aboutsummaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2011-12-14 00:33:42 +0100
committerJens Axboe <axboe@kernel.dk>2011-12-14 00:33:42 +0100
commit7e5a8794492e43e9eebb68a98a23be055888ccd0 (patch)
treecc049a23b2c994f910d3101860bc1c2ecb7aa35f /block
parent3d3c2379feb177a5fd55bb0ed76776dc9d4f3243 (diff)
block, cfq: move io_cq exit/release to blk-ioc.c
With kmem_cache managed by blk-ioc, io_cq exit/release can be moved to blk-ioc too. The odd ->io_cq->exit/release() callbacks are replaced with elevator_ops->elevator_exit_icq_fn() with unlinking from both ioc and q, and freeing automatically handled by blk-ioc. The elevator operation only need to perform exit operation specific to the elevator - in cfq's case, exiting the cfqq's. Also, clearing of io_cq's on q detach is moved to block core and automatically performed on elevator switch and q release. Because the q io_cq points to might be freed before RCU callback for the io_cq runs, blk-ioc code should remember to which cache the io_cq needs to be freed when the io_cq is released. New field io_cq->__rcu_icq_cache is added for this purpose. As both the new field and rcu_head are used only after io_cq is released and the q/ioc_node fields aren't, they are put into unions. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block')
-rw-r--r--block/blk-ioc.c76
-rw-r--r--block/blk-sysfs.c6
-rw-r--r--block/blk.h1
-rw-r--r--block/cfq-iosched.c47
-rw-r--r--block/elevator.c3
5 files changed, 78 insertions, 55 deletions
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 87ecc98b8ad..0910a5584d3 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -44,6 +44,51 @@ EXPORT_SYMBOL(get_io_context);
#define ioc_release_depth_dec(q) do { } while (0)
#endif
+static void icq_free_icq_rcu(struct rcu_head *head)
+{
+ struct io_cq *icq = container_of(head, struct io_cq, __rcu_head);
+
+ kmem_cache_free(icq->__rcu_icq_cache, icq);
+}
+
+/*
+ * Exit and free an icq. Called with both ioc and q locked.
+ */
+static void ioc_exit_icq(struct io_cq *icq)
+{
+ struct io_context *ioc = icq->ioc;
+ struct request_queue *q = icq->q;
+ struct elevator_type *et = q->elevator->type;
+
+ lockdep_assert_held(&ioc->lock);
+ lockdep_assert_held(q->queue_lock);
+
+ radix_tree_delete(&ioc->icq_tree, icq->q->id);
+ hlist_del_init(&icq->ioc_node);
+ list_del_init(&icq->q_node);
+
+ /*
+ * Both setting lookup hint to and clearing it from @icq are done
+ * under queue_lock. If it's not pointing to @icq now, it never
+ * will. Hint assignment itself can race safely.
+ */
+ if (rcu_dereference_raw(ioc->icq_hint) == icq)
+ rcu_assign_pointer(ioc->icq_hint, NULL);
+
+ if (et->ops.elevator_exit_icq_fn) {
+ ioc_release_depth_inc(q);
+ et->ops.elevator_exit_icq_fn(icq);
+ ioc_release_depth_dec(q);
+ }
+
+ /*
+ * @icq->q might have gone away by the time RCU callback runs
+ * making it impossible to determine icq_cache. Record it in @icq.
+ */
+ icq->__rcu_icq_cache = et->icq_cache;
+ call_rcu(&icq->__rcu_head, icq_free_icq_rcu);
+}
+
/*
* Slow path for ioc release in put_io_context(). Performs double-lock
* dancing to unlink all icq's and then frees ioc.
@@ -87,10 +132,7 @@ static void ioc_release_fn(struct work_struct *work)
spin_lock(&ioc->lock);
continue;
}
- ioc_release_depth_inc(this_q);
- icq->exit(icq);
- icq->release(icq);
- ioc_release_depth_dec(this_q);
+ ioc_exit_icq(icq);
}
if (last_q) {
@@ -167,10 +209,7 @@ void put_io_context(struct io_context *ioc, struct request_queue *locked_q)
last_q = this_q;
continue;
}
- ioc_release_depth_inc(this_q);
- icq->exit(icq);
- icq->release(icq);
- ioc_release_depth_dec(this_q);
+ ioc_exit_icq(icq);
}
if (last_q && last_q != locked_q)
@@ -203,6 +242,27 @@ void exit_io_context(struct task_struct *task)
put_io_context(ioc, NULL);
}
+/**
+ * ioc_clear_queue - break any ioc association with the specified queue
+ * @q: request_queue being cleared
+ *
+ * Walk @q->icq_list and exit all io_cq's. Must be called with @q locked.
+ */
+void ioc_clear_queue(struct request_queue *q)
+{
+ lockdep_assert_held(q->queue_lock);
+
+ while (!list_empty(&q->icq_list)) {
+ struct io_cq *icq = list_entry(q->icq_list.next,
+ struct io_cq, q_node);
+ struct io_context *ioc = icq->ioc;
+
+ spin_lock(&ioc->lock);
+ ioc_exit_icq(icq);
+ spin_unlock(&ioc->lock);
+ }
+}
+
void create_io_context_slowpath(struct task_struct *task, gfp_t gfp_flags,
int node)
{
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 5b4b4ab5e78..cf150011d80 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -479,8 +479,12 @@ static void blk_release_queue(struct kobject *kobj)
blk_sync_queue(q);
- if (q->elevator)
+ if (q->elevator) {
+ spin_lock_irq(q->queue_lock);
+ ioc_clear_queue(q);
+ spin_unlock_irq(q->queue_lock);
elevator_exit(q->elevator);
+ }
blk_throtl_exit(q);
diff --git a/block/blk.h b/block/blk.h
index 3c510a4b505..ed4d9bf2ab1 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -200,6 +200,7 @@ static inline int blk_do_io_stat(struct request *rq)
*/
void get_io_context(struct io_context *ioc);
struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q);
+void ioc_clear_queue(struct request_queue *q);
void create_io_context_slowpath(struct task_struct *task, gfp_t gfp_mask,
int node);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 06e59abcb57..f6d31555149 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -2674,26 +2674,6 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
cfq_put_cfqg(cfqg);
}
-static void cfq_icq_free_rcu(struct rcu_head *head)
-{
- kmem_cache_free(cfq_icq_pool,
- icq_to_cic(container_of(head, struct io_cq, rcu_head)));
-}
-
-static void cfq_icq_free(struct io_cq *icq)
-{
- call_rcu(&icq->rcu_head, cfq_icq_free_rcu);
-}
-
-static void cfq_release_icq(struct io_cq *icq)
-{
- struct io_context *ioc = icq->ioc;
-
- radix_tree_delete(&ioc->icq_tree, icq->q->id);
- hlist_del(&icq->ioc_node);
- cfq_icq_free(icq);
-}
-
static void cfq_put_cooperator(struct cfq_queue *cfqq)
{
struct cfq_queue *__cfqq, *next;
@@ -2731,17 +2711,6 @@ static void cfq_exit_icq(struct io_cq *icq)
{
struct cfq_io_cq *cic = icq_to_cic(icq);
struct cfq_data *cfqd = cic_to_cfqd(cic);
- struct io_context *ioc = icq->ioc;
-
- list_del_init(&icq->q_node);
-
- /*
- * Both setting lookup hint to and clearing it from @icq are done
- * under queue_lock. If it's not pointing to @icq now, it never
- * will. Hint assignment itself can race safely.
- */
- if (rcu_dereference_raw(ioc->icq_hint) == icq)
- rcu_assign_pointer(ioc->icq_hint, NULL);
if (cic->cfqq[BLK_RW_ASYNC]) {
cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]);
@@ -2764,8 +2733,6 @@ static struct cfq_io_cq *cfq_alloc_cic(struct cfq_data *cfqd, gfp_t gfp_mask)
cic->ttime.last_end_request = jiffies;
INIT_LIST_HEAD(&cic->icq.q_node);
INIT_HLIST_NODE(&cic->icq.ioc_node);
- cic->icq.exit = cfq_exit_icq;
- cic->icq.release = cfq_release_icq;
}
return cic;
@@ -3034,7 +3001,7 @@ out:
if (ret)
printk(KERN_ERR "cfq: icq link failed!\n");
if (icq)
- cfq_icq_free(icq);
+ kmem_cache_free(cfq_icq_pool, icq);
return ret;
}
@@ -3774,17 +3741,6 @@ static void cfq_exit_queue(struct elevator_queue *e)
if (cfqd->active_queue)
__cfq_slice_expired(cfqd, cfqd->active_queue, 0);
- while (!list_empty(&q->icq_list)) {
- struct io_cq *icq = list_entry(q->icq_list.next,
- struct io_cq, q_node);
- struct io_context *ioc = icq->ioc;
-
- spin_lock(&ioc->lock);
- cfq_exit_icq(icq);
- cfq_release_icq(icq);
- spin_unlock(&ioc->lock);
- }
-
cfq_put_async_queues(cfqd);
cfq_release_cfq_groups(cfqd);
@@ -4019,6 +3975,7 @@ static struct elevator_type iosched_cfq = {
.elevator_completed_req_fn = cfq_completed_request,
.elevator_former_req_fn = elv_rb_former_request,
.elevator_latter_req_fn = elv_rb_latter_request,
+ .elevator_exit_icq_fn = cfq_exit_icq,
.elevator_set_req_fn = cfq_set_request,
.elevator_put_req_fn = cfq_put_request,
.elevator_may_queue_fn = cfq_may_queue,
diff --git a/block/elevator.c b/block/elevator.c
index cca049fb45c..91e18f8af9b 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -979,8 +979,9 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
goto fail_register;
}
- /* done, replace the old one with new one and turn off BYPASS */
+ /* done, clear io_cq's, switch elevators and turn off BYPASS */
spin_lock_irq(q->queue_lock);
+ ioc_clear_queue(q);
old_elevator = q->elevator;
q->elevator = e;
spin_unlock_irq(q->queue_lock);