struct res_counter hugepage[HUGE_MAX_HSTATE];
};
+#define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val))
+#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;
kfree(h_cgroup);
}
+
+/*
+ * Should be called with hugetlb_lock held.
+ * Since we are holding hugetlb_lock, pages cannot get moved from
+ * active list or uncharged from the cgroup, So no need to get
+ * page reference and test for page active here. This function
+ * cannot fail.
+ */
+static void hugetlb_cgroup_move_parent(int idx, struct cgroup *cgroup,
+ 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);
+
+ page_hcg = hugetlb_cgroup_from_page(page);
+ /*
+ * We can have pages in active list without any cgroup
+ * ie, hugepage with less than 3 pages. We can safely
+ * ignore those pages.
+ */
+ if (!page_hcg || page_hcg != h_cg)
+ goto out;
+
+ csize = PAGE_SIZE << compound_order(page);
+ if (!parent) {
+ parent = root_h_cgroup;
+ /* root has no limit */
+ res_counter_charge_nofail(&parent->hugepage[idx],
+ csize, &fail_res);
+ }
+ counter = &h_cg->hugepage[idx];
+ res_counter_uncharge_until(counter, counter->parent, csize);
+
+ set_hugetlb_cgroup(page, parent);
+out:
+ return;
+}
+
+/*
+ * 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)
{
- /* We will add the cgroup removal support in later patches */
- return -EBUSY;
+ struct hstate *h;
+ struct page *page;
+ int ret = 0, 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);
+
+ spin_unlock(&hugetlb_lock);
+ idx++;
+ }
+ cond_resched();
+ } while (hugetlb_cgroup_have_usage(cgroup));
+out:
+ return ret;
}
int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
return ret;
}
+/* Should be called with hugetlb_lock held */
void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages,
struct hugetlb_cgroup *h_cg,
struct page *page)
if (hugetlb_cgroup_disabled() || !h_cg)
return;
- spin_lock(&hugetlb_lock);
set_hugetlb_cgroup(page, h_cg);
- spin_unlock(&hugetlb_lock);
return;
}
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)
+{
+ u64 val;
+ char str[64];
+ int idx, name, len;
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+
+ 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);
+}
+
+static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft,
+ const char *buffer)
+{
+ int idx, name, ret;
+ unsigned long long val;
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+
+ idx = MEMFILE_IDX(cft->private);
+ name = MEMFILE_ATTR(cft->private);
+
+ switch (name) {
+ case RES_LIMIT:
+ if (hugetlb_cgroup_is_root(h_cg)) {
+ /* Can't set limit on root */
+ ret = -EINVAL;
+ break;
+ }
+ /* This function does all necessary parse...reuse it */
+ ret = res_counter_memparse_write_strategy(buffer, &val);
+ if (ret)
+ break;
+ ret = res_counter_set_limit(&h_cg->hugepage[idx], val);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+ return ret;
+}
+
+static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event)
+{
+ int idx, name, ret = 0;
+ struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+
+ idx = MEMFILE_IDX(event);
+ name = MEMFILE_ATTR(event);
+
+ switch (name) {
+ case RES_MAX_USAGE:
+ res_counter_reset_max(&h_cg->hugepage[idx]);
+ break;
+ case RES_FAILCNT:
+ res_counter_reset_failcnt(&h_cg->hugepage[idx]);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+ return ret;
+}
+
+static char *mem_fmt(char *buf, int size, unsigned long hsize)
+{
+ if (hsize >= (1UL << 30))
+ snprintf(buf, size, "%luGB", hsize >> 30);
+ else if (hsize >= (1UL << 20))
+ snprintf(buf, size, "%luMB", hsize >> 20);
+ else
+ snprintf(buf, size, "%luKB", hsize >> 10);
+ return buf;
+}
+
+int __init hugetlb_cgroup_file_init(int idx)
+{
+ char buf[32];
+ struct cftype *cft;
+ struct hstate *h = &hstates[idx];
+
+ /* format the size */
+ mem_fmt(buf, 32, huge_page_size(h));
+
+ /* Add the limit file */
+ 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;
+
+ /* 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;
+
+ /* 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;
+
+ /* 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;
+
+ /* 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));
+
+ return 0;
+}
+
+/*
+ * hugetlb_lock will make sure a parallel cgroup rmdir won't happen
+ * when we migrate hugepages
+ */
+void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
+{
+ struct hugetlb_cgroup *h_cg;
+ struct hstate *h = page_hstate(oldhpage);
+
+ if (hugetlb_cgroup_disabled())
+ return;
+
+ VM_BUG_ON(!PageHuge(oldhpage));
+ spin_lock(&hugetlb_lock);
+ h_cg = hugetlb_cgroup_from_page(oldhpage);
+ set_hugetlb_cgroup(oldhpage, NULL);
+
+ /* move the h_cg details to new cgroup */
+ set_hugetlb_cgroup(newhpage, h_cg);
+ list_move(&newhpage->lru, &h->hugepage_activelist);
+ spin_unlock(&hugetlb_lock);
+ return;
+}
+
struct cgroup_subsys hugetlb_subsys = {
.name = "hugetlb",
.create = hugetlb_cgroup_create,
projects / platform / adaptation / renesas_rcar / renesas_kernel.git / blobdiff