chiark / gitweb /
6 years agosystemctl: suppress duplicate newline if there's not log output in "systemctl status"
Lennart Poettering [Thu, 13 Mar 2014 02:58:03 +0000 (03:58 +0100)]
systemctl: suppress duplicate newline if there's not log output in "systemctl status"

6 years agosystemctl: reorder verbs
Lennart Poettering [Thu, 13 Mar 2014 02:44:32 +0000 (03:44 +0100)]
systemctl: reorder verbs

6 years agosystemctl: make sure status -a doesn't terminate too soon
Lennart Poettering [Thu, 13 Mar 2014 02:44:21 +0000 (03:44 +0100)]
systemctl: make sure status -a doesn't terminate too soon

6 years agosystemctl: show a colored red dot in "status" output indicating the state of a unit
Lennart Poettering [Thu, 13 Mar 2014 02:43:36 +0000 (03:43 +0100)]
systemctl: show a colored red dot in "status" output indicating the state of a unit

6 years agobuild-sys: make sure we rebuild manpages when doing releases
Zbigniew Jędrzejewski-Szmek [Thu, 13 Mar 2014 01:39:31 +0000 (21:39 -0400)]
build-sys: make sure we rebuild manpages when doing releases

6 years agoupdate TODO
Lennart Poettering [Thu, 13 Mar 2014 00:39:09 +0000 (01:39 +0100)]
update TODO

6 years agonspawn: honour GPT partition flags when mounting file systems following the discovera...
Lennart Poettering [Thu, 13 Mar 2014 00:33:33 +0000 (01:33 +0100)]
nspawn: honour GPT partition flags when mounting file systems following the discoverable partitions spec

6 years agogpt-auto-generator: there's no point in looking for a superblock on raw disk, we...
Lennart Poettering [Thu, 13 Mar 2014 00:06:41 +0000 (01:06 +0100)]
gpt-auto-generator: there's no point in looking for a superblock on raw disk, we only care for a partition table

6 years agogpt-auto-generator: print debug messages when we ignore a block device
Lennart Poettering [Thu, 13 Mar 2014 00:06:19 +0000 (01:06 +0100)]
gpt-auto-generator: print debug messages when we ignore a block device

6 years agogpt-auto-generator: honour read-only and no-auto flag from GPT data
Lennart Poettering [Thu, 13 Mar 2014 00:01:56 +0000 (01:01 +0100)]
gpt-auto-generator: honour read-only and no-auto flag from GPT data

Similar to the read-only and no-automount flags of Microsoft Basic Data
Partitions, introduce our own flags. We map them to the same flag bits
as Microsoft's, to keep things simple.

6 years agocryptsetup: call static variables parsed from command line arg_XYZ like in all other...
Lennart Poettering [Wed, 12 Mar 2014 23:46:58 +0000 (00:46 +0100)]
cryptsetup: call static variables parsed from command line arg_XYZ like in all other tools

6 years agogpt-auto-generator: don't return OOM on parentless devices
Tomasz Torcz [Wed, 12 Mar 2014 18:25:11 +0000 (19:25 +0100)]
gpt-auto-generator: don't return OOM on parentless devices

6 years agosocket.c: make use of union sockaddr_union
Daniel Buch [Wed, 12 Mar 2014 19:09:25 +0000 (20:09 +0100)]
socket.c: make use of union sockaddr_union

6 years agosystemctl: when "systemctl status" is called without arguments show a short overall...
Lennart Poettering [Wed, 12 Mar 2014 22:33:46 +0000 (23:33 +0100)]
systemctl: when "systemctl status" is called without arguments show a short overall system state

Previously "systemctl status" without argument would print the status of
all loaded units. This has now been moved to "systemctl status -a".

6 years agomanager: use system state enum where appropriate
Lennart Poettering [Wed, 12 Mar 2014 21:27:13 +0000 (22:27 +0100)]
manager: use system state enum where appropriate

6 years agomacro: make sure we can use IN_SET() also with complex function calls as first argument
Lennart Poettering [Wed, 12 Mar 2014 21:26:22 +0000 (22:26 +0100)]
macro: make sure we can use IN_SET() also with complex function calls as first argument

6 years agosystemctl: add new "list-machines" command
Lennart Poettering [Wed, 12 Mar 2014 20:13:58 +0000 (21:13 +0100)]
systemctl: add new "list-machines" command

"systemctl list-machines" shows one line per local container which
includes the current system state of the container, the number of failed
units as well as the number of currently queued jobs.

6 years agocore: introduce system state enum
Lennart Poettering [Wed, 12 Mar 2014 19:55:13 +0000 (20:55 +0100)]
core: introduce system state enum

The system state knows the states starting →
running/degraded/maintenance → stopping, where:

starting = system startup
running = normal operation
degraded = at least one unit is currently in failed state
maintenance = rescue/emergency mode is active or queued
stopping = system shutdown

6 years agosd-login: add sd_machine_get_class() call
Lennart Poettering [Wed, 12 Mar 2014 19:54:29 +0000 (20:54 +0100)]
sd-login: add sd_machine_get_class() call

6 years agoutil: Make in_charset a static inline in util.h
Josh Triplett [Wed, 12 Mar 2014 01:51:17 +0000 (18:51 -0700)]
util: Make in_charset a static inline in util.h

With in_charset now reduced to a one-liner (plus asserts), make it a
static inline.

6 years agoutil: Rewrite in_charset to use strspn
Josh Triplett [Tue, 11 Mar 2014 23:45:56 +0000 (16:45 -0700)]
util: Rewrite in_charset to use strspn

This simplifies in_charset down to a one-liner, and allows for possible
optimizations of strspn in libc.

6 years agobacklight: Avoid restoring brightness to an unreadably dim level
Josh Triplett [Wed, 12 Mar 2014 04:16:33 +0000 (21:16 -0700)]
backlight: Avoid restoring brightness to an unreadably dim level

Some systems turn the backlight all the way off at the lowest levels.
Clamp saved brightness to at least 1 or 5% of max_brightness.  This
avoids preserving an unreadably dim screen, which would otherwise force
the user to disable state restoration.

6 years agobacklight: Fix copy/paste error printing an unrelated error code
Josh Triplett [Wed, 12 Mar 2014 04:09:04 +0000 (21:09 -0700)]
backlight: Fix copy/paste error printing an unrelated error code

udev_device_get_sysattr_value returns NULL on failure, but doesn't
provide an error code; thus, when printing an error from it, don't print
an unrelated error code from a previous call.

6 years agoNEWS: 211 was actually released past midnight, so let's use the correct date
Lennart Poettering [Wed, 12 Mar 2014 15:39:21 +0000 (16:39 +0100)]
NEWS: 211 was actually released past midnight, so let's use the correct date

6 years agoupdate TODO
Lennart Poettering [Wed, 12 Mar 2014 15:38:49 +0000 (16:38 +0100)]
update TODO

6 years agotest-dhcp-client: remove pointless initializer, wrongly committed earlier
Kay Sievers [Wed, 12 Mar 2014 00:25:05 +0000 (01:25 +0100)]
test-dhcp-client: remove pointless initializer, wrongly committed earlier

6 years agobuild-sys: Fix move-to-rootlibdir v211
Mike Gilbert [Tue, 11 Mar 2014 22:14:18 +0000 (18:14 -0400)]
build-sys: Fix move-to-rootlibdir

Since we now use ln -s --relative, using this sed statement is redundant
and causes broken symlinks to be installed.

6 years agologind: move lid switch handling from logind-main to logind-core
Kay Sievers [Tue, 11 Mar 2014 21:38:54 +0000 (22:38 +0100)]
logind: move lid switch handling from logind-main to logind-core

../src/login/logind-dbus.c:1352: error: undefined reference to 'manager_set_lid_switch_ignore'
collect2: error: ld returned 1 exit status
make[2]: *** [test-login-tables]

6 years agobuild-sys: add libsystemd-label to network/dhcp users
Kay Sievers [Tue, 11 Mar 2014 20:46:36 +0000 (21:46 +0100)]
build-sys: add libsystemd-label to network/dhcp users

6 years agobuild-sys: we still want to rebuild the tarball though on upload
Lennart Poettering [Tue, 11 Mar 2014 19:57:17 +0000 (20:57 +0100)]
build-sys: we still want to rebuild the tarball though on upload

6 years agoNEWS: fix typo
David Herrmann [Tue, 11 Mar 2014 19:46:57 +0000 (20:46 +0100)]
NEWS: fix typo

sittings -> settings

6 years agobuild-sys: when I upload the tarball, don't run the whole distcheck thing again
Lennart Poettering [Tue, 11 Mar 2014 19:45:47 +0000 (20:45 +0100)]
build-sys: when I upload the tarball, don't run the whole distcheck thing again

I run this anyway, and given how slow it is now due to -flto, let's make
my workflow a bit faster...

6 years agoNEWS: update
Kay Sievers [Tue, 11 Mar 2014 19:41:12 +0000 (20:41 +0100)]
NEWS: update

6 years agobuild-sys: prepare release 211
Lennart Poettering [Tue, 11 Mar 2014 19:25:00 +0000 (20:25 +0100)]
build-sys: prepare release 211

6 years agoman: improve nspawn's --user= documentation
Lennart Poettering [Tue, 11 Mar 2014 19:20:54 +0000 (20:20 +0100)]
man: improve nspawn's --user= documentation

6 years agoNEWS: prepare for release 211
Lennart Poettering [Tue, 11 Mar 2014 19:18:06 +0000 (20:18 +0100)]
NEWS: prepare for release 211

6 years agoupdate TODO
Lennart Poettering [Tue, 11 Mar 2014 18:10:49 +0000 (19:10 +0100)]
update TODO

6 years agobus: replace sd_bus_label_{escape,unescape}() by new sd_bus_path_{encode,decode}()
Lennart Poettering [Tue, 11 Mar 2014 18:03:50 +0000 (19:03 +0100)]
bus: replace sd_bus_label_{escape,unescape}() by new sd_bus_path_{encode,decode}()

The new calls work similarly, but enforce a that a common, fixed bus
path prefix is used.

This follows discussions with Simon McVittie on IRC that it should be a
good idea to make sure that people don't use the escaping applied here
too wildly as anything other than the last label of a bus path.

6 years agoupdate TODO
Lennart Poettering [Tue, 11 Mar 2014 17:02:17 +0000 (18:02 +0100)]
update TODO

6 years agofstab-generator: when running in a container, ignore fstab entries referring to devic...
Lennart Poettering [Tue, 11 Mar 2014 16:57:15 +0000 (17:57 +0100)]
fstab-generator: when running in a container, ignore fstab entries referring to device nodes

Since these device nodes will never appear in the container anyway
there's no point in waiting for them.

This makes it easier to boot images generated with general purpose
installers like Anaconda which unconditionally populate /etc/fstab to
boot in containers.

6 years agobuild-sys: sign releases
Zbigniew Jędrzejewski-Szmek [Tue, 11 Mar 2014 16:55:17 +0000 (12:55 -0400)]
build-sys: sign releases

6 years agohostnamectl: read OS pretty_name and cpe_name from remote
Djalal Harouni [Tue, 11 Mar 2014 13:57:16 +0000 (14:57 +0100)]
hostnamectl: read OS pretty_name and cpe_name from remote

6 years agohostnamed: expose OperatingSystemPrettyName and OperatingSystemCPEName on the bus
Djalal Harouni [Tue, 11 Mar 2014 13:57:15 +0000 (14:57 +0100)]
hostnamed: expose OperatingSystemPrettyName and OperatingSystemCPEName on the bus

6 years agohostnamed: minor improvements in context_write_data_other()
Djalal Harouni [Tue, 11 Mar 2014 13:57:14 +0000 (14:57 +0100)]
hostnamed: minor improvements in context_write_data_other()

Prepare context_write_data_other() and rename it to

6 years agologind: Do not fail display count if a device has no parent
Mantas Mikulėnas [Tue, 11 Mar 2014 15:49:00 +0000 (17:49 +0200)]
logind: Do not fail display count if a device has no parent

udev_device_get_parent() may return NULL when the device doesn't have a
parent, as is the case with (for example) /sys/devices/virtual/drm/ttm.

Also, log an actual error message instead of "-12 displays connected".

6 years agonspawn: fix argv[0] for getent
Mantas Mikulėnas [Tue, 11 Mar 2014 16:00:13 +0000 (18:00 +0200)]
nspawn: fix argv[0] for getent

6 years agonspawn: allow using kdbus from nspawn containers
Lennart Poettering [Tue, 11 Mar 2014 16:43:00 +0000 (17:43 +0100)]
nspawn: allow using kdbus from nspawn containers

6 years agocore: support globbing matches in DeviceAllow= when checking for device groups
Lennart Poettering [Tue, 11 Mar 2014 16:42:24 +0000 (17:42 +0100)]
core: support globbing matches in DeviceAllow= when checking for device groups

6 years agogpt-auto-generator: rename root device node symlink to /dev/gpt-auto-root
Lennart Poettering [Tue, 11 Mar 2014 16:27:58 +0000 (17:27 +0100)]
gpt-auto-generator: rename root device node symlink to /dev/gpt-auto-root

Before it was placed in /dev/disk/by-id, which makes it a bit too much
API. However, it's mostly an implementation detail for now, hence move
it out of the stable block device dir.

6 years agohwdb: Update database of Bluetooth company identifiers
Marcel Holtmann [Tue, 11 Mar 2014 16:33:31 +0000 (09:33 -0700)]
hwdb: Update database of Bluetooth company identifiers

6 years agoudev: properly detect reference to unexisting part of PROGRAM's result
Lukas Nykryn [Mon, 24 Feb 2014 16:06:21 +0000 (17:06 +0100)]
udev: properly detect reference to unexisting part of PROGRAM's result

6 years agosd-dhcp-client: use close_nointr_nofail()
Tom Gundersen [Tue, 11 Mar 2014 09:57:00 +0000 (10:57 +0100)]
sd-dhcp-client: use close_nointr_nofail()

We are already assuming the close() will not fail, so make it explicit.

6 years agonetworkd: rework startup
Tom Gundersen [Mon, 10 Mar 2014 22:40:34 +0000 (23:40 +0100)]
networkd: rework startup

Open all listenerns before loading configuration.

6 years agosd-dhcp: generalise ip header generation
Tom Gundersen [Sun, 9 Mar 2014 21:51:07 +0000 (22:51 +0100)]
sd-dhcp: generalise ip header generation

This will be needed for sd-dhcp-server.

6 years agoREADME: document that we still encourage people to turn off audit when they want...
Lennart Poettering [Tue, 11 Mar 2014 04:40:36 +0000 (05:40 +0100)]
README: document that we still encourage people to turn off audit when they want to use containers

6 years agologind: add a debug message in case the session already exists
Djalal Harouni [Wed, 19 Feb 2014 22:17:45 +0000 (23:17 +0100)]
logind: add a debug message in case the session already exists

If the session already exists then the only way to log it is to set the
debug option of pam_systemd. There are no debug messages in the login
service that permits to log if the session already exists.

So just add it, and while we are it add the "uid" field to the debug
message that indicates that the session was created.

6 years agoman: fix description of systemctl --after/--before
Andrey Borzenkov [Fri, 21 Feb 2014 16:44:06 +0000 (20:44 +0400)]
man: fix description of systemctl --after/--before

It was backward - --after fetches After property, so units shown really
come *before* unit given as argument. Same for --before.

6 years agoman: multiple sleep modes are to be separated by whitespace, not commas
Lennart Poettering [Tue, 11 Mar 2014 04:23:39 +0000 (05:23 +0100)]
man: multiple sleep modes are to be separated by whitespace, not commas

As pointed out by Jason A. Donenfeld.

6 years agosystemctl: for switch-root check, if we switch to a systemd init
Harald Hoyer [Thu, 6 Mar 2014 15:35:02 +0000 (16:35 +0100)]
systemctl: for switch-root check, if we switch to a systemd init

If "systemctl switch-root" is called with a specific "INIT" or
/proc/cmdline contains "init=", then systemd would not serialize

Let systemctl check, if the new init is in the standard systemd
installation path and if so, clear the INIT parameter,
to let systemd serialize itsself.

6 years agoutil: add files_same() helper function
Harald Hoyer [Thu, 6 Mar 2014 08:12:57 +0000 (09:12 +0100)]
util: add files_same() helper function

files_same() returns
     1, if the files are the same
     0, if the files have different inode/dev numbers
 errno, for any stat error

6 years agoupdate TODO
Lennart Poettering [Tue, 11 Mar 2014 03:19:43 +0000 (04:19 +0100)]
update TODO

6 years agodbus: suppress duplicate and misleading messages
Lennart Poettering [Tue, 11 Mar 2014 03:10:19 +0000 (04:10 +0100)]
dbus: suppress duplicate and misleading messages

When we try to send a signal on a connection we didn't hae the time to
process the Disconnected message yet, don't generate multiple warning
messages, but only a single debug message.

6 years agoupdate TODO
Lennart Poettering [Tue, 11 Mar 2014 02:09:00 +0000 (03:09 +0100)]
update TODO

6 years agonspawn: fix getent fallback
Lennart Poettering [Tue, 11 Mar 2014 02:08:54 +0000 (03:08 +0100)]
nspawn: fix getent fallback

6 years agoupdate TODO
Lennart Poettering [Tue, 11 Mar 2014 01:48:59 +0000 (02:48 +0100)]
update TODO

6 years agonspawn: when resoliving UIDs/GIDs for "-u", do so in forked off /usr/bin/getent inste...
Lennart Poettering [Tue, 11 Mar 2014 01:41:13 +0000 (02:41 +0100)]
nspawn: when resoliving UIDs/GIDs for "-u", do so in forked off /usr/bin/getent instead of in-process

When the container runs a different native architecture than the host we
shouldn't attempt to load the container's NSS modules with the host's
libc. Instead, resolve UID/GID by invoking /usr/bin/getent in the
container. The tool should be fairly universally available and allows us
to do resolving of the UID/GID with the container's libc in a parsable

6 years agonspawn: make sure we don't try to mount the container block device in the child after...
Lennart Poettering [Tue, 11 Mar 2014 00:01:38 +0000 (01:01 +0100)]
nspawn: make sure we don't try to mount the container block device in the child after the parent added us to the device cgroup

6 years agoupdate TODO
Lennart Poettering [Mon, 10 Mar 2014 22:17:42 +0000 (23:17 +0100)]
update TODO

6 years agorules: mark loop device as SYSTEMD_READY=0 if no file is attached
Peter Rajnoha [Mon, 10 Mar 2014 21:58:14 +0000 (22:58 +0100)]
rules: mark loop device as SYSTEMD_READY=0 if no file is attached

Check existence of loop/backing_file in sysfs and mark loop devices with
SYSTEMD_READY if missing. Such loop files is uninitialized and it's not
ready for use yet (there's no file attached).

6 years agobuild-sys: Find the tools for users with no /sbin:/usr/sbin in PATH since some system...
Samuli Suominen [Sat, 8 Mar 2014 07:49:29 +0000 (09:49 +0200)]
build-sys: Find the tools for users with no /sbin:/usr/sbin in PATH since some systems still make the distiction between bin and sbin.

6 years agonspawn: don't try mknod() of /dev/console with the correct major/minor
Lennart Poettering [Mon, 10 Mar 2014 20:36:01 +0000 (21:36 +0100)]
nspawn: don't try mknod() of /dev/console with the correct major/minor

We overmount /dev/console with an external pty anyway, hence there's no
point in using the real major/minor when we create the node to
overmount. Instead, use the one of /dev/null now.

This fixes a race against the cgroup device controller setup we are
using. In case /dev/console was create before the cgroup policy was
applied all was good, but if created in the opposite order the mknod()
would fail, since creating /dev/console is not allowed by it. Creating
/dev/null instances is however permitted, and hence use it.

6 years agonspawn: add --image= switch to boot GPT disk images that follow the Discoverable...
Lennart Poettering [Mon, 10 Mar 2014 19:35:52 +0000 (20:35 +0100)]
nspawn: add --image= switch to boot GPT disk images that follow the Discoverable Partitions Specification

6 years agoman: fix formatting of uuids
Lennart Poettering [Mon, 10 Mar 2014 16:21:16 +0000 (17:21 +0100)]
man: fix formatting of uuids

6 years agologind: fix policykit checks
Zbigniew Jędrzejewski-Szmek [Mon, 10 Mar 2014 12:25:15 +0000 (08:25 -0400)]
logind: fix policykit checks

6 years agoinput_id: Recognize buttonless joystick types
Martin Pitt [Mon, 10 Mar 2014 07:54:22 +0000 (08:54 +0100)]
input_id: Recognize buttonless joystick types

Input devices like rudders or pedals are joystick-like; they don't have
buttons, but axes like RX, THROTTLE, or RUDDER. These don't interfere with
other device types with absolute axes (touch screens, touchpads, and
accelerometers), so it's fairly safe to mark them as ID_INPUT_JOYSTICK and thus
hand out dynamic ACLs to the user.

6 years agoman: fix example in
poma [Sun, 9 Mar 2014 17:12:50 +0000 (18:12 +0100)]
man: fix example in

'man/' recovery from:

commit eac684ef1c29684b1bcd27a89c38c202e568e469
Author: Tom Gundersen <>
Date:   Tue Feb 25 19:30:40 2014 +0100

    man: split out{work,dev}(5) from systemd-networkd(8)

6 years agonetwork: link - simplify code a bit and remove some debug logging
Tom Gundersen [Sun, 9 Mar 2014 13:43:37 +0000 (14:43 +0100)]
network: link - simplify code a bit and remove some debug logging

6 years agofix off by one error in array index assertion
Dave Reisner [Sat, 8 Mar 2014 22:32:53 +0000 (17:32 -0500)]
fix off by one error in array index assertion

Since the index is already post-incremented when the array is appended
to, this assertion can be wrongly reached when the array is at capacity
(with the NULL terminator). The bug is reproducible on shutdown with
the following settings in /etc/systemd/system.conf:


Reported by Thermi on IRC.

6 years agounits: remove "AllowUser=root own", the bus owner can always own names
Kay Sievers [Sat, 8 Mar 2014 18:38:06 +0000 (19:38 +0100)]
units: remove "AllowUser=root own", the bus owner can always own names

6 years agosd-bus: sync kdbus.h
Daniel Mack [Sat, 8 Mar 2014 17:22:14 +0000 (18:22 +0100)]
sd-bus: sync kdbus.h

6 years agonetworkd: fix confusion from missing braces
Zbigniew Jędrzejewski-Szmek [Sat, 8 Mar 2014 16:57:28 +0000 (11:57 -0500)]
networkd: fix confusion from missing braces

Fixup for 76800848f281c3 'networkd: link - degrade failed UP to warning'.

6 years agosd-bus: check for potential integer overflow in KDBUS_ITEM_FOREACH()
Daniel Mack [Sat, 8 Mar 2014 13:18:48 +0000 (14:18 +0100)]
sd-bus: check for potential integer overflow in KDBUS_ITEM_FOREACH()

For large values of item->size, the 'part' pointer can wrap around,
which results in an illegal pointer, but currently passes the for-loop

6 years agoupdate TODO
Lennart Poettering [Sat, 8 Mar 2014 03:05:48 +0000 (04:05 +0100)]
update TODO

6 years agogpt-auto-generator: probe only partition table and partitions we are interested in
Lennart Poettering [Sat, 8 Mar 2014 02:55:43 +0000 (03:55 +0100)]
gpt-auto-generator: probe only partition table and partitions we are interested in

Instead of iterating through the list of partitions and probing them all
with blkid, simply probe the partition table and use that information to
only probe the partitions we care for.

6 years agonetworkd: link - degrade failed UP to warning
Tom Gundersen [Sat, 8 Mar 2014 00:08:30 +0000 (01:08 +0100)]
networkd: link - degrade failed UP to warning

Something else may still bring the link up, so don't enter failed state prematurely.

6 years agosd-rtnl: increase default timeout to match sd-bus
Tom Gundersen [Sat, 8 Mar 2014 00:05:02 +0000 (01:05 +0100)]
sd-rtnl: increase default timeout to match sd-bus

6 years agoMake tables for DEFINE_STRING_TABLE_LOOKUP consistent
Daniel Mack [Fri, 7 Mar 2014 20:38:48 +0000 (21:38 +0100)]
Make tables for DEFINE_STRING_TABLE_LOOKUP consistent

Bring some arrays that are used for DEFINE_STRING_TABLE_LOOKUP() in the
same order than the enums they reference.

Also, pass the corresponding _MAX value to the array initalizer where

6 years agounits: set 'AllowUser=root own' and 'AllowWorld=talk' own for all .busname files
Daniel Mack [Fri, 7 Mar 2014 16:56:53 +0000 (17:56 +0100)]
units: set 'AllowUser=root own' and 'AllowWorld=talk' own for all .busname files

6 years agodbus1-generator: set AllowWorld=own for now
Daniel Mack [Fri, 7 Mar 2014 16:56:20 +0000 (17:56 +0100)]
dbus1-generator: set AllowWorld=own for now

6 years agosd-bus: add support for policy upload on activator connections
Daniel Mack [Fri, 7 Mar 2014 16:29:01 +0000 (17:29 +0100)]
sd-bus: add support for policy upload on activator connections

Activator connections may upload policy when registering to the bus.
This patch contains code to translate between BusNamePolicy objects and
the kdbus specific items.

6 years agosd-bus: sync kdbus.h (ABI break)
Daniel Mack [Fri, 7 Mar 2014 16:14:52 +0000 (17:14 +0100)]
sd-bus: sync kdbus.h (ABI break)

Bring kdbus.h in sync with recent policy related changes. Most notably,
KDBUS_MAKE_POLICY_OPEN is now gone. The rest doesn't matter for systemd
at this point, as the policy functionality was not yet used.

6 years agobusname: add parser for bus name policies
Daniel Mack [Thu, 6 Mar 2014 21:42:42 +0000 (22:42 +0100)]
busname: add parser for bus name policies

There are three directives to specify bus name polices in .busname

 * AllowUser [username] [access]
 * AllowGroup [groupname] [access]
 * AllowWorld [access]

Where [access] is one of

 * 'see': The user/group/world is allowed to see a name on the bus
 * 'talk': The user/group/world is allowed to talk to a name
 * 'own': The user/group/world is allowed to own a name

There is no user added yet in this commit.

6 years agoman: reference the Discoverable Partitions Spec from the gpt-auto-generator man page
Lennart Poettering [Fri, 7 Mar 2014 17:50:13 +0000 (18:50 +0100)]
man: reference the Discoverable Partitions Spec from the gpt-auto-generator man page

6 years agobusname: don't drop 'service' from the result string
Lennart Poettering [Fri, 7 Mar 2014 16:29:16 +0000 (17:29 +0100)]
busname: don't drop 'service' from the result string

6 years agonetworkd: use new rtnl_message_read() API
Tom Gundersen [Fri, 7 Mar 2014 16:34:38 +0000 (17:34 +0100)]
networkd: use new rtnl_message_read() API

6 years agosd-rtnl: introduce read ether and ip address functions
Susant Sahani [Fri, 7 Mar 2014 15:08:02 +0000 (20:38 +0530)]
sd-rtnl: introduce read ether and ip address functions

This patch introduces reading ethernet address and IPV4/IPv6
as well which is based on table based look up.

[tomegun: rename read_ether() to read_ether_addr() to match the append function.]

6 years agomanager: flush memory stream before using the buffer
Daniel Mack [Fri, 7 Mar 2014 13:43:59 +0000 (14:43 +0100)]
manager: flush memory stream before using the buffer

When the manager receives a SIGUSR2 signal, it opens a memory stream
with open_memstream(), uses the returned file handle for logging, and
dumps the logged content with log_dump().

However, the char* buffer is only safe to use after the file handle has
been flushed with fflush, as the man pages states:

  When the stream is closed (fclose(3)) or flushed (fflush(3)), the
  locations pointed to by ptr and sizeloc are updated to contain,
  respectively, a pointer to the buffer and the current size of  the
  These values remain valid only as long as the caller performs no
  further output on the stream.  If further output is performed, then the
  stream must again be flushed before trying to access these variables.

Without that call, dump remains NULL and the daemon crashes in

6 years agoudev-builtin-blkid: remove dead code
Kay Sievers [Fri, 7 Mar 2014 13:37:01 +0000 (14:37 +0100)]
udev-builtin-blkid: remove dead code

6 years agocore/busname: add lookup string for BUSNAME_FAILURE_SERVICE_FAILED_PERMANENT
Daniel Mack [Fri, 7 Mar 2014 10:41:18 +0000 (11:41 +0100)]
core/busname: add lookup string for BUSNAME_FAILURE_SERVICE_FAILED_PERMANENT

serialization will not be able to look up the result as string via
busname_result_to_string(). This leads to an assertion trap during

6 years agounits: Do not unescape instance name in systemd-backlight@.service
Thomas Bächler [Fri, 7 Mar 2014 00:50:34 +0000 (01:50 +0100)]
units: Do not unescape instance name in systemd-backlight@.service

The instance name is never escaped in the udev rule, but unescaped in the unit.
This results in the following error message on Asus boards:

  Failed to get backlight or LED device 'backlight:eeepc/wmi': No such file or directory