From: Lai Jiangshan <la...@linux.alibaba.com> When worker_attach_to_pool() is called, we should not put the workers to pool->attrs->cpumask when there is not CPU online in it.
We have to use wq_online_cpumask in worker_attach_to_pool() to check if pool->attrs->cpumask is valid rather than cpu_online_mask or cpu_active_mask due to gaps between stages in cpu hot[un]plug. So for that late-spawned per-CPU kworker case: the outgoing CPU should have already been cleared from wq_online_cpumask, so it gets its affinity reset to the possible mask and the subsequent wakeup will ensure it's put on an active CPU. To use wq_online_cpumask in worker_attach_to_pool(), we need to protect wq_online_cpumask in wq_pool_attach_mutex and we modify workqueue_online_cpu() and workqueue_offline_cpu() to enlarge wq_pool_attach_mutex protected region. We also put updating wq_online_cpumask and [re|un]bind_workers() in the same wq_pool_attach_mutex protected region to make the update for percpu workqueue atomically. Cc: Qian Cai <c...@redhat.com> Cc: Peter Zijlstra <pet...@infradead.org> Cc: Vincent Donnefort <vincent.donnef...@arm.com> Link: https://lore.kernel.org/lkml/20201210163830.21514-3-valentin.schnei...@arm.com/ Reviewed-by: Valentin Schneider <valentin.schnei...@arm.com> Acked-by: Tejun Heo <t...@kernel.org> Signed-off-by: Lai Jiangshan <la...@linux.alibaba.com> --- kernel/workqueue.c | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index dd32398edf55..25d50050257c 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -310,7 +310,7 @@ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; -/* PL: online cpus (cpu_online_mask with the going-down cpu cleared) */ +/* PL&A: online cpus (cpu_online_mask with the going-down cpu cleared) */ static cpumask_var_t wq_online_cpumask; /* CPU where unbound work was last round robin scheduled from this CPU */ @@ -1848,11 +1848,11 @@ static void worker_attach_to_pool(struct worker *worker, { mutex_lock(&wq_pool_attach_mutex); - /* - * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any - * online CPUs. It'll be re-applied when any of the CPUs come up. - */ - set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); + /* Is there any cpu in pool->attrs->cpumask online? */ + if (cpumask_intersects(pool->attrs->cpumask, wq_online_cpumask)) + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask) < 0); + else + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains @@ -5082,13 +5082,12 @@ int workqueue_online_cpu(unsigned int cpu) int pi; mutex_lock(&wq_pool_mutex); - cpumask_set_cpu(cpu, wq_online_cpumask); - for_each_cpu_worker_pool(pool, cpu) { - mutex_lock(&wq_pool_attach_mutex); + mutex_lock(&wq_pool_attach_mutex); + cpumask_set_cpu(cpu, wq_online_cpumask); + for_each_cpu_worker_pool(pool, cpu) rebind_workers(pool); - mutex_unlock(&wq_pool_attach_mutex); - } + mutex_unlock(&wq_pool_attach_mutex); /* update CPU affinity of workers of unbound pools */ for_each_pool(pool, pi) { @@ -5118,14 +5117,13 @@ int workqueue_offline_cpu(unsigned int cpu) if (WARN_ON(cpu != smp_processor_id())) return -1; - for_each_cpu_worker_pool(pool, cpu) { - mutex_lock(&wq_pool_attach_mutex); - unbind_workers(pool); - mutex_unlock(&wq_pool_attach_mutex); - } - mutex_lock(&wq_pool_mutex); + + mutex_lock(&wq_pool_attach_mutex); cpumask_clear_cpu(cpu, wq_online_cpumask); + for_each_cpu_worker_pool(pool, cpu) + unbind_workers(pool); + mutex_unlock(&wq_pool_attach_mutex); /* update CPU affinity of workers of unbound pools */ for_each_pool(pool, pi) { -- 2.19.1.6.gb485710b
