#include <linux/mempolicy.h>
#include <linux/cpuset.h>
#include <linux/mutex.h>
+#include <linux/bootmem.h>
+#include <linux/sysfs.h>
#include <asm/page.h>
#include <asm/pgtable.h>
unsigned int default_hstate_idx;
struct hstate hstates[HUGE_MAX_HSTATE];
+__initdata LIST_HEAD(huge_boot_pages);
+
/* for command line parsing */
static struct hstate * __initdata parsed_hstate;
static unsigned long __initdata default_hstate_max_huge_pages;
+static unsigned long __initdata default_hstate_size;
#define for_each_hstate(h) \
for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++)
}
/* Returns true if the VMA has associated reserve pages */
-static int vma_has_private_reserves(struct vm_area_struct *vma)
+static int vma_has_reserves(struct vm_area_struct *vma)
{
if (vma->vm_flags & VM_SHARED)
- return 0;
- if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER))
- return 0;
- return 1;
+ return 1;
+ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+ return 1;
+ return 0;
}
static void clear_huge_page(struct page *page,
* have no page reserves. This check ensures that reservations are
* not "stolen". The child may still get SIGKILLed
*/
- if (!vma_has_private_reserves(vma) &&
+ if (!vma_has_reserves(vma) &&
h->free_huge_pages - h->resv_huge_pages == 0)
return NULL;
INIT_LIST_HEAD(&page->lru);
spin_lock(&hugetlb_lock);
- if (h->surplus_huge_pages_node[nid]) {
+ if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
update_and_free_page(h, page);
h->surplus_huge_pages--;
h->surplus_huge_pages_node[nid]--;
{
struct page *page;
+ if (h->order >= MAX_ORDER)
+ return NULL;
+
page = alloc_pages_node(nid,
htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
__GFP_REPEAT|__GFP_NOWARN,
return page;
}
+/*
+ * Use a helper variable to find the next node and then
+ * copy it back to hugetlb_next_nid afterwards:
+ * otherwise there's a window in which a racer might
+ * pass invalid nid MAX_NUMNODES to alloc_pages_node.
+ * But we don't need to use a spin_lock here: it really
+ * doesn't matter if occasionally a racer chooses the
+ * same nid as we do. Move nid forward in the mask even
+ * if we just successfully allocated a hugepage so that
+ * the next caller gets hugepages on the next node.
+ */
+static int hstate_next_node(struct hstate *h)
+{
+ int next_nid;
+ next_nid = next_node(h->hugetlb_next_nid, node_online_map);
+ if (next_nid == MAX_NUMNODES)
+ next_nid = first_node(node_online_map);
+ h->hugetlb_next_nid = next_nid;
+ return next_nid;
+}
+
static int alloc_fresh_huge_page(struct hstate *h)
{
struct page *page;
page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid);
if (page)
ret = 1;
- /*
- * Use a helper variable to find the next node and then
- * copy it back to hugetlb_next_nid afterwards:
- * otherwise there's a window in which a racer might
- * pass invalid nid MAX_NUMNODES to alloc_pages_node.
- * But we don't need to use a spin_lock here: it really
- * doesn't matter if occasionally a racer chooses the
- * same nid as we do. Move nid forward in the mask even
- * if we just successfully allocated a hugepage so that
- * the next caller gets hugepages on the next node.
- */
- next_nid = next_node(h->hugetlb_next_nid, node_online_map);
- if (next_nid == MAX_NUMNODES)
- next_nid = first_node(node_online_map);
- h->hugetlb_next_nid = next_nid;
+ next_nid = hstate_next_node(h);
} while (!page && h->hugetlb_next_nid != start_nid);
if (ret)
struct page *page;
unsigned int nid;
+ if (h->order >= MAX_ORDER)
+ return NULL;
+
/*
* Assume we will successfully allocate the surplus page to
* prevent racing processes from causing the surplus to exceed
/* Uncommit the reservation */
h->resv_huge_pages -= unused_resv_pages;
+ /* Cannot return gigantic pages currently */
+ if (h->order >= MAX_ORDER)
+ return;
+
nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
while (remaining_iterations-- && nr_pages) {
return page;
}
-static void __init hugetlb_init_one_hstate(struct hstate *h)
+__attribute__((weak)) int alloc_bootmem_huge_page(struct hstate *h)
{
- unsigned long i;
+ struct huge_bootmem_page *m;
+ int nr_nodes = nodes_weight(node_online_map);
- for (i = 0; i < MAX_NUMNODES; ++i)
- INIT_LIST_HEAD(&h->hugepage_freelists[i]);
+ while (nr_nodes) {
+ void *addr;
- h->hugetlb_next_nid = first_node(node_online_map);
+ addr = __alloc_bootmem_node_nopanic(
+ NODE_DATA(h->hugetlb_next_nid),
+ huge_page_size(h), huge_page_size(h), 0);
- for (i = 0; i < h->max_huge_pages; ++i) {
- if (!alloc_fresh_huge_page(h))
- break;
+ if (addr) {
+ /*
+ * Use the beginning of the huge page to store the
+ * huge_bootmem_page struct (until gather_bootmem
+ * puts them into the mem_map).
+ */
+ m = addr;
+ if (m)
+ goto found;
+ }
+ hstate_next_node(h);
+ nr_nodes--;
}
- h->max_huge_pages = h->free_huge_pages = h->nr_huge_pages = i;
-}
-
-static void __init hugetlb_init_hstates(void)
-{
- struct hstate *h;
+ return 0;
- for_each_hstate(h) {
- hugetlb_init_one_hstate(h);
- }
+found:
+ BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1));
+ /* Put them into a private list first because mem_map is not up yet */
+ list_add(&m->list, &huge_boot_pages);
+ m->hstate = h;
+ return 1;
}
-static void __init report_hugepages(void)
+/* Put bootmem huge pages into the standard lists after mem_map is up */
+static void __init gather_bootmem_prealloc(void)
{
- struct hstate *h;
+ struct huge_bootmem_page *m;
- for_each_hstate(h) {
- printk(KERN_INFO "Total HugeTLB memory allocated, "
- "%ld %dMB pages\n",
- h->free_huge_pages,
- 1 << (h->order + PAGE_SHIFT - 20));
+ list_for_each_entry(m, &huge_boot_pages, list) {
+ struct page *page = virt_to_page(m);
+ struct hstate *h = m->hstate;
+ __ClearPageReserved(page);
+ WARN_ON(page_count(page) != 1);
+ prep_compound_page(page, h->order);
+ prep_new_huge_page(h, page, page_to_nid(page));
}
}
-static int __init hugetlb_init(void)
+static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
{
- BUILD_BUG_ON(HPAGE_SHIFT == 0);
+ unsigned long i;
- if (!size_to_hstate(HPAGE_SIZE)) {
- hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
- parsed_hstate->max_huge_pages = default_hstate_max_huge_pages;
+ for (i = 0; i < h->max_huge_pages; ++i) {
+ if (h->order >= MAX_ORDER) {
+ if (!alloc_bootmem_huge_page(h))
+ break;
+ } else if (!alloc_fresh_huge_page(h))
+ break;
}
- default_hstate_idx = size_to_hstate(HPAGE_SIZE) - hstates;
-
- hugetlb_init_hstates();
-
- report_hugepages();
-
- return 0;
+ h->max_huge_pages = i;
}
-module_init(hugetlb_init);
-/* Should be called on processing a hugepagesz=... option */
-void __init hugetlb_add_hstate(unsigned order)
+static void __init hugetlb_init_hstates(void)
{
struct hstate *h;
- if (size_to_hstate(PAGE_SIZE << order)) {
- printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
- return;
+
+ for_each_hstate(h) {
+ /* oversize hugepages were init'ed in early boot */
+ if (h->order < MAX_ORDER)
+ hugetlb_hstate_alloc_pages(h);
}
- BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
- BUG_ON(order == 0);
- h = &hstates[max_hstate++];
- h->order = order;
- h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
- hugetlb_init_one_hstate(h);
- parsed_hstate = h;
}
-static int __init hugetlb_setup(char *s)
+static char * __init memfmt(char *buf, unsigned long n)
{
- unsigned long *mhp;
-
- /*
- * !max_hstate means we haven't parsed a hugepagesz= parameter yet,
- * so this hugepages= parameter goes to the "default hstate".
- */
- if (!max_hstate)
- mhp = &default_hstate_max_huge_pages;
+ if (n >= (1UL << 30))
+ sprintf(buf, "%lu GB", n >> 30);
+ else if (n >= (1UL << 20))
+ sprintf(buf, "%lu MB", n >> 20);
else
- mhp = &parsed_hstate->max_huge_pages;
-
- if (sscanf(s, "%lu", mhp) <= 0)
- *mhp = 0;
-
- return 1;
+ sprintf(buf, "%lu KB", n >> 10);
+ return buf;
}
-__setup("hugepages=", hugetlb_setup);
-static unsigned int cpuset_mems_nr(unsigned int *array)
+static void __init report_hugepages(void)
{
- int node;
- unsigned int nr = 0;
-
- for_each_node_mask(node, cpuset_current_mems_allowed)
- nr += array[node];
+ struct hstate *h;
- return nr;
+ for_each_hstate(h) {
+ char buf[32];
+ printk(KERN_INFO "HugeTLB registered %s page size, "
+ "pre-allocated %ld pages\n",
+ memfmt(buf, huge_page_size(h)),
+ h->free_huge_pages);
+ }
}
#ifdef CONFIG_SYSCTL
{
int i;
+ if (h->order >= MAX_ORDER)
+ return;
+
for (i = 0; i < MAX_NUMNODES; ++i) {
struct page *page, *next;
struct list_head *freel = &h->hugepage_freelists[i];
{
unsigned long min_count, ret;
+ if (h->order >= MAX_ORDER)
+ return h->max_huge_pages;
+
/*
* Increase the pool size
* First take pages out of surplus state. Then make up the
return ret;
}
+#define HSTATE_ATTR_RO(_name) \
+ static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
+
+#define HSTATE_ATTR(_name) \
+ static struct kobj_attribute _name##_attr = \
+ __ATTR(_name, 0644, _name##_show, _name##_store)
+
+static struct kobject *hugepages_kobj;
+static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];
+
+static struct hstate *kobj_to_hstate(struct kobject *kobj)
+{
+ int i;
+ for (i = 0; i < HUGE_MAX_HSTATE; i++)
+ if (hstate_kobjs[i] == kobj)
+ return &hstates[i];
+ BUG();
+ return NULL;
+}
+
+static ssize_t nr_hugepages_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h = kobj_to_hstate(kobj);
+ return sprintf(buf, "%lu\n", h->nr_huge_pages);
+}
+static ssize_t nr_hugepages_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t count)
+{
+ int err;
+ unsigned long input;
+ struct hstate *h = kobj_to_hstate(kobj);
+
+ err = strict_strtoul(buf, 10, &input);
+ if (err)
+ return 0;
+
+ h->max_huge_pages = set_max_huge_pages(h, input);
+
+ return count;
+}
+HSTATE_ATTR(nr_hugepages);
+
+static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h = kobj_to_hstate(kobj);
+ return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages);
+}
+static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t count)
+{
+ int err;
+ unsigned long input;
+ struct hstate *h = kobj_to_hstate(kobj);
+
+ err = strict_strtoul(buf, 10, &input);
+ if (err)
+ return 0;
+
+ spin_lock(&hugetlb_lock);
+ h->nr_overcommit_huge_pages = input;
+ spin_unlock(&hugetlb_lock);
+
+ return count;
+}
+HSTATE_ATTR(nr_overcommit_hugepages);
+
+static ssize_t free_hugepages_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h = kobj_to_hstate(kobj);
+ return sprintf(buf, "%lu\n", h->free_huge_pages);
+}
+HSTATE_ATTR_RO(free_hugepages);
+
+static ssize_t resv_hugepages_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h = kobj_to_hstate(kobj);
+ return sprintf(buf, "%lu\n", h->resv_huge_pages);
+}
+HSTATE_ATTR_RO(resv_hugepages);
+
+static ssize_t surplus_hugepages_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h = kobj_to_hstate(kobj);
+ return sprintf(buf, "%lu\n", h->surplus_huge_pages);
+}
+HSTATE_ATTR_RO(surplus_hugepages);
+
+static struct attribute *hstate_attrs[] = {
+ &nr_hugepages_attr.attr,
+ &nr_overcommit_hugepages_attr.attr,
+ &free_hugepages_attr.attr,
+ &resv_hugepages_attr.attr,
+ &surplus_hugepages_attr.attr,
+ NULL,
+};
+
+static struct attribute_group hstate_attr_group = {
+ .attrs = hstate_attrs,
+};
+
+static int __init hugetlb_sysfs_add_hstate(struct hstate *h)
+{
+ int retval;
+
+ hstate_kobjs[h - hstates] = kobject_create_and_add(h->name,
+ hugepages_kobj);
+ if (!hstate_kobjs[h - hstates])
+ return -ENOMEM;
+
+ retval = sysfs_create_group(hstate_kobjs[h - hstates],
+ &hstate_attr_group);
+ if (retval)
+ kobject_put(hstate_kobjs[h - hstates]);
+
+ return retval;
+}
+
+static void __init hugetlb_sysfs_init(void)
+{
+ struct hstate *h;
+ int err;
+
+ hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
+ if (!hugepages_kobj)
+ return;
+
+ for_each_hstate(h) {
+ err = hugetlb_sysfs_add_hstate(h);
+ if (err)
+ printk(KERN_ERR "Hugetlb: Unable to add hstate %s",
+ h->name);
+ }
+}
+
+static void __exit hugetlb_exit(void)
+{
+ struct hstate *h;
+
+ for_each_hstate(h) {
+ kobject_put(hstate_kobjs[h - hstates]);
+ }
+
+ kobject_put(hugepages_kobj);
+}
+module_exit(hugetlb_exit);
+
+static int __init hugetlb_init(void)
+{
+ BUILD_BUG_ON(HPAGE_SHIFT == 0);
+
+ if (!size_to_hstate(default_hstate_size)) {
+ default_hstate_size = HPAGE_SIZE;
+ if (!size_to_hstate(default_hstate_size))
+ hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
+ }
+ default_hstate_idx = size_to_hstate(default_hstate_size) - hstates;
+ if (default_hstate_max_huge_pages)
+ default_hstate.max_huge_pages = default_hstate_max_huge_pages;
+
+ hugetlb_init_hstates();
+
+ gather_bootmem_prealloc();
+
+ report_hugepages();
+
+ hugetlb_sysfs_init();
+
+ return 0;
+}
+module_init(hugetlb_init);
+
+/* Should be called on processing a hugepagesz=... option */
+void __init hugetlb_add_hstate(unsigned order)
+{
+ struct hstate *h;
+ unsigned long i;
+
+ if (size_to_hstate(PAGE_SIZE << order)) {
+ printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
+ return;
+ }
+ BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
+ BUG_ON(order == 0);
+ h = &hstates[max_hstate++];
+ h->order = order;
+ h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
+ h->nr_huge_pages = 0;
+ h->free_huge_pages = 0;
+ for (i = 0; i < MAX_NUMNODES; ++i)
+ INIT_LIST_HEAD(&h->hugepage_freelists[i]);
+ h->hugetlb_next_nid = first_node(node_online_map);
+ snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
+ huge_page_size(h)/1024);
+
+ parsed_hstate = h;
+}
+
+static int __init hugetlb_nrpages_setup(char *s)
+{
+ unsigned long *mhp;
+ static unsigned long *last_mhp;
+
+ /*
+ * !max_hstate means we haven't parsed a hugepagesz= parameter yet,
+ * so this hugepages= parameter goes to the "default hstate".
+ */
+ if (!max_hstate)
+ mhp = &default_hstate_max_huge_pages;
+ else
+ mhp = &parsed_hstate->max_huge_pages;
+
+ if (mhp == last_mhp) {
+ printk(KERN_WARNING "hugepages= specified twice without "
+ "interleaving hugepagesz=, ignoring\n");
+ return 1;
+ }
+
+ if (sscanf(s, "%lu", mhp) <= 0)
+ *mhp = 0;
+
+ /*
+ * Global state is always initialized later in hugetlb_init.
+ * But we need to allocate >= MAX_ORDER hstates here early to still
+ * use the bootmem allocator.
+ */
+ if (max_hstate && parsed_hstate->order >= MAX_ORDER)
+ hugetlb_hstate_alloc_pages(parsed_hstate);
+
+ last_mhp = mhp;
+
+ return 1;
+}
+__setup("hugepages=", hugetlb_nrpages_setup);
+
+static int __init hugetlb_default_setup(char *s)
+{
+ default_hstate_size = memparse(s, &s);
+ return 1;
+}
+__setup("default_hugepagesz=", hugetlb_default_setup);
+
+static unsigned int cpuset_mems_nr(unsigned int *array)
+{
+ int node;
+ unsigned int nr = 0;
+
+ for_each_node_mask(node, cpuset_current_mems_allowed)
+ nr += array[node];
+
+ return nr;
+}
+
int hugetlb_sysctl_handler(struct ctl_table *table, int write,
struct file *file, void __user *buffer,
size_t *length, loff_t *ppos)
kref_put(&reservations->refs, resv_map_release);
- if (reserve)
+ if (reserve) {
hugetlb_acct_memory(h, -reserve);
+ hugetlb_put_quota(vma->vm_file->f_mapping, reserve);
+ }
}
}
return ret;
}
+/* Can be overriden by architectures */
+__attribute__((weak)) struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+ pud_t *pud, int write)
+{
+ BUG();
+ return NULL;
+}
+
int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
struct page **pages, struct vm_area_struct **vmas,
unsigned long *position, int *length, int i,