A previous patch fixed a bug where new_prs should be assigned before
checking housekeeping conflicts. This patch addresses another potential
issue: the nocpu error check currently uses the xcpus which is not updated.
Although no issue has been observed so far, the check should be performed
using the new effective exclusive cpus.
The comment has been removed because the function returns an error if
nocpu checking fails, which is unrelated to the parent.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The 'isolcpus' parameter specified at boot time can be assigned to an
isolated partition. While it is valid put the 'isolcpus' in an isolated
partition, attempting to change a member cpuset to an isolated partition
will fail if the cpuset contains any 'isolcpus'.
For example, the system boots with 'isolcpus=9', and the following
configuration works correctly:
# cd /sys/fs/cgroup/
# mkdir test
# echo 1 > test/cpuset.cpus
# echo isolated > test/cpuset.cpus.partition
# cat test/cpuset.cpus.partition
isolated
# echo 9 > test/cpuset.cpus
# cat test/cpuset.cpus.partition
isolated
# cat test/cpuset.cpus
9
However, the following steps to convert a member cpuset to an isolated
partition will fail:
# cd /sys/fs/cgroup/
# mkdir test
# echo 9 > test/cpuset.cpus
# echo isolated > test/cpuset.cpus.partition
# cat test/cpuset.cpus.partition
isolated invalid (partition config conflicts with housekeeping setup)
The issue occurs because the new partition state (new_prs) is used for
validation against housekeeping constraints before it has been properly
updated. To resolve this, move the assignment of new_prs before the
housekeeping validation check when enabling a root partition.
Fixes: 4a74e41888 ("cgroup/cpuset: Check partition conflict with housekeeping setup")
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
And drop ns_free_inum(). Anything common that can be wasted centrally
should be wasted in the new common helper.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
There's a lot of information that namespace implementers don't need to
know about at all. Encapsulate this all in the initialization helper.
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Every namespace type has a container_of(ns, <ns_type>, ns) static inline
function that is currently not exposed in the header. So we have a bunch
of places that open-code it via container_of(). Move it to the headers
so we can use it directly.
Reviewed-by: Aleksa Sarai <cyphar@cyphar.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Support the generic ns lookup infrastructure to support file handles for
namespaces.
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
Don't cargo-cult the same thing over and over.
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
A previous patch has introduced a new helper function
partition_cpus_change(). Now replace the exclusive cpus setting logic
with this helper function.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Previous patches made parse_cpulist handle empty cpu mask input.
Now use this helper for exclusive cpus setting. Also, compute_trialcs_xcpus
can be called with empty cpus and handles it correctly.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Introduce the partition_cpus_change function to handle both regular CPU
set updates and exclusive CPU modifications, either of which may trigger
partition state changes. This generalized function will also be utilized
for exclusive CPU updates in subsequent patches.
With the introduction of compute_trialcs_excpus in a previous patch,
the trialcs->effective_xcpus field is now consistently computed and
maintained. Consequently, the legacy logic which assigned
**trialcs->allowed_cpus to a local 'xcpus' variable** when
trialcs->effective_xcpus was empty has been removed.
This removal is safe because when trialcs is not a partition member,
trialcs->effective_xcpus is now correctly populated with the intersection
of user_xcpus and the parent's effective_xcpus. This calculation inherently
covers the scenario previously handled by the removed code.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Refactor cpus_allowed_validate_change to handle the special case where
cpuset.cpus can be set even when violating partition sibling CPU
exclusivity rules. This differs from the general validation logic in
validate_change. Add a wrapper function to properly handle this
exceptional case.
The trialcs->prs_err field is cleared before performing validation checks
for both CPU changes and partition errors. If cpus_allowed_validate_change
fails its validation, trialcs->prs_err is set to PERR_NOTEXCL. If partition
validation fails, the specific error code returned by validate_partition
is assigned to trialcs->prs_err.
With the partition validation status now directly available through
trialcs->prs_err, the local boolean variable 'invalidate' becomes
redundant and can be safely removed.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Refactor the validate_partition function to handle cpuset partition
validation when modifying cpuset.cpus. This refactoring also makes the
function reusable for handling cpuset.cpus.exclusive updates in subsequent
patches.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
This patch adds cpus_excl_conflict() and mems_excl_conflict() helper
functions to improve code readability and maintainability. The exclusive
conflict checking follows these rules:
1. If either cpuset has the 'exclusive' flag set, their user_xcpus must
not have any overlap.
2. If neither cpuset has the 'exclusive' flag set, their
'cpuset.cpus.exclusive' (only for v2) values must not intersect.
3. The 'cpuset.cpus' of one cpuset must not form a subset of another
cpuset's 'cpuset.cpus.exclusive'.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The current implementation contains redundant handling for empty mask
inputs, as cpulist_parse() already properly handles these cases. This
refactoring introduces a new helper function parse_cpuset_cpulist() to
consolidate CPU list parsing logic and eliminate special-case checks for
empty inputs.
Additionally, the effective_xcpus computation for trial cpusets has been
simplified. Rather than computing effective_xcpus only when exclusive_cpus
is set or when the cpuset forms a valid partition, we now recalculate it
on every cpuset.cpus update. This approach ensures consistency and allows
removal of redundant effective_xcpus logic in subsequent patches.
The trial cpuset's effective_xcpus calculation follows two distinct cases:
1. For member cpusets: effective_xcpus is determined by the intersection
of cpuset->exclusive_cpus and the parent's effective_xcpus.
2. For non-member cpusets: effective_xcpus is derived from the intersection
of user_xcpus and the parent's effective_xcpus.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The current compute_effective_exclusive_cpumask function handles multiple
scenarios with different input parameters, making the code difficult to
follow. This patch refactors it into two separate functions:
compute_excpus and compute_trialcs_excpus.
The compute_excpus function calculates the exclusive CPU mask for a given
input and excludes exclusive CPUs from sibling cpusets when cs's
exclusive_cpus is not explicitly set.
The compute_trialcs_excpus function specifically handles exclusive CPU
computation for trial cpusets used during CPU mask configuration updates,
and always excludes exclusive CPUs from sibling cpusets.
This refactoring significantly improves code readability and clarity,
making it explicit which function to call for each use case and what
parameters should be provided.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The functions is_partition_valid() and is_partition_invalid() logically
return boolean values, but were previously declared with return type
'int'. This patch changes their return type to 'bool' to better reflect
their semantic meaning and improve type safety.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The trialcs->partition_root_state field is not used during the
configuration of 'cpuset.cpus' or 'cpuset.cpus.exclusive'. Therefore,
the assignment of values to this field can be safely removed.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The 'cpus' or 'mems' lists of the top_cpuset cannot be modified.
This check can be moved before acquiring any locks as a common code
block to improve efficiency and maintainability.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Since commit a8bb74acd8 ("rcu: Consolidate RCU-sched update-side function definitions")
there is no difference between rcu_read_lock(), rcu_read_lock_bh() and
rcu_read_lock_sched() in terms of RCU read section and the relevant grace
period. That means that spin_lock(), which implies rcu_read_lock_sched(),
also implies rcu_read_lock().
There is no need no explicitly start a RCU read section if one has already
been started implicitly by spin_lock().
Simplify the code and remove the inner rcu_read_lock() invocation.
Cc: Waiman Long <longman@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: pengdonglin <pengdonglin@xiaomi.com>
Signed-off-by: pengdonglin <dolinux.peng@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Since commit a8bb74acd8 ("rcu: Consolidate RCU-sched update-side function definitions")
there is no difference between rcu_read_lock(), rcu_read_lock_bh() and
rcu_read_lock_sched() in terms of RCU read section and the relevant grace
period. That means that spin_lock(), which implies rcu_read_lock_sched(),
also implies rcu_read_lock().
There is no need no explicitly start a RCU read section if one has already
been started implicitly by spin_lock().
Simplify the code and remove the inner rcu_read_lock() invocation.
Cc: Tejun Heo <tj@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: pengdonglin <pengdonglin@xiaomi.com>
Signed-off-by: pengdonglin <dolinux.peng@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The bpf_cgroup_from_id kfunc relies on cgroup_get_from_id to obtain the
cgroup corresponding to a given cgroup ID. This helper can be called in
a lot of contexts where the current thread can be random. A recent
example was its use in sched_ext's ops.tick(), to obtain the root cgroup
pointer. Since the current task can be whatever random user space task
preempted by the timer tick, this makes the behavior of the helper
unreliable.
Refactor out __cgroup_get_from_id as the non-namespace aware version of
cgroup_get_from_id, and change bpf_cgroup_from_id to make use of it.
There is no compatibility breakage here, since changing the namespace
against which the lookup is being done to the root cgroup namespace only
permits a wider set of lookups to succeed now. The cgroup IDs across
namespaces are globally unique, and thus don't need to be retranslated.
Reported-by: Dan Schatzberg <dschatzberg@meta.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20250915032618.1551762-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The static usage pattern of creating a cgroup, enabling controllers,
and then seeding it with CLONE_INTO_CGROUP doesn't require write
locking cgroup_threadgroup_rwsem and thus doesn't benefit from this
patch.
To avoid affecting other users, the per threadgroup rwsem is only used
when the favordynmods is enabled.
As computer hardware advances, modern systems are typically equipped
with many CPU cores and large amounts of memory, enabling the deployment
of numerous applications. On such systems, container creation and
deletion become frequent operations, making cgroup process migration no
longer a cold path. This leads to noticeable contention with common
process operations such as fork, exec, and exit.
To alleviate the contention between cgroup process migration and
operations like process fork, this patch modifies lock to take the write
lock on signal_struct->group_rwsem when writing pid to
cgroup.procs/threads instead of holding a global write lock.
Cgroup process migration has historically relied on
signal_struct->group_rwsem to protect thread group integrity. In commit
<1ed1328792ff> ("sched, cgroup: replace signal_struct->group_rwsem with
a global percpu_rwsem"), this was changed to a global
cgroup_threadgroup_rwsem. The advantage of using a global lock was
simplified handling of process group migrations. This patch retains the
use of the global lock for protecting process group migration, while
reducing contention by using per thread group lock during
cgroup.procs/threads writes.
The locking behavior is as follows:
write cgroup.procs/threads | process fork,exec,exit | process group migration
------------------------------------------------------------------------------
cgroup_lock() | down_read(&g_rwsem) | cgroup_lock()
down_write(&p_rwsem) | down_read(&p_rwsem) | down_write(&g_rwsem)
critical section | critical section | critical section
up_write(&p_rwsem) | up_read(&p_rwsem) | up_write(&g_rwsem)
cgroup_unlock() | up_read(&g_rwsem) | cgroup_unlock()
g_rwsem denotes cgroup_threadgroup_rwsem, p_rwsem denotes
signal_struct->group_rwsem.
This patch eliminates contention between cgroup migration and fork
operations for threads that belong to different thread groups, thereby
reducing the long-tail latency of cgroup migrations and lowering system
load.
With this patch, under heavy fork and exec interference, the long-tail
latency of cgroup migration has been reduced from milliseconds to
microseconds. Under heavy cgroup migration interference, the multi-CPU
score of the spawn test case in UnixBench increased by 9%.
tj: Update comment in cgroup_favor_dynmods() and switch WARN_ONCE() to
pr_warn_once().
Signed-off-by: Yi Tao <escape@linux.alibaba.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Later patches will introduce a new parameter `task` to
cgroup_attach_lock, thus adjusting the position of cgroup_attach_lock
within cgroup_procs_write_start.
Between obtaining the threadgroup leader via PID and acquiring the
cgroup attach lock, the threadgroup leader may change, which could lead
to incorrect cgroup migration. Therefore, after acquiring the cgroup
attach lock, we check whether the threadgroup leader has changed, and if
so, retry the operation.
tj: Minor comment adjustments.
Signed-off-by: Yi Tao <escape@linux.alibaba.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Dynamic cgroup migration involving threadgroup locks can be in one of
two states: no lock held, or holding the global lock. Explicitly
declaring the different lock modes to make the code easier to
understand and facilitates future extensions of the lock modes.
Signed-off-by: Yi Tao <escape@linux.alibaba.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Pull for-6.17-fixes to receive 79f919a89c ("cgroup: split
cgroup_destroy_wq into 3 workqueues") to resolve its conflict with
7fa33aa3b0 ("cgroup: WQ_PERCPU added to alloc_workqueue users"). The
latter adds WQ_PERCPU when creating cgroup_destroy_wq and the former splits
the workqueue into three. Resolve by applying WQ_PERCPU to the three split
workqueues.
Signed-off-by: Tejun Heo <tj@kernel.org>
Currently if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistentcy cannot be addressed without refactoring the API.
alloc_workqueue() treats all queues as per-CPU by default, while unbound
workqueues must opt-in via WQ_UNBOUND.
This default is suboptimal: most workloads benefit from unbound queues,
allowing the scheduler to place worker threads where they’re needed and
reducing noise when CPUs are isolated.
This patch adds a new WQ_PERCPU flag to explicitly request the use of
the per-CPU behavior. Both flags coexist for one release cycle to allow
callers to transition their calls.
Once migration is complete, WQ_UNBOUND can be removed and unbound will
become the implicit default.
With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND),
any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND
must now use WQ_PERCPU.
All existing users have been updated accordingly.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Currently if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistentcy cannot be addressed without refactoring the API.
system_wq is a per-CPU worqueue, yet nothing in its name tells about that
CPU affinity constraint, which is very often not required by users. Make
it clear by adding a system_percpu_wq.
queue_work() / queue_delayed_work() mod_delayed_work() will now use the
new per-cpu wq: whether the user still stick on the old name a warn will
be printed along a wq redirect to the new one.
This patch add the new system_percpu_wq except for mm, fs and net
subsystem, whom are handled in separated patches.
The old wq will be kept for a few release cylces.
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
d8b269e009 ("cgroup: Remove unused cgroup_subsys::post_attach") made $ss
and $ssid unused but didn't drop them leading to compilation warnings. Drop
them.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Chuyi Zhou <zhouchuyi@bytedance.com>
cgroup_subsys::post_attach callback was introduced in commit 5cf1cacb49
("cgroup, cpuset: replace cpuset_post_attach_flush() with
cgroup_subsys->post_attach callback") and only cpuset would use this
callback to wait for the mm migration to complete at the end of
__cgroup_procs_write(). Since the previous patch defer the flush operation
until returning to userspace, no one use this callback now. Remove this
callback from cgroup_subsys.
Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Now in cpuset_attach(), we need to synchronously wait for
flush_workqueue to complete. The execution time of flushing
cpuset_migrate_mm_wq depends on the amount of mm migration initiated by
cpusets at that time. When the cpuset.mems of a cgroup occupying a large
amount of memory is modified, it may trigger extensive mm migration,
causing cpuset_attach() to block on flush_workqueue for an extended period.
This could be dangerous because cpuset_attach() is within the critical
section of cgroup_mutex, which may ultimately cause all cgroup-related
operations in the system to be blocked.
This patch attempts to defer the flush_workqueue() operation until
returning to userspace using the task_work which is originally proposed by
tejun[1], so that flush happens after cgroup_mutex is dropped. That way we
maintain the operation synchronicity while avoiding bothering anyone else.
[1]: https://lore.kernel.org/cgroups/ZgMFPMjZRZCsq9Q-@slm.duckdns.org/T/#m117f606fa24f66f0823a60f211b36f24bd9e1883
Originally-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
It is unnecessary to always wait for the flush operation of
cpuset_migrate_mm_wq to complete in cpuset_write_resmask, as modifying
cpuset.cpus or cpuset.exclusive does not trigger mm migrations. The
flush_workqueue can be executed only when cpuset.mems is modified.
Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Commit 5806b3d051 ("cpuset: decouple tmpmasks and cpumasks freeing in
cgroup") separates out the freeing of tmpmasks into a new free_tmpmask()
helper but removes the NULL pointer check in the process. Unfortunately a
NULL pointer can be passed to free_tmpmasks() in cpuset_handle_hotplug()
if cpuset v1 is active. This can cause segmentation fault and crash
the kernel.
Fix that by adding the NULL pointer check to free_tmpmasks().
Fixes: 5806b3d051 ("cpuset: decouple tmpmasks and cpumasks freeing in cgroup")
Reported-by: Ashay Jaiswal <quic_ashayj@quicinc.com>
Closes: https://lore.kernel.org/lkml/20250902-cpuset-free-on-condition-v1-1-f46ffab53eac@quicinc.com/
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
With the introduction of clone3 in commit 7f192e3cd3 ("fork: add
clone3") the effective bit width of clone_flags on all architectures was
increased from 32-bit to 64-bit, with a new type of u64 for the flags.
However, for most consumers of clone_flags the interface was not
changed from the previous type of unsigned long.
While this works fine as long as none of the new 64-bit flag bits
(CLONE_CLEAR_SIGHAND and CLONE_INTO_CGROUP) are evaluated, this is still
undesirable in terms of the principle of least surprise.
Thus, this commit fixes all relevant interfaces of callees to
sys_clone3/copy_process (excluding the architecture-specific
copy_thread) to consistently pass clone_flags as u64, so that
no truncation to 32-bit integers occurs on 32-bit architectures.
Signed-off-by: Simon Schuster <schuster.simon@siemens-energy.com>
Link: https://lore.kernel.org/20250901-nios2-implement-clone3-v2-2-53fcf5577d57@siemens-energy.com
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
cpuset: add helpers for cpus_read_lock and cpuset_mutex locks.
Replace repetitive locking patterns with new helpers:
- cpuset_full_lock()
- cpuset_full_unlock()
This makes the code cleaner and ensures consistent lock ordering.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Currently, free_cpumasks() can free both tmpmasks and cpumasks of a cpuset
(cs). However, these two operations are not logically coupled. To improve
code clarity:
1. Move cpumask freeing to free_cpuset()
2. Rename free_cpumasks() to free_tmpmasks()
This change enforces the single responsibility principle.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The list_for_each_rcu() relies on the rcu_dereference() API which is not
provided by the list.h. At the same time list.h is a low-level basic header
that must not have dependencies like RCU, besides the fact of the potential
circular dependencies in some cases. With all that said, move RCU related
API to the rculist.h where it belongs.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Simona Vetter <simona.vetter@ffwll.ch>
Reviewed-by: "Paul E. McKenney" <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.upadhyay@kernel.org>
Signed-off-by: "Paul E. McKenney" <paulmck@kernel.org>
There isn't yet a clear way to identify a set of "lost" time that
everyone (or at least a wider group of users) cares about. However,
users can perform some delay accounting by iterating over components of
interest. This patch allows cgroup v2 freezing time to be one of those
components.
Track the cumulative time that each v2 cgroup spends freezing and expose
it to userland via a new local stat file in cgroupfs. Thank you to
Michal, who provided the ASCII art in the updated documentation.
To access this value:
$ mkdir /sys/fs/cgroup/test
$ cat /sys/fs/cgroup/test/cgroup.stat.local
freeze_time_total 0
Ensure consistent freeze time reads with freeze_seq, a per-cgroup
sequence counter. Writes are serialized using the css_set_lock.
Signed-off-by: Tiffany Yang <ynaffit@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
A hung task can occur during [1] LTP cgroup testing when repeatedly
mounting/unmounting perf_event and net_prio controllers with
systemd.unified_cgroup_hierarchy=1. The hang manifests in
cgroup_lock_and_drain_offline() during root destruction.
Related case:
cgroup_fj_function_perf_event cgroup_fj_function.sh perf_event
cgroup_fj_function_net_prio cgroup_fj_function.sh net_prio
Call Trace:
cgroup_lock_and_drain_offline+0x14c/0x1e8
cgroup_destroy_root+0x3c/0x2c0
css_free_rwork_fn+0x248/0x338
process_one_work+0x16c/0x3b8
worker_thread+0x22c/0x3b0
kthread+0xec/0x100
ret_from_fork+0x10/0x20
Root Cause:
CPU0 CPU1
mount perf_event umount net_prio
cgroup1_get_tree cgroup_kill_sb
rebind_subsystems // root destruction enqueues
// cgroup_destroy_wq
// kill all perf_event css
// one perf_event css A is dying
// css A offline enqueues cgroup_destroy_wq
// root destruction will be executed first
css_free_rwork_fn
cgroup_destroy_root
cgroup_lock_and_drain_offline
// some perf descendants are dying
// cgroup_destroy_wq max_active = 1
// waiting for css A to die
Problem scenario:
1. CPU0 mounts perf_event (rebind_subsystems)
2. CPU1 unmounts net_prio (cgroup_kill_sb), queuing root destruction work
3. A dying perf_event CSS gets queued for offline after root destruction
4. Root destruction waits for offline completion, but offline work is
blocked behind root destruction in cgroup_destroy_wq (max_active=1)
Solution:
Split cgroup_destroy_wq into three dedicated workqueues:
cgroup_offline_wq – Handles CSS offline operations
cgroup_release_wq – Manages resource release
cgroup_free_wq – Performs final memory deallocation
This separation eliminates blocking in the CSS free path while waiting for
offline operations to complete.
[1] https://github.com/linux-test-project/ltp/blob/master/runtest/controllers
Fixes: 334c3679ec ("cgroup: reimplement rebind_subsystems() using cgroup_apply_control() and friends")
Reported-by: Gao Yingjie <gaoyingjie@uniontech.com>
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Suggested-by: Teju Heo <tj@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
The CS_ONLINE flag was introduced prior to the CSS_ONLINE flag in the
cpuset subsystem. Currently, the flag setting sequence is as follows:
1. cpuset_css_online() sets CS_ONLINE
2. css->flags gets CSS_ONLINE set
...
3. cgroup->kill_css sets CSS_DYING
4. cpuset_css_offline() clears CS_ONLINE
5. css->flags clears CSS_ONLINE
The is_cpuset_online() check currently occurs between steps 1 and 3.
However, it would be equally safe to perform this check between steps 2
and 3, as CSS_ONLINE provides the same synchronization guarantee as
CS_ONLINE.
Since CS_ONLINE is redundant with CSS_ONLINE and provides no additional
synchronization benefits, we can safely remove it to simplify the code.
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
css_rstat_exit() may be called asynchronously in scenarios where preceding
calls to css_rstat_init() have not completed. One such example is this
sequence below:
css_create(...)
{
...
init_and_link_css(css, ...);
err = percpu_ref_init(...);
if (err)
goto err_free_css;
err = cgroup_idr_alloc(...);
if (err)
goto err_free_css;
err = css_rstat_init(css, ...);
if (err)
goto err_free_css;
...
err_free_css:
INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
return ERR_PTR(err);
}
If any of the three goto jumps are taken, async cleanup will begin and
css_rstat_exit() will be invoked on an uninitialized css->rstat_cpu.
Avoid accessing the unitialized field by returning early in
css_rstat_exit() if this is the case.
Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Suggested-by: Michal Koutný <mkoutny@suse.com>
Fixes: 5da3bfa029 ("cgroup: use separate rstat trees for each subsystem")
Cc: stable@vger.kernel.org # v6.16
Reported-by: syzbot+8d052e8b99e40bc625ed@syzkaller.appspotmail.com
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Signed-off-by: Tejun Heo <tj@kernel.org>
The css_get/put() calls in cpuset_partition_write() are unnecessary as
an active reference of the kernfs node will be taken which will prevent
its removal and guarantee the existence of the css. Only the online
check is needed.
Signed-off-by: Waiman Long <longman@redhat.com>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
It was found during testing that an invalid leaf partition with an
empty effective exclusive CPU list can become a valid empty partition
with no CPU afer an offline/online operation of an unrelated CPU. An
empty partition root is allowed in the special case that it has no
task in its cgroup and has distributed out all its CPUs to its child
partitions. That is certainly not the case here.
The problem is in the cpumask_subsets() test in the hotplug case
(update with no new mask) of update_parent_effective_cpumask() as it
also returns true if the effective exclusive CPU list is empty. Fix that
by addding the cpumask_empty() test to root out this exception case.
Also add the cpumask_empty() test in cpuset_hotplug_update_tasks()
to avoid calling update_parent_effective_cpumask() for this special case.
Fixes: 0c7f293efc ("cgroup/cpuset: Add cpuset.cpus.exclusive.effective for v2")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
