#!/usr/bin/perl
#
# This script accumulates the execution paths of all calls to kmalloc
# in the kernel.  On Ctrl-C (or exit of the command provided by -c option),
# it sorts, filters and displays them on
# stdout.
#
# The -e (exclude) option can be used to specify a comma-separated list
# - any stack with contents matching any of the items in the list will
# be excluded from the output.
#
# The -m (min) option can be used to specify the minimum number of
# occurrences a stack needs to be included in the output.
#
# The -t (top) option can be used to specify printing only the 
# top N stack traces.
#
# The -c (command) option runs starts the command and script
# only runs for the duration of the command.
#
# The -o (options) option passes the options to systemap.
#
# Usage: ./kmalloc-top [-m min] [-e exclude list] [-t top_n] [-c command]
#           [-o options]
# Ctrl-c

use Getopt::Std;

my $kmalloc_stacks;
my $total_kmallocs;
my $filtered_kmallocs;
my $sorted_stacks;
my $first_n = 1000000000;
my $min_count = 1;
my $exclude;
my $options;

$SIG{INT} = \&sigint_handler;

getopts('c:e:m:t:o:');

if ($opt_e) {
    $exclude = join('|', split(/,/, $opt_e));
    print "Will exclude stacks containing: $exclude\n";
}

if ($opt_t) {
    $first_n = $opt_t;
    print "Will print only the top $first_n stacks.\n";
}

if ($opt_m) {
    $min_count = $opt_m;
}

if ($opt_c) {
    $command="-c \"$opt_c\""
}

if ($opt_o) {
    $options=$opt_o
}

print "Will print stacks with counts >= $min_count.\n";
print STDERR "Press Ctrl-C to stop.\n";

#The systemtap script that instruments the kmalloc
$script="
global kmalloc_stack

probe kernel.function(\"__kmalloc\") { kmalloc_stack[backtrace()]++ }

probe timer.ms(100), end
{
  foreach (stack in kmalloc_stack) {
    printf(\"<hashkey>\\n\")
    print_syms(stack) 
    printf(\"</hashkey>\\n\")
    printf(\"<hashval>%d</hashval>\\n\", kmalloc_stack[stack])
  }
  delete kmalloc_stack
}
";

open STREAM, "stap $options -e '$script' $command|" or die "Couldn't get output stream $!";

while (<STREAM>) {
    if (/<hashval>(.*?)<\/hashval>/) {
	update_hash($key, $1);
	$key = "";
    } elsif ($_ !~ (/<hashkey>|<\/hashkey>/))  {
	$key .= $_;
    }
}

$num_keys_before_filtering = scalar keys %kmalloc_stacks;
$total_kmallocs = count_kmallocs();
filter_stacks();
sort_stacks();
top_stacks();
sort_stacks();
$num_keys_after_filtering = scalar keys %kmalloc_stacks;
$filtered_kmallocs = count_kmallocs();
summarize();
exit();

sub update_hash
{
    my($key, $val) = @_;
    $kmalloc_stacks{$key} += $val;
}

sub filter_stacks
{
    while (($stack, $count) = each %kmalloc_stacks) {
	if ($count < $min_count) {
	    delete $kmalloc_stacks{$stack};
	} elsif ($exclude && $stack =~ /$exclude/) {
	    delete $kmalloc_stacks{$stack};
	}
    }
}

sub top_stacks
{
    $count=0;
    foreach $stack(@sorted_stacks) {
	$count+=1;
	if ($count > $first_n) {
	    delete $kmalloc_stacks{$stack};
	}
    }
}

sub sort_stacks
{
    @sorted_stacks = sort { $kmalloc_stacks{$b} <=> $kmalloc_stacks{$a} } keys %kmalloc_stacks;
}

sub count_kmallocs {
    $count = 0;
    foreach $stack(%kmalloc_stacks) {
	$count += $kmalloc_stacks{$stack};
    }
    return $count;
}

sub summarize {
    print "\n";
    foreach $stack(@sorted_stacks) {
	print "This path seen $kmalloc_stacks{$stack} times:\n$stack\n";
    }

    if ($total_kmallocs > 0) {
	$percent = ($filtered_kmallocs)*100/$total_kmallocs;
    } else {
	$percent = 0;
    }
    print "Num stacks before filtering: $num_keys_before_filtering\n";
    print "Num stacks after filtering: $num_keys_after_filtering\n";
    print "Total kmallocs (before filtering): $total_kmallocs\n";
    print "Total kmallocs (after filtering): $filtered_kmallocs\n";
    print "The filter stacks have $percent of the total kmallocs\n";

    close(STREAM);
}

sub sigint_handler
{
    system("pkill kmalloc-stacks");
}