[llvm-objdump] Print comments for the disassembled code

LLVM disassembler can generate comments for disassembled instructions.
The patch enables printing these comments for 'llvm-objdump -d'.

Differential Revision: https://reviews.llvm.org/D104699

Author: igorkudrin

llvm/test/tools/llvm-objdump/ELF/AArch64/disassemble-align.s

@@ -3,10 +3,12 @@
 
 ## Use '|' to show where the tabs line up.
 #       CHECK:0000000000000000 <$x.0>:
-#  CHECK-NEXT:       0: 62 10 00 91  |add|x2, x3, #4
+#  CHECK-NEXT:       0: 62 10 00 91  |add|x2, x3, #4              // =4
+#  CHECK-NEXT:       4: 1f 20 03 d5  |nop
 # CHECK-EMPTY:
-#  CHECK-NEXT:0000000000000004 <$d.1>:
-#  CHECK-NEXT:       4:|ff ff 00 00|.word|0x0000ffff
+#  CHECK-NEXT:0000000000000008 <$d.1>:
+#  CHECK-NEXT:       8:|ff ff 00 00|.word|0x0000ffff
 
   add x2, x3, #4
+  nop
   .word 0xffff

llvm/test/tools/llvm-objdump/ELF/AArch64/disassemble-print-comments.s

@@ -0,0 +1,13 @@
+## Check that 'llvm-objdump -d' prints comments generated by the disassembler.
+
+# RUN: llvm-mc -filetype=obj -triple=aarch64 -mattr=+sve %s -o %t
+# RUN: llvm-objdump -d --mattr=+sve --no-show-raw-insn %t | FileCheck %s
+
+# CHECK:      0000000000000000 <foo>:
+# CHECK-NEXT:        0:   add x0, x2, #2, lsl #12    // =8192
+# CHECK-NEXT:        4:   add z31.d, z31.d, #65280   // =0xff00
+
+    .text
+foo:
+    add x0, x2, 8192
+    add z31.d, z31.d, #65280

llvm/test/tools/llvm-objdump/X86/disassemble-align.s

@@ -1,26 +1,27 @@
 # RUN: llvm-mc -filetype=obj -triple=x86_64 %s -o %t
 
 # Use '|' to show where the tabs line up.
-# RUN: llvm-objdump -d --print-imm-hex %t | tr '\t' '|' | FileCheck --strict-whitespace %s
+# RUN: llvm-objdump -d --print-imm-hex %t | tr '\t' '|' | \
+# RUN:   FileCheck --match-full-lines --strict-whitespace %s
 
 # RUN: llvm-objdump -d --print-imm-hex --no-show-raw-insn %t | tr '\t' '|' | \
-# RUN:   FileCheck -check-prefix=NORAW -strict-whitespace %s
+# RUN:   FileCheck -check-prefix=NORAW --match-full-lines -strict-whitespace %s
 
 # Instructions are expected to be aligned if the instruction in hex is not too long.
 
-# CHECK:       0: c3                           |retq
-# CHECK-NEXT:  1: 48 8b 05 56 34 12 00         |movq|0x123456(%rip), %rax
-# CHECK-NEXT:  8: 48 b8 54 55 55 55 55 55 55 55|movabsq|$0x5555555555555554, %rax
-# CHECK-NEXT: 12: 8f ea 00 12 4c 02 40 00 00 00 00     |lwpval|$0x0, 0x40(%rdx,%rax), %r15d
-# CHECK-NEXT: 1d: 8f ea 00 12 04 25 f0 1c f0 1c 00 00 00 00    |lwpins|$0x0, 0x1cf01cf0, %r15d
-# CHECK-NEXT: 2b: ff ff                        |<unknown>
+#      CHECK:       0: c3                           |retq
+# CHECK-NEXT:       1: 48 8b 05 56 34 12 00         |movq|0x123456(%rip), %rax  # 12345e <.text+0x12345e>
+# CHECK-NEXT:       8: 48 b8 54 55 55 55 55 55 55 55|movabsq|$0x5555555555555554, %rax # imm = 0x5555555555555554
+# CHECK-NEXT:      12: 8f ea 00 12 4c 02 40 00 00 00 00     |lwpval|$0x0, 0x40(%rdx,%rax), %r15d
+# CHECK-NEXT:      1d: 8f ea 00 12 04 25 f0 1c f0 1c 00 00 00 00    |lwpins|$0x0, 0x1cf01cf0, %r15d
+# CHECK-NEXT:      2b: ff ff                        |<unknown>
 
-# NORAW:       0:      |retq
-# NORAW-NEXT:  1:      |movq|0x123456(%rip), %rax
-# NORAW-NEXT:  8:      |movabsq|$0x5555555555555554, %rax
-# NORAW-NEXT: 12:      |lwpval|$0x0, 0x40(%rdx,%rax), %r15d
-# NORAW-NEXT: 1d:      |lwpins|$0x0, 0x1cf01cf0, %r15d
-# NORAW-NEXT: 2b:      |<unknown>
+#      NORAW:       0:      |retq
+# NORAW-NEXT:       1:      |movq|0x123456(%rip), %rax  # 12345e <.text+0x12345e>
+# NORAW-NEXT:       8:      |movabsq|$0x5555555555555554, %rax # imm = 0x5555555555555554
+# NORAW-NEXT:      12:      |lwpval|$0x0, 0x40(%rdx,%rax), %r15d
+# NORAW-NEXT:      1d:      |lwpins|$0x0, 0x1cf01cf0, %r15d
+# NORAW-NEXT:      2b:      |<unknown>
 
 .text
   retq

llvm/test/tools/llvm-objdump/X86/disassemble-print-comments.s

@@ -0,0 +1,13 @@
+## Check that 'llvm-objdump -d' prints comments generated by the disassembler.
+
+# RUN: llvm-mc -filetype=obj -triple=x86_64 %s -o %t
+# RUN: llvm-objdump -d --no-show-raw-insn %t | FileCheck %s
+
+# CHECK:      0000000000000000 <foo>:
+# CHECK-NEXT:        0:   nop
+# CHECK-NEXT:        1:   cmpl $305419896, %eax   # imm = 0x12345678
+
+    .text
+foo:
+    nop
+    cmpl $0x12345678, %eax

llvm/tools/llvm-objdump/llvm-objdump.cpp

@@ -1039,6 +1039,29 @@ static StringRef getSegmentName(const MachOObjectFile *MachO,
   return "";
 }
 
+static void emitPostInstructionInfo(formatted_raw_ostream &FOS,
+                                    const MCAsmInfo &MAI,
+                                    const MCSubtargetInfo &STI,
+                                    StringRef Comments,
+                                    LiveVariablePrinter &LVP) {
+  do {
+    if (!Comments.empty()) {
+      // Emit a line of comments.
+      StringRef Comment;
+      std::tie(Comment, Comments) = Comments.split('\n');
+      // MAI.getCommentColumn() assumes that instructions are printed at the
+      // position of 8, while getInstStartColumn() returns the actual position.
+      unsigned CommentColumn =
+          MAI.getCommentColumn() - 8 + getInstStartColumn(STI);
+      FOS.PadToColumn(CommentColumn);
+      FOS << MAI.getCommentString() << ' ' << Comment;
+    }
+    LVP.printAfterInst(FOS);
+    FOS << '\n';
+  } while (!Comments.empty());
+  FOS.flush();
+}
+
 static void disassembleObject(const Target *TheTarget, const ObjectFile *Obj,
                               MCContext &Ctx, MCDisassembler *PrimaryDisAsm,
                               MCDisassembler *SecondaryDisAsm,
@@ -1396,12 +1419,14 @@ static void disassembleObject(const Target *TheTarget, const ObjectFile *Obj,
           LVP.update({Index, Section.getIndex()},
                      {Index + Size, Section.getIndex()}, Index + Size != End);
 
+          IP->setCommentStream(CommentStream);
+
           PIP.printInst(
               *IP, Disassembled ? &Inst : nullptr, Bytes.slice(Index, Size),
               {SectionAddr + Index + VMAAdjustment, Section.getIndex()}, FOS,
               "", *STI, &SP, Obj->getFileName(), &Rels, LVP);
-          FOS << CommentStream.str();
-          Comments.clear();
+
+          IP->setCommentStream(llvm::nulls());
 
           // If disassembly has failed, avoid analysing invalid/incomplete
           // instruction information. Otherwise, try to resolve the target
@@ -1498,8 +1523,10 @@ static void disassembleObject(const Target *TheTarget, const ObjectFile *Obj,
           }
         }
 
-        LVP.printAfterInst(FOS);
-        FOS << "\n";
+        assert(Ctx.getAsmInfo());
+        emitPostInstructionInfo(FOS, *Ctx.getAsmInfo(), *STI,
+                                CommentStream.str(), LVP);
+        Comments.clear();
 
         // Hexagon does this in pretty printer
         if (Obj->getArch() != Triple::hexagon) {