blk-cgroup: support to track if policy is online

commit dfd6200a095440b663099d8d42f1efb0175a1ce3 upstream.

A new field 'online' is added to blkg_policy_data to fix following
2 problem:

1) In blkcg_activate_policy(), if pd_alloc_fn() with 'GFP_NOWAIT'
   failed, 'queue_lock' will be dropped and pd_alloc_fn() will try again
   without 'GFP_NOWAIT'. In the meantime, remove cgroup can race with
   it, and pd_offline_fn() will be called without pd_init_fn() and
   pd_online_fn(). This way null-ptr-deference can be triggered.

2) In order to synchronize pd_free_fn() from blkg_free_workfn() and
   blkcg_deactivate_policy(), 'list_del_init(&blkg->q_node)' will be
   delayed to blkg_free_workfn(), hence pd_offline_fn() can be called
   first in blkg_destroy(), and then blkcg_deactivate_policy() will
   call it again, we must prevent it.

The new field 'online' will be set after pd_online_fn() and will be
cleared after pd_offline_fn(), in the meantime pd_offline_fn() will only
be called if 'online' is set.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20230119110350.2287325-3-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Bin Lan <bin.lan.cn@windriver.com>
Signed-off-by: He Zhe <zhe.he@windriver.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

2 files changed, 18 insertions, 7 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index cced5a2d5fb6..ef596fc10465 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -255,6 +255,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 		blkg->pd[i] = pd;
 		pd->blkg = blkg;
 		pd->plid = i;
+		pd->online = false;
 	}
 
 	return blkg;
@@ -326,8 +327,11 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk,
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
 
-			if (blkg->pd[i] && pol->pd_online_fn)
-				pol->pd_online_fn(blkg->pd[i]);
+			if (blkg->pd[i]) {
+				if (pol->pd_online_fn)
+					pol->pd_online_fn(blkg->pd[i]);
+				blkg->pd[i]->online = true;
+			}
 		}
 	}
 	blkg->online = true;
@@ -432,8 +436,11 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 	for (i = 0; i < BLKCG_MAX_POLS; i++) {
 		struct blkcg_policy *pol = blkcg_policy[i];
 
-		if (blkg->pd[i] && pol->pd_offline_fn)
-			pol->pd_offline_fn(blkg->pd[i]);
+		if (blkg->pd[i] && blkg->pd[i]->online) {
+			if (pol->pd_offline_fn)
+				pol->pd_offline_fn(blkg->pd[i]);
+			blkg->pd[i]->online = false;
+		}
 	}
 
 	blkg->online = false;
@@ -1422,6 +1429,7 @@ retry:
 		blkg->pd[pol->plid] = pd;
 		pd->blkg = blkg;
 		pd->plid = pol->plid;
+		pd->online = false;
 	}
 
 	/* all allocated, init in the same order */
@@ -1429,9 +1437,11 @@ retry:
 		list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
 			pol->pd_init_fn(blkg->pd[pol->plid]);
 
-	if (pol->pd_online_fn)
-		list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
+	list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) {
+		if (pol->pd_online_fn)
 			pol->pd_online_fn(blkg->pd[pol->plid]);
+		blkg->pd[pol->plid]->online = true;
+	}
 
 	__set_bit(pol->plid, q->blkcg_pols);
 	ret = 0;
@@ -1493,7 +1503,7 @@ void blkcg_deactivate_policy(struct request_queue *q,
 
 		spin_lock(&blkcg->lock);
 		if (blkg->pd[pol->plid]) {
-			if (pol->pd_offline_fn)
+			if (blkg->pd[pol->plid]->online && pol->pd_offline_fn)
 				pol->pd_offline_fn(blkg->pd[pol->plid]);
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index aa2b286bc825..59815b269a20 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -125,6 +125,7 @@ struct blkg_policy_data {
 	/* the blkg and policy id this per-policy data belongs to */
 	struct blkcg_gq			*blkg;
 	int				plid;
+	bool				online;
 };
 
 /*