xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Browse Source 
Alexei Starovoitov says:

====================
pull-request: bpf-next 2018-10-08

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) sk_lookup_[tcp|udp] and sk_release helpers from Joe Stringer which allow
BPF programs to perform lookups for sockets in a network namespace. This would
allow programs to determine early on in processing whether the stack is
expecting to receive the packet, and perform some action (eg drop,
forward somewhere) based on this information.

2) per-cpu cgroup local storage from Roman Gushchin.
Per-cpu cgroup local storage is very similar to simple cgroup storage
except all the data is per-cpu. The main goal of per-cpu variant is to
implement super fast counters (e.g. packet counters), which don't require
neither lookups, neither atomic operations in a fast path.
The example of these hybrid counters is in selftests/bpf/netcnt_prog.c

3) allow HW offload of programs with BPF-to-BPF function calls from Quentin Monnet

4) support more than 64-byte key/value in HW offloaded BPF maps from Jakub Kicinski

5) rename of libbpf interfaces from Andrey Ignatov.
libbpf is maturing as a library and should follow good practices in
library design and implementation to play well with other libraries.
This patch set brings consistent naming convention to global symbols.

6) relicense libbpf as LGPL-2.1 OR BSD-2-Clause from Alexei Starovoitov
to let Apache2 projects use libbpf

7) various AF_XDP fixes from Björn and Magnus
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller
2018-10-08 23:42:44 -07:00
parent 9000a457a0 df3f94a0bb
commit 071a234ad7
66 changed files with 4142 additions and 665 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
kernel/bpf/cgroup.c
View File

@@ -25,6 +25,7 @@ EXPORT_SYMBOL(cgroup_bpf_enabled_key);
*/
void cgroup_bpf_put(struct cgroup *cgrp)
{
enum bpf_cgroup_storage_type stype;
unsigned int type;
for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) {
@@ -34,8 +35,10 @@ void cgroup_bpf_put(struct cgroup *cgrp)
list_for_each_entry_safe(pl, tmp, progs, node) {
list_del(&pl->node);
bpf_prog_put(pl->prog);
bpf_cgroup_storage_unlink(pl->storage);
bpf_cgroup_storage_free(pl->storage);
for_each_cgroup_storage_type(stype) {
bpf_cgroup_storage_unlink(pl->storage[stype]);
bpf_cgroup_storage_free(pl->storage[stype]);
}
kfree(pl);
static_branch_dec(&cgroup_bpf_enabled_key);
}
@@ -97,6 +100,7 @@ static int compute_effective_progs(struct cgroup *cgrp,
enum bpf_attach_type type,
struct bpf_prog_array __rcu **array)
{
enum bpf_cgroup_storage_type stype;
struct bpf_prog_array *progs;
struct bpf_prog_list *pl;
struct cgroup *p = cgrp;
@@ -125,7 +129,9 @@ static int compute_effective_progs(struct cgroup *cgrp,
continue;
progs->items[cnt].prog = pl->prog;
progs->items[cnt].cgroup_storage = pl->storage;
for_each_cgroup_storage_type(stype)
progs->items[cnt].cgroup_storage[stype] =
pl->storage[stype];
cnt++;
}
} while ((p = cgroup_parent(p)));
@@ -232,7 +238,9 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
{
struct list_head *progs = &cgrp->bpf.progs[type];
struct bpf_prog *old_prog = NULL;
struct bpf_cgroup_storage *storage, *old_storage = NULL;
struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE],
*old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL};
enum bpf_cgroup_storage_type stype;
struct bpf_prog_list *pl;
bool pl_was_allocated;
int err;
@@ -254,34 +262,44 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
return -E2BIG;
storage = bpf_cgroup_storage_alloc(prog);
if (IS_ERR(storage))
return -ENOMEM;
for_each_cgroup_storage_type(stype) {
storage[stype] = bpf_cgroup_storage_alloc(prog, stype);
if (IS_ERR(storage[stype])) {
storage[stype] = NULL;
for_each_cgroup_storage_type(stype)
bpf_cgroup_storage_free(storage[stype]);
return -ENOMEM;
}
}
if (flags & BPF_F_ALLOW_MULTI) {
list_for_each_entry(pl, progs, node) {
if (pl->prog == prog) {
/* disallow attaching the same prog twice */
bpf_cgroup_storage_free(storage);
for_each_cgroup_storage_type(stype)
bpf_cgroup_storage_free(storage[stype]);
return -EINVAL;
}
}
pl = kmalloc(sizeof(*pl), GFP_KERNEL);
if (!pl) {
bpf_cgroup_storage_free(storage);
for_each_cgroup_storage_type(stype)
bpf_cgroup_storage_free(storage[stype]);
return -ENOMEM;
}
pl_was_allocated = true;
pl->prog = prog;
pl->storage = storage;
for_each_cgroup_storage_type(stype)
pl->storage[stype] = storage[stype];
list_add_tail(&pl->node, progs);
} else {
if (list_empty(progs)) {
pl = kmalloc(sizeof(*pl), GFP_KERNEL);
if (!pl) {
bpf_cgroup_storage_free(storage);
for_each_cgroup_storage_type(stype)
bpf_cgroup_storage_free(storage[stype]);
return -ENOMEM;
}
pl_was_allocated = true;
@@ -289,12 +307,15 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
} else {
pl = list_first_entry(progs, typeof(*pl), node);
old_prog = pl->prog;
old_storage = pl->storage;
bpf_cgroup_storage_unlink(old_storage);
for_each_cgroup_storage_type(stype) {
old_storage[stype] = pl->storage[stype];
bpf_cgroup_storage_unlink(old_storage[stype]);
}
pl_was_allocated = false;
}
pl->prog = prog;
pl->storage = storage;
for_each_cgroup_storage_type(stype)
pl->storage[stype] = storage[stype];
}
cgrp->bpf.flags[type] = flags;
@@ -304,21 +325,27 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
goto cleanup;
static_branch_inc(&cgroup_bpf_enabled_key);
if (old_storage)
bpf_cgroup_storage_free(old_storage);
for_each_cgroup_storage_type(stype) {
if (!old_storage[stype])
continue;
bpf_cgroup_storage_free(old_storage[stype]);
}
if (old_prog) {
bpf_prog_put(old_prog);
static_branch_dec(&cgroup_bpf_enabled_key);
}
bpf_cgroup_storage_link(storage, cgrp, type);
for_each_cgroup_storage_type(stype)
bpf_cgroup_storage_link(storage[stype], cgrp, type);
return 0;
cleanup:
/* and cleanup the prog list */
pl->prog = old_prog;
bpf_cgroup_storage_free(pl->storage);
pl->storage = old_storage;
bpf_cgroup_storage_link(old_storage, cgrp, type);
for_each_cgroup_storage_type(stype) {
bpf_cgroup_storage_free(pl->storage[stype]);
pl->storage[stype] = old_storage[stype];
bpf_cgroup_storage_link(old_storage[stype], cgrp, type);
}
if (pl_was_allocated) {
list_del(&pl->node);
kfree(pl);
@@ -339,6 +366,7 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
enum bpf_attach_type type, u32 unused_flags)
{
struct list_head *progs = &cgrp->bpf.progs[type];
enum bpf_cgroup_storage_type stype;
u32 flags = cgrp->bpf.flags[type];
struct bpf_prog *old_prog = NULL;
struct bpf_prog_list *pl;
@@ -385,8 +413,10 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
/* now can actually delete it from this cgroup list */
list_del(&pl->node);
bpf_cgroup_storage_unlink(pl->storage);
bpf_cgroup_storage_free(pl->storage);
for_each_cgroup_storage_type(stype) {
bpf_cgroup_storage_unlink(pl->storage[stype]);
bpf_cgroup_storage_free(pl->storage[stype]);
}
kfree(pl);
if (list_empty(progs))
/* last program was detached, reset flags to zero */
@@ -677,6 +707,8 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_get_current_uid_gid_proto;
case BPF_FUNC_get_local_storage:
return &bpf_get_local_storage_proto;
case BPF_FUNC_get_current_cgroup_id:
return &bpf_get_current_cgroup_id_proto;
case BPF_FUNC_trace_printk:
if (capable(CAP_SYS_ADMIN))
return bpf_get_trace_printk_proto();

25
kernel/bpf/helpers.c
View File

@@ -194,16 +194,28 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
.ret_type = RET_INTEGER,
};
DECLARE_PER_CPU(void*, bpf_cgroup_storage);
#ifdef CONFIG_CGROUP_BPF
DECLARE_PER_CPU(struct bpf_cgroup_storage*,
bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
{
/* map and flags arguments are not used now,
* but provide an ability to extend the API
* for other types of local storages.
* verifier checks that their values are correct.
/* flags argument is not used now,
* but provides an ability to extend the API.
* verifier checks that its value is correct.
*/
return (unsigned long) this_cpu_read(bpf_cgroup_storage);
enum bpf_cgroup_storage_type stype = cgroup_storage_type(map);
struct bpf_cgroup_storage *storage;
void *ptr;
storage = this_cpu_read(bpf_cgroup_storage[stype]);
if (stype == BPF_CGROUP_STORAGE_SHARED)
ptr = &READ_ONCE(storage->buf)->data[0];
else
ptr = this_cpu_ptr(storage->percpu_buf);
return (unsigned long)ptr;
}
const struct bpf_func_proto bpf_get_local_storage_proto = {
@@ -214,3 +226,4 @@ const struct bpf_func_proto bpf_get_local_storage_proto = {
.arg2_type = ARG_ANYTHING,
};
#endif
#endif

169
kernel/bpf/local_storage.c
View File

@@ -7,7 +7,8 @@
#include <linux/rbtree.h>
#include <linux/slab.h>
DEFINE_PER_CPU(void*, bpf_cgroup_storage);
DEFINE_PER_CPU(struct bpf_cgroup_storage*,
bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]);
#ifdef CONFIG_CGROUP_BPF
@@ -151,6 +152,71 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
return 0;
}
int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key,
void *value)
{
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
struct bpf_cgroup_storage_key *key = _key;
struct bpf_cgroup_storage *storage;
int cpu, off = 0;
u32 size;
rcu_read_lock();
storage = cgroup_storage_lookup(map, key, false);
if (!storage) {
rcu_read_unlock();
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);
for_each_possible_cpu(cpu) {
bpf_long_memcpy(value + off,
per_cpu_ptr(storage->percpu_buf, cpu), size);
off += size;
}
rcu_read_unlock();
return 0;
}
int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key,
void *value, u64 map_flags)
{
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
struct bpf_cgroup_storage_key *key = _key;
struct bpf_cgroup_storage *storage;
int cpu, off = 0;
u32 size;
if (map_flags != BPF_ANY && map_flags != BPF_EXIST)
return -EINVAL;
rcu_read_lock();
storage = cgroup_storage_lookup(map, key, false);
if (!storage) {
rcu_read_unlock();
return -ENOENT;
}
/* 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);
for_each_possible_cpu(cpu) {
bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu),
value + off, size);
off += size;
}
rcu_read_unlock();
return 0;
}
static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
void *_next_key)
{
@@ -254,6 +320,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
{
enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map);
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
int ret = -EBUSY;
@@ -261,11 +328,12 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
if (map->prog && map->prog != prog)
goto unlock;
if (prog->aux->cgroup_storage && prog->aux->cgroup_storage != _map)
if (prog->aux->cgroup_storage[stype] &&
prog->aux->cgroup_storage[stype] != _map)
goto unlock;
map->prog = prog;
prog->aux->cgroup_storage = _map;
prog->aux->cgroup_storage[stype] = _map;
ret = 0;
unlock:
spin_unlock_bh(&map->lock);
@@ -275,70 +343,117 @@ unlock:
void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map)
{
enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map);
struct bpf_cgroup_storage_map *map = map_to_storage(_map);
spin_lock_bh(&map->lock);
if (map->prog == prog) {
WARN_ON(prog->aux->cgroup_storage != _map);
WARN_ON(prog->aux->cgroup_storage[stype] != _map);
map->prog = NULL;
prog->aux->cgroup_storage = NULL;
prog->aux->cgroup_storage[stype] = NULL;
}
spin_unlock_bh(&map->lock);
}
struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog)
static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages)
{
size_t size;
if (cgroup_storage_type(map) == BPF_CGROUP_STORAGE_SHARED) {
size = sizeof(struct bpf_storage_buffer) + map->value_size;
*pages = round_up(sizeof(struct bpf_cgroup_storage) + size,
PAGE_SIZE) >> PAGE_SHIFT;
} else {
size = map->value_size;
*pages = round_up(round_up(size, 8) * num_possible_cpus(),
PAGE_SIZE) >> PAGE_SHIFT;
}
return size;
}
struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog,
enum bpf_cgroup_storage_type stype)
{
struct bpf_cgroup_storage *storage;
struct bpf_map *map;
gfp_t flags;
size_t size;
u32 pages;
map = prog->aux->cgroup_storage;
map = prog->aux->cgroup_storage[stype];
if (!map)
return NULL;
pages = round_up(sizeof(struct bpf_cgroup_storage) +
sizeof(struct bpf_storage_buffer) +
map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
size = bpf_cgroup_storage_calculate_size(map, &pages);
if (bpf_map_charge_memlock(map, pages))
return ERR_PTR(-EPERM);
storage = kmalloc_node(sizeof(struct bpf_cgroup_storage),
__GFP_ZERO | GFP_USER, map->numa_node);
if (!storage) {
bpf_map_uncharge_memlock(map, pages);
return ERR_PTR(-ENOMEM);
}
if (!storage)
goto enomem;
storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) +
map->value_size, __GFP_ZERO | GFP_USER,
map->numa_node);
if (!storage->buf) {
bpf_map_uncharge_memlock(map, pages);
kfree(storage);
return ERR_PTR(-ENOMEM);
flags = __GFP_ZERO | GFP_USER;
if (stype == BPF_CGROUP_STORAGE_SHARED) {
storage->buf = kmalloc_node(size, flags, map->numa_node);
if (!storage->buf)
goto enomem;
} else {
storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags);
if (!storage->percpu_buf)
goto enomem;
}
storage->map = (struct bpf_cgroup_storage_map *)map;
return storage;
enomem:
bpf_map_uncharge_memlock(map, pages);
kfree(storage);
return ERR_PTR(-ENOMEM);
}
static void free_shared_cgroup_storage_rcu(struct rcu_head *rcu)
{
struct bpf_cgroup_storage *storage =
container_of(rcu, struct bpf_cgroup_storage, rcu);
kfree(storage->buf);
kfree(storage);
}
static void free_percpu_cgroup_storage_rcu(struct rcu_head *rcu)
{
struct bpf_cgroup_storage *storage =
container_of(rcu, struct bpf_cgroup_storage, rcu);
free_percpu(storage->percpu_buf);
kfree(storage);
}
void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage)
{
u32 pages;
enum bpf_cgroup_storage_type stype;
struct bpf_map *map;
u32 pages;
if (!storage)
return;
map = &storage->map->map;
pages = round_up(sizeof(struct bpf_cgroup_storage) +
sizeof(struct bpf_storage_buffer) +
map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
bpf_cgroup_storage_calculate_size(map, &pages);
bpf_map_uncharge_memlock(map, pages);
kfree_rcu(storage->buf, rcu);
kfree_rcu(storage, rcu);
stype = cgroup_storage_type(map);
if (stype == BPF_CGROUP_STORAGE_SHARED)
call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu);
else
call_rcu(&storage->rcu, free_percpu_cgroup_storage_rcu);
}
void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,

3
kernel/bpf/map_in_map.c
View File

@@ -24,7 +24,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
* 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_CGROUP_STORAGE ||
inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
fdput(f);
return ERR_PTR(-ENOTSUPP);
}

18
kernel/bpf/offload.c
View File

@@ -172,6 +172,24 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
return ret;
}
int bpf_prog_offload_finalize(struct bpf_verifier_env *env)
{
struct bpf_prog_offload *offload;
int ret = -ENODEV;
down_read(&bpf_devs_lock);
offload = env->prog->aux->offload;
if (offload) {
if (offload->dev_ops->finalize)
ret = offload->dev_ops->finalize(env);
else
ret = 0;
}
up_read(&bpf_devs_lock);
return ret;
}
static void __bpf_prog_offload_destroy(struct bpf_prog *prog)
{
struct bpf_prog_offload *offload = prog->aux->offload;

20
kernel/bpf/syscall.c
View File

@@ -686,7 +686,8 @@ static int map_lookup_elem(union bpf_attr *attr)
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else if (IS_FD_MAP(map))
value_size = sizeof(u32);
@@ -705,6 +706,8 @@ static int map_lookup_elem(union bpf_attr *attr)
err = bpf_percpu_hash_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
err = bpf_percpu_cgroup_storage_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
err = bpf_stackmap_copy(map, key, value);
} else if (IS_FD_ARRAY(map)) {
@@ -774,7 +777,8 @@ static int map_update_elem(union bpf_attr *attr)
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY ||
map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else
value_size = map->value_size;
@@ -809,6 +813,9 @@ static int map_update_elem(union bpf_attr *attr)
err = bpf_percpu_hash_update(map, key, value, attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_update(map, key, value, attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) {
err = bpf_percpu_cgroup_storage_update(map, key, value,
attr->flags);
} else if (IS_FD_ARRAY(map)) {
rcu_read_lock();
err = bpf_fd_array_map_update_elem(map, f.file, key, value,
@@ -988,10 +995,15 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
/* drop refcnt on maps used by eBPF program and free auxilary data */
static void free_used_maps(struct bpf_prog_aux *aux)
{
enum bpf_cgroup_storage_type stype;
int i;
if (aux->cgroup_storage)
bpf_cgroup_storage_release(aux->prog, aux->cgroup_storage);
for_each_cgroup_storage_type(stype) {
if (!aux->cgroup_storage[stype])
continue;
bpf_cgroup_storage_release(aux->prog,
aux->cgroup_storage[stype]);
}
for (i = 0; i < aux->used_map_cnt; i++)
bpf_map_put(aux->used_maps[i]);

638
kernel/bpf/verifier.c
View File

File diff suppressed because it is too large Load Diff