[llvm-exegesis] [AArch64] Implement memory management required functions

Author: lakshayk-nv

llvm/tools/llvm-exegesis/lib/AArch64/Target.cpp

@@ -6,11 +6,34 @@
 //
 //===----------------------------------------------------------------------===//
 #include "../Target.h"
+#include "../Error.h"
+#include "../MmapUtils.h"
+#include "../SerialSnippetGenerator.h"
+#include "../SnippetGenerator.h"
+#include "../SubprocessMemory.h"
 #include "AArch64.h"
 #include "AArch64RegisterInfo.h"
+#include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/MC/MCInstBuilder.h"
+#include "llvm/MC/MCRegisterInfo.h"
+#include <vector>
+#define DEBUG_TYPE "exegesis-aarch64-target"
 
 #if defined(__aarch64__) && defined(__linux__)
-#include <sys/prctl.h> // For PR_PAC_* constants
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include <unistd.h> // for getpagesize()
+#ifdef HAVE_LIBPFM
+#include <perfmon/perf_event.h>
+#endif                   // HAVE_LIBPFM
+#include <linux/prctl.h> // For PR_PAC_* constants
+#include <sys/prctl.h>
+#ifndef PR_PAC_SET_ENABLED_KEYS
+#define PR_PAC_SET_ENABLED_KEYS 60
+#endif
+#ifndef PR_PAC_GET_ENABLED_KEYS
+#define PR_PAC_GET_ENABLED_KEYS 61
+#endif
 #ifndef PR_PAC_APIAKEY
 #define PR_PAC_APIAKEY (1UL << 0)
 #endif
@@ -197,7 +220,39 @@ class ExegesisAArch64Target : public ExegesisTarget {
   ExegesisAArch64Target()
       : ExegesisTarget(AArch64CpuPfmCounters, AArch64_MC::isOpcodeAvailable) {}
 
+  enum ArgumentRegisters {
+    CodeSize = AArch64::X12,
+    AuxiliaryMemoryFD = AArch64::X13,
+    TempRegister = AArch64::X16,
+  };
+
+  std::vector<MCInst> _generateRegisterStackPop(MCRegister Reg,
+                                                int imm = 0) const override {
+    std::vector<MCInst> Insts;
+    if (AArch64::GPR32RegClass.contains(Reg) || 
+        AArch64::GPR64RegClass.contains(Reg)) {
+      generateRegisterStackPop(Reg, Insts, imm);
+      return Insts;
+    }
+    return {};
+  }
+
 private:
+#ifdef __linux__
+  std::vector<MCInst> generateExitSyscall(unsigned ExitCode) const override;
+  std::vector<MCInst>
+  generateMmap(uintptr_t Address, size_t Length,
+               uintptr_t FileDescriptorAddress) const override;
+  void generateMmapAuxMem(std::vector<MCInst> &GeneratedCode) const override;
+  std::vector<MCInst> generateMemoryInitialSetup() const override;
+  std::vector<MCInst> setStackRegisterToAuxMem() const override;
+  uintptr_t getAuxiliaryMemoryStartAddress() const override;
+  std::vector<MCInst> configurePerfCounter(long Request,
+                                           bool SaveRegisters) const override;
+  std::vector<MCRegister> getArgumentRegisters() const override;
+  std::vector<MCRegister> getRegistersNeedSaving() const override;
+#endif // __linux__
+
   std::vector<MCInst> setRegTo(const MCSubtargetInfo &STI, MCRegister Reg,
                                const APInt &Value) const override {
     if (AArch64::GPR32RegClass.contains(Reg))
@@ -237,6 +292,156 @@ class ExegesisAArch64Target : public ExegesisTarget {
 
 } // namespace
 
+#ifdef __linux__
+// true : let use of fixed address to Virtual Address Space Ceiling
+// false: let kernel choose the address of the auxiliary memory
+bool UseFixedAddress = true;
+
+static constexpr const uintptr_t VAddressSpaceCeiling = 0x0000800000000000;
+
+static void generateRoundToNearestPage(unsigned int TargetRegister,
+                                       std::vector<MCInst> &GeneratedCode) {
+  int PageSizeShift = static_cast<int>(round(log2(getpagesize())));
+  // Round down to the nearest page by getting rid of the least significant bits
+  // representing location in the page.
+
+  // Single instruction using AND with inverted mask (effectively BIC)
+  uint64_t BitsToClearMask = (1ULL << PageSizeShift) - 1; // 0xFFF
+  uint64_t AndMask = ~BitsToClearMask;                    // ...FFFFFFFFFFFF000
+  GeneratedCode.push_back(MCInstBuilder(AArch64::ANDXri)
+                              .addReg(TargetRegister) // Xd
+                              .addReg(TargetRegister) // Xn
+                              .addImm(AndMask)        // imm bitmask
+  );
+}
+
+std::vector<MCInst>
+ExegesisAArch64Target::generateExitSyscall(unsigned ExitCode) const {
+  std::vector<MCInst> ExitCallCode;
+  ExitCallCode.push_back(loadImmediate(AArch64::X0, 64, APInt(64, ExitCode)));
+  generateSysCall(SYS_exit, ExitCallCode); // SYS_exit is 93
+  return ExitCallCode;
+}
+
+std::vector<MCInst>
+ExegesisAArch64Target::generateMmap(uintptr_t Address, size_t Length,
+                                    uintptr_t FileDescriptorAddress) const {
+  // mmap(address, length, prot, flags, fd, offset=0)
+  int flags = MAP_SHARED;
+  if (Address != 0) {
+    flags |= MAP_FIXED_NOREPLACE;
+  }
+  std::vector<MCInst> MmapCode;
+  MmapCode.push_back(
+      loadImmediate(AArch64::X0, 64, APInt(64, Address))); // map adr
+  MmapCode.push_back(
+      loadImmediate(AArch64::X1, 64, APInt(64, Length))); // length
+  MmapCode.push_back(loadImmediate(AArch64::X2, 64,
+                                   APInt(64, PROT_READ | PROT_WRITE))); // prot
+  MmapCode.push_back(loadImmediate(AArch64::X3, 64, APInt(64, flags))); // flags
+  // FIXME: File descriptor address is not initialized.
+  // Copy file descriptor location from aux memory into X4
+  MmapCode.push_back(
+      loadImmediate(AArch64::X4, 64, APInt(64, FileDescriptorAddress))); // fd
+  // Dereference file descriptor into FD argument register
+  // MmapCode.push_back(MCInstBuilder(AArch64::LDRWui)
+  //                        .addReg(AArch64::W4)   // Destination register
+  //                        .addReg(AArch64::X4)   // Base register (address)
+  //                        .addImm(0));           // Offset (-byte words)
+  // FIXME: This is not correct.
+  MmapCode.push_back(loadImmediate(AArch64::X5, 64, APInt(64, 0))); // offset
+  generateSysCall(SYS_mmap, MmapCode); // SYS_mmap is 222
+  return MmapCode;
+}
+
+void ExegesisAArch64Target::generateMmapAuxMem(
+    std::vector<MCInst> &GeneratedCode) const {
+  int fd = -1;
+  int flags = MAP_SHARED;
+  uintptr_t address = getAuxiliaryMemoryStartAddress();
+  if (fd == -1)
+    flags |= MAP_ANONYMOUS;
+  if (address != 0)
+    flags |= MAP_FIXED_NOREPLACE;
+  int prot = PROT_READ | PROT_WRITE;
+
+  GeneratedCode.push_back(
+      loadImmediate(AArch64::X0, 64, APInt(64, address))); // map adr
+  GeneratedCode.push_back(loadImmediate(
+      AArch64::X1, 64,
+      APInt(64, SubprocessMemory::AuxiliaryMemorySize))); // length
+  GeneratedCode.push_back(
+      loadImmediate(AArch64::X2, 64, APInt(64, prot))); // prot
+  GeneratedCode.push_back(
+      loadImmediate(AArch64::X3, 64, APInt(64, flags))); // flags
+  GeneratedCode.push_back(loadImmediate(AArch64::X4, 64, APInt(64, fd))); // fd
+  GeneratedCode.push_back(
+      loadImmediate(AArch64::X5, 64, APInt(64, 0))); // offset
+  generateSysCall(SYS_mmap, GeneratedCode);          // SYS_mmap is 222
+}
+
+std::vector<MCInst> ExegesisAArch64Target::generateMemoryInitialSetup() const {
+  std::vector<MCInst> MemoryInitialSetupCode;
+  generateMmapAuxMem(MemoryInitialSetupCode); // FIXME: Uninit file descriptor
+
+  // If using fixed address for auxiliary memory skip this step,
+  // When using dynamic memory allocation (non-fixed address), we must preserve
+  // the mmap return value (X0) which contains the allocated memory address.
+  // This value is saved to the stack to ensure registers requiring memory
+  // access can retrieve the correct address even if X0 is modified by
+  // intermediate code.
+  generateRegisterStackPush(AArch64::X0, MemoryInitialSetupCode);
+  // FIXME: Ensure stack pointer remains stable to prevent loss of saved address
+  return MemoryInitialSetupCode;
+}
+
+std::vector<MCInst> ExegesisAArch64Target::setStackRegisterToAuxMem() const {
+  std::vector<MCInst> instructions; // NOP
+  // TODO: Implement this, Found no need for this in AArch64.
+  return instructions;
+}
+
+uintptr_t ExegesisAArch64Target::getAuxiliaryMemoryStartAddress() const {
+  if (!UseFixedAddress)
+    // Allow kernel to select an appropriate memory address
+    return 0;
+  // Return the second to last page in the virtual address space
+  // to try and prevent interference with memory annotations in the snippet
+  // VAddressSpaceCeiling = 0x0000800000000000
+  // FIXME: Why 2 pages?
+  return VAddressSpaceCeiling - (2 * getpagesize());
+}
+
+std::vector<MCInst>
+ExegesisAArch64Target::configurePerfCounter(long Request,
+                                            bool SaveRegisters) const {
+  std::vector<MCInst> ConfigurePerfCounterCode; // NOP
+  // FIXME: SYSCALL exits with EBADF error - file descriptor is invalid
+  // No file is opened previosly to add as file descriptor
+  return ConfigurePerfCounterCode;
+}
+
+std::vector<MCRegister> ExegesisAArch64Target::getArgumentRegisters() const {
+  return {AArch64::X0, AArch64::X1};
+}
+
+std::vector<MCRegister> ExegesisAArch64Target::getRegistersNeedSaving() const {
+  return {
+      AArch64::X0,
+      AArch64::X1,
+      AArch64::X2,
+      AArch64::X3,
+      AArch64::X4,
+      AArch64::X5,
+      AArch64::X8,
+      ArgumentRegisters::TempRegister,
+      ArgumentRegisters::CodeSize,
+      ArgumentRegisters::AuxiliaryMemoryFD,
+  };
+}
+
+#endif // __linux__
+
 static ExegesisTarget *getTheExegesisAArch64Target() {
   static ExegesisAArch64Target Target;
   return &Target;

llvm/tools/llvm-exegesis/lib/Target.h

@@ -308,6 +308,10 @@ class ExegesisTarget {
     return std::make_unique<SavedState>();
   }
 
+  virtual std::vector<MCInst> _generateRegisterStackPop(MCRegister Reg, int imm = 0) const {
+    return {};
+  }
+
 private:
   virtual bool matchesArch(Triple::ArchType Arch) const = 0;