On Mon, May 23, 2016 at 11:58:44AM +0100, Morten Rasmussen wrote:
> In commit ac66f5477239 ("sched/numa: Introduce migrate_swap()")
> select_task_rq() got a 'cpu' argument to enable overriding of prev_cpu
> in special cases (NUMA task swapping). However, the
> select_task_rq_fair() helper functions: wake_affine() and
> select_idle_sibling(), still use task_cpu(p) directly to work out
> prev_cpu which leads to inconsistencies.
>
> This patch passes prev_cpu (potentially overridden by NUMA code) into
> the helper functions to ensure prev_cpu is indeed the same cpu
> everywhere in the wakeup path.
Rik, can you get this ran through the NUMA benchmarks?
>
> cc: Ingo Molnar <[email protected]>
> cc: Peter Zijlstra <[email protected]>
>
> Signed-off-by: Morten Rasmussen <[email protected]>
> ---
> kernel/sched/fair.c | 24 +++++++++++++-----------
> 1 file changed, 13 insertions(+), 11 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 218f8e8..c49e25a 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -656,7 +656,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct
> sched_entity *se)
> }
>
> #ifdef CONFIG_SMP
> -static int select_idle_sibling(struct task_struct *p, int cpu);
> +static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
> static unsigned long task_h_load(struct task_struct *p);
>
> /*
> @@ -1502,7 +1502,8 @@ static void task_numa_compare(struct task_numa_env *env,
> * Call select_idle_sibling to maybe find a better one.
> */
> if (!cur)
> - env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
> + env->dst_cpu = select_idle_sibling(env->p, env->src_cpu,
> + env->dst_cpu);
>
> assign:
> assigned = true;
> @@ -5013,18 +5014,18 @@ static int wake_wide(struct task_struct *p)
> return 1;
> }
>
> -static int wake_affine(struct sched_domain *sd, struct task_struct *p, int
> sync)
> +static int wake_affine(struct sched_domain *sd, struct task_struct *p,
> + int prev_cpu, int sync)
> {
> s64 this_load, load;
> s64 this_eff_load, prev_eff_load;
> - int idx, this_cpu, prev_cpu;
> + int idx, this_cpu;
> struct task_group *tg;
> unsigned long weight;
> int balanced;
>
> idx = sd->wake_idx;
> this_cpu = smp_processor_id();
> - prev_cpu = task_cpu(p);
> load = source_load(prev_cpu, idx);
> this_load = target_load(this_cpu, idx);
>
> @@ -5189,11 +5190,10 @@ find_idlest_cpu(struct sched_group *group, struct
> task_struct *p, int this_cpu)
> /*
> * Try and locate an idle CPU in the sched_domain.
> */
> -static int select_idle_sibling(struct task_struct *p, int target)
> +static int select_idle_sibling(struct task_struct *p, int prev, int target)
> {
> struct sched_domain *sd;
> struct sched_group *sg;
> - int i = task_cpu(p);
>
> if (idle_cpu(target))
> return target;
> @@ -5201,8 +5201,8 @@ static int select_idle_sibling(struct task_struct *p,
> int target)
> /*
> * If the prevous cpu is cache affine and idle, don't be stupid.
> */
> - if (i != target && cpus_share_cache(i, target) && idle_cpu(i))
> - return i;
> + if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev))
> + return prev;
>
> /*
> * Otherwise, iterate the domains and find an eligible idle cpu.
> @@ -5223,6 +5223,8 @@ static int select_idle_sibling(struct task_struct *p,
> int target)
> for_each_lower_domain(sd) {
> sg = sd->groups;
> do {
> + int i;
> +
> if (!cpumask_intersects(sched_group_cpus(sg),
> tsk_cpus_allowed(p)))
> goto next;
> @@ -5331,13 +5333,13 @@ select_task_rq_fair(struct task_struct *p, int
> prev_cpu, int sd_flag, int wake_f
>
> if (affine_sd) {
> sd = NULL; /* Prefer wake_affine over balance flags */
> - if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
> + if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu,
> sync))
> new_cpu = cpu;
> }
>
> if (!sd) {
> if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
> - new_cpu = select_idle_sibling(p, new_cpu);
> + new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
>
> } else while (sd) {
> struct sched_group *group;
> --
> 1.9.1
>
