1 files changed, 97 insertions, 74 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a301c2d672bf..fe76f8fd5a73 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -240,7 +240,6 @@ get_file_region_entry_from_cache(struct resv_map *resv, long from, long to)
 
 	resv->region_cache_count--;
 	nrg = list_first_entry(&resv->region_cache, struct file_region, link);
-	VM_BUG_ON(!nrg);
 	list_del(&nrg->link);
 
 	nrg->from = from;
@@ -309,8 +308,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
 		list_del(&rg->link);
 		kfree(rg);
 
-		coalesce_file_region(resv, prg);
-		return;
+		rg = prg;
 	}
 
 	nrg = list_next_entry(rg, link);
@@ -320,22 +318,20 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
 
 		list_del(&rg->link);
 		kfree(rg);
-
-		coalesce_file_region(resv, nrg);
-		return;
 	}
 }
 
-/* Must be called with resv->lock held. Calling this with count_only == true
- * will count the number of pages to be added but will not modify the linked
- * list. If regions_needed != NULL and count_only == true, then regions_needed
- * will indicate the number of file_regions needed in the cache to carry out to
- * add the regions for this range.
+/*
+ * Must be called with resv->lock held.
+ *
+ * Calling this with regions_needed != NULL will count the number of pages
+ * to be added but will not modify the linked list. And regions_needed will
+ * indicate the number of file_regions needed in the cache to carry out to add
+ * the regions for this range.
  */
 static long add_reservation_in_range(struct resv_map *resv, long f, long t,
 				     struct hugetlb_cgroup *h_cg,
-				     struct hstate *h, long *regions_needed,
-				     bool count_only)
+				     struct hstate *h, long *regions_needed)
 {
 	long add = 0;
 	struct list_head *head = &resv->regions;
@@ -371,14 +367,14 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
 		 */
 		if (rg->from > last_accounted_offset) {
 			add += rg->from - last_accounted_offset;
-			if (!count_only) {
+			if (!regions_needed) {
 				nrg = get_file_region_entry_from_cache(
 					resv, last_accounted_offset, rg->from);
 				record_hugetlb_cgroup_uncharge_info(h_cg, h,
 								    resv, nrg);
 				list_add(&nrg->link, rg->link.prev);
 				coalesce_file_region(resv, nrg);
-			} else if (regions_needed)
+			} else
 				*regions_needed += 1;
 		}
 
@@ -390,13 +386,13 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
 	 */
 	if (last_accounted_offset < t) {
 		add += t - last_accounted_offset;
-		if (!count_only) {
+		if (!regions_needed) {
 			nrg = get_file_region_entry_from_cache(
 				resv, last_accounted_offset, t);
 			record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg);
 			list_add(&nrg->link, rg->link.prev);
 			coalesce_file_region(resv, nrg);
-		} else if (regions_needed)
+		} else
 			*regions_needed += 1;
 	}
 
@@ -448,11 +444,8 @@ static int allocate_file_region_entries(struct resv_map *resv,
 
 		spin_lock(&resv->lock);
 
-		list_for_each_entry_safe(rg, trg, &allocated_regions, link) {
-			list_del(&rg->link);
-			list_add(&rg->link, &resv->region_cache);
-			resv->region_cache_count++;
-		}
+		list_splice(&allocated_regions, &resv->region_cache);
+		resv->region_cache_count += to_allocate;
 	}
 
 	return 0;
@@ -492,8 +485,8 @@ static long region_add(struct resv_map *resv, long f, long t,
 retry:
 
 	/* Count how many regions are actually needed to execute this add. */
-	add_reservation_in_range(resv, f, t, NULL, NULL, &actual_regions_needed,
-				 true);
+	add_reservation_in_range(resv, f, t, NULL, NULL,
+				 &actual_regions_needed);
 
 	/*
 	 * Check for sufficient descriptors in the cache to accommodate
@@ -521,7 +514,7 @@ retry:
 		goto retry;
 	}
 
-	add = add_reservation_in_range(resv, f, t, h_cg, h, NULL, false);
+	add = add_reservation_in_range(resv, f, t, h_cg, h, NULL);
 
 	resv->adds_in_progress -= in_regions_needed;
 
@@ -557,9 +550,9 @@ static long region_chg(struct resv_map *resv, long f, long t,
 
 	spin_lock(&resv->lock);
 
-	/* Count how many hugepages in this range are NOT respresented. */
+	/* Count how many hugepages in this range are NOT represented. */
 	chg = add_reservation_in_range(resv, f, t, NULL, NULL,
-				       out_regions_needed, true);
+				       out_regions_needed);
 
 	if (*out_regions_needed == 0)
 		*out_regions_needed = 1;
@@ -1047,21 +1040,17 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 		if (nocma && is_migrate_cma_page(page))
 			continue;
 
-		if (!PageHWPoison(page))
-			break;
+		if (PageHWPoison(page))
+			continue;
+
+		list_move(&page->lru, &h->hugepage_activelist);
+		set_page_refcounted(page);
+		h->free_huge_pages--;
+		h->free_huge_pages_node[nid]--;
+		return page;
 	}
 
-	/*
-	 * if 'non-isolated free hugepage' not found on the list,
-	 * the allocation fails.
-	 */
-	if (&h->hugepage_freelists[nid] == &page->lru)
-		return NULL;
-	list_move(&page->lru, &h->hugepage_activelist);
-	set_page_refcounted(page);
-	h->free_huge_pages--;
-	h->free_huge_pages_node[nid]--;
-	return page;
+	return NULL;
 }
 
 static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
@@ -1250,21 +1239,32 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 		int nid, nodemask_t *nodemask)
 {
 	unsigned long nr_pages = 1UL << huge_page_order(h);
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
 
 #ifdef CONFIG_CMA
 	{
 		struct page *page;
 		int node;
 
-		for_each_node_mask(node, *nodemask) {
-			if (!hugetlb_cma[node])
-				continue;
-
-			page = cma_alloc(hugetlb_cma[node], nr_pages,
-					 huge_page_order(h), true);
+		if (hugetlb_cma[nid]) {
+			page = cma_alloc(hugetlb_cma[nid], nr_pages,
+					huge_page_order(h), true);
 			if (page)
 				return page;
 		}
+
+		if (!(gfp_mask & __GFP_THISNODE)) {
+			for_each_node_mask(node, *nodemask) {
+				if (node == nid || !hugetlb_cma[node])
+					continue;
+
+				page = cma_alloc(hugetlb_cma[node], nr_pages,
+						huge_page_order(h), true);
+				if (page)
+					return page;
+			}
+		}
 	}
 #endif
 
@@ -1500,9 +1500,9 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
 	INIT_LIST_HEAD(&page->lru);
 	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
-	spin_lock(&hugetlb_lock);
 	set_hugetlb_cgroup(page, NULL);
 	set_hugetlb_cgroup_rsvd(page, NULL);
+	spin_lock(&hugetlb_lock);
 	h->nr_huge_pages++;
 	h->nr_huge_pages_node[nid]++;
 	spin_unlock(&hugetlb_lock);
@@ -2412,7 +2412,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 			h->resv_huge_pages--;
 		}
 		spin_lock(&hugetlb_lock);
-		list_move(&page->lru, &h->hugepage_activelist);
+		list_add(&page->lru, &h->hugepage_activelist);
 		/* Fall through */
 	}
 	hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page);
@@ -3454,6 +3454,22 @@ static unsigned int allowed_mems_nr(struct hstate *h)
 }
 
 #ifdef CONFIG_SYSCTL
+static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write,
+					  void *buffer, size_t *length,
+					  loff_t *ppos, unsigned long *out)
+{
+	struct ctl_table dup_table;
+
+	/*
+	 * In order to avoid races with __do_proc_doulongvec_minmax(), we
+	 * can duplicate the @table and alter the duplicate of it.
+	 */
+	dup_table = *table;
+	dup_table.data = out;
+
+	return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
+}
+
 static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 			 struct ctl_table *table, int write,
 			 void *buffer, size_t *length, loff_t *ppos)
@@ -3465,9 +3481,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 	if (!hugepages_supported())
 		return -EOPNOTSUPP;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -3510,9 +3525,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 	if (write && hstate_is_gigantic(h))
 		return -EINVAL;
 
-	table->data = &tmp;
-	table->maxlen = sizeof(unsigned long);
-	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+					     &tmp);
 	if (ret)
 		goto out;
 
@@ -3557,18 +3571,20 @@ void hugetlb_report_meminfo(struct seq_file *m)
 	seq_printf(m, "Hugetlb:        %8lu kB\n", total / 1024);
 }
 
-int hugetlb_report_node_meminfo(int nid, char *buf)
+int hugetlb_report_node_meminfo(char *buf, int len, int nid)
 {
 	struct hstate *h = &default_hstate;
+
 	if (!hugepages_supported())
 		return 0;
-	return sprintf(buf,
-		"Node %d HugePages_Total: %5u\n"
-		"Node %d HugePages_Free:  %5u\n"
-		"Node %d HugePages_Surp:  %5u\n",
-		nid, h->nr_huge_pages_node[nid],
-		nid, h->free_huge_pages_node[nid],
-		nid, h->surplus_huge_pages_node[nid]);
+
+	return sysfs_emit_at(buf, len,
+			     "Node %d HugePages_Total: %5u\n"
+			     "Node %d HugePages_Free:  %5u\n"
+			     "Node %d HugePages_Surp:  %5u\n",
+			     nid, h->nr_huge_pages_node[nid],
+			     nid, h->free_huge_pages_node[nid],
+			     nid, h->surplus_huge_pages_node[nid]);
 }
 
 void hugetlb_show_meminfo(void)
@@ -3774,23 +3790,23 @@ bool is_hugetlb_entry_migration(pte_t pte)
 	if (huge_pte_none(pte) || pte_present(pte))
 		return false;
 	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_migration_entry(swp))
+	if (is_migration_entry(swp))
 		return true;
 	else
 		return false;
 }
 
-static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+static bool is_hugetlb_entry_hwpoisoned(pte_t pte)
 {
 	swp_entry_t swp;
 
 	if (huge_pte_none(pte) || pte_present(pte))
-		return 0;
+		return false;
 	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
-		return 1;
+	if (is_hwpoison_entry(swp))
+		return true;
 	else
-		return 0;
+		return false;
 }
 
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
@@ -5323,10 +5339,16 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
  * !shared pmd case because we can allocate the pmd later as well, it makes the
  * code much cleaner.
  *
- * This routine must be called with i_mmap_rwsem held in at least read mode.
- * For hugetlbfs, this prevents removal of any page table entries associated
- * with the address space.  This is important as we are setting up sharing
- * based on existing page table entries (mappings).
+ * This routine must be called with i_mmap_rwsem held in at least read mode if
+ * sharing is possible.  For hugetlbfs, this prevents removal of any page
+ * table entries associated with the address space.  This is important as we
+ * are setting up sharing based on existing page table entries (mappings).
+ *
+ * NOTE: This routine is only called from huge_pte_alloc.  Some callers of
+ * huge_pte_alloc know that sharing is not possible and do not take
+ * i_mmap_rwsem as a performance optimization.  This is handled by the
+ * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is
+ * only required for subsequent processing.
  */
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 {
@@ -5343,6 +5365,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	if (!vma_shareable(vma, addr))
 		return (pte_t *)pmd_alloc(mm, pud, addr);
 
+	i_mmap_assert_locked(mapping);
 	vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
 		if (svma == vma)
 			continue;
@@ -5683,12 +5706,12 @@ void __init hugetlb_cma_reserve(int order)
 	reserved = 0;
 	for_each_node_state(nid, N_ONLINE) {
 		int res;
-		char name[20];
+		char name[CMA_MAX_NAME];
 
 		size = min(per_node, hugetlb_cma_size - reserved);
 		size = round_up(size, PAGE_SIZE << order);
 
-		snprintf(name, 20, "hugetlb%d", nid);
+		snprintf(name, sizeof(name), "hugetlb%d", nid);
 		res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order,
 						 0, false, name,
 						 &hugetlb_cma[nid], nid);