diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-16 17:25:49 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-16 17:25:49 -0700 |
commit | 7e67a859997aad47727aff9c5a32e160da079ce3 (patch) | |
tree | 96f53425c2834de5b3276d7598782ab6412e4d5e /kernel/sched/topology.c | |
parent | 772c1d06bd402f7ee72c61a18c2db74cd74b6758 (diff) | |
parent | 563c4f85f9f0d63b712081d5b4522152cdcb8b6b (diff) |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- MAINTAINERS: Add Mark Rutland as perf submaintainer, Juri Lelli and
Vincent Guittot as scheduler submaintainers. Add Dietmar Eggemann,
Steven Rostedt, Ben Segall and Mel Gorman as scheduler reviewers.
As perf and the scheduler is getting bigger and more complex,
document the status quo of current responsibilities and interests,
and spread the review pain^H^H^H^H fun via an increase in the Cc:
linecount generated by scripts/get_maintainer.pl. :-)
- Add another series of patches that brings the -rt (PREEMPT_RT) tree
closer to mainline: split the monolithic CONFIG_PREEMPT dependencies
into a new CONFIG_PREEMPTION category that will allow the eventual
introduction of CONFIG_PREEMPT_RT. Still a few more hundred patches
to go though.
- Extend the CPU cgroup controller with uclamp.min and uclamp.max to
allow the finer shaping of CPU bandwidth usage.
- Micro-optimize energy-aware wake-ups from O(CPUS^2) to O(CPUS).
- Improve the behavior of high CPU count, high thread count
applications running under cpu.cfs_quota_us constraints.
- Improve balancing with SCHED_IDLE (SCHED_BATCH) tasks present.
- Improve CPU isolation housekeeping CPU allocation NUMA locality.
- Fix deadline scheduler bandwidth calculations and logic when cpusets
rebuilds the topology, or when it gets deadline-throttled while it's
being offlined.
- Convert the cpuset_mutex to percpu_rwsem, to allow it to be used from
setscheduler() system calls without creating global serialization.
Add new synchronization between cpuset topology-changing events and
the deadline acceptance tests in setscheduler(), which were broken
before.
- Rework the active_mm state machine to be less confusing and more
optimal.
- Rework (simplify) the pick_next_task() slowpath.
- Improve load-balancing on AMD EPYC systems.
- ... and misc cleanups, smaller fixes and improvements - please see
the Git log for more details.
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
sched/psi: Correct overly pessimistic size calculation
sched/fair: Speed-up energy-aware wake-ups
sched/uclamp: Always use 'enum uclamp_id' for clamp_id values
sched/uclamp: Update CPU's refcount on TG's clamp changes
sched/uclamp: Use TG's clamps to restrict TASK's clamps
sched/uclamp: Propagate system defaults to the root group
sched/uclamp: Propagate parent clamps
sched/uclamp: Extend CPU's cgroup controller
sched/topology: Improve load balancing on AMD EPYC systems
arch, ia64: Make NUMA select SMP
sched, perf: MAINTAINERS update, add submaintainers and reviewers
sched/fair: Use rq_lock/unlock in online_fair_sched_group
cpufreq: schedutil: fix equation in comment
sched: Rework pick_next_task() slow-path
sched: Allow put_prev_task() to drop rq->lock
sched/fair: Expose newidle_balance()
sched: Add task_struct pointer to sched_class::set_curr_task
sched: Rework CPU hotplug task selection
sched/{rt,deadline}: Fix set_next_task vs pick_next_task
sched: Fix kerneldoc comment for ia64_set_curr_task
...
Diffstat (limited to 'kernel/sched/topology.c')
-rw-r--r-- | kernel/sched/topology.c | 53 |
1 files changed, 47 insertions, 6 deletions
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index f751ce0b783e..b5667a273bf6 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1284,6 +1284,7 @@ static int sched_domains_curr_level; int sched_max_numa_distance; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; +int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; #endif /* @@ -1402,7 +1403,7 @@ sd_init(struct sched_domain_topology_level *tl, sd->flags &= ~SD_PREFER_SIBLING; sd->flags |= SD_SERIALIZE; - if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + if (sched_domains_numa_distance[tl->numa_level] > node_reclaim_distance) { sd->flags &= ~(SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE); @@ -1724,6 +1725,26 @@ void sched_domains_numa_masks_clear(unsigned int cpu) } } +/* + * sched_numa_find_closest() - given the NUMA topology, find the cpu + * closest to @cpu from @cpumask. + * cpumask: cpumask to find a cpu from + * cpu: cpu to be close to + * + * returns: cpu, or nr_cpu_ids when nothing found. + */ +int sched_numa_find_closest(const struct cpumask *cpus, int cpu) +{ + int i, j = cpu_to_node(cpu); + + for (i = 0; i < sched_domains_numa_levels; i++) { + cpu = cpumask_any_and(cpus, sched_domains_numa_masks[i][j]); + if (cpu < nr_cpu_ids) + return cpu; + } + return nr_cpu_ids; +} + #endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) @@ -2149,16 +2170,16 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * ndoms_new == 0 is a special case for destroying existing domains, * and it will not create the default domain. * - * Call with hotplug lock held + * Call with hotplug lock and sched_domains_mutex held */ -void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new) +void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) { bool __maybe_unused has_eas = false; int i, j, n; int new_topology; - mutex_lock(&sched_domains_mutex); + lockdep_assert_held(&sched_domains_mutex); /* Always unregister in case we don't destroy any domains: */ unregister_sched_domain_sysctl(); @@ -2183,8 +2204,19 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], for (i = 0; i < ndoms_cur; i++) { for (j = 0; j < n && !new_topology; j++) { if (cpumask_equal(doms_cur[i], doms_new[j]) && - dattrs_equal(dattr_cur, i, dattr_new, j)) + dattrs_equal(dattr_cur, i, dattr_new, j)) { + struct root_domain *rd; + + /* + * This domain won't be destroyed and as such + * its dl_bw->total_bw needs to be cleared. It + * will be recomputed in function + * update_tasks_root_domain(). + */ + rd = cpu_rq(cpumask_any(doms_cur[i]))->rd; + dl_clear_root_domain(rd); goto match1; + } } /* No match - a current sched domain not in new doms_new[] */ detach_destroy_domains(doms_cur[i]); @@ -2241,6 +2273,15 @@ match3: ndoms_cur = ndoms_new; register_sched_domain_sysctl(); +} +/* + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + mutex_lock(&sched_domains_mutex); + partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); mutex_unlock(&sched_domains_mutex); } |