Satoshi UCHIDA
2008-Oct-29 09:12 UTC
[PATCH][cfq-cgroups] Introduce cgroups structure with ioprio entry.
This patch introcude cfq_cgroup structure which is type for
group control within expanded CFQ scheduler.
In addition, the cfq_cgroup structure has "ioprio" entry which
is preference of group for I/O.
Signed-off-by: Satoshi UCHIDA <s-uchida at ap.jp.nec.com>
---
block/cfq-cgroup.c | 148 +++++++++++++++++++++++++++++++++++++++++
include/linux/cgroup_subsys.h | 6 ++
2 files changed, 154 insertions(+), 0 deletions(-)
diff --git a/block/cfq-cgroup.c b/block/cfq-cgroup.c
index aaa00ef..733980d 100644
--- a/block/cfq-cgroup.c
+++ b/block/cfq-cgroup.c
@@ -15,6 +15,154 @@
#include <linux/cgroup.h>
#include <linux/cfq-iosched.h>
+#define CFQ_CGROUP_MAX_IOPRIO (7)
+
+
+struct cfq_cgroup {
+ struct cgroup_subsys_state css;
+ unsigned int ioprio;
+};
+
+static inline struct cfq_cgroup *cgroup_to_cfq_cgroup(struct cgroup *cont)
+{
+ return container_of(cgroup_subsys_state(cont, cfq_subsys_id),
+ struct cfq_cgroup, css);
+}
+
+static inline struct cfq_cgroup *task_to_cfq_cgroup(struct task_struct *tsk)
+{
+ return container_of(task_subsys_state(tsk, cfq_subsys_id),
+ struct cfq_cgroup, css);
+}
+
+
+static struct cgroup_subsys_state *
+cfq_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ struct cfq_cgroup *cfqc;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ if (!cgroup_is_descendant(cont))
+ return ERR_PTR(-EPERM);
+
+ cfqc = kzalloc(sizeof(struct cfq_cgroup), GFP_KERNEL);
+ if (unlikely(!cfqc))
+ return ERR_PTR(-ENOMEM);
+
+ cfqc->ioprio = 3;
+
+ return &cfqc->css;
+}
+
+static void cfq_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ kfree(cgroup_to_cfq_cgroup(cont));
+}
+
+static ssize_t cfq_cgroup_read(struct cgroup *cont, struct cftype *cft,
+ struct file *file, char __user *userbuf,
+ size_t nbytes, loff_t *ppos)
+{
+ struct cfq_cgroup *cfqc;
+ char *page;
+ ssize_t ret;
+
+ page = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!page)
+ return -ENOMEM;
+
+ cgroup_lock();
+ if (cgroup_is_removed(cont)) {
+ cgroup_unlock();
+ ret = -ENODEV;
+ goto out;
+ }
+
+ cfqc = cgroup_to_cfq_cgroup(cont);
+
+ cgroup_unlock();
+
+ /* print priority */
+ ret = snprintf(page, PAGE_SIZE, "%d \n", cfqc->ioprio);
+
+ ret = simple_read_from_buffer(userbuf, nbytes, ppos, page, ret);
+
+out:
+ free_page((unsigned long)page);
+ return ret;
+}
+
+static ssize_t cfq_cgroup_write(struct cgroup *cont, struct cftype *cft,
+ struct file *file, const char __user *userbuf,
+ size_t nbytes, loff_t *ppos)
+{
+ struct cfq_cgroup *cfqc;
+ ssize_t ret;
+ long new_prio;
+ int err;
+ char *buffer = NULL;
+
+ cgroup_lock();
+ if (cgroup_is_removed(cont)) {
+ cgroup_unlock();
+ ret = -ENODEV;
+ goto out;
+ }
+
+ cfqc = cgroup_to_cfq_cgroup(cont);
+ cgroup_unlock();
+
+ /* set priority */
+ buffer = kmalloc(nbytes + 1, GFP_KERNEL);
+ if (buffer == NULL)
+ return -ENOMEM;
+
+ if (copy_from_user(buffer, userbuf, nbytes)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ buffer[nbytes] = 0;
+
+ err = strict_strtoul(buffer, 10, &new_prio);
+ if ((err) || ((new_prio < 0) || (new_prio > CFQ_CGROUP_MAX_IOPRIO))) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ cfqc->ioprio = new_prio;
+
+ ret = nbytes;
+
+out:
+ kfree(buffer);
+
+ return ret;
+}
+
+static struct cftype files[] = {
+ {
+ .name = "ioprio",
+ .read = cfq_cgroup_read,
+ .write = cfq_cgroup_write,
+ },
+};
+
+static int cfq_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
+{
+ return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
+}
+
+struct cgroup_subsys cfq_subsys = {
+ .name = "cfq",
+ .create = cfq_cgroup_create,
+ .destroy = cfq_cgroup_destroy,
+ .populate = cfq_cgroup_populate,
+ .subsys_id = cfq_subsys_id,
+};
+
+
/*
* sysfs parts below -->
*/
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 9c22396..a9482aa 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -54,3 +54,9 @@ SUBSYS(freezer)
#endif
/* */
+
+#ifdef CONFIG_IOSCHED_CFQ_CGROUP
+SUBSYS(cfq)
+#endif
+
+/* */
--
1.5.6.5