summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2012-07-17 21:39:26 +0200
committerTejun Heo <tj@kernel.org>2012-07-17 21:39:26 +0200
commit6575820221f7a4dd6eadecf7bf83cdd154335eda (patch)
tree2f9061b4eb1b6cf5a4b70acc45cb46a1a287066a
parentworkqueue: reimplement WQ_HIGHPRI using a separate worker_pool (diff)
downloadlinux-6575820221f7a4dd6eadecf7bf83cdd154335eda.tar.xz
linux-6575820221f7a4dd6eadecf7bf83cdd154335eda.zip
workqueue: perform cpu down operations from low priority cpu_notifier()
Currently, all workqueue cpu hotplug operations run off CPU_PRI_WORKQUEUE which is higher than normal notifiers. This is to ensure that workqueue is up and running while bringing up a CPU before other notifiers try to use workqueue on the CPU. Per-cpu workqueues are supposed to remain working and bound to the CPU for normal CPU_DOWN_PREPARE notifiers. This holds mostly true even with workqueue offlining running with higher priority because workqueue CPU_DOWN_PREPARE only creates a bound trustee thread which runs the per-cpu workqueue without concurrency management without explicitly detaching the existing workers. However, if the trustee needs to create new workers, it creates unbound workers which may wander off to other CPUs while CPU_DOWN_PREPARE notifiers are in progress. Furthermore, if the CPU down is cancelled, the per-CPU workqueue may end up with workers which aren't bound to the CPU. While reliably reproducible with a convoluted artificial test-case involving scheduling and flushing CPU burning work items from CPU down notifiers, this isn't very likely to happen in the wild, and, even when it happens, the effects are likely to be hidden by the following successful CPU down. Fix it by using different priorities for up and down notifiers - high priority for up operations and low priority for down operations. Workqueue cpu hotplug operations will soon go through further cleanup. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: stable@vger.kernel.org Acked-by: "Rafael J. Wysocki" <rjw@sisk.pl>
-rw-r--r--include/linux/cpu.h5
-rw-r--r--kernel/workqueue.c38
2 files changed, 40 insertions, 3 deletions
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 2e9b9ebbeb78..ce7a074f2519 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -73,8 +73,9 @@ enum {
/* migration should happen before other stuff but after perf */
CPU_PRI_PERF = 20,
CPU_PRI_MIGRATION = 10,
- /* prepare workqueues for other notifiers */
- CPU_PRI_WORKQUEUE = 5,
+ /* bring up workqueues before normal notifiers and down after */
+ CPU_PRI_WORKQUEUE_UP = 5,
+ CPU_PRI_WORKQUEUE_DOWN = -5,
};
#define CPU_ONLINE 0x0002 /* CPU (unsigned)v is up */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4fa9e3552f1e..f59b7fd26e26 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3644,6 +3644,41 @@ err_destroy:
return NOTIFY_BAD;
}
+/*
+ * Workqueues should be brought up before normal priority CPU notifiers.
+ * This will be registered high priority CPU notifier.
+ */
+static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb,
+ unsigned long action,
+ void *hcpu)
+{
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_UP_PREPARE:
+ case CPU_UP_CANCELED:
+ case CPU_DOWN_FAILED:
+ case CPU_ONLINE:
+ return workqueue_cpu_callback(nfb, action, hcpu);
+ }
+ return NOTIFY_OK;
+}
+
+/*
+ * Workqueues should be brought down after normal priority CPU notifiers.
+ * This will be registered as low priority CPU notifier.
+ */
+static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb,
+ unsigned long action,
+ void *hcpu)
+{
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DOWN_PREPARE:
+ case CPU_DYING:
+ case CPU_POST_DEAD:
+ return workqueue_cpu_callback(nfb, action, hcpu);
+ }
+ return NOTIFY_OK;
+}
+
#ifdef CONFIG_SMP
struct work_for_cpu {
@@ -3839,7 +3874,8 @@ static int __init init_workqueues(void)
unsigned int cpu;
int i;
- cpu_notifier(workqueue_cpu_callback, CPU_PRI_WORKQUEUE);
+ cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP);
+ cpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN);
/* initialize gcwqs */
for_each_gcwq_cpu(cpu) {