Re: [PATCH v2 3/8] sched/deadline: Generalize unique visiting of root domains

[Shrikanth Hegde <sshegde@linux.ibm.com>]

On 3/6/25 19:40, Juri Lelli wrote:
> Bandwidth checks and updates that work on root domains currently employ
> a cookie mechanism for efficiency. This mechanism is very much tied to
> when root domains are first created and initialized.
> 
> Generalize the cookie mechanism so that it can be used also later at
> runtime while updating root domains. Also, additionally guard it with
> sched_domains_mutex, since domains need to be stable while updating them
> (and it will be required for further dynamic changes).
> 
> Reported-by: Jon Hunter <jonathanh@nvidia.com>
> Fixes: 53916d5fd3c0 ("sched/deadline: Check bandwidth overflow earlier for hotplug")
> Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
> ---
>   include/linux/sched/deadline.h |  3 +++
>   kernel/sched/deadline.c        | 23 +++++++++++++----------
>   kernel/sched/rt.c              |  2 ++
>   kernel/sched/sched.h           |  2 +-
>   kernel/sched/topology.c        |  2 +-
>   5 files changed, 20 insertions(+), 12 deletions(-)
> 
> diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
> index 3a912ab42bb5..6ec578600b24 100644
> --- a/include/linux/sched/deadline.h
> +++ b/include/linux/sched/deadline.h
> @@ -37,4 +37,7 @@ extern void dl_clear_root_domain(struct root_domain *rd);
>   
>   #endif /* CONFIG_SMP */
>   
> +extern u64 dl_cookie;
> +extern bool dl_bw_visited(int cpu, u64 cookie);
> +
>   #endif /* _LINUX_SCHED_DEADLINE_H */
> diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
> index ab565a151355..339434271cba 100644
> --- a/kernel/sched/deadline.c
> +++ b/kernel/sched/deadline.c
> @@ -166,14 +166,14 @@ static inline unsigned long dl_bw_capacity(int i)
>   	}
>   }
>   
> -static inline bool dl_bw_visited(int cpu, u64 gen)
> +static inline bool dl_bw_visited(int cpu, u64 cookie)
>   {
>   	struct root_domain *rd = cpu_rq(cpu)->rd;
>   
> -	if (rd->visit_gen == gen)
> +	if (rd->visit_cookie == cookie)
>   		return true;
>   
> -	rd->visit_gen = gen;
> +	rd->visit_cookie = cookie;
>   	return false;
>   }
>   
> @@ -207,7 +207,7 @@ static inline unsigned long dl_bw_capacity(int i)
>   	return SCHED_CAPACITY_SCALE;
>   }
>   
> -static inline bool dl_bw_visited(int cpu, u64 gen)
> +static inline bool dl_bw_visited(int cpu, u64 cookie)
>   {
>   	return false;
>   }
> @@ -3171,15 +3171,18 @@ DEFINE_SCHED_CLASS(dl) = {
>   #endif
>   };
>   
> -/* Used for dl_bw check and update, used under sched_rt_handler()::mutex */
> -static u64 dl_generation;
> +/*
> + * Used for dl_bw check and update, used under sched_rt_handler()::mutex and
> + * sched_domains_mutex.
> + */
> +u64 dl_cookie;
>   
>   int sched_dl_global_validate(void)
>   {
>   	u64 runtime = global_rt_runtime();
>   	u64 period = global_rt_period();
>   	u64 new_bw = to_ratio(period, runtime);
> -	u64 gen = ++dl_generation;
> +	u64 cookie = ++dl_cookie;
>   	struct dl_bw *dl_b;
>   	int cpu, cpus, ret = 0;
>   	unsigned long flags;
> @@ -3192,7 +3195,7 @@ int sched_dl_global_validate(void)
>   	for_each_possible_cpu(cpu) {

This has been changed in 14672f059d83f591afb2ee1fff56858efe055e5a to 
online CPUs. So patch didn't apply cleanly to me.

>   		rcu_read_lock_sched();
>   
> -		if (dl_bw_visited(cpu, gen))
> +		if (dl_bw_visited(cpu, cookie))
>   			goto next;
>   
>   		dl_b = dl_bw_of(cpu);
> @@ -3229,7 +3232,7 @@ static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
>   void sched_dl_do_global(void)
>   {
>   	u64 new_bw = -1;
> -	u64 gen = ++dl_generation;
> +	u64 cookie = ++dl_cookie;
>   	struct dl_bw *dl_b;
>   	int cpu;
>   	unsigned long flags;
> @@ -3240,7 +3243,7 @@ void sched_dl_do_global(void)
>   	for_each_possible_cpu(cpu) {
>   		rcu_read_lock_sched();
>   
> -		if (dl_bw_visited(cpu, gen)) {
> +		if (dl_bw_visited(cpu, cookie)) {
>   			rcu_read_unlock_sched();
>   			continue;
>   		}
> diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
> index 4b8e33c615b1..8cebe71d2bb1 100644
> --- a/kernel/sched/rt.c
> +++ b/kernel/sched/rt.c
> @@ -2910,6 +2910,7 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff
>   	int ret;
>   
>   	mutex_lock(&mutex);
> +	sched_domains_mutex_lock();
>   	old_period = sysctl_sched_rt_period;
>   	old_runtime = sysctl_sched_rt_runtime;
>   
> @@ -2936,6 +2937,7 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff
>   		sysctl_sched_rt_period = old_period;
>   		sysctl_sched_rt_runtime = old_runtime;
>   	}
> +	sched_domains_mutex_unlock();
>   	mutex_unlock(&mutex);
>   
>   	return ret;
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index c8512a9fb022..c978abe38c07 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -998,7 +998,7 @@ struct root_domain {
>   	 * Also, some corner cases, like 'wrap around' is dangerous, but given
>   	 * that u64 is 'big enough'. So that shouldn't be a concern.
>   	 */
> -	u64 visit_gen;
> +	u64 visit_cookie;
>   
>   #ifdef HAVE_RT_PUSH_IPI
>   	/*
> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
> index 296ff2acfd32..44093339761c 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -568,7 +568,7 @@ static int init_rootdomain(struct root_domain *rd)
>   	rd->rto_push_work = IRQ_WORK_INIT_HARD(rto_push_irq_work_func);
>   #endif
>   
> -	rd->visit_gen = 0;
> +	rd->visit_cookie = 0;
>   	init_dl_bw(&rd->dl_bw);
>   	if (cpudl_init(&rd->cpudl) != 0)
>   		goto free_rto_mask;