diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-08-06 06:13:21 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-08-06 06:13:21 +0300 |
commit | 47ec5303d73ea344e84f46660fff693c57641386 (patch) | |
tree | a2252debab749de29620c43285295d60c4741119 /net/ipv4/udp.c | |
parent | 8186749621ed6b8fc42644c399e8c755a2b6f630 (diff) | |
parent | c1055b76ad00aed0e8b79417080f212d736246b6 (diff) | |
download | linux-47ec5303d73ea344e84f46660fff693c57641386.tar.xz |
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/ipv4/udp.c')
-rw-r--r-- | net/ipv4/udp.c | 287 |
1 files changed, 227 insertions, 60 deletions
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 4077d589b72e..e88efba07551 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -106,6 +106,7 @@ #include <net/xfrm.h> #include <trace/events/udp.h> #include <linux/static_key.h> +#include <linux/btf_ids.h> #include <trace/events/skb.h> #include <net/busy_poll.h> #include "udp_impl.h" @@ -408,6 +409,22 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr, udp_ehash_secret + net_hash_mix(net)); } +static struct sock *lookup_reuseport(struct net *net, struct sock *sk, + struct sk_buff *skb, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned short hnum) +{ + struct sock *reuse_sk = NULL; + u32 hash; + + if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { + hash = udp_ehashfn(net, daddr, hnum, saddr, sport); + reuse_sk = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + } + return reuse_sk; +} + /* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, @@ -416,9 +433,8 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct udp_hslot *hslot2, struct sk_buff *skb) { - struct sock *sk, *result, *reuseport_result; + struct sock *sk, *result; int score, badness; - u32 hash = 0; result = NULL; badness = 0; @@ -426,25 +442,42 @@ static struct sock *udp4_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { - reuseport_result = NULL; - - if (sk->sk_reuseport && - sk->sk_state != TCP_ESTABLISHED) { - hash = udp_ehashfn(net, daddr, hnum, - saddr, sport); - reuseport_result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (reuseport_result && !reuseport_has_conns(sk, false)) - return reuseport_result; - } + result = lookup_reuseport(net, sk, skb, + saddr, sport, daddr, hnum); + /* Fall back to scoring if group has connections */ + if (result && !reuseport_has_conns(sk, false)) + return result; - result = reuseport_result ? : sk; + result = result ? : sk; badness = score; } } return result; } +static struct sock *udp4_lookup_run_bpf(struct net *net, + struct udp_table *udptable, + struct sk_buff *skb, + __be32 saddr, __be16 sport, + __be32 daddr, u16 hnum) +{ + struct sock *sk, *reuse_sk; + bool no_reuseport; + + if (udptable != &udp_table) + return NULL; /* only UDP is supported */ + + no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, + saddr, sport, daddr, hnum, &sk); + if (no_reuseport || IS_ERR_OR_NULL(sk)) + return sk; + + reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + if (reuse_sk) + sk = reuse_sk; + return sk; +} + /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ @@ -452,27 +485,45 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, struct sk_buff *skb) { - struct sock *result; unsigned short hnum = ntohs(dport); unsigned int hash2, slot2; struct udp_hslot *hslot2; + struct sock *result, *sk; hash2 = ipv4_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; + /* Lookup connected or non-wildcard socket */ result = udp4_lib_lookup2(net, saddr, sport, daddr, hnum, dif, sdif, hslot2, skb); - if (!result) { - hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum); - slot2 = hash2 & udptable->mask; - hslot2 = &udptable->hash2[slot2]; - - result = udp4_lib_lookup2(net, saddr, sport, - htonl(INADDR_ANY), hnum, dif, sdif, - hslot2, skb); + if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED) + goto done; + + /* Lookup redirect from BPF */ + if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { + sk = udp4_lookup_run_bpf(net, udptable, skb, + saddr, sport, daddr, hnum); + if (sk) { + result = sk; + goto done; + } } + + /* Got non-wildcard socket or error on first lookup */ + if (result) + goto done; + + /* Lookup wildcard sockets */ + hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + + result = udp4_lib_lookup2(net, saddr, sport, + htonl(INADDR_ANY), hnum, dif, sdif, + hslot2, skb); +done: if (IS_ERR(result)) return NULL; return result; @@ -2535,7 +2586,7 @@ void udp_destroy_sock(struct sock *sk) * Socket option code for UDP */ int udp_lib_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen, + sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)) { struct udp_sock *up = udp_sk(sk); @@ -2546,7 +2597,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, if (optlen < sizeof(int)) return -EINVAL; - if (get_user(val, (int __user *)optval)) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; valbool = val ? 1 : 0; @@ -2650,26 +2701,16 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, } EXPORT_SYMBOL(udp_lib_setsockopt); -int udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) +int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, + unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, + return udp_lib_setsockopt(sk, level, optname, + optval, optlen, udp_push_pending_frames); return ip_setsockopt(sk, level, optname, optval, optlen); } -#ifdef CONFIG_COMPAT -int compat_udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) -{ - if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, - udp_push_pending_frames); - return compat_ip_setsockopt(sk, level, optname, optval, optlen); -} -#endif - int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -2735,20 +2776,11 @@ int udp_getsockopt(struct sock *sk, int level, int optname, return ip_getsockopt(sk, level, optname, optval, optlen); } -#ifdef CONFIG_COMPAT -int compat_udp_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_getsockopt(sk, level, optname, optval, optlen); - return compat_ip_getsockopt(sk, level, optname, optval, optlen); -} -#endif /** * udp_poll - wait for a UDP event. - * @file - file struct - * @sock - socket - * @wait - poll table + * @file: - file struct + * @sock: - socket + * @wait: - poll table * * This is same as datagram poll, except for the special case of * blocking sockets. If application is using a blocking fd @@ -2815,10 +2847,6 @@ struct proto udp_prot = { .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp_sock), .h.udp_table = &udp_table, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udp_setsockopt, - .compat_getsockopt = compat_udp_getsockopt, -#endif .diag_destroy = udp_abort, }; EXPORT_SYMBOL(udp_prot); @@ -2829,10 +2857,15 @@ EXPORT_SYMBOL(udp_prot); static struct sock *udp_get_first(struct seq_file *seq, int start) { struct sock *sk; - struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); + struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + if (state->bpf_seq_afinfo) + afinfo = state->bpf_seq_afinfo; + else + afinfo = PDE_DATA(file_inode(seq->file)); + for (state->bucket = start; state->bucket <= afinfo->udp_table->mask; ++state->bucket) { struct udp_hslot *hslot = &afinfo->udp_table->hash[state->bucket]; @@ -2844,7 +2877,8 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) sk_for_each(sk, &hslot->head) { if (!net_eq(sock_net(sk), net)) continue; - if (sk->sk_family == afinfo->family) + if (afinfo->family == AF_UNSPEC || + sk->sk_family == afinfo->family) goto found; } spin_unlock_bh(&hslot->lock); @@ -2856,13 +2890,20 @@ found: static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) { - struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); + struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + if (state->bpf_seq_afinfo) + afinfo = state->bpf_seq_afinfo; + else + afinfo = PDE_DATA(file_inode(seq->file)); + do { sk = sk_next(sk); - } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != afinfo->family)); + } while (sk && (!net_eq(sock_net(sk), net) || + (afinfo->family != AF_UNSPEC && + sk->sk_family != afinfo->family))); if (!sk) { if (state->bucket <= afinfo->udp_table->mask) @@ -2907,9 +2948,14 @@ EXPORT_SYMBOL(udp_seq_next); void udp_seq_stop(struct seq_file *seq, void *v) { - struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); + struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; + if (state->bpf_seq_afinfo) + afinfo = state->bpf_seq_afinfo; + else + afinfo = PDE_DATA(file_inode(seq->file)); + if (state->bucket <= afinfo->udp_table->mask) spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); } @@ -2953,6 +2999,67 @@ int udp4_seq_show(struct seq_file *seq, void *v) return 0; } +#ifdef CONFIG_BPF_SYSCALL +struct bpf_iter__udp { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct udp_sock *, udp_sk); + uid_t uid __aligned(8); + int bucket __aligned(8); +}; + +static int udp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, + struct udp_sock *udp_sk, uid_t uid, int bucket) +{ + struct bpf_iter__udp ctx; + + meta->seq_num--; /* skip SEQ_START_TOKEN */ + ctx.meta = meta; + ctx.udp_sk = udp_sk; + ctx.uid = uid; + ctx.bucket = bucket; + return bpf_iter_run_prog(prog, &ctx); +} + +static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v) +{ + struct udp_iter_state *state = seq->private; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + struct sock *sk = v; + uid_t uid; + + if (v == SEQ_START_TOKEN) + return 0; + + uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); + meta.seq = seq; + prog = bpf_iter_get_info(&meta, false); + return udp_prog_seq_show(prog, &meta, v, uid, state->bucket); +} + +static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + if (!v) { + meta.seq = seq; + prog = bpf_iter_get_info(&meta, true); + if (prog) + (void)udp_prog_seq_show(prog, &meta, v, 0, 0); + } + + udp_seq_stop(seq, v); +} + +static const struct seq_operations bpf_iter_udp_seq_ops = { + .start = udp_seq_start, + .next = udp_seq_next, + .stop = bpf_iter_udp_seq_stop, + .show = bpf_iter_udp_seq_show, +}; +#endif + const struct seq_operations udp_seq_ops = { .start = udp_seq_start, .next = udp_seq_next, @@ -3070,6 +3177,62 @@ static struct pernet_operations __net_initdata udp_sysctl_ops = { .init = udp_sysctl_init, }; +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) +DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta, + struct udp_sock *udp_sk, uid_t uid, int bucket) + +static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux) +{ + struct udp_iter_state *st = priv_data; + struct udp_seq_afinfo *afinfo; + int ret; + + afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN); + if (!afinfo) + return -ENOMEM; + + afinfo->family = AF_UNSPEC; + afinfo->udp_table = &udp_table; + st->bpf_seq_afinfo = afinfo; + ret = bpf_iter_init_seq_net(priv_data, aux); + if (ret) + kfree(afinfo); + return ret; +} + +static void bpf_iter_fini_udp(void *priv_data) +{ + struct udp_iter_state *st = priv_data; + + kfree(st->bpf_seq_afinfo); + bpf_iter_fini_seq_net(priv_data); +} + +static const struct bpf_iter_seq_info udp_seq_info = { + .seq_ops = &bpf_iter_udp_seq_ops, + .init_seq_private = bpf_iter_init_udp, + .fini_seq_private = bpf_iter_fini_udp, + .seq_priv_size = sizeof(struct udp_iter_state), +}; + +static struct bpf_iter_reg udp_reg_info = { + .target = "udp", + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__udp, udp_sk), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &udp_seq_info, +}; + +static void __init bpf_iter_register(void) +{ + udp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UDP]; + if (bpf_iter_reg_target(&udp_reg_info)) + pr_warn("Warning: could not register bpf iterator udp\n"); +} +#endif + void __init udp_init(void) { unsigned long limit; @@ -3095,4 +3258,8 @@ void __init udp_init(void) if (register_pernet_subsys(&udp_sysctl_ops)) panic("UDP: failed to init sysctl parameters.\n"); + +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) + bpf_iter_register(); +#endif } |