struct cfq_queue {
/* reference count */
atomic_t ref;
+ /* various state flags, see below */
+ unsigned int flags;
/* parent cfq_data */
struct cfq_data *cfqd;
/* service_tree member */
int queued[2];
/* currently allocated requests */
int allocated[2];
- /* pending metadata requests */
- int meta_pending;
/* fifo list of requests in sort_list */
struct list_head fifo;
unsigned long slice_end;
long slice_resid;
+ /* pending metadata requests */
+ int meta_pending;
/* number of requests that are on the dispatch list or inside driver */
int dispatched;
unsigned short ioprio, org_ioprio;
unsigned short ioprio_class, org_ioprio_class;
- /* various state flags, see below */
- unsigned int flags;
};
enum cfqq_state_flags {
}
/*
- * Call func for each cic attached to this ioc. Returns number of cic's seen.
+ * Must always be called with the rcu_read_lock() held
*/
-static unsigned int
-call_for_each_cic(struct io_context *ioc,
- void (*func)(struct io_context *, struct cfq_io_context *))
+static void
+__call_for_each_cic(struct io_context *ioc,
+ void (*func)(struct io_context *, struct cfq_io_context *))
{
struct cfq_io_context *cic;
struct hlist_node *n;
- int called = 0;
- rcu_read_lock();
- hlist_for_each_entry_rcu(cic, n, &ioc->cic_list, cic_list) {
+ hlist_for_each_entry_rcu(cic, n, &ioc->cic_list, cic_list)
func(ioc, cic);
- called++;
- }
+}
+
+/*
+ * Call func for each cic attached to this ioc.
+ */
+static void
+call_for_each_cic(struct io_context *ioc,
+ void (*func)(struct io_context *, struct cfq_io_context *))
+{
+ rcu_read_lock();
+ __call_for_each_cic(ioc, func);
rcu_read_unlock();
+}
+
+static void cfq_cic_free_rcu(struct rcu_head *head)
+{
+ struct cfq_io_context *cic;
+
+ cic = container_of(head, struct cfq_io_context, rcu_head);
+
+ kmem_cache_free(cfq_ioc_pool, cic);
+ elv_ioc_count_dec(ioc_count);
- return called;
+ if (ioc_gone && !elv_ioc_count_read(ioc_count))
+ complete(ioc_gone);
+}
+
+static void cfq_cic_free(struct cfq_io_context *cic)
+{
+ call_rcu(&cic->rcu_head, cfq_cic_free_rcu);
}
static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic)
hlist_del_rcu(&cic->cic_list);
spin_unlock_irqrestore(&ioc->lock, flags);
- kmem_cache_free(cfq_ioc_pool, cic);
+ cfq_cic_free(cic);
}
+/*
+ * Must be called with rcu_read_lock() held or preemption otherwise disabled.
+ * Only two callers of this - ->dtor() which is called with the rcu_read_lock(),
+ * and ->trim() which is called with the task lock held
+ */
static void cfq_free_io_context(struct io_context *ioc)
{
- int freed;
-
/*
- * ioc->refcount is zero here, so no more cic's are allowed to be
- * linked into this ioc. So it should be ok to iterate over the known
- * list, we will see all cic's since no new ones are added.
+ * ioc->refcount is zero here, or we are called from elv_unregister(),
+ * so no more cic's are allowed to be linked into this ioc. So it
+ * should be ok to iterate over the known list, we will see all cic's
+ * since no new ones are added.
*/
- freed = call_for_each_cic(ioc, cic_free_func);
-
- elv_ioc_count_mod(ioc_count, -freed);
-
- if (ioc_gone && !elv_ioc_count_read(ioc_count))
- complete(ioc_gone);
+ __call_for_each_cic(ioc, cic_free_func);
}
static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
struct cfq_io_context *cic)
{
+ struct io_context *ioc = cic->ioc;
+
list_del_init(&cic->queue_list);
/*
cic->dead_key = (unsigned long) cic->key;
cic->key = NULL;
+ if (ioc->ioc_data == cic)
+ rcu_assign_pointer(ioc->ioc_data, NULL);
+
if (cic->cfqq[ASYNC]) {
cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]);
cic->cfqq[ASYNC] = NULL;
*/
static void cfq_exit_io_context(struct io_context *ioc)
{
- rcu_assign_pointer(ioc->ioc_data, NULL);
call_for_each_cic(ioc, cfq_exit_single_io_context);
}
printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
case IOPRIO_CLASS_NONE:
/*
- * no prio set, place us in the middle of the BE classes
+ * no prio set, inherit CPU scheduling settings
*/
cfqq->ioprio = task_nice_ioprio(tsk);
- cfqq->ioprio_class = IOPRIO_CLASS_BE;
+ cfqq->ioprio_class = task_nice_ioclass(tsk);
break;
case IOPRIO_CLASS_RT:
cfqq->ioprio = task_ioprio(ioc);
return cfqq;
}
-static void cfq_cic_free(struct cfq_io_context *cic)
-{
- kmem_cache_free(cfq_ioc_pool, cic);
- elv_ioc_count_dec(ioc_count);
-
- if (ioc_gone && !elv_ioc_count_read(ioc_count))
- complete(ioc_gone);
-}
-
/*
* We drop cfq io contexts lazily, so we may find a dead one.
*/
spin_lock_irqsave(&ioc->lock, flags);
- if (ioc->ioc_data == cic)
- rcu_assign_pointer(ioc->ioc_data, NULL);
+ BUG_ON(ioc->ioc_data == cic);
radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd);
hlist_del_rcu(&cic->cic_list);
cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc)
{
struct cfq_io_context *cic;
+ unsigned long flags;
void *k;
if (unlikely(!ioc))
return NULL;
+ rcu_read_lock();
+
/*
* we maintain a last-hit cache, to avoid browsing over the tree
*/
cic = rcu_dereference(ioc->ioc_data);
- if (cic && cic->key == cfqd)
+ if (cic && cic->key == cfqd) {
+ rcu_read_unlock();
return cic;
+ }
do {
- rcu_read_lock();
cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd);
rcu_read_unlock();
if (!cic)
k = cic->key;
if (unlikely(!k)) {
cfq_drop_dead_cic(cfqd, ioc, cic);
+ rcu_read_lock();
continue;
}
+ spin_lock_irqsave(&ioc->lock, flags);
rcu_assign_pointer(ioc->ioc_data, cic);
+ spin_unlock_irqrestore(&ioc->lock, flags);
break;
} while (1);
static void cfq_slab_kill(void)
{
+ /*
+ * Caller already ensured that pending RCU callbacks are completed,
+ * so we should have no busy allocations at this point.
+ */
if (cfq_pool)
kmem_cache_destroy(cfq_pool);
if (cfq_ioc_pool)
if (!cfq_pool)
goto fail;
- cfq_ioc_pool = KMEM_CACHE(cfq_io_context, SLAB_DESTROY_BY_RCU);
+ cfq_ioc_pool = KMEM_CACHE(cfq_io_context, 0);
if (!cfq_ioc_pool)
goto fail;
ioc_gone = &all_gone;
/* ioc_gone's update must be visible before reading ioc_count */
smp_wmb();
+
+ /*
+ * this also protects us from entering cfq_slab_kill() with
+ * pending RCU callbacks
+ */
if (elv_ioc_count_read(ioc_count))
wait_for_completion(ioc_gone);
- synchronize_rcu();
cfq_slab_kill();
}