diff options
| -rw-r--r-- | drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/cavium/thunder/nicvf_main.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40e/i40e_txrx.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx4/en_rx.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/qlogic/qede/qede_fp.c | 1 | ||||
| -rw-r--r-- | drivers/net/tun.c | 1 | ||||
| -rw-r--r-- | drivers/net/virtio_net.c | 2 | ||||
| -rw-r--r-- | include/linux/bpf.h | 1 | ||||
| -rw-r--r-- | include/linux/filter.h | 21 | ||||
| -rw-r--r-- | include/linux/skbuff.h | 68 | ||||
| -rw-r--r-- | include/uapi/linux/bpf.h | 13 | ||||
| -rw-r--r-- | kernel/bpf/verifier.c | 114 | ||||
| -rw-r--r-- | net/bpf/test_run.c | 1 | ||||
| -rw-r--r-- | net/core/dev.c | 31 | ||||
| -rw-r--r-- | net/core/filter.c | 77 | ||||
| -rw-r--r-- | net/core/skbuff.c | 2 |
19 files changed, 297 insertions, 42 deletions
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index d8f0c83..06ce63c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -94,6 +94,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, xdp.data_hard_start = *data_ptr - offset; xdp.data = *data_ptr; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = *data_ptr + *len; orig_data = xdp.data; mapping = rx_buf->mapping - bp->rx_dma_offset; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 49b80da..d68478a 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -523,6 +523,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, xdp.data_hard_start = page_address(page); xdp.data = (void *)cpu_addr; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 1519dfb..f426762 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2107,6 +2107,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_hard_start = xdp.data - i40e_rx_offset(rx_ring); xdp.data_end = xdp.data + size; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d962368..04bb03b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2326,6 +2326,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, if (!skb) { xdp.data = page_address(rx_buffer->page) + rx_buffer->page_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_hard_start = xdp.data - ixgbe_rx_offset(rx_ring); xdp.data_end = xdp.data + size; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b97a55c8..8f9cb8a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -762,6 +762,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud xdp.data_hard_start = va - frags[0].page_offset; xdp.data = va; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + length; orig_data = xdp.data; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index f1dd638..30b3f3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -794,6 +794,7 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq, return false; xdp.data = va + *rx_headroom; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + *len; xdp.data_hard_start = va; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 1c0187f..e3a38be 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1583,6 +1583,7 @@ static int nfp_net_run_xdp(struct bpf_prog *prog, void *data, void *hard_start, xdp.data_hard_start = hard_start; xdp.data = data + *off; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = data + *off + *len; orig_data = xdp.data; diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 6fc854b..48ec4c5 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1004,6 +1004,7 @@ static bool qede_rx_xdp(struct qede_dev *edev, xdp.data_hard_start = page_address(bd->data); xdp.data = xdp.data_hard_start + *data_offset; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + *len; /* Queues always have a full reset currently, so for the time diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2c36f6e..a6e0bff 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1468,6 +1468,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, xdp.data_hard_start = buf; xdp.data = buf + pad; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index dd14a45..fc059f1 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -554,6 +554,7 @@ static struct sk_buff *receive_small(struct net_device *dev, xdp.data_hard_start = buf + VIRTNET_RX_PAD + vi->hdr_len; xdp.data = xdp.data_hard_start + xdp_headroom; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp); @@ -686,6 +687,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, data = page_address(xdp_page) + offset; xdp.data_hard_start = data - VIRTIO_XDP_HEADROOM + vi->hdr_len; xdp.data = data + vi->hdr_len; + xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + (len - vi->hdr_len); act = bpf_prog_run_xdp(xdp_prog, &xdp); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8390859..2b672c5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -137,6 +137,7 @@ enum bpf_reg_type { PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ PTR_TO_STACK, /* reg == frame_pointer + offset */ + PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 052bab3..911d454 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -487,12 +487,14 @@ struct sk_filter { struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; + void *data_meta; void *data_end; }; struct xdp_buff { void *data; void *data_end; + void *data_meta; void *data_hard_start; }; @@ -507,7 +509,8 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb) struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb)); - cb->data_end = skb->data + skb_headlen(skb); + cb->data_meta = skb->data - skb_metadata_len(skb); + cb->data_end = skb->data + skb_headlen(skb); } static inline u8 *bpf_skb_cb(struct sk_buff *skb) @@ -728,8 +731,22 @@ int xdp_do_redirect(struct net_device *dev, struct bpf_prog *prog); void xdp_do_flush_map(void); +/* Drivers not supporting XDP metadata can use this helper, which + * rejects any room expansion for metadata as a result. + */ +static __always_inline void +xdp_set_data_meta_invalid(struct xdp_buff *xdp) +{ + xdp->data_meta = xdp->data + 1; +} + +static __always_inline bool +xdp_data_meta_unsupported(const struct xdp_buff *xdp) +{ + return unlikely(xdp->data_meta > xdp->data); +} + void bpf_warn_invalid_xdp_action(u32 act); -void bpf_warn_invalid_xdp_redirect(u32 ifindex); struct sock *do_sk_redirect_map(void); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f9db553..19e64bf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -489,8 +489,9 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, * the end of the header data, ie. at skb->end. */ struct skb_shared_info { - unsigned short _unused; - unsigned char nr_frags; + __u8 __unused; + __u8 meta_len; + __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ @@ -3400,6 +3401,69 @@ static inline ktime_t net_invalid_timestamp(void) return 0; } +static inline u8 skb_metadata_len(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->meta_len; +} + +static inline void *skb_metadata_end(const struct sk_buff *skb) +{ + return skb_mac_header(skb); +} + +static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b, + u8 meta_len) +{ + const void *a = skb_metadata_end(skb_a); + const void *b = skb_metadata_end(skb_b); + /* Using more efficient varaiant than plain call to memcmp(). */ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + u64 diffs = 0; + + switch (meta_len) { +#define __it(x, op) (x -= sizeof(u##op)) +#define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) + case 32: diffs |= __it_diff(a, b, 64); + case 24: diffs |= __it_diff(a, b, 64); + case 16: diffs |= __it_diff(a, b, 64); + case 8: diffs |= __it_diff(a, b, 64); + break; + case 28: diffs |= __it_diff(a, b, 64); + case 20: diffs |= __it_diff(a, b, 64); + case 12: diffs |= __it_diff(a, b, 64); + case 4: diffs |= __it_diff(a, b, 32); + break; + } + return diffs; +#else + return memcmp(a - meta_len, b - meta_len, meta_len); +#endif +} + +static inline bool skb_metadata_differs(const struct sk_buff *skb_a, + const struct sk_buff *skb_b) +{ + u8 len_a = skb_metadata_len(skb_a); + u8 len_b = skb_metadata_len(skb_b); + + if (!(len_a | len_b)) + return false; + + return len_a != len_b ? + true : __skb_metadata_differs(skb_a, skb_b, len_a); +} + +static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) +{ + skb_shinfo(skb)->meta_len = meta_len; +} + +static inline void skb_metadata_clear(struct sk_buff *skb) +{ + skb_metadata_set(skb, 0); +} + struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 43ab5c4..e43491a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -582,6 +582,12 @@ union bpf_attr { * @map: pointer to sockmap to update * @key: key to insert/update sock in map * @flags: same flags as map update elem + * + * int bpf_xdp_adjust_meta(xdp_md, delta) + * Adjust the xdp_md.data_meta by delta + * @xdp_md: pointer to xdp_md + * @delta: An positive/negative integer to be added to xdp_md.data_meta + * Return: 0 on success or negative on error */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -638,6 +644,7 @@ union bpf_attr { FN(redirect_map), \ FN(sk_redirect_map), \ FN(sock_map_update), \ + FN(xdp_adjust_meta), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -715,7 +722,7 @@ struct __sk_buff { __u32 data_end; __u32 napi_id; - /* accessed by BPF_PROG_TYPE_sk_skb types */ + /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ __u32 family; __u32 remote_ip4; /* Stored in network byte order */ __u32 local_ip4; /* Stored in network byte order */ @@ -723,6 +730,9 @@ struct __sk_buff { __u32 local_ip6[4]; /* Stored in network byte order */ __u32 remote_port; /* Stored in network byte order */ __u32 local_port; /* stored in host byte order */ + /* ... here. */ + + __u32 data_meta; }; struct bpf_tunnel_key { @@ -783,6 +793,7 @@ enum xdp_action { struct xdp_md { __u32 data; __u32 data_end; + __u32 data_meta; }; enum sk_action { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b914fbe..f849eca 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -177,6 +177,12 @@ static __printf(1, 2) void verbose(const char *fmt, ...) va_end(args); } +static bool type_is_pkt_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_PACKET || + type == PTR_TO_PACKET_META; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -187,6 +193,7 @@ static const char * const reg_type_str[] = { [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", }; @@ -226,7 +233,7 @@ static void print_verifier_state(struct bpf_verifier_state *state) verbose("(id=%d", reg->id); if (t != SCALAR_VALUE) verbose(",off=%d", reg->off); - if (t == PTR_TO_PACKET) + if (type_is_pkt_pointer(t)) verbose(",r=%d", reg->range); else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || @@ -519,6 +526,31 @@ static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno) __mark_reg_known_zero(regs + regno); } +static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) +{ + return type_is_pkt_pointer(reg->type); +} + +static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) +{ + return reg_is_pkt_pointer(reg) || + reg->type == PTR_TO_PACKET_END; +} + +/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ +static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, + enum bpf_reg_type which) +{ + /* The register can already have a range from prior markings. + * This is fine as long as it hasn't been advanced from its + * origin. + */ + return reg->type == which && + reg->id == 0 && + reg->off == 0 && + tnum_equals_const(reg->var_off, 0); +} + /* Attempts to improve min/max values based on var_off information */ static void __update_reg_bounds(struct bpf_reg_state *reg) { @@ -702,6 +734,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: + case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: case CONST_PTR_TO_MAP: return true; @@ -1047,7 +1080,10 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, switch (reg->type) { case PTR_TO_PACKET: - /* special case, because of NET_IP_ALIGN */ + case PTR_TO_PACKET_META: + /* Special case, because of NET_IP_ALIGN. Given metadata sits + * right in front, treat it the very same way. + */ return check_pkt_ptr_alignment(reg, off, size, strict); case PTR_TO_MAP_VALUE: pointer_desc = "value "; @@ -1124,8 +1160,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a - * PTR_TO_PACKET[_END]. In the latter case, we know - * the offset is zero. + * PTR_TO_PACKET[_META,_END]. In the latter + * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) mark_reg_unknown(state->regs, value_regno); @@ -1170,7 +1206,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else { err = check_stack_read(state, off, size, value_regno); } - } else if (reg->type == PTR_TO_PACKET) { + } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose("cannot write into packet\n"); return -EACCES; @@ -1310,6 +1346,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, switch (reg->type) { case PTR_TO_PACKET: + case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size); case PTR_TO_MAP_VALUE: return check_map_access(env, regno, reg->off, access_size); @@ -1342,7 +1379,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return 0; } - if (type == PTR_TO_PACKET && + if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose("helper access to the packet is not allowed\n"); return -EACCES; @@ -1351,7 +1388,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - if (type != PTR_TO_PACKET && type != expected_type) + if (!type_is_pkt_pointer(type) && + type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO) { @@ -1375,7 +1413,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (register_is_null(*reg)) /* final test in check_stack_boundary() */; - else if (type != PTR_TO_PACKET && type != PTR_TO_MAP_VALUE && + else if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; @@ -1401,7 +1440,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->key\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->key_size); else @@ -1417,7 +1456,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->value\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->value_size); else @@ -1590,8 +1629,8 @@ static int check_raw_mode(const struct bpf_func_proto *fn) return count > 1 ? -EINVAL : 0; } -/* Packet data might have moved, any old PTR_TO_PACKET[_END] are now invalid, - * so turn them into unknown SCALAR_VALUE. +/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] + * are now invalid, so turn them into unknown SCALAR_VALUE. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { @@ -1600,18 +1639,15 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) int i; for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET || - regs[i].type == PTR_TO_PACKET_END) + if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(regs, i); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type != PTR_TO_PACKET && - reg->type != PTR_TO_PACKET_END) - continue; - __mark_reg_unknown(reg); + if (reg_is_pkt_pointer_any(reg)) + __mark_reg_unknown(reg); } } @@ -1871,7 +1907,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ dst_reg->range = 0; @@ -1931,7 +1967,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) @@ -2421,7 +2457,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } static void find_good_pkt_pointers(struct bpf_verifier_state *state, - struct bpf_reg_state *dst_reg) + struct bpf_reg_state *dst_reg, + enum bpf_reg_type type) { struct bpf_reg_state *regs = state->regs, *reg; int i; @@ -2483,7 +2520,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) + if (regs[i].type == type && regs[i].id == dst_reg->id) /* keep the maximum range already checked */ regs[i].range = max_t(u16, regs[i].range, dst_reg->off); @@ -2491,7 +2528,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) + if (reg->type == type && reg->id == dst_reg->id) reg->range = max_t(u16, reg->range, dst_reg->off); } } @@ -2856,19 +2893,39 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(this_branch, dst_reg); + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(other_branch, dst_reg); + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(other_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(this_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); } else if (is_pointer_value(env, insn->dst_reg)) { verbose("R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; @@ -3298,8 +3355,9 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; /* Check our ids match any regs they're supposed to */ return check_ids(rold->id, rcur->id, idmap); + case PTR_TO_PACKET_META: case PTR_TO_PACKET: - if (rcur->type != PTR_TO_PACKET) + if (rcur->type != rold->type) return false; /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index df67251..a86e668 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -162,6 +162,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, xdp.data_hard_start = data; xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN; + xdp.data_meta = xdp.data; xdp.data_end = xdp.data + size; retval = bpf_test_run(prog, &xdp, repeat, &duration); diff --git a/net/core/dev.c b/net/core/dev.c index 97abddd..e350c76 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3864,8 +3864,8 @@ drop: static u32 netif_receive_generic_xdp(struct sk_buff *skb, struct bpf_prog *xdp_prog) { + u32 metalen, act = XDP_DROP; struct xdp_buff xdp; - u32 act = XDP_DROP; void *orig_data; int hlen, off; u32 mac_len; @@ -3876,8 +3876,25 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, if (skb_cloned(skb)) return XDP_PASS; - if (skb_linearize(skb)) - goto do_drop; + /* XDP packets must be linear and must have sufficient headroom + * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also + * native XDP provides, thus we need to do it here as well. + */ + if (skb_is_nonlinear(skb) || + skb_headroom(skb) < XDP_PACKET_HEADROOM) { + int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); + int troom = skb->tail + skb->data_len - skb->end; + + /* In case we have to go down the path and also linearize, + * then lets do the pskb_expand_head() work just once here. + */ + if (pskb_expand_head(skb, + hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, + troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) + goto do_drop; + if (troom > 0 && __skb_linearize(skb)) + goto do_drop; + } /* The XDP program wants to see the packet starting at the MAC * header. @@ -3885,6 +3902,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, mac_len = skb->data - skb_mac_header(skb); hlen = skb_headlen(skb) + mac_len; xdp.data = skb->data - mac_len; + xdp.data_meta = xdp.data; xdp.data_end = xdp.data + hlen; xdp.data_hard_start = skb->data - skb_headroom(skb); orig_data = xdp.data; @@ -3902,10 +3920,12 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); - /* fall through */ + break; case XDP_PASS: + metalen = xdp.data - xdp.data_meta; + if (metalen) + skb_metadata_set(skb, metalen); break; - default: bpf_warn_invalid_xdp_action(act); /* fall through */ @@ -4695,6 +4715,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; diffs |= skb_metadata_dst_cmp(p, skb); + diffs |= skb_metadata_differs(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); diff --git a/net/core/filter.c b/net/core/filter.c index c468e7c..9b6e7e8 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2447,14 +2447,26 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; +static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) +{ + return xdp_data_meta_unsupported(xdp) ? 0 : + xdp->data - xdp->data_meta; +} + BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { + unsigned long metalen = xdp_get_metalen(xdp); + void *data_start = xdp->data_hard_start + metalen; void *data = xdp->data + offset; - if (unlikely(data < xdp->data_hard_start || + if (unlikely(data < data_start || data > xdp->data_end - ETH_HLEN)) return -EINVAL; + if (metalen) + memmove(xdp->data_meta + offset, + xdp->data_meta, metalen); + xdp->data_meta += offset; xdp->data = data; return 0; @@ -2468,6 +2480,33 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) +{ + void *meta = xdp->data_meta + offset; + unsigned long metalen = xdp->data - meta; + + if (xdp_data_meta_unsupported(xdp)) + return -ENOTSUPP; + if (unlikely(meta < xdp->data_hard_start || + meta > xdp->data)) + return -EINVAL; + if (unlikely((metalen & (sizeof(__u32) - 1)) || + (metalen > 32))) + return -EACCES; + + xdp->data_meta = meta; + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { + .func = bpf_xdp_adjust_meta, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + static int __bpf_tx_xdp(struct net_device *dev, struct bpf_map *map, struct xdp_buff *xdp, @@ -2692,7 +2731,8 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || - func == bpf_xdp_adjust_head) + func == bpf_xdp_adjust_head || + func == bpf_xdp_adjust_meta) return true; return false; @@ -3288,6 +3328,8 @@ xdp_func_proto(enum bpf_func_id func_id) return &bpf_get_smp_processor_id_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; + case BPF_FUNC_xdp_adjust_meta: + return &bpf_xdp_adjust_meta_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: @@ -3418,6 +3460,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; @@ -3444,6 +3487,7 @@ static bool sk_filter_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; @@ -3468,6 +3512,7 @@ static bool lwt_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): + case bpf_ctx_range(struct __sk_buff, data_meta): return false; } @@ -3586,6 +3631,9 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; + case bpf_ctx_range(struct __sk_buff, data_meta): + info->reg_type = PTR_TO_PACKET_META; + break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; @@ -3619,6 +3667,9 @@ static bool xdp_is_valid_access(int off, int size, case offsetof(struct xdp_md, data): info->reg_type = PTR_TO_PACKET; break; + case offsetof(struct xdp_md, data_meta): + info->reg_type = PTR_TO_PACKET_META; + break; case offsetof(struct xdp_md, data_end): info->reg_type = PTR_TO_PACKET_END; break; @@ -3677,6 +3728,12 @@ static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { + switch (off) { + case bpf_ctx_range(struct __sk_buff, tc_classid): + case bpf_ctx_range(struct __sk_buff, data_meta): + return false; + } + if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): @@ -3689,8 +3746,6 @@ static bool sk_skb_is_valid_access(int off, int size, } switch (off) { - case bpf_ctx_range(struct __sk_buff, tc_classid): - return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; @@ -3847,6 +3902,15 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, offsetof(struct sk_buff, data)); break; + case offsetof(struct __sk_buff, data_meta): + off = si->off; + off -= offsetof(struct __sk_buff, data_meta); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct bpf_skb_data_end, data_meta); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, + si->src_reg, off); + break; + case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); @@ -4095,6 +4159,11 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; + case offsetof(struct xdp_md, data_meta): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta), + si->dst_reg, si->src_reg, + offsetof(struct xdp_buff, data_meta)); + break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), si->dst_reg, si->src_reg, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 000ce73..d98c2e3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1509,6 +1509,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); + skb_metadata_clear(skb); + /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). |
