| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <33c543f8-97c9-cb18-a2f8-a90b8a5769cc@linux.intel.com>
Date: Tue, 15 Dec 2020 13:35:46 +0800
From: Xing Zhengjun <zhengjun.xing@...ux.intel.com>
To: Peter Zijlstra <peterz@...radead.org>,
kernel test robot <oliver.sang@...el.com>
Cc: Valentin Schneider <valentin.schneider@....com>,
Daniel Bristot de Oliveira <bristot@...hat.com>,
LKML <linux-kernel@...r.kernel.org>, x86@...nel.org,
lkp@...ts.01.org, lkp@...el.com, zhengjun.xing@...el.com,
aubrey.li@...ux.intel.com, yu.c.chen@...el.com
Subject: Re: [LKP] Re: [sched/hotplug] 2558aacff8:
will-it-scale.per_thread_ops -1.6% regression
On 12/11/2020 12:14 AM, Peter Zijlstra wrote:
> On Thu, Dec 10, 2020 at 04:18:59PM +0800, kernel test robot wrote:
>> FYI, we noticed a -1.6% regression of will-it-scale.per_thread_ops due to commit:
>> commit: 2558aacff8586699bcd248b406febb28b0a25de2 ("sched/hotplug: Ensure only per-cpu kthreads run during hotplug")
>
> Mooo, weird but whatever. Does the below help at all?
I test the patch, the regression reduced to -0.6%.
=========================================================================================
tbox_group/testcase/rootfs/kconfig/compiler/nr_task/mode/test/cpufreq_governor/ucode:
lkp-cpl-4sp1/will-it-scale/debian-10.4-x86_64-20200603.cgz/x86_64-rhel-8.3/gcc-9/100%/thread/sched_yield/performance/0x700001e
commit:
565790d28b1e33ee2f77bad5348b99f6dfc366fd
2558aacff8586699bcd248b406febb28b0a25de2
4b26139b8db627a55043183614a32b0aba799d27 (this test patch)
565790d28b1e33ee 2558aacff8586699bcd248b406f 4b26139b8db627a55043183614a
---------------- --------------------------- ---------------------------
%stddev %change %stddev %change %stddev
\ | \ | \
4.011e+08 -1.6% 3.945e+08 -0.6% 3.989e+08
will-it-scale.144.threads
2785455 -1.6% 2739520 -0.6% 2769967
will-it-scale.per_thread_ops
4.011e+08 -1.6% 3.945e+08 -0.6% 3.989e+08
will-it-scale.workload
>
> ---
> kernel/sched/core.c | 40 +++++++++++++++-------------------------
> kernel/sched/sched.h | 13 +++++--------
> 2 files changed, 20 insertions(+), 33 deletions(-)
>
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 7af80c3fce12..f80245c7f903 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -3985,15 +3985,20 @@ static void do_balance_callbacks(struct rq *rq, struct callback_head *head)
> }
> }
>
> +static void balance_push(struct rq *rq);
> +
> +struct callback_head balance_push_callback = {
> + .next = NULL,
> + .func = (void (*)(struct callback_head *))balance_push,
> +};
> +
> static inline struct callback_head *splice_balance_callbacks(struct rq *rq)
> {
> struct callback_head *head = rq->balance_callback;
>
> lockdep_assert_held(&rq->lock);
> - if (head) {
> + if (head)
> rq->balance_callback = NULL;
> - rq->balance_flags &= ~BALANCE_WORK;
> - }
>
> return head;
> }
> @@ -4014,21 +4019,6 @@ static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
> }
> }
>
> -static void balance_push(struct rq *rq);
> -
> -static inline void balance_switch(struct rq *rq)
> -{
> - if (likely(!rq->balance_flags))
> - return;
> -
> - if (rq->balance_flags & BALANCE_PUSH) {
> - balance_push(rq);
> - return;
> - }
> -
> - __balance_callbacks(rq);
> -}
> -
> #else
>
> static inline void __balance_callbacks(struct rq *rq)
> @@ -4044,10 +4034,6 @@ static inline void balance_callbacks(struct rq *rq, struct callback_head *head)
> {
> }
>
> -static inline void balance_switch(struct rq *rq)
> -{
> -}
> -
> #endif
>
> static inline void
> @@ -4075,7 +4061,7 @@ static inline void finish_lock_switch(struct rq *rq)
> * prev into current:
> */
> spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
> - balance_switch(rq);
> + __balance_callbacks(rq);
> raw_spin_unlock_irq(&rq->lock);
> }
>
> @@ -7256,6 +7242,10 @@ static void balance_push(struct rq *rq)
>
> lockdep_assert_held(&rq->lock);
> SCHED_WARN_ON(rq->cpu != smp_processor_id());
> + /*
> + * Ensure the thing is persistent until balance_push_set(, on = false);
> + */
> + rq->balance_callback = &balance_push_callback;
>
> /*
> * Both the cpu-hotplug and stop task are in this case and are
> @@ -7305,9 +7295,9 @@ static void balance_push_set(int cpu, bool on)
>
> rq_lock_irqsave(rq, &rf);
> if (on)
> - rq->balance_flags |= BALANCE_PUSH;
> + rq->balance_callback = &balance_push_callback;
> else
> - rq->balance_flags &= ~BALANCE_PUSH;
> + rq->balance_callback = NULL;
> rq_unlock_irqrestore(rq, &rf);
> }
>
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index f5acb6c5ce49..12ada79d40f3 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -975,7 +975,6 @@ struct rq {
> unsigned long cpu_capacity_orig;
>
> struct callback_head *balance_callback;
> - unsigned char balance_flags;
>
> unsigned char nohz_idle_balance;
> unsigned char idle_balance;
> @@ -1226,6 +1225,8 @@ struct rq_flags {
> #endif
> };
>
> +extern struct callback_head balance_push_callback;
> +
> /*
> * Lockdep annotation that avoids accidental unlocks; it's like a
> * sticky/continuous lockdep_assert_held().
> @@ -1243,9 +1244,9 @@ static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
> #ifdef CONFIG_SCHED_DEBUG
> rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
> rf->clock_update_flags = 0;
> -#endif
> #ifdef CONFIG_SMP
> - SCHED_WARN_ON(rq->balance_callback);
> + SCHED_WARN_ON(rq->balance_callback && rq->balance_callback != &balance_push_callback);
> +#endif
> #endif
> }
>
> @@ -1408,9 +1409,6 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
>
> #ifdef CONFIG_SMP
>
> -#define BALANCE_WORK 0x01
> -#define BALANCE_PUSH 0x02
> -
> static inline void
> queue_balance_callback(struct rq *rq,
> struct callback_head *head,
> @@ -1418,13 +1416,12 @@ queue_balance_callback(struct rq *rq,
> {
> lockdep_assert_held(&rq->lock);
>
> - if (unlikely(head->next || (rq->balance_flags & BALANCE_PUSH)))
> + if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
> return;
>
> head->func = (void (*)(struct callback_head *))func;
> head->next = rq->balance_callback;
> rq->balance_callback = head;
> - rq->balance_flags |= BALANCE_WORK;
> }
>
> #define rcu_dereference_check_sched_domain(p) \
> _______________________________________________
> LKP mailing list -- lkp@...ts.01.org
> To unsubscribe send an email to lkp-leave@...ts.01.org
>
--
Zhengjun Xing
Powered by blists - more mailing lists