1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-25 14:02:52 +02:00
llvm-mirror/lib/CodeGen/XRayInstrumentation.cpp
Dean Michael Berris b135433036 [XRay] Support for for tail calls for ARM no-Thumb
This patch adds simplified support for tail calls on ARM with XRay instrumentation.

Known issue: compiled with generic flags: `-O3 -g -fxray-instrument -Wall
-std=c++14  -ffunction-sections -fdata-sections` (this list doesn't include my
specific flags like --target=armv7-linux-gnueabihf etc.), the following program

    #include <cstdio>
    #include <cassert>
    #include <xray/xray_interface.h>

    [[clang::xray_always_instrument]] void __attribute__ ((noinline)) fC() {
      std::printf("In fC()\n");
    }

    [[clang::xray_always_instrument]] void __attribute__ ((noinline)) fB() {
      std::printf("In fB()\n");
      fC();
    }

    [[clang::xray_always_instrument]] void __attribute__ ((noinline)) fA() {
      std::printf("In fA()\n");
      fB();
    }

    // Avoid infinite recursion in case the logging function is instrumented (so calls logging
    //   function again).
    [[clang::xray_never_instrument]] void simplyPrint(int32_t functionId, XRayEntryType xret)
    {
      printf("XRay: functionId=%d type=%d.\n", int(functionId), int(xret));
    }

    int main(int argc, char* argv[]) {
      __xray_set_handler(simplyPrint);

      printf("Patching...\n");
      __xray_patch();
      fA();

      printf("Unpatching...\n");
      __xray_unpatch();
      fA();

      return 0;
    }

gives the following output:

    Patching...
    XRay: functionId=3 type=0.
    In fA()
    XRay: functionId=3 type=1.
    XRay: functionId=2 type=0.
    In fB()
    XRay: functionId=2 type=1.
    XRay: functionId=1 type=0.
    XRay: functionId=1 type=1.
    In fC()
    Unpatching...
    In fA()
    In fB()
    In fC()

So for function fC() the exit sled seems to be called too much before function
exit: before printing In fC().

Debugging shows that the above happens because printf from fC is also called as
a tail call. So first the exit sled of fC is executed, and only then printf is
jumped into. So it seems we can't do anything about this with the current
approach (i.e. within the simplification described in
https://reviews.llvm.org/D23988 ).

Differential Revision: https://reviews.llvm.org/D25030

llvm-svn: 284456
2016-10-18 05:54:15 +00:00

167 lines
6.0 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/CodeGen/Analysis.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Target/TargetInstrInfo.h"
#include "llvm/Target/TargetSubtargetInfo.h"
using namespace llvm;
namespace {
struct XRayInstrumentation : public MachineFunctionPass {
static char ID;
XRayInstrumentation() : MachineFunctionPass(ID) {
initializeXRayInstrumentationPass(*PassRegistry::getPassRegistry());
}
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);
};
} // 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.addOperand(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.
if (F.size() < XRayThreshold)
return false; // Function is too small.
}
auto &FirstMBB = *MF.begin();
auto &FirstMI = *FirstMBB.begin();
if (!MF.getSubtarget().isXRaySupported()) {
FirstMI.emitError("An attempt to perform XRay instrumentation for an"
" unsupported target.");
return false;
}
// FIXME: Do the loop triviality analysis here or in an earlier pass.
// First, insert an PATCHABLE_FUNCTION_ENTER as the first instruction of the
// MachineFunction.
auto *TII = MF.getSubtarget().getInstrInfo();
BuildMI(FirstMBB, FirstMI, FirstMI.getDebugLoc(),
TII->get(TargetOpcode::PATCHABLE_FUNCTION_ENTER));
switch (MF.getTarget().getTargetTriple().getArch()) {
case Triple::ArchType::arm:
case Triple::ArchType::thumb:
// 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(XRayInstrumentation, "xray-instrumentation", "Insert XRay ops",
false, false)