diff options
author | David S. Miller <davem@davemloft.net> | 2020-08-03 18:27:40 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2020-08-03 18:27:40 -0700 |
commit | 2e7199bd773bff3220184d071ed9c9cd34950e51 (patch) | |
tree | 37d2bee56e5687f8f50c60dee7c9767c7fe77770 /net | |
parent | 76769c38b45d94f5492ff9be363ac7007fd8e58b (diff) | |
parent | 21594c44083c375697d418729c4b2e4522cf9f70 (diff) | |
download | linux-2e7199bd773bff3220184d071ed9c9cd34950e51.tar.gz linux-2e7199bd773bff3220184d071ed9c9cd34950e51.tar.bz2 linux-2e7199bd773bff3220184d071ed9c9cd34950e51.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
pull-request: bpf-next 2020-08-04
The following pull-request contains BPF updates for your *net-next* tree.
We've added 73 non-merge commits during the last 9 day(s) which contain
a total of 135 files changed, 4603 insertions(+), 1013 deletions(-).
The main changes are:
1) Implement bpf_link support for XDP. Also add LINK_DETACH operation for the BPF
syscall allowing processes with BPF link FD to force-detach, from Andrii Nakryiko.
2) Add BPF iterator for map elements and to iterate all BPF programs for efficient
in-kernel inspection, from Yonghong Song and Alexei Starovoitov.
3) Separate bpf_get_{stack,stackid}() helpers for perf events in BPF to avoid
unwinder errors, from Song Liu.
4) Allow cgroup local storage map to be shared between programs on the same
cgroup. Also extend BPF selftests with coverage, from YiFei Zhu.
5) Add BPF exception tables to ARM64 JIT in order to be able to JIT BPF_PROBE_MEM
load instructions, from Jean-Philippe Brucker.
6) Follow-up fixes on BPF socket lookup in combination with reuseport group
handling. Also add related BPF selftests, from Jakub Sitnicki.
7) Allow to use socket storage in BPF_PROG_TYPE_CGROUP_SOCK-typed programs for
socket create/release as well as bind functions, from Stanislav Fomichev.
8) Fix an info leak in xsk_getsockopt() when retrieving XDP stats via old struct
xdp_statistics, from Peilin Ye.
9) Fix PT_REGS_RC{,_CORE}() macros in libbpf for MIPS arch, from Jerry Crunchtime.
10) Extend BPF kernel test infra with skb->family and skb->{local,remote}_ip{4,6}
fields and allow user space to specify skb->dev via ifindex, from Dmitry Yakunin.
11) Fix a bpftool segfault due to missing program type name and make it more robust
to prevent them in future gaps, from Quentin Monnet.
12) Consolidate cgroup helper functions across selftests and fix a v6 localhost
resolver issue, from John Fastabend.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r-- | net/bpf/test_run.c | 43 | ||||
-rw-r--r-- | net/core/bpf_sk_storage.c | 216 | ||||
-rw-r--r-- | net/core/dev.c | 539 | ||||
-rw-r--r-- | net/core/filter.c | 3 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 5 | ||||
-rw-r--r-- | net/core/xdp.c | 9 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 12 | ||||
-rw-r--r-- | net/ipv4/udp.c | 14 | ||||
-rw-r--r-- | net/ipv6/route.c | 8 | ||||
-rw-r--r-- | net/ipv6/udp.c | 5 | ||||
-rw-r--r-- | net/netlink/af_netlink.c | 8 | ||||
-rw-r--r-- | net/xdp/xsk.c | 2 |
12 files changed, 698 insertions, 166 deletions
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index b03c469cd01f..99eb8c6c0fbc 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -327,6 +327,12 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) /* priority is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, priority), + offsetof(struct __sk_buff, ifindex))) + return -EINVAL; + + /* ifindex is allowed */ + + if (!range_is_zero(__skb, offsetofend(struct __sk_buff, ifindex), offsetof(struct __sk_buff, cb))) return -EINVAL; @@ -381,6 +387,7 @@ static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb) __skb->mark = skb->mark; __skb->priority = skb->priority; + __skb->ifindex = skb->dev->ifindex; __skb->tstamp = skb->tstamp; memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN); __skb->wire_len = cb->pkt_len; @@ -391,6 +398,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { bool is_l2 = false, is_direct_pkt_access = false; + struct net *net = current->nsproxy->net_ns; + struct net_device *dev = net->loopback_dev; u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; struct __sk_buff *ctx = NULL; @@ -432,7 +441,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, kfree(ctx); return -ENOMEM; } - sock_net_set(sk, current->nsproxy->net_ns); + sock_net_set(sk, net); sock_init_data(NULL, sk); skb = build_skb(data, 0); @@ -446,9 +455,37 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); __skb_put(skb, size); - skb->protocol = eth_type_trans(skb, current->nsproxy->net_ns->loopback_dev); + if (ctx && ctx->ifindex > 1) { + dev = dev_get_by_index(net, ctx->ifindex); + if (!dev) { + ret = -ENODEV; + goto out; + } + } + skb->protocol = eth_type_trans(skb, dev); skb_reset_network_header(skb); + switch (skb->protocol) { + case htons(ETH_P_IP): + sk->sk_family = AF_INET; + if (sizeof(struct iphdr) <= skb_headlen(skb)) { + sk->sk_rcv_saddr = ip_hdr(skb)->saddr; + sk->sk_daddr = ip_hdr(skb)->daddr; + } + break; +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + sk->sk_family = AF_INET6; + if (sizeof(struct ipv6hdr) <= skb_headlen(skb)) { + sk->sk_v6_rcv_saddr = ipv6_hdr(skb)->saddr; + sk->sk_v6_daddr = ipv6_hdr(skb)->daddr; + } + break; +#endif + default: + break; + } + if (is_l2) __skb_push(skb, hh_len); if (is_direct_pkt_access) @@ -481,6 +518,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, ret = bpf_ctx_finish(kattr, uattr, ctx, sizeof(struct __sk_buff)); out: + if (dev && dev != net->loopback_dev) + dev_put(dev); kfree_skb(skb); bpf_sk_storage_free(sk); kfree(sk); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 6f921c4ddc2c..d3377c90a291 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> +#include <linux/btf_ids.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> @@ -943,6 +944,16 @@ const struct bpf_func_proto bpf_sk_storage_get_proto = { .arg4_type = ARG_ANYTHING, }; +const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto = { + .func = bpf_sk_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_CTX, /* context is 'struct sock' */ + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + const struct bpf_func_proto bpf_sk_storage_delete_proto = { .func = bpf_sk_storage_delete, .gpl_only = false, @@ -1217,3 +1228,208 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, return err; } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_put); + +struct bpf_iter_seq_sk_storage_map_info { + struct bpf_map *map; + unsigned int bucket_id; + unsigned skip_elems; +}; + +static struct bpf_sk_storage_elem * +bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, + struct bpf_sk_storage_elem *prev_selem) +{ + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_elem *selem; + u32 skip_elems = info->skip_elems; + struct bpf_sk_storage_map *smap; + u32 bucket_id = info->bucket_id; + u32 i, count, n_buckets; + struct bucket *b; + + smap = (struct bpf_sk_storage_map *)info->map; + n_buckets = 1U << smap->bucket_log; + if (bucket_id >= n_buckets) + return NULL; + + /* try to find next selem in the same bucket */ + selem = prev_selem; + count = 0; + while (selem) { + selem = hlist_entry_safe(selem->map_node.next, + struct bpf_sk_storage_elem, map_node); + if (!selem) { + /* not found, unlock and go to the next bucket */ + b = &smap->buckets[bucket_id++]; + raw_spin_unlock_bh(&b->lock); + skip_elems = 0; + break; + } + sk_storage = rcu_dereference_raw(selem->sk_storage); + if (sk_storage) { + info->skip_elems = skip_elems + count; + return selem; + } + count++; + } + + for (i = bucket_id; i < (1U << smap->bucket_log); i++) { + b = &smap->buckets[i]; + raw_spin_lock_bh(&b->lock); + count = 0; + hlist_for_each_entry(selem, &b->list, map_node) { + sk_storage = rcu_dereference_raw(selem->sk_storage); + if (sk_storage && count >= skip_elems) { + info->bucket_id = i; + info->skip_elems = count; + return selem; + } + count++; + } + raw_spin_unlock_bh(&b->lock); + skip_elems = 0; + } + + info->bucket_id = i; + info->skip_elems = 0; + return NULL; +} + +static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_sk_storage_elem *selem; + + selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); + if (!selem) + return NULL; + + if (*pos == 0) + ++*pos; + return selem; +} + +static void *bpf_sk_storage_map_seq_next(struct seq_file *seq, void *v, + loff_t *pos) +{ + struct bpf_iter_seq_sk_storage_map_info *info = seq->private; + + ++*pos; + ++info->skip_elems; + return bpf_sk_storage_map_seq_find_next(seq->private, v); +} + +struct bpf_iter__bpf_sk_storage_map { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_map *, map); + __bpf_md_ptr(struct sock *, sk); + __bpf_md_ptr(void *, value); +}; + +DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, + struct bpf_map *map, struct sock *sk, + void *value) + +static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, + struct bpf_sk_storage_elem *selem) +{ + struct bpf_iter_seq_sk_storage_map_info *info = seq->private; + struct bpf_iter__bpf_sk_storage_map ctx = {}; + struct bpf_sk_storage *sk_storage; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + int ret = 0; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, selem == NULL); + if (prog) { + ctx.meta = &meta; + ctx.map = info->map; + if (selem) { + sk_storage = rcu_dereference_raw(selem->sk_storage); + ctx.sk = sk_storage->sk; + ctx.value = SDATA(selem)->data; + } + ret = bpf_iter_run_prog(prog, &ctx); + } + + return ret; +} + +static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) +{ + return __bpf_sk_storage_map_seq_show(seq, v); +} + +static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_seq_sk_storage_map_info *info = seq->private; + struct bpf_sk_storage_map *smap; + struct bucket *b; + + if (!v) { + (void)__bpf_sk_storage_map_seq_show(seq, v); + } else { + smap = (struct bpf_sk_storage_map *)info->map; + b = &smap->buckets[info->bucket_id]; + raw_spin_unlock_bh(&b->lock); + } +} + +static int bpf_iter_init_sk_storage_map(void *priv_data, + struct bpf_iter_aux_info *aux) +{ + struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data; + + seq_info->map = aux->map; + return 0; +} + +static int bpf_iter_check_map(struct bpf_prog *prog, + struct bpf_iter_aux_info *aux) +{ + struct bpf_map *map = aux->map; + + if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) + return -EINVAL; + + if (prog->aux->max_rdonly_access > map->value_size) + return -EACCES; + + return 0; +} + +static const struct seq_operations bpf_sk_storage_map_seq_ops = { + .start = bpf_sk_storage_map_seq_start, + .next = bpf_sk_storage_map_seq_next, + .stop = bpf_sk_storage_map_seq_stop, + .show = bpf_sk_storage_map_seq_show, +}; + +static const struct bpf_iter_seq_info iter_seq_info = { + .seq_ops = &bpf_sk_storage_map_seq_ops, + .init_seq_private = bpf_iter_init_sk_storage_map, + .fini_seq_private = NULL, + .seq_priv_size = sizeof(struct bpf_iter_seq_sk_storage_map_info), +}; + +static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { + .target = "bpf_sk_storage_map", + .check_target = bpf_iter_check_map, + .req_linfo = BPF_ITER_LINK_MAP_FD, + .ctx_arg_info_size = 2, + .ctx_arg_info = { + { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), + PTR_TO_BTF_ID_OR_NULL }, + { offsetof(struct bpf_iter__bpf_sk_storage_map, value), + PTR_TO_RDWR_BUF_OR_NULL }, + }, + .seq_info = &iter_seq_info, +}; + +static int __init bpf_sk_storage_map_iter_init(void) +{ + bpf_sk_storage_map_reg_info.ctx_arg_info[0].btf_id = + btf_sock_ids[BTF_SOCK_TYPE_SOCK]; + return bpf_iter_reg_target(&bpf_sk_storage_map_reg_info); +} +late_initcall(bpf_sk_storage_map_iter_init); diff --git a/net/core/dev.c b/net/core/dev.c index f7ef0f5c5569..7df6c9617321 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5467,10 +5467,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) } break; - case XDP_QUERY_PROG: - xdp->prog_id = old ? old->aux->id : 0; - break; - default: ret = -EINVAL; break; @@ -8740,189 +8736,464 @@ void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, } EXPORT_SYMBOL(dev_change_proto_down_reason); -u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op, - enum bpf_netdev_command cmd) +struct bpf_xdp_link { + struct bpf_link link; + struct net_device *dev; /* protected by rtnl_lock, no refcnt held */ + int flags; +}; + +static enum bpf_xdp_mode dev_xdp_mode(u32 flags) { - struct netdev_bpf xdp; + if (flags & XDP_FLAGS_HW_MODE) + return XDP_MODE_HW; + if (flags & XDP_FLAGS_DRV_MODE) + return XDP_MODE_DRV; + return XDP_MODE_SKB; +} - if (!bpf_op) - return 0; +static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) +{ + switch (mode) { + case XDP_MODE_SKB: + return generic_xdp_install; + case XDP_MODE_DRV: + case XDP_MODE_HW: + return dev->netdev_ops->ndo_bpf; + default: + return NULL; + }; +} - memset(&xdp, 0, sizeof(xdp)); - xdp.command = cmd; +static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev, + enum bpf_xdp_mode mode) +{ + return dev->xdp_state[mode].link; +} + +static struct bpf_prog *dev_xdp_prog(struct net_device *dev, + enum bpf_xdp_mode mode) +{ + struct bpf_xdp_link *link = dev_xdp_link(dev, mode); + + if (link) + return link->link.prog; + return dev->xdp_state[mode].prog; +} + +u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) +{ + struct bpf_prog *prog = dev_xdp_prog(dev, mode); - /* Query must always succeed. */ - WARN_ON(bpf_op(dev, &xdp) < 0 && cmd == XDP_QUERY_PROG); + return prog ? prog->aux->id : 0; +} - return xdp.prog_id; +static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode, + struct bpf_xdp_link *link) +{ + dev->xdp_state[mode].link = link; + dev->xdp_state[mode].prog = NULL; } -static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op, - struct netlink_ext_ack *extack, u32 flags, - struct bpf_prog *prog) +static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode, + struct bpf_prog *prog) +{ + dev->xdp_state[mode].link = NULL; + dev->xdp_state[mode].prog = prog; +} + +static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, + bpf_op_t bpf_op, struct netlink_ext_ack *extack, + u32 flags, struct bpf_prog *prog) { - bool non_hw = !(flags & XDP_FLAGS_HW_MODE); - struct bpf_prog *prev_prog = NULL; struct netdev_bpf xdp; int err; - if (non_hw) { - prev_prog = bpf_prog_by_id(__dev_xdp_query(dev, bpf_op, - XDP_QUERY_PROG)); - if (IS_ERR(prev_prog)) - prev_prog = NULL; - } - memset(&xdp, 0, sizeof(xdp)); - if (flags & XDP_FLAGS_HW_MODE) - xdp.command = XDP_SETUP_PROG_HW; - else - xdp.command = XDP_SETUP_PROG; + xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG; xdp.extack = extack; xdp.flags = flags; xdp.prog = prog; + /* Drivers assume refcnt is already incremented (i.e, prog pointer is + * "moved" into driver), so they don't increment it on their own, but + * they do decrement refcnt when program is detached or replaced. + * Given net_device also owns link/prog, we need to bump refcnt here + * to prevent drivers from underflowing it. + */ + if (prog) + bpf_prog_inc(prog); err = bpf_op(dev, &xdp); - if (!err && non_hw) - bpf_prog_change_xdp(prev_prog, prog); + if (err) { + if (prog) + bpf_prog_put(prog); + return err; + } - if (prev_prog) - bpf_prog_put(prev_prog); + if (mode != XDP_MODE_HW) + bpf_prog_change_xdp(dev_xdp_prog(dev, mode), prog); - return err; + return 0; } static void dev_xdp_uninstall(struct net_device *dev) { - struct netdev_bpf xdp; - bpf_op_t ndo_bpf; + struct bpf_xdp_link *link; + struct bpf_prog *prog; + enum bpf_xdp_mode mode; + bpf_op_t bpf_op; - /* Remove generic XDP */ - WARN_ON(dev_xdp_install(dev, generic_xdp_install, NULL, 0, NULL)); + ASSERT_RTNL(); - /* Remove from the driver */ - ndo_bpf = dev->netdev_ops->ndo_bpf; - if (!ndo_bpf) - return; + for (mode = XDP_MODE_SKB; mode < __MAX_XDP_MODE; mode++) { + prog = dev_xdp_prog(dev, mode); + if (!prog) + continue; - memset(&xdp, 0, sizeof(xdp)); - xdp.command = XDP_QUERY_PROG; - WARN_ON(ndo_bpf(dev, &xdp)); - if (xdp.prog_id) - WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, - NULL)); + bpf_op = dev_xdp_bpf_op(dev, mode); + if (!bpf_op) + continue; - /* Remove HW offload */ - memset(&xdp, 0, sizeof(xdp)); - xdp.command = XDP_QUERY_PROG_HW; - if (!ndo_bpf(dev, &xdp) && xdp.prog_id) - WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, - NULL)); + WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); + + /* auto-detach link from net device */ + link = dev_xdp_link(dev, mode); + if (link) + link->dev = NULL; + else + bpf_prog_put(prog); + + dev_xdp_set_link(dev, mode, NULL); + } } -/** - * dev_change_xdp_fd - set or clear a bpf program for a device rx path - * @dev: device - * @extack: netlink extended ack - * @fd: new program fd or negative value to clear - * @expected_fd: old program fd that userspace expects to replace or clear - * @flags: xdp-related flags - * - * Set or clear a bpf program for a device - */ -int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, - int fd, int expected_fd, u32 flags) +static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack, + struct bpf_xdp_link *link, struct bpf_prog *new_prog, + struct bpf_prog *old_prog, u32 flags) { - const struct net_device_ops *ops = dev->netdev_ops; - enum bpf_netdev_command query; - u32 prog_id, expected_id = 0; - bpf_op_t bpf_op, bpf_chk; - struct bpf_prog *prog; - bool offload; + struct bpf_prog *cur_prog; + enum bpf_xdp_mode mode; + bpf_op_t bpf_op; int err; ASSERT_RTNL(); - offload = flags & XDP_FLAGS_HW_MODE; - query = offload ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG; + /* either link or prog attachment, never both */ + if (link && (new_prog || old_prog)) + return -EINVAL; + /* link supports only XDP mode flags */ + if (link && (flags & ~XDP_FLAGS_MODES)) { + NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); + return -EINVAL; + } + /* just one XDP mode bit should be set, zero defaults to SKB mode */ + if (hweight32(flags & XDP_FLAGS_MODES) > 1) { + NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); + return -EINVAL; + } + /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ + if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { + NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); + return -EINVAL; + } - bpf_op = bpf_chk = ops->ndo_bpf; - if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) { - NL_SET_ERR_MSG(extack, "underlying driver does not support XDP in native mode"); - return -EOPNOTSUPP; + mode = dev_xdp_mode(flags); + /* can't replace attached link */ + if (dev_xdp_link(dev, mode)) { + NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link"); + return -EBUSY; } - if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE)) - bpf_op = generic_xdp_install; - if (bpf_op == bpf_chk) - bpf_chk = generic_xdp_install; - - prog_id = __dev_xdp_query(dev, bpf_op, query); - if (flags & XDP_FLAGS_REPLACE) { - if (expected_fd >= 0) { - prog = bpf_prog_get_type_dev(expected_fd, - BPF_PROG_TYPE_XDP, - bpf_op == ops->ndo_bpf); - if (IS_ERR(prog)) - return PTR_ERR(prog); - expected_id = prog->aux->id; - bpf_prog_put(prog); - } - if (prog_id != expected_id) { - NL_SET_ERR_MSG(extack, "Active program does not match expected"); - return -EEXIST; - } + cur_prog = dev_xdp_prog(dev, mode); + /* can't replace attached prog with link */ + if (link && cur_prog) { + NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link"); + return -EBUSY; + } + if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) { + NL_SET_ERR_MSG(extack, "Active program does not match expected"); + return -EEXIST; + } + if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { + NL_SET_ERR_MSG(extack, "XDP program already attached"); + return -EBUSY; } - if (fd >= 0) { - if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) { - NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time"); - return -EEXIST; - } - if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && prog_id) { - NL_SET_ERR_MSG(extack, "XDP program already attached"); - return -EBUSY; - } + /* put effective new program into new_prog */ + if (link) + new_prog = link->link.prog; - prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, - bpf_op == ops->ndo_bpf); - if (IS_ERR(prog)) - return PTR_ERR(prog); + if (new_prog) { + bool offload = mode == XDP_MODE_HW; + enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB + ? XDP_MODE_DRV : XDP_MODE_SKB; - if (!offload && bpf_prog_is_dev_bound(prog->aux)) { - NL_SET_ERR_MSG(extack, "using device-bound program without HW_MODE flag is not supported"); - bpf_prog_put(prog); + if (!offload && dev_xdp_prog(dev, other_mode)) { + NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time"); + return -EEXIST; + } + if (!offload && bpf_prog_is_dev_bound(new_prog->aux)) { + NL_SET_ERR_MSG(extack, "Using device-bound program without HW_MODE flag is not supported"); return -EINVAL; } - - if (prog->expected_attach_type == BPF_XDP_DEVMAP) { + if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); - bpf_prog_put(prog); return -EINVAL; } - - if (prog->expected_attach_type == BPF_XDP_CPUMAP) { - NL_SET_ERR_MSG(extack, - "BPF_XDP_CPUMAP programs can not be attached to a device"); - bpf_prog_put(prog); + if (new_prog->expected_attach_type == BPF_XDP_CPUMAP) { + NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device"); return -EINVAL; } + } - /* prog->aux->id may be 0 for orphaned device-bound progs */ - if (prog->aux->id && prog->aux->id == prog_id) { - bpf_prog_put(prog); - return 0; + /* don't call drivers if the effective program didn't change */ + if (new_prog != cur_prog) { + bpf_op = dev_xdp_bpf_op(dev, mode); + if (!bpf_op) { + NL_SET_ERR_MSG(extack, "Underlying driver does not support XDP in native mode"); + return -EOPNOTSUPP; + } + + err = dev_xdp_install(dev, mode, bpf_op, extack, flags, new_prog); + if (err) + return err; + } + + if (link) + dev_xdp_set_link(dev, mode, link); + else + dev_xdp_set_prog(dev, mode, new_prog); + if (cur_prog) + bpf_prog_put(cur_prog); + + return 0; +} + +static int dev_xdp_attach_link(struct net_device *dev, + struct netlink_ext_ack *extack, + struct bpf_xdp_link *link) +{ + return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags); +} + +static int dev_xdp_detach_link(struct net_device *dev, + struct netlink_ext_ack *extack, + struct bpf_xdp_link *link) +{ + enum bpf_xdp_mode mode; + bpf_op_t bpf_op; + + ASSERT_RTNL(); + + mode = dev_xdp_mode(link->flags); + if (dev_xdp_link(dev, mode) != link) + return -EINVAL; + + bpf_op = dev_xdp_bpf_op(dev, mode); + WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); + dev_xdp_set_link(dev, mode, NULL); + return 0; +} + +static void bpf_xdp_link_release(struct bpf_link *link) +{ + struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); + + rtnl_lock(); + + /* if racing with net_device's tear down, xdp_link->dev might be + * already NULL, in which case link was already auto-detached + */ + if (xdp_link->dev) { + WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link)); + xdp_link->dev = NULL; + } + + rtnl_unlock(); +} + +static int bpf_xdp_link_detach(struct bpf_link *link) +{ + bpf_xdp_link_release(link); + return 0; +} + +static void bpf_xdp_link_dealloc(struct bpf_link *link) +{ + struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); + + kfree(xdp_link); +} + +static void bpf_xdp_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) +{ + struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); + u32 ifindex = 0; + + rtnl_lock(); + if (xdp_link->dev) + ifindex = xdp_link->dev->ifindex; + rtnl_unlock(); + + seq_printf(seq, "ifindex:\t%u\n", ifindex); +} + +static int bpf_xdp_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); + u32 ifindex = 0; + + rtnl_lock(); + if (xdp_link->dev) + ifindex = xdp_link->dev->ifindex; + rtnl_unlock(); + + info->xdp.ifindex = ifindex; + return 0; +} + +static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, + struct bpf_prog *old_prog) +{ + struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); + enum bpf_xdp_mode mode; + bpf_op_t bpf_op; + int err = 0; + + rtnl_lock(); + + /* link might have been auto-released already, so fail */ + if (!xdp_link->dev) { + err = -ENOLINK; + goto out_unlock; + } + + if (old_prog && link->prog != old_prog) { + err = -EPERM; + goto out_unlock; + } + old_prog = link->prog; + if (old_prog == new_prog) { + /* no-op, don't disturb drivers */ + bpf_prog_put(new_prog); + goto out_unlock; + } + + mode = dev_xdp_mode(xdp_link->flags); + bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); + err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, + xdp_link->flags, new_prog); + if (err) + goto out_unlock; + + old_prog = xchg(&link->prog, new_prog); + bpf_prog_put(old_prog); + +out_unlock: + rtnl_unlock(); + return err; +} + +static const struct bpf_link_ops bpf_xdp_link_lops = { + .release = bpf_xdp_link_release, + .dealloc = bpf_xdp_link_dealloc, + .detach = bpf_xdp_link_detach, + .show_fdinfo = bpf_xdp_link_show_fdinfo, + .fill_link_info = bpf_xdp_link_fill_link_info, + .update_prog = bpf_xdp_link_update, +}; + +int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct net *net = current->nsproxy->net_ns; + struct bpf_link_primer link_primer; + struct bpf_xdp_link *link; + struct net_device *dev; + int err, fd; + + dev = dev_get_by_index(net, attr->link_create.target_ifindex); + if (!dev) + return -EINVAL; + + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto out_put_dev; + } + + bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog); + link->dev = dev; + link->flags = attr->link_create.flags; + + err = bpf_link_prime(&link->link, &link_primer); + if (err) { + kfree(link); + goto out_put_dev; + } + + rtnl_lock(); + err = dev_xdp_attach_link(dev, NULL, link); + rtnl_unlock(); + + if (err) { + bpf_link_cleanup(&link_primer); + goto out_put_dev; + } + + fd = bpf_link_settle(&link_primer); + /* link itself doesn't hold dev's refcnt to not complicate shutdown */ + dev_put(dev); + return fd; + +out_put_dev: + dev_put(dev); + return err; +} + +/** + * dev_change_xdp_fd - set or clear a bpf program for a device rx path + * @dev: device + * @extack: netlink extended ack + * @fd: new program fd or negative value to clear + * @expected_fd: old program fd that userspace expects to replace or clear + * @flags: xdp-related flags + * + * Set or clear a bpf program for a device + */ +int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, + int fd, int expected_fd, u32 flags) +{ + enum bpf_xdp_mode mode = dev_xdp_mode(flags); + struct bpf_prog *new_prog = NULL, *old_prog = NULL; + int err; + + ASSERT_RTNL(); + + if (fd >= 0) { + new_prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, + mode != XDP_MODE_SKB); + if (IS_ERR(new_prog)) + return PTR_ERR(new_prog); + } + + if (expected_fd >= 0) { + old_prog = bpf_prog_get_type_dev(expected_fd, BPF_PROG_TYPE_XDP, + mode != XDP_MODE_SKB); + if (IS_ERR(old_prog)) { + err = PTR_ERR(old_prog); + old_prog = NULL; + goto err_out; } - } else { - if (!prog_id) - return 0; - prog = NULL; } - err = dev_xdp_install(dev, bpf_op, extack, flags, prog); - if (err < 0 && prog) - bpf_prog_put(prog); + err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags); +err_out: + if (err && new_prog) + bpf_prog_put(new_prog); + if (old_prog) + bpf_prog_put(old_prog); return err; } diff --git a/net/core/filter.c b/net/core/filter.c index 29e3455122f7..7124f0fe6974 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6187,6 +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) @@ -6219,6 +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); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a54c3e0f2ee1..68e0682450c6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1426,13 +1426,12 @@ static u32 rtnl_xdp_prog_skb(struct net_device *dev) static u32 rtnl_xdp_prog_drv(struct net_device *dev) { - return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf, XDP_QUERY_PROG); + return dev_xdp_prog_id(dev, XDP_MODE_DRV); } static u32 rtnl_xdp_prog_hw(struct net_device *dev) { - return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf, - XDP_QUERY_PROG_HW); + return dev_xdp_prog_id(dev, XDP_MODE_HW); } static int rtnl_xdp_report_one(struct sk_buff *skb, struct net_device *dev, diff --git a/net/core/xdp.c b/net/core/xdp.c index 3c45f99e26d5..48aba933a5a8 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -400,15 +400,6 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem) } EXPORT_SYMBOL_GPL(__xdp_release_frame); -int xdp_attachment_query(struct xdp_attachment_info *info, - struct netdev_bpf *bpf) -{ - bpf->prog_id = info->prog ? info->prog->aux->id : 0; - bpf->prog_flags = info->prog ? info->flags : 0; - return 0; -} -EXPORT_SYMBOL_GPL(xdp_attachment_query); - bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f8913923a6c0..5084333b5ab6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2921,7 +2921,7 @@ static struct pernet_operations __net_initdata tcp_sk_ops = { DEFINE_BPF_ITER_FUNC(tcp, struct bpf_iter_meta *meta, struct sock_common *sk_common, uid_t uid) -static int bpf_iter_init_tcp(void *priv_data) +static int bpf_iter_init_tcp(void *priv_data, struct bpf_iter_aux_info *aux) { struct tcp_iter_state *st = priv_data; struct tcp_seq_afinfo *afinfo; @@ -2933,7 +2933,7 @@ static int bpf_iter_init_tcp(void *priv_data) afinfo->family = AF_UNSPEC; st->bpf_seq_afinfo = afinfo; - ret = bpf_iter_init_seq_net(priv_data); + ret = bpf_iter_init_seq_net(priv_data, aux); if (ret) kfree(afinfo); return ret; @@ -2947,17 +2947,21 @@ static void bpf_iter_fini_tcp(void *priv_data) bpf_iter_fini_seq_net(priv_data); } -static struct bpf_iter_reg tcp_reg_info = { - .target = "tcp", +static const struct bpf_iter_seq_info tcp_seq_info = { .seq_ops = &bpf_iter_tcp_seq_ops, .init_seq_private = bpf_iter_init_tcp, .fini_seq_private = bpf_iter_fini_tcp, .seq_priv_size = sizeof(struct tcp_iter_state), +}; + +static struct bpf_iter_reg tcp_reg_info = { + .target = "tcp", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__tcp, sk_common), PTR_TO_BTF_ID_OR_NULL }, }, + .seq_info = &tcp_seq_info, }; static void __init bpf_iter_register(void) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0fb5e4ea133f..e88efba07551 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -473,7 +473,7 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, return sk; reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); - if (reuse_sk && !reuseport_has_conns(sk, false)) + if (reuse_sk) sk = reuse_sk; return sk; } @@ -3181,7 +3181,7 @@ static struct pernet_operations __net_initdata udp_sysctl_ops = { 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) +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; @@ -3194,7 +3194,7 @@ static int bpf_iter_init_udp(void *priv_data) afinfo->family = AF_UNSPEC; afinfo->udp_table = &udp_table; st->bpf_seq_afinfo = afinfo; - ret = bpf_iter_init_seq_net(priv_data); + ret = bpf_iter_init_seq_net(priv_data, aux); if (ret) kfree(afinfo); return ret; @@ -3208,17 +3208,21 @@ static void bpf_iter_fini_udp(void *priv_data) bpf_iter_fini_seq_net(priv_data); } -static struct bpf_iter_reg udp_reg_info = { - .target = "udp", +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) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 48d499d763fa..5e7e25e2523a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6427,17 +6427,21 @@ DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *r BTF_ID_LIST(btf_fib6_info_id) BTF_ID(struct, fib6_info) -static struct bpf_iter_reg ipv6_route_reg_info = { - .target = "ipv6_route", +static const struct bpf_iter_seq_info ipv6_route_seq_info = { .seq_ops = &ipv6_route_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct ipv6_route_iter), +}; + +static struct bpf_iter_reg ipv6_route_reg_info = { + .target = "ipv6_route", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__ipv6_route, rt), PTR_TO_BTF_ID_OR_NULL }, }, + .seq_info = &ipv6_route_seq_info, }; static int __init bpf_iter_register(void) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 5530c9dcb61c..29d9691359b9 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -155,9 +155,6 @@ static struct sock *lookup_reuseport(struct net *net, struct sock *sk, hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); reuse_sk = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - /* Fall back to scoring if group has connections */ - if (reuseport_has_conns(sk, false)) - return NULL; } return reuse_sk; } @@ -211,7 +208,7 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net, return sk; reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); - if (reuse_sk && !reuseport_has_conns(sk, false)) + if (reuse_sk) sk = reuse_sk; return sk; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index d8921b833744..b5f30d7d30d0 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2807,17 +2807,21 @@ static const struct rhashtable_params netlink_rhashtable_params = { BTF_ID_LIST(btf_netlink_sock_id) BTF_ID(struct, netlink_sock) -static struct bpf_iter_reg netlink_reg_info = { - .target = "netlink", +static const struct bpf_iter_seq_info netlink_seq_info = { .seq_ops = &netlink_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct nl_seq_iter), +}; + +static struct bpf_iter_reg netlink_reg_info = { + .target = "netlink", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__netlink, sk), PTR_TO_BTF_ID_OR_NULL }, }, + .seq_info = &netlink_seq_info, }; static int __init bpf_iter_register(void) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 2e94a7e94671..c3231620d210 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -840,7 +840,7 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname, switch (optname) { case XDP_STATISTICS: { - struct xdp_statistics stats; + struct xdp_statistics stats = {}; bool extra_stats = true; size_t stats_size; |