summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorDennis Zhou (Facebook) <dennisszhou@gmail.com>2018-08-31 16:22:43 -0400
committerJens Axboe <axboe@kernel.dk>2018-08-31 14:48:56 -0600
commit59b57717fff8b562825d9d25e0180ad7e8048ca9 (patch)
treed3e3158cd0f5e9ff6340ba0f9d070772429401b2 /include
parent6b06546206868f723f2061d703a3c3c378dcbf4c (diff)
downloadlinux-59b57717fff8b562825d9d25e0180ad7e8048ca9.tar.bz2
blkcg: delay blkg destruction until after writeback has finished
Currently, blkcg destruction relies on a sequence of events: 1. Destruction starts. blkcg_css_offline() is called and blkgs release their reference to the blkcg. This immediately destroys the cgwbs (writeback). 2. With blkgs giving up their reference, the blkcg ref count should become zero and eventually call blkcg_css_free() which finally frees the blkcg. Jiufei Xue reported that there is a race between blkcg_bio_issue_check() and cgroup_rmdir(). To remedy this, blkg destruction becomes contingent on the completion of all writeback associated with the blkcg. A count of the number of cgwbs is maintained and once that goes to zero, blkg destruction can follow. This should prevent premature blkg destruction related to writeback. The new process for blkcg cleanup is as follows: 1. Destruction starts. blkcg_css_offline() is called which offlines writeback. Blkg destruction is delayed on the cgwb_refcnt count to avoid punting potentially large amounts of outstanding writeback to root while maintaining any ongoing policies. Here, the base cgwb_refcnt is put back. 2. When the cgwb_refcnt becomes zero, blkcg_destroy_blkgs() is called and handles destruction of blkgs. This is where the css reference held by each blkg is released. 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. This finally frees the blkg. It seems in the past blk-throttle didn't do the most understandable things with taking data from a blkg while associating with current. So, the simplification and unification of what blk-throttle is doing caused this. Fixes: 08e18eab0c579 ("block: add bi_blkg to the bio for cgroups") Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Dennis Zhou <dennisszhou@gmail.com> Cc: Jiufei Xue <jiufei.xue@linux.alibaba.com> Cc: Joseph Qi <joseph.qi@linux.alibaba.com> Cc: Tejun Heo <tj@kernel.org> Cc: Josef Bacik <josef@toxicpanda.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'include')
-rw-r--r--include/linux/blk-cgroup.h44
1 files changed, 44 insertions, 0 deletions
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 1615cdd4c797..6d766a19f2bb 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -56,6 +56,7 @@ struct blkcg {
struct list_head all_blkcgs_node;
#ifdef CONFIG_CGROUP_WRITEBACK
struct list_head cgwb_list;
+ refcount_t cgwb_refcnt;
#endif
};
@@ -386,6 +387,49 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd)
return cpd ? cpd->blkcg : NULL;
}
+extern void blkcg_destroy_blkgs(struct blkcg *blkcg);
+
+#ifdef CONFIG_CGROUP_WRITEBACK
+
+/**
+ * blkcg_cgwb_get - get a reference for blkcg->cgwb_list
+ * @blkcg: blkcg of interest
+ *
+ * This is used to track the number of active wb's related to a blkcg.
+ */
+static inline void blkcg_cgwb_get(struct blkcg *blkcg)
+{
+ refcount_inc(&blkcg->cgwb_refcnt);
+}
+
+/**
+ * blkcg_cgwb_put - put a reference for @blkcg->cgwb_list
+ * @blkcg: blkcg of interest
+ *
+ * This is used to track the number of active wb's related to a blkcg.
+ * When this count goes to zero, all active wb has finished so the
+ * blkcg can continue destruction by calling blkcg_destroy_blkgs().
+ * This work may occur in cgwb_release_workfn() on the cgwb_release
+ * workqueue.
+ */
+static inline void blkcg_cgwb_put(struct blkcg *blkcg)
+{
+ if (refcount_dec_and_test(&blkcg->cgwb_refcnt))
+ blkcg_destroy_blkgs(blkcg);
+}
+
+#else
+
+static inline void blkcg_cgwb_get(struct blkcg *blkcg) { }
+
+static inline void blkcg_cgwb_put(struct blkcg *blkcg)
+{
+ /* wb isn't being accounted, so trigger destruction right away */
+ blkcg_destroy_blkgs(blkcg);
+}
+
+#endif
+
/**
* blkg_path - format cgroup path of blkg
* @blkg: blkg of interest