aboutsummaryrefslogtreecommitdiff
path: root/mm/hugetlb_cgroup.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/hugetlb_cgroup.c')
-rw-r--r--mm/hugetlb_cgroup.c149
1 files changed, 70 insertions, 79 deletions
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index a3f358fb8a0..493f758445e 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -30,27 +30,18 @@ struct hugetlb_cgroup {
#define MEMFILE_IDX(val) (((val) >> 16) & 0xffff)
#define MEMFILE_ATTR(val) ((val) & 0xffff)
-struct cgroup_subsys hugetlb_subsys __read_mostly;
static struct hugetlb_cgroup *root_h_cgroup __read_mostly;
static inline
struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s)
{
- return container_of(s, struct hugetlb_cgroup, css);
-}
-
-static inline
-struct hugetlb_cgroup *hugetlb_cgroup_from_cgroup(struct cgroup *cgroup)
-{
- return hugetlb_cgroup_from_css(cgroup_subsys_state(cgroup,
- hugetlb_subsys_id));
+ return s ? container_of(s, struct hugetlb_cgroup, css) : NULL;
}
static inline
struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task)
{
- return hugetlb_cgroup_from_css(task_subsys_state(task,
- hugetlb_subsys_id));
+ return hugetlb_cgroup_from_css(task_css(task, hugetlb_cgrp_id));
}
static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg)
@@ -58,17 +49,15 @@ static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg)
return (h_cg == root_h_cgroup);
}
-static inline struct hugetlb_cgroup *parent_hugetlb_cgroup(struct cgroup *cg)
+static inline struct hugetlb_cgroup *
+parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg)
{
- if (!cg->parent)
- return NULL;
- return hugetlb_cgroup_from_cgroup(cg->parent);
+ return hugetlb_cgroup_from_css(h_cg->css.parent);
}
-static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg)
+static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
{
int idx;
- struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cg);
for (idx = 0; idx < hugetlb_max_hstate; idx++) {
if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0)
@@ -77,19 +66,18 @@ static inline bool hugetlb_cgroup_have_usage(struct cgroup *cg)
return false;
}
-static struct cgroup_subsys_state *hugetlb_cgroup_create(struct cgroup *cgroup)
+static struct cgroup_subsys_state *
+hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
+ struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css);
+ struct hugetlb_cgroup *h_cgroup;
int idx;
- struct cgroup *parent_cgroup;
- struct hugetlb_cgroup *h_cgroup, *parent_h_cgroup;
h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL);
if (!h_cgroup)
return ERR_PTR(-ENOMEM);
- parent_cgroup = cgroup->parent;
- if (parent_cgroup) {
- parent_h_cgroup = hugetlb_cgroup_from_cgroup(parent_cgroup);
+ if (parent_h_cgroup) {
for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
res_counter_init(&h_cgroup->hugepage[idx],
&parent_h_cgroup->hugepage[idx]);
@@ -101,11 +89,11 @@ static struct cgroup_subsys_state *hugetlb_cgroup_create(struct cgroup *cgroup)
return &h_cgroup->css;
}
-static void hugetlb_cgroup_destroy(struct cgroup *cgroup)
+static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
{
struct hugetlb_cgroup *h_cgroup;
- h_cgroup = hugetlb_cgroup_from_cgroup(cgroup);
+ h_cgroup = hugetlb_cgroup_from_css(css);
kfree(h_cgroup);
}
@@ -117,15 +105,14 @@ static void hugetlb_cgroup_destroy(struct cgroup *cgroup)
* page reference and test for page active here. This function
* cannot fail.
*/
-static void hugetlb_cgroup_move_parent(int idx, struct cgroup *cgroup,
+static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
struct page *page)
{
int csize;
struct res_counter *counter;
struct res_counter *fail_res;
struct hugetlb_cgroup *page_hcg;
- struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
- struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(cgroup);
+ struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg);
page_hcg = hugetlb_cgroup_from_page(page);
/*
@@ -155,30 +142,24 @@ out:
* Force the hugetlb cgroup to empty the hugetlb resources by moving them to
* the parent cgroup.
*/
-static int hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
+static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css)
{
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
struct hstate *h;
struct page *page;
- int ret = 0, idx = 0;
+ int idx = 0;
do {
- if (cgroup_task_count(cgroup) ||
- !list_empty(&cgroup->children)) {
- ret = -EBUSY;
- goto out;
- }
for_each_hstate(h) {
spin_lock(&hugetlb_lock);
list_for_each_entry(page, &h->hugepage_activelist, lru)
- hugetlb_cgroup_move_parent(idx, cgroup, page);
+ hugetlb_cgroup_move_parent(idx, h_cg, page);
spin_unlock(&hugetlb_lock);
idx++;
}
cond_resched();
- } while (hugetlb_cgroup_have_usage(cgroup));
-out:
- return ret;
+ } while (hugetlb_cgroup_have_usage(h_cg));
}
int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
@@ -200,7 +181,7 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
again:
rcu_read_lock();
h_cg = hugetlb_cgroup_from_task(current);
- if (!css_tryget(&h_cg->css)) {
+ if (!css_tryget_online(&h_cg->css)) {
rcu_read_unlock();
goto again;
}
@@ -260,32 +241,28 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
return;
}
-static ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft,
- struct file *file, char __user *buf,
- size_t nbytes, loff_t *ppos)
+static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
+ struct cftype *cft)
{
- u64 val;
- char str[64];
- int idx, name, len;
- struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+ int idx, name;
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
idx = MEMFILE_IDX(cft->private);
name = MEMFILE_ATTR(cft->private);
- val = res_counter_read_u64(&h_cg->hugepage[idx], name);
- len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val);
- return simple_read_from_buffer(buf, nbytes, ppos, str, len);
+ return res_counter_read_u64(&h_cg->hugepage[idx], name);
}
-static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft,
- const char *buffer)
+static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
{
int idx, name, ret;
unsigned long long val;
- struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
- idx = MEMFILE_IDX(cft->private);
- name = MEMFILE_ATTR(cft->private);
+ buf = strstrip(buf);
+ idx = MEMFILE_IDX(of_cft(of)->private);
+ name = MEMFILE_ATTR(of_cft(of)->private);
switch (name) {
case RES_LIMIT:
@@ -295,7 +272,7 @@ static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft,
break;
}
/* This function does all necessary parse...reuse it */
- ret = res_counter_memparse_write_strategy(buffer, &val);
+ ret = res_counter_memparse_write_strategy(buf, &val);
if (ret)
break;
ret = res_counter_set_limit(&h_cg->hugepage[idx], val);
@@ -304,16 +281,17 @@ static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft,
ret = -EINVAL;
break;
}
- return ret;
+ return ret ?: nbytes;
}
-static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event)
+static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
{
int idx, name, ret = 0;
- struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
- idx = MEMFILE_IDX(event);
- name = MEMFILE_ATTR(event);
+ idx = MEMFILE_IDX(of_cft(of)->private);
+ name = MEMFILE_ATTR(of_cft(of)->private);
switch (name) {
case RES_MAX_USAGE:
@@ -326,7 +304,7 @@ static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event)
ret = -EINVAL;
break;
}
- return ret;
+ return ret ?: nbytes;
}
static char *mem_fmt(char *buf, int size, unsigned long hsize)
@@ -340,7 +318,7 @@ static char *mem_fmt(char *buf, int size, unsigned long hsize)
return buf;
}
-int __init hugetlb_cgroup_file_init(int idx)
+static void __init __hugetlb_cgroup_file_init(int idx)
{
char buf[32];
struct cftype *cft;
@@ -353,36 +331,51 @@ int __init hugetlb_cgroup_file_init(int idx)
cft = &h->cgroup_files[0];
snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf);
cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT);
- cft->read = hugetlb_cgroup_read;
- cft->write_string = hugetlb_cgroup_write;
+ cft->read_u64 = hugetlb_cgroup_read_u64;
+ cft->write = hugetlb_cgroup_write;
/* Add the usage file */
cft = &h->cgroup_files[1];
snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf);
cft->private = MEMFILE_PRIVATE(idx, RES_USAGE);
- cft->read = hugetlb_cgroup_read;
+ cft->read_u64 = hugetlb_cgroup_read_u64;
/* Add the MAX usage file */
cft = &h->cgroup_files[2];
snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf);
cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE);
- cft->trigger = hugetlb_cgroup_reset;
- cft->read = hugetlb_cgroup_read;
+ cft->write = hugetlb_cgroup_reset;
+ cft->read_u64 = hugetlb_cgroup_read_u64;
/* Add the failcntfile */
cft = &h->cgroup_files[3];
snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf);
cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT);
- cft->trigger = hugetlb_cgroup_reset;
- cft->read = hugetlb_cgroup_read;
+ cft->write = hugetlb_cgroup_reset;
+ cft->read_u64 = hugetlb_cgroup_read_u64;
/* NULL terminate the last cft */
cft = &h->cgroup_files[4];
memset(cft, 0, sizeof(*cft));
- WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files));
+ WARN_ON(cgroup_add_cftypes(&hugetlb_cgrp_subsys, h->cgroup_files));
+
+ return;
+}
- return 0;
+void __init hugetlb_cgroup_file_init(void)
+{
+ struct hstate *h;
+
+ for_each_hstate(h) {
+ /*
+ * Add cgroup control files only if the huge page consists
+ * of more than two normal pages. This is because we use
+ * page[2].lru.next for storing cgroup details.
+ */
+ if (huge_page_order(h) >= HUGETLB_CGROUP_MIN_ORDER)
+ __hugetlb_cgroup_file_init(hstate_index(h));
+ }
}
/*
@@ -397,7 +390,7 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
if (hugetlb_cgroup_disabled())
return;
- VM_BUG_ON(!PageHuge(oldhpage));
+ VM_BUG_ON_PAGE(!PageHuge(oldhpage), oldhpage);
spin_lock(&hugetlb_lock);
h_cg = hugetlb_cgroup_from_page(oldhpage);
set_hugetlb_cgroup(oldhpage, NULL);
@@ -409,10 +402,8 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
return;
}
-struct cgroup_subsys hugetlb_subsys = {
- .name = "hugetlb",
- .create = hugetlb_cgroup_create,
- .pre_destroy = hugetlb_cgroup_pre_destroy,
- .destroy = hugetlb_cgroup_destroy,
- .subsys_id = hugetlb_subsys_id,
+struct cgroup_subsys hugetlb_cgrp_subsys = {
+ .css_alloc = hugetlb_cgroup_css_alloc,
+ .css_offline = hugetlb_cgroup_css_offline,
+ .css_free = hugetlb_cgroup_css_free,
};
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 03:39:09 +0000