#! stap

global pidnames, faults, fault_types

probe kernel.function(%( kernel_v > "2.6.9" %? "__handle_mm_fault"
                                          %: "handle_mm_fault" %)) {

   # Maintain a pid-to-execname mapping.  This logic should get transplanted
   # into a tapset script that is automatically included upon reference to
   # its exported global variable.
   pidnames[pid()] = execname()

   faults [pid(), $write_access ? 1 : 0] ++
}

# (needed only until bug 1132 supports $retvalue)
function get_retvalue:long () %{ THIS->__retvalue = fetch_register(0); %}

probe kernel.function(%( kernel_v > "2.6.9" %? "__handle_mm_fault"
                                          %: "handle_mm_fault" %)).return {
  fault_types [pid(), get_retvalue()] ++
}


# Some constants, to come from a future "VM tapset"

global VM_FAULT_OOM, VM_FAULT_SIGBUS, VM_FAULT_MINOR, VM_FAULT_MAJOR
probe begin {
  VM_FAULT_OOM=-1
  VM_FAULT_SIGBUS=0
  VM_FAULT_MINOR=1
  VM_FAULT_MAJOR=2
}


# Shut down the probing session after a while
probe timer.ms(1000) { report() }
probe timer.ms(10000) { exit() }

function _(n) { return sprint(n) } # let's abbreviate

function report () {
  print ("time=" . _(gettimeofday_s()) . "\n")
  foreach ([pid] in pidnames) {
    if (faults[pid,0]+faults[pid,1] == 0) continue
    print (pidnames[pid] . "[" . _(pid) . "]" .
           " reads=" . _(faults[pid,0]) . 
           " writes=" . _(faults[pid,1]) .
           " oom=" . _(fault_types[pid,VM_FAULT_OOM]) .
           " sigbus=" . _(fault_types[pid,VM_FAULT_SIGBUS]) .
           " minor=" . _(fault_types[pid,VM_FAULT_MINOR]) .
           " major=" . _(fault_types[pid,VM_FAULT_MAJOR]) .
           "\n")
    }
  delete faults
  delete fault_types
}

probe begin {
  print ("Page fault tracking, start time=" . _(gettimeofday_s()) . "\n")
}
probe end {
  print ("Page fault tracking, end time=" . _(gettimeofday_s()) . "\n")
}