linux/kernel/cgroup/rstat.c, branch v6.0

sched/core: add forced idle accounting for cgroups

2022-07-04T07:23:07Z

4feee7d1260 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 Signed-off-by: Peter Zijlstra (Intel) Acked-by: Tejun Heo Link: https://lkml.kernel.org/r/20220629211426.3329954-1-joshdon@google.com

Merge branch 'akpm' (patches from Andrew)

2022-03-24T21:14:07Z

Merge more updates from Andrew Morton: "Various misc subsystems, before getting into the post-linux-next material. 41 patches. Subsystems affected by this patch series: procfs, misc, core-kernel, lib, checkpatch, init, pipe, minix, fat, cgroups, kexec, kdump, taskstats, panic, kcov, resource, and ubsan" * emailed patches from Andrew Morton : (41 commits) Revert "ubsan, kcsan: Don't combine sanitizer with kcov on clang" kernel/resource: fix kfree() of bootmem memory again kcov: properly handle subsequent mmap calls kcov: split ioctl handling into locked and unlocked parts panic: move panic_print before kmsg dumpers panic: add option to dump all CPUs backtraces in panic_print docs: sysctl/kernel: add missing bit to panic_print taskstats: remove unneeded dead assignment kasan: no need to unset panic_on_warn in end_report() ubsan: no need to unset panic_on_warn in ubsan_epilogue() panic: unset panic_on_warn inside panic() docs: kdump: add scp example to write out the dump file docs: kdump: update description about sysfs file system support arm64: mm: use IS_ENABLED(CONFIG_KEXEC_CORE) instead of #ifdef x86/setup: use IS_ENABLED(CONFIG_KEXEC_CORE) instead of #ifdef riscv: mm: init: use IS_ENABLED(CONFIG_KEXEC_CORE) instead of #ifdef kexec: make crashk_res, crashk_low_res and crash_notes symbols always visible cgroup: use irqsave in cgroup_rstat_flush_locked(). fat: use pointer to simple type in put_user() minix: fix bug when opening a file with O_DIRECT ...

cgroup: use irqsave in cgroup_rstat_flush_locked().

2022-03-24T02:00:34Z

All callers of cgroup_rstat_flush_locked() acquire cgroup_rstat_lock either with spin_lock_irq() or spin_lock_irqsave(). cgroup_rstat_flush_locked() itself acquires cgroup_rstat_cpu_lock which is a raw_spin_lock. This lock is also acquired in cgroup_rstat_updated() in IRQ context and therefore requires _irqsave() locking suffix in cgroup_rstat_flush_locked(). Since there is no difference between spin_lock_t and raw_spin_lock_t on !RT lockdep does not complain here. On RT lockdep complains because the interrupts were not disabled here and a deadlock is possible. Acquire the raw_spin_lock_t with disabled interrupts. Link: https://lkml.kernel.org/r/20220301122143.1521823-2-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Acked-by: Tejun Heo Cc: Johannes Weiner Cc: Thomas Gleixner Cc: Zefan Li From: Sebastian Andrzej Siewior Subject: cgroup: add a comment to cgroup_rstat_flush_locked(). Add a comment why spin_lock_irq() -> raw_spin_lock_irqsave() is needed. Link: https://lkml.kernel.org/r/Yh+DOK73hfVV5ThX@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Acked-by: Tejun Heo Cc: Johannes Weiner Cc: Thomas Gleixner Cc: Zefan Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds

cgroup: rstat: retrieve current bstat to delta directly

2022-01-12T19:55:12Z

Instead of retrieve current bstat to cur and copy it to delta, let's use delta directly. This saves one copy operation and has the same code convention as propagating delta to parent. Signed-off-by: Wei Yang Signed-off-by: Tejun Heo

cgroup: rstat: use same convention to assign cgroup_base_stat

2022-01-12T19:55:02Z

In function cgroup_base_stat_flush(), we update cgroup_base_stat by getting rstatc->bstat and adjust delta to related fields. There are two convention to assign cgroup_base_stat in this function: * rstat2 = rstat1 * rstat2.cputime = rstat1.cputime The second convention may make audience think just field "cputime" is updated, while cputime is the only field in cgroup_base_stat. Let's use the same convention to eliminate this confusion. Signed-off-by: Wei Yang Signed-off-by: Tejun Heo

cgroup/rstat: check updated_next only for root

2022-01-06T21:50:34Z

After commit dc26532aed0a ("cgroup: rstat: punt root-level optimization to individual controllers"), each rstat on updated_children list has its ->updated_next not NULL. This means we can remove the check on ->updated_next, if we make sure the subtree from @root is on list, which could be done by checking updated_next for root. tj: Coding style fixes. Signed-off-by: Wei Yang Reviewed-by: Michal Koutný Signed-off-by: Tejun Heo

cgroup: rstat: explicitly put loop variant in while

2022-01-06T21:10:06Z

Instead of do while unconditionally, let's put the loop variant in while. Signed-off-by: Wei Yang Reviewed-by: Michal Koutný Signed-off-by: Tejun Heo

cgroup: rstat: Mark benign data race to silence KCSAN

2021-11-15T21:34:17Z

There is a race between updaters and flushers (flush can possibly miss the latest update(s)). This is expected as explained in cgroup_rstat_updated() comment, add also machine readable annotation so that KCSAN results aren't noisy. Reported-by: Hao Sun Link: https://lore.kernel.org/r/CACkBjsbPVdkub=e-E-p1WBOLxS515ith-53SFdmFHWV_QMo40w@mail.gmail.com Suggested-by: Hao Sun Signed-off-by: Michal Koutný Reviewed-by: Shakeel Butt Signed-off-by: Tejun Heo

cgroup: Fix rootcg cpu.stat guest double counting

2021-11-01T16:47:08Z

In account_guest_time in kernel/sched/cputime.c guest time is attributed to both CPUTIME_NICE and CPUTIME_USER in addition to CPUTIME_GUEST_NICE and CPUTIME_GUEST respectively. Therefore, adding both to calculate usage results in double counting any guest time at the rootcg. Fixes: 936f2a70f207 ("cgroup: add cpu.stat file to root cgroup") Signed-off-by: Dan Schatzberg Signed-off-by: Tejun Heo

cgroup: rstat: fix A-A deadlock on 32bit around u64_stats_sync

2021-07-27T23:12:20Z

0fa294fb1985 ("cgroup: Replace cgroup_rstat_mutex with a spinlock") added cgroup_rstat_flush_irqsafe() allowing flushing to happen from the irq context. However, rstat paths use u64_stats_sync to synchronize access to 64bit stat counters on 32bit machines. u64_stats_sync is implemented using seq_lock and trying to read from an irq context can lead to A-A deadlock if the irq happens to interrupt the stat update. Fix it by using the irqsafe variants - u64_stats_update_begin_irqsave() and u64_stats_update_end_irqrestore() - in the update paths. Note that none of this matters on 64bit machines. All these are just for 32bit SMP setups. Note that the interface was introduced way back, its first and currently only use was recently added by 2d146aa3aa84 ("mm: memcontrol: switch to rstat"). Stable tagging targets this commit. Signed-off-by: Tejun Heo Reported-by: Rik van Riel Fixes: 2d146aa3aa84 ("mm: memcontrol: switch to rstat") Cc: stable@vger.kernel.org # v5.13+