[X86] Emit .cfi_escape GNU_ARGS_SIZE when adjusting the stack before …

…calls When outgoing function arguments are passed using push instructions, and EH is enabled, we may need to indicate to the stack unwinder that the stack pointer was adjusted before the call. This should fix the exception handling issues in PR24792. Differential Revision: http://reviews.llvm.org/D13132 llvm-svn: 249522
llvm · Oct 7, 2015 · 259f150 · 259f150
1 parent 1a6fd1c
commit 259f150
Show file tree

Hide file tree

Showing 9 changed files with 257 additions and 4 deletions.
diff --git a/llvm/include/llvm/MC/MCDwarf.h b/llvm/include/llvm/MC/MCDwarf.h
@@ -340,7 +340,8 @@ class MCCFIInstruction {
     OpRestore,
     OpUndefined,
     OpRegister,
-    OpWindowSave
+    OpWindowSave,
+    OpGnuArgsSize
   };
 
 private:
@@ -454,6 +455,11 @@ class MCCFIInstruction {
     return MCCFIInstruction(OpEscape, L, 0, 0, Vals);
   }
 
+  /// \brief A special wrapper for .cfi_escape that indicates GNU_ARGS_SIZE
+  static MCCFIInstruction createGnuArgsSize(MCSymbol *L, int Size) {
+    return MCCFIInstruction(OpGnuArgsSize, L, 0, Size, "");
+  }
+
   OpType getOperation() const { return Operation; }
   MCSymbol *getLabel() const { return Label; }
 
@@ -473,7 +479,7 @@ class MCCFIInstruction {
   int getOffset() const {
     assert(Operation == OpDefCfa || Operation == OpOffset ||
            Operation == OpRelOffset || Operation == OpDefCfaOffset ||
-           Operation == OpAdjustCfaOffset);
+           Operation == OpAdjustCfaOffset || Operation == OpGnuArgsSize);
     return Offset;
   }
 

diff --git a/llvm/include/llvm/MC/MCStreamer.h b/llvm/include/llvm/MC/MCStreamer.h
@@ -661,6 +661,7 @@ class MCStreamer {
   virtual void EmitCFIRelOffset(int64_t Register, int64_t Offset);
   virtual void EmitCFIAdjustCfaOffset(int64_t Adjustment);
   virtual void EmitCFIEscape(StringRef Values);
+  virtual void EmitCFIGnuArgsSize(int64_t Size);
   virtual void EmitCFISignalFrame();
   virtual void EmitCFIUndefined(int64_t Register);
   virtual void EmitCFIRegister(int64_t Register1, int64_t Register2);

diff --git a/llvm/lib/CodeGen/AsmPrinter/AsmPrinterDwarf.cpp b/llvm/lib/CodeGen/AsmPrinter/AsmPrinterDwarf.cpp
@@ -246,6 +246,12 @@ void AsmPrinter::emitCFIInstruction(const MCCFIInstruction &Inst) const {
   case MCCFIInstruction::OpSameValue:
     OutStreamer->EmitCFISameValue(Inst.getRegister());
     break;
+  case MCCFIInstruction::OpGnuArgsSize:
+    OutStreamer->EmitCFIGnuArgsSize(Inst.getOffset());
+    break;
+  case MCCFIInstruction::OpEscape:
+    OutStreamer->EmitCFIEscape(Inst.getValues());
+    break;
   }
 }
 

diff --git a/llvm/lib/MC/MCAsmStreamer.cpp b/llvm/lib/MC/MCAsmStreamer.cpp
@@ -29,6 +29,7 @@
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/Format.h"
 #include "llvm/Support/FormattedStream.h"
+#include "llvm/Support/LEB128.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/Path.h"
 #include <cctype>
@@ -210,6 +211,8 @@ class MCAsmStreamer final : public MCStreamer {
   void EmitCFISameValue(int64_t Register) override;
   void EmitCFIRelOffset(int64_t Register, int64_t Offset) override;
   void EmitCFIAdjustCfaOffset(int64_t Adjustment) override;
+  void EmitCFIEscape(StringRef Values) override;
+  void EmitCFIGnuArgsSize(int64_t Size) override;
   void EmitCFISignalFrame() override;
   void EmitCFIUndefined(int64_t Register) override;
   void EmitCFIRegister(int64_t Register1, int64_t Register2) override;
@@ -1010,6 +1013,32 @@ void MCAsmStreamer::EmitCFIDefCfaOffset(int64_t Offset) {
   EmitEOL();
 }
 
+static void PrintCFIEscape(llvm::formatted_raw_ostream &OS, StringRef Values) {
+  OS << "\t.cfi_escape ";
+  if (!Values.empty()) {
+    size_t e = Values.size() - 1;
+    for (size_t i = 0; i < e; ++i)
+      OS << format("0x%02x", uint8_t(Values[i])) << ", ";
+    OS << format("0x%02x", uint8_t(Values[e]));
+  }
+}
+
+void MCAsmStreamer::EmitCFIEscape(StringRef Values) {
+  MCStreamer::EmitCFIEscape(Values);
+  PrintCFIEscape(OS, Values);
+  EmitEOL();
+}
+
+void MCAsmStreamer::EmitCFIGnuArgsSize(int64_t Size) {
+  MCStreamer::EmitCFIGnuArgsSize(Size);
+
+  uint8_t Buffer[16] = { dwarf::DW_CFA_GNU_args_size };
+  unsigned Len = encodeULEB128(Size, Buffer + 1) + 1;
+
+  PrintCFIEscape(OS, StringRef((const char *)&Buffer[0], Len));
+  EmitEOL();
+}
+
 void MCAsmStreamer::EmitCFIDefCfaRegister(int64_t Register) {
   MCStreamer::EmitCFIDefCfaRegister(Register);
   OS << "\t.cfi_def_cfa_register ";

diff --git a/llvm/lib/MC/MCDwarf.cpp b/llvm/lib/MC/MCDwarf.cpp
@@ -1147,6 +1147,11 @@ void FrameEmitterImpl::EmitCFIInstruction(MCObjectStreamer &Streamer,
     Streamer.EmitIntValue(dwarf::DW_CFA_restore | Reg, 1);
     return;
   }
+  case MCCFIInstruction::OpGnuArgsSize: {
+    Streamer.EmitIntValue(dwarf::DW_CFA_GNU_args_size, 1);
+    Streamer.EmitULEB128IntValue(Instr.getOffset());
+    return;
+  }
   case MCCFIInstruction::OpEscape:
     Streamer.EmitBytes(Instr.getValues());
     return;

diff --git a/llvm/lib/MC/MCStreamer.cpp b/llvm/lib/MC/MCStreamer.cpp
@@ -359,6 +359,14 @@ void MCStreamer::EmitCFIEscape(StringRef Values) {
   CurFrame->Instructions.push_back(Instruction);
 }
 
+void MCStreamer::EmitCFIGnuArgsSize(int64_t Size) {
+  MCSymbol *Label = EmitCFICommon();
+  MCCFIInstruction Instruction = 
+    MCCFIInstruction::createGnuArgsSize(Label, Size);
+  MCDwarfFrameInfo *CurFrame = getCurrentDwarfFrameInfo();
+  CurFrame->Instructions.push_back(Instruction);
+}
+
 void MCStreamer::EmitCFISignalFrame() {
   EnsureValidDwarfFrame();
   MCDwarfFrameInfo *CurFrame = getCurrentDwarfFrameInfo();

diff --git a/llvm/lib/Target/X86/X86FrameLowering.cpp b/llvm/lib/Target/X86/X86FrameLowering.cpp
@@ -2073,15 +2073,32 @@ eliminateCallFramePseudoInstr(MachineFunction &MF, MachineBasicBlock &MBB,
     // If the stack pointer can be changed after prologue, turn the
     // adjcallstackup instruction into a 'sub ESP, <amt>' and the
     // adjcallstackdown instruction into 'add ESP, <amt>'
-    if (Amount == 0)
-      return;
 
     // We need to keep the stack aligned properly.  To do this, we round the
     // amount of space needed for the outgoing arguments up to the next
     // alignment boundary.
     unsigned StackAlign = getStackAlignment();
     Amount = RoundUpToAlignment(Amount, StackAlign);
 
+    // If we have any exception handlers in this function, and we adjust
+    // the SP before calls, we may need to indicate this to the unwinder,
+    // using GNU_ARGS_SIZE. Note that this may be necessary
+    // even when Amount == 0, because the preceding function may have
+    // set a non-0 GNU_ARGS_SIZE.
+    // TODO: We don't need to reset this between subsequent functions,
+    // if it didn't change.
+    bool HasDwarfEHHandlers =
+      !MF.getTarget().getMCAsmInfo()->usesWindowsCFI() &&
+      !MF.getMMI().getLandingPads().empty();
+
+    if (HasDwarfEHHandlers && !isDestroy && 
+        MF.getInfo<X86MachineFunctionInfo>()->getHasPushSequences())
+      BuildCFI(MBB, I, DL,
+               MCCFIInstruction::createGnuArgsSize(nullptr, Amount));
+
+    if (Amount == 0)
+      return;
+
     // Factor out the amount that gets handled inside the sequence
     // (Pushes of argument for frame setup, callee pops for frame destroy)
     Amount -= InternalAmt;

diff --git a/llvm/test/CodeGen/X86/push-cfi-obj.ll b/llvm/test/CodeGen/X86/push-cfi-obj.ll
@@ -0,0 +1,38 @@
+; RUN: llc < %s -mtriple=i686-pc-linux -filetype=obj | llvm-readobj -s -sr -sd | FileCheck %s
+
+; CHECK:         Index: 8
+; CHECK-NEXT:    Name: .eh_frame (41)
+; CHECK-NEXT:    Type: SHT_PROGBITS (0x1)
+; CHECK-NEXT:    Flags [ (0x2)
+; CHECK-NEXT:      SHF_ALLOC (0x2)
+; CHECK-NEXT:    ]
+; CHECK-NEXT:    Address: 0x0
+; CHECK-NEXT:    Offset: 0x64
+; CHECK-NEXT:    Size: 60
+; CHECK-NEXT:    Link: 0
+; CHECK-NEXT:    Info: 0
+; CHECK-NEXT:    AddressAlignment: 4
+; CHECK-NEXT:    EntrySize: 0
+; CHECK-NEXT:    Relocations [
+; CHECK-NEXT:    ]
+; CHECK-NEXT:    SectionData (
+; CHECK-NEXT:      0000: 1C000000 00000000 017A504C 5200017C  |.........zPLR..||
+; CHECK-NEXT:      0010: 08070000 00000000 1B0C0404 88010000  |................|
+; CHECK-NEXT:      0020: 18000000 24000000 00000000 19000000  |....$...........|
+; CHECK-NEXT:      0030: 04000000 00430E10 2E100000           |.....C......|
+; CHECK-NEXT:    )
+
+declare i32 @__gxx_personality_v0(...)
+declare void @good(i32 %a, i32 %b, i32 %c, i32 %d)
+
+define void @test() optsize personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  invoke void @good(i32 1, i32 2, i32 3, i32 4)
+          to label %continue unwind label %cleanup
+continue:
+  ret void
+cleanup:  
+  landingpad { i8*, i32 }
+     cleanup
+  ret void
+}
diff --git a/llvm/test/CodeGen/X86/push-cfi.ll b/llvm/test/CodeGen/X86/push-cfi.ll
@@ -0,0 +1,143 @@
+; RUN: llc < %s -mtriple=i686-pc-linux | FileCheck %s
+
+declare i32 @__gxx_personality_v0(...)
+declare void @good(i32 %a, i32 %b, i32 %c, i32 %d)
+declare void @large(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f)
+declare void @empty()
+
+; We use an invoke, and expect a .cfi_escape GNU_ARGS_SIZE with size 16
+; before the invocation
+; CHECK-LABEL: test1:
+; CHECK: .cfi_escape 0x2e, 0x10
+; CHECK-NEXT: pushl   $4
+; CHECK-NEXT: pushl   $3
+; CHECK-NEXT: pushl   $2
+; CHECK-NEXT: pushl   $1
+; CHECK-NEXT: call
+; CHECK-NEXT: addl $16, %esp
+define void @test1() optsize personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  invoke void @good(i32 1, i32 2, i32 3, i32 4)
+          to label %continue unwind label %cleanup
+continue:
+  ret void
+cleanup:  
+  landingpad { i8*, i32 }
+     cleanup
+  ret void
+}
+
+; If the function has no handlers, we don't need to generate GNU_ARGS_SIZE,
+; even if it has an unwind table.
+; CHECK-LABEL: test2:
+; CHECK-NOT: .cfi_escape
+; CHECK: pushl   $4
+; CHECK-NEXT: pushl   $3
+; CHECK-NEXT: pushl   $2
+; CHECK-NEXT: pushl   $1
+; CHECK-NEXT: call
+; CHECK-NEXT: addl $16, %esp
+define void @test2() optsize personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  call void @good(i32 1, i32 2, i32 3, i32 4)
+  ret void
+}
+
+; If we did not end up using any pushes, no need for GNU_ARGS_SIZE anywhere
+; CHECK-LABEL: test3:
+; CHECK-NOT: .cfi_escape
+; CHECK-NOT: pushl
+; CHECK: retl
+define void @test3() optsize personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  invoke void @empty()
+          to label %continue unwind label %cleanup
+continue:
+  ret void
+cleanup:  
+  landingpad { i8*, i32 }
+     cleanup
+  ret void
+}
+
+; Different sized stacks need different GNU_ARGS_SIZEs
+; CHECK-LABEL: test4:
+; CHECK: .cfi_escape 0x2e, 0x10
+; CHECK-NEXT: pushl   $4
+; CHECK-NEXT: pushl   $3
+; CHECK-NEXT: pushl   $2
+; CHECK-NEXT: pushl   $1
+; CHECK-NEXT: call
+; CHECK-NEXT: addl $16, %esp
+; CHECK: .cfi_escape 0x2e, 0x20
+; CHECK-NEXT: subl    $8, %esp
+; CHECK-NEXT: pushl   $11
+; CHECK-NEXT: pushl   $10
+; CHECK-NEXT: pushl   $9
+; CHECK-NEXT: pushl   $8
+; CHECK-NEXT: pushl   $7
+; CHECK-NEXT: pushl   $6
+; CHECK-NEXT: calll   large
+; CHECK-NEXT: addl $32, %esp
+define void @test4() optsize personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  invoke void @good(i32 1, i32 2, i32 3, i32 4)
+          to label %continue1 unwind label %cleanup
+continue1:
+  invoke void @large(i32 6, i32 7, i32 8, i32 9, i32 10, i32 11)
+          to label %continue2 unwind label %cleanup
+continue2:
+  ret void          
+cleanup:  
+  landingpad { i8*, i32 }
+     cleanup
+  ret void
+}
+
+; If we did use pushes, we need to reset GNU_ARGS_SIZE before a call
+; without parameters
+; CHECK-LABEL: test5:
+; CHECK: .cfi_escape 0x2e, 0x10
+; CHECK-NEXT: pushl   $4
+; CHECK-NEXT: pushl   $3
+; CHECK-NEXT: pushl   $2
+; CHECK-NEXT: pushl   $1
+; CHECK-NEXT: call
+; CHECK-NEXT: addl $16, %esp
+; CHECK: .cfi_escape 0x2e, 0x00
+; CHECK-NEXT: call
+define void @test5() optsize personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  invoke void @good(i32 1, i32 2, i32 3, i32 4)
+          to label %continue1 unwind label %cleanup
+continue1:
+  invoke void @empty()
+          to label %continue2 unwind label %cleanup
+continue2:
+  ret void          
+cleanup:  
+  landingpad { i8*, i32 }
+     cleanup
+  ret void
+}
+
+; This is actually inefficient - we don't need to repeat the .cfi_escape twice.
+; CHECK-LABEL: test6:
+; CHECK: .cfi_escape 0x2e, 0x10
+; CHECK: call
+; CHECK: .cfi_escape 0x2e, 0x10
+; CHECK: call
+define void @test6() optsize personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+entry:
+  invoke void @good(i32 1, i32 2, i32 3, i32 4)
+          to label %continue1 unwind label %cleanup
+continue1:
+  invoke void @good(i32 5, i32 6, i32 7, i32 8)
+          to label %continue2 unwind label %cleanup
+continue2:
+  ret void          
+cleanup:  
+  landingpad { i8*, i32 }
+     cleanup
+  ret void
+}