Persistent Checkpointing (#2184)

CMakeLists.txt

@@ -556,17 +556,26 @@ endforeach(generated_file)
 
 add_custom_target(Generated DEPENDS ${GENERATED_FILES})
 
-add_custom_command(OUTPUT "${CMAKE_CURRENT_BINARY_DIR}/rr_trace.capnp.c++"
-                          "${CMAKE_CURRENT_BINARY_DIR}/rr_trace.capnp.h"
-                   COMMAND capnp compile
-                           "--src-prefix=${CMAKE_CURRENT_SOURCE_DIR}/src"
-                           "-oc++:${CMAKE_CURRENT_BINARY_DIR}"
-                           "${CMAKE_CURRENT_SOURCE_DIR}/src/rr_trace.capnp"
-                   DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/src/rr_trace.capnp")
-set_source_files_properties("${CMAKE_CURRENT_BINARY_DIR}/rr_trace.capnp.c++"
-                            PROPERTIES GENERATED true)
-set_source_files_properties("${CMAKE_CURRENT_BINARY_DIR}/rr_trace.capnp.h"
-                            PROPERTIES GENERATED true HEADER_FILE_ONLY true)
+
+set(CAPNP_FILES
+  rr_trace
+  rr_pcp
+)
+
+# Compile capnproto files
+foreach(capnp_file ${CAPNP_FILES})
+add_custom_command(OUTPUT "${CMAKE_CURRENT_BINARY_DIR}/${capnp_file}.capnp.c++"
+                            "${CMAKE_CURRENT_BINARY_DIR}/${capnp_file}.capnp.h"
+                     COMMAND capnp compile
+                             "--src-prefix=${CMAKE_CURRENT_SOURCE_DIR}/src"
+                             "-oc++:${CMAKE_CURRENT_BINARY_DIR}"
+                             "${CMAKE_CURRENT_SOURCE_DIR}/src/${capnp_file}.capnp"
+                     DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/src/${capnp_file}.capnp")
+  set_source_files_properties("${CMAKE_CURRENT_BINARY_DIR}/${capnp_file}.capnp.c++"
+                              PROPERTIES GENERATED true)
+  set_source_files_properties("${CMAKE_CURRENT_BINARY_DIR}/${capnp_file}.capnp.h"
+                              PROPERTIES GENERATED true HEADER_FILE_ONLY true)
+endforeach()
 
 if (${CMAKE_SYSTEM_PROCESSOR} STREQUAL "aarch64")
   set(BLAKE_ARCH_DIR third-party/blake2/neon)
@@ -578,12 +587,14 @@ set(RR_SOURCES
   src/AddressSpace.cc
   src/AutoRemoteSyscalls.cc
   src/BuildidCommand.cc
+  src/CheckpointInfo.cc
   src/Command.cc
   src/CompressedReader.cc
   src/CompressedWriter.cc
   src/ContextSwitchEvent.cc
   src/CPUFeaturesCommand.cc
   src/CPUIDBugDetector.cc
+  src/CreateCheckpointsCommand.cc
   src/DiversionSession.cc
   src/DumpCommand.cc
   src/Dwarf.cc
@@ -621,6 +632,7 @@ set(RR_SOURCES
   src/PackCommand.cc
   src/PerfCounters.cc
   src/PerfCounterBuffers.cc
+  src/PersistentCheckpointing.cc
   src/PidFdMonitor.cc
   src/processor_trace_check.cc
   src/ProcFdDirMonitor.cc
@@ -660,6 +672,7 @@ set(RR_SOURCES
   src/WaitManager.cc
   src/WaitStatus.cc
   ${CMAKE_CURRENT_BINARY_DIR}/rr_trace.capnp.c++
+  ${CMAKE_CURRENT_BINARY_DIR}/rr_pcp.capnp.c++
   ${BLAKE_ARCH_DIR}/blake2b.c
 )
 
@@ -1499,6 +1512,7 @@ set(TESTS_WITH_PROGRAM
   # check_session_leaks
   checkpoint_dying_threads
   checkpoint_mixed_mode
+  checkpoint_persistent_shmem
   checksum_sanity
   check_lost_interrupts
   clone_file_range

src/AddressSpace.cc

@@ -554,6 +554,11 @@ void AddressSpace::save_auxv(Task* t) {
   save_interpreter_base(t, saved_auxv());
 }
 
+void AddressSpace::restore_auxv(Task* t, std::vector<uint8_t>&& auxv) {
+  saved_auxv_ = std::move(auxv);
+  save_interpreter_base(t, saved_auxv());
+}
+
 void AddressSpace::save_interpreter_base(Task* t, std::vector<uint8_t> auxv) {
   saved_interpreter_base_ = read_interpreter_base(auxv);
   save_ld_path(t, saved_interpreter_base());

src/AddressSpace.h

@@ -662,6 +662,14 @@ class AddressSpace : public HasTaskSet {
    * Dies if no shm size is registered for the address.
    */
   size_t get_shm_size(remote_ptr<void> addr) { return shm_sizes[addr]; }
+
+  /**
+   * Check if `map` is shared memory
+   */
+  bool has_shm_at(const KernelMapping& map) const {
+    return shm_sizes.find(map.start()) != std::cend(shm_sizes);
+  }
+
   void remove_shm_size(remote_ptr<void> addr) { shm_sizes.erase(addr); }
 
   /**
@@ -795,6 +803,9 @@ class AddressSpace : public HasTaskSet {
   const std::vector<uint8_t>& saved_auxv() { return saved_auxv_; }
   void save_auxv(Task* t);
 
+  /* Used when restoring persistent checkpoints. */
+  void restore_auxv(Task* t, std::vector<uint8_t>&& auxv);
+
   remote_ptr<void> saved_interpreter_base() { return saved_interpreter_base_; }
   void save_interpreter_base(Task* t, std::vector<uint8_t> auxv);
 
@@ -873,6 +884,15 @@ class AddressSpace : public HasTaskSet {
 
   bool legacy_breakpoint_mode() { return stopping_breakpoint_table_ != nullptr; }
   remote_code_ptr do_breakpoint_fault_addr() { return do_breakpoint_fault_addr_; }
+
+  void set_breakpoint_fault_addr(remote_code_ptr addr) {
+    do_breakpoint_fault_addr_ = addr;
+  }
+
+  void set_uses_syscall_buffer(bool uses_syscall_buffer = true) {
+    syscallbuf_enabled_ = uses_syscall_buffer;
+  }
+
   remote_code_ptr stopping_breakpoint_table() { return stopping_breakpoint_table_; }
   int stopping_breakpoint_table_entry_size() { return stopping_breakpoint_table_entry_size_; }
 

src/BpfMapMonitor.h

@@ -14,12 +14,19 @@ class BpfMapMonitor : public FileMonitor {
 public:
   BpfMapMonitor(uint64_t key_size, uint64_t value_size) : key_size_(key_size), value_size_(value_size) {}
 
-  virtual Type type() override { return BpfMap; }
+  virtual Type type() const override { return BpfMap; }
 
   uint64_t key_size() const { return key_size_; }
   uint64_t value_size() const { return value_size_; }
 
 private:
+  virtual void serialize_type(
+      pcp::FileMonitor::Builder& builder) const noexcept override {
+    auto bpf = builder.initBpf();
+    bpf.setKeySize(key_size_);
+    bpf.setValueSize(value_size_);
+  }
+
   uint64_t key_size_;
   uint64_t value_size_;
 };