core: Add optional FDPOLL=0 argument to fdstore

A service can specify FDSTORE=1 FDPOLL=0 to request that PID1 does not
poll the fd to remove them on error. If set, fds will only be removed on
FDSTOREREMOVE=1 or when the service is done.

Fixes: #12086

2 files changed, 26 insertions, 14 deletions

diff --git a/man/sd_notify.xml b/man/sd_notify.xml
index 3046ca88ee..0157ce864a 100644
--- a/man/sd_notify.xml
+++ b/man/sd_notify.xml
@@ -219,8 +219,8 @@
         in a <citerefentry><refentrytitle>memfd_create</refentrytitle><manvolnum>2</manvolnum></citerefentry> memory
         file descriptor. Note that the service manager will accept messages for a service only if its
         <varname>FileDescriptorStoreMax=</varname> setting is non-zero (defaults to zero, see
-        <citerefentry><refentrytitle>systemd.service</refentrytitle><manvolnum>5</manvolnum></citerefentry>). If file
-        descriptors sent are pollable (see
+        <citerefentry><refentrytitle>systemd.service</refentrytitle><manvolnum>5</manvolnum></citerefentry>). If
+        <varname>FDPOLL=0</varname> is not set and the file descriptors sent are pollable (see
         <citerefentry><refentrytitle>epoll_ctl</refentrytitle><manvolnum>2</manvolnum></citerefentry>), then any
         <constant>EPOLLHUP</constant> or <constant>EPOLLERR</constant> event seen on them will result in their
         automatic removal from the store. Multiple arrays of file descriptors may be sent in separate messages, in
@@ -251,6 +251,16 @@
         submitted name does not follow these restrictions, it is ignored.</para></listitem>
       </varlistentry>
 
+      <varlistentry>
+        <term>FDPOLL=0</term>
+
+        <listitem><para>When used in combination with <varname>FDSTORE=1</varname>, disables polling of the stored
+        file descriptors regardless of whether or not they are pollable. As this option disables automatic cleanup
+        of the stored file descriptors on EPOLLERR and EPOLLHUP, care must be taken to ensure proper manual cleanup.
+        Use of this option is not generally recommended except for when automatic cleanup has unwanted behavior such
+        as prematurely discarding file descriptors from the store.</para></listitem>
+      </varlistentry>
+
     </variablelist>
 
     <para>It is recommended to prefix variable names that are not
diff --git a/src/core/service.c b/src/core/service.c
index 7d5928e455..cc8b44f1c8 100644
--- a/src/core/service.c
+++ b/src/core/service.c
@@ -423,7 +423,7 @@ static int on_fd_store_io(sd_event_source *e, int fd, uint32_t revents, void *us
         return 0;
 }
 
-static int service_add_fd_store(Service *s, int fd, const char *name) {
+static int service_add_fd_store(Service *s, int fd, const char *name, bool do_poll) {
         ServiceFDStore *fs;
         int r;
 
@@ -459,13 +459,15 @@ static int service_add_fd_store(Service *s, int fd, const char *name) {
                 return -ENOMEM;
         }
 
-        r = sd_event_add_io(UNIT(s)->manager->event, &fs->event_source, fd, 0, on_fd_store_io, fs);
-        if (r < 0 && r != -EPERM) { /* EPERM indicates fds that aren't pollable, which is OK */
-                free(fs->fdname);
-                free(fs);
-                return r;
-        } else if (r >= 0)
-                (void) sd_event_source_set_description(fs->event_source, "service-fd-store");
+        if (do_poll) {
+                r = sd_event_add_io(UNIT(s)->manager->event, &fs->event_source, fd, 0, on_fd_store_io, fs);
+                if (r < 0 && r != -EPERM) { /* EPERM indicates fds that aren't pollable, which is OK */
+                        free(fs->fdname);
+                        free(fs);
+                        return r;
+                } else if (r >= 0)
+                        (void) sd_event_source_set_description(fs->event_source, "service-fd-store");
+        }
 
         LIST_PREPEND(fd_store, s->fd_store, fs);
         s->n_fd_store++;
@@ -473,7 +475,7 @@ static int service_add_fd_store(Service *s, int fd, const char *name) {
         return 1; /* fd newly stored */
 }
 
-static int service_add_fd_store_set(Service *s, FDSet *fds, const char *name) {
+static int service_add_fd_store_set(Service *s, FDSet *fds, const char *name, bool do_poll) {
         int r;
 
         assert(s);
@@ -485,7 +487,7 @@ static int service_add_fd_store_set(Service *s, FDSet *fds, const char *name) {
                 if (fd < 0)
                         break;
 
-                r = service_add_fd_store(s, fd, name);
+                r = service_add_fd_store(s, fd, name, do_poll);
                 if (r == -EXFULL)
                         return log_unit_warning_errno(UNIT(s), r,
                                                       "Cannot store more fds than FileDescriptorStoreMax=%u, closing remaining.",
@@ -2961,7 +2963,7 @@ static int service_deserialize_item(Unit *u, const char *key, const char *value,
                         fdn += strspn(fdn, WHITESPACE);
                         (void) cunescape(fdn, 0, &t);
 
-                        r = service_add_fd_store(s, fd, t);
+                        r = service_add_fd_store(s, fd, t, true);
                         if (r < 0)
                                 log_unit_error_errno(u, r, "Failed to add fd to store: %m");
                         else
@@ -4068,7 +4070,7 @@ static void service_notify_message(
                         name = NULL;
                 }
 
-                (void) service_add_fd_store_set(s, fds, name);
+                (void) service_add_fd_store_set(s, fds, name, !strv_contains(tags, "FDPOLL=0"));
         }
 
         /* Notify clients about changed status or main pid */