A blkg (blkcg_gq) represents the relationship between a cgroup and
request_queue. Each active policy has a pd (blkg_policy_data) on each
blkg. The pd's were allocated by blkcg core and each policy could
request to allocate extra space at the end by setting
blkcg_policy->pd_size larger than the size of pd.
This is a bit unusual but was done this way mostly to simplify error
handling and all the existing use cases could be handled this way;
however, this is becoming too restrictive now that percpu memory can
be allocated without blocking.
This introduces two new mandatory blkcg_policy methods - pd_alloc_fn()
and pd_free_fn() - which are used to allocate and release pd for a
given policy. As pd allocation is now done from policy side, it can
simply allocate a larger area which embeds pd at the beginning. This
change makes ->pd_size pointless. Removed.
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Cc: Vivek Goyal <vgoyal@xxxxxxxxxx>
---
block/blk-cgroup.c | 18 +++++++++---------
block/blk-throttle.c | 13 ++++++++++++-
block/cfq-iosched.c | 13 ++++++++++++-
include/linux/blk-cgroup.h | 18 +++++++++---------
4 files changed, 42 insertions(+), 20 deletions(-)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 617a586..574971a 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -55,7 +55,8 @@ static void blkg_free(struct blkcg_gq *blkg)
return;
for (i = 0; i < BLKCG_MAX_POLS; i++)
- kfree(blkg->pd[i]);
+ if (blkg->pd[i])
+ blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
if (blkg->blkcg != &blkcg_root)
blk_exit_rl(&blkg->rl);
@@ -101,7 +102,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
continue;
/* alloc per-policy data and attach it to blkg */
- pd = kzalloc_node(pol->pd_size, gfp_mask, q->node);
+ pd = pol->pd_alloc_fn(gfp_mask, q->node);
if (!pd)
goto err_free;
@@ -1016,7 +1017,7 @@ int blkcg_activate_policy(struct request_queue *q,
spin_unlock_irq(q->queue_lock);
while (cnt--) {
- pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node);
+ pd = pol->pd_alloc_fn(GFP_KERNEL, q->node);
if (!pd) {
ret = -ENOMEM;
goto out_free;
@@ -1058,7 +1059,7 @@ int blkcg_activate_policy(struct request_queue *q,
out_free:
blk_queue_bypass_end(q);
list_for_each_entry_safe(pd, n, &pds, alloc_node)
- kfree(pd);
+ pol->pd_free_fn(pd);
return ret;
}
EXPORT_SYMBOL_GPL(blkcg_activate_policy);
@@ -1093,8 +1094,10 @@ void blkcg_deactivate_policy(struct request_queue *q,
if (pol->pd_exit_fn)
pol->pd_exit_fn(blkg);
- kfree(blkg->pd[pol->plid]);
- blkg->pd[pol->plid] = NULL;
+ if (blkg->pd[pol->plid]) {
+ pol->pd_free_fn(blkg->pd[pol->plid]);
+ blkg->pd[pol->plid] = NULL;
+ }
spin_unlock(&blkg->blkcg->lock);
}
@@ -1115,9 +1118,6 @@ int blkcg_policy_register(struct blkcg_policy *pol)
{
int i, ret;
- if (WARN_ON(pol->pd_size < sizeof(struct blkg_policy_data)))
- return -EINVAL;
-
mutex_lock(&blkcg_pol_mutex);
/* find an empty slot */
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index b231935..f1dd691 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -403,6 +403,11 @@ static void throtl_service_queue_exit(struct throtl_service_queue *sq)
del_timer_sync(&sq->pending_timer);
}
+static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
+{
+ return kzalloc_node(sizeof(struct throtl_grp), gfp, node);
+}
+
static void throtl_pd_init(struct blkcg_gq *blkg)
{
struct throtl_grp *tg = blkg_to_tg(blkg);
@@ -493,6 +498,11 @@ static void throtl_pd_exit(struct blkcg_gq *blkg)
throtl_service_queue_exit(&tg->service_queue);
}
+static void throtl_pd_free(struct blkg_policy_data *pd)
+{
+ kfree(pd);
+}
+
static void throtl_pd_reset_stats(struct blkcg_gq *blkg)
{
struct throtl_grp *tg = blkg_to_tg(blkg);
@@ -1468,12 +1478,13 @@ static void throtl_shutdown_wq(struct request_queue *q)
}
static struct blkcg_policy blkcg_policy_throtl = {
- .pd_size = sizeof(struct throtl_grp),
.cftypes = throtl_files,
+ .pd_alloc_fn = throtl_pd_alloc,
.pd_init_fn = throtl_pd_init,
.pd_online_fn = throtl_pd_online,
.pd_exit_fn = throtl_pd_exit,
+ .pd_free_fn = throtl_pd_free,
.pd_reset_stats_fn = throtl_pd_reset_stats,
};
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index c09ef15..6b7bf94 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1543,6 +1543,11 @@ static void cfqg_stats_init(struct cfqg_stats *stats)
#endif
}
+static struct blkg_policy_data *cfq_pd_alloc(gfp_t gfp, int node)
+{
+ return kzalloc_node(sizeof(struct cfq_group), gfp, node);
+}
+
static void cfq_pd_init(struct blkcg_gq *blkg)
{
struct cfq_group *cfqg = blkg_to_cfqg(blkg);
@@ -1578,6 +1583,11 @@ static void cfq_pd_offline(struct blkcg_gq *blkg)
cfqg_stats_xfer_dead(cfqg);
}
+static void cfq_pd_free(struct blkg_policy_data *pd)
+{
+ return kfree(pd);
+}
+
/* offset delta from cfqg->stats to cfqg->dead_stats */
static const int dead_stats_off_delta = offsetof(struct cfq_group, dead_stats) -
offsetof(struct cfq_group, stats);
@@ -4552,11 +4562,12 @@ static struct elevator_type iosched_cfq = {
#ifdef CONFIG_CFQ_GROUP_IOSCHED
static struct blkcg_policy blkcg_policy_cfq = {
- .pd_size = sizeof(struct cfq_group),
.cftypes = cfq_blkcg_files,
+ .pd_alloc_fn = cfq_pd_alloc,
.pd_init_fn = cfq_pd_init,
.pd_offline_fn = cfq_pd_offline,
+ .pd_free_fn = cfq_pd_free,
.pd_reset_stats_fn = cfq_pd_reset_stats,
};
#endif
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 50d1009..63f6340 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -74,13 +74,11 @@ struct blkg_rwstat {
* request_queue (q). This is used by blkcg policies which need to track
* information per blkcg - q pair.
*
- * There can be multiple active blkcg policies and each has its private
- * data on each blkg, the size of which is determined by
- * blkcg_policy->pd_size. blkcg core allocates and frees such areas
- * together with blkg and invokes pd_init/exit_fn() methods.
- *
- * Such private data must embed struct blkg_policy_data (pd) at the
- * beginning and pd_size can't be smaller than pd.
+ * There can be multiple active blkcg policies and each blkg:policy pair is
+ * represented by a blkg_policy_data which is allocated and freed by each
+ * policy's pd_alloc/free_fn() methods. A policy can allocate private data
+ * area by allocating larger data structure which embeds blkg_policy_data
+ * at the beginning.
*/
struct blkg_policy_data {
/* the blkg and policy id this per-policy data belongs to */
@@ -122,24 +120,26 @@ struct blkcg_gq {
struct rcu_head rcu_head;
};
+typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, int node);
typedef void (blkcg_pol_init_pd_fn)(struct blkcg_gq *blkg);
typedef void (blkcg_pol_online_pd_fn)(struct blkcg_gq *blkg);
typedef void (blkcg_pol_offline_pd_fn)(struct blkcg_gq *blkg);
typedef void (blkcg_pol_exit_pd_fn)(struct blkcg_gq *blkg);
+typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkcg_gq *blkg);
struct blkcg_policy {
int plid;
- /* policy specific private data size */
- size_t pd_size;
/* cgroup files for the policy */
struct cftype *cftypes;
/* operations */
+ blkcg_pol_alloc_pd_fn *pd_alloc_fn;
blkcg_pol_init_pd_fn *pd_init_fn;
blkcg_pol_online_pd_fn *pd_online_fn;
blkcg_pol_offline_pd_fn *pd_offline_fn;
blkcg_pol_exit_pd_fn *pd_exit_fn;
+ blkcg_pol_free_pd_fn *pd_free_fn;
blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn;
};
--
2.4.3
--
To unsubscribe from this list: send the line "unsubscribe cgroups" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
