) {
case Instruction::Call:
case Instruction::Invoke: {
CallSite CS(I);
// Not captured if the callee is readonly, doesn't return a copy through
// its return value and doesn't unwind (a readonly function can leak bits
// by throwing an exception or not depending on the input value).
if (CS.onlyReadsMemory() && CS.doesNotThrow() && I->getType()->isVoidTy())
break;
// Not captured if only passed via 'nocapture' arguments. Note that
// calling a function pointer does not in itself cause the pointer to
// be captured. This is a subtle point considering that (for example)
// the callee might return its own address. It is analogous to saying
// that loading a value from a pointer does not cause the pointer to be
// captured, even though the loaded value might be the pointer itself
// (think of self-referential objects).
CallSite::arg_iterator B = CS.arg_begin(), E = CS.arg_end();
for (CallSite::arg_iterator A = B; A != E; ++A)
if (A->get() == V && !CS.doesNotCapture(A - B))
// The parameter is not marked 'nocapture' - captured.
if (Tracker->captured(U))
return;
break;
}
case Instruction::Load:
// Loading from a pointer does not cause it to be captured.
break;
case Instruction::VAArg:
// "va-arg" from a pointer does not cause it to be captured.
break;
case Instruction::Store:
if (V == I->getOperand(0))
// Stored the pointer - conservatively assume it may be captured.
if (Tracker->captured(U))
return;
// Storing to the pointee does not cause the pointer to be captured.
break;
case Instruction::BitCast:
case Instruction::GetElementPtr:
case Instruction::PHI:
case Instruction::Select:
case Instruction::AddrSpaceCast:
// The original value is not captured via this if the new value isn't.
Count = 0;
[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. =] git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@203364 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-09 03:16:01 +00:00
for (Use &UU : I->uses()) {
// If there are lots of uses, conservatively say that the value
// is captured to avoid taking too much compile time.
if (Count++ >= Threshold)
return Tracker->tooManyUses();
[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. =] git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@203364 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-09 03:16:01 +00:00
if (Visited.insert(&UU))
if (Tracker->shouldExplore(&UU))
Worklist.push_back(&UU);
}
break;
case Instruction::ICmp:
// Don't count comparisons of a no-alias return value against null as
// captures. This allows us to ignore comparisons of malloc results
// with null, for example.
if (ConstantPointerNull *CPN =
dyn_cast<ConstantPointerNull>(I->getOperand(1)))
if (CPN->getType()->getAddressSpace() == 0)
if (isNoAliasCall(V->stripPointerCasts()))
break;
// Otherwise, be conservative. There are crazy ways to capture pointers
// using comparisons.
if (Tracker->captured(U))
return;
break;
default:
// Something else - be conservative and say it is captured.
if (Tracker->captured(U))
return;
break;
}
}
// All uses examined.
}