mdmon: Improve switchroot interactions.

We need a new mdmon@mdfoo instance to run in the root filesystem after
switch root, as /sys and /dev are removed from the initrd.

systemd will not start a new unit with the same name running while the
old unit is still active, and we want the two mdmon processes to overlap
in time to avoid any risk of deadlock, which can happen when a write is
attempted with no mdmon running.

So we need a different unit name in the initrd than in the root.  Apart
from the name, everything else should be the same.

This is easily achieved using a different instance name as the
mdmon@.service unit file already supports multiple instances (for
different arrays).

So start "mdmon@mdfoo.service" from root, but
"mdmon@initrd-mdfoo.service" from the initrd.  udev can tell which
circumstance is the case by looking for /etc/initrd-release.
continue_from_systemd() is enhanced so that the "initrd-" prefix can be
requested.

Teach mdmon that a container name like "initrd/foo" should be treated
just like "foo".  Note that systemd passes the instance name
"initrd-foo" as "initrd/foo".

We don't need a similar mechanism at shutdown because dracut runs
"mdmon --takeover --all" when appropriate.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Jes Sorensen <jes@trained-monkey.org>

6 files changed, 16 insertions, 9 deletions

diff --git a/Grow.c b/Grow.c
index bb5fe45..06001f2 100644
--- a/Grow.c
+++ b/Grow.c
@@ -3516,7 +3516,7 @@ started:
 
 	if (!forked)
 		if (continue_via_systemd(container ?: sra->sys_name,
-					 GROW_SERVICE)) {
+					 GROW_SERVICE, NULL)) {
 			free(fdlist);
 			free(offsets);
 			sysfs_free(sra);
@@ -3714,7 +3714,7 @@ int reshape_container(char *container, char *devname,
 	ping_monitor(container);
 
 	if (!forked && !freeze_reshape)
-		if (continue_via_systemd(container, GROW_SERVICE))
+		if (continue_via_systemd(container, GROW_SERVICE, NULL))
 			return 0;
 
 	switch (forked ? 0 : fork()) {
diff --git a/mdadm.h b/mdadm.h
index b9127f9..1e51827 100644
--- a/mdadm.h
+++ b/mdadm.h
@@ -1608,7 +1608,7 @@ extern int same_dev(char *one, char *two);
 extern int compare_paths (char* path1,char* path2);
 extern void enable_fds(int devices);
 extern void manage_fork_fds(int close_all);
-extern int continue_via_systemd(char *devnm, char *service_name);
+extern int continue_via_systemd(char *devnm, char *service_name, char *prefix);
 
 extern void ident_init(struct mddev_ident *ident);
 
diff --git a/mdmon.c b/mdmon.c
index f8fd2f0..096b4d7 100644
--- a/mdmon.c
+++ b/mdmon.c
@@ -362,7 +362,12 @@ int main(int argc, char *argv[])
 	}
 
 	if (!all && argv[optind]) {
-		container_name = get_md_name(argv[optind]);
+		static const char prefix[] = "initrd/";
+		container_name = argv[optind];
+		if (strncmp(container_name, prefix,
+			    sizeof(prefix) - 1) == 0)
+			container_name += sizeof(prefix)-1;
+		container_name = get_md_name(container_name);
 		if (!container_name)
 			return 1;
 	}
diff --git a/systemd/mdmon@.service b/systemd/mdmon@.service
index 303ad05..23a375f 100644
--- a/systemd/mdmon@.service
+++ b/systemd/mdmon@.service
@@ -6,7 +6,7 @@
 #  (at your option) any later version.
 
 [Unit]
-Description=MD Metadata Monitor on /dev/%I
+Description=MD Metadata Monitor on %I
 DefaultDependencies=no
 Before=initrd-switch-root.target
 Documentation=man:mdmon(8)
diff --git a/udev-md-raid-arrays.rules b/udev-md-raid-arrays.rules
index 2967ace..4e64b24 100644
--- a/udev-md-raid-arrays.rules
+++ b/udev-md-raid-arrays.rules
@@ -38,7 +38,8 @@ ENV{MD_LEVEL}=="raid[1-9]*", ENV{SYSTEMD_WANTS}+="mdmonitor.service"
 
 # Tell systemd to run mdmon for our container, if we need it.
 ENV{MD_LEVEL}=="raid[1-9]*", ENV{MD_CONTAINER}=="?*", PROGRAM="/usr/bin/readlink $env{MD_CONTAINER}", ENV{MD_MON_THIS}="%c"
-ENV{MD_MON_THIS}=="?*", PROGRAM="/usr/bin/basename $env{MD_MON_THIS}", ENV{SYSTEMD_WANTS}+="mdmon@%c.service"
+ENV{MD_MON_THIS}=="?*", TEST=="/etc/initrd-release", PROGRAM="/usr/bin/basename $env{MD_MON_THIS}", ENV{SYSTEMD_WANTS}+="mdmon@initrd-%c.service"
+ENV{MD_MON_THIS}=="?*", TEST!="/etc/initrd-release", PROGRAM="/usr/bin/basename $env{MD_MON_THIS}", ENV{SYSTEMD_WANTS}+="mdmon@%c.service"
 ENV{RESHAPE_ACTIVE}=="yes", PROGRAM="/usr/bin/basename $env{MD_MON_THIS}", ENV{SYSTEMD_WANTS}+="mdadm-grow-continue@%c.service"
 
 LABEL="md_end"
diff --git a/util.c b/util.c
index 509fb43..d70ca43 100644
--- a/util.c
+++ b/util.c
@@ -1916,6 +1916,7 @@ int start_mdmon(char *devnm)
 	int len;
 	pid_t pid;
 	int status;
+	char *prefix = in_initrd() ? "initrd-" : "";
 	char pathbuf[1024];
 	char *paths[4] = {
 		pathbuf,
@@ -1926,7 +1927,7 @@ int start_mdmon(char *devnm)
 
 	if (check_env("MDADM_NO_MDMON"))
 		return 0;
-	if (continue_via_systemd(devnm, MDMON_SERVICE))
+	if (continue_via_systemd(devnm, MDMON_SERVICE, prefix))
 		return 0;
 
 	/* That failed, try running mdmon directly */
@@ -2197,7 +2198,7 @@ void manage_fork_fds(int close_all)
  *	1- if systemd service has been started
  *	0- otherwise
  */
-int continue_via_systemd(char *devnm, char *service_name)
+int continue_via_systemd(char *devnm, char *service_name, char *prefix)
 {
 	int pid, status;
 	char pathbuf[1024];
@@ -2209,7 +2210,7 @@ int continue_via_systemd(char *devnm, char *service_name)
 	case  0:
 		manage_fork_fds(1);
 		snprintf(pathbuf, sizeof(pathbuf),
-			 "%s@%s.service", service_name, devnm);
+			 "%s@%s%s.service", service_name, prefix ?: "", devnm);
 		status = execl("/usr/bin/systemctl", "systemctl", "restart",
 			       pathbuf, NULL);
 		status = execl("/bin/systemctl", "systemctl", "restart",