From 1726a17135905e2d2773f18d47bd4e17dd26e1ed Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Thu, 4 Jul 2024 11:49:13 +0800 Subject: [PATCH] workqueue: Put PWQ allocation and WQ enlistment in the same lock C.S. The PWQ allocation and WQ enlistment are not within the same lock-held critical section; therefore, their states can become out of sync when the user modifies the unbound mask or if CPU hotplug events occur in the interim since those operations only update the WQs that are already in the list. Make the PWQ allocation and WQ enlistment atomic. Signed-off-by: Lai Jiangshan Signed-off-by: Tejun Heo --- kernel/workqueue.c | 54 ++++++++++++++++++++++++---------------------- 1 file changed, 28 insertions(+), 26 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ab0aca0ccc8f..0c06ffd0174e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5108,6 +5108,19 @@ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, return pwq; } +static void apply_wqattrs_lock(void) +{ + /* CPUs should stay stable across pwq creations and installations */ + cpus_read_lock(); + mutex_lock(&wq_pool_mutex); +} + +static void apply_wqattrs_unlock(void) +{ + mutex_unlock(&wq_pool_mutex); + cpus_read_unlock(); +} + /** * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod * @attrs: the wq_attrs of the default pwq of the target workqueue @@ -5419,6 +5432,9 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; + lockdep_assert_cpus_held(); + lockdep_assert_held(&wq_pool_mutex); + wq->cpu_pwq = alloc_percpu(struct pool_workqueue *); if (!wq->cpu_pwq) goto enomem; @@ -5452,20 +5468,18 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) return 0; } - cpus_read_lock(); if (wq->flags & __WQ_ORDERED) { struct pool_workqueue *dfl_pwq; - ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); + ret = apply_workqueue_attrs_locked(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ dfl_pwq = rcu_access_pointer(wq->dfl_pwq); WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node || wq->pwqs.prev != &dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { - ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); + ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]); } - cpus_read_unlock(); return ret; @@ -5672,15 +5686,15 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, goto err_unreg_lockdep; } - if (alloc_and_link_pwqs(wq) < 0) - goto err_free_node_nr_active; - /* - * wq_pool_mutex protects global freeze state and workqueues list. - * Grab it, adjust max_active and add the new @wq to workqueues - * list. + * wq_pool_mutex protects the workqueues list, allocations of PWQs, + * and the global freeze state. alloc_and_link_pwqs() also requires + * cpus_read_lock() for PWQs' affinities. */ - mutex_lock(&wq_pool_mutex); + apply_wqattrs_lock(); + + if (alloc_and_link_pwqs(wq) < 0) + goto err_unlock_free_node_nr_active; mutex_lock(&wq->mutex); wq_adjust_max_active(wq); @@ -5688,7 +5702,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, list_add_tail_rcu(&wq->list, &workqueues); - mutex_unlock(&wq_pool_mutex); + apply_wqattrs_unlock(); if (wq_online && init_rescuer(wq) < 0) goto err_destroy; @@ -5698,7 +5712,8 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, return wq; -err_free_node_nr_active: +err_unlock_free_node_nr_active: + apply_wqattrs_unlock(); /* * Failed alloc_and_link_pwqs() may leave pending pwq->release_work, * flushing the pwq_release_worker ensures that the pwq_release_workfn() @@ -6987,19 +7002,6 @@ static struct attribute *wq_sysfs_attrs[] = { }; ATTRIBUTE_GROUPS(wq_sysfs); -static void apply_wqattrs_lock(void) -{ - /* CPUs should stay stable across pwq creations and installations */ - cpus_read_lock(); - mutex_lock(&wq_pool_mutex); -} - -static void apply_wqattrs_unlock(void) -{ - mutex_unlock(&wq_pool_mutex); - cpus_read_unlock(); -} - static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) {