mirror of
https://github.com/RPCSX/llvm.git
synced 2024-11-23 19:59:57 +00:00
30c75827fc
Summary: Currently XRay compares its threshold against `Function::size()` . However, `Function::size()` returns the number of basic blocks (as I understand, such as cycle bodies, if/else bodies, switch-case bodies, etc.), rather than the number of instructions. The name of the parameter `-fxray-instruction-threshold=N`, as well as XRay documentation at http://llvm.org/docs/XRay.html , suggests that instructions should be counted, rather than the number of basic blocks. I see two options: 1. Count the number of MachineInstr`s in MachineFunction : this gives better estimate for the number of assembly instructions on the target. So a user can check in disassembly that the threshold works more or less correctly. 2. Count the number of Instruction`s in a Function : AFAIK, this gives correct number of IR instructions, which the user can check in IR listing. However, this number may be far (several times for small functions) from the number of assembly instructions finally emitted. Option 1 is implemented in this patch because I think that having the closer estimate for the number of assembly instructions emitted is more important than to have a clear definition of the metric. Reviewers: dberris, rengolin Reviewed By: dberris Subscribers: llvm-commits, iid_iunknown Differential Revision: https://reviews.llvm.org/D34027 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@305072 91177308-0d34-0410-b5e6-96231b3b80d8
207 lines
7.6 KiB
C++
207 lines
7.6 KiB
C++
//===- XRayInstrumentation.cpp - Adds XRay instrumentation to functions. --===//
|
|
//
|
|
// 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 MachineFunctionPass that inserts the appropriate
|
|
// XRay instrumentation instructions. We look for XRay-specific attributes
|
|
// on the function to determine whether we should insert the replacement
|
|
// operations.
|
|
//
|
|
//===---------------------------------------------------------------------===//
|
|
|
|
#include "llvm/ADT/SmallVector.h"
|
|
#include "llvm/ADT/STLExtras.h"
|
|
#include "llvm/ADT/Triple.h"
|
|
#include "llvm/CodeGen/MachineBasicBlock.h"
|
|
#include "llvm/CodeGen/MachineDominators.h"
|
|
#include "llvm/CodeGen/MachineFunction.h"
|
|
#include "llvm/CodeGen/MachineFunctionPass.h"
|
|
#include "llvm/CodeGen/MachineInstrBuilder.h"
|
|
#include "llvm/CodeGen/MachineLoopInfo.h"
|
|
#include "llvm/IR/Attributes.h"
|
|
#include "llvm/IR/Function.h"
|
|
#include "llvm/Pass.h"
|
|
#include "llvm/Target/TargetInstrInfo.h"
|
|
#include "llvm/Target/TargetMachine.h"
|
|
#include "llvm/Target/TargetSubtargetInfo.h"
|
|
|
|
using namespace llvm;
|
|
|
|
namespace {
|
|
|
|
struct XRayInstrumentation : public MachineFunctionPass {
|
|
static char ID;
|
|
|
|
XRayInstrumentation() : MachineFunctionPass(ID) {
|
|
initializeXRayInstrumentationPass(*PassRegistry::getPassRegistry());
|
|
}
|
|
|
|
void getAnalysisUsage(AnalysisUsage &AU) const override {
|
|
AU.setPreservesCFG();
|
|
AU.addRequired<MachineLoopInfo>();
|
|
AU.addPreserved<MachineLoopInfo>();
|
|
AU.addPreserved<MachineDominatorTree>();
|
|
MachineFunctionPass::getAnalysisUsage(AU);
|
|
}
|
|
|
|
bool runOnMachineFunction(MachineFunction &MF) override;
|
|
|
|
private:
|
|
// Replace the original RET instruction with the exit sled code ("patchable
|
|
// ret" pseudo-instruction), so that at runtime XRay can replace the sled
|
|
// with a code jumping to XRay trampoline, which calls the tracing handler
|
|
// and, in the end, issues the RET instruction.
|
|
// This is the approach to go on CPUs which have a single RET instruction,
|
|
// like x86/x86_64.
|
|
void replaceRetWithPatchableRet(MachineFunction &MF,
|
|
const TargetInstrInfo *TII);
|
|
|
|
// Prepend the original return instruction with the exit sled code ("patchable
|
|
// function exit" pseudo-instruction), preserving the original return
|
|
// instruction just after the exit sled code.
|
|
// This is the approach to go on CPUs which have multiple options for the
|
|
// return instruction, like ARM. For such CPUs we can't just jump into the
|
|
// XRay trampoline and issue a single return instruction there. We rather
|
|
// have to call the trampoline and return from it to the original return
|
|
// instruction of the function being instrumented.
|
|
void prependRetWithPatchableExit(MachineFunction &MF,
|
|
const TargetInstrInfo *TII);
|
|
};
|
|
|
|
} // end anonymous namespace
|
|
|
|
void XRayInstrumentation::replaceRetWithPatchableRet(
|
|
MachineFunction &MF, const TargetInstrInfo *TII) {
|
|
// We look for *all* terminators and returns, then replace those with
|
|
// PATCHABLE_RET instructions.
|
|
SmallVector<MachineInstr *, 4> Terminators;
|
|
for (auto &MBB : MF) {
|
|
for (auto &T : MBB.terminators()) {
|
|
unsigned Opc = 0;
|
|
if (T.isReturn() && T.getOpcode() == TII->getReturnOpcode()) {
|
|
// Replace return instructions with:
|
|
// PATCHABLE_RET <Opcode>, <Operand>...
|
|
Opc = TargetOpcode::PATCHABLE_RET;
|
|
}
|
|
if (TII->isTailCall(T)) {
|
|
// Treat the tail call as a return instruction, which has a
|
|
// different-looking sled than the normal return case.
|
|
Opc = TargetOpcode::PATCHABLE_TAIL_CALL;
|
|
}
|
|
if (Opc != 0) {
|
|
auto MIB = BuildMI(MBB, T, T.getDebugLoc(), TII->get(Opc))
|
|
.addImm(T.getOpcode());
|
|
for (auto &MO : T.operands())
|
|
MIB.add(MO);
|
|
Terminators.push_back(&T);
|
|
}
|
|
}
|
|
}
|
|
|
|
for (auto &I : Terminators)
|
|
I->eraseFromParent();
|
|
}
|
|
|
|
void XRayInstrumentation::prependRetWithPatchableExit(
|
|
MachineFunction &MF, const TargetInstrInfo *TII) {
|
|
for (auto &MBB : MF) {
|
|
for (auto &T : MBB.terminators()) {
|
|
unsigned Opc = 0;
|
|
if (T.isReturn()) {
|
|
Opc = TargetOpcode::PATCHABLE_FUNCTION_EXIT;
|
|
}
|
|
if (TII->isTailCall(T)) {
|
|
Opc = TargetOpcode::PATCHABLE_TAIL_CALL;
|
|
}
|
|
if (Opc != 0) {
|
|
// Prepend the return instruction with PATCHABLE_FUNCTION_EXIT or
|
|
// PATCHABLE_TAIL_CALL .
|
|
BuildMI(MBB, T, T.getDebugLoc(), TII->get(Opc));
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
bool XRayInstrumentation::runOnMachineFunction(MachineFunction &MF) {
|
|
auto &F = *MF.getFunction();
|
|
auto InstrAttr = F.getFnAttribute("function-instrument");
|
|
bool AlwaysInstrument = !InstrAttr.hasAttribute(Attribute::None) &&
|
|
InstrAttr.isStringAttribute() &&
|
|
InstrAttr.getValueAsString() == "xray-always";
|
|
Attribute Attr = F.getFnAttribute("xray-instruction-threshold");
|
|
unsigned XRayThreshold = 0;
|
|
if (!AlwaysInstrument) {
|
|
if (Attr.hasAttribute(Attribute::None) || !Attr.isStringAttribute())
|
|
return false; // XRay threshold attribute not found.
|
|
if (Attr.getValueAsString().getAsInteger(10, XRayThreshold))
|
|
return false; // Invalid value for threshold.
|
|
|
|
// Count the number of MachineInstr`s in MachineFunction
|
|
int64_t MICount = 0;
|
|
for (const auto& MBB : MF)
|
|
MICount += MBB.size();
|
|
|
|
// Check if we have a loop.
|
|
// FIXME: Maybe make this smarter, and see whether the loops are dependent
|
|
// on inputs or side-effects?
|
|
MachineLoopInfo &MLI = getAnalysis<MachineLoopInfo>();
|
|
if (MLI.empty() && MICount < XRayThreshold)
|
|
return false; // Function is too small and has no loops.
|
|
}
|
|
|
|
// We look for the first non-empty MachineBasicBlock, so that we can insert
|
|
// the function instrumentation in the appropriate place.
|
|
auto MBI = llvm::find_if(
|
|
MF, [&](const MachineBasicBlock &MBB) { return !MBB.empty(); });
|
|
if (MBI == MF.end())
|
|
return false; // The function is empty.
|
|
|
|
auto *TII = MF.getSubtarget().getInstrInfo();
|
|
auto &FirstMBB = *MBI;
|
|
auto &FirstMI = *FirstMBB.begin();
|
|
|
|
if (!MF.getSubtarget().isXRaySupported()) {
|
|
FirstMI.emitError("An attempt to perform XRay instrumentation for an"
|
|
" unsupported target.");
|
|
return false;
|
|
}
|
|
|
|
// First, insert an PATCHABLE_FUNCTION_ENTER as the first instruction of the
|
|
// MachineFunction.
|
|
BuildMI(FirstMBB, FirstMI, FirstMI.getDebugLoc(),
|
|
TII->get(TargetOpcode::PATCHABLE_FUNCTION_ENTER));
|
|
|
|
switch (MF.getTarget().getTargetTriple().getArch()) {
|
|
case Triple::ArchType::arm:
|
|
case Triple::ArchType::thumb:
|
|
case Triple::ArchType::aarch64:
|
|
case Triple::ArchType::ppc64le:
|
|
case Triple::ArchType::mips:
|
|
case Triple::ArchType::mipsel:
|
|
case Triple::ArchType::mips64:
|
|
case Triple::ArchType::mips64el:
|
|
// For the architectures which don't have a single return instruction
|
|
prependRetWithPatchableExit(MF, TII);
|
|
break;
|
|
default:
|
|
// For the architectures that have a single return instruction (such as
|
|
// RETQ on x86_64).
|
|
replaceRetWithPatchableRet(MF, TII);
|
|
break;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
char XRayInstrumentation::ID = 0;
|
|
char &llvm::XRayInstrumentationID = XRayInstrumentation::ID;
|
|
INITIALIZE_PASS_BEGIN(XRayInstrumentation, "xray-instrumentation",
|
|
"Insert XRay ops", false, false)
|
|
INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
|
|
INITIALIZE_PASS_END(XRayInstrumentation, "xray-instrumentation",
|
|
"Insert XRay ops", false, false)
|