[AMDGPU] llvm-objdump: Minimal HSA Code Object disassembler support.

Reenable reverted r265550 with endianness issue fixed. Variables of
endian-aware types such as ulittle32_t should be explicitly casted
to their natural equivalent types before passing it as vararg to
printf like functions (format in my case). Added lit config file
depending on AMDGPU target as the testcase uses assembler.

Differential revision: http://reviews.llvm.org/D16998

llvm-svn: 265645

1 files changed, 43 insertions, 0 deletions

diff --git a/llvm/tools/llvm-objdump/llvm-objdump.cpp b/llvm/tools/llvm-objdump/llvm-objdump.cpp
index 38de13be6fc..6c26b4516b8 100644
--- a/llvm/tools/llvm-objdump/llvm-objdump.cpp
+++ b/llvm/tools/llvm-objdump/llvm-objdump.cpp
@@ -395,12 +395,43 @@ public:
   }
 };
 HexagonPrettyPrinter HexagonPrettyPrinterInst;
+
+class AMDGCNPrettyPrinter : public PrettyPrinter {
+public:
+  void printInst(MCInstPrinter &IP,
+                 const MCInst *MI,
+                 ArrayRef<uint8_t> Bytes,
+                 uint64_t Address,
+                 raw_ostream &OS,
+                 StringRef Annot,
+                 MCSubtargetInfo const &STI) override {
+    SmallString<40> InstStr;
+    raw_svector_ostream IS(InstStr);
+
+    IP.printInst(MI, IS, "", STI);
+
+    OS << left_justify(IS.str(), 60) << format("// %012X: ", Address);
+    typedef support::ulittle32_t U32;
+    for (auto D : makeArrayRef(reinterpret_cast<const U32*>(Bytes.data()),
+                               Bytes.size() / sizeof(U32)))
+      // D should be explicitly casted to uint32_t here as it is passed
+      // by format to snprintf as vararg.
+      OS << format("%08X ", static_cast<uint32_t>(D));
+
+    if (!Annot.empty())
+      OS << "// " << Annot;
+  }
+};
+AMDGCNPrettyPrinter AMDGCNPrettyPrinterInst;
+
 PrettyPrinter &selectPrettyPrinter(Triple const &Triple) {
   switch(Triple.getArch()) {
   default:
     return PrettyPrinterInst;
   case Triple::hexagon:
     return HexagonPrettyPrinterInst;
+  case Triple::amdgcn:
+    return AMDGCNPrettyPrinterInst;
   }
 }
 }
@@ -1057,6 +1088,18 @@ static void DisassembleObject(const ObjectFile *Obj, bool InlineRelocs) {
       if (Start >= End)
         continue;
 
+      if (Obj->isELF() && Obj->getArch() == Triple::amdgcn) {
+        // make size 4 bytes folded
+        End = Start + ((End - Start) & ~0x3ull);
+        Start += 256; // add sizeof(amd_kernel_code_t)
+        // cut trailing zeroes - up to 256 bytes (align)
+        const uint64_t EndAlign = 256;
+        const auto Limit = End - (std::min)(EndAlign, End - Start);
+        while (End > Limit &&
+          *reinterpret_cast<const support::ulittle32_t*>(&Bytes[End - 4]) == 0)
+          End -= 4;
+      }
+
       outs() << '\n' << Symbols[si].second << ":\n";
 
 #ifndef NDEBUG