const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages;
static unsigned long surplus_huge_pages;
+static unsigned long nr_overcommit_huge_pages;
unsigned long max_huge_pages;
+unsigned long sysctl_overcommit_huge_pages;
static struct list_head hugepage_freelists[MAX_NUMNODES];
static unsigned int nr_huge_pages_node[MAX_NUMNODES];
static unsigned int free_huge_pages_node[MAX_NUMNODES];
static unsigned int surplus_huge_pages_node[MAX_NUMNODES];
static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
unsigned long hugepages_treat_as_movable;
-int hugetlb_dynamic_pool;
static int hugetlb_next_nid;
/*
unsigned long address)
{
struct page *page;
+ unsigned int nid;
- /* Check if the dynamic pool is enabled */
- if (!hugetlb_dynamic_pool)
+ /*
+ * Assume we will successfully allocate the surplus page to
+ * prevent racing processes from causing the surplus to exceed
+ * overcommit
+ *
+ * This however introduces a different race, where a process B
+ * tries to grow the static hugepage pool while alloc_pages() is
+ * called by process A. B will only examine the per-node
+ * counters in determining if surplus huge pages can be
+ * converted to normal huge pages in adjust_pool_surplus(). A
+ * won't be able to increment the per-node counter, until the
+ * lock is dropped by B, but B doesn't drop hugetlb_lock until
+ * no more huge pages can be converted from surplus to normal
+ * state (and doesn't try to convert again). Thus, we have a
+ * case where a surplus huge page exists, the pool is grown, and
+ * the surplus huge page still exists after, even though it
+ * should just have been converted to a normal huge page. This
+ * does not leak memory, though, as the hugepage will be freed
+ * once it is out of use. It also does not allow the counters to
+ * go out of whack in adjust_pool_surplus() as we don't modify
+ * the node values until we've gotten the hugepage and only the
+ * per-node value is checked there.
+ */
+ spin_lock(&hugetlb_lock);
+ if (surplus_huge_pages >= nr_overcommit_huge_pages) {
+ spin_unlock(&hugetlb_lock);
return NULL;
+ } else {
+ nr_huge_pages++;
+ surplus_huge_pages++;
+ }
+ spin_unlock(&hugetlb_lock);
page = alloc_pages(htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
HUGETLB_PAGE_ORDER);
+
+ spin_lock(&hugetlb_lock);
if (page) {
+ nid = page_to_nid(page);
set_compound_page_dtor(page, free_huge_page);
- spin_lock(&hugetlb_lock);
- nr_huge_pages++;
- nr_huge_pages_node[page_to_nid(page)]++;
- surplus_huge_pages++;
- surplus_huge_pages_node[page_to_nid(page)]++;
- spin_unlock(&hugetlb_lock);
+ /*
+ * We incremented the global counters already
+ */
+ nr_huge_pages_node[nid]++;
+ surplus_huge_pages_node[nid]++;
+ } else {
+ nr_huge_pages--;
+ surplus_huge_pages--;
}
+ spin_unlock(&hugetlb_lock);
return page;
}
if (free_huge_pages > resv_huge_pages)
page = dequeue_huge_page(vma, addr);
spin_unlock(&hugetlb_lock);
- if (!page)
+ if (!page) {
page = alloc_buddy_huge_page(vma, addr);
- return page ? page : ERR_PTR(-VM_FAULT_OOM);
+ if (!page) {
+ hugetlb_put_quota(vma->vm_file->f_mapping, 1);
+ return ERR_PTR(-VM_FAULT_OOM);
+ }
+ }
+ return page;
}
static struct page *alloc_huge_page(struct vm_area_struct *vma,
* Increase the pool size
* First take pages out of surplus state. Then make up the
* remaining difference by allocating fresh huge pages.
+ *
+ * We might race with alloc_buddy_huge_page() here and be unable
+ * to convert a surplus huge page to a normal huge page. That is
+ * not critical, though, it just means the overall size of the
+ * pool might be one hugepage larger than it needs to be, but
+ * within all the constraints specified by the sysctls.
*/
spin_lock(&hugetlb_lock);
while (surplus_huge_pages && count > persistent_huge_pages) {
* to keep enough around to satisfy reservations). Then place
* pages into surplus state as needed so the pool will shrink
* to the desired size as pages become free.
+ *
+ * By placing pages into the surplus state independent of the
+ * overcommit value, we are allowing the surplus pool size to
+ * exceed overcommit. There are few sane options here. Since
+ * alloc_buddy_huge_page() is checking the global counter,
+ * though, we'll note that we're not allowed to exceed surplus
+ * and won't grow the pool anywhere else. Not until one of the
+ * sysctls are changed, or the surplus pages go out of use.
*/
min_count = resv_huge_pages + nr_huge_pages - free_huge_pages;
min_count = max(count, min_count);
return 0;
}
+int hugetlb_overcommit_handler(struct ctl_table *table, int write,
+ struct file *file, void __user *buffer,
+ size_t *length, loff_t *ppos)
+{
+ proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+ spin_lock(&hugetlb_lock);
+ nr_overcommit_huge_pages = sysctl_overcommit_huge_pages;
+ spin_unlock(&hugetlb_lock);
+ return 0;
+}
+
#endif /* CONFIG_SYSCTL */
int hugetlb_report_meminfo(char *buf)
dst_pte = huge_pte_alloc(dst, addr);
if (!dst_pte)
goto nomem;
+
+ /* If the pagetables are shared don't copy or take references */
+ if (dst_pte == src_pte)
+ continue;
+
spin_lock(&dst->page_table_lock);
spin_lock(&src->page_table_lock);
if (!pte_none(*src_pte)) {
spin_unlock(&mm->page_table_lock);
copy_huge_page(new_page, old_page, address, vma);
+ __SetPageUptodate(new_page);
spin_lock(&mm->page_table_lock);
ptep = huge_pte_offset(mm, address & HPAGE_MASK);
goto out;
}
clear_huge_page(page, address);
+ __SetPageUptodate(page);
if (vma->vm_flags & VM_SHARED) {
int err;
if (hugetlb_get_quota(inode->i_mapping, chg))
return -ENOSPC;
ret = hugetlb_acct_memory(chg);
- if (ret < 0)
+ if (ret < 0) {
+ hugetlb_put_quota(inode->i_mapping, chg);
return ret;
+ }
region_add(&inode->i_mapping->private_list, from, to);
return 0;
}