chiark / gitweb /
elogind.git
10 years agoDo not return -1 (EINVAL) on allocation error
Zbigniew Jędrzejewski-Szmek [Fri, 14 Mar 2014 13:05:56 +0000 (09:05 -0400)]
Do not return -1 (EINVAL) on allocation error

10 years agomachine-id-setup: use path_kill_slashes and modernizations
Zbigniew Jędrzejewski-Szmek [Fri, 14 Mar 2014 12:43:21 +0000 (08:43 -0400)]
machine-id-setup: use path_kill_slashes and modernizations

10 years agoman: network - clarify which options may be specified more than once.
Tom Gundersen [Fri, 14 Mar 2014 12:04:57 +0000 (13:04 +0100)]
man: network - clarify which options may be specified more than once.

10 years agomachine-id: add --root option to operate on an alternate fs tree
Greg KH [Fri, 14 Mar 2014 04:43:04 +0000 (04:43 +0000)]
machine-id: add --root option to operate on an alternate fs tree

This makes it possible to initialize the /etc/machine-id file on an
arbitrary filesystem hierarchy.  This helps systems that wish to run
this at image creation time in a subdirectory, or from initramfs before
pivot-root is called.

[tomegun: converted to using _cleanup_free_ macros]

10 years agonetworkd: allow more than one static DNS server
Tom Gundersen [Thu, 13 Mar 2014 19:46:45 +0000 (20:46 +0100)]
networkd: allow more than one static DNS server

10 years agonetworkd: fix creation of runtime dirs at startup
Tom Gundersen [Thu, 13 Mar 2014 18:02:28 +0000 (19:02 +0100)]
networkd: fix creation of runtime dirs at startup

This allows us to drop the repeated attempted creations of the runtime dirs during runtime.

10 years agonetworkd: lease - store (up to) one dhcp lease file per interface
Tom Gundersen [Thu, 13 Mar 2014 17:42:56 +0000 (18:42 +0100)]
networkd: lease - store (up to) one dhcp lease file per interface

This removes an accidentally left-over test fragment.

10 years agonspawn: remove unused variable
Dave Reisner [Fri, 14 Mar 2014 01:56:07 +0000 (21:56 -0400)]
nspawn: remove unused variable

10 years agonspawn: allow -EEXIST on mkdir_safe /home/${uid}
Brandon Philips [Thu, 13 Mar 2014 22:19:40 +0000 (15:19 -0700)]
nspawn: allow -EEXIST on mkdir_safe /home/${uid}

With systemd 211 nspawn attempts to create the home directory for the
given uid. However, if the home directory already exists then it will
fail. Don't error out on -EEXIST.

10 years agoupdate TODO
Lennart Poettering [Fri, 14 Mar 2014 00:49:32 +0000 (01:49 +0100)]
update TODO

10 years agologind: automatically remove SysV + POSIX IPC objects when the users owning them...
Lennart Poettering [Fri, 14 Mar 2014 00:38:19 +0000 (01:38 +0100)]
logind: automatically remove SysV + POSIX IPC objects when the users owning them fully log out

10 years agotimedated: add SNTP client/query hookup (unused for now)
Kay Sievers [Mon, 10 Mar 2014 21:15:56 +0000 (22:15 +0100)]
timedated: add SNTP client/query hookup (unused for now)

10 years agosd-bus: don't look for a 64bit value when we only have 32bit value on reply cookie...
Lennart Poettering [Thu, 13 Mar 2014 19:33:22 +0000 (20:33 +0100)]
sd-bus: don't look for a 64bit value when we only have 32bit value on reply cookie hash table access

This broke hashtable lookups for the message cookies on s390x, which is
a 64bit BE machine where accessing 32bit values as 64bit and vice versa
will explode.

Also, while we are at it, be a bit more careful when dealing with the
64bit cookies we expose and the 32bit serial numbers dbus uses in its
payload.

Problem identified by Fridrich Strba.

10 years agobus: fix memory leak when kdbus is not enabled
Lennart Poettering [Thu, 13 Mar 2014 19:00:50 +0000 (20:00 +0100)]
bus: fix memory leak when kdbus is not enabled

10 years agonspawn: make host0's MAC address persistent
Tom Gundersen [Thu, 13 Mar 2014 16:47:30 +0000 (17:47 +0100)]
nspawn: make host0's MAC address persistent

We still need to make sure that no two MAC addresses are the same, so we use
a logic similar to what is used in udev to generate MAC addresses, and base
it on a hash of the host's machine ID and thecontainer's name.

10 years agogetty: Start getty on 3270 terminals available on Linux on System z
Hendrik Brueckner [Tue, 11 Mar 2014 17:41:09 +0000 (18:41 +0100)]
getty: Start getty on 3270 terminals available on Linux on System z

Add the first 3270 terminal device that is associated with the Linux preferred
console to the list of virtualization consoles.  This is required to
automatically start a getty if the conmode=3270 kernel parameter is specified
for Linux on z/VM instances.  Note that a queued upstream patch also enable
the 3270 terminal device if it is associated with the Linux preferred console.
How

To successfully start agetty on a 3270 terminal, a change in the agetty
parameter order is required.  Previously, agetty would started like this:

    /sbin/agetty --keep-baud 3270/tty1 115200,38400,9600 TERM

The agetty program interprets the "3270/tty1" as baud rate and fails to start
with the "bad speed: 3270/tty1" error message.  Fixing this in agetty is more
complex rather than reordering the command line parameters like this:

    /sbin/agetty --keep-baud 115200,38400,9600 3270/tty1 TERM

According to agetty sources and "agetty --help", agetty accepts the "tty",
"baudrate tty", and "tty baudrate" specifications.

P.S. The "tty: Set correct tty name in 'active' sysfs attribute" introduces
     a change to display the terminal device which is associated with the
     Linux preferred console.  This change helps to let systemd handle this
     particular case only.  Without the changes of this commit, no additional
     3270 terminal device can be managed by systemd.

     https://git.kernel.org/cgit/linux/kernel/git/gregkh/tty.git/commit/?id=723abd87f6e536f1353c8f64f621520bc29523a3

10 years agosystemctl: autopage always if systemctl status is invoked without args
Lennart Poettering [Thu, 13 Mar 2014 02:58:56 +0000 (03:58 +0100)]
systemctl: autopage always if systemctl status is invoked without args

10 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"

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

10 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

10 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

10 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

https://bugs.freedesktop.org/show_bug.cgi?id=76056

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

10 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

10 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

10 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

10 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.

10 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

10 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

10 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

10 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".

10 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

10 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

10 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.

10 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

10 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

10 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.

10 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.

10 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.

10 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.

10 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

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

10 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

10 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.

10 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]

10 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

10 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

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

sittings -> settings

10 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...

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

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

10 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

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

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

10 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.

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

10 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.

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

10 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

10 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

10 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
context_write_data_machine_info()

10 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".

10 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

10 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

10 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

10 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.

10 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

10 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

10 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.

10 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.

10 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.

10 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

10 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.

10 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.

10 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.

10 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
itsself.

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.

10 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

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

10 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.

https://bugs.freedesktop.org/show_bug.cgi?id=75874

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

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

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

10 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
format.

https://bugs.freedesktop.org/show_bug.cgi?id=75733

10 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

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

10 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).

10 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.

10 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.

10 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

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

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

10 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.

https://bugs.freedesktop.org/show_bug.cgi?id=70734

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

'man/systemd.link.xml' recovery from:

commit eac684ef1c29684b1bcd27a89c38c202e568e469
Author: Tom Gundersen <teg@jklm.no>
Date:   Tue Feb 25 19:30:40 2014 +0100

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

10 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

10 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:

  LogTarget=journal-or-kmsg
  LogColor=yes
  LogLocation=yes

Reported by Thermi on IRC.

10 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

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

10 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'.

10 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
condition.

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