mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-24 01:41:39 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
Core: - support "prefer busy polling" NAPI operation mode, where we defer softirq for some time expecting applications to periodically busy poll - AF_XDP: improve efficiency by more batching and hindering the adjacency cache prefetcher - af_packet: make packet_fanout.arr size configurable up to 64K - tcp: optimize TCP zero copy receive in presence of partial or unaligned reads making zero copy a performance win for much smaller messages - XDP: add bulk APIs for returning / freeing frames - sched: support fragmenting IP packets as they come out of conntrack - net: allow virtual netdevs to forward UDP L4 and fraglist GSO skbs BPF: - BPF switch from crude rlimit-based to memcg-based memory accounting - BPF type format information for kernel modules and related tracing enhancements - BPF implement task local storage for BPF LSM - allow the FENTRY/FEXIT/RAW_TP tracing programs to use bpf_sk_storage Protocols: - mptcp: improve multiple xmit streams support, memory accounting and many smaller improvements - TLS: support CHACHA20-POLY1305 cipher - seg6: add support for SRv6 End.DT4/DT6 behavior - sctp: Implement RFC 6951: UDP Encapsulation of SCTP - ppp_generic: add ability to bridge channels directly - bridge: Connectivity Fault Management (CFM) support as is defined in IEEE 802.1Q section 12.14. Drivers: - mlx5: make use of the new auxiliary bus to organize the driver internals - mlx5: more accurate port TX timestamping support - mlxsw: - improve the efficiency of offloaded next hop updates by using the new nexthop object API - support blackhole nexthops - support IEEE 802.1ad (Q-in-Q) bridging - rtw88: major bluetooth co-existance improvements - iwlwifi: support new 6 GHz frequency band - ath11k: Fast Initial Link Setup (FILS) - mt7915: dual band concurrent (DBDC) support - net: ipa: add basic support for IPA v4.5 Refactor: - a few pieces of in_interrupt() cleanup work from Sebastian Andrzej Siewior - phy: add support for shared interrupts; get rid of multiple driver APIs and have the drivers write a full IRQ handler, slight growth of driver code should be compensated by the simpler API which also allows shared IRQs - add common code for handling netdev per-cpu counters - move TX packet re-allocation from Ethernet switch tag drivers to a central place - improve efficiency and rename nla_strlcpy - number of W=1 warning cleanups as we now catch those in a patchwork build bot Old code removal: - wan: delete the DLCI / SDLA drivers - wimax: move to staging - wifi: remove old WDS wifi bridging support Signed-off-by: Jakub Kicinski <kuba@kernel.org> -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEE6jPA+I1ugmIBA4hXMUZtbf5SIrsFAl/YXmUACgkQMUZtbf5S IrvSQBAAgOrt4EFopEvVqlTHZbqI45IEqgtXS+YWmlgnjZCgshyMj8q1yK1zzane qYxr/NNJ9kV3FdtaynmmHPgEEEfR5kJ/D3B2BsxYDkaDDrD0vbNsBGw+L+/Gbhxl N/5l/9FjLyLY1D+EErknuwR5XGuQ6BSDVaKQMhYOiK2hgdnAAI4hszo8Chf6wdD0 XDBslQ7vpD/05r+eMj0IkS5dSAoGOIFXUxhJ5dqrDbRHiKsIyWqA3PLbYemfAhxI s2XckjfmSgGE3FKL8PSFu+EcfHbJQQjLcULJUnqgVcdwEEtRuE9ggEi52nZRXMWM 4e8sQJAR9Fx7pZy0G1xfS149j6iPU5LjRlU9TNSpVABz14Vvvo3gEL6gyIdsz+xh hMN7UBdp0FEaP028CXoIYpaBesvQqj0BSndmee8qsYAtN6j+QKcM2AOSr7JN1uMH C/86EDoGAATiEQIVWJvnX5MPmlAoblyLA+RuVhmxkIBx2InGXkFmWqRkXT5l4jtk LVl8/TArR4alSQqLXictXCjYlCm9j5N4zFFtEVasSYi7/ZoPfgRNWT+lJ2R8Y+Zv +htzGaFuyj6RJTVeFQMrkl3whAtBamo2a0kwg45NnxmmXcspN6kJX1WOIy82+MhD Yht7uplSs7MGKA78q/CDU0XBeGjpABUvmplUQBIfrR/jKLW2730= =GXs1 -----END PGP SIGNATURE----- Merge tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - support "prefer busy polling" NAPI operation mode, where we defer softirq for some time expecting applications to periodically busy poll - AF_XDP: improve efficiency by more batching and hindering the adjacency cache prefetcher - af_packet: make packet_fanout.arr size configurable up to 64K - tcp: optimize TCP zero copy receive in presence of partial or unaligned reads making zero copy a performance win for much smaller messages - XDP: add bulk APIs for returning / freeing frames - sched: support fragmenting IP packets as they come out of conntrack - net: allow virtual netdevs to forward UDP L4 and fraglist GSO skbs BPF: - BPF switch from crude rlimit-based to memcg-based memory accounting - BPF type format information for kernel modules and related tracing enhancements - BPF implement task local storage for BPF LSM - allow the FENTRY/FEXIT/RAW_TP tracing programs to use bpf_sk_storage Protocols: - mptcp: improve multiple xmit streams support, memory accounting and many smaller improvements - TLS: support CHACHA20-POLY1305 cipher - seg6: add support for SRv6 End.DT4/DT6 behavior - sctp: Implement RFC 6951: UDP Encapsulation of SCTP - ppp_generic: add ability to bridge channels directly - bridge: Connectivity Fault Management (CFM) support as is defined in IEEE 802.1Q section 12.14. Drivers: - mlx5: make use of the new auxiliary bus to organize the driver internals - mlx5: more accurate port TX timestamping support - mlxsw: - improve the efficiency of offloaded next hop updates by using the new nexthop object API - support blackhole nexthops - support IEEE 802.1ad (Q-in-Q) bridging - rtw88: major bluetooth co-existance improvements - iwlwifi: support new 6 GHz frequency band - ath11k: Fast Initial Link Setup (FILS) - mt7915: dual band concurrent (DBDC) support - net: ipa: add basic support for IPA v4.5 Refactor: - a few pieces of in_interrupt() cleanup work from Sebastian Andrzej Siewior - phy: add support for shared interrupts; get rid of multiple driver APIs and have the drivers write a full IRQ handler, slight growth of driver code should be compensated by the simpler API which also allows shared IRQs - add common code for handling netdev per-cpu counters - move TX packet re-allocation from Ethernet switch tag drivers to a central place - improve efficiency and rename nla_strlcpy - number of W=1 warning cleanups as we now catch those in a patchwork build bot Old code removal: - wan: delete the DLCI / SDLA drivers - wimax: move to staging - wifi: remove old WDS wifi bridging support" * tag 'net-next-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1922 commits) net: hns3: fix expression that is currently always true net: fix proc_fs init handling in af_packet and tls nfc: pn533: convert comma to semicolon af_vsock: Assign the vsock transport considering the vsock address flags af_vsock: Set VMADDR_FLAG_TO_HOST flag on the receive path vsock_addr: Check for supported flag values vm_sockets: Add VMADDR_FLAG_TO_HOST vsock flag vm_sockets: Add flags field in the vsock address data structure net: Disable NETIF_F_HW_TLS_TX when HW_CSUM is disabled tcp: Add logic to check for SYN w/ data in tcp_simple_retransmit net: mscc: ocelot: install MAC addresses in .ndo_set_rx_mode from process context nfc: s3fwrn5: Release the nfc firmware net: vxget: clean up sparse warnings mlxsw: spectrum_router: Use eXtended mezzanine to offload IPv4 router mlxsw: spectrum: Set KVH XLT cache mode for Spectrum2/3 mlxsw: spectrum_router_xm: Introduce basic XM cache flushing mlxsw: reg: Add Router LPM Cache Enable Register mlxsw: reg: Add Router LPM Cache ML Delete Register mlxsw: spectrum_router_xm: Implement L-value tracking for M-index mlxsw: reg: Add XM Router M Table Register ...
618 lines
16 KiB
C
618 lines
16 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef MM_SLAB_H
|
|
#define MM_SLAB_H
|
|
/*
|
|
* Internal slab definitions
|
|
*/
|
|
|
|
#ifdef CONFIG_SLOB
|
|
/*
|
|
* Common fields provided in kmem_cache by all slab allocators
|
|
* This struct is either used directly by the allocator (SLOB)
|
|
* or the allocator must include definitions for all fields
|
|
* provided in kmem_cache_common in their definition of kmem_cache.
|
|
*
|
|
* Once we can do anonymous structs (C11 standard) we could put a
|
|
* anonymous struct definition in these allocators so that the
|
|
* separate allocations in the kmem_cache structure of SLAB and
|
|
* SLUB is no longer needed.
|
|
*/
|
|
struct kmem_cache {
|
|
unsigned int object_size;/* The original size of the object */
|
|
unsigned int size; /* The aligned/padded/added on size */
|
|
unsigned int align; /* Alignment as calculated */
|
|
slab_flags_t flags; /* Active flags on the slab */
|
|
unsigned int useroffset;/* Usercopy region offset */
|
|
unsigned int usersize; /* Usercopy region size */
|
|
const char *name; /* Slab name for sysfs */
|
|
int refcount; /* Use counter */
|
|
void (*ctor)(void *); /* Called on object slot creation */
|
|
struct list_head list; /* List of all slab caches on the system */
|
|
};
|
|
|
|
#endif /* CONFIG_SLOB */
|
|
|
|
#ifdef CONFIG_SLAB
|
|
#include <linux/slab_def.h>
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLUB
|
|
#include <linux/slub_def.h>
|
|
#endif
|
|
|
|
#include <linux/memcontrol.h>
|
|
#include <linux/fault-inject.h>
|
|
#include <linux/kasan.h>
|
|
#include <linux/kmemleak.h>
|
|
#include <linux/random.h>
|
|
#include <linux/sched/mm.h>
|
|
|
|
/*
|
|
* State of the slab allocator.
|
|
*
|
|
* This is used to describe the states of the allocator during bootup.
|
|
* Allocators use this to gradually bootstrap themselves. Most allocators
|
|
* have the problem that the structures used for managing slab caches are
|
|
* allocated from slab caches themselves.
|
|
*/
|
|
enum slab_state {
|
|
DOWN, /* No slab functionality yet */
|
|
PARTIAL, /* SLUB: kmem_cache_node available */
|
|
PARTIAL_NODE, /* SLAB: kmalloc size for node struct available */
|
|
UP, /* Slab caches usable but not all extras yet */
|
|
FULL /* Everything is working */
|
|
};
|
|
|
|
extern enum slab_state slab_state;
|
|
|
|
/* The slab cache mutex protects the management structures during changes */
|
|
extern struct mutex slab_mutex;
|
|
|
|
/* The list of all slab caches on the system */
|
|
extern struct list_head slab_caches;
|
|
|
|
/* The slab cache that manages slab cache information */
|
|
extern struct kmem_cache *kmem_cache;
|
|
|
|
/* A table of kmalloc cache names and sizes */
|
|
extern const struct kmalloc_info_struct {
|
|
const char *name[NR_KMALLOC_TYPES];
|
|
unsigned int size;
|
|
} kmalloc_info[];
|
|
|
|
#ifndef CONFIG_SLOB
|
|
/* Kmalloc array related functions */
|
|
void setup_kmalloc_cache_index_table(void);
|
|
void create_kmalloc_caches(slab_flags_t);
|
|
|
|
/* Find the kmalloc slab corresponding for a certain size */
|
|
struct kmem_cache *kmalloc_slab(size_t, gfp_t);
|
|
#endif
|
|
|
|
gfp_t kmalloc_fix_flags(gfp_t flags);
|
|
|
|
/* Functions provided by the slab allocators */
|
|
int __kmem_cache_create(struct kmem_cache *, slab_flags_t flags);
|
|
|
|
struct kmem_cache *create_kmalloc_cache(const char *name, unsigned int size,
|
|
slab_flags_t flags, unsigned int useroffset,
|
|
unsigned int usersize);
|
|
extern void create_boot_cache(struct kmem_cache *, const char *name,
|
|
unsigned int size, slab_flags_t flags,
|
|
unsigned int useroffset, unsigned int usersize);
|
|
|
|
int slab_unmergeable(struct kmem_cache *s);
|
|
struct kmem_cache *find_mergeable(unsigned size, unsigned align,
|
|
slab_flags_t flags, const char *name, void (*ctor)(void *));
|
|
#ifndef CONFIG_SLOB
|
|
struct kmem_cache *
|
|
__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
|
|
slab_flags_t flags, void (*ctor)(void *));
|
|
|
|
slab_flags_t kmem_cache_flags(unsigned int object_size,
|
|
slab_flags_t flags, const char *name,
|
|
void (*ctor)(void *));
|
|
#else
|
|
static inline struct kmem_cache *
|
|
__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
|
|
slab_flags_t flags, void (*ctor)(void *))
|
|
{ return NULL; }
|
|
|
|
static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
|
|
slab_flags_t flags, const char *name,
|
|
void (*ctor)(void *))
|
|
{
|
|
return flags;
|
|
}
|
|
#endif
|
|
|
|
|
|
/* Legal flag mask for kmem_cache_create(), for various configurations */
|
|
#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \
|
|
SLAB_CACHE_DMA32 | SLAB_PANIC | \
|
|
SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS )
|
|
|
|
#if defined(CONFIG_DEBUG_SLAB)
|
|
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
|
|
#elif defined(CONFIG_SLUB_DEBUG)
|
|
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
|
|
SLAB_TRACE | SLAB_CONSISTENCY_CHECKS)
|
|
#else
|
|
#define SLAB_DEBUG_FLAGS (0)
|
|
#endif
|
|
|
|
#if defined(CONFIG_SLAB)
|
|
#define SLAB_CACHE_FLAGS (SLAB_MEM_SPREAD | SLAB_NOLEAKTRACE | \
|
|
SLAB_RECLAIM_ACCOUNT | SLAB_TEMPORARY | \
|
|
SLAB_ACCOUNT)
|
|
#elif defined(CONFIG_SLUB)
|
|
#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \
|
|
SLAB_TEMPORARY | SLAB_ACCOUNT)
|
|
#else
|
|
#define SLAB_CACHE_FLAGS (0)
|
|
#endif
|
|
|
|
/* Common flags available with current configuration */
|
|
#define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS)
|
|
|
|
/* Common flags permitted for kmem_cache_create */
|
|
#define SLAB_FLAGS_PERMITTED (SLAB_CORE_FLAGS | \
|
|
SLAB_RED_ZONE | \
|
|
SLAB_POISON | \
|
|
SLAB_STORE_USER | \
|
|
SLAB_TRACE | \
|
|
SLAB_CONSISTENCY_CHECKS | \
|
|
SLAB_MEM_SPREAD | \
|
|
SLAB_NOLEAKTRACE | \
|
|
SLAB_RECLAIM_ACCOUNT | \
|
|
SLAB_TEMPORARY | \
|
|
SLAB_ACCOUNT)
|
|
|
|
bool __kmem_cache_empty(struct kmem_cache *);
|
|
int __kmem_cache_shutdown(struct kmem_cache *);
|
|
void __kmem_cache_release(struct kmem_cache *);
|
|
int __kmem_cache_shrink(struct kmem_cache *);
|
|
void slab_kmem_cache_release(struct kmem_cache *);
|
|
|
|
struct seq_file;
|
|
struct file;
|
|
|
|
struct slabinfo {
|
|
unsigned long active_objs;
|
|
unsigned long num_objs;
|
|
unsigned long active_slabs;
|
|
unsigned long num_slabs;
|
|
unsigned long shared_avail;
|
|
unsigned int limit;
|
|
unsigned int batchcount;
|
|
unsigned int shared;
|
|
unsigned int objects_per_slab;
|
|
unsigned int cache_order;
|
|
};
|
|
|
|
void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo);
|
|
void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
|
|
ssize_t slabinfo_write(struct file *file, const char __user *buffer,
|
|
size_t count, loff_t *ppos);
|
|
|
|
/*
|
|
* Generic implementation of bulk operations
|
|
* These are useful for situations in which the allocator cannot
|
|
* perform optimizations. In that case segments of the object listed
|
|
* may be allocated or freed using these operations.
|
|
*/
|
|
void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
|
|
int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
|
|
|
|
static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
|
|
{
|
|
return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
|
|
NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
|
|
}
|
|
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
#ifdef CONFIG_SLUB_DEBUG_ON
|
|
DECLARE_STATIC_KEY_TRUE(slub_debug_enabled);
|
|
#else
|
|
DECLARE_STATIC_KEY_FALSE(slub_debug_enabled);
|
|
#endif
|
|
extern void print_tracking(struct kmem_cache *s, void *object);
|
|
#else
|
|
static inline void print_tracking(struct kmem_cache *s, void *object)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Returns true if any of the specified slub_debug flags is enabled for the
|
|
* cache. Use only for flags parsed by setup_slub_debug() as it also enables
|
|
* the static key.
|
|
*/
|
|
static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags)
|
|
{
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
|
|
if (static_branch_unlikely(&slub_debug_enabled))
|
|
return s->flags & flags;
|
|
#endif
|
|
return false;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
|
|
gfp_t gfp);
|
|
|
|
static inline void memcg_free_page_obj_cgroups(struct page *page)
|
|
{
|
|
kfree(page_objcgs(page));
|
|
page->memcg_data = 0;
|
|
}
|
|
|
|
static inline size_t obj_full_size(struct kmem_cache *s)
|
|
{
|
|
/*
|
|
* For each accounted object there is an extra space which is used
|
|
* to store obj_cgroup membership. Charge it too.
|
|
*/
|
|
return s->size + sizeof(struct obj_cgroup *);
|
|
}
|
|
|
|
/*
|
|
* Returns false if the allocation should fail.
|
|
*/
|
|
static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup **objcgp,
|
|
size_t objects, gfp_t flags)
|
|
{
|
|
struct obj_cgroup *objcg;
|
|
|
|
if (!memcg_kmem_enabled())
|
|
return true;
|
|
|
|
if (!(flags & __GFP_ACCOUNT) && !(s->flags & SLAB_ACCOUNT))
|
|
return true;
|
|
|
|
objcg = get_obj_cgroup_from_current();
|
|
if (!objcg)
|
|
return true;
|
|
|
|
if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) {
|
|
obj_cgroup_put(objcg);
|
|
return false;
|
|
}
|
|
|
|
*objcgp = objcg;
|
|
return true;
|
|
}
|
|
|
|
static inline void mod_objcg_state(struct obj_cgroup *objcg,
|
|
struct pglist_data *pgdat,
|
|
enum node_stat_item idx, int nr)
|
|
{
|
|
struct mem_cgroup *memcg;
|
|
struct lruvec *lruvec;
|
|
|
|
rcu_read_lock();
|
|
memcg = obj_cgroup_memcg(objcg);
|
|
lruvec = mem_cgroup_lruvec(memcg, pgdat);
|
|
mod_memcg_lruvec_state(lruvec, idx, nr);
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup *objcg,
|
|
gfp_t flags, size_t size,
|
|
void **p)
|
|
{
|
|
struct page *page;
|
|
unsigned long off;
|
|
size_t i;
|
|
|
|
if (!memcg_kmem_enabled() || !objcg)
|
|
return;
|
|
|
|
flags &= ~__GFP_ACCOUNT;
|
|
for (i = 0; i < size; i++) {
|
|
if (likely(p[i])) {
|
|
page = virt_to_head_page(p[i]);
|
|
|
|
if (!page_objcgs(page) &&
|
|
memcg_alloc_page_obj_cgroups(page, s, flags)) {
|
|
obj_cgroup_uncharge(objcg, obj_full_size(s));
|
|
continue;
|
|
}
|
|
|
|
off = obj_to_index(s, page, p[i]);
|
|
obj_cgroup_get(objcg);
|
|
page_objcgs(page)[off] = objcg;
|
|
mod_objcg_state(objcg, page_pgdat(page),
|
|
cache_vmstat_idx(s), obj_full_size(s));
|
|
} else {
|
|
obj_cgroup_uncharge(objcg, obj_full_size(s));
|
|
}
|
|
}
|
|
obj_cgroup_put(objcg);
|
|
}
|
|
|
|
static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
|
|
void **p, int objects)
|
|
{
|
|
struct kmem_cache *s;
|
|
struct obj_cgroup **objcgs;
|
|
struct obj_cgroup *objcg;
|
|
struct page *page;
|
|
unsigned int off;
|
|
int i;
|
|
|
|
if (!memcg_kmem_enabled())
|
|
return;
|
|
|
|
for (i = 0; i < objects; i++) {
|
|
if (unlikely(!p[i]))
|
|
continue;
|
|
|
|
page = virt_to_head_page(p[i]);
|
|
objcgs = page_objcgs(page);
|
|
if (!objcgs)
|
|
continue;
|
|
|
|
if (!s_orig)
|
|
s = page->slab_cache;
|
|
else
|
|
s = s_orig;
|
|
|
|
off = obj_to_index(s, page, p[i]);
|
|
objcg = objcgs[off];
|
|
if (!objcg)
|
|
continue;
|
|
|
|
objcgs[off] = NULL;
|
|
obj_cgroup_uncharge(objcg, obj_full_size(s));
|
|
mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
|
|
-obj_full_size(s));
|
|
obj_cgroup_put(objcg);
|
|
}
|
|
}
|
|
|
|
#else /* CONFIG_MEMCG_KMEM */
|
|
static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int memcg_alloc_page_obj_cgroups(struct page *page,
|
|
struct kmem_cache *s, gfp_t gfp)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void memcg_free_page_obj_cgroups(struct page *page)
|
|
{
|
|
}
|
|
|
|
static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup **objcgp,
|
|
size_t objects, gfp_t flags)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup *objcg,
|
|
gfp_t flags, size_t size,
|
|
void **p)
|
|
{
|
|
}
|
|
|
|
static inline void memcg_slab_free_hook(struct kmem_cache *s,
|
|
void **p, int objects)
|
|
{
|
|
}
|
|
#endif /* CONFIG_MEMCG_KMEM */
|
|
|
|
static inline struct kmem_cache *virt_to_cache(const void *obj)
|
|
{
|
|
struct page *page;
|
|
|
|
page = virt_to_head_page(obj);
|
|
if (WARN_ONCE(!PageSlab(page), "%s: Object is not a Slab page!\n",
|
|
__func__))
|
|
return NULL;
|
|
return page->slab_cache;
|
|
}
|
|
|
|
static __always_inline void account_slab_page(struct page *page, int order,
|
|
struct kmem_cache *s)
|
|
{
|
|
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
|
|
PAGE_SIZE << order);
|
|
}
|
|
|
|
static __always_inline void unaccount_slab_page(struct page *page, int order,
|
|
struct kmem_cache *s)
|
|
{
|
|
if (memcg_kmem_enabled())
|
|
memcg_free_page_obj_cgroups(page);
|
|
|
|
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
|
|
-(PAGE_SIZE << order));
|
|
}
|
|
|
|
static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
|
|
{
|
|
struct kmem_cache *cachep;
|
|
|
|
if (!IS_ENABLED(CONFIG_SLAB_FREELIST_HARDENED) &&
|
|
!kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS))
|
|
return s;
|
|
|
|
cachep = virt_to_cache(x);
|
|
if (WARN(cachep && cachep != s,
|
|
"%s: Wrong slab cache. %s but object is from %s\n",
|
|
__func__, s->name, cachep->name))
|
|
print_tracking(cachep, x);
|
|
return cachep;
|
|
}
|
|
|
|
static inline size_t slab_ksize(const struct kmem_cache *s)
|
|
{
|
|
#ifndef CONFIG_SLUB
|
|
return s->object_size;
|
|
|
|
#else /* CONFIG_SLUB */
|
|
# ifdef CONFIG_SLUB_DEBUG
|
|
/*
|
|
* Debugging requires use of the padding between object
|
|
* and whatever may come after it.
|
|
*/
|
|
if (s->flags & (SLAB_RED_ZONE | SLAB_POISON))
|
|
return s->object_size;
|
|
# endif
|
|
if (s->flags & SLAB_KASAN)
|
|
return s->object_size;
|
|
/*
|
|
* If we have the need to store the freelist pointer
|
|
* back there or track user information then we can
|
|
* only use the space before that information.
|
|
*/
|
|
if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER))
|
|
return s->inuse;
|
|
/*
|
|
* Else we can use all the padding etc for the allocation
|
|
*/
|
|
return s->size;
|
|
#endif
|
|
}
|
|
|
|
static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup **objcgp,
|
|
size_t size, gfp_t flags)
|
|
{
|
|
flags &= gfp_allowed_mask;
|
|
|
|
might_alloc(flags);
|
|
|
|
if (should_failslab(s, flags))
|
|
return NULL;
|
|
|
|
if (!memcg_slab_pre_alloc_hook(s, objcgp, size, flags))
|
|
return NULL;
|
|
|
|
return s;
|
|
}
|
|
|
|
static inline void slab_post_alloc_hook(struct kmem_cache *s,
|
|
struct obj_cgroup *objcg,
|
|
gfp_t flags, size_t size, void **p)
|
|
{
|
|
size_t i;
|
|
|
|
flags &= gfp_allowed_mask;
|
|
for (i = 0; i < size; i++) {
|
|
p[i] = kasan_slab_alloc(s, p[i], flags);
|
|
/* As p[i] might get tagged, call kmemleak hook after KASAN. */
|
|
kmemleak_alloc_recursive(p[i], s->object_size, 1,
|
|
s->flags, flags);
|
|
}
|
|
|
|
memcg_slab_post_alloc_hook(s, objcg, flags, size, p);
|
|
}
|
|
|
|
#ifndef CONFIG_SLOB
|
|
/*
|
|
* The slab lists for all objects.
|
|
*/
|
|
struct kmem_cache_node {
|
|
spinlock_t list_lock;
|
|
|
|
#ifdef CONFIG_SLAB
|
|
struct list_head slabs_partial; /* partial list first, better asm code */
|
|
struct list_head slabs_full;
|
|
struct list_head slabs_free;
|
|
unsigned long total_slabs; /* length of all slab lists */
|
|
unsigned long free_slabs; /* length of free slab list only */
|
|
unsigned long free_objects;
|
|
unsigned int free_limit;
|
|
unsigned int colour_next; /* Per-node cache coloring */
|
|
struct array_cache *shared; /* shared per node */
|
|
struct alien_cache **alien; /* on other nodes */
|
|
unsigned long next_reap; /* updated without locking */
|
|
int free_touched; /* updated without locking */
|
|
#endif
|
|
|
|
#ifdef CONFIG_SLUB
|
|
unsigned long nr_partial;
|
|
struct list_head partial;
|
|
#ifdef CONFIG_SLUB_DEBUG
|
|
atomic_long_t nr_slabs;
|
|
atomic_long_t total_objects;
|
|
struct list_head full;
|
|
#endif
|
|
#endif
|
|
|
|
};
|
|
|
|
static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
|
|
{
|
|
return s->node[node];
|
|
}
|
|
|
|
/*
|
|
* Iterator over all nodes. The body will be executed for each node that has
|
|
* a kmem_cache_node structure allocated (which is true for all online nodes)
|
|
*/
|
|
#define for_each_kmem_cache_node(__s, __node, __n) \
|
|
for (__node = 0; __node < nr_node_ids; __node++) \
|
|
if ((__n = get_node(__s, __node)))
|
|
|
|
#endif
|
|
|
|
void *slab_start(struct seq_file *m, loff_t *pos);
|
|
void *slab_next(struct seq_file *m, void *p, loff_t *pos);
|
|
void slab_stop(struct seq_file *m, void *p);
|
|
int memcg_slab_show(struct seq_file *m, void *p);
|
|
|
|
#if defined(CONFIG_SLAB) || defined(CONFIG_SLUB_DEBUG)
|
|
void dump_unreclaimable_slab(void);
|
|
#else
|
|
static inline void dump_unreclaimable_slab(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr);
|
|
|
|
#ifdef CONFIG_SLAB_FREELIST_RANDOM
|
|
int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count,
|
|
gfp_t gfp);
|
|
void cache_random_seq_destroy(struct kmem_cache *cachep);
|
|
#else
|
|
static inline int cache_random_seq_create(struct kmem_cache *cachep,
|
|
unsigned int count, gfp_t gfp)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { }
|
|
#endif /* CONFIG_SLAB_FREELIST_RANDOM */
|
|
|
|
static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c)
|
|
{
|
|
if (static_branch_unlikely(&init_on_alloc)) {
|
|
if (c->ctor)
|
|
return false;
|
|
if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))
|
|
return flags & __GFP_ZERO;
|
|
return true;
|
|
}
|
|
return flags & __GFP_ZERO;
|
|
}
|
|
|
|
static inline bool slab_want_init_on_free(struct kmem_cache *c)
|
|
{
|
|
if (static_branch_unlikely(&init_on_free))
|
|
return !(c->ctor ||
|
|
(c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)));
|
|
return false;
|
|
}
|
|
|
|
#endif /* MM_SLAB_H */
|