[XRay][compiler-rt] Runtime changes to support custom event logging

Summary:
This change implements support for the custom event logging sleds and
intrinsics at runtime. For now it only supports handling the sleds in
x86_64, with the implementations for other architectures stubbed out to
do nothing.

NOTE: Work in progress, uploaded for exposition/exploration purposes.

Depends on D27503, D30018, and D33032.

Reviewers: echristo, javed.absar, timshen

Subscribers: mehdi_amini, nemanjai, llvm-commits

Differential Revision: https://reviews.llvm.org/D30630

git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@302857 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 36 insertions, 0 deletions

diff --git a/lib/xray/xray_x86_64.cc b/lib/xray/xray_x86_64.cc
index 2e9a8d270..e34806fa1 100644
--- a/lib/xray/xray_x86_64.cc
+++ b/lib/xray/xray_x86_64.cc
@@ -75,8 +75,10 @@ uint64_t getTSCFrequency() XRAY_NEVER_INSTRUMENT {
 static constexpr uint8_t CallOpCode = 0xe8;
 static constexpr uint16_t MovR10Seq = 0xba41;
 static constexpr uint16_t Jmp9Seq = 0x09eb;
+static constexpr uint16_t Jmp20Seq = 0x14eb;
 static constexpr uint8_t JmpOpCode = 0xe9;
 static constexpr uint8_t RetOpCode = 0xc3;
+static constexpr uint16_t NopwSeq = 0x9066;
 
 static constexpr int64_t MinOffset{std::numeric_limits<int32_t>::min()};
 static constexpr int64_t MaxOffset{std::numeric_limits<int32_t>::max()};
@@ -201,6 +203,40 @@ bool patchFunctionTailExit(const bool Enable, const uint32_t FuncId,
   return true;
 }
 
+bool patchCustomEvent(const bool Enable, const uint32_t FuncId,
+                      const XRaySledEntry &Sled) XRAY_NEVER_INSTRUMENT {
+  // Here we do the dance of replacing the following sled:
+  //
+  // xray_sled_n:
+  //   jmp +19          // 2 bytes
+  //   ...
+  //
+  // With the following:
+  //
+  //   nopw             // 2 bytes*
+  //   ...
+  //
+  // We need to do this in the following order:
+  //
+  // 1. Overwrite the 5-byte nop with the call (relative), where (relative) is
+  //    the relative offset to the __xray_CustomEvent trampoline.
+  // 2. Do a two-byte atomic write over the 'jmp +24' to turn it into a 'nopw'.
+  //    This allows us to "enable" this code once the changes have committed.
+  //
+  // The "unpatch" should just turn the 'nopw' back to a 'jmp +24'.
+  //
+  if (Enable) {
+    std::atomic_store_explicit(
+        reinterpret_cast<std::atomic<uint16_t> *>(Sled.Address), NopwSeq,
+        std::memory_order_release);
+  } else {
+    std::atomic_store_explicit(
+        reinterpret_cast<std::atomic<uint16_t> *>(Sled.Address), Jmp20Seq,
+        std::memory_order_release);
+  }
+  return false;
+}
+
 // We determine whether the CPU we're running on has the correct features we
 // need. In x86_64 this will be rdtscp support.
 bool probeRequiredCPUFeatures() XRAY_NEVER_INSTRUMENT {