From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
X-Spam-Status: No, score=-4.2 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00,
	DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,
	T_SCC_BODY_TEXT_LINE shortcircuit=no autolearn=ham autolearn_force=no
	version=3.4.6
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id 17BC71F4BE
	for <meta@public-inbox.org>; Mon, 29 Jan 2024 21:27:56 +0000 (UTC)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=80x24.org;
	s=selector1; t=1706563676;
	bh=noaGeD0faAKijEYAsYRiu4MVjVrIAdkIsHt8sq18cHQ=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=m7GatSEfmPPq4SGY3hnHAIY406JHoJ5DqogS0ahMFbI6mAB3REbDndM3ThJEWtObJ
	 9BnBTEmoMBGSueGMP6ZedYFWFUttzWGpc7sHlAgxfxVWC/pWGbfX5+ZSymCDHiIn1g
	 wC4X1Ik3TfO0rbwV99Ed0KH+jWEDSblVClrPBpxU=
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 2/2] syscall: use pure Perl sendmsg/recvmsg on *BSD
Date: Mon, 29 Jan 2024 21:23:19 +0000
Message-ID: <20240129212319.98910-3-e@80x24.org>
In-Reply-To: <20240129212319.98910-1-e@80x24.org>
References: <20240129212319.98910-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

While syscall symbols (e.g. SYS_*) have changed on us in FreeBSD
during the history of Sys::Syscall and this project and did bite
us in some cases; the actual numbers don't get recycled for new
syscalls.  We're also fortunate that sendmsg and recvmsg syscalls
and associated msghdr and cmsg structs predate the BSD forks and
are compatible across all the BSDs I've tried.

OpenBSD routes Perl `syscall' through libc; while NetBSD + FreeBSD
document procedures for maintaining backwards compatibility.
It looks like Dragonfly follows FreeBSD, here.

Tested on i386 OpenBSD, and amd64 {Free,Net,Open,Dragonfly}BSD

This enables *BSD users to use lei, -cindex and future SCM_RIGHTS-only
features without needing Inline::C.

[1] https://cvsweb.openbsd.org/src/gnu/usr.bin/perl/gen_syscall_emulator.pl
[2] https://www.netbsd.org/docs/internals/en/chap-processes.html#syscall_versioning
[3] https://wiki.freebsd.org/AddingSyscalls#Backward_compatibily
---
 devel/sysdefs-list         |   9 +++-
 lib/PublicInbox/Syscall.pm | 102 +++++++++++++++++++++++--------------
 t/cmd_ipc.t                |   9 ++--
 3 files changed, 74 insertions(+), 46 deletions(-)

diff --git a/devel/sysdefs-list b/devel/sysdefs-list
index 61532cf2..ba51de6c 100755
--- a/devel/sysdefs-list
+++ b/devel/sysdefs-list
@@ -2,8 +2,6 @@
 # License: AGPL-3.0+ <http://www.gnu.org/licenses/agpl-3.0.txt>
 # Dump system-specific constant numbers this is to maintain
 # PublicInbox::Syscall and any other system-specific pieces.
-# DO NOT USE syscall numbers for *BSDs, none of the current BSD kernels
-# we know about promise stable syscall numbers (unlike Linux).
 # However, sysconf(3) constants are stable ABI on all safe to dump.
 eval 'exec perl -S $0 ${1+"$@"}' # no shebang
 	if 0; # running under some shell
@@ -179,5 +177,12 @@ int main(void)
 		PR_NUM(cmsg_type);
 	STRUCT_END;
 
+	{
+		struct cmsghdr cmsg;
+		uintptr_t cmsg_data_off;
+		cmsg_data_off = (uintptr_t)CMSG_DATA(&cmsg) - (uintptr_t)&cmsg;
+		D(cmsg_data_off);
+	}
+
 	return 0;
 }
diff --git a/lib/PublicInbox/Syscall.pm b/lib/PublicInbox/Syscall.pm
index 9071e6b1..829cfa3c 100644
--- a/lib/PublicInbox/Syscall.pm
+++ b/lib/PublicInbox/Syscall.pm
@@ -22,7 +22,7 @@ use POSIX qw(ENOENT ENOSYS EINVAL O_NONBLOCK);
 use Socket qw(SOL_SOCKET SCM_RIGHTS);
 use Config;
 our %SIGNUM = (WINCH => 28); # most Linux, {Free,Net,Open}BSD, *Darwin
-our $INOTIFY;
+our ($INOTIFY, %PACK);
 
 # $VERSION = '0.25'; # Sys::Syscall version
 our @EXPORT_OK = qw(epoll_ctl epoll_create epoll_wait
@@ -44,26 +44,21 @@ use constant {
 	EPOLL_CTL_MOD => 3,
 	SIZEOF_int => $Config{intsize},
 	SIZEOF_size_t => $Config{sizesize},
+	SIZEOF_ptr => $Config{ptrsize},
 	NUL => "\0",
 };
 
-use constant {
-	TMPL_size_t => SIZEOF_size_t == 8 ? 'Q' : 'L',
-	BYTES_4_hole => SIZEOF_size_t == 8 ? 'L' : '',
-	# cmsg_len, cmsg_level, cmsg_type
-	SIZEOF_cmsghdr => SIZEOF_int * 2 + SIZEOF_size_t,
-};
-
-my @BYTES_4_hole = BYTES_4_hole ? (0) : ();
+use constant TMPL_size_t => SIZEOF_size_t == 8 ? 'Q' : 'L';
 
 our ($SYS_epoll_create,
 	$SYS_epoll_ctl,
 	$SYS_epoll_wait,
 	$SYS_signalfd4,
 	$SYS_renameat2,
-	$F_SETPIPE_SZ);
+	$F_SETPIPE_SZ,
+	$SYS_sendmsg,
+	$SYS_recvmsg);
 
-my ($SYS_sendmsg, $SYS_recvmsg);
 my $SYS_fstatfs; # don't need fstatfs64, just statfs.f_type
 my ($FS_IOC_GETFLAGS, $FS_IOC_SETFLAGS);
 my $SFD_CLOEXEC = 02000000; # Perl does not expose O_CLOEXEC
@@ -78,7 +73,7 @@ if ($^O eq "linux") {
 	# boundaries.
 	my $u64_mod_8 = 0;
 
-	if ($Config{ptrsize} == 4) {
+	if (SIZEOF_ptr == 4) {
 		# if we're running on an x86_64 kernel, but a 32-bit process,
 		# we need to use the x32 or i386 syscall numbers.
 		if ($machine eq 'x86_64') {
@@ -281,16 +276,52 @@ EOM
 		*epoll_wait = \&epoll_wait_mod4;
 		*epoll_ctl = \&epoll_ctl_mod4;
 	}
+} elsif ($^O =~ /\A(?:freebsd|openbsd|netbsd|dragonfly)\z/) {
+# don't use syscall.ph here, name => number mappings are not stable on *BSD
+# but the actual numbers are.
+# OpenBSD perl redirects syscall perlop to libc functions
+# https://cvsweb.openbsd.org/src/gnu/usr.bin/perl/gen_syscall_emulator.pl
+# https://www.netbsd.org/docs/internals/en/chap-processes.html#syscall_versioning
+# https://wiki.freebsd.org/AddingSyscalls#Backward_compatibily
+# (I'm assuming Dragonfly copies FreeBSD, here, too)
+	$SYS_recvmsg = 27;
+	$SYS_sendmsg = 28;
+}
+
+BEGIN {
+	if ($^O eq 'linux') {
+		%PACK = (
+			TMPL_cmsg_len => TMPL_size_t,
+			# cmsg_len, cmsg_level, cmsg_type
+			SIZEOF_cmsghdr => SIZEOF_int * 2 + SIZEOF_size_t,
+			CMSG_DATA_off => '',
+			TMPL_msghdr => 'PL' . # msg_name, msg_namelen
+				'@'.(2 * SIZEOF_ptr).'P'. # msg_iov
+				'i'. # msg_iovlen
+				'@'.(4 * SIZEOF_ptr).'P'. # msg_control
+				'L'. # msg_controllen (socklen_t)
+				'i', # msg_flags
+		);
+	} elsif ($^O =~ /\A(?:freebsd|openbsd|netbsd|dragonfly)\z/) {
+		%PACK = (
+			TMPL_cmsg_len => 'L', # socklen_t
+			SIZEOF_cmsghdr => SIZEOF_int * 3,
+			CMSG_DATA_off => SIZEOF_ptr == 8 ? '@16' : '',
+			TMPL_msghdr => 'PL' . # msg_name, msg_namelen
+				'@'.(2 * SIZEOF_ptr).'P'. # msg_iov
+				TMPL_size_t. # msg_iovlen
+				'@'.(4 * SIZEOF_ptr).'P'. # msg_control
+				TMPL_size_t. # msg_controllen
+				'i', # msg_flags
+
+		)
+	}
+	$PACK{CMSG_ALIGN_size} = SIZEOF_size_t;
 }
 
 # SFD_CLOEXEC is arch-dependent, so IN_CLOEXEC may be, too
 $INOTIFY->{IN_CLOEXEC} //= 0x80000 if $INOTIFY;
 
-# use Inline::C for *BSD-only or general POSIX stuff.
-# Linux guarantees stable syscall numbering, BSDs only offer a stable libc
-# use devel/sysdefs-list on Linux to detect new syscall numbers and
-# other system constants
-
 sub epoll_create {
 	syscall($SYS_epoll_create, $no_deprecated ? 0 : 100);
 }
@@ -420,11 +451,13 @@ sub nodatacow_dir {
 	if (open my $fh, '<', $_[0]) { nodatacow_fh($fh) }
 }
 
-sub CMSG_ALIGN ($) { ($_[0] + SIZEOF_size_t - 1) & ~(SIZEOF_size_t - 1) }
+use constant \%PACK;
+sub CMSG_ALIGN ($) { ($_[0] + CMSG_ALIGN_size - 1) & ~(CMSG_ALIGN_size - 1) }
 use constant CMSG_ALIGN_SIZEOF_cmsghdr => CMSG_ALIGN(SIZEOF_cmsghdr);
 sub CMSG_SPACE ($) { CMSG_ALIGN($_[0]) + CMSG_ALIGN_SIZEOF_cmsghdr }
 sub CMSG_LEN ($) { CMSG_ALIGN_SIZEOF_cmsghdr + $_[0] }
-use constant msg_controllen => CMSG_SPACE(10 * SIZEOF_int) + 16; # 10 FDs
+use constant msg_controllen_max =>
+	CMSG_SPACE(10 * SIZEOF_int) + SIZEOF_cmsghdr; # space for 10 FDs
 
 if (defined($SYS_sendmsg) && defined($SYS_recvmsg)) {
 no warnings 'once';
@@ -436,20 +469,15 @@ require PublicInbox::CmdIPC4;
 			$_[2] // NUL, length($_[2] // NUL) || 1);
 	my $fd_space = scalar(@$fds) * SIZEOF_int;
 	my $msg_controllen = CMSG_SPACE($fd_space);
-	my $cmsghdr = pack(TMPL_size_t . # cmsg_len
+	my $cmsghdr = pack(TMPL_cmsg_len .
 			'LL' .  # cmsg_level, cmsg_type,
-			('i' x scalar(@$fds)) . # CMSG_DATA
+			CMSG_DATA_off.('i' x scalar(@$fds)). # CMSG_DATA
 			'@'.($msg_controllen - 1).'x1', # pad to space, not len
 			CMSG_LEN($fd_space), # cmsg_len
 			SOL_SOCKET, SCM_RIGHTS, # cmsg_{level,type}
 			@$fds); # CMSG_DATA
-	my $mh = pack('PL' . # msg_name, msg_namelen (socklen_t (U32))
-			BYTES_4_hole . # 4-byte padding on 64-bit
-			'P'.TMPL_size_t . # msg_iov, msg_iovlen,
-			'P'.TMPL_size_t . # msg_control, msg_controllen,
-			'i', # msg_flags
-			NUL, 0, # msg_name, msg_namelen (unused)
-			@BYTES_4_hole,
+	my $mh = pack(TMPL_msghdr,
+			undef, 0, # msg_name, msg_namelen (unused)
 			$iov, 1, # msg_iov, msg_iovlen
 			$cmsghdr, # msg_control
 			$msg_controllen,
@@ -465,18 +493,13 @@ require PublicInbox::CmdIPC4;
 *recv_cmd4 = sub ($$$) {
 	my ($sock, undef, $len) = @_;
 	vec($_[1] //= '', $len - 1, 8) = 0;
-	my $cmsghdr = "\0" x msg_controllen; # 10 * sizeof(int)
+	my $cmsghdr = "\0" x msg_controllen_max; # 10 * sizeof(int)
 	my $iov = pack('P'.TMPL_size_t, $_[1], $len);
-	my $mh = pack('PL' . # msg_name, msg_namelen (socklen_t (U32))
-			BYTES_4_hole . # 4-byte padding on 64-bit
-			'P'.TMPL_size_t . # msg_iov, msg_iovlen,
-			'P'.TMPL_size_t . # msg_control, msg_controllen,
-			'i', # msg_flags
-			NUL, 0, # msg_name, msg_namelen (unused)
-			@BYTES_4_hole,
+	my $mh = pack(TMPL_msghdr,
+			undef, 0, # msg_name, msg_namelen (unused)
 			$iov, 1, # msg_iov, msg_iovlen
 			$cmsghdr, # msg_control
-			msg_controllen,
+			msg_controllen_max,
 			0); # msg_flags
 	my $r;
 	do {
@@ -489,8 +512,9 @@ require PublicInbox::CmdIPC4;
 	substr($_[1], $r, length($_[1]), '');
 	my @ret;
 	if ($r > 0) {
-		my ($len, $lvl, $type, @fds) = unpack(TMPL_size_t . # cmsg_len
-					'LLi*', # cmsg_level, cmsg_type, @fds
+		my ($len, $lvl, $type, @fds) = unpack(TMPL_cmsg_len.
+					'LL'. # cmsg_level, cmsg_type
+					CMSG_DATA_off.'i*', # @fds
 					$cmsghdr);
 		if ($lvl == SOL_SOCKET && $type == SCM_RIGHTS) {
 			$len -= CMSG_ALIGN_SIZEOF_cmsghdr;
diff --git a/t/cmd_ipc.t b/t/cmd_ipc.t
index 08a4dcc3..c973c6f0 100644
--- a/t/cmd_ipc.t
+++ b/t/cmd_ipc.t
@@ -143,14 +143,13 @@ SKIP: {
 }
 
 SKIP: {
-	skip 'not Linux', 1 if $^O ne 'linux';
 	require_ok 'PublicInbox::Syscall';
 	$send = PublicInbox::Syscall->can('send_cmd4') or
-		skip 'send_cmd4 not defined for arch', 1;
+		skip "send_cmd4 not defined for $^O arch", 1;
 	$recv = PublicInbox::Syscall->can('recv_cmd4') or
-		skip 'recv_cmd4 not defined for arch', 1;
-	$do_test->(SOCK_STREAM, 0, 'PP Linux stream');
-	$do_test->(SOCK_SEQPACKET, 0, 'PP Linux seqpacket');
+		skip "recv_cmd4 not defined for $^O arch", 1;
+	$do_test->(SOCK_STREAM, 0, 'pure Perl stream');
+	$do_test->(SOCK_SEQPACKET, 0, 'pure Perl seqpacket');
 }
 
 done_testing;