Merge tag 'mm-stable-2024-05-22-17-22' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull more mm updates from Andrew Morton:
 "A series from Dave Chinner which cleans up and fixes the handling of
  nested allocations within stackdepot and page-owner"

* tag 'mm-stable-2024-05-22-17-22' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm/page-owner: use gfp_nested_mask() instead of open coded masking
  stackdepot: use gfp_nested_mask() instead of open coded masking
  mm: lift gfp_kmemleak_mask() to gfp.h

4 files changed, 32 insertions, 23 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 450c2cbcf04b..7f9691d375f0 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -157,6 +157,31 @@ static inline int gfp_zonelist(gfp_t flags)
 }
 
 /*
+ * gfp flag masking for nested internal allocations.
+ *
+ * For code that needs to do allocations inside the public allocation API (e.g.
+ * memory allocation tracking code) the allocations need to obey the caller
+ * allocation context constrains to prevent allocation context mismatches (e.g.
+ * GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock
+ * situations.
+ *
+ * It is also assumed that these nested allocations are for internal kernel
+ * object storage purposes only and are not going to be used for DMA, etc. Hence
+ * we strip out all the zone information and leave just the context information
+ * intact.
+ *
+ * Further, internal allocations must fail before the higher level allocation
+ * can fail, so we must make them fail faster and fail silently. We also don't
+ * want them to deplete emergency reserves.  Hence nested allocations must be
+ * prepared for these allocations to fail.
+ */
+static inline gfp_t gfp_nested_mask(gfp_t flags)
+{
+	return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) |
+		(__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN));
+}
+
+/*
  * We get the zone list from the current node and the gfp_mask.
  * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones.
  * There are two zonelists per node, one for all zones with memory and
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index cd8f23455285..5ed34cc963fc 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -624,15 +624,8 @@ depot_stack_handle_t stack_depot_save_flags(unsigned long *entries,
 	 * we won't be able to do that under the lock.
 	 */
 	if (unlikely(can_alloc && !READ_ONCE(new_pool))) {
-		/*
-		 * Zero out zone modifiers, as we don't have specific zone
-		 * requirements. Keep the flags related to allocation in atomic
-		 * contexts, I/O, nolockdep.
-		 */
-		alloc_flags &= ~GFP_ZONEMASK;
-		alloc_flags &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP);
-		alloc_flags |= __GFP_NOWARN;
-		page = alloc_pages(alloc_flags, DEPOT_POOL_ORDER);
+		page = alloc_pages(gfp_nested_mask(alloc_flags),
+				   DEPOT_POOL_ORDER);
 		if (page)
 			prealloc = page_address(page);
 	}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index fdcf01f62202..d5b6fba44fc9 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -114,12 +114,6 @@
 
 #define BYTES_PER_POINTER	sizeof(void *)
 
-/* GFP bitmask for kmemleak internal allocations */
-#define gfp_kmemleak_mask(gfp)	(((gfp) & (GFP_KERNEL | GFP_ATOMIC | \
-					   __GFP_NOLOCKDEP)) | \
-				 __GFP_NORETRY | __GFP_NOMEMALLOC | \
-				 __GFP_NOWARN)
-
 /* scanning area inside a memory block */
 struct kmemleak_scan_area {
 	struct hlist_node node;
@@ -463,7 +457,8 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp)
 
 	/* try the slab allocator first */
 	if (object_cache) {
-		object = kmem_cache_alloc_noprof(object_cache, gfp_kmemleak_mask(gfp));
+		object = kmem_cache_alloc_noprof(object_cache,
+						 gfp_nested_mask(gfp));
 		if (object)
 			return object;
 	}
@@ -947,7 +942,8 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 	untagged_objp = (unsigned long)kasan_reset_tag((void *)object->pointer);
 
 	if (scan_area_cache)
-		area = kmem_cache_alloc_noprof(scan_area_cache, gfp_kmemleak_mask(gfp));
+		area = kmem_cache_alloc_noprof(scan_area_cache,
+					       gfp_nested_mask(gfp));
 
 	raw_spin_lock_irqsave(&object->lock, flags);
 	if (!area) {
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 0a448d76e0af..2d6360eaccbb 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -168,13 +168,8 @@ static void add_stack_record_to_list(struct stack_record *stack_record,
 	unsigned long flags;
 	struct stack *stack;
 
-	/* Filter gfp_mask the same way stackdepot does, for consistency */
-	gfp_mask &= ~GFP_ZONEMASK;
-	gfp_mask &= (GFP_ATOMIC | GFP_KERNEL | __GFP_NOLOCKDEP);
-	gfp_mask |= __GFP_NOWARN;
-
 	set_current_in_page_owner();
-	stack = kmalloc(sizeof(*stack), gfp_mask);
+	stack = kmalloc(sizeof(*stack), gfp_nested_mask(gfp_mask));
 	if (!stack) {
 		unset_current_in_page_owner();
 		return;