core: add "invocation ID" concept to service manager

This adds a new invocation ID concept to the service manager. The invocation ID
identifies each runtime cycle of a unit uniquely. A new randomized 128bit ID is
generated each time a unit moves from and inactive to an activating or active
state.

The primary usecase for this concept is to connect the runtime data PID 1
maintains about a service with the offline data the journal stores about it.
Previously we'd use the unit name plus start/stop times, which however is
highly racy since the journal will generally process log data after the service
already ended.

The "invocation ID" kinda matches the "boot ID" concept of the Linux kernel,
except that it applies to an individual unit instead of the whole system.

The invocation ID is passed to the activated processes as environment variable.
It is additionally stored as extended attribute on the cgroup of the unit. The
latter is used by journald to automatically retrieve it for each log logged
message and attach it to the log entry. The environment variable is very easily
accessible, even for unprivileged services. OTOH the extended attribute is only
accessible to privileged processes (this is because cgroupfs only supports the
"trusted." xattr namespace, not "user."). The environment variable may be
altered by services, the extended attribute may not be, hence is the better
choice for the journal.

Note that reading the invocation ID off the extended attribute from journald is
racy, similar to the way reading the unit name for a logging process is.

This patch adds APIs to read the invocation ID to sd-id128:
sd_id128_get_invocation() may be used in a similar fashion to
sd_id128_get_boot().

PID1's own logging is updated to always include the invocation ID when it logs
information about a unit.

A new bus call GetUnitByInvocationID() is added that allows retrieving a bus
path to a unit by its invocation ID. The bus path is built using the invocation
ID, thus providing a path for referring to a unit that is valid only for the
current runtime cycleof it.

Outlook for the future: should the kernel eventually allow passing of cgroup
information along AF_UNIX/SOCK_DGRAM messages via a unique cgroup id, then we
can alter the invocation ID to be generated as hash from that rather than
entirely randomly. This way we can derive the invocation race-freely from the
messages.

2 files changed, 54 insertions, 8 deletions

diff --git a/src/journal/journald-server.c b/src/journal/journald-server.c
index 015b74b203..f01cf1d937 100644
--- a/src/journal/journald-server.c
+++ b/src/journal/journald-server.c
@@ -44,6 +44,7 @@
 #include "fs-util.h"
 #include "hashmap.h"
 #include "hostname-util.h"
+#include "id128-util.h"
 #include "io-util.h"
 #include "journal-authenticate.h"
 #include "journal-file.h"
@@ -56,6 +57,7 @@
 #include "journald-server.h"
 #include "journald-stream.h"
 #include "journald-syslog.h"
+#include "log.h"
 #include "missing.h"
 #include "mkdir.h"
 #include "parse-util.h"
@@ -69,7 +71,6 @@
 #include "string-table.h"
 #include "string-util.h"
 #include "user-util.h"
-#include "log.h"
 
 #define USER_JOURNALS_MAX 1024
 
@@ -675,6 +676,44 @@ static void write_to_journal(Server *s, uid_t uid, struct iovec *iovec, unsigned
                 server_schedule_sync(s, priority);
 }
 
+static int get_invocation_id(const char *cgroup_root, const char *slice, const char *unit, char **ret) {
+        _cleanup_free_ char *escaped = NULL, *slice_path = NULL, *p = NULL;
+        char *copy, ids[SD_ID128_STRING_MAX];
+        int r;
+
+        /* Read the invocation ID of a unit off a unit. It's stored in the "trusted.invocation_id" extended attribute
+         * on the cgroup path. */
+
+        r = cg_slice_to_path(slice, &slice_path);
+        if (r < 0)
+                return r;
+
+        escaped = cg_escape(unit);
+        if (!escaped)
+                return -ENOMEM;
+
+        p = strjoin(cgroup_root, "/", slice_path, "/", escaped, NULL);
+        if (!p)
+                return -ENOMEM;
+
+        r = cg_get_xattr(SYSTEMD_CGROUP_CONTROLLER, p, "trusted.invocation_id", ids, 32);
+        if (r < 0)
+                return r;
+        if (r != 32)
+                return -EINVAL;
+        ids[32] = 0;
+
+        if (!id128_is_valid(ids))
+                return -EINVAL;
+
+        copy = strdup(ids);
+        if (!copy)
+                return -ENOMEM;
+
+        *ret = copy;
+        return 0;
+}
+
 static void dispatch_message_real(
                 Server *s,
                 struct iovec *iovec, unsigned n, unsigned m,
@@ -771,6 +810,7 @@ static void dispatch_message_real(
 
                 r = cg_pid_get_path_shifted(ucred->pid, s->cgroup_root, &c);
                 if (r >= 0) {
+                        _cleanup_free_ char *raw_unit = NULL, *raw_slice = NULL;
                         char *session = NULL;
 
                         x = strjoina("_SYSTEMD_CGROUP=", c);
@@ -790,9 +830,8 @@ static void dispatch_message_real(
                                 IOVEC_SET_STRING(iovec[n++], owner_uid);
                         }
 
-                        if (cg_path_get_unit(c, &t) >= 0) {
-                                x = strjoina("_SYSTEMD_UNIT=", t);
-                                free(t);
+                        if (cg_path_get_unit(c, &raw_unit) >= 0) {
+                                x = strjoina("_SYSTEMD_UNIT=", raw_unit);
                                 IOVEC_SET_STRING(iovec[n++], x);
                         } else if (unit_id && !session) {
                                 x = strjoina("_SYSTEMD_UNIT=", unit_id);
@@ -808,9 +847,8 @@ static void dispatch_message_real(
                                 IOVEC_SET_STRING(iovec[n++], x);
                         }
 
-                        if (cg_path_get_slice(c, &t) >= 0) {
-                                x = strjoina("_SYSTEMD_SLICE=", t);
-                                free(t);
+                        if (cg_path_get_slice(c, &raw_slice) >= 0) {
+                                x = strjoina("_SYSTEMD_SLICE=", raw_slice);
                                 IOVEC_SET_STRING(iovec[n++], x);
                         }
 
@@ -820,6 +858,14 @@ static void dispatch_message_real(
                                 IOVEC_SET_STRING(iovec[n++], x);
                         }
 
+                        if (raw_slice && raw_unit) {
+                                if (get_invocation_id(s->cgroup_root, raw_slice, raw_unit, &t) >= 0) {
+                                        x = strjoina("_SYSTEMD_INVOCATION_ID=", t);
+                                        free(t);
+                                        IOVEC_SET_STRING(iovec[n++], x);
+                                }
+                        }
+
                         free(c);
                 } else if (unit_id) {
                         x = strjoina("_SYSTEMD_UNIT=", unit_id);
diff --git a/src/journal/journald-server.h b/src/journal/journald-server.h
index 784d24833d..dfb5724794 100644
--- a/src/journal/journald-server.h
+++ b/src/journal/journald-server.h
@@ -153,7 +153,7 @@ struct Server {
 
 #define SERVER_MACHINE_ID(s) ((s)->machine_id_field + strlen("_MACHINE_ID="))
 
-#define N_IOVEC_META_FIELDS 21
+#define N_IOVEC_META_FIELDS 22
 #define N_IOVEC_KERNEL_FIELDS 64
 #define N_IOVEC_UDEV_FIELDS 32
 #define N_IOVEC_OBJECT_FIELDS 14