diff options
Diffstat (limited to 'net/core/filter.c')
-rw-r--r-- | net/core/filter.c | 1454 |
1 files changed, 1037 insertions, 417 deletions
diff --git a/net/core/filter.c b/net/core/filter.c index 4603b7cd3cd1..bb0136e7a8e4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -18,6 +18,7 @@ */ #include <linux/atomic.h> +#include <linux/bpf_verifier.h> #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> @@ -78,6 +79,7 @@ #include <linux/btf_ids.h> #include <net/tls.h> #include <net/xdp.h> +#include <net/mptcp.h> static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id); @@ -236,7 +238,7 @@ BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb, BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { - u16 tmp, *ptr; + __be16 tmp, *ptr; const int len = sizeof(tmp); if (offset >= 0) { @@ -263,7 +265,7 @@ BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb, BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { - u32 tmp, *ptr; + __be32 tmp, *ptr; const int len = sizeof(tmp); if (likely(offset >= 0)) { @@ -1213,10 +1215,11 @@ void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) { u32 filter_size = bpf_prog_size(fp->prog->len); + int optmem_max = READ_ONCE(sysctl_optmem_max); /* same check as in sock_kmalloc() */ - if (filter_size <= sysctl_optmem_max && - atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) { + if (filter_size <= optmem_max && + atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) { atomic_add(filter_size, &sk->sk_omem_alloc); return true; } @@ -1547,7 +1550,7 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - if (bpf_prog_size(prog->len) > sysctl_optmem_max) + if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) err = -ENOMEM; else err = reuseport_attach_prog(sk, prog); @@ -1614,7 +1617,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) } } else { /* BPF_PROG_TYPE_SOCKET_FILTER */ - if (bpf_prog_size(prog->len) > sysctl_optmem_max) { + if (bpf_prog_size(prog->len) > READ_ONCE(sysctl_optmem_max)) { err = -ENOMEM; goto err_prog_put; } @@ -1687,7 +1690,7 @@ BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset, if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; - if (unlikely(offset > 0xffff)) + if (unlikely(offset > INT_MAX)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; @@ -1722,7 +1725,7 @@ BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset, { void *ptr; - if (unlikely(offset > 0xffff)) + if (unlikely(offset > INT_MAX)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); @@ -2107,7 +2110,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) } skb->dev = dev; - skb->tstamp = 0; + skb_clear_tstamp(skb); dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); @@ -2176,7 +2179,7 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, } skb->dev = dev; - skb->tstamp = 0; + skb_clear_tstamp(skb); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); @@ -2274,7 +2277,7 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, } skb->dev = dev; - skb->tstamp = 0; + skb_clear_tstamp(skb); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); @@ -2603,7 +2606,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, * account for the headroom. */ bytes_sg_total = start - offset + bytes; - if (!test_bit(i, &msg->sg.copy) && bytes_sg_total <= len) + if (!test_bit(i, msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist @@ -2710,6 +2713,9 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, if (unlikely(flags)) return -EINVAL; + if (unlikely(len == 0)) + return 0; + /* First find the starting scatterlist element */ i = msg->sg.start; do { @@ -2809,7 +2815,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; - __clear_bit(new, &msg->sg.copy); + __clear_bit(new, msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); @@ -3005,7 +3011,7 @@ BPF_CALL_0(bpf_get_cgroup_classid_curr) return __task_get_classid(current); } -static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { +const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { .func = bpf_get_cgroup_classid_curr, .gpl_only = false, .ret_type = RET_INTEGER, @@ -3783,6 +3789,28 @@ static const struct bpf_func_proto sk_skb_change_head_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; + +BPF_CALL_1(bpf_xdp_get_buff_len, struct xdp_buff*, xdp) +{ + return xdp_get_buff_len(xdp); +} + +static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = { + .func = bpf_xdp_get_buff_len, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +BTF_ID_LIST_SINGLE(bpf_xdp_get_buff_len_bpf_ids, struct, xdp_buff) + +const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto = { + .func = bpf_xdp_get_buff_len, + .gpl_only = false, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_xdp_get_buff_len_bpf_ids[0], +}; + static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : @@ -3817,11 +3845,208 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +static void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, + void *buf, unsigned long len, bool flush) +{ + unsigned long ptr_len, ptr_off = 0; + skb_frag_t *next_frag, *end_frag; + struct skb_shared_info *sinfo; + void *src, *dst; + u8 *ptr_buf; + + if (likely(xdp->data_end - xdp->data >= off + len)) { + src = flush ? buf : xdp->data + off; + dst = flush ? xdp->data + off : buf; + memcpy(dst, src, len); + return; + } + + sinfo = xdp_get_shared_info_from_buff(xdp); + end_frag = &sinfo->frags[sinfo->nr_frags]; + next_frag = &sinfo->frags[0]; + + ptr_len = xdp->data_end - xdp->data; + ptr_buf = xdp->data; + + while (true) { + if (off < ptr_off + ptr_len) { + unsigned long copy_off = off - ptr_off; + unsigned long copy_len = min(len, ptr_len - copy_off); + + src = flush ? buf : ptr_buf + copy_off; + dst = flush ? ptr_buf + copy_off : buf; + memcpy(dst, src, copy_len); + + off += copy_len; + len -= copy_len; + buf += copy_len; + } + + if (!len || next_frag == end_frag) + break; + + ptr_off += ptr_len; + ptr_buf = skb_frag_address(next_frag); + ptr_len = skb_frag_size(next_frag); + next_frag++; + } +} + +static void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + u32 size = xdp->data_end - xdp->data; + void *addr = xdp->data; + int i; + + if (unlikely(offset > 0xffff || len > 0xffff)) + return ERR_PTR(-EFAULT); + + if (offset + len > xdp_get_buff_len(xdp)) + return ERR_PTR(-EINVAL); + + if (offset < size) /* linear area */ + goto out; + + offset -= size; + for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */ + u32 frag_size = skb_frag_size(&sinfo->frags[i]); + + if (offset < frag_size) { + addr = skb_frag_address(&sinfo->frags[i]); + size = frag_size; + break; + } + offset -= frag_size; + } +out: + return offset + len <= size ? addr + offset : NULL; +} + +BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset, + void *, buf, u32, len) +{ + void *ptr; + + ptr = bpf_xdp_pointer(xdp, offset, len); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + if (!ptr) + bpf_xdp_copy_buf(xdp, offset, buf, len, false); + else + memcpy(buf, ptr, len); + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_load_bytes_proto = { + .func = bpf_xdp_load_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + +BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset, + void *, buf, u32, len) +{ + void *ptr; + + ptr = bpf_xdp_pointer(xdp, offset, len); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + if (!ptr) + bpf_xdp_copy_buf(xdp, offset, buf, len, true); + else + memcpy(ptr, buf, len); + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_store_bytes_proto = { + .func = bpf_xdp_store_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + +static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; + struct xdp_rxq_info *rxq = xdp->rxq; + unsigned int tailroom; + + if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) + return -EOPNOTSUPP; + + tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag); + if (unlikely(offset > tailroom)) + return -EINVAL; + + memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset); + skb_frag_size_add(frag, offset); + sinfo->xdp_frags_size += offset; + + return 0; +} + +static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + int i, n_frags_free = 0, len_free = 0; + + if (unlikely(offset > (int)xdp_get_buff_len(xdp) - ETH_HLEN)) + return -EINVAL; + + for (i = sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) { + skb_frag_t *frag = &sinfo->frags[i]; + int shrink = min_t(int, offset, skb_frag_size(frag)); + + len_free += shrink; + offset -= shrink; + + if (skb_frag_size(frag) == shrink) { + struct page *page = skb_frag_page(frag); + + __xdp_return(page_address(page), &xdp->rxq->mem, + false, NULL); + n_frags_free++; + } else { + skb_frag_size_sub(frag, shrink); + break; + } + } + sinfo->nr_frags -= n_frags_free; + sinfo->xdp_frags_size -= len_free; + + if (unlikely(!sinfo->nr_frags)) { + xdp_buff_clear_frags_flag(xdp); + xdp->data_end -= offset; + } + + return 0; +} + BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) { void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */ void *data_end = xdp->data_end + offset; + if (unlikely(xdp_buff_has_frags(xdp))) { /* non-linear xdp buff */ + if (offset < 0) + return bpf_xdp_frags_shrink_tail(xdp, -offset); + + return bpf_xdp_frags_increase_tail(xdp, offset); + } + /* Notice that xdp_data_hard_end have reserved some tailroom */ if (unlikely(data_end > data_hard_end)) return -EINVAL; @@ -4047,6 +4272,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); enum bpf_map_type map_type = ri->map_type; + /* XDP_REDIRECT is not fully supported yet for xdp frags since + * not all XDP capable drivers can map non-linear xdp_frame in + * ndo_xdp_xmit. + */ + if (unlikely(xdp_buff_has_frags(xdp) && + map_type != BPF_MAP_TYPE_CPUMAP)) + return -EOPNOTSUPP; + if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); @@ -4257,7 +4490,8 @@ BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key void *to_orig = to; int err; - if (unlikely(!info || (flags & ~(BPF_F_TUNINFO_IPV6)))) { + if (unlikely(!info || (flags & ~(BPF_F_TUNINFO_IPV6 | + BPF_F_TUNINFO_FLAGS)))) { err = -EINVAL; goto err_clear; } @@ -4268,6 +4502,7 @@ BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key if (unlikely(size != sizeof(struct bpf_tunnel_key))) { err = -EINVAL; switch (size) { + case offsetof(struct bpf_tunnel_key, local_ipv6[0]): case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): goto set_compat; @@ -4288,15 +4523,22 @@ set_compat: to->tunnel_id = be64_to_cpu(info->key.tun_id); to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; - to->tunnel_ext = 0; + if (flags & BPF_F_TUNINFO_FLAGS) + to->tunnel_flags = info->key.tun_flags; + else + to->tunnel_ext = 0; if (flags & BPF_F_TUNINFO_IPV6) { memcpy(to->remote_ipv6, &info->key.u.ipv6.src, sizeof(to->remote_ipv6)); + memcpy(to->local_ipv6, &info->key.u.ipv6.dst, + sizeof(to->local_ipv6)); to->tunnel_label = be32_to_cpu(info->key.label); } else { to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); + to->local_ipv4 = be32_to_cpu(info->key.u.ipv4.dst); + memset(&to->local_ipv6[1], 0, sizeof(__u32) * 3); to->tunnel_label = 0; } @@ -4367,6 +4609,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { + case offsetof(struct bpf_tunnel_key, local_ipv6[0]): case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): @@ -4409,10 +4652,14 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, info->mode |= IP_TUNNEL_INFO_IPV6; memcpy(&info->key.u.ipv6.dst, from->remote_ipv6, sizeof(from->remote_ipv6)); + memcpy(&info->key.u.ipv6.src, from->local_ipv6, + sizeof(from->local_ipv6)); info->key.label = cpu_to_be32(from->tunnel_label) & IPV6_FLOWLABEL_MASK; } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); + info->key.u.ipv4.src = cpu_to_be32(from->local_ipv4); + info->key.flow_flags = FLOWI_FLAG_ANYSRC; } return 0; @@ -4590,10 +4837,12 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { }; #endif -static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, +static unsigned long bpf_xdp_copy(void *dst, const void *ctx, unsigned long off, unsigned long len) { - memcpy(dst_buff, src_buff + off, len); + struct xdp_buff *xdp = (struct xdp_buff *)ctx; + + bpf_xdp_copy_buf(xdp, off, dst, len, false); return 0; } @@ -4604,11 +4853,11 @@ BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; - if (unlikely(!xdp || - xdp_size > (unsigned long)(xdp->data_end - xdp->data))) + + if (unlikely(!xdp || xdp_size > xdp_get_buff_len(xdp))) return -EFAULT; - return bpf_event_output(map, flags, meta, meta_size, xdp->data, + return bpf_event_output(map, flags, meta, meta_size, xdp, xdp_size, bpf_xdp_copy); } @@ -4770,353 +5019,316 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -static int _bpf_setsockopt(struct sock *sk, int level, int optname, - char *optval, int optlen) +static int sol_socket_sockopt(struct sock *sk, int optname, + char *optval, int *optlen, + bool getopt) +{ + switch (optname) { + case SO_REUSEADDR: + case SO_SNDBUF: + case SO_RCVBUF: + case SO_KEEPALIVE: + case SO_PRIORITY: + case SO_REUSEPORT: + case SO_RCVLOWAT: + case SO_MARK: + case SO_MAX_PACING_RATE: + case SO_BINDTOIFINDEX: + case SO_TXREHASH: + if (*optlen != sizeof(int)) + return -EINVAL; + break; + case SO_BINDTODEVICE: + break; + default: + return -EINVAL; + } + + if (getopt) { + if (optname == SO_BINDTODEVICE) + return -EINVAL; + return sk_getsockopt(sk, SOL_SOCKET, optname, + KERNEL_SOCKPTR(optval), + KERNEL_SOCKPTR(optlen)); + } + + return sk_setsockopt(sk, SOL_SOCKET, optname, + KERNEL_SOCKPTR(optval), *optlen); +} + +static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname, + char *optval, int optlen) { - char devname[IFNAMSIZ]; - int val, valbool; - struct net *net; - int ifindex; - int ret = 0; + struct tcp_sock *tp = tcp_sk(sk); + unsigned long timeout; + int val; - if (!sk_fullsock(sk)) + if (optlen != sizeof(int)) return -EINVAL; - sock_owned_by_me(sk); + val = *(int *)optval; - if (level == SOL_SOCKET) { - if (optlen != sizeof(int) && optname != SO_BINDTODEVICE) + /* Only some options are supported */ + switch (optname) { + case TCP_BPF_IW: + if (val <= 0 || tp->data_segs_out > tp->syn_data) return -EINVAL; - val = *((int *)optval); - valbool = val ? 1 : 0; - - /* Only some socketops are supported */ - switch (optname) { - case SO_RCVBUF: - val = min_t(u32, val, sysctl_rmem_max); - val = min_t(int, val, INT_MAX / 2); - sk->sk_userlocks |= SOCK_RCVBUF_LOCK; - WRITE_ONCE(sk->sk_rcvbuf, - max_t(int, val * 2, SOCK_MIN_RCVBUF)); - break; - case SO_SNDBUF: - val = min_t(u32, val, sysctl_wmem_max); - val = min_t(int, val, INT_MAX / 2); - sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - WRITE_ONCE(sk->sk_sndbuf, - max_t(int, val * 2, SOCK_MIN_SNDBUF)); - break; - case SO_MAX_PACING_RATE: /* 32bit version */ - if (val != ~0U) - cmpxchg(&sk->sk_pacing_status, - SK_PACING_NONE, - SK_PACING_NEEDED); - sk->sk_max_pacing_rate = (val == ~0U) ? - ~0UL : (unsigned int)val; - sk->sk_pacing_rate = min(sk->sk_pacing_rate, - sk->sk_max_pacing_rate); - break; - case SO_PRIORITY: - sk->sk_priority = val; - break; - case SO_RCVLOWAT: - if (val < 0) - val = INT_MAX; - WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); - break; - case SO_MARK: - if (sk->sk_mark != val) { - sk->sk_mark = val; - sk_dst_reset(sk); - } - break; - case SO_BINDTODEVICE: - optlen = min_t(long, optlen, IFNAMSIZ - 1); - strncpy(devname, optval, optlen); - devname[optlen] = 0; + tcp_snd_cwnd_set(tp, val); + break; + case TCP_BPF_SNDCWND_CLAMP: + if (val <= 0) + return -EINVAL; + tp->snd_cwnd_clamp = val; + tp->snd_ssthresh = val; + break; + case TCP_BPF_DELACK_MAX: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_DELACK_MAX || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_delack_max = timeout; + break; + case TCP_BPF_RTO_MIN: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_RTO_MIN || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_rto_min = timeout; + break; + default: + return -EINVAL; + } - ifindex = 0; - if (devname[0] != '\0') { - struct net_device *dev; + return 0; +} - ret = -ENODEV; +static int sol_tcp_sockopt_congestion(struct sock *sk, char *optval, + int *optlen, bool getopt) +{ + struct tcp_sock *tp; + int ret; - net = sock_net(sk); - dev = dev_get_by_name(net, devname); - if (!dev) - break; - ifindex = dev->ifindex; - dev_put(dev); - } - fallthrough; - case SO_BINDTOIFINDEX: - if (optname == SO_BINDTOIFINDEX) - ifindex = val; - ret = sock_bindtoindex(sk, ifindex, false); - break; - case SO_KEEPALIVE: - if (sk->sk_prot->keepalive) - sk->sk_prot->keepalive(sk, valbool); - sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); - break; - case SO_REUSEPORT: - sk->sk_reuseport = valbool; - break; - default: - ret = -EINVAL; - } -#ifdef CONFIG_INET - } else if (level == SOL_IP) { - if (optlen != sizeof(int) || sk->sk_family != AF_INET) + if (*optlen < 2) + return -EINVAL; + + if (getopt) { + if (!inet_csk(sk)->icsk_ca_ops) return -EINVAL; + /* BPF expects NULL-terminated tcp-cc string */ + optval[--(*optlen)] = '\0'; + return do_tcp_getsockopt(sk, SOL_TCP, TCP_CONGESTION, + KERNEL_SOCKPTR(optval), + KERNEL_SOCKPTR(optlen)); + } - val = *((int *)optval); - /* Only some options are supported */ - switch (optname) { - case IP_TOS: - if (val < -1 || val > 0xff) { - ret = -EINVAL; - } else { - struct inet_sock *inet = inet_sk(sk); + /* "cdg" is the only cc that alloc a ptr + * in inet_csk_ca area. The bpf-tcp-cc may + * overwrite this ptr after switching to cdg. + */ + if (*optlen >= sizeof("cdg") - 1 && !strncmp("cdg", optval, *optlen)) + return -ENOTSUPP; - if (val == -1) - val = 0; - inet->tos = val; - } - break; - default: - ret = -EINVAL; - } -#if IS_ENABLED(CONFIG_IPV6) - } else if (level == SOL_IPV6) { - if (optlen != sizeof(int) || sk->sk_family != AF_INET6) - return -EINVAL; + /* It stops this looping + * + * .init => bpf_setsockopt(tcp_cc) => .init => + * bpf_setsockopt(tcp_cc)" => .init => .... + * + * The second bpf_setsockopt(tcp_cc) is not allowed + * in order to break the loop when both .init + * are the same bpf prog. + * + * This applies even the second bpf_setsockopt(tcp_cc) + * does not cause a loop. This limits only the first + * '.init' can call bpf_setsockopt(TCP_CONGESTION) to + * pick a fallback cc (eg. peer does not support ECN) + * and the second '.init' cannot fallback to + * another. + */ + tp = tcp_sk(sk); + if (tp->bpf_chg_cc_inprogress) + return -EBUSY; + + tp->bpf_chg_cc_inprogress = 1; + ret = do_tcp_setsockopt(sk, SOL_TCP, TCP_CONGESTION, + KERNEL_SOCKPTR(optval), *optlen); + tp->bpf_chg_cc_inprogress = 0; + return ret; +} - val = *((int *)optval); - /* Only some options are supported */ - switch (optname) { - case IPV6_TCLASS: - if (val < -1 || val > 0xff) { - ret = -EINVAL; - } else { - struct ipv6_pinfo *np = inet6_sk(sk); +static int sol_tcp_sockopt(struct sock *sk, int optname, + char *optval, int *optlen, + bool getopt) +{ + if (sk->sk_prot->setsockopt != tcp_setsockopt) + return -EINVAL; - if (val == -1) - val = 0; - np->tclass = val; - } - break; - default: - ret = -EINVAL; - } -#endif - } else if (level == SOL_TCP && - sk->sk_prot->setsockopt == tcp_setsockopt) { - if (optname == TCP_CONGESTION) { - char name[TCP_CA_NAME_MAX]; - - strncpy(name, optval, min_t(long, optlen, - TCP_CA_NAME_MAX-1)); - name[TCP_CA_NAME_MAX-1] = 0; - ret = tcp_set_congestion_control(sk, name, false, true); - } else { - struct inet_connection_sock *icsk = inet_csk(sk); + switch (optname) { + case TCP_NODELAY: + case TCP_MAXSEG: + case TCP_KEEPIDLE: + case TCP_KEEPINTVL: + case TCP_KEEPCNT: + case TCP_SYNCNT: + case TCP_WINDOW_CLAMP: + case TCP_THIN_LINEAR_TIMEOUTS: + case TCP_USER_TIMEOUT: + case TCP_NOTSENT_LOWAT: + case TCP_SAVE_SYN: + if (*optlen != sizeof(int)) + return -EINVAL; + break; + case TCP_CONGESTION: + return sol_tcp_sockopt_congestion(sk, optval, optlen, getopt); + case TCP_SAVED_SYN: + if (*optlen < 1) + return -EINVAL; + break; + default: + if (getopt) + return -EINVAL; + return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen); + } + + if (getopt) { + if (optname == TCP_SAVED_SYN) { struct tcp_sock *tp = tcp_sk(sk); - unsigned long timeout; - if (optlen != sizeof(int)) + if (!tp->saved_syn || + *optlen > tcp_saved_syn_len(tp->saved_syn)) return -EINVAL; - - val = *((int *)optval); - /* Only some options are supported */ - switch (optname) { - case TCP_BPF_IW: - if (val <= 0 || tp->data_segs_out > tp->syn_data) - ret = -EINVAL; - else - tp->snd_cwnd = val; - break; - case TCP_BPF_SNDCWND_CLAMP: - if (val <= 0) { - ret = -EINVAL; - } else { - tp->snd_cwnd_clamp = val; - tp->snd_ssthresh = val; - } - break; - case TCP_BPF_DELACK_MAX: - timeout = usecs_to_jiffies(val); - if (timeout > TCP_DELACK_MAX || - timeout < TCP_TIMEOUT_MIN) - return -EINVAL; - inet_csk(sk)->icsk_delack_max = timeout; - break; - case TCP_BPF_RTO_MIN: - timeout = usecs_to_jiffies(val); - if (timeout > TCP_RTO_MIN || - timeout < TCP_TIMEOUT_MIN) - return -EINVAL; - inet_csk(sk)->icsk_rto_min = timeout; - break; - case TCP_SAVE_SYN: - if (val < 0 || val > 1) - ret = -EINVAL; - else - tp->save_syn = val; - break; - case TCP_KEEPIDLE: - ret = tcp_sock_set_keepidle_locked(sk, val); - break; - case TCP_KEEPINTVL: - if (val < 1 || val > MAX_TCP_KEEPINTVL) - ret = -EINVAL; - else - tp->keepalive_intvl = val * HZ; - break; - case TCP_KEEPCNT: - if (val < 1 || val > MAX_TCP_KEEPCNT) - ret = -EINVAL; - else - tp->keepalive_probes = val; - break; - case TCP_SYNCNT: - if (val < 1 || val > MAX_TCP_SYNCNT) - ret = -EINVAL; - else - icsk->icsk_syn_retries = val; - break; - case TCP_USER_TIMEOUT: - if (val < 0) - ret = -EINVAL; - else - icsk->icsk_user_timeout = val; - break; - case TCP_NOTSENT_LOWAT: - tp->notsent_lowat = val; - sk->sk_write_space(sk); - break; - case TCP_WINDOW_CLAMP: - ret = tcp_set_window_clamp(sk, val); - break; - default: - ret = -EINVAL; - } + memcpy(optval, tp->saved_syn->data, *optlen); + /* It cannot free tp->saved_syn here because it + * does not know if the user space still needs it. + */ + return 0; } -#endif - } else { - ret = -EINVAL; + + return do_tcp_getsockopt(sk, SOL_TCP, optname, + KERNEL_SOCKPTR(optval), + KERNEL_SOCKPTR(optlen)); } - return ret; + + return do_tcp_setsockopt(sk, SOL_TCP, optname, + KERNEL_SOCKPTR(optval), *optlen); } -static int _bpf_getsockopt(struct sock *sk, int level, int optname, - char *optval, int optlen) +static int sol_ip_sockopt(struct sock *sk, int optname, + char *optval, int *optlen, + bool getopt) { - if (!sk_fullsock(sk)) - goto err_clear; + if (sk->sk_family != AF_INET) + return -EINVAL; - sock_owned_by_me(sk); + switch (optname) { + case IP_TOS: + if (*optlen != sizeof(int)) + return -EINVAL; + break; + default: + return -EINVAL; + } - if (level == SOL_SOCKET) { - if (optlen != sizeof(int)) - goto err_clear; + if (getopt) + return do_ip_getsockopt(sk, SOL_IP, optname, + KERNEL_SOCKPTR(optval), + KERNEL_SOCKPTR(optlen)); - switch (optname) { - case SO_RCVBUF: - *((int *)optval) = sk->sk_rcvbuf; - break; - case SO_SNDBUF: - *((int *)optval) = sk->sk_sndbuf; - break; - case SO_MARK: - *((int *)optval) = sk->sk_mark; - break; - case SO_PRIORITY: - *((int *)optval) = sk->sk_priority; - break; - case SO_BINDTOIFINDEX: - *((int *)optval) = sk->sk_bound_dev_if; - break; - case SO_REUSEPORT: - *((int *)optval) = sk->sk_reuseport; - break; - default: - goto err_clear; - } -#ifdef CONFIG_INET - } else if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { - struct inet_connection_sock *icsk; - struct tcp_sock *tp; + return do_ip_setsockopt(sk, SOL_IP, optname, + KERNEL_SOCKPTR(optval), *optlen); +} - switch (optname) { - case TCP_CONGESTION: - icsk = inet_csk(sk); +static int sol_ipv6_sockopt(struct sock *sk, int optname, + char *optval, int *optlen, + bool getopt) +{ + if (sk->sk_family != AF_INET6) + return -EINVAL; - if (!icsk->icsk_ca_ops || optlen <= 1) - goto err_clear; - strncpy(optval, icsk->icsk_ca_ops->name, optlen); - optval[optlen - 1] = 0; - break; - case TCP_SAVED_SYN: - tp = tcp_sk(sk); + switch (optname) { + case IPV6_TCLASS: + case IPV6_AUTOFLOWLABEL: + if (*optlen != sizeof(int)) + return -EINVAL; + break; + default: + return -EINVAL; + } - if (optlen <= 0 || !tp->saved_syn || - optlen > tcp_saved_syn_len(tp->saved_syn)) - goto err_clear; - memcpy(optval, tp->saved_syn->data, optlen); - break; - default: - goto err_clear; - } - } else if (level == SOL_IP) { - struct inet_sock *inet = inet_sk(sk); + if (getopt) + return ipv6_bpf_stub->ipv6_getsockopt(sk, SOL_IPV6, optname, + KERNEL_SOCKPTR(optval), + KERNEL_SOCKPTR(optlen)); - if (optlen != sizeof(int) || sk->sk_family != AF_INET) - goto err_clear; + return ipv6_bpf_stub->ipv6_setsockopt(sk, SOL_IPV6, optname, + KERNEL_SOCKPTR(optval), *optlen); +} - /* Only some options are supported */ - switch (optname) { - case IP_TOS: - *((int *)optval) = (int)inet->tos; - break; - default: - goto err_clear; - } -#if IS_ENABLED(CONFIG_IPV6) - } else if (level == SOL_IPV6) { - struct ipv6_pinfo *np = inet6_sk(sk); +static int __bpf_setsockopt(struct sock *sk, int level, int optname, + char *optval, int optlen) +{ + if (!sk_fullsock(sk)) + return -EINVAL; - if (optlen != sizeof(int) || sk->sk_family != AF_INET6) - goto err_clear; + if (level == SOL_SOCKET) + return sol_socket_sockopt(sk, optname, optval, &optlen, false); + else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) + return sol_ip_sockopt(sk, optname, optval, &optlen, false); + else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) + return sol_ipv6_sockopt(sk, optname, optval, &optlen, false); + else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) + return sol_tcp_sockopt(sk, optname, optval, &optlen, false); - /* Only some options are supported */ - switch (optname) { - case IPV6_TCLASS: - *((int *)optval) = (int)np->tclass; - break; - default: - goto err_clear; - } -#endif -#endif - } else { - goto err_clear; - } - return 0; -err_clear: - memset(optval, 0, optlen); return -EINVAL; } -BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level, - int, optname, char *, optval, int, optlen) +static int _bpf_setsockopt(struct sock *sk, int level, int optname, + char *optval, int optlen) { - if (level == SOL_TCP && optname == TCP_CONGESTION) { - if (optlen >= sizeof("cdg") - 1 && - !strncmp("cdg", optval, optlen)) - return -ENOTSUPP; + if (sk_fullsock(sk)) + sock_owned_by_me(sk); + return __bpf_setsockopt(sk, level, optname, optval, optlen); +} + +static int __bpf_getsockopt(struct sock *sk, int level, int optname, + char *optval, int optlen) +{ + int err, saved_optlen = optlen; + + if (!sk_fullsock(sk)) { + err = -EINVAL; + goto done; } + if (level == SOL_SOCKET) + err = sol_socket_sockopt(sk, optname, optval, &optlen, true); + else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) + err = sol_tcp_sockopt(sk, optname, optval, &optlen, true); + else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) + err = sol_ip_sockopt(sk, optname, optval, &optlen, true); + else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) + err = sol_ipv6_sockopt(sk, optname, optval, &optlen, true); + else + err = -EINVAL; + +done: + if (err) + optlen = 0; + if (optlen < saved_optlen) + memset(optval + optlen, 0, saved_optlen - optlen); + return err; +} + +static int _bpf_getsockopt(struct sock *sk, int level, int optname, + char *optval, int optlen) +{ + if (sk_fullsock(sk)) + sock_owned_by_me(sk); + return __bpf_getsockopt(sk, level, optname, optval, optlen); +} + +BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level, + int, optname, char *, optval, int, optlen) +{ return _bpf_setsockopt(sk, level, optname, optval, optlen); } @@ -5148,6 +5360,40 @@ const struct bpf_func_proto bpf_sk_getsockopt_proto = { .arg5_type = ARG_CONST_SIZE, }; +BPF_CALL_5(bpf_unlocked_sk_setsockopt, struct sock *, sk, int, level, + int, optname, char *, optval, int, optlen) +{ + return __bpf_setsockopt(sk, level, optname, optval, optlen); +} + +const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto = { + .func = bpf_unlocked_sk_setsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg5_type = ARG_CONST_SIZE, +}; + +BPF_CALL_5(bpf_unlocked_sk_getsockopt, struct sock *, sk, int, level, + int, optname, char *, optval, int, optlen) +{ + return __bpf_getsockopt(sk, level, optname, optval, optlen); +} + +const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto = { + .func = bpf_unlocked_sk_getsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_UNINIT_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { @@ -5906,7 +6152,6 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len if (err) return err; - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); return seg6_lookup_nexthop(skb, NULL, 0); @@ -6167,6 +6412,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, int dif, int sdif, u8 family, u8 proto) { + struct inet_hashinfo *hinfo = net->ipv4.tcp_death_row.hashinfo; bool refcounted = false; struct sock *sk = NULL; @@ -6175,7 +6421,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, __be32 dst4 = tuple->ipv4.daddr; if (proto == IPPROTO_TCP) - sk = __inet_lookup(net, &tcp_hashinfo, NULL, 0, + sk = __inet_lookup(net, hinfo, NULL, 0, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, &refcounted); @@ -6189,7 +6435,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; if (proto == IPPROTO_TCP) - sk = __inet6_lookup(net, &tcp_hashinfo, NULL, 0, + sk = __inet6_lookup(net, hinfo, NULL, 0, src6, tuple->ipv6.sport, dst6, ntohs(tuple->ipv6.dport), dif, sdif, &refcounted); @@ -6211,8 +6457,6 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, /* bpf_skc_lookup performs the core lookup for different types of sockets, * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE. - * Returns the socket as an 'unsigned long' to simplify the casting in the - * callers to satisfy BPF_CALL declarations. */ static struct sock * __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, @@ -6220,8 +6464,8 @@ __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u64 flags) { struct sock *sk = NULL; - u8 family = AF_UNSPEC; struct net *net; + u8 family; int sdif; if (len == sizeof(tuple->ipv4)) @@ -6231,8 +6475,7 @@ __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, else return NULL; - if (unlikely(family == AF_UNSPEC || flags || - !((s32)netns_id < 0 || netns_id <= S32_MAX))) + if (unlikely(flags || !((s32)netns_id < 0 || netns_id <= S32_MAX))) goto out; if (family == AF_INET) @@ -6264,10 +6507,21 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, ifindex, proto, netns_id, flags); if (sk) { - sk = sk_to_full_sk(sk); - if (!sk_fullsock(sk)) { + struct sock *sk2 = sk_to_full_sk(sk); + + /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk + * sock refcnt is decremented to prevent a request_sock leak. + */ + if (!sk_fullsock(sk2)) + sk2 = NULL; + if (sk2 != sk) { sock_gen_put(sk); - return NULL; + /* Ensure there is no need to bump sk2 refcnt */ + if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { + WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); + return NULL; + } + sk = sk2; } } @@ -6301,10 +6555,21 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, flags); if (sk) { - sk = sk_to_full_sk(sk); - if (!sk_fullsock(sk)) { + struct sock *sk2 = sk_to_full_sk(sk); + + /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk + * sock refcnt is decremented to prevent a request_sock leak. + */ + if (!sk_fullsock(sk2)) + sk2 = NULL; + if (sk2 != sk) { sock_gen_put(sk); - return NULL; + /* Ensure there is no need to bump sk2 refcnt */ + if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { + WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); + return NULL; + } + sk = sk2; } } @@ -6379,7 +6644,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = { .func = bpf_sk_release, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | OBJ_RELEASE, }; BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, @@ -6768,30 +7033,39 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -EINVAL; if (!th->ack || th->rst || th->syn) return -ENOENT; + if (unlikely(iph_len < sizeof(struct iphdr))) + return -EINVAL; + if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; cookie = ntohl(th->ack_seq) - 1; - switch (sk->sk_family) { - case AF_INET: - if (unlikely(iph_len < sizeof(struct iphdr))) + /* Both struct iphdr and struct ipv6hdr have the version field at the + * same offset so we can cast to the shorter header (struct iphdr). + */ + switch (((struct iphdr *)iph)->version) { + case 4: + if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th, cookie); break; #if IS_BUILTIN(CONFIG_IPV6) - case AF_INET6: + case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; + if (sk->sk_family != AF_INET6) + return -EINVAL; + ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie); break; #endif /* CONFIG_IPV6 */ @@ -6834,7 +7108,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -ENOENT; if (!th->syn || th->ack || th->fin || th->rst) @@ -6848,7 +7122,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, */ switch (((struct iphdr *)iph)->version) { case 4: - if (sk->sk_family == AF_INET6 && sk->sk_ipv6only) + if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; mss = tcp_v4_get_syncookie(sk, iph, th, &cookie); @@ -7146,6 +7420,151 @@ static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb, + u64, tstamp, u32, tstamp_type) +{ + /* skb_clear_delivery_time() is done for inet protocol */ + if (skb->protocol != htons(ETH_P_IP) && + skb->protocol != htons(ETH_P_IPV6)) + return -EOPNOTSUPP; + + switch (tstamp_type) { + case BPF_SKB_TSTAMP_DELIVERY_MONO: + if (!tstamp) + return -EINVAL; + skb->tstamp = tstamp; + skb->mono_delivery_time = 1; + break; + case BPF_SKB_TSTAMP_UNSPEC: + if (tstamp) + return -EINVAL; + skb->tstamp = 0; + skb->mono_delivery_time = 0; + break; + default: + return -EINVAL; + } + + return 0; +} + +static const struct bpf_func_proto bpf_skb_set_tstamp_proto = { + .func = bpf_skb_set_tstamp, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + +#ifdef CONFIG_SYN_COOKIES +BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv4, struct iphdr *, iph, + struct tcphdr *, th, u32, th_len) +{ + u32 cookie; + u16 mss; + + if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) + return -EINVAL; + + mss = tcp_parse_mss_option(th, 0) ?: TCP_MSS_DEFAULT; + cookie = __cookie_v4_init_sequence(iph, th, &mss); + + return cookie | ((u64)mss << 32); +} + +static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = { + .func = bpf_tcp_raw_gen_syncookie_ipv4, + .gpl_only = true, /* __cookie_v4_init_sequence() is GPL */ + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_size = sizeof(struct iphdr), + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + +BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph, + struct tcphdr *, th, u32, th_len) +{ +#if IS_BUILTIN(CONFIG_IPV6) + const u16 mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - + sizeof(struct ipv6hdr); + u32 cookie; + u16 mss; + + if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) + return -EINVAL; + + mss = tcp_parse_mss_option(th, 0) ?: mss_clamp; + cookie = __cookie_v6_init_sequence(iph, th, &mss); + + return cookie | ((u64)mss << 32); +#else + return -EPROTONOSUPPORT; +#endif +} + +static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { + .func = bpf_tcp_raw_gen_syncookie_ipv6, + .gpl_only = true, /* __cookie_v6_init_sequence() is GPL */ + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_size = sizeof(struct ipv6hdr), + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + +BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph, + struct tcphdr *, th) +{ + u32 cookie = ntohl(th->ack_seq) - 1; + + if (__cookie_v4_check(iph, th, cookie) > 0) + return 0; + + return -EACCES; +} + +static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv4_proto = { + .func = bpf_tcp_raw_check_syncookie_ipv4, + .gpl_only = true, /* __cookie_v4_check is GPL */ + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_size = sizeof(struct iphdr), + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg2_size = sizeof(struct tcphdr), +}; + +BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph, + struct tcphdr *, th) +{ +#if IS_BUILTIN(CONFIG_IPV6) + u32 cookie = ntohl(th->ack_seq) - 1; + + if (__cookie_v6_check(iph, th, cookie) > 0) + return 0; + + return -EACCES; +#else + return -EPROTONOSUPPORT; +#endif +} + +static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = { + .func = bpf_tcp_raw_check_syncookie_ipv6, + .gpl_only = true, /* __cookie_v6_check is GPL */ + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg1_size = sizeof(struct ipv6hdr), + .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, + .arg2_size = sizeof(struct tcphdr), +}; +#endif /* CONFIG_SYN_COOKIES */ + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -7192,34 +7611,23 @@ const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto __weak; static const struct bpf_func_proto * sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { + const struct bpf_func_proto *func_proto; + + func_proto = cgroup_common_func_proto(func_id, prog); + if (func_proto) + return func_proto; + + func_proto = cgroup_current_func_proto(func_id, prog); + if (func_proto) + return func_proto; + switch (func_id) { - /* inet and inet6 sockets are created in a process - * context so there is always a valid uid/gid - */ - case BPF_FUNC_get_current_uid_gid: - return &bpf_get_current_uid_gid_proto; - case BPF_FUNC_get_local_storage: - return &bpf_get_local_storage_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; - case BPF_FUNC_get_current_pid_tgid: - return &bpf_get_current_pid_tgid_proto; - case BPF_FUNC_get_current_comm: - return &bpf_get_current_comm_proto; -#ifdef CONFIG_CGROUPS - case BPF_FUNC_get_current_cgroup_id: - return &bpf_get_current_cgroup_id_proto; - case BPF_FUNC_get_current_ancestor_cgroup_id: - return &bpf_get_current_ancestor_cgroup_id_proto; -#endif -#ifdef CONFIG_CGROUP_NET_CLASSID - case BPF_FUNC_get_cgroup_classid: - return &bpf_get_cgroup_classid_curr_proto; -#endif case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_cg_sock_proto; case BPF_FUNC_ktime_get_coarse_ns: @@ -7232,12 +7640,17 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) static const struct bpf_func_proto * sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { + const struct bpf_func_proto *func_proto; + + func_proto = cgroup_common_func_proto(func_id, prog); + if (func_proto) + return func_proto; + + func_proto = cgroup_current_func_proto(func_id, prog); + if (func_proto) + return func_proto; + switch (func_id) { - /* inet and inet6 sockets are created in a process - * context so there is always a valid uid/gid - */ - case BPF_FUNC_get_current_uid_gid: - return &bpf_get_current_uid_gid_proto; case BPF_FUNC_bind: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_CONNECT: @@ -7250,24 +7663,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_cookie_sock_addr_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_addr_proto; - case BPF_FUNC_get_local_storage: - return &bpf_get_local_storage_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; - case BPF_FUNC_get_current_pid_tgid: - return &bpf_get_current_pid_tgid_proto; - case BPF_FUNC_get_current_comm: - return &bpf_get_current_comm_proto; -#ifdef CONFIG_CGROUPS - case BPF_FUNC_get_current_cgroup_id: - return &bpf_get_current_cgroup_id_proto; - case BPF_FUNC_get_current_ancestor_cgroup_id: - return &bpf_get_current_ancestor_cgroup_id_proto; -#endif -#ifdef CONFIG_CGROUP_NET_CLASSID - case BPF_FUNC_get_cgroup_classid: - return &bpf_get_cgroup_classid_curr_proto; -#endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sock_addr_sk_lookup_tcp_proto; @@ -7348,9 +7745,13 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto __weak; static const struct bpf_func_proto * cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { + const struct bpf_func_proto *func_proto; + + func_proto = cgroup_common_func_proto(func_id, prog); + if (func_proto) + return func_proto; + switch (func_id) { - case BPF_FUNC_get_local_storage: - return &bpf_get_local_storage_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: @@ -7507,6 +7908,18 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_gen_syncookie_proto; case BPF_FUNC_sk_assign: return &bpf_sk_assign_proto; + case BPF_FUNC_skb_set_tstamp: + return &bpf_skb_set_tstamp_proto; +#ifdef CONFIG_SYN_COOKIES + case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: + return &bpf_tcp_raw_gen_syncookie_ipv4_proto; + case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: + return &bpf_tcp_raw_gen_syncookie_ipv6_proto; + case BPF_FUNC_tcp_raw_check_syncookie_ipv4: + return &bpf_tcp_raw_check_syncookie_ipv4_proto; + case BPF_FUNC_tcp_raw_check_syncookie_ipv6: + return &bpf_tcp_raw_check_syncookie_ipv6_proto; +#endif #endif default: return bpf_sk_base_func_proto(func_id); @@ -7533,6 +7946,12 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_redirect_map_proto; case BPF_FUNC_xdp_adjust_tail: return &bpf_xdp_adjust_tail_proto; + case BPF_FUNC_xdp_get_buff_len: + return &bpf_xdp_get_buff_len_proto; + case BPF_FUNC_xdp_load_bytes: + return &bpf_xdp_load_bytes_proto; + case BPF_FUNC_xdp_store_bytes: + return &bpf_xdp_store_bytes_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; case BPF_FUNC_check_mtu: @@ -7550,6 +7969,16 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; +#ifdef CONFIG_SYN_COOKIES + case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: + return &bpf_tcp_raw_gen_syncookie_ipv4_proto; + case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: + return &bpf_tcp_raw_gen_syncookie_ipv6_proto; + case BPF_FUNC_tcp_raw_check_syncookie_ipv4: + return &bpf_tcp_raw_check_syncookie_ipv4_proto; + case BPF_FUNC_tcp_raw_check_syncookie_ipv6: + return &bpf_tcp_raw_check_syncookie_ipv6_proto; +#endif #endif default: return bpf_sk_base_func_proto(func_id); @@ -7562,6 +7991,12 @@ const struct bpf_func_proto bpf_sock_hash_update_proto __weak; static const struct bpf_func_proto * sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { + const struct bpf_func_proto *func_proto; + + func_proto = cgroup_common_func_proto(func_id, prog); + if (func_proto) + return func_proto; + switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_sock_ops_setsockopt_proto; @@ -7575,8 +8010,6 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sock_hash_update_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_ops_proto; - case BPF_FUNC_get_local_storage: - return &bpf_get_local_storage_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: @@ -7840,7 +8273,9 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; - case offsetofend(struct __sk_buff, gso_size) ... offsetof(struct __sk_buff, hwtstamp) - 1: + case offsetof(struct __sk_buff, tstamp_type): + return false; + case offsetofend(struct __sk_buff, tstamp_type) ... offsetof(struct __sk_buff, hwtstamp) - 1: /* Explicitly prohibit access to padding in __sk_buff. */ return false; default: @@ -8030,6 +8465,7 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); + int field_size; if (off < 0 || off >= sizeof(struct bpf_sock)) return false; @@ -8041,7 +8477,6 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, case offsetof(struct bpf_sock, family): case offsetof(struct bpf_sock, type): case offsetof(struct bpf_sock, protocol): - case offsetof(struct bpf_sock, dst_port): case offsetof(struct bpf_sock, src_port): case offsetof(struct bpf_sock, rx_queue_mapping): case bpf_ctx_range(struct bpf_sock, src_ip4): @@ -8050,6 +8485,14 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); + case bpf_ctx_range(struct bpf_sock, dst_port): + field_size = size == size_default ? + size_default : sizeof_field(struct bpf_sock, dst_port); + bpf_ctx_record_field_size(info, field_size); + return bpf_ctx_narrow_access_ok(off, size, field_size); + case offsetofend(struct bpf_sock, dst_port) ... + offsetof(struct bpf_sock, dst_ip4) - 1: + return false; } return size == size_default; @@ -8187,11 +8630,50 @@ static bool tc_cls_act_is_valid_access(int off, int size, break; case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; + case offsetof(struct __sk_buff, tstamp_type): + /* The convert_ctx_access() on reading and writing + * __sk_buff->tstamp depends on whether the bpf prog + * has used __sk_buff->tstamp_type or not. + * Thus, we need to set prog->tstamp_type_access + * earlier during is_valid_access() here. + */ + ((struct bpf_prog *)prog)->tstamp_type_access = 1; + return size == sizeof(__u8); } return bpf_skb_is_valid_access(off, size, type, prog, info); } +DEFINE_MUTEX(nf_conn_btf_access_lock); +EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock); + +int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, u32 *next_btf_id, + enum bpf_type_flag *flag); +EXPORT_SYMBOL_GPL(nfct_btf_struct_access); + +static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int off, + int size, enum bpf_access_type atype, + u32 *next_btf_id, + enum bpf_type_flag *flag) +{ + int ret = -EACCES; + + if (atype == BPF_READ) + return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, + flag); + + mutex_lock(&nf_conn_btf_access_lock); + if (nfct_btf_struct_access) + ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag); + mutex_unlock(&nf_conn_btf_access_lock); + + return ret; +} + static bool __is_valid_xdp_access(int off, int size) { if (off < 0 || off >= sizeof(struct xdp_md)) @@ -8251,6 +8733,27 @@ void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); +static int xdp_btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int off, + int size, enum bpf_access_type atype, + u32 *next_btf_id, + enum bpf_type_flag *flag) +{ + int ret = -EACCES; + + if (atype == BPF_READ) + return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, + flag); + + mutex_lock(&nf_conn_btf_access_lock); + if (nfct_btf_struct_access) + ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag); + mutex_unlock(&nf_conn_btf_access_lock); + + return ret; +} + static bool sock_addr_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, @@ -8582,6 +9085,25 @@ static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } +static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, + struct bpf_insn *insn) +{ + __u8 value_reg = si->dst_reg; + __u8 skb_reg = si->src_reg; + /* AX is needed because src_reg and dst_reg could be the same */ + __u8 tmp_reg = BPF_REG_AX; + + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, + PKT_VLAN_PRESENT_OFFSET); + *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, + SKB_MONO_DELIVERY_TIME_MASK, 2); + *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC); + *insn++ = BPF_JMP_A(1); + *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_MONO); + + return insn; +} + static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si, struct bpf_insn *insn) { @@ -8603,6 +9125,74 @@ static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si, return insn; } +static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, + const struct bpf_insn *si, + struct bpf_insn *insn) +{ + __u8 value_reg = si->dst_reg; + __u8 skb_reg = si->src_reg; + +#ifdef CONFIG_NET_CLS_ACT + /* If the tstamp_type is read, + * the bpf prog is aware the tstamp could have delivery time. + * Thus, read skb->tstamp as is if tstamp_type_access is true. + */ + if (!prog->tstamp_type_access) { + /* AX is needed because src_reg and dst_reg could be the same */ + __u8 tmp_reg = BPF_REG_AX; + + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, PKT_VLAN_PRESENT_OFFSET); + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, + TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK); + *insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg, + TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK, 2); + /* skb->tc_at_ingress && skb->mono_delivery_time, + * read 0 as the (rcv) timestamp. + */ + *insn++ = BPF_MOV64_IMM(value_reg, 0); + *insn++ = BPF_JMP_A(1); + } +#endif + + *insn++ = BPF_LDX_MEM(BPF_DW, value_reg, skb_reg, + offsetof(struct sk_buff, tstamp)); + return insn; +} + +static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, + const struct bpf_insn *si, + struct bpf_insn *insn) +{ + __u8 value_reg = si->src_reg; + __u8 skb_reg = si->dst_reg; + +#ifdef CONFIG_NET_CLS_ACT + /* If the tstamp_type is read, + * the bpf prog is aware the tstamp could have delivery time. + * Thus, write skb->tstamp as is if tstamp_type_access is true. + * Otherwise, writing at ingress will have to clear the + * mono_delivery_time bit also. + */ + if (!prog->tstamp_type_access) { + __u8 tmp_reg = BPF_REG_AX; + + *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, PKT_VLAN_PRESENT_OFFSET); + /* Writing __sk_buff->tstamp as ingress, goto <clear> */ + *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); + /* goto <store> */ + *insn++ = BPF_JMP_A(2); + /* <clear>: mono_delivery_time */ + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_MONO_DELIVERY_TIME_MASK); + *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, PKT_VLAN_PRESENT_OFFSET); + } +#endif + + /* <store>: skb->tstamp = tstamp */ + *insn++ = BPF_STX_MEM(BPF_DW, skb_reg, value_reg, + offsetof(struct sk_buff, tstamp)); + return insn; +} + static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, @@ -8911,17 +9501,13 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) - *insn++ = BPF_STX_MEM(BPF_DW, - si->dst_reg, si->src_reg, - bpf_target_off(struct sk_buff, - tstamp, 8, - target_size)); + insn = bpf_convert_tstamp_write(prog, si, insn); else - *insn++ = BPF_LDX_MEM(BPF_DW, - si->dst_reg, si->src_reg, - bpf_target_off(struct sk_buff, - tstamp, 8, - target_size)); + insn = bpf_convert_tstamp_read(prog, si, insn); + break; + + case offsetof(struct __sk_buff, tstamp_type): + insn = bpf_convert_tstamp_type_read(si, insn); break; case offsetof(struct __sk_buff, gso_segs): @@ -10062,7 +10648,7 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, .gen_ld_abs = bpf_gen_ld_abs, - .check_kfunc_call = bpf_prog_test_check_kfunc_call, + .btf_struct_access = tc_cls_act_btf_struct_access, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { @@ -10074,6 +10660,7 @@ const struct bpf_verifier_ops xdp_verifier_ops = { .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, .gen_prologue = bpf_noop_prologue, + .btf_struct_access = xdp_btf_struct_access, }; const struct bpf_prog_ops xdp_prog_ops = { @@ -10208,14 +10795,13 @@ int sk_detach_filter(struct sock *sk) } EXPORT_SYMBOL_GPL(sk_detach_filter); -int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, - unsigned int len) +int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len) { struct sock_fprog_kern *fprog; struct sk_filter *filter; int ret = 0; - lock_sock(sk); + sockopt_lock_sock(sk); filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (!filter) @@ -10240,7 +10826,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, goto out; ret = -EFAULT; - if (copy_to_user(ubuf, fprog->filter, bpf_classic_proglen(fprog))) + if (copy_to_sockptr(optval, fprog->filter, bpf_classic_proglen(fprog))) goto out; /* Instead of bytes, the API requests to return the number @@ -10248,7 +10834,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, */ ret = fprog->len; out: - release_sock(sk); + sockopt_release_sock(sk); return ret; } @@ -10601,12 +11187,24 @@ static bool sk_lookup_is_valid_access(int off, int size, case bpf_ctx_range(struct bpf_sk_lookup, local_ip4): case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): - case bpf_ctx_range(struct bpf_sk_lookup, remote_port): case bpf_ctx_range(struct bpf_sk_lookup, local_port): case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex): bpf_ctx_record_field_size(info, sizeof(__u32)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32)); + case bpf_ctx_range(struct bpf_sk_lookup, remote_port): + /* Allow 4-byte access to 2-byte field for backward compatibility */ + if (size == sizeof(__u32)) + return true; + bpf_ctx_record_field_size(info, sizeof(__be16)); + return bpf_ctx_narrow_access_ok(off, size, sizeof(__be16)); + + case offsetofend(struct bpf_sk_lookup, remote_port) ... + offsetof(struct bpf_sk_lookup, local_ip4) - 1: + /* Allow access to zero padding for backward compatibility */ + bpf_ctx_record_field_size(info, sizeof(__u16)); + return bpf_ctx_narrow_access_ok(off, size, sizeof(__u16)); + default: return false; } @@ -10688,6 +11286,11 @@ static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type, sport, 2, target_size)); break; + case offsetofend(struct bpf_sk_lookup, remote_port): + *target_size = 2; + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); + break; + case offsetof(struct bpf_sk_lookup, local_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, @@ -10858,6 +11461,20 @@ const struct bpf_func_proto bpf_skc_to_unix_sock_proto = { .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX], }; +BPF_CALL_1(bpf_skc_to_mptcp_sock, struct sock *, sk) +{ + BTF_TYPE_EMIT(struct mptcp_sock); + return (unsigned long)bpf_mptcp_sock_from_subflow(sk); +} + +const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto = { + .func = bpf_skc_to_mptcp_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_MPTCP], +}; + BPF_CALL_1(bpf_sock_from_file, struct file *, file) { return (unsigned long)sock_from_file(file); @@ -10900,6 +11517,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skc_to_unix_sock: func = &bpf_skc_to_unix_sock_proto; break; + case BPF_FUNC_skc_to_mptcp_sock: + func = &bpf_skc_to_mptcp_sock_proto; + break; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: |