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;
/*
free_huge_pages_node[nid]++;
}
-static struct page *dequeue_huge_page(struct vm_area_struct *vma,
+static struct page *dequeue_huge_page(void)
+{
+ int nid;
+ struct page *page = NULL;
+
+ for (nid = 0; nid < MAX_NUMNODES; ++nid) {
+ if (!list_empty(&hugepage_freelists[nid])) {
+ page = list_entry(hugepage_freelists[nid].next,
+ struct page, lru);
+ list_del(&page->lru);
+ free_huge_pages--;
+ free_huge_pages_node[nid]--;
+ break;
+ }
+ }
+ return page;
+}
+
+static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
unsigned long address)
{
int nid;
struct page *page = NULL;
struct mempolicy *mpol;
+ nodemask_t *nodemask;
struct zonelist *zonelist = huge_zonelist(vma, address,
- htlb_alloc_mask, &mpol);
- struct zone **z;
-
- for (z = zonelist->zones; *z; z++) {
- nid = zone_to_nid(*z);
- if (cpuset_zone_allowed_softwall(*z, htlb_alloc_mask) &&
+ htlb_alloc_mask, &mpol, &nodemask);
+ struct zone *zone;
+ struct zoneref *z;
+
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ MAX_NR_ZONES - 1, nodemask) {
+ nid = zone_to_nid(zone);
+ if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
!list_empty(&hugepage_freelists[nid])) {
page = list_entry(hugepage_freelists[nid].next,
struct page, lru);
break;
}
}
- mpol_free(mpol); /* unref if mpol !NULL */
+ mpol_cond_put(mpol);
return page;
}
}
set_compound_page_dtor(page, NULL);
set_page_refcounted(page);
+ arch_release_hugepage(page);
__free_pages(page, HUGETLB_PAGE_ORDER);
}
struct address_space *mapping;
mapping = (struct address_space *) page_private(page);
+ set_page_private(page, 0);
BUG_ON(page_count(page));
INIT_LIST_HEAD(&page->lru);
spin_unlock(&hugetlb_lock);
if (mapping)
hugetlb_put_quota(mapping, 1);
- set_page_private(page, 0);
}
/*
struct page *page;
page = alloc_pages_node(nid,
- htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|__GFP_NOWARN,
+ htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+ __GFP_REPEAT|__GFP_NOWARN,
HUGETLB_PAGE_ORDER);
if (page) {
+ if (arch_prepare_hugepage(page)) {
+ __free_pages(page, HUGETLB_PAGE_ORDER);
+ return NULL;
+ }
set_compound_page_dtor(page, free_huge_page);
spin_lock(&hugetlb_lock);
nr_huge_pages++;
hugetlb_next_nid = next_nid;
} while (!page && hugetlb_next_nid != start_nid);
+ if (ret)
+ count_vm_event(HTLB_BUDDY_PGALLOC);
+ else
+ count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
+
return ret;
}
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,
+ page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
+ __GFP_REPEAT|__GFP_NOWARN,
HUGETLB_PAGE_ORDER);
+
+ spin_lock(&hugetlb_lock);
if (page) {
+ /*
+ * This page is now managed by the hugetlb allocator and has
+ * no users -- drop the buddy allocator's reference.
+ */
+ put_page_testzero(page);
+ VM_BUG_ON(page_count(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]++;
+ __count_vm_event(HTLB_BUDDY_PGALLOC);
+ } else {
+ nr_huge_pages--;
+ surplus_huge_pages--;
+ __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
}
+ spin_unlock(&hugetlb_lock);
return page;
}
int needed, allocated;
needed = (resv_huge_pages + delta) - free_huge_pages;
- if (needed <= 0)
+ if (needed <= 0) {
+ resv_huge_pages += delta;
return 0;
+ }
allocated = 0;
INIT_LIST_HEAD(&surplus_list);
* The surplus_list now contains _at_least_ the number of extra pages
* needed to accomodate the reservation. Add the appropriate number
* of pages to the hugetlb pool and free the extras back to the buddy
- * allocator.
+ * allocator. Commit the entire reservation here to prevent another
+ * process from stealing the pages as they are added to the pool but
+ * before they are reserved.
*/
needed += allocated;
+ resv_huge_pages += delta;
ret = 0;
free:
+ /* Free the needed pages to the hugetlb pool */
list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
+ if ((--needed) < 0)
+ break;
list_del(&page->lru);
- if ((--needed) >= 0)
- enqueue_huge_page(page);
- else {
+ enqueue_huge_page(page);
+ }
+
+ /* Free unnecessary surplus pages to the buddy allocator */
+ if (!list_empty(&surplus_list)) {
+ spin_unlock(&hugetlb_lock);
+ list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
+ list_del(&page->lru);
/*
- * Decrement the refcount and free the page using its
- * destructor. This must be done with hugetlb_lock
+ * The page has a reference count of zero already, so
+ * call free_huge_page directly instead of using
+ * put_page. This must be done with hugetlb_lock
* unlocked which is safe because free_huge_page takes
* hugetlb_lock before deciding how to free the page.
*/
- spin_unlock(&hugetlb_lock);
- put_page(page);
- spin_lock(&hugetlb_lock);
+ free_huge_page(page);
}
+ spin_lock(&hugetlb_lock);
}
return ret;
* allocated to satisfy the reservation must be explicitly freed if they were
* never used.
*/
-void return_unused_surplus_pages(unsigned long unused_resv_pages)
+static void return_unused_surplus_pages(unsigned long unused_resv_pages)
{
static int nid = -1;
struct page *page;
unsigned long nr_pages;
+ /*
+ * We want to release as many surplus pages as possible, spread
+ * evenly across all nodes. Iterate across all nodes until we
+ * can no longer free unreserved surplus pages. This occurs when
+ * the nodes with surplus pages have no free pages.
+ */
+ unsigned long remaining_iterations = num_online_nodes();
+
+ /* Uncommit the reservation */
+ resv_huge_pages -= unused_resv_pages;
+
nr_pages = min(unused_resv_pages, surplus_huge_pages);
- while (nr_pages) {
+ while (remaining_iterations-- && nr_pages) {
nid = next_node(nid, node_online_map);
if (nid == MAX_NUMNODES)
nid = first_node(node_online_map);
surplus_huge_pages--;
surplus_huge_pages_node[nid]--;
nr_pages--;
+ remaining_iterations = num_online_nodes();
}
}
}
struct page *page;
spin_lock(&hugetlb_lock);
- page = dequeue_huge_page(vma, addr);
+ page = dequeue_huge_page_vma(vma, addr);
spin_unlock(&hugetlb_lock);
return page ? page : ERR_PTR(-VM_FAULT_OOM);
}
spin_lock(&hugetlb_lock);
if (free_huge_pages > resv_huge_pages)
- page = dequeue_huge_page(vma, addr);
+ page = dequeue_huge_page_vma(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);
try_to_free_low(min_count);
while (min_count < persistent_huge_pages) {
- struct page *page = dequeue_huge_page(NULL, 0);
+ struct page *page = dequeue_huge_page();
if (!page)
break;
update_and_free_page(page);
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)
{
return sprintf(buf,
"Node %d HugePages_Total: %5u\n"
- "Node %d HugePages_Free: %5u\n",
+ "Node %d HugePages_Free: %5u\n"
+ "Node %d HugePages_Surp: %5u\n",
nid, nr_huge_pages_node[nid],
- nid, free_huge_pages_node[nid]);
+ nid, free_huge_pages_node[nid],
+ nid, surplus_huge_pages_node[nid]);
}
/* Return the number pages of memory we physically have, in PAGE_SIZE units. */
entry =
pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
} else {
- entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
+ entry = huge_pte_wrprotect(mk_pte(page, vma->vm_page_prot));
}
entry = pte_mkyoung(entry);
entry = pte_mkhuge(entry);
{
pte_t entry;
- entry = pte_mkwrite(pte_mkdirty(*ptep));
- if (ptep_set_access_flags(vma, address, ptep, entry, 1)) {
+ entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
+ if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) {
update_mmu_cache(vma, address, entry);
}
}
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)) {
+ if (!huge_pte_none(huge_ptep_get(src_pte))) {
if (cow)
- ptep_set_wrprotect(src, addr, src_pte);
- entry = *src_pte;
+ huge_ptep_set_wrprotect(src, addr, src_pte);
+ entry = huge_ptep_get(src_pte);
ptepage = pte_page(entry);
get_page(ptepage);
set_huge_pte_at(dst, addr, dst_pte, entry);
continue;
pte = huge_ptep_get_and_clear(mm, address, ptep);
- if (pte_none(pte))
+ if (huge_pte_none(pte))
continue;
page = pte_page(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);
- if (likely(pte_same(*ptep, pte))) {
+ if (likely(pte_same(huge_ptep_get(ptep), pte))) {
/* Break COW */
+ huge_ptep_clear_flush(vma, address, ptep);
set_huge_pte_at(mm, address, ptep,
make_huge_pte(vma, new_page, 1));
/* Make the old page be freed below */
goto out;
}
clear_huge_page(page, address);
+ __SetPageUptodate(page);
if (vma->vm_flags & VM_SHARED) {
int err;
+ struct inode *inode = mapping->host;
err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
if (err) {
goto retry;
goto out;
}
+
+ spin_lock(&inode->i_lock);
+ inode->i_blocks += BLOCKS_PER_HUGEPAGE;
+ spin_unlock(&inode->i_lock);
} else
lock_page(page);
}
goto backout;
ret = 0;
- if (!pte_none(*ptep))
+ if (!huge_pte_none(huge_ptep_get(ptep)))
goto backout;
new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
* the same page in the page cache.
*/
mutex_lock(&hugetlb_instantiation_mutex);
- entry = *ptep;
- if (pte_none(entry)) {
+ entry = huge_ptep_get(ptep);
+ if (huge_pte_none(entry)) {
ret = hugetlb_no_page(mm, vma, address, ptep, write_access);
mutex_unlock(&hugetlb_instantiation_mutex);
return ret;
spin_lock(&mm->page_table_lock);
/* Check for a racing update before calling hugetlb_cow */
- if (likely(pte_same(entry, *ptep)))
+ if (likely(pte_same(entry, huge_ptep_get(ptep))))
if (write_access && !pte_write(entry))
ret = hugetlb_cow(mm, vma, address, ptep, entry);
spin_unlock(&mm->page_table_lock);
*/
pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
- if (!pte || pte_none(*pte)) {
+ if (!pte || huge_pte_none(huge_ptep_get(pte)) ||
+ (write && !pte_write(huge_ptep_get(pte)))) {
int ret;
spin_unlock(&mm->page_table_lock);
}
pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT;
- page = pte_page(*pte);
+ page = pte_page(huge_ptep_get(pte));
same_page:
if (pages) {
get_page(page);
continue;
if (huge_pmd_unshare(mm, &address, ptep))
continue;
- if (!pte_none(*ptep)) {
+ if (!huge_pte_none(huge_ptep_get(ptep))) {
pte = huge_ptep_get_and_clear(mm, address, ptep);
pte = pte_mkhuge(pte_modify(pte, newprot));
set_huge_pte_at(mm, address, ptep, pte);
if (gather_surplus_pages(delta) < 0)
goto out;
- if (delta > cpuset_mems_nr(free_huge_pages_node))
+ if (delta > cpuset_mems_nr(free_huge_pages_node)) {
+ return_unused_surplus_pages(delta);
goto out;
+ }
}
ret = 0;
- resv_huge_pages += delta;
if (delta < 0)
return_unused_surplus_pages((unsigned long) -delta);
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;
}
void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
{
long chg = region_truncate(&inode->i_mapping->private_list, offset);
+
+ spin_lock(&inode->i_lock);
+ inode->i_blocks -= BLOCKS_PER_HUGEPAGE * freed;
+ spin_unlock(&inode->i_lock);
+
hugetlb_put_quota(inode->i_mapping, (chg - freed));
hugetlb_acct_memory(-(chg - freed));
}