From: Lei Chen <lennychen@xxxxxxxxxxx>
Introduce new attribute "priority" to control group, which
could be used as scale by subssytem to manipulate the behaviors
of processes.
The default value of "priority" is set to 0 which means the
highest priority, and the totally levels of priority is defined
by CGROUP_PRIORITY_MAX.
Signed-off-by: Lei Chen <lennychen@xxxxxxxxxxx>
Signed-off-by: Liu Yu <allanyuliu@xxxxxxxxxxx>
Signed-off-by: Peng Zhiguang <zgpeng@xxxxxxxxxxx>
Signed-off-by: Yulei Zhang <yuleixzhang@xxxxxxxxxxx>
---
include/linux/cgroup-defs.h | 2 +
include/linux/cgroup.h | 2 +
kernel/cgroup/cgroup.c | 90 +++++++++++++++++++++++++++++++++++++
3 files changed, 94 insertions(+)
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 559ee05f8..3fa2f28a9 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -417,6 +417,7 @@ struct cgroup {
u16 subtree_ss_mask;
u16 old_subtree_control;
u16 old_subtree_ss_mask;
+ u16 priority;
/* Private pointers for each registered subsystem */
struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];
@@ -640,6 +641,7 @@ struct cgroup_subsys {
void (*exit)(struct task_struct *task);
void (*release)(struct task_struct *task);
void (*bind)(struct cgroup_subsys_state *root_css);
+ int (*css_priority_change)(struct cgroup_subsys_state *css, u16 old, u16 new);
bool early_init:1;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4f2f79de0..734d51aba 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -47,6 +47,7 @@ struct kernel_clone_args;
/* internal flags */
#define CSS_TASK_ITER_SKIPPED (1U << 16)
+#define CGROUP_PRIORITY_MAX 8
/* a css_task_iter should be treated as an opaque object */
struct css_task_iter {
@@ -957,5 +958,6 @@ static inline void cgroup_bpf_get(struct cgroup *cgrp) {}
static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
#endif /* CONFIG_CGROUP_BPF */
+ssize_t cgroup_priority(struct cgroup_subsys_state *css);
#endif /* _LINUX_CGROUP_H */
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 9153b20e5..aa019ad24 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1892,6 +1892,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
cgrp->dom_cgrp = cgrp;
cgrp->max_descendants = INT_MAX;
cgrp->max_depth = INT_MAX;
+ cgrp->priority = 0;
INIT_LIST_HEAD(&cgrp->rstat_css_list);
prev_cputime_init(&cgrp->prev_cputime);
@@ -4783,6 +4784,88 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
return __cgroup_procs_write(of, buf, false) ?: nbytes;
}
+static int cgroup_priority_show(struct seq_file *seq, void *v)
+{
+ struct cgroup *cgrp = seq_css(seq)->cgroup;
+ u16 prio = cgrp->priority;
+
+ seq_printf(seq, "%d\n", prio);
+
+ return 0;
+}
+
+static void cgroup_set_priority(struct cgroup *cgrp, unsigned int priority)
+{
+ u16 old = cgrp->priority;
+ struct cgroup_subsys_state *css;
+ int ssid;
+
+ cgrp->priority = priority;
+ for_each_css(css, ssid, cgrp) {
+ if (css->ss->css_priority_change)
+ css->ss->css_priority_change(css, old, priority);
+ }
+}
+
+static void cgroup_priority_propagate(struct cgroup *cgrp)
+{
+ struct cgroup *dsct;
+ struct cgroup_subsys_state *d_css;
+ u16 priority = cgrp->priority;
+
+ lockdep_assert_held(&cgroup_mutex);
+ cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) {
+ if (dsct->priority < priority)
+ cgroup_set_priority(dsct, priority);
+ }
+}
+
+static ssize_t cgroup_priority_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct cgroup *cgrp, *parent;
+ ssize_t ret;
+ u16 prio, orig;
+
+ buf = strstrip(buf);
+ ret = kstrtou16(buf, 0, &prio);
+ if (ret)
+ return ret;
+
+ if (prio < 0 || prio >= CGROUP_PRIORITY_MAX)
+ return -ERANGE;
+
+ cgrp = cgroup_kn_lock_live(of->kn, false);
+ if (!cgrp)
+ return -ENOENT;
+ parent = cgroup_parent(cgrp);
+ if (parent && prio < parent->priority) {
+ ret = -EINVAL;
+ goto unlock_out;
+ }
+ orig = cgrp->priority;
+ if (prio == orig)
+ goto unlock_out;
+
+ cgroup_set_priority(cgrp, prio);
+ cgroup_priority_propagate(cgrp);
+unlock_out:
+ cgroup_kn_unlock(of->kn);
+
+ return ret ?: nbytes;
+}
+
+ssize_t cgroup_priority(struct cgroup_subsys_state *css)
+{
+ struct cgroup *cgrp = css->cgroup;
+ unsigned int prio = 0;
+
+ if (cgrp)
+ prio = cgrp->priority;
+ return prio;
+}
+EXPORT_SYMBOL(cgroup_priority);
+
/* cgroup core interface files for the default hierarchy */
static struct cftype cgroup_base_files[] = {
{
@@ -4836,6 +4919,12 @@ static struct cftype cgroup_base_files[] = {
.seq_show = cgroup_max_depth_show,
.write = cgroup_max_depth_write,
},
+ {
+ .name = "cgroup.priority",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = cgroup_priority_show,
+ .write = cgroup_priority_write,
+ },
{
.name = "cgroup.stat",
.seq_show = cgroup_stat_show,
@@ -5178,6 +5267,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
cgrp->self.parent = &parent->self;
cgrp->root = root;
cgrp->level = level;
+ cgrp->priority = parent->priority;
ret = psi_cgroup_alloc(cgrp);
if (ret)
--
2.28.0
