blk-cgroup: allow controllers to output their own stats

blk-iolatency has a few stats that it would like to print out, and
instead of adding a bunch of crap to the generic code just provide a
helper so that controllers can add stuff to the stat line if they want
to.

Hide it behind a boot option since it changes the output of io.stat from
normal, and these stats are only interesting to developers.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 47 insertions, 3 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index eb85cb87c40f..7dc6f05cc44b 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -50,6 +50,8 @@ static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
 static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
 
+static bool blkcg_debug_stats = false;
+
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
@@ -954,13 +956,25 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
 		const char *dname;
+		char *buf;
 		struct blkg_rwstat rwstat;
 		u64 rbytes, wbytes, rios, wios;
+		size_t size = seq_get_buf(sf, &buf), off = 0;
+		int i;
+		bool has_stats = false;
 
 		dname = blkg_dev_name(blkg);
 		if (!dname)
 			continue;
 
+		/*
+		 * Hooray string manipulation, count is the size written NOT
+		 * INCLUDING THE \0, so size is now count+1 less than what we
+		 * had before, but we want to start writing the next bit from
+		 * the \0 so we only add count to buf.
+		 */
+		off += scnprintf(buf+off, size-off, "%s ", dname);
+
 		spin_lock_irq(blkg->q->queue_lock);
 
 		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
@@ -975,9 +989,33 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 
 		spin_unlock_irq(blkg->q->queue_lock);
 
-		if (rbytes || wbytes || rios || wios)
-			seq_printf(sf, "%s rbytes=%llu wbytes=%llu rios=%llu wios=%llu\n",
-				   dname, rbytes, wbytes, rios, wios);
+		if (rbytes || wbytes || rios || wios) {
+			has_stats = true;
+			off += scnprintf(buf+off, size-off,
+					 "rbytes=%llu wbytes=%llu rios=%llu wios=%llu",
+					 rbytes, wbytes, rios, wios);
+		}
+
+		if (!blkcg_debug_stats)
+			goto next;
+
+		for (i = 0; i < BLKCG_MAX_POLS; i++) {
+			struct blkcg_policy *pol = blkcg_policy[i];
+			size_t written;
+
+			if (!blkg->pd[i] || !pol->pd_stat_fn)
+				continue;
+
+			written = pol->pd_stat_fn(blkg->pd[i], buf+off, size-off);
+			if (written)
+				has_stats = true;
+			off += written;
+		}
+next:
+		if (has_stats) {
+			off += scnprintf(buf+off, size-off, "\n");
+			seq_commit(sf, off);
+		}
 	}
 
 	rcu_read_unlock();
@@ -1547,3 +1585,6 @@ out_unlock:
 	mutex_unlock(&blkcg_pol_register_mutex);
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_unregister);
+
+module_param(blkcg_debug_stats, bool, 0644);
+MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not");
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 69aa71dc0c04..b41292726c0f 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -148,6 +148,8 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
+typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf,
+				      size_t size);
 
 struct blkcg_policy {
 	int				plid;
@@ -167,6 +169,7 @@ struct blkcg_policy {
 	blkcg_pol_offline_pd_fn		*pd_offline_fn;
 	blkcg_pol_free_pd_fn		*pd_free_fn;
 	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;
+	blkcg_pol_stat_pd_fn		*pd_stat_fn;
 };
 
 extern struct blkcg blkcg_root;