diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 14 | ||||
-rw-r--r-- | net/core/drop_monitor.c | 23 | ||||
-rw-r--r-- | net/core/dst.c | 59 | ||||
-rw-r--r-- | net/core/filter.c | 12 | ||||
-rw-r--r-- | net/core/flow_dissector.c | 8 | ||||
-rw-r--r-- | net/core/skmsg.c | 12 | ||||
-rw-r--r-- | net/core/sock.c | 12 | ||||
-rw-r--r-- | net/core/xdp.c | 3 |
8 files changed, 96 insertions, 47 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 75ca6c6d01d6..62ff7121b22d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1195,6 +1195,18 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) return -ENOMEM; for_each_netdev(net, d) { + struct netdev_name_node *name_node; + list_for_each_entry(name_node, &d->name_node->list, list) { + if (!sscanf(name_node->name, name, &i)) + continue; + if (i < 0 || i >= max_netdevices) + continue; + + /* avoid cases where sscanf is not exact inverse of printf */ + snprintf(buf, IFNAMSIZ, name, i); + if (!strncmp(buf, name_node->name, IFNAMSIZ)) + set_bit(i, inuse); + } if (!sscanf(d->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) @@ -11094,7 +11106,7 @@ static void __net_exit default_device_exit(struct net *net) continue; /* Leave virtual devices for the generic cleanup */ - if (dev->rtnl_link_ops) + if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 571f191c06d9..db65ce62b625 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1053,6 +1053,20 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) return 0; err_module_put: + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); + struct sk_buff *skb; + + del_timer_sync(&hw_data->send_timer); + cancel_work_sync(&hw_data->dm_alert_work); + while ((skb = __skb_dequeue(&hw_data->drop_queue))) { + struct devlink_trap_metadata *hw_metadata; + + hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; + net_dm_hw_metadata_free(hw_metadata); + consume_skb(skb); + } + } module_put(THIS_MODULE); return rc; } @@ -1134,6 +1148,15 @@ static int net_dm_trace_on_set(struct netlink_ext_ack *extack) err_unregister_trace: unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); err_module_put: + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct sk_buff *skb; + + del_timer_sync(&data->send_timer); + cancel_work_sync(&data->dm_alert_work); + while ((skb = __skb_dequeue(&data->drop_queue))) + consume_skb(skb); + } module_put(THIS_MODULE); return rc; } diff --git a/net/core/dst.c b/net/core/dst.c index 0c01bd8d9d81..fb3bcba87744 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -237,37 +237,62 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) } EXPORT_SYMBOL(__dst_destroy_metrics_generic); -static struct dst_ops md_dst_ops = { - .family = AF_UNSPEC, -}; +struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie) +{ + return NULL; +} -static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) +u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old) { - WARN_ONCE(1, "Attempting to call output on metadata dst\n"); - kfree_skb(skb); - return 0; + return NULL; } -static int dst_md_discard(struct sk_buff *skb) +struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) { - WARN_ONCE(1, "Attempting to call input on metadata dst\n"); - kfree_skb(skb); - return 0; + return NULL; +} + +void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) +{ +} +EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu); + +void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ +} +EXPORT_SYMBOL_GPL(dst_blackhole_redirect); + +unsigned int dst_blackhole_mtu(const struct dst_entry *dst) +{ + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } +EXPORT_SYMBOL_GPL(dst_blackhole_mtu); + +static struct dst_ops dst_blackhole_ops = { + .family = AF_UNSPEC, + .neigh_lookup = dst_blackhole_neigh_lookup, + .check = dst_blackhole_check, + .cow_metrics = dst_blackhole_cow_metrics, + .update_pmtu = dst_blackhole_update_pmtu, + .redirect = dst_blackhole_redirect, + .mtu = dst_blackhole_mtu, +}; static void __metadata_dst_init(struct metadata_dst *md_dst, enum metadata_type type, u8 optslen) - { struct dst_entry *dst; dst = &md_dst->dst; - dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE, + dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, DST_METADATA | DST_NOCOUNT); - - dst->input = dst_md_discard; - dst->output = dst_md_discard_out; - memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); md_dst->type = type; } diff --git a/net/core/filter.c b/net/core/filter.c index f0a19a48c048..9358bc4a3711 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3552,11 +3552,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, return 0; } -static u32 __bpf_skb_max_len(const struct sk_buff *skb) -{ - return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len : - SKB_MAX_ALLOC; -} +#define BPF_SKB_MAX_LEN SKB_MAX_ALLOC BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) @@ -3605,7 +3601,7 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, { u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); - u32 len_max = __bpf_skb_max_len(skb); + u32 len_max = BPF_SKB_MAX_LEN; __be16 proto = skb->protocol; bool shrink = len_diff < 0; u32 off; @@ -3688,7 +3684,7 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, u64 flags) { - u32 max_len = __bpf_skb_max_len(skb); + u32 max_len = BPF_SKB_MAX_LEN; u32 min_len = __bpf_skb_min_len(skb); int ret; @@ -3764,7 +3760,7 @@ static const struct bpf_func_proto sk_skb_change_tail_proto = { static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u64 flags) { - u32 max_len = __bpf_skb_max_len(skb); + u32 max_len = BPF_SKB_MAX_LEN; u32 new_len = skb->len + head_room; int ret; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index e21950a2c897..d48b37b15b27 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -175,7 +175,7 @@ void skb_flow_get_icmp_tci(const struct sk_buff *skb, * avoid confusion with packets without such field */ if (icmp_has_id(ih->type)) - key_icmp->id = ih->un.echo.id ? : 1; + key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1; else key_icmp->id = 0; } @@ -1050,6 +1050,9 @@ proto_again: key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } + __skb_flow_dissect_ipv4(skb, flow_dissector, + target_container, data, iph); + if (ip_is_fragment(iph)) { key_control->flags |= FLOW_DIS_IS_FRAGMENT; @@ -1066,9 +1069,6 @@ proto_again: } } - __skb_flow_dissect_ipv4(skb, flow_dissector, - target_container, data, iph); - break; } case htons(ETH_P_IPV6): { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 25cdbb20f3a0..923a1d0f84ca 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -488,6 +488,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb if (unlikely(!msg)) return -EAGAIN; sk_msg_init(msg); + skb_set_owner_r(skb, sk); return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); } @@ -791,7 +792,6 @@ static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int { switch (verdict) { case __SK_REDIRECT: - skb_set_owner_r(skb, sk); sk_psock_skb_redirect(skb); break; case __SK_PASS: @@ -809,10 +809,6 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) rcu_read_lock(); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { - /* We skip full set_owner_r here because if we do a SK_PASS - * or SK_DROP we can skip skb memory accounting and use the - * TLS context. - */ skb->sk = psock->sk; tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); @@ -881,12 +877,13 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) kfree_skb(skb); goto out; } - skb_set_owner_r(skb, sk); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { + skb->sk = sk; tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + skb->sk = NULL; } sk_psock_verdict_apply(psock, skb, ret); out: @@ -957,12 +954,13 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, kfree_skb(skb); goto out; } - skb_set_owner_r(skb, sk); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { + skb->sk = sk; tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + skb->sk = NULL; } sk_psock_verdict_apply(psock, skb, ret); out: diff --git a/net/core/sock.c b/net/core/sock.c index 6fa3cdc74105..27be3db26de6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2099,16 +2099,10 @@ void skb_orphan_partial(struct sk_buff *skb) if (skb_is_tcp_pure_ack(skb)) return; - if (can_skb_orphan_partial(skb)) { - struct sock *sk = skb->sk; - - if (refcount_inc_not_zero(&sk->sk_refcnt)) { - WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); - skb->destructor = sock_efree; - } - } else { + if (can_skb_orphan_partial(skb)) + skb_set_owner_sk_safe(skb, skb->sk); + else skb_orphan(skb); - } } EXPORT_SYMBOL(skb_orphan_partial); diff --git a/net/core/xdp.c b/net/core/xdp.c index d900cebc0acd..b8d7fa47d293 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -349,7 +349,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); - napi_direct &= !xdp_return_frame_no_direct(); + if (napi_direct && xdp_return_frame_no_direct()) + napi_direct = false; page_pool_put_full_page(xa->page_pool, page, napi_direct); rcu_read_unlock(); break; |