#! /bin/sh

# suppress some run-time errors here for cleaner output
//bin/true && exec stap --suppress-handler-errors --skip-badvars $0 ${1+"$@"}

/*
 * Compile:
 * stap -p4 -DSTP_NO_OVERLOAD -m strace
 * Run:
 * /usr/bin/staprun -R -c "/sbin/wpa_supplicant -u -O /run/wpa_supplicant -c /etc/wpa_supplicant.conf -i wlan0" -w /root/strace.ko only_capability_use=1 timestamp=0
 */

/* configuration options; set these with stap -G */
global follow_fork = 0   /* -Gfollow_fork=1 means trace descendant processes too */
global timestamp = 1     /* -Gtimestamp=0 means don't print a syscall timestamp */
global elapsed_time = 0  /* -Gelapsed_time=1 means print a syscall duration too */
global only_capability_use = 0 /* -Gonly_capability_use=1 means print only when capabilities are used */
global thread_argstr%
global thread_time%

global syscalls_nonreturn[2]
global capnames[64]
global used_caps
global missing_caps
global all_used_caps
global all_missing_caps
global accessed_devices[1000]
global all_accessed_devices[1000]
global highwatermark_fsize
global highwatermark_data
global highwatermark_stack
global highwatermark_core
global highwatermark_nproc
global highwatermark_nofile
global highwatermark_memlock
global highwatermark_as
global highwatermark_sigpending
global highwatermark_msgqueue
global highwatermark_nice
global highwatermark_rtprio
global old_highwatermark_fsize
global old_highwatermark_data
global old_highwatermark_stack
global old_highwatermark_core
global old_highwatermark_nproc
global old_highwatermark_nofile
global old_highwatermark_memlock
global old_highwatermark_as
global old_highwatermark_sigpending
global old_highwatermark_msgqueue
global old_highwatermark_nice
global old_highwatermark_rtprio
global afnames[64]
global used_afs
global missing_afs
global all_used_afs
global all_missing_afs
global no_memory_deny_write_execute
global all_memory_deny_write_execute = "true"
global print_syscall


probe begin 
  {
    /* list those syscalls that never .return */
    syscalls_nonreturn["exit"]=1
    syscalls_nonreturn["exit_group"]=1

    // grep '#define CAP_.*[0-9]+$' /usr/src/linux-headers*/include/uapi/linux/capability.h | awk '{ print "capnames[" $3 "] = \"" $2 "\";" }'
    capnames[0] = "CAP_CHOWN";
    capnames[1] = "CAP_DAC_OVERRIDE";
    capnames[2] = "CAP_DAC_READ_SEARCH";
    capnames[3] = "CAP_FOWNER";
    capnames[4] = "CAP_FSETID";
    capnames[5] = "CAP_KILL";
    capnames[6] = "CAP_SETGID";
    capnames[7] = "CAP_SETUID";
    capnames[8] = "CAP_SETPCAP";
    capnames[9] = "CAP_LINUX_IMMUTABLE";
    capnames[10] = "CAP_NET_BIND_SERVICE";
    capnames[11] = "CAP_NET_BROADCAST";
    capnames[12] = "CAP_NET_ADMIN";
    capnames[13] = "CAP_NET_RAW";
    capnames[14] = "CAP_IPC_LOCK";
    capnames[15] = "CAP_IPC_OWNER";
    capnames[16] = "CAP_SYS_MODULE";
    capnames[17] = "CAP_SYS_RAWIO";
    capnames[18] = "CAP_SYS_CHROOT";
    capnames[19] = "CAP_SYS_PTRACE";
    capnames[20] = "CAP_SYS_PACCT";
    capnames[21] = "CAP_SYS_ADMIN";
    capnames[22] = "CAP_SYS_BOOT";
    capnames[23] = "CAP_SYS_NICE";
    capnames[24] = "CAP_SYS_RESOURCE";
    capnames[25] = "CAP_SYS_TIME";
    capnames[26] = "CAP_SYS_TTY_CONFIG";
    capnames[27] = "CAP_MKNOD";
    capnames[28] = "CAP_LEASE";
    capnames[29] = "CAP_AUDIT_WRITE";
    capnames[30] = "CAP_AUDIT_CONTROL";
    capnames[31] = "CAP_SETFCAP";
    capnames[32] = "CAP_MAC_OVERRIDE";
    capnames[33] = "CAP_MAC_ADMIN";
    capnames[34] = "CAP_SYSLOG";
    capnames[35] = "CAP_WAKE_ALARM";
    capnames[36] = "CAP_BLOCK_SUSPEND";
    capnames[37] = "CAP_AUDIT_READ";

    //grep '#define AF_.*' /usr/src/linux-headers-*/include/linux/socket.h | awk '{ print "afnames[" $3 "] = \"" $2 "\"" }'
    afnames[0] = "AF_UNSPEC"
    afnames[1] = "AF_UNIX"
    afnames[2] = "AF_INET"
    afnames[3] = "AF_AX25"
    afnames[4] = "AF_IPX"
    afnames[5] = "AF_APPLETALK"
    afnames[6] = "AF_NETROM"
    afnames[7] = "AF_BRIDGE"
    afnames[8] = "AF_ATMPVC"
    afnames[9] = "AF_X25"
    afnames[10] = "AF_INET6"
    afnames[11] = "AF_ROSE"
    afnames[12] = "AF_DECnet"
    afnames[13] = "AF_NETBEUI"
    afnames[14] = "AF_SECURITY"
    afnames[15] = "AF_KEY"
    afnames[16] = "AF_NETLINK"
    afnames[17] = "AF_PACKET"
    afnames[18] = "AF_ASH"
    afnames[19] = "AF_ECONET"
    afnames[20] = "AF_ATMSVC"
    afnames[21] = "AF_RDS"
    afnames[22] = "AF_SNA"
    afnames[23] = "AF_IRDA"
    afnames[24] = "AF_PPPOX"
    afnames[25] = "AF_WANPIPE"
    afnames[26] = "AF_LLC"
    afnames[27] = "AF_IB"
    afnames[28] = "AF_MPLS"
    afnames[29] = "AF_CAN"
    afnames[30] = "AF_TIPC"
    afnames[31] = "AF_BLUETOOTH"
    afnames[32] = "AF_IUCV"
    afnames[33] = "AF_RXRPC"
    afnames[34] = "AF_ISDN"
    afnames[35] = "AF_PHONET"
    afnames[36] = "AF_IEEE802154"
    afnames[37] = "AF_CAIF"
    afnames[38] = "AF_ALG"
    afnames[39] = "AF_NFC"
    afnames[40] = "AF_VSOCK"
    afnames[41] = "AF_KCM"
  }



function filter_p()
  {
    if (target() == 0) return 0; /* system-wide */
    if (!follow_fork && pid() != target()) return 1; /* single-process */
    if (follow_fork && !target_set_pid(pid())) return 1; /* multi-process */
    return 0;
  }

function caps_to_str(caps)
  {
    str = ""
    for (i = 0; i < 37; i++) # CAP_LAST_CAP
      if (caps & (1 << i)) {
        str .= capnames[i]
	if ((caps & ~((1 << (i + 1)) - 1)) != 0)
	  str .= " "
      }
    return str
  }

function dev_to_str(type, dev, access)
  {
    devs = "/dev/"
    if (type == 1) # DEV_BLOCK
      devs .= "block"
    else
      devs .= "char"
    devs .= sprintf("/%d:%d ", dev >> 32, dev & 0xffffffff)
    if (access & 2) # ACC_READ
      devs .= "r"
    if (access & 4) # ACC_WRITE
      devs .= "w"
    if (access & 1) # ACC_MKNOD
      devs .= "m"
    return devs
  }

function afs_to_str(afs)
  {
    str = ""
    for (i = 0; i < 42; i++) # MAX_AF
      if (afs & (1 << i)) {
        str .= afnames[i]
	if ((afs & ~((1 << (i + 1)) - 1)) != 0)
	  str .= " "
      }
    return str
  }

/* Capabilities */
probe kernel.function("cap_capable@security/commoncap.c").return
  {
    if (filter_p()) next;

    if ($return == 0 && $audit)
      used_caps |= 1 << $cap;
    else
      missing_caps |= 1 << $cap;
  }

/* Devices */
probe kernel.function("__devcgroup_check_permission@security/device_cgroup.c").return
  {
    if (filter_p()) next;

    if ($return == 0)
      accessed_devices[$type, $major << 32 | $minor] |= $access
  }

/* RLIMIT_FSIZE */
probe kernel.function("inode_newsize_ok@fs/attr.c").return
  {
    if (filter_p()) next;

    if ($return == 0 && highwatermark_fsize < $offset)
      highwatermark_fsize = $offset
  }

/* RLIMIT_DATA */
probe kernel.function("prctl_set_mm@kernel/sys.c").return
  {
    if (filter_p()) next;

    if ($return == 0 && highwatermark_data < $prctl_map->end_data - $prctl_map->start_data) {
      highwatermark_data = $prctl_map->end_data - $prctl_map->start_data
      print_syscall = 1
    }
  }

probe kernel.function("do_brk@mm/mmap.c").return
  {
    if (filter_p()) next;

    task = task_current()
    if ($return > 0 && highwatermark_data < task->mm->data_vm << 12) { # PAGE_SHIFT
      highwatermark_data = task->mm->data_vm << 12
      print_syscall = 1
    }
    if ($return > 0 && highwatermark_as < task->mm->total_vm << 12) {
      highwatermark_as = task->mm->total_vm << 12
      print_syscall = 1
    }
  }

/* also RLIMIT_STACK and RLIMIT_MEMLOCK */
probe kernel.function("vm_stat_account@mm/mmap.c").return
  {
    if (filter_p()) next;

    if (highwatermark_data < $mm->data_vm << 12) { # PAGE_SHIFT
      highwatermark_data = $mm->data_vm << 12
      print_syscall = 1
    }
    if (highwatermark_stack < $mm->stack_vm << 12) {
      highwatermark_stack = $mm->stack_vm << 12
      print_syscall = 1
    }
    if (highwatermark_memlock < atomic_long_read(&$mm->locked_vm) << 12) {
      highwatermark_memlock = atomic_long_read(&$mm->locked_vm) << 12
      print_syscall = 1
    }
    if (highwatermark_as < $mm->total_vm << 12) {
      highwatermark_as = $mm->total_vm << 12
      print_syscall = 1
    }
  }

/* RLIMIT_CORE */
probe kernel.function("dump_emit@fs/coredump.c").return
  {
    if (filter_p()) next;

    if (highwatermark_core < $cprm->written) {
      highwatermark_core = $cprm->written
      print_syscall = 1
    }
  }

/* RLIMIT_NPROC */
probe kernel.function("commit_creds@kernel/cred.c").return
  {
    if (filter_p()) next;

    if (highwatermark_nproc < atomic_read(&$new->user->processes)) {
      highwatermark_nproc = atomic_read(&$new->user->processes)
      print_syscall = 1
    }
  }

probe kernel.function("copy_process@kernel/fork.c").return
  {
    if (filter_p()) next;
    printf("return %d\n", $return);
    try {
    if (($return > 0 || $return < -1000) && $return->real_cred && $return->real_cred->user)
      printf("good return %d\n", $return);
      if (highwatermark_nproc < atomic_read(&$return->real_cred->user->processes)) {
	highwatermark_nproc = atomic_read(&$return->real_cred->user->processes)
	print_syscall = 1
      }
    } catch {}
  }

/* RLIMIT_NOFILE */
probe kernel.function("__alloc_fd@fs/file.c").return
  {
    if (filter_p()) next;

    if (($return >= 0 || $return < -1000) && highwatermark_nofile < $return) {
      highwatermark_nofile = $return
      print_syscall = 1
    }
  }

probe kernel.function("do_dup2@fs/file.c").return
  {
    if (filter_p()) next;

    if (($return >= 0 || $return < -1000) && highwatermark_nofile < $return) {
      highwatermark_nofile = $return
      print_syscall = 1
    }
  }

/* RLIMIT_MEMLOCK */
probe kernel.function("sys_bpf@kernel/bpf/syscall.c").return
  {
    if (filter_p()) next;

    task = task_current()
    user = task->real_cred->user
    if ($return == 0 && highwatermark_memlock < atomic_long_read(&user->locked_vm) << 12) { # PAGE_SHIFT
      highwatermark_memlock = atomic_long_read(&user->locked_vm) << 12
      print_syscall = 1
    }
  }

probe kernel.function("perf_mmap@kernel/events/core.c").return
  {
    if (filter_p()) next;

    task = task_current()
    if ($return == 0 && highwatermark_memlock < task->mm->pinned_vm << 12) { # PAGE_SHIFT
      highwatermark_memlock = task->mm->pinned_vm << 12
      print_syscall = 1
    }
  }

probe kernel.function("do_mlock@mm/mlock.c").return
  {
    if (filter_p()) next;

    task = task_current()
    if ($return == 0 && highwatermark_memlock < task->mm->locked_vm << 12) { # PAGE_SHIFT
      highwatermark_memlock = task->mm->locked_vm << 12
      print_syscall = 1
    }
  }

probe kernel.function("sys_mlockall@mm/mlock.c").return
  {
    if (filter_p()) next;

    task = task_current()
    if ($return == 0 && highwatermark_memlock < task->mm->total_vm << 12) { # PAGE_SHIFT
      highwatermark_memlock = task->mm->total_vm << 12
      print_syscall = 1
    }
  }

/* RLIMIT_SIGPENDING */
probe kernel.function("__sigqueue_alloc@kernel/signal.c").return
  {
    if (filter_p()) next;

    task = task_current()
    user = task->real_cred->user
    if ($return == 0 && highwatermark_sigpending < atomic_read(&user->sigpending)) {
      highwatermark_sigpending = atomic_read(&user->sigpending)
      print_syscall = 1
    }
  }

/* RLIMIT_MSGGQUEUE */
probe kernel.function("mqueue_get_inode@ipc/mqueue.c").return
  {
    if (filter_p()) next;

    task = task_current()
    user = task->real_cred->user
    if ($return == 0 && highwatermark_msgqueue < user->mq_bytes) {
      highwatermark_msgqueue = user->mq_bytes
      print_syscall = 1
    }
  }

/* RLIMIT_NICE */
probe kernel.function("set_user_nice@kernel/sched/core.c").return
  {
    if (filter_p()) next;

    if (highwatermark_nice < $nice) {
      highwatermark_nice = $nice
      print_syscall = 1
    }
  }

/* RLIMIT_RTPRIO */
probe kernel.function("__sched_setscheduler@kernel/sched/core.c").return
  {
    if (filter_p()) next;

    if (highwatermark_rtprio < $attr->sched_priority) {
      highwatermark_rtprio = $attr->sched_priority
      print_syscall = 1
    }
  }

/* socket address families */
probe kernel.function("__sock_create@net/socket.c").return
  {
    if (filter_p()) next;

    if ($return == 0) {
      used_afs |= 1 << $family
      print_syscall = 1
    } else if ($return == 93) { # EPROTONOSUPPORT
      missing_afs |= 1 << $family
      print_syscall = 1
    }
  }

/* mmap flags */
probe kernel.function("do_mmap@mm/mmap.c").return
  {
    if (filter_p()) next;

    if (($return >= 0 || $return < -1000) && ($flags & (2 | 4)) == (2 | 4)) { # PROT_WRITE | PROT_EXEC
      no_memory_deny_write_execute = 1
      print_syscall = 1
    }
  }

/* system call printing */
probe nd_syscall.* 
  {
    # TODO: filter out apparently-nested syscalls (that are implemented
    # in terms of each other within the kernel); PR6762

    if (filter_p()) next;

    thread_argstr[tid()]=argstr
    if (timestamp || elapsed_time)
      thread_time[tid()]=gettimeofday_us()

    if (name in syscalls_nonreturn)
      report(name,argstr,"")
  }

probe nd_syscall.*.return
  {
    if (filter_p()) next;

    report(name,thread_argstr[tid()],retstr)
  }

function report(syscall_name, syscall_argstr, syscall_retstr)
  {
    if (timestamp || elapsed_time)
      {
        now = gettimeofday_us()
        then = thread_time[tid()]

        if (timestamp)
          prefix=sprintf("%s.%06d ", ctime(then/1000000), then%1000000)

        if (elapsed_time && (now>then)) {
          diff = now-then
          suffix=sprintf(" <%d.%06d>", diff/1000000, diff%1000000)
        }

        delete thread_time[tid()]
      }

    /* add a thread-id string in lots of cases, except if
       stap strace.stp -c SINGLE_THREADED_CMD */
    if (tid() != target()) {
      prefix .= sprintf("%s[%d] ", execname(), tid())
    }

    if (used_caps) {
       suffix .= " [Capabilities=" . caps_to_str(used_caps) . "]"
       all_used_caps |= used_caps
       print_syscall = 1
    }		       
    if (missing_caps) {
       suffix .= " missing [Capabilities=" . caps_to_str(missing_caps) . "]"
       all_missing_caps |= missing_caps
       print_syscall = 1
    }		       

    foreach ([type, dev] in accessed_devices) {
      devs .= dev_to_str(type, dev, accessed_devices[type, dev]) . " "
      if (has_devs == 0) {
        has_devs = 1
	print_syscall = 1
	devs = " [DeviceAllow=" . devs
      }
      all_accessed_devices[type, dev] = accessed_devices[type, dev];
    }
    if (has_devs) {
      devs .= "]"
      suffix .= devs
    }

    if (used_afs) {
      suffix .= " [RestrictAddressFamilies=" . afs_to_str(used_afs) . "]"
      all_used_afs |= used_afs
      print_syscall = 1
    }		       
    if (missing_afs) {
      suffix .= " missing [RestrictAddressFamilies=" . afs_to_str(missing_afs) . "]"
      all_missing_afs |= missing_afs
      print_syscall = 1
    }		       

    if (no_memory_deny_write_execute) {
      suffix .= " [MemoryDenyWriteExecute=false]"
      all_memory_deny_write_execute = "false"
    }		       

    if (highwatermark_fsize > old_highwatermark_fsize) {
      suffix .= sprintf(" [FSIZE %d -> %d]", old_highwatermark_fsize, highwatermark_fsize)
      old_highwatermark_fsize = highwatermark_fsize
    }
    if (highwatermark_data > old_highwatermark_data) {
      suffix .= sprintf(" [DATA %d -> %d]", old_highwatermark_data, highwatermark_data)
      old_highwatermark_data = highwatermark_data
    }
    if (highwatermark_stack > old_highwatermark_stack) {
      suffix .= sprintf(" [STACK %d -> %d]", old_highwatermark_stack, highwatermark_stack)
      old_highwatermark_stack = highwatermark_stack
    }
    if (highwatermark_core > old_highwatermark_core) {
      suffix .= sprintf(" [CORE %d -> %d]", old_highwatermark_core, highwatermark_core)
      old_highwatermark_core = highwatermark_core
    }
    if (highwatermark_nofile > old_highwatermark_nofile) {
      suffix .= sprintf(" [NOFILE %d -> %d]", old_highwatermark_nofile, highwatermark_nofile)
      old_highwatermark_nofile = highwatermark_nofile
    }
    if (highwatermark_as > old_highwatermark_as) {
      suffix .= sprintf(" [AS %d -> %d]", old_highwatermark_as, highwatermark_as)
      old_highwatermark_as = highwatermark_as
    }
    if (highwatermark_nproc > old_highwatermark_nproc) {
      suffix .= sprintf(" [NPROC %d -> %d]", old_highwatermark_nproc, highwatermark_nproc)
      old_highwatermark_nproc = highwatermark_nproc
    }
    if (highwatermark_memlock > old_highwatermark_memlock) {
      suffix .= sprintf(" [MEMLOCK %d -> %d]", old_highwatermark_memlock, highwatermark_memlock)
      old_highwatermark_memlock = highwatermark_memlock
    }
    if (highwatermark_sigpending > old_highwatermark_sigpending) {
      suffix .= sprintf(" [SIGPENDING %d -> %d]", old_highwatermark_sigpending, highwatermark_sigpending)
      old_highwatermark_sigpending = highwatermark_sigpending
    }
    if (highwatermark_msgqueue > old_highwatermark_msgqueue) {
      suffix .= sprintf(" [MSGQUEUE %d -> %d]", old_highwatermark_msgqueue, highwatermark_msgqueue)
      old_highwatermark_msgqueue = highwatermark_msgqueue
    }
    if (highwatermark_nice > old_highwatermark_nice) {
      suffix .= sprintf(" [NICE %d -> %d]", old_highwatermark_nice, highwatermark_nice)
      old_highwatermark_nice = highwatermark_nice
    }
    if (highwatermark_rtprio > old_highwatermark_rtprio) {
      suffix .= sprintf(" [RTPRIO %d -> %d]", old_highwatermark_rtprio, highwatermark_rtprio)
      old_highwatermark_rtprio = highwatermark_rtprio
    }

    if (!only_capability_use || print_syscall)
        printf("%s%s(%s) = %s%s\n",
             prefix, 
             syscall_name, syscall_argstr, syscall_retstr,
	     suffix)

    used_caps = 0
    missing_caps = 0
    used_afs = 0
    print_syscall = 0
    no_memory_deny_write_execute = 0
    delete accessed_devices

    delete thread_argstr[tid()]
  }

probe end
  {
    printf("\nSummary:\n")
    printf("CapabilityBoundingSet=%s\n", caps_to_str(all_used_caps))
    if (all_missing_caps)
	    printf("Consider also missing CapabilityBoundingSet=%s\n", caps_to_str(all_missing_caps))
    foreach ([type, dev] in all_accessed_devices)
      printf("DeviceAllow=%s\n", dev_to_str(type, dev, all_accessed_devices[type, dev]))
    printf("LimitFSIZE=%d\n", highwatermark_fsize)
    printf("LimitDATA=%d\n", highwatermark_data)
    printf("LimitSTACK=%d\n", highwatermark_stack)
    printf("LimitCORE=%d\n", highwatermark_core)
    printf("LimitNOFILE=%d\n", highwatermark_nofile)
    printf("LimitAS=%d\n", highwatermark_as)
    printf("LimitNPROC=%d\n", highwatermark_nproc)
    printf("LimitMEMLOCK=%d\n", highwatermark_memlock)
    printf("LimitSIGPENDING=%d\n", highwatermark_sigpending)
    printf("LimitMSGQUEUE=%d\n", highwatermark_msgqueue)
    printf("LimitNICE=%d\n", highwatermark_nice)
    printf("LimitRTPRIO=%d\n", highwatermark_rtprio)
    printf("RestrictAddressFamilies=%s\n", afs_to_str(all_used_afs))
    if (all_missing_afs)
	    printf("Consider also missing RestrictAddressFamilies=%s\n", afs_to_str(all_missing_afs))
    printf("MemoryDenyWriteExecute=%s\n", all_memory_deny_write_execute)
  }