linux-stable.git/kernel/cgroup/cgroup.c, branch v6.0

cgroup: cgroup_get_from_id() must check the looked-up kn is a directory

2022-09-23T17:18:45+00:00

cgroup has to be one kernfs dir, otherwise kernel panic is caused,
especially cgroup id is provide from userspace.

Reported-by: Marco Patalano 
Fixes: 6b658c4863c1 ("scsi: cgroup: Add cgroup_get_from_id()")
Cc: Muneendra 
Signed-off-by: Ming Lei 
Acked-by: Mukesh Ojha 
Cc: stable@vger.kernel.org # v5.14+
Signed-off-by: Tejun Heo

cgroup: Fix race condition at rebind_subsystems()

2022-08-23T18:11:06+00:00

Root cause:
The rebind_subsystems() is no lock held when move css object from A
list to B list,then let B's head be treated as css node at
list_for_each_entry_rcu().

Solution:
Add grace period before invalidating the removed rstat_css_node.

Reported-by: Jing-Ting Wu 
Suggested-by: Michal Koutný 
Signed-off-by: Jing-Ting Wu 
Tested-by: Jing-Ting Wu 
Link: https://lore.kernel.org/linux-arm-kernel/d8f0bc5e2fb6ed259f9334c83279b4c011283c41.camel@mediatek.com/T/
Acked-by: Mukesh Ojha 
Fixes: a7df69b81aac ("cgroup: rstat: support cgroup1")
Cc: stable@vger.kernel.org # v5.13+
Signed-off-by: Tejun Heo

cgroup: Fix threadgroup_rwsem <-> cpus_read_lock() deadlock

2022-08-17T17:36:05+00:00

Bringing up a CPU may involve creating and destroying tasks which requires
read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside
cpus_read_lock(). However, cpuset's ->attach(), which may be called with
thredagroup_rwsem write-locked, also wants to disable CPU hotplug and
acquires cpus_read_lock(), leading to a deadlock.

Fix it by guaranteeing that ->attach() is always called with CPU hotplug
disabled and removing cpus_read_lock() call from cpuset_attach().

Signed-off-by: Tejun Heo 
Reviewed-and-tested-by: Imran Khan 
Reported-and-tested-by: Xuewen Yan 
Fixes: 05c7b7a92cc8 ("cgroup/cpuset: Fix a race between cpuset_attach() and cpu hotplug")
Cc: stable@vger.kernel.org # v5.17+

sched/psi: Remove unused parameter nbytes of psi_trigger_create()

2022-08-15T22:35:25+00:00

psi_trigger_create()'s 'nbytes' parameter is not used, so we can remove it.

Signed-off-by: Hao Jia 
Reviewed-by: Ingo Molnar 
Acked-by: Johannes Weiner 
Signed-off-by: Tejun Heo

Merge tag 'cgroup-for-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

2022-08-03T16:45:08+00:00

Pull cgroup updates from Tejun Heo:
 "Several core optimizations:

   - threadgroup_rwsem write locking is skipped when configuring
     controllers in empty subtrees.

     Combined with CLONE_INTO_CGROUP, this allows the common static
     usage pattern to not grab threadgroup_rwsem at all (glibc still
     doesn't seem ready for CLONE_INTO_CGROUP unfortunately).

   - threadgroup_rwsem used to be put into non-percpu mode by default
     due to latency concerns in specific use cases. There's no reason
     for everyone else to pay for it. Make the behavior optional.

   - psi no longer allocates memory when disabled.

  ... along with some code cleanups"

* tag 'cgroup-for-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: Skip subtree root in cgroup_update_dfl_csses()
  cgroup: remove "no" prefixed mount options
  cgroup: Make !percpu threadgroup_rwsem operations optional
  cgroup: Add "no" prefixed mount options
  cgroup: Elide write-locking threadgroup_rwsem when updating csses on an empty subtree
  cgroup.c: remove redundant check for mixable cgroup in cgroup_migrate_vet_dst
  cgroup.c: add helper __cset_cgroup_from_root to cleanup duplicated codes
  psi: dont alloc memory for psi by default

cgroup: Skip subtree root in cgroup_update_dfl_csses()

2022-07-28T17:26:30+00:00

The cgroup_update_dfl_csses() function updates css associations when a
cgroup's subtree_control file is modified. Any changes made to a cgroup's
subtree_control file, however, will only affect its descendants but not
the cgroup itself. So there is no point in migrating csses associated
with that cgroup. We can skip them instead.

Signed-off-by: Waiman Long 
Reviewed-by: Michal Koutný 
Signed-off-by: Tejun Heo

cgroup: remove "no" prefixed mount options

2022-07-27T17:54:55+00:00

30312730bd02 ("cgroup: Add "no" prefixed mount options") added "no" prefixed
mount options to allow turning them off and 6a010a49b63a ("cgroup: Make
!percpu threadgroup_rwsem operations optional") added one more "no" prefixed
mount option. However, Michal pointed out that the "no" prefixed options
aren't necessary in allowing mount options to be turned off:

  # grep group /proc/mounts
  cgroup2 /sys/fs/cgroup cgroup2 rw,nosuid,nodev,relatime,nsdelegate,memory_recursiveprot 0 0
  # mount -o remount,nsdelegate,memory_recursiveprot none /sys/fs/cgroup
  # grep cgroup /proc/mounts
  cgroup2 /sys/fs/cgroup cgroup2 rw,relatime,nsdelegate,memory_recursiveprot 0 0

Note that this is different from the remount behavior when the mount(1) is
invoked without the device argument - "none":

 # grep cgroup /proc/mounts
 cgroup2 /sys/fs/cgroup cgroup2 rw,nosuid,nodev,noexec,relatime,nsdelegate,memory_recursiveprot 0 0
 # mount -o remount,nsdelegate,memory_recursiveprot /sys/fs/cgroup
 # grep cgroup /proc/mounts
 cgroup2 /sys/fs/cgroup cgroup2 rw,nosuid,nodev,noexec,relatime,nsdelegate,memory_recursiveprot 0 0

While a bit confusing, given that there is a way to turn off the options,
there's no reason to have the explicit "no" prefixed options. Let's remove
them.

Signed-off-by: Tejun Heo 
Cc: Michal Koutný 
Signed-off-by: Tejun Heo

cgroup: Make !percpu threadgroup_rwsem operations optional

2022-07-23T14:29:02+00:00

3942a9bd7b58 ("locking, rcu, cgroup: Avoid synchronize_sched() in
__cgroup_procs_write()") disabled percpu operations on threadgroup_rwsem
because the impiled synchronize_rcu() on write locking was pushing up the
latencies too much for android which constantly moves processes between
cgroups.

This makes the hotter paths - fork and exit - slower as they're always
forced into the slow path. There is no reason to force this on everyone
especially given that more common static usage pattern can now completely
avoid write-locking the rwsem. Write-locking is elided when turning on and
off controllers on empty sub-trees and CLONE_INTO_CGROUP enables seeding a
cgroup without grabbing the rwsem.

Restore the default percpu operations and introduce the mount option
"favordynmods" and config option CGROUP_FAVOR_DYNMODS for users who need
lower latencies for the dynamic operations.

Signed-off-by: Tejun Heo 
Cc: Christian Brauner 
Cc: Michal Koutnï¿½ 
Cc: Peter Zijlstra 
Cc: John Stultz 
Cc: Dmitry Shmidt 
Cc: Oleg Nesterov

cgroup: Add "no" prefixed mount options

2022-07-23T05:12:52+00:00

We allow modifying these mount options via remount. Let's add "no" prefixed
variants so that they can be turned off too.

Signed-off-by: Tejun Heo 
Cc: Christian Brauner 
Cc: Michal Koutný

cgroup: Elide write-locking threadgroup_rwsem when updating csses on an empty subtree

2022-07-23T05:12:37+00:00

cgroup_update_dfl_csses() write-lock the threadgroup_rwsem as updating the
csses can trigger process migrations. However, if the subtree doesn't
contain any tasks, there aren't gonna be any cgroup migrations. This
condition can be trivially detected by testing whether
mgctx.preloaded_src_csets is empty. Elide write-locking threadgroup_rwsem if
the subtree is empty.

After this optimization, the usage pattern of creating a cgroup, enabling
the necessary controllers, and then seeding it with CLONE_INTO_CGROUP and
then removing the cgroup after it becomes empty doesn't need to write-lock
threadgroup_rwsem at all.

Signed-off-by: Tejun Heo 
Cc: Christian Brauner 
Cc: Michal Koutný