#include <linux/cgroup.h>
#include <linux/u64_stats_sync.h>
#include <linux/seq_file.h>
-
-enum blkio_policy_id {
- BLKIO_POLICY_PROP = 0, /* Proportional Bandwidth division */
- BLKIO_POLICY_THROTL, /* Throttling */
-
- BLKIO_NR_POLICIES,
-};
+#include <linux/radix-tree.h>
/* Max limits for throttle policy */
#define THROTL_IOPS_MAX UINT_MAX
-#ifdef CONFIG_BLK_CGROUP
+/* CFQ specific, out here for blkcg->cfq_weight */
+#define CFQ_WEIGHT_MIN 10
+#define CFQ_WEIGHT_MAX 1000
+#define CFQ_WEIGHT_DEFAULT 500
-/* cft->private [un]packing for stat printing */
-#define BLKCG_STAT_PRIV(pol, off) (((unsigned)(pol) << 16) | (off))
-#define BLKCG_STAT_POL(prv) ((unsigned)(prv) >> 16)
-#define BLKCG_STAT_OFF(prv) ((unsigned)(prv) & 0xffff)
+#ifdef CONFIG_BLK_CGROUP
enum blkg_rwstat_type {
BLKG_RWSTAT_READ,
BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
};
-struct blkio_cgroup {
- struct cgroup_subsys_state css;
- unsigned int weight;
- spinlock_t lock;
- struct hlist_head blkg_list;
+struct blkcg_gq;
+
+struct blkcg {
+ struct cgroup_subsys_state css;
+ spinlock_t lock;
+
+ struct radix_tree_root blkg_tree;
+ struct blkcg_gq *blkg_hint;
+ struct hlist_head blkg_list;
/* for policies to test whether associated blkcg has changed */
- uint64_t id;
+ uint64_t id;
+
+ /* TODO: per-policy storage in blkcg */
+ unsigned int cfq_weight; /* belongs to cfq */
};
struct blkg_stat {
uint64_t cnt[BLKG_RWSTAT_NR];
};
-struct blkio_group_stats {
- /* number of ios merged */
- struct blkg_rwstat merged;
- /* total time spent on device in ns, may not be accurate w/ queueing */
- struct blkg_rwstat service_time;
- /* total time spent waiting in scheduler queue in ns */
- struct blkg_rwstat wait_time;
- /* number of IOs queued up */
- struct blkg_rwstat queued;
- /* total disk time and nr sectors dispatched by this group */
- struct blkg_stat time;
-#ifdef CONFIG_DEBUG_BLK_CGROUP
- /* time not charged to this cgroup */
- struct blkg_stat unaccounted_time;
- /* sum of number of ios queued across all samples */
- struct blkg_stat avg_queue_size_sum;
- /* count of samples taken for average */
- struct blkg_stat avg_queue_size_samples;
- /* how many times this group has been removed from service tree */
- struct blkg_stat dequeue;
- /* total time spent waiting for it to be assigned a timeslice. */
- struct blkg_stat group_wait_time;
- /* time spent idling for this blkio_group */
- struct blkg_stat idle_time;
- /* total time with empty current active q with other requests queued */
- struct blkg_stat empty_time;
- /* fields after this shouldn't be cleared on stat reset */
- uint64_t start_group_wait_time;
- uint64_t start_idle_time;
- uint64_t start_empty_time;
- uint16_t flags;
-#endif
-};
-
-/* Per cpu blkio group stats */
-struct blkio_group_stats_cpu {
- /* total bytes transferred */
- struct blkg_rwstat service_bytes;
- /* total IOs serviced, post merge */
- struct blkg_rwstat serviced;
- /* total sectors transferred */
- struct blkg_stat sectors;
-};
-
-struct blkio_group_conf {
- unsigned int weight;
- u64 iops[2];
- u64 bps[2];
-};
-
-/* per-blkg per-policy data */
+/*
+ * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a
+ * request_queue (q). This is used by blkcg policies which need to track
+ * information per blkcg - q pair.
+ *
+ * There can be multiple active blkcg policies and each has its private
+ * data on each blkg, the size of which is determined by
+ * blkcg_policy->pd_size. blkcg core allocates and frees such areas
+ * together with blkg and invokes pd_init/exit_fn() methods.
+ *
+ * Such private data must embed struct blkg_policy_data (pd) at the
+ * beginning and pd_size can't be smaller than pd.
+ */
struct blkg_policy_data {
/* the blkg this per-policy data belongs to */
- struct blkio_group *blkg;
-
- /* Configuration */
- struct blkio_group_conf conf;
-
- struct blkio_group_stats stats;
- /* Per cpu stats pointer */
- struct blkio_group_stats_cpu __percpu *stats_cpu;
+ struct blkcg_gq *blkg;
- /* pol->pdata_size bytes of private data used by policy impl */
- char pdata[] __aligned(__alignof__(unsigned long long));
+ /* used during policy activation */
+ struct list_head alloc_node;
};
-struct blkio_group {
+/* association between a blk cgroup and a request queue */
+struct blkcg_gq {
/* Pointer to the associated request_queue */
- struct request_queue *q;
- struct list_head q_node;
- struct hlist_node blkcg_node;
- struct blkio_cgroup *blkcg;
- /* Store cgroup path */
- char path[128];
+ struct request_queue *q;
+ struct list_head q_node;
+ struct hlist_node blkcg_node;
+ struct blkcg *blkcg;
/* reference count */
- int refcnt;
+ int refcnt;
- struct blkg_policy_data *pd[BLKIO_NR_POLICIES];
+ struct blkg_policy_data *pd[BLKCG_MAX_POLS];
- /* List of blkg waiting for per cpu stats memory to be allocated */
- struct list_head alloc_node;
- struct rcu_head rcu_head;
+ struct rcu_head rcu_head;
};
-typedef void (blkio_init_group_fn)(struct blkio_group *blkg);
-
-struct blkio_policy_ops {
- blkio_init_group_fn *blkio_init_group_fn;
+typedef void (blkcg_pol_init_pd_fn)(struct blkcg_gq *blkg);
+typedef void (blkcg_pol_exit_pd_fn)(struct blkcg_gq *blkg);
+typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkcg_gq *blkg);
+
+struct blkcg_policy {
+ int plid;
+ /* policy specific private data size */
+ size_t pd_size;
+ /* cgroup files for the policy */
+ struct cftype *cftypes;
+
+ /* operations */
+ blkcg_pol_init_pd_fn *pd_init_fn;
+ blkcg_pol_exit_pd_fn *pd_exit_fn;
+ blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn;
};
-struct blkio_policy_type {
- struct list_head list;
- struct blkio_policy_ops ops;
- enum blkio_policy_id plid;
- size_t pdata_size; /* policy specific private data size */
- struct cftype *cftypes; /* cgroup files for the policy */
-};
+extern struct blkcg blkcg_root;
-extern int blkcg_init_queue(struct request_queue *q);
-extern void blkcg_drain_queue(struct request_queue *q);
-extern void blkcg_exit_queue(struct request_queue *q);
+struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup);
+struct blkcg *bio_blkcg(struct bio *bio);
+struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q);
+struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
+ struct request_queue *q);
+int blkcg_init_queue(struct request_queue *q);
+void blkcg_drain_queue(struct request_queue *q);
+void blkcg_exit_queue(struct request_queue *q);
/* Blkio controller policy registration */
-extern void blkio_policy_register(struct blkio_policy_type *);
-extern void blkio_policy_unregister(struct blkio_policy_type *);
-extern void blkg_destroy_all(struct request_queue *q, bool destroy_root);
-extern void update_root_blkg_pd(struct request_queue *q,
- enum blkio_policy_id plid);
-
-void blkcg_print_blkgs(struct seq_file *sf, struct blkio_cgroup *blkcg,
- u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int),
- int pol, int data, bool show_total);
+int blkcg_policy_register(struct blkcg_policy *pol);
+void blkcg_policy_unregister(struct blkcg_policy *pol);
+int blkcg_activate_policy(struct request_queue *q,
+ const struct blkcg_policy *pol);
+void blkcg_deactivate_policy(struct request_queue *q,
+ const struct blkcg_policy *pol);
+
+void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
+ u64 (*prfill)(struct seq_file *,
+ struct blkg_policy_data *, int),
+ const struct blkcg_policy *pol, int data,
+ bool show_total);
u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v);
u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
const struct blkg_rwstat *rwstat);
-int blkcg_print_stat(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf);
-int blkcg_print_rwstat(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf);
-int blkcg_print_cpu_stat(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf);
-int blkcg_print_cpu_rwstat(struct cgroup *cgrp, struct cftype *cft,
- struct seq_file *sf);
+u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off);
+u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
+ int off);
struct blkg_conf_ctx {
- struct gendisk *disk;
- struct blkio_group *blkg;
- u64 v;
+ struct gendisk *disk;
+ struct blkcg_gq *blkg;
+ u64 v;
};
-int blkg_conf_prep(struct blkio_cgroup *blkcg, const char *input,
- struct blkg_conf_ctx *ctx);
+int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
+ const char *input, struct blkg_conf_ctx *ctx);
void blkg_conf_finish(struct blkg_conf_ctx *ctx);
*
* Return pointer to private data associated with the @blkg-@pol pair.
*/
-static inline void *blkg_to_pdata(struct blkio_group *blkg,
- struct blkio_policy_type *pol)
+static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
+ struct blkcg_policy *pol)
{
- return blkg ? blkg->pd[pol->plid]->pdata : NULL;
+ return blkg ? blkg->pd[pol->plid] : NULL;
}
/**
* pdata_to_blkg - get blkg associated with policy private data
- * @pdata: policy private data of interest
+ * @pd: policy private data of interest
*
- * @pdata is policy private data. Determine the blkg it's associated with.
+ * @pd is policy private data. Determine the blkg it's associated with.
*/
-static inline struct blkio_group *pdata_to_blkg(void *pdata)
+static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd)
{
- if (pdata) {
- struct blkg_policy_data *pd =
- container_of(pdata, struct blkg_policy_data, pdata);
- return pd->blkg;
- }
- return NULL;
+ return pd ? pd->blkg : NULL;
}
-static inline char *blkg_path(struct blkio_group *blkg)
+/**
+ * blkg_path - format cgroup path of blkg
+ * @blkg: blkg of interest
+ * @buf: target buffer
+ * @buflen: target buffer length
+ *
+ * Format the path of the cgroup of @blkg into @buf.
+ */
+static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
{
- return blkg->path;
+ int ret;
+
+ rcu_read_lock();
+ ret = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
+ rcu_read_unlock();
+ if (ret)
+ strncpy(buf, "<unavailable>", buflen);
+ return ret;
}
/**
*
* The caller should be holding queue_lock and an existing reference.
*/
-static inline void blkg_get(struct blkio_group *blkg)
+static inline void blkg_get(struct blkcg_gq *blkg)
{
lockdep_assert_held(blkg->q->queue_lock);
WARN_ON_ONCE(!blkg->refcnt);
blkg->refcnt++;
}
-void __blkg_release(struct blkio_group *blkg);
+void __blkg_release(struct blkcg_gq *blkg);
/**
* blkg_put - put a blkg reference
*
* The caller should be holding queue_lock.
*/
-static inline void blkg_put(struct blkio_group *blkg)
+static inline void blkg_put(struct blkcg_gq *blkg)
{
lockdep_assert_held(blkg->q->queue_lock);
WARN_ON_ONCE(blkg->refcnt <= 0);
* This function can be called without synchronization and takes care of
* u64 atomicity.
*/
-static struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
+static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
{
unsigned int start;
struct blkg_rwstat tmp;
memset(rwstat->cnt, 0, sizeof(rwstat->cnt));
}
-#else
+#else /* CONFIG_BLK_CGROUP */
-struct blkio_group {
+struct cgroup;
+
+struct blkg_policy_data {
+};
+
+struct blkcg_gq {
};
-struct blkio_policy_type {
+struct blkcg_policy {
};
+static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup) { return NULL; }
+static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
+static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
static inline void blkcg_drain_queue(struct request_queue *q) { }
static inline void blkcg_exit_queue(struct request_queue *q) { }
-static inline void blkio_policy_register(struct blkio_policy_type *blkiop) { }
-static inline void blkio_policy_unregister(struct blkio_policy_type *blkiop) { }
-static inline void blkg_destroy_all(struct request_queue *q,
- bool destory_root) { }
-static inline void update_root_blkg_pd(struct request_queue *q,
- enum blkio_policy_id plid) { }
-
-static inline void *blkg_to_pdata(struct blkio_group *blkg,
- struct blkio_policy_type *pol) { return NULL; }
-static inline struct blkio_group *pdata_to_blkg(void *pdata,
- struct blkio_policy_type *pol) { return NULL; }
-static inline char *blkg_path(struct blkio_group *blkg) { return NULL; }
-static inline void blkg_get(struct blkio_group *blkg) { }
-static inline void blkg_put(struct blkio_group *blkg) { }
-
-#endif
-
-#define BLKIO_WEIGHT_MIN 10
-#define BLKIO_WEIGHT_MAX 1000
-#define BLKIO_WEIGHT_DEFAULT 500
-
-#ifdef CONFIG_BLK_CGROUP
-extern struct blkio_cgroup blkio_root_cgroup;
-extern struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup);
-extern struct blkio_cgroup *bio_blkio_cgroup(struct bio *bio);
-extern struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
- struct request_queue *q);
-struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
- struct request_queue *q,
- bool for_root);
-#else
-struct cgroup;
-static inline struct blkio_cgroup *
-cgroup_to_blkio_cgroup(struct cgroup *cgroup) { return NULL; }
-static inline struct blkio_cgroup *
-bio_blkio_cgroup(struct bio *bio) { return NULL; }
-
-static inline struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
- void *key) { return NULL; }
-#endif
-#endif /* _BLK_CGROUP_H */
+static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
+static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { }
+static inline int blkcg_activate_policy(struct request_queue *q,
+ const struct blkcg_policy *pol) { return 0; }
+static inline void blkcg_deactivate_policy(struct request_queue *q,
+ const struct blkcg_policy *pol) { }
+
+static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
+ struct blkcg_policy *pol) { return NULL; }
+static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; }
+static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; }
+static inline void blkg_get(struct blkcg_gq *blkg) { }
+static inline void blkg_put(struct blkcg_gq *blkg) { }
+
+#endif /* CONFIG_BLK_CGROUP */
+#endif /* _BLK_CGROUP_H */