diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-30 08:33:04 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-30 08:33:04 -0700 |
commit | d8ec19857b095b39d114ae299713bd8ea6c1e66a (patch) | |
tree | 57a75bbcf7ef6e671208c61e35ae570ba51b3359 /net | |
parent | 4a4be1ad3a6efea16c56615f31117590fd881358 (diff) | |
parent | 13c7c941e72908b8cce5a84b45a7b5e485ca12ed (diff) |
Merge tag 'net-6.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from bpf and netfilter.
Current release - regressions:
- gro: initialize network_offset in network layer
- tcp: reduce accepted window in NEW_SYN_RECV state
Current release - new code bugs:
- eth: mlx5e: do not use ptp structure for tx ts stats when not
initialized
- eth: ice: check for unregistering correct number of devlink params
Previous releases - regressions:
- bpf: Allow delete from sockmap/sockhash only if update is allowed
- sched: taprio: extend minimum interval restriction to entire cycle
too
- netfilter: ipset: add list flush to cancel_gc
- ipv4: fix address dump when IPv4 is disabled on an interface
- sock_map: avoid race between sock_map_close and sk_psock_put
- eth: mlx5: use mlx5_ipsec_rx_status_destroy to correctly delete
status rules
Previous releases - always broken:
- core: fix __dst_negative_advice() race
- bpf:
- fix multi-uprobe PID filtering logic
- fix pkt_type override upon netkit pass verdict
- netfilter: tproxy: bail out if IP has been disabled on the device
- af_unix: annotate data-race around unix_sk(sk)->addr
- eth: mlx5e: fix UDP GSO for encapsulated packets
- eth: idpf: don't enable NAPI and interrupts prior to allocating Rx
buffers
- eth: i40e: fully suspend and resume IO operations in EEH case
- eth: octeontx2-pf: free send queue buffers incase of leaf to inner
- eth: ipvlan: dont Use skb->sk in ipvlan_process_v{4,6}_outbound"
* tag 'net-6.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (69 commits)
netdev: add qstat for csum complete
ipvlan: Dont Use skb->sk in ipvlan_process_v{4,6}_outbound
net: ena: Fix redundant device NUMA node override
ice: check for unregistering correct number of devlink params
ice: fix 200G PHY types to link speed mapping
i40e: Fully suspend and resume IO operations in EEH case
i40e: factoring out i40e_suspend/i40e_resume
e1000e: move force SMBUS near the end of enable_ulp function
net: dsa: microchip: fix RGMII error in KSZ DSA driver
ipv4: correctly iterate over the target netns in inet_dump_ifaddr()
net: fix __dst_negative_advice() race
nfc/nci: Add the inconsistency check between the input data length and count
MAINTAINERS: dwmac: starfive: update Maintainer
net/sched: taprio: extend minimum interval restriction to entire cycle too
net/sched: taprio: make q->picos_per_byte available to fill_sched_entry()
netfilter: nft_fib: allow from forward/input without iif selector
netfilter: tproxy: bail out if IP has been disabled on the device
netfilter: nft_payload: skbuff vlan metadata mangle support
net: ti: icssg-prueth: Fix start counter for ft1 filter
sock_map: avoid race between sock_map_close and sk_psock_put
...
Diffstat (limited to 'net')
-rw-r--r-- | net/core/sock_map.c | 22 | ||||
-rw-r--r-- | net/ethernet/eth.c | 4 | ||||
-rw-r--r-- | net/ipv4/af_inet.c | 2 | ||||
-rw-r--r-- | net/ipv4/devinet.c | 7 | ||||
-rw-r--r-- | net/ipv4/netfilter/nf_tproxy_ipv4.c | 2 | ||||
-rw-r--r-- | net/ipv4/route.c | 22 | ||||
-rw-r--r-- | net/ipv4/tcp_ipv4.c | 7 | ||||
-rw-r--r-- | net/ipv4/tcp_minisocks.c | 7 | ||||
-rw-r--r-- | net/ipv6/ip6_offload.c | 2 | ||||
-rw-r--r-- | net/ipv6/route.c | 29 | ||||
-rw-r--r-- | net/ipv6/tcp_ipv6.c | 7 | ||||
-rw-r--r-- | net/netfilter/ipset/ip_set_list_set.c | 3 | ||||
-rw-r--r-- | net/netfilter/nfnetlink_queue.c | 2 | ||||
-rw-r--r-- | net/netfilter/nft_fib.c | 8 | ||||
-rw-r--r-- | net/netfilter/nft_payload.c | 95 | ||||
-rw-r--r-- | net/sched/sch_taprio.c | 14 | ||||
-rw-r--r-- | net/unix/af_unix.c | 19 | ||||
-rw-r--r-- | net/xfrm/xfrm_policy.c | 11 |
18 files changed, 152 insertions, 111 deletions
diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 9402889840bf..d3dbb92153f2 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -423,9 +423,6 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; - if (irqs_disabled()) - return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ - spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -948,9 +945,6 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; - if (irqs_disabled()) - return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ - hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); @@ -1680,19 +1674,23 @@ void sock_map_close(struct sock *sk, long timeout) lock_sock(sk); rcu_read_lock(); - psock = sk_psock_get(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - release_sock(sk); - saved_close = READ_ONCE(sk->sk_prot)->close; - } else { + psock = sk_psock(sk); + if (likely(psock)) { saved_close = psock->saved_close; sock_map_remove_links(sk, psock); + psock = sk_psock_get(sk); + if (unlikely(!psock)) + goto no_psock; rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); + } else { + saved_close = READ_ONCE(sk->sk_prot)->close; +no_psock: + rcu_read_unlock(); + release_sock(sk); } /* Make sure we do not recurse. This is a bug. diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 049c3adeb850..4e3651101b86 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -161,9 +161,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb_reset_mac_header(skb); - eth = (struct ethhdr *)skb->data; - skb_pull_inline(skb, ETH_HLEN); - + eth = eth_skb_pull_mac(skb); eth_skb_pkt_type(skb, dev); /* diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e03ba4a21c39..b24d74616637 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1532,7 +1532,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) } NAPI_GRO_CB(skb)->flush |= flush; - NAPI_GRO_CB(skb)->inner_network_offset = off; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 96accde527da..f3892ee9dfb3 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1887,10 +1887,11 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) goto done; if (fillargs.ifindex) { - err = -ENODEV; dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); - if (!dev) + if (!dev) { + err = -ENODEV; goto done; + } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto done; @@ -1902,7 +1903,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = inet_base_seq(tgt_net); - for_each_netdev_dump(net, dev, ctx->ifindex) { + for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 69e331799604..73e66a088e25 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -58,6 +58,8 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) laddr = 0; indev = __in_dev_get_rcu(skb->dev); + if (!indev) + return daddr; in_dev_for_each_ifa_rcu(ifa, indev) { if (ifa->ifa_flags & IFA_F_SECONDARY) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5fd54103174f..b3073d1c8f8f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -129,7 +129,8 @@ struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst); -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, @@ -825,22 +826,15 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf __ip_do_redirect(rt, skb, &fl4, true); } -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst) { struct rtable *rt = dst_rtable(dst); - struct dst_entry *ret = dst; - if (rt) { - if (dst->obsolete > 0) { - ip_rt_put(rt); - ret = NULL; - } else if ((rt->rt_flags & RTCF_REDIRECTED) || - rt->dst.expires) { - ip_rt_put(rt); - ret = NULL; - } - } - return ret; + if ((dst->obsolete > 0) || + (rt->rt_flags & RTCF_REDIRECTED) || + rt->dst.expires) + sk_dst_reset(sk); } /* diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 30ef0c8f5e92..b710958393e6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1144,14 +1144,9 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, #endif } - /* RFC 7323 2.3 - * The window field (SEG.WND) of every outgoing segment, with the - * exception of <SYN> segments, MUST be right-shifted by - * Rcv.Wind.Shift bits: - */ tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, - req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, + tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), 0, &key, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b93619b2384b..538c06f95918 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -783,8 +783,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* RFC793: "first check sequence number". */ - if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) { + if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + tcp_rsk(req)->rcv_nxt, + tcp_rsk(req)->rcv_nxt + + tcp_synack_window(req))) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST) && !tcp_oow_rate_limited(sock_net(sk), skb, diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index bd5aff97d8b1..9822163428b0 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -236,7 +236,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, if (unlikely(!iph)) goto out; - NAPI_GRO_CB(skb)->inner_network_offset = off; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; flush += ntohs(iph->payload_len) != skb->len - hlen; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index bbc2a0dd9314..a504b88ec06b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -87,7 +87,8 @@ struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); -static struct dst_entry *ip6_negative_advice(struct dst_entry *); +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); @@ -2770,24 +2771,24 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); -static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); - if (rt) { - if (rt->rt6i_flags & RTF_CACHE) { - rcu_read_lock(); - if (rt6_check_expired(rt)) { - rt6_remove_exception_rt(rt); - dst = NULL; - } - rcu_read_unlock(); - } else { - dst_release(dst); - dst = NULL; + if (rt->rt6i_flags & RTF_CACHE) { + rcu_read_lock(); + if (rt6_check_expired(rt)) { + /* counteract the dst_release() in sk_dst_reset() */ + dst_hold(dst); + sk_dst_reset(sk); + + rt6_remove_exception_rt(rt); } + rcu_read_unlock(); + return; } - return dst; + sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4c3605485b68..8c577b651bfc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1272,15 +1272,10 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ - /* RFC 7323 2.3 - * The window field (SEG.WND) of every outgoing segment, with the - * exception of <SYN> segments, MUST be right-shifted by - * Rcv.Wind.Shift bits: - */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, - req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, + tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, &key, ipv6_get_dsfield(ipv6_hdr(skb)), 0, diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 6c3f28bc59b3..54e2a1dd7f5f 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -549,6 +549,9 @@ list_set_cancel_gc(struct ip_set *set) if (SET_WITH_TIMEOUT(set)) timer_shutdown_sync(&map->gc); + + /* Flush list to drop references to other ipsets */ + list_set_flush(set); } static const struct ip_set_type_variant set_variant = { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 00f4bd21c59b..f1c31757e496 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -169,7 +169,9 @@ instance_destroy_rcu(struct rcu_head *head) struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance, rcu); + rcu_read_lock(); nfqnl_flush(inst, NULL, 0); + rcu_read_unlock(); kfree(inst); module_put(THIS_MODULE); } diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 37cfe6dd712d..b58f62195ff3 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -35,11 +35,9 @@ int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, switch (priv->result) { case NFT_FIB_RESULT_OIF: case NFT_FIB_RESULT_OIFNAME: - hooks = (1 << NF_INET_PRE_ROUTING); - if (priv->flags & NFTA_FIB_F_IIF) { - hooks |= (1 << NF_INET_LOCAL_IN) | - (1 << NF_INET_FORWARD); - } + hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD); break; case NFT_FIB_RESULT_ADDRTYPE: if (priv->flags & NFTA_FIB_F_IIF) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 0a689c8e0295..0c43d748e23a 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -45,36 +45,27 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) int mac_off = skb_mac_header(skb) - skb->data; u8 *vlanh, *dst_u8 = (u8 *) d; struct vlan_ethhdr veth; - u8 vlan_hlen = 0; - - if ((skb->protocol == htons(ETH_P_8021AD) || - skb->protocol == htons(ETH_P_8021Q)) && - offset >= VLAN_ETH_HLEN && offset < VLAN_ETH_HLEN + VLAN_HLEN) - vlan_hlen += VLAN_HLEN; vlanh = (u8 *) &veth; - if (offset < VLAN_ETH_HLEN + vlan_hlen) { + if (offset < VLAN_ETH_HLEN) { u8 ethlen = len; - if (vlan_hlen && - skb_copy_bits(skb, mac_off, &veth, VLAN_ETH_HLEN) < 0) - return false; - else if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth)) + if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth)) return false; - if (offset + len > VLAN_ETH_HLEN + vlan_hlen) - ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen; + if (offset + len > VLAN_ETH_HLEN) + ethlen -= offset + len - VLAN_ETH_HLEN; - memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen); + memcpy(dst_u8, vlanh + offset, ethlen); len -= ethlen; if (len == 0) return true; dst_u8 += ethlen; - offset = ETH_HLEN + vlan_hlen; + offset = ETH_HLEN; } else { - offset -= VLAN_HLEN + vlan_hlen; + offset -= VLAN_HLEN; } return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0; @@ -154,12 +145,12 @@ int nft_payload_inner_offset(const struct nft_pktinfo *pkt) return pkt->inneroff; } -static bool nft_payload_need_vlan_copy(const struct nft_payload *priv) +static bool nft_payload_need_vlan_adjust(u32 offset, u32 len) { - unsigned int len = priv->offset + priv->len; + unsigned int boundary = offset + len; /* data past ether src/dst requested, copy needed */ - if (len > offsetof(struct ethhdr, h_proto)) + if (boundary > offsetof(struct ethhdr, h_proto)) return true; return false; @@ -183,7 +174,7 @@ void nft_payload_eval(const struct nft_expr *expr, goto err; if (skb_vlan_tag_present(skb) && - nft_payload_need_vlan_copy(priv)) { + nft_payload_need_vlan_adjust(priv->offset, priv->len)) { if (!nft_payload_copy_vlan(dest, skb, priv->offset, priv->len)) goto err; @@ -810,21 +801,79 @@ struct nft_payload_set { u8 csum_flags; }; +/* This is not struct vlan_hdr. */ +struct nft_payload_vlan_hdr { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; +}; + +static bool +nft_payload_set_vlan(const u32 *src, struct sk_buff *skb, u8 offset, u8 len, + int *vlan_hlen) +{ + struct nft_payload_vlan_hdr *vlanh; + __be16 vlan_proto; + u16 vlan_tci; + + if (offset >= offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto)) { + *vlan_hlen = VLAN_HLEN; + return true; + } + + switch (offset) { + case offsetof(struct vlan_ethhdr, h_vlan_proto): + if (len == 2) { + vlan_proto = nft_reg_load_be16(src); + skb->vlan_proto = vlan_proto; + } else if (len == 4) { + vlanh = (struct nft_payload_vlan_hdr *)src; + __vlan_hwaccel_put_tag(skb, vlanh->h_vlan_proto, + ntohs(vlanh->h_vlan_TCI)); + } else { + return false; + } + break; + case offsetof(struct vlan_ethhdr, h_vlan_TCI): + if (len != 2) + return false; + + vlan_tci = ntohs(nft_reg_load_be16(src)); + skb->vlan_tci = vlan_tci; + break; + default: + return false; + } + + return true; +} + static void nft_payload_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_payload_set *priv = nft_expr_priv(expr); - struct sk_buff *skb = pkt->skb; const u32 *src = ®s->data[priv->sreg]; - int offset, csum_offset; + int offset, csum_offset, vlan_hlen = 0; + struct sk_buff *skb = pkt->skb; __wsum fsum, tsum; switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: if (!skb_mac_header_was_set(skb)) goto err; - offset = skb_mac_header(skb) - skb->data; + + if (skb_vlan_tag_present(skb) && + nft_payload_need_vlan_adjust(priv->offset, priv->len)) { + if (!nft_payload_set_vlan(src, skb, + priv->offset, priv->len, + &vlan_hlen)) + goto err; + + if (!vlan_hlen) + return; + } + + offset = skb_mac_header(skb) - skb->data - vlan_hlen; break; case NFT_PAYLOAD_NETWORK_HEADER: offset = skb_network_offset(skb); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 1ab17e8a7260..937a0c513c17 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1151,11 +1151,6 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, list_for_each_entry(entry, &new->entries, list) cycle = ktime_add_ns(cycle, entry->interval); - if (!cycle) { - NL_SET_ERR_MSG(extack, "'cycle_time' can never be 0"); - return -EINVAL; - } - if (cycle < 0 || cycle > INT_MAX) { NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); return -EINVAL; @@ -1164,6 +1159,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, new->cycle_time = cycle; } + if (new->cycle_time < new->num_entries * length_to_duration(q, ETH_ZLEN)) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too small"); + return -EINVAL; + } + taprio_calculate_gate_durations(q, new); return 0; @@ -1848,6 +1848,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, } q->flags = taprio_flags; + /* Needed for length_to_duration() during netlink attribute parsing */ + taprio_set_picos_per_byte(dev, q); + err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags); if (err < 0) return err; @@ -1907,7 +1910,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (err < 0) goto free_sched; - taprio_set_picos_per_byte(dev, q); taprio_update_queue_max_sdu(q, new_admin, stab); if (FULL_OFFLOAD_IS_ENABLED(q->flags)) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e4af6616e1df..25b49efc0926 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -731,7 +731,7 @@ static int unix_listen(struct socket *sock, int backlog) if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) goto out; /* Only stream/seqpacket sockets accept */ err = -EINVAL; - if (!u->addr) + if (!READ_ONCE(u->addr)) goto out; /* No listens on an unbound socket */ unix_state_lock(sk); if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN) @@ -1131,8 +1131,8 @@ static struct sock *unix_find_other(struct net *net, static int unix_autobind(struct sock *sk) { - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct unix_address *addr; u32 lastnum, ordernum; @@ -1155,6 +1155,7 @@ static int unix_autobind(struct sock *sk) addr->name->sun_family = AF_UNIX; refcount_set(&addr->refcnt, 1); + old_hash = sk->sk_hash; ordernum = get_random_u32(); lastnum = ordernum & 0xFFFFF; retry: @@ -1195,8 +1196,8 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, { umode_t mode = S_IFSOCK | (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask()); - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct mnt_idmap *idmap; struct unix_address *addr; @@ -1234,6 +1235,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, if (u->addr) goto out_unlock; + old_hash = sk->sk_hash; new_hash = unix_bsd_hash(d_backing_inode(dentry)); unix_table_double_lock(net, old_hash, new_hash); u->path.mnt = mntget(parent.mnt); @@ -1261,8 +1263,8 @@ out: static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, int addr_len) { - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct unix_address *addr; int err; @@ -1280,6 +1282,7 @@ static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, goto out_mutex; } + old_hash = sk->sk_hash; new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type); unix_table_double_lock(net, old_hash, new_hash); @@ -1369,7 +1372,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if ((test_bit(SOCK_PASSCRED, &sock->flags) || test_bit(SOCK_PASSPIDFD, &sock->flags)) && - !unix_sk(sk)->addr) { + !READ_ONCE(unix_sk(sk)->addr)) { err = unix_autobind(sk); if (err) goto out; @@ -1481,7 +1484,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, goto out; if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { + test_bit(SOCK_PASSPIDFD, &sock->flags)) && + !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; @@ -1950,7 +1954,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, } if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { + test_bit(SOCK_PASSPIDFD, &sock->flags)) && + !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 475b904fe68b..66e07de2de35 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3910,15 +3910,10 @@ static void xfrm_link_failure(struct sk_buff *skb) /* Impossible. Such dst must be popped before reaches point of failure. */ } -static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) +static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst) { - if (dst) { - if (dst->obsolete) { - dst_release(dst); - dst = NULL; - } - } - return dst; + if (dst->obsolete) + sk_dst_reset(sk); } static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr) |