chiark / gitweb /
elogind.git
6 years agoupdate TODO
Lennart Poettering [Wed, 5 Mar 2014 21:31:03 +0000 (22:31 +0100)]
update TODO

6 years agogenerators: rework mount generators
Lennart Poettering [Wed, 5 Mar 2014 21:26:10 +0000 (22:26 +0100)]
generators: rework mount generators

- Add support for finding and mounting /srv based on GPT data, similar
  to how we already handly /home.

- Share the fsck logic between GPT, EFI and fstab generators

- Make sure we never run the EFI generator inside containers

- Drop DefaultDependencies=no from EFI mount units

- Other fixes

6 years agoman: ipv4 link-local
Umut Tezduyar Lindskog [Wed, 5 Mar 2014 19:51:36 +0000 (20:51 +0100)]
man: ipv4 link-local

6 years agosystemd-run: don't print error messages twice
Lennart Poettering [Wed, 5 Mar 2014 18:02:53 +0000 (19:02 +0100)]
systemd-run: don't print error messages twice

6 years agosystemd-run: make sure --nice=, --uid=, --gid=, --setenv= also work in --scope mode
Lennart Poettering [Wed, 5 Mar 2014 17:57:21 +0000 (18:57 +0100)]
systemd-run: make sure --nice=, --uid=, --gid=, --setenv= also work in --scope mode

6 years agonetworkd: listen to changes to the MAC address
Tom Gundersen [Wed, 5 Mar 2014 10:53:26 +0000 (11:53 +0100)]
networkd: listen to changes to the MAC address

Bridges will change their MAC address when other devices are enslaved. We need
the correct MAC address to acquire a DHCP lease, so take note of it whenever
it changes.

6 years agosd-rtnl: do not blindly enter containers in message_read()
Tom Gundersen [Wed, 5 Mar 2014 10:47:38 +0000 (11:47 +0100)]
sd-rtnl: do not blindly enter containers in message_read()

We need a separate container_enter() function, which will be part of a largerg
API change. For now, just fix message_read().

6 years agosd-dhcp-client: log the MAC address we are using
Tom Gundersen [Wed, 5 Mar 2014 10:07:15 +0000 (11:07 +0100)]
sd-dhcp-client: log the MAC address we are using

6 years agonetworkd: restore logic for enslaving to a master bonding interface
Mark Oteiza [Wed, 5 Mar 2014 09:41:13 +0000 (10:41 +0100)]
networkd: restore logic for enslaving to a master bonding interface

This partially reverts commit 54abf46, which unintentionally removed the
enslaving support for bonding interfaces

6 years agojournal: forget file after encountering an error
Zbigniew Jędrzejewski-Szmek [Thu, 27 Feb 2014 05:11:54 +0000 (00:11 -0500)]
journal: forget file after encountering an error

If we encounter an inconsistency in a file, let's just
ignore it. Otherwise, after previous patch, we would try,
and fail, to use this file in every invocation of sd_journal_next
or sd_journal_previous that happens afterwards.

6 years agojournal: assume that next entry is after previous entry
Zbigniew Jędrzejewski-Szmek [Thu, 27 Feb 2014 05:07:29 +0000 (00:07 -0500)]
journal: assume that next entry is after previous entry

With a corrupted file, we can get in a situation where two entries
in the entry array point to the same object. Then journal_file_next_entry
will find the first one using generic_arrray_bisect, and try to move to
the second one, but since the address is the same, generic_array_get will
return the first one. journal_file_next_entry ends up in an infinite loop.

https://bugzilla.redhat.com/show_bug.cgi?id=1047039

6 years agoupdate TODO
Lennart Poettering [Wed, 5 Mar 2014 03:41:40 +0000 (04:41 +0100)]
update TODO

6 years agocore: don't override NoNewPriviliges= from SystemCallFilter= if it is already explici...
Lennart Poettering [Wed, 5 Mar 2014 03:41:01 +0000 (04:41 +0100)]
core: don't override NoNewPriviliges= from SystemCallFilter= if it is already explicitly set

6 years agosystemd-run: support all currently exported properties with -p
Lennart Poettering [Wed, 5 Mar 2014 03:07:37 +0000 (04:07 +0100)]
systemd-run: support all currently exported properties with -p

6 years agocore: make the LimitXYZ= properties settable for transient service units
Lennart Poettering [Wed, 5 Mar 2014 02:49:00 +0000 (03:49 +0100)]
core: make the LimitXYZ= properties settable for transient service units

6 years agosystemd-run: add some extra safety checks
Lennart Poettering [Wed, 5 Mar 2014 02:38:36 +0000 (03:38 +0100)]
systemd-run: add some extra safety checks

6 years agoman: document missing options of systemd-run
Lennart Poettering [Wed, 5 Mar 2014 02:37:48 +0000 (03:37 +0100)]
man: document missing options of systemd-run

6 years agosystemd-run: add new --property= switch that can set arbitrary properties for the...
Lennart Poettering [Wed, 5 Mar 2014 02:36:22 +0000 (03:36 +0100)]
systemd-run: add new --property= switch that can set arbitrary properties for the unit that is created

The code for parsing these properties is shared with "systemctl
set-property", which means all the resource control settings are
immediately available.

6 years agostrv: add new STR_IN_SET() macro that operates similar to IN_SET() but for strings
Lennart Poettering [Wed, 5 Mar 2014 02:34:48 +0000 (03:34 +0100)]
strv: add new STR_IN_SET() macro that operates similar to IN_SET() but for strings

6 years agoupdate TODO
Lennart Poettering [Wed, 5 Mar 2014 01:30:47 +0000 (02:30 +0100)]
update TODO

6 years agomissing: if RLIMIT_RTTIME is not defined by the libc, then we need a new define for...
Lennart Poettering [Wed, 5 Mar 2014 01:29:58 +0000 (02:29 +0100)]
missing: if RLIMIT_RTTIME is not defined by the libc, then we need a new define for the max number of rlimits, too

6 years agocore: when passing resource limit values to client, map RLIM_INFINITY into portable...
Lennart Poettering [Wed, 5 Mar 2014 01:27:37 +0000 (02:27 +0100)]
core: when passing resource limit values to client, map RLIM_INFINITY into portable value (uint64_t) -1

6 years agoadd bash completion for systemd-cat
Thomas Hindoe Paaboel Andersen [Tue, 4 Mar 2014 22:16:30 +0000 (23:16 +0100)]
add bash completion for systemd-cat

6 years agoarchitecture: Add cris
Umut Tezduyar Lindskog [Tue, 4 Mar 2014 12:58:35 +0000 (13:58 +0100)]
architecture: Add cris

6 years agoupdate TODO
Lennart Poettering [Tue, 4 Mar 2014 19:01:44 +0000 (20:01 +0100)]
update TODO

6 years agologind: make $XDG_RUNTIME_DIR a per-user tmpfs
Lennart Poettering [Tue, 4 Mar 2014 18:20:21 +0000 (19:20 +0100)]
logind: make $XDG_RUNTIME_DIR a per-user tmpfs

This way each user allocates from his own pool, with its own size limit.

This puts the size limit by default to 10% of the physical RAM size but
makes it configurable in logind.conf.

6 years agoDo not print invalid UTF-8 in error messages
Zbigniew Jędrzejewski-Szmek [Tue, 4 Mar 2014 14:50:26 +0000 (09:50 -0500)]
Do not print invalid UTF-8 in error messages

Inexplicably, 550a40ec ('core: do not print invalid utf-8 in error
messages') only fixed two paths. Convert all of them now.

6 years agoIntroduce strv_consume which takes ownership
Zbigniew Jędrzejewski-Szmek [Tue, 4 Mar 2014 14:20:51 +0000 (09:20 -0500)]
Introduce strv_consume which takes ownership

This mirrors set_consume and makes the common use a bit nicer.

6 years agoshutdownd: modernizations
Zbigniew Jędrzejewski-Szmek [Thu, 13 Feb 2014 01:40:11 +0000 (20:40 -0500)]
shutdownd: modernizations

6 years agologind: small simplifications
Zbigniew Jędrzejewski-Szmek [Mon, 3 Feb 2014 04:58:16 +0000 (23:58 -0500)]
logind: small simplifications

6 years agoman: networkd - fix typo
Umut Tezduyar Lindskog [Mon, 3 Mar 2014 20:13:56 +0000 (21:13 +0100)]
man: networkd - fix typo

6 years agobuild-sys: work around broken ln --relative -s -f
Lennart Poettering [Mon, 3 Mar 2014 22:47:40 +0000 (23:47 +0100)]
build-sys: work around broken ln --relative -s -f

As it appears "ln -s --relative" in conjunction with "-f" is broken,
let's work around that by explicitly remove the destination of the
symlink before we create it.

https://bugzilla.redhat.com/show_bug.cgi?id=1072103

6 years agosd-network: IPv4 link-local support [v2]
Umut Tezduyar Lindskog [Fri, 28 Feb 2014 15:10:20 +0000 (16:10 +0100)]
sd-network: IPv4 link-local support [v2]

Implements IPv4LL with respect to RFC 3927
(http://tools.ietf.org/rfc/rfc3927.txt) and integrates it
with networkd. Majority of the IPv4LL state machine is
taken from avahi (http://avahi.org/) project's autoip.

IPv4LL can be enabled by IPv4LL=yes under [Network]
section of .network file.

IPv4LL works independent of DHCP but if DHCP lease is
aquired, then LL address will be dropped.

[tomegun: removed a trailing newline and a compiler warning]

6 years agonetworkd: wait-online - fix typo
Tom Gundersen [Mon, 3 Mar 2014 19:16:12 +0000 (20:16 +0100)]
networkd: wait-online - fix typo

6 years agoupdate TODO
Lennart Poettering [Mon, 3 Mar 2014 22:18:19 +0000 (23:18 +0100)]
update TODO

6 years agocore: fix assert when trying to serialize non-initialized bus peer tracker object
Lennart Poettering [Mon, 3 Mar 2014 22:17:27 +0000 (23:17 +0100)]
core: fix assert when trying to serialize non-initialized bus peer tracker object

6 years agosilence warning
Thomas Hindoe Paaboel Andersen [Mon, 3 Mar 2014 21:22:14 +0000 (22:22 +0100)]
silence warning

6 years agocore: add missing show-status.[ch]
Lennart Poettering [Mon, 3 Mar 2014 21:26:34 +0000 (22:26 +0100)]
core: add missing show-status.[ch]

6 years agoadd bash completion for systemd-detect-virt
Thomas Hindoe Paaboel Andersen [Mon, 3 Mar 2014 21:16:04 +0000 (22:16 +0100)]
add bash completion for systemd-detect-virt

6 years agoupdate bash completion for systemd-analyze
Thomas Hindoe Paaboel Andersen [Mon, 3 Mar 2014 21:01:42 +0000 (22:01 +0100)]
update bash completion for systemd-analyze

6 years agoupdate TODO
Lennart Poettering [Mon, 3 Mar 2014 20:55:41 +0000 (21:55 +0100)]
update TODO

6 years agoconf-parser: minor optimization in config_parse_string()
Lennart Poettering [Mon, 3 Mar 2014 20:53:19 +0000 (21:53 +0100)]
conf-parser: minor optimization in config_parse_string()

6 years agoconf-parser: drop special casing in config_parse_path()
Lennart Poettering [Mon, 3 Mar 2014 20:42:38 +0000 (21:42 +0100)]
conf-parser: drop special casing in config_parse_path()

The code checked for two lvalues that aren't even using
config_parse_path(), so let's drop these checks and make the function
completely generic again.

6 years agoconf-parser: config_parse_path_strv() is not generic, so let's move it into load...
Lennart Poettering [Mon, 3 Mar 2014 20:40:55 +0000 (21:40 +0100)]
conf-parser: config_parse_path_strv() is not generic, so let's move it into load-fragment.c

The parse code actually checked for specific lvalue names, which is
really wrong for supposedly generic parsers...

6 years agocore: move config_parse_set_status() into load-fragment.c
Lennart Poettering [Mon, 3 Mar 2014 20:26:53 +0000 (21:26 +0100)]
core: move config_parse_set_status() into load-fragment.c

Let's keep specific config parsers close to where they are needed. Only
the really generic ones should be defined in conf-parser.[ch].

6 years agocore: move ShowStatus type into the core
Lennart Poettering [Mon, 3 Mar 2014 20:23:12 +0000 (21:23 +0100)]
core: move ShowStatus type into the core

Let's make the scope of the show-status stuff a bit smaller, and make it
private to the core, rather than shared API in shared/.

6 years agoconf-parse: rename config_parse_level() to config_parse_log_level()
Lennart Poettering [Mon, 3 Mar 2014 20:14:07 +0000 (21:14 +0100)]
conf-parse: rename config_parse_level() to config_parse_log_level()

"level" is a bit too generic, let's clarify what kind of level we are
referring to here.

6 years agoupdate TODO
Lennart Poettering [Mon, 3 Mar 2014 20:08:49 +0000 (21:08 +0100)]
update TODO

6 years agologind: ignore lid switch events for 30s after each suspend and 3min after startup
Lennart Poettering [Mon, 3 Mar 2014 19:49:33 +0000 (20:49 +0100)]
logind: ignore lid switch events for 30s after each suspend and 3min after startup

This is needed to give USB docking stations and suchlike time to settle,
so that a display connected to an USB docking station can actually act
as a lid swith inhibitor correctly.

With this change we should have somewhat reliable docking station
support in place.

6 years agologind: fix printf format
Lennart Poettering [Mon, 3 Mar 2014 18:39:51 +0000 (19:39 +0100)]
logind: fix printf format

6 years agologind: ignore lid switch if more than 1 display is connected
Lennart Poettering [Mon, 3 Mar 2014 18:30:16 +0000 (19:30 +0100)]
logind: ignore lid switch if more than 1 display is connected

Previously we expected the desktop environment to take an inhibitor
lock, but this opened a race on boot-up where logind might already be
running but no DE is active.

Hence, let's move checking for additional displays into logind. This
also opens up this logic for other DEs, given that only GNOME
implemented the inhibitor logic so far.

6 years agoman: networkd - mention resolv.conf symlink
Tom Gundersen [Mon, 3 Mar 2014 17:25:37 +0000 (18:25 +0100)]
man: networkd - mention resolv.conf symlink

6 years agocore: introduce new RuntimeDirectory= and RuntimeDirectoryMode= unit settings
Lennart Poettering [Mon, 3 Mar 2014 16:14:07 +0000 (17:14 +0100)]
core: introduce new RuntimeDirectory= and RuntimeDirectoryMode= unit settings

As discussed on the ML these are useful to manage runtime directories
below /run for services.

6 years agoexecute: no need to include seccomp.h from execute.h
Lennart Poettering [Mon, 3 Mar 2014 16:12:56 +0000 (17:12 +0100)]
execute: no need to include seccomp.h from execute.h

6 years agoexecute: free directory path if we fail to remove it because we cannot allocate a...
Lennart Poettering [Mon, 3 Mar 2014 16:11:39 +0000 (17:11 +0100)]
execute: free directory path if we fail to remove it because we cannot allocate a thread

6 years agobuild-sys: prefer using ln --relative -s where appropriate
Lennart Poettering [Mon, 3 Mar 2014 16:10:16 +0000 (17:10 +0100)]
build-sys: prefer using ln --relative -s where appropriate

By using --relative symlinks look nicer when dealing with OS image trees
that are placed in arbitrary places of the OS.

6 years agosd-dhcp-lease: add sd_dhcp_lease_get_next_server()
Tom Gundersen [Mon, 3 Mar 2014 16:13:59 +0000 (17:13 +0100)]
sd-dhcp-lease: add sd_dhcp_lease_get_next_server()

6 years agosd-dhcp-lease: add sd_dhcp_lease_get_server_identifier()
Tom Gundersen [Mon, 3 Mar 2014 15:46:10 +0000 (16:46 +0100)]
sd-dhcp-lease: add sd_dhcp_lease_get_server_identifier()

6 years agosd-dhcp-lease: add Root Path support
Tom Gundersen [Mon, 3 Mar 2014 14:43:02 +0000 (15:43 +0100)]
sd-dhcp-lease: add Root Path support

This is necessary when mounting /dev/nfs based on a DHCP lease.

6 years agoFix systemd-stdio-bridge symlink
Mike Gilbert [Mon, 3 Mar 2014 04:37:39 +0000 (23:37 -0500)]
Fix systemd-stdio-bridge symlink

The symlink is created in bindir (/usr/bin), and points to a binary
which lives in rootlibexecdir (/lib/systemd or /usr/lib/systemd). A
relative symlink does not work here.

6 years agobus: add sd_bus_track object for tracking peers, and port core over to it
Lennart Poettering [Mon, 3 Mar 2014 00:33:45 +0000 (01:33 +0100)]
bus: add sd_bus_track object for tracking peers, and port core over to it

This is primarily useful for services that need to track clients which
reference certain objects they maintain, or which explicitly want to
subscribe to certain events. Something like this is done in a large
number of services, and not trivial to do. Hence, let's unify this at
one place.

This also ports over PID 1 to use this to ensure that subscriptions to
job and manager events are correctly tracked. As a side-effect this
makes sure we properly serialize and restore the track list across
daemon reexec/reload, which didn't work correctly before.

This also simplifies how we distribute messages to broadcast to the
direct busses: we only track subscriptions for the API bus and
implicitly assume that all direct busses are subscribed. This should be
a pretty OK simplification since clients connected via direct bus
connections are shortlived anyway.

6 years agoadd bash completion for systemd-cgtop
Thomas Hindoe Paaboel Andersen [Sun, 2 Mar 2014 21:58:18 +0000 (22:58 +0100)]
add bash completion for systemd-cgtop

6 years agoDisallow sizes with increasing unit size
Zbigniew Jędrzejewski-Szmek [Sun, 2 Mar 2014 18:28:05 +0000 (13:28 -0500)]
Disallow sizes with increasing unit size

Things like 3B4T, 4B50B, 400 100 (meaning 4*1024**4+3, 54, and 500,
respectively) are now disallowed. It is necessary to say 4T3B, 54B,
500 instead. I think this was confusing and error prone.

As a special form, 400B 100 is allowed, i.e. "B" suffix is treated
as different from "", although they mean the same thing.

6 years agoAllow fractional parts in disk sizes
Zbigniew Jędrzejewski-Szmek [Sun, 2 Mar 2014 05:05:16 +0000 (00:05 -0500)]
Allow fractional parts in disk sizes

It seems natural to be able to say SystemMaxUsage=1.5G.

https://bugzilla.redhat.com/show_bug.cgi?id=1047568

6 years agohwdb: Update database of Bluetooth company identifiers
Marcel Holtmann [Sun, 2 Mar 2014 18:02:10 +0000 (10:02 -0800)]
hwdb: Update database of Bluetooth company identifiers

6 years agobuild-sys: fix location of network-util.h
Zbigniew Jędrzejewski-Szmek [Sun, 2 Mar 2014 02:45:27 +0000 (21:45 -0500)]
build-sys: fix location of network-util.h

6 years agonetworkd-wait-online: use automatic cleanup
Thomas Hindoe Paaboel Andersen [Sat, 1 Mar 2014 21:52:25 +0000 (22:52 +0100)]
networkd-wait-online: use automatic cleanup

6 years agoadd bash completion for systemd-cgls
Thomas Hindoe Paaboel Andersen [Sat, 1 Mar 2014 22:08:38 +0000 (23:08 +0100)]
add bash completion for systemd-cgls

6 years agoTODO
Tom Gundersen [Sat, 1 Mar 2014 13:13:18 +0000 (14:13 +0100)]
TODO

6 years agobuild-sys: distribute kdbus documentation
Zbigniew Jędrzejewski-Szmek [Sat, 1 Mar 2014 12:44:47 +0000 (07:44 -0500)]
build-sys: distribute kdbus documentation

6 years agoUpdate gitignore
Zbigniew Jędrzejewski-Szmek [Sat, 1 Mar 2014 12:39:14 +0000 (07:39 -0500)]
Update gitignore

6 years agoupdate TODO
Thomas Hindoe Paaboel Andersen [Sat, 1 Mar 2014 03:03:52 +0000 (04:03 +0100)]
update TODO

6 years agobash: add completion for systemd-nspawn
Thomas Andersen [Sat, 1 Mar 2014 02:27:49 +0000 (03:27 +0100)]
bash: add completion for systemd-nspawn

6 years agonspawn: fix detection of missing /proc/self/loginuid
Tero Roponen [Tue, 25 Feb 2014 15:19:35 +0000 (17:19 +0200)]
nspawn: fix detection of missing /proc/self/loginuid

Running 'systemd-nspawn -D /srv/Fedora/' gave me this error:
 Failed to read /proc/self/loginuid: No such file or directory

 Container Fedora failed with error code 1.

This patch fixes the problem.

6 years agosd-network: turn states 'unknown' and 'unmanaged' into errnos
Tom Gundersen [Fri, 28 Feb 2014 01:07:29 +0000 (02:07 +0100)]
sd-network: turn states 'unknown' and 'unmanaged' into errnos

6 years agosd-network: fix header
Tom Gundersen [Fri, 28 Feb 2014 00:49:41 +0000 (01:49 +0100)]
sd-network: fix header

6 years agoarchitecture: Add tilegx
Henrik Grindal Bakken [Thu, 27 Feb 2014 20:19:13 +0000 (21:19 +0100)]
architecture: Add tilegx

Add Tilera's TILE-GX processor family support.

6 years agonetworkd: add networkd-wait-online
Tom Gundersen [Fri, 28 Feb 2014 00:02:01 +0000 (01:02 +0100)]
networkd: add networkd-wait-online

This is mostly a proof of concept to try sd-network, so we don't
hook it up with a .service file quite yet. We probably want it to
be more clever about deciding when we are 'online'.

The binary  will wait for at least one network managed by networkd,
and until all networks managed by networkd are configured.

6 years agosd-network: add new library
Tom Gundersen [Thu, 27 Feb 2014 00:24:05 +0000 (01:24 +0100)]
sd-network: add new library

This is similar to sd-login, but exposes the state of networkd rather than logind.

Include it in libsystemd-dhcp and rename it to libsystemd-network.

6 years agoudev/rules: setup tty permissions and group for sclp_line, ttysclp and 3270/tty
Lukas Nykryn [Thu, 27 Feb 2014 10:19:09 +0000 (11:19 +0100)]
udev/rules: setup tty permissions and group for sclp_line, ttysclp and 3270/tty

6 years agocdrom_id: use the old MMC fallback
Lukas Nykryn [Thu, 27 Feb 2014 10:06:37 +0000 (11:06 +0100)]
cdrom_id: use the old MMC fallback

https://bugzilla.redhat.com/show_bug.cgi?id=1038015
The problem seems to be that the your virtual DVD is emulating a really
old DVD device, and doing it kind of strangely.

> dracut:# /lib/udev/cdrom_id --debug /dev/sr0
> probing: '/dev/sr0'
> INQUIRY: [IMM     ][Virtual CD/DVD   ][0316]
> GET CONFIGURATION failed with SK=5h/ASC=24h/ACQ=00h

So your virtual drive rejects the GET CONFIGURATION command as illegal.

Other pre-MMC2 drives that don't accept this command usually return the
error
SK=5h,ASC=20h (invalid/unsupported command code), in which case cdrom_id
tries an older method, and then ID_CDROM_MEDIA_TRACK_COUNT_DATA gets set
and all the /dev/disk/by-label (etc) links get set up.

The virtual drive returns the error SK=5h,ASC=24h (invalid field in
Command Descriptor Block), which cdrom_id doesn't handle, so it gives up
and the links never get made.

The ideal solution would be to make the IMM to emulate a device that's
less than 15 years old, but I'm not going to hold my breath waiting for
that.

So probably cdrom_id should also use the old MMC fallback when the error
is SK=5h,ASC=24h, and then all of this would work as expected.

Suggested-by:Luca Miccini <lmiccini@redhat.com>

6 years agoautogen: Allow running autogen from a builddir != srcdir
Stef Walter [Tue, 25 Feb 2014 08:45:46 +0000 (09:45 +0100)]
autogen: Allow running autogen from a builddir != srcdir

While the configure correctly supports being run outside of
the top source directory by default, it's nice if autogen.sh
does too:

 $ git clone git://anongit.freedesktop.org/systemd/systemd
 $ cd systemd
 $ mkdir $(uname -m)
 $ cd $(uname -m)
 $ ../autogen.sh a
 $ make

6 years agobuild-sys: Do not distribute generated udev service files
Armin K [Wed, 26 Feb 2014 14:02:55 +0000 (15:02 +0100)]
build-sys: Do not distribute generated udev service files

They are already in nodist_systemunit_DATA and if they are
shipped, they contain hardcoded paths to udevadm and
systemd-udevd which will cause them to fail to start when
rootprefix != prefix and rootlibdir != libdir.

6 years agohwdb: keymaps for Samsung 900X3E/900X3F
Kieran Clancy [Thu, 27 Feb 2014 05:32:57 +0000 (16:02 +1030)]
hwdb: keymaps for Samsung 900X3E/900X3F

Keymaps for Samsung 900X3E and 900X3F should be the same as for other
models in the series.

I have also moved the comment for '# Series 9' to the right place

6 years agojournalctl: refuse extra arguments with --verify and similar
Zbigniew Jędrzejewski-Szmek [Thu, 27 Feb 2014 04:01:43 +0000 (23:01 -0500)]
journalctl: refuse extra arguments with --verify and similar

Positional arguments only make sense with the default action.
For other actions, complain instead of ignoring them silently.

6 years agologs-show: fix corrupt output with empty messages
Uoti Urpala [Thu, 20 Feb 2014 01:00:09 +0000 (03:00 +0200)]
logs-show: fix corrupt output with empty messages

If a message had zero length, journalctl would print no newline, and
two output lines would be concatenated. Fix. The problem was
introduced in commit 31f7bf199452 ("logs-show: print multiline
messages"). Affected short and verbose output modes.

Before fix:

Feb 09 21:16:17 glyph dhclient[1323]: Feb 09 21:16:17 glyph NetworkManager[788]: <info> (enp4s2): DHCPv4 state changed nbi -> preinit

after:

Feb 09 21:16:17 glyph dhclient[1323]:
Feb 09 21:16:17 glyph NetworkManager[788]: <info> (enp4s2): DHCPv4 state changed nbi -> preinit

6 years agobuild-sys: networkd - simplify makefile fragment
Tom Gundersen [Wed, 26 Feb 2014 22:16:34 +0000 (23:16 +0100)]
build-sys: networkd - simplify makefile fragment

6 years agomount: don't fire PropertiesChanged signals for mounts that are stopped
Lennart Poettering [Wed, 26 Feb 2014 03:28:37 +0000 (04:28 +0100)]
mount: don't fire PropertiesChanged signals for mounts that are stopped

6 years agomount: don't send out PropertiesChanged message if actually nothing got changed
Lennart Poettering [Wed, 26 Feb 2014 03:27:50 +0000 (04:27 +0100)]
mount: don't send out PropertiesChanged message if actually nothing got changed

6 years agomount: minor modernization
Lennart Poettering [Wed, 26 Feb 2014 02:46:04 +0000 (03:46 +0100)]
mount: minor modernization

6 years agoUse /var/run/dbus/system_bus_socket for the D-Bus socket
Zbigniew Jędrzejewski-Szmek [Wed, 26 Feb 2014 02:26:31 +0000 (21:26 -0500)]
Use /var/run/dbus/system_bus_socket for the D-Bus socket

6 years agoREADME: document that /var/run must be a symlink → /run
Lennart Poettering [Wed, 26 Feb 2014 01:54:37 +0000 (02:54 +0100)]
README: document that /var/run must be a symlink → /run

6 years agoRevert back to /var/run at a couple of problems
Lennart Poettering [Wed, 26 Feb 2014 01:47:43 +0000 (02:47 +0100)]
Revert back to /var/run at a couple of problems

This partially reverts 41a55c46ab8fb4ef6727434227071321fc762cce

Some specifications we want to stay compatibility actually document
/var/run, not /run, and we should stay compatible with that. In order to
make sure our D-Bus implementation works on any system, regardless if
running systemd or not, we should always use /var/run which is the
only path mandated by the D-Bus spec.

Similar, glibc hardcodes the utmp location to /var/run, and this is
exposed in _UTMP_PATH in limits.h, hence let's stay in sync with this
public API, too.

We simply do not support systems where /var/run is not a symlink → /run.
Hence both are equivalent. Staying compatible with upstream
specifications hence weighs more than cleaning up superficial
appearance.

6 years agoReplace /var/run with /run in remaining places
Zbigniew Jędrzejewski-Szmek [Wed, 26 Feb 2014 01:11:04 +0000 (20:11 -0500)]
Replace /var/run with /run in remaining places

/run was already used almost everywhere, fix the remaining places
for consistency.

6 years agoexec: imply NoNewPriviliges= only when seccomp filters are used in user mode
Lennart Poettering [Wed, 26 Feb 2014 01:28:52 +0000 (02:28 +0100)]
exec: imply NoNewPriviliges= only when seccomp filters are used in user mode

6 years agoupdate TODO
Lennart Poettering [Wed, 26 Feb 2014 01:19:17 +0000 (02:19 +0100)]
update TODO

6 years agobuild-sys: add missing makefile symlinks
Lennart Poettering [Wed, 26 Feb 2014 01:16:46 +0000 (02:16 +0100)]
build-sys: add missing makefile symlinks

6 years agocore: add new RestrictAddressFamilies= switch
Lennart Poettering [Tue, 25 Feb 2014 19:37:03 +0000 (20:37 +0100)]
core: add new RestrictAddressFamilies= switch

This new unit settings allows restricting which address families are
available to processes. This is an effective way to minimize the attack
surface of services, by turning off entire network stacks for them.

This is based on seccomp, and does not work on x86-32, since seccomp
cannot filter socketcall() syscalls on that platform.

6 years agonspawn: no need for duplicate checks against EEXIST
Lennart Poettering [Tue, 25 Feb 2014 19:33:17 +0000 (20:33 +0100)]
nspawn: no need for duplicate checks against EEXIST

6 years agoseccomp: we should control NO_NEW_PRIVS on our own, not let seccomp do this for us
Lennart Poettering [Tue, 25 Feb 2014 19:32:27 +0000 (20:32 +0100)]
seccomp: we should control NO_NEW_PRIVS on our own, not let seccomp do this for us