diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 10 | ||||
-rw-r--r-- | net/core/dst.c | 14 | ||||
-rw-r--r-- | net/core/filter.c | 41 | ||||
-rw-r--r-- | net/core/lwtunnel.c | 4 | ||||
-rw-r--r-- | net/core/neighbour.c | 17 | ||||
-rw-r--r-- | net/core/request_sock.c | 1 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 2 | ||||
-rw-r--r-- | net/core/sock.c | 31 | ||||
-rw-r--r-- | net/core/sock_diag.c | 14 | ||||
-rw-r--r-- | net/core/utils.c | 49 |
10 files changed, 92 insertions, 91 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 323c04edd779..1225b4be8ed6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2974,6 +2974,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) new_index = skb_tx_hash(dev, skb); if (queue_index != new_index && sk && + sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); @@ -5345,6 +5346,12 @@ static int __netdev_upper_dev_link(struct net_device *dev, changeupper_info.master = master; changeupper_info.linking = true; + ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + &changeupper_info.info); + ret = notifier_to_errno(ret); + if (ret) + return ret; + ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private, master); if (ret) @@ -5487,6 +5494,9 @@ void netdev_upper_dev_unlink(struct net_device *dev, changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; changeupper_info.linking = false; + call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + &changeupper_info.info); + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); /* Here is the tricky part. We must remove all dev's lower diff --git a/net/core/dst.c b/net/core/dst.c index 0771c8cb9307..2a1818065e12 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -144,12 +144,12 @@ loop: mutex_unlock(&dst_gc_mutex); } -int dst_discard_sk(struct sock *sk, struct sk_buff *skb) +int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } -EXPORT_SYMBOL(dst_discard_sk); +EXPORT_SYMBOL(dst_discard_out); const u32 dst_default_metrics[RTAX_MAX + 1] = { /* This initializer is needed to force linker to place this variable @@ -177,7 +177,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, dst->xfrm = NULL; #endif dst->input = dst_discard; - dst->output = dst_discard_sk; + dst->output = dst_discard_out; dst->error = 0; dst->obsolete = initial_obsolete; dst->header_len = 0; @@ -224,7 +224,7 @@ static void ___dst_free(struct dst_entry *dst) */ if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { dst->input = dst_discard; - dst->output = dst_discard_sk; + dst->output = dst_discard_out; } dst->obsolete = DST_OBSOLETE_DEAD; } @@ -352,7 +352,7 @@ static struct dst_ops md_dst_ops = { .family = AF_UNSPEC, }; -static int dst_md_discard_sk(struct sock *sk, struct sk_buff *skb) +static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { WARN_ONCE(1, "Attempting to call output on metadata dst\n"); kfree_skb(skb); @@ -375,7 +375,7 @@ static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen) DST_METADATA | DST_NOCACHE | DST_NOCOUNT); dst->input = dst_md_discard; - dst->output = dst_md_discard_sk; + dst->output = dst_md_discard_out; memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); } @@ -430,7 +430,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, if (!unregister) { dst->input = dst_discard; - dst->output = dst_discard_sk; + dst->output = dst_discard_out; } else { dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); diff --git a/net/core/filter.c b/net/core/filter.c index 53a5036fb32d..0b00094932ab 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -56,10 +56,10 @@ * @sk: sock associated with &sk_buff * @skb: buffer to filter * - * Run the filter code and then cut skb->data to correct size returned by - * SK_RUN_FILTER. If pkt_len is 0 we toss packet. If skb->len is smaller + * Run the eBPF program and then cut skb->data to correct size returned by + * the program. If pkt_len is 0 we toss packet. If skb->len is smaller * than pkt_len we keep whole skb->data. This is the socket level - * wrapper to SK_RUN_FILTER. It returns 0 if the packet should + * wrapper to BPF_PROG_RUN. It returns 0 if the packet should * be accepted or -EPERM if the packet should be tossed. * */ @@ -83,7 +83,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter) { - unsigned int pkt_len = SK_RUN_FILTER(filter, skb); + unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb); err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } @@ -149,12 +149,6 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) return raw_smp_processor_id(); } -/* note that this only generates 32-bit random numbers */ -static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) -{ - return prandom_u32(); -} - static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, struct bpf_insn *insn_buf) { @@ -313,7 +307,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, *insn = BPF_EMIT_CALL(__get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: - *insn = BPF_EMIT_CALL(__get_random_u32); + *insn = BPF_EMIT_CALL(bpf_user_rnd_u32); + bpf_user_rnd_init_once(); break; } break; @@ -1084,16 +1079,18 @@ EXPORT_SYMBOL_GPL(bpf_prog_create); * @pfp: the unattached filter that is created * @fprog: the filter program * @trans: post-classic verifier transformation handler + * @save_orig: save classic BPF program * * This function effectively does the same as bpf_prog_create(), only * that it builds up its insns buffer from user space provided buffer. * It also allows for passing a bpf_aux_classic_check_t handler. */ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, - bpf_aux_classic_check_t trans) + bpf_aux_classic_check_t trans, bool save_orig) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; + int err; /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) @@ -1109,12 +1106,16 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, } fp->len = fprog->len; - /* Since unattached filters are not copied back to user - * space through sk_get_filter(), we do not need to hold - * a copy here, and can spare us the work. - */ fp->orig_prog = NULL; + if (save_orig) { + err = bpf_prog_store_orig_filter(fp, fprog); + if (err) { + __bpf_prog_free(fp); + return -ENOMEM; + } + } + /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ @@ -1456,6 +1457,7 @@ int skb_do_redirect(struct sk_buff *skb) return dev_forward_skb(dev, skb); skb->dev = dev; + skb_sender_cpu_clear(skb); return dev_queue_xmit(skb); } @@ -1638,7 +1640,8 @@ sk_filter_func_proto(enum bpf_func_id func_id) case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_trace_printk: - return bpf_get_trace_printk_proto(); + if (capable(CAP_SYS_ADMIN)) + return bpf_get_trace_printk_proto(); default: return NULL; } @@ -1734,7 +1737,8 @@ static bool tc_cls_act_is_valid_access(int off, int size, static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, - struct bpf_insn *insn_buf) + struct bpf_insn *insn_buf, + struct bpf_prog *prog) { struct bpf_insn *insn = insn_buf; @@ -1825,6 +1829,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, offsetof(struct __sk_buff, cb[4]): BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + prog->cb_access = 1; ctx_off -= offsetof(struct __sk_buff, cb[0]); ctx_off += offsetof(struct sk_buff, cb); ctx_off += offsetof(struct qdisc_skb_cb, data); diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index dfb1a9ca0835..299cfc24d888 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -180,7 +180,7 @@ int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) } EXPORT_SYMBOL(lwtunnel_cmp_encap); -int lwtunnel_output(struct sock *sk, struct sk_buff *skb) +int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; @@ -199,7 +199,7 @@ int lwtunnel_output(struct sock *sk, struct sk_buff *skb) rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->output)) - ret = ops->output(sk, skb); + ret = ops->output(net, sk, skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8c57fdf4d68e..1aa8437ed6c4 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2249,6 +2249,14 @@ static bool neigh_master_filtered(struct net_device *dev, int master_idx) return false; } +static bool neigh_ifindex_filtered(struct net_device *dev, int filter_idx) +{ + if (filter_idx && dev->ifindex != filter_idx) + return true; + + return false; +} + static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { @@ -2259,16 +2267,19 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; struct neigh_hash_table *nht; - int filter_master_idx = 0; + int filter_master_idx = 0, filter_idx = 0; unsigned int flags = NLM_F_MULTI; int err; err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL); if (!err) { + if (tb[NDA_IFINDEX]) + filter_idx = nla_get_u32(tb[NDA_IFINDEX]); + if (tb[NDA_MASTER]) filter_master_idx = nla_get_u32(tb[NDA_MASTER]); - if (filter_master_idx) + if (filter_idx || filter_master_idx) flags |= NLM_F_DUMP_FILTERED; } @@ -2283,6 +2294,8 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, n = rcu_dereference_bh(n->next)) { if (!net_eq(dev_net(n->dev), net)) continue; + if (neigh_ifindex_filtered(n->dev, filter_idx)) + continue; if (neigh_master_filtered(n->dev, filter_master_idx)) continue; if (idx < s_idx) diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 15c853806518..5d26056b6d8f 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -45,7 +45,6 @@ void reqsk_queue_alloc(struct request_sock_queue *queue) queue->fastopenq.rskq_rst_head = NULL; queue->fastopenq.rskq_rst_tail = NULL; queue->fastopenq.qlen = 0; - queue->fastopenq.max_qlen = 0; queue->rskq_accept_head = NULL; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b2258a36d894..24775953fa68 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -96,7 +96,7 @@ int rtnl_is_locked(void) EXPORT_SYMBOL(rtnl_is_locked); #ifdef CONFIG_PROVE_LOCKING -int lockdep_rtnl_is_held(void) +bool lockdep_rtnl_is_held(void) { return lockdep_is_held(&rtnl_mutex); } diff --git a/net/core/sock.c b/net/core/sock.c index 7dd1263e4c24..dcc7d62654d5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -988,6 +988,10 @@ set_rcvbuf: sk->sk_max_pacing_rate); break; + case SO_INCOMING_CPU: + sk->sk_incoming_cpu = val; + break; + default: ret = -ENOPROTOOPT; break; @@ -1852,6 +1856,32 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, } EXPORT_SYMBOL(sock_alloc_send_skb); +int sock_cmsg_send(struct sock *sk, struct msghdr *msg, + struct sockcm_cookie *sockc) +{ + struct cmsghdr *cmsg; + + for_each_cmsghdr(cmsg, msg) { + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + if (cmsg->cmsg_level != SOL_SOCKET) + continue; + switch (cmsg->cmsg_type) { + case SO_MARK: + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) + return -EINVAL; + sockc->mark = *(u32 *)CMSG_DATA(cmsg); + break; + default: + return -EINVAL; + } + } + return 0; +} +EXPORT_SYMBOL(sock_cmsg_send); + /* On 32bit arches, an skb frag is limited to 2^15 */ #define SKB_FRAG_PAGE_ORDER get_order(32768) @@ -2353,6 +2383,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_max_pacing_rate = ~0U; sk->sk_pacing_rate = ~0U; + sk->sk_incoming_cpu = -1; /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 817622f3dbb7..0c1d58d43f67 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -1,3 +1,5 @@ +/* License: GPL */ + #include <linux/mutex.h> #include <linux/socket.h> #include <linux/skbuff.h> @@ -323,14 +325,4 @@ static int __init sock_diag_init(void) BUG_ON(!broadcast_wq); return register_pernet_subsys(&diag_net_ops); } - -static void __exit sock_diag_exit(void) -{ - unregister_pernet_subsys(&diag_net_ops); - destroy_workqueue(broadcast_wq); -} - -module_init(sock_diag_init); -module_exit(sock_diag_exit); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_SOCK_DIAG); +device_initcall(sock_diag_init); diff --git a/net/core/utils.c b/net/core/utils.c index 3dffce953c39..3d17ca8b4744 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -348,52 +348,3 @@ void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, } } EXPORT_SYMBOL(inet_proto_csum_replace_by_diff); - -struct __net_random_once_work { - struct work_struct work; - struct static_key *key; -}; - -static void __net_random_once_deferred(struct work_struct *w) -{ - struct __net_random_once_work *work = - container_of(w, struct __net_random_once_work, work); - BUG_ON(!static_key_enabled(work->key)); - static_key_slow_dec(work->key); - kfree(work); -} - -static void __net_random_once_disable_jump(struct static_key *key) -{ - struct __net_random_once_work *w; - - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (!w) - return; - - INIT_WORK(&w->work, __net_random_once_deferred); - w->key = key; - schedule_work(&w->work); -} - -bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *once_key) -{ - static DEFINE_SPINLOCK(lock); - unsigned long flags; - - spin_lock_irqsave(&lock, flags); - if (*done) { - spin_unlock_irqrestore(&lock, flags); - return false; - } - - get_random_bytes(buf, nbytes); - *done = true; - spin_unlock_irqrestore(&lock, flags); - - __net_random_once_disable_jump(once_key); - - return true; -} -EXPORT_SYMBOL(__net_get_random_once); |