linux/kernel/bpf/arraymap.c
Andrii Nakryiko fc9702273e bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY
Add ability to memory-map contents of BPF array map. This is extremely useful
for working with BPF global data from userspace programs. It allows to avoid
typical bpf_map_{lookup,update}_elem operations, improving both performance
and usability.

There had to be special considerations for map freezing, to avoid having
writable memory view into a frozen map. To solve this issue, map freezing and
mmap-ing is happening under mutex now:
  - if map is already frozen, no writable mapping is allowed;
  - if map has writable memory mappings active (accounted in map->writecnt),
    map freezing will keep failing with -EBUSY;
  - once number of writable memory mappings drops to zero, map freezing can be
    performed again.

Only non-per-CPU plain arrays are supported right now. Maps with spinlocks
can't be memory mapped either.

For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc()
to be mmap()'able. We also need to make sure that array data memory is
page-sized and page-aligned, so we over-allocate memory in such a way that
struct bpf_array is at the end of a single page of memory with array->value
being aligned with the start of the second page. On deallocation we need to
accomodate this memory arrangement to free vmalloc()'ed memory correctly.

One important consideration regarding how memory-mapping subsystem functions.
Memory-mapping subsystem provides few optional callbacks, among them open()
and close().  close() is called for each memory region that is unmapped, so
that users can decrease their reference counters and free up resources, if
necessary. open() is *almost* symmetrical: it's called for each memory region
that is being mapped, **except** the very first one. So bpf_map_mmap does
initial refcnt bump, while open() will do any extra ones after that. Thus
number of close() calls is equal to number of open() calls plus one more.

Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com
2019-11-18 11:41:59 +01:00

893 lines
23 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
* Copyright (c) 2016,2017 Facebook
*/
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/filter.h>
#include <linux/perf_event.h>
#include <uapi/linux/btf.h>
#include "map_in_map.h"
#define ARRAY_CREATE_FLAG_MASK \
(BPF_F_NUMA_NODE | BPF_F_MMAPABLE | BPF_F_ACCESS_MASK)
static void bpf_array_free_percpu(struct bpf_array *array)
{
int i;
for (i = 0; i < array->map.max_entries; i++) {
free_percpu(array->pptrs[i]);
cond_resched();
}
}
static int bpf_array_alloc_percpu(struct bpf_array *array)
{
void __percpu *ptr;
int i;
for (i = 0; i < array->map.max_entries; i++) {
ptr = __alloc_percpu_gfp(array->elem_size, 8,
GFP_USER | __GFP_NOWARN);
if (!ptr) {
bpf_array_free_percpu(array);
return -ENOMEM;
}
array->pptrs[i] = ptr;
cond_resched();
}
return 0;
}
/* Called from syscall */
int array_map_alloc_check(union bpf_attr *attr)
{
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
int numa_node = bpf_map_attr_numa_node(attr);
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
attr->value_size == 0 ||
attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
!bpf_map_flags_access_ok(attr->map_flags) ||
(percpu && numa_node != NUMA_NO_NODE))
return -EINVAL;
if (attr->map_type != BPF_MAP_TYPE_ARRAY &&
attr->map_flags & BPF_F_MMAPABLE)
return -EINVAL;
if (attr->value_size > KMALLOC_MAX_SIZE)
/* if value_size is bigger, the user space won't be able to
* access the elements.
*/
return -E2BIG;
return 0;
}
static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
int ret, numa_node = bpf_map_attr_numa_node(attr);
u32 elem_size, index_mask, max_entries;
bool unpriv = !capable(CAP_SYS_ADMIN);
u64 cost, array_size, mask64;
struct bpf_map_memory mem;
struct bpf_array *array;
elem_size = round_up(attr->value_size, 8);
max_entries = attr->max_entries;
/* On 32 bit archs roundup_pow_of_two() with max_entries that has
* upper most bit set in u32 space is undefined behavior due to
* resulting 1U << 32, so do it manually here in u64 space.
*/
mask64 = fls_long(max_entries - 1);
mask64 = 1ULL << mask64;
mask64 -= 1;
index_mask = mask64;
if (unpriv) {
/* round up array size to nearest power of 2,
* since cpu will speculate within index_mask limits
*/
max_entries = index_mask + 1;
/* Check for overflows. */
if (max_entries < attr->max_entries)
return ERR_PTR(-E2BIG);
}
array_size = sizeof(*array);
if (percpu) {
array_size += (u64) max_entries * sizeof(void *);
} else {
/* rely on vmalloc() to return page-aligned memory and
* ensure array->value is exactly page-aligned
*/
if (attr->map_flags & BPF_F_MMAPABLE) {
array_size = PAGE_ALIGN(array_size);
array_size += PAGE_ALIGN((u64) max_entries * elem_size);
} else {
array_size += (u64) max_entries * elem_size;
}
}
/* make sure there is no u32 overflow later in round_up() */
cost = array_size;
if (percpu)
cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
ret = bpf_map_charge_init(&mem, cost);
if (ret < 0)
return ERR_PTR(ret);
/* allocate all map elements and zero-initialize them */
if (attr->map_flags & BPF_F_MMAPABLE) {
void *data;
/* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */
data = bpf_map_area_mmapable_alloc(array_size, numa_node);
if (!data) {
bpf_map_charge_finish(&mem);
return ERR_PTR(-ENOMEM);
}
array = data + PAGE_ALIGN(sizeof(struct bpf_array))
- offsetof(struct bpf_array, value);
} else {
array = bpf_map_area_alloc(array_size, numa_node);
}
if (!array) {
bpf_map_charge_finish(&mem);
return ERR_PTR(-ENOMEM);
}
array->index_mask = index_mask;
array->map.unpriv_array = unpriv;
/* copy mandatory map attributes */
bpf_map_init_from_attr(&array->map, attr);
bpf_map_charge_move(&array->map.memory, &mem);
array->elem_size = elem_size;
if (percpu && bpf_array_alloc_percpu(array)) {
bpf_map_charge_finish(&array->map.memory);
bpf_map_area_free(array);
return ERR_PTR(-ENOMEM);
}
return &array->map;
}
/* Called from syscall or from eBPF program */
static void *array_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
if (unlikely(index >= array->map.max_entries))
return NULL;
return array->value + array->elem_size * (index & array->index_mask);
}
static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm,
u32 off)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
if (map->max_entries != 1)
return -ENOTSUPP;
if (off >= map->value_size)
return -EINVAL;
*imm = (unsigned long)array->value;
return 0;
}
static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm,
u32 *off)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u64 base = (unsigned long)array->value;
u64 range = array->elem_size;
if (map->max_entries != 1)
return -ENOTSUPP;
if (imm < base || imm >= base + range)
return -ENOENT;
*off = imm - base;
return 0;
}
/* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_insn *insn = insn_buf;
u32 elem_size = round_up(map->value_size, 8);
const int ret = BPF_REG_0;
const int map_ptr = BPF_REG_1;
const int index = BPF_REG_2;
*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
if (map->unpriv_array) {
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4);
*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
} else {
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3);
}
if (is_power_of_2(elem_size)) {
*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
} else {
*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
}
*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
*insn++ = BPF_MOV64_IMM(ret, 0);
return insn - insn_buf;
}
/* Called from eBPF program */
static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
if (unlikely(index >= array->map.max_entries))
return NULL;
return this_cpu_ptr(array->pptrs[index & array->index_mask]);
}
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
void __percpu *pptr;
int cpu, off = 0;
u32 size;
if (unlikely(index >= array->map.max_entries))
return -ENOENT;
/* per_cpu areas are zero-filled and bpf programs can only
* access 'value_size' of them, so copying rounded areas
* will not leak any kernel data
*/
size = round_up(map->value_size, 8);
rcu_read_lock();
pptr = array->pptrs[index & array->index_mask];
for_each_possible_cpu(cpu) {
bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size);
off += size;
}
rcu_read_unlock();
return 0;
}
/* Called from syscall */
static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = key ? *(u32 *)key : U32_MAX;
u32 *next = (u32 *)next_key;
if (index >= array->map.max_entries) {
*next = 0;
return 0;
}
if (index == array->map.max_entries - 1)
return -ENOENT;
*next = index + 1;
return 0;
}
/* Called from syscall or from eBPF program */
static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
char *val;
if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST))
/* unknown flags */
return -EINVAL;
if (unlikely(index >= array->map.max_entries))
/* all elements were pre-allocated, cannot insert a new one */
return -E2BIG;
if (unlikely(map_flags & BPF_NOEXIST))
/* all elements already exist */
return -EEXIST;
if (unlikely((map_flags & BPF_F_LOCK) &&
!map_value_has_spin_lock(map)))
return -EINVAL;
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]),
value, map->value_size);
} else {
val = array->value +
array->elem_size * (index & array->index_mask);
if (map_flags & BPF_F_LOCK)
copy_map_value_locked(map, val, value, false);
else
copy_map_value(map, val, value);
}
return 0;
}
int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
void __percpu *pptr;
int cpu, off = 0;
u32 size;
if (unlikely(map_flags > BPF_EXIST))
/* unknown flags */
return -EINVAL;
if (unlikely(index >= array->map.max_entries))
/* all elements were pre-allocated, cannot insert a new one */
return -E2BIG;
if (unlikely(map_flags == BPF_NOEXIST))
/* all elements already exist */
return -EEXIST;
/* the user space will provide round_up(value_size, 8) bytes that
* will be copied into per-cpu area. bpf programs can only access
* value_size of it. During lookup the same extra bytes will be
* returned or zeros which were zero-filled by percpu_alloc,
* so no kernel data leaks possible
*/
size = round_up(map->value_size, 8);
rcu_read_lock();
pptr = array->pptrs[index & array->index_mask];
for_each_possible_cpu(cpu) {
bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size);
off += size;
}
rcu_read_unlock();
return 0;
}
/* Called from syscall or from eBPF program */
static int array_map_delete_elem(struct bpf_map *map, void *key)
{
return -EINVAL;
}
static void *array_map_vmalloc_addr(struct bpf_array *array)
{
return (void *)round_down((unsigned long)array, PAGE_SIZE);
}
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
static void array_map_free(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
* so the programs (can be more than one that used this map) were
* disconnected from events. Wait for outstanding programs to complete
* and free the array
*/
synchronize_rcu();
if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
bpf_array_free_percpu(array);
if (array->map.map_flags & BPF_F_MMAPABLE)
bpf_map_area_free(array_map_vmalloc_addr(array));
else
bpf_map_area_free(array);
}
static void array_map_seq_show_elem(struct bpf_map *map, void *key,
struct seq_file *m)
{
void *value;
rcu_read_lock();
value = array_map_lookup_elem(map, key);
if (!value) {
rcu_read_unlock();
return;
}
if (map->btf_key_type_id)
seq_printf(m, "%u: ", *(u32 *)key);
btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
seq_puts(m, "\n");
rcu_read_unlock();
}
static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key,
struct seq_file *m)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
void __percpu *pptr;
int cpu;
rcu_read_lock();
seq_printf(m, "%u: {\n", *(u32 *)key);
pptr = array->pptrs[index & array->index_mask];
for_each_possible_cpu(cpu) {
seq_printf(m, "\tcpu%d: ", cpu);
btf_type_seq_show(map->btf, map->btf_value_type_id,
per_cpu_ptr(pptr, cpu), m);
seq_puts(m, "\n");
}
seq_puts(m, "}\n");
rcu_read_unlock();
}
static int array_map_check_btf(const struct bpf_map *map,
const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type)
{
u32 int_data;
/* One exception for keyless BTF: .bss/.data/.rodata map */
if (btf_type_is_void(key_type)) {
if (map->map_type != BPF_MAP_TYPE_ARRAY ||
map->max_entries != 1)
return -EINVAL;
if (BTF_INFO_KIND(value_type->info) != BTF_KIND_DATASEC)
return -EINVAL;
return 0;
}
if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
return -EINVAL;
int_data = *(u32 *)(key_type + 1);
/* bpf array can only take a u32 key. This check makes sure
* that the btf matches the attr used during map_create.
*/
if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
return -EINVAL;
return 0;
}
int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
pgoff_t pgoff = PAGE_ALIGN(sizeof(*array)) >> PAGE_SHIFT;
if (!(map->map_flags & BPF_F_MMAPABLE))
return -EINVAL;
return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff);
}
const struct bpf_map_ops array_map_ops = {
.map_alloc_check = array_map_alloc_check,
.map_alloc = array_map_alloc,
.map_free = array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = array_map_lookup_elem,
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
.map_gen_lookup = array_map_gen_lookup,
.map_direct_value_addr = array_map_direct_value_addr,
.map_direct_value_meta = array_map_direct_value_meta,
.map_mmap = array_map_mmap,
.map_seq_show_elem = array_map_seq_show_elem,
.map_check_btf = array_map_check_btf,
};
const struct bpf_map_ops percpu_array_map_ops = {
.map_alloc_check = array_map_alloc_check,
.map_alloc = array_map_alloc,
.map_free = array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = percpu_array_map_lookup_elem,
.map_update_elem = array_map_update_elem,
.map_delete_elem = array_map_delete_elem,
.map_seq_show_elem = percpu_array_map_seq_show_elem,
.map_check_btf = array_map_check_btf,
};
static int fd_array_map_alloc_check(union bpf_attr *attr)
{
/* only file descriptors can be stored in this type of map */
if (attr->value_size != sizeof(u32))
return -EINVAL;
/* Program read-only/write-only not supported for special maps yet. */
if (attr->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG))
return -EINVAL;
return array_map_alloc_check(attr);
}
static void fd_array_map_free(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
synchronize_rcu();
/* make sure it's empty */
for (i = 0; i < array->map.max_entries; i++)
BUG_ON(array->ptrs[i] != NULL);
bpf_map_area_free(array);
}
static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
{
return ERR_PTR(-EOPNOTSUPP);
}
/* only called from syscall */
int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value)
{
void **elem, *ptr;
int ret = 0;
if (!map->ops->map_fd_sys_lookup_elem)
return -ENOTSUPP;
rcu_read_lock();
elem = array_map_lookup_elem(map, key);
if (elem && (ptr = READ_ONCE(*elem)))
*value = map->ops->map_fd_sys_lookup_elem(ptr);
else
ret = -ENOENT;
rcu_read_unlock();
return ret;
}
/* only called from syscall */
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
void *new_ptr, *old_ptr;
u32 index = *(u32 *)key, ufd;
if (map_flags != BPF_ANY)
return -EINVAL;
if (index >= array->map.max_entries)
return -E2BIG;
ufd = *(u32 *)value;
new_ptr = map->ops->map_fd_get_ptr(map, map_file, ufd);
if (IS_ERR(new_ptr))
return PTR_ERR(new_ptr);
old_ptr = xchg(array->ptrs + index, new_ptr);
if (old_ptr)
map->ops->map_fd_put_ptr(old_ptr);
return 0;
}
static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
void *old_ptr;
u32 index = *(u32 *)key;
if (index >= array->map.max_entries)
return -E2BIG;
old_ptr = xchg(array->ptrs + index, NULL);
if (old_ptr) {
map->ops->map_fd_put_ptr(old_ptr);
return 0;
} else {
return -ENOENT;
}
}
static void *prog_fd_array_get_ptr(struct bpf_map *map,
struct file *map_file, int fd)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_prog *prog = bpf_prog_get(fd);
if (IS_ERR(prog))
return prog;
if (!bpf_prog_array_compatible(array, prog)) {
bpf_prog_put(prog);
return ERR_PTR(-EINVAL);
}
return prog;
}
static void prog_fd_array_put_ptr(void *ptr)
{
bpf_prog_put(ptr);
}
static u32 prog_fd_array_sys_lookup_elem(void *ptr)
{
return ((struct bpf_prog *)ptr)->aux->id;
}
/* decrement refcnt of all bpf_progs that are stored in this map */
static void bpf_fd_array_map_clear(struct bpf_map *map)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
int i;
for (i = 0; i < array->map.max_entries; i++)
fd_array_map_delete_elem(map, &i);
}
static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key,
struct seq_file *m)
{
void **elem, *ptr;
u32 prog_id;
rcu_read_lock();
elem = array_map_lookup_elem(map, key);
if (elem) {
ptr = READ_ONCE(*elem);
if (ptr) {
seq_printf(m, "%u: ", *(u32 *)key);
prog_id = prog_fd_array_sys_lookup_elem(ptr);
btf_type_seq_show(map->btf, map->btf_value_type_id,
&prog_id, m);
seq_puts(m, "\n");
}
}
rcu_read_unlock();
}
const struct bpf_map_ops prog_array_map_ops = {
.map_alloc_check = fd_array_map_alloc_check,
.map_alloc = array_map_alloc,
.map_free = fd_array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = fd_array_map_lookup_elem,
.map_delete_elem = fd_array_map_delete_elem,
.map_fd_get_ptr = prog_fd_array_get_ptr,
.map_fd_put_ptr = prog_fd_array_put_ptr,
.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
.map_release_uref = bpf_fd_array_map_clear,
.map_seq_show_elem = prog_array_map_seq_show_elem,
};
static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
struct file *map_file)
{
struct bpf_event_entry *ee;
ee = kzalloc(sizeof(*ee), GFP_ATOMIC);
if (ee) {
ee->event = perf_file->private_data;
ee->perf_file = perf_file;
ee->map_file = map_file;
}
return ee;
}
static void __bpf_event_entry_free(struct rcu_head *rcu)
{
struct bpf_event_entry *ee;
ee = container_of(rcu, struct bpf_event_entry, rcu);
fput(ee->perf_file);
kfree(ee);
}
static void bpf_event_entry_free_rcu(struct bpf_event_entry *ee)
{
call_rcu(&ee->rcu, __bpf_event_entry_free);
}
static void *perf_event_fd_array_get_ptr(struct bpf_map *map,
struct file *map_file, int fd)
{
struct bpf_event_entry *ee;
struct perf_event *event;
struct file *perf_file;
u64 value;
perf_file = perf_event_get(fd);
if (IS_ERR(perf_file))
return perf_file;
ee = ERR_PTR(-EOPNOTSUPP);
event = perf_file->private_data;
if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP)
goto err_out;
ee = bpf_event_entry_gen(perf_file, map_file);
if (ee)
return ee;
ee = ERR_PTR(-ENOMEM);
err_out:
fput(perf_file);
return ee;
}
static void perf_event_fd_array_put_ptr(void *ptr)
{
bpf_event_entry_free_rcu(ptr);
}
static void perf_event_fd_array_release(struct bpf_map *map,
struct file *map_file)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_event_entry *ee;
int i;
rcu_read_lock();
for (i = 0; i < array->map.max_entries; i++) {
ee = READ_ONCE(array->ptrs[i]);
if (ee && ee->map_file == map_file)
fd_array_map_delete_elem(map, &i);
}
rcu_read_unlock();
}
const struct bpf_map_ops perf_event_array_map_ops = {
.map_alloc_check = fd_array_map_alloc_check,
.map_alloc = array_map_alloc,
.map_free = fd_array_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = fd_array_map_lookup_elem,
.map_delete_elem = fd_array_map_delete_elem,
.map_fd_get_ptr = perf_event_fd_array_get_ptr,
.map_fd_put_ptr = perf_event_fd_array_put_ptr,
.map_release = perf_event_fd_array_release,
.map_check_btf = map_check_no_btf,
};
#ifdef CONFIG_CGROUPS
static void *cgroup_fd_array_get_ptr(struct bpf_map *map,
struct file *map_file /* not used */,
int fd)
{
return cgroup_get_from_fd(fd);
}
static void cgroup_fd_array_put_ptr(void *ptr)
{
/* cgroup_put free cgrp after a rcu grace period */
cgroup_put(ptr);
}
static void cgroup_fd_array_free(struct bpf_map *map)
{
bpf_fd_array_map_clear(map);
fd_array_map_free(map);
}
const struct bpf_map_ops cgroup_array_map_ops = {
.map_alloc_check = fd_array_map_alloc_check,
.map_alloc = array_map_alloc,
.map_free = cgroup_fd_array_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = fd_array_map_lookup_elem,
.map_delete_elem = fd_array_map_delete_elem,
.map_fd_get_ptr = cgroup_fd_array_get_ptr,
.map_fd_put_ptr = cgroup_fd_array_put_ptr,
.map_check_btf = map_check_no_btf,
};
#endif
static struct bpf_map *array_of_map_alloc(union bpf_attr *attr)
{
struct bpf_map *map, *inner_map_meta;
inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd);
if (IS_ERR(inner_map_meta))
return inner_map_meta;
map = array_map_alloc(attr);
if (IS_ERR(map)) {
bpf_map_meta_free(inner_map_meta);
return map;
}
map->inner_map_meta = inner_map_meta;
return map;
}
static void array_of_map_free(struct bpf_map *map)
{
/* map->inner_map_meta is only accessed by syscall which
* is protected by fdget/fdput.
*/
bpf_map_meta_free(map->inner_map_meta);
bpf_fd_array_map_clear(map);
fd_array_map_free(map);
}
static void *array_of_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_map **inner_map = array_map_lookup_elem(map, key);
if (!inner_map)
return NULL;
return READ_ONCE(*inner_map);
}
static u32 array_of_map_gen_lookup(struct bpf_map *map,
struct bpf_insn *insn_buf)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 elem_size = round_up(map->value_size, 8);
struct bpf_insn *insn = insn_buf;
const int ret = BPF_REG_0;
const int map_ptr = BPF_REG_1;
const int index = BPF_REG_2;
*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
if (map->unpriv_array) {
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6);
*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
} else {
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5);
}
if (is_power_of_2(elem_size))
*insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size));
else
*insn++ = BPF_ALU64_IMM(BPF_MUL, ret, elem_size);
*insn++ = BPF_ALU64_REG(BPF_ADD, ret, map_ptr);
*insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0);
*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1);
*insn++ = BPF_MOV64_IMM(ret, 0);
return insn - insn_buf;
}
const struct bpf_map_ops array_of_maps_map_ops = {
.map_alloc_check = fd_array_map_alloc_check,
.map_alloc = array_of_map_alloc,
.map_free = array_of_map_free,
.map_get_next_key = array_map_get_next_key,
.map_lookup_elem = array_of_map_lookup_elem,
.map_delete_elem = fd_array_map_delete_elem,
.map_fd_get_ptr = bpf_map_fd_get_ptr,
.map_fd_put_ptr = bpf_map_fd_put_ptr,
.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
.map_gen_lookup = array_of_map_gen_lookup,
.map_check_btf = map_check_no_btf,
};