CodeGen support for x86_64 SEH catch handlers in LLVM

This adds handling for ExceptionHandling::MSVC, used by the
x86_64-pc-windows-msvc triple. It assumes that filter functions have
already been outlined in either the frontend or the backend. Filter
functions are used in place of the landingpad catch clause type info
operands. In catch clause order, the first filter to return true will
catch the exception.

The C specific handler table expects the landing pad to be split into
one block per handler, but LLVM IR uses a single landing pad for all
possible unwind actions. This patch papers over the mismatch by
synthesizing single instruction BBs for every catch clause to fill in
the EH selector that the landing pad block expects.

Missing functionality:
- Accessing data in the parent frame from outlined filters
- Cleanups (from __finally) are unsupported, as they will require
  outlining and parent frame access
- Filter clauses are unsupported, as there's no clear analogue in SEH

In other words, this is the minimal set of changes needed to write IR to
catch arbitrary exceptions and resume normal execution.

Reviewers: majnemer

Differential Revision: http://reviews.llvm.org/D6300

llvm-svn: 225904

4 files changed, 173 insertions, 12 deletions

diff --git a/llvm/lib/CodeGen/AsmPrinter/EHStreamer.cpp b/llvm/lib/CodeGen/AsmPrinter/EHStreamer.cpp
index f112120c1ab..1bc86f6c222 100644
--- a/llvm/lib/CodeGen/AsmPrinter/EHStreamer.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/EHStreamer.cpp
@@ -121,7 +121,8 @@ computeActionsTable(const SmallVectorImpl<const LandingPadInfo*> &LandingPads,
       for (unsigned J = NumShared, M = TypeIds.size(); J != M; ++J) {
         int TypeID = TypeIds[J];
         assert(-1 - TypeID < (int)FilterOffsets.size() && "Unknown filter id!");
-        int ValueForTypeID = TypeID < 0 ? FilterOffsets[-1 - TypeID] : TypeID;
+        int ValueForTypeID =
+            isFilterEHSelector(TypeID) ? FilterOffsets[-1 - TypeID] : TypeID;
         unsigned SizeTypeID = getSLEB128Size(ValueForTypeID);
 
         int NextAction = SizeAction ? -(SizeAction + SizeTypeID) : 0;
@@ -269,14 +270,14 @@ computeCallSiteTable(SmallVectorImpl<CallSiteEntry> &CallSites,
         CallSiteEntry Site = {
           BeginLabel,
           LastLabel,
-          LandingPad->LandingPadLabel,
+          LandingPad,
           FirstActions[P.PadIndex]
         };
 
         // Try to merge with the previous call-site. SJLJ doesn't do this
         if (PreviousIsInvoke && !IsSJLJ) {
           CallSiteEntry &Prev = CallSites.back();
-          if (Site.PadLabel == Prev.PadLabel && Site.Action == Prev.Action) {
+          if (Site.LPad == Prev.LPad && Site.Action == Prev.Action) {
             // Extend the range of the previous entry.
             Prev.EndLabel = Site.EndLabel;
             continue;
@@ -576,15 +577,15 @@ void EHStreamer::emitExceptionTable() {
 
       // Offset of the landing pad, counted in 16-byte bundles relative to the
       // @LPStart address.
-      if (!S.PadLabel) {
+      if (!S.LPad) {
         if (VerboseAsm)
           Asm->OutStreamer.AddComment("    has no landing pad");
         Asm->OutStreamer.EmitIntValue(0, 4/*size*/);
       } else {
         if (VerboseAsm)
           Asm->OutStreamer.AddComment(Twine("    jumps to ") +
-                                      S.PadLabel->getName());
-        Asm->EmitLabelDifference(S.PadLabel, EHFuncBeginSym, 4);
+                                      S.LPad->LandingPadLabel->getName());
+        Asm->EmitLabelDifference(S.LPad->LandingPadLabel, EHFuncBeginSym, 4);
       }
 
       // Offset of the first associated action record, relative to the start of
@@ -681,7 +682,7 @@ void EHStreamer::emitTypeInfos(unsigned TTypeEncoding) {
     unsigned TypeID = *I;
     if (VerboseAsm) {
       --Entry;
-      if (TypeID != 0)
+      if (isFilterEHSelector(TypeID))
         Asm->OutStreamer.AddComment("FilterInfo " + Twine(Entry));
     }
 
diff --git a/llvm/lib/CodeGen/AsmPrinter/EHStreamer.h b/llvm/lib/CodeGen/AsmPrinter/EHStreamer.h
index e93055ce865..9b316ff00e9 100644
--- a/llvm/lib/CodeGen/AsmPrinter/EHStreamer.h
+++ b/llvm/lib/CodeGen/AsmPrinter/EHStreamer.h
@@ -23,6 +23,8 @@ class MachineModuleInfo;
 class MachineInstr;
 class MachineFunction;
 class AsmPrinter;
+class MCSymbol;
+class MCSymbolRefExpr;
 
 template <typename T>
 class SmallVectorImpl;
@@ -60,11 +62,11 @@ protected:
   /// Structure describing an entry in the call-site table.
   struct CallSiteEntry {
     // The 'try-range' is BeginLabel .. EndLabel.
-    MCSymbol *BeginLabel; // zero indicates the start of the function.
-    MCSymbol *EndLabel;   // zero indicates the end of the function.
+    MCSymbol *BeginLabel; // Null indicates the start of the function.
+    MCSymbol *EndLabel;   // Null indicates the end of the function.
 
-    // The landing pad starts at PadLabel.
-    MCSymbol *PadLabel;   // zero indicates that there is no landing pad.
+    // LPad contains the landing pad start labels.
+    const LandingPadInfo *LPad; // Null indicates that there is no landing pad.
     unsigned Action;
   };
 
@@ -112,6 +114,13 @@ protected:
 
   virtual void emitTypeInfos(unsigned TTypeEncoding);
 
+  // Helpers for for identifying what kind of clause an EH typeid or selector
+  // corresponds to. Negative selectors are for filter clauses, the zero
+  // selector is for cleanups, and positive selectors are for catch clauses.
+  static bool isFilterEHSelector(int Selector) { return Selector < 0; }
+  static bool isCleanupEHSelector(int Selector) { return Selector == 0; }
+  static bool isCatchEHSelector(int Selector) { return Selector > 0; }
+
 public:
   EHStreamer(AsmPrinter *A);
   virtual ~EHStreamer();
diff --git a/llvm/lib/CodeGen/AsmPrinter/Win64Exception.cpp b/llvm/lib/CodeGen/AsmPrinter/Win64Exception.cpp
index 0f0ad755835..2138cb9514f 100644
--- a/llvm/lib/CodeGen/AsmPrinter/Win64Exception.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/Win64Exception.cpp
@@ -99,9 +99,156 @@ void Win64Exception::endFunction(const MachineFunction *) {
 
   if (shouldEmitPersonality) {
     Asm->OutStreamer.PushSection();
+
+    // Emit an UNWIND_INFO struct describing the prologue.
     Asm->OutStreamer.EmitWinEHHandlerData();
-    emitExceptionTable();
+
+    // Emit either MSVC-compatible tables or the usual Itanium-style LSDA after
+    // the UNWIND_INFO struct.
+    if (Asm->MAI->getExceptionHandlingType() == ExceptionHandling::MSVC) {
+      const Function *Per = MMI->getPersonalities()[MMI->getPersonalityIndex()];
+      if (Per->getName() == "__C_specific_handler")
+        emitCSpecificHandlerTable();
+      else
+        report_fatal_error(Twine("unexpected personality function: ") +
+                           Per->getName());
+    } else {
+      emitExceptionTable();
+    }
+
     Asm->OutStreamer.PopSection();
   }
   Asm->OutStreamer.EmitWinCFIEndProc();
 }
+
+const MCSymbolRefExpr *Win64Exception::createImageRel32(const MCSymbol *Value) {
+  return MCSymbolRefExpr::Create(Value, MCSymbolRefExpr::VK_COFF_IMGREL32,
+                                 Asm->OutContext);
+}
+
+/// Emit the language-specific data that __C_specific_handler expects.  This
+/// handler lives in the x64 Microsoft C runtime and allows catching or cleaning
+/// up after faults with __try, __except, and __finally.  The typeinfo values
+/// are not really RTTI data, but pointers to filter functions that return an
+/// integer (1, 0, or -1) indicating how to handle the exception. For __finally
+/// blocks and other cleanups, the landing pad label is zero, and the filter
+/// function is actually a cleanup handler with the same prototype.  A catch-all
+/// entry is modeled with a null filter function field and a non-zero landing
+/// pad label.
+///
+/// Possible filter function return values:
+///   EXCEPTION_EXECUTE_HANDLER (1):
+///     Jump to the landing pad label after cleanups.
+///   EXCEPTION_CONTINUE_SEARCH (0):
+///     Continue searching this table or continue unwinding.
+///   EXCEPTION_CONTINUE_EXECUTION (-1):
+///     Resume execution at the trapping PC.
+///
+/// Inferred table structure:
+///   struct Table {
+///     int NumEntries;
+///     struct Entry {
+///       imagerel32 LabelStart;
+///       imagerel32 LabelEnd;
+///       imagerel32 FilterOrFinally;  // Zero means catch-all.
+///       imagerel32 LabelLPad;        // Zero means __finally.
+///     } Entries[NumEntries];
+///   };
+void Win64Exception::emitCSpecificHandlerTable() {
+  const std::vector<LandingPadInfo> &PadInfos = MMI->getLandingPads();
+
+  // Simplifying assumptions for first implementation:
+  // - Cleanups are not implemented.
+  // - Filters are not implemented.
+
+  // The Itanium LSDA table sorts similar landing pads together to simplify the
+  // actions table, but we don't need that.
+  SmallVector<const LandingPadInfo *, 64> LandingPads;
+  LandingPads.reserve(PadInfos.size());
+  for (const auto &LP : PadInfos)
+    LandingPads.push_back(&LP);
+
+  // Compute label ranges for call sites as we would for the Itanium LSDA, but
+  // use an all zero action table because we aren't using these actions.
+  SmallVector<unsigned, 64> FirstActions;
+  FirstActions.resize(LandingPads.size());
+  SmallVector<CallSiteEntry, 64> CallSites;
+  computeCallSiteTable(CallSites, LandingPads, FirstActions);
+
+  MCSymbol *EHFuncBeginSym =
+      Asm->GetTempSymbol("eh_func_begin", Asm->getFunctionNumber());
+  MCSymbol *EHFuncEndSym =
+      Asm->GetTempSymbol("eh_func_end", Asm->getFunctionNumber());
+
+  // Emit the number of table entries.
+  unsigned NumEntries = 0;
+  for (const CallSiteEntry &CSE : CallSites) {
+    if (!CSE.LPad)
+      continue; // Ignore gaps.
+    for (int Selector : CSE.LPad->TypeIds) {
+      // Ignore C++ filter clauses in SEH.
+      // FIXME: Implement cleanup clauses.
+      if (isCatchEHSelector(Selector))
+        ++NumEntries;
+    }
+  }
+  Asm->OutStreamer.EmitIntValue(NumEntries, 4);
+
+  // Emit the four-label records for each call site entry. The table has to be
+  // sorted in layout order, and the call sites should already be sorted.
+  for (const CallSiteEntry &CSE : CallSites) {
+    // Ignore gaps. Unlike the Itanium model, unwinding through a frame without
+    // an EH table entry will propagate the exception rather than terminating
+    // the program.
+    if (!CSE.LPad)
+      continue;
+    const LandingPadInfo *LPad = CSE.LPad;
+
+    // Compute the label range. We may reuse the function begin and end labels
+    // rather than forming new ones.
+    const MCExpr *Begin =
+        createImageRel32(CSE.BeginLabel ? CSE.BeginLabel : EHFuncBeginSym);
+    const MCExpr *End;
+    if (CSE.EndLabel) {
+      // The interval is half-open, so we have to add one to include the return
+      // address of the last invoke in the range.
+      End = MCBinaryExpr::CreateAdd(createImageRel32(CSE.EndLabel),
+                                    MCConstantExpr::Create(1, Asm->OutContext),
+                                    Asm->OutContext);
+    } else {
+      End = createImageRel32(EHFuncEndSym);
+    }
+
+    // These aren't really type info globals, they are actually pointers to
+    // filter functions ordered by selector. The zero selector is used for
+    // cleanups, so slot zero corresponds to selector 1.
+    const std::vector<const GlobalValue *> &SelectorToFilter = MMI->getTypeInfos();
+
+    // Do a parallel iteration across typeids and clause labels, skipping filter
+    // clauses.
+    assert(LPad->TypeIds.size() == LPad->ClauseLabels.size());
+    for (size_t I = 0, E = LPad->TypeIds.size(); I < E; ++I) {
+      // AddLandingPadInfo stores the clauses in reverse, but there is a FIXME
+      // to change that.
+      int Selector = LPad->TypeIds[E - I - 1];
+      MCSymbol *ClauseLabel = LPad->ClauseLabels[I];
+
+      // Ignore C++ filter clauses in SEH.
+      // FIXME: Implement cleanup clauses.
+      if (!isCatchEHSelector(Selector))
+        continue;
+
+      Asm->OutStreamer.EmitValue(Begin, 4);
+      Asm->OutStreamer.EmitValue(End, 4);
+      if (isCatchEHSelector(Selector)) {
+        assert(unsigned(Selector - 1) < SelectorToFilter.size());
+        const GlobalValue *TI = SelectorToFilter[Selector - 1];
+        if (TI) // Emit the filter function pointer.
+          Asm->OutStreamer.EmitValue(createImageRel32(Asm->getSymbol(TI)), 4);
+        else  // Otherwise, this is a "catch i8* null", or catch all.
+          Asm->OutStreamer.EmitIntValue(0, 4);
+      }
+      Asm->OutStreamer.EmitValue(createImageRel32(ClauseLabel), 4);
+    }
+  }
+}
diff --git a/llvm/lib/CodeGen/AsmPrinter/Win64Exception.h b/llvm/lib/CodeGen/AsmPrinter/Win64Exception.h
index 538e1328157..b2d5d1bce56 100644
--- a/llvm/lib/CodeGen/AsmPrinter/Win64Exception.h
+++ b/llvm/lib/CodeGen/AsmPrinter/Win64Exception.h
@@ -29,6 +29,10 @@ class Win64Exception : public EHStreamer {
   /// Per-function flag to indicate if frame moves info should be emitted.
   bool shouldEmitMoves;
 
+  void emitCSpecificHandlerTable();
+
+  const MCSymbolRefExpr *createImageRel32(const MCSymbol *Value);
+
 public:
   //===--------------------------------------------------------------------===//
   // Main entry points.