The patch titled
Subject: mm: slub: implement SLUB version of obj_to_index()
has been removed from the -mm tree. Its filename was
mm-slub-implement-slub-version-of-obj_to_index.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Roman Gushchin <guro@xxxxxx>
Subject: 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 ("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().
Link: http://lkml.kernel.org/r/20200623174037.3951353-5-guro@xxxxxx
Signed-off-by: Roman Gushchin <guro@xxxxxx>
Reviewed-by: Vlastimil Babka <vbabka@xxxxxxx>
Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/slub_def.h | 16 ++++++++++++++++
mm/slub.c | 15 +++++----------
2 files changed, 21 insertions(+), 10 deletions(-)
--- a/include/linux/slub_def.h~mm-slub-implement-slub-version-of-obj_to_index
+++ a/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 k
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 */
--- a/mm/slub.c~mm-slub-implement-slub-version-of-obj_to_index
+++ a/mm/slub.c
@@ -317,12 +317,6 @@ static inline void set_freepointer(struc
__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;
@@ -465,7 +459,7 @@ static unsigned long *get_map(struct kme
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;
}
@@ -3754,6 +3748,7 @@ static int calculate_sizes(struct kmem_c
*/
size = ALIGN(size, s->align);
s->size = size;
+ s->reciprocal_size = reciprocal_value(size);
if (forced_order >= 0)
order = forced_order;
else
@@ -3858,7 +3853,7 @@ static void list_slab_objects(struct kme
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);
}
@@ -4574,7 +4569,7 @@ static void validate_slab(struct kmem_ca
/* 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))
@@ -4765,7 +4760,7 @@ static void process_slab(struct loc_trac
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);
}
_
Patches currently in -mm which might be from guro@xxxxxx are
percpu-return-number-of-released-bytes-from-pcpu_free_area.patch
mm-memcg-percpu-account-percpu-memory-to-memory-cgroups.patch
mm-memcg-percpu-per-memcg-percpu-memory-statistics.patch
mm-memcg-percpu-per-memcg-percpu-memory-statistics-v3.patch
mm-memcg-charge-memcg-percpu-memory-to-the-parent-cgroup.patch
kselftests-cgroup-add-perpcu-memory-accounting-test.patch
mm-vmstat-fix-proc-sys-vm-stat_refresh-generating-false-warnings.patch
mm-vmstat-fix-proc-sys-vm-stat_refresh-generating-false-warnings-fix.patch
