blkcg: replace blkcg_policy->pd_size with ->pd_alloc/free_fn() methods
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@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4defbba..d1bc609 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -68,7 +68,8 @@
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);
@@ -114,7 +115,7 @@
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;
@@ -1057,7 +1058,7 @@
blk_queue_bypass_start(q);
pd_prealloc:
if (!pd_prealloc) {
- pd_prealloc = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node);
+ pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
if (!pd_prealloc) {
ret = -ENOMEM;
goto out_bypass_end;
@@ -1072,7 +1073,7 @@
if (blkg->pd[pol->plid])
continue;
- pd = kzalloc_node(pol->pd_size, GFP_NOWAIT, q->node);
+ pd = pol->pd_alloc_fn(GFP_NOWAIT, q->node);
if (!pd)
swap(pd, pd_prealloc);
if (!pd) {
@@ -1093,7 +1094,8 @@
spin_unlock_irq(q->queue_lock);
out_bypass_end:
blk_queue_bypass_end(q);
- kfree(pd_prealloc);
+ if (pd_prealloc)
+ pol->pd_free_fn(pd_prealloc);
return ret;
}
EXPORT_SYMBOL_GPL(blkcg_activate_policy);
@@ -1128,8 +1130,10 @@
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);
}
@@ -1151,9 +1155,6 @@
struct blkcg *blkcg;
int i, ret;
- if (WARN_ON(pol->pd_size < sizeof(struct blkg_policy_data)))
- return -EINVAL;
-
mutex_lock(&blkcg_pol_register_mutex);
mutex_lock(&blkcg_pol_mutex);
