block/mq-deadline: Add cgroup support

Maintain statistics per cgroup and export these to user space. These
statistics are essential for verifying whether the proper I/O priorities
have been assigned to requests. An example of the statistics data with
this patch applied:

$ cat /sys/fs/cgroup/io.stat
11:2 rbytes=0 wbytes=0 rios=3 wios=0 dbytes=0 dios=0 [NONE] dispatched=0 inserted=0 merged=171 [RT] dispatched=0 inserted=0 merged=0 [BE] dispatched=0 inserted=0 merged=0 [IDLE] dispatched=0 inserted=0 merged=0
8:32 rbytes=2142720 wbytes=0 rios=105 wios=0 dbytes=0 dios=0 [NONE] dispatched=0 inserted=0 merged=171 [RT] dispatched=0 inserted=0 merged=0 [BE] dispatched=0 inserted=0 merged=0 [IDLE] dispatched=0 inserted=0 merged=0

Cc: Damien Le Moal <[email protected]>
Cc: Hannes Reinecke <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Ming Lei <[email protected]>
Cc: Johannes Thumshirn <[email protected]>
Cc: Himanshu Madhani <[email protected]>
Signed-off-by: Bart Van Assche <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>

block/Kconfig.iosched

@@ -9,6 +9,12 @@ config MQ_IOSCHED_DEADLINE
 	help
 	  MQ version of the deadline IO scheduler.
 
+config MQ_IOSCHED_DEADLINE_CGROUP
+       tristate
+       default y
+       depends on MQ_IOSCHED_DEADLINE
+       depends on BLK_CGROUP
+
 config MQ_IOSCHED_KYBER
 	tristate "Kyber I/O scheduler"
 	default y

block/Makefile

@@ -21,6 +21,8 @@ obj-$(CONFIG_BLK_CGROUP_IOPRIO)	+= blk-ioprio.o
 obj-$(CONFIG_BLK_CGROUP_IOLATENCY)	+= blk-iolatency.o
 obj-$(CONFIG_BLK_CGROUP_IOCOST)	+= blk-iocost.o
 obj-$(CONFIG_MQ_IOSCHED_DEADLINE)	+= mq-deadline.o
+mq-deadline-y += mq-deadline-main.o
+mq-deadline-$(CONFIG_MQ_IOSCHED_DEADLINE_CGROUP)+= mq-deadline-cgroup.o
 obj-$(CONFIG_MQ_IOSCHED_KYBER)	+= kyber-iosched.o
 bfq-y				:= bfq-iosched.o bfq-wf2q.o bfq-cgroup.o
 obj-$(CONFIG_IOSCHED_BFQ)	+= bfq.o

block/mq-deadline-cgroup.c

@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/blk-cgroup.h>
+#include <linux/ioprio.h>
+
+#include "mq-deadline-cgroup.h"
+
+static struct blkcg_policy dd_blkcg_policy;
+
+static struct blkcg_policy_data *dd_cpd_alloc(gfp_t gfp)
+{
+	struct dd_blkcg *pd;
+
+	pd = kzalloc(sizeof(*pd), gfp);
+	if (!pd)
+		return NULL;
+	pd->stats = alloc_percpu_gfp(typeof(*pd->stats),
+				     GFP_KERNEL | __GFP_ZERO);
+	if (!pd->stats) {
+		kfree(pd);
+		return NULL;
+	}
+	return &pd->cpd;
+}
+
+static void dd_cpd_free(struct blkcg_policy_data *cpd)
+{
+	struct dd_blkcg *dd_blkcg = container_of(cpd, typeof(*dd_blkcg), cpd);
+
+	free_percpu(dd_blkcg->stats);
+	kfree(dd_blkcg);
+}
+
+static struct dd_blkcg *dd_blkcg_from_pd(struct blkg_policy_data *pd)
+{
+	return container_of(blkcg_to_cpd(pd->blkg->blkcg, &dd_blkcg_policy),
+			    struct dd_blkcg, cpd);
+}
+
+/*
+ * Convert an association between a block cgroup and a request queue into a
+ * pointer to the mq-deadline information associated with a (blkcg, queue) pair.
+ */
+struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio)
+{
+	struct blkg_policy_data *pd;
+
+	pd = blkg_to_pd(bio->bi_blkg, &dd_blkcg_policy);
+	if (!pd)
+		return NULL;
+
+	return dd_blkcg_from_pd(pd);
+}
+
+static size_t dd_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size)
+{
+	static const char *const prio_class_name[] = {
+		[IOPRIO_CLASS_NONE]	= "NONE",
+		[IOPRIO_CLASS_RT]	= "RT",
+		[IOPRIO_CLASS_BE]	= "BE",
+		[IOPRIO_CLASS_IDLE]	= "IDLE",
+	};
+	struct dd_blkcg *blkcg = dd_blkcg_from_pd(pd);
+	int res = 0;
+	u8 prio;
+
+	for (prio = 0; prio < ARRAY_SIZE(blkcg->stats->stats); prio++)
+		res += scnprintf(buf + res, size - res,
+			" [%s] dispatched=%u inserted=%u merged=%u",
+			prio_class_name[prio],
+			ddcg_sum(blkcg, dispatched, prio) +
+			ddcg_sum(blkcg, merged, prio) -
+			ddcg_sum(blkcg, completed, prio),
+			ddcg_sum(blkcg, inserted, prio) -
+			ddcg_sum(blkcg, completed, prio),
+			ddcg_sum(blkcg, merged, prio));
+
+	return res;
+}
+
+static struct blkg_policy_data *dd_pd_alloc(gfp_t gfp, struct request_queue *q,
+					    struct blkcg *blkcg)
+{
+	struct dd_blkg *pd;
+
+	pd = kzalloc(sizeof(*pd), gfp);
+	if (!pd)
+		return NULL;
+	return &pd->pd;
+}
+
+static void dd_pd_free(struct blkg_policy_data *pd)
+{
+	struct dd_blkg *dd_blkg = container_of(pd, typeof(*dd_blkg), pd);
+
+	kfree(dd_blkg);
+}
+
+static struct blkcg_policy dd_blkcg_policy = {
+	.cpd_alloc_fn		= dd_cpd_alloc,
+	.cpd_free_fn		= dd_cpd_free,
+
+	.pd_alloc_fn		= dd_pd_alloc,
+	.pd_free_fn		= dd_pd_free,
+	.pd_stat_fn		= dd_pd_stat,
+};
+
+int dd_activate_policy(struct request_queue *q)
+{
+	return blkcg_activate_policy(q, &dd_blkcg_policy);
+}
+
+void dd_deactivate_policy(struct request_queue *q)
+{
+	blkcg_deactivate_policy(q, &dd_blkcg_policy);
+}
+
+int __init dd_blkcg_init(void)
+{
+	return blkcg_policy_register(&dd_blkcg_policy);
+}
+
+void __exit dd_blkcg_exit(void)
+{
+	blkcg_policy_unregister(&dd_blkcg_policy);
+}

block/mq-deadline-cgroup.h

@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#if !defined(_MQ_DEADLINE_CGROUP_H_)
+#define _MQ_DEADLINE_CGROUP_H_
+
+#include <linux/blk-cgroup.h>
+
+struct request_queue;
+
+/**
+ * struct io_stats_per_prio - I/O statistics per I/O priority class.
+ * @inserted: Number of inserted requests.
+ * @merged: Number of merged requests.
+ * @dispatched: Number of dispatched requests.
+ * @completed: Number of I/O completions.
+ */
+struct io_stats_per_prio {
+	local_t inserted;
+	local_t merged;
+	local_t dispatched;
+	local_t completed;
+};
+
+/* I/O statistics per I/O cgroup per I/O priority class (IOPRIO_CLASS_*). */
+struct blkcg_io_stats {
+	struct io_stats_per_prio stats[4];
+};
+
+/**
+ * struct dd_blkcg - Per cgroup data.
+ * @cpd: blkcg_policy_data structure.
+ * @stats: I/O statistics.
+ */
+struct dd_blkcg {
+	struct blkcg_policy_data cpd;	/* must be the first member */
+	struct blkcg_io_stats __percpu *stats;
+};
+
+/*
+ * Count one event of type 'event_type' and with I/O priority class
+ * 'prio_class'.
+ */
+#define ddcg_count(ddcg, event_type, prio_class) do {			\
+if (ddcg) {								\
+	struct blkcg_io_stats *io_stats = get_cpu_ptr((ddcg)->stats);	\
+									\
+	BUILD_BUG_ON(!__same_type((ddcg), struct dd_blkcg *));		\
+	BUILD_BUG_ON(!__same_type((prio_class), u8));			\
+	local_inc(&io_stats->stats[(prio_class)].event_type);		\
+	put_cpu_ptr(io_stats);						\
+}									\
+} while (0)
+
+/*
+ * Returns the total number of ddcg_count(ddcg, event_type, prio_class) calls
+ * across all CPUs. No locking or barriers since it is fine if the returned
+ * sum is slightly outdated.
+ */
+#define ddcg_sum(ddcg, event_type, prio) ({				\
+	unsigned int cpu;						\
+	u32 sum = 0;							\
+									\
+	BUILD_BUG_ON(!__same_type((ddcg), struct dd_blkcg *));		\
+	BUILD_BUG_ON(!__same_type((prio), u8));				\
+	for_each_present_cpu(cpu)					\
+		sum += local_read(&per_cpu_ptr((ddcg)->stats, cpu)->	\
+				  stats[(prio)].event_type);		\
+	sum;								\
+})
+
+#ifdef CONFIG_BLK_CGROUP
+
+/**
+ * struct dd_blkg - Per (cgroup, request queue) data.
+ * @pd: blkg_policy_data structure.
+ */
+struct dd_blkg {
+	struct blkg_policy_data pd;	/* must be the first member */
+};
+
+struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio);
+int dd_activate_policy(struct request_queue *q);
+void dd_deactivate_policy(struct request_queue *q);
+int __init dd_blkcg_init(void);
+void __exit dd_blkcg_exit(void);
+
+#else /* CONFIG_BLK_CGROUP */
+
+static inline struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio)
+{
+	return NULL;
+}
+
+static inline int dd_activate_policy(struct request_queue *q)
+{
+	return 0;
+}
+
+static inline void dd_deactivate_policy(struct request_queue *q)
+{
+}
+
+static inline int dd_blkcg_init(void)
+{
+	return 0;
+}
+
+static inline void dd_blkcg_exit(void)
+{
+}
+
+#endif /* CONFIG_BLK_CGROUP */
+
+#endif /* _MQ_DEADLINE_CGROUP_H_ */