Add support for dwarf unwinding on windows on x86_64

Clang doesn't currently support building for windows/x86_64 with
dwarf by setting command line parameters, but if manually modified
to use dwarf, we can make libunwind work in this configuration
as well.

Also include i386 in the docs when adding this as a supported
configuration; libunwind already works for i386 windows, but
can fail due to an issue unrelated to windows itself.

Differential Revision: https://reviews.llvm.org/D38819

git-svn-id: https://llvm.org/svn/llvm-project/libunwind/trunk@316747 91177308-0d34-0410-b5e6-96231b3b80d8

9 files changed, 171 insertions, 37 deletions

diff --git a/docs/index.rst b/docs/index.rst
index a48a159..831bd0e 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -52,6 +52,7 @@ Linux        ARM                  Clang, GCC   EHABI
 Linux        i386, x86_64, ARM64  Clang, GCC   DWARF CFI
 Mac OS X     i386, x86_64         Clang, GCC   DWARF CFI
 NetBSD       x86_64               Clang, GCC   DWARF CFI
+Windows      i386, x86_64         Clang        DWARF CFI
 ============ ==================== ============ ========================
 
 The following minimum compiler versions are strongly recommended.
diff --git a/include/__libunwind_config.h b/include/__libunwind_config.h
index 8043a22..92494b9 100644
--- a/include/__libunwind_config.h
+++ b/include/__libunwind_config.h
@@ -23,9 +23,15 @@
 #  define _LIBUNWIND_HIGHEST_DWARF_REGISTER 8
 # elif defined(__x86_64__)
 #  define _LIBUNWIND_TARGET_X86_64 1
-#  define _LIBUNWIND_CONTEXT_SIZE 21
-#  define _LIBUNWIND_CURSOR_SIZE 33
-#  define _LIBUNWIND_HIGHEST_DWARF_REGISTER 16
+#  if defined(_WIN64)
+#    define _LIBUNWIND_CONTEXT_SIZE 54
+#    define _LIBUNWIND_CURSOR_SIZE 66
+#    define _LIBUNWIND_HIGHEST_DWARF_REGISTER 32
+#  else
+#    define _LIBUNWIND_CONTEXT_SIZE 21
+#    define _LIBUNWIND_CURSOR_SIZE 33
+#    define _LIBUNWIND_HIGHEST_DWARF_REGISTER 16
+#  endif
 # elif defined(__ppc__)
 #  define _LIBUNWIND_TARGET_PPC 1
 #  define _LIBUNWIND_CONTEXT_SIZE 117
diff --git a/include/libunwind.h b/include/libunwind.h
index cd09037..4df4183 100644
--- a/include/libunwind.h
+++ b/include/libunwind.h
@@ -188,7 +188,24 @@ enum {
   UNW_X86_64_R12 = 12,
   UNW_X86_64_R13 = 13,
   UNW_X86_64_R14 = 14,
-  UNW_X86_64_R15 = 15
+  UNW_X86_64_R15 = 15,
+  UNW_X86_64_RIP = 16,
+  UNW_X86_64_XMM0 = 17,
+  UNW_X86_64_XMM1 = 18,
+  UNW_X86_64_XMM2 = 19,
+  UNW_X86_64_XMM3 = 20,
+  UNW_X86_64_XMM4 = 21,
+  UNW_X86_64_XMM5 = 22,
+  UNW_X86_64_XMM6 = 23,
+  UNW_X86_64_XMM7 = 24,
+  UNW_X86_64_XMM8 = 25,
+  UNW_X86_64_XMM9 = 26,
+  UNW_X86_64_XMM10 = 27,
+  UNW_X86_64_XMM11 = 28,
+  UNW_X86_64_XMM12 = 29,
+  UNW_X86_64_XMM13 = 30,
+  UNW_X86_64_XMM14 = 31,
+  UNW_X86_64_XMM15 = 32,
 };
 
 
diff --git a/include/unwind.h b/include/unwind.h
index 58dc3d9..0ab87dd 100644
--- a/include/unwind.h
+++ b/include/unwind.h
@@ -122,7 +122,7 @@ struct _Unwind_Exception {
                             _Unwind_Exception *exc);
   uintptr_t private_1; // non-zero means forced unwind
   uintptr_t private_2; // holds sp that phase1 found for phase2 to use
-#ifndef __LP64__
+#if __SIZEOF_POINTER__ == 4
   // The implementation of _Unwind_Exception uses an attribute mode on the
   // above fields which has the side effect of causing this whole struct to
   // round up to 32 bytes in size. To be more explicit, we add pad fields
diff --git a/src/AddressSpace.hpp b/src/AddressSpace.hpp
index a71ed11..f7cb767 100644
--- a/src/AddressSpace.hpp
+++ b/src/AddressSpace.hpp
@@ -142,13 +142,8 @@ struct UnwindInfoSections {
 /// making local unwinds fast.
 class __attribute__((visibility("hidden"))) LocalAddressSpace {
 public:
-#ifdef __LP64__
-  typedef uint64_t pint_t;
-  typedef int64_t  sint_t;
-#else
-  typedef uint32_t pint_t;
-  typedef int32_t  sint_t;
-#endif
+  typedef uintptr_t pint_t;
+  typedef intptr_t  sint_t;
   uint8_t         get8(pint_t addr) {
     uint8_t val;
     memcpy(&val, (void *)addr, sizeof(val));
@@ -194,7 +189,7 @@ public:
 };
 
 inline uintptr_t LocalAddressSpace::getP(pint_t addr) {
-#ifdef __LP64__
+#if __SIZEOF_POINTER__ == 8
   return get64(addr);
 #else
   return get32(addr);
diff --git a/src/Registers.hpp b/src/Registers.hpp
index 760818f..db0ee5d 100644
--- a/src/Registers.hpp
+++ b/src/Registers.hpp
@@ -245,7 +245,7 @@ public:
   bool        validFloatRegister(int) const { return false; }
   double      getFloatRegister(int num) const;
   void        setFloatRegister(int num, double value);
-  bool        validVectorRegister(int) const { return false; }
+  bool        validVectorRegister(int) const;
   v128        getVectorRegister(int num) const;
   void        setVectorRegister(int num, v128 value);
   const char *getRegisterName(int num);
@@ -292,8 +292,14 @@ private:
     uint64_t __cs;
     uint64_t __fs;
     uint64_t __gs;
+#if defined(_WIN64)
+    uint64_t __padding; // 16-byte align
+#endif
   };
   GPRs _registers;
+#if defined(_WIN64)
+  v128 _xmm[16];
+#endif
 };
 
 inline Registers_x86_64::Registers_x86_64(const void *registers) {
@@ -458,6 +464,38 @@ inline const char *Registers_x86_64::getRegisterName(int regNum) {
     return "r14";
   case UNW_X86_64_R15:
     return "r15";
+  case UNW_X86_64_XMM0:
+    return "xmm0";
+  case UNW_X86_64_XMM1:
+    return "xmm1";
+  case UNW_X86_64_XMM2:
+    return "xmm2";
+  case UNW_X86_64_XMM3:
+    return "xmm3";
+  case UNW_X86_64_XMM4:
+    return "xmm4";
+  case UNW_X86_64_XMM5:
+    return "xmm5";
+  case UNW_X86_64_XMM6:
+    return "xmm6";
+  case UNW_X86_64_XMM7:
+    return "xmm7";
+  case UNW_X86_64_XMM8:
+    return "xmm8";
+  case UNW_X86_64_XMM9:
+    return "xmm9";
+  case UNW_X86_64_XMM10:
+    return "xmm10";
+  case UNW_X86_64_XMM11:
+    return "xmm11";
+  case UNW_X86_64_XMM12:
+    return "xmm12";
+  case UNW_X86_64_XMM13:
+    return "xmm13";
+  case UNW_X86_64_XMM14:
+    return "xmm14";
+  case UNW_X86_64_XMM15:
+    return "xmm15";
   default:
     return "unknown register";
   }
@@ -471,12 +509,34 @@ inline void Registers_x86_64::setFloatRegister(int, double) {
   _LIBUNWIND_ABORT("no x86_64 float registers");
 }
 
-inline v128 Registers_x86_64::getVectorRegister(int) const {
+inline bool Registers_x86_64::validVectorRegister(int regNum) const {
+#if defined(_WIN64)
+  if (regNum < UNW_X86_64_XMM0)
+    return false;
+  if (regNum > UNW_X86_64_XMM15)
+    return false;
+  return true;
+#else
+  return false;
+#endif
+}
+
+inline v128 Registers_x86_64::getVectorRegister(int regNum) const {
+#if defined(_WIN64)
+  assert(validVectorRegister(regNum));
+  return _xmm[regNum - UNW_X86_64_XMM0];
+#else
   _LIBUNWIND_ABORT("no x86_64 vector registers");
+#endif
 }
 
-inline void Registers_x86_64::setVectorRegister(int, v128) {
+inline void Registers_x86_64::setVectorRegister(int regNum, v128 value) {
+#if defined(_WIN64)
+  assert(validVectorRegister(regNum));
+  _xmm[regNum - UNW_X86_64_XMM0] = value;
+#else
   _LIBUNWIND_ABORT("no x86_64 vector registers");
+#endif
 }
 #endif // _LIBUNWIND_TARGET_X86_64
 
diff --git a/src/UnwindLevel1.c b/src/UnwindLevel1.c
index 3a908a5..aa7b7d5 100644
--- a/src/UnwindLevel1.c
+++ b/src/UnwindLevel1.c
@@ -86,7 +86,7 @@ unwind_phase1(unw_context_t *uc, unw_cursor_t *cursor, _Unwind_Exception *except
     // this frame.
     if (frameInfo.handler != 0) {
       __personality_routine p =
-          (__personality_routine)(long)(frameInfo.handler);
+          (__personality_routine)(uintptr_t)(frameInfo.handler);
       _LIBUNWIND_TRACE_UNWINDING(
           "unwind_phase1(ex_ojb=%p): calling personality function %p",
           (void *)exception_object, (void *)(uintptr_t)p);
@@ -181,7 +181,7 @@ unwind_phase2(unw_context_t *uc, unw_cursor_t *cursor, _Unwind_Exception *except
     // If there is a personality routine, tell it we are unwinding.
     if (frameInfo.handler != 0) {
       __personality_routine p =
-          (__personality_routine)(long)(frameInfo.handler);
+          (__personality_routine)(uintptr_t)(frameInfo.handler);
       _Unwind_Action action = _UA_CLEANUP_PHASE;
       if (sp == exception_object->private_2) {
         // Tell personality this was the frame it marked in phase 1.
diff --git a/src/UnwindRegistersRestore.S b/src/UnwindRegistersRestore.S
index e721192..96106de 100644
--- a/src/UnwindRegistersRestore.S
+++ b/src/UnwindRegistersRestore.S
@@ -65,7 +65,16 @@ DEFINE_LIBUNWIND_PRIVATE_FUNCTION(_ZN9libunwind16Registers_x86_646jumptoEv)
 #
 # void libunwind::Registers_x86_64::jumpto()
 #
+#if defined(_WIN64)
+# On entry, thread_state pointer is in rcx; move it into rdi
+# to share restore code below. Since this routine restores and
+# overwrites all registers, we can use the same registers for
+# pointers and temporaries as on unix even though win64 normally
+# mustn't clobber some of them.
+  movq  %rcx, %rdi
+#else
 # On entry, thread_state pointer is in rdi
+#endif
 
   movq  56(%rdi), %rax # rax holds new stack pointer
   subq  $16, %rax
@@ -95,6 +104,25 @@ DEFINE_LIBUNWIND_PRIVATE_FUNCTION(_ZN9libunwind16Registers_x86_646jumptoEv)
   # skip cs
   # skip fs
   # skip gs
+
+#if defined(_WIN64)
+  movdqu 176(%rdi),%xmm0
+  movdqu 192(%rdi),%xmm1
+  movdqu 208(%rdi),%xmm2
+  movdqu 224(%rdi),%xmm3
+  movdqu 240(%rdi),%xmm4
+  movdqu 256(%rdi),%xmm5
+  movdqu 272(%rdi),%xmm6
+  movdqu 288(%rdi),%xmm7
+  movdqu 304(%rdi),%xmm8
+  movdqu 320(%rdi),%xmm9
+  movdqu 336(%rdi),%xmm10
+  movdqu 352(%rdi),%xmm11
+  movdqu 368(%rdi),%xmm12
+  movdqu 384(%rdi),%xmm13
+  movdqu 400(%rdi),%xmm14
+  movdqu 416(%rdi),%xmm15
+#endif
   movq  56(%rdi), %rsp  # cut back rsp to new location
   pop    %rdi      # rdi was saved here earlier
   ret            # rip was saved here
diff --git a/src/UnwindRegistersSave.S b/src/UnwindRegistersSave.S
index 716073b..873a16e 100644
--- a/src/UnwindRegistersSave.S
+++ b/src/UnwindRegistersSave.S
@@ -63,29 +63,56 @@ DEFINE_LIBUNWIND_FUNCTION(unw_getcontext)
 #  thread_state pointer is in rdi
 #
 DEFINE_LIBUNWIND_FUNCTION(unw_getcontext)
-  movq  %rax,   (%rdi)
-  movq  %rbx,  8(%rdi)
-  movq  %rcx, 16(%rdi)
-  movq  %rdx, 24(%rdi)
-  movq  %rdi, 32(%rdi)
-  movq  %rsi, 40(%rdi)
-  movq  %rbp, 48(%rdi)
-  movq  %rsp, 56(%rdi)
-  addq  $8,   56(%rdi)
-  movq  %r8,  64(%rdi)
-  movq  %r9,  72(%rdi)
-  movq  %r10, 80(%rdi)
-  movq  %r11, 88(%rdi)
-  movq  %r12, 96(%rdi)
-  movq  %r13,104(%rdi)
-  movq  %r14,112(%rdi)
-  movq  %r15,120(%rdi)
-  movq  (%rsp),%rsi
-  movq  %rsi,128(%rdi) # store return address as rip
+#if defined(_WIN64)
+#define PTR %rcx
+#define TMP %rdx
+#else
+#define PTR %rdi
+#define TMP %rsi
+#endif
+
+  movq  %rax,   (PTR)
+  movq  %rbx,  8(PTR)
+  movq  %rcx, 16(PTR)
+  movq  %rdx, 24(PTR)
+  movq  %rdi, 32(PTR)
+  movq  %rsi, 40(PTR)
+  movq  %rbp, 48(PTR)
+  movq  %rsp, 56(PTR)
+  addq  $8,   56(PTR)
+  movq  %r8,  64(PTR)
+  movq  %r9,  72(PTR)
+  movq  %r10, 80(PTR)
+  movq  %r11, 88(PTR)
+  movq  %r12, 96(PTR)
+  movq  %r13,104(PTR)
+  movq  %r14,112(PTR)
+  movq  %r15,120(PTR)
+  movq  (%rsp),TMP
+  movq  TMP,128(PTR) # store return address as rip
   # skip rflags
   # skip cs
   # skip fs
   # skip gs
+
+#if defined(_WIN64)
+  movdqu %xmm0,176(PTR)
+  movdqu %xmm1,192(PTR)
+  movdqu %xmm2,208(PTR)
+  movdqu %xmm3,224(PTR)
+  movdqu %xmm4,240(PTR)
+  movdqu %xmm5,256(PTR)
+  movdqu %xmm6,272(PTR)
+  movdqu %xmm7,288(PTR)
+  movdqu %xmm8,304(PTR)
+  movdqu %xmm9,320(PTR)
+  movdqu %xmm10,336(PTR)
+  movdqu %xmm11,352(PTR)
+  movdqu %xmm12,368(PTR)
+  movdqu %xmm13,384(PTR)
+  movdqu %xmm14,400(PTR)
+  movdqu %xmm15,416(PTR)
+#endif
   xorl  %eax, %eax    # return UNW_ESUCCESS
   ret