forked from Minki/linux
1e0bd5a091
92117d8443 ("bpf: fix refcnt overflow") turned refcounting of bpf_map into
potentially failing operation, when refcount reaches BPF_MAX_REFCNT limit
(32k). Due to using 32-bit counter, it's possible in practice to overflow
refcounter and make it wrap around to 0, causing erroneous map free, while
there are still references to it, causing use-after-free problems.
But having a failing refcounting operations are problematic in some cases. One
example is mmap() interface. After establishing initial memory-mapping, user
is allowed to arbitrarily map/remap/unmap parts of mapped memory, arbitrarily
splitting it into multiple non-contiguous regions. All this happening without
any control from the users of mmap subsystem. Rather mmap subsystem sends
notifications to original creator of memory mapping through open/close
callbacks, which are optionally specified during initial memory mapping
creation. These callbacks are used to maintain accurate refcount for bpf_map
(see next patch in this series). The problem is that open() callback is not
supposed to fail, because memory-mapped resource is set up and properly
referenced. This is posing a problem for using memory-mapping with BPF maps.
One solution to this is to maintain separate refcount for just memory-mappings
and do single bpf_map_inc/bpf_map_put when it goes from/to zero, respectively.
There are similar use cases in current work on tcp-bpf, necessitating extra
counter as well. This seems like a rather unfortunate and ugly solution that
doesn't scale well to various new use cases.
Another approach to solve this is to use non-failing refcount_t type, which
uses 32-bit counter internally, but, once reaching overflow state at UINT_MAX,
stays there. This utlimately causes memory leak, but prevents use after free.
But given refcounting is not the most performance-critical operation with BPF
maps (it's not used from running BPF program code), we can also just switch to
64-bit counter that can't overflow in practice, potentially disadvantaging
32-bit platforms a tiny bit. This simplifies semantics and allows above
described scenarios to not worry about failing refcount increment operation.
In terms of struct bpf_map size, we are still good and use the same amount of
space:
BEFORE (3 cache lines, 8 bytes of padding at the end):
struct bpf_map {
const struct bpf_map_ops * ops __attribute__((__aligned__(64))); /* 0 8 */
struct bpf_map * inner_map_meta; /* 8 8 */
void * security; /* 16 8 */
enum bpf_map_type map_type; /* 24 4 */
u32 key_size; /* 28 4 */
u32 value_size; /* 32 4 */
u32 max_entries; /* 36 4 */
u32 map_flags; /* 40 4 */
int spin_lock_off; /* 44 4 */
u32 id; /* 48 4 */
int numa_node; /* 52 4 */
u32 btf_key_type_id; /* 56 4 */
u32 btf_value_type_id; /* 60 4 */
/* --- cacheline 1 boundary (64 bytes) --- */
struct btf * btf; /* 64 8 */
struct bpf_map_memory memory; /* 72 16 */
bool unpriv_array; /* 88 1 */
bool frozen; /* 89 1 */
/* XXX 38 bytes hole, try to pack */
/* --- cacheline 2 boundary (128 bytes) --- */
atomic_t refcnt __attribute__((__aligned__(64))); /* 128 4 */
atomic_t usercnt; /* 132 4 */
struct work_struct work; /* 136 32 */
char name[16]; /* 168 16 */
/* size: 192, cachelines: 3, members: 21 */
/* sum members: 146, holes: 1, sum holes: 38 */
/* padding: 8 */
/* forced alignments: 2, forced holes: 1, sum forced holes: 38 */
} __attribute__((__aligned__(64)));
AFTER (same 3 cache lines, no extra padding now):
struct bpf_map {
const struct bpf_map_ops * ops __attribute__((__aligned__(64))); /* 0 8 */
struct bpf_map * inner_map_meta; /* 8 8 */
void * security; /* 16 8 */
enum bpf_map_type map_type; /* 24 4 */
u32 key_size; /* 28 4 */
u32 value_size; /* 32 4 */
u32 max_entries; /* 36 4 */
u32 map_flags; /* 40 4 */
int spin_lock_off; /* 44 4 */
u32 id; /* 48 4 */
int numa_node; /* 52 4 */
u32 btf_key_type_id; /* 56 4 */
u32 btf_value_type_id; /* 60 4 */
/* --- cacheline 1 boundary (64 bytes) --- */
struct btf * btf; /* 64 8 */
struct bpf_map_memory memory; /* 72 16 */
bool unpriv_array; /* 88 1 */
bool frozen; /* 89 1 */
/* XXX 38 bytes hole, try to pack */
/* --- cacheline 2 boundary (128 bytes) --- */
atomic64_t refcnt __attribute__((__aligned__(64))); /* 128 8 */
atomic64_t usercnt; /* 136 8 */
struct work_struct work; /* 144 32 */
char name[16]; /* 176 16 */
/* size: 192, cachelines: 3, members: 21 */
/* sum members: 154, holes: 1, sum holes: 38 */
/* forced alignments: 2, forced holes: 1, sum forced holes: 38 */
} __attribute__((__aligned__(64)));
This patch, while modifying all users of bpf_map_inc, also cleans up its
interface to match bpf_map_put with separate operations for bpf_map_inc and
bpf_map_inc_with_uref (to match bpf_map_put and bpf_map_put_with_uref,
respectively). Also, given there are no users of bpf_map_inc_not_zero
specifying uref=true, remove uref flag and default to uref=false internally.
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191117172806.2195367-2-andriin@fb.com
121 lines
3.0 KiB
C
121 lines
3.0 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/* Copyright (c) 2017 Facebook
|
|
*/
|
|
#include <linux/slab.h>
|
|
#include <linux/bpf.h>
|
|
|
|
#include "map_in_map.h"
|
|
|
|
struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
|
|
{
|
|
struct bpf_map *inner_map, *inner_map_meta;
|
|
u32 inner_map_meta_size;
|
|
struct fd f;
|
|
|
|
f = fdget(inner_map_ufd);
|
|
inner_map = __bpf_map_get(f);
|
|
if (IS_ERR(inner_map))
|
|
return inner_map;
|
|
|
|
/* prog_array->owner_prog_type and owner_jited
|
|
* is a runtime binding. Doing static check alone
|
|
* in the verifier is not enough.
|
|
*/
|
|
if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
|
|
inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE ||
|
|
inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
|
|
fdput(f);
|
|
return ERR_PTR(-ENOTSUPP);
|
|
}
|
|
|
|
/* Does not support >1 level map-in-map */
|
|
if (inner_map->inner_map_meta) {
|
|
fdput(f);
|
|
return ERR_PTR(-EINVAL);
|
|
}
|
|
|
|
if (map_value_has_spin_lock(inner_map)) {
|
|
fdput(f);
|
|
return ERR_PTR(-ENOTSUPP);
|
|
}
|
|
|
|
inner_map_meta_size = sizeof(*inner_map_meta);
|
|
/* In some cases verifier needs to access beyond just base map. */
|
|
if (inner_map->ops == &array_map_ops)
|
|
inner_map_meta_size = sizeof(struct bpf_array);
|
|
|
|
inner_map_meta = kzalloc(inner_map_meta_size, GFP_USER);
|
|
if (!inner_map_meta) {
|
|
fdput(f);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
inner_map_meta->map_type = inner_map->map_type;
|
|
inner_map_meta->key_size = inner_map->key_size;
|
|
inner_map_meta->value_size = inner_map->value_size;
|
|
inner_map_meta->map_flags = inner_map->map_flags;
|
|
inner_map_meta->max_entries = inner_map->max_entries;
|
|
inner_map_meta->spin_lock_off = inner_map->spin_lock_off;
|
|
|
|
/* Misc members not needed in bpf_map_meta_equal() check. */
|
|
inner_map_meta->ops = inner_map->ops;
|
|
if (inner_map->ops == &array_map_ops) {
|
|
inner_map_meta->unpriv_array = inner_map->unpriv_array;
|
|
container_of(inner_map_meta, struct bpf_array, map)->index_mask =
|
|
container_of(inner_map, struct bpf_array, map)->index_mask;
|
|
}
|
|
|
|
fdput(f);
|
|
return inner_map_meta;
|
|
}
|
|
|
|
void bpf_map_meta_free(struct bpf_map *map_meta)
|
|
{
|
|
kfree(map_meta);
|
|
}
|
|
|
|
bool bpf_map_meta_equal(const struct bpf_map *meta0,
|
|
const struct bpf_map *meta1)
|
|
{
|
|
/* No need to compare ops because it is covered by map_type */
|
|
return meta0->map_type == meta1->map_type &&
|
|
meta0->key_size == meta1->key_size &&
|
|
meta0->value_size == meta1->value_size &&
|
|
meta0->map_flags == meta1->map_flags &&
|
|
meta0->max_entries == meta1->max_entries;
|
|
}
|
|
|
|
void *bpf_map_fd_get_ptr(struct bpf_map *map,
|
|
struct file *map_file /* not used */,
|
|
int ufd)
|
|
{
|
|
struct bpf_map *inner_map;
|
|
struct fd f;
|
|
|
|
f = fdget(ufd);
|
|
inner_map = __bpf_map_get(f);
|
|
if (IS_ERR(inner_map))
|
|
return inner_map;
|
|
|
|
if (bpf_map_meta_equal(map->inner_map_meta, inner_map))
|
|
bpf_map_inc(inner_map);
|
|
else
|
|
inner_map = ERR_PTR(-EINVAL);
|
|
|
|
fdput(f);
|
|
return inner_map;
|
|
}
|
|
|
|
void bpf_map_fd_put_ptr(void *ptr)
|
|
{
|
|
/* ptr->ops->map_free() has to go through one
|
|
* rcu grace period by itself.
|
|
*/
|
|
bpf_map_put(ptr);
|
|
}
|
|
|
|
u32 bpf_map_fd_sys_lookup_elem(void *ptr)
|
|
{
|
|
return ((struct bpf_map *)ptr)->id;
|
|
}
|