[PATCH v2 3/4] mm: avoid slub allocation while holding list_lock

From: Yu Zhao
Date: Wed Sep 11 2019 - 22:31:28 EST


If we are already under list_lock, don't call kmalloc(). Otherwise we
will run into deadlock because kmalloc() also tries to grab the same
lock.

Fixing the problem by using a static bitmap instead.

WARNING: possible recursive locking detected
--------------------------------------------
mount-encrypted/4921 is trying to acquire lock:
(&(&n->list_lock)->rlock){-.-.}, at: ___slab_alloc+0x104/0x437

but task is already holding lock:
(&(&n->list_lock)->rlock){-.-.}, at: __kmem_cache_shutdown+0x81/0x3cb

other info that might help us debug this:
Possible unsafe locking scenario:

CPU0
----
lock(&(&n->list_lock)->rlock);
lock(&(&n->list_lock)->rlock);

*** DEADLOCK ***

Signed-off-by: Yu Zhao <yuzhao@xxxxxxxxxx>
---
mm/slub.c | 88 +++++++++++++++++++++++++++++--------------------------
1 file changed, 47 insertions(+), 41 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 7b7e1ee264ef..baa60dd73942 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -443,19 +443,38 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
}

#ifdef CONFIG_SLUB_DEBUG
+static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)];
+static DEFINE_SPINLOCK(object_map_lock);
+
/*
* Determine a map of object in use on a page.
*
* Node listlock must be held to guarantee that the page does
* not vanish from under us.
*/
-static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
+static unsigned long *get_map(struct kmem_cache *s, struct page *page)
{
void *p;
void *addr = page_address(page);

+ VM_BUG_ON(!irqs_disabled());
+
+ spin_lock(&object_map_lock);
+
+ bitmap_zero(object_map, page->objects);
+
for (p = page->freelist; p; p = get_freepointer(s, p))
- set_bit(slab_index(p, s, addr), map);
+ set_bit(slab_index(p, s, addr), object_map);
+
+ return object_map;
+}
+
+static void put_map(unsigned long *map)
+{
+ VM_BUG_ON(map != object_map);
+ lockdep_assert_held(&object_map_lock);
+
+ spin_unlock(&object_map_lock);
}

static inline unsigned int size_from_object(struct kmem_cache *s)
@@ -3685,13 +3704,12 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
#ifdef CONFIG_SLUB_DEBUG
void *addr = page_address(page);
void *p;
- unsigned long *map = bitmap_zalloc(page->objects, GFP_ATOMIC);
- if (!map)
- return;
+ unsigned long *map;
+
slab_err(s, page, text, s->name);
slab_lock(page);

- get_map(s, page, map);
+ map = get_map(s, page);
for_each_object(p, s, addr, page->objects) {

if (!test_bit(slab_index(p, s, addr), map)) {
@@ -3699,8 +3717,9 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
print_tracking(s, p);
}
}
+ put_map(map);
+
slab_unlock(page);
- bitmap_free(map);
#endif
}

@@ -4386,19 +4405,19 @@ static int count_total(struct page *page)
#endif

#ifdef CONFIG_SLUB_DEBUG
-static void validate_slab(struct kmem_cache *s, struct page *page,
- unsigned long *map)
+static void validate_slab(struct kmem_cache *s, struct page *page)
{
void *p;
void *addr = page_address(page);
+ unsigned long *map;
+
+ slab_lock(page);

if (!check_slab(s, page) || !on_freelist(s, page, NULL))
- return;
+ goto unlock;

/* Now we know that a valid freelist exists */
- bitmap_zero(map, page->objects);
-
- get_map(s, page, map);
+ map = get_map(s, page);
for_each_object(p, s, addr, page->objects) {
u8 val = test_bit(slab_index(p, s, addr), map) ?
SLUB_RED_INACTIVE : SLUB_RED_ACTIVE;
@@ -4406,18 +4425,13 @@ static void validate_slab(struct kmem_cache *s, struct page *page,
if (!check_object(s, page, p, val))
break;
}
-}
-
-static void validate_slab_slab(struct kmem_cache *s, struct page *page,
- unsigned long *map)
-{
- slab_lock(page);
- validate_slab(s, page, map);
+ put_map(map);
+unlock:
slab_unlock(page);
}

static int validate_slab_node(struct kmem_cache *s,
- struct kmem_cache_node *n, unsigned long *map)
+ struct kmem_cache_node *n)
{
unsigned long count = 0;
struct page *page;
@@ -4426,7 +4440,7 @@ static int validate_slab_node(struct kmem_cache *s,
spin_lock_irqsave(&n->list_lock, flags);

list_for_each_entry(page, &n->partial, slab_list) {
- validate_slab_slab(s, page, map);
+ validate_slab(s, page);
count++;
}
if (count != n->nr_partial)
@@ -4437,7 +4451,7 @@ static int validate_slab_node(struct kmem_cache *s,
goto out;

list_for_each_entry(page, &n->full, slab_list) {
- validate_slab_slab(s, page, map);
+ validate_slab(s, page);
count++;
}
if (count != atomic_long_read(&n->nr_slabs))
@@ -4454,15 +4468,11 @@ static long validate_slab_cache(struct kmem_cache *s)
int node;
unsigned long count = 0;
struct kmem_cache_node *n;
- unsigned long *map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL);
-
- if (!map)
- return -ENOMEM;

flush_all(s);
for_each_kmem_cache_node(s, node, n)
- count += validate_slab_node(s, n, map);
- bitmap_free(map);
+ count += validate_slab_node(s, n);
+
return count;
}
/*
@@ -4592,18 +4602,17 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
}

static void process_slab(struct loc_track *t, struct kmem_cache *s,
- struct page *page, enum track_item alloc,
- unsigned long *map)
+ struct page *page, enum track_item alloc)
{
void *addr = page_address(page);
void *p;
+ unsigned long *map;

- bitmap_zero(map, page->objects);
- get_map(s, page, map);
-
+ map = get_map(s, page);
for_each_object(p, s, addr, page->objects)
if (!test_bit(slab_index(p, s, addr), map))
add_location(t, s, get_track(s, p, alloc));
+ put_map(map);
}

static int list_locations(struct kmem_cache *s, char *buf,
@@ -4614,11 +4623,9 @@ static int list_locations(struct kmem_cache *s, char *buf,
struct loc_track t = { 0, 0, NULL };
int node;
struct kmem_cache_node *n;
- unsigned long *map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL);

- if (!map || !alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
- GFP_KERNEL)) {
- bitmap_free(map);
+ if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
+ GFP_KERNEL)) {
return sprintf(buf, "Out of memory\n");
}
/* Push back cpu slabs */
@@ -4633,9 +4640,9 @@ static int list_locations(struct kmem_cache *s, char *buf,

spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry(page, &n->partial, slab_list)
- process_slab(&t, s, page, alloc, map);
+ process_slab(&t, s, page, alloc);
list_for_each_entry(page, &n->full, slab_list)
- process_slab(&t, s, page, alloc, map);
+ process_slab(&t, s, page, alloc);
spin_unlock_irqrestore(&n->list_lock, flags);
}

@@ -4684,7 +4691,6 @@ static int list_locations(struct kmem_cache *s, char *buf,
}

free_loc_track(&t);
- bitmap_free(map);
if (!t.count)
len += sprintf(buf, "No data\n");
return len;
--
2.23.0.162.g0b9fbb3734-goog