[libunwind] [libunwind] [SEH] Implement parsing of aarch64 pdata/xdata (PR #137949)

[Martin Storsjö via cfe-commits]

https://github.com/mstorsjo created https://github.com/llvm/llvm-project/pull/137949

This is needed for forced unwind, for some testcases in libunwind/libcxxabi.

This adds an aarch64 case for extracting the LanguageHandler and HandlerData fields from unwind info, in UnwindCursor::getInfoFromSEH, corresponding to the existing case for x86_64.

This uses the struct IMAGE_ARM64_RUNTIME_FUNCTION_ENTRY_XDATA; this only became available in WinSDK 10.0.19041.0 and mingw-w64 v11.0 (or a mingw-w64 git snapshot after April 2023).

(This is only a build-time requirement though; the format for the unwind data has been fixed since the start of Windows 10 on ARM64, so this doesn't impose any runtime requirement.)

>From 8a03c40961c30bc7a73d4bb841e1811722d2f23a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Martin=20Storsj=C3=B6?= <martin at martin.st>
Date: Tue, 18 Apr 2023 15:02:54 +0300
Subject: [PATCH] [libunwind] [SEH] Implement parsing of aarch64 pdata/xdata

This is needed for forced unwind.

This adds an aarch64 case for extracting the LanguageHandler and
HandlerData fields from unwind info, in UnwindCursor::getInfoFromSEH,
corresponding to the existing case for x86_64.

This uses the struct IMAGE_ARM64_RUNTIME_FUNCTION_ENTRY_XDATA; this
only became available in WinSDK 10.0.19041.0 and mingw-w64 v11.0 (or
a mingw-w64 git snapshot after April 2023).

(This is only a build-time requirement though; the format for the
unwind data has been fixed since the start of Windows 10 on ARM64,
so this doesn't impose any runtime requirement.)
---
 libunwind/src/UnwindCursor.hpp | 46 ++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/libunwind/src/UnwindCursor.hpp b/libunwind/src/UnwindCursor.hpp
index ca9927edc9990..5c1d77ebeddaf 100644
--- a/libunwind/src/UnwindCursor.hpp
+++ b/libunwind/src/UnwindCursor.hpp
@@ -2018,6 +2018,52 @@ bool UnwindCursor<A, R>::getInfoFromSEH(pint_t pc) {
       _info.handler = 0;
     }
   }
+#elif defined(_LIBUNWIND_TARGET_AARCH64)
+  if (unwindEntry->Flag != 0) { // Packed unwind info
+    _info.end_ip = _info.start_ip + unwindEntry->FunctionLength * 4;
+    // Only fill in the handler and LSDA if they're stale.
+    if (pc != getLastPC()) {
+      // Packed unwind info doesn't have an exception handler.
+      _info.lsda = 0;
+      _info.handler = 0;
+    }
+  } else {
+    IMAGE_ARM64_RUNTIME_FUNCTION_ENTRY_XDATA *xdata =
+        reinterpret_cast<IMAGE_ARM64_RUNTIME_FUNCTION_ENTRY_XDATA *>(
+            base + unwindEntry->UnwindData);
+    _info.end_ip = _info.start_ip + xdata->FunctionLength * 4;
+    // Only fill in the handler and LSDA if they're stale.
+    if (pc != getLastPC()) {
+      if (xdata->ExceptionDataPresent) {
+        uint32_t offset = 1; // The main xdata
+        uint32_t codeWords = xdata->CodeWords;
+        uint32_t epilogScopes = xdata->EpilogCount;
+        if (xdata->EpilogCount == 0 && xdata->CodeWords == 0) {
+          uint32_t extensionWord = reinterpret_cast<uint32_t *>(xdata)[1];
+          codeWords = (extensionWord >> 16) & 0xff;
+          epilogScopes = extensionWord & 0xffff;
+          offset++;
+        }
+        if (!xdata->EpilogInHeader)
+          offset += epilogScopes;
+        offset += codeWords;
+        uint32_t *exceptionHandlerInfo =
+            reinterpret_cast<uint32_t *>(xdata) + offset;
+        _dispContext.HandlerData = &exceptionHandlerInfo[1];
+        _dispContext.LanguageHandler = reinterpret_cast<EXCEPTION_ROUTINE *>(
+            base + exceptionHandlerInfo[0]);
+        _info.lsda = reinterpret_cast<unw_word_t>(_dispContext.HandlerData);
+        if (_dispContext.LanguageHandler)
+          _info.handler =
+              reinterpret_cast<unw_word_t>(__libunwind_seh_personality);
+        else
+          _info.handler = 0;
+      } else {
+        _info.lsda = 0;
+        _info.handler = 0;
+      }
+    }
+  }
 #endif
   setLastPC(pc);
   return true;