add name builtin

src/ast/ast.h

@@ -49,6 +49,7 @@ class Builtin : public Expression {
 public:
   explicit Builtin(std::string ident) : ident(ident) { }
   std::string ident;
+  int name_id;
 
   void accept(Visitor &v) override;
 };
@@ -196,6 +197,7 @@ public:
 
   void accept(Visitor &v) override;
   std::string name() const;
+  bool need_expansion = false;	// must build a BPF program per wildcard match
 };
 using ProbeList = std::vector<Probe *>;
 

src/ast/codegen_llvm.cpp

@@ -97,6 +97,14 @@ void CodegenLLVM::visit(Builtin &builtin)
     expr_ = b_.CreateLoad(dst);
     b_.CreateLifetimeEnd(dst);
   }
+  else if (builtin.ident == "name")
+  {
+    static int name_id = 0;
+    bpftrace_.name_ids_.push_back(probefull_);
+    builtin.name_id = name_id;
+    name_id++;
+    expr_ = b_.getInt64(builtin.name_id);
+  }
   else
   {
     abort();
@@ -659,21 +667,70 @@ void CodegenLLVM::visit(Probe &probe)
       b_.getInt64Ty(),
       {b_.getInt8PtrTy()}, // struct pt_regs *ctx
       false);
-  Function *func = Function::Create(func_type, Function::ExternalLinkage, probe.name(), module_.get());
-  func->setSection("s_" + probe.name());
-  BasicBlock *entry = BasicBlock::Create(module_->getContext(), "entry", func);
-  b_.SetInsertPoint(entry);
 
-  ctx_ = func->arg_begin();
+  /*
+   * Most of the time, we can take a probe like kprobe:do_f* and build a
+   * single BPF program for that, called "s_kprobe:do_f*", and attach it to
+   * each wildcard match. An exception is the "name" builtin, where we need
+   * to build different BPF programs for each wildcard match that cantains an
+   * ID for the match. Those programs will be called "s_kprobe:do_fcntl" etc.
+   */
+  if (probe.need_expansion == false) {
+    // build a single BPF program pre-wildcards
+    Function *func = Function::Create(func_type, Function::ExternalLinkage, probe.name(), module_.get());
+    func->setSection("s_" + probe.name());
+    BasicBlock *entry = BasicBlock::Create(module_->getContext(), "entry", func);
+    b_.SetInsertPoint(entry);
 
-  if (probe.pred) {
-    probe.pred->accept(*this);
-  }
-  for (Statement *stmt : *probe.stmts) {
-    stmt->accept(*this);
-  }
+    ctx_ = func->arg_begin();
 
-  b_.CreateRet(ConstantInt::get(module_->getContext(), APInt(64, 0)));
+    if (probe.pred) {
+      probe.pred->accept(*this);
+    }
+    for (Statement *stmt : *probe.stmts) {
+      stmt->accept(*this);
+    }
+
+    b_.CreateRet(ConstantInt::get(module_->getContext(), APInt(64, 0)));
+
+  } else {
+    // build a separate BPF programs for each wildcard match
+    for (auto &attach_point : *probe.attach_points) {
+      std::string file_name;
+      switch (probetype(attach_point->provider))
+      {
+        case ProbeType::kprobe:
+        case ProbeType::kretprobe:
+          file_name = "/sys/kernel/debug/tracing/available_filter_functions";
+          break;
+        case ProbeType::tracepoint:
+          file_name = "/sys/kernel/debug/tracing/available_events";
+          break;
+        default:
+          std::cerr << "Wildcard matches aren't available on probe type '"
+                    << attach_point->provider << "'" << std::endl;
+          return;
+      }
+      auto matches = bpftrace_.find_wildcard_matches(attach_point->target, attach_point->func, file_name);
+      for (auto &match : matches) {
+        probefull_ = attach_point->name(match);
+        Function *func = Function::Create(func_type, Function::ExternalLinkage, attach_point->name(match), module_.get());
+        func->setSection("s_" + attach_point->name(match));
+        BasicBlock *entry = BasicBlock::Create(module_->getContext(), "entry", func);
+        b_.SetInsertPoint(entry);
+
+        // check: do the following 8 lines need to be in the wildcard loop?
+        ctx_ = func->arg_begin();
+        if (probe.pred) {
+          probe.pred->accept(*this);
+        }
+        for (Statement *stmt : *probe.stmts) {
+          stmt->accept(*this);
+        }
+        b_.CreateRet(ConstantInt::get(module_->getContext(), APInt(64, 0)));
+      }
+    }
+  }
 }
 
 void CodegenLLVM::visit(Include &include)

src/ast/codegen_llvm.h

@@ -65,6 +65,7 @@ private:
   Value *expr_ = nullptr;
   Value *ctx_;
   BPFtrace &bpftrace_;
+  std::string probefull_;
 
   std::map<std::string, Value *> variables_;
 };

src/ast/semantic_analyser.cpp

@@ -68,6 +68,10 @@ void SemanticAnalyser::visit(Builtin &builtin)
       err_ << arch::name() << " doesn't support " << builtin.ident << std::endl;
     builtin.type = SizedType(Type::integer, 8);
   }
+  else if (builtin.ident == "name") {
+    builtin.type = SizedType(Type::name, 8);
+    probe_->need_expansion = true;
+  }
   else {
     builtin.type = SizedType(Type::none, 0);
     err_ << "Unknown builtin variable: '" << builtin.ident << "'" << std::endl;

src/attached_probe.cpp

@@ -55,6 +55,8 @@ AttachedProbe::AttachedProbe(Probe &probe, std::tuple<uint8_t *, uintptr_t> func
   : probe_(probe), func_(func)
 {
   load_prog();
+  if (bt_verbose)
+    std::cerr << "Attaching " << probe_.name << std::endl;
   switch (probe_.type)
   {
     case ProbeType::kprobe:
@@ -277,8 +279,16 @@ void AttachedProbe::attach_kprobe()
   int perf_event_fd = bpf_attach_kprobe(progfd_, attachtype(probe_.type),
       eventname().c_str(), probe_.attach_point.c_str(), 0);
 
-  if (perf_event_fd < 0)
-    throw std::runtime_error("Error attaching probe: '" + probe_.name + "'");
+  if (perf_event_fd < 0) {
+    if (probe_.orig_name != probe_.name) {
+      // a wildcard expansion couldn't probe something, just print a warning
+      // as this is normal for some kernel functions (eg, do_debug())
+      std::cerr << "Warning: could not attach probe " << probe_.name << ", skipping." << std::endl;
+    } else {
+      // an explicit match failed, so fail as the user must have wanted it
+      throw std::runtime_error("Error attaching probe: '" + probe_.name + "'");
+    }
+  }
 
   perf_event_fds_.push_back(perf_event_fd);
 }

src/bpftrace.cpp

@@ -30,7 +30,7 @@ int BPFtrace::add_probe(ast::Probe &p)
       probe.path = "/proc/self/exe";
       probe.attach_point = "BEGIN_trigger";
       probe.type = probetype(attach_point->provider);
-      probe.prog_name = p.name();
+      probe.orig_name = p.name();
       probe.name = p.name();
       special_probes_.push_back(probe);
       continue;
@@ -41,7 +41,7 @@ int BPFtrace::add_probe(ast::Probe &p)
       probe.path = "/proc/self/exe";
       probe.attach_point = "END_trigger";
       probe.type = probetype(attach_point->provider);
-      probe.prog_name = p.name();
+      probe.orig_name = p.name();
       probe.name = p.name();
       special_probes_.push_back(probe);
       continue;
@@ -83,7 +83,7 @@ int BPFtrace::add_probe(ast::Probe &p)
       probe.path = attach_point->target;
       probe.attach_point = func;
       probe.type = probetype(attach_point->provider);
-      probe.prog_name = p.name();
+      probe.orig_name = p.name();
       probe.name = attach_point->name(func);
       probe.freq = attach_point->freq;
       probes_.push_back(probe);
@@ -117,7 +117,9 @@ std::set<std::string> BPFtrace::find_wildcard_matches(const std::string &prefix,
     if (std::regex_search(line, match, func_regex))
     {
       assert(match.size() == 2);
-      matches.insert(match[1]);
+      // skip the ".part.N" kprobe variants, as they can't be traced:
+      if (std::strstr(match.str(1).c_str(), ".part.") == NULL)
+        matches.insert(match[1]);
     }
   }
   return matches;
@@ -201,6 +203,7 @@ void perf_event_printer(void *cb_cookie, void *data, int size)
   auto args = std::get<1>(bpftrace->printf_args_[printf_id]);
   std::vector<uint64_t> arg_values;
   std::vector<std::unique_ptr<char>> resolved_symbols;
+  char *name;
   for (auto arg : args)
   {
     switch (arg.type)
@@ -221,6 +224,10 @@ void perf_event_printer(void *cb_cookie, void *data, int size)
               bpftrace->resolve_usym(*(uint64_t*)arg_data).c_str()));
         arg_values.push_back((uint64_t)resolved_symbols.back().get());
         break;
+      case Type::name:
+        name = strdup(bpftrace->resolve_name(*(uint64_t*)arg_data).c_str());
+        arg_values.push_back((uint64_t)name);
+        break;
       default:
         abort();
     }
@@ -265,10 +272,19 @@ void perf_event_lost(void *cb_cookie, uint64_t lost)
 
 std::unique_ptr<AttachedProbe> BPFtrace::attach_probe(Probe &probe, const BpfOrc &bpforc)
 {
-  auto func = bpforc.sections_.find("s_" + probe.prog_name);
+  // use the single-probe program if it exists (as is the case with wildcards
+  // and the name builtin, which must be expanded into separate programs per
+  // probe), else try to find a the program based on the original probe name
+  // that includes wildcards.
+  auto func = bpforc.sections_.find("s_" + probe.name);
+  if (func == bpforc.sections_.end())
+    func = bpforc.sections_.find("s_" + probe.orig_name);
   if (func == bpforc.sections_.end())
   {
-    std::cerr << "Code not generated for probe: " << probe.name << std::endl;
+    if (probe.name != probe.orig_name)
+      std::cerr << "Code not generated for probe: " << probe.name << " from: " << probe.orig_name << std::endl;
+    else
+      std::cerr << "Code not generated for probe: " << probe.name << std::endl;
     return nullptr;
   }
   try
@@ -309,6 +325,9 @@ int BPFtrace::run(std::unique_ptr<BpfOrc> bpforc)
     attached_probes_.push_back(std::move(attached_probe));
   }
 
+  if (bt_verbose)
+    std::cerr << "Running..." << std::endl;
+
   poll_perf_events(epollfd);
   attached_probes_.clear();
 
@@ -623,6 +642,8 @@ int BPFtrace::print_map(IMap &map, uint32_t top, uint32_t div)
       std::cout << min_value(value, ncpus_) / div << std::endl;
     else if (map.type_.type == Type::max)
       std::cout << max_value(value, ncpus_) / div << std::endl;
+    else if (map.type_.type == Type::name)
+      std::cout << resolve_name(*(uint64_t*)value.data()) << std::endl;
     else
       std::cout << *(int64_t*)value.data() / div << std::endl;
   }
@@ -1044,6 +1065,12 @@ std::string BPFtrace::resolve_usym(uintptr_t addr) const
   return symbol.str();
 }
 
+std::string BPFtrace::resolve_name(uint64_t name_id)
+{
+  assert(name_id < name_ids_.size());
+  return name_ids_[name_id];
+}
+
 void BPFtrace::sort_by_key(std::vector<SizedType> key_args,
     std::vector<std::pair<std::vector<uint8_t>, std::vector<uint8_t>>> &values_by_key)
 {

src/bpftrace.h

@@ -37,6 +37,7 @@ public:
   std::string get_stack(uint32_t stackid, bool ustack, int indent=0);
   std::string resolve_sym(uintptr_t addr, bool show_offset=false);
   std::string resolve_usym(uintptr_t addr) const;
+  std::string resolve_name(uint64_t name_id);
   int pid_;
 
   std::map<std::string, std::unique_ptr<IMap>> maps_;
@@ -46,14 +47,15 @@ public:
   std::unique_ptr<IMap> stackid_map_;
   std::unique_ptr<IMap> join_map_;
   std::unique_ptr<IMap> perf_event_map_;
+  std::vector<std::string> name_ids_;
   int join_argnum_;
   int join_argsize_;
 
   static void sort_by_key(std::vector<SizedType> key_args,
       std::vector<std::pair<std::vector<uint8_t>, std::vector<uint8_t>>> &values_by_key);
+  virtual std::set<std::string> find_wildcard_matches(const std::string &prefix, const std::string &attach_point, const std::string &file_name);
 
 protected:
-  virtual std::set<std::string> find_wildcard_matches(const std::string &prefix, const std::string &attach_point, const std::string &file_name);
   std::vector<Probe> probes_;
   std::vector<Probe> special_probes_;
 

src/lexer.l

@@ -38,7 +38,7 @@ header <(\\.|[_\-\./a-zA-Z0-9])*>
 {vspace}+               { loc.lines(yyleng); loc.step(); }
 "//".*$  // Comments
 
-pid|tid|uid|gid|nsecs|cpu|comm|stack|ustack|arg[0-9]|retval|func {
+pid|tid|uid|gid|nsecs|cpu|comm|stack|ustack|arg[0-9]|retval|func|name {
                           return Parser::make_BUILTIN(yytext, loc); }
 {ident}                 { return Parser::make_IDENT(yytext, loc); }
 {path}                  { return Parser::make_PATH(yytext, loc); }

src/mapkey.cpp

@@ -73,6 +73,8 @@ std::string MapKey::argument_value(BPFtrace &bpftrace,
       return bpftrace.resolve_sym(*(uint64_t*)data);
     case Type::usym:
       return bpftrace.resolve_usym(*(uint64_t*)data);
+    case Type::name:
+      return bpftrace.name_ids_[*(uint64_t*)data];
     case Type::string:
       return std::string((char*)data);
   }

src/printf.cpp

@@ -32,7 +32,7 @@ std::string verify_format_string(const std::string &fmt, std::vector<SizedType>
   for (int i=0; i<num_args; i++, token_iter++)
   {
     Type arg_type = args.at(i).type;
-    if (arg_type == Type::sym || arg_type == Type::usym)
+    if (arg_type == Type::sym || arg_type == Type::usym || arg_type == Type::name)
       arg_type = Type::string; // Symbols should be printed as strings
     int offset = 1;
 

src/types.cpp

@@ -41,6 +41,7 @@ std::string typestr(Type t)
     case Type::sym:      return "sym";      break;
     case Type::usym:     return "usym";     break;
     case Type::cast:     return "cast";     break;
+    case Type::name:     return "name";     break;
     default: abort();
   }
 }

src/types.h

@@ -30,6 +30,7 @@ enum class Type
   usym,
   cast,
   join,
+  name,
 };
 
 std::ostream &operator<<(std::ostream &os, Type type);
@@ -71,10 +72,11 @@ class Probe
 {
 public:
   ProbeType type;
-  std::string path;
-  std::string attach_point;
-  std::string prog_name;
-  std::string name;
+  std::string path;		// file path if used
+  std::string attach_point;	// probe name (last component)
+  std::string orig_name;	// original full probe name,
+				// before wildcard expansion
+  std::string name;		// full probe name
   uint64_t loc;
   int freq;
 };

tests/codegen.cpp

@@ -667,6 +667,118 @@ attributes #1 = { argmemonly nounwind }
 )EXPECTED");
 }
 
+TEST(codegen, builtin_name)
+{
+  test("tracepoint:syscalls:sys_enter_nanosleep { @x = name }",
+
+R"EXPECTED(; Function Attrs: nounwind
+declare i64 @llvm.bpf.pseudo(i64, i64) #0
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1
+
+define i64 @"tracepoint:syscalls:sys_enter_nanosleep"(i8* nocapture readnone) local_unnamed_addr section "s_tracepoint:syscalls:sys_enter_nanosleep" {
+entry:
+  %"@x_val" = alloca i64, align 8
+  %"@x_key" = alloca i64, align 8
+  %1 = bitcast i64* %"@x_key" to i8*
+  call void @llvm.lifetime.start.p0i8(i64 -1, i8* nonnull %1)
+  store i64 0, i64* %"@x_key", align 8
+  %2 = bitcast i64* %"@x_val" to i8*
+  call void @llvm.lifetime.start.p0i8(i64 -1, i8* nonnull %2)
+  store i64 0, i64* %"@x_val", align 8
+  %pseudo = tail call i64 @llvm.bpf.pseudo(i64 1, i64 1)
+  %update_elem = call i64 inttoptr (i64 2 to i64 (i8*, i8*, i8*, i64)*)(i64 %pseudo, i64* nonnull %"@x_key", i64* nonnull %"@x_val", i64 0)
+  call void @llvm.lifetime.end.p0i8(i64 -1, i8* nonnull %1)
+  call void @llvm.lifetime.end.p0i8(i64 -1, i8* nonnull %2)
+  ret i64 0
+}
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1
+
+attributes #0 = { nounwind }
+attributes #1 = { argmemonly nounwind }
+)EXPECTED");
+}
+
+TEST(codegen, builtin_func_wild)
+{
+  test("tracepoint:syscalls:sys_enter_nanoslee* { @x = func }",
+
+R"EXPECTED(; Function Attrs: nounwind
+declare i64 @llvm.bpf.pseudo(i64, i64) #0
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1
+
+define i64 @"tracepoint:syscalls:sys_enter_nanoslee*"(i8*) local_unnamed_addr section "s_tracepoint:syscalls:sys_enter_nanoslee*" {
+entry:
+  %"@x_val" = alloca i64, align 8
+  %"@x_key" = alloca i64, align 8
+  %func = alloca i64, align 8
+  %1 = bitcast i64* %func to i8*
+  call void @llvm.lifetime.start.p0i8(i64 -1, i8* nonnull %1)
+  %2 = getelementptr i8, i8* %0, i64 128
+  %probe_read = call i64 inttoptr (i64 4 to i64 (i8*, i64, i8*)*)(i64* nonnull %func, i64 8, i8* %2)
+  %3 = load i64, i64* %func, align 8
+  call void @llvm.lifetime.end.p0i8(i64 -1, i8* nonnull %1)
+  %4 = bitcast i64* %"@x_key" to i8*
+  call void @llvm.lifetime.start.p0i8(i64 -1, i8* nonnull %4)
+  store i64 0, i64* %"@x_key", align 8
+  %5 = bitcast i64* %"@x_val" to i8*
+  call void @llvm.lifetime.start.p0i8(i64 -1, i8* nonnull %5)
+  store i64 %3, i64* %"@x_val", align 8
+  %pseudo = call i64 @llvm.bpf.pseudo(i64 1, i64 1)
+  %update_elem = call i64 inttoptr (i64 2 to i64 (i8*, i8*, i8*, i64)*)(i64 %pseudo, i64* nonnull %"@x_key", i64* nonnull %"@x_val", i64 0)
+  call void @llvm.lifetime.end.p0i8(i64 -1, i8* nonnull %4)
+  call void @llvm.lifetime.end.p0i8(i64 -1, i8* nonnull %5)
+  ret i64 0
+}
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1
+
+attributes #0 = { nounwind }
+attributes #1 = { argmemonly nounwind }
+)EXPECTED");
+}
+
+TEST(codegen, builtin_name_wild)
+{
+  test("tracepoint:syscalls:sys_enter_nanoslee* { @x = name }",
+
+R"EXPECTED(; Function Attrs: nounwind
+declare i64 @llvm.bpf.pseudo(i64, i64) #0
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1
+
+define i64 @"tracepoint:syscalls:sys_enter_nanosleep"(i8* nocapture readnone) local_unnamed_addr section "s_tracepoint:syscalls:sys_enter_nanosleep" {
+entry:
+  %"@x_val" = alloca i64, align 8
+  %"@x_key" = alloca i64, align 8
+  %1 = bitcast i64* %"@x_key" to i8*
+  call void @llvm.lifetime.start.p0i8(i64 -1, i8* nonnull %1)
+  store i64 0, i64* %"@x_key", align 8
+  %2 = bitcast i64* %"@x_val" to i8*
+  call void @llvm.lifetime.start.p0i8(i64 -1, i8* nonnull %2)
+  store i64 1, i64* %"@x_val", align 8
+  %pseudo = tail call i64 @llvm.bpf.pseudo(i64 1, i64 1)
+  %update_elem = call i64 inttoptr (i64 2 to i64 (i8*, i8*, i8*, i64)*)(i64 %pseudo, i64* nonnull %"@x_key", i64* nonnull %"@x_val", i64 0)
+  call void @llvm.lifetime.end.p0i8(i64 -1, i8* nonnull %1)
+  call void @llvm.lifetime.end.p0i8(i64 -1, i8* nonnull %2)
+  ret i64 0
+}
+
+; Function Attrs: argmemonly nounwind
+declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1
+
+attributes #0 = { nounwind }
+attributes #1 = { argmemonly nounwind }
+)EXPECTED");
+}
+
 TEST(codegen, call_reg) // Identical to builtin_func apart from variable names
 {
   test("kprobe:f { @x = reg(\"ip\") }",

tests/parser.cpp

@@ -35,6 +35,7 @@ TEST(Parser, builtin_variables)
   test("kprobe:f { arg0 }", "Program\n kprobe:f\n  builtin: arg0\n");
   test("kprobe:f { retval }", "Program\n kprobe:f\n  builtin: retval\n");
   test("kprobe:f { func }", "Program\n kprobe:f\n  builtin: func\n");
+  test("kprobe:f { name }", "Program\n kprobe:f\n  builtin: name\n");
 }
 
 TEST(Parser, map_assign)

tests/semantic_analyser.cpp

@@ -73,6 +73,7 @@ TEST(semantic_analyser, builtin_variables)
   test("kprobe:f { arg0 }", 0);
   test("kprobe:f { retval }", 0);
   test("kprobe:f { func }", 0);
+  test("kprobe:f { name }", 0);
 //  test("kprobe:f { fake }", 1);
 }
 
@@ -260,6 +261,24 @@ TEST(semantic_analyser, call_reg)
   test("kprobe:f { reg(123); }", 1);
 }
 
+TEST(semantic_analyser, call_func)
+{
+  test("kprobe:f { @[func] = count(); }", 0);
+  test("kprobe:f { printf(\"%s\", func);  }", 0);
+  test("kprobe:f { func(\"blah\"); }", 1);
+  test("kprobe:f { func(); }", 1);
+  test("kprobe:f { func(123); }", 1);
+}
+
+TEST(semantic_analyser, call_name)
+{
+  test("kprobe:f { @[name] = count(); }", 0);
+  test("kprobe:f { printf(\"%s\", name);  }", 0);
+  test("kprobe:f { name(\"blah\"); }", 1);
+  test("kprobe:f { name(); }", 1);
+  test("kprobe:f { name(123); }", 1);
+}
+
 TEST(semantic_analyser, map_reassignment)
 {
   test("kprobe:f { @x = 1; @x = 2; }", 0);