linux-stable/include/linux/slub_def.h
Vlastimil Babka bd0e7491a9 mm, slub: convert kmem_cpu_slab protection to local_lock
Embed local_lock into struct kmem_cpu_slab and use the irq-safe versions of
local_lock instead of plain local_irq_save/restore. On !PREEMPT_RT that's
equivalent, with better lockdep visibility. On PREEMPT_RT that means better
preemption.

However, the cost on PREEMPT_RT is the loss of lockless fast paths which only
work with cpu freelist. Those are designed to detect and recover from being
preempted by other conflicting operations (both fast or slow path), but the
slow path operations assume they cannot be preempted by a fast path operation,
which is guaranteed naturally with disabled irqs. With local locks on
PREEMPT_RT, the fast paths now also need to take the local lock to avoid races.

In the allocation fastpath slab_alloc_node() we can just defer to the slowpath
__slab_alloc() which also works with cpu freelist, but under the local lock.
In the free fastpath do_slab_free() we have to add a new local lock protected
version of freeing to the cpu freelist, as the existing slowpath only works
with the page freelist.

Also update the comment about locking scheme in SLUB to reflect changes done
by this series.

[ Mike Galbraith <efault@gmx.de>: use local_lock() without irq in PREEMPT_RT
  scope; debugging of RT crashes resulting in put_cpu_partial() locking changes ]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
2021-09-04 10:22:01 +02:00

205 lines
6.2 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_SLUB_DEF_H
#define _LINUX_SLUB_DEF_H
/*
* SLUB : A Slab allocator without object queues.
*
* (C) 2007 SGI, Christoph Lameter
*/
#include <linux/kfence.h>
#include <linux/kobject.h>
#include <linux/reciprocal_div.h>
#include <linux/local_lock.h>
enum stat_item {
ALLOC_FASTPATH, /* Allocation from cpu slab */
ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */
FREE_FASTPATH, /* Free to cpu slab */
FREE_SLOWPATH, /* Freeing not to cpu slab */
FREE_FROZEN, /* Freeing to frozen slab */
FREE_ADD_PARTIAL, /* Freeing moves slab to partial list */
FREE_REMOVE_PARTIAL, /* Freeing removes last object */
ALLOC_FROM_PARTIAL, /* Cpu slab acquired from node partial list */
ALLOC_SLAB, /* Cpu slab acquired from page allocator */
ALLOC_REFILL, /* Refill cpu slab from slab freelist */
ALLOC_NODE_MISMATCH, /* Switching cpu slab */
FREE_SLAB, /* Slab freed to the page allocator */
CPUSLAB_FLUSH, /* Abandoning of the cpu slab */
DEACTIVATE_FULL, /* Cpu slab was full when deactivated */
DEACTIVATE_EMPTY, /* Cpu slab was empty when deactivated */
DEACTIVATE_TO_HEAD, /* Cpu slab was moved to the head of partials */
DEACTIVATE_TO_TAIL, /* Cpu slab was moved to the tail of partials */
DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
DEACTIVATE_BYPASS, /* Implicit deactivation */
ORDER_FALLBACK, /* Number of times fallback was necessary */
CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */
CMPXCHG_DOUBLE_FAIL, /* Number of times that cmpxchg double did not match */
CPU_PARTIAL_ALLOC, /* Used cpu partial on alloc */
CPU_PARTIAL_FREE, /* Refill cpu partial on free */
CPU_PARTIAL_NODE, /* Refill cpu partial from node partial */
CPU_PARTIAL_DRAIN, /* Drain cpu partial to node partial */
NR_SLUB_STAT_ITEMS };
/*
* When changing the layout, make sure freelist and tid are still compatible
* with this_cpu_cmpxchg_double() alignment requirements.
*/
struct kmem_cache_cpu {
void **freelist; /* Pointer to next available object */
unsigned long tid; /* Globally unique transaction id */
struct page *page; /* The slab from which we are allocating */
#ifdef CONFIG_SLUB_CPU_PARTIAL
struct page *partial; /* Partially allocated frozen slabs */
#endif
local_lock_t lock; /* Protects the fields above */
#ifdef CONFIG_SLUB_STATS
unsigned stat[NR_SLUB_STAT_ITEMS];
#endif
};
#ifdef CONFIG_SLUB_CPU_PARTIAL
#define slub_percpu_partial(c) ((c)->partial)
#define slub_set_percpu_partial(c, p) \
({ \
slub_percpu_partial(c) = (p)->next; \
})
#define slub_percpu_partial_read_once(c) READ_ONCE(slub_percpu_partial(c))
#else
#define slub_percpu_partial(c) NULL
#define slub_set_percpu_partial(c, p)
#define slub_percpu_partial_read_once(c) NULL
#endif // CONFIG_SLUB_CPU_PARTIAL
/*
* Word size structure that can be atomically updated or read and that
* contains both the order and the number of objects that a slab of the
* given order would contain.
*/
struct kmem_cache_order_objects {
unsigned int x;
};
/*
* Slab cache management.
*/
struct kmem_cache {
struct kmem_cache_cpu __percpu *cpu_slab;
/* Used for retrieving partial slabs, etc. */
slab_flags_t flags;
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 */
unsigned int cpu_partial;
#endif
struct kmem_cache_order_objects oo;
/* Allocation and freeing of slabs */
struct kmem_cache_order_objects max;
struct kmem_cache_order_objects min;
gfp_t allocflags; /* gfp flags to use on each alloc */
int refcount; /* Refcount for slab cache destroy */
void (*ctor)(void *);
unsigned int inuse; /* Offset to metadata */
unsigned int align; /* Alignment */
unsigned int red_left_pad; /* Left redzone padding size */
const char *name; /* Name (only for display!) */
struct list_head list; /* List of slab caches */
#ifdef CONFIG_SYSFS
struct kobject kobj; /* For sysfs */
#endif
#ifdef CONFIG_SLAB_FREELIST_HARDENED
unsigned long random;
#endif
#ifdef CONFIG_NUMA
/*
* Defragmentation by allocating from a remote node.
*/
unsigned int remote_node_defrag_ratio;
#endif
#ifdef CONFIG_SLAB_FREELIST_RANDOM
unsigned int *random_seq;
#endif
#ifdef CONFIG_KASAN
struct kasan_cache kasan_info;
#endif
unsigned int useroffset; /* Usercopy region offset */
unsigned int usersize; /* Usercopy region size */
struct kmem_cache_node *node[MAX_NUMNODES];
};
#ifdef CONFIG_SLUB_CPU_PARTIAL
#define slub_cpu_partial(s) ((s)->cpu_partial)
#define slub_set_cpu_partial(s, n) \
({ \
slub_cpu_partial(s) = (n); \
})
#else
#define slub_cpu_partial(s) (0)
#define slub_set_cpu_partial(s, n)
#endif /* CONFIG_SLUB_CPU_PARTIAL */
#ifdef CONFIG_SYSFS
#define SLAB_SUPPORTS_SYSFS
void sysfs_slab_unlink(struct kmem_cache *);
void sysfs_slab_release(struct kmem_cache *);
#else
static inline void sysfs_slab_unlink(struct kmem_cache *s)
{
}
static inline void sysfs_slab_release(struct kmem_cache *s)
{
}
#endif
void object_err(struct kmem_cache *s, struct page *page,
u8 *object, char *reason);
void *fixup_red_left(struct kmem_cache *s, void *p);
static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
void *x) {
void *object = x - (x - page_address(page)) % cache->size;
void *last_object = page_address(page) +
(page->objects - 1) * cache->size;
void *result = (unlikely(object > last_object)) ? last_object : object;
result = fixup_red_left(cache, result);
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)
{
if (is_kfence_address(obj))
return 0;
return __obj_to_index(cache, page_address(page), obj);
}
static inline int objs_per_slab_page(const struct kmem_cache *cache,
const struct page *page)
{
return page->objects;
}
#endif /* _LINUX_SLUB_DEF_H */