From cb084637ba1c8558f1538ce300c5520a6764dc76 Mon Sep 17 00:00:00 2001

From: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>

Date: Mon, 28 Oct 2019 19:35:24 +0900

Subject: [PATCH] core, job: fix breakage of ordering dependencies by systemctl

 reload command

Currently, systemctl reload command breaks ordering dependencies if it's

executed when its target service unit is in activating state.

For example, prepare A.service, B.service and C.target as follows:

    # systemctl cat A.service B.service C.target

    # /etc/systemd/system/A.service

    [Unit]

    Description=A

    [Service]

    Type=oneshot

    ExecStart=/usr/bin/echo A1

    ExecStart=/usr/bin/sleep 60

    ExecStart=/usr/bin/echo A2

    ExecReload=/usr/bin/echo A reloaded

    RemainAfterExit=yes

    # /etc/systemd/system/B.service

    [Unit]

    Description=B

    After=A.service

    [Service]

    Type=oneshot

    ExecStart=/usr/bin/echo B

    RemainAfterExit=yes

    # /etc/systemd/system/C.target

    [Unit]

    Description=C

    Wants=A.service B.service

Start them.

    # systemctl daemon-reload

    # systemctl start C.target

Then, we have:

    # LANG=C journalctl --no-pager -u A.service -u B.service -u C.target -b

    -- Logs begin at Mon 2019-09-09 00:25:06 EDT, end at Thu 2019-10-24 22:28:47 EDT. --

    Oct 24 22:27:47 localhost.localdomain systemd[1]: Starting A...

    Oct 24 22:27:47 localhost.localdomain systemd[1]: A.service: Child 967 belongs to A.service.

    Oct 24 22:27:47 localhost.localdomain systemd[1]: A.service: Main process exited, code=exited, status=0/SUCCESS

    Oct 24 22:27:47 localhost.localdomain systemd[1]: A.service: Running next main command for state start.

    Oct 24 22:27:47 localhost.localdomain systemd[1]: A.service: Passing 0 fds to service

    Oct 24 22:27:47 localhost.localdomain systemd[1]: A.service: About to execute: /usr/bin/sleep 60

    Oct 24 22:27:47 localhost.localdomain systemd[1]: A.service: Forked /usr/bin/sleep as 968

    Oct 24 22:27:47 localhost.localdomain systemd[968]: A.service: Executing: /usr/bin/sleep 60

    Oct 24 22:27:52 localhost.localdomain systemd[1]: A.service: Trying to enqueue job A.service/reload/replace

    Oct 24 22:27:52 localhost.localdomain systemd[1]: A.service: Merged into running job, re-running: A.service/reload as 1288

    Oct 24 22:27:52 localhost.localdomain systemd[1]: A.service: Enqueued job A.service/reload as 1288

    Oct 24 22:27:52 localhost.localdomain systemd[1]: A.service: Unit cannot be reloaded because it is inactive.

    Oct 24 22:27:52 localhost.localdomain systemd[1]: A.service: Job 1288 A.service/reload finished, result=invalid

    Oct 24 22:27:52 localhost.localdomain systemd[1]: B.service: Passing 0 fds to service

    Oct 24 22:27:52 localhost.localdomain systemd[1]: B.service: About to execute: /usr/bin/echo B

    Oct 24 22:27:52 localhost.localdomain systemd[1]: B.service: Forked /usr/bin/echo as 970

    Oct 24 22:27:52 localhost.localdomain systemd[970]: B.service: Executing: /usr/bin/echo B

    Oct 24 22:27:52 localhost.localdomain systemd[1]: B.service: Failed to send unit change signal for B.service: Connection reset by peer

    Oct 24 22:27:52 localhost.localdomain systemd[1]: B.service: Changed dead -> start

    Oct 24 22:27:52 localhost.localdomain systemd[1]: Starting B...

    Oct 24 22:27:52 localhost.localdomain echo[970]: B

    Oct 24 22:27:52 localhost.localdomain systemd[1]: B.service: Child 970 belongs to B.service.

    Oct 24 22:27:52 localhost.localdomain systemd[1]: B.service: Main process exited, code=exited, status=0/SUCCESS

    Oct 24 22:27:52 localhost.localdomain systemd[1]: B.service: Changed start -> exited

    Oct 24 22:27:52 localhost.localdomain systemd[1]: B.service: Job 1371 B.service/start finished, result=done

    Oct 24 22:27:52 localhost.localdomain systemd[1]: Started B.

    Oct 24 22:27:52 localhost.localdomain systemd[1]: C.target: Job 1287 C.target/start finished, result=done

    Oct 24 22:27:52 localhost.localdomain systemd[1]: Reached target C.

    Oct 24 22:27:52 localhost.localdomain systemd[1]: C.target: Failed to send unit change signal for C.target: Connection reset by peer

    Oct 24 22:28:47 localhost.localdomain systemd[1]: A.service: Child 968 belongs to A.service.

    Oct 24 22:28:47 localhost.localdomain systemd[1]: A.service: Main process exited, code=exited, status=0/SUCCESS

    Oct 24 22:28:47 localhost.localdomain systemd[1]: A.service: Running next main command for state start.

    Oct 24 22:28:47 localhost.localdomain systemd[1]: A.service: Passing 0 fds to service

    Oct 24 22:28:47 localhost.localdomain systemd[1]: A.service: About to execute: /usr/bin/echo A2

    Oct 24 22:28:47 localhost.localdomain systemd[1]: A.service: Forked /usr/bin/echo as 972

    Oct 24 22:28:47 localhost.localdomain systemd[972]: A.service: Executing: /usr/bin/echo A2

    Oct 24 22:28:47 localhost.localdomain echo[972]: A2

    Oct 24 22:28:47 localhost.localdomain systemd[1]: A.service: Child 972 belongs to A.service.

    Oct 24 22:28:47 localhost.localdomain systemd[1]: A.service: Main process exited, code=exited, status=0/SUCCESS

    Oct 24 22:28:47 localhost.localdomain systemd[1]: A.service: Changed start -> exited

The issue occurs not only in reload command, i.e.:

  - reload

  - try-restart

  - reload-or-restart

  - reload-or-try-restart commands

The cause of this issue is that job_type_collapse() doesn't take care of the

activating state.

Fixes: #10464

(cherry picked from commit d1559793df555212271e490a4a72f55826caf5b4)

Resolves: #1766417

---

 src/core/job.c | 6 +++---

 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/core/job.c b/src/core/job.c

index 8552ffb704..769ed6d603 100644

--- a/src/core/job.c

+++ b/src/core/job.c

@@ -403,21 +403,21 @@ JobType job_type_collapse(JobType t, Unit *u) {

         case JOB_TRY_RESTART:

                 s = unit_active_state(u);

-                if (UNIT_IS_INACTIVE_OR_DEACTIVATING(s))

+                if (!UNIT_IS_ACTIVE_OR_RELOADING(s))

                         return JOB_NOP;

                 return JOB_RESTART;

         case JOB_TRY_RELOAD:

                 s = unit_active_state(u);

-                if (UNIT_IS_INACTIVE_OR_DEACTIVATING(s))

+                if (!UNIT_IS_ACTIVE_OR_RELOADING(s))

                         return JOB_NOP;

                 return JOB_RELOAD;

         case JOB_RELOAD_OR_START:

                 s = unit_active_state(u);

-                if (UNIT_IS_INACTIVE_OR_DEACTIVATING(s))

+                if (!UNIT_IS_ACTIVE_OR_RELOADING(s))

                         return JOB_START;

                 return JOB_RELOAD;