From 44ecaabc0729fb75fcfec1d46a6bef6bc7c9e1e1 Mon Sep 17 00:00:00 2001
From: Eli Friedman <efriedma@quicinc.com>
Date: Wed, 13 May 2020 11:44:03 -0700
Subject: [BitcodeReader] datalayout must be specified before it is queried.

This isn't really a new invariant; it effectively already existed due to
existing DataLayout queries.  But this makes it explicit.

This is technically not backward-compatible with the existing bitcode
reader, but it's backward-compatible with the output of the bitcode
writer, which is what matters in practice.

No testcase because I don't know a good way to write one: there are no
existing tools that can generate a bitcode file that would trigger the
error.

Split off from D78403.

Differential Revision: https://reviews.llvm.org/D79900
---
 llvm/lib/Bitcode/Reader/BitcodeReader.cpp | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

(limited to 'llvm/lib/Bitcode/Reader/BitcodeReader.cpp')

diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index 6e9ff6e..9e5f0e0 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -3428,6 +3428,22 @@ Error BitcodeReader::parseModule(uint64_t ResumeBit,
 
   SmallVector<uint64_t, 64> Record;
 
+  // Parts of bitcode parsing depend on the datalayout.  Make sure we
+  // finalize the datalayout before we run any of that code.
+  bool ResolvedDataLayout = false;
+  auto ResolveDataLayout = [&] {
+    if (ResolvedDataLayout)
+      return;
+
+    // datalayout and triple can't be parsed after this point.
+    ResolvedDataLayout = true;
+
+    // Upgrade data layout string.
+    std::string DL = llvm::UpgradeDataLayoutString(
+        TheModule->getDataLayoutStr(), TheModule->getTargetTriple());
+    TheModule->setDataLayout(DL);
+  };
+
   // Read all the records for this module.
   while (true) {
     Expected<llvm::BitstreamEntry> MaybeEntry = Stream.advance();
@@ -3439,6 +3455,7 @@ Error BitcodeReader::parseModule(uint64_t ResumeBit,
     case BitstreamEntry::Error:
       return error("Malformed block");
     case BitstreamEntry::EndBlock:
+      ResolveDataLayout();
       return globalCleanup();
 
     case BitstreamEntry::SubBlock:
@@ -3503,6 +3520,8 @@ Error BitcodeReader::parseModule(uint64_t ResumeBit,
           return Err;
         break;
       case bitc::FUNCTION_BLOCK_ID:
+        ResolveDataLayout();
+
         // If this is the first function body we've seen, reverse the
         // FunctionsWithBodies list.
         if (!SeenFirstFunctionBody) {
@@ -3589,6 +3608,8 @@ Error BitcodeReader::parseModule(uint64_t ResumeBit,
       break;
     }
     case bitc::MODULE_CODE_TRIPLE: {  // TRIPLE: [strchr x N]
+      if (ResolvedDataLayout)
+        return error("target triple too late in module");
       std::string S;
       if (convertToString(Record, 0, S))
         return error("Invalid record");
@@ -3596,6 +3617,8 @@ Error BitcodeReader::parseModule(uint64_t ResumeBit,
       break;
     }
     case bitc::MODULE_CODE_DATALAYOUT: {  // DATALAYOUT: [strchr x N]
+      if (ResolvedDataLayout)
+        return error("datalayout too late in module");
       std::string S;
       if (convertToString(Record, 0, S))
         return error("Invalid record");
@@ -3640,6 +3663,7 @@ Error BitcodeReader::parseModule(uint64_t ResumeBit,
         return Err;
       break;
     case bitc::MODULE_CODE_FUNCTION:
+      ResolveDataLayout();
       if (Error Err = parseFunctionRecord(Record))
         return Err;
       break;
@@ -3667,11 +3691,6 @@ Error BitcodeReader::parseModule(uint64_t ResumeBit,
       break;
     }
     Record.clear();
-
-    // Upgrade data layout string.
-    std::string DL = llvm::UpgradeDataLayoutString(
-        TheModule->getDataLayoutStr(), TheModule->getTargetTriple());
-    TheModule->setDataLayout(DL);
   }
 }
 
-- 
cgit v1.1