From 3159f943aafdbacb2f94c38fdaadabf2bbde2a14 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox
Date: Fri, 3 Nov 2017 13:30:42 -0400
Subject: xarray: Replace exceptional entries

Introduce xarray value entries and tagged pointers to replace radix
tree exceptional entries.  This is a slight change in encoding to allow
the use of an extra bit (we can now store BITS_PER_LONG - 1 bits in a
value entry).  It is also a change in emphasis; exceptional entries are
intimidating and different.  As the comment explains, you can choose
to store values or pointers in the xarray and they are both first-class
citizens.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Josef Bacik <jbacik@fb.com>
---
 mm/shmem.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/mm/shmem.c b/mm/shmem.c
index 446942677cd4..c1062760fe41 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -709,7 +709,7 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping,
 			continue;
 		}
 
-		if (radix_tree_exceptional_entry(page))
+		if (xa_is_value(page))
 			swapped++;
 
 		if (need_resched()) {
@@ -824,7 +824,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (unfalloc)
 					continue;
 				nr_swaps_freed += !shmem_free_swap(mapping,
@@ -921,7 +921,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (index >= end)
 				break;
 
-			if (radix_tree_exceptional_entry(page)) {
+			if (xa_is_value(page)) {
 				if (unfalloc)
 					continue;
 				if (shmem_free_swap(mapping, index, page)) {
@@ -1643,7 +1643,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 repeat:
 	swap.val = 0;
 	page = find_lock_entry(mapping, index);
-	if (radix_tree_exceptional_entry(page)) {
+	if (xa_is_value(page)) {
 		swap = radix_to_swp_entry(page);
 		page = NULL;
 	}
@@ -2578,7 +2578,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 				index = indices[i];
 			}
 			page = pvec.pages[i];
-			if (page && !radix_tree_exceptional_entry(page)) {
+			if (page && !xa_is_value(page)) {
 				if (!PageUptodate(page))
 					page = NULL;
 			}
-- 
cgit v1.2.3-55-g7522


From 62f945b6a7b8cda6d1f35941eb374276f7b8749a Mon Sep 17 00:00:00 2001
From: Matthew Wilcox
Date: Fri, 17 Nov 2017 10:22:37 -0500
Subject: shmem: Convert shmem_radix_tree_replace to XArray

Rename shmem_radix_tree_replace() to shmem_replace_entry() and
convert it to use the XArray API.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 mm/shmem.c | 22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/mm/shmem.c b/mm/shmem.c
index c1062760fe41..5697c8fecdfc 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -322,24 +322,20 @@ void shmem_uncharge(struct inode *inode, long pages)
 }
 
 /*
- * Replace item expected in radix tree by a new item, while holding tree lock.
+ * Replace item expected in xarray by a new item, while holding xa_lock.
  */
-static int shmem_radix_tree_replace(struct address_space *mapping,
+static int shmem_replace_entry(struct address_space *mapping,
 			pgoff_t index, void *expected, void *replacement)
 {
-	struct radix_tree_node *node;
-	void __rcu **pslot;
+	XA_STATE(xas, &mapping->i_pages, index);
 	void *item;
 
 	VM_BUG_ON(!expected);
 	VM_BUG_ON(!replacement);
-	item = __radix_tree_lookup(&mapping->i_pages, index, &node, &pslot);
-	if (!item)
-		return -ENOENT;
+	item = xas_load(&xas);
 	if (item != expected)
 		return -ENOENT;
-	__radix_tree_replace(&mapping->i_pages, node, pslot,
-			     replacement, NULL);
+	xas_store(&xas, replacement);
 	return 0;
 }
 
@@ -624,8 +620,7 @@ static int shmem_add_to_page_cache(struct page *page,
 	} else if (!expected) {
 		error = radix_tree_insert(&mapping->i_pages, index, page);
 	} else {
-		error = shmem_radix_tree_replace(mapping, index, expected,
-								 page);
+		error = shmem_replace_entry(mapping, index, expected, page);
 	}
 
 	if (!error) {
@@ -654,7 +649,7 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap)
 	VM_BUG_ON_PAGE(PageCompound(page), page);
 
 	xa_lock_irq(&mapping->i_pages);
-	error = shmem_radix_tree_replace(mapping, page->index, page, radswap);
+	error = shmem_replace_entry(mapping, page->index, page, radswap);
 	page->mapping = NULL;
 	mapping->nrpages--;
 	__dec_node_page_state(page, NR_FILE_PAGES);
@@ -1578,8 +1573,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 	 * a nice clean interface for us to replace oldpage by newpage there.
 	 */
 	xa_lock_irq(&swap_mapping->i_pages);
-	error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
-								   newpage);
+	error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage);
 	if (!error) {
 		__inc_node_page_state(newpage, NR_FILE_PAGES);
 		__dec_node_page_state(oldpage, NR_FILE_PAGES);
-- 
cgit v1.2.3-55-g7522


From a12831bf4293d38518e41b80dd897af0122bb268 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox
Date: Wed, 22 Nov 2017 08:34:58 -0500
Subject: shmem: Convert shmem_confirm_swap to XArray

xa_load has its own RCU locking, so we can eliminate it here.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 mm/shmem.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/mm/shmem.c b/mm/shmem.c
index 5697c8fecdfc..ce91569426f3 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -349,12 +349,7 @@ static int shmem_replace_entry(struct address_space *mapping,
 static bool shmem_confirm_swap(struct address_space *mapping,
 			       pgoff_t index, swp_entry_t swap)
 {
-	void *item;
-
-	rcu_read_lock();
-	item = radix_tree_lookup(&mapping->i_pages, index);
-	rcu_read_unlock();
-	return item == swp_to_radix_entry(swap);
+	return xa_load(&mapping->i_pages, index) == swp_to_radix_entry(swap);
 }
 
 /*
-- 
cgit v1.2.3-55-g7522


From e21a29552fa3f44ea41c53488875015ae70fd7f8 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox
Date: Wed, 22 Nov 2017 08:36:00 -0500
Subject: shmem: Convert find_swap_entry to XArray

This is a 1:1 conversion.  The major part of this patch is converting
the test framework from userspace to kernel space and mirroring the
algorithm now used in find_swap_entry().

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 lib/test_xarray.c               | 56 +++++++++++++++++++++++++++++++++++++
 mm/shmem.c                      | 27 +++++++-----------
 tools/testing/radix-tree/main.c | 61 -----------------------------------------
 tools/testing/radix-tree/test.c | 22 ---------------
 tools/testing/radix-tree/test.h |  1 -
 5 files changed, 66 insertions(+), 101 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 128c6489082f..815daffdd8c9 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -631,6 +631,61 @@ static noinline void check_find(struct xarray *xa)
 	check_multi_find_2(xa);
 }
 
+/* See find_swap_entry() in mm/shmem.c */
+static noinline unsigned long xa_find_entry(struct xarray *xa, void *item)
+{
+	XA_STATE(xas, xa, 0);
+	unsigned int checked = 0;
+	void *entry;
+
+	rcu_read_lock();
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		if (xas_retry(&xas, entry))
+			continue;
+		if (entry == item)
+			break;
+		checked++;
+		if ((checked % 4) != 0)
+			continue;
+		xas_pause(&xas);
+	}
+	rcu_read_unlock();
+
+	return entry ? xas.xa_index : -1;
+}
+
+static noinline void check_find_entry(struct xarray *xa)
+{
+#ifdef CONFIG_XARRAY_MULTI
+	unsigned int order;
+	unsigned long offset, index;
+
+	for (order = 0; order < 20; order++) {
+		for (offset = 0; offset < (1UL << (order + 3));
+		     offset += (1UL << order)) {
+			for (index = 0; index < (1UL << (order + 5));
+			     index += (1UL << order)) {
+				xa_store_order(xa, index, order,
+						xa_mk_value(index), GFP_KERNEL);
+				XA_BUG_ON(xa, xa_load(xa, index) !=
+						xa_mk_value(index));
+				XA_BUG_ON(xa, xa_find_entry(xa,
+						xa_mk_value(index)) != index);
+			}
+			XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1);
+			xa_destroy(xa);
+		}
+	}
+#endif
+
+	XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1);
+	xa_store_index(xa, ULONG_MAX, GFP_KERNEL);
+	XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1);
+	XA_BUG_ON(xa, xa_find_entry(xa, xa_mk_value(LONG_MAX)) != -1);
+	xa_erase_index(xa, ULONG_MAX);
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
 static noinline void check_move_small(struct xarray *xa, unsigned long idx)
 {
 	XA_STATE(xas, xa, 0);
@@ -972,6 +1027,7 @@ static int xarray_checks(void)
 	check_multi_store(&array);
 	check_xa_alloc();
 	check_find(&array);
+	check_find_entry(&array);
 	check_destroy(&array);
 	check_move(&array);
 	check_create_range(&array);
diff --git a/mm/shmem.c b/mm/shmem.c
index ce91569426f3..a305529d6b89 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1100,34 +1100,27 @@ static void shmem_evict_inode(struct inode *inode)
 	clear_inode(inode);
 }
 
-static unsigned long find_swap_entry(struct radix_tree_root *root, void *item)
+static unsigned long find_swap_entry(struct xarray *xa, void *item)
 {
-	struct radix_tree_iter iter;
-	void __rcu **slot;
-	unsigned long found = -1;
+	XA_STATE(xas, xa, 0);
 	unsigned int checked = 0;
+	void *entry;
 
 	rcu_read_lock();
-	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		void *entry = radix_tree_deref_slot(slot);
-
-		if (radix_tree_deref_retry(entry)) {
-			slot = radix_tree_iter_retry(&iter);
+	xas_for_each(&xas, entry, ULONG_MAX) {
+		if (xas_retry(&xas, entry))
 			continue;
-		}
-		if (entry == item) {
-			found = iter.index;
+		if (entry == item)
 			break;
-		}
 		checked++;
-		if ((checked % 4096) != 0)
+		if ((checked % XA_CHECK_SCHED) != 0)
 			continue;
-		slot = radix_tree_iter_resume(slot, &iter);
+		xas_pause(&xas);
 		cond_resched_rcu();
 	}
-
 	rcu_read_unlock();
-	return found;
+
+	return entry ? xas.xa_index : -1;
 }
 
 /*
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index 09deaf4f0959..79589ea570ab 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -236,63 +236,6 @@ void copy_tag_check(void)
 	item_kill_tree(&tree);
 }
 
-static void __locate_check(struct radix_tree_root *tree, unsigned long index,
-			unsigned order)
-{
-	struct item *item;
-	unsigned long index2;
-
-	item_insert_order(tree, index, order);
-	item = item_lookup(tree, index);
-	index2 = find_item(tree, item);
-	if (index != index2) {
-		printv(2, "index %ld order %d inserted; found %ld\n",
-			index, order, index2);
-		abort();
-	}
-}
-
-static void __order_0_locate_check(void)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	int i;
-
-	for (i = 0; i < 50; i++)
-		__locate_check(&tree, rand() % INT_MAX, 0);
-
-	item_kill_tree(&tree);
-}
-
-static void locate_check(void)
-{
-	RADIX_TREE(tree, GFP_KERNEL);
-	unsigned order;
-	unsigned long offset, index;
-
-	__order_0_locate_check();
-
-	for (order = 0; order < 20; order++) {
-		for (offset = 0; offset < (1 << (order + 3));
-		     offset += (1UL << order)) {
-			for (index = 0; index < (1UL << (order + 5));
-			     index += (1UL << order)) {
-				__locate_check(&tree, index + offset, order);
-			}
-			if (find_item(&tree, &tree) != -1)
-				abort();
-
-			item_kill_tree(&tree);
-		}
-	}
-
-	if (find_item(&tree, &tree) != -1)
-		abort();
-	__locate_check(&tree, -1, 0);
-	if (find_item(&tree, &tree) != -1)
-		abort();
-	item_kill_tree(&tree);
-}
-
 static void single_thread_tests(bool long_run)
 {
 	int i;
@@ -303,10 +246,6 @@ static void single_thread_tests(bool long_run)
 	rcu_barrier();
 	printv(2, "after multiorder_check: %d allocated, preempt %d\n",
 		nr_allocated, preempt_count);
-	locate_check();
-	rcu_barrier();
-	printv(2, "after locate_check: %d allocated, preempt %d\n",
-		nr_allocated, preempt_count);
 	tag_check();
 	rcu_barrier();
 	printv(2, "after tag_check: %d allocated, preempt %d\n",
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 70ddf964d51c..470419bfd49d 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -209,28 +209,6 @@ int tag_tagged_items(struct radix_tree_root *root, pthread_mutex_t *lock,
 	return tagged;
 }
 
-/* Use the same pattern as find_swap_entry() in mm/shmem.c */
-unsigned long find_item(struct radix_tree_root *root, void *item)
-{
-	struct radix_tree_iter iter;
-	void **slot;
-	unsigned long found = -1;
-	unsigned long checked = 0;
-
-	radix_tree_for_each_slot(slot, root, &iter, 0) {
-		if (*slot == item) {
-			found = iter.index;
-			break;
-		}
-		checked++;
-		if ((checked % 4) != 0)
-			continue;
-		slot = radix_tree_iter_resume(slot, &iter);
-	}
-
-	return found;
-}
-
 static int verify_node(struct radix_tree_node *slot, unsigned int tag,
 			int tagged)
 {
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index e3dc7a16f09b..9532c18c6cb1 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -32,7 +32,6 @@ void item_kill_tree(struct radix_tree_root *root);
 int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *,
 			unsigned long start, unsigned long end, unsigned batch,
 			unsigned iftag, unsigned thentag);
-unsigned long find_item(struct radix_tree_root *, void *item);
 
 void xarray_tests(void);
 void tag_check(void);
-- 
cgit v1.2.3-55-g7522


From 552446a4166189a8c2515571dd6e25fd64a2dc78 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox
Date: Fri, 1 Dec 2017 13:25:14 -0500
Subject: shmem: Convert shmem_add_to_page_cache to XArray

We can use xas_find_conflict() instead of radix_tree_gang_lookup_slot()
to find any conflicting entry and combine the three paths through this
function into one.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 mm/shmem.c | 81 ++++++++++++++++++++++++++------------------------------------
 1 file changed, 34 insertions(+), 47 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/mm/shmem.c b/mm/shmem.c
index a305529d6b89..8633bd3dc433 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -577,9 +577,11 @@ static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo)
  */
 static int shmem_add_to_page_cache(struct page *page,
 				   struct address_space *mapping,
-				   pgoff_t index, void *expected)
+				   pgoff_t index, void *expected, gfp_t gfp)
 {
-	int error, nr = hpage_nr_pages(page);
+	XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page));
+	unsigned long i = 0;
+	unsigned long nr = 1UL << compound_order(page);
 
 	VM_BUG_ON_PAGE(PageTail(page), page);
 	VM_BUG_ON_PAGE(index != round_down(index, nr), page);
@@ -591,46 +593,39 @@ static int shmem_add_to_page_cache(struct page *page,
 	page->mapping = mapping;
 	page->index = index;
 
-	xa_lock_irq(&mapping->i_pages);
-	if (PageTransHuge(page)) {
-		void __rcu **results;
-		pgoff_t idx;
-		int i;
-
-		error = 0;
-		if (radix_tree_gang_lookup_slot(&mapping->i_pages,
-					&results, &idx, index, 1) &&
-				idx < index + HPAGE_PMD_NR) {
-			error = -EEXIST;
+	do {
+		void *entry;
+		xas_lock_irq(&xas);
+		entry = xas_find_conflict(&xas);
+		if (entry != expected)
+			xas_set_err(&xas, -EEXIST);
+		xas_create_range(&xas);
+		if (xas_error(&xas))
+			goto unlock;
+next:
+		xas_store(&xas, page + i);
+		if (++i < nr) {
+			xas_next(&xas);
+			goto next;
 		}
-
-		if (!error) {
-			for (i = 0; i < HPAGE_PMD_NR; i++) {
-				error = radix_tree_insert(&mapping->i_pages,
-						index + i, page + i);
-				VM_BUG_ON(error);
-			}
+		if (PageTransHuge(page)) {
 			count_vm_event(THP_FILE_ALLOC);
+			__inc_node_page_state(page, NR_SHMEM_THPS);
 		}
-	} else if (!expected) {
-		error = radix_tree_insert(&mapping->i_pages, index, page);
-	} else {
-		error = shmem_replace_entry(mapping, index, expected, page);
-	}
-
-	if (!error) {
 		mapping->nrpages += nr;
-		if (PageTransHuge(page))
-			__inc_node_page_state(page, NR_SHMEM_THPS);
 		__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
 		__mod_node_page_state(page_pgdat(page), NR_SHMEM, nr);
-		xa_unlock_irq(&mapping->i_pages);
-	} else {
+unlock:
+		xas_unlock_irq(&xas);
+	} while (xas_nomem(&xas, gfp));
+
+	if (xas_error(&xas)) {
 		page->mapping = NULL;
-		xa_unlock_irq(&mapping->i_pages);
 		page_ref_sub(page, nr);
+		return xas_error(&xas);
 	}
-	return error;
+
+	return 0;
 }
 
 /*
@@ -1183,7 +1178,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info,
 	 */
 	if (!error)
 		error = shmem_add_to_page_cache(*pagep, mapping, index,
-						radswap);
+						radswap, gfp);
 	if (error != -ENOMEM) {
 		/*
 		 * Truncation and eviction use free_swap_and_cache(), which
@@ -1700,7 +1695,7 @@ repeat:
 				false);
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
-						swp_to_radix_entry(swap));
+						swp_to_radix_entry(swap), gfp);
 			/*
 			 * We already confirmed swap under page lock, and make
 			 * no memory allocation here, so usually no possibility
@@ -1806,13 +1801,8 @@ alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, inode,
 				PageTransHuge(page));
 		if (error)
 			goto unacct;
-		error = radix_tree_maybe_preload_order(gfp & GFP_RECLAIM_MASK,
-				compound_order(page));
-		if (!error) {
-			error = shmem_add_to_page_cache(page, mapping, hindex,
-							NULL);
-			radix_tree_preload_end();
-		}
+		error = shmem_add_to_page_cache(page, mapping, hindex,
+						NULL, gfp & GFP_RECLAIM_MASK);
 		if (error) {
 			mem_cgroup_cancel_charge(page, memcg,
 					PageTransHuge(page));
@@ -2281,11 +2271,8 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	if (ret)
 		goto out_release;
 
-	ret = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK);
-	if (!ret) {
-		ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL);
-		radix_tree_preload_end();
-	}
+	ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL,
+						gfp & GFP_RECLAIM_MASK);
 	if (ret)
 		goto out_release_uncharge;
 
-- 
cgit v1.2.3-55-g7522


From 7b8d046fba91d62beb8a8f78244aaa3c23a60cdd Mon Sep 17 00:00:00 2001
From: Matthew Wilcox
Date: Fri, 1 Dec 2017 22:13:06 -0500
Subject: shmem: Convert shmem_alloc_hugepage to XArray

xa_find() is a slightly easier API to use than
radix_tree_gang_lookup_slot() because it contains its own RCU locking.
This commit removes the last user of radix_tree_gang_lookup_slot()
so remove the function too.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 include/linux/radix-tree.h |  6 +-----
 lib/radix-tree.c           | 44 +-------------------------------------------
 mm/shmem.c                 | 14 ++++----------
 3 files changed, 6 insertions(+), 58 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 023e888e1163..8a4280bc350f 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -147,12 +147,11 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter)
  * radix_tree_lookup_slot
  * radix_tree_tag_get
  * radix_tree_gang_lookup
- * radix_tree_gang_lookup_slot
  * radix_tree_gang_lookup_tag
  * radix_tree_gang_lookup_tag_slot
  * radix_tree_tagged
  *
- * The first 8 functions are able to be called locklessly, using RCU. The
+ * The first 7 functions are able to be called locklessly, using RCU. The
  * caller must ensure calls to these functions are made within rcu_read_lock()
  * regions. Other readers (lock-free or otherwise) and modifications may be
  * running concurrently.
@@ -263,9 +262,6 @@ void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *,
 unsigned int radix_tree_gang_lookup(const struct radix_tree_root *,
 			void **results, unsigned long first_index,
 			unsigned int max_items);
-unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *,
-			void __rcu ***results, unsigned long *indices,
-			unsigned long first_index, unsigned int max_items);
 int radix_tree_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 8a58051eb5b3..2f9c0e45eeb7 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1097,7 +1097,7 @@ void __radix_tree_replace(struct radix_tree_root *root,
  * @slot:	pointer to slot
  * @item:	new item to store in the slot.
  *
- * For use with radix_tree_lookup_slot(), radix_tree_gang_lookup_slot(),
+ * For use with radix_tree_lookup_slot() and
  * radix_tree_gang_lookup_tag_slot().  Caller must hold tree write locked
  * across slot lookup and replacement.
  *
@@ -1731,48 +1731,6 @@ radix_tree_gang_lookup(const struct radix_tree_root *root, void **results,
 }
 EXPORT_SYMBOL(radix_tree_gang_lookup);
 
-/**
- *	radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree
- *	@root:		radix tree root
- *	@results:	where the results of the lookup are placed
- *	@indices:	where their indices should be placed (but usually NULL)
- *	@first_index:	start the lookup from this key
- *	@max_items:	place up to this many items at *results
- *
- *	Performs an index-ascending scan of the tree for present items.  Places
- *	their slots at *@results and returns the number of items which were
- *	placed at *@results.
- *
- *	The implementation is naive.
- *
- *	Like radix_tree_gang_lookup as far as RCU and locking goes. Slots must
- *	be dereferenced with radix_tree_deref_slot, and if using only RCU
- *	protection, radix_tree_deref_slot may fail requiring a retry.
- */
-unsigned int
-radix_tree_gang_lookup_slot(const struct radix_tree_root *root,
-			void __rcu ***results, unsigned long *indices,
-			unsigned long first_index, unsigned int max_items)
-{
-	struct radix_tree_iter iter;
-	void __rcu **slot;
-	unsigned int ret = 0;
-
-	if (unlikely(!max_items))
-		return 0;
-
-	radix_tree_for_each_slot(slot, root, &iter, first_index) {
-		results[ret] = slot;
-		if (indices)
-			indices[ret] = iter.index;
-		if (++ret == max_items)
-			break;
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL(radix_tree_gang_lookup_slot);
-
 /**
  *	radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree
  *	                             based on a tag
diff --git a/mm/shmem.c b/mm/shmem.c
index 8633bd3dc433..608c9252248f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1431,23 +1431,17 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
 		struct shmem_inode_info *info, pgoff_t index)
 {
 	struct vm_area_struct pvma;
-	struct inode *inode = &info->vfs_inode;
-	struct address_space *mapping = inode->i_mapping;
-	pgoff_t idx, hindex;
-	void __rcu **results;
+	struct address_space *mapping = info->vfs_inode.i_mapping;
+	pgoff_t hindex;
 	struct page *page;
 
 	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
 		return NULL;
 
 	hindex = round_down(index, HPAGE_PMD_NR);
-	rcu_read_lock();
-	if (radix_tree_gang_lookup_slot(&mapping->i_pages, &results, &idx,
-				hindex, 1) && idx < hindex + HPAGE_PMD_NR) {
-		rcu_read_unlock();
+	if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1,
+								XA_PRESENT))
 		return NULL;
-	}
-	rcu_read_unlock();
 
 	shmem_pseudo_vma_init(&pvma, info, hindex);
 	page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN,
-- 
cgit v1.2.3-55-g7522


From c121d3bb717ee932caf031c6a7923547f7f83163 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox
Date: Mon, 4 Dec 2017 03:13:54 -0500
Subject: shmem: Convert shmem_free_swap to XArray

Since we are conditionally storing NULL in the XArray, we do not need
to allocate memory and the GFP flags will be unused.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 mm/shmem.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/mm/shmem.c b/mm/shmem.c
index 608c9252248f..8e9bbfb7ed15 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -650,7 +650,7 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap)
 }
 
 /*
- * Remove swap entry from radix tree, free the swap and its page cache.
+ * Remove swap entry from page cache, free the swap and its page cache.
  */
 static int shmem_free_swap(struct address_space *mapping,
 			   pgoff_t index, void *radswap)
@@ -658,7 +658,7 @@ static int shmem_free_swap(struct address_space *mapping,
 	void *old;
 
 	xa_lock_irq(&mapping->i_pages);
-	old = radix_tree_delete_item(&mapping->i_pages, index, radswap);
+	old = __xa_cmpxchg(&mapping->i_pages, index, radswap, NULL, 0);
 	xa_unlock_irq(&mapping->i_pages);
 	if (old != radswap)
 		return -ENOENT;
-- 
cgit v1.2.3-55-g7522


From 7ae3424fb4b5587d9b2db12a4b1040c52073dd5c Mon Sep 17 00:00:00 2001
From: Matthew Wilcox
Date: Mon, 4 Dec 2017 03:28:00 -0500
Subject: shmem: Convert shmem_partial_swap_usage to XArray

Simpler code because the xarray takes care of things like the limit and
dereferencing the slot.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 mm/shmem.c | 18 ++++--------------
 1 file changed, 4 insertions(+), 14 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/mm/shmem.c b/mm/shmem.c
index 8e9bbfb7ed15..5588205f4259 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -676,29 +676,19 @@ static int shmem_free_swap(struct address_space *mapping,
 unsigned long shmem_partial_swap_usage(struct address_space *mapping,
 						pgoff_t start, pgoff_t end)
 {
-	struct radix_tree_iter iter;
-	void __rcu **slot;
+	XA_STATE(xas, &mapping->i_pages, start);
 	struct page *page;
 	unsigned long swapped = 0;
 
 	rcu_read_lock();
-
-	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
-		if (iter.index >= end)
-			break;
-
-		page = radix_tree_deref_slot(slot);
-
-		if (radix_tree_deref_retry(page)) {
-			slot = radix_tree_iter_retry(&iter);
+	xas_for_each(&xas, page, end - 1) {
+		if (xas_retry(&xas, page))
 			continue;
-		}
-
 		if (xa_is_value(page))
 			swapped++;
 
 		if (need_resched()) {
-			slot = radix_tree_iter_resume(slot, &iter);
+			xas_pause(&xas);
 			cond_resched_rcu();
 		}
 	}
-- 
cgit v1.2.3-55-g7522


From 7f4446eefe9fbbe68e9543946c9a20f67897ff9b Mon Sep 17 00:00:00 2001
From: Matthew Wilcox
Date: Mon, 4 Dec 2017 03:31:13 -0500
Subject: shmem: Comment fixups

Remove the last mentions of radix tree from various comments.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
---
 mm/shmem.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/mm/shmem.c b/mm/shmem.c
index 5588205f4259..56bf122e0bb4 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -763,7 +763,7 @@ void shmem_unlock_mapping(struct address_space *mapping)
 }
 
 /*
- * Remove range of pages and swap entries from radix tree, and free them.
+ * Remove range of pages and swap entries from page cache, and free them.
  * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
  */
 static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
@@ -1143,10 +1143,10 @@ static int shmem_unuse_inode(struct shmem_inode_info *info,
 		 * We needed to drop mutex to make that restrictive page
 		 * allocation, but the inode might have been freed while we
 		 * dropped it: although a racing shmem_evict_inode() cannot
-		 * complete without emptying the radix_tree, our page lock
+		 * complete without emptying the page cache, our page lock
 		 * on this swapcache page is not enough to prevent that -
 		 * free_swap_and_cache() of our swap entry will only
-		 * trylock_page(), removing swap from radix_tree whatever.
+		 * trylock_page(), removing swap from page cache whatever.
 		 *
 		 * We must not proceed to shmem_add_to_page_cache() if the
 		 * inode has been freed, but of course we cannot rely on
@@ -1212,7 +1212,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 					    &memcg, false);
 	if (error)
 		goto out;
-	/* No radix_tree_preload: swap entry keeps a place for page in tree */
+	/* No memory allocation: swap entry occupies the slot for the page */
 	error = -EAGAIN;
 
 	mutex_lock(&shmem_swaplist_mutex);
@@ -1887,7 +1887,7 @@ unlock:
 		spin_unlock_irq(&info->lock);
 		goto repeat;
 	}
-	if (error == -EEXIST)	/* from above or from radix_tree_insert */
+	if (error == -EEXIST)
 		goto repeat;
 	return error;
 }
@@ -2501,7 +2501,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 }
 
 /*
- * llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
+ * llseek SEEK_DATA or SEEK_HOLE through the page cache.
  */
 static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 				    pgoff_t index, pgoff_t end, int whence)
-- 
cgit v1.2.3-55-g7522


From 89c83fb539f95491be80cdd5158e6f0ce329e317 Mon Sep 17 00:00:00 2001
From: Michal Hocko
Date: Fri, 2 Nov 2018 15:48:31 -0700
Subject: mm, thp: consolidate THP gfp handling into
 alloc_hugepage_direct_gfpmask

THP allocation mode is quite complex and it depends on the defrag mode.
This complexity is hidden in alloc_hugepage_direct_gfpmask from a large
part currently. The NUMA special casing (namely __GFP_THISNODE) is
however independent and placed in alloc_pages_vma currently. This both
adds an unnecessary branch to all vma based page allocation requests and
it makes the code more complex unnecessarily as well. Not to mention
that e.g. shmem THP used to do the node reclaiming unconditionally
regardless of the defrag mode until recently. This was not only
unexpected behavior but it was also hardly a good default behavior and I
strongly suspect it was just a side effect of the code sharing more than
a deliberate decision which suggests that such a layering is wrong.

Get rid of the thp special casing from alloc_pages_vma and move the
logic to alloc_hugepage_direct_gfpmask. __GFP_THISNODE is applied to the
resulting gfp mask only when the direct reclaim is not requested and
when there is no explicit numa binding to preserve the current logic.

Please note that there's also a slight difference wrt MPOL_BIND now. The
previous code would avoid using __GFP_THISNODE if the local node was
outside of policy_nodemask(). After this patch __GFP_THISNODE is avoided
for all MPOL_BIND policies. So there's a difference that if local node
is actually allowed by the bind policy's nodemask, previously
__GFP_THISNODE would be added, but now it won't be. From the behavior
POV this is still correct because the policy nodemask is used.

Link: http://lkml.kernel.org/r/20180925120326.24392-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h       | 12 +++------
 include/linux/mempolicy.h |  2 ++
 mm/huge_memory.c          | 38 +++++++++++++++++++++-------
 mm/mempolicy.c            | 63 +++--------------------------------------------
 mm/shmem.c                |  2 +-
 5 files changed, 40 insertions(+), 77 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 24bcc5eec6b4..76f8db0b0e71 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order)
 }
 extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 			struct vm_area_struct *vma, unsigned long addr,
-			int node, bool hugepage);
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order)	\
-	alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
+			int node);
 #else
 #define alloc_pages(gfp_mask, order) \
 		alloc_pages_node(numa_node_id(), gfp_mask, order)
-#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
-	alloc_pages(gfp_mask, order)
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order)	\
+#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\
 	alloc_pages(gfp_mask, order)
 #endif
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
 #define alloc_page_vma(gfp_mask, vma, addr)			\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false)
+	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id())
 #define alloc_page_vma_node(gfp_mask, vma, addr, node)		\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
+	alloc_pages_vma(gfp_mask, 0, vma, addr, node)
 
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5228c62af416..bac395f1d00a 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -139,6 +139,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
 struct mempolicy *get_task_policy(struct task_struct *p);
 struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
 		unsigned long addr);
+struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+						unsigned long addr);
 bool vma_policy_mof(struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4e4ef8fa479d..55478ab3c83b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -629,21 +629,40 @@ release:
  *	    available
  * never: never stall for any thp allocation
  */
-static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
+static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr)
 {
 	const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+	gfp_t this_node = 0;
+
+#ifdef CONFIG_NUMA
+	struct mempolicy *pol;
+	/*
+	 * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not
+	 * specified, to express a general desire to stay on the current
+	 * node for optimistic allocation attempts. If the defrag mode
+	 * and/or madvise hint requires the direct reclaim then we prefer
+	 * to fallback to other node rather than node reclaim because that
+	 * can lead to excessive reclaim even though there is free memory
+	 * on other nodes. We expect that NUMA preferences are specified
+	 * by memory policies.
+	 */
+	pol = get_vma_policy(vma, addr);
+	if (pol->mode != MPOL_BIND)
+		this_node = __GFP_THISNODE;
+	mpol_cond_put(pol);
+#endif
 
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
-		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+		return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node;
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
-							     __GFP_KSWAPD_RECLAIM);
+							     __GFP_KSWAPD_RECLAIM | this_node);
 	if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
 		return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
-							     0);
-	return GFP_TRANSHUGE_LIGHT;
+							     this_node);
+	return GFP_TRANSHUGE_LIGHT | this_node;
 }
 
 /* Caller must hold page table lock. */
@@ -715,8 +734,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 			pte_free(vma->vm_mm, pgtable);
 		return ret;
 	}
-	gfp = alloc_hugepage_direct_gfpmask(vma);
-	page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
+	gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+	page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id());
 	if (unlikely(!page)) {
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1286,8 +1305,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
 	    !transparent_hugepage_debug_cow()) {
-		huge_gfp = alloc_hugepage_direct_gfpmask(vma);
-		new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
+		huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+		new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma,
+				haddr, numa_node_id());
 	} else
 		new_page = NULL;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 58fb833fce0c..5837a067124d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1116,8 +1116,8 @@ static struct page *new_page(struct page *page, unsigned long start)
 	} else if (PageTransHuge(page)) {
 		struct page *thp;
 
-		thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
-					 HPAGE_PMD_ORDER);
+		thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma,
+				address, numa_node_id());
 		if (!thp)
 			return NULL;
 		prep_transhuge_page(thp);
@@ -1662,7 +1662,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
  * freeing by another task.  It is the caller's responsibility to free the
  * extra reference for shared policies.
  */
-static struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
 						unsigned long addr)
 {
 	struct mempolicy *pol = __get_vma_policy(vma, addr);
@@ -2011,7 +2011,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  * 	@vma:  Pointer to VMA or NULL if not available.
  *	@addr: Virtual Address of the allocation. Must be inside the VMA.
  *	@node: Which node to prefer for allocation (modulo policy).
- *	@hugepage: for hugepages try only the preferred node if possible
  *
  * 	This function allocates a page from the kernel page pool and applies
  *	a NUMA policy associated with the VMA or the current process.
@@ -2022,7 +2021,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  */
 struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
-		unsigned long addr, int node, bool hugepage)
+		unsigned long addr, int node)
 {
 	struct mempolicy *pol;
 	struct page *page;
@@ -2040,60 +2039,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		goto out;
 	}
 
-	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
-		int hpage_node = node;
-
-		/*
-		 * For hugepage allocation and non-interleave policy which
-		 * allows the current node (or other explicitly preferred
-		 * node) we only try to allocate from the current/preferred
-		 * node and don't fall back to other nodes, as the cost of
-		 * remote accesses would likely offset THP benefits.
-		 *
-		 * If the policy is interleave, or does not allow the current
-		 * node in its nodemask, we allocate the standard way.
-		 */
-		if (pol->mode == MPOL_PREFERRED &&
-						!(pol->flags & MPOL_F_LOCAL))
-			hpage_node = pol->v.preferred_node;
-
-		nmask = policy_nodemask(gfp, pol);
-		if (!nmask || node_isset(hpage_node, *nmask)) {
-			mpol_cond_put(pol);
-			/*
-			 * We cannot invoke reclaim if __GFP_THISNODE
-			 * is set. Invoking reclaim with
-			 * __GFP_THISNODE set, would cause THP
-			 * allocations to trigger heavy swapping
-			 * despite there may be tons of free memory
-			 * (including potentially plenty of THP
-			 * already available in the buddy) on all the
-			 * other NUMA nodes.
-			 *
-			 * At most we could invoke compaction when
-			 * __GFP_THISNODE is set (but we would need to
-			 * refrain from invoking reclaim even if
-			 * compaction returned COMPACT_SKIPPED because
-			 * there wasn't not enough memory to succeed
-			 * compaction). For now just avoid
-			 * __GFP_THISNODE instead of limiting the
-			 * allocation path to a strict and single
-			 * compaction invocation.
-			 *
-			 * Supposedly if direct reclaim was enabled by
-			 * the caller, the app prefers THP regardless
-			 * of the node it comes from so this would be
-			 * more desiderable behavior than only
-			 * providing THP originated from the local
-			 * node in such case.
-			 */
-			if (!(gfp & __GFP_DIRECT_RECLAIM))
-				gfp |= __GFP_THISNODE;
-			page = __alloc_pages_node(hpage_node, gfp, order);
-			goto out;
-		}
-	}
-
 	nmask = policy_nodemask(gfp, pol);
 	preferred_nid = policy_node(gfp, pol, node);
 	page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);
diff --git a/mm/shmem.c b/mm/shmem.c
index 56bf122e0bb4..ea26d7a0342d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1435,7 +1435,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp,
 
 	shmem_pseudo_vma_init(&pvma, info, hindex);
 	page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN,
-			HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true);
+			HPAGE_PMD_ORDER, &pvma, 0, numa_node_id());
 	shmem_pseudo_vma_destroy(&pvma);
 	if (page)
 		prep_transhuge_page(page);
-- 
cgit v1.2.3-55-g7522


From 1a413646931cb14442065cfc17561e50f5b5bb44 Mon Sep 17 00:00:00 2001
From: Yufen Yu
Date: Fri, 16 Nov 2018 15:08:39 -0800
Subject: tmpfs: make lseek(SEEK_DATA/SEK_HOLE) return ENXIO with a negative
 offset

Other filesystems such as ext4, f2fs and ubifs all return ENXIO when
lseek (SEEK_DATA or SEEK_HOLE) requests a negative offset.

man 2 lseek says

:      EINVAL whence  is  not  valid.   Or: the resulting file offset would be
:             negative, or beyond the end of a seekable device.
:
:      ENXIO  whence is SEEK_DATA or SEEK_HOLE, and the file offset is  beyond
:             the end of the file.

Make tmpfs return ENXIO under these circumstances as well.  After this,
tmpfs also passes xfstests's generic/448.

[akpm@linux-foundation.org: rewrite changelog]
Link: http://lkml.kernel.org/r/1540434176-14349-1-git-send-email-yuyufen@huawei.com
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Hugh Dickins <hughd@google.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/shmem.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'mm/shmem.c')

diff --git a/mm/shmem.c b/mm/shmem.c
index ea26d7a0342d..d44991ea5ed4 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2563,9 +2563,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 	inode_lock(inode);
 	/* We're holding i_mutex so we can access i_size directly */
 
-	if (offset < 0)
-		offset = -EINVAL;
-	else if (offset >= inode->i_size)
+	if (offset < 0 || offset >= inode->i_size)
 		offset = -ENXIO;
 	else {
 		start = offset >> PAGE_SHIFT;
-- 
cgit v1.2.3-55-g7522