llvm-project/llvm/lib/CodeGen/StackProtector.cpp

442 lines
16 KiB
C++
Raw Normal View History

//===-- StackProtector.cpp - Stack Protector Insertion --------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This pass inserts stack protectors into functions which need them. A variable
// with a random value in it is stored onto the stack before the local variables
// are allocated. Upon exiting the block, the stored value is checked. If it's
// changed, then there was some sort of violation and the program aborts.
//
//===----------------------------------------------------------------------===//
#include "llvm/CodeGen/StackProtector.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/BranchProbabilityInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/CodeGen/Analysis.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/Module.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Target/TargetSubtargetInfo.h"
#include <cstdlib>
using namespace llvm;
#define DEBUG_TYPE "stack-protector"
STATISTIC(NumFunProtected, "Number of functions protected");
STATISTIC(NumAddrTaken, "Number of local variables that have their address"
" taken.");
static cl::opt<bool> EnableSelectionDAGSP("enable-selectiondag-sp",
cl::init(true), cl::Hidden);
char StackProtector::ID = 0;
INITIALIZE_PASS(StackProtector, "stack-protector", "Insert stack protectors",
false, true)
FunctionPass *llvm::createStackProtectorPass(const TargetMachine *TM) {
return new StackProtector(TM);
}
StackProtector::SSPLayoutKind
StackProtector::getSSPLayout(const AllocaInst *AI) const {
return AI ? Layout.lookup(AI) : SSPLK_None;
}
void StackProtector::adjustForColoring(const AllocaInst *From,
const AllocaInst *To) {
// When coloring replaces one alloca with another, transfer the SSPLayoutKind
// tag from the remapped to the target alloca. The remapped alloca should
// have a size smaller than or equal to the replacement alloca.
SSPLayoutMap::iterator I = Layout.find(From);
if (I != Layout.end()) {
SSPLayoutKind Kind = I->second;
Layout.erase(I);
// Transfer the tag, but make sure that SSPLK_AddrOf does not overwrite
// SSPLK_SmallArray or SSPLK_LargeArray, and make sure that
// SSPLK_SmallArray does not overwrite SSPLK_LargeArray.
I = Layout.find(To);
if (I == Layout.end())
Layout.insert(std::make_pair(To, Kind));
else if (I->second != SSPLK_LargeArray && Kind != SSPLK_AddrOf)
I->second = Kind;
}
}
bool StackProtector::runOnFunction(Function &Fn) {
F = &Fn;
M = F->getParent();
DominatorTreeWrapperPass *DTWP =
getAnalysisIfAvailable<DominatorTreeWrapperPass>();
DT = DTWP ? &DTWP->getDomTree() : nullptr;
TLI = TM->getSubtargetImpl(Fn)->getTargetLowering();
HasPrologue = false;
HasIRCheck = false;
Attribute Attr = Fn.getFnAttribute("stack-protector-buffer-size");
if (Attr.isStringAttribute() &&
Attr.getValueAsString().getAsInteger(10, SSPBufferSize))
return false; // Invalid integer string
if (!RequiresStackProtector())
return false;
++NumFunProtected;
return InsertStackProtectors();
}
/// \param [out] IsLarge is set to true if a protectable array is found and
/// it is "large" ( >= ssp-buffer-size). In the case of a structure with
/// multiple arrays, this gets set if any of them is large.
bool StackProtector::ContainsProtectableArray(Type *Ty, bool &IsLarge,
bool Strong,
bool InStruct) const {
if (!Ty)
return false;
if (ArrayType *AT = dyn_cast<ArrayType>(Ty)) {
if (!AT->getElementType()->isIntegerTy(8)) {
// If we're on a non-Darwin platform or we're inside of a structure, don't
// add stack protectors unless the array is a character array.
// However, in strong mode any array, regardless of type and size,
// triggers a protector.
if (!Strong && (InStruct || !Trip.isOSDarwin()))
return false;
}
// If an array has more than SSPBufferSize bytes of allocated space, then we
// emit stack protectors.
if (SSPBufferSize <= M->getDataLayout().getTypeAllocSize(AT)) {
IsLarge = true;
return true;
}
if (Strong)
// Require a protector for all arrays in strong mode
return true;
}
const StructType *ST = dyn_cast<StructType>(Ty);
if (!ST)
return false;
bool NeedsProtector = false;
for (StructType::element_iterator I = ST->element_begin(),
E = ST->element_end();
I != E; ++I)
if (ContainsProtectableArray(*I, IsLarge, Strong, true)) {
// If the element is a protectable array and is large (>= SSPBufferSize)
// then we are done. If the protectable array is not large, then
// keep looking in case a subsequent element is a large array.
if (IsLarge)
return true;
NeedsProtector = true;
}
return NeedsProtector;
}
bool StackProtector::HasAddressTaken(const Instruction *AI) {
[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 User *U : AI->users()) {
if (const StoreInst *SI = dyn_cast<StoreInst>(U)) {
if (AI == SI->getValueOperand())
return true;
} else if (const PtrToIntInst *SI = dyn_cast<PtrToIntInst>(U)) {
if (AI == SI->getOperand(0))
return true;
} else if (isa<CallInst>(U)) {
return true;
} else if (isa<InvokeInst>(U)) {
return true;
} else if (const SelectInst *SI = dyn_cast<SelectInst>(U)) {
if (HasAddressTaken(SI))
return true;
} else if (const PHINode *PN = dyn_cast<PHINode>(U)) {
// Keep track of what PHI nodes we have already visited to ensure
// they are only visited once.
if (VisitedPHIs.insert(PN).second)
if (HasAddressTaken(PN))
return true;
} else if (const GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(U)) {
if (HasAddressTaken(GEP))
return true;
} else if (const BitCastInst *BI = dyn_cast<BitCastInst>(U)) {
if (HasAddressTaken(BI))
return true;
}
}
return false;
}
/// \brief Check whether or not this function needs a stack protector based
/// upon the stack protector level.
///
/// We use two heuristics: a standard (ssp) and strong (sspstrong).
/// The standard heuristic which will add a guard variable to functions that
/// call alloca with a either a variable size or a size >= SSPBufferSize,
/// functions with character buffers larger than SSPBufferSize, and functions
/// with aggregates containing character buffers larger than SSPBufferSize. The
/// strong heuristic will add a guard variables to functions that call alloca
/// regardless of size, functions with any buffer regardless of type and size,
/// functions with aggregates that contain any buffer regardless of type and
/// size, and functions that contain stack-based variables that have had their
/// address taken.
bool StackProtector::RequiresStackProtector() {
bool Strong = false;
bool NeedsProtector = false;
for (const BasicBlock &BB : *F)
for (const Instruction &I : BB)
if (const CallInst *CI = dyn_cast<CallInst>(&I))
if (CI->getCalledFunction() ==
Intrinsic::getDeclaration(F->getParent(),
Intrinsic::stackprotector))
HasPrologue = true;
if (F->hasFnAttribute(Attribute::SafeStack))
return false;
if (F->hasFnAttribute(Attribute::StackProtectReq)) {
NeedsProtector = true;
Strong = true; // Use the same heuristic as strong to determine SSPLayout
} else if (F->hasFnAttribute(Attribute::StackProtectStrong))
Strong = true;
else if (HasPrologue)
NeedsProtector = true;
else if (!F->hasFnAttribute(Attribute::StackProtect))
return false;
for (const BasicBlock &BB : *F) {
for (const Instruction &I : BB) {
if (const AllocaInst *AI = dyn_cast<AllocaInst>(&I)) {
if (AI->isArrayAllocation()) {
// SSP-Strong: Enable protectors for any call to alloca, regardless
// of size.
if (Strong)
return true;
if (const auto *CI = dyn_cast<ConstantInt>(AI->getArraySize())) {
if (CI->getLimitedValue(SSPBufferSize) >= SSPBufferSize) {
// A call to alloca with size >= SSPBufferSize requires
// stack protectors.
Layout.insert(std::make_pair(AI, SSPLK_LargeArray));
NeedsProtector = true;
} else if (Strong) {
// Require protectors for all alloca calls in strong mode.
Layout.insert(std::make_pair(AI, SSPLK_SmallArray));
NeedsProtector = true;
}
} else {
// A call to alloca with a variable size requires protectors.
Layout.insert(std::make_pair(AI, SSPLK_LargeArray));
NeedsProtector = true;
}
continue;
}
bool IsLarge = false;
if (ContainsProtectableArray(AI->getAllocatedType(), IsLarge, Strong)) {
Layout.insert(std::make_pair(AI, IsLarge ? SSPLK_LargeArray
: SSPLK_SmallArray));
NeedsProtector = true;
continue;
}
if (Strong && HasAddressTaken(AI)) {
++NumAddrTaken;
Layout.insert(std::make_pair(AI, SSPLK_AddrOf));
NeedsProtector = true;
}
}
}
}
return NeedsProtector;
}
/// Create a stack guard loading and populate whether SelectionDAG SSP is
/// supported.
static Value *getStackGuard(const TargetLoweringBase *TLI, Module *M,
IRBuilder<> &B,
bool *SupportsSelectionDAGSP = nullptr) {
if (Value *Guard = TLI->getIRStackGuard(B))
return B.CreateLoad(Guard, true, "StackGuard");
// Use SelectionDAG SSP handling, since there isn't an IR guard.
//
// This is more or less weird, since we optionally output whether we
// should perform a SelectionDAG SP here. The reason is that it's strictly
// defined as !TLI->getIRStackGuard(B), where getIRStackGuard is also
// mutating. There is no way to get this bit without mutating the IR, so
// getting this bit has to happen in this right time.
//
// We could have define a new function TLI::supportsSelectionDAGSP(), but that
// will put more burden on the backends' overriding work, especially when it
// actually conveys the same information getIRStackGuard() already gives.
if (SupportsSelectionDAGSP)
*SupportsSelectionDAGSP = true;
TLI->insertSSPDeclarations(*M);
return B.CreateCall(Intrinsic::getDeclaration(M, Intrinsic::stackguard));
}
/// Insert code into the entry block that stores the stack guard
/// variable onto the stack:
///
/// entry:
/// StackGuardSlot = alloca i8*
/// StackGuard = <stack guard>
/// call void @llvm.stackprotector(StackGuard, StackGuardSlot)
///
/// Returns true if the platform/triple supports the stackprotectorcreate pseudo
/// node.
static bool CreatePrologue(Function *F, Module *M, ReturnInst *RI,
const TargetLoweringBase *TLI, AllocaInst *&AI) {
bool SupportsSelectionDAGSP = false;
IRBuilder<> B(&F->getEntryBlock().front());
PointerType *PtrTy = Type::getInt8PtrTy(RI->getContext());
AI = B.CreateAlloca(PtrTy, nullptr, "StackGuardSlot");
Value *Guard = getStackGuard(TLI, M, B, &SupportsSelectionDAGSP);
B.CreateCall(Intrinsic::getDeclaration(M, Intrinsic::stackprotector),
{Guard, AI});
return SupportsSelectionDAGSP;
}
/// InsertStackProtectors - Insert code into the prologue and epilogue of the
/// function.
///
/// - The prologue code loads and stores the stack guard onto the stack.
/// - The epilogue checks the value stored in the prologue against the original
/// value. It calls __stack_chk_fail if they differ.
bool StackProtector::InsertStackProtectors() {
bool SupportsSelectionDAGSP =
EnableSelectionDAGSP && !TM->Options.EnableFastISel;
AllocaInst *AI = nullptr; // Place on stack that stores the stack guard.
for (Function::iterator I = F->begin(), E = F->end(); I != E;) {
BasicBlock *BB = &*I++;
ReturnInst *RI = dyn_cast<ReturnInst>(BB->getTerminator());
if (!RI)
continue;
if (!HasPrologue) {
HasPrologue = true;
SupportsSelectionDAGSP &= CreatePrologue(F, M, RI, TLI, AI);
}
if (!SupportsSelectionDAGSP) {
// If we do not support SelectionDAG based tail calls, generate IR level
// tail calls.
//
// For each block with a return instruction, convert this:
//
// return:
// ...
// ret ...
//
// into this:
//
// return:
// ...
// %1 = <stack guard>
// %2 = load StackGuardSlot
// %3 = cmp i1 %1, %2
// br i1 %3, label %SP_return, label %CallStackCheckFailBlk
//
// SP_return:
// ret ...
//
// CallStackCheckFailBlk:
// call void @__stack_chk_fail()
// unreachable
// Create the FailBB. We duplicate the BB every time since the MI tail
// merge pass will merge together all of the various BB into one including
// fail BB generated by the stack protector pseudo instruction.
BasicBlock *FailBB = CreateFailBB();
// Set HasIRCheck to true, so that SelectionDAG will not generate its own
// version.
HasIRCheck = true;
// Split the basic block before the return instruction.
BasicBlock *NewBB = BB->splitBasicBlock(RI->getIterator(), "SP_return");
// Update the dominator tree if we need to.
if (DT && DT->isReachableFromEntry(BB)) {
DT->addNewBlock(NewBB, BB);
DT->addNewBlock(FailBB, BB);
}
// Remove default branch instruction to the new BB.
BB->getTerminator()->eraseFromParent();
// Move the newly created basic block to the point right after the old
// basic block so that it's in the "fall through" position.
NewBB->moveAfter(BB);
// Generate the stack protector instructions in the old basic block.
IRBuilder<> B(BB);
Value *Guard = getStackGuard(TLI, M, B);
LoadInst *LI2 = B.CreateLoad(AI, true);
Value *Cmp = B.CreateICmpEQ(Guard, LI2);
auto SuccessProb =
BranchProbabilityInfo::getBranchProbStackProtector(true);
auto FailureProb =
BranchProbabilityInfo::getBranchProbStackProtector(false);
MDNode *Weights = MDBuilder(F->getContext())
.createBranchWeights(SuccessProb.getNumerator(),
FailureProb.getNumerator());
B.CreateCondBr(Cmp, NewBB, FailBB, Weights);
}
}
// Return if we didn't modify any basic blocks. i.e., there are no return
// statements in the function.
return HasPrologue;
}
/// CreateFailBB - Create a basic block to jump to when the stack protector
/// check fails.
BasicBlock *StackProtector::CreateFailBB() {
LLVMContext &Context = F->getContext();
BasicBlock *FailBB = BasicBlock::Create(Context, "CallStackCheckFailBlk", F);
IRBuilder<> B(FailBB);
if (Trip.isOSOpenBSD()) {
Constant *StackChkFail =
M->getOrInsertFunction("__stack_smash_handler",
Type::getVoidTy(Context),
Type::getInt8PtrTy(Context), nullptr);
B.CreateCall(StackChkFail, B.CreateGlobalStringPtr(F->getName(), "SSH"));
} else {
Constant *StackChkFail =
M->getOrInsertFunction("__stack_chk_fail", Type::getVoidTy(Context),
nullptr);
B.CreateCall(StackChkFail, {});
}
B.CreateUnreachable();
return FailBB;
}
bool StackProtector::shouldEmitSDCheck(const BasicBlock &BB) const {
return HasPrologue && !HasIRCheck && dyn_cast<ReturnInst>(BB.getTerminator());
}