1 files changed, 215 insertions, 162 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9a334f5fb730..7c204e3d132b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -34,10 +34,9 @@
 #include <linux/hugetlb_cgroup.h>
 #include <linux/node.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/page_owner.h>
 #include "internal.h"
 
-int hugepages_treat_as_movable;
-
 int hugetlb_max_hstate __read_mostly;
 unsigned int default_hstate_idx;
 struct hstate hstates[HUGE_MAX_HSTATE];
@@ -926,7 +925,7 @@ retry_cpuset:
 /* Movability of hugepages depends on migration support. */
 static inline gfp_t htlb_alloc_mask(struct hstate *h)
 {
-	if (hugepages_treat_as_movable || hugepage_migration_supported(h))
+	if (hugepage_migration_supported(h))
 		return GFP_HIGHUSER_MOVABLE;
 	else
 		return GFP_HIGHUSER;
@@ -1108,7 +1107,8 @@ static bool zone_spans_last_pfn(const struct zone *zone,
 	return zone_spans_pfn(zone, last_pfn);
 }
 
-static struct page *alloc_gigantic_page(int nid, struct hstate *h)
+static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
+		int nid, nodemask_t *nodemask)
 {
 	unsigned int order = huge_page_order(h);
 	unsigned long nr_pages = 1 << order;
@@ -1116,11 +1116,9 @@ static struct page *alloc_gigantic_page(int nid, struct hstate *h)
 	struct zonelist *zonelist;
 	struct zone *zone;
 	struct zoneref *z;
-	gfp_t gfp_mask;
 
-	gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 	zonelist = node_zonelist(nid, gfp_mask);
-	for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), NULL) {
+	for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) {
 		spin_lock_irqsave(&zone->lock, flags);
 
 		pfn = ALIGN(zone->zone_start_pfn, nr_pages);
@@ -1151,41 +1149,13 @@ static struct page *alloc_gigantic_page(int nid, struct hstate *h)
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
 static void prep_compound_gigantic_page(struct page *page, unsigned int order);
 
-static struct page *alloc_fresh_gigantic_page_node(struct hstate *h, int nid)
-{
-	struct page *page;
-
-	page = alloc_gigantic_page(nid, h);
-	if (page) {
-		prep_compound_gigantic_page(page, huge_page_order(h));
-		prep_new_huge_page(h, page, nid);
-	}
-
-	return page;
-}
-
-static int alloc_fresh_gigantic_page(struct hstate *h,
-				nodemask_t *nodes_allowed)
-{
-	struct page *page = NULL;
-	int nr_nodes, node;
-
-	for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
-		page = alloc_fresh_gigantic_page_node(h, node);
-		if (page)
-			return 1;
-	}
-
-	return 0;
-}
-
 #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */
 static inline bool gigantic_page_supported(void) { return false; }
+static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
+		int nid, nodemask_t *nodemask) { return NULL; }
 static inline void free_gigantic_page(struct page *page, unsigned int order) { }
 static inline void destroy_compound_gigantic_page(struct page *page,
 						unsigned int order) { }
-static inline int alloc_fresh_gigantic_page(struct hstate *h,
-					nodemask_t *nodes_allowed) { return 0; }
 #endif
 
 static void update_and_free_page(struct hstate *h, struct page *page)
@@ -1250,6 +1220,28 @@ static void clear_page_huge_active(struct page *page)
 	ClearPagePrivate(&page[1]);
 }
 
+/*
+ * Internal hugetlb specific page flag. Do not use outside of the hugetlb
+ * code
+ */
+static inline bool PageHugeTemporary(struct page *page)
+{
+	if (!PageHuge(page))
+		return false;
+
+	return (unsigned long)page[2].mapping == -1U;
+}
+
+static inline void SetPageHugeTemporary(struct page *page)
+{
+	page[2].mapping = (void *)-1U;
+}
+
+static inline void ClearPageHugeTemporary(struct page *page)
+{
+	page[2].mapping = NULL;
+}
+
 void free_huge_page(struct page *page)
 {
 	/*
@@ -1284,7 +1276,11 @@ void free_huge_page(struct page *page)
 	if (restore_reserve)
 		h->resv_huge_pages++;
 
-	if (h->surplus_huge_pages_node[nid]) {
+	if (PageHugeTemporary(page)) {
+		list_del(&page->lru);
+		ClearPageHugeTemporary(page);
+		update_and_free_page(h, page);
+	} else if (h->surplus_huge_pages_node[nid]) {
 		/* remove the page from active list */
 		list_del(&page->lru);
 		update_and_free_page(h, page);
@@ -1306,7 +1302,6 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
 	spin_unlock(&hugetlb_lock);
-	put_page(page); /* free it into the hugepage allocator */
 }
 
 static void prep_compound_gigantic_page(struct page *page, unsigned int order)
@@ -1383,41 +1378,70 @@ pgoff_t __basepage_index(struct page *page)
 	return (index << compound_order(page_head)) + compound_idx;
 }
 
-static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
+static struct page *alloc_buddy_huge_page(struct hstate *h,
+		gfp_t gfp_mask, int nid, nodemask_t *nmask)
 {
+	int order = huge_page_order(h);
 	struct page *page;
 
-	page = __alloc_pages_node(nid,
-		htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
-						__GFP_RETRY_MAYFAIL|__GFP_NOWARN,
-		huge_page_order(h));
-	if (page) {
-		prep_new_huge_page(h, page, nid);
-	}
+	gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
+	page = __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
+	if (page)
+		__count_vm_event(HTLB_BUDDY_PGALLOC);
+	else
+		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
+
+	return page;
+}
+
+/*
+ * Common helper to allocate a fresh hugetlb page. All specific allocators
+ * should use this function to get new hugetlb pages
+ */
+static struct page *alloc_fresh_huge_page(struct hstate *h,
+		gfp_t gfp_mask, int nid, nodemask_t *nmask)
+{
+	struct page *page;
+
+	if (hstate_is_gigantic(h))
+		page = alloc_gigantic_page(h, gfp_mask, nid, nmask);
+	else
+		page = alloc_buddy_huge_page(h, gfp_mask,
+				nid, nmask);
+	if (!page)
+		return NULL;
+
+	if (hstate_is_gigantic(h))
+		prep_compound_gigantic_page(page, huge_page_order(h));
+	prep_new_huge_page(h, page, page_to_nid(page));
 
 	return page;
 }
 
-static int alloc_fresh_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
+/*
+ * Allocates a fresh page to the hugetlb allocator pool in the node interleaved
+ * manner.
+ */
+static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
 {
 	struct page *page;
 	int nr_nodes, node;
-	int ret = 0;
+	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 
 	for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
-		page = alloc_fresh_huge_page_node(h, node);
-		if (page) {
-			ret = 1;
+		page = alloc_fresh_huge_page(h, gfp_mask, node, nodes_allowed);
+		if (page)
 			break;
-		}
 	}
 
-	if (ret)
-		count_vm_event(HTLB_BUDDY_PGALLOC);
-	else
-		count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
+	if (!page)
+		return 0;
 
-	return ret;
+	put_page(page); /* free it into the hugepage allocator */
+
+	return 1;
 }
 
 /*
@@ -1525,79 +1549,66 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 	return rc;
 }
 
-static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
-		gfp_t gfp_mask, int nid, nodemask_t *nmask)
-{
-	int order = huge_page_order(h);
-
-	gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
-	if (nid == NUMA_NO_NODE)
-		nid = numa_mem_id();
-	return __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
-}
-
-static struct page *__alloc_buddy_huge_page(struct hstate *h, gfp_t gfp_mask,
+/*
+ * Allocates a fresh surplus page from the page allocator.
+ */
+static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
 		int nid, nodemask_t *nmask)
 {
-	struct page *page;
-	unsigned int r_nid;
+	struct page *page = NULL;
 
 	if (hstate_is_gigantic(h))
 		return NULL;
 
+	spin_lock(&hugetlb_lock);
+	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages)
+		goto out_unlock;
+	spin_unlock(&hugetlb_lock);
+
+	page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask);
+	if (!page)
+		return NULL;
+
+	spin_lock(&hugetlb_lock);
 	/*
-	 * 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.
+	 * We could have raced with the pool size change.
+	 * Double check that and simply deallocate the new page
+	 * if we would end up overcommiting the surpluses. Abuse
+	 * temporary page to workaround the nasty free_huge_page
+	 * codeflow
 	 */
-	spin_lock(&hugetlb_lock);
 	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
-		spin_unlock(&hugetlb_lock);
-		return NULL;
+		SetPageHugeTemporary(page);
+		put_page(page);
+		page = NULL;
 	} else {
-		h->nr_huge_pages++;
 		h->surplus_huge_pages++;
+		h->nr_huge_pages_node[page_to_nid(page)]++;
 	}
+
+out_unlock:
 	spin_unlock(&hugetlb_lock);
 
-	page = __hugetlb_alloc_buddy_huge_page(h, gfp_mask, nid, nmask);
+	return page;
+}
 
-	spin_lock(&hugetlb_lock);
-	if (page) {
-		INIT_LIST_HEAD(&page->lru);
-		r_nid = page_to_nid(page);
-		set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
-		set_hugetlb_cgroup(page, NULL);
-		/*
-		 * We incremented the global counters already
-		 */
-		h->nr_huge_pages_node[r_nid]++;
-		h->surplus_huge_pages_node[r_nid]++;
-		__count_vm_event(HTLB_BUDDY_PGALLOC);
-	} else {
-		h->nr_huge_pages--;
-		h->surplus_huge_pages--;
-		__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
-	}
-	spin_unlock(&hugetlb_lock);
+static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+		int nid, nodemask_t *nmask)
+{
+	struct page *page;
+
+	if (hstate_is_gigantic(h))
+		return NULL;
+
+	page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask);
+	if (!page)
+		return NULL;
+
+	/*
+	 * We do not account these pages as surplus because they are only
+	 * temporary and will be released properly on the last reference
+	 */
+	SetPageHugeTemporary(page);
 
 	return page;
 }
@@ -1606,7 +1617,7 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h, gfp_t gfp_mask,
  * Use the VMA's mpolicy to allocate a huge page from the buddy.
  */
 static
-struct page *__alloc_buddy_huge_page_with_mpol(struct hstate *h,
+struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
 		struct vm_area_struct *vma, unsigned long addr)
 {
 	struct page *page;
@@ -1616,17 +1627,13 @@ struct page *__alloc_buddy_huge_page_with_mpol(struct hstate *h,
 	nodemask_t *nodemask;
 
 	nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
-	page = __alloc_buddy_huge_page(h, gfp_mask, nid, nodemask);
+	page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask);
 	mpol_cond_put(mpol);
 
 	return page;
 }
 
-/*
- * This allocation function is useful in the context where vma is irrelevant.
- * E.g. soft-offlining uses this function because it only cares physical
- * address of error page.
- */
+/* page migration callback function */
 struct page *alloc_huge_page_node(struct hstate *h, int nid)
 {
 	gfp_t gfp_mask = htlb_alloc_mask(h);
@@ -1641,12 +1648,12 @@ struct page *alloc_huge_page_node(struct hstate *h, int nid)
 	spin_unlock(&hugetlb_lock);
 
 	if (!page)
-		page = __alloc_buddy_huge_page(h, gfp_mask, nid, NULL);
+		page = alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
 
 	return page;
 }
 
-
+/* page migration callback function */
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
 		nodemask_t *nmask)
 {
@@ -1664,9 +1671,25 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
 	}
 	spin_unlock(&hugetlb_lock);
 
-	/* No reservations, try to overcommit */
+	return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask);
+}
+
+/* mempolicy aware migration callback */
+struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
+		unsigned long address)
+{
+	struct mempolicy *mpol;
+	nodemask_t *nodemask;
+	struct page *page;
+	gfp_t gfp_mask;
+	int node;
+
+	gfp_mask = htlb_alloc_mask(h);
+	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
+	page = alloc_huge_page_nodemask(h, node, nodemask);
+	mpol_cond_put(mpol);
 
-	return __alloc_buddy_huge_page(h, gfp_mask, preferred_nid, nmask);
+	return page;
 }
 
 /*
@@ -1694,7 +1717,7 @@ static int gather_surplus_pages(struct hstate *h, int delta)
 retry:
 	spin_unlock(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
-		page = __alloc_buddy_huge_page(h, htlb_alloc_mask(h),
+		page = alloc_surplus_huge_page(h, htlb_alloc_mask(h),
 				NUMA_NO_NODE, NULL);
 		if (!page) {
 			alloc_ok = false;
@@ -2031,7 +2054,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg);
 	if (!page) {
 		spin_unlock(&hugetlb_lock);
-		page = __alloc_buddy_huge_page_with_mpol(h, vma, addr);
+		page = alloc_buddy_huge_page_with_mpol(h, vma, addr);
 		if (!page)
 			goto out_uncharge_cgroup;
 		if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
@@ -2074,20 +2097,6 @@ out_subpool_put:
 	return ERR_PTR(-ENOSPC);
 }
 
-/*
- * alloc_huge_page()'s wrapper which simply returns the page if allocation
- * succeeds, otherwise NULL. This function is called from new_vma_page(),
- * where no ERR_VALUE is expected to be returned.
- */
-struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
-				unsigned long addr, int avoid_reserve)
-{
-	struct page *page = alloc_huge_page(vma, addr, avoid_reserve);
-	if (IS_ERR(page))
-		page = NULL;
-	return page;
-}
-
 int alloc_bootmem_huge_page(struct hstate *h)
 	__attribute__ ((weak, alias("__alloc_bootmem_huge_page")));
 int __alloc_bootmem_huge_page(struct hstate *h)
@@ -2150,6 +2159,8 @@ static void __init gather_bootmem_prealloc(void)
 		prep_compound_huge_page(page, h->order);
 		WARN_ON(PageReserved(page));
 		prep_new_huge_page(h, page, page_to_nid(page));
+		put_page(page); /* free it into the hugepage allocator */
+
 		/*
 		 * If we had gigantic hugepages allocated at boot time, we need
 		 * to restore the 'stolen' pages to totalram_pages in order to
@@ -2169,7 +2180,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 		if (hstate_is_gigantic(h)) {
 			if (!alloc_bootmem_huge_page(h))
 				break;
-		} else if (!alloc_fresh_huge_page(h,
+		} else if (!alloc_pool_huge_page(h,
 					 &node_states[N_MEMORY]))
 			break;
 		cond_resched();
@@ -2289,7 +2300,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 	 * 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
+	 * We might race with alloc_surplus_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
@@ -2312,10 +2323,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 		/* yield cpu to avoid soft lockup */
 		cond_resched();
 
-		if (hstate_is_gigantic(h))
-			ret = alloc_fresh_gigantic_page(h, nodes_allowed);
-		else
-			ret = alloc_fresh_huge_page(h, nodes_allowed);
+		ret = alloc_pool_huge_page(h, nodes_allowed);
 		spin_lock(&hugetlb_lock);
 		if (!ret)
 			goto out;
@@ -2335,7 +2343,7 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 	 * 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,
+	 * alloc_surplus_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.
@@ -2975,20 +2983,32 @@ out:
 
 void hugetlb_report_meminfo(struct seq_file *m)
 {
-	struct hstate *h = &default_hstate;
+	struct hstate *h;
+	unsigned long total = 0;
+
 	if (!hugepages_supported())
 		return;
-	seq_printf(m,
-			"HugePages_Total:   %5lu\n"
-			"HugePages_Free:    %5lu\n"
-			"HugePages_Rsvd:    %5lu\n"
-			"HugePages_Surp:    %5lu\n"
-			"Hugepagesize:   %8lu kB\n",
-			h->nr_huge_pages,
-			h->free_huge_pages,
-			h->resv_huge_pages,
-			h->surplus_huge_pages,
-			1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
+
+	for_each_hstate(h) {
+		unsigned long count = h->nr_huge_pages;
+
+		total += (PAGE_SIZE << huge_page_order(h)) * count;
+
+		if (h == &default_hstate)
+			seq_printf(m,
+				   "HugePages_Total:   %5lu\n"
+				   "HugePages_Free:    %5lu\n"
+				   "HugePages_Rsvd:    %5lu\n"
+				   "HugePages_Surp:    %5lu\n"
+				   "Hugepagesize:   %8lu kB\n",
+				   count,
+				   h->free_huge_pages,
+				   h->resv_huge_pages,
+				   h->surplus_huge_pages,
+				   (PAGE_SIZE << huge_page_order(h)) / 1024);
+	}
+
+	seq_printf(m, "Hugetlb:        %8lu kB\n", total / 1024);
 }
 
 int hugetlb_report_node_meminfo(int nid, char *buf)
@@ -4799,3 +4819,36 @@ void putback_active_hugepage(struct page *page)
 	spin_unlock(&hugetlb_lock);
 	put_page(page);
 }
+
+void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason)
+{
+	struct hstate *h = page_hstate(oldpage);
+
+	hugetlb_cgroup_migrate(oldpage, newpage);
+	set_page_owner_migrate_reason(newpage, reason);
+
+	/*
+	 * transfer temporary state of the new huge page. This is
+	 * reverse to other transitions because the newpage is going to
+	 * be final while the old one will be freed so it takes over
+	 * the temporary status.
+	 *
+	 * Also note that we have to transfer the per-node surplus state
+	 * here as well otherwise the global surplus count will not match
+	 * the per-node's.
+	 */
+	if (PageHugeTemporary(newpage)) {
+		int old_nid = page_to_nid(oldpage);
+		int new_nid = page_to_nid(newpage);
+
+		SetPageHugeTemporary(oldpage);
+		ClearPageHugeTemporary(newpage);
+
+		spin_lock(&hugetlb_lock);
+		if (h->surplus_huge_pages_node[old_nid]) {
+			h->surplus_huge_pages_node[old_nid]--;
+			h->surplus_huge_pages_node[new_nid]++;
+		}
+		spin_unlock(&hugetlb_lock);
+	}
+}