#!/usr/bin/perl
#
# errinfo - report on syscall failures and print errno error messages.
#	    Written using Perl and DTrace (Solaris 10 03/05)
#
# When system calls fail, an errno variable is set to convay a meaningful
# message to the end user - so long as the program does something with it
# (eg, "ls" printing "No such file or directory"). This program fetches
# and prints details for all syscall failures along with their message,
# whether the failing program is already printing this info or not.
#
# $Id: errinfo 3 2007-08-01 10:50:08Z brendan $
#
# USAGE:	errinfo [-ch] [-p PID] [-n name]
#
#		-c		# counts - aggregate style
#		-p PID		# examine this PID only
#		-n name		# examine processes with this name only
#	eg,
#		errinfo			# default output - snoop event style
#		errinfo -n ssh		# examine "ssh" processes only
#		errinfo -cn ssh		# examine "ssh" using counts
#
# FIELDS:
#		EXEC		Program name (truncated)
#		SYSCALL		System call name
#		ERR		Value of errno
#		DESC		Description of errno message
#
# SEE ALSO:	/usr/include/sys/errno.h
#
# COPYRIGHT: Copyright (c) 2005, 2006 Brendan Gregg.
#
# CDDL HEADER START
#
#  The contents of this file are subject to the terms of the
#  Common Development and Distribution License, Version 1.0 only
#  (the "License").  You may not use this file except in compliance
#  with the License.
#
#  You can obtain a copy of the license at Docs/cddl1.txt
#  or http://www.opensolaris.org/os/licensing.
#  See the License for the specific language governing permissions
#  and limitations under the License.
#
# CDDL HEADER END
#
# Author: Brendan Gregg  [Sydney, Australia]
#
# 18-Apr-2005   Brendan Gregg   Created this.
# 20-Apr-2006	   "      "	Last update.
#

use Getopt::Std;

#
#  Defaults
#
$FILTER = "";
$COUNT = 0;

#
#  Command line arguments
#
&Usage() if $ARGV[0] eq "--help";
getopts('ch:n:p:') || &Usage();
&Usage() if $opt_h;
$COUNT = 1 if $opt_c;
$FILTER = "&& execname == \"$opt_n\"" if defined $opt_n;
$FILTER = "&& pid == $opt_p" if defined $opt_p;

#
#  Load errno descriptions
#
open(ERRNO,"/usr/include/sys/errno.h") || die "ERROR1: reading errno.h: $!\n";
while (chomp($line = <ERRNO>)) {
	next unless $line =~ /^#define/;
	($errno,$desc) = $line =~ /^#define\s+\S+\s+(\d+)\s+\/\*(.*)\*\//;
	$Errno{$errno} = $desc;
}
close ERRNO;

#
#  Declare DTrace script
#
 if ($COUNT) {		# aggregate style
$dtrace = <<END;
/usr/sbin/dtrace -n '
	#pragma D option quiet
	syscall:::return 
	/errno != 0 && pid != \$pid $FILTER/ 
	{ 
		\@Errs[execname, probefunc, errno] = count(); 
	}
	dtrace:::END {
		printa("%s %s %d %\@d\\n", \@Errs);
	}'
END
 } else {		# snoop style
$dtrace = <<END; 
/usr/sbin/dtrace -n '
	#pragma D option quiet
	#pragma D option switchrate=5hz
	syscall:::return 
	/errno != 0 && pid != \$pid $FILTER/ 
	{ 
		printf("%s %s %d\\n", execname, probefunc, errno); 
	}'
END
 }

#
#  Cleanup on signals
#
$SIG{INT} = \&Cleanup_Signal;    # Ctrl-C
$SIG{QUIT} = \&Cleanup_Signal;   # Ctrl-\
$SIG{TERM} = \&Cleanup_Signal;   # TERM

#
#  Run DTrace, process output
#

if ($COUNT) {
	print STDERR "Tracing... Hit Ctrl-C to end.\n";
	$header = 1;
} else {
	printf("%16s %16s %4s  %s\n","EXEC","SYSCALL","ERR","DESC");
}

### Open DTrace
open(DTRACE,"$dtrace |") || die "ERROR2: Can't start dtrace (perms?): $!\n";

### Process DTrace output
while (chomp($line = <DTRACE>)) {

	### Print count header
	if ($COUNT && $header) {
		printf("\n%16s %16s %4s %6s  %s\n",
		 "EXEC","SYSCALL","ERR","COUNT","DESC");
		$header = 0;
	}

	### Split data
	($execname,$syscall,$errno,$counts) = split(' ',$line);
	next if $errno eq "";

	### Fetch errno description
	$desc = $Errno{$errno};

	### Print output line
	if ($COUNT) {
		printf("%16s %16s %4d %6d %s\n",
		 $execname,$syscall,$errno,$counts,$desc);
	} else {
		printf("%16s %16s %4d %s\n",$execname,$syscall,$errno,$desc);
	}
}
close(DTRACE);

#
#  Triggered by signals
#
sub Cleanup_Signal {
}

#
#  Usage message
#
sub Usage {
        print STDERR "USAGE: errinfo [-ch] [-p PID] [-n name]\n";
	print STDERR <<ENDUSAGE;
     eg,
       errinfo       # default output - snoop event style
          -c         # counts - aggregate style
          -p 871     # examine PID 871 only
          -n ssh     # examine processes with the name "ssh" only
          -cn ssh    # examine "ssh" using counts
ENDUSAGE
        exit(1);
}