[PATCH 04/13] spawn: support RLIMIT_CPU, RLIMIT_DATA and RLIMIT_CORE

[Eric Wong <e@80x24.org>]

We'll be spawning cgit and git-diff, which can take gigantic
amounts of CPU time and/or heap given the right (ermm... wrong)
input.  Limit the damage that large/expensive diffs can cause.
---
 lib/PublicInbox/Spawn.pm   | 43 ++++++++++++++++++++++++++++++++++----
 lib/PublicInbox/SpawnPP.pm |  9 ++++++--
 t/spawn.t                  | 18 ++++++++++++++++
 3 files changed, 64 insertions(+), 6 deletions(-)

diff --git a/lib/PublicInbox/Spawn.pm b/lib/PublicInbox/Spawn.pm
index 91a3c12..8ea255a 100644
--- a/lib/PublicInbox/Spawn.pm
+++ b/lib/PublicInbox/Spawn.pm
@@ -22,6 +22,8 @@ our @EXPORT_OK = qw/which spawn popen_rd/;
 my $vfork_spawn = <<'VFORK_SPAWN';
 #include <sys/types.h>
 #include <sys/uio.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include <unistd.h>
 #include <alloca.h>
 #include <signal.h>
@@ -74,11 +76,12 @@ static void xerr(const char *msg)
  * whatever we'll need in the future.
  * Be sure to update PublicInbox::SpawnPP if this changes
  */
-int public_inbox_fork_exec(int in, int out, int err,
-			SV *file, SV *cmdref, SV *envref)
+int pi_fork_exec(int in, int out, int err,
+			SV *file, SV *cmdref, SV *envref, SV *rlimref)
 {
 	AV *cmd = (AV *)SvRV(cmdref);
 	AV *env = (AV *)SvRV(envref);
+	AV *rlim = (AV *)SvRV(rlimref);
 	const char *filename = SvPV_nolen(file);
 	pid_t pid;
 	char **argv, **envp;
@@ -99,12 +102,27 @@ int public_inbox_fork_exec(int in, int out, int err,
 	pid = vfork();
 	if (pid == 0) {
 		int sig;
+		I32 i, max;
 
 		REDIR(in, 0);
 		REDIR(out, 1);
 		REDIR(err, 2);
 		for (sig = 1; sig < NSIG; sig++)
 			signal(sig, SIG_DFL); /* ignore errors on signals */
+
+		max = av_len(rlim);
+		for (i = 0; i < max; i += 3) {
+			struct rlimit rl;
+			SV **res = av_fetch(rlim, i, 0);
+			SV **soft = av_fetch(rlim, i + 1, 0);
+			SV **hard = av_fetch(rlim, i + 2, 0);
+
+			rl.rlim_cur = SvIV(*soft);
+			rl.rlim_max = SvIV(*hard);
+			if (setrlimit(SvIV(*res), &rl) < 0)
+				xerr("sertlimit");
+		}
+
 		/*
 		 * don't bother unblocking, we don't want signals
 		 * to the group taking out a subprocess
@@ -145,7 +163,7 @@ if (defined $vfork_spawn) {
 unless (defined $vfork_spawn) {
 	require PublicInbox::SpawnPP;
 	no warnings 'once';
-	*public_inbox_fork_exec = *PublicInbox::SpawnPP::public_inbox_fork_exec
+	*pi_fork_exec = *PublicInbox::SpawnPP::pi_fork_exec
 }
 
 # n.b. we never use absolute paths with this
@@ -182,7 +200,24 @@ sub spawn ($;$$) {
 	my $in = $opts->{0} || 0;
 	my $out = $opts->{1} || 1;
 	my $err = $opts->{2} || 2;
-	my $pid = public_inbox_fork_exec($in, $out, $err, $f, $cmd, \@env);
+	my $rlim = [];
+
+	foreach my $l (qw(RLIMIT_CPU RLIMIT_CORE RLIMIT_DATA)) {
+		defined(my $v = $opts->{$l}) or next;
+		my ($soft, $hard);
+		if (ref($v)) {
+			($soft, $hard) = @$v;
+		} else {
+			$soft = $hard = $v;
+		}
+		my $r = eval "require BSD::Resource; BSD::Resource::$l();";
+		unless (defined $r) {
+			warn "$l undefined by BSD::Resource: $@\n";
+			next;
+		}
+		push @$rlim, $r, $soft, $hard;
+	}
+	my $pid = pi_fork_exec($in, $out, $err, $f, $cmd, \@env, $rlim);
 	$pid < 0 ? undef : $pid;
 }
 
diff --git a/lib/PublicInbox/SpawnPP.pm b/lib/PublicInbox/SpawnPP.pm
index 743db22..8692b76 100644
--- a/lib/PublicInbox/SpawnPP.pm
+++ b/lib/PublicInbox/SpawnPP.pm
@@ -9,8 +9,8 @@ use warnings;
 use POSIX qw(dup2 :signal_h);
 
 # Pure Perl implementation for folks that do not use Inline::C
-sub public_inbox_fork_exec ($$$$$$) {
-	my ($in, $out, $err, $f, $cmd, $env) = @_;
+sub pi_fork_exec ($$$$$$) {
+	my ($in, $out, $err, $f, $cmd, $env, $rlim) = @_;
 	my $old = POSIX::SigSet->new();
 	my $set = POSIX::SigSet->new();
 	$set->fillset or die "fillset failed: $!";
@@ -22,6 +22,11 @@ sub public_inbox_fork_exec ($$$$$$) {
 		$pid = -1;
 	}
 	if ($pid == 0) {
+		while (@$rlim) {
+			my ($r, $soft, $hard) = splice(@$rlim, 0, 3);
+			BSD::Resource::setrlimit($r, $soft, $hard) or
+			  warn "failed to set $r=[$soft,$hard]\n";
+		}
 		if ($in != 0) {
 			dup2($in, 0) or die "dup2 failed for stdin: $!";
 		}
diff --git a/t/spawn.t b/t/spawn.t
index db3f2dc..5abedc9 100644
--- a/t/spawn.t
+++ b/t/spawn.t
@@ -92,6 +92,24 @@ use PublicInbox::Spawn qw(which spawn popen_rd);
 	isnt($?, 0, '$? set properly: '.$?);
 }
 
+SKIP: {
+	eval {
+		require BSD::Resource;
+		defined(BSD::Resource::RLIMIT_CPU())
+	} or skip 'BSD::Resource::RLIMIT_CPU missing', 3;
+	my ($r, $w);
+	pipe($r, $w) or die "pipe: $!";
+	my $cmd = ['sh', '-c', 'while true; do :; done'];
+	my $opt = { RLIMIT_CPU => [ 1, 1 ], RLIMIT_CORE => 0, 1 => fileno($w) };
+	my $pid = spawn($cmd, undef, $opt);
+	close $w or die "close(w): $!";
+	my $rset = '';
+	vec($rset, fileno($r), 1) = 1;
+	ok(select($rset, undef, undef, 5), 'child died before timeout');
+	is(waitpid($pid, 0), $pid, 'XCPU child process reaped');
+	isnt($?, 0, 'non-zero exit status');
+}
+
 done_testing();
 
 1;
-- 
EW