[llvm-branch-commits] [llvm-objdump] Support --symbolize-operand on AArch64 (PR #145009)

[via llvm-branch-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-binary-utilities

Author: Alexis Engelke (aengelke)

<details>
<summary>Changes</summary>

Similar to the existing implementations for X86 and PPC, support
symbolizing branch targets for AArch64. Do not omit the address for ADRP
as the target is typically not at an intended location.


---
Full diff: https://github.com/llvm/llvm-project/pull/145009.diff


3 Files Affected:

- (modified) llvm/lib/Target/AArch64/MCTargetDesc/AArch64InstPrinter.cpp (+10) 
- (added) llvm/test/tools/llvm-objdump/AArch64/elf-disassemble-symbololize-operands.yaml (+42) 
- (modified) llvm/tools/llvm-objdump/llvm-objdump.cpp (+2-1) 


``````````diff
diff --git a/llvm/lib/Target/AArch64/MCTargetDesc/AArch64InstPrinter.cpp b/llvm/lib/Target/AArch64/MCTargetDesc/AArch64InstPrinter.cpp
index bbe83821eca8e..fa7610db82bfb 100644
--- a/llvm/lib/Target/AArch64/MCTargetDesc/AArch64InstPrinter.cpp
+++ b/llvm/lib/Target/AArch64/MCTargetDesc/AArch64InstPrinter.cpp
@@ -1784,6 +1784,10 @@ void AArch64InstPrinter::printAlignedLabel(const MCInst *MI, uint64_t Address,
                                            unsigned OpNum,
                                            const MCSubtargetInfo &STI,
                                            raw_ostream &O) {
+  // Do not print the numberic target address when symbolizing.
+  if (SymbolizeOperands)
+    return;
+
   const MCOperand &Op = MI->getOperand(OpNum);
 
   // If the label has already been resolved to an immediate offset (say, when
@@ -1813,6 +1817,12 @@ void AArch64InstPrinter::printAdrAdrpLabel(const MCInst *MI, uint64_t Address,
                                            unsigned OpNum,
                                            const MCSubtargetInfo &STI,
                                            raw_ostream &O) {
+  // Do not print the numberic target address when symbolizing.
+  // However, do print for ADRP, as this is typically used together with an ADD
+  // or an immediate-offset ldr/str and the label is likely at the wrong point.
+  if (SymbolizeOperands && MI->getOpcode() != AArch64::ADRP)
+    return;
+
   const MCOperand &Op = MI->getOperand(OpNum);
 
   // If the label has already been resolved to an immediate offset (say, when
diff --git a/llvm/test/tools/llvm-objdump/AArch64/elf-disassemble-symbololize-operands.yaml b/llvm/test/tools/llvm-objdump/AArch64/elf-disassemble-symbololize-operands.yaml
new file mode 100644
index 0000000000000..3f3c6f33e620f
--- /dev/null
+++ b/llvm/test/tools/llvm-objdump/AArch64/elf-disassemble-symbololize-operands.yaml
@@ -0,0 +1,42 @@
+# RUN: yaml2obj %s -o %t
+# RUN: llvm-objdump %t -d --symbolize-operands --no-show-raw-insn --no-leading-addr | \
+# RUN:   FileCheck %s --match-full-lines
+# RUN: llvm-objdump %t -d --symbolize-operands --no-show-raw-insn --no-leading-addr --adjust-vma=0x2000 | \
+# RUN:   FileCheck %s --match-full-lines
+
+## Expect to find the branch labels and global variable name.
+# CHECK:      <_start>:
+# CHECK-NEXT:   ldr x0, <symbol>
+# CHECK-NEXT: <L0>:
+# CHECK-NEXT:   adrp x1, 0x{{[68]}}000 <symbol+0xff4>
+# CHECK-NEXT:   adr x2, <symbol>
+# CHECK-NEXT:   cmp x1, x2
+# CHECK-NEXT:   b.eq <L1>
+# CHECK-NEXT:   b <L0>
+# CHECK-NEXT: <L1>:
+# CHECK-NEXT:   cbz x2, <L0>
+# CHECK-NEXT:   ret
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_EXEC
+  Machine: EM_AARCH64
+Sections:
+  - Name:    .text
+    Type:    SHT_PROGBITS
+    Address: 0x4000
+    Flags:   [SHF_ALLOC, SHF_EXECINSTR]
+    Content: '60800058010000d0228000103f0002eb40000054fcffff1762ffffb4c0035fd6'
+  - Name:    .data
+    Type:    SHT_PROGBITS
+    Flags:   [SHF_ALLOC, SHF_WRITE]
+    Address: 0x5000
+Symbols:
+  - Name:    _start
+    Section: .text
+    Value:   0x4000
+  - Name:    symbol
+    Section: .data
+    Value:   0x500c
diff --git a/llvm/tools/llvm-objdump/llvm-objdump.cpp b/llvm/tools/llvm-objdump/llvm-objdump.cpp
index 5ecb33375943f..c5967cd090eec 100644
--- a/llvm/tools/llvm-objdump/llvm-objdump.cpp
+++ b/llvm/tools/llvm-objdump/llvm-objdump.cpp
@@ -1495,8 +1495,9 @@ collectLocalBranchTargets(ArrayRef<uint8_t> Bytes, MCInstrAnalysis *MIA,
   // Supported by certain targets.
   const bool isPPC = STI->getTargetTriple().isPPC();
   const bool isX86 = STI->getTargetTriple().isX86();
+  const bool isAArch64 = STI->getTargetTriple().isAArch64();
   const bool isBPF = STI->getTargetTriple().isBPF();
-  if (!isPPC && !isX86 && !isBPF)
+  if (!isPPC && !isX86 && !isAArch64 && !isBPF)
     return;
 
   if (MIA)

``````````

</details>


https://github.com/llvm/llvm-project/pull/145009