]> git.ipfire.org Git - thirdparty/systemd.git/log
thirdparty/systemd.git
5 years agoRe-add uaccess tag for /dev/dri/renderD*
Michael Biebl [Wed, 13 Mar 2019 22:22:26 +0000 (23:22 +0100)] 
Re-add uaccess tag for /dev/dri/renderD*

Setting an access mode != 0666 is explicitly supported via -Dgroup-render-mode
In such a case, re-add the uaccess tag.

This is basically the same change that was done for /dev/kvm in
commit fa53e24130af3a389573acb9585eadbf7192955f and
ace5e3111c0b8d8bfd84b32f2c689b0a4d92c061
and partially reverts the changes from
4e15a7343cb389e97f3eb4f49699161862d8b8b2

5 years agoman: provide an example how to plug systemd-mount into udev
Lennart Poettering [Thu, 14 Mar 2019 09:12:36 +0000 (10:12 +0100)] 
man: provide an example how to plug systemd-mount into udev

Prompted by: #11982

5 years agoMerge pull request #11971 from keszybz/kernel-install-directory
Lennart Poettering [Thu, 14 Mar 2019 09:51:55 +0000 (10:51 +0100)] 
Merge pull request #11971 from keszybz/kernel-install-directory

Make kernel-install create entry directory

5 years agoMerge pull request #11968 from yuwata/network-l2tp
Lennart Poettering [Thu, 14 Mar 2019 09:36:21 +0000 (10:36 +0100)] 
Merge pull request #11968 from yuwata/network-l2tp

network: introduce L2TP tunnel

5 years agohwdb: Fix airplane mode triggering when resuming HP Spectre x360 13
Benjamin Berg [Fri, 8 Mar 2019 16:42:23 +0000 (17:42 +0100)] 
hwdb: Fix airplane mode triggering when resuming HP Spectre x360 13

On these devices the key randomly fires during/after suspend/resume
triggering spurious airplane mode changes. The scancode simply needs to
be ignored.

5 years agoman: mention that DynamicUser= should not be mixed with ReadWriteDirectory= or AF_UNI...
Lennart Poettering [Tue, 12 Mar 2019 14:57:25 +0000 (15:57 +0100)] 
man: mention that DynamicUser= should not be mixed with ReadWriteDirectory= or AF_UNIX dir fd passing

5 years agobootctl: use path_join() to join paths 11971/head
Zbigniew Jędrzejewski-Szmek [Tue, 12 Mar 2019 08:30:45 +0000 (09:30 +0100)] 
bootctl: use path_join() to join paths

We would say "/boot/efi//loader/entries"...

5 years agoman: be even more explicit that RestartPreventExitStatus= does not affect ExecStartPre=
Lennart Poettering [Wed, 13 Mar 2019 19:28:28 +0000 (20:28 +0100)] 
man: be even more explicit that RestartPreventExitStatus= does not affect ExecStartPre=

The man page was already pretty clear about this, but apparently not
clear enough, let's hence extend this further.

Fixes: #11868
5 years agotest-network: add tests for L2TP 11968/head
Yu Watanabe [Tue, 12 Mar 2019 08:11:24 +0000 (17:11 +0900)] 
test-network: add tests for L2TP

5 years agonetwork: wait for L2TP tunnel to be created before creating sessions
Yu Watanabe [Wed, 13 Mar 2019 07:46:30 +0000 (16:46 +0900)] 
network: wait for L2TP tunnel to be created before creating sessions

And if failed to create L2TP tunnel, then do not try to create sessions.

5 years agonetlink: support NLMSG_ERROR message in genl
Yu Watanabe [Wed, 13 Mar 2019 07:45:06 +0000 (16:45 +0900)] 
netlink: support NLMSG_ERROR message in genl

This resolves the following log message after L2TP tunnel or session is
created:
```
sd-netlink: ignored message with unknown type: 2
```

5 years agonetwork: automatically pick an address on link when L2TP.Local= is not specified
Yu Watanabe [Tue, 12 Mar 2019 02:35:23 +0000 (11:35 +0900)] 
network: automatically pick an address on link when L2TP.Local= is not specified

This makes L2TP.Local= support an empty string, 'auto', 'static', and
'dynamic'. When one of the values are specified, a local address is
automatically picked from the local interface of the tunnel.

5 years agonetworkd: Introduce l2tp tunnel
Susant Sahani [Wed, 6 Mar 2019 19:51:29 +0000 (01:21 +0530)] 
networkd: Introduce l2tp tunnel

This works allows networkd to configure l2tp tunnel.
See http://man7.org/linux/man-pages/man8/ip-l2tp.8.html

5 years agonetwork: introduce new netdev create type NETDEV_CREATE_AFTER_CONFIGURED
Yu Watanabe [Mon, 11 Mar 2019 07:11:47 +0000 (16:11 +0900)] 
network: introduce new netdev create type NETDEV_CREATE_AFTER_CONFIGURED

It will be used to support L2TP tunnel in later commits.

5 years agonetwork: introduce netdev_get_create_type() helper function
Yu Watanabe [Mon, 11 Mar 2019 06:49:09 +0000 (15:49 +0900)] 
network: introduce netdev_get_create_type() helper function

5 years agonetwork: do not call link_joined() when not all netdevs are configured
Yu Watanabe [Mon, 11 Mar 2019 06:35:35 +0000 (15:35 +0900)] 
network: do not call link_joined() when not all netdevs are configured

If some of stacked netdevs are already configured, then link_joined()
is called before netdevs are fully configured.

5 years agovirt: detect WSL environment as a container (id: wsl)
Balint Reczey [Wed, 6 Mar 2019 17:46:04 +0000 (18:46 +0100)] 
virt: detect WSL environment as a container (id: wsl)

5 years agotests: add tests for embedded newlines in /proc/cmdline
Lennart Poettering [Tue, 12 Mar 2019 19:41:14 +0000 (20:41 +0100)] 
tests: add tests for embedded newlines in /proc/cmdline

Prompted by: #7097

5 years agobootspec: don't log in boot_entries_load_config_auto() about no ESP
Lennart Poettering [Tue, 12 Mar 2019 19:13:29 +0000 (20:13 +0100)] 
bootspec: don't log in boot_entries_load_config_auto() about no ESP

Let's do it in the caller instead. That way, logind can stay silent
about it.

Fixes: #11950
5 years agotest: avoid double-fsck'ing of the rootfs on Arch
Frantisek Sumsal [Wed, 13 Mar 2019 09:07:44 +0000 (10:07 +0100)] 
test: avoid double-fsck'ing of the rootfs on Arch

Since systemd 206 the combination of systemd and mkinitcpio
causes, under certain conditions, the rootfs to be double fsck'd.

Symptoms:
```
:: performing fsck on '/dev/sda1'
systemd: clean, 3523/125488 files, 141738/501760 blocks
********************** WARNING **********************
*                                                   *
*  The root device is not configured to be mounted  *
*  read-write! It may be fsck'd again later.        *
*                                                   *
*****************************************************
<snip>
[  OK  ] Started File System Check on Root Device
```

This occurs when neither 'ro' or 'rw', or only 'ro' is present
on the kernel command line. The solution is to mount the roofs
as read-write on the kernel command line, so systemd knows to not fsck
it again.

5 years agoman: clarify that sd_journal_seek_head() seeks *before* the first entry
Lennart Poettering [Wed, 13 Mar 2019 11:29:25 +0000 (12:29 +0100)] 
man: clarify that sd_journal_seek_head() seeks *before* the first entry

5 years agoMerge pull request #11986 from poettering/util-split
Zbigniew Jędrzejewski-Szmek [Wed, 13 Mar 2019 16:02:14 +0000 (17:02 +0100)] 
Merge pull request #11986 from poettering/util-split

some splitting up of util.[ch]

5 years agonetworkd: Add bridge port capabilities
Tobias Jungel [Sun, 10 Mar 2019 20:25:24 +0000 (21:25 +0100)] 
networkd: Add bridge port capabilities

This PR adds the configuration switches for multicast flooding, neighbor
suppression and learning of a bridge port.

5 years agologin: mark nomodeset fb devices as master-of-seat
Adam Jackson [Tue, 12 Mar 2019 19:22:13 +0000 (20:22 +0100)] 
login: mark nomodeset fb devices as master-of-seat

When 'nomodeset' is specified, there's no DRM driver to take over from
efifb. This means no device will be marked as a seat master, so gdm will
never find a sufficiently active seat to start on.

I'm not aware of an especially good way to detect this through a proper
kernel API, so check for the word 'nomodeset' on the command line and
allow fbdev devices to be seat masters if found.

For https://bugzilla.redhat.com/show_bug.cgi?id=1683197.

5 years agoutil: split out sorting related calls to new sort-util.[ch] 11986/head
Lennart Poettering [Wed, 13 Mar 2019 11:14:47 +0000 (12:14 +0100)] 
util: split out sorting related calls to new sort-util.[ch]

5 years agoutil: split out memcmp()/memset() related calls into memory-util.[ch]
Lennart Poettering [Wed, 13 Mar 2019 11:02:21 +0000 (12:02 +0100)] 
util: split out memcmp()/memset() related calls into memory-util.[ch]

Just some source rearranging.

5 years agoutil: split out some stuff into a new file limits-util.[ch]
Lennart Poettering [Wed, 13 Mar 2019 10:35:47 +0000 (11:35 +0100)] 
util: split out some stuff into a new file limits-util.[ch]

5 years agoutil: split out namespace related stuff into a new namespace-util.[ch] pair
Lennart Poettering [Wed, 13 Mar 2019 10:21:49 +0000 (11:21 +0100)] 
util: split out namespace related stuff into a new namespace-util.[ch] pair

Just some minor reorganiztion.

5 years agotest: don't overwrite TESTDIR if already set
Frantisek Sumsal [Tue, 12 Mar 2019 21:44:25 +0000 (22:44 +0100)] 
test: don't overwrite TESTDIR if already set

5 years agoMerge pull request #11861 from yuwata/network-verify-2
Lennart Poettering [Wed, 13 Mar 2019 09:15:27 +0000 (10:15 +0100)] 
Merge pull request #11861 from yuwata/network-verify-2

network: config parser updates and wireguard refactoring

5 years agoMerge pull request #11893 from yuwata/wait-online-take-operstate
Lennart Poettering [Wed, 13 Mar 2019 09:10:43 +0000 (10:10 +0100)] 
Merge pull request #11893 from yuwata/wait-online-take-operstate

wait-online: optionally take required minimum operational state

5 years agoMerge pull request #11283 from yuwata/fix-11276
Lennart Poettering [Wed, 13 Mar 2019 08:57:18 +0000 (09:57 +0100)] 
Merge pull request #11283 from yuwata/fix-11276

core/namespace: introduce new mount mode READWRITE_IMPLICIT

5 years agocryptsetup: add same-cpu-crypt and submit-from-crypt-cpus options
Yu Watanabe [Mon, 11 Mar 2019 05:04:06 +0000 (14:04 +0900)] 
cryptsetup: add same-cpu-crypt and submit-from-crypt-cpus options

Closes #11946.

5 years agoMerge pull request #11933 from keszybz/coverity
Lennart Poettering [Wed, 13 Mar 2019 08:36:57 +0000 (09:36 +0100)] 
Merge pull request #11933 from keszybz/coverity

Minor tweaks to boot/efi code inspired by coverity

5 years agowait-online: use log_link_debug() or friends 11893/head
Yu Watanabe [Wed, 6 Mar 2019 15:16:54 +0000 (00:16 +0900)] 
wait-online: use log_link_debug() or friends

5 years agonetwork: move log_link_debug() or friends to log-link.h
Yu Watanabe [Wed, 6 Mar 2019 14:54:57 +0000 (23:54 +0900)] 
network: move log_link_debug() or friends to log-link.h

5 years agoman: update wait-online and RequiredForOnline= setting
Yu Watanabe [Wed, 6 Mar 2019 14:47:29 +0000 (23:47 +0900)] 
man: update wait-online and RequiredForOnline= setting

5 years agowait-online: support $REQUIRED_OPER_STATE_FOR_ONLINE= in state file
Yu Watanabe [Wed, 6 Mar 2019 14:46:33 +0000 (23:46 +0900)] 
wait-online: support $REQUIRED_OPER_STATE_FOR_ONLINE= in state file

This also make wait-online optionally take operstate in -i option,
and adds '--operstate' option to wait-online which also takes operstate.

Also, this contains huge refactoring for wait-online.

5 years agosd-network: add sd_network_link_get_required_operstate_for_online()
Yu Watanabe [Wed, 6 Mar 2019 05:45:17 +0000 (14:45 +0900)] 
sd-network: add sd_network_link_get_required_operstate_for_online()

It reads $REQUIRED_OPER_STATE_FOR_ONLINE in serialized link data.

5 years agonetwork: make RequiredForOnline= also take operational state
Yu Watanabe [Wed, 6 Mar 2019 05:29:49 +0000 (14:29 +0900)] 
network: make RequiredForOnline= also take operational state

This will be used by systemd-networkd-wait-online.

5 years agohashmap: add hashmap_free_free_keyp and friend
Yu Watanabe [Tue, 5 Mar 2019 06:15:40 +0000 (15:15 +0900)] 
hashmap: add hashmap_free_free_keyp and friend

5 years agonetwork: introduce 'degraded-carrier' operstate to order all states
Yu Watanabe [Tue, 5 Mar 2019 05:41:56 +0000 (14:41 +0900)] 
network: introduce 'degraded-carrier' operstate to order all states

Previously, 'degraded' state is ambiguous for bonding or bridge master:
1. one or more slave interfaces does not have carrier,
2. no link local address is assigned to the master,
3. combination of the above two.

This makes the above case 1 and 3 are in the new 'degraded-carrier'
state, and makes 'degraded' state as all slaves are active but no
link local address on master.

5 years agonetwork: move LinkOperationalState and relevant functions to network-util.[ch]
Yu Watanabe [Tue, 5 Mar 2019 05:39:57 +0000 (14:39 +0900)] 
network: move LinkOperationalState and relevant functions to network-util.[ch]

5 years agotest-network: wait more and fix wrong operational state
Yu Watanabe [Wed, 13 Mar 2019 05:26:38 +0000 (14:26 +0900)] 
test-network: wait more and fix wrong operational state

Closes #11977.

5 years agotest-network: add test for WireGuard.PrivateKeyFile= 11861/head
Yu Watanabe [Mon, 4 Mar 2019 05:42:03 +0000 (14:42 +0900)] 
test-network: add test for WireGuard.PrivateKeyFile=

5 years agowireguard: add PrivateKeyFile= option
Yu Watanabe [Mon, 4 Mar 2019 05:19:21 +0000 (14:19 +0900)] 
wireguard: add PrivateKeyFile= option

Closes #11878.

5 years agowireguard: check whether PrivateKey= and PublicKey= are set
Yu Watanabe [Mon, 4 Mar 2019 05:31:36 +0000 (14:31 +0900)] 
wireguard: check whether PrivateKey= and PublicKey= are set

5 years agowireguard: drop unused arguments and rename parse_wireguard_key()
Yu Watanabe [Tue, 5 Mar 2019 03:35:43 +0000 (12:35 +0900)] 
wireguard: drop unused arguments and rename parse_wireguard_key()

5 years agowireguard: do not log wireguard key
Yu Watanabe [Mon, 4 Mar 2019 05:12:03 +0000 (14:12 +0900)] 
wireguard: do not log wireguard key

It may be PrivateKey=.

5 years agowireguard: reuse sd_event_source object
Yu Watanabe [Fri, 1 Mar 2019 06:41:47 +0000 (15:41 +0900)] 
wireguard: reuse sd_event_source object

5 years agowireguard: use NetworkConfigSection to manage [WireGuardPeer] sections
Yu Watanabe [Thu, 28 Feb 2019 08:12:02 +0000 (17:12 +0900)] 
wireguard: use NetworkConfigSection to manage [WireGuardPeer] sections

This also contains huge refactoring of wireguard support.

5 years agotest-network: add tests for invalid Address sections
Yu Watanabe [Fri, 1 Mar 2019 06:21:22 +0000 (15:21 +0900)] 
test-network: add tests for invalid Address sections

5 years agotest: make network_verify() public and use it in test-networkd-conf
Yu Watanabe [Fri, 1 Mar 2019 08:39:45 +0000 (17:39 +0900)] 
test: make network_verify() public and use it in test-networkd-conf

5 years agonetwork: drop sections contain invalid settings in network_verify()
Yu Watanabe [Fri, 1 Mar 2019 04:27:47 +0000 (13:27 +0900)] 
network: drop sections contain invalid settings in network_verify()

If e.g., an [Address] section has an invalid setting, then
previously assigned settings in the section is freed, and
only later settings are stored. That may cause partially broken
section stored in Network object.

This makes if an invalid setting is found, then set 'invalid' flag
instead of freeing it. And invalid sections are dropped later by
network_verify().

5 years agonetwork: make all xxx_new_static() static
Yu Watanabe [Fri, 1 Mar 2019 04:19:53 +0000 (13:19 +0900)] 
network: make all xxx_new_static() static

These functions are called from only config parsers, and the parsers are
in the same files. So, let's make them static.

5 years agonetwork: add IPv4LL route right after .network file is parsed
Yu Watanabe [Tue, 5 Mar 2019 01:51:57 +0000 (10:51 +0900)] 
network: add IPv4LL route right after .network file is parsed

Previously, the route is added when the .network config is assigned
to a Link. So, if multiple links match the .network file, the route
entry becomes duplicated in the corresponding Network object.

5 years agonetwork: move NetworkConfigSection and related functions to networkd-util.[ch]
Yu Watanabe [Thu, 28 Feb 2019 07:30:14 +0000 (16:30 +0900)] 
network: move NetworkConfigSection and related functions to networkd-util.[ch]

5 years agonetwork: use ltype to determine netdev kind in config_parse_stacked_netdev()
Yu Watanabe [Thu, 28 Feb 2019 07:18:57 +0000 (16:18 +0900)] 
network: use ltype to determine netdev kind in config_parse_stacked_netdev()

5 years agotest: add a testcase for ProtectHome=tmpfs vs ProtectSystem=strict 11283/head
Yu Watanabe [Fri, 28 Dec 2018 07:30:21 +0000 (16:30 +0900)] 
test: add a testcase for ProtectHome=tmpfs vs ProtectSystem=strict

5 years agocore/namespace: logs mount mode when the entry is dropped
Yu Watanabe [Sat, 29 Dec 2018 10:59:15 +0000 (19:59 +0900)] 
core/namespace: logs mount mode when the entry is dropped

5 years agocore/namespace: introduce new mount mode READWRITE_IMPLICIT
Yu Watanabe [Fri, 28 Dec 2018 07:11:52 +0000 (16:11 +0900)] 
core/namespace: introduce new mount mode READWRITE_IMPLICIT

ProtectSystem=strict or ProtectKernelTunable=yes create implicit
read-write mounts, but they are not overridable by TemporaryFileSystem=.
This makes such implicit read-write mounts use the new mount mode.
So, they can be override by TemproraryFileSystem= now.
A typical usecase is that ProtectSystem=strict and ProtectHome=tmpfs.

Fixes #11276.

5 years agoMerge pull request #11919 from poettering/login-simplify
Lennart Poettering [Tue, 12 Mar 2019 17:33:14 +0000 (18:33 +0100)] 
Merge pull request #11919 from poettering/login-simplify

various fixes to $HOME and $SHELL validation

5 years agoupdate TODO 11919/head
Lennart Poettering [Tue, 12 Mar 2019 14:53:05 +0000 (15:53 +0100)] 
update TODO

5 years agologin: drop redundant newline
Lennart Poettering [Mon, 11 Mar 2019 17:28:06 +0000 (18:28 +0100)] 
login: drop redundant newline

5 years agouser-util: extra paranoia, make sure $SHELL can't be fucked with in suid programs
Lennart Poettering [Tue, 12 Mar 2019 14:52:06 +0000 (15:52 +0100)] 
user-util: extra paranoia, make sure $SHELL can't be fucked with in suid programs

It's better to be safe than sorry, let's not allow overriding of the
user shell in suid binaries. Similar for $USER.

5 years agoexecute: no need to synthesize $HOME for uid==0 again, get_home_dir() already does...
Lennart Poettering [Thu, 7 Mar 2019 10:00:40 +0000 (11:00 +0100)] 
execute: no need to synthesize $HOME for uid==0 again, get_home_dir() already does that

5 years agoexecute: simplify paths we set as HOME/SHELL for invoked programs
Lennart Poettering [Thu, 7 Mar 2019 10:00:13 +0000 (11:00 +0100)] 
execute: simplify paths we set as HOME/SHELL for invoked programs

5 years agouser-util: simplify paths retrieved from $HOME and $SHELL
Lennart Poettering [Thu, 7 Mar 2019 09:54:11 +0000 (10:54 +0100)] 
user-util: simplify paths retrieved from $HOME and $SHELL

Let's add some extra paranoia, after #11910

5 years agouser-util: be more strict when reading $HOME and $SHELL
Lennart Poettering [Thu, 7 Mar 2019 09:53:23 +0000 (10:53 +0100)] 
user-util: be more strict when reading $HOME and $SHELL

5 years agouser-util: paranoia — add overflow check on ERANGE loop
Lennart Poettering [Thu, 7 Mar 2019 09:52:35 +0000 (10:52 +0100)] 
user-util: paranoia — add overflow check on ERANGE loop

5 years agouser-util: use SYNTHETIC_ERRNO() where we can
Lennart Poettering [Thu, 7 Mar 2019 09:45:14 +0000 (10:45 +0100)] 
user-util: use SYNTHETIC_ERRNO() where we can

5 years agopath-util: minimize variable scope
Lennart Poettering [Thu, 7 Mar 2019 09:44:59 +0000 (10:44 +0100)] 
path-util: minimize variable scope

5 years agopath-util: check validity before normalization in path_simplify_and_warn()
Lennart Poettering [Thu, 7 Mar 2019 09:37:04 +0000 (10:37 +0100)] 
path-util: check validity before normalization in path_simplify_and_warn()

As the normalization check includes a validation check the order
matters.

5 years agouser-util: filter out invalid user record data a bit more thorougly
Lennart Poettering [Thu, 7 Mar 2019 09:32:48 +0000 (10:32 +0100)] 
user-util: filter out invalid user record data a bit more thorougly

5 years agologind: normalize home path when creating user object
Lennart Poettering [Thu, 7 Mar 2019 09:31:26 +0000 (10:31 +0100)] 
logind: normalize home path when creating user object

Triggered by: #11910

5 years agoMerge pull request #11964 from mrc0mmand/even-more-fuzzers
Zbigniew Jędrzejewski-Szmek [Tue, 12 Mar 2019 14:08:20 +0000 (15:08 +0100)] 
Merge pull request #11964 from mrc0mmand/even-more-fuzzers

fuzz: add fuzzers for calendar & time expressions

5 years agomeson: scope more git invocations with current_source_dir()
Davide Cavalca [Wed, 27 Feb 2019 16:19:07 +0000 (11:19 -0500)] 
meson: scope more git invocations with current_source_dir()

5 years agoMerge pull request #11927 from poettering/network-namespace-path
Zbigniew Jędrzejewski-Szmek [Tue, 12 Mar 2019 13:29:14 +0000 (14:29 +0100)] 
Merge pull request #11927 from poettering/network-namespace-path

Add NetworkNamespacePath= to unit files

5 years agopo: update French translation
Sylvain Plantefève [Thu, 7 Mar 2019 22:10:46 +0000 (23:10 +0100)] 
po: update French translation

5 years agoshared/bootspec: avoid going through -1 when calculating array index 11933/head
Zbigniew Jędrzejewski-Szmek [Fri, 8 Mar 2019 13:37:26 +0000 (14:37 +0100)] 
shared/bootspec: avoid going through -1 when calculating array index

Coverity was complaining in CID#1399407 that config->entries might be used
while NULL. Let's add an assert to make sure it's not.

Also, let's quit early if we have no entries to loop through. The code was
not incorrect, but it's cleaner to avoid any negative indices.

5 years agoboot: avoid 32-bit calculation for a 64-bit lvalue
Zbigniew Jędrzejewski-Szmek [Fri, 8 Mar 2019 13:16:40 +0000 (14:16 +0100)] 
boot: avoid 32-bit calculation for a 64-bit lvalue

Coverity CID#1399116:
> Potentially overflowing expression
> gpt_header_buffer.gpt_header.SizeOfPartitionEntry * gpt_header_buffer.gpt_header.NumberOfPartitionEntries
> with type unsigned int (32 bits, unsigned) is evaluated using 32-bit
> arithmetic, and then used in a context that expects an expression of type
> UINTN (64 bits, unsigned).

Let's import the ALIGN_TO macro to sd-boot and use it to avoid the issue.

5 years agoMerge pull request #11943 from yuwata/device-action-seqnum-cleanups
Zbigniew Jędrzejewski-Szmek [Tue, 12 Mar 2019 12:17:33 +0000 (13:17 +0100)] 
Merge pull request #11943 from yuwata/device-action-seqnum-cleanups

sd-device: store parsed SEQNUM and ACTION string

5 years agofuzz: add a fuzzer for time utils 11964/head
Frantisek Sumsal [Mon, 11 Mar 2019 18:57:09 +0000 (19:57 +0100)] 
fuzz: add a fuzzer for time utils

5 years agofuzz: add a fuzzer for calendarspec
Frantisek Sumsal [Mon, 11 Mar 2019 18:56:34 +0000 (19:56 +0100)] 
fuzz: add a fuzzer for calendarspec

5 years agobash-completion: also suggest units in reloading or activating
Yu Watanabe [Mon, 11 Mar 2019 04:26:29 +0000 (13:26 +0900)] 
bash-completion: also suggest units in reloading or activating

Closes #11942.

5 years agoMerge pull request #11897 from mrc0mmand/parallelize-TEST-24-UNIT-TESTS
Zbigniew Jędrzejewski-Szmek [Tue, 12 Mar 2019 10:21:06 +0000 (11:21 +0100)] 
Merge pull request #11897 from mrc0mmand/parallelize-TEST-24-UNIT-TESTS

test: parallelize tasks in TEST-24-UNIT-TESTS

5 years agolgtm: replace the query used for looking for fgets with a more general query
Evgeny Vereshchagin [Mon, 11 Mar 2019 20:05:13 +0000 (21:05 +0100)] 
lgtm: replace the query used for looking for fgets with a more general query

to make it easier to comlain about `strtok` :-)

Inspired by https://github.com/systemd/systemd/pull/11963, which, in turn,
was prompted by https://github.com/systemd/systemd/pull/11555.

5 years agoman: say $BOOT not /boot in kernel-install(8)
Zbigniew Jędrzejewski-Szmek [Fri, 8 Mar 2019 18:21:54 +0000 (19:21 +0100)] 
man: say $BOOT not /boot in kernel-install(8)

5 years agokernel-install: create the entry directory only if $BOOT/$MACHINE_ID exists
Zbigniew Jędrzejewski-Szmek [Thu, 7 Mar 2019 20:18:56 +0000 (21:18 +0100)] 
kernel-install: create the entry directory only if $BOOT/$MACHINE_ID exists

Things are currently fairly ugly in Fedora: we create $BOOT/$MACHINE_ID/$KERNEL_VERSION/,
and then 20-grub.install that is installed by grub2-common.rpm wants to remove that
directory before 50-dracut.install get a chance to run. 50-dracut.install
checks for the presence of that directory to decide where to install the
kernel. So let's make the creation of the directory conditional. Previous
commit changes bootctl install to create $BOOT/$MACHINE_ID, and this commit
makes kernel-install not create it. In effect, the entry directory will only be
created if 'bootctl install' or something else created the parent directory.

https://bugzilla.redhat.com/show_bug.cgi?id=1648907

5 years agobootctl: create $BOOT/<machine-id> when installing sd-boot
Zbigniew Jędrzejewski-Szmek [Fri, 8 Mar 2019 15:33:57 +0000 (16:33 +0100)] 
bootctl: create $BOOT/<machine-id> when installing sd-boot

5 years agokernel-install: rename $BOOT_DIR[_ABS] to $ENTRY_DIR[_ABS]
Zbigniew Jędrzejewski-Szmek [Fri, 8 Mar 2019 14:37:35 +0000 (15:37 +0100)] 
kernel-install: rename $BOOT_DIR[_ABS] to $ENTRY_DIR[_ABS]

"BOOT" is misleading, because it sounds like this refers to /boot or $BOOT,
when in fact it refers to some subdirectory. Those variable names are purely
interal, so we can change them. $BOOT_DIR_ABS was used in NEWS, but it should
not be (because it is an internal detail), so the old NEWS entry is reworded to
use "entry directory".

5 years agoudev: fix memleak in 'udevadm trigger --settle'
Yu Watanabe [Tue, 12 Mar 2019 03:20:13 +0000 (12:20 +0900)] 
udev: fix memleak in 'udevadm trigger --settle'

Fixes #11966.

5 years agotest: wait for a while active state of .device is updated 11943/head
Yu Watanabe [Mon, 11 Mar 2019 18:53:22 +0000 (03:53 +0900)] 
test: wait for a while active state of .device is updated

5 years agoefivars: make sure efi_loader_entry_name_valid() is always compiled in
Lennart Poettering [Mon, 11 Mar 2019 14:58:52 +0000 (15:58 +0100)] 
efivars: make sure efi_loader_entry_name_valid() is always compiled in

The string validation should always be done correctly, and not fail just
because EFI is turned off. After all an EFI loader entry name string
remains properly formatted regardless if EFI is on or off...

Fixes: #11948
5 years agolibudev: use device_get_seqnum() and device_get_action()
Yu Watanabe [Sat, 9 Mar 2019 02:07:26 +0000 (11:07 +0900)] 
libudev: use device_get_seqnum() and device_get_action()

5 years agologin: use device_is_in_action()
Yu Watanabe [Sat, 9 Mar 2019 01:45:48 +0000 (10:45 +0900)] 
login: use device_is_in_action()

5 years agonetwork: use device_get_action()
Yu Watanabe [Sat, 9 Mar 2019 01:37:12 +0000 (10:37 +0900)] 
network: use device_get_action()

5 years agocore/device: use device_get_action()
Yu Watanabe [Sat, 9 Mar 2019 01:28:11 +0000 (10:28 +0900)] 
core/device: use device_get_action()

5 years agoudevadm-test: check action string earlier
Yu Watanabe [Sat, 9 Mar 2019 01:20:42 +0000 (10:20 +0900)] 
udevadm-test: check action string earlier

The string will be checked later in device_new_from_synthetic_event(),
but let's check it earlier in parse_argv().

5 years agoudevadm: use device_get_action()
Yu Watanabe [Sat, 9 Mar 2019 01:14:38 +0000 (10:14 +0900)] 
udevadm: use device_get_action()