blkcg: implement interface for the unified hierarchy

blkcg interface grew to be the biggest of all controllers and
unfortunately most inconsistent too.  The interface files are
inconsistent with a number of cloes duplicates.  Some files have
recursive variants while others don't.  There's distinction between
normal and leaf weights which isn't intuitive and there are a lot of
stat knobs which don't make much sense outside of debugging and expose
too much implementation details to userland.

In the unified hierarchy, everything is always hierarchical and
internal nodes can't have tasks rendering the two structural issues
twisting the current interface.  The interface has to be updated in a
significant anyway and this is a good chance to revamp it as a whole.
This patch implements blkcg interface for the unified hierarchy.

* (from a previous patch) blkcg is identified by "io" instead of
  "blkio" on the unified hierarchy.  Given that the whole interface is
  updated anyway, the rename shouldn't carry noticeable conversion
  overhead.

* The original interface consisted of 27 files is replaced with the
  following three files.

  blkio.stat	: per-blkcg stats
  blkio.weight	: per-cgroup and per-cgroup-queue weight settings
  blkio.max	: per-cgroup-queue bps and iops max limits

Documentation/cgroups/unified-hierarchy.txt updated accordingly.

v2: blkcg_policy->dfl_cftypes wasn't removed on
    blkcg_policy_unregister() corrupting the cftypes list.  Fixed.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 53 insertions, 0 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index b5e72d756be1f..88bdb73bd5e00 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -854,6 +854,53 @@ void blkg_conf_finish(struct blkg_conf_ctx *ctx)
 }
 EXPORT_SYMBOL_GPL(blkg_conf_finish);
 
+static int blkcg_print_stat(struct seq_file *sf, void *v)
+{
+	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+	struct blkcg_gq *blkg;
+
+	rcu_read_lock();
+
+	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
+		const char *dname;
+		struct blkg_rwstat rwstat;
+		u64 rbytes, wbytes, rios, wios;
+
+		dname = blkg_dev_name(blkg);
+		if (!dname)
+			continue;
+
+		spin_lock_irq(blkg->q->queue_lock);
+
+		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
+					offsetof(struct blkcg_gq, stat_bytes));
+		rbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
+		wbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
+
+		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
+					offsetof(struct blkcg_gq, stat_ios));
+		rios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
+		wios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
+
+		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);
+	}
+
+	rcu_read_unlock();
+	return 0;
+}
+
+struct cftype blkcg_files[] = {
+	{
+		.name = "stat",
+		.seq_show = blkcg_print_stat,
+	},
+	{ }	/* terminate */
+};
+
 struct cftype blkcg_legacy_files[] = {
 	{
 		.name = "reset_stats",
@@ -1101,6 +1148,7 @@ struct cgroup_subsys io_cgrp_subsys = {
 	.css_offline = blkcg_css_offline,
 	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,
+	.dfl_cftypes = blkcg_files,
 	.legacy_cftypes = blkcg_legacy_files,
 	.legacy_name = "blkio",
 #ifdef CONFIG_MEMCG
@@ -1273,6 +1321,9 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 	mutex_unlock(&blkcg_pol_mutex);
 
 	/* everything is in place, add intf files for the new policy */
+	if (pol->dfl_cftypes)
+		WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys,
+					       pol->dfl_cftypes));
 	if (pol->legacy_cftypes)
 		WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys,
 						  pol->legacy_cftypes));
@@ -1312,6 +1363,8 @@ void blkcg_policy_unregister(struct blkcg_policy *pol)
 		goto out_unlock;
 
 	/* kill the intf files first */
+	if (pol->dfl_cftypes)
+		cgroup_rm_cftypes(pol->dfl_cftypes);
 	if (pol->legacy_cftypes)
 		cgroup_rm_cftypes(pol->legacy_cftypes);