From 6e823d288c023f2cf463a29347b1fe1b7855bd71 Mon Sep 17 00:00:00 2001 From: JosiahMg Date: Thu, 1 Aug 2024 09:09:35 +0800 Subject: [PATCH] isisd: vlan-subif isis neighbor Fixed the problem that physical interfaces can establish isis neighbor relationships with vlan subinterfaces Signed-off-by: JosiahMg --- include/linux/if_packet.h | 317 +++++++++++++++++++++++++++++++++++++- isisd/isis_pfpacket.c | 56 ++++++- 2 files changed, 362 insertions(+), 11 deletions(-) diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 057edb33dcf3..9efc42382fdb 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -1,16 +1,319 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ #ifndef __LINUX_IF_PACKET_H #define __LINUX_IF_PACKET_H +#include #include +struct sockaddr_pkt { + unsigned short spkt_family; + unsigned char spkt_device[14]; + __be16 spkt_protocol; +}; + struct sockaddr_ll { - unsigned short sll_family; - __be16 sll_protocol; - int sll_ifindex; - unsigned short sll_hatype; - unsigned char sll_pkttype; - unsigned char sll_halen; - unsigned char sll_addr[8]; + unsigned short sll_family; + __be16 sll_protocol; + int sll_ifindex; + unsigned short sll_hatype; + unsigned char sll_pkttype; + unsigned char sll_halen; + unsigned char sll_addr[8]; +}; + +/* Packet types */ + +#define PACKET_HOST 0 /* To us */ +#define PACKET_BROADCAST 1 /* To all */ +#define PACKET_MULTICAST 2 /* To group */ +#define PACKET_OTHERHOST 3 /* To someone else */ +#define PACKET_OUTGOING 4 /* Outgoing of any type */ +#define PACKET_LOOPBACK 5 /* MC/BRD frame looped back */ +#define PACKET_USER 6 /* To user space */ +#define PACKET_KERNEL 7 /* To kernel space */ +/* Unused, PACKET_FASTROUTE and PACKET_LOOPBACK are invisible to user space */ +#define PACKET_FASTROUTE 6 /* Fastrouted frame */ + +/* Packet socket options */ + +#define PACKET_ADD_MEMBERSHIP 1 +#define PACKET_DROP_MEMBERSHIP 2 +#define PACKET_RECV_OUTPUT 3 +/* Value 4 is still used by obsolete turbo-packet. */ +#define PACKET_RX_RING 5 +#define PACKET_STATISTICS 6 +#define PACKET_COPY_THRESH 7 +#define PACKET_AUXDATA 8 +#define PACKET_ORIGDEV 9 +#define PACKET_VERSION 10 +#define PACKET_HDRLEN 11 +#define PACKET_RESERVE 12 +#define PACKET_TX_RING 13 +#define PACKET_LOSS 14 +#define PACKET_VNET_HDR 15 +#define PACKET_TX_TIMESTAMP 16 +#define PACKET_TIMESTAMP 17 +#define PACKET_FANOUT 18 +#define PACKET_TX_HAS_OFF 19 +#define PACKET_QDISC_BYPASS 20 +#define PACKET_ROLLOVER_STATS 21 +#define PACKET_FANOUT_DATA 22 +#define PACKET_IGNORE_OUTGOING 23 +#define PACKET_VNET_HDR_SZ 24 + +#define PACKET_FANOUT_HASH 0 +#define PACKET_FANOUT_LB 1 +#define PACKET_FANOUT_CPU 2 +#define PACKET_FANOUT_ROLLOVER 3 +#define PACKET_FANOUT_RND 4 +#define PACKET_FANOUT_QM 5 +#define PACKET_FANOUT_CBPF 6 +#define PACKET_FANOUT_EBPF 7 +#define PACKET_FANOUT_FLAG_ROLLOVER 0x1000 +#define PACKET_FANOUT_FLAG_UNIQUEID 0x2000 +#define PACKET_FANOUT_FLAG_IGNORE_OUTGOING 0x4000 +#define PACKET_FANOUT_FLAG_DEFRAG 0x8000 + +struct tpacket_stats { + unsigned int tp_packets; + unsigned int tp_drops; +}; + +struct tpacket_stats_v3 { + unsigned int tp_packets; + unsigned int tp_drops; + unsigned int tp_freeze_q_cnt; +}; + +struct tpacket_rollover_stats { + __aligned_u64 tp_all; + __aligned_u64 tp_huge; + __aligned_u64 tp_failed; +}; + +union tpacket_stats_u { + struct tpacket_stats stats1; + struct tpacket_stats_v3 stats3; +}; + +struct tpacket_auxdata { + __u32 tp_status; + __u32 tp_len; + __u32 tp_snaplen; + __u16 tp_mac; + __u16 tp_net; + __u16 tp_vlan_tci; + __u16 tp_vlan_tpid; +}; + +/* Rx ring - header status */ +#define TP_STATUS_KERNEL 0 +#define TP_STATUS_USER (1 << 0) +#define TP_STATUS_COPY (1 << 1) +#define TP_STATUS_LOSING (1 << 2) +#define TP_STATUS_CSUMNOTREADY (1 << 3) +#define TP_STATUS_VLAN_VALID (1 << 4) /* auxdata has valid tp_vlan_tci */ +#define TP_STATUS_BLK_TMO (1 << 5) +#define TP_STATUS_VLAN_TPID_VALID (1 << 6) /* auxdata has valid tp_vlan_tpid */ +#define TP_STATUS_CSUM_VALID (1 << 7) +#define TP_STATUS_GSO_TCP (1 << 8) + +/* Tx ring - header status */ +#define TP_STATUS_AVAILABLE 0 +#define TP_STATUS_SEND_REQUEST (1 << 0) +#define TP_STATUS_SENDING (1 << 1) +#define TP_STATUS_WRONG_FORMAT (1 << 2) + +/* Rx and Tx ring - header status */ +#define TP_STATUS_TS_SOFTWARE (1 << 29) +#define TP_STATUS_TS_SYS_HARDWARE (1 << 30) /* deprecated, never set */ +#define TP_STATUS_TS_RAW_HARDWARE (1U << 31) + +/* Rx ring - feature request bits */ +#define TP_FT_REQ_FILL_RXHASH 0x1 + +struct tpacket_hdr { + unsigned long tp_status; + unsigned int tp_len; + unsigned int tp_snaplen; + unsigned short tp_mac; + unsigned short tp_net; + unsigned int tp_sec; + unsigned int tp_usec; +}; + +#define TPACKET_ALIGNMENT 16 +#define TPACKET_ALIGN(x) (((x)+TPACKET_ALIGNMENT-1)&~(TPACKET_ALIGNMENT-1)) +#define TPACKET_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket_hdr)) + sizeof(struct sockaddr_ll)) + +struct tpacket2_hdr { + __u32 tp_status; + __u32 tp_len; + __u32 tp_snaplen; + __u16 tp_mac; + __u16 tp_net; + __u32 tp_sec; + __u32 tp_nsec; + __u16 tp_vlan_tci; + __u16 tp_vlan_tpid; + __u8 tp_padding[4]; +}; + +struct tpacket_hdr_variant1 { + __u32 tp_rxhash; + __u32 tp_vlan_tci; + __u16 tp_vlan_tpid; + __u16 tp_padding; +}; + +struct tpacket3_hdr { + __u32 tp_next_offset; + __u32 tp_sec; + __u32 tp_nsec; + __u32 tp_snaplen; + __u32 tp_len; + __u32 tp_status; + __u16 tp_mac; + __u16 tp_net; + /* pkt_hdr variants */ + union { + struct tpacket_hdr_variant1 hv1; + }; + __u8 tp_padding[8]; +}; + +struct tpacket_bd_ts { + unsigned int ts_sec; + union { + unsigned int ts_usec; + unsigned int ts_nsec; + }; +}; + +struct tpacket_hdr_v1 { + __u32 block_status; + __u32 num_pkts; + __u32 offset_to_first_pkt; + + /* Number of valid bytes (including padding) + * blk_len <= tp_block_size + */ + __u32 blk_len; + + /* + * Quite a few uses of sequence number: + * 1. Make sure cache flush etc worked. + * Well, one can argue - why not use the increasing ts below? + * But look at 2. below first. + * 2. When you pass around blocks to other user space decoders, + * you can see which blk[s] is[are] outstanding etc. + * 3. Validate kernel code. + */ + __aligned_u64 seq_num; + + /* + * ts_last_pkt: + * + * Case 1. Block has 'N'(N >=1) packets and TMO'd(timed out) + * ts_last_pkt == 'time-stamp of last packet' and NOT the + * time when the timer fired and the block was closed. + * By providing the ts of the last packet we can absolutely + * guarantee that time-stamp wise, the first packet in the + * next block will never precede the last packet of the + * previous block. + * Case 2. Block has zero packets and TMO'd + * ts_last_pkt = time when the timer fired and the block + * was closed. + * Case 3. Block has 'N' packets and NO TMO. + * ts_last_pkt = time-stamp of the last pkt in the block. + * + * ts_first_pkt: + * Is always the time-stamp when the block was opened. + * Case a) ZERO packets + * No packets to deal with but atleast you know the + * time-interval of this block. + * Case b) Non-zero packets + * Use the ts of the first packet in the block. + * + */ + struct tpacket_bd_ts ts_first_pkt, ts_last_pkt; +}; + +union tpacket_bd_header_u { + struct tpacket_hdr_v1 bh1; +}; + +struct tpacket_block_desc { + __u32 version; + __u32 offset_to_priv; + union tpacket_bd_header_u hdr; +}; + +#define TPACKET2_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket2_hdr)) + sizeof(struct sockaddr_ll)) +#define TPACKET3_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket3_hdr)) + sizeof(struct sockaddr_ll)) + +enum tpacket_versions { + TPACKET_V1, + TPACKET_V2, + TPACKET_V3 }; +/* + Frame structure: + + - Start. Frame must be aligned to TPACKET_ALIGNMENT=16 + - struct tpacket_hdr + - pad to TPACKET_ALIGNMENT=16 + - struct sockaddr_ll + - Gap, chosen so that packet data (Start+tp_net) alignes to TPACKET_ALIGNMENT=16 + - Start+tp_mac: [ Optional MAC header ] + - Start+tp_net: Packet data, aligned to TPACKET_ALIGNMENT=16. + - Pad to align to TPACKET_ALIGNMENT=16 + */ + +struct tpacket_req { + unsigned int tp_block_size; /* Minimal size of contiguous block */ + unsigned int tp_block_nr; /* Number of blocks */ + unsigned int tp_frame_size; /* Size of frame */ + unsigned int tp_frame_nr; /* Total number of frames */ +}; + +struct tpacket_req3 { + unsigned int tp_block_size; /* Minimal size of contiguous block */ + unsigned int tp_block_nr; /* Number of blocks */ + unsigned int tp_frame_size; /* Size of frame */ + unsigned int tp_frame_nr; /* Total number of frames */ + unsigned int tp_retire_blk_tov; /* timeout in msecs */ + unsigned int tp_sizeof_priv; /* offset to private data area */ + unsigned int tp_feature_req_word; +}; + +union tpacket_req_u { + struct tpacket_req req; + struct tpacket_req3 req3; +}; + +struct packet_mreq { + int mr_ifindex; + unsigned short mr_type; + unsigned short mr_alen; + unsigned char mr_address[8]; +}; + +struct fanout_args { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u16 id; + __u16 type_flags; +#else + __u16 type_flags; + __u16 id; +#endif + __u32 max_num_members; +}; + +#define PACKET_MR_MULTICAST 0 +#define PACKET_MR_PROMISC 1 +#define PACKET_MR_ALLMULTI 2 +#define PACKET_MR_UNICAST 3 + #endif diff --git a/isisd/isis_pfpacket.c b/isisd/isis_pfpacket.c index af69fac1cd9a..634bdca7cb8d 100644 --- a/isisd/isis_pfpacket.c +++ b/isisd/isis_pfpacket.c @@ -10,7 +10,7 @@ #include #if ISIS_METHOD == ISIS_METHOD_PFPACKET #include /* the L2 protocols */ -#include +#include "linux/if_packet.h" #include @@ -134,6 +134,13 @@ static int open_packet_socket(struct isis_circuit *circuit) return ISIS_WARNING; } + int val = 1; + if (setsockopt(fd, SOL_PACKET, PACKET_AUXDATA, &val, sizeof(val)) == -1 && + errno != ENOPROTOOPT) { + zlog_warn("%s: PACKET_AUXDATA failed: %s", __func__, + safe_strerror(errno)); + } + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf, sizeof(bpf))) { zlog_warn("%s: SO_ATTACH_FILTER failed: %s", __func__, safe_strerror(errno)); @@ -284,13 +291,54 @@ int isis_recv_pdu_bcast(struct isis_circuit *circuit, uint8_t *ssnpa) ? circuit->interface->mtu : circuit->interface->mtu6; uint8_t temp_buff[max_size]; - bytesread = - recvfrom(circuit->fd, temp_buff, max_size, MSG_DONTWAIT, - (struct sockaddr *)&s_addr, (socklen_t *)&addr_len); + + union { + struct cmsghdr cmsg; + char buf[CMSG_SPACE(sizeof(struct tpacket_auxdata))]; + } cmsg_buf; + struct iovec iov; + struct msghdr msg; + memset(&cmsg_buf, 0x00, sizeof(cmsg_buf)); + memset(&iov, 0x00, sizeof(iov)); + memset(&msg, 0x00, sizeof(msg)); + + iov.iov_base = temp_buff; + iov.iov_len = max_size; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_name = &s_addr; + msg.msg_namelen = addr_len; + + msg.msg_control = &cmsg_buf; + msg.msg_controllen = sizeof(cmsg_buf); + + bytesread = recvmsg(circuit->fd, &msg, MSG_DONTWAIT); if (bytesread < 0) { zlog_warn("%s: recvfrom() failed", __func__); return ISIS_WARNING; } + + bool vlan_packet = false; + + for (struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg); cmsg; + cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_len >= CMSG_LEN(sizeof(struct tpacket_auxdata)) && + cmsg->cmsg_level == SOL_PACKET && + cmsg->cmsg_type == PACKET_AUXDATA) { + struct tpacket_auxdata *aux = + (struct tpacket_auxdata *)CMSG_DATA(cmsg); + + if (aux && (aux->tp_status & TP_STATUS_VLAN_VALID)) + vlan_packet = true; + break; + } + } + + if (vlan_packet) + return ISIS_WARNING; + /* then we lose the LLC */ stream_write(circuit->rcv_stream, temp_buff + LLC_LEN, bytesread - LLC_LEN);