llvm-project/llvm/lib/IR/BasicBlock.cpp

494 lines
17 KiB
C++
Raw Normal View History

//===-- BasicBlock.cpp - Implement BasicBlock related methods -------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
2001-06-07 04:29:01 +08:00
//
// This file implements the BasicBlock class for the IR library.
2001-06-07 04:29:01 +08:00
//
//===----------------------------------------------------------------------===//
#include "llvm/IR/BasicBlock.h"
#include "SymbolTableListTraitsImpl.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/IR/CFG.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Type.h"
#include <algorithm>
using namespace llvm;
ValueSymbolTable *BasicBlock::getValueSymbolTable() {
if (Function *F = getParent())
return F->getValueSymbolTable();
return nullptr;
}
LLVMContext &BasicBlock::getContext() const {
return getType()->getContext();
}
// Explicit instantiation of SymbolTableListTraits since some of the methods
// are not in the public header file...
template class llvm::SymbolTableListTraits<Instruction>;
BasicBlock::BasicBlock(LLVMContext &C, const Twine &Name, Function *NewParent,
BasicBlock *InsertBefore)
: Value(Type::getLabelTy(C), Value::BasicBlockVal), Parent(nullptr) {
if (NewParent)
insertInto(NewParent, InsertBefore);
else
assert(!InsertBefore &&
"Cannot insert block before another block with no function!");
2011-08-10 07:12:56 +08:00
setName(Name);
}
void BasicBlock::insertInto(Function *NewParent, BasicBlock *InsertBefore) {
assert(NewParent && "Expected a parent");
assert(!Parent && "Already has a parent");
if (InsertBefore)
NewParent->getBasicBlockList().insert(InsertBefore->getIterator(), this);
else
NewParent->getBasicBlockList().push_back(this);
}
BasicBlock::~BasicBlock() {
// If the address of the block is taken and it is being deleted (e.g. because
// it is dead), this means that there is either a dangling constant expr
// hanging off the block, or an undefined use of the block (source code
// expecting the address of a label to keep the block alive even though there
// is no indirect branch). Handle these cases by zapping the BlockAddress
// nodes. There are no other possible uses at this point.
if (hasAddressTaken()) {
assert(!use_empty() && "There should be at least one blockaddress!");
Constant *Replacement =
ConstantInt::get(llvm::Type::getInt32Ty(getContext()), 1);
while (!use_empty()) {
[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
BlockAddress *BA = cast<BlockAddress>(user_back());
BA->replaceAllUsesWith(ConstantExpr::getIntToPtr(Replacement,
BA->getType()));
BA->destroyConstant();
}
}
2011-08-10 07:12:56 +08:00
assert(getParent() == nullptr && "BasicBlock still linked into the program!");
dropAllReferences();
InstList.clear();
2001-06-07 04:29:01 +08:00
}
void BasicBlock::setParent(Function *parent) {
// Set Parent=parent, updating instruction symtab entries as appropriate.
InstList.setSymTabObject(&Parent, parent);
}
iterator_range<filter_iterator<BasicBlock::const_iterator,
std::function<bool(const Instruction &)>>>
BasicBlock::instructionsWithoutDebug() const {
std::function<bool(const Instruction &)> Fn = [](const Instruction &I) {
return !isa<DbgInfoIntrinsic>(I);
};
return make_filter_range(*this, Fn);
}
iterator_range<filter_iterator<BasicBlock::iterator,
std::function<bool(Instruction &)>>>
BasicBlock::instructionsWithoutDebug() {
std::function<bool(Instruction &)> Fn = [](Instruction &I) {
return !isa<DbgInfoIntrinsic>(I);
};
return make_filter_range(*this, Fn);
}
void BasicBlock::removeFromParent() {
getParent()->getBasicBlockList().remove(getIterator());
}
iplist<BasicBlock>::iterator BasicBlock::eraseFromParent() {
return getParent()->getBasicBlockList().erase(getIterator());
}
/// Unlink this basic block from its current function and
/// insert it into the function that MovePos lives in, right before MovePos.
2005-08-13 06:14:06 +08:00
void BasicBlock::moveBefore(BasicBlock *MovePos) {
MovePos->getParent()->getBasicBlockList().splice(
MovePos->getIterator(), getParent()->getBasicBlockList(), getIterator());
2005-08-13 06:14:06 +08:00
}
/// Unlink this basic block from its current function and
/// insert it into the function that MovePos lives in, right after MovePos.
void BasicBlock::moveAfter(BasicBlock *MovePos) {
MovePos->getParent()->getBasicBlockList().splice(
++MovePos->getIterator(), getParent()->getBasicBlockList(),
getIterator());
}
const Module *BasicBlock::getModule() const {
return getParent()->getParent();
}
const Instruction *BasicBlock::getTerminator() const {
if (InstList.empty() || !InstList.back().isTerminator())
return nullptr;
return &InstList.back();
2001-06-07 04:29:01 +08:00
}
const CallInst *BasicBlock::getTerminatingMustTailCall() const {
if (InstList.empty())
return nullptr;
const ReturnInst *RI = dyn_cast<ReturnInst>(&InstList.back());
if (!RI || RI == &InstList.front())
return nullptr;
const Instruction *Prev = RI->getPrevNode();
if (!Prev)
return nullptr;
if (Value *RV = RI->getReturnValue()) {
if (RV != Prev)
return nullptr;
// Look through the optional bitcast.
if (auto *BI = dyn_cast<BitCastInst>(Prev)) {
RV = BI->getOperand(0);
Prev = BI->getPrevNode();
if (!Prev || RV != Prev)
return nullptr;
}
}
if (auto *CI = dyn_cast<CallInst>(Prev)) {
if (CI->isMustTailCall())
return CI;
}
return nullptr;
}
const CallInst *BasicBlock::getTerminatingDeoptimizeCall() const {
if (InstList.empty())
return nullptr;
auto *RI = dyn_cast<ReturnInst>(&InstList.back());
if (!RI || RI == &InstList.front())
return nullptr;
if (auto *CI = dyn_cast_or_null<CallInst>(RI->getPrevNode()))
if (Function *F = CI->getCalledFunction())
if (F->getIntrinsicID() == Intrinsic::experimental_deoptimize)
return CI;
return nullptr;
}
const Instruction* BasicBlock::getFirstNonPHI() const {
for (const Instruction &I : *this)
if (!isa<PHINode>(I))
return &I;
return nullptr;
}
const Instruction* BasicBlock::getFirstNonPHIOrDbg() const {
for (const Instruction &I : *this)
if (!isa<PHINode>(I) && !isa<DbgInfoIntrinsic>(I))
return &I;
return nullptr;
}
const Instruction* BasicBlock::getFirstNonPHIOrDbgOrLifetime() const {
for (const Instruction &I : *this) {
if (isa<PHINode>(I) || isa<DbgInfoIntrinsic>(I))
continue;
if (I.isLifetimeStartOrEnd())
continue;
return &I;
}
return nullptr;
}
BasicBlock::const_iterator BasicBlock::getFirstInsertionPt() const {
const Instruction *FirstNonPHI = getFirstNonPHI();
if (!FirstNonPHI)
return end();
const_iterator InsertPt = FirstNonPHI->getIterator();
if (InsertPt->isEHPad()) ++InsertPt;
return InsertPt;
}
2001-06-07 04:29:01 +08:00
void BasicBlock::dropAllReferences() {
for (Instruction &I : *this)
I.dropAllReferences();
2001-06-07 04:29:01 +08:00
}
/// If this basic block has a single predecessor block,
2005-02-24 10:37:26 +08:00
/// return the block, otherwise return a null pointer.
const BasicBlock *BasicBlock::getSinglePredecessor() const {
const_pred_iterator PI = pred_begin(this), E = pred_end(this);
if (PI == E) return nullptr; // No preds.
const BasicBlock *ThePred = *PI;
2005-02-24 10:37:26 +08:00
++PI;
return (PI == E) ? ThePred : nullptr /*multiple preds*/;
2005-02-24 10:37:26 +08:00
}
/// If this basic block has a unique predecessor block,
/// return the block, otherwise return a null pointer.
2011-08-10 07:12:56 +08:00
/// Note that unique predecessor doesn't mean single edge, there can be
/// multiple edges from the unique predecessor to this block (for example
/// a switch statement with multiple cases having the same destination).
const BasicBlock *BasicBlock::getUniquePredecessor() const {
const_pred_iterator PI = pred_begin(this), E = pred_end(this);
if (PI == E) return nullptr; // No preds.
const BasicBlock *PredBB = *PI;
++PI;
for (;PI != E; ++PI) {
if (*PI != PredBB)
return nullptr;
// The same predecessor appears multiple times in the predecessor list.
// This is OK.
}
return PredBB;
}
bool BasicBlock::hasNPredecessors(unsigned N) const {
return hasNItems(pred_begin(this), pred_end(this), N);
}
bool BasicBlock::hasNPredecessorsOrMore(unsigned N) const {
return hasNItemsOrMore(pred_begin(this), pred_end(this), N);
}
const BasicBlock *BasicBlock::getSingleSuccessor() const {
succ_const_iterator SI = succ_begin(this), E = succ_end(this);
if (SI == E) return nullptr; // no successors
const BasicBlock *TheSucc = *SI;
++SI;
return (SI == E) ? TheSucc : nullptr /* multiple successors */;
}
const BasicBlock *BasicBlock::getUniqueSuccessor() const {
succ_const_iterator SI = succ_begin(this), E = succ_end(this);
if (SI == E) return nullptr; // No successors
const BasicBlock *SuccBB = *SI;
Add a pass for inserting safepoints into (nearly) arbitrary IR This pass is responsible for figuring out where to place call safepoints and safepoint polls. It doesn't actually make the relocations explicit; that's the job of the RewriteStatepointsForGC pass (http://reviews.llvm.org/D6975). Note that this code is not yet finalized. Its moving in tree for incremental development, but further cleanup is needed and will happen over the next few days. It is not yet part of the standard pass order. Planned changes in the near future: - I plan on restructuring the statepoint rewrite to use the functions add to the IRBuilder a while back. - In the current pass, the function "gc.safepoint_poll" is treated specially but is not an intrinsic. I plan to make identifying the poll function a property of the GCStrategy at some point in the near future. - As follow on patches, I will be separating a collection of test cases we have out of tree and submitting them upstream. - It's not explicit in the code, but these two patches are introducing a new state for a statepoint which looks a lot like a patchpoint. There's no a transient form which doesn't yet have the relocations explicitly represented, but does prevent reordering of memory operations. Once this is in, I need to update actually make this explicit by reserving the 'unused' argument of the statepoint as a flag, updating the docs, and making the code explicitly check for such a thing. This wasn't really planned, but once I split the two passes - which was done for other reasons - the intermediate state fell out. Just reminds us once again that we need to merge statepoints and patchpoints at some point in the not that distant future. Future directions planned: - Identifying more cases where a backedge safepoint isn't required to ensure timely execution of a safepoint poll. - Tweaking the insertion process to generate easier to optimize IR. (For example, investigating making SplitBackedge) the default. - Adding opt-in flags for a GCStrategy to use this pass. Once done, add this pass to the actual pass ordering. Differential Revision: http://reviews.llvm.org/D6981 llvm-svn: 228090
2015-02-04 08:37:33 +08:00
++SI;
for (;SI != E; ++SI) {
if (*SI != SuccBB)
return nullptr;
Add a pass for inserting safepoints into (nearly) arbitrary IR This pass is responsible for figuring out where to place call safepoints and safepoint polls. It doesn't actually make the relocations explicit; that's the job of the RewriteStatepointsForGC pass (http://reviews.llvm.org/D6975). Note that this code is not yet finalized. Its moving in tree for incremental development, but further cleanup is needed and will happen over the next few days. It is not yet part of the standard pass order. Planned changes in the near future: - I plan on restructuring the statepoint rewrite to use the functions add to the IRBuilder a while back. - In the current pass, the function "gc.safepoint_poll" is treated specially but is not an intrinsic. I plan to make identifying the poll function a property of the GCStrategy at some point in the near future. - As follow on patches, I will be separating a collection of test cases we have out of tree and submitting them upstream. - It's not explicit in the code, but these two patches are introducing a new state for a statepoint which looks a lot like a patchpoint. There's no a transient form which doesn't yet have the relocations explicitly represented, but does prevent reordering of memory operations. Once this is in, I need to update actually make this explicit by reserving the 'unused' argument of the statepoint as a flag, updating the docs, and making the code explicitly check for such a thing. This wasn't really planned, but once I split the two passes - which was done for other reasons - the intermediate state fell out. Just reminds us once again that we need to merge statepoints and patchpoints at some point in the not that distant future. Future directions planned: - Identifying more cases where a backedge safepoint isn't required to ensure timely execution of a safepoint poll. - Tweaking the insertion process to generate easier to optimize IR. (For example, investigating making SplitBackedge) the default. - Adding opt-in flags for a GCStrategy to use this pass. Once done, add this pass to the actual pass ordering. Differential Revision: http://reviews.llvm.org/D6981 llvm-svn: 228090
2015-02-04 08:37:33 +08:00
// The same successor appears multiple times in the successor list.
// This is OK.
}
return SuccBB;
}
iterator_range<BasicBlock::phi_iterator> BasicBlock::phis() {
PHINode *P = empty() ? nullptr : dyn_cast<PHINode>(&*begin());
return make_range<phi_iterator>(P, nullptr);
}
/// This method is used to notify a BasicBlock that the
/// specified Predecessor of the block is no longer able to reach it. This is
/// actually not used to update the Predecessor list, but is actually used to
/// update the PHI nodes that reside in the block. Note that this should be
/// called while the predecessor still refers to this block.
///
void BasicBlock::removePredecessor(BasicBlock *Pred,
bool DontDeleteUselessPHIs) {
assert((hasNUsesOrMore(16)||// Reduce cost of this assertion for complex CFGs.
find(pred_begin(this), pred_end(this), Pred) != pred_end(this)) &&
"removePredecessor: BB is not a predecessor!");
if (InstList.empty()) return;
PHINode *APN = dyn_cast<PHINode>(&front());
if (!APN) return; // Quick exit.
// If there are exactly two predecessors, then we want to nuke the PHI nodes
// altogether. However, we cannot do this, if this in this case:
//
// Loop:
// %x = phi [X, Loop]
// %x2 = add %x, 1 ;; This would become %x2 = add %x2, 1
// br Loop ;; %x2 does not dominate all uses
//
// This is because the PHI node input is actually taken from the predecessor
// basic block. The only case this can happen is with a self loop, so we
// check for this case explicitly now.
//
unsigned max_idx = APN->getNumIncomingValues();
assert(max_idx != 0 && "PHI Node in block with 0 predecessors!?!?!");
if (max_idx == 2) {
BasicBlock *Other = APN->getIncomingBlock(APN->getIncomingBlock(0) == Pred);
// Disable PHI elimination!
if (this == Other) max_idx = 3;
}
// <= Two predecessors BEFORE I remove one?
if (max_idx <= 2 && !DontDeleteUselessPHIs) {
// Yup, loop through and nuke the PHI nodes
while (PHINode *PN = dyn_cast<PHINode>(&front())) {
// Remove the predecessor first.
PN->removeIncomingValue(Pred, !DontDeleteUselessPHIs);
// If the PHI _HAD_ two uses, replace PHI node with its now *single* value
if (max_idx == 2) {
if (PN->getIncomingValue(0) != PN)
PN->replaceAllUsesWith(PN->getIncomingValue(0));
else
// We are left with an infinite loop with no entries: kill the PHI.
PN->replaceAllUsesWith(UndefValue::get(PN->getType()));
getInstList().pop_front(); // Remove the PHI node
}
// If the PHI node already only had one entry, it got deleted by
// removeIncomingValue.
}
} else {
// Okay, now we know that we need to remove predecessor #pred_idx from all
// PHI nodes. Iterate over each PHI node fixing them up
PHINode *PN;
for (iterator II = begin(); (PN = dyn_cast<PHINode>(II)); ) {
++II;
PN->removeIncomingValue(Pred, false);
// If all incoming values to the Phi are the same, we can replace the Phi
// with that value.
Value* PNV = nullptr;
if (!DontDeleteUselessPHIs && (PNV = PN->hasConstantValue()))
if (PNV != PN) {
PN->replaceAllUsesWith(PNV);
PN->eraseFromParent();
}
}
}
}
bool BasicBlock::canSplitPredecessors() const {
const Instruction *FirstNonPHI = getFirstNonPHI();
if (isa<LandingPadInst>(FirstNonPHI))
return true;
// This is perhaps a little conservative because constructs like
// CleanupBlockInst are pretty easy to split. However, SplitBlockPredecessors
// cannot handle such things just yet.
if (FirstNonPHI->isEHPad())
return false;
return true;
}
2001-06-07 04:29:01 +08:00
bool BasicBlock::isLegalToHoistInto() const {
auto *Term = getTerminator();
// No terminator means the block is under construction.
if (!Term)
return true;
// If the block has no successors, there can be no instructions to hoist.
assert(Term->getNumSuccessors() > 0);
// Instructions should not be hoisted across exception handling boundaries.
return !Term->isExceptionalTerminator();
}
/// This splits a basic block into two at the specified
/// instruction. Note that all instructions BEFORE the specified iterator stay
/// as part of the original basic block, an unconditional branch is added to
/// the new BB, and the rest of the instructions in the BB are moved to the new
/// BB, including the old terminator. This invalidates the iterator.
///
/// Note that this only works on well formed basic blocks (must have a
/// terminator), and 'I' must not be the end of instruction list (which would
/// cause a degenerate basic block to be formed, having a terminator inside of
/// the basic block).
///
BasicBlock *BasicBlock::splitBasicBlock(iterator I, const Twine &BBName) {
2001-06-07 04:29:01 +08:00
assert(getTerminator() && "Can't use splitBasicBlock on degenerate BB!");
assert(I != InstList.end() &&
"Trying to get me to create degenerate basic block!");
2001-06-07 04:29:01 +08:00
BasicBlock *New = BasicBlock::Create(getContext(), BBName, getParent(),
this->getNextNode());
2001-06-07 04:29:01 +08:00
// Save DebugLoc of split point before invalidating iterator.
DebugLoc Loc = I->getDebugLoc();
// Move all of the specified instructions from the original basic block into
// the new basic block.
New->getInstList().splice(New->end(), this->getInstList(), I, end());
2001-06-07 04:29:01 +08:00
// Add a branch instruction to the newly formed basic block.
BranchInst *BI = BranchInst::Create(New, this);
BI->setDebugLoc(Loc);
// Now we must loop through all of the successors of the New block (which
// _were_ the successors of the 'this' block), and update any PHI nodes in
// successors. If there were PHI nodes in the successors, then they need to
// know that incoming branches will be from New, not from Old.
//
for (succ_iterator I = succ_begin(New), E = succ_end(New); I != E; ++I) {
// Loop over any phi nodes in the basic block, updating the BB field of
// incoming values...
BasicBlock *Successor = *I;
for (auto &PN : Successor->phis()) {
int Idx = PN.getBasicBlockIndex(this);
while (Idx != -1) {
PN.setIncomingBlock((unsigned)Idx, New);
Idx = PN.getBasicBlockIndex(this);
}
}
}
2001-06-07 04:29:01 +08:00
return New;
}
void BasicBlock::replaceSuccessorsPhiUsesWith(BasicBlock *New) {
Instruction *TI = getTerminator();
if (!TI)
// Cope with being called on a BasicBlock that doesn't have a terminator
// yet. Clang's CodeGenFunction::EmitReturnBlock() likes to do this.
return;
for (BasicBlock *Succ : successors(TI)) {
// N.B. Succ might not be a complete BasicBlock, so don't assume
// that it ends with a non-phi instruction.
for (iterator II = Succ->begin(), IE = Succ->end(); II != IE; ++II) {
PHINode *PN = dyn_cast<PHINode>(II);
if (!PN)
break;
int i;
while ((i = PN->getBasicBlockIndex(this)) >= 0)
PN->setIncomingBlock(i, New);
}
}
}
/// Return true if this basic block is a landing pad. I.e., it's
/// the destination of the 'unwind' edge of an invoke instruction.
bool BasicBlock::isLandingPad() const {
return isa<LandingPadInst>(getFirstNonPHI());
}
/// Return the landingpad instruction associated with the landing pad.
const LandingPadInst *BasicBlock::getLandingPadInst() const {
return dyn_cast<LandingPadInst>(getFirstNonPHI());
}
Optional<uint64_t> BasicBlock::getIrrLoopHeaderWeight() const {
const Instruction *TI = getTerminator();
if (MDNode *MDIrrLoopHeader =
TI->getMetadata(LLVMContext::MD_irr_loop)) {
MDString *MDName = cast<MDString>(MDIrrLoopHeader->getOperand(0));
if (MDName->getString().equals("loop_header_weight")) {
auto *CI = mdconst::extract<ConstantInt>(MDIrrLoopHeader->getOperand(1));
return Optional<uint64_t>(CI->getValue().getZExtValue());
}
}
return Optional<uint64_t>();
}
BasicBlock::iterator llvm::skipDebugIntrinsics(BasicBlock::iterator It) {
while (isa<DbgInfoIntrinsic>(It))
++It;
return It;
}