- Various performance optimizations, resulting in a 4%-9% speedup
in the mmtests/config-scheduler-perfpipe micro-benchmark.
- New interface to turn PSI on/off on a per cgroup level.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=91tB
-----END PGP SIGNATURE-----
Merge tag 'sched-psi-2022-10-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull PSI updates from Ingo Molnar:
- Various performance optimizations, resulting in a 4%-9% speedup in
the mmtests/config-scheduler-perfpipe micro-benchmark.
- New interface to turn PSI on/off on a per cgroup level.
* tag 'sched-psi-2022-10-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/psi: Per-cgroup PSI accounting disable/re-enable interface
sched/psi: Cache parent psi_group to speed up group iteration
sched/psi: Consolidate cgroup_psi()
sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure
sched/psi: Remove NR_ONCPU task accounting
sched/psi: Optimize task switch inside shared cgroups again
sched/psi: Move private helpers to sched/stats.h
sched/psi: Save percpu memory when !psi_cgroups_enabled
sched/psi: Don't create cgroup PSI files when psi_disabled
sched/psi: Fix periodic aggregation shut off
PSI accounts stalls for each cgroup separately and aggregates it
at each level of the hierarchy. This may cause non-negligible overhead
for some workloads when under deep level of the hierarchy.
commit 3958e2d0c3 ("cgroup: make per-cgroup pressure stall tracking configurable")
make PSI to skip per-cgroup stall accounting, only account system-wide
to avoid this each level overhead.
But for our use case, we also want leaf cgroup PSI stats accounted for
userspace adjustment on that cgroup, apart from only system-wide adjustment.
So this patch introduce a per-cgroup PSI accounting disable/re-enable
interface "cgroup.pressure", which is a read-write single value file that
allowed values are "0" and "1", the defaults is "1" so per-cgroup
PSI stats is enabled by default.
Implementation details:
It should be relatively straight-forward to disable and re-enable
state aggregation, time tracking, averaging on a per-cgroup level,
if we can live with losing history from while it was disabled.
I.e. the avgs will restart from 0, total= will have gaps.
But it's hard or complex to stop/restart groupc->tasks[] updates,
which is not implemented in this patch. So we always update
groupc->tasks[] and PSI_ONCPU bit in psi_group_change() even when
the cgroup PSI stats is disabled.
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20220907090332.2078-1-zhouchengming@bytedance.com
CFTYPE_PRESSURE is used to flag PSI related files so that they are not
created if PSI is disabled during boot. It's a bit weird to use a generic
flag to mark a specific file type. Let's instead move the PSI files into its
own cftypes array and add/rm them conditionally. This is a bit more code but
cleaner.
No userland visible changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Let's track whether a cftype is currently added or not using a new flag
__CFTYPE_ADDED so that duplicate operations can be failed safely and
consistently allow using empty cftypes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Every cgroup knows all its ancestors through its ->ancestor_ids[]. There's
no advantage to remembering the IDs instead of the pointers directly and
this makes the array useless for finding an actual ancestor cgroup forcing
cgroup_ancestor() to iteratively walk up the hierarchy instead. Let's
replace cgroup->ancestor_ids[] with ->ancestors[] and remove the walking-up
from cgroup_ancestor().
While at it, improve comments around cgroup_root->cgrp_ancestor_storage.
This patch shouldn't cause user-visible behavior differences.
v2: Update cgroup_ancestor() to use ->ancestors[].
v3: cgroup_root->cgrp_ancestor_storage's type is updated to match
cgroup->ancestors[]. Better comments.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
* 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.
-----BEGIN PGP SIGNATURE-----
iIQEABYIACwWIQTfIjM1kS57o3GsC/uxYfJx3gVYGQUCYugHIQ4cdGpAa2VybmVs
Lm9yZwAKCRCxYfJx3gVYGd+oAP9lfD3fTRdNo4qWV2VsZsYzoOxzNIuJSwN/dnYx
IEbQOwD/cd2YMfeo6zcb427U/VfTFqjJjFK04OeljYtJU8fFywo=
=sucy
-----END PGP SIGNATURE-----
Merge tag 'cgroup-for-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
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
Load-balancing improvements:
============================
- Improve NUMA balancing on AMD Zen systems for affine workloads.
- Improve the handling of reduced-capacity CPUs in load-balancing.
- Energy Model improvements: fix & refine all the energy fairness metrics (PELT),
and remove the conservative threshold requiring 6% energy savings to
migrate a task. Doing this improves power efficiency for most workloads,
and also increases the reliability of energy-efficiency scheduling.
- Optimize/tweak select_idle_cpu() to spend (much) less time searching
for an idle CPU on overloaded systems. There's reports of several
milliseconds spent there on large systems with large workloads ...
[ Since the search logic changed, there might be behavioral side effects. ]
- Improve NUMA imbalance behavior. On certain systems
with spare capacity, initial placement of tasks is non-deterministic,
and such an artificial placement imbalance can persist for a long time,
hurting (and sometimes helping) performance.
The fix is to make fork-time task placement consistent with runtime
NUMA balancing placement.
Note that some performance regressions were reported against this,
caused by workloads that are not memory bandwith limited, which benefit
from the artificial locality of the placement bug(s). Mel Gorman's
conclusion, with which we concur, was that consistency is better than
random workload benefits from non-deterministic bugs:
"Given there is no crystal ball and it's a tradeoff, I think it's
better to be consistent and use similar logic at both fork time
and runtime even if it doesn't have universal benefit."
- Improve core scheduling by fixing a bug in sched_core_update_cookie() that
caused unnecessary forced idling.
- Improve wakeup-balancing by allowing same-LLC wakeup of idle CPUs for newly
woken tasks.
- Fix a newidle balancing bug that introduced unnecessary wakeup latencies.
ABI improvements/fixes:
=======================
- Do not check capabilities and do not issue capability check denial messages
when a scheduler syscall doesn't require privileges. (Such as increasing niceness.)
- Add forced-idle accounting to cgroups too.
- Fix/improve the RSEQ ABI to not just silently accept unknown flags.
(No existing tooling is known to have learned to rely on the previous behavior.)
- Depreciate the (unused) RSEQ_CS_FLAG_NO_RESTART_ON_* flags.
Optimizations:
==============
- Optimize & simplify leaf_cfs_rq_list()
- Micro-optimize set_nr_{and_not,if}_polling() via try_cmpxchg().
Misc fixes & cleanups:
======================
- Fix the RSEQ self-tests on RISC-V and Glibc 2.35 systems.
- Fix a full-NOHZ bug that can in some cases result in the tick not being
re-enabled when the last SCHED_RT task is gone from a runqueue but there's
still SCHED_OTHER tasks around.
- Various PREEMPT_RT related fixes.
- Misc cleanups & smaller fixes.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=xr2b
-----END PGP SIGNATURE-----
Merge tag 'sched-core-2022-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
"Load-balancing improvements:
- Improve NUMA balancing on AMD Zen systems for affine workloads.
- Improve the handling of reduced-capacity CPUs in load-balancing.
- Energy Model improvements: fix & refine all the energy fairness
metrics (PELT), and remove the conservative threshold requiring 6%
energy savings to migrate a task. Doing this improves power
efficiency for most workloads, and also increases the reliability
of energy-efficiency scheduling.
- Optimize/tweak select_idle_cpu() to spend (much) less time
searching for an idle CPU on overloaded systems. There's reports of
several milliseconds spent there on large systems with large
workloads ...
[ Since the search logic changed, there might be behavioral side
effects. ]
- Improve NUMA imbalance behavior. On certain systems with spare
capacity, initial placement of tasks is non-deterministic, and such
an artificial placement imbalance can persist for a long time,
hurting (and sometimes helping) performance.
The fix is to make fork-time task placement consistent with runtime
NUMA balancing placement.
Note that some performance regressions were reported against this,
caused by workloads that are not memory bandwith limited, which
benefit from the artificial locality of the placement bug(s). Mel
Gorman's conclusion, with which we concur, was that consistency is
better than random workload benefits from non-deterministic bugs:
"Given there is no crystal ball and it's a tradeoff, I think
it's better to be consistent and use similar logic at both fork
time and runtime even if it doesn't have universal benefit."
- Improve core scheduling by fixing a bug in
sched_core_update_cookie() that caused unnecessary forced idling.
- Improve wakeup-balancing by allowing same-LLC wakeup of idle CPUs
for newly woken tasks.
- Fix a newidle balancing bug that introduced unnecessary wakeup
latencies.
ABI improvements/fixes:
- Do not check capabilities and do not issue capability check denial
messages when a scheduler syscall doesn't require privileges. (Such
as increasing niceness.)
- Add forced-idle accounting to cgroups too.
- Fix/improve the RSEQ ABI to not just silently accept unknown flags.
(No existing tooling is known to have learned to rely on the
previous behavior.)
- Depreciate the (unused) RSEQ_CS_FLAG_NO_RESTART_ON_* flags.
Optimizations:
- Optimize & simplify leaf_cfs_rq_list()
- Micro-optimize set_nr_{and_not,if}_polling() via try_cmpxchg().
Misc fixes & cleanups:
- Fix the RSEQ self-tests on RISC-V and Glibc 2.35 systems.
- Fix a full-NOHZ bug that can in some cases result in the tick not
being re-enabled when the last SCHED_RT task is gone from a
runqueue but there's still SCHED_OTHER tasks around.
- Various PREEMPT_RT related fixes.
- Misc cleanups & smaller fixes"
* tag 'sched-core-2022-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
rseq: Kill process when unknown flags are encountered in ABI structures
rseq: Deprecate RSEQ_CS_FLAG_NO_RESTART_ON_* flags
sched/core: Fix the bug that task won't enqueue into core tree when update cookie
nohz/full, sched/rt: Fix missed tick-reenabling bug in dequeue_task_rt()
sched/core: Always flush pending blk_plug
sched/fair: fix case with reduced capacity CPU
sched/core: Use try_cmpxchg in set_nr_{and_not,if}_polling
sched/core: add forced idle accounting for cgroups
sched/fair: Remove the energy margin in feec()
sched/fair: Remove task_util from effective utilization in feec()
sched/fair: Use the same cpumask per-PD throughout find_energy_efficient_cpu()
sched/fair: Rename select_idle_mask to select_rq_mask
sched, drivers: Remove max param from effective_cpu_util()/sched_cpu_util()
sched/fair: Decay task PELT values during wakeup migration
sched/fair: Provide u64 read for 32-bits arch helper
sched/fair: Introduce SIS_UTIL to search idle CPU based on sum of util_avg
sched: only perform capability check on privileged operation
sched: Remove unused function group_first_cpu()
sched/fair: Remove redundant word " *"
selftests/rseq: check if libc rseq support is registered
...
3942a9bd7b ("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 <tj@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Michal Koutn� <mkoutny@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Dmitry Shmidt <dimitrysh@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
4feee7d126 previously added per-task forced idle accounting. This patch
extends this to also include cgroups.
rstat is used for cgroup accounting, except for the root, which uses
kcpustat in order to bypass the need for doing an rstat flush when
reading root stats.
Only cgroup v2 is supported. Similar to the task accounting, the cgroup
accounting requires that schedstats is enabled.
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lkml.kernel.org/r/20220629211426.3329954-1-joshdon@google.com
Each cset (css_set) is pinned by its tasks. When we're moving tasks around
across csets for a migration, we need to hold the source and destination
csets to ensure that they don't go away while we're moving tasks about. This
is done by linking cset->mg_preload_node on either the
mgctx->preloaded_src_csets or mgctx->preloaded_dst_csets list. Using the
same cset->mg_preload_node for both the src and dst lists was deemed okay as
a cset can't be both the source and destination at the same time.
Unfortunately, this overloading becomes problematic when multiple tasks are
involved in a migration and some of them are identity noop migrations while
others are actually moving across cgroups. For example, this can happen with
the following sequence on cgroup1:
#1> mkdir -p /sys/fs/cgroup/misc/a/b
#2> echo $$ > /sys/fs/cgroup/misc/a/cgroup.procs
#3> RUN_A_COMMAND_WHICH_CREATES_MULTIPLE_THREADS &
#4> PID=$!
#5> echo $PID > /sys/fs/cgroup/misc/a/b/tasks
#6> echo $PID > /sys/fs/cgroup/misc/a/cgroup.procs
the process including the group leader back into a. In this final migration,
non-leader threads would be doing identity migration while the group leader
is doing an actual one.
After #3, let's say the whole process was in cset A, and that after #4, the
leader moves to cset B. Then, during #6, the following happens:
1. cgroup_migrate_add_src() is called on B for the leader.
2. cgroup_migrate_add_src() is called on A for the other threads.
3. cgroup_migrate_prepare_dst() is called. It scans the src list.
4. It notices that B wants to migrate to A, so it tries to A to the dst
list but realizes that its ->mg_preload_node is already busy.
5. and then it notices A wants to migrate to A as it's an identity
migration, it culls it by list_del_init()'ing its ->mg_preload_node and
putting references accordingly.
6. The rest of migration takes place with B on the src list but nothing on
the dst list.
This means that A isn't held while migration is in progress. If all tasks
leave A before the migration finishes and the incoming task pins it, the
cset will be destroyed leading to use-after-free.
This is caused by overloading cset->mg_preload_node for both src and dst
preload lists. We wanted to exclude the cset from the src list but ended up
inadvertently excluding it from the dst list too.
This patch fixes the issue by separating out cset->mg_preload_node into
->mg_src_preload_node and ->mg_dst_preload_node, so that the src and dst
preloadings don't interfere with each other.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Mukesh Ojha <quic_mojha@quicinc.com>
Reported-by: shisiyuan <shisiyuan19870131@gmail.com>
Link: http://lkml.kernel.org/r/1654187688-27411-1-git-send-email-shisiyuan@xiaomi.com
Link: https://www.spinics.net/lists/cgroups/msg33313.html
Fixes: f817de9851 ("cgroup: prepare migration path for unified hierarchy")
Cc: stable@vger.kernel.org # v3.16+
Memory about struct psi_group is allocated by default for
each cgroup even if psi_disabled is true, in this case, these
allocated memory is waste, so alloc memory for struct psi_group
only when psi_disabled is false.
Signed-off-by: Chen Wandun <chenwandun@huawei.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
Pull cgroup updates from Tejun Heo:
"Nothing too interesting. The only two noticeable changes are a subtle
cpuset behavior fix and trace event id field being expanded to u64
from int. Most others are code cleanups"
* 'for-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cpuset: convert 'allowed' in __cpuset_node_allowed() to be boolean
cgroup/rstat: check updated_next only for root
cgroup: rstat: explicitly put loop variant in while
cgroup: return early if it is already on preloaded list
cgroup/cpuset: Don't let child cpusets restrict parent in default hierarchy
cgroup: Trace event cgroup id fields should be u64
cgroup: fix a typo in comment
cgroup: get the wrong css for css_alloc() during cgroup_init_subsys()
cgroup: rstat: Mark benign data race to silence KCSAN
Remove the dependency from cgroup-defs.h to bpf-cgroup.h and bpf.h.
This reduces the incremental build size of x86 allmodconfig after
bpf.h was touched from ~17k objects rebuilt to ~5k objects.
bpf.h is 2.2kLoC and is modified relatively often.
We need a new header with just the definition of struct cgroup_bpf
and enum cgroup_bpf_attach_type, this is akin to cgroup-defs.h.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/bpf/20211216025538.1649516-4-kuba@kernel.org
In commit 8699b7762a ("cgroup: s/child_subsys_mask/subtree_ss_mask/"),
we rename child_subsys_mask to subtree_ss_mask. While it missed to
rename this in comment.
Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Fix cgroup v1 interference when non-root cgroup v2 BPF programs are used.
Back in the days, commit bd1060a1d6 ("sock, cgroup: add sock->sk_cgroup")
embedded per-socket cgroup information into sock->sk_cgrp_data and in order
to save 8 bytes in struct sock made both mutually exclusive, that is, when
cgroup v1 socket tagging (e.g. net_cls/net_prio) is used, then cgroup v2
falls back to the root cgroup in sock_cgroup_ptr() (&cgrp_dfl_root.cgrp).
The assumption made was "there is no reason to mix the two and this is in line
with how legacy and v2 compatibility is handled" as stated in bd1060a1d6.
However, with Kubernetes more widely supporting cgroups v2 as well nowadays,
this assumption no longer holds, and the possibility of the v1/v2 mixed mode
with the v2 root fallback being hit becomes a real security issue.
Many of the cgroup v2 BPF programs are also used for policy enforcement, just
to pick _one_ example, that is, to programmatically deny socket related system
calls like connect(2) or bind(2). A v2 root fallback would implicitly cause
a policy bypass for the affected Pods.
In production environments, we have recently seen this case due to various
circumstances: i) a different 3rd party agent and/or ii) a container runtime
such as [0] in the user's environment configuring legacy cgroup v1 net_cls
tags, which triggered implicitly mentioned root fallback. Another case is
Kubernetes projects like kind [1] which create Kubernetes nodes in a container
and also add cgroup namespaces to the mix, meaning programs which are attached
to the cgroup v2 root of the cgroup namespace get attached to a non-root
cgroup v2 path from init namespace point of view. And the latter's root is
out of reach for agents on a kind Kubernetes node to configure. Meaning, any
entity on the node setting cgroup v1 net_cls tag will trigger the bypass
despite cgroup v2 BPF programs attached to the namespace root.
Generally, this mutual exclusiveness does not hold anymore in today's user
environments and makes cgroup v2 usage from BPF side fragile and unreliable.
This fix adds proper struct cgroup pointer for the cgroup v2 case to struct
sock_cgroup_data in order to address these issues; this implicitly also fixes
the tradeoffs being made back then with regards to races and refcount leaks
as stated in bd1060a1d6, and removes the fallback, so that cgroup v2 BPF
programs always operate as expected.
[0] https://github.com/nestybox/sysbox/
[1] https://kind.sigs.k8s.io/
Fixes: bd1060a1d6 ("sock, cgroup: add sock->sk_cgroup")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/bpf/20210913230759.2313-1-daniel@iogearbox.net
PSI accounts stalls for each cgroup separately and aggregates it at each
level of the hierarchy. This causes additional overhead with psi_avgs_work
being called for each cgroup in the hierarchy. psi_avgs_work has been
highly optimized, however on systems with large number of cgroups the
overhead becomes noticeable.
Systems which use PSI only at the system level could avoid this overhead
if PSI can be configured to skip per-cgroup stall accounting.
Add "cgroup_disable=pressure" kernel command-line option to allow
requesting system-wide only pressure stall accounting. When set, it
keeps system-wide accounting under /proc/pressure/ but skips accounting
for individual cgroups and does not expose PSI nodes in cgroup hierarchy.
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
Fix some spelling mistakes in comments:
hierarhcy ==> hierarchy
automtically ==> automatically
overriden ==> overridden
In absense of .. or ==> In absence of .. and
assocaited ==> associated
taget ==> target
initate ==> initiate
succeded ==> succeeded
curremt ==> current
udpated ==> updated
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Introduce the cgroup.kill file. It does what it says on the tin and
allows a caller to kill a cgroup by writing "1" into cgroup.kill.
The file is available in non-root cgroups.
Killing cgroups is a process directed operation, i.e. the whole
thread-group is affected. Consequently trying to write to cgroup.kill in
threaded cgroups will be rejected and EOPNOTSUPP returned. This behavior
aligns with cgroup.procs where reads in threaded-cgroups are rejected
with EOPNOTSUPP.
The cgroup.kill file is write-only since killing a cgroup is an event
not which makes it different from e.g. freezer where a cgroup
transitions between the two states.
As with all new cgroup features cgroup.kill is recursive by default.
Killing a cgroup is protected against concurrent migrations through the
cgroup mutex. To protect against forkbombs and to mitigate the effect of
racing forks a new CGRP_KILL css set lock protected flag is introduced
that is set prior to killing a cgroup and unset after the cgroup has
been killed. We can then check in cgroup_post_fork() where we hold the
css set lock already whether the cgroup is currently being killed. If so
we send the child a SIGKILL signal immediately taking it down as soon as
it returns to userspace. To make the killing of the child semantically
clean it is killed after all cgroup attachment operations have been
finalized.
There are various use-cases of this interface:
- Containers usually have a conservative layout where each container
usually has a delegated cgroup. For such layouts there is a 1:1
mapping between container and cgroup. If the container in addition
uses a separate pid namespace then killing a container usually becomes
a simple kill -9 <container-init-pid> from an ancestor pid namespace.
However, there are quite a few scenarios where that isn't true. For
example, there are containers that share the cgroup with other
processes on purpose that are supposed to be bound to the lifetime of
the container but are not in the same pidns of the container.
Containers that are in a delegated cgroup but share the pid namespace
with the host or other containers.
- Service managers such as systemd use cgroups to group and organize
processes belonging to a service. They usually rely on a recursive
algorithm now to kill a service. With cgroup.kill this becomes a
simple write to cgroup.kill.
- Userspace OOM implementations can make good use of this feature to
efficiently take down whole cgroups quickly.
- The kill program can gain a new
kill --cgroup /sys/fs/cgroup/delegated
flag to take down cgroups.
A few observations about the semantics:
- If parent and child are in the same cgroup and CLONE_INTO_CGROUP is
not specified we are not taking cgroup mutex meaning the cgroup can be
killed while a process in that cgroup is forking.
If the kill request happens right before cgroup_can_fork() and before
the parent grabs its siglock the parent is guaranteed to see the
pending SIGKILL. In addition we perform another check in
cgroup_post_fork() whether the cgroup is being killed and is so take
down the child (see above). This is robust enough and protects gainst
forkbombs. If userspace really really wants to have stricter
protection the simple solution would be to grab the write side of the
cgroup threadgroup rwsem which will force all ongoing forks to
complete before killing starts. We concluded that this is not
necessary as the semantics for concurrent forking should simply align
with freezer where a similar check as cgroup_post_fork() is performed.
For all other cases CLONE_INTO_CGROUP is required. In this case we
will grab the cgroup mutex so the cgroup can't be killed while we
fork. Once we're done with the fork and have dropped cgroup mutex we
are visible and will be found by any subsequent kill request.
- We obviously don't kill kthreads. This means a cgroup that has a
kthread will not become empty after killing and consequently no
unpopulated event will be generated. The assumption is that kthreads
should be in the root cgroup only anyway so this is not an issue.
- We skip killing tasks that already have pending fatal signals.
- Freezer doesn't care about tasks in different pid namespaces, i.e. if
you have two tasks in different pid namespaces the cgroup would still
be frozen. The cgroup.kill mechanism consequently behaves the same
way, i.e. we kill all processes and ignore in which pid namespace they
exist.
- If the caller is located in a cgroup that is killed the caller will
obviously be killed as well.
Link: https://lore.kernel.org/r/20210503143922.3093755-1-brauner@kernel.org
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: cgroups@vger.kernel.org
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Acked-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
With the deprecation of the non-hierarchical mode of the memory controller
there are no more examples of broken hierarchies left.
Let's remove the cgroup core code which was supposed to print warnings
about creating of broken hierarchies.
Link: https://lkml.kernel.org/r/20201110220800.929549-4-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In order for no_refcnt and is_data to be the lowest order two
bits in the 'val' we have to pad out the bitfield of the u8.
Fixes: ad0f75e5f5 ("cgroup: fix cgroup_sk_alloc() for sk_clone_lock()")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
When we clone a socket in sk_clone_lock(), its sk_cgrp_data is
copied, so the cgroup refcnt must be taken too. And, unlike the
sk_alloc() path, sock_update_netprioidx() is not called here.
Therefore, it is safe and necessary to grab the cgroup refcnt
even when cgroup_sk_alloc is disabled.
sk_clone_lock() is in BH context anyway, the in_interrupt()
would terminate this function if called there. And for sk_alloc()
skcd->val is always zero. So it's safe to factor out the code
to make it more readable.
The global variable 'cgroup_sk_alloc_disabled' is used to determine
whether to take these reference counts. It is impossible to make
the reference counting correct unless we save this bit of information
in skcd->val. So, add a new bit there to record whether the socket
has already taken the reference counts. This obviously relies on
kmalloc() to align cgroup pointers to at least 4 bytes,
ARCH_KMALLOC_MINALIGN is certainly larger than that.
This bug seems to be introduced since the beginning, commit
d979a39d72 ("cgroup: duplicate cgroup reference when cloning sockets")
tried to fix it but not compeletely. It seems not easy to trigger until
the recent commit 090e28b229
("netprio_cgroup: Fix unlimited memory leak of v2 cgroups") was merged.
Fixes: bd1060a1d6 ("sock, cgroup: add sock->sk_cgroup")
Reported-by: Cameron Berkenpas <cam@neo-zeon.de>
Reported-by: Peter Geis <pgwipeout@gmail.com>
Reported-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reported-by: Daniël Sonck <dsonck92@gmail.com>
Reported-by: Zhang Qiang <qiang.zhang@windriver.com>
Tested-by: Cameron Berkenpas <cam@neo-zeon.de>
Tested-by: Peter Geis <pgwipeout@gmail.com>
Tested-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Zefan Li <lizefan@huawei.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull cgroup updates from Tejun Heo:
- Christian extended clone3 so that processes can be spawned into
cgroups directly.
This is not only neat in terms of semantics but also avoids grabbing
the global cgroup_threadgroup_rwsem for migration.
- Daniel added !root xattr support to cgroupfs.
Userland already uses xattrs on cgroupfs for bookkeeping. This will
allow delegated cgroups to support such usages.
- Prateek tried to make cpuset hotplug handling synchronous but that
led to possible deadlock scenarios. Reverted.
- Other minor changes including release_agent_path handling cleanup.
* 'for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
docs: cgroup-v1: Document the cpuset_v2_mode mount option
Revert "cpuset: Make cpuset hotplug synchronous"
cgroupfs: Support user xattrs
kernfs: Add option to enable user xattrs
kernfs: Add removed_size out param for simple_xattr_set
kernfs: kvmalloc xattr value instead of kmalloc
cgroup: Restructure release_agent_path handling
selftests/cgroup: add tests for cloning into cgroups
clone3: allow spawning processes into cgroups
cgroup: add cgroup_may_write() helper
cgroup: refactor fork helpers
cgroup: add cgroup_get_from_file() helper
cgroup: unify attach permission checking
cpuset: Make cpuset hotplug synchronous
cgroup.c: Use built-in RCU list checking
kselftest/cgroup: add cgroup destruction test
cgroup: Clean up css_set task traversal
Right now, the effective protection of any given cgroup is capped by its
own explicit memory.low setting, regardless of what the parent says. The
reasons for this are mostly historical and ease of implementation: to make
delegation of memory.low safe, effective protection is the min() of all
memory.low up the tree.
Unfortunately, this limitation makes it impossible to protect an entire
subtree from another without forcing the user to make explicit protection
allocations all the way to the leaf cgroups - something that is highly
undesirable in real life scenarios.
Consider memory in a data center host. At the cgroup top level, we have a
distinction between system management software and the actual workload the
system is executing. Both branches are further subdivided into individual
services, job components etc.
We want to protect the workload as a whole from the system management
software, but that doesn't mean we want to protect and prioritize
individual workload wrt each other. Their memory demand can vary over
time, and we'd want the VM to simply cache the hottest data within the
workload subtree. Yet, the current memory.low limitations force us to
allocate a fixed amount of protection to each workload component in order
to get protection from system management software in general. This
results in very inefficient resource distribution.
Another concern with mandating downward allocation is that, as the
complexity of the cgroup tree grows, it gets harder for the lower levels
to be informed about decisions made at the host-level. Consider a
container inside a namespace that in turn creates its own nested tree of
cgroups to run multiple workloads. It'd be extremely difficult to
configure memory.low parameters in those leaf cgroups that on one hand
balance pressure among siblings as the container desires, while also
reflecting the host-level protection from e.g. rpm upgrades, that lie
beyond one or more delegation and namespacing points in the tree.
It's highly unusual from a cgroup interface POV that nested levels have to
be aware of and reflect decisions made at higher levels for them to be
effective.
To enable such use cases and scale configurability for complex trees, this
patch implements a resource inheritance model for memory that is similar
to how the CPU and the IO controller implement work-conserving resource
allocations: a share of a resource allocated to a subree always applies to
the entire subtree recursively, while allowing, but not mandating,
children to further specify distribution rules.
That means that if protection is explicitly allocated among siblings,
those configured shares are being followed during page reclaim just like
they are now. However, if the memory.low set at a higher level is not
fully claimed by the children in that subtree, the "floating" remainder is
applied to each cgroup in the tree in proportion to its size. Since
reclaim pressure is applied in proportion to size as well, each child in
that tree gets the same boost, and the effect is neutral among siblings -
with respect to each other, they behave as if no memory control was
enabled at all, and the VM simply balances the memory demands optimally
within the subtree. But collectively those cgroups enjoy a boost over the
cgroups in neighboring trees.
E.g. a leaf cgroup with a memory.low setting of 0 no longer means that
it's not getting a share of the hierarchically assigned resource, just
that it doesn't claim a fixed amount of it to protect from its siblings.
This allows us to recursively protect one subtree (workload) from another
(system management), while letting subgroups compete freely among each
other - without having to assign fixed shares to each leaf, and without
nested groups having to echo higher-level settings.
The floating protection composes naturally with fixed protection.
Consider the following example tree:
A A: low = 2G
/ \ A1: low = 1G
A1 A2 A2: low = 0G
As outside pressure is applied to this tree, A1 will enjoy a fixed
protection from A2 of 1G, but the remaining, unclaimed 1G from A is split
evenly among A1 and A2, coming out to 1.5G and 0.5G.
There is a slight risk of regressing theoretical setups where the
top-level cgroups don't know about the true budgeting and set bogusly high
"bypass" values that are meaningfully allocated down the tree. Such
setups would rely on unclaimed protection to be discarded, and
distributing it would change the intended behavior. Be safe and hide the
new behavior behind a mount option, 'memory_recursiveprot'.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: Chris Down <chris@chrisdown.name>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Michal Koutný <mkoutny@suse.com>
Link: http://lkml.kernel.org/r/20200227195606.46212-4-hannes@cmpxchg.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This adds support for creating a process in a different cgroup than its
parent. Callers can limit and account processes and threads right from
the moment they are spawned:
- A service manager can directly spawn new services into dedicated
cgroups.
- A process can be directly created in a frozen cgroup and will be
frozen as well.
- The initial accounting jitter experienced by process supervisors and
daemons is eliminated with this.
- Threaded applications or even thread implementations can choose to
create a specific cgroup layout where each thread is spawned
directly into a dedicated cgroup.
This feature is limited to the unified hierarchy. Callers need to pass
a directory file descriptor for the target cgroup. The caller can
choose to pass an O_PATH file descriptor. All usual migration
restrictions apply, i.e. there can be no processes in inner nodes. In
general, creating a process directly in a target cgroup adheres to all
migration restrictions.
One of the biggest advantages of this feature is that CLONE_INTO_GROUP does
not need to grab the write side of the cgroup cgroup_threadgroup_rwsem.
This global lock makes moving tasks/threads around super expensive. With
clone3() this lock is avoided.
Cc: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: cgroups@vger.kernel.org
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
cgroup ID is currently allocated using a dedicated per-hierarchy idr
and used internally and exposed through tracepoints and bpf. This is
confusing because there are tracepoints and other interfaces which use
the cgroupfs ino as IDs.
The preceding changes made kn->id exposed as ino as 64bit ino on
supported archs or ino+gen (low 32bits as ino, high gen). There's no
reason for cgroup to use different IDs. The kernfs IDs are unique and
userland can easily discover them and map them back to paths using
standard file operations.
This patch replaces cgroup IDs with kernfs IDs.
* cgroup_id() is added and all cgroup ID users are converted to use it.
* kernfs_node creation is moved to earlier during cgroup init so that
cgroup_id() is available during init.
* While at it, s/cgroup/cgrp/ in psi helpers for consistency.
* Fallback ID value is changed to 1 to be consistent with root cgroup
ID.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
cgroup->bstat_pending is used to determine the base stat delta to
propagate to the parent. While correct, this is different from how
percpu delta is determined for no good reason and the inconsistency
makes the code more difficult to understand.
This patch makes parent propagation delta calculation use the same
method as percpu to global propagation.
* cgroup_base_stat_accumulate() is renamed to cgroup_base_stat_add()
and cgroup_base_stat_sub() is added.
* percpu propagation calculation is updated to use the above helpers.
* cgroup->bstat_pending is replaced with cgroup->last_bstat and
updated to use the same calculation as percpu propagation.
Signed-off-by: Tejun Heo <tj@kernel.org>
Pull cgroup updates from Tejun Heo:
"Documentation updates and the addition of cgroup_parse_float() which
will be used by new controllers including blk-iocost"
* 'for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
docs: cgroup-v1: convert docs to ReST and rename to *.rst
cgroup: Move cgroup_parse_float() implementation out of CONFIG_SYSFS
cgroup: add cgroup_parse_float()
Pull cgroup fixes from Tejun Heo:
"This has an unusually high density of tricky fixes:
- task_get_css() could deadlock when it races against a dying cgroup.
- cgroup.procs didn't list thread group leaders with live threads.
This could mislead readers to think that a cgroup is empty when
it's not. Fixed by making PROCS iterator include dead tasks. I made
a couple mistakes making this change and this pull request contains
a couple follow-up patches.
- When cpusets run out of online cpus, it updates cpusmasks of member
tasks in bizarre ways. Joel improved the behavior significantly"
* 'for-5.2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cpuset: restore sanity to cpuset_cpus_allowed_fallback()
cgroup: Fix css_task_iter_advance_css_set() cset skip condition
cgroup: css_task_iter_skip()'d iterators must be advanced before accessed
cgroup: Include dying leaders with live threads in PROCS iterations
cgroup: Implement css_task_iter_skip()
cgroup: Call cgroup_release() before __exit_signal()
docs cgroups: add another example size for hugetlb
cgroup: Use css_tryget() instead of css_tryget_online() in task_get_css()
Convert the cgroup-v1 files to ReST format, in order to
allow a later addition to the admin-guide.
The conversion is actually:
- add blank lines and identation in order to identify paragraphs;
- fix tables markups;
- add some lists markups;
- mark literal blocks;
- adjust title markups.
At its new index.rst, let's add a :orphan: while this is not linked to
the main index.rst file, in order to avoid build warnings.
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
There's some discussion on how to do this the best, and Tejun prefers
that BFQ just create the file itself instead of having cgroups support
a symlink feature.
Hence revert commit 54b7b868e8 and 19e9da9e86 for 5.2, and this
can be done properly for 5.3.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit enables a cftype to have a symlink (of any name) that
points to the file associated with the cftype.
Signed-off-by: Angelo Ruocco <angeloruocco90@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
memory.stat and other files already consider subtrees in their output, and
we should too in order to not present an inconsistent interface.
The current situation is fairly confusing, because people interacting with
cgroups expect hierarchical behaviour in the vein of memory.stat,
cgroup.events, and other files. For example, this causes confusion when
debugging reclaim events under low, as currently these always read "0" at
non-leaf memcg nodes, which frequently causes people to misdiagnose breach
behaviour. The same confusion applies to other counters in this file when
debugging issues.
Aggregation is done at write time instead of at read-time since these
counters aren't hot (unlike memory.stat which is per-page, so it does it
at read time), and it makes sense to bundle this with the file
notifications.
After this patch, events are propagated up the hierarchy:
[root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events
low 0
high 0
max 0
oom 0
oom_kill 0
[root@ktst ~]# systemd-run -p MemoryMax=1 true
Running as unit: run-r251162a189fb4562b9dabfdc9b0422f5.service
[root@ktst ~]# cat /sys/fs/cgroup/system.slice/memory.events
low 0
high 0
max 7
oom 1
oom_kill 1
As this is a change in behaviour, this can be reverted to the old
behaviour by mounting with the `memory_localevents' flag set. However, we
use the new behaviour by default as there's a lack of evidence that there
are any current users of memory.events that would find this change
undesirable.
akpm: this is a behaviour change, so Cc:stable. THis is so that
forthcoming distros which use cgroup v2 are more likely to pick up the
revised behaviour.
Link: http://lkml.kernel.org/r/20190208224419.GA24772@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
CSS_TASK_ITER_PROCS currently iterates live group leaders; however,
this means that a process with dying leader and live threads will be
skipped. IOW, cgroup.procs might be empty while cgroup.threads isn't,
which is confusing to say the least.
Fix it by making cset track dying tasks and include dying leaders with
live threads in PROCS iteration.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-and-tested-by: Topi Miettinen <toiwoton@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cgroup v1 implements the freezer controller, which provides an ability
to stop the workload in a cgroup and temporarily free up some
resources (cpu, io, network bandwidth and, potentially, memory)
for some other tasks. Cgroup v2 lacks this functionality.
This patch implements freezer for cgroup v2.
Cgroup v2 freezer tries to put tasks into a state similar to jobctl
stop. This means that tasks can be killed, ptraced (using
PTRACE_SEIZE*), and interrupted. It is possible to attach to
a frozen task, get some information (e.g. read registers) and detach.
It's also possible to migrate a frozen tasks to another cgroup.
This differs cgroup v2 freezer from cgroup v1 freezer, which mostly
tried to imitate the system-wide freezer. However uninterruptible
sleep is fine when all tasks are going to be frozen (hibernation case),
it's not the acceptable state for some subset of the system.
Cgroup v2 freezer is not supporting freezing kthreads.
If a non-root cgroup contains kthread, the cgroup still can be frozen,
but the kthread will remain running, the cgroup will be shown
as non-frozen, and the notification will not be delivered.
* PTRACE_ATTACH is not working because non-fatal signal delivery
is blocked in frozen state.
There are some interface differences between cgroup v1 and cgroup v2
freezer too, which are required to conform the cgroup v2 interface
design principles:
1) There is no separate controller, which has to be turned on:
the functionality is always available and is represented by
cgroup.freeze and cgroup.events cgroup control files.
2) The desired state is defined by the cgroup.freeze control file.
Any hierarchical configuration is allowed.
3) The interface is asynchronous. The actual state is available
using cgroup.events control file ("frozen" field). There are no
dedicated transitional states.
4) It's allowed to make any changes with the cgroup hierarchy
(create new cgroups, remove old cgroups, move tasks between cgroups)
no matter if some cgroups are frozen.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
No-objection-from-me-by: Oleg Nesterov <oleg@redhat.com>
Cc: kernel-team@fb.com
The number of descendant cgroups and the number of dying
descendant cgroups are currently synchronized using the cgroup_mutex.
The number of descendant cgroups will be required by the cgroup v2
freezer, which will use it to determine if a cgroup is frozen
(depending on total number of descendants and number of frozen
descendants). It's not always acceptable to grab the cgroup_mutex,
especially from quite hot paths (e.g. exit()).
To avoid this, let's additionally synchronize these counters using
the css_set_lock.
So, it's safe to read these counters with either cgroup_mutex or
css_set_lock locked, and for changing both locks should be acquired.
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: kernel-team@fb.com
Cgroup has a standardized poll/notification mechanism for waking all
pollers on all fds when a filesystem node changes. To allow polling for
custom events, add a .poll callback that can override the default.
This is in preparation for pollable cgroup pressure files which have
per-fd trigger configurations.
Link: http://lkml.kernel.org/r/20190124211518.244221-3-surenb@google.com
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The only user of cgroup_subsys->free() callback is pids_cgrp_subsys which
needs pids_free() to uncharge the pid.
However, ->free() is called from __put_task_struct()->cgroup_free() and this
is too late. Even the trivial program which does
for (;;) {
int pid = fork();
assert(pid >= 0);
if (pid)
wait(NULL);
else
exit(0);
}
can run out of limits because release_task()->call_rcu(delayed_put_task_struct)
implies an RCU gp after the task/pid goes away and before the final put().
Test-case:
mkdir -p /tmp/CG
mount -t cgroup2 none /tmp/CG
echo '+pids' > /tmp/CG/cgroup.subtree_control
mkdir /tmp/CG/PID
echo 2 > /tmp/CG/PID/pids.max
perl -e 'while ($p = fork) { wait; } $p // die "fork failed: $!\n"' &
echo $! > /tmp/CG/PID/cgroup.procs
Without this patch the forking process fails soon after migration.
Rename cgroup_subsys->free() to cgroup_subsys->release() and move the callsite
into the new helper, cgroup_release(), called by release_task() which actually
frees the pid(s).
Reported-by: Herton R. Krzesinski <hkrzesin@redhat.com>
Reported-by: Jan Stancek <jstancek@redhat.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
For debugging purpose, it will be useful to expose the content of the
subparts_cpus as a read-only file to see if the code work correctly.
However, subparts_cpus will not be used at all in most use cases. So
adding a new cpuset file that clutters the cgroup directory may not be
desirable. This is now being done by using the hidden "cgroup_debug"
kernel command line option to expose a new "cpuset.cpus.subpartitions"
file.
That option was originally used by the debug controller to expose
itself when configured into the kernel. This is now extended to set an
internal flag used by cgroup_addrm_files(). A new CFTYPE_DEBUG flag
can now be used to specify that a cgroup file should only be created
when the "cgroup_debug" option is specified.
Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
On a system that executes multiple cgrouped jobs and independent
workloads, we don't just care about the health of the overall system, but
also that of individual jobs, so that we can ensure individual job health,
fairness between jobs, or prioritize some jobs over others.
This patch implements pressure stall tracking for cgroups. In kernels
with CONFIG_PSI=y, cgroup2 groups will have cpu.pressure, memory.pressure,
and io.pressure files that track aggregate pressure stall times for only
the tasks inside the cgroup.
Link: http://lkml.kernel.org/r/20180828172258.3185-10-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Drake <drake@endlessm.com>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Enderborg <peter.enderborg@sony.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A cgroup which is already a threaded domain may be converted into a
threaded cgroup if the prerequisite conditions are met. When this
happens, all threaded descendant should also have their ->dom_cgrp
updated to the new threaded domain cgroup. Unfortunately, this
propagation was missing leading to the following failure.
# cd /sys/fs/cgroup/unified
# cat cgroup.subtree_control # show that no controllers are enabled
# mkdir -p mycgrp/a/b/c
# echo threaded > mycgrp/a/b/cgroup.type
At this point, the hierarchy looks as follows:
mycgrp [d]
a [dt]
b [t]
c [inv]
Now let's make node "a" threaded (and thus "mycgrp" s made "domain threaded"):
# echo threaded > mycgrp/a/cgroup.type
By this point, we now have a hierarchy that looks as follows:
mycgrp [dt]
a [t]
b [t]
c [inv]
But, when we try to convert the node "c" from "domain invalid" to
"threaded", we get ENOTSUP on the write():
# echo threaded > mycgrp/a/b/c/cgroup.type
sh: echo: write error: Operation not supported
This patch fixes the problem by
* Moving the opencoded ->dom_cgrp save and restoration in
cgroup_enable_threaded() into cgroup_{save|restore}_control() so
that mulitple cgroups can be handled.
* Updating all threaded descendants' ->dom_cgrp to point to the new
dom_cgrp when enabling threaded mode.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-and-tested-by: "Michael Kerrisk (man-pages)" <mtk.manpages@gmail.com>
Reported-by: Amin Jamali <ajamali@pivotal.io>
Reported-by: Joao De Almeida Pereira <jpereira@pivotal.io>
Link: https://lore.kernel.org/r/CAKgNAkhHYCMn74TCNiMJ=ccLd7DcmXSbvw3CbZ1YREeG7iJM5g@mail.gmail.com
Fixes: 454000adaa ("cgroup: introduce cgroup->dom_cgrp and threaded css_set handling")
Cc: stable@vger.kernel.org # v4.14+
Since IO can be issued from literally anywhere it's almost impossible to
do throttling without having some sort of adverse effect somewhere else
in the system because of locking or other dependencies. The best way to
solve this is to do the throttling when we know we aren't holding any
other kernel resources. Do this by tracking throttling in a per-blkg
basis, and if we require throttling flag the task that it needs to check
before it returns to user space and possibly sleep there.
This is to address the case where a process is doing work that is
generating IO that can't be throttled, whether that is directly with a
lot of REQ_META IO, or indirectly by allocating so much memory that it
is swamping the disk with REQ_SWAP. We can't use task_add_work as we
don't want to induce a memory allocation in the IO path, so simply
saving the request queue in the task and flagging it to do the
notify_resume thing achieves the same result without the overhead of a
memory allocation.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This patch adds cgroup_subsys->css_rstat_flush(). If a subsystem has
this callback, its csses are linked on cgrp->css_rstat_list and rstat
will call the function whenever the associated cgroup is flushed.
Flush is also performed when such csses are released so that residual
counts aren't lost.
Combined with the rstat API previous patches factored out, this allows
controllers to plug into rstat to manage their statistics in a
scalable way.
Signed-off-by: Tejun Heo <tj@kernel.org>
Base resource stat accounts universial (not specific to any
controller) resource consumptions on top of rstat. Currently, its
implementation is intermixed with rstat implementation making the code
confusing to follow.
This patch clarifies the distintion by doing the followings.
* Encapsulate base resource stat counters, currently only cputime, in
struct cgroup_base_stat.
* Move prev_cputime into struct cgroup and initialize it with cgroup.
* Rename the related functions so that they start with cgroup_base_stat.
* Prefix the related variables and field names with b.
This patch doesn't make any functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
stat is too generic a name and ends up causing subtle confusions.
It'll be made generic so that controllers can plug into it, which will
make the problem worse. Let's rename it to something more specific -
cgroup_rstat for cgroup recursive stat.
This patch does the following renames. No other changes.
* cpu_stat -> rstat_cpu
* stat -> rstat
* ?cstat -> ?rstatc
Note that the renames are selective. The unrenamed are the ones which
implement basic resource statistics on top of rstat. This will be
further cleaned up in the following patches.
Signed-off-by: Tejun Heo <tj@kernel.org>
".events" files generate file modified event to notify userland of
possible new events. Some of the events can be quite bursty
(e.g. memory high event) and generating notification each time is
costly and pointless.
This patch implements a event rate limit mechanism. If a new
notification is requested before 10ms has passed since the previous
notification, the new notification is delayed till then.
As this only delays from the second notification on in a given close
cluster of notifications, userland reactions to notifications
shouldn't be delayed at all in most cases while avoiding notification
storms.
Signed-off-by: Tejun Heo <tj@kernel.org>
Pull workqueue updates from Tejun Heo:
"rcu_work addition and a couple trivial changes"
* 'for-4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
workqueue: remove the comment about the old manager_arb mutex
workqueue: fix the comments of nr_idle
fs/aio: Use rcu_work instead of explicit rcu and work item
cgroup: Use rcu_work instead of explicit rcu and work item
RCU, workqueue: Implement rcu_work
Linus Torvalds