Systemd/src/libsystemd/sd-id128/sd-id128.c

339 lines
9.1 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: LGPL-2.1+ */
#include <errno.h>
#include <fcntl.h>
#include <unistd.h>
#include "sd-id128.h"
core: store the invocation ID in the per-service keyring Let's store the invocation ID in the per-service keyring as a root-owned key, with strict access rights. This has the advantage over the environment-based ID passing that it also works from SUID binaries (as they key cannot be overidden by unprivileged code starting them), in contrast to the secure_getenv() based mode. The invocation ID is now passed in three different ways to a service: - As environment variable $INVOCATION_ID. This is easy to use, but may be overriden by unprivileged code (which might be a bad or a good thing), which means it's incompatible with SUID code (see above). - As extended attribute on the service cgroup. This cannot be overriden by unprivileged code, and may be queried safely from "outside" of a service. However, it is incompatible with containers right now, as unprivileged containers generally cannot set xattrs on cgroupfs. - As "invocation_id" key in the kernel keyring. This has the benefit that the key cannot be changed by unprivileged service code, and thus is safe to access from SUID code (see above). But do note that service code can replace the session keyring with a fresh one that lacks the key. However in that case the key will not be owned by root, which is easily detectable. The keyring is also incompatible with containers right now, as it is not properly namespace aware (but this is being worked on), and thus most container managers mask the keyring-related system calls. Ideally we'd only have one way to pass the invocation ID, but the different ways all have limitations. The invocation ID hookup in journald is currently only available on the host but not in containers, due to the mentioned limitations. How to verify the new invocation ID in the keyring: # systemd-run -t /bin/sh Running as unit: run-rd917366c04f847b480d486017f7239d6.service Press ^] three times within 1s to disconnect TTY. # keyctl show Session Keyring 680208392 --alswrv 0 0 keyring: _ses 250926536 ----s-rv 0 0 \_ user: invocation_id # keyctl request user invocation_id 250926536 # keyctl read 250926536 16 bytes of data in key: 9c96317c ac64495a a42b9cd7 4f3ff96b # echo $INVOCATION_ID 9c96317cac64495aa42b9cd74f3ff96b # ^D This creates a new transient service runnint a shell. Then verifies the contents of the keyring, requests the invocation ID key, and reads its payload. For comparison the invocation ID as passed via the environment variable is also displayed.
2016-12-02 15:05:55 +01:00
#include "alloc-util.h"
#include "fd-util.h"
#include "hexdecoct.h"
#include "id128-util.h"
#include "io-util.h"
#include "khash.h"
#include "macro.h"
core: store the invocation ID in the per-service keyring Let's store the invocation ID in the per-service keyring as a root-owned key, with strict access rights. This has the advantage over the environment-based ID passing that it also works from SUID binaries (as they key cannot be overidden by unprivileged code starting them), in contrast to the secure_getenv() based mode. The invocation ID is now passed in three different ways to a service: - As environment variable $INVOCATION_ID. This is easy to use, but may be overriden by unprivileged code (which might be a bad or a good thing), which means it's incompatible with SUID code (see above). - As extended attribute on the service cgroup. This cannot be overriden by unprivileged code, and may be queried safely from "outside" of a service. However, it is incompatible with containers right now, as unprivileged containers generally cannot set xattrs on cgroupfs. - As "invocation_id" key in the kernel keyring. This has the benefit that the key cannot be changed by unprivileged service code, and thus is safe to access from SUID code (see above). But do note that service code can replace the session keyring with a fresh one that lacks the key. However in that case the key will not be owned by root, which is easily detectable. The keyring is also incompatible with containers right now, as it is not properly namespace aware (but this is being worked on), and thus most container managers mask the keyring-related system calls. Ideally we'd only have one way to pass the invocation ID, but the different ways all have limitations. The invocation ID hookup in journald is currently only available on the host but not in containers, due to the mentioned limitations. How to verify the new invocation ID in the keyring: # systemd-run -t /bin/sh Running as unit: run-rd917366c04f847b480d486017f7239d6.service Press ^] three times within 1s to disconnect TTY. # keyctl show Session Keyring 680208392 --alswrv 0 0 keyring: _ses 250926536 ----s-rv 0 0 \_ user: invocation_id # keyctl request user invocation_id 250926536 # keyctl read 250926536 16 bytes of data in key: 9c96317c ac64495a a42b9cd7 4f3ff96b # echo $INVOCATION_ID 9c96317cac64495aa42b9cd74f3ff96b # ^D This creates a new transient service runnint a shell. Then verifies the contents of the keyring, requests the invocation ID key, and reads its payload. For comparison the invocation ID as passed via the environment variable is also displayed.
2016-12-02 15:05:55 +01:00
#include "missing.h"
2015-04-10 22:27:10 +02:00
#include "random-util.h"
core: store the invocation ID in the per-service keyring Let's store the invocation ID in the per-service keyring as a root-owned key, with strict access rights. This has the advantage over the environment-based ID passing that it also works from SUID binaries (as they key cannot be overidden by unprivileged code starting them), in contrast to the secure_getenv() based mode. The invocation ID is now passed in three different ways to a service: - As environment variable $INVOCATION_ID. This is easy to use, but may be overriden by unprivileged code (which might be a bad or a good thing), which means it's incompatible with SUID code (see above). - As extended attribute on the service cgroup. This cannot be overriden by unprivileged code, and may be queried safely from "outside" of a service. However, it is incompatible with containers right now, as unprivileged containers generally cannot set xattrs on cgroupfs. - As "invocation_id" key in the kernel keyring. This has the benefit that the key cannot be changed by unprivileged service code, and thus is safe to access from SUID code (see above). But do note that service code can replace the session keyring with a fresh one that lacks the key. However in that case the key will not be owned by root, which is easily detectable. The keyring is also incompatible with containers right now, as it is not properly namespace aware (but this is being worked on), and thus most container managers mask the keyring-related system calls. Ideally we'd only have one way to pass the invocation ID, but the different ways all have limitations. The invocation ID hookup in journald is currently only available on the host but not in containers, due to the mentioned limitations. How to verify the new invocation ID in the keyring: # systemd-run -t /bin/sh Running as unit: run-rd917366c04f847b480d486017f7239d6.service Press ^] three times within 1s to disconnect TTY. # keyctl show Session Keyring 680208392 --alswrv 0 0 keyring: _ses 250926536 ----s-rv 0 0 \_ user: invocation_id # keyctl request user invocation_id 250926536 # keyctl read 250926536 16 bytes of data in key: 9c96317c ac64495a a42b9cd7 4f3ff96b # echo $INVOCATION_ID 9c96317cac64495aa42b9cd74f3ff96b # ^D This creates a new transient service runnint a shell. Then verifies the contents of the keyring, requests the invocation ID key, and reads its payload. For comparison the invocation ID as passed via the environment variable is also displayed.
2016-12-02 15:05:55 +01:00
#include "user-util.h"
#include "util.h"
_public_ char *sd_id128_to_string(sd_id128_t id, char s[SD_ID128_STRING_MAX]) {
unsigned n;
assert_return(s, NULL);
for (n = 0; n < 16; n++) {
s[n*2] = hexchar(id.bytes[n] >> 4);
s[n*2+1] = hexchar(id.bytes[n] & 0xF);
}
s[32] = 0;
return s;
}
_public_ int sd_id128_from_string(const char s[], sd_id128_t *ret) {
unsigned n, i;
sd_id128_t t;
bool is_guid = false;
assert_return(s, -EINVAL);
for (n = 0, i = 0; n < 16;) {
int a, b;
if (s[i] == '-') {
/* Is this a GUID? Then be nice, and skip over
* the dashes */
if (i == 8)
is_guid = true;
2017-09-28 10:17:04 +02:00
else if (IN_SET(i, 13, 18, 23)) {
if (!is_guid)
return -EINVAL;
} else
return -EINVAL;
i++;
continue;
}
a = unhexchar(s[i++]);
if (a < 0)
return -EINVAL;
b = unhexchar(s[i++]);
if (b < 0)
return -EINVAL;
t.bytes[n++] = (a << 4) | b;
}
if (i != (is_guid ? 36 : 32))
return -EINVAL;
if (s[i] != 0)
return -EINVAL;
if (ret)
*ret = t;
return 0;
}
_public_ int sd_id128_get_machine(sd_id128_t *ret) {
static thread_local sd_id128_t saved_machine_id = {};
int r;
assert_return(ret, -EINVAL);
if (sd_id128_is_null(saved_machine_id)) {
r = id128_read("/etc/machine-id", ID128_PLAIN, &saved_machine_id);
if (r < 0)
return r;
if (sd_id128_is_null(saved_machine_id))
return -ENOMEDIUM;
}
*ret = saved_machine_id;
return 0;
}
_public_ int sd_id128_get_boot(sd_id128_t *ret) {
static thread_local sd_id128_t saved_boot_id = {};
int r;
assert_return(ret, -EINVAL);
if (sd_id128_is_null(saved_boot_id)) {
r = id128_read("/proc/sys/kernel/random/boot_id", ID128_UUID, &saved_boot_id);
if (r < 0)
return r;
}
*ret = saved_boot_id;
return 0;
}
core: store the invocation ID in the per-service keyring Let's store the invocation ID in the per-service keyring as a root-owned key, with strict access rights. This has the advantage over the environment-based ID passing that it also works from SUID binaries (as they key cannot be overidden by unprivileged code starting them), in contrast to the secure_getenv() based mode. The invocation ID is now passed in three different ways to a service: - As environment variable $INVOCATION_ID. This is easy to use, but may be overriden by unprivileged code (which might be a bad or a good thing), which means it's incompatible with SUID code (see above). - As extended attribute on the service cgroup. This cannot be overriden by unprivileged code, and may be queried safely from "outside" of a service. However, it is incompatible with containers right now, as unprivileged containers generally cannot set xattrs on cgroupfs. - As "invocation_id" key in the kernel keyring. This has the benefit that the key cannot be changed by unprivileged service code, and thus is safe to access from SUID code (see above). But do note that service code can replace the session keyring with a fresh one that lacks the key. However in that case the key will not be owned by root, which is easily detectable. The keyring is also incompatible with containers right now, as it is not properly namespace aware (but this is being worked on), and thus most container managers mask the keyring-related system calls. Ideally we'd only have one way to pass the invocation ID, but the different ways all have limitations. The invocation ID hookup in journald is currently only available on the host but not in containers, due to the mentioned limitations. How to verify the new invocation ID in the keyring: # systemd-run -t /bin/sh Running as unit: run-rd917366c04f847b480d486017f7239d6.service Press ^] three times within 1s to disconnect TTY. # keyctl show Session Keyring 680208392 --alswrv 0 0 keyring: _ses 250926536 ----s-rv 0 0 \_ user: invocation_id # keyctl request user invocation_id 250926536 # keyctl read 250926536 16 bytes of data in key: 9c96317c ac64495a a42b9cd7 4f3ff96b # echo $INVOCATION_ID 9c96317cac64495aa42b9cd74f3ff96b # ^D This creates a new transient service runnint a shell. Then verifies the contents of the keyring, requests the invocation ID key, and reads its payload. For comparison the invocation ID as passed via the environment variable is also displayed.
2016-12-02 15:05:55 +01:00
static int get_invocation_from_keyring(sd_id128_t *ret) {
_cleanup_free_ char *description = NULL;
char *d, *p, *g, *u, *e;
unsigned long perms;
key_serial_t key;
size_t sz = 256;
uid_t uid;
gid_t gid;
int r, c;
#define MAX_PERMS ((unsigned long) (KEY_POS_VIEW|KEY_POS_READ|KEY_POS_SEARCH| \
KEY_USR_VIEW|KEY_USR_READ|KEY_USR_SEARCH))
assert(ret);
key = request_key("user", "invocation_id", NULL, 0);
if (key == -1) {
/* Keyring support not available? No invocation key stored? */
if (IN_SET(errno, ENOSYS, ENOKEY))
return 0;
return -errno;
}
for (;;) {
description = new(char, sz);
if (!description)
return -ENOMEM;
c = keyctl(KEYCTL_DESCRIBE, key, (unsigned long) description, sz, 0);
if (c < 0)
return -errno;
if ((size_t) c <= sz)
break;
sz = c;
free(description);
}
/* The kernel returns a final NUL in the string, verify that. */
assert(description[c-1] == 0);
/* Chop off the final description string */
d = strrchr(description, ';');
if (!d)
return -EIO;
*d = 0;
/* Look for the permissions */
p = strrchr(description, ';');
if (!p)
return -EIO;
errno = 0;
perms = strtoul(p + 1, &e, 16);
if (errno > 0)
return -errno;
if (e == p + 1) /* Read at least one character */
return -EIO;
if (e != d) /* Must reached the end */
return -EIO;
if ((perms & ~MAX_PERMS) != 0)
return -EPERM;
*p = 0;
/* Look for the group ID */
g = strrchr(description, ';');
if (!g)
return -EIO;
r = parse_gid(g + 1, &gid);
if (r < 0)
return r;
if (gid != 0)
return -EPERM;
*g = 0;
/* Look for the user ID */
u = strrchr(description, ';');
if (!u)
return -EIO;
r = parse_uid(u + 1, &uid);
if (r < 0)
return r;
if (uid != 0)
return -EPERM;
c = keyctl(KEYCTL_READ, key, (unsigned long) ret, sizeof(sd_id128_t), 0);
if (c < 0)
return -errno;
if (c != sizeof(sd_id128_t))
return -EIO;
return 1;
}
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.
2016-08-30 23:18:46 +02:00
_public_ int sd_id128_get_invocation(sd_id128_t *ret) {
static thread_local sd_id128_t saved_invocation_id = {};
int r;
assert_return(ret, -EINVAL);
if (sd_id128_is_null(saved_invocation_id)) {
core: store the invocation ID in the per-service keyring Let's store the invocation ID in the per-service keyring as a root-owned key, with strict access rights. This has the advantage over the environment-based ID passing that it also works from SUID binaries (as they key cannot be overidden by unprivileged code starting them), in contrast to the secure_getenv() based mode. The invocation ID is now passed in three different ways to a service: - As environment variable $INVOCATION_ID. This is easy to use, but may be overriden by unprivileged code (which might be a bad or a good thing), which means it's incompatible with SUID code (see above). - As extended attribute on the service cgroup. This cannot be overriden by unprivileged code, and may be queried safely from "outside" of a service. However, it is incompatible with containers right now, as unprivileged containers generally cannot set xattrs on cgroupfs. - As "invocation_id" key in the kernel keyring. This has the benefit that the key cannot be changed by unprivileged service code, and thus is safe to access from SUID code (see above). But do note that service code can replace the session keyring with a fresh one that lacks the key. However in that case the key will not be owned by root, which is easily detectable. The keyring is also incompatible with containers right now, as it is not properly namespace aware (but this is being worked on), and thus most container managers mask the keyring-related system calls. Ideally we'd only have one way to pass the invocation ID, but the different ways all have limitations. The invocation ID hookup in journald is currently only available on the host but not in containers, due to the mentioned limitations. How to verify the new invocation ID in the keyring: # systemd-run -t /bin/sh Running as unit: run-rd917366c04f847b480d486017f7239d6.service Press ^] three times within 1s to disconnect TTY. # keyctl show Session Keyring 680208392 --alswrv 0 0 keyring: _ses 250926536 ----s-rv 0 0 \_ user: invocation_id # keyctl request user invocation_id 250926536 # keyctl read 250926536 16 bytes of data in key: 9c96317c ac64495a a42b9cd7 4f3ff96b # echo $INVOCATION_ID 9c96317cac64495aa42b9cd74f3ff96b # ^D This creates a new transient service runnint a shell. Then verifies the contents of the keyring, requests the invocation ID key, and reads its payload. For comparison the invocation ID as passed via the environment variable is also displayed.
2016-12-02 15:05:55 +01:00
/* We first try to read the invocation ID from the kernel keyring. This has the benefit that it is not
* fakeable by unprivileged code. If the information is not available in the keyring, we use
* $INVOCATION_ID but ignore the data if our process was called by less privileged code
* (i.e. secure_getenv() instead of getenv()).
*
* The kernel keyring is only relevant for system services (as for user services we don't store the
* invocation ID in the keyring, as there'd be no trust benefit in that). The environment variable is
* primarily relevant for user services, and sufficiently safe as no privilege boundary is involved. */
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.
2016-08-30 23:18:46 +02:00
core: store the invocation ID in the per-service keyring Let's store the invocation ID in the per-service keyring as a root-owned key, with strict access rights. This has the advantage over the environment-based ID passing that it also works from SUID binaries (as they key cannot be overidden by unprivileged code starting them), in contrast to the secure_getenv() based mode. The invocation ID is now passed in three different ways to a service: - As environment variable $INVOCATION_ID. This is easy to use, but may be overriden by unprivileged code (which might be a bad or a good thing), which means it's incompatible with SUID code (see above). - As extended attribute on the service cgroup. This cannot be overriden by unprivileged code, and may be queried safely from "outside" of a service. However, it is incompatible with containers right now, as unprivileged containers generally cannot set xattrs on cgroupfs. - As "invocation_id" key in the kernel keyring. This has the benefit that the key cannot be changed by unprivileged service code, and thus is safe to access from SUID code (see above). But do note that service code can replace the session keyring with a fresh one that lacks the key. However in that case the key will not be owned by root, which is easily detectable. The keyring is also incompatible with containers right now, as it is not properly namespace aware (but this is being worked on), and thus most container managers mask the keyring-related system calls. Ideally we'd only have one way to pass the invocation ID, but the different ways all have limitations. The invocation ID hookup in journald is currently only available on the host but not in containers, due to the mentioned limitations. How to verify the new invocation ID in the keyring: # systemd-run -t /bin/sh Running as unit: run-rd917366c04f847b480d486017f7239d6.service Press ^] three times within 1s to disconnect TTY. # keyctl show Session Keyring 680208392 --alswrv 0 0 keyring: _ses 250926536 ----s-rv 0 0 \_ user: invocation_id # keyctl request user invocation_id 250926536 # keyctl read 250926536 16 bytes of data in key: 9c96317c ac64495a a42b9cd7 4f3ff96b # echo $INVOCATION_ID 9c96317cac64495aa42b9cd74f3ff96b # ^D This creates a new transient service runnint a shell. Then verifies the contents of the keyring, requests the invocation ID key, and reads its payload. For comparison the invocation ID as passed via the environment variable is also displayed.
2016-12-02 15:05:55 +01:00
r = get_invocation_from_keyring(&saved_invocation_id);
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.
2016-08-30 23:18:46 +02:00
if (r < 0)
return r;
core: store the invocation ID in the per-service keyring Let's store the invocation ID in the per-service keyring as a root-owned key, with strict access rights. This has the advantage over the environment-based ID passing that it also works from SUID binaries (as they key cannot be overidden by unprivileged code starting them), in contrast to the secure_getenv() based mode. The invocation ID is now passed in three different ways to a service: - As environment variable $INVOCATION_ID. This is easy to use, but may be overriden by unprivileged code (which might be a bad or a good thing), which means it's incompatible with SUID code (see above). - As extended attribute on the service cgroup. This cannot be overriden by unprivileged code, and may be queried safely from "outside" of a service. However, it is incompatible with containers right now, as unprivileged containers generally cannot set xattrs on cgroupfs. - As "invocation_id" key in the kernel keyring. This has the benefit that the key cannot be changed by unprivileged service code, and thus is safe to access from SUID code (see above). But do note that service code can replace the session keyring with a fresh one that lacks the key. However in that case the key will not be owned by root, which is easily detectable. The keyring is also incompatible with containers right now, as it is not properly namespace aware (but this is being worked on), and thus most container managers mask the keyring-related system calls. Ideally we'd only have one way to pass the invocation ID, but the different ways all have limitations. The invocation ID hookup in journald is currently only available on the host but not in containers, due to the mentioned limitations. How to verify the new invocation ID in the keyring: # systemd-run -t /bin/sh Running as unit: run-rd917366c04f847b480d486017f7239d6.service Press ^] three times within 1s to disconnect TTY. # keyctl show Session Keyring 680208392 --alswrv 0 0 keyring: _ses 250926536 ----s-rv 0 0 \_ user: invocation_id # keyctl request user invocation_id 250926536 # keyctl read 250926536 16 bytes of data in key: 9c96317c ac64495a a42b9cd7 4f3ff96b # echo $INVOCATION_ID 9c96317cac64495aa42b9cd74f3ff96b # ^D This creates a new transient service runnint a shell. Then verifies the contents of the keyring, requests the invocation ID key, and reads its payload. For comparison the invocation ID as passed via the environment variable is also displayed.
2016-12-02 15:05:55 +01:00
if (r == 0) {
const char *e;
e = secure_getenv("INVOCATION_ID");
if (!e)
return -ENXIO;
r = sd_id128_from_string(e, &saved_invocation_id);
if (r < 0)
return r;
}
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.
2016-08-30 23:18:46 +02:00
}
*ret = saved_invocation_id;
return 0;
}
static sd_id128_t make_v4_uuid(sd_id128_t id) {
/* Stolen from generate_random_uuid() of drivers/char/random.c
* in the kernel sources */
/* Set UUID version to 4 --- truly random generation */
id.bytes[6] = (id.bytes[6] & 0x0F) | 0x40;
/* Set the UUID variant to DCE */
id.bytes[8] = (id.bytes[8] & 0x3F) | 0x80;
return id;
}
_public_ int sd_id128_randomize(sd_id128_t *ret) {
sd_id128_t t;
2014-02-19 17:50:15 +01:00
int r;
assert_return(ret, -EINVAL);
basic/random-util: do not fall back to /dev/urandom if getrandom() returns short During early boot, we'd call getrandom(), and immediately fall back to reading from /dev/urandom unless we got the full requested number of bytes. Those two sources are the same, so the most likely result is /dev/urandom producing some pseudorandom numbers for us, complaining widely on the way. Let's change our behaviour to be more conservative: - if the numbers are only used to initialize a hash table, a short read is OK, we don't really care if we get the first part of the seed truly random and then some pseudorandom bytes. So just do that and return "success". - if getrandom() returns -EAGAIN, fall back to rand() instead of querying /dev/urandom again. The idea with those two changes is to avoid generating a warning about reading from an /dev/urandom when the kernel doesn't have enough entropy. - only in the cases where we really need to make the best effort possible (sd_id128_randomize and firstboot password hashing), fall back to /dev/urandom. When calling getrandom(), drop the checks whether the argument fits in an int — getrandom() should do that for us already, and we call it with small arguments only anyway. Note that this does not really change the (relatively high) number of random bytes we request from the kernel. On my laptop, during boot, PID 1 and all other processes using this code through libsystemd request: 74780 bytes with high_quality_required == false 464 bytes with high_quality_required == true and it does not eliminate reads from /dev/urandom completely. If the kernel was short on entropy and getrandom() would fail, we would fall back to /dev/urandom for those 464 bytes. When falling back to /dev/urandom, don't lose the short read we already got, and just read the remaining bytes. If getrandom() syscall is not available, we fall back to /dev/urandom same as before. Fixes #4167 (possibly partially, let's see).
2017-06-25 23:09:05 +02:00
r = acquire_random_bytes(&t, sizeof t, true);
2014-02-19 17:50:15 +01:00
if (r < 0)
return r;
/* Turn this into a valid v4 UUID, to be nice. Note that we
* only guarantee this for newly generated UUIDs, not for
* pre-existing ones. */
*ret = make_v4_uuid(t);
return 0;
}
static int get_app_specific(sd_id128_t base, sd_id128_t app_id, sd_id128_t *ret) {
_cleanup_(khash_unrefp) khash *h = NULL;
sd_id128_t result;
const void *p;
int r;
assert(ret);
r = khash_new_with_key(&h, "hmac(sha256)", &base, sizeof(base));
if (r < 0)
return r;
r = khash_put(h, &app_id, sizeof(app_id));
if (r < 0)
return r;
r = khash_digest_data(h, &p);
if (r < 0)
return r;
/* We chop off the trailing 16 bytes */
memcpy(&result, p, MIN(khash_get_size(h), sizeof(result)));
*ret = make_v4_uuid(result);
return 0;
}
_public_ int sd_id128_get_machine_app_specific(sd_id128_t app_id, sd_id128_t *ret) {
sd_id128_t id;
int r;
assert_return(ret, -EINVAL);
r = sd_id128_get_machine(&id);
if (r < 0)
return r;
return get_app_specific(id, app_id, ret);
}
_public_ int sd_id128_get_boot_app_specific(sd_id128_t app_id, sd_id128_t *ret) {
sd_id128_t id;
int r;
assert_return(ret, -EINVAL);
r = sd_id128_get_boot(&id);
if (r < 0)
return r;
return get_app_specific(id, app_id, ret);
}