From: Tejun Heo tj@kernel.org
stable inclusion from stable-v6.6.7 commit b2c562a7a88b402bfd747b4ddb5ec21b54147de1 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8SSQ4
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
commit 4a6c5607d4502ccd1b15b57d57f17d12b6f257a7 upstream.
During boot, depending on how the housekeeping and workqueue.unbound_cpus masks are set, wq_unbound_cpumask can end up empty. Since 8639ecebc9b1 ("workqueue: Implement non-strict affinity scope for unbound workqueues"), this may end up feeding -1 as a CPU number into scheduler leading to oopses.
BUG: unable to handle page fault for address: ffffffff8305e9c0 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page ... Call Trace: <TASK> select_idle_sibling+0x79/0xaf0 select_task_rq_fair+0x1cb/0x7b0 try_to_wake_up+0x29c/0x5c0 wake_up_process+0x19/0x20 kick_pool+0x5e/0xb0 __queue_work+0x119/0x430 queue_work_on+0x29/0x30 ...
An empty wq_unbound_cpumask is a clear misconfiguration and already disallowed once system is booted up. Let's warn on and ignore unbound_cpumask restrictions which lead to no unbound cpus. While at it, also remove now unncessary empty check on wq_unbound_cpumask in wq_select_unbound_cpu().
Signed-off-by: Tejun Heo tj@kernel.org Reported-and-Tested-by: Yong He alexyonghe@tencent.com Link: http://lkml.kernel.org/r/20231120121623.119780-1-alexyonghe@tencent.com Fixes: 8639ecebc9b1 ("workqueue: Implement non-strict affinity scope for unbound workqueues") Cc: stable@vger.kernel.org # v6.6+ Reviewed-by: Waiman Long longman@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- kernel/workqueue.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3eabf97c4e9a..1888741f5edd 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1684,9 +1684,6 @@ static int wq_select_unbound_cpu(int cpu) pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n"); }
- if (cpumask_empty(wq_unbound_cpumask)) - return cpu; - new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) { @@ -6518,6 +6515,17 @@ static inline void wq_watchdog_init(void) { }
#endif /* CONFIG_WQ_WATCHDOG */
+static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) +{ + if (!cpumask_intersects(wq_unbound_cpumask, mask)) { + pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n", + cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask)); + return; + } + + cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask); +} + /** * workqueue_init_early - early init for workqueue subsystem * @@ -6537,11 +6545,11 @@ void __init workqueue_init_early(void) BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); - cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ)); - cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN)); - + cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); + restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ)); + restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN)); if (!cpumask_empty(&wq_cmdline_cpumask)) - cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, &wq_cmdline_cpumask); + restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask);
pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);