Add 'cat' builtin (#543)

README.md

@@ -282,6 +282,7 @@ Functions:
 - `reg(char *name)` - Returns the value stored in the named register
 - `join(char *arr[] [, char *delim])` - Prints the string array
 - `time(char *fmt)` - Print the current time
+- `cat(char *filename)` - Print file content
 - `system(char *fmt)` - Execute shell command
 - `exit()` - Quit bpftrace
 

docs/reference_guide.md

@@ -68,6 +68,7 @@ This is a work in progress. If something is missing, check the bpftrace source t
     - [14. `ntop()`: Convert IP address data to text](#14-ntop-convert-ip-address-data-to-text)
     - [15. `kstack()`: Stack Traces, Kernel](#15-kstack-stack-traces-kernel)
     - [16. `ustack()`: Stack Traces, User](#16-ustack-stack-traces-user)
+    - [17. `cat()`: Print file content](#17-cat-print-file-content)
 - [Map Functions](#map-functions)
     - [1. Builtins](#1-builtins-2)
     - [2. `count()`: Count](#2-count-count)
@@ -1391,6 +1392,7 @@ Tracing block I/O sizes > 0 bytes
 - `kstack([StackMode mode, ][int level])` - Kernel stack trace
 - `ustack([StackMode mode, ][int level])` - User stack trace
 - `ntop(int af, int addr)` - Convert IP address data to text
+- `cat(char *filename)` - Print file content
 
 Some of these are asynchronous: the kernel queues the event, but some time
 later (milliseconds) it is processed in user-space. The asynchronous actions
@@ -1913,6 +1915,26 @@ Attaching 1 probe...
 Note that for these examples to work, bash had to be recompiled with frame
 pointers.
 
+## 17. `cat()`: Print file content
+
+Syntax: `cat(filename)`
+
+This prints the file content. For example:
+
+```
+# bpftrace -e 't:syscalls:sys_enter_execve { printf("%s ", str(args->filename)); cat("/proc/loadavg"); }'
+Attaching 1 probe...
+/usr/libexec/grepconf.sh 3.18 2.90 2.94 2/977 30138
+/usr/bin/grep 3.18 2.90 2.94 4/978 30139
+/usr/bin/flatpak 3.18 2.90 2.94 2/980 30143
+/usr/bin/grep 3.18 2.90 2.94 3/977 30144
+/usr/bin/sed 3.18 2.90 2.94 7/978 30146
+/usr/bin/tclsh 3.18 2.90 2.94 5/978 30150
+/usr/bin/manpath 3.18 2.90 2.94 2/978 30152
+/bin/ps 3.18 2.90 2.94 2/979 30155
+^C
+```
+
 # Map Functions
 
 Maps are special BPF data types that can be used to store counts, statistics, and histograms. They are also used for some variable types as discussed in the previous section, whenever `@` is used: [globals](#21-global), [per thread variables](#22-per-thread), and [associative arrays](#3--associative-arrays).

man/man8/bpftrace.8

@@ -376,6 +376,10 @@ Prints the string array
 Print the current time
 .
 .TP
+\fBcat(char *filename)\fR
+Print file content
+.
+.TP
 \fBsystem(char *fmt)\fR
 Execute shell command
 .

src/ast/codegen_llvm.cpp

@@ -703,6 +703,18 @@ void CodegenLLVM::visit(Call &call)
     b_.CreateLifetimeEnd(perfdata);
     expr_ = nullptr;
   }
+  else if (call.func == "cat")
+  {
+    ArrayType *perfdata_type = ArrayType::get(b_.getInt8Ty(), sizeof(uint64_t) * 2);
+    AllocaInst *perfdata = b_.CreateAllocaBPF(perfdata_type, "perfdata");
+    b_.CreateStore(b_.getInt64(asyncactionint(AsyncAction::cat)), perfdata);
+    b_.CreateStore(b_.getInt64(cat_id_), b_.CreateGEP(perfdata, {b_.getInt64(0), b_.getInt64(sizeof(uint64_t))}));
+
+    cat_id_++;
+    b_.CreatePerfEventOutput(ctx_, perfdata, sizeof(uint64_t) * 2);
+    b_.CreateLifetimeEnd(perfdata);
+    expr_ = nullptr;
+  }
   else if (call.func == "kstack" || call.func == "ustack")
   {
     Value *stackid = b_.CreateGetStackId(ctx_, call.func == "ustack", call.type.stack_type);

src/ast/codegen_llvm.h

@@ -81,6 +81,7 @@ class CodegenLLVM : public Visitor {
   std::map<std::string, AllocaInst *> variables_;
   int printf_id_ = 0;
   int time_id_ = 0;
+  int cat_id_ = 0;
   uint64_t join_id_ = 0;
   int system_id_ = 0;
 };

src/ast/semantic_analyser.cpp

@@ -456,6 +456,17 @@ void SemanticAnalyser::visit(Call &call)
       }
     }
   }
+  else if (call.func == "cat") {
+    check_assignment(call, false, false);
+    if (check_nargs(call, 1)) {
+      if (check_arg(call, Type::string, 0, true)) {
+        if (is_final_pass()) {
+          auto &arg = *call.vargs->at(0);
+          bpftrace_.cat_args_.push_back(static_cast<String&>(arg).str);
+        }
+      }
+    }
+  }
   else if (call.func == "kstack") {
     check_stack_call(call, Type::kstack);
   }

src/bpftrace.cpp

@@ -262,6 +262,13 @@ void perf_event_printer(void *cb_cookie, void *data, int size __attribute__((unu
     printf("%s", timestr);
     return;
   }
+  else if (printf_id == asyncactionint(AsyncAction::cat))
+  {
+    uint64_t cat_id = (uint64_t)*(static_cast<uint64_t*>(data) + sizeof(uint64_t) / sizeof(uint64_t));
+    auto filename = bpftrace->cat_args_[cat_id].c_str();
+    cat_file(filename);
+    return;
+  }
   else if (printf_id == asyncactionint(AsyncAction::join))
   {
     uint64_t join_id = (uint64_t)*(static_cast<uint64_t*>(data) + sizeof(uint64_t) / sizeof(uint64_t));

src/bpftrace.h

@@ -88,6 +88,7 @@ class BPFtrace
   std::vector<std::tuple<std::string, std::vector<Field>>> system_args_;
   std::vector<std::string> join_args_;
   std::vector<std::string> time_args_;
+  std::vector<std::string> cat_args_;
   std::unordered_map<StackType, std::unique_ptr<IMap>> stackid_maps_;
   std::unique_ptr<IMap> join_map_;
   std::unique_ptr<IMap> perf_event_map_;

src/types.h

@@ -153,6 +153,7 @@ enum class AsyncAction
   zero,
   time,
   join,
+  cat
 };
 
 uint64_t asyncactionint(AsyncAction a);

src/utils.cpp

@@ -209,4 +209,20 @@ std::string resolve_binary_path(const std::string& cmd)
   }
 }
 
+void cat_file(const char *filename)
+{
+  std::ifstream file(filename);
+  std::string line;
+
+  if (file.fail())
+  {
+    std::cerr << "ERROR: file not found: " << filename << std::endl;
+    return;
+  }
+  while (getline(file, line))
+  {
+    std::cout << line << std::endl;
+  }
+}
+
 } // namespace bpftrace

src/utils.h

@@ -39,6 +39,7 @@ std::vector<std::string> get_kernel_cflags(
 std::string is_deprecated(std::string &str);
 std::string exec_system(const char* cmd);
 std::string resolve_binary_path(const std::string& cmd);
+void cat_file(const char *filename);
 
 // trim from end of string (right)
 inline std::string& rtrim(std::string& s)

tests/codegen.cpp

@@ -43,6 +43,7 @@
 #include "codegen/call_sum.cpp"
 #include "codegen/call_system.cpp"
 #include "codegen/call_time.cpp"
+#include "codegen/call_cat.cpp"
 #include "codegen/call_usym_key.cpp"
 #include "codegen/call_ustack.cpp"
 #include "codegen/call_zero.cpp"

tests/codegen/call_cat.cpp

@@ -0,0 +1,42 @@
+#include "common.h"
+
+namespace bpftrace {
+namespace test {
+namespace codegen {
+
+TEST(codegen, call_cat)
+{
+  test("kprobe:f { cat(\"/proc/loadavg\"); }",
+
+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 @"kprobe:f"(i8*) local_unnamed_addr section "s_kprobe:f_1" {
+entry:
+  %perfdata = alloca [16 x i8], align 8
+  %1 = getelementptr inbounds [16 x i8], [16 x i8]* %perfdata, i64 0, i64 0
+  call void @llvm.lifetime.start.p0i8(i64 -1, i8* nonnull %1)
+  store i64 20006, [16 x i8]* %perfdata, align 8
+  %2 = getelementptr inbounds [16 x i8], [16 x i8]* %perfdata, i64 0, i64 8
+  store i64 0, i8* %2, align 8
+  %pseudo = tail call i64 @llvm.bpf.pseudo(i64 1, i64 1)
+  %get_cpu_id = tail call i64 inttoptr (i64 8 to i64 ()*)()
+  %perf_event_output = call i64 inttoptr (i64 25 to i64 (i8*, i8*, i64, i8*, i64)*)(i8* %0, i64 %pseudo, i64 %get_cpu_id, [16 x i8]* nonnull %perfdata, i64 16)
+  call void @llvm.lifetime.end.p0i8(i64 -1, i8* nonnull %1)
+  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");
+}
+
+} // namespace codegen
+} // namespace test
+} // namespace bpftrace

tests/runtime/call

@@ -103,3 +103,8 @@ RUN bpftrace -e 'k:do_nanosleep { printf("SUCCESS '$test' %s\n%s\n", ustack(), u
 EXPECT SUCCESS ustack
 TIMEOUT 5
 BEFORE sleep 0.1 && sleep 0.1 &
+
+NAME cat
+RUN bpftrace -e 'i:ms:1 { cat("/proc/uptime"); exit();}'
+EXPECT [0-9]*.[0-9]* [0-9]*.[0-9]*
+TIMEOUT 5

tests/semantic_analyser.cpp

@@ -100,6 +100,7 @@ TEST(semantic_analyser, builtin_functions)
   test("kprobe:f { @x = count(pid) }", 1);
   test("kprobe:f { @x = sum(pid, 123) }", 1);
   test("kprobe:f { fake() }", 1);
+  test("kprobe:f { cat(\"/proc/uptime\") }", 0);
 }
 
 TEST(semantic_analyser, undefined_map)
@@ -313,6 +314,14 @@ TEST(semantic_analyser, call_probe)
   test("kprobe:f { probe(123); }", 1);
 }
 
+TEST(semantic_analyser, call_cat)
+{
+  test("kprobe:f { cat(\"/proc/loadavg\"); }", 0);
+  test("kprobe:f { cat(); }", 1);
+  test("kprobe:f { cat(123); }", 1);
+  test("kprobe:f { @x = cat(\"/proc/loadavg\"); }", 1);
+}
+
 TEST(semantic_analyser, map_reassignment)
 {
   test("kprobe:f { @x = 1; @x = 2; }", 0);