diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-08-05 20:13:21 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-08-05 20:13:21 -0700 |
commit | 47ec5303d73ea344e84f46660fff693c57641386 (patch) | |
tree | a2252debab749de29620c43285295d60c4741119 /net/core/filter.c | |
parent | 8186749621ed6b8fc42644c399e8c755a2b6f630 (diff) | |
parent | c1055b76ad00aed0e8b79417080f212d736246b6 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Support 6Ghz band in ath11k driver, from Rajkumar Manoharan.
2) Support UDP segmentation in code TSO code, from Eric Dumazet.
3) Allow flashing different flash images in cxgb4 driver, from Vishal
Kulkarni.
4) Add drop frames counter and flow status to tc flower offloading,
from Po Liu.
5) Support n-tuple filters in cxgb4, from Vishal Kulkarni.
6) Various new indirect call avoidance, from Eric Dumazet and Brian
Vazquez.
7) Fix BPF verifier failures on 32-bit pointer arithmetic, from
Yonghong Song.
8) Support querying and setting hardware address of a port function via
devlink, use this in mlx5, from Parav Pandit.
9) Support hw ipsec offload on bonding slaves, from Jarod Wilson.
10) Switch qca8k driver over to phylink, from Jonathan McDowell.
11) In bpftool, show list of processes holding BPF FD references to
maps, programs, links, and btf objects. From Andrii Nakryiko.
12) Several conversions over to generic power management, from Vaibhav
Gupta.
13) Add support for SO_KEEPALIVE et al. to bpf_setsockopt(), from Dmitry
Yakunin.
14) Various https url conversions, from Alexander A. Klimov.
15) Timestamping and PHC support for mscc PHY driver, from Antoine
Tenart.
16) Support bpf iterating over tcp and udp sockets, from Yonghong Song.
17) Support 5GBASE-T i40e NICs, from Aleksandr Loktionov.
18) Add kTLS RX HW offload support to mlx5e, from Tariq Toukan.
19) Fix the ->ndo_start_xmit() return type to be netdev_tx_t in several
drivers. From Luc Van Oostenryck.
20) XDP support for xen-netfront, from Denis Kirjanov.
21) Support receive buffer autotuning in MPTCP, from Florian Westphal.
22) Support EF100 chip in sfc driver, from Edward Cree.
23) Add XDP support to mvpp2 driver, from Matteo Croce.
24) Support MPTCP in sock_diag, from Paolo Abeni.
25) Commonize UDP tunnel offloading code by creating udp_tunnel_nic
infrastructure, from Jakub Kicinski.
26) Several pci_ --> dma_ API conversions, from Christophe JAILLET.
27) Add FLOW_ACTION_POLICE support to mlxsw, from Ido Schimmel.
28) Add SK_LOOKUP bpf program type, from Jakub Sitnicki.
29) Refactor a lot of networking socket option handling code in order to
avoid set_fs() calls, from Christoph Hellwig.
30) Add rfc4884 support to icmp code, from Willem de Bruijn.
31) Support TBF offload in dpaa2-eth driver, from Ioana Ciornei.
32) Support XDP_REDIRECT in qede driver, from Alexander Lobakin.
33) Support PCI relaxed ordering in mlx5 driver, from Aya Levin.
34) Support TCP syncookies in MPTCP, from Flowian Westphal.
35) Fix several tricky cases of PMTU handling wrt. briding, from Stefano
Brivio.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2056 commits)
net: thunderx: initialize VF's mailbox mutex before first usage
usb: hso: remove bogus check for EINPROGRESS
usb: hso: no complaint about kmalloc failure
hso: fix bailout in error case of probe
ip_tunnel_core: Fix build for archs without _HAVE_ARCH_IPV6_CSUM
selftests/net: relax cpu affinity requirement in msg_zerocopy test
mptcp: be careful on subflow creation
selftests: rtnetlink: make kci_test_encap() return sub-test result
selftests: rtnetlink: correct the final return value for the test
net: dsa: sja1105: use detected device id instead of DT one on mismatch
tipc: set ub->ifindex for local ipv6 address
ipv6: add ipv6_dev_find()
net: openvswitch: silence suspicious RCU usage warning
Revert "vxlan: fix tos value before xmit"
ptp: only allow phase values lower than 1 period
farsync: switch from 'pci_' to 'dma_' API
wan: wanxl: switch from 'pci_' to 'dma_' API
hv_netvsc: do not use VF device if link is down
dpaa2-eth: Fix passing zero to 'PTR_ERR' warning
net: macb: Properly handle phylink on at91sam9x
...
Diffstat (limited to 'net/core/filter.c')
-rw-r--r-- | net/core/filter.c | 386 |
1 files changed, 383 insertions, 3 deletions
diff --git a/net/core/filter.c b/net/core/filter.c index 82e1b5b06167..7124f0fe6974 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -47,6 +47,7 @@ #include <linux/seccomp.h> #include <linux/if_vlan.h> #include <linux/bpf.h> +#include <linux/btf.h> #include <net/sch_generic.h> #include <net/cls_cgroup.h> #include <net/dst_metadata.h> @@ -73,6 +74,31 @@ #include <net/lwtunnel.h> #include <net/ipv6_stubs.h> #include <net/bpf_sk_storage.h> +#include <net/transp_v6.h> +#include <linux/btf_ids.h> + +int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) +{ + if (in_compat_syscall()) { + struct compat_sock_fprog f32; + + if (len != sizeof(f32)) + return -EINVAL; + if (copy_from_sockptr(&f32, src, sizeof(f32))) + return -EFAULT; + memset(dst, 0, sizeof(*dst)); + dst->len = f32.len; + dst->filter = compat_ptr(f32.filter); + } else { + if (len != sizeof(*dst)) + return -EINVAL; + if (copy_from_sockptr(dst, src, sizeof(*dst))) + return -EFAULT; + } + + return 0; +} +EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user); /** * sk_filter_trim_cap - run a packet through a socket filter @@ -3777,7 +3803,9 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; -static int bpf_skb_output_btf_ids[5]; +BTF_ID_LIST(bpf_skb_output_btf_ids) +BTF_ID(struct, sk_buff) + const struct bpf_func_proto bpf_skb_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, @@ -4171,7 +4199,9 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; -static int bpf_xdp_output_btf_ids[5]; +BTF_ID_LIST(bpf_xdp_output_btf_ids) +BTF_ID(struct, xdp_buff) + const struct bpf_func_proto bpf_xdp_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, @@ -4289,10 +4319,10 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen, u32 flags) { char devname[IFNAMSIZ]; + int val, valbool; struct net *net; int ifindex; int ret = 0; - int val; if (!sk_fullsock(sk)) return -EINVAL; @@ -4303,6 +4333,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, if (optlen != sizeof(int) && optname != SO_BINDTODEVICE) return -EINVAL; val = *((int *)optval); + valbool = val ? 1 : 0; /* Only some socketops are supported */ switch (optname) { @@ -4361,6 +4392,11 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, } 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; default: ret = -EINVAL; } @@ -4421,6 +4457,7 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, ret = tcp_set_congestion_control(sk, name, false, reinit, true); } else { + struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); if (optlen != sizeof(int)) @@ -4449,6 +4486,33 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, 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; default: ret = -EINVAL; } @@ -6123,6 +6187,7 @@ bool bpf_helper_changes_pkt_data(void *func) } const struct bpf_func_proto bpf_event_output_data_proto __weak; +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) @@ -6155,6 +6220,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) 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; default: return bpf_base_func_proto(func_id); } @@ -6858,6 +6925,7 @@ static bool __sock_filter_check_attach_type(int off, case offsetof(struct bpf_sock, priority): switch (attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_INET_SOCK_RELEASE: goto full_access; default: return false; @@ -9187,6 +9255,189 @@ const struct bpf_verifier_ops sk_reuseport_verifier_ops = { const struct bpf_prog_ops sk_reuseport_prog_ops = { }; + +DEFINE_STATIC_KEY_FALSE(bpf_sk_lookup_enabled); +EXPORT_SYMBOL(bpf_sk_lookup_enabled); + +BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx, + struct sock *, sk, u64, flags) +{ + if (unlikely(flags & ~(BPF_SK_LOOKUP_F_REPLACE | + BPF_SK_LOOKUP_F_NO_REUSEPORT))) + return -EINVAL; + if (unlikely(sk && sk_is_refcounted(sk))) + return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */ + if (unlikely(sk && sk->sk_state == TCP_ESTABLISHED)) + return -ESOCKTNOSUPPORT; /* reject connected sockets */ + + /* Check if socket is suitable for packet L3/L4 protocol */ + if (sk && sk->sk_protocol != ctx->protocol) + return -EPROTOTYPE; + if (sk && sk->sk_family != ctx->family && + (sk->sk_family == AF_INET || ipv6_only_sock(sk))) + return -EAFNOSUPPORT; + + if (ctx->selected_sk && !(flags & BPF_SK_LOOKUP_F_REPLACE)) + return -EEXIST; + + /* Select socket as lookup result */ + ctx->selected_sk = sk; + ctx->no_reuseport = flags & BPF_SK_LOOKUP_F_NO_REUSEPORT; + return 0; +} + +static const struct bpf_func_proto bpf_sk_lookup_assign_proto = { + .func = bpf_sk_lookup_assign, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_SOCKET_OR_NULL, + .arg3_type = ARG_ANYTHING, +}; + +static const struct bpf_func_proto * +sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_perf_event_output: + return &bpf_event_output_data_proto; + case BPF_FUNC_sk_assign: + return &bpf_sk_lookup_assign_proto; + case BPF_FUNC_sk_release: + return &bpf_sk_release_proto; + default: + return bpf_base_func_proto(func_id); + } +} + +static bool sk_lookup_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= sizeof(struct bpf_sk_lookup)) + return false; + if (off % size != 0) + return false; + if (type != BPF_READ) + return false; + + switch (off) { + case offsetof(struct bpf_sk_lookup, sk): + info->reg_type = PTR_TO_SOCKET_OR_NULL; + return size == sizeof(__u64); + + case bpf_ctx_range(struct bpf_sk_lookup, family): + case bpf_ctx_range(struct bpf_sk_lookup, protocol): + case bpf_ctx_range(struct bpf_sk_lookup, remote_ip4): + 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): + bpf_ctx_record_field_size(info, sizeof(__u32)); + return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32)); + + default: + return false; + } +} + +static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + struct bpf_insn *insn = insn_buf; + + switch (si->off) { + case offsetof(struct bpf_sk_lookup, sk): + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, + offsetof(struct bpf_sk_lookup_kern, selected_sk)); + break; + + case offsetof(struct bpf_sk_lookup, family): + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, + bpf_target_off(struct bpf_sk_lookup_kern, + family, 2, target_size)); + break; + + case offsetof(struct bpf_sk_lookup, protocol): + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, + bpf_target_off(struct bpf_sk_lookup_kern, + protocol, 2, target_size)); + break; + + case offsetof(struct bpf_sk_lookup, remote_ip4): + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + bpf_target_off(struct bpf_sk_lookup_kern, + v4.saddr, 4, target_size)); + break; + + case offsetof(struct bpf_sk_lookup, local_ip4): + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + bpf_target_off(struct bpf_sk_lookup_kern, + v4.daddr, 4, target_size)); + break; + + case bpf_ctx_range_till(struct bpf_sk_lookup, + remote_ip6[0], remote_ip6[3]): { +#if IS_ENABLED(CONFIG_IPV6) + int off = si->off; + + off -= offsetof(struct bpf_sk_lookup, remote_ip6[0]); + off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, + offsetof(struct bpf_sk_lookup_kern, v6.saddr)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + } + case bpf_ctx_range_till(struct bpf_sk_lookup, + local_ip6[0], local_ip6[3]): { +#if IS_ENABLED(CONFIG_IPV6) + int off = si->off; + + off -= offsetof(struct bpf_sk_lookup, local_ip6[0]); + off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); + *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, + offsetof(struct bpf_sk_lookup_kern, v6.daddr)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); +#endif + break; + } + case offsetof(struct bpf_sk_lookup, remote_port): + *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, + bpf_target_off(struct bpf_sk_lookup_kern, + sport, 2, target_size)); + 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, + dport, 2, target_size)); + break; + } + + return insn - insn_buf; +} + +const struct bpf_prog_ops sk_lookup_prog_ops = { +}; + +const struct bpf_verifier_ops sk_lookup_verifier_ops = { + .get_func_proto = sk_lookup_func_proto, + .is_valid_access = sk_lookup_is_valid_access, + .convert_ctx_access = sk_lookup_convert_ctx_access, +}; + #endif /* CONFIG_INET */ DEFINE_BPF_DISPATCHER(xdp) @@ -9195,3 +9446,132 @@ void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog) { bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog); } + +#ifdef CONFIG_DEBUG_INFO_BTF +BTF_ID_LIST_GLOBAL(btf_sock_ids) +#define BTF_SOCK_TYPE(name, type) BTF_ID(struct, type) +BTF_SOCK_TYPE_xxx +#undef BTF_SOCK_TYPE +#else +u32 btf_sock_ids[MAX_BTF_SOCK_TYPE]; +#endif + +static bool check_arg_btf_id(u32 btf_id, u32 arg) +{ + int i; + + /* only one argument, no need to check arg */ + for (i = 0; i < MAX_BTF_SOCK_TYPE; i++) + if (btf_sock_ids[i] == btf_id) + return true; + return false; +} + +BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) +{ + /* tcp6_sock type is not generated in dwarf and hence btf, + * trigger an explicit type generation here. + */ + BTF_TYPE_EMIT(struct tcp6_sock); + if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && + sk->sk_family == AF_INET6) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { + .func = bpf_skc_to_tcp6_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_BTF_ID, + .check_btf_id = check_arg_btf_id, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP6], +}; + +BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk) +{ + if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { + .func = bpf_skc_to_tcp_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_BTF_ID, + .check_btf_id = check_arg_btf_id, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP], +}; + +BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk) +{ +#ifdef CONFIG_INET + if (sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) + return (unsigned long)sk; +#endif + +#if IS_BUILTIN(CONFIG_IPV6) + if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT) + return (unsigned long)sk; +#endif + + return (unsigned long)NULL; +} + +const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = { + .func = bpf_skc_to_tcp_timewait_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_BTF_ID, + .check_btf_id = check_arg_btf_id, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW], +}; + +BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk) +{ +#ifdef CONFIG_INET + if (sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV) + return (unsigned long)sk; +#endif + +#if IS_BUILTIN(CONFIG_IPV6) + if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV) + return (unsigned long)sk; +#endif + + return (unsigned long)NULL; +} + +const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = { + .func = bpf_skc_to_tcp_request_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_BTF_ID, + .check_btf_id = check_arg_btf_id, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ], +}; + +BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk) +{ + /* udp6_sock type is not generated in dwarf and hence btf, + * trigger an explicit type generation here. + */ + BTF_TYPE_EMIT(struct udp6_sock); + if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP && + sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { + .func = bpf_skc_to_udp6_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_BTF_ID, + .check_btf_id = check_arg_btf_id, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], +}; |