@@ -234,8 +234,12 @@ will exist, of the form::
hugepages-${size}kB
-Inside each of these directories, the same set of files will exist::
+Inside each of these directories, the set of files contained in ``/proc``
+will exist. In addition, two additional interfaces for demoting huge
+pages may exist::
+ demote
+ demote_size
nr_hugepages
nr_hugepages_mempolicy
nr_overcommit_hugepages
@@ -243,7 +247,29 @@ Inside each of these directories, the sa
resv_hugepages
surplus_hugepages
-which function as described above for the default huge page-sized case.
+The demote interfaces provide the ability to split a huge page into
+smaller huge pages. For example, the x86 architecture supports both
+1GB and 2MB huge pages sizes. A 1GB huge page can be split into 512
+2MB huge pages. Demote interfaces are not available for the smallest
+huge page size. The demote interfaces are:
+
+demote_size
+ is the size of demoted pages. When a page is demoted a corresponding
+ number of huge pages of demote_size will be created. By default,
+ demote_size is set to the next smaller huge page size. If there are
+ multiple smaller huge page sizes, demote_size can be set to any of
+ these smaller sizes. Only huge page sizes less than the current huge
+ pages size are allowed.
+
+demote
+ is used to demote a number of huge pages. A user with root privileges
+ can write to this file. It may not be possible to demote the
+ requested number of huge pages. To determine how many pages were
+ actually demoted, compare the value of nr_hugepages before and after
+ writing to the demote interface. demote is a write only interface.
+
+The interfaces which are the same as in ``/proc`` (all except demote and
+demote_size) function as described above for the default huge page-sized case.
.. _mem_policy_and_hp_alloc:
@@ -586,6 +586,7 @@ struct hstate {
int next_nid_to_alloc;
int next_nid_to_free;
unsigned int order;
+ unsigned int demote_order;
unsigned long mask;
unsigned long max_huge_pages;
unsigned long nr_huge_pages;
@@ -2986,7 +2986,7 @@ free:
static void __init hugetlb_init_hstates(void)
{
- struct hstate *h;
+ struct hstate *h, *h2;
for_each_hstate(h) {
if (minimum_order > huge_page_order(h))
@@ -2995,6 +2995,22 @@ static void __init hugetlb_init_hstates(
/* oversize hugepages were init'ed in early boot */
if (!hstate_is_gigantic(h))
hugetlb_hstate_alloc_pages(h);
+
+ /*
+ * Set demote order for each hstate. Note that
+ * h->demote_order is initially 0.
+ * - We can not demote gigantic pages if runtime freeing
+ * is not supported, so skip this.
+ */
+ if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
+ continue;
+ for_each_hstate(h2) {
+ if (h2 == h)
+ continue;
+ if (h2->order < h->order &&
+ h2->order > h->demote_order)
+ h->demote_order = h2->order;
+ }
}
VM_BUG_ON(minimum_order == UINT_MAX);
}
@@ -3235,9 +3251,31 @@ out:
return 0;
}
+static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
+ __must_hold(&hugetlb_lock)
+{
+ int rc = 0;
+
+ lockdep_assert_held(&hugetlb_lock);
+
+ /* We should never get here if no demote order */
+ if (!h->demote_order) {
+ pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n");
+ return -EINVAL; /* internal error */
+ }
+
+ /*
+ * TODO - demote fucntionality will be added in subsequent patch
+ */
+ return rc;
+}
+
#define HSTATE_ATTR_RO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
+#define HSTATE_ATTR_WO(_name) \
+ static struct kobj_attribute _name##_attr = __ATTR_WO(_name)
+
#define HSTATE_ATTR(_name) \
static struct kobj_attribute _name##_attr = \
__ATTR(_name, 0644, _name##_show, _name##_store)
@@ -3433,6 +3471,105 @@ static ssize_t surplus_hugepages_show(st
}
HSTATE_ATTR_RO(surplus_hugepages);
+static ssize_t demote_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t len)
+{
+ unsigned long nr_demote;
+ unsigned long nr_available;
+ nodemask_t nodes_allowed, *n_mask;
+ struct hstate *h;
+ int err = 0;
+ int nid;
+
+ err = kstrtoul(buf, 10, &nr_demote);
+ if (err)
+ return err;
+ h = kobj_to_hstate(kobj, &nid);
+
+ if (nid != NUMA_NO_NODE) {
+ init_nodemask_of_node(&nodes_allowed, nid);
+ n_mask = &nodes_allowed;
+ } else {
+ n_mask = &node_states[N_MEMORY];
+ }
+
+ /* Synchronize with other sysfs operations modifying huge pages */
+ mutex_lock(&h->resize_lock);
+ spin_lock_irq(&hugetlb_lock);
+
+ while (nr_demote) {
+ /*
+ * Check for available pages to demote each time thorough the
+ * loop as demote_pool_huge_page will drop hugetlb_lock.
+ *
+ * NOTE: demote_pool_huge_page does not yet drop hugetlb_lock
+ * but will when full demote functionality is added in a later
+ * patch.
+ */
+ if (nid != NUMA_NO_NODE)
+ nr_available = h->free_huge_pages_node[nid];
+ else
+ nr_available = h->free_huge_pages;
+ nr_available -= h->resv_huge_pages;
+ if (!nr_available)
+ break;
+
+ err = demote_pool_huge_page(h, n_mask);
+ if (err)
+ break;
+
+ nr_demote--;
+ }
+
+ spin_unlock_irq(&hugetlb_lock);
+ mutex_unlock(&h->resize_lock);
+
+ if (err)
+ return err;
+ return len;
+}
+HSTATE_ATTR_WO(demote);
+
+static ssize_t demote_size_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ int nid;
+ struct hstate *h = kobj_to_hstate(kobj, &nid);
+ unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K;
+
+ return sysfs_emit(buf, "%lukB\n", demote_size);
+}
+
+static ssize_t demote_size_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct hstate *h, *demote_hstate;
+ unsigned long demote_size;
+ unsigned int demote_order;
+ int nid;
+
+ demote_size = (unsigned long)memparse(buf, NULL);
+
+ demote_hstate = size_to_hstate(demote_size);
+ if (!demote_hstate)
+ return -EINVAL;
+ demote_order = demote_hstate->order;
+
+ /* demote order must be smaller than hstate order */
+ h = kobj_to_hstate(kobj, &nid);
+ if (demote_order >= h->order)
+ return -EINVAL;
+
+ /* resize_lock synchronizes access to demote size and writes */
+ mutex_lock(&h->resize_lock);
+ h->demote_order = demote_order;
+ mutex_unlock(&h->resize_lock);
+
+ return count;
+}
+HSTATE_ATTR(demote_size);
+
static struct attribute *hstate_attrs[] = {
&nr_hugepages_attr.attr,
&nr_overcommit_hugepages_attr.attr,
@@ -3449,6 +3586,16 @@ static const struct attribute_group hsta
.attrs = hstate_attrs,
};
+static struct attribute *hstate_demote_attrs[] = {
+ &demote_size_attr.attr,
+ &demote_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group hstate_demote_attr_group = {
+ .attrs = hstate_demote_attrs,
+};
+
static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
struct kobject **hstate_kobjs,
const struct attribute_group *hstate_attr_group)
@@ -3466,6 +3613,12 @@ static int hugetlb_sysfs_add_hstate(stru
hstate_kobjs[hi] = NULL;
}
+ if (h->demote_order) {
+ if (sysfs_create_group(hstate_kobjs[hi],
+ &hstate_demote_attr_group))
+ pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name);
+ }
+
return retval;
}