diff options
author | David S. Miller <davem@davemloft.net> | 2020-10-01 14:29:01 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2020-10-01 14:29:01 -0700 |
commit | 23a1f682a925c0e15443bd2ea01bd0cbbc70e66a (patch) | |
tree | 3f30c9df70f2a99c9873dcabc0e547eb42251327 /net | |
parent | 7c89d9d9f90931f170e510e9e4b84d9dafdd616a (diff) | |
parent | 6208689fb3e623d3576dd61866cb99b40f75dc53 (diff) | |
download | linux-23a1f682a925c0e15443bd2ea01bd0cbbc70e66a.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
pull-request: bpf-next 2020-10-01
The following pull-request contains BPF updates for your *net-next* tree.
We've added 90 non-merge commits during the last 8 day(s) which contain
a total of 103 files changed, 7662 insertions(+), 1894 deletions(-).
Note that once bpf(/net) tree gets merged into net-next, there will be a small
merge conflict in tools/lib/bpf/btf.c between commit 1245008122d7 ("libbpf: Fix
native endian assumption when parsing BTF") from the bpf tree and the commit
3289959b97ca ("libbpf: Support BTF loading and raw data output in both endianness")
from the bpf-next tree. Correct resolution would be to stick with bpf-next, it
should look like:
[...]
/* check BTF magic */
if (fread(&magic, 1, sizeof(magic), f) < sizeof(magic)) {
err = -EIO;
goto err_out;
}
if (magic != BTF_MAGIC && magic != bswap_16(BTF_MAGIC)) {
/* definitely not a raw BTF */
err = -EPROTO;
goto err_out;
}
/* get file size */
[...]
The main changes are:
1) Add bpf_snprintf_btf() and bpf_seq_printf_btf() helpers to support displaying
BTF-based kernel data structures out of BPF programs, from Alan Maguire.
2) Speed up RCU tasks trace grace periods by a factor of 50 & fix a few race
conditions exposed by it. It was discussed to take these via BPF and
networking tree to get better testing exposure, from Paul E. McKenney.
3) Support multi-attach for freplace programs, needed for incremental attachment
of multiple XDP progs using libxdp dispatcher model, from Toke Høiland-Jørgensen.
4) libbpf support for appending new BTF types at the end of BTF object, allowing
intrusive changes of prog's BTF (useful for future linking), from Andrii Nakryiko.
5) Several BPF helper improvements e.g. avoid atomic op in cookie generator and add
a redirect helper into neighboring subsys, from Daniel Borkmann.
6) Allow map updates on sockmaps from bpf_iter context in order to migrate sockmaps
from one to another, from Lorenz Bauer.
7) Fix 32 bit to 64 bit assignment from latest alu32 bounds tracking which caused
a verifier issue due to type downgrade to scalar, from John Fastabend.
8) Follow-up on tail-call support in BPF subprogs which optimizes x64 JIT prologue
and epilogue sections, from Maciej Fijalkowski.
9) Add an option to perf RB map to improve sharing of event entries by avoiding remove-
on-close behavior. Also, add BPF_PROG_TEST_RUN for raw_tracepoint, from Song Liu.
10) Fix a crash in AF_XDP's socket_release when memory allocation for UMEMs fails,
from Magnus Karlsson.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r-- | net/bpf/test_run.c | 88 | ||||
-rw-r--r-- | net/core/bpf_sk_storage.c | 29 | ||||
-rw-r--r-- | net/core/filter.c | 418 | ||||
-rw-r--r-- | net/core/net_namespace.c | 12 | ||||
-rw-r--r-- | net/core/sock_diag.c | 9 | ||||
-rw-r--r-- | net/core/sock_map.c | 7 | ||||
-rw-r--r-- | net/ipv4/bpf_tcp_ca.c | 23 | ||||
-rw-r--r-- | net/xdp/xsk.c | 1 | ||||
-rw-r--r-- | net/xdp/xsk_queue.h | 2 |
9 files changed, 472 insertions, 117 deletions
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index a66f211726e7..c1c30a9f76f3 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -11,6 +11,7 @@ #include <net/sock.h> #include <net/tcp.h> #include <linux/error-injection.h> +#include <linux/smp.h> #define CREATE_TRACE_POINTS #include <trace/events/bpf_test_run.h> @@ -204,6 +205,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog, int b = 2, err = -EFAULT; u32 retval = 0; + if (kattr->test.flags || kattr->test.cpu) + return -EINVAL; + switch (prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: @@ -236,6 +240,84 @@ out: return err; } +struct bpf_raw_tp_test_run_info { + struct bpf_prog *prog; + void *ctx; + u32 retval; +}; + +static void +__bpf_prog_test_run_raw_tp(void *data) +{ + struct bpf_raw_tp_test_run_info *info = data; + + rcu_read_lock(); + info->retval = BPF_PROG_RUN(info->prog, info->ctx); + rcu_read_unlock(); +} + +int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in); + __u32 ctx_size_in = kattr->test.ctx_size_in; + struct bpf_raw_tp_test_run_info info; + int cpu = kattr->test.cpu, err = 0; + int current_cpu; + + /* doesn't support data_in/out, ctx_out, duration, or repeat */ + if (kattr->test.data_in || kattr->test.data_out || + kattr->test.ctx_out || kattr->test.duration || + kattr->test.repeat) + return -EINVAL; + + if (ctx_size_in < prog->aux->max_ctx_offset) + return -EINVAL; + + if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 && cpu != 0) + return -EINVAL; + + if (ctx_size_in) { + info.ctx = kzalloc(ctx_size_in, GFP_USER); + if (!info.ctx) + return -ENOMEM; + if (copy_from_user(info.ctx, ctx_in, ctx_size_in)) { + err = -EFAULT; + goto out; + } + } else { + info.ctx = NULL; + } + + info.prog = prog; + + current_cpu = get_cpu(); + if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 || + cpu == current_cpu) { + __bpf_prog_test_run_raw_tp(&info); + } else if (cpu >= nr_cpu_ids || !cpu_online(cpu)) { + /* smp_call_function_single() also checks cpu_online() + * after csd_lock(). However, since cpu is from user + * space, let's do an extra quick check to filter out + * invalid value before smp_call_function_single(). + */ + err = -ENXIO; + } else { + err = smp_call_function_single(cpu, __bpf_prog_test_run_raw_tp, + &info, 1); + } + put_cpu(); + + if (!err && + copy_to_user(&uattr->test.retval, &info.retval, sizeof(u32))) + err = -EFAULT; + +out: + kfree(info.ctx); + return err; +} + static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size) { void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in); @@ -410,6 +492,9 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, void *data; int ret; + if (kattr->test.flags || kattr->test.cpu) + return -EINVAL; + data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN, SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); if (IS_ERR(data)) @@ -607,6 +692,9 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) return -EINVAL; + if (kattr->test.flags || kattr->test.cpu) + return -EINVAL; + if (size < ETH_HLEN) return -EINVAL; diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 838efc682cff..c907f0dc7f87 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -269,7 +269,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, { struct bpf_local_storage_data *sdata; - if (flags > BPF_SK_STORAGE_GET_F_CREATE) + if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; sdata = sk_storage_lookup(sk, map, true); @@ -299,6 +299,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) { + if (!sk || !sk_fullsock(sk)) + return -EINVAL; + if (refcount_inc_not_zero(&sk->sk_refcnt)) { int err; @@ -355,7 +358,7 @@ const struct bpf_func_proto bpf_sk_storage_get_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_SOCKET, + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; @@ -375,27 +378,7 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_SOCKET, -}; - -const struct bpf_func_proto sk_storage_get_btf_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_BTF_ID, - .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], - .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, - .arg4_type = ARG_ANYTHING, -}; - -const struct bpf_func_proto sk_storage_delete_btf_proto = { - .func = bpf_sk_storage_delete, - .gpl_only = false, - .ret_type = RET_INTEGER, - .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_BTF_ID, - .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; struct bpf_sk_storage_diag { diff --git a/net/core/filter.c b/net/core/filter.c index 706f8db0ccf8..3fb6adad1957 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -77,6 +77,9 @@ #include <net/transp_v6.h> #include <linux/btf_ids.h> +static const struct bpf_func_proto * +bpf_sk_base_func_proto(enum bpf_func_id func_id); + int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { if (in_compat_syscall()) { @@ -2160,13 +2163,233 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev, return __bpf_redirect_no_mac(skb, dev, flags); } +#if IS_ENABLED(CONFIG_IPV6) +static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct net_device *dev = dst->dev; + u32 hh_len = LL_RESERVED_SPACE(dev); + const struct in6_addr *nexthop; + struct neighbour *neigh; + + if (dev_xmit_recursion()) { + net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); + goto out_drop; + } + + skb->dev = dev; + skb->tstamp = 0; + + if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { + struct sk_buff *skb2; + + skb2 = skb_realloc_headroom(skb, hh_len); + if (unlikely(!skb2)) { + kfree_skb(skb); + return -ENOMEM; + } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + consume_skb(skb); + skb = skb2; + } + + rcu_read_lock_bh(); + nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst), + &ipv6_hdr(skb)->daddr); + neigh = ip_neigh_gw6(dev, nexthop); + if (likely(!IS_ERR(neigh))) { + int ret; + + sock_confirm_neigh(skb, neigh); + dev_xmit_recursion_inc(); + ret = neigh_output(neigh, skb, false); + dev_xmit_recursion_dec(); + rcu_read_unlock_bh(); + return ret; + } + rcu_read_unlock_bh(); + IP6_INC_STATS(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); +out_drop: + kfree_skb(skb); + return -ENETDOWN; +} + +static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct net *net = dev_net(dev); + int err, ret = NET_XMIT_DROP; + struct dst_entry *dst; + struct flowi6 fl6 = { + .flowi6_flags = FLOWI_FLAG_ANYSRC, + .flowi6_mark = skb->mark, + .flowlabel = ip6_flowinfo(ip6h), + .flowi6_oif = dev->ifindex, + .flowi6_proto = ip6h->nexthdr, + .daddr = ip6h->daddr, + .saddr = ip6h->saddr, + }; + + dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); + if (IS_ERR(dst)) + goto out_drop; + + skb_dst_set(skb, dst); + + err = bpf_out_neigh_v6(net, skb); + if (unlikely(net_xmit_eval(err))) + dev->stats.tx_errors++; + else + ret = NET_XMIT_SUCCESS; + goto out_xmit; +out_drop: + dev->stats.tx_errors++; + kfree_skb(skb); +out_xmit: + return ret; +} +#else +static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} +#endif /* CONFIG_IPV6 */ + +#if IS_ENABLED(CONFIG_INET) +static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct rtable *rt = container_of(dst, struct rtable, dst); + struct net_device *dev = dst->dev; + u32 hh_len = LL_RESERVED_SPACE(dev); + struct neighbour *neigh; + bool is_v6gw = false; + + if (dev_xmit_recursion()) { + net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); + goto out_drop; + } + + skb->dev = dev; + skb->tstamp = 0; + + if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { + struct sk_buff *skb2; + + skb2 = skb_realloc_headroom(skb, hh_len); + if (unlikely(!skb2)) { + kfree_skb(skb); + return -ENOMEM; + } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + consume_skb(skb); + skb = skb2; + } + + rcu_read_lock_bh(); + neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); + if (likely(!IS_ERR(neigh))) { + int ret; + + sock_confirm_neigh(skb, neigh); + dev_xmit_recursion_inc(); + ret = neigh_output(neigh, skb, is_v6gw); + dev_xmit_recursion_dec(); + rcu_read_unlock_bh(); + return ret; + } + rcu_read_unlock_bh(); +out_drop: + kfree_skb(skb); + return -ENETDOWN; +} + +static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev) +{ + const struct iphdr *ip4h = ip_hdr(skb); + struct net *net = dev_net(dev); + int err, ret = NET_XMIT_DROP; + struct rtable *rt; + struct flowi4 fl4 = { + .flowi4_flags = FLOWI_FLAG_ANYSRC, + .flowi4_mark = skb->mark, + .flowi4_tos = RT_TOS(ip4h->tos), + .flowi4_oif = dev->ifindex, + .flowi4_proto = ip4h->protocol, + .daddr = ip4h->daddr, + .saddr = ip4h->saddr, + }; + + rt = ip_route_output_flow(net, &fl4, NULL); + if (IS_ERR(rt)) + goto out_drop; + if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { + ip_rt_put(rt); + goto out_drop; + } + + skb_dst_set(skb, &rt->dst); + + err = bpf_out_neigh_v4(net, skb); + if (unlikely(net_xmit_eval(err))) + dev->stats.tx_errors++; + else + ret = NET_XMIT_SUCCESS; + goto out_xmit; +out_drop: + dev->stats.tx_errors++; + kfree_skb(skb); +out_xmit: + return ret; +} +#else +static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} +#endif /* CONFIG_INET */ + +static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev) +{ + struct ethhdr *ethh = eth_hdr(skb); + + if (unlikely(skb->mac_header >= skb->network_header)) + goto out; + bpf_push_mac_rcsum(skb); + if (is_multicast_ether_addr(ethh->h_dest)) + goto out; + + skb_pull(skb, sizeof(*ethh)); + skb_unset_mac_header(skb); + skb_reset_network_header(skb); + + if (skb->protocol == htons(ETH_P_IP)) + return __bpf_redirect_neigh_v4(skb, dev); + else if (skb->protocol == htons(ETH_P_IPV6)) + return __bpf_redirect_neigh_v6(skb, dev); +out: + kfree_skb(skb); + return -ENOTSUPP; +} + +/* Internal, non-exposed redirect flags. */ +enum { + BPF_F_NEIGH = (1ULL << 1), +#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH) +}; + BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; struct sk_buff *clone; int ret; - if (unlikely(flags & ~(BPF_F_INGRESS))) + if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); @@ -2203,23 +2426,11 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); -BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) -{ - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - - if (unlikely(flags & ~(BPF_F_INGRESS))) - return TC_ACT_SHOT; - - ri->flags = flags; - ri->tgt_index = ifindex; - - return TC_ACT_REDIRECT; -} - int skb_do_redirect(struct sk_buff *skb) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct net_device *dev; + u32 flags = ri->flags; dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index); ri->tgt_index = 0; @@ -2228,7 +2439,22 @@ int skb_do_redirect(struct sk_buff *skb) return -EINVAL; } - return __bpf_redirect(skb, dev, ri->flags); + return flags & BPF_F_NEIGH ? + __bpf_redirect_neigh(skb, dev) : + __bpf_redirect(skb, dev, flags); +} + +BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) + return TC_ACT_SHOT; + + ri->flags = flags; + ri->tgt_index = ifindex; + + return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_proto = { @@ -2239,6 +2465,27 @@ static const struct bpf_func_proto bpf_redirect_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + if (unlikely(flags)) + return TC_ACT_SHOT; + + ri->flags = BPF_F_NEIGH; + ri->tgt_index = ifindex; + + return TC_ACT_REDIRECT; +} + +static const struct bpf_func_proto bpf_redirect_neigh_proto = { + .func = bpf_redirect_neigh, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes) { msg->apply_bytes = bytes; @@ -2704,6 +2951,23 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { .gpl_only = false, .ret_type = RET_INTEGER, }; + +BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb) +{ + struct sock *sk = skb_to_full_sk(skb); + + if (!sk || !sk_fullsock(sk)) + return 0; + + return sock_cgroup_classid(&sk->sk_cgrp_data); +} + +static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = { + .func = bpf_skb_cgroup_classid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; #endif BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) @@ -4085,18 +4349,17 @@ static inline u64 __bpf_sk_cgroup_id(struct sock *sk) { struct cgroup *cgrp; + sk = sk_to_full_sk(sk); + if (!sk || !sk_fullsock(sk)) + return 0; + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return cgroup_id(cgrp); } BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) { - struct sock *sk = skb_to_full_sk(skb); - - if (!sk || !sk_fullsock(sk)) - return 0; - - return __bpf_sk_cgroup_id(sk); + return __bpf_sk_cgroup_id(skb->sk); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { @@ -4112,6 +4375,10 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, struct cgroup *ancestor; struct cgroup *cgrp; + sk = sk_to_full_sk(sk); + if (!sk || !sk_fullsock(sk)) + return 0; + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ancestor = cgroup_ancestor(cgrp, ancestor_level); if (!ancestor) @@ -4123,12 +4390,7 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, ancestor_level) { - struct sock *sk = skb_to_full_sk(skb); - - if (!sk || !sk_fullsock(sk)) - return 0; - - return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level); + return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { @@ -4148,7 +4410,7 @@ static const struct bpf_func_proto bpf_sk_cgroup_id_proto = { .func = bpf_sk_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCKET, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level) @@ -4160,7 +4422,7 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { .func = bpf_sk_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCKET, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, }; #endif @@ -4214,7 +4476,7 @@ const struct bpf_func_proto bpf_xdp_output_proto = { BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) { - return skb->sk ? sock_gen_cookie(skb->sk) : 0; + return skb->sk ? __sock_gen_cookie(skb->sk) : 0; } static const struct bpf_func_proto bpf_get_socket_cookie_proto = { @@ -4226,7 +4488,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_proto = { BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { - return sock_gen_cookie(ctx->sk); + return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { @@ -4238,7 +4500,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx) { - return sock_gen_cookie(ctx); + return __sock_gen_cookie(ctx); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { @@ -4250,7 +4512,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { - return sock_gen_cookie(ctx->sk); + return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { @@ -4263,7 +4525,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { static u64 __bpf_get_netns_cookie(struct sock *sk) { #ifdef CONFIG_NET_NS - return net_gen_cookie(sk ? sk->sk_net.net : &init_net); + return __net_gen_cookie(sk ? sk->sk_net.net : &init_net); #else return 0; #endif @@ -5694,7 +5956,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { BPF_CALL_1(bpf_sk_release, struct sock *, sk) { - if (sk_is_refcounted(sk)) + if (sk && sk_is_refcounted(sk)) sock_gen_put(sk); return 0; } @@ -5703,7 +5965,7 @@ 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_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, @@ -6085,7 +6347,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len u32 cookie; int ret; - if (unlikely(th_len < sizeof(*th))) + if (unlikely(!sk || th_len < sizeof(*th))) return -EINVAL; /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */ @@ -6138,7 +6400,7 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .gpl_only = true, .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM, @@ -6152,7 +6414,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, u32 cookie; u16 mss; - if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) + if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) @@ -6207,7 +6469,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM, @@ -6216,7 +6478,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) { - if (flags != 0) + if (!sk || flags != 0) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EOPNOTSUPP; @@ -6240,7 +6502,7 @@ static const struct bpf_func_proto bpf_sk_assign_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_SOCK_COMMON, + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_ANYTHING, }; @@ -6620,7 +6882,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6639,7 +6901,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6741,6 +7003,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; + case BPF_FUNC_redirect_neigh: + return &bpf_redirect_neigh_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: @@ -6771,6 +7035,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; #endif +#ifdef CONFIG_CGROUP_NET_CLASSID + case BPF_FUNC_skb_cgroup_classid: + return &bpf_skb_cgroup_classid_proto; +#endif #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; @@ -6800,7 +7068,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_assign_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6841,7 +7109,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_gen_syncookie_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6883,7 +7151,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6929,7 +7197,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_cgroup_classid_curr_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6971,7 +7239,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_lookup_tcp_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6982,7 +7250,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -7009,7 +7277,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -9746,7 +10014,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -9913,8 +10181,7 @@ 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, - .arg1_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP6], }; @@ -9930,8 +10197,7 @@ 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, - .arg1_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP], }; @@ -9954,8 +10220,7 @@ 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, - .arg1_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW], }; @@ -9978,8 +10243,7 @@ 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, - .arg1_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ], }; @@ -10000,7 +10264,37 @@ 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, - .arg1_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; + +static const struct bpf_func_proto * +bpf_sk_base_func_proto(enum bpf_func_id func_id) +{ + const struct bpf_func_proto *func; + + switch (func_id) { + case BPF_FUNC_skc_to_tcp6_sock: + func = &bpf_skc_to_tcp6_sock_proto; + break; + case BPF_FUNC_skc_to_tcp_sock: + func = &bpf_skc_to_tcp_sock_proto; + break; + case BPF_FUNC_skc_to_tcp_timewait_sock: + func = &bpf_skc_to_tcp_timewait_sock_proto; + break; + case BPF_FUNC_skc_to_tcp_request_sock: + func = &bpf_skc_to_tcp_request_sock_proto; + break; + case BPF_FUNC_skc_to_udp6_sock: + func = &bpf_skc_to_udp6_sock_proto; + break; + default: + return bpf_base_func_proto(func_id); + } + + if (!perfmon_capable()) + return NULL; + + return func; +} diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 944ab214e5ae..dbc66b896287 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -19,6 +19,7 @@ #include <linux/net_namespace.h> #include <linux/sched/task.h> #include <linux/uidgid.h> +#include <linux/cookie.h> #include <net/sock.h> #include <net/netlink.h> @@ -69,16 +70,16 @@ EXPORT_SYMBOL_GPL(pernet_ops_rwsem); static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; -static atomic64_t cookie_gen; +DEFINE_COOKIE(net_cookie); -u64 net_gen_cookie(struct net *net) +u64 __net_gen_cookie(struct net *net) { while (1) { u64 res = atomic64_read(&net->net_cookie); if (res) return res; - res = atomic64_inc_return(&cookie_gen); + res = gen_cookie_next(&net_cookie); atomic64_cmpxchg(&net->net_cookie, 0, res); } } @@ -1101,7 +1102,10 @@ static int __init net_ns_init(void) panic("Could not allocate generic netns"); rcu_assign_pointer(init_net.gen, ng); - net_gen_cookie(&init_net); + + preempt_disable(); + __net_gen_cookie(&init_net); + preempt_enable(); down_write(&pernet_ops_rwsem); if (setup_net(&init_net, &init_user_ns)) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index c13ffbd33d8d..c9c45b935f99 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -11,7 +11,7 @@ #include <linux/tcp.h> #include <linux/workqueue.h> #include <linux/nospec.h> - +#include <linux/cookie.h> #include <linux/inet_diag.h> #include <linux/sock_diag.h> @@ -19,16 +19,17 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); static struct workqueue_struct *broadcast_wq; -static atomic64_t cookie_gen; -u64 sock_gen_cookie(struct sock *sk) +DEFINE_COOKIE(sock_cookie); + +u64 __sock_gen_cookie(struct sock *sk) { while (1) { u64 res = atomic64_read(&sk->sk_cookie); if (res) return res; - res = atomic64_inc_return(&cookie_gen); + res = gen_cookie_next(&sock_cookie); atomic64_cmpxchg(&sk->sk_cookie, 0, res); } } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index e1f05e3fa1d0..e83a80e8f13b 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -401,7 +401,7 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key) if (!sk) return ERR_PTR(-ENOENT); - sock_gen_cookie(sk); + __sock_gen_cookie(sk); return &sk->sk_cookie; } @@ -610,6 +610,9 @@ static int sock_map_update_elem(struct bpf_map *map, void *key, struct sock *sk = (struct sock *)value; int ret; + if (unlikely(!sk || !sk_fullsock(sk))) + return -EINVAL; + if (!sock_map_sk_is_suitable(sk)) return -EOPNOTSUPP; @@ -1206,7 +1209,7 @@ static void *sock_hash_lookup_sys(struct bpf_map *map, void *key) if (!sk) return ERR_PTR(-ENOENT); - sock_gen_cookie(sk); + __sock_gen_cookie(sk); return &sk->sk_cookie; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 74a2ef598c31..618954f82764 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -28,22 +28,6 @@ static u32 unsupported_ops[] = { static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; -static struct bpf_func_proto btf_sk_storage_get_proto __read_mostly; -static struct bpf_func_proto btf_sk_storage_delete_proto __read_mostly; - -static void convert_sk_func_proto(struct bpf_func_proto *to, const struct bpf_func_proto *from) -{ - int i; - - *to = *from; - for (i = 0; i < ARRAY_SIZE(to->arg_type); i++) { - if (to->arg_type[i] == ARG_PTR_TO_SOCKET) { - to->arg_type[i] = ARG_PTR_TO_BTF_ID; - to->arg_btf_id[i] = &tcp_sock_id; - } - } -} - static int bpf_tcp_ca_init(struct btf *btf) { s32 type_id; @@ -59,9 +43,6 @@ static int bpf_tcp_ca_init(struct btf *btf) tcp_sock_id = type_id; tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); - convert_sk_func_proto(&btf_sk_storage_get_proto, &bpf_sk_storage_get_proto); - convert_sk_func_proto(&btf_sk_storage_delete_proto, &bpf_sk_storage_delete_proto); - return 0; } @@ -188,9 +169,9 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_tcp_send_ack: return &bpf_tcp_send_ack_proto; case BPF_FUNC_sk_storage_get: - return &btf_sk_storage_get_proto; + return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: - return &btf_sk_storage_delete_proto; + return &bpf_sk_storage_delete_proto; default: return bpf_base_func_proto(func_id); } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 3895697f8540..ba4dfb17c666 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -703,6 +703,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xs->pool = xp_create_and_assign_umem(xs, umem_xs->umem); if (!xs->pool) { + err = -ENOMEM; sockfd_put(sock); goto out_unlock; } diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 2d883f631c85..dc1dd5ef70d1 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -96,7 +96,7 @@ struct xsk_queue { * seen and read by the consumer. * * The consumer peeks into the ring to see if the producer has written - * any new entries. If so, the producer can then read these entries + * any new entries. If so, the consumer can then read these entries * and when it is done reading them release them back to the producer * so that the producer can use these slots to fill in new entries. * |