From 0b8b771e9f2f251460a6f200c45efe9d55640d60 Mon Sep 17 00:00:00 2001
From: Benjamin Kramer <benny.kra@googlemail.com>
Date: Mon, 19 Sep 2011 17:56:04 +0000
Subject: Add a MachO-specific "mode" to llvm-objdump, that, if enabled,
 gathers additional information that are only available on MachO.

- It can take FunctionStarts from a binary to find entry points more accurately.
- Symbol offsets in executables are correct now.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@140028 91177308-0d34-0410-b5e6-96231b3b80d8
---
 tools/llvm-objdump/MCFunction.cpp | 91 ++++++++++++++++++++++++++-------------
 1 file changed, 61 insertions(+), 30 deletions(-)

(limited to 'tools/llvm-objdump/MCFunction.cpp')

diff --git a/tools/llvm-objdump/MCFunction.cpp b/tools/llvm-objdump/MCFunction.cpp
index 5f1649694d..03390c2b58 100644
--- a/tools/llvm-objdump/MCFunction.cpp
+++ b/tools/llvm-objdump/MCFunction.cpp
@@ -30,48 +30,77 @@ MCFunction
 MCFunction::createFunctionFromMC(StringRef Name, const MCDisassembler *DisAsm,
                                  const MemoryObject &Region, uint64_t Start,
                                  uint64_t End, const MCInstrAnalysis *Ana,
-                                 raw_ostream &DebugOut) {
+                                 raw_ostream &DebugOut,
+                                 SmallVectorImpl<uint64_t> &Calls) {
+  std::vector<MCDecodedInst> Instructions;
   std::set<uint64_t> Splits;
   Splits.insert(Start);
-  std::vector<MCDecodedInst> Instructions;
   uint64_t Size;
 
+  MCFunction f(Name);
+
+  {
+  DenseSet<uint64_t> VisitedInsts;
+  SmallVector<uint64_t, 16> WorkList;
+  WorkList.push_back(Start);
   // Disassemble code and gather basic block split points.
-  for (uint64_t Index = Start; Index < End; Index += Size) {
-    MCInst Inst;
+  while (!WorkList.empty()) {
+    uint64_t Index = WorkList.pop_back_val();
+    if (VisitedInsts.find(Index) != VisitedInsts.end())
+      continue;
 
-    if (DisAsm->getInstruction(Inst, Size, Region, Index, DebugOut, nulls())) {
-      if (Ana->isBranch(Inst)) {
-        uint64_t targ = Ana->evaluateBranch(Inst, Index, Size);
-        // FIXME: Distinguish relocations from nop jumps.
-        if (targ != -1ULL && (targ == Index+Size || targ >= End)) {
+    for (;Index < End; Index += Size) {
+      MCInst Inst;
+
+      if (DisAsm->getInstruction(Inst, Size, Region, Index, DebugOut, nulls())){
+        if (Ana->isBranch(Inst)) {
+          uint64_t targ = Ana->evaluateBranch(Inst, Index, Size);
+          if (targ != -1ULL && targ == Index+Size) {
+            Instructions.push_back(MCDecodedInst(Index, Size, Inst));
+            VisitedInsts.insert(Index);
+            continue;
+          }
+          if (targ != -1ULL) {
+            Splits.insert(targ);
+            WorkList.push_back(targ);
+            WorkList.push_back(Index+Size);
+          }
+          Splits.insert(Index+Size);
+          Instructions.push_back(MCDecodedInst(Index, Size, Inst));
+          VisitedInsts.insert(Index);
+          break;
+        } else if (Ana->isReturn(Inst)) {
+          Splits.insert(Index+Size);
           Instructions.push_back(MCDecodedInst(Index, Size, Inst));
-          continue; // Skip branches that leave the function.
+          VisitedInsts.insert(Index);
+          break;
+        } else if (Ana->isCall(Inst)) {
+          uint64_t targ = Ana->evaluateBranch(Inst, Index, Size);
+          if (targ != -1ULL && targ != Index+Size) {
+            Calls.push_back(targ);
+          }
         }
-        if (targ != -1ULL)
-          Splits.insert(targ);
-        Splits.insert(Index+Size);
-      } else if (Ana->isReturn(Inst)) {
-        Splits.insert(Index+Size);
-      }
 
-      Instructions.push_back(MCDecodedInst(Index, Size, Inst));
-    } else {
-      errs() << "warning: invalid instruction encoding\n";
-      if (Size == 0)
-        Size = 1; // skip illegible bytes
+        Instructions.push_back(MCDecodedInst(Index, Size, Inst));
+        VisitedInsts.insert(Index);
+      } else {
+        VisitedInsts.insert(Index);
+        errs().write_hex(Index) << ": warning: invalid instruction encoding\n";
+        if (Size == 0)
+          Size = 1; // skip illegible bytes
+      }
     }
-
+  }
   }
 
-  MCFunction f(Name);
+  std::sort(Instructions.begin(), Instructions.end());
 
-  // Create basic blocks.
+   // Create basic blocks.
   unsigned ii = 0, ie = Instructions.size();
   for (std::set<uint64_t>::iterator spi = Splits.begin(),
-       spe = Splits.end(); spi != spe; ++spi) {
+       spe = llvm::prior(Splits.end()); spi != spe; ++spi) {
     MCBasicBlock BB;
-    uint64_t BlockEnd = llvm::next(spi) == spe ? End : *llvm::next(spi);
+    uint64_t BlockEnd = *llvm::next(spi);
     // Add instructions to the BB.
     for (; ii != ie; ++ii) {
       if (Instructions[ii].Address < *spi ||
@@ -82,6 +111,8 @@ MCFunction::createFunctionFromMC(StringRef Name, const MCDisassembler *DisAsm,
     f.addBlock(*spi, BB);
   }
 
+  std::sort(f.Blocks.begin(), f.Blocks.end());
+
   // Calculate successors of each block.
   for (MCFunction::iterator i = f.begin(), e = f.end(); i != e; ++i) {
     MCBasicBlock &BB = i->second;
@@ -94,16 +125,16 @@ MCFunction::createFunctionFromMC(StringRef Name, const MCDisassembler *DisAsm,
         // Indirect branch. Bail and add all blocks of the function as a
         // successor.
         for (MCFunction::iterator i = f.begin(), e = f.end(); i != e; ++i)
-          BB.addSucc(&i->second);
+          BB.addSucc(i->first);
       } else if (targ != Inst.Address+Inst.Size)
-        BB.addSucc(&f.getBlockAtAddress(targ));
+        BB.addSucc(targ);
       // Conditional branches can also fall through to the next block.
       if (Ana->isConditionalBranch(Inst.Inst) && llvm::next(i) != e)
-        BB.addSucc(&llvm::next(i)->second);
+        BB.addSucc(llvm::next(i)->first);
     } else {
       // No branch. Fall through to the next block.
       if (!Ana->isReturn(Inst.Inst) && llvm::next(i) != e)
-        BB.addSucc(&llvm::next(i)->second);
+        BB.addSucc(llvm::next(i)->first);
     }
   }
 
-- 
cgit v1.2.3