mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
b27683b417
Move abstractMemberAccess and PreserveDIType passes as early as possible, right after clang code generation. Currently, compiler may transform the above code p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0); p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2); a = llvm.bpf.builtin.preserve_field_info(p2, EXIST); if (a) { p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0); p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2); bpf_probe_read(buf, buf_size, p2); } to p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0); p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2); a = llvm.bpf.builtin.preserve_field_info(p2, EXIST); if (a) { bpf_probe_read(buf, buf_size, p2); } and eventually assembly code looks like reloc_exist = 1; reloc_member_offset = 10; //calculate member offset from base p2 = base + reloc_member_offset; if (reloc_exist) { bpf_probe_read(bpf, buf_size, p2); } if during libbpf relocation resolution, reloc_exist is actually resolved to 0 (not exist), reloc_member_offset relocation cannot be resolved and will be patched with illegal instruction. This will cause verifier failure. This patch attempts to address this issue by do chaining analysis and replace chains with special globals right after clang code gen. This will remove the cse possibility described in the above. The IR typically looks like %6 = load @llvm.sk_buff:0:50$0:0:0:2:0 %7 = bitcast %struct.sk_buff* %2 to i8* %8 = getelementptr i8, i8* %7, %6 for a particular address computation relocation. But this transformation has another consequence, code sinking may happen like below: PHI = <possibly different @preserve_*_access_globals> %7 = bitcast %struct.sk_buff* %2 to i8* %8 = getelementptr i8, i8* %7, %6 For such cases, we will not able to generate relocations since multiple relocations are merged into one. This patch introduced a passthrough builtin to prevent such optimization. Looks like inline assembly has more impact for optimizaiton, e.g., inlining. Using passthrough has less impact on optimizations. A new IR pass is introduced at the beginning of target-dependent IR optimization, which does: - report fatal error if any reloc global in PHI nodes - remove all bpf passthrough builtin functions Changes for existing CORE tests: - for clang tests, add "-Xclang -disable-llvm-passes" flags to avoid builtin->reloc_global transformation so the test is still able to check correctness for clang generated IR. - for llvm CodeGen/BPF tests, add "opt -O2 <ir_file> | llvm-dis" command before "llc" command since "opt" is needed to call newly-placed builtin->reloc_global transformation. Add target triple in the IR file since "opt" requires it. - Since target triple is added in IR file, if a test may produce different results for different endianness, two tests will be created, one for bpfeb and another for bpfel, e.g., some tests for relocation of lshift/rshift of bitfields. - field-reloc-bitfield-1.ll has different relocations compared to old codes. This is because for the structure in the test, new code returns struct layout alignment 4 while old code is 8. Align 8 is more precise and permits double load. With align 4, the new mechanism uses 4-byte load, so generating different relocations. - test intrinsic-transforms.ll is removed. This is used to test cse on intrinsics so we do not lose metadata. Now metadata is attached to global and not instruction, it won't get lost with cse. Differential Revision: https://reviews.llvm.org/D87153
131 lines
3.8 KiB
C++
131 lines
3.8 KiB
C++
//===------------ BPFCheckAndAdjustIR.cpp - Check and Adjust IR -----------===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Check IR and adjust IR for verifier friendly codes.
|
|
// The following are done for IR checking:
|
|
// - no relocation globals in PHI node.
|
|
// The following are done for IR adjustment:
|
|
// - remove __builtin_bpf_passthrough builtins. Target independent IR
|
|
// optimizations are done and those builtins can be removed.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "BPF.h"
|
|
#include "BPFCORE.h"
|
|
#include "BPFTargetMachine.h"
|
|
#include "llvm/IR/DebugInfoMetadata.h"
|
|
#include "llvm/IR/GlobalVariable.h"
|
|
#include "llvm/IR/Instruction.h"
|
|
#include "llvm/IR/Instructions.h"
|
|
#include "llvm/IR/Module.h"
|
|
#include "llvm/IR/Type.h"
|
|
#include "llvm/IR/User.h"
|
|
#include "llvm/IR/Value.h"
|
|
#include "llvm/Pass.h"
|
|
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
|
|
|
|
#define DEBUG_TYPE "bpf-check-and-opt-ir"
|
|
|
|
using namespace llvm;
|
|
|
|
namespace {
|
|
|
|
class BPFCheckAndAdjustIR final : public ModulePass {
|
|
bool runOnModule(Module &F) override;
|
|
|
|
public:
|
|
static char ID;
|
|
BPFCheckAndAdjustIR() : ModulePass(ID) {}
|
|
|
|
private:
|
|
void checkIR(Module &M);
|
|
bool adjustIR(Module &M);
|
|
bool removePassThroughBuiltin(Module &M);
|
|
};
|
|
} // End anonymous namespace
|
|
|
|
char BPFCheckAndAdjustIR::ID = 0;
|
|
INITIALIZE_PASS(BPFCheckAndAdjustIR, DEBUG_TYPE, "BPF Check And Adjust IR",
|
|
false, false)
|
|
|
|
ModulePass *llvm::createBPFCheckAndAdjustIR() {
|
|
return new BPFCheckAndAdjustIR();
|
|
}
|
|
|
|
void BPFCheckAndAdjustIR::checkIR(Module &M) {
|
|
// Ensure relocation global won't appear in PHI node
|
|
// This may happen if the compiler generated the following code:
|
|
// B1:
|
|
// g1 = @llvm.skb_buff:0:1...
|
|
// ...
|
|
// goto B_COMMON
|
|
// B2:
|
|
// g2 = @llvm.skb_buff:0:2...
|
|
// ...
|
|
// goto B_COMMON
|
|
// B_COMMON:
|
|
// g = PHI(g1, g2)
|
|
// x = load g
|
|
// ...
|
|
// If anything likes the above "g = PHI(g1, g2)", issue a fatal error.
|
|
for (Function &F : M)
|
|
for (auto &BB : F)
|
|
for (auto &I : BB) {
|
|
PHINode *PN = dyn_cast<PHINode>(&I);
|
|
if (!PN || PN->use_empty())
|
|
continue;
|
|
for (int i = 0, e = PN->getNumIncomingValues(); i < e; ++i) {
|
|
auto *GV = dyn_cast<GlobalVariable>(PN->getIncomingValue(i));
|
|
if (!GV)
|
|
continue;
|
|
if (GV->hasAttribute(BPFCoreSharedInfo::AmaAttr) ||
|
|
GV->hasAttribute(BPFCoreSharedInfo::TypeIdAttr))
|
|
report_fatal_error("relocation global in PHI node");
|
|
}
|
|
}
|
|
}
|
|
|
|
bool BPFCheckAndAdjustIR::removePassThroughBuiltin(Module &M) {
|
|
// Remove __builtin_bpf_passthrough()'s which are used to prevent
|
|
// certain IR optimizations. Now major IR optimizations are done,
|
|
// remove them.
|
|
bool Changed = false;
|
|
CallInst *ToBeDeleted = nullptr;
|
|
for (Function &F : M)
|
|
for (auto &BB : F)
|
|
for (auto &I : BB) {
|
|
if (ToBeDeleted) {
|
|
ToBeDeleted->eraseFromParent();
|
|
ToBeDeleted = nullptr;
|
|
}
|
|
|
|
auto *Call = dyn_cast<CallInst>(&I);
|
|
if (!Call)
|
|
continue;
|
|
auto *GV = dyn_cast<GlobalValue>(Call->getCalledOperand());
|
|
if (!GV)
|
|
continue;
|
|
if (!GV->getName().startswith("llvm.bpf.passthrough"))
|
|
continue;
|
|
Changed = true;
|
|
Value *Arg = Call->getArgOperand(1);
|
|
Call->replaceAllUsesWith(Arg);
|
|
ToBeDeleted = Call;
|
|
}
|
|
return Changed;
|
|
}
|
|
|
|
bool BPFCheckAndAdjustIR::adjustIR(Module &M) {
|
|
return removePassThroughBuiltin(M);
|
|
}
|
|
|
|
bool BPFCheckAndAdjustIR::runOnModule(Module &M) {
|
|
checkIR(M);
|
|
return adjustIR(M);
|
|
}
|