2022-09-03 05:10:43 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
|
|
|
/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/llist.h>
|
|
|
|
#include <linux/bpf.h>
|
|
|
|
#include <linux/irq_work.h>
|
|
|
|
#include <linux/bpf_mem_alloc.h>
|
|
|
|
#include <linux/memcontrol.h>
|
|
|
|
#include <asm/local.h>
|
|
|
|
|
|
|
|
/* Any context (including NMI) BPF specific memory allocator.
|
|
|
|
*
|
|
|
|
* Tracing BPF programs can attach to kprobe and fentry. Hence they
|
|
|
|
* run in unknown context where calling plain kmalloc() might not be safe.
|
|
|
|
*
|
|
|
|
* Front-end kmalloc() with per-cpu per-bucket cache of free elements.
|
|
|
|
* Refill this cache asynchronously from irq_work.
|
|
|
|
*
|
|
|
|
* CPU_0 buckets
|
|
|
|
* 16 32 64 96 128 196 256 512 1024 2048 4096
|
|
|
|
* ...
|
|
|
|
* CPU_N buckets
|
|
|
|
* 16 32 64 96 128 196 256 512 1024 2048 4096
|
|
|
|
*
|
|
|
|
* The buckets are prefilled at the start.
|
|
|
|
* BPF programs always run with migration disabled.
|
|
|
|
* It's safe to allocate from cache of the current cpu with irqs disabled.
|
|
|
|
* Free-ing is always done into bucket of the current cpu as well.
|
|
|
|
* irq_work trims extra free elements from buckets with kfree
|
|
|
|
* and refills them with kmalloc, so global kmalloc logic takes care
|
|
|
|
* of freeing objects allocated by one cpu and freed on another.
|
|
|
|
*
|
|
|
|
* Every allocated objected is padded with extra 8 bytes that contains
|
|
|
|
* struct llist_node.
|
|
|
|
*/
|
|
|
|
#define LLIST_NODE_SZ sizeof(struct llist_node)
|
|
|
|
|
|
|
|
/* similar to kmalloc, but sizeof == 8 bucket is gone */
|
|
|
|
static u8 size_index[24] __ro_after_init = {
|
|
|
|
3, /* 8 */
|
|
|
|
3, /* 16 */
|
|
|
|
4, /* 24 */
|
|
|
|
4, /* 32 */
|
|
|
|
5, /* 40 */
|
|
|
|
5, /* 48 */
|
|
|
|
5, /* 56 */
|
|
|
|
5, /* 64 */
|
|
|
|
1, /* 72 */
|
|
|
|
1, /* 80 */
|
|
|
|
1, /* 88 */
|
|
|
|
1, /* 96 */
|
|
|
|
6, /* 104 */
|
|
|
|
6, /* 112 */
|
|
|
|
6, /* 120 */
|
|
|
|
6, /* 128 */
|
|
|
|
2, /* 136 */
|
|
|
|
2, /* 144 */
|
|
|
|
2, /* 152 */
|
|
|
|
2, /* 160 */
|
|
|
|
2, /* 168 */
|
|
|
|
2, /* 176 */
|
|
|
|
2, /* 184 */
|
|
|
|
2 /* 192 */
|
|
|
|
};
|
|
|
|
|
|
|
|
static int bpf_mem_cache_idx(size_t size)
|
|
|
|
{
|
|
|
|
if (!size || size > 4096)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
if (size <= 192)
|
|
|
|
return size_index[(size - 1) / 8] - 1;
|
|
|
|
|
|
|
|
return fls(size - 1) - 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define NUM_CACHES 11
|
|
|
|
|
|
|
|
struct bpf_mem_cache {
|
|
|
|
/* per-cpu list of free objects of size 'unit_size'.
|
|
|
|
* All accesses are done with interrupts disabled and 'active' counter
|
|
|
|
* protection with __llist_add() and __llist_del_first().
|
|
|
|
*/
|
|
|
|
struct llist_head free_llist;
|
|
|
|
local_t active;
|
|
|
|
|
|
|
|
/* Operations on the free_list from unit_alloc/unit_free/bpf_mem_refill
|
|
|
|
* are sequenced by per-cpu 'active' counter. But unit_free() cannot
|
|
|
|
* fail. When 'active' is busy the unit_free() will add an object to
|
|
|
|
* free_llist_extra.
|
|
|
|
*/
|
|
|
|
struct llist_head free_llist_extra;
|
|
|
|
|
|
|
|
struct irq_work refill_work;
|
|
|
|
struct obj_cgroup *objcg;
|
|
|
|
int unit_size;
|
|
|
|
/* count of objects in free_llist */
|
|
|
|
int free_cnt;
|
2022-09-03 05:10:50 +08:00
|
|
|
int low_watermark, high_watermark, batch;
|
2022-09-03 05:10:57 +08:00
|
|
|
int percpu_size;
|
2022-09-03 05:10:51 +08:00
|
|
|
|
|
|
|
struct rcu_head rcu;
|
|
|
|
struct llist_head free_by_rcu;
|
|
|
|
struct llist_head waiting_for_gp;
|
|
|
|
atomic_t call_rcu_in_progress;
|
2022-09-03 05:10:43 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
struct bpf_mem_caches {
|
|
|
|
struct bpf_mem_cache cache[NUM_CACHES];
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct llist_node notrace *__llist_del_first(struct llist_head *head)
|
|
|
|
{
|
|
|
|
struct llist_node *entry, *next;
|
|
|
|
|
|
|
|
entry = head->first;
|
|
|
|
if (!entry)
|
|
|
|
return NULL;
|
|
|
|
next = entry->next;
|
|
|
|
head->first = next;
|
|
|
|
return entry;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void *__alloc(struct bpf_mem_cache *c, int node)
|
|
|
|
{
|
|
|
|
/* Allocate, but don't deplete atomic reserves that typical
|
|
|
|
* GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc
|
|
|
|
* will allocate from the current numa node which is what we
|
|
|
|
* want here.
|
|
|
|
*/
|
|
|
|
gfp_t flags = GFP_NOWAIT | __GFP_NOWARN | __GFP_ACCOUNT;
|
|
|
|
|
2022-09-03 05:10:57 +08:00
|
|
|
if (c->percpu_size) {
|
|
|
|
void **obj = kmalloc_node(c->percpu_size, flags, node);
|
2022-09-03 05:10:52 +08:00
|
|
|
void *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags);
|
|
|
|
|
|
|
|
if (!obj || !pptr) {
|
|
|
|
free_percpu(pptr);
|
|
|
|
kfree(obj);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
obj[1] = pptr;
|
|
|
|
return obj;
|
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:43 +08:00
|
|
|
return kmalloc_node(c->unit_size, flags, node);
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
|
|
if (c->objcg)
|
|
|
|
return get_mem_cgroup_from_objcg(c->objcg);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
|
|
return root_mem_cgroup;
|
|
|
|
#else
|
|
|
|
return NULL;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Mostly runs from irq_work except __init phase. */
|
|
|
|
static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node)
|
|
|
|
{
|
|
|
|
struct mem_cgroup *memcg = NULL, *old_memcg;
|
|
|
|
unsigned long flags;
|
|
|
|
void *obj;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
memcg = get_memcg(c);
|
|
|
|
old_memcg = set_active_memcg(memcg);
|
|
|
|
for (i = 0; i < cnt; i++) {
|
|
|
|
obj = __alloc(c, node);
|
|
|
|
if (!obj)
|
|
|
|
break;
|
|
|
|
if (IS_ENABLED(CONFIG_PREEMPT_RT))
|
|
|
|
/* In RT irq_work runs in per-cpu kthread, so disable
|
|
|
|
* interrupts to avoid preemption and interrupts and
|
|
|
|
* reduce the chance of bpf prog executing on this cpu
|
|
|
|
* when active counter is busy.
|
|
|
|
*/
|
|
|
|
local_irq_save(flags);
|
|
|
|
/* alloc_bulk runs from irq_work which will not preempt a bpf
|
|
|
|
* program that does unit_alloc/unit_free since IRQs are
|
|
|
|
* disabled there. There is no race to increment 'active'
|
|
|
|
* counter. It protects free_llist from corruption in case NMI
|
|
|
|
* bpf prog preempted this loop.
|
|
|
|
*/
|
|
|
|
WARN_ON_ONCE(local_inc_return(&c->active) != 1);
|
|
|
|
__llist_add(obj, &c->free_llist);
|
|
|
|
c->free_cnt++;
|
|
|
|
local_dec(&c->active);
|
|
|
|
if (IS_ENABLED(CONFIG_PREEMPT_RT))
|
|
|
|
local_irq_restore(flags);
|
|
|
|
}
|
|
|
|
set_active_memcg(old_memcg);
|
|
|
|
mem_cgroup_put(memcg);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void free_one(struct bpf_mem_cache *c, void *obj)
|
|
|
|
{
|
2022-09-03 05:10:57 +08:00
|
|
|
if (c->percpu_size) {
|
2022-09-03 05:10:52 +08:00
|
|
|
free_percpu(((void **)obj)[1]);
|
2022-09-03 05:10:57 +08:00
|
|
|
kfree(obj);
|
2022-09-03 05:10:52 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:57 +08:00
|
|
|
kfree(obj);
|
2022-09-03 05:10:43 +08:00
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:51 +08:00
|
|
|
static void __free_rcu(struct rcu_head *head)
|
|
|
|
{
|
|
|
|
struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
|
|
|
|
struct llist_node *llnode = llist_del_all(&c->waiting_for_gp);
|
|
|
|
struct llist_node *pos, *t;
|
|
|
|
|
|
|
|
llist_for_each_safe(pos, t, llnode)
|
|
|
|
free_one(c, pos);
|
|
|
|
atomic_set(&c->call_rcu_in_progress, 0);
|
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:55 +08:00
|
|
|
static void __free_rcu_tasks_trace(struct rcu_head *head)
|
|
|
|
{
|
|
|
|
struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu);
|
|
|
|
|
|
|
|
call_rcu(&c->rcu, __free_rcu);
|
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:51 +08:00
|
|
|
static void enque_to_free(struct bpf_mem_cache *c, void *obj)
|
|
|
|
{
|
|
|
|
struct llist_node *llnode = obj;
|
|
|
|
|
|
|
|
/* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work.
|
|
|
|
* Nothing races to add to free_by_rcu list.
|
|
|
|
*/
|
|
|
|
__llist_add(llnode, &c->free_by_rcu);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void do_call_rcu(struct bpf_mem_cache *c)
|
|
|
|
{
|
|
|
|
struct llist_node *llnode, *t;
|
|
|
|
|
|
|
|
if (atomic_xchg(&c->call_rcu_in_progress, 1))
|
|
|
|
return;
|
|
|
|
|
|
|
|
WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp));
|
|
|
|
llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
|
|
|
|
/* There is no concurrent __llist_add(waiting_for_gp) access.
|
|
|
|
* It doesn't race with llist_del_all either.
|
|
|
|
* But there could be two concurrent llist_del_all(waiting_for_gp):
|
|
|
|
* from __free_rcu() and from drain_mem_cache().
|
|
|
|
*/
|
|
|
|
__llist_add(llnode, &c->waiting_for_gp);
|
2022-09-03 05:10:55 +08:00
|
|
|
/* Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
|
|
|
|
* Then use call_rcu() to wait for normal progs to finish
|
|
|
|
* and finally do free_one() on each element.
|
|
|
|
*/
|
|
|
|
call_rcu_tasks_trace(&c->rcu, __free_rcu_tasks_trace);
|
2022-09-03 05:10:51 +08:00
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:43 +08:00
|
|
|
static void free_bulk(struct bpf_mem_cache *c)
|
|
|
|
{
|
|
|
|
struct llist_node *llnode, *t;
|
|
|
|
unsigned long flags;
|
|
|
|
int cnt;
|
|
|
|
|
|
|
|
do {
|
|
|
|
if (IS_ENABLED(CONFIG_PREEMPT_RT))
|
|
|
|
local_irq_save(flags);
|
|
|
|
WARN_ON_ONCE(local_inc_return(&c->active) != 1);
|
|
|
|
llnode = __llist_del_first(&c->free_llist);
|
|
|
|
if (llnode)
|
|
|
|
cnt = --c->free_cnt;
|
|
|
|
else
|
|
|
|
cnt = 0;
|
|
|
|
local_dec(&c->active);
|
|
|
|
if (IS_ENABLED(CONFIG_PREEMPT_RT))
|
|
|
|
local_irq_restore(flags);
|
2022-09-03 05:10:51 +08:00
|
|
|
enque_to_free(c, llnode);
|
2022-09-03 05:10:50 +08:00
|
|
|
} while (cnt > (c->high_watermark + c->low_watermark) / 2);
|
2022-09-03 05:10:43 +08:00
|
|
|
|
|
|
|
/* and drain free_llist_extra */
|
|
|
|
llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
|
2022-09-03 05:10:51 +08:00
|
|
|
enque_to_free(c, llnode);
|
|
|
|
do_call_rcu(c);
|
2022-09-03 05:10:43 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void bpf_mem_refill(struct irq_work *work)
|
|
|
|
{
|
|
|
|
struct bpf_mem_cache *c = container_of(work, struct bpf_mem_cache, refill_work);
|
|
|
|
int cnt;
|
|
|
|
|
|
|
|
/* Racy access to free_cnt. It doesn't need to be 100% accurate */
|
|
|
|
cnt = c->free_cnt;
|
2022-09-03 05:10:50 +08:00
|
|
|
if (cnt < c->low_watermark)
|
2022-09-03 05:10:43 +08:00
|
|
|
/* irq_work runs on this cpu and kmalloc will allocate
|
|
|
|
* from the current numa node which is what we want here.
|
|
|
|
*/
|
2022-09-03 05:10:50 +08:00
|
|
|
alloc_bulk(c, c->batch, NUMA_NO_NODE);
|
|
|
|
else if (cnt > c->high_watermark)
|
2022-09-03 05:10:43 +08:00
|
|
|
free_bulk(c);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void notrace irq_work_raise(struct bpf_mem_cache *c)
|
|
|
|
{
|
|
|
|
irq_work_queue(&c->refill_work);
|
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:50 +08:00
|
|
|
/* For typical bpf map case that uses bpf_mem_cache_alloc and single bucket
|
|
|
|
* the freelist cache will be elem_size * 64 (or less) on each cpu.
|
|
|
|
*
|
|
|
|
* For bpf programs that don't have statically known allocation sizes and
|
|
|
|
* assuming (low_mark + high_mark) / 2 as an average number of elements per
|
|
|
|
* bucket and all buckets are used the total amount of memory in freelists
|
|
|
|
* on each cpu will be:
|
|
|
|
* 64*16 + 64*32 + 64*64 + 64*96 + 64*128 + 64*196 + 64*256 + 32*512 + 16*1024 + 8*2048 + 4*4096
|
|
|
|
* == ~ 116 Kbyte using below heuristic.
|
|
|
|
* Initialized, but unused bpf allocator (not bpf map specific one) will
|
|
|
|
* consume ~ 11 Kbyte per cpu.
|
|
|
|
* Typical case will be between 11K and 116K closer to 11K.
|
|
|
|
* bpf progs can and should share bpf_mem_cache when possible.
|
|
|
|
*/
|
|
|
|
|
2022-09-03 05:10:43 +08:00
|
|
|
static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
|
|
|
|
{
|
|
|
|
init_irq_work(&c->refill_work, bpf_mem_refill);
|
2022-09-03 05:10:50 +08:00
|
|
|
if (c->unit_size <= 256) {
|
|
|
|
c->low_watermark = 32;
|
|
|
|
c->high_watermark = 96;
|
|
|
|
} else {
|
|
|
|
/* When page_size == 4k, order-0 cache will have low_mark == 2
|
|
|
|
* and high_mark == 6 with batch alloc of 3 individual pages at
|
|
|
|
* a time.
|
|
|
|
* 8k allocs and above low == 1, high == 3, batch == 1.
|
|
|
|
*/
|
|
|
|
c->low_watermark = max(32 * 256 / c->unit_size, 1);
|
|
|
|
c->high_watermark = max(96 * 256 / c->unit_size, 3);
|
|
|
|
}
|
|
|
|
c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1);
|
|
|
|
|
2022-09-03 05:10:43 +08:00
|
|
|
/* To avoid consuming memory assume that 1st run of bpf
|
|
|
|
* prog won't be doing more than 4 map_update_elem from
|
|
|
|
* irq disabled region
|
|
|
|
*/
|
|
|
|
alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu));
|
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:57 +08:00
|
|
|
/* When size != 0 bpf_mem_cache for each cpu.
|
2022-09-03 05:10:43 +08:00
|
|
|
* This is typical bpf hash map use case when all elements have equal size.
|
|
|
|
*
|
|
|
|
* When size == 0 allocate 11 bpf_mem_cache-s for each cpu, then rely on
|
|
|
|
* kmalloc/kfree. Max allocation size is 4096 in this case.
|
|
|
|
* This is bpf_dynptr and bpf_kptr use case.
|
|
|
|
*/
|
2022-09-03 05:10:52 +08:00
|
|
|
int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
|
2022-09-03 05:10:43 +08:00
|
|
|
{
|
|
|
|
static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
|
|
|
|
struct bpf_mem_caches *cc, __percpu *pcc;
|
|
|
|
struct bpf_mem_cache *c, __percpu *pc;
|
|
|
|
struct obj_cgroup *objcg = NULL;
|
2022-09-03 05:10:57 +08:00
|
|
|
int cpu, i, unit_size, percpu_size = 0;
|
2022-09-03 05:10:43 +08:00
|
|
|
|
|
|
|
if (size) {
|
|
|
|
pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL);
|
|
|
|
if (!pc)
|
|
|
|
return -ENOMEM;
|
2022-09-03 05:10:52 +08:00
|
|
|
|
2022-09-03 05:10:57 +08:00
|
|
|
if (percpu)
|
2022-09-03 05:10:52 +08:00
|
|
|
/* room for llist_node and per-cpu pointer */
|
2022-09-03 05:10:57 +08:00
|
|
|
percpu_size = LLIST_NODE_SZ + sizeof(void *);
|
|
|
|
else
|
2022-09-03 05:10:52 +08:00
|
|
|
size += LLIST_NODE_SZ; /* room for llist_node */
|
2022-09-03 05:10:57 +08:00
|
|
|
unit_size = size;
|
2022-09-03 05:10:52 +08:00
|
|
|
|
2022-09-03 05:10:43 +08:00
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
|
|
objcg = get_obj_cgroup_from_current();
|
|
|
|
#endif
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
|
|
c = per_cpu_ptr(pc, cpu);
|
2022-09-03 05:10:52 +08:00
|
|
|
c->unit_size = unit_size;
|
2022-09-03 05:10:43 +08:00
|
|
|
c->objcg = objcg;
|
2022-09-03 05:10:57 +08:00
|
|
|
c->percpu_size = percpu_size;
|
2022-09-03 05:10:43 +08:00
|
|
|
prefill_mem_cache(c, cpu);
|
|
|
|
}
|
|
|
|
ma->cache = pc;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:52 +08:00
|
|
|
/* size == 0 && percpu is an invalid combination */
|
|
|
|
if (WARN_ON_ONCE(percpu))
|
|
|
|
return -EINVAL;
|
|
|
|
|
2022-09-03 05:10:43 +08:00
|
|
|
pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
|
|
|
|
if (!pcc)
|
|
|
|
return -ENOMEM;
|
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
|
|
objcg = get_obj_cgroup_from_current();
|
|
|
|
#endif
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
|
|
cc = per_cpu_ptr(pcc, cpu);
|
|
|
|
for (i = 0; i < NUM_CACHES; i++) {
|
|
|
|
c = &cc->cache[i];
|
|
|
|
c->unit_size = sizes[i];
|
|
|
|
c->objcg = objcg;
|
|
|
|
prefill_mem_cache(c, cpu);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
ma->caches = pcc;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void drain_mem_cache(struct bpf_mem_cache *c)
|
|
|
|
{
|
|
|
|
struct llist_node *llnode, *t;
|
|
|
|
|
2022-09-03 05:10:58 +08:00
|
|
|
/* No progs are using this bpf_mem_cache, but htab_map_free() called
|
|
|
|
* bpf_mem_cache_free() for all remaining elements and they can be in
|
|
|
|
* free_by_rcu or in waiting_for_gp lists, so drain those lists now.
|
2022-09-03 05:10:51 +08:00
|
|
|
*/
|
|
|
|
llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
|
|
|
|
free_one(c, llnode);
|
|
|
|
llist_for_each_safe(llnode, t, llist_del_all(&c->waiting_for_gp))
|
|
|
|
free_one(c, llnode);
|
2022-09-03 05:10:43 +08:00
|
|
|
llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist))
|
|
|
|
free_one(c, llnode);
|
|
|
|
llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
|
|
|
|
free_one(c, llnode);
|
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:58 +08:00
|
|
|
static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma)
|
|
|
|
{
|
|
|
|
free_percpu(ma->cache);
|
|
|
|
free_percpu(ma->caches);
|
|
|
|
ma->cache = NULL;
|
|
|
|
ma->caches = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void free_mem_alloc(struct bpf_mem_alloc *ma)
|
|
|
|
{
|
|
|
|
/* waiting_for_gp lists was drained, but __free_rcu might
|
|
|
|
* still execute. Wait for it now before we freeing percpu caches.
|
|
|
|
*/
|
|
|
|
rcu_barrier_tasks_trace();
|
|
|
|
rcu_barrier();
|
|
|
|
free_mem_alloc_no_barrier(ma);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void free_mem_alloc_deferred(struct work_struct *work)
|
|
|
|
{
|
|
|
|
struct bpf_mem_alloc *ma = container_of(work, struct bpf_mem_alloc, work);
|
|
|
|
|
|
|
|
free_mem_alloc(ma);
|
|
|
|
kfree(ma);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress)
|
|
|
|
{
|
|
|
|
struct bpf_mem_alloc *copy;
|
|
|
|
|
|
|
|
if (!rcu_in_progress) {
|
|
|
|
/* Fast path. No callbacks are pending, hence no need to do
|
|
|
|
* rcu_barrier-s.
|
|
|
|
*/
|
|
|
|
free_mem_alloc_no_barrier(ma);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
copy = kmalloc(sizeof(*ma), GFP_KERNEL);
|
|
|
|
if (!copy) {
|
|
|
|
/* Slow path with inline barrier-s */
|
|
|
|
free_mem_alloc(ma);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Defer barriers into worker to let the rest of map memory to be freed */
|
|
|
|
copy->cache = ma->cache;
|
|
|
|
ma->cache = NULL;
|
|
|
|
copy->caches = ma->caches;
|
|
|
|
ma->caches = NULL;
|
|
|
|
INIT_WORK(©->work, free_mem_alloc_deferred);
|
|
|
|
queue_work(system_unbound_wq, ©->work);
|
|
|
|
}
|
|
|
|
|
2022-09-03 05:10:43 +08:00
|
|
|
void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
|
|
|
|
{
|
|
|
|
struct bpf_mem_caches *cc;
|
|
|
|
struct bpf_mem_cache *c;
|
2022-09-03 05:10:58 +08:00
|
|
|
int cpu, i, rcu_in_progress;
|
2022-09-03 05:10:43 +08:00
|
|
|
|
|
|
|
if (ma->cache) {
|
2022-09-03 05:10:58 +08:00
|
|
|
rcu_in_progress = 0;
|
2022-09-03 05:10:43 +08:00
|
|
|
for_each_possible_cpu(cpu) {
|
|
|
|
c = per_cpu_ptr(ma->cache, cpu);
|
|
|
|
drain_mem_cache(c);
|
2022-09-03 05:10:58 +08:00
|
|
|
rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
|
2022-09-03 05:10:43 +08:00
|
|
|
}
|
2022-09-03 05:10:57 +08:00
|
|
|
/* objcg is the same across cpus */
|
2022-09-03 05:10:43 +08:00
|
|
|
if (c->objcg)
|
|
|
|
obj_cgroup_put(c->objcg);
|
2022-09-03 05:10:58 +08:00
|
|
|
destroy_mem_alloc(ma, rcu_in_progress);
|
2022-09-03 05:10:43 +08:00
|
|
|
}
|
|
|
|
if (ma->caches) {
|
2022-09-03 05:10:58 +08:00
|
|
|
rcu_in_progress = 0;
|
2022-09-03 05:10:43 +08:00
|
|
|
for_each_possible_cpu(cpu) {
|
|
|
|
cc = per_cpu_ptr(ma->caches, cpu);
|
|
|
|
for (i = 0; i < NUM_CACHES; i++) {
|
|
|
|
c = &cc->cache[i];
|
|
|
|
drain_mem_cache(c);
|
2022-09-03 05:10:58 +08:00
|
|
|
rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
|
2022-09-03 05:10:43 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
if (c->objcg)
|
|
|
|
obj_cgroup_put(c->objcg);
|
2022-09-03 05:10:58 +08:00
|
|
|
destroy_mem_alloc(ma, rcu_in_progress);
|
2022-09-03 05:10:43 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* notrace is necessary here and in other functions to make sure
|
|
|
|
* bpf programs cannot attach to them and cause llist corruptions.
|
|
|
|
*/
|
|
|
|
static void notrace *unit_alloc(struct bpf_mem_cache *c)
|
|
|
|
{
|
|
|
|
struct llist_node *llnode = NULL;
|
|
|
|
unsigned long flags;
|
|
|
|
int cnt = 0;
|
|
|
|
|
|
|
|
/* Disable irqs to prevent the following race for majority of prog types:
|
|
|
|
* prog_A
|
|
|
|
* bpf_mem_alloc
|
|
|
|
* preemption or irq -> prog_B
|
|
|
|
* bpf_mem_alloc
|
|
|
|
*
|
|
|
|
* but prog_B could be a perf_event NMI prog.
|
|
|
|
* Use per-cpu 'active' counter to order free_list access between
|
|
|
|
* unit_alloc/unit_free/bpf_mem_refill.
|
|
|
|
*/
|
|
|
|
local_irq_save(flags);
|
|
|
|
if (local_inc_return(&c->active) == 1) {
|
|
|
|
llnode = __llist_del_first(&c->free_llist);
|
|
|
|
if (llnode)
|
|
|
|
cnt = --c->free_cnt;
|
|
|
|
}
|
|
|
|
local_dec(&c->active);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
|
|
|
|
WARN_ON(cnt < 0);
|
|
|
|
|
2022-09-03 05:10:50 +08:00
|
|
|
if (cnt < c->low_watermark)
|
2022-09-03 05:10:43 +08:00
|
|
|
irq_work_raise(c);
|
|
|
|
return llnode;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Though 'ptr' object could have been allocated on a different cpu
|
|
|
|
* add it to the free_llist of the current cpu.
|
|
|
|
* Let kfree() logic deal with it when it's later called from irq_work.
|
|
|
|
*/
|
|
|
|
static void notrace unit_free(struct bpf_mem_cache *c, void *ptr)
|
|
|
|
{
|
|
|
|
struct llist_node *llnode = ptr - LLIST_NODE_SZ;
|
|
|
|
unsigned long flags;
|
|
|
|
int cnt = 0;
|
|
|
|
|
|
|
|
BUILD_BUG_ON(LLIST_NODE_SZ > 8);
|
|
|
|
|
|
|
|
local_irq_save(flags);
|
|
|
|
if (local_inc_return(&c->active) == 1) {
|
|
|
|
__llist_add(llnode, &c->free_llist);
|
|
|
|
cnt = ++c->free_cnt;
|
|
|
|
} else {
|
|
|
|
/* unit_free() cannot fail. Therefore add an object to atomic
|
|
|
|
* llist. free_bulk() will drain it. Though free_llist_extra is
|
|
|
|
* a per-cpu list we have to use atomic llist_add here, since
|
|
|
|
* it also can be interrupted by bpf nmi prog that does another
|
|
|
|
* unit_free() into the same free_llist_extra.
|
|
|
|
*/
|
|
|
|
llist_add(llnode, &c->free_llist_extra);
|
|
|
|
}
|
|
|
|
local_dec(&c->active);
|
|
|
|
local_irq_restore(flags);
|
|
|
|
|
2022-09-03 05:10:50 +08:00
|
|
|
if (cnt > c->high_watermark)
|
2022-09-03 05:10:43 +08:00
|
|
|
/* free few objects from current cpu into global kmalloc pool */
|
|
|
|
irq_work_raise(c);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Called from BPF program or from sys_bpf syscall.
|
|
|
|
* In both cases migration is disabled.
|
|
|
|
*/
|
|
|
|
void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
|
|
|
|
{
|
|
|
|
int idx;
|
|
|
|
void *ret;
|
|
|
|
|
|
|
|
if (!size)
|
|
|
|
return ZERO_SIZE_PTR;
|
|
|
|
|
|
|
|
idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ);
|
|
|
|
if (idx < 0)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
ret = unit_alloc(this_cpu_ptr(ma->caches)->cache + idx);
|
|
|
|
return !ret ? NULL : ret + LLIST_NODE_SZ;
|
|
|
|
}
|
|
|
|
|
|
|
|
void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
|
|
|
|
{
|
|
|
|
int idx;
|
|
|
|
|
|
|
|
if (!ptr)
|
|
|
|
return;
|
|
|
|
|
2022-09-07 10:38:53 +08:00
|
|
|
idx = bpf_mem_cache_idx(ksize(ptr - LLIST_NODE_SZ));
|
2022-09-03 05:10:43 +08:00
|
|
|
if (idx < 0)
|
|
|
|
return;
|
|
|
|
|
|
|
|
unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr);
|
|
|
|
}
|
|
|
|
|
|
|
|
void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma)
|
|
|
|
{
|
|
|
|
void *ret;
|
|
|
|
|
|
|
|
ret = unit_alloc(this_cpu_ptr(ma->cache));
|
|
|
|
return !ret ? NULL : ret + LLIST_NODE_SZ;
|
|
|
|
}
|
|
|
|
|
|
|
|
void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr)
|
|
|
|
{
|
|
|
|
if (!ptr)
|
|
|
|
return;
|
|
|
|
|
|
|
|
unit_free(this_cpu_ptr(ma->cache), ptr);
|
|
|
|
}
|