Revert "[XRay] ARM 32-bit no-Thumb support in compiler-rt"

This reverts commit r280890, as the related LLVM commit broke the thumb bots.

llvm-svn: 280969

1 files changed, 111 insertions, 30 deletions

diff --git a/compiler-rt/lib/xray/xray_interface.cc b/compiler-rt/lib/xray/xray_interface.cc
index 360a6ad5b0a..5ef3fc7aac9 100644
--- a/compiler-rt/lib/xray/xray_interface.cc
+++ b/compiler-rt/lib/xray/xray_interface.cc
@@ -26,15 +26,6 @@
 
 namespace __xray {
 
-#if defined(__x86_64__)
-  // FIXME: The actual length is 11 bytes. Why was length 12 passed to mprotect() ?
-  static const int16_t cSledLength = 12;
-#elif defined(__arm__)
-  static const int16_t cSledLength = 28;
-#else
-  #error "Unsupported CPU Architecture"
-#endif /* CPU architecture */
-
 // This is the function to call when we encounter the entry or exit sleds.
 std::atomic<void (*)(int32_t, XRayEntryType)> XRayPatchedFunction{nullptr};
 
@@ -73,6 +64,13 @@ public:
 
 } // namespace __xray
 
+extern "C" {
+// The following functions have to be defined in assembler, on a per-platform
+// basis. See xray_trampoline_*.s files for implementations.
+extern void __xray_FunctionEntry();
+extern void __xray_FunctionExit();
+}
+
 extern std::atomic<bool> XRayInitialized;
 extern std::atomic<__xray::XRaySledMap> XRayInstrMap;
 
@@ -135,13 +133,12 @@ XRayPatchingStatus ControlPatching(bool Enable) {
   if (InstrMap.Entries == 0)
     return XRayPatchingStatus::NOT_INITIALIZED;
 
-  const uint64_t PageSize = GetPageSizeCached();
-  if((PageSize == 0) || ( (PageSize & (PageSize-1)) != 0) ) {
-    Report("System page size is not a power of two: %lld", PageSize);
-    return XRayPatchingStatus::FAILED;
-  }
-
-  uint32_t FuncId = 1;
+  int32_t FuncId = 1;
+  static constexpr uint8_t CallOpCode = 0xe8;
+  static constexpr uint16_t MovR10Seq = 0xba41;
+  static constexpr uint16_t Jmp9Seq = 0x09eb;
+  static constexpr uint8_t JmpOpCode = 0xe9;
+  static constexpr uint8_t RetOpCode = 0xc3;
   uint64_t CurFun = 0;
   for (std::size_t I = 0; I < InstrMap.Entries; I++) {
     auto Sled = InstrMap.Sleds[I];
@@ -156,28 +153,112 @@ XRayPatchingStatus ControlPatching(bool Enable) {
     // While we're here, we should patch the nop sled. To do that we mprotect
     // the page containing the function to be writeable.
     void *PageAlignedAddr =
-        reinterpret_cast<void *>(Sled.Address & ~(PageSize-1));
+        reinterpret_cast<void *>(Sled.Address & ~((2 << 16) - 1));
     std::size_t MProtectLen =
-        (Sled.Address + cSledLength) - reinterpret_cast<uint64_t>(PageAlignedAddr);
+        (Sled.Address + 12) - reinterpret_cast<uint64_t>(PageAlignedAddr);
     MProtectHelper Protector(PageAlignedAddr, MProtectLen);
     if (Protector.MakeWriteable() == -1) {
       printf("Failed mprotect: %d\n", errno);
       return XRayPatchingStatus::FAILED;
     }
 
-    bool Success = false;
-    switch(Sled.Kind) {
-    case XRayEntryType::ENTRY:
-      Success = patchFunctionEntry(Enable, FuncId, Sled);
-      break;
-    case XRayEntryType::EXIT:
-      Success = patchFunctionExit(Enable, FuncId, Sled);
-      break;
-    default:
-      Report("Unsupported sled kind: %d", int(Sled.Kind));
-      continue;
+    static constexpr int64_t MinOffset{std::numeric_limits<int32_t>::min()};
+    static constexpr int64_t MaxOffset{std::numeric_limits<int32_t>::max()};
+    if (Sled.Kind == XRayEntryType::ENTRY) {
+      // FIXME: Implement this in a more extensible manner, per-platform.
+      // Here we do the dance of replacing the following sled:
+      //
+      // xray_sled_n:
+      //   jmp +9
+      //   <9 byte nop>
+      //
+      // With the following:
+      //
+      //   mov r10d, <function id>
+      //   call <relative 32bit offset to entry trampoline>
+      //
+      // We need to do this in the following order:
+      //
+      // 1. Put the function id first, 2 bytes from the start of the sled (just
+      // after the 2-byte jmp instruction).
+      // 2. Put the call opcode 6 bytes from the start of the sled.
+      // 3. Put the relative offset 7 bytes from the start of the sled.
+      // 4. Do an atomic write over the jmp instruction for the "mov r10d"
+      // opcode and first operand.
+      //
+      // Prerequisite is to compute the relative offset to the
+      // __xray_FunctionEntry function's address.
+      int64_t TrampolineOffset =
+          reinterpret_cast<int64_t>(__xray_FunctionEntry) -
+          (static_cast<int64_t>(Sled.Address) + 11);
+      if (TrampolineOffset < MinOffset || TrampolineOffset > MaxOffset) {
+        Report("XRay Entry trampoline (%p) too far from sled (%p); distance = "
+               "%ld\n",
+               __xray_FunctionEntry, reinterpret_cast<void *>(Sled.Address),
+               TrampolineOffset);
+        continue;
+      }
+      if (Enable) {
+        *reinterpret_cast<uint32_t *>(Sled.Address + 2) = FuncId;
+        *reinterpret_cast<uint8_t *>(Sled.Address + 6) = CallOpCode;
+        *reinterpret_cast<uint32_t *>(Sled.Address + 7) = TrampolineOffset;
+        std::atomic_store_explicit(
+            reinterpret_cast<std::atomic<uint16_t> *>(Sled.Address), MovR10Seq,
+            std::memory_order_release);
+      } else {
+        std::atomic_store_explicit(
+            reinterpret_cast<std::atomic<uint16_t> *>(Sled.Address), Jmp9Seq,
+            std::memory_order_release);
+        // FIXME: Write out the nops still?
+      }
+    }
+
+    if (Sled.Kind == XRayEntryType::EXIT) {
+      // FIXME: Implement this in a more extensible manner, per-platform.
+      // Here we do the dance of replacing the following sled:
+      //
+      // xray_sled_n:
+      //   ret
+      //   <10 byte nop>
+      //
+      // With the following:
+      //
+      //   mov r10d, <function id>
+      //   jmp <relative 32bit offset to exit trampoline>
+      //
+      // 1. Put the function id first, 2 bytes from the start of the sled (just
+      // after the 1-byte ret instruction).
+      // 2. Put the jmp opcode 6 bytes from the start of the sled.
+      // 3. Put the relative offset 7 bytes from the start of the sled.
+      // 4. Do an atomic write over the jmp instruction for the "mov r10d"
+      // opcode and first operand.
+      //
+      // Prerequisite is to compute the relative offset fo the
+      // __xray_FunctionExit function's address.
+      int64_t TrampolineOffset =
+          reinterpret_cast<int64_t>(__xray_FunctionExit) -
+          (static_cast<int64_t>(Sled.Address) + 11);
+      if (TrampolineOffset < MinOffset || TrampolineOffset > MaxOffset) {
+        Report("XRay Exit trampoline (%p) too far from sled (%p); distance = "
+               "%ld\n",
+               __xray_FunctionExit, reinterpret_cast<void *>(Sled.Address),
+               TrampolineOffset);
+        continue;
+      }
+      if (Enable) {
+        *reinterpret_cast<uint32_t *>(Sled.Address + 2) = FuncId;
+        *reinterpret_cast<uint8_t *>(Sled.Address + 6) = JmpOpCode;
+        *reinterpret_cast<uint32_t *>(Sled.Address + 7) = TrampolineOffset;
+        std::atomic_store_explicit(
+            reinterpret_cast<std::atomic<uint16_t> *>(Sled.Address), MovR10Seq,
+            std::memory_order_release);
+      } else {
+        std::atomic_store_explicit(
+            reinterpret_cast<std::atomic<uint8_t> *>(Sled.Address), RetOpCode,
+            std::memory_order_release);
+        // FIXME: Write out the nops still?
+      }
     }
-    (void)Success;
   }
   XRayPatching.store(false, std::memory_order_release);
   PatchingSuccess = true;