Add to the disassembler C API output reference types for

Objective-C data structures.

This is allows tools such as darwin's otool(1) that uses the
LLVM disassembler take a pointer value being loaded by
an instruction and add a comment to what it is being referenced
to make following disassembly of Objective-C programs
more readable.

For example disassembling the Mac OS X TextEdit app one
will see comments like the following:

movq    0x20684(%rip), %rsi ## Objc selector ref: standardUserDefaults
movq    0x21985(%rip), %rdi ## Objc class ref: _OBJC_CLASS_$_NSUserDefaults
movq    0x1d156(%rip), %r14 ## Objc message: +[NSUserDefaults standardUserDefaults]
leaq    0x23615(%rip), %rdx ## Objc cfstring ref: @"SelectLinePanel"
callq   0x10001386c ## Objc message: -[[%rdi super] initWithWindowNibName:]

These diffs also include putting quotes around C strings
in literal pools and uses "symbol address" in the comment
when adding a symbol name to the comment to tell these
types of references apart:

leaq	0x4f(%rip), %rax ## literal pool for: "Hello world"
movq    0x1c3ea(%rip), %rax ## literal pool symbol address: ___stack_chk_guard

Of course the easy changes are in the LLVM disassembler and
the hard work is up to the implementer of the SymbolLookUp()
call back.

rdar://10602439

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193833 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm-c/Disassembler.h b/include/llvm-c/Disassembler.h
index 5e0b6183bbc317e6a878f3f36cab777c5dca9736..79bcfcdab9e86877e950a256e4b4d6e1e035b811 100644 (file)
--- a/include/llvm-c/Disassembler.h
+++ b/include/llvm-c/Disassembler.h
@@ -130,6 +130,17 @@ typedef const char *(*LLVMSymbolLookupCallback)(void *DisInfo,
 /* The output reference is to a cstring address in a literal pool. */
 #define LLVMDisassembler_ReferenceType_Out_LitPool_CstrAddr 3
 
+/* The output reference is to a Objective-C CoreFoundation string. */
+#define LLVMDisassembler_ReferenceType_Out_Objc_CFString_Ref 4
+/* The output reference is to a Objective-C message. */
+#define LLVMDisassembler_ReferenceType_Out_Objc_Message 5
+/* The output reference is to a Objective-C message ref. */
+#define LLVMDisassembler_ReferenceType_Out_Objc_Message_Ref 6
+/* The output reference is to a Objective-C selector ref. */
+#define LLVMDisassembler_ReferenceType_Out_Objc_Selector_Ref 7
+/* The output reference is to a Objective-C class ref. */
+#define LLVMDisassembler_ReferenceType_Out_Objc_Class_Ref 8
+
 #ifdef __cplusplus
 extern "C" {
 #endif /* !defined(__cplusplus) */

diff --git a/lib/MC/MCExternalSymbolizer.cpp b/lib/MC/MCExternalSymbolizer.cpp
index 47ef6c41fed357d5735a34323025651e5f86b5fc..ca368b27e1958426f5f7db23f632d1fda1bcfaf7 100644 (file)
--- a/lib/MC/MCExternalSymbolizer.cpp
+++ b/lib/MC/MCExternalSymbolizer.cpp
@@ -63,6 +63,8 @@ bool MCExternalSymbolizer::tryAddingSymbolicOperand(MCInst &MI,
     }
     if(ReferenceType == LLVMDisassembler_ReferenceType_Out_SymbolStub)
       cStream << "symbol stub for: " << ReferenceName;
+    else if(ReferenceType == LLVMDisassembler_ReferenceType_Out_Objc_Message)
+      cStream << "Objc message: " << ReferenceName;
     if (!Name && !IsBranch)
       return false;
   }
@@ -132,6 +134,8 @@ bool MCExternalSymbolizer::tryAddingSymbolicOperand(MCInst &MI,
 // literal pool's entry if the referenced address is that of a symbol. Or it
 // will return a pointer to a literal 'C' string if the referenced address of
 // the literal pool's entry is an address into a section with C string literals.
+// Or if the reference is to an Objective-C data structure it will return a
+// specific reference type for it and a string.
 void MCExternalSymbolizer::tryAddingPcLoadReferenceComment(raw_ostream &cStream,
                                                            int64_t Value,
                                                            uint64_t Address) {
@@ -139,9 +143,26 @@ void MCExternalSymbolizer::tryAddingPcLoadReferenceComment(raw_ostream &cStream,
     uint64_t ReferenceType = LLVMDisassembler_ReferenceType_In_PCrel_Load;
     const char *ReferenceName;
     (void)SymbolLookUp(DisInfo, Value, &ReferenceType, Address, &ReferenceName);
-    if(ReferenceType == LLVMDisassembler_ReferenceType_Out_LitPool_SymAddr ||
-       ReferenceType == LLVMDisassembler_ReferenceType_Out_LitPool_CstrAddr)
-      cStream << "literal pool for: " << ReferenceName;
+    if(ReferenceType == LLVMDisassembler_ReferenceType_Out_LitPool_SymAddr)
+      cStream << "literal pool symbol address: " << ReferenceName;
+    else if(ReferenceType ==
+            LLVMDisassembler_ReferenceType_Out_LitPool_CstrAddr)
+      cStream << "literal pool for: \"" << ReferenceName << "\"";
+    else if(ReferenceType ==
+            LLVMDisassembler_ReferenceType_Out_Objc_CFString_Ref)
+      cStream << "Objc cfstring ref: @\"" << ReferenceName << "\"";
+    else if(ReferenceType ==
+            LLVMDisassembler_ReferenceType_Out_Objc_Message)
+      cStream << "Objc message: " << ReferenceName;
+    else if(ReferenceType ==
+            LLVMDisassembler_ReferenceType_Out_Objc_Message_Ref)
+      cStream << "Objc message ref: " << ReferenceName;
+    else if(ReferenceType ==
+            LLVMDisassembler_ReferenceType_Out_Objc_Selector_Ref)
+      cStream << "Objc selector ref: " << ReferenceName;
+    else if(ReferenceType ==
+            LLVMDisassembler_ReferenceType_Out_Objc_Class_Ref)
+      cStream << "Objc class ref: " << ReferenceName;
   }
 }