diff options
Diffstat (limited to 'kernel/bpf')
-rw-r--r-- | kernel/bpf/Makefile | 3 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 12 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 45 | ||||
-rw-r--r-- | kernel/bpf/xskmap.c | 265 |
4 files changed, 52 insertions, 273 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 37b2d8620153..375b933010dd 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -12,9 +12,6 @@ obj-$(CONFIG_BPF_JIT) += dispatcher.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o -ifeq ($(CONFIG_XDP_SOCKETS),y) -obj-$(CONFIG_BPF_SYSCALL) += xskmap.o -endif obj-$(CONFIG_BPF_SYSCALL) += offload.o endif ifeq ($(CONFIG_PERF_EVENTS),y) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 57dfc98289d5..431241c74614 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1978,6 +1978,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: @@ -2767,6 +2771,10 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: @@ -2912,6 +2920,10 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_INET4_GETPEERNAME: + case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_INET4_GETSOCKNAME: + case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 25b14ee0e26d..d2e27dba4ac6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -393,6 +393,15 @@ static bool type_is_sk_pointer(enum bpf_reg_type type) type == PTR_TO_XDP_SOCK; } +static bool reg_type_not_null(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET || + type == PTR_TO_TCP_SOCK || + type == PTR_TO_MAP_VALUE || + type == PTR_TO_SOCK_COMMON || + type == PTR_TO_BTF_ID; +} + static bool reg_type_may_be_null(enum bpf_reg_type type) { return type == PTR_TO_MAP_VALUE_OR_NULL || @@ -6308,8 +6317,25 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, bool is_jmp32) { - if (__is_pointer_value(false, reg)) - return -1; + if (__is_pointer_value(false, reg)) { + if (!reg_type_not_null(reg->type)) + return -1; + + /* If pointer is valid tests against zero will fail so we can + * use this to direct branch taken. + */ + if (val != 0) + return -1; + + switch (opcode) { + case BPF_JEQ: + return 0; + case BPF_JNE: + return 1; + default: + return -1; + } + } if (is_jmp32) return is_branch32_taken(reg, val, opcode); @@ -6808,7 +6834,11 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } if (pred >= 0) { - err = mark_chain_precision(env, insn->dst_reg); + /* If we get here with a dst_reg pointer type it is because + * above is_branch_taken() special cased the 0 comparison. + */ + if (!__is_pointer_value(false, dst_reg)) + err = mark_chain_precision(env, insn->dst_reg); if (BPF_SRC(insn->code) == BPF_X && !err) err = mark_chain_precision(env, insn->src_reg); if (err) @@ -7094,7 +7124,11 @@ static int check_return_code(struct bpf_verifier_env *env) switch (env->prog->type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || - env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG) + env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG || + env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME || + env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME || + env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || + env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME) range = tnum_range(1, 1); break; case BPF_PROG_TYPE_CGROUP_SKB: @@ -7120,10 +7154,11 @@ static int check_return_code(struct bpf_verifier_env *env) case BPF_TRACE_FEXIT: range = tnum_const(0); break; - case BPF_TRACE_ITER: case BPF_TRACE_RAW_TP: case BPF_MODIFY_RETURN: return 0; + case BPF_TRACE_ITER: + break; default: return -ENOTSUPP; } diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c deleted file mode 100644 index 2cc5c8f4c800..000000000000 --- a/kernel/bpf/xskmap.c +++ /dev/null @@ -1,265 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* XSKMAP used for AF_XDP sockets - * Copyright(c) 2018 Intel Corporation. - */ - -#include <linux/bpf.h> -#include <linux/capability.h> -#include <net/xdp_sock.h> -#include <linux/slab.h> -#include <linux/sched.h> - -int xsk_map_inc(struct xsk_map *map) -{ - bpf_map_inc(&map->map); - return 0; -} - -void xsk_map_put(struct xsk_map *map) -{ - bpf_map_put(&map->map); -} - -static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map, - struct xdp_sock **map_entry) -{ - struct xsk_map_node *node; - int err; - - node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN); - if (!node) - return ERR_PTR(-ENOMEM); - - err = xsk_map_inc(map); - if (err) { - kfree(node); - return ERR_PTR(err); - } - - node->map = map; - node->map_entry = map_entry; - return node; -} - -static void xsk_map_node_free(struct xsk_map_node *node) -{ - xsk_map_put(node->map); - kfree(node); -} - -static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node) -{ - spin_lock_bh(&xs->map_list_lock); - list_add_tail(&node->node, &xs->map_list); - spin_unlock_bh(&xs->map_list_lock); -} - -static void xsk_map_sock_delete(struct xdp_sock *xs, - struct xdp_sock **map_entry) -{ - struct xsk_map_node *n, *tmp; - - spin_lock_bh(&xs->map_list_lock); - list_for_each_entry_safe(n, tmp, &xs->map_list, node) { - if (map_entry == n->map_entry) { - list_del(&n->node); - xsk_map_node_free(n); - } - } - spin_unlock_bh(&xs->map_list_lock); -} - -static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) -{ - struct bpf_map_memory mem; - int err, numa_node; - struct xsk_map *m; - u64 size; - - if (!capable(CAP_NET_ADMIN)) - return ERR_PTR(-EPERM); - - if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || - attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)) - return ERR_PTR(-EINVAL); - - numa_node = bpf_map_attr_numa_node(attr); - size = struct_size(m, xsk_map, attr->max_entries); - - err = bpf_map_charge_init(&mem, size); - if (err < 0) - return ERR_PTR(err); - - m = bpf_map_area_alloc(size, numa_node); - if (!m) { - bpf_map_charge_finish(&mem); - return ERR_PTR(-ENOMEM); - } - - bpf_map_init_from_attr(&m->map, attr); - bpf_map_charge_move(&m->map.memory, &mem); - spin_lock_init(&m->lock); - - return &m->map; -} - -static void xsk_map_free(struct bpf_map *map) -{ - struct xsk_map *m = container_of(map, struct xsk_map, map); - - bpf_clear_redirect_map(map); - synchronize_net(); - bpf_map_area_free(m); -} - -static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key) -{ - struct xsk_map *m = container_of(map, struct xsk_map, map); - u32 index = key ? *(u32 *)key : U32_MAX; - u32 *next = next_key; - - if (index >= m->map.max_entries) { - *next = 0; - return 0; - } - - if (index == m->map.max_entries - 1) - return -ENOENT; - *next = index + 1; - return 0; -} - -static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) -{ - const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2; - struct bpf_insn *insn = insn_buf; - - *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); - *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5); - *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(sizeof(struct xsk_sock *))); - *insn++ = BPF_ALU64_IMM(BPF_ADD, mp, offsetof(struct xsk_map, xsk_map)); - *insn++ = BPF_ALU64_REG(BPF_ADD, ret, mp); - *insn++ = BPF_LDX_MEM(BPF_SIZEOF(struct xsk_sock *), ret, ret, 0); - *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); - *insn++ = BPF_MOV64_IMM(ret, 0); - return insn - insn_buf; -} - -static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return __xsk_map_lookup_elem(map, *(u32 *)key); -} - -static void *xsk_map_lookup_elem_sys_only(struct bpf_map *map, void *key) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) -{ - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *xs, *old_xs, **map_entry; - u32 i = *(u32 *)key, fd = *(u32 *)value; - struct xsk_map_node *node; - struct socket *sock; - int err; - - if (unlikely(map_flags > BPF_EXIST)) - return -EINVAL; - if (unlikely(i >= m->map.max_entries)) - return -E2BIG; - - sock = sockfd_lookup(fd, &err); - if (!sock) - return err; - - if (sock->sk->sk_family != PF_XDP) { - sockfd_put(sock); - return -EOPNOTSUPP; - } - - xs = (struct xdp_sock *)sock->sk; - - if (!xsk_is_setup_for_bpf_map(xs)) { - sockfd_put(sock); - return -EOPNOTSUPP; - } - - map_entry = &m->xsk_map[i]; - node = xsk_map_node_alloc(m, map_entry); - if (IS_ERR(node)) { - sockfd_put(sock); - return PTR_ERR(node); - } - - spin_lock_bh(&m->lock); - old_xs = READ_ONCE(*map_entry); - if (old_xs == xs) { - err = 0; - goto out; - } else if (old_xs && map_flags == BPF_NOEXIST) { - err = -EEXIST; - goto out; - } else if (!old_xs && map_flags == BPF_EXIST) { - err = -ENOENT; - goto out; - } - xsk_map_sock_add(xs, node); - WRITE_ONCE(*map_entry, xs); - if (old_xs) - xsk_map_sock_delete(old_xs, map_entry); - spin_unlock_bh(&m->lock); - sockfd_put(sock); - return 0; - -out: - spin_unlock_bh(&m->lock); - sockfd_put(sock); - xsk_map_node_free(node); - return err; -} - -static int xsk_map_delete_elem(struct bpf_map *map, void *key) -{ - struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *old_xs, **map_entry; - int k = *(u32 *)key; - - if (k >= map->max_entries) - return -EINVAL; - - spin_lock_bh(&m->lock); - map_entry = &m->xsk_map[k]; - old_xs = xchg(map_entry, NULL); - if (old_xs) - xsk_map_sock_delete(old_xs, map_entry); - spin_unlock_bh(&m->lock); - - return 0; -} - -void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, - struct xdp_sock **map_entry) -{ - spin_lock_bh(&map->lock); - if (READ_ONCE(*map_entry) == xs) { - WRITE_ONCE(*map_entry, NULL); - xsk_map_sock_delete(xs, map_entry); - } - spin_unlock_bh(&map->lock); -} - -const struct bpf_map_ops xsk_map_ops = { - .map_alloc = xsk_map_alloc, - .map_free = xsk_map_free, - .map_get_next_key = xsk_map_get_next_key, - .map_lookup_elem = xsk_map_lookup_elem, - .map_gen_lookup = xsk_map_gen_lookup, - .map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only, - .map_update_elem = xsk_map_update_elem, - .map_delete_elem = xsk_map_delete_elem, - .map_check_btf = map_check_no_btf, -}; |