mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![Muchun Song](/assets/img/avatar_default.png)
We currently allocate scope for every memcg to be able to tracked on every superblock instantiated in the system, regardless of whether that superblock is even accessible to that memcg. These huge memcg counts come from container hosts where memcgs are confined to just a small subset of the total number of superblocks that instantiated at any given point in time. For these systems with huge container counts, list_lru does not need the capability of tracking every memcg on every superblock. What it comes down to is that adding the memcg to the list_lru at the first insert. So introduce kmem_cache_alloc_lru to allocate objects and its list_lru. In the later patch, we will convert all inode and dentry allocation from kmem_cache_alloc to kmem_cache_alloc_lru. Link: https://lkml.kernel.org/r/20220228122126.37293-3-songmuchun@bytedance.com Signed-off-by: Muchun Song <songmuchun@bytedance.com> Cc: Alex Shi <alexs@kernel.org> Cc: Anna Schumaker <Anna.Schumaker@Netapp.com> Cc: Chao Yu <chao@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Fam Zheng <fam.zheng@bytedance.com> Cc: Jaegeuk Kim <jaegeuk@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kari Argillander <kari.argillander@gmail.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Trond Myklebust <trond.myklebust@hammerspace.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Xiongchun Duan <duanxiongchun@bytedance.com> Cc: Yang Shi <shy828301@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
776 lines
24 KiB
C
776 lines
24 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk).
|
|
*
|
|
* (C) SGI 2006, Christoph Lameter
|
|
* Cleaned up and restructured to ease the addition of alternative
|
|
* implementations of SLAB allocators.
|
|
* (C) Linux Foundation 2008-2013
|
|
* Unified interface for all slab allocators
|
|
*/
|
|
|
|
#ifndef _LINUX_SLAB_H
|
|
#define _LINUX_SLAB_H
|
|
|
|
#include <linux/gfp.h>
|
|
#include <linux/overflow.h>
|
|
#include <linux/types.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/percpu-refcount.h>
|
|
|
|
|
|
/*
|
|
* Flags to pass to kmem_cache_create().
|
|
* The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set.
|
|
*/
|
|
/* DEBUG: Perform (expensive) checks on alloc/free */
|
|
#define SLAB_CONSISTENCY_CHECKS ((slab_flags_t __force)0x00000100U)
|
|
/* DEBUG: Red zone objs in a cache */
|
|
#define SLAB_RED_ZONE ((slab_flags_t __force)0x00000400U)
|
|
/* DEBUG: Poison objects */
|
|
#define SLAB_POISON ((slab_flags_t __force)0x00000800U)
|
|
/* Align objs on cache lines */
|
|
#define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U)
|
|
/* Use GFP_DMA memory */
|
|
#define SLAB_CACHE_DMA ((slab_flags_t __force)0x00004000U)
|
|
/* Use GFP_DMA32 memory */
|
|
#define SLAB_CACHE_DMA32 ((slab_flags_t __force)0x00008000U)
|
|
/* DEBUG: Store the last owner for bug hunting */
|
|
#define SLAB_STORE_USER ((slab_flags_t __force)0x00010000U)
|
|
/* Panic if kmem_cache_create() fails */
|
|
#define SLAB_PANIC ((slab_flags_t __force)0x00040000U)
|
|
/*
|
|
* SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
|
|
*
|
|
* This delays freeing the SLAB page by a grace period, it does _NOT_
|
|
* delay object freeing. This means that if you do kmem_cache_free()
|
|
* that memory location is free to be reused at any time. Thus it may
|
|
* be possible to see another object there in the same RCU grace period.
|
|
*
|
|
* This feature only ensures the memory location backing the object
|
|
* stays valid, the trick to using this is relying on an independent
|
|
* object validation pass. Something like:
|
|
*
|
|
* rcu_read_lock()
|
|
* again:
|
|
* obj = lockless_lookup(key);
|
|
* if (obj) {
|
|
* if (!try_get_ref(obj)) // might fail for free objects
|
|
* goto again;
|
|
*
|
|
* if (obj->key != key) { // not the object we expected
|
|
* put_ref(obj);
|
|
* goto again;
|
|
* }
|
|
* }
|
|
* rcu_read_unlock();
|
|
*
|
|
* This is useful if we need to approach a kernel structure obliquely,
|
|
* from its address obtained without the usual locking. We can lock
|
|
* the structure to stabilize it and check it's still at the given address,
|
|
* only if we can be sure that the memory has not been meanwhile reused
|
|
* for some other kind of object (which our subsystem's lock might corrupt).
|
|
*
|
|
* rcu_read_lock before reading the address, then rcu_read_unlock after
|
|
* taking the spinlock within the structure expected at that address.
|
|
*
|
|
* Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU.
|
|
*/
|
|
/* Defer freeing slabs to RCU */
|
|
#define SLAB_TYPESAFE_BY_RCU ((slab_flags_t __force)0x00080000U)
|
|
/* Spread some memory over cpuset */
|
|
#define SLAB_MEM_SPREAD ((slab_flags_t __force)0x00100000U)
|
|
/* Trace allocations and frees */
|
|
#define SLAB_TRACE ((slab_flags_t __force)0x00200000U)
|
|
|
|
/* Flag to prevent checks on free */
|
|
#ifdef CONFIG_DEBUG_OBJECTS
|
|
# define SLAB_DEBUG_OBJECTS ((slab_flags_t __force)0x00400000U)
|
|
#else
|
|
# define SLAB_DEBUG_OBJECTS 0
|
|
#endif
|
|
|
|
/* Avoid kmemleak tracing */
|
|
#define SLAB_NOLEAKTRACE ((slab_flags_t __force)0x00800000U)
|
|
|
|
/* Fault injection mark */
|
|
#ifdef CONFIG_FAILSLAB
|
|
# define SLAB_FAILSLAB ((slab_flags_t __force)0x02000000U)
|
|
#else
|
|
# define SLAB_FAILSLAB 0
|
|
#endif
|
|
/* Account to memcg */
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
# define SLAB_ACCOUNT ((slab_flags_t __force)0x04000000U)
|
|
#else
|
|
# define SLAB_ACCOUNT 0
|
|
#endif
|
|
|
|
#ifdef CONFIG_KASAN
|
|
#define SLAB_KASAN ((slab_flags_t __force)0x08000000U)
|
|
#else
|
|
#define SLAB_KASAN 0
|
|
#endif
|
|
|
|
/* The following flags affect the page allocator grouping pages by mobility */
|
|
/* Objects are reclaimable */
|
|
#define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U)
|
|
#define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */
|
|
|
|
/* Slab deactivation flag */
|
|
#define SLAB_DEACTIVATED ((slab_flags_t __force)0x10000000U)
|
|
|
|
/*
|
|
* ZERO_SIZE_PTR will be returned for zero sized kmalloc requests.
|
|
*
|
|
* Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault.
|
|
*
|
|
* ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can.
|
|
* Both make kfree a no-op.
|
|
*/
|
|
#define ZERO_SIZE_PTR ((void *)16)
|
|
|
|
#define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \
|
|
(unsigned long)ZERO_SIZE_PTR)
|
|
|
|
#include <linux/kasan.h>
|
|
|
|
struct list_lru;
|
|
struct mem_cgroup;
|
|
/*
|
|
* struct kmem_cache related prototypes
|
|
*/
|
|
void __init kmem_cache_init(void);
|
|
bool slab_is_available(void);
|
|
|
|
struct kmem_cache *kmem_cache_create(const char *name, unsigned int size,
|
|
unsigned int align, slab_flags_t flags,
|
|
void (*ctor)(void *));
|
|
struct kmem_cache *kmem_cache_create_usercopy(const char *name,
|
|
unsigned int size, unsigned int align,
|
|
slab_flags_t flags,
|
|
unsigned int useroffset, unsigned int usersize,
|
|
void (*ctor)(void *));
|
|
void kmem_cache_destroy(struct kmem_cache *s);
|
|
int kmem_cache_shrink(struct kmem_cache *s);
|
|
|
|
/*
|
|
* Please use this macro to create slab caches. Simply specify the
|
|
* name of the structure and maybe some flags that are listed above.
|
|
*
|
|
* The alignment of the struct determines object alignment. If you
|
|
* f.e. add ____cacheline_aligned_in_smp to the struct declaration
|
|
* then the objects will be properly aligned in SMP configurations.
|
|
*/
|
|
#define KMEM_CACHE(__struct, __flags) \
|
|
kmem_cache_create(#__struct, sizeof(struct __struct), \
|
|
__alignof__(struct __struct), (__flags), NULL)
|
|
|
|
/*
|
|
* To whitelist a single field for copying to/from usercopy, use this
|
|
* macro instead for KMEM_CACHE() above.
|
|
*/
|
|
#define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \
|
|
kmem_cache_create_usercopy(#__struct, \
|
|
sizeof(struct __struct), \
|
|
__alignof__(struct __struct), (__flags), \
|
|
offsetof(struct __struct, __field), \
|
|
sizeof_field(struct __struct, __field), NULL)
|
|
|
|
/*
|
|
* Common kmalloc functions provided by all allocators
|
|
*/
|
|
void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __alloc_size(2);
|
|
void kfree(const void *objp);
|
|
void kfree_sensitive(const void *objp);
|
|
size_t __ksize(const void *objp);
|
|
size_t ksize(const void *objp);
|
|
#ifdef CONFIG_PRINTK
|
|
bool kmem_valid_obj(void *object);
|
|
void kmem_dump_obj(void *object);
|
|
#endif
|
|
|
|
/*
|
|
* Some archs want to perform DMA into kmalloc caches and need a guaranteed
|
|
* alignment larger than the alignment of a 64-bit integer.
|
|
* Setting ARCH_KMALLOC_MINALIGN in arch headers allows that.
|
|
*/
|
|
#if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8
|
|
#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN
|
|
#define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN
|
|
#define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN)
|
|
#else
|
|
#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long)
|
|
#endif
|
|
|
|
/*
|
|
* Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment.
|
|
* Intended for arches that get misalignment faults even for 64 bit integer
|
|
* aligned buffers.
|
|
*/
|
|
#ifndef ARCH_SLAB_MINALIGN
|
|
#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
|
|
#endif
|
|
|
|
/*
|
|
* kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned
|
|
* pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN
|
|
* aligned pointers.
|
|
*/
|
|
#define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN)
|
|
#define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN)
|
|
#define __assume_page_alignment __assume_aligned(PAGE_SIZE)
|
|
|
|
/*
|
|
* Kmalloc array related definitions
|
|
*/
|
|
|
|
#ifdef CONFIG_SLAB
|
|
/*
|
|
* The largest kmalloc size supported by the SLAB allocators is
|
|
* 32 megabyte (2^25) or the maximum allocatable page order if that is
|
|
* less than 32 MB.
|
|
*
|
|
* WARNING: Its not easy to increase this value since the allocators have
|
|
* to do various tricks to work around compiler limitations in order to
|
|
* ensure proper constant folding.
|
|
*/
|
|
#define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \
|
|
(MAX_ORDER + PAGE_SHIFT - 1) : 25)
|
|
#define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH
|
|
#ifndef KMALLOC_SHIFT_LOW
|
|
#define KMALLOC_SHIFT_LOW 5
|
|
#endif
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLUB
|
|
/*
|
|
* SLUB directly allocates requests fitting in to an order-1 page
|
|
* (PAGE_SIZE*2). Larger requests are passed to the page allocator.
|
|
*/
|
|
#define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1)
|
|
#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1)
|
|
#ifndef KMALLOC_SHIFT_LOW
|
|
#define KMALLOC_SHIFT_LOW 3
|
|
#endif
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLOB
|
|
/*
|
|
* SLOB passes all requests larger than one page to the page allocator.
|
|
* No kmalloc array is necessary since objects of different sizes can
|
|
* be allocated from the same page.
|
|
*/
|
|
#define KMALLOC_SHIFT_HIGH PAGE_SHIFT
|
|
#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1)
|
|
#ifndef KMALLOC_SHIFT_LOW
|
|
#define KMALLOC_SHIFT_LOW 3
|
|
#endif
|
|
#endif
|
|
|
|
/* Maximum allocatable size */
|
|
#define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX)
|
|
/* Maximum size for which we actually use a slab cache */
|
|
#define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH)
|
|
/* Maximum order allocatable via the slab allocator */
|
|
#define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT)
|
|
|
|
/*
|
|
* Kmalloc subsystem.
|
|
*/
|
|
#ifndef KMALLOC_MIN_SIZE
|
|
#define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW)
|
|
#endif
|
|
|
|
/*
|
|
* This restriction comes from byte sized index implementation.
|
|
* Page size is normally 2^12 bytes and, in this case, if we want to use
|
|
* byte sized index which can represent 2^8 entries, the size of the object
|
|
* should be equal or greater to 2^12 / 2^8 = 2^4 = 16.
|
|
* If minimum size of kmalloc is less than 16, we use it as minimum object
|
|
* size and give up to use byte sized index.
|
|
*/
|
|
#define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \
|
|
(KMALLOC_MIN_SIZE) : 16)
|
|
|
|
/*
|
|
* Whenever changing this, take care of that kmalloc_type() and
|
|
* create_kmalloc_caches() still work as intended.
|
|
*
|
|
* KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP
|
|
* is for accounted but unreclaimable and non-dma objects. All the other
|
|
* kmem caches can have both accounted and unaccounted objects.
|
|
*/
|
|
enum kmalloc_cache_type {
|
|
KMALLOC_NORMAL = 0,
|
|
#ifndef CONFIG_ZONE_DMA
|
|
KMALLOC_DMA = KMALLOC_NORMAL,
|
|
#endif
|
|
#ifndef CONFIG_MEMCG_KMEM
|
|
KMALLOC_CGROUP = KMALLOC_NORMAL,
|
|
#else
|
|
KMALLOC_CGROUP,
|
|
#endif
|
|
KMALLOC_RECLAIM,
|
|
#ifdef CONFIG_ZONE_DMA
|
|
KMALLOC_DMA,
|
|
#endif
|
|
NR_KMALLOC_TYPES
|
|
};
|
|
|
|
#ifndef CONFIG_SLOB
|
|
extern struct kmem_cache *
|
|
kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1];
|
|
|
|
/*
|
|
* Define gfp bits that should not be set for KMALLOC_NORMAL.
|
|
*/
|
|
#define KMALLOC_NOT_NORMAL_BITS \
|
|
(__GFP_RECLAIMABLE | \
|
|
(IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \
|
|
(IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0))
|
|
|
|
static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags)
|
|
{
|
|
/*
|
|
* The most common case is KMALLOC_NORMAL, so test for it
|
|
* with a single branch for all the relevant flags.
|
|
*/
|
|
if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0))
|
|
return KMALLOC_NORMAL;
|
|
|
|
/*
|
|
* At least one of the flags has to be set. Their priorities in
|
|
* decreasing order are:
|
|
* 1) __GFP_DMA
|
|
* 2) __GFP_RECLAIMABLE
|
|
* 3) __GFP_ACCOUNT
|
|
*/
|
|
if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA))
|
|
return KMALLOC_DMA;
|
|
if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || (flags & __GFP_RECLAIMABLE))
|
|
return KMALLOC_RECLAIM;
|
|
else
|
|
return KMALLOC_CGROUP;
|
|
}
|
|
|
|
/*
|
|
* Figure out which kmalloc slab an allocation of a certain size
|
|
* belongs to.
|
|
* 0 = zero alloc
|
|
* 1 = 65 .. 96 bytes
|
|
* 2 = 129 .. 192 bytes
|
|
* n = 2^(n-1)+1 .. 2^n
|
|
*
|
|
* Note: __kmalloc_index() is compile-time optimized, and not runtime optimized;
|
|
* typical usage is via kmalloc_index() and therefore evaluated at compile-time.
|
|
* Callers where !size_is_constant should only be test modules, where runtime
|
|
* overheads of __kmalloc_index() can be tolerated. Also see kmalloc_slab().
|
|
*/
|
|
static __always_inline unsigned int __kmalloc_index(size_t size,
|
|
bool size_is_constant)
|
|
{
|
|
if (!size)
|
|
return 0;
|
|
|
|
if (size <= KMALLOC_MIN_SIZE)
|
|
return KMALLOC_SHIFT_LOW;
|
|
|
|
if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96)
|
|
return 1;
|
|
if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192)
|
|
return 2;
|
|
if (size <= 8) return 3;
|
|
if (size <= 16) return 4;
|
|
if (size <= 32) return 5;
|
|
if (size <= 64) return 6;
|
|
if (size <= 128) return 7;
|
|
if (size <= 256) return 8;
|
|
if (size <= 512) return 9;
|
|
if (size <= 1024) return 10;
|
|
if (size <= 2 * 1024) return 11;
|
|
if (size <= 4 * 1024) return 12;
|
|
if (size <= 8 * 1024) return 13;
|
|
if (size <= 16 * 1024) return 14;
|
|
if (size <= 32 * 1024) return 15;
|
|
if (size <= 64 * 1024) return 16;
|
|
if (size <= 128 * 1024) return 17;
|
|
if (size <= 256 * 1024) return 18;
|
|
if (size <= 512 * 1024) return 19;
|
|
if (size <= 1024 * 1024) return 20;
|
|
if (size <= 2 * 1024 * 1024) return 21;
|
|
if (size <= 4 * 1024 * 1024) return 22;
|
|
if (size <= 8 * 1024 * 1024) return 23;
|
|
if (size <= 16 * 1024 * 1024) return 24;
|
|
if (size <= 32 * 1024 * 1024) return 25;
|
|
|
|
if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant)
|
|
BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()");
|
|
else
|
|
BUG();
|
|
|
|
/* Will never be reached. Needed because the compiler may complain */
|
|
return -1;
|
|
}
|
|
#define kmalloc_index(s) __kmalloc_index(s, true)
|
|
#endif /* !CONFIG_SLOB */
|
|
|
|
void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1);
|
|
void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc;
|
|
void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
|
|
gfp_t gfpflags) __assume_slab_alignment __malloc;
|
|
void kmem_cache_free(struct kmem_cache *s, void *objp);
|
|
|
|
/*
|
|
* Bulk allocation and freeing operations. These are accelerated in an
|
|
* allocator specific way to avoid taking locks repeatedly or building
|
|
* metadata structures unnecessarily.
|
|
*
|
|
* Note that interrupts must be enabled when calling these functions.
|
|
*/
|
|
void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p);
|
|
int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p);
|
|
|
|
/*
|
|
* Caller must not use kfree_bulk() on memory not originally allocated
|
|
* by kmalloc(), because the SLOB allocator cannot handle this.
|
|
*/
|
|
static __always_inline void kfree_bulk(size_t size, void **p)
|
|
{
|
|
kmem_cache_free_bulk(NULL, size, p);
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA
|
|
void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment
|
|
__alloc_size(1);
|
|
void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment
|
|
__malloc;
|
|
#else
|
|
static __always_inline __alloc_size(1) void *__kmalloc_node(size_t size, gfp_t flags, int node)
|
|
{
|
|
return __kmalloc(size, flags);
|
|
}
|
|
|
|
static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node)
|
|
{
|
|
return kmem_cache_alloc(s, flags);
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_TRACING
|
|
extern void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size)
|
|
__assume_slab_alignment __alloc_size(3);
|
|
|
|
#ifdef CONFIG_NUMA
|
|
extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags,
|
|
int node, size_t size) __assume_slab_alignment
|
|
__alloc_size(4);
|
|
#else
|
|
static __always_inline __alloc_size(4) void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
|
|
gfp_t gfpflags, int node, size_t size)
|
|
{
|
|
return kmem_cache_alloc_trace(s, gfpflags, size);
|
|
}
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
#else /* CONFIG_TRACING */
|
|
static __always_inline __alloc_size(3) void *kmem_cache_alloc_trace(struct kmem_cache *s,
|
|
gfp_t flags, size_t size)
|
|
{
|
|
void *ret = kmem_cache_alloc(s, flags);
|
|
|
|
ret = kasan_kmalloc(s, ret, size, flags);
|
|
return ret;
|
|
}
|
|
|
|
static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags,
|
|
int node, size_t size)
|
|
{
|
|
void *ret = kmem_cache_alloc_node(s, gfpflags, node);
|
|
|
|
ret = kasan_kmalloc(s, ret, size, gfpflags);
|
|
return ret;
|
|
}
|
|
#endif /* CONFIG_TRACING */
|
|
|
|
extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment
|
|
__alloc_size(1);
|
|
|
|
#ifdef CONFIG_TRACING
|
|
extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
|
|
__assume_page_alignment __alloc_size(1);
|
|
#else
|
|
static __always_inline __alloc_size(1) void *kmalloc_order_trace(size_t size, gfp_t flags,
|
|
unsigned int order)
|
|
{
|
|
return kmalloc_order(size, flags, order);
|
|
}
|
|
#endif
|
|
|
|
static __always_inline __alloc_size(1) void *kmalloc_large(size_t size, gfp_t flags)
|
|
{
|
|
unsigned int order = get_order(size);
|
|
return kmalloc_order_trace(size, flags, order);
|
|
}
|
|
|
|
/**
|
|
* kmalloc - allocate memory
|
|
* @size: how many bytes of memory are required.
|
|
* @flags: the type of memory to allocate.
|
|
*
|
|
* kmalloc is the normal method of allocating memory
|
|
* for objects smaller than page size in the kernel.
|
|
*
|
|
* The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN
|
|
* bytes. For @size of power of two bytes, the alignment is also guaranteed
|
|
* to be at least to the size.
|
|
*
|
|
* The @flags argument may be one of the GFP flags defined at
|
|
* include/linux/gfp.h and described at
|
|
* :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>`
|
|
*
|
|
* The recommended usage of the @flags is described at
|
|
* :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>`
|
|
*
|
|
* Below is a brief outline of the most useful GFP flags
|
|
*
|
|
* %GFP_KERNEL
|
|
* Allocate normal kernel ram. May sleep.
|
|
*
|
|
* %GFP_NOWAIT
|
|
* Allocation will not sleep.
|
|
*
|
|
* %GFP_ATOMIC
|
|
* Allocation will not sleep. May use emergency pools.
|
|
*
|
|
* %GFP_HIGHUSER
|
|
* Allocate memory from high memory on behalf of user.
|
|
*
|
|
* Also it is possible to set different flags by OR'ing
|
|
* in one or more of the following additional @flags:
|
|
*
|
|
* %__GFP_HIGH
|
|
* This allocation has high priority and may use emergency pools.
|
|
*
|
|
* %__GFP_NOFAIL
|
|
* Indicate that this allocation is in no way allowed to fail
|
|
* (think twice before using).
|
|
*
|
|
* %__GFP_NORETRY
|
|
* If memory is not immediately available,
|
|
* then give up at once.
|
|
*
|
|
* %__GFP_NOWARN
|
|
* If allocation fails, don't issue any warnings.
|
|
*
|
|
* %__GFP_RETRY_MAYFAIL
|
|
* Try really hard to succeed the allocation but fail
|
|
* eventually.
|
|
*/
|
|
static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags)
|
|
{
|
|
if (__builtin_constant_p(size)) {
|
|
#ifndef CONFIG_SLOB
|
|
unsigned int index;
|
|
#endif
|
|
if (size > KMALLOC_MAX_CACHE_SIZE)
|
|
return kmalloc_large(size, flags);
|
|
#ifndef CONFIG_SLOB
|
|
index = kmalloc_index(size);
|
|
|
|
if (!index)
|
|
return ZERO_SIZE_PTR;
|
|
|
|
return kmem_cache_alloc_trace(
|
|
kmalloc_caches[kmalloc_type(flags)][index],
|
|
flags, size);
|
|
#endif
|
|
}
|
|
return __kmalloc(size, flags);
|
|
}
|
|
|
|
static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node)
|
|
{
|
|
#ifndef CONFIG_SLOB
|
|
if (__builtin_constant_p(size) &&
|
|
size <= KMALLOC_MAX_CACHE_SIZE) {
|
|
unsigned int i = kmalloc_index(size);
|
|
|
|
if (!i)
|
|
return ZERO_SIZE_PTR;
|
|
|
|
return kmem_cache_alloc_node_trace(
|
|
kmalloc_caches[kmalloc_type(flags)][i],
|
|
flags, node, size);
|
|
}
|
|
#endif
|
|
return __kmalloc_node(size, flags, node);
|
|
}
|
|
|
|
/**
|
|
* kmalloc_array - allocate memory for an array.
|
|
* @n: number of elements.
|
|
* @size: element size.
|
|
* @flags: the type of memory to allocate (see kmalloc).
|
|
*/
|
|
static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_t flags)
|
|
{
|
|
size_t bytes;
|
|
|
|
if (unlikely(check_mul_overflow(n, size, &bytes)))
|
|
return NULL;
|
|
if (__builtin_constant_p(n) && __builtin_constant_p(size))
|
|
return kmalloc(bytes, flags);
|
|
return __kmalloc(bytes, flags);
|
|
}
|
|
|
|
/**
|
|
* krealloc_array - reallocate memory for an array.
|
|
* @p: pointer to the memory chunk to reallocate
|
|
* @new_n: new number of elements to alloc
|
|
* @new_size: new size of a single member of the array
|
|
* @flags: the type of memory to allocate (see kmalloc)
|
|
*/
|
|
static inline __alloc_size(2, 3) void * __must_check krealloc_array(void *p,
|
|
size_t new_n,
|
|
size_t new_size,
|
|
gfp_t flags)
|
|
{
|
|
size_t bytes;
|
|
|
|
if (unlikely(check_mul_overflow(new_n, new_size, &bytes)))
|
|
return NULL;
|
|
|
|
return krealloc(p, bytes, flags);
|
|
}
|
|
|
|
/**
|
|
* kcalloc - allocate memory for an array. The memory is set to zero.
|
|
* @n: number of elements.
|
|
* @size: element size.
|
|
* @flags: the type of memory to allocate (see kmalloc).
|
|
*/
|
|
static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flags)
|
|
{
|
|
return kmalloc_array(n, size, flags | __GFP_ZERO);
|
|
}
|
|
|
|
/*
|
|
* kmalloc_track_caller is a special version of kmalloc that records the
|
|
* calling function of the routine calling it for slab leak tracking instead
|
|
* of just the calling function (confusing, eh?).
|
|
* It's useful when the call to kmalloc comes from a widely-used standard
|
|
* allocator where we care about the real place the memory allocation
|
|
* request comes from.
|
|
*/
|
|
extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller);
|
|
#define kmalloc_track_caller(size, flags) \
|
|
__kmalloc_track_caller(size, flags, _RET_IP_)
|
|
|
|
static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags,
|
|
int node)
|
|
{
|
|
size_t bytes;
|
|
|
|
if (unlikely(check_mul_overflow(n, size, &bytes)))
|
|
return NULL;
|
|
if (__builtin_constant_p(n) && __builtin_constant_p(size))
|
|
return kmalloc_node(bytes, flags, node);
|
|
return __kmalloc_node(bytes, flags, node);
|
|
}
|
|
|
|
static inline __alloc_size(1, 2) void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node)
|
|
{
|
|
return kmalloc_array_node(n, size, flags | __GFP_ZERO, node);
|
|
}
|
|
|
|
|
|
#ifdef CONFIG_NUMA
|
|
extern void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node,
|
|
unsigned long caller) __alloc_size(1);
|
|
#define kmalloc_node_track_caller(size, flags, node) \
|
|
__kmalloc_node_track_caller(size, flags, node, \
|
|
_RET_IP_)
|
|
|
|
#else /* CONFIG_NUMA */
|
|
|
|
#define kmalloc_node_track_caller(size, flags, node) \
|
|
kmalloc_track_caller(size, flags)
|
|
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
/*
|
|
* Shortcuts
|
|
*/
|
|
static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags)
|
|
{
|
|
return kmem_cache_alloc(k, flags | __GFP_ZERO);
|
|
}
|
|
|
|
/**
|
|
* kzalloc - allocate memory. The memory is set to zero.
|
|
* @size: how many bytes of memory are required.
|
|
* @flags: the type of memory to allocate (see kmalloc).
|
|
*/
|
|
static inline __alloc_size(1) void *kzalloc(size_t size, gfp_t flags)
|
|
{
|
|
return kmalloc(size, flags | __GFP_ZERO);
|
|
}
|
|
|
|
/**
|
|
* kzalloc_node - allocate zeroed memory from a particular memory node.
|
|
* @size: how many bytes of memory are required.
|
|
* @flags: the type of memory to allocate (see kmalloc).
|
|
* @node: memory node from which to allocate
|
|
*/
|
|
static inline __alloc_size(1) void *kzalloc_node(size_t size, gfp_t flags, int node)
|
|
{
|
|
return kmalloc_node(size, flags | __GFP_ZERO, node);
|
|
}
|
|
|
|
extern void *kvmalloc_node(size_t size, gfp_t flags, int node) __alloc_size(1);
|
|
static inline __alloc_size(1) void *kvmalloc(size_t size, gfp_t flags)
|
|
{
|
|
return kvmalloc_node(size, flags, NUMA_NO_NODE);
|
|
}
|
|
static inline __alloc_size(1) void *kvzalloc_node(size_t size, gfp_t flags, int node)
|
|
{
|
|
return kvmalloc_node(size, flags | __GFP_ZERO, node);
|
|
}
|
|
static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags)
|
|
{
|
|
return kvmalloc(size, flags | __GFP_ZERO);
|
|
}
|
|
|
|
static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags)
|
|
{
|
|
size_t bytes;
|
|
|
|
if (unlikely(check_mul_overflow(n, size, &bytes)))
|
|
return NULL;
|
|
|
|
return kvmalloc(bytes, flags);
|
|
}
|
|
|
|
static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t flags)
|
|
{
|
|
return kvmalloc_array(n, size, flags | __GFP_ZERO);
|
|
}
|
|
|
|
extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
|
|
__alloc_size(3);
|
|
extern void kvfree(const void *addr);
|
|
extern void kvfree_sensitive(const void *addr, size_t len);
|
|
|
|
unsigned int kmem_cache_size(struct kmem_cache *s);
|
|
void __init kmem_cache_init_late(void);
|
|
|
|
#if defined(CONFIG_SMP) && defined(CONFIG_SLAB)
|
|
int slab_prepare_cpu(unsigned int cpu);
|
|
int slab_dead_cpu(unsigned int cpu);
|
|
#else
|
|
#define slab_prepare_cpu NULL
|
|
#define slab_dead_cpu NULL
|
|
#endif
|
|
|
|
#endif /* _LINUX_SLAB_H */
|