summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2015-01-16 14:21:16 -0500
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2015-02-05 22:35:40 -0800
commit85be16bad779a187bedc4292f2adc54863b4375b (patch)
tree88ac9cb8a572727dc32563993f6ffccf29dbc90a /kernel
parent60e353b14ad68daaef8685cc324fa45501615bee (diff)
workqueue: fix subtle pool management issue which can stall whole worker_pool
commit 29187a9eeaf362d8422e62e17a22a6e115277a49 upstream. A worker_pool's forward progress is guaranteed by the fact that the last idle worker assumes the manager role to create more workers and summon the rescuers if creating workers doesn't succeed in timely manner before proceeding to execute work items. This manager role is implemented in manage_workers(), which indicates whether the worker may proceed to work item execution with its return value. This is necessary because multiple workers may contend for the manager role, and, if there already is a manager, others should proceed to work item execution. Unfortunately, the function also indicates that the worker may proceed to work item execution if need_to_create_worker() is false at the head of the function. need_to_create_worker() tests the following conditions. pending work items && !nr_running && !nr_idle The first and third conditions are protected by pool->lock and thus won't change while holding pool->lock; however, nr_running can change asynchronously as other workers block and resume and while it's likely to be zero, as someone woke this worker up in the first place, some other workers could have become runnable inbetween making it non-zero. If this happens, manage_worker() could return false even with zero nr_idle making the worker, the last idle one, proceed to execute work items. If then all workers of the pool end up blocking on a resource which can only be released by a work item which is pending on that pool, the whole pool can deadlock as there's no one to create more workers or summon the rescuers. This patch fixes the problem by removing the early exit condition from maybe_create_worker() and making manage_workers() return false iff there's already another manager, which ensures that the last worker doesn't start executing work items. We can leave the early exit condition alone and just ignore the return value but the only reason it was put there is because the manage_workers() used to perform both creations and destructions of workers and thus the function may be invoked while the pool is trying to reduce the number of workers. Now that manage_workers() is called only when more workers are needed, the only case this early exit condition is triggered is rare race conditions rendering it pointless. Tested with simulated workload and modified workqueue code which trigger the pool deadlock reliably without this patch. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Eric Sandeen <sandeen@sandeen.net> Link: http://lkml.kernel.org/g/54B019F4.8030009@sandeen.net Cc: Dave Chinner <david@fromorbit.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/workqueue.c39
1 files changed, 13 insertions, 26 deletions
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c2f9d6ca7e5e..16730a9c8cac 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1934,17 +1934,13 @@ static void pool_mayday_timeout(unsigned long __pool)
* spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Does GFP_KERNEL allocations. Called only from
* manager.
- *
- * RETURNS:
- * %false if no action was taken and pool->lock stayed locked, %true
- * otherwise.
*/
-static bool maybe_create_worker(struct worker_pool *pool)
+static void maybe_create_worker(struct worker_pool *pool)
__releases(&pool->lock)
__acquires(&pool->lock)
{
if (!need_to_create_worker(pool))
- return false;
+ return;
restart:
spin_unlock_irq(&pool->lock);
@@ -1961,7 +1957,7 @@ restart:
start_worker(worker);
if (WARN_ON_ONCE(need_to_create_worker(pool)))
goto restart;
- return true;
+ return;
}
if (!need_to_create_worker(pool))
@@ -1978,7 +1974,7 @@ restart:
spin_lock_irq(&pool->lock);
if (need_to_create_worker(pool))
goto restart;
- return true;
+ return;
}
/**
@@ -1991,15 +1987,9 @@ restart:
* LOCKING:
* spin_lock_irq(pool->lock) which may be released and regrabbed
* multiple times. Called only from manager.
- *
- * RETURNS:
- * %false if no action was taken and pool->lock stayed locked, %true
- * otherwise.
*/
-static bool maybe_destroy_workers(struct worker_pool *pool)
+static void maybe_destroy_workers(struct worker_pool *pool)
{
- bool ret = false;
-
while (too_many_workers(pool)) {
struct worker *worker;
unsigned long expires;
@@ -2013,10 +2003,7 @@ static bool maybe_destroy_workers(struct worker_pool *pool)
}
destroy_worker(worker);
- ret = true;
}
-
- return ret;
}
/**
@@ -2036,13 +2023,14 @@ static bool maybe_destroy_workers(struct worker_pool *pool)
* multiple times. Does GFP_KERNEL allocations.
*
* RETURNS:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
- * multiple times. Does GFP_KERNEL allocations.
+ * %false if the pool doesn't need management and the caller can safely
+ * start processing works, %true if management function was performed and
+ * the conditions that the caller verified before calling the function may
+ * no longer be true.
*/
static bool manage_workers(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
- bool ret = false;
/*
* Managership is governed by two mutexes - manager_arb and
@@ -2066,7 +2054,7 @@ static bool manage_workers(struct worker *worker)
* manager_mutex.
*/
if (!mutex_trylock(&pool->manager_arb))
- return ret;
+ return false;
/*
* With manager arbitration won, manager_mutex would be free in
@@ -2076,7 +2064,6 @@ static bool manage_workers(struct worker *worker)
spin_unlock_irq(&pool->lock);
mutex_lock(&pool->manager_mutex);
spin_lock_irq(&pool->lock);
- ret = true;
}
pool->flags &= ~POOL_MANAGE_WORKERS;
@@ -2085,12 +2072,12 @@ static bool manage_workers(struct worker *worker)
* Destroy and then create so that may_start_working() is true
* on return.
*/
- ret |= maybe_destroy_workers(pool);
- ret |= maybe_create_worker(pool);
+ maybe_destroy_workers(pool);
+ maybe_create_worker(pool);
mutex_unlock(&pool->manager_mutex);
mutex_unlock(&pool->manager_arb);
- return ret;
+ return true;
}
/**