llvm-project/llvm/lib/Analysis/CaptureTracking.cpp

360 lines
14 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/Analysis/CaptureTracking.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/CFG.h"
#include "llvm/Analysis/OrderedBasicBlock.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.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)
2012-05-11 07:38:07 +08:00
return false;
Captured = true;
return true;
}
bool ReturnCaptures;
bool Captured;
};
/// Only find pointer captures which happen before the given instruction. Uses
/// the dominator tree to determine whether one instruction is before another.
/// Only support the case where the Value is defined in the same basic block
/// as the given instruction and the use.
struct CapturesBefore : public CaptureTracker {
CapturesBefore(bool ReturnCaptures, const Instruction *I, DominatorTree *DT,
bool IncludeI, OrderedBasicBlock *IC)
: OrderedBB(IC), BeforeHere(I), DT(DT),
ReturnCaptures(ReturnCaptures), IncludeI(IncludeI), Captured(false) {}
void tooManyUses() override { Captured = true; }
bool isSafeToPrune(Instruction *I) {
BasicBlock *BB = I->getParent();
// We explore this usage only if the usage can reach "BeforeHere".
// If use is not reachable from entry, there is no need to explore.
if (BeforeHere != I && !DT->isReachableFromEntry(BB))
return true;
// Compute the case where both instructions are inside the same basic
// block. Since instructions in the same BB as BeforeHere are numbered in
// 'OrderedBB', avoid using 'dominates' and 'isPotentiallyReachable'
// which are very expensive for large basic blocks.
if (BB == BeforeHere->getParent()) {
// 'I' dominates 'BeforeHere' => not safe to prune.
//
[IR] Reformulate LLVM's EH funclet IR While we have successfully implemented a funclet-oriented EH scheme on top of LLVM IR, our scheme has some notable deficiencies: - catchendpad and cleanupendpad are necessary in the current design but they are difficult to explain to others, even to seasoned LLVM experts. - catchendpad and cleanupendpad are optimization barriers. They cannot be split and force all potentially throwing call-sites to be invokes. This has a noticable effect on the quality of our code generation. - catchpad, while similar in some aspects to invoke, is fairly awkward. It is unsplittable, starts a funclet, and has control flow to other funclets. - The nesting relationship between funclets is currently a property of control flow edges. Because of this, we are forced to carefully analyze the flow graph to see if there might potentially exist illegal nesting among funclets. While we have logic to clone funclets when they are illegally nested, it would be nicer if we had a representation which forbade them upfront. Let's clean this up a bit by doing the following: - Instead, make catchpad more like cleanuppad and landingpad: no control flow, just a bunch of simple operands; catchpad would be splittable. - Introduce catchswitch, a control flow instruction designed to model the constraints of funclet oriented EH. - Make funclet scoping explicit by having funclet instructions consume the token produced by the funclet which contains them. - Remove catchendpad and cleanupendpad. Their presence can be inferred implicitly using coloring information. N.B. The state numbering code for the CLR has been updated but the veracity of it's output cannot be spoken for. An expert should take a look to make sure the results are reasonable. Reviewers: rnk, JosephTremoulet, andrew.w.kaylor Differential Revision: http://reviews.llvm.org/D15139 llvm-svn: 255422
2015-12-12 13:38:55 +08:00
// The value defined by an invoke dominates an instruction only
// if it dominates every instruction in UseBB. A PHI is dominated only
// if the instruction dominates every possible use in the UseBB. Since
// UseBB == BB, avoid pruning.
[IR] Reformulate LLVM's EH funclet IR While we have successfully implemented a funclet-oriented EH scheme on top of LLVM IR, our scheme has some notable deficiencies: - catchendpad and cleanupendpad are necessary in the current design but they are difficult to explain to others, even to seasoned LLVM experts. - catchendpad and cleanupendpad are optimization barriers. They cannot be split and force all potentially throwing call-sites to be invokes. This has a noticable effect on the quality of our code generation. - catchpad, while similar in some aspects to invoke, is fairly awkward. It is unsplittable, starts a funclet, and has control flow to other funclets. - The nesting relationship between funclets is currently a property of control flow edges. Because of this, we are forced to carefully analyze the flow graph to see if there might potentially exist illegal nesting among funclets. While we have logic to clone funclets when they are illegally nested, it would be nicer if we had a representation which forbade them upfront. Let's clean this up a bit by doing the following: - Instead, make catchpad more like cleanuppad and landingpad: no control flow, just a bunch of simple operands; catchpad would be splittable. - Introduce catchswitch, a control flow instruction designed to model the constraints of funclet oriented EH. - Make funclet scoping explicit by having funclet instructions consume the token produced by the funclet which contains them. - Remove catchendpad and cleanupendpad. Their presence can be inferred implicitly using coloring information. N.B. The state numbering code for the CLR has been updated but the veracity of it's output cannot be spoken for. An expert should take a look to make sure the results are reasonable. Reviewers: rnk, JosephTremoulet, andrew.w.kaylor Differential Revision: http://reviews.llvm.org/D15139 llvm-svn: 255422
2015-12-12 13:38:55 +08:00
if (isa<InvokeInst>(BeforeHere) || isa<PHINode>(I) || I == BeforeHere)
return false;
if (!OrderedBB->dominates(BeforeHere, I))
return false;
// 'BeforeHere' comes before 'I', it's safe to prune if we also
// guarantee that 'I' never reaches 'BeforeHere' through a back-edge or
// by its successors, i.e, prune if:
//
// (1) BB is an entry block or have no sucessors.
// (2) There's no path coming back through BB sucessors.
if (BB == &BB->getParent()->getEntryBlock() ||
!BB->getTerminator()->getNumSuccessors())
return true;
SmallVector<BasicBlock*, 32> Worklist;
Worklist.append(succ_begin(BB), succ_end(BB));
return !isPotentiallyReachableFromMany(Worklist, BB, DT);
}
// If the value is defined in the same basic block as use and BeforeHere,
// there is no need to explore the use if BeforeHere dominates use.
// Check whether there is a path from I to BeforeHere.
if (BeforeHere != I && DT->dominates(BeforeHere, I) &&
!isPotentiallyReachable(I, BeforeHere, DT))
return true;
return false;
}
bool shouldExplore(const Use *U) override {
Instruction *I = cast<Instruction>(U->getUser());
if (BeforeHere == I && !IncludeI)
return false;
if (isSafeToPrune(I))
return false;
return true;
}
bool captured(const Use *U) override {
if (isa<ReturnInst>(U->getUser()) && !ReturnCaptures)
return false;
if (!shouldExplore(U))
return false;
Captured = true;
return true;
}
OrderedBasicBlock *OrderedBB;
const Instruction *BeforeHere;
DominatorTree *DT;
bool ReturnCaptures;
bool IncludeI;
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;
}
/// PointerMayBeCapturedBefore - Return true if this pointer value may be
/// captured by the enclosing function (which is required to exist). If a
/// DominatorTree is provided, only captures which happen before the given
/// instruction are considered. 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. A ordered basic block \p OBB can be used in order to speed up
/// queries about relative order among instructions in the same basic block.
bool llvm::PointerMayBeCapturedBefore(const Value *V, bool ReturnCaptures,
bool StoreCaptures, const Instruction *I,
DominatorTree *DT, bool IncludeI,
OrderedBasicBlock *OBB) {
assert(!isa<GlobalValue>(V) &&
"It doesn't make sense to ask whether a global is captured.");
bool UseNewOBB = OBB == nullptr;
if (!DT)
return PointerMayBeCaptured(V, ReturnCaptures, StoreCaptures);
if (UseNewOBB)
OBB = new OrderedBasicBlock(I->getParent());
// TODO: See comment in PointerMayBeCaptured regarding what could be done
// with StoreCaptures.
CapturesBefore CB(ReturnCaptures, I, DT, IncludeI, OBB);
PointerMayBeCaptured(V, &CB);
if (UseNewOBB)
delete OBB;
return CB.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. =] llvm-svn: 203364
2014-03-09 11:16:01 +08:00
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. =] llvm-svn: 203364
2014-03-09 11:16:01 +08:00
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;
// Volatile operations effectively capture the memory location that they
// load and store to.
if (auto *MI = dyn_cast<MemIntrinsic>(I))
if (MI->isVolatile())
if (Tracker->captured(U))
return;
// 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::data_operand_iterator B =
CS.data_operands_begin(), E = CS.data_operands_end();
for (CallSite::data_operand_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:
// Volatile loads make the address observable.
if (cast<LoadInst>(I)->isVolatile())
if (Tracker->captured(U))
return;
break;
case Instruction::VAArg:
// "va-arg" from a pointer does not cause it to be captured.
break;
case Instruction::Store:
// Stored the pointer - conservatively assume it may be captured.
// Volatile stores make the address observable.
if (V == I->getOperand(0) || cast<StoreInst>(I)->isVolatile())
if (Tracker->captured(U))
return;
break;
case Instruction::AtomicRMW: {
// atomicrmw conceptually includes both a load and store from
// the same location.
// As with a store, the location being accessed is not captured,
// but the value being stored is.
// Volatile stores make the address observable.
auto *ARMWI = cast<AtomicRMWInst>(I);
if (ARMWI->getValOperand() == V || ARMWI->isVolatile())
if (Tracker->captured(U))
return;
break;
}
case Instruction::AtomicCmpXchg: {
// cmpxchg conceptually includes both a load and store from
// the same location.
// As with a store, the location being accessed is not captured,
// but the value being stored is.
// Volatile stores make the address observable.
auto *ACXI = cast<AtomicCmpXchgInst>(I);
if (ACXI->getCompareOperand() == V || ACXI->getNewValOperand() == V ||
ACXI->isVolatile())
if (Tracker->captured(U))
return;
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. =] llvm-svn: 203364
2014-03-09 11:16:01 +08:00
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();
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 11:16:01 +08:00
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;
// Comparison against value stored in global variable. Given the pointer
// does not escape, its value cannot be guessed and stored separately in a
// global variable.
unsigned OtherIndex = (I->getOperand(0) == V) ? 1 : 0;
auto *LI = dyn_cast<LoadInst>(I->getOperand(OtherIndex));
if (LI && isa<GlobalVariable>(LI->getPointerOperand()))
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.
}