linux-kernel - [PATCH v4 04/19] mm: slub: implement SLUB version of obj_to

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200526214227.989341-5-guro@fb.com>
Date:   Tue, 26 May 2020 14:42:12 -0700
From:   Roman Gushchin <guro@...com>
To:     Andrew Morton <akpm@...ux-foundation.org>,
        Christoph Lameter <cl@...ux.com>
CC:     Johannes Weiner <hannes@...xchg.org>,
        Michal Hocko <mhocko@...nel.org>,
        Shakeel Butt <shakeelb@...gle.com>, <linux-mm@...ck.org>,
        Vlastimil Babka <vbabka@...e.cz>, <kernel-team@...com>,
        <linux-kernel@...r.kernel.org>, Roman Gushchin <guro@...com>
Subject: [PATCH v4 04/19] mm: slub: implement SLUB version of obj_to_index()

This commit implements SLUB version of the obj_to_index() function,
which will be required to calculate the offset of obj_cgroup in the
obj_cgroups vector to store/obtain the objcg ownership data.

To make it faster, let's repeat the SLAB's trick introduced by
commit 6a2d7a955d8d ("[PATCH] SLAB: use a multiply instead of a
divide in obj_to_index()") and avoid an expensive division.

Vlastimil Babka noticed, that SLUB does have already a similar
function called slab_index(), which is defined only if SLUB_DEBUG
is enabled. The function does a similar math, but with a division,
and it also takes a page address instead of a page pointer.

Let's remove slab_index() and replace it with the new helper
__obj_to_index(), which takes a page address. obj_to_index()
will be a simple wrapper taking a page pointer and passing
page_address(page) into __obj_to_index().

Signed-off-by: Roman Gushchin <guro@...com>
Reviewed-by: Vlastimil Babka <vbabka@...e.cz>
---
 include/linux/slub_def.h | 16 ++++++++++++++++
 mm/slub.c                | 15 +++++----------
 2 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index d2153789bd9f..30e91c83d401 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -8,6 +8,7 @@
  * (C) 2007 SGI, Christoph Lameter
  */
 #include <linux/kobject.h>
+#include <linux/reciprocal_div.h>
 
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
@@ -86,6 +87,7 @@ struct kmem_cache {
 	unsigned long min_partial;
 	unsigned int size;	/* The size of an object including metadata */
 	unsigned int object_size;/* The size of an object without metadata */
+	struct reciprocal_value reciprocal_size;
 	unsigned int offset;	/* Free pointer offset */
 #ifdef CONFIG_SLUB_CPU_PARTIAL
 	/* Number of per cpu partial objects to keep around */
@@ -182,4 +184,18 @@ static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
 	return result;
 }
 
+/* Determine object index from a given position */
+static inline unsigned int __obj_to_index(const struct kmem_cache *cache,
+					  void *addr, void *obj)
+{
+	return reciprocal_divide(kasan_reset_tag(obj) - addr,
+				 cache->reciprocal_size);
+}
+
+static inline unsigned int obj_to_index(const struct kmem_cache *cache,
+					const struct page *page, void *obj)
+{
+	return __obj_to_index(cache, page_address(page), obj);
+}
+
 #endif /* _LINUX_SLUB_DEF_H */
diff --git a/mm/slub.c b/mm/slub.c
index dbed2cfd2776..601c0fc3c83a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -313,12 +313,6 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
 		__p < (__addr) + (__objects) * (__s)->size; \
 		__p += (__s)->size)
 
-/* Determine object index from a given position */
-static inline unsigned int slab_index(void *p, struct kmem_cache *s, void *addr)
-{
-	return (kasan_reset_tag(p) - addr) / s->size;
-}
-
 static inline unsigned int order_objects(unsigned int order, unsigned int size)
 {
 	return ((unsigned int)PAGE_SIZE << order) / size;
@@ -461,7 +455,7 @@ static unsigned long *get_map(struct kmem_cache *s, struct page *page)
 	bitmap_zero(object_map, page->objects);
 
 	for (p = page->freelist; p; p = get_freepointer(s, p))
-		set_bit(slab_index(p, s, addr), object_map);
+		set_bit(__obj_to_index(s, addr, p), object_map);
 
 	return object_map;
 }
@@ -3675,6 +3669,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 	 */
 	size = ALIGN(size, s->align);
 	s->size = size;
+	s->reciprocal_size = reciprocal_value(size);
 	if (forced_order >= 0)
 		order = forced_order;
 	else
@@ -3781,7 +3776,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 	map = get_map(s, page);
 	for_each_object(p, s, addr, page->objects) {
 
-		if (!test_bit(slab_index(p, s, addr), map)) {
+		if (!test_bit(__obj_to_index(s, addr, p), map)) {
 			pr_err("INFO: Object 0x%p @offset=%tu\n", p, p - addr);
 			print_tracking(s, p);
 		}
@@ -4506,7 +4501,7 @@ static void validate_slab(struct kmem_cache *s, struct page *page)
 	/* Now we know that a valid freelist exists */
 	map = get_map(s, page);
 	for_each_object(p, s, addr, page->objects) {
-		u8 val = test_bit(slab_index(p, s, addr), map) ?
+		u8 val = test_bit(__obj_to_index(s, addr, p), map) ?
 			 SLUB_RED_INACTIVE : SLUB_RED_ACTIVE;
 
 		if (!check_object(s, page, p, val))
@@ -4697,7 +4692,7 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s,
 
 	map = get_map(s, page);
 	for_each_object(p, s, addr, page->objects)
-		if (!test_bit(slab_index(p, s, addr), map))
+		if (!test_bit(__obj_to_index(s, addr, p), map))
 			add_location(t, s, get_track(s, p, alloc));
 	put_map(map);
 }
-- 
2.25.4