#include <linux/module.h>
#include <linux/err.h>
#include <linux/blkdev.h>
+#include <linux/slab.h>
#include "blk-cgroup.h"
+#include <linux/genhd.h>
#define MAX_KEY_LEN 100
};
EXPORT_SYMBOL_GPL(blkio_subsys);
+static inline void blkio_policy_insert_node(struct blkio_cgroup *blkcg,
+ struct blkio_policy_node *pn)
+{
+ list_add(&pn->node, &blkcg->policy_list);
+}
+
+/* Must be called with blkcg->lock held */
+static inline void blkio_policy_delete_node(struct blkio_policy_node *pn)
+{
+ list_del(&pn->node);
+}
+
+/* Must be called with blkcg->lock held */
+static struct blkio_policy_node *
+blkio_policy_search_node(const struct blkio_cgroup *blkcg, dev_t dev)
+{
+ struct blkio_policy_node *pn;
+
+ list_for_each_entry(pn, &blkcg->policy_list, node) {
+ if (pn->dev == dev)
+ return pn;
+ }
+
+ return NULL;
+}
+
struct blkio_cgroup *cgroup_to_blkio_cgroup(struct cgroup *cgroup)
{
return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
}
EXPORT_SYMBOL_GPL(cgroup_to_blkio_cgroup);
-void blkio_group_init(struct blkio_group *blkg)
-{
- spin_lock_init(&blkg->stats_lock);
-}
-EXPORT_SYMBOL_GPL(blkio_group_init);
-
/*
* Add to the appropriate stat variable depending on the request type.
* This should be called with the blkg->stats_lock held.
}
EXPORT_SYMBOL_GPL(blkiocg_update_idle_time_stats);
-void blkiocg_update_set_active_queue_stats(struct blkio_group *blkg)
+void blkiocg_update_avg_queue_size_stats(struct blkio_group *blkg)
{
unsigned long flags;
struct blkio_group_stats *stats;
blkio_update_group_wait_time(stats);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
-EXPORT_SYMBOL_GPL(blkiocg_update_set_active_queue_stats);
+EXPORT_SYMBOL_GPL(blkiocg_update_avg_queue_size_stats);
+
+void blkiocg_set_start_empty_time(struct blkio_group *blkg)
+{
+ unsigned long flags;
+ struct blkio_group_stats *stats;
+
+ spin_lock_irqsave(&blkg->stats_lock, flags);
+ stats = &blkg->stats;
+
+ if (stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] ||
+ stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]) {
+ spin_unlock_irqrestore(&blkg->stats_lock, flags);
+ return;
+ }
+
+ /*
+ * group is already marked empty. This can happen if cfqq got new
+ * request in parent group and moved to this group while being added
+ * to service tree. Just ignore the event and move on.
+ */
+ if(blkio_blkg_empty(stats)) {
+ spin_unlock_irqrestore(&blkg->stats_lock, flags);
+ return;
+ }
+
+ stats->start_empty_time = sched_clock();
+ blkio_mark_blkg_empty(stats);
+ spin_unlock_irqrestore(&blkg->stats_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blkiocg_set_start_empty_time);
+
+void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
+ unsigned long dequeue)
+{
+ blkg->stats.dequeue += dequeue;
+}
+EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats);
#else
static inline void blkio_set_start_group_wait_time(struct blkio_group *blkg,
struct blkio_group *curr_blkg) {}
static inline void blkio_end_empty_time(struct blkio_group_stats *stats) {}
#endif
-void blkiocg_update_request_add_stats(struct blkio_group *blkg,
+void blkiocg_update_io_add_stats(struct blkio_group *blkg,
struct blkio_group *curr_blkg, bool direction,
bool sync)
{
blkio_set_start_group_wait_time(blkg, curr_blkg);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
-EXPORT_SYMBOL_GPL(blkiocg_update_request_add_stats);
+EXPORT_SYMBOL_GPL(blkiocg_update_io_add_stats);
-void blkiocg_update_request_remove_stats(struct blkio_group *blkg,
+void blkiocg_update_io_remove_stats(struct blkio_group *blkg,
bool direction, bool sync)
{
unsigned long flags;
direction, sync);
spin_unlock_irqrestore(&blkg->stats_lock, flags);
}
-EXPORT_SYMBOL_GPL(blkiocg_update_request_remove_stats);
+EXPORT_SYMBOL_GPL(blkiocg_update_io_remove_stats);
void blkiocg_update_timeslice_used(struct blkio_group *blkg, unsigned long time)
{
}
EXPORT_SYMBOL_GPL(blkiocg_update_timeslice_used);
-void blkiocg_set_start_empty_time(struct blkio_group *blkg, bool ignore)
-{
- unsigned long flags;
- struct blkio_group_stats *stats;
-
- spin_lock_irqsave(&blkg->stats_lock, flags);
- stats = &blkg->stats;
-
- if (stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_READ] ||
- stats->stat_arr[BLKIO_STAT_QUEUED][BLKIO_STAT_WRITE]) {
- spin_unlock_irqrestore(&blkg->stats_lock, flags);
- return;
- }
-
- /*
- * If ignore is set, we do not panic on the empty flag being set
- * already. This is to avoid cases where there are superfluous timeslice
- * complete events (for eg., forced_dispatch in CFQ) when no IOs are
- * served which could result in triggering the empty check incorrectly.
- */
- BUG_ON(!ignore && blkio_blkg_empty(stats));
- stats->start_empty_time = sched_clock();
- blkio_mark_blkg_empty(stats);
- spin_unlock_irqrestore(&blkg->stats_lock, flags);
-}
-EXPORT_SYMBOL_GPL(blkiocg_set_start_empty_time);
-
void blkiocg_update_dispatch_stats(struct blkio_group *blkg,
uint64_t bytes, bool direction, bool sync)
{
unsigned long flags;
spin_lock_irqsave(&blkcg->lock, flags);
+ spin_lock_init(&blkg->stats_lock);
rcu_assign_pointer(blkg->key, key);
blkg->blkcg_id = css_id(&blkcg->css);
hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
spin_unlock_irqrestore(&blkcg->lock, flags);
-#ifdef CONFIG_DEBUG_BLK_CGROUP
/* Need to take css reference ? */
cgroup_path(blkcg->css.cgroup, blkg->path, sizeof(blkg->path));
-#endif
blkg->dev = dev;
}
EXPORT_SYMBOL_GPL(blkiocg_add_blkio_group);
rcu_read_lock();
css = css_lookup(&blkio_subsys, blkg->blkcg_id);
- if (!css)
- goto out;
-
- blkcg = container_of(css, struct blkio_cgroup, css);
- spin_lock_irqsave(&blkcg->lock, flags);
- if (!hlist_unhashed(&blkg->blkcg_node)) {
- __blkiocg_del_blkio_group(blkg);
- ret = 0;
+ if (css) {
+ blkcg = container_of(css, struct blkio_cgroup, css);
+ spin_lock_irqsave(&blkcg->lock, flags);
+ if (!hlist_unhashed(&blkg->blkcg_node)) {
+ __blkiocg_del_blkio_group(blkg);
+ ret = 0;
+ }
+ spin_unlock_irqrestore(&blkcg->lock, flags);
}
- spin_unlock_irqrestore(&blkcg->lock, flags);
-out:
+
rcu_read_unlock();
return ret;
}
struct blkio_group *blkg;
struct hlist_node *n;
struct blkio_policy_type *blkiop;
+ struct blkio_policy_node *pn;
if (val < BLKIO_WEIGHT_MIN || val > BLKIO_WEIGHT_MAX)
return -EINVAL;
spin_lock(&blkio_list_lock);
spin_lock_irq(&blkcg->lock);
blkcg->weight = (unsigned int)val;
+
hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
+ pn = blkio_policy_search_node(blkcg, blkg->dev);
+
+ if (pn)
+ continue;
+
list_for_each_entry(blkiop, &blkio_list, list)
blkiop->ops.blkio_update_group_weight_fn(blkg,
blkcg->weight);
#endif
#undef SHOW_FUNCTION_PER_GROUP
-#ifdef CONFIG_DEBUG_BLK_CGROUP
-void blkiocg_update_dequeue_stats(struct blkio_group *blkg,
- unsigned long dequeue)
+static int blkio_check_dev_num(dev_t dev)
{
- blkg->stats.dequeue += dequeue;
+ int part = 0;
+ struct gendisk *disk;
+
+ disk = get_gendisk(dev, &part);
+ if (!disk || part)
+ return -ENODEV;
+
+ return 0;
+}
+
+static int blkio_policy_parse_and_set(char *buf,
+ struct blkio_policy_node *newpn)
+{
+ char *s[4], *p, *major_s = NULL, *minor_s = NULL;
+ int ret;
+ unsigned long major, minor, temp;
+ int i = 0;
+ dev_t dev;
+
+ memset(s, 0, sizeof(s));
+
+ while ((p = strsep(&buf, " ")) != NULL) {
+ if (!*p)
+ continue;
+
+ s[i++] = p;
+
+ /* Prevent from inputing too many things */
+ if (i == 3)
+ break;
+ }
+
+ if (i != 2)
+ return -EINVAL;
+
+ p = strsep(&s[0], ":");
+ if (p != NULL)
+ major_s = p;
+ else
+ return -EINVAL;
+
+ minor_s = s[0];
+ if (!minor_s)
+ return -EINVAL;
+
+ ret = strict_strtoul(major_s, 10, &major);
+ if (ret)
+ return -EINVAL;
+
+ ret = strict_strtoul(minor_s, 10, &minor);
+ if (ret)
+ return -EINVAL;
+
+ dev = MKDEV(major, minor);
+
+ ret = blkio_check_dev_num(dev);
+ if (ret)
+ return ret;
+
+ newpn->dev = dev;
+
+ if (s[1] == NULL)
+ return -EINVAL;
+
+ ret = strict_strtoul(s[1], 10, &temp);
+ if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) ||
+ temp > BLKIO_WEIGHT_MAX)
+ return -EINVAL;
+
+ newpn->weight = temp;
+
+ return 0;
+}
+
+unsigned int blkcg_get_weight(struct blkio_cgroup *blkcg,
+ dev_t dev)
+{
+ struct blkio_policy_node *pn;
+
+ pn = blkio_policy_search_node(blkcg, dev);
+ if (pn)
+ return pn->weight;
+ else
+ return blkcg->weight;
+}
+EXPORT_SYMBOL_GPL(blkcg_get_weight);
+
+
+static int blkiocg_weight_device_write(struct cgroup *cgrp, struct cftype *cft,
+ const char *buffer)
+{
+ int ret = 0;
+ char *buf;
+ struct blkio_policy_node *newpn, *pn;
+ struct blkio_cgroup *blkcg;
+ struct blkio_group *blkg;
+ int keep_newpn = 0;
+ struct hlist_node *n;
+ struct blkio_policy_type *blkiop;
+
+ buf = kstrdup(buffer, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ newpn = kzalloc(sizeof(*newpn), GFP_KERNEL);
+ if (!newpn) {
+ ret = -ENOMEM;
+ goto free_buf;
+ }
+
+ ret = blkio_policy_parse_and_set(buf, newpn);
+ if (ret)
+ goto free_newpn;
+
+ blkcg = cgroup_to_blkio_cgroup(cgrp);
+
+ spin_lock_irq(&blkcg->lock);
+
+ pn = blkio_policy_search_node(blkcg, newpn->dev);
+ if (!pn) {
+ if (newpn->weight != 0) {
+ blkio_policy_insert_node(blkcg, newpn);
+ keep_newpn = 1;
+ }
+ spin_unlock_irq(&blkcg->lock);
+ goto update_io_group;
+ }
+
+ if (newpn->weight == 0) {
+ /* weight == 0 means deleteing a specific weight */
+ blkio_policy_delete_node(pn);
+ spin_unlock_irq(&blkcg->lock);
+ goto update_io_group;
+ }
+ spin_unlock_irq(&blkcg->lock);
+
+ pn->weight = newpn->weight;
+
+update_io_group:
+ /* update weight for each cfqg */
+ spin_lock(&blkio_list_lock);
+ spin_lock_irq(&blkcg->lock);
+
+ hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
+ if (newpn->dev == blkg->dev) {
+ list_for_each_entry(blkiop, &blkio_list, list)
+ blkiop->ops.blkio_update_group_weight_fn(blkg,
+ newpn->weight ?
+ newpn->weight :
+ blkcg->weight);
+ }
+ }
+
+ spin_unlock_irq(&blkcg->lock);
+ spin_unlock(&blkio_list_lock);
+
+free_newpn:
+ if (!keep_newpn)
+ kfree(newpn);
+free_buf:
+ kfree(buf);
+ return ret;
+}
+
+static int blkiocg_weight_device_read(struct cgroup *cgrp, struct cftype *cft,
+ struct seq_file *m)
+{
+ struct blkio_cgroup *blkcg;
+ struct blkio_policy_node *pn;
+
+ seq_printf(m, "dev\tweight\n");
+
+ blkcg = cgroup_to_blkio_cgroup(cgrp);
+ if (!list_empty(&blkcg->policy_list)) {
+ spin_lock_irq(&blkcg->lock);
+ list_for_each_entry(pn, &blkcg->policy_list, node) {
+ seq_printf(m, "%u:%u\t%u\n", MAJOR(pn->dev),
+ MINOR(pn->dev), pn->weight);
+ }
+ spin_unlock_irq(&blkcg->lock);
+ }
+
+ return 0;
}
-EXPORT_SYMBOL_GPL(blkiocg_update_dequeue_stats);
-#endif
struct cftype blkio_files[] = {
{
+ .name = "weight_device",
+ .read_seq_string = blkiocg_weight_device_read,
+ .write_string = blkiocg_weight_device_write,
+ .max_write_len = 256,
+ },
+ {
.name = "weight",
.read_u64 = blkiocg_weight_read,
.write_u64 = blkiocg_weight_write,
struct blkio_group *blkg;
void *key;
struct blkio_policy_type *blkiop;
+ struct blkio_policy_node *pn, *pntmp;
rcu_read_lock();
-remove_entry:
- spin_lock_irqsave(&blkcg->lock, flags);
+ do {
+ spin_lock_irqsave(&blkcg->lock, flags);
+
+ if (hlist_empty(&blkcg->blkg_list)) {
+ spin_unlock_irqrestore(&blkcg->lock, flags);
+ break;
+ }
+
+ blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group,
+ blkcg_node);
+ key = rcu_dereference(blkg->key);
+ __blkiocg_del_blkio_group(blkg);
- if (hlist_empty(&blkcg->blkg_list)) {
spin_unlock_irqrestore(&blkcg->lock, flags);
- goto done;
- }
- blkg = hlist_entry(blkcg->blkg_list.first, struct blkio_group,
- blkcg_node);
- key = rcu_dereference(blkg->key);
- __blkiocg_del_blkio_group(blkg);
+ /*
+ * This blkio_group is being unlinked as associated cgroup is
+ * going away. Let all the IO controlling policies know about
+ * this event. Currently this is static call to one io
+ * controlling policy. Once we have more policies in place, we
+ * need some dynamic registration of callback function.
+ */
+ spin_lock(&blkio_list_lock);
+ list_for_each_entry(blkiop, &blkio_list, list)
+ blkiop->ops.blkio_unlink_group_fn(key, blkg);
+ spin_unlock(&blkio_list_lock);
+ } while (1);
- spin_unlock_irqrestore(&blkcg->lock, flags);
+ list_for_each_entry_safe(pn, pntmp, &blkcg->policy_list, node) {
+ blkio_policy_delete_node(pn);
+ kfree(pn);
+ }
- /*
- * This blkio_group is being unlinked as associated cgroup is going
- * away. Let all the IO controlling policies know about this event.
- *
- * Currently this is static call to one io controlling policy. Once
- * we have more policies in place, we need some dynamic registration
- * of callback function.
- */
- spin_lock(&blkio_list_lock);
- list_for_each_entry(blkiop, &blkio_list, list)
- blkiop->ops.blkio_unlink_group_fn(key, blkg);
- spin_unlock(&blkio_list_lock);
- goto remove_entry;
-done:
free_css_id(&blkio_subsys, &blkcg->css);
rcu_read_unlock();
if (blkcg != &blkio_root_cgroup)
static struct cgroup_subsys_state *
blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
{
- struct blkio_cgroup *blkcg, *parent_blkcg;
+ struct blkio_cgroup *blkcg;
+ struct cgroup *parent = cgroup->parent;
- if (!cgroup->parent) {
+ if (!parent) {
blkcg = &blkio_root_cgroup;
goto done;
}
/* Currently we do not support hierarchy deeper than two level (0,1) */
- parent_blkcg = cgroup_to_blkio_cgroup(cgroup->parent);
- if (css_depth(&parent_blkcg->css) > 0)
+ if (parent != cgroup->top_cgroup)
return ERR_PTR(-EINVAL);
blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
spin_lock_init(&blkcg->lock);
INIT_HLIST_HEAD(&blkcg->blkg_list);
+ INIT_LIST_HEAD(&blkcg->policy_list);
return &blkcg->css;
}