@@ -95,6 +95,9 @@ struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
spin_lock_init(&ret->lock);
ret->ioprio_changed = 0;
ret->ioprio = 0;
+#ifdef CONFIG_GROUP_IOSCHED
+ ret->cgroup_changed = 0;
+#endif
ret->last_waited = jiffies; /* doesn't matter... */
ret->nr_batch_requests = 0; /* because this is 0 */
ret->aic = NULL;
@@ -265,7 +265,7 @@ static void entity_served(struct io_entity *entity, unsigned long served,
unsigned long charge = queue_charge;
for_each_entity(entity) {
- entity->vdisktime += elv_delta_fair(queue_charge, entity);
+ entity->vdisktime += elv_delta_fair(charge, entity);
update_min_vdisktime(entity->st);
/* Group charge can be different from queue charge */
charge = group_charge;
@@ -920,6 +920,173 @@ EXPORT_SYMBOL(elv_io_group_set_async_queue);
#ifdef CONFIG_GROUP_IOSCHED
+struct io_cgroup io_root_cgroup = {
+ .weight = IO_WEIGHT_DEFAULT,
+ .ioprio_class = IOPRIO_CLASS_BE,
+};
+
+static struct io_cgroup *cgroup_to_io_cgroup(struct cgroup *cgroup)
+{
+ return container_of(cgroup_subsys_state(cgroup, io_subsys_id),
+ struct io_cgroup, css);
+}
+
+#define SHOW_FUNCTION(__VAR) \
+static u64 io_cgroup_##__VAR##_read(struct cgroup *cgroup, \
+ struct cftype *cftype) \
+{ \
+ struct io_cgroup *iocg; \
+ u64 ret; \
+ \
+ if (!cgroup_lock_live_group(cgroup)) \
+ return -ENODEV; \
+ \
+ iocg = cgroup_to_io_cgroup(cgroup); \
+ spin_lock_irq(&iocg->lock); \
+ ret = iocg->__VAR; \
+ spin_unlock_irq(&iocg->lock); \
+ \
+ cgroup_unlock(); \
+ \
+ return ret; \
+}
+
+SHOW_FUNCTION(weight);
+SHOW_FUNCTION(ioprio_class);
+#undef SHOW_FUNCTION
+
+#define STORE_FUNCTION(__VAR, __MIN, __MAX) \
+static int io_cgroup_##__VAR##_write(struct cgroup *cgroup, \
+ struct cftype *cftype, \
+ u64 val) \
+{ \
+ struct io_cgroup *iocg; \
+ struct io_group *iog; \
+ struct hlist_node *n; \
+ \
+ if (val < (__MIN) || val > (__MAX)) \
+ return -EINVAL; \
+ \
+ if (!cgroup_lock_live_group(cgroup)) \
+ return -ENODEV; \
+ \
+ iocg = cgroup_to_io_cgroup(cgroup); \
+ \
+ spin_lock_irq(&iocg->lock); \
+ iocg->__VAR = (unsigned long)val; \
+ hlist_for_each_entry(iog, n, &iocg->group_data, group_node) { \
+ iog->entity.__VAR = (unsigned long)val; \
+ smp_wmb(); \
+ iog->entity.ioprio_changed = 1; \
+ } \
+ spin_unlock_irq(&iocg->lock); \
+ \
+ cgroup_unlock(); \
+ \
+ return 0; \
+}
+
+STORE_FUNCTION(weight, IO_WEIGHT_MIN, IO_WEIGHT_MAX);
+STORE_FUNCTION(ioprio_class, IOPRIO_CLASS_RT, IOPRIO_CLASS_IDLE);
+#undef STORE_FUNCTION
+
+struct cftype io_files[] = {
+ {
+ .name = "weight",
+ .read_u64 = io_cgroup_weight_read,
+ .write_u64 = io_cgroup_weight_write,
+ },
+ {
+ .name = "ioprio_class",
+ .read_u64 = io_cgroup_ioprio_class_read,
+ .write_u64 = io_cgroup_ioprio_class_write,
+ },
+};
+
+static int iocg_populate(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+ return cgroup_add_files(cgroup, subsys, io_files, ARRAY_SIZE(io_files));
+}
+
+static struct cgroup_subsys_state *iocg_create(struct cgroup_subsys *subsys,
+ struct cgroup *cgroup)
+{
+ struct io_cgroup *iocg;
+
+ if (cgroup->parent != NULL) {
+ iocg = kzalloc(sizeof(*iocg), GFP_KERNEL);
+ if (iocg == NULL)
+ return ERR_PTR(-ENOMEM);
+ } else
+ iocg = &io_root_cgroup;
+
+ spin_lock_init(&iocg->lock);
+ INIT_HLIST_HEAD(&iocg->group_data);
+ iocg->weight = IO_WEIGHT_DEFAULT;
+ iocg->ioprio_class = IOPRIO_CLASS_BE;
+
+ return &iocg->css;
+}
+
+/*
+ * We cannot support shared io contexts, as we have no mean to support
+ * two tasks with the same ioc in two different groups without major rework
+ * of the main cic data structures. By now we allow a task to change
+ * its cgroup only if it's the only owner of its ioc; the drawback of this
+ * behavior is that a group containing a task that forked using CLONE_IO
+ * will not be destroyed until the tasks sharing the ioc die.
+ */
+static int iocg_can_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup,
+ struct task_struct *tsk)
+{
+ struct io_context *ioc;
+ int ret = 0;
+
+ /* task_lock() is needed to avoid races with exit_io_context() */
+ task_lock(tsk);
+ ioc = tsk->io_context;
+ if (ioc != NULL && atomic_read(&ioc->nr_tasks) > 1)
+ /*
+ * ioc == NULL means that the task is either too young or
+ * exiting: if it has still no ioc the ioc can't be shared,
+ * if the task is exiting the attach will fail anyway, no
+ * matter what we return here.
+ */
+ ret = -EINVAL;
+ task_unlock(tsk);
+
+ return ret;
+}
+
+static void iocg_attach(struct cgroup_subsys *subsys, struct cgroup *cgroup,
+ struct cgroup *prev, struct task_struct *tsk)
+{
+ struct io_context *ioc;
+
+ task_lock(tsk);
+ ioc = tsk->io_context;
+ if (ioc != NULL)
+ ioc->cgroup_changed = 1;
+ task_unlock(tsk);
+}
+
+static void iocg_destroy(struct cgroup_subsys *subsys, struct cgroup *cgroup)
+{
+
+ /* Implemented in later patch */
+}
+
+struct cgroup_subsys io_subsys = {
+ .name = "io",
+ .create = iocg_create,
+ .can_attach = iocg_can_attach,
+ .attach = iocg_attach,
+ .destroy = iocg_destroy,
+ .populate = iocg_populate,
+ .subsys_id = io_subsys_id,
+ .use_id = 1,
+};
+
static void io_free_root_group(struct elevator_queue *e)
{
struct io_group *iog = e->efqd->root_group;
@@ -13,6 +13,7 @@
#ifdef CONFIG_BLOCK
#include <linux/blkdev.h>
+#include <linux/cgroup.h>
#ifndef _ELV_SCHED_H
#define _ELV_SCHED_H
@@ -98,6 +99,8 @@ struct io_group {
struct io_entity entity;
atomic_t ref;
struct io_sched_data sched_data;
+ struct hlist_node group_node;
+ unsigned short iocg_id;
/*
* async queue for each priority case for RT and BE class.
* Used only for cfq.
@@ -108,6 +111,17 @@ struct io_group {
void *key;
};
+struct io_cgroup {
+ struct cgroup_subsys_state css;
+
+ unsigned int weight;
+ unsigned short ioprio_class;
+
+ spinlock_t lock;
+ struct hlist_head group_data;
+};
+
+
#else /* CONFIG_GROUP_IOSCHED */
struct io_group {
@@ -60,3 +60,9 @@ SUBSYS(net_cls)
#endif
/* */
+
+#ifdef CONFIG_GROUP_IOSCHED
+SUBSYS(io)
+#endif
+
+/* */
@@ -73,6 +73,11 @@ struct io_context {
unsigned short ioprio;
unsigned short ioprio_changed;
+#ifdef CONFIG_GROUP_IOSCHED
+ /* If task changes the cgroup, elevator processes it asynchronously */
+ unsigned short cgroup_changed;
+#endif
+
/*
* For request batching
*/