From 874bbfe600a660cba9c776b3957b1ce393151b76 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 30 Sep 2015 09:05:30 -0700 Subject: workqueue: make sure delayed work run in local cpu My system keeps crashing with below message. vmstat_update() schedules a delayed work in current cpu and expects the work runs in the cpu. schedule_delayed_work() is expected to make delayed work run in local cpu. The problem is timer can be migrated with NO_HZ. __queue_work() queues work in timer handler, which could run in a different cpu other than where the delayed work is scheduled. The end result is the delayed work runs in different cpu. The patch makes __queue_delayed_work records local cpu earlier. Where the timer runs doesn't change where the work runs with the change. [ 28.010131] ------------[ cut here ]------------ [ 28.010609] kernel BUG at ../mm/vmstat.c:1392! [ 28.011099] invalid opcode: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC KASAN [ 28.011860] Modules linked in: [ 28.012245] CPU: 0 PID: 289 Comm: kworker/0:3 Tainted: G W4.3.0-rc3+ #634 [ 28.013065] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140709_153802- 04/01/2014 [ 28.014160] Workqueue: events vmstat_update [ 28.014571] task: ffff880117682580 ti: ffff8800ba428000 task.ti: ffff8800ba428000 [ 28.015445] RIP: 0010:[] []vmstat_update+0x31/0x80 [ 28.016282] RSP: 0018:ffff8800ba42fd80 EFLAGS: 00010297 [ 28.016812] RAX: 0000000000000000 RBX: ffff88011a858dc0 RCX:0000000000000000 [ 28.017585] RDX: ffff880117682580 RSI: ffffffff81f14d8c RDI:ffffffff81f4df8d [ 28.018366] RBP: ffff8800ba42fd90 R08: 0000000000000001 R09:0000000000000000 [ 28.019169] R10: 0000000000000000 R11: 0000000000000121 R12:ffff8800baa9f640 [ 28.019947] R13: ffff88011a81e340 R14: ffff88011a823700 R15:0000000000000000 [ 28.020071] FS: 0000000000000000(0000) GS:ffff88011a800000(0000)knlGS:0000000000000000 [ 28.020071] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 28.020071] CR2: 00007ff6144b01d0 CR3: 00000000b8e93000 CR4:00000000000006f0 [ 28.020071] Stack: [ 28.020071] ffff88011a858dc0 ffff8800baa9f640 ffff8800ba42fe00ffffffff8106bd88 [ 28.020071] ffffffff8106bd0b 0000000000000096 0000000000000000ffffffff82f9b1e8 [ 28.020071] ffffffff829f0b10 0000000000000000 ffffffff81f18460ffff88011a81e340 [ 28.020071] Call Trace: [ 28.020071] [] process_one_work+0x1c8/0x540 [ 28.020071] [] ? process_one_work+0x14b/0x540 [ 28.020071] [] worker_thread+0x114/0x460 [ 28.020071] [] ? process_one_work+0x540/0x540 [ 28.020071] [] kthread+0xf8/0x110 [ 28.020071] [] ?kthread_create_on_node+0x200/0x200 [ 28.020071] [] ret_from_fork+0x3f/0x70 [ 28.020071] [] ?kthread_create_on_node+0x200/0x200 Signed-off-by: Shaohua Li Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org # v2.6.31+ --- kernel/workqueue.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ca71582fcfab..bcb14cafe007 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1458,13 +1458,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, timer_stats_timer_set_start_info(&dwork->timer); dwork->wq = wq; + /* timer isn't guaranteed to run in this cpu, record earlier */ + if (cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); dwork->cpu = cpu; timer->expires = jiffies + delay; - if (unlikely(cpu != WORK_CPU_UNBOUND)) - add_timer_on(timer, cpu); - else - add_timer(timer); + add_timer_on(timer, cpu); } /** -- cgit v1.2.3 From e2273584d3f33f7f2cfe6d7aaade0fa2f1cb3db5 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Fri, 9 Oct 2015 11:53:12 +0800 Subject: workqueue: Allocate the unbound pool using local node memory Currently, get_unbound_pool() uses kzalloc() to allocate the worker pool. Actually, we can use the right node to do the allocation, achieving local memory access. This patch selects target node first, and uses kzalloc_node() instead. Signed-off-by: Xunlei Pang Signed-off-by: Tejun Heo --- kernel/workqueue.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) (limited to 'kernel/workqueue.c') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ca71582fcfab..96d374735040 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3199,6 +3199,7 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int node; + int target_node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); @@ -3210,13 +3211,25 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) } } + /* if cpumask is contained inside a NUMA node, we belong to that node */ + if (wq_numa_enabled) { + for_each_node(node) { + if (cpumask_subset(attrs->cpumask, + wq_numa_possible_cpumask[node])) { + target_node = node; + break; + } + } + } + /* nope, create a new one */ - pool = kzalloc(sizeof(*pool), GFP_KERNEL); + pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, target_node); if (!pool || init_worker_pool(pool) < 0) goto fail; lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */ copy_workqueue_attrs(pool->attrs, attrs); + pool->node = target_node; /* * no_numa isn't a worker_pool attribute, always clear it. See @@ -3224,17 +3237,6 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) */ pool->attrs->no_numa = false; - /* if cpumask is contained inside a NUMA node, we belong to that node */ - if (wq_numa_enabled) { - for_each_node(node) { - if (cpumask_subset(pool->attrs->cpumask, - wq_numa_possible_cpumask[node])) { - pool->node = node; - break; - } - } - } - if (worker_pool_assign_id(pool) < 0) goto fail; -- cgit v1.2.3