Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Mon, 14 Oct 2019 11:50:27 -0700
From:   Tejun Heo <tj@kernel.org>
To:     Jens Axboe <axboe@kernel.dk>
Cc:     linux-block@vger.kernel.org, newella@fb.com, kernel-team@fb.com,
        linux-kernel@vger.kernel.org
Subject: [PATCH block/for-linus] blkcg: Fix ->pd_alloc_fn() being called with
 the wrong blkcg on policy activation
Message-ID: <20191014185027.GH18794@devbig004.ftw2.facebook.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

cf09a8ee19ad ("blkcg: pass @q and @blkcg into
blkcg_pol_alloc_pd_fn()") added @blkcg to ->pd_alloc_fn(); however,
blkcg_activate_policy() ends up using pd's allocated for the root
blkcg for all preallocations, so ->pd_init_fn() for non-root blkcgs
can be passed in pd's which are allocated for the root blkcg.

For blk-iocost, this means that ->pd_init_fn() can write beyond the
end of the allocated object as it determines the length of the flex
array at the end based on the blkcg's nesting level.

Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: cf09a8ee19ad ("blkcg: pass @q and @blkcg into blkcg_pol_alloc_pd_fn()")
---
 block/blk-cgroup.c |   43 +++++++++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 14 deletions(-)

--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1362,7 +1362,7 @@ int blkcg_activate_policy(struct request
 			  const struct blkcg_policy *pol)
 {
 	struct blkg_policy_data *pd_prealloc = NULL;
-	struct blkcg_gq *blkg;
+	struct blkcg_gq *blkg, *pinned_blkg = NULL;
 	int ret;
 
 	if (blkcg_policy_enabled(q, pol))
@@ -1370,15 +1370,7 @@ int blkcg_activate_policy(struct request
 
 	if (queue_is_mq(q))
 		blk_mq_freeze_queue(q);
-pd_prealloc:
-	if (!pd_prealloc) {
-		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, &blkcg_root);
-		if (!pd_prealloc) {
-			ret = -ENOMEM;
-			goto out_bypass_end;
-		}
-	}
-
+retry:
 	spin_lock_irq(&q->queue_lock);
 
 	/* blkg_list is pushed at the head, reverse walk to init parents first */
@@ -1388,12 +1380,31 @@ pd_prealloc:
 		if (blkg->pd[pol->plid])
 			continue;
 
-		pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, &blkcg_root);
-		if (!pd)
-			swap(pd, pd_prealloc);
+		if (blkg == pinned_blkg) {
+			pd = pd_prealloc;
+			pd_prealloc = NULL;
+		} else {
+			pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q,
+					      blkg->blkcg);
+		}
+
 		if (!pd) {
+			if (pinned_blkg)
+				blkg_put(pinned_blkg);
+			blkg_get(blkg);
+			pinned_blkg = blkg;
+
 			spin_unlock_irq(&q->queue_lock);
-			goto pd_prealloc;
+
+			kfree(pd_prealloc);
+			pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q,
+						       blkg->blkcg);
+			if (pd_prealloc) {
+				goto retry;
+			} else {
+				ret = -ENOMEM;
+				goto out_bypass_end;
+			}
 		}
 
 		blkg->pd[pol->plid] = pd;
@@ -1403,6 +1414,10 @@ pd_prealloc:
 			pol->pd_init_fn(pd);
 	}
 
+	if (pinned_blkg)
+		blkg_put(pinned_blkg);
+	kfree(pd_prealloc);
+
 	__set_bit(pol->plid, q->blkcg_pols);
 	ret = 0;