[llvm] [RISCV][MC] Implement evaluateBranch for auipc+jalr pairs (PR #65480)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Oct 2 01:36:15 PDT 2023
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-binary-utilities
<details>
<summary>Changes</summary>
This patch implements `MCInstrAnalysis` state in order to be able analyze auipc+jalr pairs inside `evaluateBranch`.
This is implemented as follows:
- State: array of currently known GPR values;
- Whenever an auipc is detected in `updateState`, update the state value of RD with the immediate;
- Whenever a jalr is detected in `evaluateBranch`, check if the state holds a value for RS1 and use that to compute its target.
Note that this is similar to how binutils implements it and the output of llvm-objdump should now mostly match the one of GNU objdump.
This patch also updates the relevant llvm-objdump patches and adds a new one testing the output for interleaved auipc+jalr pairs.
This PR builds on #<!-- -->65479. Please only review the top commit here.
---
Full diff: https://github.com/llvm/llvm-project/pull/65480.diff
5 Files Affected:
- (modified) llvm/include/llvm/MC/MCInstrAnalysis.h (+15)
- (modified) llvm/lib/Target/RISCV/MCTargetDesc/RISCVMCTargetDesc.cpp (+64)
- (modified) llvm/test/tools/llvm-objdump/ELF/RISCV/branches.s (+2-2)
- (added) llvm/test/tools/llvm-objdump/ELF/RISCV/multi-instr-target.s (+45)
- (modified) llvm/tools/llvm-objdump/llvm-objdump.cpp (+20-5)
``````````diff
diff --git a/llvm/include/llvm/MC/MCInstrAnalysis.h b/llvm/include/llvm/MC/MCInstrAnalysis.h
index c3c675c39c5590c..dac12af599e6f34 100644
--- a/llvm/include/llvm/MC/MCInstrAnalysis.h
+++ b/llvm/include/llvm/MC/MCInstrAnalysis.h
@@ -37,6 +37,21 @@ class MCInstrAnalysis {
MCInstrAnalysis(const MCInstrInfo *Info) : Info(Info) {}
virtual ~MCInstrAnalysis() = default;
+ /// Clear the internal state. See updateState for more information.
+ virtual void resetState() {}
+
+ /// Update internal state with \p Inst at \p Addr.
+ ///
+ /// For some types a analyses, inspecting a single instruction is not
+ /// sufficient. Some examples are auipc/jalr pairs on RISC-V or adrp/ldr pairs
+ /// on AArch64. To support inspecting multiple instructions, targets may keep
+ /// track of an internal state while analysing instructions. Clients should
+ /// call updateState for every instruction which allows later calls to one of
+ /// the analysis functions to take previous instructions into account.
+ /// Whenever state becomes irrelevant (e.g., when starting to disassemble a
+ /// new function), clients should call resetState to clear it.
+ virtual void updateState(const MCInst &Inst, uint64_t Addr) {}
+
virtual bool isBranch(const MCInst &Inst) const {
return Info->get(Inst.getOpcode()).isBranch();
}
diff --git a/llvm/lib/Target/RISCV/MCTargetDesc/RISCVMCTargetDesc.cpp b/llvm/lib/Target/RISCV/MCTargetDesc/RISCVMCTargetDesc.cpp
index 75af5c2de09469b..5349fa0a4b30881 100644
--- a/llvm/lib/Target/RISCV/MCTargetDesc/RISCVMCTargetDesc.cpp
+++ b/llvm/lib/Target/RISCV/MCTargetDesc/RISCVMCTargetDesc.cpp
@@ -114,10 +114,65 @@ static MCTargetStreamer *createRISCVNullTargetStreamer(MCStreamer &S) {
namespace {
class RISCVMCInstrAnalysis : public MCInstrAnalysis {
+ std::optional<int64_t> GPRState[31];
+
+ static bool isGPR(unsigned Reg) {
+ return Reg >= RISCV::X0 && Reg <= RISCV::X31;
+ }
+
+ void setGPRState(unsigned Reg, std::optional<int64_t> Value) {
+ assert(isGPR(Reg) && "Invalid GPR reg");
+
+ if (Reg != RISCV::X0)
+ GPRState[Reg - RISCV::X1] = Value;
+ }
+
+ std::optional<int64_t> getGPRState(unsigned Reg) const {
+ assert(isGPR(Reg) && "Invalid GPR reg");
+
+ if (Reg == RISCV::X0)
+ return 0;
+ return GPRState[Reg - RISCV::X1];
+ }
+
public:
explicit RISCVMCInstrAnalysis(const MCInstrInfo *Info)
: MCInstrAnalysis(Info) {}
+ void resetState() override {
+ std::fill(std::begin(GPRState), std::end(GPRState), std::nullopt);
+ }
+
+ void updateState(const MCInst &Inst, uint64_t Addr) override {
+ // Terminators mark the end of a basic block which means the sequentially
+ // next instruction will be the first of another basic block and the current
+ // state will typically not be valid anymore. For calls, we assume all
+ // registers may be clobbered by the callee (TODO: should we take the
+ // calling convention into account?).
+ if (isTerminator(Inst) || isCall(Inst)) {
+ resetState();
+ return;
+ }
+
+ switch (Inst.getOpcode()) {
+ default: {
+ // Clear the state of all defined registers for instructions that we don't
+ // explicitly support.
+ auto NumDefs = Info->get(Inst.getOpcode()).getNumDefs();
+ for (unsigned I = 0; I < NumDefs; ++I) {
+ auto DefReg = Inst.getOperand(I).getReg();
+ if (isGPR(DefReg))
+ setGPRState(DefReg, std::nullopt);
+ }
+ break;
+ }
+ case RISCV::AUIPC:
+ setGPRState(Inst.getOperand(0).getReg(),
+ Addr + (Inst.getOperand(1).getImm() << 12));
+ break;
+ }
+ }
+
bool evaluateBranch(const MCInst &Inst, uint64_t Addr, uint64_t Size,
uint64_t &Target) const override {
if (isConditionalBranch(Inst)) {
@@ -140,6 +195,15 @@ class RISCVMCInstrAnalysis : public MCInstrAnalysis {
return true;
}
+ if (Inst.getOpcode() == RISCV::JALR) {
+ if (auto TargetRegState = getGPRState(Inst.getOperand(1).getReg())) {
+ Target = *TargetRegState + Inst.getOperand(2).getImm();
+ return true;
+ }
+
+ return false;
+ }
+
return false;
}
diff --git a/llvm/test/tools/llvm-objdump/ELF/RISCV/branches.s b/llvm/test/tools/llvm-objdump/ELF/RISCV/branches.s
index 5fec4e6e25a39a3..ebd86a702b70e7c 100644
--- a/llvm/test/tools/llvm-objdump/ELF/RISCV/branches.s
+++ b/llvm/test/tools/llvm-objdump/ELF/RISCV/branches.s
@@ -57,11 +57,11 @@ c.jal bar
c.j bar
# CHECK: auipc ra, 0
-# CHECK: jalr ra, 16(ra){{$}}
+# CHECK: jalr ra, 16(ra) <foo+0x58>
call .Llocal
# CHECK: auipc ra, 0
-# CHECK: jalr ra, 16(ra){{$}}
+# CHECK: jalr ra, 16(ra) <bar>
call bar
.Llocal:
diff --git a/llvm/test/tools/llvm-objdump/ELF/RISCV/multi-instr-target.s b/llvm/test/tools/llvm-objdump/ELF/RISCV/multi-instr-target.s
new file mode 100644
index 000000000000000..91b643e961fc6df
--- /dev/null
+++ b/llvm/test/tools/llvm-objdump/ELF/RISCV/multi-instr-target.s
@@ -0,0 +1,45 @@
+# RUN: llvm-mc -filetype=obj -triple riscv32 -mattr=+c < %s | \
+# RUN: llvm-objdump -d -M no-aliases --no-show-raw-insn - | \
+# RUN: FileCheck %s
+
+## Test multiple interleaved auipc/jalr pairs
+# CHECK: auipc t0, 0
+1: auipc t0, %pcrel_hi(bar)
+# CHECK: auipc t1, 0
+2: auipc t1, %pcrel_hi(bar)
+# CHECK: jalr ra, {{[0-9]+}}(t0) <bar>
+jalr %pcrel_lo(1b)(t0)
+## Target should not be printed because the call above clobbers register state
+# CHECK: jalr ra, {{[0-9]+}}(t1){{$}}
+jalr %pcrel_lo(2b)(t1)
+
+## Test that auipc+jalr with a write to the target register in between does not
+## print the target
+# CHECK: auipc t0, 0
+1: auipc t0, %pcrel_hi(bar)
+# CHECK: c.li t0, 0
+li t0, 0
+# CHECK: jalr ra, {{[0-9]+}}(t0){{$}}
+jalr %pcrel_lo(1b)(t0)
+
+## Test that auipc+jalr with a write to an unrelated register in between does
+## print the target
+# CHECK: auipc t0, 0
+1: auipc t0, %pcrel_hi(bar)
+# CHECK: c.li t1, 0
+li t1, 0
+# CHECK: jalr ra, {{[0-9]+}}(t0) <bar>
+jalr %pcrel_lo(1b)(t0)
+
+## Test that auipc+jalr with a terminator in between does not print the target
+# CHECK: auipc t0, 0
+1: auipc t0, %pcrel_hi(bar)
+# CHECK: c.j {{.*}} <bar>
+j bar
+# CHECK: jalr ra, {{[0-9]+}}(t0){{$}}
+jalr %pcrel_lo(1b)(t0)
+
+# CHECK-LABEL: <bar>:
+bar:
+# CHECK: c.nop
+nop
diff --git a/llvm/tools/llvm-objdump/llvm-objdump.cpp b/llvm/tools/llvm-objdump/llvm-objdump.cpp
index 96d74d6e2d5e865..385be9fb9257e16 100644
--- a/llvm/tools/llvm-objdump/llvm-objdump.cpp
+++ b/llvm/tools/llvm-objdump/llvm-objdump.cpp
@@ -842,7 +842,7 @@ class DisassemblerTarget {
std::unique_ptr<const MCSubtargetInfo> SubtargetInfo;
std::shared_ptr<MCContext> Context;
std::unique_ptr<MCDisassembler> DisAsm;
- std::shared_ptr<const MCInstrAnalysis> InstrAnalysis;
+ std::shared_ptr<MCInstrAnalysis> InstrAnalysis;
std::shared_ptr<MCInstPrinter> InstPrinter;
PrettyPrinter *Printer;
@@ -1265,14 +1265,19 @@ collectBBAddrMapLabels(const std::unordered_map<uint64_t, BBAddrMap> &AddrToBBAd
}
}
-static void collectLocalBranchTargets(
- ArrayRef<uint8_t> Bytes, const MCInstrAnalysis *MIA, MCDisassembler *DisAsm,
- MCInstPrinter *IP, const MCSubtargetInfo *STI, uint64_t SectionAddr,
- uint64_t Start, uint64_t End, std::unordered_map<uint64_t, std::string> &Labels) {
+static void
+collectLocalBranchTargets(ArrayRef<uint8_t> Bytes, MCInstrAnalysis *MIA,
+ MCDisassembler *DisAsm, MCInstPrinter *IP,
+ const MCSubtargetInfo *STI, uint64_t SectionAddr,
+ uint64_t Start, uint64_t End,
+ std::unordered_map<uint64_t, std::string> &Labels) {
// So far only supports PowerPC and X86.
if (!STI->getTargetTriple().isPPC() && !STI->getTargetTriple().isX86())
return;
+ if (MIA)
+ MIA->resetState();
+
Labels.clear();
unsigned LabelCount = 0;
Start += SectionAddr;
@@ -1298,6 +1303,9 @@ static void collectLocalBranchTargets(
!Labels.count(Target) &&
!(STI->getTargetTriple().isPPC() && Target == Index))
Labels[Target] = ("L" + Twine(LabelCount++)).str();
+ MIA->updateState(Inst, Index);
+ } else if (!Disassembled && MIA) {
+ MIA->resetState();
}
Index += Size;
}
@@ -1939,6 +1947,9 @@ disassembleObject(ObjectFile &Obj, const ObjectFile &DbgObj,
BBAddrMapLabels);
}
+ if (DT->InstrAnalysis)
+ DT->InstrAnalysis->resetState();
+
while (Index < End) {
// ARM and AArch64 ELF binaries can interleave data and text in the
// same section. We rely on the markers introduced to understand what
@@ -2155,6 +2166,10 @@ disassembleObject(ObjectFile &Obj, const ObjectFile &DbgObj,
if (TargetOS == &CommentStream)
*TargetOS << "\n";
}
+
+ DT->InstrAnalysis->updateState(Inst, SectionAddr + Index);
+ } else if (!Disassembled && DT->InstrAnalysis) {
+ DT->InstrAnalysis->resetState();
}
}
``````````
</details>
https://github.com/llvm/llvm-project/pull/65480
More information about the llvm-commits
mailing list