From 79eecf631c14e7f4057186570ac20e2cfac3802e Mon Sep 17 00:00:00 2001 From: Chengen Du Date: Sat, 13 Jul 2024 19:47:35 +0800 Subject: [PATCH 1/2] af_packet: Handle outgoing VLAN packets without hardware offloading The issue initially stems from libpcap. The ethertype will be overwritten as the VLAN TPID if the network interface lacks hardware VLAN offloading. In the outbound packet path, if hardware VLAN offloading is unavailable, the VLAN tag is inserted into the payload but then cleared from the sk_buff struct. Consequently, this can lead to a false negative when checking for the presence of a VLAN tag, causing the packet sniffing outcome to lack VLAN tag information (i.e., TCI-TPID). As a result, the packet capturing tool may be unable to parse packets as expected. The TCI-TPID is missing because the prb_fill_vlan_info() function does not modify the tp_vlan_tci/tp_vlan_tpid values, as the information is in the payload and not in the sk_buff struct. The skb_vlan_tag_present() function only checks vlan_all in the sk_buff struct. In cooked mode, the L2 header is stripped, preventing the packet capturing tool from determining the correct TCI-TPID value. Additionally, the protocol in SLL is incorrect, which means the packet capturing tool cannot parse the L3 header correctly. Link: https://github.com/the-tcpdump-group/libpcap/issues/1105 Link: https://lore.kernel.org/netdev/20240520070348.26725-1-chengen.du@canonical.com/T/#u Fixes: 393e52e33c6c ("packet: deliver VLAN TCI to userspace") Cc: stable@vger.kernel.org Signed-off-by: Chengen Du Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240713114735.62360-1-chengen.du@canonical.com Signed-off-by: Jakub Kicinski --- net/packet/af_packet.c | 86 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 84 insertions(+), 2 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ea3ebc160e25..4692a9ef110b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -538,6 +538,61 @@ static void *packet_current_frame(struct packet_sock *po, return packet_lookup_frame(po, rb, rb->head, status); } +static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) +{ + u8 *skb_orig_data = skb->data; + int skb_orig_len = skb->len; + struct vlan_hdr vhdr, *vh; + unsigned int header_len; + + if (!dev) + return 0; + + /* In the SOCK_DGRAM scenario, skb data starts at the network + * protocol, which is after the VLAN headers. The outer VLAN + * header is at the hard_header_len offset in non-variable + * length link layer headers. If it's a VLAN device, the + * min_header_len should be used to exclude the VLAN header + * size. + */ + if (dev->min_header_len == dev->hard_header_len) + header_len = dev->hard_header_len; + else if (is_vlan_dev(dev)) + header_len = dev->min_header_len; + else + return 0; + + skb_push(skb, skb->data - skb_mac_header(skb)); + vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); + if (skb_orig_data != skb->data) { + skb->data = skb_orig_data; + skb->len = skb_orig_len; + } + if (unlikely(!vh)) + return 0; + + return ntohs(vh->h_vlan_TCI); +} + +static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) +{ + __be16 proto = skb->protocol; + + if (unlikely(eth_type_vlan(proto))) { + u8 *skb_orig_data = skb->data; + int skb_orig_len = skb->len; + + skb_push(skb, skb->data - skb_mac_header(skb)); + proto = __vlan_get_protocol(skb, proto, NULL); + if (skb_orig_data != skb->data) { + skb->data = skb_orig_data; + skb->len = skb_orig_len; + } + } + + return proto; +} + static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { del_timer_sync(&pkc->retire_blk_timer); @@ -1007,10 +1062,16 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { + struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); + if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { + ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); + ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); + ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; @@ -2428,6 +2489,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { + h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); + h.h2->tp_vlan_tpid = ntohs(skb->protocol); + status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; @@ -2457,7 +2522,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; - sll->sll_protocol = skb->protocol; + sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? + vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; @@ -3482,7 +3548,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; - sll->sll_protocol = skb->protocol; + sll->sll_protocol = (sock->type == SOCK_DGRAM) ? + vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_cmsgs(msg, sk, skb); @@ -3539,6 +3606,21 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { + struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); + if (dev) { + aux.tp_vlan_tci = vlan_get_tci(skb, dev); + aux.tp_vlan_tpid = ntohs(skb->protocol); + aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else { + aux.tp_vlan_tci = 0; + aux.tp_vlan_tpid = 0; + } + rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; From 59a931c5b732ca5fc2ca727f5a72aeabaafa85ec Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 12 Jul 2024 09:51:16 +0000 Subject: [PATCH 2/2] xdp: fix invalid wait context of page_pool_destroy() If the driver uses a page pool, it creates a page pool with page_pool_create(). The reference count of page pool is 1 as default. A page pool will be destroyed only when a reference count reaches 0. page_pool_destroy() is used to destroy page pool, it decreases a reference count. When a page pool is destroyed, ->disconnect() is called, which is mem_allocator_disconnect(). This function internally acquires mutex_lock(). If the driver uses XDP, it registers a memory model with xdp_rxq_info_reg_mem_model(). The xdp_rxq_info_reg_mem_model() internally increases a page pool reference count if a memory model is a page pool. Now the reference count is 2. To destroy a page pool, the driver should call both page_pool_destroy() and xdp_unreg_mem_model(). The xdp_unreg_mem_model() internally calls page_pool_destroy(). Only page_pool_destroy() decreases a reference count. If a driver calls page_pool_destroy() then xdp_unreg_mem_model(), we will face an invalid wait context warning. Because xdp_unreg_mem_model() calls page_pool_destroy() with rcu_read_lock(). The page_pool_destroy() internally acquires mutex_lock(). Splat looks like: ============================= [ BUG: Invalid wait context ] 6.10.0-rc6+ #4 Tainted: G W ----------------------------- ethtool/1806 is trying to lock: ffffffff90387b90 (mem_id_lock){+.+.}-{4:4}, at: mem_allocator_disconnect+0x73/0x150 other info that might help us debug this: context-{5:5} 3 locks held by ethtool/1806: stack backtrace: CPU: 0 PID: 1806 Comm: ethtool Tainted: G W 6.10.0-rc6+ #4 f916f41f172891c800f2fed Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021 Call Trace: dump_stack_lvl+0x7e/0xc0 __lock_acquire+0x1681/0x4de0 ? _printk+0x64/0xe0 ? __pfx_mark_lock.part.0+0x10/0x10 ? __pfx___lock_acquire+0x10/0x10 lock_acquire+0x1b3/0x580 ? mem_allocator_disconnect+0x73/0x150 ? __wake_up_klogd.part.0+0x16/0xc0 ? __pfx_lock_acquire+0x10/0x10 ? dump_stack_lvl+0x91/0xc0 __mutex_lock+0x15c/0x1690 ? mem_allocator_disconnect+0x73/0x150 ? __pfx_prb_read_valid+0x10/0x10 ? mem_allocator_disconnect+0x73/0x150 ? __pfx_llist_add_batch+0x10/0x10 ? console_unlock+0x193/0x1b0 ? lockdep_hardirqs_on+0xbe/0x140 ? __pfx___mutex_lock+0x10/0x10 ? tick_nohz_tick_stopped+0x16/0x90 ? __irq_work_queue_local+0x1e5/0x330 ? irq_work_queue+0x39/0x50 ? __wake_up_klogd.part.0+0x79/0xc0 ? mem_allocator_disconnect+0x73/0x150 mem_allocator_disconnect+0x73/0x150 ? __pfx_mem_allocator_disconnect+0x10/0x10 ? mark_held_locks+0xa5/0xf0 ? rcu_is_watching+0x11/0xb0 page_pool_release+0x36e/0x6d0 page_pool_destroy+0xd7/0x440 xdp_unreg_mem_model+0x1a7/0x2a0 ? __pfx_xdp_unreg_mem_model+0x10/0x10 ? kfree+0x125/0x370 ? bnxt_free_ring.isra.0+0x2eb/0x500 ? bnxt_free_mem+0x5ac/0x2500 xdp_rxq_info_unreg+0x4a/0xd0 bnxt_free_mem+0x1356/0x2500 bnxt_close_nic+0xf0/0x3b0 ? __pfx_bnxt_close_nic+0x10/0x10 ? ethnl_parse_bit+0x2c6/0x6d0 ? __pfx___nla_validate_parse+0x10/0x10 ? __pfx_ethnl_parse_bit+0x10/0x10 bnxt_set_features+0x2a8/0x3e0 __netdev_update_features+0x4dc/0x1370 ? ethnl_parse_bitset+0x4ff/0x750 ? __pfx_ethnl_parse_bitset+0x10/0x10 ? __pfx___netdev_update_features+0x10/0x10 ? mark_held_locks+0xa5/0xf0 ? _raw_spin_unlock_irqrestore+0x42/0x70 ? __pm_runtime_resume+0x7d/0x110 ethnl_set_features+0x32d/0xa20 To fix this problem, it uses rhashtable_lookup_fast() instead of rhashtable_lookup() with rcu_read_lock(). Using xa without rcu_read_lock() here is safe. xa is freed by __xdp_mem_allocator_rcu_free() and this is called by call_rcu() of mem_xa_remove(). The mem_xa_remove() is called by page_pool_destroy() if a reference count reaches 0. The xa is already protected by the reference count mechanism well in the control plane. So removing rcu_read_lock() for page_pool_destroy() is safe. Fixes: c3f812cea0d7 ("page_pool: do not release pool until inflight == 0.") Signed-off-by: Taehee Yoo Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20240712095116.3801586-1-ap420073@gmail.com Signed-off-by: Jakub Kicinski --- net/core/xdp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/core/xdp.c b/net/core/xdp.c index 022c12059cf2..bcc5551c6424 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -127,10 +127,8 @@ void xdp_unreg_mem_model(struct xdp_mem_info *mem) return; if (type == MEM_TYPE_PAGE_POOL) { - rcu_read_lock(); - xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); + xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); - rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(xdp_unreg_mem_model);