#include "internal.h"
const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-static unsigned long nr_huge_pages, free_huge_pages;
+static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages;
unsigned long max_huge_pages;
static struct list_head hugepage_freelists[MAX_NUMNODES];
static unsigned int nr_huge_pages_node[MAX_NUMNODES];
return page;
}
+static void free_huge_page(struct page *page)
+{
+ BUG_ON(page_count(page));
+
+ INIT_LIST_HEAD(&page->lru);
+
+ spin_lock(&hugetlb_lock);
+ enqueue_huge_page(page);
+ spin_unlock(&hugetlb_lock);
+}
+
static int alloc_fresh_huge_page(void)
{
static int nid = 0;
struct page *page;
page = alloc_pages_node(nid, GFP_HIGHUSER|__GFP_COMP|__GFP_NOWARN,
HUGETLB_PAGE_ORDER);
- nid = (nid + 1) % num_online_nodes();
+ nid = next_node(nid, node_online_map);
+ if (nid == MAX_NUMNODES)
+ nid = first_node(node_online_map);
if (page) {
page[1].lru.next = (void *)free_huge_page; /* dtor */
spin_lock(&hugetlb_lock);
return 0;
}
-void free_huge_page(struct page *page)
-{
- BUG_ON(page_count(page));
-
- INIT_LIST_HEAD(&page->lru);
-
- spin_lock(&hugetlb_lock);
- enqueue_huge_page(page);
- spin_unlock(&hugetlb_lock);
-}
-
-struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr)
+static struct page *alloc_huge_page(struct vm_area_struct *vma,
+ unsigned long addr)
{
struct page *page;
spin_lock(&hugetlb_lock);
+ if (vma->vm_flags & VM_MAYSHARE)
+ resv_huge_pages--;
+ else if (free_huge_pages <= resv_huge_pages)
+ goto fail;
+
page = dequeue_huge_page(vma, addr);
- if (!page) {
- spin_unlock(&hugetlb_lock);
- return NULL;
- }
+ if (!page)
+ goto fail;
+
spin_unlock(&hugetlb_lock);
set_page_refcounted(page);
return page;
+
+fail:
+ spin_unlock(&hugetlb_lock);
+ return NULL;
}
static int __init hugetlb_init(void)
return nr_huge_pages;
spin_lock(&hugetlb_lock);
+ count = max(count, resv_huge_pages);
try_to_free_low(count);
while (count < nr_huge_pages) {
struct page *page = dequeue_huge_page(NULL, 0);
return sprintf(buf,
"HugePages_Total: %5lu\n"
"HugePages_Free: %5lu\n"
+ "HugePages_Rsvd: %5lu\n"
"Hugepagesize: %5lu kB\n",
nr_huge_pages,
free_huge_pages,
+ resv_huge_pages,
HPAGE_SIZE/1024);
}
nid, free_huge_pages_node[nid]);
}
-int is_hugepage_mem_enough(size_t size)
-{
- return (size + ~HPAGE_MASK)/HPAGE_SIZE <= free_huge_pages;
-}
-
/* Return the number pages of memory we physically have, in PAGE_SIZE units. */
unsigned long hugetlb_total_pages(void)
{
struct page **pages, struct vm_area_struct **vmas,
unsigned long *position, int *length, int i)
{
- unsigned long vpfn, vaddr = *position;
+ unsigned long pfn_offset;
+ unsigned long vaddr = *position;
int remainder = *length;
- vpfn = vaddr/PAGE_SIZE;
spin_lock(&mm->page_table_lock);
while (vaddr < vma->vm_end && remainder) {
pte_t *pte;
break;
}
+ pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT;
+ page = pte_page(*pte);
+same_page:
if (pages) {
- page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
get_page(page);
- pages[i] = page;
+ pages[i] = page + pfn_offset;
}
if (vmas)
vmas[i] = vma;
vaddr += PAGE_SIZE;
- ++vpfn;
+ ++pfn_offset;
--remainder;
++i;
+ if (vaddr < vma->vm_end && remainder &&
+ pfn_offset < HPAGE_SIZE/PAGE_SIZE) {
+ /*
+ * We use pfn_offset to avoid touching the pageframes
+ * of this compound page.
+ */
+ goto same_page;
+ }
}
spin_unlock(&mm->page_table_lock);
*length = remainder;
flush_tlb_range(vma, start, end);
}
+struct file_region {
+ struct list_head link;
+ long from;
+ long to;
+};
+
+static long region_add(struct list_head *head, long f, long t)
+{
+ struct file_region *rg, *nrg, *trg;
+
+ /* Locate the region we are either in or before. */
+ list_for_each_entry(rg, head, link)
+ if (f <= rg->to)
+ break;
+
+ /* Round our left edge to the current segment if it encloses us. */
+ if (f > rg->from)
+ f = rg->from;
+
+ /* Check for and consume any regions we now overlap with. */
+ nrg = rg;
+ list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+ if (&rg->link == head)
+ break;
+ if (rg->from > t)
+ break;
+
+ /* If this area reaches higher then extend our area to
+ * include it completely. If this is not the first area
+ * which we intend to reuse, free it. */
+ if (rg->to > t)
+ t = rg->to;
+ if (rg != nrg) {
+ list_del(&rg->link);
+ kfree(rg);
+ }
+ }
+ nrg->from = f;
+ nrg->to = t;
+ return 0;
+}
+
+static long region_chg(struct list_head *head, long f, long t)
+{
+ struct file_region *rg, *nrg;
+ long chg = 0;
+
+ /* Locate the region we are before or in. */
+ list_for_each_entry(rg, head, link)
+ if (f <= rg->to)
+ break;
+
+ /* If we are below the current region then a new region is required.
+ * Subtle, allocate a new region at the position but make it zero
+ * size such that we can guarentee to record the reservation. */
+ if (&rg->link == head || t < rg->from) {
+ nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
+ if (nrg == 0)
+ return -ENOMEM;
+ nrg->from = f;
+ nrg->to = f;
+ INIT_LIST_HEAD(&nrg->link);
+ list_add(&nrg->link, rg->link.prev);
+
+ return t - f;
+ }
+
+ /* Round our left edge to the current segment if it encloses us. */
+ if (f > rg->from)
+ f = rg->from;
+ chg = t - f;
+
+ /* Check for and consume any regions we now overlap with. */
+ list_for_each_entry(rg, rg->link.prev, link) {
+ if (&rg->link == head)
+ break;
+ if (rg->from > t)
+ return chg;
+
+ /* We overlap with this area, if it extends futher than
+ * us then we must extend ourselves. Account for its
+ * existing reservation. */
+ if (rg->to > t) {
+ chg += rg->to - t;
+ t = rg->to;
+ }
+ chg -= rg->to - rg->from;
+ }
+ return chg;
+}
+
+static long region_truncate(struct list_head *head, long end)
+{
+ struct file_region *rg, *trg;
+ long chg = 0;
+
+ /* Locate the region we are either in or before. */
+ list_for_each_entry(rg, head, link)
+ if (end <= rg->to)
+ break;
+ if (&rg->link == head)
+ return 0;
+
+ /* If we are in the middle of a region then adjust it. */
+ if (end > rg->from) {
+ chg = rg->to - end;
+ rg->to = end;
+ rg = list_entry(rg->link.next, typeof(*rg), link);
+ }
+
+ /* Drop any remaining regions. */
+ list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+ if (&rg->link == head)
+ break;
+ chg += rg->to - rg->from;
+ list_del(&rg->link);
+ kfree(rg);
+ }
+ return chg;
+}
+
+static int hugetlb_acct_memory(long delta)
+{
+ int ret = -ENOMEM;
+
+ spin_lock(&hugetlb_lock);
+ if ((delta + resv_huge_pages) <= free_huge_pages) {
+ resv_huge_pages += delta;
+ ret = 0;
+ }
+ spin_unlock(&hugetlb_lock);
+ return ret;
+}
+
+int hugetlb_reserve_pages(struct inode *inode, long from, long to)
+{
+ long ret, chg;
+
+ chg = region_chg(&inode->i_mapping->private_list, from, to);
+ if (chg < 0)
+ return chg;
+ ret = hugetlb_acct_memory(chg);
+ if (ret < 0)
+ return ret;
+ region_add(&inode->i_mapping->private_list, from, to);
+ return 0;
+}
+
+void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
+{
+ long chg = region_truncate(&inode->i_mapping->private_list, offset);
+ hugetlb_acct_memory(freed - chg);
+}