cmd/zgenhostid: replace with simple c implementation

It was discovered that dracut scripts and zgenhostid
always generate little-endian /etc/hostid.

This commit provides simple endianess-aware binary
and updates the scripts to use it.

New features include:
 -f flag to force overwrite.
 -o flag to write to different file (for dracut)
 accepting both 0x01234567 and 01234567 values as input

Reviewed-by: Brian Behlendorf <[email protected]>
Reviewed-by: Olaf Faaland <[email protected]>
Signed-off-by: Georgy Yakovlev <[email protected]>
Closes #10887 
Closes #10925 

7 files changed, 213 insertions, 93 deletions

diff --git a/cmd/zgenhostid/.gitignore b/cmd/zgenhostid/.gitignore
new file mode 100644
index 000000000..072246c73
--- /dev/null
+++ b/cmd/zgenhostid/.gitignore
@@ -0,0 +1 @@
+/zgenhostid
diff --git a/cmd/zgenhostid/Makefile.am b/cmd/zgenhostid/Makefile.am
index 69c99ca9d..0ba791f7c 100644
--- a/cmd/zgenhostid/Makefile.am
+++ b/cmd/zgenhostid/Makefile.am
@@ -1 +1,5 @@
-dist_bin_SCRIPTS = zgenhostid
+include $(top_srcdir)/config/Rules.am
+
+bin_PROGRAMS = zgenhostid
+
+zgenhostid_SOURCES = zgenhostid.c
diff --git a/cmd/zgenhostid/zgenhostid b/cmd/zgenhostid/zgenhostid
deleted file mode 100755
index 8b468740c..000000000
--- a/cmd/zgenhostid/zgenhostid
+++ /dev/null
@@ -1,61 +0,0 @@
-#!/usr/bin/env bash
-
-# Emulate genhostid(1) available on RHEL/CENTOS, for use on distros
-# which do not provide that utility.
-#
-# Usage:
-#    zgenhostid
-#    zgenhostid <value>
-#
-# If /etc/hostid already exists and is size > 0, the script exits immediately
-# and changes nothing.  Unlike genhostid, this generates an error message.
-#
-# The first form generates a random hostid and stores it in /etc/hostid.
-# The second form checks that the provided value is between 0x1 and 0xFFFFFFFF
-# and if so, stores it in /etc/hostid.  This form is not supported by
-# genhostid(1).
-
-hostid_file=/etc/hostid
-
-function usage {
-	echo "$0 [value]"
-	echo "If $hostid_file is not present, store a hostid in it." >&2
-	echo "The optional value must be an 8-digit hex number between" >&2
-	echo "1 and 2^32-1.  If no value is provided, a random one will" >&2
-	echo "be generated.  The value must be unique among your systems." >&2
-}
-
-# hostid(1) ignores contents of /etc/hostid if size < 4 bytes.  It would
-# be better if this checked size >= 4 bytes but it the method must be
-# widely portable.
-if [ -s $hostid_file ]; then
-	echo "$hostid_file already exists.  No change made." >&2
-	exit 1
-fi
-
-if [ -n "$1" ]; then
-	host_id=$1
-else
-	# $RANDOM goes from 0..32k-1
-	number=$((((RANDOM % 4) * 32768 + RANDOM) * 32768 + RANDOM))
-	host_id=$(printf "%08x" $number)
-fi
-
-if egrep -o '^0{8}$' <<< $host_id >/dev/null 2>&1; then
-	usage
-	exit 2
-fi
-
-if ! egrep -o '^[a-fA-F0-9]{8}$' <<< $host_id >/dev/null 2>&1; then
-	usage
-	exit 3
-fi
-
-a=${host_id:6:2}
-b=${host_id:4:2}
-c=${host_id:2:2}
-d=${host_id:0:2}
-
-echo -ne \\x$a\\x$b\\x$c\\x$d > $hostid_file
-
-exit 0
diff --git a/cmd/zgenhostid/zgenhostid.c b/cmd/zgenhostid/zgenhostid.c
new file mode 100644
index 000000000..562262928
--- /dev/null
+++ b/cmd/zgenhostid/zgenhostid.c
@@ -0,0 +1,152 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+ * or http://www.opensolaris.org/os/licensing.
+ * See the License for the specific language governing permissions
+ * and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+
+/*
+ * Copyright (c) 2020, Georgy Yakovlev.  All rights reserved.
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <time.h>
+#include <unistd.h>
+
+static void usage(void);
+
+static void
+usage(void)
+{
+	(void) fprintf(stderr,
+	    "usage: zgenhostid [-fh] [-o path] [value]\n\n"
+	    "  -f\t\t force hostid file write\n"
+	    "  -h\t\t print this usage and exit\n"
+	    "  -o <filename>\t write hostid to this file\n\n"
+	    "If hostid file is not present, store a hostid in it.\n"
+	    "The optional value must be an 8-digit hex number between"
+	    "1 and 2^32-1.\n"
+	    "If no value is provided, a random one will"
+	    "be generated.\n"
+	    "The value must be unique among your systems.\n");
+	exit(EXIT_FAILURE);
+	/* NOTREACHED */
+}
+
+int
+main(int argc, char **argv)
+{
+	/* default file path, can be optionally set by user */
+	char path[PATH_MAX] = "/etc/hostid";
+	/* holds converted user input or lrand48() generated value */
+	unsigned long input_i = 0;
+
+	int opt;
+	int pathlen;
+	int force_fwrite = 0;
+	while ((opt = getopt_long(argc, argv, "fo:h?", 0, 0)) != -1) {
+		switch (opt) {
+		case 'f':
+			force_fwrite = 1;
+			break;
+		case 'o':
+			pathlen = snprintf(path, sizeof (path), "%s", optarg);
+			if (pathlen >= sizeof (path)) {
+				fprintf(stderr, "%s\n", strerror(EOVERFLOW));
+				exit(EXIT_FAILURE);
+			} else if (pathlen < 1) {
+				fprintf(stderr, "%s\n", strerror(EINVAL));
+				exit(EXIT_FAILURE);
+			}
+			break;
+		case 'h':
+		case '?':
+			usage();
+		}
+	}
+
+	char *in_s = argv[optind];
+	if (in_s != NULL) {
+		/* increment pointer by 2 if string is 0x prefixed */
+		if (strncasecmp("0x", in_s, 2) == 0) {
+			in_s += 2;
+		}
+
+		/* need to be exactly 8 characters */
+		const char *hex = "0123456789abcdefABCDEF";
+		if (strlen(in_s) != 8 || strspn(in_s, hex) != 8) {
+			fprintf(stderr, "%s\n", strerror(ERANGE));
+			usage();
+		}
+
+		input_i = strtoul(in_s, NULL, 16);
+		if (errno != 0) {
+			perror("strtoul");
+			exit(EXIT_FAILURE);
+		}
+
+		if (input_i < 0x1 || input_i > UINT32_MAX) {
+			fprintf(stderr, "%s\n", strerror(ERANGE));
+			usage();
+		}
+	}
+
+	struct stat fstat;
+	if (force_fwrite == 0 && stat(path, &fstat) == 0 &&
+	    S_ISREG(fstat.st_mode)) {
+		fprintf(stderr, "%s: %s\n", path, strerror(EEXIST));
+			exit(EXIT_FAILURE);
+	}
+
+	/*
+	 * generate if not provided by user
+	 * also handle unlikely zero return from lrand48()
+	 */
+	while (input_i == 0) {
+		srand48(getpid() ^ time(NULL));
+		input_i = lrand48();
+	}
+
+	FILE *fp = fopen(path, "wb");
+	if (!fp) {
+		perror("fopen");
+		exit(EXIT_FAILURE);
+	}
+
+	/*
+	 * we need just 4 bytes in native endianess
+	 * not using sethostid() because it may be missing or just a stub
+	 */
+	uint32_t hostid = input_i;
+	int written = fwrite(&hostid, 1, 4, fp);
+	if (written != 4) {
+		perror("fwrite");
+		exit(EXIT_FAILURE);
+	}
+
+	fclose(fp);
+	exit(EXIT_SUCCESS);
+}
diff --git a/contrib/dracut/90zfs/module-setup.sh.in b/contrib/dracut/90zfs/module-setup.sh.in
index 7e7a96d6e..5b746049f 100755
--- a/contrib/dracut/90zfs/module-setup.sh.in
+++ b/contrib/dracut/90zfs/module-setup.sh.in
@@ -5,7 +5,7 @@ check() {
 	[ "${1}" = "-d" ] && return 0
 
 	# Verify the zfs tool chain
-	for tool in "@sbindir@/zpool" "@sbindir@/zfs" "@mounthelperdir@/mount.zfs" ; do
+	for tool in "@bindir@/zgenhostid" "@sbindir@/zpool" "@sbindir@/zfs" "@mounthelperdir@/mount.zfs" ; do
 		test -x "$tool" || return 1
 	done
 	# Verify grep exists
@@ -38,6 +38,7 @@ install() {
 	inst_rules @udevruledir@/60-zvol.rules
 	dracut_install hostid
 	dracut_install grep
+	dracut_install @bindir@/zgenhostid
 	dracut_install @sbindir@/zfs
 	dracut_install @sbindir@/zpool
 	# Workaround for zfsonlinux/zfs#4749 by ensuring libgcc_s.so(.1) is included
@@ -83,11 +84,7 @@ install() {
 	fi
 
 	# Synchronize initramfs and system hostid
-	AA=`hostid | cut -b 1,2`
-	BB=`hostid | cut -b 3,4`
-	CC=`hostid | cut -b 5,6`
-	DD=`hostid | cut -b 7,8`
-	echo -ne "\\x${DD}\\x${CC}\\x${BB}\\x${AA}" > "${initdir}/etc/hostid"
+	zgenhostid -o "${initdir}/etc/hostid" "$(hostid)"
 
 	if dracut_module_included "systemd"; then
 		mkdir -p "${initdir}/$systemdsystemunitdir/zfs-import.target.wants"
diff --git a/contrib/dracut/90zfs/parse-zfs.sh.in b/contrib/dracut/90zfs/parse-zfs.sh.in
index 6a805ae24..2ff76d8fa 100755
--- a/contrib/dracut/90zfs/parse-zfs.sh.in
+++ b/contrib/dracut/90zfs/parse-zfs.sh.in
@@ -6,11 +6,7 @@
 spl_hostid=$(getarg spl_hostid=)
 if [ -n "${spl_hostid}" ] ; then
 	info "ZFS: Using hostid from command line: ${spl_hostid}"
-	AA=$(echo "${spl_hostid}" | cut -b 1,2)
-	BB=$(echo "${spl_hostid}" | cut -b 3,4)
-	CC=$(echo "${spl_hostid}" | cut -b 5,6)
-	DD=$(echo "${spl_hostid}" | cut -b 7,8)
-	echo -ne "\\x${DD}\\x${CC}\\x${BB}\\x${AA}" >/etc/hostid
+	zgenhostid -f "${spl_hostid}"
 elif [ -f "/etc/hostid" ] ; then
 	info "ZFS: Using hostid from /etc/hostid: $(hostid)"
 else
diff --git a/man/man8/zgenhostid.8 b/man/man8/zgenhostid.8
index ff3d2d960..ff198443d 100644
--- a/man/man8/zgenhostid.8
+++ b/man/man8/zgenhostid.8
@@ -21,7 +21,7 @@
 .\"
 .\" Copyright (c) 2017 by Lawrence Livermore National Security, LLC.
 .\"
-.Dd September 16, 2017
+.Dd September 13, 2020
 .Dt ZGENHOSTID 8 SMM
 .Os
 .Sh NAME
@@ -30,42 +30,73 @@
 .Em /etc/hostid
 .Sh SYNOPSIS
 .Nm
+.Op Fl f
+.Op Fl o Ar filename
 .Op Ar hostid
 .Sh DESCRIPTION
-If
-.Em /etc/hostid
-does not exist, create it and store a hostid in it.  If the user provides
-.Op Ar hostid
-on the command line, store that value.  Otherwise, randomly generate a
-value to store.
-.Pp
-This emulates the
-.Xr genhostid 1
-utility and is provided for use on systems which do not include the utility.
-.Sh OPTIONS
+Creates
+.Pa /etc/hostid
+file and stores hostid in it.
+If the user provides
 .Op Ar hostid
+on the command line, validates and stores that value.
+Otherwise, randomly generates a value to store.
+.Bl -tag -width "hostid"
+.It Fl h
+Display a summary of the command-line options.
+.It Fl f
+Force file overwrite.
+.It Fl o Ar filename
+Write to
+.Pa filename
+instead of default
+.Pa /etc/hostd
+.It Ar hostid
 Specifies the value to be placed in
-.Em /etc/hostid .
-It must be a number with a value between 1 and 2^32-1.  This value
+.Pa /etc/hostid .
+It must be a number with a value between 1 and 2^32-1.
+This value
 .Sy must
-be unique among your systems.  It must be expressed in hexadecimal and be
-exactly 8 digits long.
+be unique among your systems.
+It
+.Sy must
+be expressed in hexadecimal and be exactly
+.Em 8
+digits long, optionally prefixed by
+.Em 0x .
+.El
+.Sh FILES
+.Pa /etc/hostid
 .Sh EXAMPLES
-.Bl -tag -width Ds
+.Bl -tag -width Bd
 .It Generate a random hostid and store it
 .Bd -literal
 # zgenhostid
 .Ed
-.It Record the libc-generated hostid in Em /etc/hostid
+.It Record the libc-generated hostid in Pa /etc/hostid
 .Bd -literal
-# zgenhostid $(hostid)
+# zgenhostid "$(hostid)"
 .Ed
-.It Record a custom hostid (0xdeadbeef) in Em etc/hostid
+.It Record a custom hostid (0xdeadbeef) in Pa /etc/hostid
 .Bd -literal
 # zgenhostid deadbeef
 .Ed
+.It Record a custom hostid (0x01234567) in Pa /tmp/hostid
+and ovewrite the file if it exists
+.Bd -literal
+# zgenhostid -f -o /tmp/hostid 0x01234567
+.Ed
 .El
 .Sh SEE ALSO
 .Xr genhostid 1 ,
 .Xr hostid 1 ,
+.Xr sethostid 3 ,
 .Xr spl-module-parameters 5
+.Sh HISTORY
+.Nm
+emulates the
+.Xr genhostid 1
+utility and is provided for use on systems which
+do not include the utility or do not provide
+.Xr sethostid 3
+call.