From c8a927696cf4e39a813be4c42fe5b48bfbddcc76 Mon Sep 17 00:00:00 2001
From: Maksim Panchenko <maks@fb.com>
Date: Wed, 3 Apr 2019 22:31:12 -0700
Subject: [PATCH] [BOLT] Detect internal references into a middle of
 instruction

Summary:
Some instructions in assembly-written functions could reference 8-byte
constants from another instructions using 4-byte offsets, presumably to
save a couple of bytes.

Detect such cases, and skip processing such functions until we teach
BOLT how to handle references into a middle of instruction.

(cherry picked from FBD14768212)
---
 bolt/src/BinaryFunction.cpp | 25 ++++++++++++++++++++++++-
 bolt/src/BinaryFunction.h   |  3 +++
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/bolt/src/BinaryFunction.cpp b/bolt/src/BinaryFunction.cpp
index 37c4536b34b7..711d7282e30d 100644
--- a/bolt/src/BinaryFunction.cpp
+++ b/bolt/src/BinaryFunction.cpp
@@ -1464,9 +1464,32 @@ add_instruction:
 
   updateState(State::Disassembled);
 
+  postProcessEntryPoints();
+
   postProcessJumpTables();
 }
 
+void BinaryFunction::postProcessEntryPoints() {
+  for (auto Offset : EntryOffsets) {
+    if (!getInstructionAtOffset(Offset)) {
+      // On AArch64 there are legitimate reasons to have references past the
+      // end of the function, e.g. jump tables.
+      if (BC.isAArch64() && Offset == getSize()) {
+        continue;
+      }
+
+      errs() << "BOLT-WARNING: reference in the middle of instruction "
+                "detected in function " << *this
+             << " at offset 0x" << Twine::utohexstr(Offset) << '\n';
+      if (BC.HasRelocations) {
+        errs() << "BOLT-ERROR: unable to keep processing in relocation mode\n";
+        exit(1);
+      }
+      setSimple(false);
+    }
+  }
+}
+
 void BinaryFunction::postProcessJumpTables() {
   // Create labels for all entries.
   for (auto &JTI : JumpTables) {
@@ -1683,7 +1706,7 @@ bool BinaryFunction::buildCFG() {
     return false;
   }
 
-  if (!(CurrentState == State::Disassembled))
+  if (CurrentState != State::Disassembled)
     return false;
 
   assert(BasicBlocks.empty() && "basic block list should be empty");
diff --git a/bolt/src/BinaryFunction.h b/bolt/src/BinaryFunction.h
index be33aab8c50f..5d117e1d14d9 100644
--- a/bolt/src/BinaryFunction.h
+++ b/bolt/src/BinaryFunction.h
@@ -1960,6 +1960,9 @@ public:
   /// Returns false if disassembly failed.
   void disassemble(ArrayRef<uint8_t> FunctionData);
 
+  /// Validate entry points.
+  void postProcessEntryPoints();
+
   /// Post-processing for jump tables after disassembly. Since their
   /// boundaries are not known until all call sites are seen, we need this
   /// extra pass to perform any final adjustments.